From 0650d437cf76eeb5cdecaad2f11979ac7c4ef9ce Mon Sep 17 00:00:00 2001 From: zhenghui Date: Thu, 27 Feb 2025 19:51:25 +0800 Subject: [PATCH] pcre2 update Signed-off-by: zhenghui --- BUILD.gn | 1 + pcre2/.github/workflows/build.yml | 61 +- pcre2/.github/workflows/cifuzz.yml | 2 +- pcre2/.github/workflows/codeql.yml | 2 +- pcre2/.github/workflows/dev.yml | 81 + pcre2/.github/workflows/scorecards.yml | 4 +- pcre2/132html | 3 + pcre2/AUTHORS | 6 +- pcre2/BUILD.bazel | 5 +- pcre2/CMakeLists.txt | 170 +- pcre2/ChangeLog | 294 +- pcre2/HACKING | 59 +- pcre2/LICENCE | 6 +- pcre2/Makefile.am | 107 +- pcre2/NEWS | 56 + pcre2/NON-AUTOTOOLS-BUILD | 71 +- pcre2/PrepareRelease | 24 +- pcre2/README | 42 +- pcre2/RunGrepTest | 22 + pcre2/RunTest | 2 +- pcre2/RunTest.bat | 5 +- pcre2/build.zig | 83 + pcre2/cmake/pcre2-config.cmake.in | 9 +- pcre2/config-cmake.h.in | 6 +- pcre2/configure.ac | 87 +- pcre2/doc/html/NON-AUTOTOOLS-BUILD.txt | 71 +- pcre2/doc/html/README.txt | 42 +- pcre2/doc/html/index.html | 8 +- pcre2/doc/html/pcre2_compile.html | 18 +- .../html/pcre2_general_context_create.html | 2 +- .../pcre2_get_match_data_heapframes_size.html | 40 + pcre2/doc/html/pcre2_jit_match.html | 14 +- pcre2/doc/html/pcre2_jit_stack_create.html | 4 +- pcre2/doc/html/pcre2_match.html | 2 + pcre2/doc/html/pcre2_match_data_free.html | 8 +- .../html/pcre2_set_compile_extra_options.html | 6 + ...pcre2_set_max_pattern_compiled_length.html | 44 + .../doc/html/pcre2_set_max_varlookbehind.html | 42 + ...pcre2_set_recursion_memory_management.html | 2 +- pcre2/doc/html/pcre2_substring_list_free.html | 2 +- pcre2/doc/html/pcre2api.html | 349 +- pcre2/doc/html/pcre2build.html | 98 +- pcre2/doc/html/pcre2callout.html | 18 +- pcre2/doc/html/pcre2compat.html | 120 +- pcre2/doc/html/pcre2convert.html | 2 +- pcre2/doc/html/pcre2demo.html | 5 +- pcre2/doc/html/pcre2grep.html | 143 +- pcre2/doc/html/pcre2jit.html | 95 +- pcre2/doc/html/pcre2limits.html | 11 +- pcre2/doc/html/pcre2matching.html | 6 +- pcre2/doc/html/pcre2partial.html | 2 +- pcre2/doc/html/pcre2pattern.html | 396 +- pcre2/doc/html/pcre2posix.html | 45 +- pcre2/doc/html/pcre2sample.html | 2 +- pcre2/doc/html/pcre2serialize.html | 6 +- pcre2/doc/html/pcre2syntax.html | 174 +- pcre2/doc/html/pcre2test.html | 151 +- pcre2/doc/html/pcre2unicode.html | 50 +- pcre2/doc/index.html.src | 8 +- pcre2/doc/pcre2-config.txt | 22 +- pcre2/doc/pcre2.txt | 5326 ++++++++-------- pcre2/doc/pcre2_compile.3 | 20 +- pcre2/doc/pcre2_general_context_create.3 | 2 +- .../pcre2_get_match_data_heapframes_size.3 | 28 + pcre2/doc/pcre2_jit_match.3 | 14 +- pcre2/doc/pcre2_jit_stack_create.3 | 4 +- pcre2/doc/pcre2_match.3 | 4 +- pcre2/doc/pcre2_match_data_free.3 | 10 +- pcre2/doc/pcre2_set_compile_extra_options.3 | 14 +- .../pcre2_set_max_pattern_compiled_length.3 | 32 + pcre2/doc/pcre2_set_max_varlookbehind.3 | 30 + .../pcre2_set_recursion_memory_management.3 | 2 +- pcre2/doc/pcre2_substring_list_free.3 | 4 +- pcre2/doc/pcre2api.3 | 281 +- pcre2/doc/pcre2build.3 | 39 +- pcre2/doc/pcre2callout.3 | 20 +- pcre2/doc/pcre2compat.3 | 115 +- pcre2/doc/pcre2convert.3 | 2 +- pcre2/doc/pcre2demo.3 | 10 +- pcre2/doc/pcre2grep.1 | 135 +- pcre2/doc/pcre2grep.txt | 641 +- pcre2/doc/pcre2jit.3 | 103 +- pcre2/doc/pcre2limits.3 | 13 +- pcre2/doc/pcre2matching.3 | 8 +- pcre2/doc/pcre2partial.3 | 2 +- pcre2/doc/pcre2pattern.3 | 397 +- pcre2/doc/pcre2posix.3 | 43 +- pcre2/doc/pcre2sample.3 | 2 +- pcre2/doc/pcre2serialize.3 | 6 +- pcre2/doc/pcre2syntax.3 | 59 +- pcre2/doc/pcre2test.1 | 152 +- pcre2/doc/pcre2test.txt | 729 ++- pcre2/doc/pcre2unicode.3 | 48 +- pcre2/libpcre2-posix.pc.in | 2 +- pcre2/m4/pcre2_visibility.m4 | 9 +- pcre2/maint/GenerateCommon.py | 55 +- pcre2/maint/GenerateTest26.py | 2 +- pcre2/maint/GenerateUcd.py | 45 +- pcre2/maint/GenerateUcpTables.py | 2 +- pcre2/maint/ManyConfigTests | 76 +- pcre2/maint/README | 20 +- pcre2/maint/Unicode.tables/BidiMirroring.txt | 8 +- pcre2/maint/Unicode.tables/CaseFolding.txt | 10 +- .../maint/Unicode.tables/DerivedBidiClass.txt | 324 +- .../Unicode.tables/DerivedCoreProperties.txt | 253 +- .../Unicode.tables/DerivedGeneralCategory.txt | 157 +- .../Unicode.tables/GraphemeBreakProperty.txt | 38 +- pcre2/maint/Unicode.tables/PropList.txt | 56 +- .../maint/Unicode.tables/PropertyAliases.txt | 10 +- .../Unicode.tables/PropertyValueAliases.txt | 24 +- .../maint/Unicode.tables/ScriptExtensions.txt | 10 +- pcre2/maint/Unicode.tables/Scripts.txt | 106 +- pcre2/maint/Unicode.tables/UnicodeData.txt | 300 +- pcre2/maint/Unicode.tables/emoji-data.txt | 85 +- pcre2/maint/pcre2_chartables.c.non-standard | 16 +- pcre2/maint/ucptest.c | 195 +- pcre2/maint/ucptestdata/testinput1 | 1 + pcre2/maint/ucptestdata/testinput2 | 2 + pcre2/maint/ucptestdata/testoutput1 | 650 +- pcre2/maint/ucptestdata/testoutput2 | 555 +- pcre2/pcre2-config.in | 2 +- pcre2/pcre2_fuzzer.options | 1 + pcre2/pcre2_fuzzer_16.dict | 50 + pcre2/pcre2_fuzzer_16.options | 3 + pcre2/pcre2_fuzzer_32.dict | 50 + pcre2/pcre2_fuzzer_32.options | 3 + pcre2/perltest.sh | 4 +- pcre2/src/config.h.generic | 64 +- pcre2/src/config.h.in | 59 +- pcre2/src/pcre2.h.generic | 33 +- pcre2/src/pcre2.h.in | 29 +- pcre2/src/pcre2_auto_possess.c | 16 +- pcre2/src/pcre2_chartables.c.dist | 12 +- pcre2/src/pcre2_chkdint.c | 96 + pcre2/src/pcre2_compile.c | 1298 ++-- pcre2/src/pcre2_context.c | 54 +- pcre2/src/pcre2_convert.c | 8 + pcre2/src/pcre2_dfa_match.c | 167 +- pcre2/src/pcre2_dftables.c | 20 +- pcre2/src/pcre2_error.c | 10 +- pcre2/src/pcre2_extuni.c | 28 +- pcre2/src/pcre2_find_bracket.c | 10 +- pcre2/src/pcre2_fuzzsupport.c | 639 +- pcre2/src/pcre2_internal.h | 155 +- pcre2/src/pcre2_intmodedep.h | 58 +- pcre2/src/pcre2_jit_compile.c | 1429 +++-- pcre2/src/pcre2_jit_match.c | 16 +- pcre2/src/pcre2_jit_misc.c | 4 +- pcre2/src/pcre2_jit_neon_inc.h | 53 +- pcre2/src/pcre2_jit_simd_inc.h | 1061 +++- pcre2/src/pcre2_jit_test.c | 47 +- pcre2/src/pcre2_maketables.c | 8 +- pcre2/src/pcre2_match.c | 469 +- pcre2/src/pcre2_match_data.c | 12 + pcre2/src/pcre2_printint.c | 194 +- pcre2/src/pcre2_study.c | 104 +- pcre2/src/pcre2_substring.c | 7 +- pcre2/src/pcre2_tables.c | 12 +- pcre2/src/pcre2_ucd.c | 5584 +++++++++-------- pcre2/src/pcre2_ucp.h | 48 +- pcre2/src/pcre2_ucptables.c | 529 +- pcre2/src/pcre2_valid_utf.c | 48 +- pcre2/src/pcre2_xclass.c | 53 +- pcre2/src/pcre2grep.c | 67 +- pcre2/src/pcre2posix.c | 130 +- pcre2/src/pcre2posix.h | 25 +- pcre2/src/pcre2posix_test.c | 2 +- pcre2/src/pcre2test.c | 467 +- .../allocator_src/sljitExecAllocatorApple.c | 137 + .../allocator_src/sljitExecAllocatorCore.c | 327 + .../allocator_src/sljitExecAllocatorFreeBSD.c | 89 + .../allocator_src/sljitExecAllocatorPosix.c | 62 + .../allocator_src/sljitExecAllocatorWindows.c | 40 + .../sljitProtExecAllocatorNetBSD.c | 72 + .../sljitProtExecAllocatorPosix.c | 172 + .../allocator_src/sljitWXExecAllocatorPosix.c | 141 + .../sljitWXExecAllocatorWindows.c | 102 + pcre2/src/sljit/sljitConfig.h | 26 +- pcre2/src/sljit/sljitConfigCPU.h | 188 + pcre2/src/sljit/sljitConfigInternal.h | 388 +- pcre2/src/sljit/sljitLir.c | 1987 +++--- pcre2/src/sljit/sljitLir.h | 1157 +++- pcre2/src/sljit/sljitNativeARM_32.c | 2470 +++++--- pcre2/src/sljit/sljitNativeARM_64.c | 1744 ++++- pcre2/src/sljit/sljitNativeARM_T2_32.c | 1786 +++++- pcre2/src/sljit/sljitNativeLOONGARCH_64.c | 3765 +++++++++++ pcre2/src/sljit/sljitNativeMIPS_32.c | 178 +- pcre2/src/sljit/sljitNativeMIPS_64.c | 84 +- pcre2/src/sljit/sljitNativeMIPS_common.c | 1439 +++-- pcre2/src/sljit/sljitNativePPC_32.c | 153 +- pcre2/src/sljit/sljitNativePPC_64.c | 152 +- pcre2/src/sljit/sljitNativePPC_common.c | 1318 ++-- pcre2/src/sljit/sljitNativeRISCV_32.c | 71 +- pcre2/src/sljit/sljitNativeRISCV_64.c | 43 +- pcre2/src/sljit/sljitNativeRISCV_common.c | 1073 ++-- pcre2/src/sljit/sljitNativeS390X.c | 1671 +++-- pcre2/src/sljit/sljitNativeX86_32.c | 549 +- pcre2/src/sljit/sljitNativeX86_64.c | 582 +- pcre2/src/sljit/sljitNativeX86_common.c | 3687 +++++++---- pcre2/src/sljit/sljitSerialize.c | 516 ++ pcre2/testdata/grepinput8 | 4 + pcre2/testdata/grepoutput | 37 +- pcre2/testdata/grepoutput8 | 13 + pcre2/testdata/testinput1 | 261 +- pcre2/testdata/testinput10 | 34 +- pcre2/testdata/testinput12 | 57 + pcre2/testdata/testinput14 | 27 + pcre2/testdata/testinput15 | 14 +- pcre2/testdata/testinput17 | 8 +- pcre2/testdata/testinput2 | 193 +- pcre2/testdata/testinput25 | 4 + pcre2/testdata/testinput26 | 48 +- pcre2/testdata/testinput3 | 5 + pcre2/testdata/testinput4 | 80 + pcre2/testdata/testinput5 | 355 +- pcre2/testdata/testinput6 | 16 + pcre2/testdata/testinput7 | 302 +- pcre2/testdata/testinputheap | 24 +- pcre2/testdata/testoutput1 | 412 +- pcre2/testdata/testoutput10 | 52 +- pcre2/testdata/testoutput12-16 | 84 + pcre2/testdata/testoutput12-32 | 76 + pcre2/testdata/testoutput14-16 | 38 + pcre2/testdata/testoutput14-32 | 34 + pcre2/testdata/testoutput14-8 | 38 + pcre2/testdata/testoutput15 | 16 +- pcre2/testdata/testoutput16 | 1 + pcre2/testdata/testoutput17 | 15 +- pcre2/testdata/testoutput18 | 10 +- pcre2/testdata/testoutput2 | 450 +- pcre2/testdata/testoutput25 | 6 + pcre2/testdata/testoutput26 | 68 +- pcre2/testdata/testoutput3 | 7 + pcre2/testdata/testoutput3A | 7 + pcre2/testdata/testoutput3B | 7 + pcre2/testdata/testoutput4 | 137 + pcre2/testdata/testoutput5 | 561 +- pcre2/testdata/testoutput6 | 29 +- pcre2/testdata/testoutput7 | 473 +- pcre2/testdata/testoutput8-16-2 | 170 +- pcre2/testdata/testoutput8-16-3 | 168 +- pcre2/testdata/testoutput8-16-4 | 168 +- pcre2/testdata/testoutput8-32-2 | 168 +- pcre2/testdata/testoutput8-32-3 | 168 +- pcre2/testdata/testoutput8-32-4 | 168 +- pcre2/testdata/testoutput8-8-2 | 170 +- pcre2/testdata/testoutput8-8-3 | 168 +- pcre2/testdata/testoutput8-8-4 | 168 +- pcre2/testdata/testoutputheap-16 | 50 +- pcre2/testdata/testoutputheap-32 | 50 +- pcre2/testdata/testoutputheap-8 | 50 +- pcre2/vms/configure.com | 1144 ++++ pcre2/vms/openvms_readme.txt | 20 + pcre2/vms/pcre2.h_patch | 12 + pcre2/vms/stdint.h | 9 + 255 files changed, 43473 insertions(+), 17310 deletions(-) create mode 100644 pcre2/.github/workflows/dev.yml create mode 100644 pcre2/build.zig create mode 100644 pcre2/doc/html/pcre2_get_match_data_heapframes_size.html create mode 100644 pcre2/doc/html/pcre2_set_max_pattern_compiled_length.html create mode 100644 pcre2/doc/html/pcre2_set_max_varlookbehind.html create mode 100644 pcre2/doc/pcre2_get_match_data_heapframes_size.3 create mode 100644 pcre2/doc/pcre2_set_max_pattern_compiled_length.3 create mode 100644 pcre2/doc/pcre2_set_max_varlookbehind.3 create mode 100644 pcre2/pcre2_fuzzer_16.dict create mode 100644 pcre2/pcre2_fuzzer_16.options create mode 100644 pcre2/pcre2_fuzzer_32.dict create mode 100644 pcre2/pcre2_fuzzer_32.options create mode 100644 pcre2/src/pcre2_chkdint.c create mode 100644 pcre2/src/sljit/allocator_src/sljitExecAllocatorApple.c create mode 100644 pcre2/src/sljit/allocator_src/sljitExecAllocatorCore.c create mode 100644 pcre2/src/sljit/allocator_src/sljitExecAllocatorFreeBSD.c create mode 100644 pcre2/src/sljit/allocator_src/sljitExecAllocatorPosix.c create mode 100644 pcre2/src/sljit/allocator_src/sljitExecAllocatorWindows.c create mode 100644 pcre2/src/sljit/allocator_src/sljitProtExecAllocatorNetBSD.c create mode 100644 pcre2/src/sljit/allocator_src/sljitProtExecAllocatorPosix.c create mode 100644 pcre2/src/sljit/allocator_src/sljitWXExecAllocatorPosix.c create mode 100644 pcre2/src/sljit/allocator_src/sljitWXExecAllocatorWindows.c create mode 100644 pcre2/src/sljit/sljitConfigCPU.h create mode 100644 pcre2/src/sljit/sljitNativeLOONGARCH_64.c create mode 100644 pcre2/src/sljit/sljitSerialize.c create mode 100644 pcre2/vms/configure.com create mode 100644 pcre2/vms/openvms_readme.txt create mode 100644 pcre2/vms/pcre2.h_patch create mode 100644 pcre2/vms/stdint.h diff --git a/BUILD.gn b/BUILD.gn index 02ad2f8..6ff9dd6 100644 --- a/BUILD.gn +++ b/BUILD.gn @@ -22,6 +22,7 @@ config("third_party_pcre2_config") { pcre2_sources = [ "$PCRE2_LIB_DIR/src/pcre2_auto_possess.c", + "$PCRE2_LIB_DIR/src/pcre2_chkdint.c", "$PCRE2_LIB_DIR/src/pcre2_compile.c", "$PCRE2_LIB_DIR/src/pcre2_config.c", "$PCRE2_LIB_DIR/src/pcre2_context.c", diff --git a/pcre2/.github/workflows/build.yml b/pcre2/.github/workflows/build.yml index ae2602d..f5b15f0 100644 --- a/pcre2/.github/workflows/build.yml +++ b/pcre2/.github/workflows/build.yml @@ -8,17 +8,17 @@ jobs: runs-on: ubuntu-latest steps: - name: Checkout - uses: actions/checkout@v3 - - - name: Autogen + uses: actions/checkout@v4 + + - name: Prepare run: ./autogen.sh - + - name: Configure - run: ./configure CPPFLAGS='-Wall -Wextra' --enable-jit --enable-pcre2-8 --enable-pcre2-16 --enable-pcre2-32 - + run: ./configure CPPFLAGS='-Wall -Wextra' --enable-jit --enable-pcre2-16 --enable-pcre2-32 + - name: Build - run: make - + run: make -j2 + - name: Test (main test script) run: ./RunTest @@ -27,27 +27,30 @@ jobs: - name: Test (pcre2grep test script) run: ./RunGrepTest - + + - name: Test (pcre2posix program) + run: ./pcre2posix_test -v + alpine: name: alpine runs-on: ubuntu-latest - container: alpine + container: alpine steps: - name: Checkout - uses: actions/checkout@v3 - + uses: actions/checkout@v4 + - name: Setup - run: apk add --no-cache automake autoconf gcc libtool make musl-dev - - - name: Autogen + run: apk add --no-cache automake autoconf gcc libtool make musl-dev #musl-locales + + - name: Prepare run: ./autogen.sh - + - name: Configure - run: ./configure CPPFLAGS='-Wall -Wextra' --enable-jit --enable-pcre2-8 --enable-pcre2-16 --enable-pcre2-32 - + run: ./configure CPPFLAGS='-Wall -Wextra' --enable-jit --enable-pcre2-16 --enable-pcre2-32 + - name: Build - run: make - + run: make -j2 + - name: Test (main test script) run: ./RunTest @@ -56,13 +59,16 @@ jobs: - name: Test (pcre2grep test script) run: ./RunGrepTest - + + - name: Test (pcre2posix program) + run: ./pcre2posix_test -v + macos: name: macOS universal runs-on: macos-latest steps: - name: Checkout - uses: actions/checkout@v3 + uses: actions/checkout@v4 - name: Configure run: cmake -DPCRE2_SUPPORT_JIT=ON -DPCRE2_BUILD_PCRE2_16=ON -DPCRE2_BUILD_PCRE2_32=ON -DCMAKE_OSX_ARCHITECTURES='arm64;x86_64' -DCMAKE_C_FLAGS='-Wall -Wextra' -B build @@ -85,12 +91,17 @@ jobs: cd build ../RunGrepTest - windows: + - name: Test (pcre2posix program) + run: | + cd build + ./pcre2posix_test -v + + windows: name: 32bit Windows runs-on: windows-latest steps: - name: Checkout - uses: actions/checkout@v3 + uses: actions/checkout@v4 - name: Configure run: cmake -DPCRE2_SUPPORT_JIT=ON -DPCRE2_BUILD_PCRE2_16=ON -DPCRE2_BUILD_PCRE2_32=ON -DCMAKE_IGNORE_PREFIX_PATH=C:/Strawberry/c -B build -A Win32 @@ -102,4 +113,4 @@ jobs: run: | cd build\Debug ..\..\RunTest.bat - + ./pcre2posix_test -v diff --git a/pcre2/.github/workflows/cifuzz.yml b/pcre2/.github/workflows/cifuzz.yml index 8ac7dc2..52ef4f6 100644 --- a/pcre2/.github/workflows/cifuzz.yml +++ b/pcre2/.github/workflows/cifuzz.yml @@ -17,7 +17,7 @@ jobs: fuzz-seconds: 300 dry-run: false - name: Upload Crash - uses: actions/upload-artifact@v3 + uses: actions/upload-artifact@v4 if: failure() && steps.build.outcome == 'success' with: name: artifacts diff --git a/pcre2/.github/workflows/codeql.yml b/pcre2/.github/workflows/codeql.yml index 3d0e891..4d40c32 100644 --- a/pcre2/.github/workflows/codeql.yml +++ b/pcre2/.github/workflows/codeql.yml @@ -41,7 +41,7 @@ jobs: steps: - name: Checkout repository - uses: actions/checkout@v3 + uses: actions/checkout@v4 # Initializes the CodeQL tools for scanning. - name: Initialize CodeQL diff --git a/pcre2/.github/workflows/dev.yml b/pcre2/.github/workflows/dev.yml new file mode 100644 index 0000000..b3ba802 --- /dev/null +++ b/pcre2/.github/workflows/dev.yml @@ -0,0 +1,81 @@ +name: Dev +on: + workflow_dispatch: + pull_request: + branches: + - master + +jobs: + + canary: + name: gcc + runs-on: ubuntu-latest + steps: + - name: Checkout + uses: actions/checkout@v4 + + - name: Prepare + run: ./autogen.sh + + - name: Configure + run: ./configure CC='gcc -O0 -fsanitize=undefined,address -fsanitize-undefined-trap-on-error' CPPFLAGS='-Wall -Wextra -Werror -Wno-error=unused-but-set-parameter' --enable-jit --enable-pcre2-16 --enable-pcre2-32 --enable-debug --with-link-size=4 + + - name: Build + run: make -j3 + + - name: Test (main test script) + run: ./RunTest + + - name: Test (JIT test program) + run: ./pcre2_jit_test + + - name: Test (pcre2grep test script) + run: ./RunGrepTest + + - name: Test (pcre2posix program) + run: ./pcre2posix_test -v + + dragon: + name: clang + runs-on: ubuntu-latest + steps: + - name: Checkout + uses: actions/checkout@v4 + + - name: Prepare + run: ./autogen.sh + + - name: Configure + run: ./configure CC='clang -fsanitize=undefined,address,integer -fno-sanitize=unsigned-integer-overflow' CPPFLAGS='-Wall -Wextra -Werror -Wno-error=unused-but-set-parameter -Wno-error=deprecated-declarations -Wno-error=incompatible-library-redeclaration' --enable-jit --enable-pcre2-16 --enable-pcre2-32 --enable-debug --with-link-size=3 + + - name: Build + run: make -j3 + + - name: Test (main test script) + run: ./RunTest + + - name: Test (JIT test program) + run: ./pcre2_jit_test + + - name: Test (pcre2grep test script) + run: ./RunGrepTest + + - name: Test (pcre2posix program) + run: ./pcre2posix_test -v + + bigbird: + name: manyconfig + runs-on: ubuntu-latest + steps: + - name: Checkout + uses: actions/checkout@v4 + + - name: Prepare + run: | + sudo apt-get update + sudo apt-get install -y valgrind + + - name: Run + run: | + ./autogen.sh + ./maint/ManyConfigTests diff --git a/pcre2/.github/workflows/scorecards.yml b/pcre2/.github/workflows/scorecards.yml index 690f191..4e18e07 100644 --- a/pcre2/.github/workflows/scorecards.yml +++ b/pcre2/.github/workflows/scorecards.yml @@ -22,12 +22,12 @@ jobs: steps: - name: "Checkout code" - uses: actions/checkout@v3 + uses: actions/checkout@v4 with: persist-credentials: false - name: "Run analysis" - uses: ossf/scorecard-action@c1aec4ac820532bab364f02a81873c555a0ba3a1 # v1.0.4 + uses: ossf/scorecard-action@3e15ea8318eee9b333819ec77a36aca8d39df13e # tag=v1.1.1 with: results_file: results.sarif results_format: sarif diff --git a/pcre2/132html b/pcre2/132html index 30c02fe..05ab60e 100755 --- a/pcre2/132html +++ b/pcre2/132html @@ -180,6 +180,9 @@ while () $wrotetext = 1; } + # Remove the "AUTOMATICALLY GENERATED" warning from pcre2demo.3 + elsif (/^\.\\"AUTOMATICALLY GENERATED/) { next; } + # A comment that starts "HREF" takes the next line as a name that # is turned into a hyperlink, using the text given, which might be # in a special font. If it ends in () or (digits) or punctuation, they diff --git a/pcre2/AUTHORS b/pcre2/AUTHORS index 11ef898..9669f77 100644 --- a/pcre2/AUTHORS +++ b/pcre2/AUTHORS @@ -8,7 +8,7 @@ Email domain: gmail.com Retired from University of Cambridge Computing Service, Cambridge, England. -Copyright (c) 1997-2022 University of Cambridge +Copyright (c) 1997-2024 University of Cambridge All rights reserved @@ -19,7 +19,7 @@ Written by: Zoltan Herczeg Email local part: hzmester Emain domain: freemail.hu -Copyright(c) 2010-2022 Zoltan Herczeg +Copyright(c) 2010-2024 Zoltan Herczeg All rights reserved. @@ -30,7 +30,7 @@ Written by: Zoltan Herczeg Email local part: hzmester Emain domain: freemail.hu -Copyright(c) 2009-2022 Zoltan Herczeg +Copyright(c) 2009-2024 Zoltan Herczeg All rights reserved. #### diff --git a/pcre2/BUILD.bazel b/pcre2/BUILD.bazel index 1bd314e..30d53a4 100644 --- a/pcre2/BUILD.bazel +++ b/pcre2/BUILD.bazel @@ -19,10 +19,14 @@ copy_file( out = "src/pcre2_chartables.c", ) +# Removed src/pcre2_ucptables.c below because it is #included in +# src/pcre2_tables.c. Also fixed typo: ckdint should be chkdint. +# PH, 22-March-2023. cc_library( name = "pcre2", srcs = [ "src/pcre2_auto_possess.c", + "src/pcre2_chkdint.c", "src/pcre2_compile.c", "src/pcre2_config.c", "src/pcre2_context.c", @@ -45,7 +49,6 @@ cc_library( "src/pcre2_substring.c", "src/pcre2_tables.c", "src/pcre2_ucd.c", - "src/pcre2_ucptables.c", "src/pcre2_valid_utf.c", "src/pcre2_xclass.c", ":pcre2_chartables_c", diff --git a/pcre2/CMakeLists.txt b/pcre2/CMakeLists.txt index cec7dfb..b73ed73 100644 --- a/pcre2/CMakeLists.txt +++ b/pcre2/CMakeLists.txt @@ -100,11 +100,18 @@ # 2021-08-28 PH increased minimum version # 2021-08-28 PH added test for realpath() # 2022-12-10 PH added support for pcre2posix_test +# 2023-01-15 Carlo added C99 as the minimum required +# 2023-08-06 PH added support for setting variable length lookbehind maximum -# Increased minimum to 2.8.5 to support GNUInstallDirs. -# Increased minimum to 3.1 to support imported targets. -CMAKE_MINIMUM_REQUIRED(VERSION 3.1) -PROJECT(PCRE2 C) +# Increased minimum to 3.5 to workaround deprecated backward compatibility +# since 3.27. +cmake_minimum_required(VERSION 3.5 FATAL_ERROR) +project(PCRE2 C) +set(CMAKE_C_STANDARD 99) +set(CMAKE_C_STANDARD_REQUIRED TRUE) + +set(CMAKE_C_VISIBILITY_PRESET hidden) +cmake_policy(SET CMP0063 NEW) # Set policy CMP0026 to avoid warnings for the use of LOCATION in # GET_TARGET_PROPERTY. This should no longer be required. @@ -153,16 +160,37 @@ CHECK_SYMBOL_EXISTS(strerror "string.h" HAVE_STRERROR) CHECK_C_SOURCE_COMPILES( "#include #include - int main(int c, char *v[]) { char buf[PATH_MAX]; realpath(v[1], buf); return 0; }" + int main(int c, char *v[]) { char buf[PATH_MAX]; realpath(v[c], buf); return 0; }" HAVE_REALPATH ) set(ORIG_CMAKE_REQUIRED_FLAGS ${CMAKE_REQUIRED_FLAGS}) set(CMAKE_REQUIRED_FLAGS "${CMAKE_REQUIRED_FLAGS} -Werror") + CHECK_C_SOURCE_COMPILES( - "int main() { char buf[128] __attribute__((uninitialized)); (void)buf; return 0; }" + "#include + int main(void) { int a,b; size_t m; __builtin_mul_overflow(a,b,&m); return 0; }" + HAVE_BUILTIN_MUL_OVERFLOW +) + +CHECK_C_SOURCE_COMPILES( + "int main(void) { char buf[128] __attribute__((uninitialized)); (void)buf; return 0; }" HAVE_ATTRIBUTE_UNINITIALIZED ) + +CHECK_C_SOURCE_COMPILES([=[ + extern __attribute__ ((visibility ("default"))) int f(void); + int main(void) { return f(); } + int f(void) { return 42; } + ]=] HAVE_VISIBILITY +) + +if (HAVE_VISIBILITY) + set(PCRE2_EXPORT [=[__attribute__ ((visibility ("default")))]=]) +else() + set(PCRE2_EXPORT) +endif() + set(CMAKE_REQUIRED_FLAGS ${ORIG_CMAKE_REQUIRED_FLAGS}) # Check whether Intel CET is enabled, and if so, adjust compiler flags. This @@ -181,8 +209,6 @@ IF (INTEL_CET_ENABLED) SET(CMAKE_C_FLAGS "${CMAKE_C_FLAGS} -mshstk") ENDIF(INTEL_CET_ENABLED) - - # User-configurable options # # Note: CMakeSetup displays these in alphabetical order, regardless of @@ -219,6 +245,9 @@ SET(PCRE2_PARENS_NEST_LIMIT "250" CACHE STRING SET(PCRE2_HEAP_LIMIT "20000000" CACHE STRING "Default limit on heap memory (kibibytes). See HEAP_LIMIT in config.h.in for details.") +SET(PCRE2_MAX_VARLOOKBEHIND "255" CACHE STRING + "Default limit on variable lookbehinds.") + SET(PCRE2_MATCH_LIMIT "10000000" CACHE STRING "Default limit on internal looping. See MATCH_LIMIT in config.h.in for details.") @@ -542,46 +571,6 @@ IF(WIN32) SET(CMAKE_DEBUG_POSTFIX "d") ENDIF(WIN32) -# Generate pkg-config files - -SET(PACKAGE_VERSION "${PCRE2_MAJOR}.${PCRE2_MINOR}") -SET(prefix ${CMAKE_INSTALL_PREFIX}) - -SET(exec_prefix "\${prefix}") -SET(libdir "\${exec_prefix}/${CMAKE_INSTALL_LIBDIR}") -SET(includedir "\${prefix}/include") -IF(WIN32 AND (CMAKE_BUILD_TYPE MATCHES Debug)) - SET(LIB_POSTFIX ${CMAKE_DEBUG_POSTFIX}) -ENDIF() -CONFIGURE_FILE(libpcre2-posix.pc.in libpcre2-posix.pc @ONLY) -SET(pkg_config_files ${pkg_config_files} "${CMAKE_CURRENT_BINARY_DIR}/libpcre2-posix.pc") - -IF(PCRE2_BUILD_PCRE2_8) - CONFIGURE_FILE(libpcre2-8.pc.in libpcre2-8.pc @ONLY) - SET(pkg_config_files ${pkg_config_files} "${CMAKE_CURRENT_BINARY_DIR}/libpcre2-8.pc") - SET(enable_pcre2_8 "yes") -ELSE() - SET(enable_pcre2_8 "no") -ENDIF() - -IF(PCRE2_BUILD_PCRE2_16) - CONFIGURE_FILE(libpcre2-16.pc.in libpcre2-16.pc @ONLY) - SET(pkg_config_files ${pkg_config_files} "${CMAKE_CURRENT_BINARY_DIR}/libpcre2-16.pc") - SET(enable_pcre2_16 "yes") -ELSE() - SET(enable_pcre2_16 "no") -ENDIF() - -IF(PCRE2_BUILD_PCRE2_32) - CONFIGURE_FILE(libpcre2-32.pc.in libpcre2-32.pc @ONLY) - SET(pkg_config_files ${pkg_config_files} "${CMAKE_CURRENT_BINARY_DIR}/libpcre2-32.pc") - SET(enable_pcre2_32 "yes") -ELSE() - SET(enable_pcre2_32 "no") -ENDIF() - -CONFIGURE_FILE(pcre2-config.in pcre2-config @ONLY) - # Character table generation OPTION(PCRE2_REBUILD_CHARTABLES "Rebuild char tables" OFF) @@ -607,6 +596,7 @@ SET(PCRE2_HEADERS ${PROJECT_BINARY_DIR}/pcre2.h) SET(PCRE2_SOURCES src/pcre2_auto_possess.c ${PROJECT_BINARY_DIR}/pcre2_chartables.c + src/pcre2_chkdint.c src/pcre2_compile.c src/pcre2_config.c src/pcre2_context.c @@ -691,7 +681,7 @@ ENDIF(MSVC) SET(CMAKE_INCLUDE_CURRENT_DIR 1) -SET(targets) +set(targets) # 8-bit library @@ -718,9 +708,8 @@ IF(PCRE2_BUILD_PCRE2_8) VERSION ${LIBPCRE2_POSIX_VERSION} SOVERSION ${LIBPCRE2_POSIX_SOVERSION}) TARGET_LINK_LIBRARIES(pcre2-posix-static pcre2-8-static) - TARGET_COMPILE_DEFINITIONS(pcre2-posix-static PUBLIC PCRE2_STATIC) - TARGET_INCLUDE_DIRECTORIES(pcre2-posix-static PUBLIC ${PROJECT_BINARY_DIR}) - SET(targets ${targets} pcre2-posix-static) + TARGET_INCLUDE_DIRECTORIES(pcre2-posix-static PUBLIC ${PROJECT_SOURCE_DIR}/src) + set(targets ${targets} pcre2-posix-static) IF(MSVC) SET_TARGET_PROPERTIES(pcre2-8-static PROPERTIES OUTPUT_NAME pcre2-8-static) @@ -747,9 +736,10 @@ IF(PCRE2_BUILD_PCRE2_8) IF(REQUIRE_PTHREAD) TARGET_LINK_LIBRARIES(pcre2-8-shared Threads::Threads) ENDIF(REQUIRE_PTHREAD) - SET(targets ${targets} pcre2-8-shared) + set(targets ${targets} pcre2-8-shared) + ADD_LIBRARY(pcre2-posix-shared SHARED ${PCRE2POSIX_HEADERS} ${PCRE2POSIX_SOURCES}) - TARGET_INCLUDE_DIRECTORIES(pcre2-posix-shared PUBLIC ${PROJECT_BINARY_DIR}) + TARGET_INCLUDE_DIRECTORIES(pcre2-posix-shared PUBLIC ${PROJECT_SOURCE_DIR}/src) SET_TARGET_PROPERTIES(pcre2-posix-shared PROPERTIES COMPILE_DEFINITIONS PCRE2_CODE_UNIT_WIDTH=8 MACHO_COMPATIBILITY_VERSION "${LIBPCRE2_POSIX_MACHO_COMPATIBILITY_VERSION}" @@ -757,6 +747,8 @@ IF(PCRE2_BUILD_PCRE2_8) VERSION ${LIBPCRE2_POSIX_VERSION} SOVERSION ${LIBPCRE2_POSIX_SOVERSION} OUTPUT_NAME pcre2-posix) + set(PCRE2POSIX_CFLAG "-DPCRE2POSIX_SHARED") + TARGET_COMPILE_DEFINITIONS(pcre2-posix-shared PUBLIC ${PCRE2POSIX_CFLAG}) TARGET_LINK_LIBRARIES(pcre2-posix-shared pcre2-8-shared) SET(targets ${targets} pcre2-posix-shared) SET(dll_pdb_files ${PROJECT_BINARY_DIR}/pcre2-8.pdb ${dll_pdb_files}) @@ -787,7 +779,7 @@ IF(PCRE2_BUILD_PCRE2_16) IF(BUILD_STATIC_LIBS) ADD_LIBRARY(pcre2-16-static STATIC ${PCRE2_HEADERS} ${PCRE2_SOURCES} ${PROJECT_BINARY_DIR}/config.h) TARGET_INCLUDE_DIRECTORIES(pcre2-16-static PUBLIC ${PROJECT_BINARY_DIR}) - SET_TARGET_PROPERTIES(pcre2-16-static PROPERTIES + SET_TARGET_PROPERTIES(pcre2-16-static PROPERTIES UNITY_BUILD OFF COMPILE_DEFINITIONS PCRE2_CODE_UNIT_WIDTH=16 MACHO_COMPATIBILITY_VERSION "${LIBPCRE2_32_MACHO_COMPATIBILITY_VERSION}" MACHO_CURRENT_VERSION "${LIBPCRE2_32_MACHO_CURRENT_VERSION}" @@ -797,7 +789,7 @@ IF(PCRE2_BUILD_PCRE2_16) IF(REQUIRE_PTHREAD) TARGET_LINK_LIBRARIES(pcre2-16-static Threads::Threads) ENDIF(REQUIRE_PTHREAD) - SET(targets ${targets} pcre2-16-static) + set(targets ${targets} pcre2-16-static) IF(MSVC) SET_TARGET_PROPERTIES(pcre2-16-static PROPERTIES OUTPUT_NAME pcre2-16-static) @@ -812,7 +804,7 @@ IF(PCRE2_BUILD_PCRE2_16) IF(BUILD_SHARED_LIBS) ADD_LIBRARY(pcre2-16-shared SHARED ${PCRE2_HEADERS} ${PCRE2_SOURCES} ${PROJECT_BINARY_DIR}/config.h) TARGET_INCLUDE_DIRECTORIES(pcre2-16-shared PUBLIC ${PROJECT_BINARY_DIR}) - SET_TARGET_PROPERTIES(pcre2-16-shared PROPERTIES + SET_TARGET_PROPERTIES(pcre2-16-shared PROPERTIES UNITY_BUILD OFF COMPILE_DEFINITIONS PCRE2_CODE_UNIT_WIDTH=16 MACHO_COMPATIBILITY_VERSION "${LIBPCRE2_32_MACHO_COMPATIBILITY_VERSION}" MACHO_CURRENT_VERSION "${LIBPCRE2_32_MACHO_CURRENT_VERSION}" @@ -822,7 +814,7 @@ IF(PCRE2_BUILD_PCRE2_16) IF(REQUIRE_PTHREAD) TARGET_LINK_LIBRARIES(pcre2-16-shared Threads::Threads) ENDIF(REQUIRE_PTHREAD) - SET(targets ${targets} pcre2-16-shared) + set(targets ${targets} pcre2-16-shared) SET(dll_pdb_files ${PROJECT_BINARY_DIR}/pcre2-16.pdb ${dll_pdb_files}) SET(dll_pdb_debug_files ${PROJECT_BINARY_DIR}/pcre2-16d.pdb ${dll_pdb_debug_files}) @@ -849,7 +841,7 @@ IF(PCRE2_BUILD_PCRE2_32) IF(BUILD_STATIC_LIBS) ADD_LIBRARY(pcre2-32-static STATIC ${PCRE2_HEADERS} ${PCRE2_SOURCES} ${PROJECT_BINARY_DIR}/config.h) TARGET_INCLUDE_DIRECTORIES(pcre2-32-static PUBLIC ${PROJECT_BINARY_DIR}) - SET_TARGET_PROPERTIES(pcre2-32-static PROPERTIES + SET_TARGET_PROPERTIES(pcre2-32-static PROPERTIES UNITY_BUILD OFF COMPILE_DEFINITIONS PCRE2_CODE_UNIT_WIDTH=32 MACHO_COMPATIBILITY_VERSION "${LIBPCRE2_32_MACHO_COMPATIBILITY_VERSION}" MACHO_CURRENT_VERSION "${LIBPCRE2_32_MACHO_CURRENT_VERSION}" @@ -859,7 +851,7 @@ IF(PCRE2_BUILD_PCRE2_32) IF(REQUIRE_PTHREAD) TARGET_LINK_LIBRARIES(pcre2-32-static Threads::Threads) ENDIF(REQUIRE_PTHREAD) - SET(targets ${targets} pcre2-32-static) + set(targets ${targets} pcre2-32-static) IF(MSVC) SET_TARGET_PROPERTIES(pcre2-32-static PROPERTIES OUTPUT_NAME pcre2-32-static) @@ -874,7 +866,7 @@ IF(PCRE2_BUILD_PCRE2_32) IF(BUILD_SHARED_LIBS) ADD_LIBRARY(pcre2-32-shared SHARED ${PCRE2_HEADERS} ${PCRE2_SOURCES} ${PROJECT_BINARY_DIR}/config.h) TARGET_INCLUDE_DIRECTORIES(pcre2-32-shared PUBLIC ${PROJECT_BINARY_DIR}) - SET_TARGET_PROPERTIES(pcre2-32-shared PROPERTIES + SET_TARGET_PROPERTIES(pcre2-32-shared PROPERTIES UNITY_BUILD OFF COMPILE_DEFINITIONS PCRE2_CODE_UNIT_WIDTH=32 MACHO_COMPATIBILITY_VERSION "${LIBPCRE2_32_MACHO_COMPATIBILITY_VERSION}" MACHO_CURRENT_VERSION "${LIBPCRE2_32_MACHO_CURRENT_VERSION}" @@ -884,7 +876,7 @@ IF(PCRE2_BUILD_PCRE2_32) IF(REQUIRE_PTHREAD) TARGET_LINK_LIBRARIES(pcre2-32-shared Threads::Threads) ENDIF(REQUIRE_PTHREAD) - SET(targets ${targets} pcre2-32-shared) + set(targets ${targets} pcre2-32-shared) SET(dll_pdb_files ${PROJECT_BINARY_DIR}/pcre2-32.pdb ${dll_pdb_files}) SET(dll_pdb_debug_files ${PROJECT_BINARY_DIR}/pcre2-32d.pdb ${dll_pdb_debug_files}) @@ -905,13 +897,53 @@ IF(PCRE2_BUILD_PCRE2_32) ENDIF(BUILD_STATIC_LIBS) ENDIF(PCRE2_BUILD_PCRE2_32) +# Generate pkg-config files + +set(PACKAGE_VERSION "${PCRE2_MAJOR}.${PCRE2_MINOR}") +set(prefix ${CMAKE_INSTALL_PREFIX}) + +set(exec_prefix "\${prefix}") +set(libdir "\${exec_prefix}/${CMAKE_INSTALL_LIBDIR}") +set(includedir "\${prefix}/include") +if(WIN32 AND (CMAKE_BUILD_TYPE MATCHES Debug)) + set(LIB_POSTFIX ${CMAKE_DEBUG_POSTFIX}) +endif() + +if(PCRE2_BUILD_PCRE2_8) + configure_file(libpcre2-posix.pc.in libpcre2-posix.pc @ONLY) + list(APPEND pkg_config_files "${CMAKE_CURRENT_BINARY_DIR}/libpcre2-posix.pc") + configure_file(libpcre2-8.pc.in libpcre2-8.pc @ONLY) + list(APPEND pkg_config_files "${CMAKE_CURRENT_BINARY_DIR}/libpcre2-8.pc") + set(enable_pcre2_8 "yes") +else() + set(enable_pcre2_8 "no") +endif() + +if(PCRE2_BUILD_PCRE2_16) + configure_file(libpcre2-16.pc.in libpcre2-16.pc @ONLY) + list(APPEND pkg_config_files "${CMAKE_CURRENT_BINARY_DIR}/libpcre2-16.pc") + set(enable_pcre2_16 "yes") +else() + set(enable_pcre2_16 "no") +endif() + +if(PCRE2_BUILD_PCRE2_32) + configure_file(libpcre2-32.pc.in libpcre2-32.pc @ONLY) + list(APPEND pkg_config_files "${CMAKE_CURRENT_BINARY_DIR}/libpcre2-32.pc") + set(enable_pcre2_32 "yes") +else() + set(enable_pcre2_32 "no") +endif() + +configure_file(pcre2-config.in pcre2-config @ONLY NEWLINE_STYLE LF) + # Executables IF(PCRE2_BUILD_PCRE2GREP) ADD_EXECUTABLE(pcre2grep src/pcre2grep.c) SET_PROPERTY(TARGET pcre2grep PROPERTY COMPILE_DEFINITIONS PCRE2_CODE_UNIT_WIDTH=8) - SET(targets ${targets} pcre2grep) + set(targets ${targets} pcre2grep) TARGET_LINK_LIBRARIES(pcre2grep pcre2-posix ${PCRE2GREP_LIBS}) ENDIF(PCRE2_BUILD_PCRE2GREP) @@ -930,7 +962,7 @@ IF(PCRE2_BUILD_TESTS) ENDIF(MSVC) ADD_EXECUTABLE(pcre2test ${PCRE2TEST_SOURCES}) - SET(targets ${targets} pcre2test) + set(targets ${targets} pcre2test) IF(PCRE2_BUILD_PCRE2_8) LIST(APPEND PCRE2TEST_LIBS pcre2-posix pcre2-8) ENDIF(PCRE2_BUILD_PCRE2_8) @@ -944,13 +976,11 @@ IF(PCRE2_BUILD_TESTS) IF(PCRE2_BUILD_PCRE2_8) ADD_EXECUTABLE(pcre2posix_test src/pcre2posix_test.c) - SET(targets ${targets} pcre2posix_test) TARGET_LINK_LIBRARIES(pcre2posix_test pcre2-posix pcre2-8) ENDIF(PCRE2_BUILD_PCRE2_8) IF(PCRE2_SUPPORT_JIT) ADD_EXECUTABLE(pcre2_jit_test src/pcre2_jit_test.c) - SET(targets ${targets} pcre2_jit_test) SET(PCRE2_JIT_TEST_LIBS) IF(PCRE2_BUILD_PCRE2_8) LIST(APPEND PCRE2_JIT_TEST_LIBS pcre2-8) @@ -999,6 +1029,7 @@ MESSAGE(\" \") FILE(WRITE ${PROJECT_BINARY_DIR}/pcre2_test.sh "#! /bin/sh # This is a generated file. +srcdir=${PROJECT_SOURCE_DIR} . ${PROJECT_SOURCE_DIR}/RunTest if test \"$?\" != \"0\"; then exit 1; fi # End @@ -1012,6 +1043,7 @@ if test \"$?\" != \"0\"; then exit 1; fi FILE(WRITE ${PROJECT_BINARY_DIR}/pcre2_grep_test.sh "#! /bin/sh # This is a generated file. +srcdir=${PROJECT_SOURCE_DIR} . ${PROJECT_SOURCE_DIR}/RunGrepTest if test \"$?\" != \"0\"; then exit 1; fi # End @@ -1067,7 +1099,6 @@ echo RunTest.bat tests successfully completed ADD_TEST(pcre2posix_test pcre2posix_test) ENDIF(PCRE2_BUILD_PCRE2_8) - ENDIF(PCRE2_BUILD_TESTS) # Installation @@ -1099,8 +1130,8 @@ FILE(GLOB html ${PROJECT_SOURCE_DIR}/doc/html/*.html) FILE(GLOB man1 ${PROJECT_SOURCE_DIR}/doc/*.1) FILE(GLOB man3 ${PROJECT_SOURCE_DIR}/doc/*.3) -INSTALL(FILES ${man1} DESTINATION man/man1) -INSTALL(FILES ${man3} DESTINATION man/man3) +INSTALL(FILES ${man1} DESTINATION ${CMAKE_INSTALL_MANDIR}/man1) +INSTALL(FILES ${man3} DESTINATION ${CMAKE_INSTALL_MANDIR}/man3) INSTALL(FILES ${html} DESTINATION share/doc/pcre2/html) IF(MSVC AND INSTALL_MSVC_PDB) @@ -1145,6 +1176,7 @@ IF(PCRE2_SHOW_REPORT) MESSAGE(STATUS " EBCDIC coding with NL=0x25 ...... : ${PCRE2_EBCDIC_NL25}") MESSAGE(STATUS " Rebuild char tables ............. : ${PCRE2_REBUILD_CHARTABLES}") MESSAGE(STATUS " Internal link size .............. : ${PCRE2_LINK_SIZE}") + MESSAGE(STATUS " Maximum variable lookbehind ..... : ${PCRE2_MAX_VARLOOKBEHIND}") MESSAGE(STATUS " Parentheses nest limit .......... : ${PCRE2_PARENS_NEST_LIMIT}") MESSAGE(STATUS " Heap limit ...................... : ${PCRE2_HEAP_LIMIT}") MESSAGE(STATUS " Match limit ..................... : ${PCRE2_MATCH_LIMIT}") diff --git a/pcre2/ChangeLog b/pcre2/ChangeLog index 2b10036..ea228c1 100644 --- a/pcre2/ChangeLog +++ b/pcre2/ChangeLog @@ -1,5 +1,268 @@ -Change Log for PCRE2 - see also the Git log -------------------------------------------- +Change Log for PCRE2 +-------------------- + +Before the move to GitHub, this was the only record of changes to PCRE2. Now +there is also the log of commit messages. + +Version 10.44 07-June-2024 +-------------------------- + +1. If a pattern contained a variable-length lookbehind in which the first +branch was not the one with the shortest minimum length, and the lookbehind +contained a capturing group, and elsewhere in the pattern there was another +lookbehind that referenced that group, the pattern was incorrectly compiled, +leading to unpredictable results, including crashes in JIT compiling. An +example pattern is: /(((?<=123?456456|ABC)))(?<=\2)/ + +2. Further updates to the oss-fuzz support: + + (a) Limit quantifiers for groups and classes to be no more than 10. This + avoids very long JIT compile times that happen in some cases when groups + are replicated for quantification, and very long match times when + classes contain a lot of non-ascii characters. + + (b) Added PCRE2_EXTENDED_MORE to the list of allowed options. + + (c) Arranged for text error messages to be shown in 16-bit and 32-bit modes. + + (d) Made the output in standalone mode more readable. + + (e) General code tidies. + + (f) Limit the size of compiled patterns to 10MB (see 6 below). + + (g) Do not run JIT on patterns whose compiled length is greater than 200K + bytes because this takes a long time, causing oss-fuzz to time out. + + (h) Avoid compiling or matching twice with the same options (this could + happen if the input didn't set any options). + +3. Increase the maximum length of a name for a group from 32 to 128 because +there is a user for whom 32 is too small. + +4. Cause pcre2test to output a message when pcre2_jit_compile() gives an error +return if either jitverify or info is specified. + +5. Some auxiliary files for building under OpenVMS that were contributed by +Alexey Chupahin have been installed. + +6. Added pcre2_set_max_pattern_compiled_length() to limit the size of compiled +patterns. + +7. There was a bug in the implementation of \X caused by my (PH) misreading or +misunderstanding one of the grapheme sequence breaking rules in Unicode Annex +#29. A break should occur between two characters with the Extended Pictographic +break property unless a zero-width joiner intervenes. PCRE2 was not insisting +on the ZWJ, causing \X to match more than it should. See GitHub issue #410. + +8. Avoid compilation issues with proprietary compilers in UNIX since 10.43. + + +Version 10.43 16-February-2024 +------------------------------ + +1. The test program added by change 2 of 10.42 didn't work when the default +newline setting didn't include \n as a newline. One test needed (*LF) to ensure +that it worked. + +2. Added the new freestanding POSIX test program to the ManyConfigTests script +in the maint directory (overlooked in 2 below). Also improved the selection +facilities in that script, and added a test with JIT in a non-source directory, +fixing an oversight that would have made such a test fail before. + +3. Added pcre2_get_match_data_heapframes_size() and related pcre2test flags +to allow for finer control of the heap used when pcre2_match() without JIT is +used and the match_data might be reused. This began as PR #191, but has had +further refinement and documentation edits. + +4. Applied PR #181, which tidies some casts in pcre2_valid_utf.c. + +5. Applied PR #184, which avoids overflow issues with the heap limit +(introduced in 10.41/9). + +6. Applied PR #192, which changes the timing units for pcre2test from +milliseconds to microseconds. This is more useful for modern CPUs. + +7. Applied PR #193, which makes the requirement for C99 explicit in +configure.ac and CMakeLists.txt. + +8. Fixed a bug in pcre2test when a ridiculously large string repeat required a +stupid amount of memory. It now gives a clean realloc() failure error. + +9. Updates to restrict the interaction between ASCII and non-ASCII characters +for caseless matching and items like \d: + + (a) Added PCRE2_EXTRA_CASELESS_RESTRICT to lock out mixing of ASCII and + non-ASCII when matching caselessly. This is also /r in pcre2test and + (?r) within patterns. + + (b) Added PCRE2_EXTRA_ASCII_{BSD,BSS,BSW,POSIX} and corresponding (?aD) etc + in patterns and /a in pcre2test. + + (c) Corresponding updates to pcre2test. + +10. Unicode has been updated to 15.0.0. + +11. The Python scripts and ucptest.c in maint have been updated (a) a minor +change needed for 9(a) above; (b) fix bugs in ucptest, + +12. Integer overflow testing is now centralized in a new function. + +13. Made PCRE2_UCP the default in UTF mode in pcre2grep, and added new options +--case-restrict and --no-ucp. + +14. In the debugging printint module (which is normally only linked into +pcre2test), avoid the use of a variable called "not" because that's deprecated +in C and forbidden in C++. Also rewrite some code to avoid a goto into a block +that bypassed its initialization (though it didn't actually matter). + +15. More minor code adjustments to avoid using reserved C++ words as variable +names ("new" and "typename") and another jump that bypassed an (irrelevant) +initialization. + +16. Merged a pull request that removed pcre2_ucptables.c from the list of files +to compile in NON-AUTOTOOLS-BUILD because it is #included in pcre2_tables.c. +Also adjusted the BUILD.bazel and build.zig files, which had the same issue. At +the same time, fixed a typo in the Bazel file. + +17. Add PCRE2_EXTRA_ASCII_DIGIT to allow [:digit:] to be kept on sync with \d +even in UCP mode. + +18. Fix an invalid match of ascii word classes when invalid utf is enabled. + +19. Add a --posix-digit to pcre2grep for compatibility with GNU grep, and +other tools that prefer the POSIX compatible unicode definition for \d. + +20. Report the bit width of the library in use by pcre2test for usability. + +21. A pathological pattern conversion test could result in a string longer than +the available input buffer. Cause such a test to fail. + +22. Add a check that forces a compiler error if PCRE2_CODE_UNIT_WIDTH is not 8, +16, or 32 when compiling any of the library modules. + +23. Update pcre2_compile() to treat a NULL pattern with zero length as an empty +string. + +24. Add support for limited-length variable-length lookbehind assertions, with +default maximum length 255 characters (same as Perl) but with a function to +adjust the limit. + +25. Applied pull request #262, which updates the zig configuration, and #278 +which fixes a bug with out-of-source-tree CMake build testing. + +26. Add support for LoongArch to JIT. + +27. Fixed a bug in pcre2_match() in the code for handling the vector of +backtracking frames on the heap, which caused a heap overflow if *LIMIT_HEAP +restricted an attempt to extend to less than the frame size. Generally tidy up +the code for extending the heap frames vector. This fixes GitHub issue #275. + +28. Update pcre2_fuzzsupport.c to avoid clang sanitize complaint about shifting +left by 16 when there are non-zeros in the top 16 bits. + +29. Perl 5.34.0 changed the meaning of (for example) {,3} which did not used to +be treated as a quantifier. Now it is interpreted as {0,3} and PCRE2 has +changed to match. Note that {,} is still not a quantifier. + +30. Perl allows spaces and/or horizontal tabs after { or before } in all items +that use braces, and also before or after the comma in quantifiers. PCRE2 now +does the same, except for \u{...}, which is recognized only when +PCRE2_EXTRA_ALT_BSUX is set. This an ECMAScript, non-Perl compatible, +extension, so PCRE2 follows ECMAScript rather than Perl. + +31. Applied pull request #300 by Carlo, which fixes #261. The bug was that +pcre2_match() was not fully resetting all captures that had been set within a +(possibly recursive) subroutine call such as (?3). + +32. Changed the meaning of \w (and its synonyms) in UCP mode to match Perl. It +now matches characters whose general categories are L or N or whose particular +categories are Mn (non-spacing mark) or Pc (combining punctuation). The latter +includes underscore. + +33. Changed the meaning of [:xdigit:] in UCP mode to match Perl. It now also +matches the "fullwidth" versions of the hex digits. Just like it is done for +[:digit:], PCRE2_EXTRA_ASCII_DIGIT can be used to keep this class ASCII only +without affecting other POSIX classes. + +34. GitHub PR305 fixes a potential integer overflow in pcre2_dfa_match(). + +35. Updated handling of \b and \B in UCP mode to match the changes to \w in 32 +above because \b and \B are defined in terms of \w. + +36. Within a pattern (?aT) and (?-aT) set and reset the PCRE2_EXTRA_ASCII_DIGIT +option, and (?aP) also sets (?aT) so that (?-aP) disables all ASCII +restrictions on POSIX classes. + +37. If PCRE2_FIRSTLINE was set on an anchored pattern, pcre2_match() and +pcre2_dfa_match() misbehaved. PCRE2_FIRSTLINE is now ignored for anchored +patterns. + +38. Add a test for ridiculous ovector offset values to the substring extraction +functions. + +39. Make OP_REVERSE use IMM2_SIZE for its data instead of LINK_SIZE, for +consistency with OP_VREVERSE. + +40. In some legacy environments with a pre C99 snprintf, pcre2_regerror could +return an incorrect value when the provided buffer was too small. + +41. Applied pull request #342 which adds sanity checks for ctype functions and +locks out any accidental sign-extension. + +42. In the 32-bit library, in non-UTF mode, a quantifier that followed a +literal character with a value greater than or equal to 0x80000000u caused +undefined behaviour. + +43. \z was misbehaving when matching fragments inside invalid UTF strings. + +44. Implement --group-separator and --no-group-separator for pcre2grep. + +45. Fix \X matching in 32 bit mode without UTF in JIT. + +46. Fix backref iterators when PCRE2_MATCH_UNSET_BACKREF is set in JIT. + +47. Refactor the handling of whole-pattern recursion (?0) in pcre2_match() so +that its end is handled similarly to other recursions. This has altered the +behaviour of /|(?0)./endanchored which was previously not right. + +48. Improved the test for looping recursion by checking the last referenced +character as well as the current character. This allows some patterns that +previously triggered the check to run to completion instead of giving the loop +error. + +49. In 32-bit mode, the compiler looped for the pattern /[\x{ffffffff}]/ when +PCRE2_CASELESS and PCRE2_UCP (but not PCRE2_UTF) were set. Fixed by not trying +to look for other cases for characters above the Unicode range. + +50. In caseless 32-bit mode with UCP (but not UTF) set, the character +0xffffffff incorrectly matched any character that has more than one other case, +in particular k and s. + +51. Fix accept and endanchored interaction in JIT. + +52. Fix backreferences with unset backref and non-greedy iterators in JIT. + +53. Improve the logic that checks for a list of starting code units -- positive +lookahead assertions are now ignored if the immediately following item is one +that sets a mandatory starting character. For example, /a?(?=bc|)d/ used to set +all of a, b, and d as possible starting code units; now it sets only a and d. + +54. Fix incorrect class character matches in JIT. + +55. In pcre2test, ensure pcre2_jit_match() is used when jitfast is used with +substitution testing. + +56. Insert omitted setting of subject length in match data at the end of +pcre2_jit_match(). + +57. Implemented PCRE2_DISABLE_RECURSELOOP_CHECK for pcre2_match() to enable +some apparently looping recursions to run to completion and therefore match the +JIT behaviour. With this set, real loops will eventually get caught by match or +heap limits or run out of resource. + +58. AC did a lot of work on pcre2_fuzzsupport.c to extend it to 16-bit and +32-bit libraries and to compare JIT and non-JIT matching. Version 10.42 11-December-2022 @@ -24,6 +287,13 @@ maximum of 65535 is now silently applied. 5. Merged @carenas patch #175 which fixes #86 - segfault on aarch64 (ARM), +6. The prototype for pcre2_substring_list_free() specified its argument as +PCRE2_SPTR * which is a const data type, whereas the yield from +pcre2_substring_list() is not const. This caused compiler warnings. I have +changed the argument of pcre2_substring_list_free() to be PCRE2_UCHAR ** to +remove this anomaly. This might cause new warnings in existing code where a +cast has been used to avoid previous ones. + Version 10.41 06-December-2022 ------------------------------ @@ -80,7 +350,7 @@ elsewhere that can never be obeyed in normal testing has been excluded from coverage. 15. Fixed a bug in pcre2grep that could cause an extra newline to be written -after output generaed by --output. +after output generated by --output. 16. If a file has a .bz2 extension but is not in fact compressed, pcre2grep should process it as a plain text file. A bug stopped this happening; now fixed @@ -235,7 +505,7 @@ Version 10.39 29-October-2021 that an appropriate width is chosen if pointers are 64bit wide and long is not (ex: Windows 64bit). - IMHO removing the cast (and therefore the possibilty of truncation) + IMHO removing the cast (and therefore the possibility of truncation) make the code cleaner and the fallback is likely portable enough with all 64-bit POSIX systems doing LP64 except for Windows. @@ -370,7 +640,7 @@ now the same as Perl. quantifier was nevertheless complaining that a quantifier number was too big. 5. A run of autoconf suggested that configure.ac was out-of-date with respect -to the lastest autoconf. Running autoupdate made some valid changes, some valid +to the latest autoconf. Running autoupdate made some valid changes, some valid suggestions, and also some invalid changes, which were fixed by hand. Autoconf now runs clean and the resulting "configure" seems to work, so I hope nothing is broken. Later: the requirement for autoconf 2.70 broke some automatic test @@ -402,7 +672,7 @@ compiler. This fixes https://bugs.exim.org/show_bug.cgi?id=2578. Patch for Makefile.am and configure.ac by H.J. Lu. Equivalent patch for CMakeLists.txt invented by PH. -2. Fix inifinite loop when a single byte newline is searched in JIT when +2. Fix infinite loop when a single byte newline is searched in JIT when invalid utf8 mode is enabled. 3. Updated CMakeLists.txt with patch from Wolfgang Stöggl (Bugzilla #2584): @@ -515,7 +785,7 @@ after the end a repeated group, the captured substrings had their values from the final repetition, not from an earlier repetition that might be the destination of a backtrack. This feature was documented, and was carried over into PCRE2. However, it has now been realized that the major refactoring that -was done for 10.30 has made this atomicizing unnecessary, and it is confusing +was done for 10.30 has made this atomizing unnecessary, and it is confusing when users are unaware of it, making some patterns appear not to be working as expected. Capture values of recursive back references in repeated groups are now correctly backtracked, so this unnecessary restriction has been removed. @@ -965,7 +1235,7 @@ gets rid of the warnings. There were also two missing casts in pcre2test. Version 10.32 10-September-2018 ------------------------------- -1. When matching using the the REG_STARTEND feature of the POSIX API with a +1. When matching using the REG_STARTEND feature of the POSIX API with a non-zero starting offset, unset capturing groups with lower numbers than a group that did capture something were not being correctly returned as "unset" (that is, with offset values of -1). @@ -1140,7 +1410,7 @@ assumed empty second branch cannot be anchored. Demonstrated by test patterns such as /(?(1)^())b/ or /(?(?=^))b/. 40. A repeated conditional subpattern that could match an empty string was -always assumed to be unanchored. Now it it checked just like any other +always assumed to be unanchored. Now it is checked just like any other repeated conditional subpattern, and can be found to be anchored if the minimum quantifier is one or more. I can't see much use for a repeated anchored pattern, but the behaviour is now consistent. @@ -1678,7 +1948,7 @@ not recognize this syntax. 7. Automatic callouts are no longer generated before and after callouts in the pattern. -8. When pcre2test was outputing information from a callout, the caret indicator +8. When pcre2test was outputting information from a callout, the caret indicator for the current position in the subject line was incorrect if it was after an escape sequence for a character whose code point was greater than \x{ff}. @@ -2059,7 +2329,7 @@ if it fails when running the interpreter with a 16MiB stack (and if changing the stack size via pcre2test is possible). This avoids having to manually set a large stack size when testing with clang. -42. Fix register overwite in JIT when SSE2 acceleration is enabled. +42. Fix register overwrite in JIT when SSE2 acceleration is enabled. 43. Detect integer overflow in pcre2test pattern and data repetition counts. @@ -2812,7 +3082,7 @@ characters, for example: /(?:(?=.)|(?= META_END -META_OPTIONS (?i) and friends (data is new option bits) META_POSIX POSIX class item (data identifies the class) META_POSIX_NEG negative POSIX class item (ditto) @@ -282,22 +282,34 @@ The following is followed just by an offset, for use in error messages: META_COND_DEFINE (?(DEFINE) -The following are also followed just by an offset, but also the lower 16 bits -of the main word contain the length of the first branch of the lookbehind -group; this is used when generating OP_REVERSE for that branch. +The following are at first also followed just by an offset for use in error +messages. After the lengths of the branches of a lookbehind group have been +checked the error offset is no longer needed. The lower 16 bits of the main +word are now set to the maximum length of the first branch of the lookbehind +group, and the second word is set to the mimimum matching length for a +variable-length lookbehind group, or to LOOKBEHIND_MAX for a group whose +branches are all of fixed length. These values are used when generating +OP_REVERSE or OP_VREVERSE for the first branch. The miminum value is also used +for any subsequent branches because there is only room for one value (the +branch maximum length) in a META_ALT item. META_LOOKBEHIND (?<= start of lookbehind META_LOOKBEHIND_NA (*naplb: start of non-atomic lookbehind META_LOOKBEHINDNOT (?' and 1 for '>='; the next two are the major and minor numbers: @@ -369,7 +381,7 @@ data that follows it. In many cases listed below, LINK_SIZE data values are specified for offsets within the compiled pattern. LINK_SIZE always specifies a number of bytes. The default value for LINK_SIZE is 2, except for the 32-bit library, where it can -only be 4. The 8-bit library can be compiled to used 3-byte or 4-byte values, +only be 4. The 8-bit library can be compiled to use 3-byte or 4-byte values, and the 16-bit library can be compiled to use 4-byte values, though this impairs performance. Specifying a LINK_SIZE larger than 2 for these libraries is necessary only when patterns whose compiled length is greater than 65535 code @@ -718,14 +730,25 @@ Assertions Forward assertions are also just like other subpatterns, but starting with one of the opcodes OP_ASSERT, OP_ASSERT_NA (non-atomic assertion), or -OP_ASSERT_NOT. Backward assertions use the opcodes OP_ASSERTBACK, -OP_ASSERTBACK_NA, and OP_ASSERTBACK_NOT, and the first opcode inside the -assertion is OP_REVERSE, followed by a count of the number of characters to -move back the pointer in the subject string. In ASCII or UTF-32 mode, the count -is also the number of code units, but in UTF-8/16 mode each character may -occupy more than one code unit. A separate count is present in each alternative -of a lookbehind assertion, allowing each branch to have a different (but fixed) -length. +OP_ASSERT_NOT. + +Backward assertions use the opcodes OP_ASSERTBACK, OP_ASSERTBACK_NA, and +OP_ASSERTBACK_NOT. If all the branches of a backward assertion are of fixed +length (not necessarily the same), the first opcode inside each branch is +OP_REVERSE, followed by an IMM2_SIZE count of the number of characters to move +back the pointer in the subject string, thus allowing each branch to have a +different (but fixed) length. + +Variable-length backward assertions whose maximum matching length is limited +are also supported. For such assertions, the first opcode inside each branch is +OP_VREVERSE, followed by the minimum and maximum lengths for that branch, +unless these happen to be equal, in which case OP_REVERSE is used. These +IMM2_SIZE values occupy two code units each in 8-bit mode, and 1 code unit in +16/32 bit modes. + +In ASCII or UTF-32 mode, the character counts in OP_REVERSE and OP_VREVERSE are +also the number of code units, but in UTF-8/16 mode each character may occupy +more than one code unit. Conditional subpatterns @@ -827,4 +850,4 @@ not a real opcode, but is used to check at compile time that tables indexed by opcode are the correct length, in order to catch updating errors. Philip Hazel -April 2022 +November 2023 diff --git a/pcre2/LICENCE b/pcre2/LICENCE index 2f3cd5c..3c1ef03 100644 --- a/pcre2/LICENCE +++ b/pcre2/LICENCE @@ -26,7 +26,7 @@ Email domain: gmail.com Retired from University of Cambridge Computing Service, Cambridge, England. -Copyright (c) 1997-2022 University of Cambridge +Copyright (c) 1997-2024 University of Cambridge All rights reserved. @@ -37,7 +37,7 @@ Written by: Zoltan Herczeg Email local part: hzmester Email domain: freemail.hu -Copyright(c) 2010-2022 Zoltan Herczeg +Copyright(c) 2010-2024 Zoltan Herczeg All rights reserved. @@ -48,7 +48,7 @@ Written by: Zoltan Herczeg Email local part: hzmester Email domain: freemail.hu -Copyright(c) 2009-2022 Zoltan Herczeg +Copyright(c) 2009-2024 Zoltan Herczeg All rights reserved. diff --git a/pcre2/Makefile.am b/pcre2/Makefile.am index 1a15d11..ca6a638 100644 --- a/pcre2/Makefile.am +++ b/pcre2/Makefile.am @@ -46,6 +46,7 @@ dist_html_DATA = \ doc/html/pcre2_general_context_free.html \ doc/html/pcre2_get_error_message.html \ doc/html/pcre2_get_mark.html \ + doc/html/pcre2_get_match_data_heapframes_size.html \ doc/html/pcre2_get_match_data_size.html \ doc/html/pcre2_get_ovector_count.html \ doc/html/pcre2_get_ovector_pointer.html \ @@ -81,7 +82,9 @@ dist_html_DATA = \ doc/html/pcre2_set_glob_separator.html \ doc/html/pcre2_set_heap_limit.html \ doc/html/pcre2_set_match_limit.html \ + doc/html/pcre2_set_max_pattern_compiled_length.html \ doc/html/pcre2_set_max_pattern_length.html \ + doc/html/pcre2_set_max_varlookbehind.html \ doc/html/pcre2_set_offset_limit.html \ doc/html/pcre2_set_newline.html \ doc/html/pcre2_set_parens_nest_limit.html \ @@ -142,6 +145,7 @@ dist_man_MANS = \ doc/pcre2_general_context_free.3 \ doc/pcre2_get_error_message.3 \ doc/pcre2_get_mark.3 \ + doc/pcre2_get_match_data_heapframes_size.3 \ doc/pcre2_get_match_data_size.3 \ doc/pcre2_get_ovector_count.3 \ doc/pcre2_get_ovector_pointer.3 \ @@ -177,7 +181,9 @@ dist_man_MANS = \ doc/pcre2_set_glob_separator.3 \ doc/pcre2_set_heap_limit.3 \ doc/pcre2_set_match_limit.3 \ + doc/pcre2_set_max_pattern_compiled_length.3 \ doc/pcre2_set_max_pattern_length.3 \ + doc/pcre2_set_max_varlookbehind.3 \ doc/pcre2_set_offset_limit.3 \ doc/pcre2_set_newline.3 \ doc/pcre2_set_parens_nest_limit.3 \ @@ -234,9 +240,19 @@ bin_PROGRAMS = noinst_PROGRAMS = # Additional files to delete on 'make clean', 'make distclean', -# and 'make maintainer-clean'. +# and 'make maintainer-clean'. It turns out that the default is to delete only +# those binaries that *this* configuration has created. If the configuration +# has been changed, some binaries may not get automatically deleted. Therefore +# we list them here. + +CLEANFILES = \ + pcre2_dftables \ + pcre2_jit_test \ + pcre2fuzzcheck-8 \ + pcre2fuzzcheck-16 \ + pcre2fuzzcheck-32 \ + pcre2demo -CLEANFILES = DISTCLEANFILES = src/config.h.in~ MAINTAINERCLEANFILES = @@ -256,6 +272,14 @@ EXTRA_DIST += \ NON-AUTOTOOLS-BUILD \ HACKING +# These are support files for building under VMS + +EXTRA_DIST += \ + vms/configure.com \ + vms/openvms_readme.txt \ + vms/pcre2.h_patch \ + vms/stdint.h + # These files are used in the preparation of a release EXTRA_DIST += \ @@ -290,8 +314,7 @@ src/pcre2.h.generic: src/pcre2.h.in configure.ac # config.status out of the way while doing the default configuration. The # resulting config.h is munged by perl to put #ifdefs round any #defines for # macros with values, and to #undef all boolean macros such as HAVE_xxx and -# SUPPORT_xxx. We also get rid of any gcc-specific visibility settings. Make -# sure that PCRE2_EXP_DEFN is unset (in case it has visibility settings). +# SUPPORT_xxx. We also get rid of any gcc-specific visibility settings. src/config.h.generic: configure.ac rm -rf $@ _generic @@ -302,9 +325,7 @@ src/config.h.generic: configure.ac test -f _generic/src/config.h perl -n \ -e 'BEGIN{$$blank=0;}' \ - -e 'if(/PCRE2_EXP_DEFN/){print"/* #undef PCRE2_EXP_DEFN */\n";$$blank=0;next;}' \ - -e 'if(/to make a symbol visible/){next;}' \ - -e 'if(/__attribute__ \(\(visibility/){next;}' \ + -e 'if(/(.+?)\s*__attribute__ \(\(visibility/){print"$$1\n";$$blank=0;next;}' \ -e 'if(/LT_OBJDIR/){print"/* This is ignored unless you are using libtool. */\n";}' \ -e 'if(/^#define\s((?:HAVE|SUPPORT|STDC)_\w+)/){print"/* #undef $$1 */\n";$$blank=0;next;}' \ -e 'if(/^#define\s(?!PACKAGE|VERSION)(\w+)/){print"#ifndef $$1\n$$_#endif\n";$$blank=0;next;}' \ @@ -351,6 +372,7 @@ NODIST_SOURCES = src/pcre2_chartables.c COMMON_SOURCES = \ src/pcre2_auto_possess.c \ + src/pcre2_chkdint.c \ src/pcre2_compile.c \ src/pcre2_config.c \ src/pcre2_context.c \ @@ -439,13 +461,14 @@ CLEANFILES += src/pcre2_chartables.c EXTRA_DIST += \ src/sljit/sljitConfig.h \ + src/sljit/sljitConfigCPU.h \ src/sljit/sljitConfigInternal.h \ - src/sljit/sljitExecAllocator.c \ src/sljit/sljitLir.c \ src/sljit/sljitLir.h \ src/sljit/sljitNativeARM_32.c \ src/sljit/sljitNativeARM_64.c \ src/sljit/sljitNativeARM_T2_32.c \ + src/sljit/sljitNativeLOONGARCH_64.c \ src/sljit/sljitNativeMIPS_32.c \ src/sljit/sljitNativeMIPS_64.c \ src/sljit/sljitNativeMIPS_common.c \ @@ -459,9 +482,17 @@ EXTRA_DIST += \ src/sljit/sljitNativeX86_32.c \ src/sljit/sljitNativeX86_64.c \ src/sljit/sljitNativeX86_common.c \ - src/sljit/sljitProtExecAllocator.c \ + src/sljit/sljitSerialize.c \ src/sljit/sljitUtils.c \ - src/sljit/sljitWXExecAllocator.c + src/sljit/allocator_src/sljitExecAllocatorApple.c \ + src/sljit/allocator_src/sljitExecAllocatorCore.c \ + src/sljit/allocator_src/sljitExecAllocatorFreeBSD.c \ + src/sljit/allocator_src/sljitExecAllocatorPosix.c \ + src/sljit/allocator_src/sljitExecAllocatorWindows.c \ + src/sljit/allocator_src/sljitProtExecAllocatorNetBSD.c \ + src/sljit/allocator_src/sljitProtExecAllocatorPosix.c \ + src/sljit/allocator_src/sljitWXExecAllocatorPosix.c \ + src/sljit/allocator_src/sljitWXExecAllocatorWindows.c # Some of the JIT sources are also in separate files that are #included. @@ -509,7 +540,7 @@ if WITH_PCRE2_8 lib_LTLIBRARIES += libpcre2-posix.la libpcre2_posix_la_SOURCES = src/pcre2posix.c libpcre2_posix_la_CFLAGS = \ - -DPCRE2_CODE_UNIT_WIDTH=8 \ + -DPCRE2_CODE_UNIT_WIDTH=8 @PCRE2POSIX_CFLAG@ \ $(VISIBILITY_CFLAGS) $(AM_CFLAGS) libpcre2_posix_la_LDFLAGS = $(EXTRA_LIBPCRE2_POSIX_LDFLAGS) libpcre2_posix_la_LIBADD = libpcre2-8.la @@ -530,28 +561,64 @@ if WITH_GCOV pcre2grep_CFLAGS += $(GCOV_CFLAGS) pcre2grep_LDADD += $(GCOV_LIBS) endif # WITH_GCOV +endif # WITH_PCRE2_8 ## If fuzzer support is enabled, build a non-distributed library containing the ## fuzzing function. Also build the standalone checking binary from the same ## source but using -DSTANDALONE. if WITH_FUZZ_SUPPORT -noinst_LIBRARIES = .libs/libpcre2-fuzzsupport.a +noinst_LIBRARIES = +if WITH_PCRE2_8 +noinst_LIBRARIES += .libs/libpcre2-fuzzsupport.a _libs_libpcre2_fuzzsupport_a_SOURCES = src/pcre2_fuzzsupport.c _libs_libpcre2_fuzzsupport_a_CFLAGS = $(AM_CFLAGS) _libs_libpcre2_fuzzsupport_a_LIBADD = -noinst_PROGRAMS += pcre2fuzzcheck -pcre2fuzzcheck_SOURCES = src/pcre2_fuzzsupport.c -pcre2fuzzcheck_CFLAGS = -DSTANDALONE $(AM_CFLAGS) -pcre2fuzzcheck_LDADD = libpcre2-8.la +noinst_PROGRAMS += pcre2fuzzcheck-8 +pcre2fuzzcheck_8_SOURCES = src/pcre2_fuzzsupport.c +pcre2fuzzcheck_8_CFLAGS = -DSTANDALONE $(AM_CFLAGS) +pcre2fuzzcheck_8_LDADD = libpcre2-8.la if WITH_GCOV -pcre2fuzzcheck_CFLAGS += $(GCOV_CFLAGS) -pcre2fuzzcheck_LDADD += $(GCOV_LIBS) +pcre2fuzzcheck_8_CFLAGS += $(GCOV_CFLAGS) +pcre2fuzzcheck_8_LDADD += $(GCOV_LIBS) endif # WITH_GCOV -endif # WITH FUZZ_SUPPORT endif # WITH_PCRE2_8 +if WITH_PCRE2_16 +noinst_LIBRARIES += .libs/libpcre2-fuzzsupport-16.a +_libs_libpcre2_fuzzsupport_16_a_SOURCES = src/pcre2_fuzzsupport.c +_libs_libpcre2_fuzzsupport_16_a_CFLAGS = $(AM_CFLAGS) -DPCRE2_CODE_UNIT_WIDTH=16 +_libs_libpcre2_fuzzsupport_16_a_LIBADD = + +noinst_PROGRAMS += pcre2fuzzcheck-16 +pcre2fuzzcheck_16_SOURCES = src/pcre2_fuzzsupport.c +pcre2fuzzcheck_16_CFLAGS = -DSTANDALONE $(AM_CFLAGS) -DPCRE2_CODE_UNIT_WIDTH=16 +pcre2fuzzcheck_16_LDADD = libpcre2-16.la +if WITH_GCOV +pcre2fuzzcheck_16_CFLAGS += $(GCOV_CFLAGS) +pcre2fuzzcheck_16_LDADD += $(GCOV_LIBS) +endif # WITH_GCOV +endif # WITH_PCRE2_16 + +if WITH_PCRE2_32 +noinst_LIBRARIES += .libs/libpcre2-fuzzsupport-32.a +_libs_libpcre2_fuzzsupport_32_a_SOURCES = src/pcre2_fuzzsupport.c +_libs_libpcre2_fuzzsupport_32_a_CFLAGS = $(AM_CFLAGS) -DPCRE2_CODE_UNIT_WIDTH=32 +_libs_libpcre2_fuzzsupport_32_a_LIBADD = + +noinst_PROGRAMS += pcre2fuzzcheck-32 +pcre2fuzzcheck_32_SOURCES = src/pcre2_fuzzsupport.c +pcre2fuzzcheck_32_CFLAGS = -DSTANDALONE $(AM_CFLAGS) -DPCRE2_CODE_UNIT_WIDTH=32 +pcre2fuzzcheck_32_LDADD = libpcre2-32.la +if WITH_GCOV +pcre2fuzzcheck_32_CFLAGS += $(GCOV_CFLAGS) +pcre2fuzzcheck_32_LDADD += $(GCOV_LIBS) +endif # WITH_GCOV +endif # WITH_PCRE2_32 + +endif # WITH_FUZZ_SUPPORT + ## -------- Testing ---------- ## If the 8-bit library is enabled, build the POSIX wrapper test program and @@ -561,7 +628,7 @@ if WITH_PCRE2_8 TESTS += pcre2posix_test noinst_PROGRAMS += pcre2posix_test pcre2posix_test_SOURCES = src/pcre2posix_test.c -pcre2posix_test_CFLAGS = $(AM_CFLAGS) +pcre2posix_test_CFLAGS = $(AM_CFLAGS) @PCRE2POSIX_CFLAG@ pcre2posix_test_LDADD = libpcre2-posix.la libpcre2-8.la endif # WITH_PCRE2_8 diff --git a/pcre2/NEWS b/pcre2/NEWS index 97da19e..5f8dde3 100644 --- a/pcre2/NEWS +++ b/pcre2/NEWS @@ -2,6 +2,62 @@ News about PCRE2 releases ------------------------- +Version 10.44 07-June-2024 +-------------------------- + +This is mostly a bug-fix and tidying release. There is one new function, to set +a maximum size for a compiled pattern. The maximum name length for groups is +increased to 128. Some auxiliary files for building under VMS are added. + + +Version 10.43 16-February-2024 +------------------------------ + +There are quite a lot of changes in this release (see ChangeLog and git log for +a list). Those that are not bugfixes or code tidies are: + +* The JIT code no longer supports ARMv5 architecture. + +* A new function pcre2_get_match_data_heapframes_size() for finer heap control. + +* New option flags to restrict the interaction between ASCII and non-ASCII + characters for caseless matching and \d and friends. There are also new + pattern constructs to control these flags from within a pattern. + +* Upgrade to Unicode 15.0.0. + +* Treat a NULL pattern with zero length as an empty string. + +* Added support for limited-length variable-length lookbehind assertions, with + a default maximum length of 255 characters (same as Perl) but with a function + to adjust the limit. + +* Support for LoongArch in JIT. + +* Perl changed the meaning of (for example) {,3} which did not used to be + recognized as a quantifier. Now it means {0,3} and PCRE2 has also changed. + Note that {,} is still not a quantifier. + +* Following Perl, allow spaces and tabs after { and before } in all Perl- + compatible items that use braces, and also around commas in quantifiers. The + one exception in PCRE2 is \u{...}, which is from ECMAScript, not Perl, and + PCRE2 follows ECMAScript usage. + +* Changed the meaning of \w and its synonyms and derivatives (\b and \B) in UCP + mode to follow Perl. It now matches characters whose general categories are L + or N or whose particular categories are Mn (non-spacing mark) or Pc + (combining punctuation). + +* Changed the default meaning of [:xdigit:] in UCP mode to follow Perl. It now + matches the "fullwidth" versions of hex digits. PCRE2_EXTRA_ASCII_DIGIT can + be used to keep it ASCII only. + +* Make PCRE2_UCP the default in UTF mode in pcre2grep and add -no_ucp, + --case-restrict and --posix-digit. + +* Add --group-separator and --no-group-separator to pcre2grep. + + Version 10.42 11-December-2022 ------------------------------ diff --git a/pcre2/NON-AUTOTOOLS-BUILD b/pcre2/NON-AUTOTOOLS-BUILD index d83591a..851976a 100644 --- a/pcre2/NON-AUTOTOOLS-BUILD +++ b/pcre2/NON-AUTOTOOLS-BUILD @@ -4,7 +4,7 @@ Building PCRE2 without using autotools This document contains the following sections: General - Generic instructions for the PCRE2 C library + Generic instructions for the PCRE2 C libraries Stack size in Windows environments Linking programs in Windows environments Calling conventions in Windows environments @@ -13,13 +13,14 @@ This document contains the following sections: Building PCRE2 on Windows with Visual Studio Testing with RunTest.bat Building PCRE2 on native z/OS and z/VM + Building PCRE2 under VMS GENERAL -The basic PCRE2 library consists entirely of code written in Standard C, and so -should compile successfully on any system that has a Standard C compiler and -library. +The source of the PCRE2 libraries consists entirely of code written in Standard +C, and so should compile successfully on any system that has a Standard C +compiler and library. The PCRE2 distribution includes a "configure" file for use by the configure/make (autotools) build system, as found in many Unix-like @@ -36,21 +37,25 @@ provided for those who build PCRE2 without using "configure" or CMake. If you use "configure" or CMake, the .generic versions are not used. -GENERIC INSTRUCTIONS FOR THE PCRE2 C LIBRARY +GENERIC INSTRUCTIONS FOR THE PCRE2 C LIBRARIES -The following are generic instructions for building the PCRE2 C library "by -hand". If you are going to use CMake, this section does not apply to you; you -can skip ahead to the CMake section. Note that the settings concerned with -8-bit, 16-bit, and 32-bit code units relate to the type of data string that -PCRE2 processes. They are NOT referring to the underlying operating system bit -width. You do not have to do anything special to compile in a 64-bit -environment, for example. +There are three possible PCRE2 libraries, each handling data with a specific +code unit width: 8, 16, or 32 bits. You can build any combination of them. The +following are generic instructions for building a PCRE2 C library "by hand". If +you are going to use CMake, this section does not apply to you; you can skip +ahead to the CMake section. Note that the settings concerned with 8-bit, +16-bit, and 32-bit code units relate to the type of data string that PCRE2 +processes. They are NOT referring to the underlying operating system bit width. +You do not have to do anything special to compile in a 64-bit environment, for +example. (1) Copy or rename the file src/config.h.generic as src/config.h, and edit the macro settings that it contains to whatever is appropriate for your environment. In particular, you can alter the definition of the NEWLINE macro to specify what character(s) you want to be interpreted as line - terminators by default. + terminators by default. You need to #define at least one of + SUPPORT_PCRE2_8, SUPPORT_PCRE2_16, or SUPPORT_PCRE2_32, depending on which + libraries you are going to build. You must set all that apply. When you subsequently compile any of the PCRE2 modules, you must specify -DHAVE_CONFIG_H to your compiler so that src/config.h is included in the @@ -97,6 +102,7 @@ environment, for example. or else use other -D settings to change the configuration as required. pcre2_auto_possess.c + pcre2_chkdint.c pcre2_chartables.c pcre2_compile.c pcre2_config.c @@ -121,7 +127,6 @@ environment, for example. pcre2_substring.c pcre2_tables.c pcre2_ucd.c - pcre2_ucptables.c pcre2_valid_utf.c pcre2_xclass.c @@ -143,22 +148,24 @@ environment, for example. you are doing that, you can ignore it. (5) Now link all the compiled code into an object library in whichever form - your system keeps such libraries. This is the basic PCRE2 C 8-bit library. - If your system has static and shared libraries, you may have to do this - once for each type. + your system keeps such libraries. This is the PCRE2 C 8-bit library, + typically called something like libpcre2-8. If your system has static and + shared libraries, you may have to do this once for each type. (6) If you want to build a library that supports 16-bit or 32-bit code units, - (as well as, or instead of the 8-bit library) just supply 16 or 32 as the - value of -DPCRE2_CODE_UNIT_WIDTH when you are compiling. + set 16 or 32 as the value of -DPCRE2_CODE_UNIT_WIDTH when obeying step 4 + above. If you want to build more than one PCRE2 library, repeat steps 4 + and 5 as necessary. (7) If you want to build the POSIX wrapper functions (which apply only to the 8-bit library), ensure that you have the src/pcre2posix.h file and then compile src/pcre2posix.c. Link the result (on its own) as the pcre2posix - library. + library. If targeting a DLL in Windows, make sure to include + -DPCRE2POSIX_SHARED with your compiler flags. (8) The pcre2test program can be linked with any combination of the 8-bit, - 16-bit and 32-bit libraries (depending on what you selected in - src/config.h). Compile src/pcre2test.c; don't forget -DHAVE_CONFIG_H if + 16-bit and 32-bit libraries (depending on what you specfied in + src/config.h) . Compile src/pcre2test.c; don't forget -DHAVE_CONFIG_H if necessary, but do NOT define PCRE2_CODE_UNIT_WIDTH. Then link with the appropriate library/ies. If you compiled an 8-bit library, pcre2test also needs the pcre2posix wrapper library. @@ -191,8 +198,8 @@ environment, for example. both the pcre2posix library and the 8-bit PCRE2 library. (12) If you want to use the pcre2grep command, compile and link - src/pcre2grep.c; it uses only the basic 8-bit PCRE2 library (it does not - need the pcre2posix library). If you have built the PCRE2 library with JIT + src/pcre2grep.c; it uses only the 8-bit PCRE2 library (it does not need + the pcre2posix library). If you have built the PCRE2 library with JIT support by defining SUPPORT_JIT in src/config.h, you can also define SUPPORT_PCRE2GREP_JIT, which causes pcre2grep to make use of JIT (unless it is run with --no-jit). If you define SUPPORT_PCRE2GREP_JIT without @@ -216,7 +223,7 @@ CALLING CONVENTIONS IN WINDOWS ENVIRONMENTS It is possible to compile programs to use different calling conventions using MSVC. Search the web for "calling conventions" for more information. To make it -easier to change the calling convention for the exported functions in the +easier to change the calling convention for the exported functions in a PCRE2 library, the macro PCRE2_CALL_CONVENTION is present in all the external definitions. It can be set externally when compiling (e.g. in CFLAGS). If it is not set, it defaults to empty; the default calling convention is then used @@ -410,6 +417,14 @@ Everything in that location, source and executable, is in EBCDIC and native z/OS file formats. The port provides an API for LE languages such as COBOL and for the z/OS and z/VM versions of the Rexx languages. -============================== -Last Updated: 10 December 2022 -============================== + +BUILDING PCRE2 UNDER VMS + +Alexey Chuphin has contributed some auxiliary files for building PCRE2 under +OpenVMS. They are in the "vms" directory in the distribution tarball. Please +read the file called vms/openvms_readme.txt. The pcre2test and pcre2grep +programs contain some VMS-specific code. + +=========================== +Last Updated: 16 April 2024 +=========================== diff --git a/pcre2/PrepareRelease b/pcre2/PrepareRelease index 1852c76..0dc6e30 100755 --- a/pcre2/PrepareRelease +++ b/pcre2/PrepareRelease @@ -92,27 +92,44 @@ done echo "Making pcre2demo.3" perl <<"END" >pcre2demo.3 + use Time::Piece; + open(VH, "<", "../src/config.h.generic") || die "Failed to open src/config.h.generic\n"; open(IN, "../src/pcre2demo.c") || die "Failed to open src/pcre2demo.c\n"; open(OUT, ">pcre2demo.3") || die "Failed to open pcre2demo.3\n"; - print OUT ".SH NAME\n" . - "// - A demonstration C program for PCRE2 - //\n" . - ".sp\n" . + my $version; + while () + { + chomp; + if ( /^#define PACKAGE_STRING "([^"]+)"/ ) { $version = $1 ; last } + } + my $t = localtime; + print OUT ".TH PCRE2DEMO 3 \"", $t->strftime('%e %B %Y'), '" "', $version, "\"\n" . + ".\\\"AUTOMATICALLY GENERATED BY PrepareRelease - do not EDIT!\n" . + ".SH NAME\n" . + "PCRE2DEMO - A demonstration C program for PCRE2\n" . + ".SH \"SOURCE CODE\"\n" . + ".rs\n" . + ".sp\n" . ".\\\" Start example.\n" . ".de EX\n" . + ". do ds mF \\\\n[.fam]\n" . ". nr mE \\\\n(.f\n" . ". nf\n" . ". nh\n" . + ". do fam C\n" . ". ft CW\n" . "..\n" . ".\n" . ".\n" . ".\\\" End example.\n" . ".de EE\n" . + ". do fam \\\\*(mF\n" . ". ft \\\\n(mE\n" . ". fi\n" . ". hy \\\\n(HY\n" . "..\n" . ".\n" . + ".RS -7\n" . ".EX\n" ; while () { @@ -150,6 +167,7 @@ for file in *.3 ; do if [ `expr $base : '.*_'` -ne 0 ] ; then toc="" ; fi if [ "$base" = "pcre2sample" ] || \ [ "$base" = "pcre2compat" ] || \ + [ "$base" = "pcre2demo" ] || \ [ "$base" = "pcre2limits" ] || \ [ "$base" = "pcre2unicode" ] ; then toc="" diff --git a/pcre2/README b/pcre2/README index c88acff..dab5e94 100644 --- a/pcre2/README +++ b/pcre2/README @@ -24,7 +24,6 @@ contents of this README file are: The PCRE2 APIs Documentation for PCRE2 - Contributions by users of PCRE2 Building PCRE2 on non-Unix-like systems Building PCRE2 without using autotools Building PCRE2 using autotools @@ -157,7 +156,18 @@ library. They are also documented in the pcre2build man page. --disable-shared --disable-static - (See also "Shared libraries on Unix-like systems" below.) + Setting --disable-shared ensures that PCRE2 libraries are built as static + libraries. The binaries that are then created as part of the build process + (for example, pcre2test and pcre2grep) are linked statically with one or more + PCRE2 libraries, but may also be dynamically linked with other libraries such + as libc. If you want these binaries to be fully statically linked, you can + set LDFLAGS like this: + + LDFLAGS=--static ./configure --disable-shared + + Note the two hyphens in --static. Of course, this works only if static + versions of all the relevant libraries are available for linking. See also + "Shared libraries" below. . By default, only the 8-bit library is built. If you add --enable-pcre2-16 to the "configure" command, the 16-bit library is also built. If you add @@ -271,6 +281,17 @@ library. They are also documented in the pcre2build man page. performance in the 8-bit and 16-bit libraries. In the 32-bit library, the link size setting is ignored, as 4-byte offsets are always used. +. Lookbehind assertions in which one or more branches can match a variable + number of characters are supported only if there is a maximum matching length + for each top-level branch. There is a limit to this maximum that defaults to + 255 characters. You can alter this default by a setting such as + + --with-max-varlookbehind=100 + + The limit can be changed at runtime by calling pcre2_set_max_varlookbehind(). + Lookbehind assertions in which every branch matches a fixed number of + characters (not necessarily all the same) are not constrained by this limit. + . For speed, PCRE2 uses four tables for manipulating and identifying characters whose code point values are less than 256. By default, it uses a set of tables for ASCII encoding that is part of the distribution. If you specify @@ -369,7 +390,7 @@ library. They are also documented in the pcre2build man page. avoided by linking with libedit (which has a BSD licence) instead. Enabling libreadline causes the -lreadline option to be added to the - pcre2test build. In many operating environments with a sytem-installed + pcre2test build. In many operating environments with a system-installed readline library this is sufficient. However, in some environments (e.g. if an unmodified distribution version of readline is in use), it may be necessary to specify something like LIBS="-lncurses" as well. This is @@ -549,7 +570,10 @@ configuring it. For example: ./configure --prefix=/usr/gnu --disable-shared Then run "make" in the usual way. Similarly, you can use --disable-static to -build only shared libraries. +build only shared libraries. Note, however, that when you build only static +libraries, binary programs such as pcre2test and pcre2grep may still be +dynamically linked with other libraries (for example, libc) unless you set +LDFLAGS to --static when running "configure". Cross-compiling using autotools @@ -800,6 +824,7 @@ The distribution should contain the files listed below. src/pcre2posix.c ) src/pcre2_auto_possess.c ) + src/pcre2_chkdint.c ) src/pcre2_compile.c ) src/pcre2_config.c ) src/pcre2_context.c ) @@ -918,7 +943,14 @@ The distribution should contain the files listed below. src/config.h.generic ) a version of config.h for use in non-"configure" ) environments +(F) Auxiliary files for building PCRE2 under OpenVMS + + vms/configure.com ) + vms/openvms_readme.txt ) These files were contributed by a PCRE2 user. + vms/pcre2.h_patch ) + vms/stdint.h ) + Philip Hazel Email local part: Philip.Hazel Email domain: gmail.com -Last updated: 10 December 2022 +Last updated: 15 April 2024 diff --git a/pcre2/RunGrepTest b/pcre2/RunGrepTest index 0a00e82..c382187 100755 --- a/pcre2/RunGrepTest +++ b/pcre2/RunGrepTest @@ -853,7 +853,13 @@ fi echo "---------------------------- Test 151 -----------------------------" >>testtrygrep (cd $srcdir; $valgrind $vjs $pcre2grep --colour=always -e this -e The -e 'The wo' testdata/grepinputv) >>testtrygrep +echo "---------------------------- Test 152 -----------------------------" >>testtrygrep +(cd $srcdir; $valgrind $vjs $pcre2grep -nA3 --group-separator='++' 'four' ./testdata/grepinputx) >>testtrygrep +echo "RC=$?" >>testtrygrep +echo "---------------------------- Test 153 -----------------------------" >>testtrygrep +(cd $srcdir; $valgrind $vjs $pcre2grep -nA3 --no-group-separator 'four' ./testdata/grepinputx) >>testtrygrep +echo "RC=$?" >>testtrygrep # Now compare the results. @@ -893,6 +899,22 @@ if [ $utf8 -ne 0 ] ; then (cd $srcdir; $valgrind $vjs $pcre2grep -u -m1 -O '=$x{1d3}$o{744}=' 'fox') <$srcdir/testdata/grepinputv >>testtrygrep 2>&1 echo "RC=$?" >>testtrygrep + echo "---------------------------- Test U7 ------------------------------" >>testtrygrep + (cd $srcdir; $valgrind $vjs $pcre2grep -ui --colour=always 'k+|\babc\b' ./testdata/grepinput8) >>testtrygrep + echo "RC=$?" >>testtrygrep + + echo "---------------------------- Test U8 ------------------------------" >>testtrygrep + (cd $srcdir; $valgrind $vjs $pcre2grep -UiEP --colour=always 'k+|\babc\b' ./testdata/grepinput8) >>testtrygrep + echo "RC=$?" >>testtrygrep + + echo "---------------------------- Test U9 ------------------------------" >>testtrygrep + (cd $srcdir; $valgrind $vjs $pcre2grep -u --colour=always 'A\d' ./testdata/grepinput8) >>testtrygrep + echo "RC=$?" >>testtrygrep + + echo "---------------------------- Test U10 ------------------------------" >>testtrygrep + (cd $srcdir; $valgrind $vjs $pcre2grep -u --posix-digit --colour=always 'A\d' ./testdata/grepinput8) >>testtrygrep + echo "RC=$?" >>testtrygrep + $cf $srcdir/testdata/grepoutput8 testtrygrep if [ $? != 0 ] ; then exit 1; fi diff --git a/pcre2/RunTest b/pcre2/RunTest index ae32f5d..d426a59 100755 --- a/pcre2/RunTest +++ b/pcre2/RunTest @@ -527,7 +527,7 @@ for bmode in "$test8" "$test16" "$test32"; do $sim $valgrind ${opt:+$vjs} ./pcre2test -q $setstack $bmode $opt $testdata/testinput2 testtry saverc=$? if [ $saverc = 0 ] ; then - $sim $valgrind ${opt:+$vjs} ./pcre2test -q $bmode $opt -error -70,-62,-2,-1,0,100,101,191,200 >>testtry + $sim $valgrind ${opt:+$vjs} ./pcre2test -q $bmode $opt -error -70,-62,-2,-1,0,100,101,191,300 >>testtry checkresult $? 2 "$opt" else checkresult $saverc 2 "$opt" diff --git a/pcre2/RunTest.bat b/pcre2/RunTest.bat index 401b95a..9f203fe 100644 --- a/pcre2/RunTest.bat +++ b/pcre2/RunTest.bat @@ -27,6 +27,8 @@ @rem Tidied and updated for new tests 21, 22, 23 by PH, October 2015. @rem PH added missing "set type" for test 22, April 2016. @rem PH added copy command for new testbtables file, November 2020 +@rem PH caused it to show comparison output when comparison faile, July 2023 +@rem PH updated unknown error number in test setlocal enabledelayedexpansion @@ -264,7 +266,7 @@ if errorlevel 1 ( set failed="yes" goto :eof ) else if [%1]==[2] ( - %pcre2test% %mode% %4 %5 %6 %7 %8 %9 -error -70,-62,-2,-1,0,100,101,191,200 >>%2%bits%\%testoutput% + %pcre2test% %mode% %4 %5 %6 %7 %8 %9 -error -70,-62,-2,-1,0,100,101,191,300 >>%2%bits%\%testoutput% ) set type= @@ -292,6 +294,7 @@ if errorlevel 1 ( echo. goto :eof ) + fc /n %srcdir%\testdata\%testoutput%%type% %2%bits%\%testoutput% set failed="yes" goto :eof diff --git a/pcre2/build.zig b/pcre2/build.zig new file mode 100644 index 0000000..048aa7e --- /dev/null +++ b/pcre2/build.zig @@ -0,0 +1,83 @@ +const std = @import("std"); + +pub const CodeUnitWidth = enum { + @"8", + @"16", + @"32", +}; + +pub fn build(b: *std.Build) !void { + const target = b.standardTargetOptions(.{}); + const optimize = b.standardOptimizeOption(.{}); + const linkage = b.option(std.builtin.LinkMode, "linkage", "whether to statically or dynamically link the library") orelse @as(std.builtin.LinkMode, if (target.result.isGnuLibC()) .dynamic else .static); + const codeUnitWidth = b.option(CodeUnitWidth, "code-unit-width", "Sets the code unit width") orelse .@"8"; + + const copyFiles = b.addWriteFiles(); + _ = copyFiles.addCopyFile(.{ .path = "src/config.h.generic" }, "config.h"); + _ = copyFiles.addCopyFile(.{ .path = "src/pcre2.h.generic" }, "pcre2.h"); + + const lib = std.Build.Step.Compile.create(b, .{ + .name = b.fmt("pcre2-{s}", .{@tagName(codeUnitWidth)}), + .root_module = .{ + .target = target, + .optimize = optimize, + .link_libc = true, + }, + .kind = .lib, + .linkage = linkage, + }); + + if (linkage == .static) { + try lib.root_module.c_macros.append(b.allocator, "-DPCRE2_STATIC"); + } + + lib.root_module.addCMacro("PCRE2_CODE_UNIT_WIDTH", @tagName(codeUnitWidth)); + + lib.addCSourceFile(.{ + .file = copyFiles.addCopyFile(.{ .path = "src/pcre2_chartables.c.dist" }, "pcre2_chartables.c"), + .flags = &.{ + "-DHAVE_CONFIG_H", + }, + }); + + lib.addIncludePath(.{ .path = b.pathFromRoot("src") }); + lib.addIncludePath(copyFiles.getDirectory()); + + lib.addCSourceFiles(.{ + .files = &.{ + "src/pcre2_auto_possess.c", + "src/pcre2_chkdint.c", + "src/pcre2_compile.c", + "src/pcre2_config.c", + "src/pcre2_context.c", + "src/pcre2_convert.c", + "src/pcre2_dfa_match.c", + "src/pcre2_error.c", + "src/pcre2_extuni.c", + "src/pcre2_find_bracket.c", + "src/pcre2_maketables.c", + "src/pcre2_match.c", + "src/pcre2_match_data.c", + "src/pcre2_newline.c", + "src/pcre2_ord2utf.c", + "src/pcre2_pattern_info.c", + "src/pcre2_script_run.c", + "src/pcre2_serialize.c", + "src/pcre2_string_utils.c", + "src/pcre2_study.c", + "src/pcre2_substitute.c", + "src/pcre2_substring.c", + "src/pcre2_tables.c", + "src/pcre2_ucd.c", + "src/pcre2_valid_utf.c", + "src/pcre2_xclass.c", + }, + .flags = &.{ + "-DHAVE_CONFIG_H", + "-DPCRE2_STATIC", + }, + }); + + lib.installHeader(.{ .path = "src/pcre2.h.generic" }, "pcre2.h"); + b.installArtifact(lib); +} diff --git a/pcre2/cmake/pcre2-config.cmake.in b/pcre2/cmake/pcre2-config.cmake.in index b313d6d..84eebad 100644 --- a/pcre2/cmake/pcre2-config.cmake.in +++ b/pcre2/cmake/pcre2-config.cmake.in @@ -49,12 +49,14 @@ else () set(PCRE2_SUFFIX ${CMAKE_SHARED_LIBRARY_SUFFIX}) if (MINGW AND PCRE2_NON_STANDARD_LIB_SUFFIX) set(PCRE2_SUFFIX "-0.dll") + elseif(MSVC) + set(PCRE2_SUFFIX ${CMAKE_STATIC_LIBRARY_SUFFIX}) endif () endif () find_library(PCRE2_8BIT_LIBRARY NAMES ${PCRE2_PREFIX}${PCRE2_8BIT_NAME}${PCRE2_SUFFIX} ${PCRE2_PREFIX}${PCRE2_8BIT_NAME}d${PCRE2_SUFFIX} DOC "8 bit PCRE2 library") -find_library(PCRE2_16BIT_LIBRARY NAMES ${PCRE2_PREFIX}${PCRE2_16BIT_NAME}${PCRE2_SUFFIX} ${PCRE2_PREFIX}${PCRE2_8BIT_NAME}d${PCRE2_SUFFIX} DOC "16 bit PCRE2 library") -find_library(PCRE2_32BIT_LIBRARY NAMES ${PCRE2_PREFIX}${PCRE2_32BIT_NAME}${PCRE2_SUFFIX} ${PCRE2_PREFIX}${PCRE2_8BIT_NAME}d${PCRE2_SUFFIX} DOC "32 bit PCRE2 library") -find_library(PCRE2_POSIX_LIBRARY NAMES ${PCRE2_PREFIX}${PCRE2_POSIX_NAME}${PCRE2_SUFFIX} ${PCRE2_PREFIX}${PCRE2_8BIT_NAME}d${PCRE2_SUFFIX} DOC "8 bit POSIX PCRE2 library") +find_library(PCRE2_16BIT_LIBRARY NAMES ${PCRE2_PREFIX}${PCRE2_16BIT_NAME}${PCRE2_SUFFIX} ${PCRE2_PREFIX}${PCRE2_16BIT_NAME}d${PCRE2_SUFFIX} DOC "16 bit PCRE2 library") +find_library(PCRE2_32BIT_LIBRARY NAMES ${PCRE2_PREFIX}${PCRE2_32BIT_NAME}${PCRE2_SUFFIX} ${PCRE2_PREFIX}${PCRE2_32BIT_NAME}d${PCRE2_SUFFIX} DOC "32 bit PCRE2 library") +find_library(PCRE2_POSIX_LIBRARY NAMES ${PCRE2_PREFIX}${PCRE2_POSIX_NAME}${PCRE2_SUFFIX} ${PCRE2_PREFIX}${PCRE2_POSIX_NAME}d${PCRE2_SUFFIX} DOC "8 bit POSIX PCRE2 library") unset(PCRE2_NON_STANDARD_LIB_PREFIX) unset(PCRE2_NON_STANDARD_LIB_SUFFIX) unset(PCRE2_8BIT_NAME) @@ -126,6 +128,7 @@ if (PCRE2_FOUND) endif () set_target_properties(PCRE2::${component} PROPERTIES IMPORTED_LOCATION "${PCRE2_${component}_LIBRARY}" + IMPORTED_IMPLIB "${PCRE2_${component}_LIBRARY}" INTERFACE_INCLUDE_DIRECTORIES "${PCRE2_INCLUDE_DIR}" ) if (component STREQUAL "POSIX") diff --git a/pcre2/config-cmake.h.in b/pcre2/config-cmake.h.in index f560afe..6539d77 100644 --- a/pcre2/config-cmake.h.in +++ b/pcre2/config-cmake.h.in @@ -1,8 +1,8 @@ /* config.h for CMake builds */ +#cmakedefine HAVE_BUILTIN_MUL_OVERFLOW 1 #cmakedefine HAVE_ATTRIBUTE_UNINITIALIZED 1 #cmakedefine HAVE_DIRENT_H 1 -#cmakedefine HAVE_STRERROR 1 #cmakedefine HAVE_SYS_STAT_H 1 #cmakedefine HAVE_SYS_TYPES_H 1 #cmakedefine HAVE_UNISTD_H 1 @@ -39,16 +39,18 @@ #cmakedefine HEAP_MATCH_RECURSE 1 #cmakedefine NEVER_BACKSLASH_C 1 +#define PCRE2_EXPORT @PCRE2_EXPORT@ #define LINK_SIZE @PCRE2_LINK_SIZE@ #define HEAP_LIMIT @PCRE2_HEAP_LIMIT@ #define MATCH_LIMIT @PCRE2_MATCH_LIMIT@ #define MATCH_LIMIT_DEPTH @PCRE2_MATCH_LIMIT_DEPTH@ +#define MAX_VARLOOKBEHIND @PCRE2_MAX_VARLOOKBEHIND@ #define NEWLINE_DEFAULT @NEWLINE_DEFAULT@ #define PARENS_NEST_LIMIT @PCRE2_PARENS_NEST_LIMIT@ #define PCRE2GREP_BUFSIZE @PCRE2GREP_BUFSIZE@ #define PCRE2GREP_MAX_BUFSIZE @PCRE2GREP_MAX_BUFSIZE@ -#define MAX_NAME_SIZE 32 +#define MAX_NAME_SIZE 128 #define MAX_NAME_COUNT 10000 /* end config.h for CMake builds */ diff --git a/pcre2/configure.ac b/pcre2/configure.ac index ce5bda3..6091ea4 100644 --- a/pcre2/configure.ac +++ b/pcre2/configure.ac @@ -9,20 +9,20 @@ dnl The PCRE2_PRERELEASE feature is for identifying release candidates. It might dnl be defined as -RC2, for example. For real releases, it should be empty. m4_define(pcre2_major, [10]) -m4_define(pcre2_minor, [42]) +m4_define(pcre2_minor, [44]) m4_define(pcre2_prerelease, []) -m4_define(pcre2_date, [2022-12-11]) +m4_define(pcre2_date, [2024-06-07]) # Libtool shared library interface versions (current:revision:age) -m4_define(libpcre2_8_version, [11:2:11]) -m4_define(libpcre2_16_version, [11:2:11]) -m4_define(libpcre2_32_version, [11:2:11]) -m4_define(libpcre2_posix_version, [3:4:0]) +m4_define(libpcre2_8_version, [13:0:13]) +m4_define(libpcre2_16_version, [13:0:13]) +m4_define(libpcre2_32_version, [13:0:13]) +m4_define(libpcre2_posix_version, [3:5:0]) # NOTE: The CMakeLists.txt file searches for the above variables in the first # 50 lines of this file. Please update that if the variables above are moved. -AC_PREREQ([2.60]) +AC_PREREQ([2.62]) AC_INIT([PCRE2],pcre2_major.pcre2_minor[]pcre2_prerelease,[],[pcre2]) AC_CONFIG_SRCDIR([src/pcre2.h.in]) AM_INIT_AUTOMAKE([dist-bzip2 dist-zip]) @@ -42,7 +42,7 @@ AC_CONFIG_MACRO_DIR([m4]) remember_set_CFLAGS="$CFLAGS" -AC_PROG_CC +m4_version_prereq(2.70, [AC_PROG_CC], [AC_PROG_CC_C99]) AM_PROG_CC_C_O AC_USE_SYSTEM_EXTENSIONS @@ -73,6 +73,28 @@ AC_SYS_LARGEFILE PCRE2_VISIBILITY +# Check for the mul_overflow() builtin + +AC_MSG_CHECKING([for __builtin_mul_overflow()]) +AC_LANG_PUSH([C]) +AC_LINK_IFELSE([AC_LANG_PROGRAM([[ + #ifdef HAVE_SYS_TYPES_H + #include + #endif + #include + + int a, b; + size_t m; + ]], [[__builtin_mul_overflow(a, b, &m)]])], + [pcre2_cc_cv_builtin_mul_overflow=yes], + [pcre2_cc_cv_builtin_mul_overflow=no]) +AC_MSG_RESULT([$pcre2_cc_cv_builtin_mul_overflow]) +if test "$pcre2_cc_cv_builtin_mul_overflow" = yes; then + AC_DEFINE([HAVE_BUILTIN_MUL_OVERFLOW], 1, + [Define this if your compiler provides __builtin_mul_overflow()]) +fi +AC_LANG_POP([C]) + # Check for Clang __attribute__((uninitialized)) feature AC_MSG_CHECKING([for __attribute__((uninitialized))]) @@ -169,7 +191,7 @@ if test "$enable_jit" = "auto"; then CPPFLAGS=-I$srcdir AC_COMPILE_IFELSE([AC_LANG_SOURCE([[ #define SLJIT_CONFIG_AUTO 1 - #include "src/sljit/sljitConfigInternal.h" + #include "src/sljit/sljitConfigCPU.h" #if (defined SLJIT_CONFIG_UNSUPPORTED && SLJIT_CONFIG_UNSUPPORTED) #error unsupported #endif]])], enable_jit=yes, enable_jit=no) @@ -314,6 +336,12 @@ AC_ARG_WITH(link-size, [internal link size (2, 3, or 4 allowed; default=2)]), , with_link_size=2) +# Handle --with-max-varlookbehind=N +AC_ARG_WITH(max-varlookbehind, + AS_HELP_STRING([--with-max-varlookbehind=N], + [maximum length of variable lookbehind (default=255)]), + , with_max_varlookbehind=255) + # Handle --with-parens-nest-limit=N AC_ARG_WITH(parens-nest-limit, AS_HELP_STRING([--with-parens-nest-limit=N], @@ -367,6 +395,12 @@ AC_ARG_ENABLE(fuzz_support, [enable fuzzer support]), , enable_fuzz_support=no) +# Handle --enable-diff-fuzz-support +AC_ARG_ENABLE(diff_fuzz_support, + AS_HELP_STRING([--enable-diff-fuzz-support], + [enable differential fuzzer support]), + , enable_diff_fuzz_support=no) + # Handle --disable-stack-for-recursion # This option became obsolete at release 10.30. AC_ARG_ENABLE(stack-for-recursion,, @@ -501,12 +535,26 @@ AM_CONDITIONAL(WITH_JIT, test "x$enable_jit" = "xyes") AM_CONDITIONAL(WITH_UNICODE, test "x$enable_unicode" = "xyes") AM_CONDITIONAL(WITH_VALGRIND, test "x$enable_valgrind" = "xyes") AM_CONDITIONAL(WITH_FUZZ_SUPPORT, test "x$enable_fuzz_support" = "xyes") +AM_CONDITIONAL(WITH_DIFF_FUZZ_SUPPORT, test "x$enable_diff_fuzz_support" = "xyes") if test "$enable_fuzz_support" = "yes" -a "$enable_pcre2_8" = "no"; then echo "** ERROR: Fuzzer support requires the 8-bit library" exit 1 fi +if test "$enable_diff_fuzz_support" = "yes"; then + if test "$enable_fuzz_support" = "no"; then + echo "** ERROR: Differential fuzzing support requires fuzzing support" + exit 1 + fi + if test "$enable_jit" = "no"; then + echo "** ERROR: Differential fuzzing support requires Just-in-Time compilation support" + exit 1 + fi + AC_DEFINE([SUPPORT_DIFF_FUZZ], [], [ + Define to any value to enable differential fuzzing support.]) +fi + # Checks for typedefs, structures, and compiler characteristics. AC_C_CONST @@ -618,6 +666,12 @@ if test "x$enable_shared" = "xno" ; then fi AC_SUBST(PCRE2_STATIC_CFLAG) +PCRE2POSIX_CFLAG="" +if test "x$enable_shared" = "xyes" ; then + PCRE2POSIX_CFLAG="-DPCRE2POSIX_SHARED" +fi +AC_SUBST(PCRE2POSIX_CFLAG) + # Here is where PCRE2-specific defines are handled if test "$enable_pcre2_8" = "yes"; then @@ -779,6 +833,10 @@ AC_DEFINE_UNQUOTED([LINK_SIZE], [$with_link_size], [ vast majority of cases. However, PCRE2 can also be compiled to use 3 or 4 bytes instead. This allows for longer patterns in extreme cases.]) +AC_DEFINE_UNQUOTED([MAX_VARLOOKBEHIND], [$with_max_varlookbehind], [ + The value of MAX_VARLOOKBEHIND specifies the default maximum length, in + characters, for a variable-length lookbehind assertion.]) + AC_DEFINE_UNQUOTED([PARENS_NEST_LIMIT], [$with_parens_nest_limit], [ The value of PARENS_NEST_LIMIT specifies the maximum depth of nested parentheses (of any kind) in a pattern. This limits the amount of system @@ -790,7 +848,7 @@ AC_DEFINE_UNQUOTED([MATCH_LIMIT], [$with_match_limit], [ matching attempt. The value is also used to limit a loop counter in pcre2_dfa_match(). There is a runtime interface for setting a different limit. The limit exists in order to catch runaway regular expressions that - take for ever to determine that they do not match. The default is set very + take forever to determine that they do not match. The default is set very large so that it does not accidentally catch legitimate cases.]) # --with-match-limit-recursion is an obsolete synonym for --with-match-limit-depth @@ -825,7 +883,7 @@ AC_DEFINE_UNQUOTED([HEAP_LIMIT], [$with_heap_limit], [ a pattern. It applies to both pcre2_match() and pcre2_dfa_match(). It does not apply to JIT matching. The value is in kibibytes (units of 1024 bytes).]) -AC_DEFINE([MAX_NAME_SIZE], [32], [ +AC_DEFINE([MAX_NAME_SIZE], [128], [ This limit is parameterized just in case anybody ever wants to change it. Care must be taken if it is increased, because it guards against integer overflow caused by enormously large patterns.]) @@ -840,8 +898,9 @@ AH_VERBATIM([PCRE2_EXP_DEFN], [ Win32, and it needs some magic to be inserted before the definition of a function that is exported by the library, define this macro to contain the relevant magic. If you do not define this macro, a suitable - __declspec value is used for Windows systems; in other environments - "extern" is used for a C compiler and "extern C" for a C++ compiler. + __declspec value is used for Windows systems; in other environments + a compiler relevant "extern" is used with any "visibility" related + attributes from PCRE2_EXPORT included. This macro apears at the start of every exported function that is part of the external API. It does not appear on functions that are "external" in the C sense, but which are internal to the library. */ @@ -1104,6 +1163,7 @@ $PACKAGE-$VERSION configuration summary: EBCDIC code for NL ................. : ${ebcdic_nl_code} Rebuild char tables ................ : ${enable_rebuild_chartables} Internal link size ................. : ${with_link_size} + Maximum variable lookbehind ........ : ${with_max_varlookbehind} Nested parentheses limit ........... : ${with_parens_nest_limit} Heap limit ......................... : ${with_heap_limit} kibibytes Match limit ........................ : ${with_match_limit} @@ -1122,6 +1182,7 @@ $PACKAGE-$VERSION configuration summary: Valgrind support ................... : ${enable_valgrind} Code coverage ...................... : ${enable_coverage} Fuzzer support ..................... : ${enable_fuzz_support} + Differential fuzzer support ........ : ${enable_diff_fuzz_support} Use %zu and %td .................... : ${enable_percent_zt} EOF diff --git a/pcre2/doc/html/NON-AUTOTOOLS-BUILD.txt b/pcre2/doc/html/NON-AUTOTOOLS-BUILD.txt index d83591a..851976a 100644 --- a/pcre2/doc/html/NON-AUTOTOOLS-BUILD.txt +++ b/pcre2/doc/html/NON-AUTOTOOLS-BUILD.txt @@ -4,7 +4,7 @@ Building PCRE2 without using autotools This document contains the following sections: General - Generic instructions for the PCRE2 C library + Generic instructions for the PCRE2 C libraries Stack size in Windows environments Linking programs in Windows environments Calling conventions in Windows environments @@ -13,13 +13,14 @@ This document contains the following sections: Building PCRE2 on Windows with Visual Studio Testing with RunTest.bat Building PCRE2 on native z/OS and z/VM + Building PCRE2 under VMS GENERAL -The basic PCRE2 library consists entirely of code written in Standard C, and so -should compile successfully on any system that has a Standard C compiler and -library. +The source of the PCRE2 libraries consists entirely of code written in Standard +C, and so should compile successfully on any system that has a Standard C +compiler and library. The PCRE2 distribution includes a "configure" file for use by the configure/make (autotools) build system, as found in many Unix-like @@ -36,21 +37,25 @@ provided for those who build PCRE2 without using "configure" or CMake. If you use "configure" or CMake, the .generic versions are not used. -GENERIC INSTRUCTIONS FOR THE PCRE2 C LIBRARY +GENERIC INSTRUCTIONS FOR THE PCRE2 C LIBRARIES -The following are generic instructions for building the PCRE2 C library "by -hand". If you are going to use CMake, this section does not apply to you; you -can skip ahead to the CMake section. Note that the settings concerned with -8-bit, 16-bit, and 32-bit code units relate to the type of data string that -PCRE2 processes. They are NOT referring to the underlying operating system bit -width. You do not have to do anything special to compile in a 64-bit -environment, for example. +There are three possible PCRE2 libraries, each handling data with a specific +code unit width: 8, 16, or 32 bits. You can build any combination of them. The +following are generic instructions for building a PCRE2 C library "by hand". If +you are going to use CMake, this section does not apply to you; you can skip +ahead to the CMake section. Note that the settings concerned with 8-bit, +16-bit, and 32-bit code units relate to the type of data string that PCRE2 +processes. They are NOT referring to the underlying operating system bit width. +You do not have to do anything special to compile in a 64-bit environment, for +example. (1) Copy or rename the file src/config.h.generic as src/config.h, and edit the macro settings that it contains to whatever is appropriate for your environment. In particular, you can alter the definition of the NEWLINE macro to specify what character(s) you want to be interpreted as line - terminators by default. + terminators by default. You need to #define at least one of + SUPPORT_PCRE2_8, SUPPORT_PCRE2_16, or SUPPORT_PCRE2_32, depending on which + libraries you are going to build. You must set all that apply. When you subsequently compile any of the PCRE2 modules, you must specify -DHAVE_CONFIG_H to your compiler so that src/config.h is included in the @@ -97,6 +102,7 @@ environment, for example. or else use other -D settings to change the configuration as required. pcre2_auto_possess.c + pcre2_chkdint.c pcre2_chartables.c pcre2_compile.c pcre2_config.c @@ -121,7 +127,6 @@ environment, for example. pcre2_substring.c pcre2_tables.c pcre2_ucd.c - pcre2_ucptables.c pcre2_valid_utf.c pcre2_xclass.c @@ -143,22 +148,24 @@ environment, for example. you are doing that, you can ignore it. (5) Now link all the compiled code into an object library in whichever form - your system keeps such libraries. This is the basic PCRE2 C 8-bit library. - If your system has static and shared libraries, you may have to do this - once for each type. + your system keeps such libraries. This is the PCRE2 C 8-bit library, + typically called something like libpcre2-8. If your system has static and + shared libraries, you may have to do this once for each type. (6) If you want to build a library that supports 16-bit or 32-bit code units, - (as well as, or instead of the 8-bit library) just supply 16 or 32 as the - value of -DPCRE2_CODE_UNIT_WIDTH when you are compiling. + set 16 or 32 as the value of -DPCRE2_CODE_UNIT_WIDTH when obeying step 4 + above. If you want to build more than one PCRE2 library, repeat steps 4 + and 5 as necessary. (7) If you want to build the POSIX wrapper functions (which apply only to the 8-bit library), ensure that you have the src/pcre2posix.h file and then compile src/pcre2posix.c. Link the result (on its own) as the pcre2posix - library. + library. If targeting a DLL in Windows, make sure to include + -DPCRE2POSIX_SHARED with your compiler flags. (8) The pcre2test program can be linked with any combination of the 8-bit, - 16-bit and 32-bit libraries (depending on what you selected in - src/config.h). Compile src/pcre2test.c; don't forget -DHAVE_CONFIG_H if + 16-bit and 32-bit libraries (depending on what you specfied in + src/config.h) . Compile src/pcre2test.c; don't forget -DHAVE_CONFIG_H if necessary, but do NOT define PCRE2_CODE_UNIT_WIDTH. Then link with the appropriate library/ies. If you compiled an 8-bit library, pcre2test also needs the pcre2posix wrapper library. @@ -191,8 +198,8 @@ environment, for example. both the pcre2posix library and the 8-bit PCRE2 library. (12) If you want to use the pcre2grep command, compile and link - src/pcre2grep.c; it uses only the basic 8-bit PCRE2 library (it does not - need the pcre2posix library). If you have built the PCRE2 library with JIT + src/pcre2grep.c; it uses only the 8-bit PCRE2 library (it does not need + the pcre2posix library). If you have built the PCRE2 library with JIT support by defining SUPPORT_JIT in src/config.h, you can also define SUPPORT_PCRE2GREP_JIT, which causes pcre2grep to make use of JIT (unless it is run with --no-jit). If you define SUPPORT_PCRE2GREP_JIT without @@ -216,7 +223,7 @@ CALLING CONVENTIONS IN WINDOWS ENVIRONMENTS It is possible to compile programs to use different calling conventions using MSVC. Search the web for "calling conventions" for more information. To make it -easier to change the calling convention for the exported functions in the +easier to change the calling convention for the exported functions in a PCRE2 library, the macro PCRE2_CALL_CONVENTION is present in all the external definitions. It can be set externally when compiling (e.g. in CFLAGS). If it is not set, it defaults to empty; the default calling convention is then used @@ -410,6 +417,14 @@ Everything in that location, source and executable, is in EBCDIC and native z/OS file formats. The port provides an API for LE languages such as COBOL and for the z/OS and z/VM versions of the Rexx languages. -============================== -Last Updated: 10 December 2022 -============================== + +BUILDING PCRE2 UNDER VMS + +Alexey Chuphin has contributed some auxiliary files for building PCRE2 under +OpenVMS. They are in the "vms" directory in the distribution tarball. Please +read the file called vms/openvms_readme.txt. The pcre2test and pcre2grep +programs contain some VMS-specific code. + +=========================== +Last Updated: 16 April 2024 +=========================== diff --git a/pcre2/doc/html/README.txt b/pcre2/doc/html/README.txt index c88acff..dab5e94 100644 --- a/pcre2/doc/html/README.txt +++ b/pcre2/doc/html/README.txt @@ -24,7 +24,6 @@ contents of this README file are: The PCRE2 APIs Documentation for PCRE2 - Contributions by users of PCRE2 Building PCRE2 on non-Unix-like systems Building PCRE2 without using autotools Building PCRE2 using autotools @@ -157,7 +156,18 @@ library. They are also documented in the pcre2build man page. --disable-shared --disable-static - (See also "Shared libraries on Unix-like systems" below.) + Setting --disable-shared ensures that PCRE2 libraries are built as static + libraries. The binaries that are then created as part of the build process + (for example, pcre2test and pcre2grep) are linked statically with one or more + PCRE2 libraries, but may also be dynamically linked with other libraries such + as libc. If you want these binaries to be fully statically linked, you can + set LDFLAGS like this: + + LDFLAGS=--static ./configure --disable-shared + + Note the two hyphens in --static. Of course, this works only if static + versions of all the relevant libraries are available for linking. See also + "Shared libraries" below. . By default, only the 8-bit library is built. If you add --enable-pcre2-16 to the "configure" command, the 16-bit library is also built. If you add @@ -271,6 +281,17 @@ library. They are also documented in the pcre2build man page. performance in the 8-bit and 16-bit libraries. In the 32-bit library, the link size setting is ignored, as 4-byte offsets are always used. +. Lookbehind assertions in which one or more branches can match a variable + number of characters are supported only if there is a maximum matching length + for each top-level branch. There is a limit to this maximum that defaults to + 255 characters. You can alter this default by a setting such as + + --with-max-varlookbehind=100 + + The limit can be changed at runtime by calling pcre2_set_max_varlookbehind(). + Lookbehind assertions in which every branch matches a fixed number of + characters (not necessarily all the same) are not constrained by this limit. + . For speed, PCRE2 uses four tables for manipulating and identifying characters whose code point values are less than 256. By default, it uses a set of tables for ASCII encoding that is part of the distribution. If you specify @@ -369,7 +390,7 @@ library. They are also documented in the pcre2build man page. avoided by linking with libedit (which has a BSD licence) instead. Enabling libreadline causes the -lreadline option to be added to the - pcre2test build. In many operating environments with a sytem-installed + pcre2test build. In many operating environments with a system-installed readline library this is sufficient. However, in some environments (e.g. if an unmodified distribution version of readline is in use), it may be necessary to specify something like LIBS="-lncurses" as well. This is @@ -549,7 +570,10 @@ configuring it. For example: ./configure --prefix=/usr/gnu --disable-shared Then run "make" in the usual way. Similarly, you can use --disable-static to -build only shared libraries. +build only shared libraries. Note, however, that when you build only static +libraries, binary programs such as pcre2test and pcre2grep may still be +dynamically linked with other libraries (for example, libc) unless you set +LDFLAGS to --static when running "configure". Cross-compiling using autotools @@ -800,6 +824,7 @@ The distribution should contain the files listed below. src/pcre2posix.c ) src/pcre2_auto_possess.c ) + src/pcre2_chkdint.c ) src/pcre2_compile.c ) src/pcre2_config.c ) src/pcre2_context.c ) @@ -918,7 +943,14 @@ The distribution should contain the files listed below. src/config.h.generic ) a version of config.h for use in non-"configure" ) environments +(F) Auxiliary files for building PCRE2 under OpenVMS + + vms/configure.com ) + vms/openvms_readme.txt ) These files were contributed by a PCRE2 user. + vms/pcre2.h_patch ) + vms/stdint.h ) + Philip Hazel Email local part: Philip.Hazel Email domain: gmail.com -Last updated: 10 December 2022 +Last updated: 15 April 2024 diff --git a/pcre2/doc/html/index.html b/pcre2/doc/html/index.html index 2c7c5fb..e4dc786 100644 --- a/pcre2/doc/html/index.html +++ b/pcre2/doc/html/index.html @@ -252,8 +252,14 @@ in the library. pcre2_set_match_limit   Set the match limit +pcre2_set_max_pattern_compiled_length +   Set the maximum length of a compiled pattern + pcre2_set_max_pattern_length -   Set the maximum length of pattern +   Set the maximum length of a pattern + +pcre2_set_max_varlookbehind +   Set the maximum match length for a variable-length lookbehind pcre2_set_newline   Set the newline convention diff --git a/pcre2/doc/html/pcre2_compile.html b/pcre2/doc/html/pcre2_compile.html index 615e090..f0080ea 100644 --- a/pcre2/doc/html/pcre2_compile.html +++ b/pcre2/doc/html/pcre2_compile.html @@ -32,24 +32,26 @@ arguments are: 
   pattern       A string containing expression to be compiled
   length        The length of the string or PCRE2_ZERO_TERMINATED
-  options       Option bits
+  options       Primary option bits
   errorcode     Where to put an error code
   erroffset     Where to put an error offset
   ccontext      Pointer to a compile context or NULL
The length of the pattern and any error offset that is returned are in code -units, not characters. A compile context is needed only if you want to provide -custom memory allocation functions, or to provide an external function for -system stack size checking, or to change one or more of these parameters: +units, not characters. A NULL pattern with zero length is treated as an empty +string. A compile context is needed only if you want to provide custom memory +allocation functions, or to provide an external function for system stack size +checking (see pcre2_set_compile_recursion_guard()), or to change one or +more of these parameters: 
   What \R matches (Unicode newlines, or CR, LF, CRLF only);
   PCRE2's character tables;
   The newline character sequence;
   The compile time nested parentheses limit;
-  The maximum pattern length (in code units) that is allowed.
-  The additional options bits (see pcre2_set_compile_extra_options())
+  The maximum pattern length (in code units) that is allowed;
+  The additional options bits.
-The option bits are: +The primary option bits are: 
   PCRE2_ANCHORED           Force pattern anchoring
   PCRE2_ALLOW_EMPTY_CLASS  Allow empty classes
@@ -96,7 +98,7 @@ If either of errorcode or erroroffset is NULL, the function return
 NULL immediately. Otherwise, the yield of this function is a pointer to a
 private data structure that contains the compiled pattern, or NULL if an error
 was detected. In the error case, a text error message can be obtained by
-passing the value returned via the errorcode argument to the the
+passing the value returned via the errorcode argument to the
 pcre2_get_error_message() function. The offset (in code units) where the
 error was encountered is returned via the erroroffset argument.
 

diff --git a/pcre2/doc/html/pcre2_general_context_create.html b/pcre2/doc/html/pcre2_general_context_create.html
index bc31ee8..a1a165d 100644
--- a/pcre2/doc/html/pcre2_general_context_create.html
+++ b/pcre2/doc/html/pcre2_general_context_create.html
@@ -20,7 +20,7 @@ SYNOPSIS
 

 

 pcre2_general_context *pcre2_general_context_create(
-  void *(*private_malloc)(PCRE2_SIZE, void *),
+  void *(*private_malloc)(size_t, void *),
   void (*private_free)(void *, void *), void *memory_data);
 

 

diff --git a/pcre2/doc/html/pcre2_get_match_data_heapframes_size.html b/pcre2/doc/html/pcre2_get_match_data_heapframes_size.html
new file mode 100644
index 0000000..3c705c6
--- /dev/null
+++ b/pcre2/doc/html/pcre2_get_match_data_heapframes_size.html
@@ -0,0 +1,40 @@
+
+
+pcre2_get_match_data_heapframes_size specification
+
+
+
pcre2_get_match_data_heapframes_size man page

+

+Return to the PCRE2 index page.
+

+

+This page is part of the PCRE2 HTML documentation. It was generated
+automatically from the original man page. If there is any nonsense in it,
+please consult the man page, in case the conversion went wrong.
+

+

+SYNOPSIS
+

+

+#include <pcre2.h>
+

+

+PCRE2_SIZE pcre2_get_match_data_heapframes_size(
+  pcre2_match_data *match_data);
+

+

+DESCRIPTION
+

+

+This function returns the size, in bytes, of the heapframes data block that is
+owned by its argument.
+

+

+There is a complete description of the PCRE2 native API in the
+pcre2api
+page and a description of the POSIX API in the
+pcre2posix
+page.
+

+Return to the PCRE2 index page.
+

diff --git a/pcre2/doc/html/pcre2_jit_match.html b/pcre2/doc/html/pcre2_jit_match.html
index 8629e4a..56144ff 100644
--- a/pcre2/doc/html/pcre2_jit_match.html
+++ b/pcre2/doc/html/pcre2_jit_match.html
@@ -32,7 +32,17 @@ This function matches a compiled regular expression that has been successfully
 processed by the JIT compiler against a given subject string, using a matching
 algorithm that is similar to Perl's. It is a "fast path" interface to JIT, and
 it bypasses some of the sanity checks that pcre2_match() applies.
-Its arguments are exactly the same as for
+

+

+In UTF mode, the subject string is not checked for UTF validity. Unless
+PCRE2_MATCH_INVALID_UTF was set when the pattern was compiled, passing an
+invalid UTF string results in undefined behaviour. Your program may crash or
+loop or give wrong results. In the absence of PCRE2_MATCH_INVALID_UTF you
+should only call pcre2_jit_match() in UTF mode if you are sure the
+subject is valid.
+

+

+The arguments for pcre2_jit_match() are exactly the same as for
 pcre2_match(),
 except that the subject string must be specified with a length;
 PCRE2_ZERO_TERMINATED is not supported.
@@ -40,7 +50,7 @@ PCRE2_ZERO_TERMINATED is not supported.
 

 The supported options are PCRE2_NOTBOL, PCRE2_NOTEOL, PCRE2_NOTEMPTY,
 PCRE2_NOTEMPTY_ATSTART, PCRE2_PARTIAL_HARD, and PCRE2_PARTIAL_SOFT. Unsupported
-options are ignored. The subject string is not checked for UTF validity.
+options are ignored.
 

 

 The return values are the same as for pcre2_match() plus
diff --git a/pcre2/doc/html/pcre2_jit_stack_create.html b/pcre2/doc/html/pcre2_jit_stack_create.html
index 548947c..b9dc59d 100644
--- a/pcre2/doc/html/pcre2_jit_stack_create.html
+++ b/pcre2/doc/html/pcre2_jit_stack_create.html
@@ -19,8 +19,8 @@ SYNOPSIS
 #include <pcre2.h>
 

 

-pcre2_jit_stack *pcre2_jit_stack_create(PCRE2_SIZE startsize,
-  PCRE2_SIZE maxsize, pcre2_general_context *gcontext);
+pcre2_jit_stack *pcre2_jit_stack_create(size_t startsize,
+  size_t maxsize, pcre2_general_context *gcontext);
 

 

 DESCRIPTION
diff --git a/pcre2/doc/html/pcre2_match.html b/pcre2/doc/html/pcre2_match.html
index 90f7fcc..5584ae3 100644
--- a/pcre2/doc/html/pcre2_match.html
+++ b/pcre2/doc/html/pcre2_match.html
@@ -62,6 +62,8 @@ terminated by a binary zero code unit. The options are:
   PCRE2_ANCHORED          Match only at the first position
   PCRE2_COPY_MATCHED_SUBJECT
                           On success, make a private subject copy
+  PCRE2_DISABLE_RECURSELOOP_CHECK
+                          Only useful in rare cases; use with care
   PCRE2_ENDANCHORED       Pattern can match only at end of subject
   PCRE2_NOTBOL            Subject string is not the beginning of a line
   PCRE2_NOTEOL            Subject string is not the end of a line
diff --git a/pcre2/doc/html/pcre2_match_data_free.html b/pcre2/doc/html/pcre2_match_data_free.html
index 6ba6162..1c2520b 100644
--- a/pcre2/doc/html/pcre2_match_data_free.html
+++ b/pcre2/doc/html/pcre2_match_data_free.html
@@ -28,12 +28,14 @@ DESCRIPTION
 If match_data is NULL, this function does nothing. Otherwise,
 match_data must point to a match data block, which this function frees,
 using the memory freeing function from the general context or compiled pattern
-with which it was created, or free() if that was not set.
+with which it was created, or free() if that was not set. If the match
+data block was previously passed to pcre2_match(), it will have an
+attached heapframe vector; this is also freed.
 

 

 If the PCRE2_COPY_MATCHED_SUBJECT was used for a successful match using this
-match data block, the copy of the subject that was remembered with the block is
-also freed.
+match data block, the copy of the subject that was referenced within the block
+is also freed.
 

 

 There is a complete description of the PCRE2 native API in the
diff --git a/pcre2/doc/html/pcre2_set_compile_extra_options.html b/pcre2/doc/html/pcre2_set_compile_extra_options.html
index 2f2bf61..4924ed7 100644
--- a/pcre2/doc/html/pcre2_set_compile_extra_options.html
+++ b/pcre2/doc/html/pcre2_set_compile_extra_options.html
@@ -33,7 +33,13 @@ options are:
   PCRE2_EXTRA_ALLOW_LOOKAROUND_BSK     Allow \K in lookarounds
   PCRE2_EXTRA_ALLOW_SURROGATE_ESCAPES  Allow \x{d800} to \x{dfff} in UTF-8 and UTF-32 modes
   PCRE2_EXTRA_ALT_BSUX                 Extended alternate \u, \U, and \x handling
+  PCRE2_EXTRA_ASCII_BSD                \d remains ASCII in UCP mode
+  PCRE2_EXTRA_ASCII_BSS                \s remains ASCII in UCP mode
+  PCRE2_EXTRA_ASCII_BSW                \w remains ASCII in UCP mode
+  PCRE2_EXTRA_ASCII_DIGIT              [:digit:] and [:xdigit:] POSIX classes remain ASCII in UCP mode
+  PCRE2_EXTRA_ASCII_POSIX              POSIX classes remain ASCII in UCP mode
   PCRE2_EXTRA_BAD_ESCAPE_IS_LITERAL    Treat all invalid escapes as a literal following character
+  PCRE2_EXTRA_CASELESS_RESTRICT        Disable mixed ASCII/non-ASCII case folding
   PCRE2_EXTRA_ESCAPED_CR_IS_LF         Interpret \r as \n
   PCRE2_EXTRA_MATCH_LINE               Pattern matches whole lines
   PCRE2_EXTRA_MATCH_WORD               Pattern matches "words"
diff --git a/pcre2/doc/html/pcre2_set_max_pattern_compiled_length.html b/pcre2/doc/html/pcre2_set_max_pattern_compiled_length.html
new file mode 100644
index 0000000..ab570cf
--- /dev/null
+++ b/pcre2/doc/html/pcre2_set_max_pattern_compiled_length.html
@@ -0,0 +1,44 @@
+
+
+pcre2_set_max_pattern_compiled_length specification
+
+
+
pcre2_set_max_pattern_compiled_length man page

+

+Return to the PCRE2 index page.
+

+

+This page is part of the PCRE2 HTML documentation. It was generated
+automatically from the original man page. If there is any nonsense in it,
+please consult the man page, in case the conversion went wrong.
+

+

+SYNOPSIS
+

+

+#include <pcre2.h>
+

+

+int pcre2_set_max_pattern_compiled_length(
+  pcre2_compile_context *ccontext, PCRE2_SIZE value);
+

+

+DESCRIPTION
+

+

+This function sets, in a compile context, the maximum size (in bytes) for the
+memory needed to hold the compiled version of a pattern that is compiled with
+this context. The result is always zero. If a pattern that is passed to
+pcre2_compile() with this context needs more memory, an error is
+generated. The default is the largest number that a PCRE2_SIZE variable can
+hold, which is effectively unlimited.
+

+

+There is a complete description of the PCRE2 native API in the
+pcre2api
+page and a description of the POSIX API in the
+pcre2posix
+page.
+

+Return to the PCRE2 index page.
+

diff --git a/pcre2/doc/html/pcre2_set_max_varlookbehind.html b/pcre2/doc/html/pcre2_set_max_varlookbehind.html
new file mode 100644
index 0000000..1c03def
--- /dev/null
+++ b/pcre2/doc/html/pcre2_set_max_varlookbehind.html
@@ -0,0 +1,42 @@
+
+
+pcre2_set_max_varlookbehind specification
+
+
+
pcre2_set_max_varlookbehind man page

+

+Return to the PCRE2 index page.
+

+

+This page is part of the PCRE2 HTML documentation. It was generated
+automatically from the original man page. If there is any nonsense in it,
+please consult the man page, in case the conversion went wrong.
+

+

+SYNOPSIS
+

+

+#include <pcre2.h>
+

+

+int pcre2_set_max_varlookbehind(pcre2_compile_context *ccontext,
+  uint32_t value);
+

+

+DESCRIPTION
+

+

+This sets a maximum length for the number of characters matched by a
+variable-length lookbehind assertion. The default is set when PCRE2 is built,
+with the ultimate default being 255, the same as Perl. Lookbehind assertions
+without a bounding length are not supported. The result is always zero.
+

+

+There is a complete description of the PCRE2 native API in the
+pcre2api
+page and a description of the POSIX API in the
+pcre2posix
+page.
+

+Return to the PCRE2 index page.
+

diff --git a/pcre2/doc/html/pcre2_set_recursion_memory_management.html b/pcre2/doc/html/pcre2_set_recursion_memory_management.html
index 1e057b9..37af73c 100644
--- a/pcre2/doc/html/pcre2_set_recursion_memory_management.html
+++ b/pcre2/doc/html/pcre2_set_recursion_memory_management.html
@@ -21,7 +21,7 @@ SYNOPSIS
 

 int pcre2_set_recursion_memory_management(
   pcre2_match_context *mcontext,
-  void *(*private_malloc)(PCRE2_SIZE, void *),
+  void *(*private_malloc)(size_t, void *),
   void (*private_free)(void *, void *), void *memory_data);
 

 

diff --git a/pcre2/doc/html/pcre2_substring_list_free.html b/pcre2/doc/html/pcre2_substring_list_free.html
index 0919d1e..dea8bc5 100644
--- a/pcre2/doc/html/pcre2_substring_list_free.html
+++ b/pcre2/doc/html/pcre2_substring_list_free.html
@@ -19,7 +19,7 @@ SYNOPSIS
 #include <pcre2.h>
 

 

-void pcre2_substring_list_free(PCRE2_SPTR *list);
+void pcre2_substring_list_free(PCRE2_UCHAR **list);
 

 

 DESCRIPTION
diff --git a/pcre2/doc/html/pcre2api.html b/pcre2/doc/html/pcre2api.html
index d5ffd7c..6b60ee9 100644
--- a/pcre2/doc/html/pcre2api.html
+++ b/pcre2/doc/html/pcre2api.html
@@ -39,22 +39,23 @@ please consult the man page, in case the conversion went wrong.
 
  • INFORMATION ABOUT A PATTERN'S CALLOUTS
 
  • SERIALIZATION AND PRECOMPILING
 
  • THE MATCH DATA BLOCK
-
  • MATCHING A PATTERN: THE TRADITIONAL FUNCTION
-
  • NEWLINE HANDLING WHEN MATCHING
-
  • HOW PCRE2_MATCH() RETURNS A STRING AND CAPTURED SUBSTRINGS
-
  • OTHER INFORMATION ABOUT A MATCH
-
  • ERROR RETURNS FROM pcre2_match()
-
  • OBTAINING A TEXTUAL ERROR MESSAGE
-
  • EXTRACTING CAPTURED SUBSTRINGS BY NUMBER
-
  • EXTRACTING A LIST OF ALL CAPTURED SUBSTRINGS
-
  • EXTRACTING CAPTURED SUBSTRINGS BY NAME
-
  • CREATING A NEW STRING WITH SUBSTITUTIONS
-
  • DUPLICATE CAPTURE GROUP NAMES
-
  • FINDING ALL POSSIBLE MATCHES AT ONE POSITION
-
  • MATCHING A PATTERN: THE ALTERNATIVE FUNCTION
-
  • SEE ALSO
-
  • AUTHOR
-
  • REVISION
+
  • MEMORY USE FOR MATCH DATA BLOCKS
+
  • MATCHING A PATTERN: THE TRADITIONAL FUNCTION
+
  • NEWLINE HANDLING WHEN MATCHING
+
  • HOW PCRE2_MATCH() RETURNS A STRING AND CAPTURED SUBSTRINGS
+
  • OTHER INFORMATION ABOUT A MATCH
+
  • ERROR RETURNS FROM pcre2_match()
+
  • OBTAINING A TEXTUAL ERROR MESSAGE
+
  • EXTRACTING CAPTURED SUBSTRINGS BY NUMBER
+
  • EXTRACTING A LIST OF ALL CAPTURED SUBSTRINGS
+
  • EXTRACTING CAPTURED SUBSTRINGS BY NAME
+
  • CREATING A NEW STRING WITH SUBSTITUTIONS
+
  • DUPLICATE CAPTURE GROUP NAMES
+
  • FINDING ALL POSSIBLE MATCHES AT ONE POSITION
+
  • MATCHING A PATTERN: THE ALTERNATIVE FUNCTION
+
  • SEE ALSO
+
  • AUTHOR
+
  • REVISION
 
 
    
 #include <pcre2.h>
@@ -103,6 +104,13 @@ document for an overview of all the PCRE2 documentation.
 PCRE2_SPTR pcre2_get_mark(pcre2_match_data *match_data);
 
    
 
    
+PCRE2_SIZE pcre2_get_match_data_size(pcre2_match_data *match_data);
+
    
+
    
+PCRE2_SIZE pcre2_get_match_data_heapframes_size(
+  pcre2_match_data *match_data);
+
    
+
    
 uint32_t pcre2_get_ovector_count(pcre2_match_data *match_data);
 
    
 
    
@@ -153,6 +161,14 @@ document for an overview of all the PCRE2 documentation.
   PCRE2_SIZE value);
 
    
 
    
+int pcre2_set_max_pattern_compiled_length(
+  pcre2_compile_context *ccontext, PCRE2_SIZE value);
+
    
+
    
+int pcre2_set_max_varlookbehind(pcre2_compile_contest *ccontext,
+"  uint32_t value);
+
    
+
    
 int pcre2_set_newline(pcre2_compile_context *ccontext,
   uint32_t value);
 
    
@@ -241,7 +257,7 @@ document for an overview of all the PCRE2 documentation.
   PCRE2_SPTR name);
 
    
 
    
-void pcre2_substring_list_free(PCRE2_SPTR *list);
+void pcre2_substring_list_free(PCRE2_UCHAR **list);
 
    
 
    
 int pcre2_substring_list_get(pcre2_match_data *match_data,
@@ -270,8 +286,8 @@ document for an overview of all the PCRE2 documentation.
 void pcre2_jit_free_unused_memory(pcre2_general_context *gcontext);
 
    
 
    
-pcre2_jit_stack *pcre2_jit_stack_create(PCRE2_SIZE startsize,
-  PCRE2_SIZE maxsize, pcre2_general_context *gcontext);
+pcre2_jit_stack *pcre2_jit_stack_create(size_t startsize,
+  size_t maxsize, pcre2_general_context *gcontext);
 
    
 
    
 void pcre2_jit_stack_assign(pcre2_match_context *mcontext,
@@ -335,7 +351,7 @@ document for an overview of all the PCRE2 documentation.
 
    
 int pcre2_set_recursion_memory_management(
   pcre2_match_context *mcontext,
-  void *(*private_malloc)(PCRE2_SIZE, void *),
+  void *(*private_malloc)(size_t, void *),
   void (*private_free)(void *, void *), void *memory_data);
 
    
 
    
@@ -388,11 +404,8 @@ This contains the function prototypes and other definitions for all three
 libraries. One, two, or all three can be installed simultaneously. On Unix-like
 systems the libraries are called libpcre2-8, libpcre2-16, and
 libpcre2-32, and they can also co-exist with the original PCRE libraries.
-
    
-
    
-Character strings are passed to and from a PCRE2 library as a sequence of
-unsigned integers in code units of the appropriate width. Every PCRE2 function
-comes in three different forms, one for each library, for example:
+Every PCRE2 function comes in three different forms, one for each library, for
+example:
 
       pcre2_compile_8()
   pcre2_compile_16()
@@ -403,10 +416,16 @@ There are also three different sets of data types:
   PCRE2_UCHAR8, PCRE2_UCHAR16, PCRE2_UCHAR32
   PCRE2_SPTR8,  PCRE2_SPTR16,  PCRE2_SPTR32
 
    
-The UCHAR types define unsigned code units of the appropriate widths. For
-example, PCRE2_UCHAR16 is usually defined as `uint16_t'. The SPTR types are
-constant pointers to the equivalent UCHAR types, that is, they are pointers to
-vectors of unsigned code units.
+The UCHAR types define unsigned code units of the appropriate widths.
+For example, PCRE2_UCHAR16 is usually defined as `uint16_t'.
+The SPTR types are pointers to constants of the equivalent UCHAR types,
+that is, they are pointers to vectors of unsigned code units.
+
    
+
    
+Character strings are passed to a PCRE2 library as sequences of unsigned
+integers in code units of the appropriate width. The length of a string may
+be given as a number of code units, or the string may be specified as
+zero-terminated.
 
    
 
    
 Many applications use only one code unit width. For their convenience, macros
@@ -446,7 +465,7 @@ names, without the _8, _16, or _32 suffix.
 PCRE2 has its own native API, which is described in this document. There are
 also some wrapper functions for the 8-bit library that correspond to the
 POSIX regular expression API, but they do not give access to all the
-functionality of PCRE2. They are described in the
+functionality of PCRE2 and they are not thread-safe. They are described in the
 pcre2posix
 documentation. Both these APIs define a set of C function calls.
 
    
@@ -559,7 +578,8 @@ unsigned integer type, currently always defined as size_t. The largest
 value that can be stored in such a type (that is ~(PCRE2_SIZE)0) is reserved
 as a special indicator for zero-terminated strings and unset offsets.
 Therefore, the longest string that can be handled is one less than this
-maximum.
+maximum. Note that string lengths are always given in code units. Only in the
+8-bit library is such a length the same as the number of bytes in the string.
 
    
 
    NEWLINES
    
 
    
@@ -858,6 +878,28 @@ external sources can limit their size. The default is the largest number that a
 PCRE2_SIZE variable can hold, which is effectively unlimited.
 
    
 
    
+int pcre2_set_max_pattern_compiled_length(
+  pcre2_compile_context *ccontext, PCRE2_SIZE value);
+
    
+
    
+This sets a maximum size, in bytes, for the memory needed to hold the compiled
+version of a pattern that is compiled with this context. If the pattern needs
+more memory, an error is generated. This facility is provided so that
+applications that accept patterns from external sources can limit the amount of
+memory they use. The default is the largest number that a PCRE2_SIZE variable
+can hold, which is effectively unlimited.
+
    
+
    
+int pcre2_set_max_varlookbehind(pcre2_compile_contest *ccontext,
+"  uint32_t value);
+
    
+
    
+This sets a maximum length for the number of characters matched by a
+variable-length lookbehind assertion. The default is set when PCRE2 is built,
+with the ultimate default being 255, the same as Perl. Lookbehind assertions
+without a bounding length are not supported.
+
    
+
    
 int pcre2_set_newline(pcre2_compile_context *ccontext,
   uint32_t value);
 
    
@@ -1070,10 +1112,9 @@ is also used in this case (but in a different way) to limit how long the
 matching can continue.
 
    
 
    
-The default value for the limit can be set when PCRE2 is built; the default
-default is 10 million, which handles all but the most extreme cases. A value
-for the match limit may also be supplied by an item at the start of a pattern
-of the form
+The default value for the limit can be set when PCRE2 is built; the default is
+10 million, which handles all but the most extreme cases. A value for the match
+limit may also be supplied by an item at the start of a pattern of the form
 
       (*LIMIT_MATCH=ddd)
 
    
@@ -1185,7 +1226,11 @@ for the amount of heap memory used by pcre2_match() or
   PCRE2_CONFIG_JIT
    • The output is a uint32_t integer that is set to one if support for just-in-time -compiling is available; otherwise it is set to zero. +compiling is included in the library; otherwise it is set to zero. Note that +having the support in the library does not guarantee that JIT will be used for +any given match. See the +pcre2jit +documentation for more details. 
       PCRE2_CONFIG_JITTARGET
    @@ -1302,10 +1347,12 @@ zero.

    The pcre2_compile() function compiles a pattern into an internal form. -The pattern is defined by a pointer to a string of code units and a length (in -code units). If the pattern is zero-terminated, the length can be specified as -PCRE2_ZERO_TERMINATED. The function returns a pointer to a block of memory that -contains the compiled pattern and related data, or NULL if an error occurred. +The pattern is defined by a pointer to a string of code units and a length in +code units. If the pattern is zero-terminated, the length can be specified as +PCRE2_ZERO_TERMINATED. A NULL pattern pointer with a length of zero is treated +as an empty string (NULL with a non-zero length causes an error return). The +function returns a pointer to a block of memory that contains the compiled +pattern and related data, or NULL if an error occurred.

    If the compile context argument ccontext is NULL, memory for the compiled @@ -1524,11 +1571,14 @@ PCRE2_UCP is set, Unicode properties are used for all characters with more than one other case, and for all characters whose code points are greater than U+007F. Note that there are two ASCII characters, K and S, that, in addition to their lower case ASCII equivalents, are case-equivalent with U+212A (Kelvin -sign) and U+017F (long S) respectively. For lower valued characters with only -one other case, a lookup table is used for speed. When neither PCRE2_UTF nor -PCRE2_UCP is set, a lookup table is used for all code points less than 256, and -higher code points (available only in 16-bit or 32-bit mode) are treated as not -having another case. +sign) and U+017F (long S) respectively. If you do not want this case +equivalence, you can suppress it by setting PCRE2_EXTRA_CASELESS_RESTRICT. +

    +

    +For lower valued characters with only one other case, a lookup table is used +for speed. When neither PCRE2_UTF nor PCRE2_UCP is set, a lookup table is used +for all code points less than 256, and higher code points (available only in +16-bit or 32-bit mode) are treated as not having another case. 

       PCRE2_DOLLAR_ENDONLY
    @@ -1586,13 +1636,13 @@ the end of the subject. PCRE2_EXTENDED If this bit is set, most white space characters in the pattern are totally -ignored except when escaped or inside a character class. However, white space -is not allowed within sequences such as (?> that introduce various -parenthesized groups, nor within numerical quantifiers such as {1,3}. Ignorable -white space is permitted between an item and a following quantifier and between -a quantifier and a following + that indicates possessiveness. PCRE2_EXTENDED is -equivalent to Perl's /x option, and it can be changed within a pattern by a -(?x) option setting. +ignored except when escaped, inside a character class, or inside a \Q...\E +sequence. However, white space is not allowed within sequences such as (?> that +introduce various parenthesized groups, nor within numerical quantifiers such +as {1,3}. Ignorable white space is permitted between an item and a following +quantifier and between a quantifier and a following + that indicates +possessiveness. PCRE2_EXTENDED is equivalent to Perl's /x option, and it can be +changed within a pattern by a (?x) option setting.

    When PCRE2 is compiled without Unicode support, PCRE2_EXTENDED recognizes as @@ -1651,7 +1701,7 @@ PCRE2_FIRSTLINE if startoffset is greater than 3. See also PCRE2_USE_OFFSET_LIMIT, which provides a more general limiting facility. If PCRE2_FIRSTLINE is set with an offset limit, a match must occur in the first line and also within the offset limit. In other words, whichever limit comes -first is used. +first is used. This option has no effect for anchored patterns. 

       PCRE2_LITERAL
    @@ -1670,7 +1720,11 @@ PCRE2_EXTRA_MATCH_WORD are also supported. Any other options cause an error. This option forces PCRE2_UTF (see below) and also enables support for matching by pcre2_match() in subject strings that contain invalid UTF sequences. -This facility is not supported for DFA matching. For details, see the +Note, however, that the 16-bit and 32-bit PCRE2 libraries process strings as +sequences of uint16_t or uint32_t code points. They cannot find valid UTF +sequences within an arbitrary string of bytes unless such sequences are +suitably aligned. This facility is not supported for DFA matching. For details, +see the pcre2unicode documentation. 
    @@ -1864,20 +1918,22 @@ are not representable in UTF-16.
 This option has two effects. Firstly, it change the way PCRE2 processes \B,
 \b, \D, \d, \S, \s, \W, \w, and some of the POSIX character classes. By
 default, only ASCII characters are recognized, but if PCRE2_UCP is set, Unicode
-properties are used instead to classify characters. More details are given in
-the section on
+properties are used to classify characters. There are some PCRE2_EXTRA
+options (see below) that add finer control to this behaviour. More details are
+given in the section on
 generic character types
 in the
 pcre2pattern
-page. If you set PCRE2_UCP, matching one of the items it affects takes much
-longer.
+page.
 
    
 
    
 The second effect of PCRE2_UCP is to force the use of Unicode properties for
-upper/lower casing operations on characters with code points greater than 127,
-even when PCRE2_UTF is not set. This makes it possible, for example, to process
-strings in the 16-bit UCS-2 code. This option is available only if PCRE2 has
-been compiled with Unicode support (which is the default).
+upper/lower casing operations, even when PCRE2_UTF is not set. This makes it
+possible to process strings in the 16-bit UCS-2 code. This option is available
+only if PCRE2 has been compiled with Unicode support (which is the default).
+The PCRE2_EXTRA_CASELESS_RESTRICT option (see below) restricts caseless
+matching such that ASCII characters match only ASCII characters and non-ASCII
+characters match only non-ASCII characters.
 
       PCRE2_UNGREEDY
 
    
@@ -1905,8 +1961,7 @@ Unicode support (which is the default). If Unicode support is not available,
 the use of this option provokes an error. Details of how PCRE2_UTF changes the
 behaviour of PCRE2 are given in the
 pcre2unicode
-page. In particular, note that it changes the way PCRE2_CASELESS handles
-characters with code points greater than 127.
+page. In particular, note that it changes the way PCRE2_CASELESS works.
 
    
 
    
 Extra compile options
@@ -1953,6 +2008,37 @@ the way that ECMAscript (aka JavaScript) does. Additional functionality was
 defined by ECMAscript 6; setting PCRE2_EXTRA_ALT_BSUX has the effect of
 PCRE2_ALT_BSUX, but in addition it recognizes \u{hhh..} as a hexadecimal
 character code, where hhh.. is any number of hexadecimal digits.
+
    +  PCRE2_EXTRA_ASCII_BSD
+
    
+This option forces \d to match only ASCII digits, even when PCRE2_UCP is set.
+It can be changed within a pattern by means of the (?aD) option setting.
+
    +  PCRE2_EXTRA_ASCII_BSS
+
    
+This option forces \s to match only ASCII space characters, even when
+PCRE2_UCP is set. It can be changed within a pattern by means of the (?aS)
+option setting.
+
    +  PCRE2_EXTRA_ASCII_BSW
+
    
+This option forces \w to match only ASCII word characters, even when PCRE2_UCP
+is set. It can be changed within a pattern by means of the (?aW) option
+setting.
+
    +  PCRE2_EXTRA_ASCII_DIGIT
+
    
+This option forces the POSIX character classes [:digit:] and [:xdigit:] to
+match only ASCII digits, even when PCRE2_UCP is set. It can be changed within
+a pattern by means of the (?aT) option setting.
+
    +  PCRE2_EXTRA_ASCII_POSIX
+
    
+This option forces all the POSIX character classes, including [:digit:] and
+[:xdigit:], to match only ASCII characters, even when PCRE2_UCP is set. It can
+be changed within a pattern by means of the (?aP) option setting, but note that
+this also sets PCRE2_EXTRA_ASCII_DIGIT in order to ensure that (?-aP) unsets
+all ASCII restrictions for POSIX classes.
 
       PCRE2_EXTRA_BAD_ESCAPE_IS_LITERAL
 
    
@@ -1974,6 +2060,17 @@ that a sequence such as [\N{] is interpreted as a malformed attempt at
 [\N{...}] and so is treated as [N{] whereas [\N] gives an error because an
 unqualified \N is a valid escape sequence but is not supported in a character
 class. To reiterate: this is a dangerous option. Use with great care.
+
    +  PCRE2_EXTRA_CASELESS_RESTRICT
+
    
+When either PCRE2_UCP or PCRE2_UTF is set, caseless matching follows Unicode
+rules, which allow for more than two cases per character. There are two
+case-equivalent character sets that contain both ASCII and non-ASCII
+characters. The ASCII letter S is case-equivalent to U+017f (long S) and the
+ASCII letter K is case-equivalent to U+212a (Kelvin sign). This option disables
+recognition of case-equivalences that cross the ASCII/non-ASCII boundary. In a
+caseless match, both characters must either be ASCII or non-ASCII. The option
+can be changed with a pattern by the (?r) option setting.
 
       PCRE2_EXTRA_ESCAPED_CR_IS_LF
 
    
@@ -2015,8 +2112,8 @@ also set.
 void pcre2_jit_free_unused_memory(pcre2_general_context *gcontext);
 
    
 
    
-pcre2_jit_stack *pcre2_jit_stack_create(PCRE2_SIZE startsize,
-  PCRE2_SIZE maxsize, pcre2_general_context *gcontext);
+pcre2_jit_stack *pcre2_jit_stack_create(size_t startsize,
+  size_t maxsize, pcre2_general_context *gcontext);
 
    
 
    
 void pcre2_jit_stack_assign(pcre2_match_context *mcontext,
@@ -2061,7 +2158,8 @@ PCRE2_UCP option can be set when a pattern is compiled; this causes \w and
 friends to use Unicode property support instead of the built-in tables.
 PCRE2_UCP also causes upper/lower casing operations on characters with code
 points greater than 127 to use Unicode properties. These effects apply even
-when PCRE2_UTF is not set.
+when PCRE2_UTF is not set. There are, however, some PCRE2_EXTRA options (see
+above) that can be used to modify or suppress them.
 
    
 
    
 The use of locales with Unicode is discouraged. If you are handling characters
@@ -2543,7 +2641,7 @@ large enough to hold as many as are expected.
 A minimum of at least 1 pair is imposed by pcre2_match_data_create(), so
 it is always possible to return the overall matched string in the case of
 pcre2_match() or the longest match in the case of
-pcre2_dfa_match(). The maximum number of pairs is 65535; if the the first
+pcre2_dfa_match(). The maximum number of pairs is 65535; if the first
 argument of pcre2_match_data_create() is greater than this, 65535 is
 used.
 
    
@@ -2593,7 +2691,44 @@ When a match data block itself is no longer needed, it should be freed by
 calling pcre2_match_data_free(). If this function is called with a NULL
 argument, it returns immediately, without doing anything.
 
    
-
    MATCHING A PATTERN: THE TRADITIONAL FUNCTION
    
+
    MEMORY USE FOR MATCH DATA BLOCKS
    
+
    
+PCRE2_SIZE pcre2_get_match_data_size(pcre2_match_data *match_data);
+
    
+
    
+PCRE2_SIZE pcre2_get_match_data_heapframes_size(
+  pcre2_match_data *match_data);
+
    
+
    
+The size of a match data block depends on the size of the ovector that it
+contains. The function pcre2_get_match_data_size() returns the size, in
+bytes, of the block that is its argument.
+
    
+
    
+When pcre2_match() runs interpretively (that is, without using JIT), it
+makes use of a vector of data frames for remembering backtracking positions.
+The size of each individual frame depends on the number of capturing
+parentheses in the pattern and can be obtained by calling
+pcre2_pattern_info() with the PCRE2_INFO_FRAMESIZE option (see the
+section entitled "Information about a compiled pattern"
+above).
+
    
+
    
+Heap memory is used for the frames vector; if the initial memory block turns
+out to be too small during matching, it is automatically expanded. When
+pcre2_match() returns, the memory is not freed, but remains attached to
+the match data block, for use by any subsequent matches that use the same
+block. It is automatically freed when the match data block itself is freed.
+
    
+
    
+You can find the current size of the frames vector that a match data block owns
+by calling pcre2_get_match_data_heapframes_size(). For a newly created
+match data block the size will be zero. Some types of match may require a lot
+of frames and thus a large vector; applications that run in environments where
+memory is constrained can check this and free the match data block if the heap
+frames vector has become too big.
+
    
+
    MATCHING A PATTERN: THE TRADITIONAL FUNCTION
    
 
    
 int pcre2_match(const pcre2_code *code, PCRE2_SPTR subject,
   PCRE2_SIZE length, PCRE2_SIZE startoffset,
@@ -2701,14 +2836,16 @@ Option bits for pcre2_match()
 
    
 The unused bits of the options argument for pcre2_match() must be
 zero. The only bits that may be set are PCRE2_ANCHORED,
-PCRE2_COPY_MATCHED_SUBJECT, PCRE2_ENDANCHORED, PCRE2_NOTBOL, PCRE2_NOTEOL,
-PCRE2_NOTEMPTY, PCRE2_NOTEMPTY_ATSTART, PCRE2_NO_JIT, PCRE2_NO_UTF_CHECK,
-PCRE2_PARTIAL_HARD, and PCRE2_PARTIAL_SOFT. Their action is described below.
+PCRE2_COPY_MATCHED_SUBJECT, PCRE2_DISABLE_RECURSELOOP_CHECK, PCRE2_ENDANCHORED,
+PCRE2_NOTBOL, PCRE2_NOTEOL, PCRE2_NOTEMPTY, PCRE2_NOTEMPTY_ATSTART,
+PCRE2_NO_JIT, PCRE2_NO_UTF_CHECK, PCRE2_PARTIAL_HARD, and PCRE2_PARTIAL_SOFT.
+Their action is described below.
 
    
 
    
 Setting PCRE2_ANCHORED or PCRE2_ENDANCHORED at match time is not supported by
 the just-in-time (JIT) compiler. If it is set, JIT matching is disabled and the
-interpretive code in pcre2_match() is run. Apart from PCRE2_NO_JIT
+interpretive code in pcre2_match() is run.
+PCRE2_DISABLE_RECURSELOOP_CHECK is ignored by JIT, but apart from PCRE2_NO_JIT
 (obviously), the remaining options are supported for JIT matching.
 
       PCRE2_ANCHORED
@@ -2734,6 +2871,25 @@ the match block itself is used. The copy is automatically freed when
 pcre2_match_data_free() is called to free the match data block. It is also
 automatically freed if the match data block is re-used for another match
 operation.
+
    +  PCRE2_DISABLE_RECURSELOOP_CHECK
+
    
+This option is relevant only to pcre2_match() for interpretive matching.
+It is ignored when JIT is used, and is forbidden for pcre2_dfa_match().
+
    
+
    
+The use of recursion in patterns can lead to infinite loops. In the
+interpretive matcher these would be eventually caught by the match or heap
+limits, but this could take a long time and/or use a lot of memory if the
+limits are large. There is therefore a check at the start of each recursion.
+If the same group is still active from a previous call, and the current subject
+pointer is the same as it was at the start of that group, and the furthest
+inspected character of the subject has not changed, an error is generated.
+
    
+
    
+There are rare cases of matches that would complete, but nevertheless trigger
+this error. This option disables the check. It is provided mainly for testing
+when comparing JIT and interpretive behaviour.
 
       PCRE2_ENDANCHORED
 
    
@@ -2862,7 +3018,7 @@ examples, in the
 pcre2partial
 documentation.
 
    
-
    NEWLINE HANDLING WHEN MATCHING
    
+
    NEWLINE HANDLING WHEN MATCHING
    
 
    
 When PCRE2 is built, a default newline convention is set; this is usually the
 standard convention for the operating system. The default can be overridden in
@@ -2902,7 +3058,7 @@ does \s, even though it includes CR and LF in the characters that it matches.
 Notwithstanding the above, anomalous effects may still occur when CRLF is a
 valid newline sequence and explicit \r or \n escapes appear in the pattern.
 
    
-
    HOW PCRE2_MATCH() RETURNS A STRING AND CAPTURED SUBSTRINGS
    
+
    HOW PCRE2_MATCH() RETURNS A STRING AND CAPTURED SUBSTRINGS
    
 
    
 uint32_t pcre2_get_ovector_count(pcre2_match_data *match_data);
 
    
@@ -2989,8 +3145,8 @@ Offset values that correspond to unused groups at the end of the expression are
 also set to PCRE2_UNSET. For example, if the string "abc" is matched against
 the pattern (abc)(x(yz)?)? groups 2 and 3 are not matched. The return from the
 function is 2, because the highest used capture group number is 1. The offsets
-for for the second and third capture groupss (assuming the vector is large
-enough, of course) are set to PCRE2_UNSET.
+for the second and third capture groups (assuming the vector is large enough,
+of course) are set to PCRE2_UNSET.
 
    
 
    
 Elements in the ovector that do not correspond to capturing parentheses in the
@@ -2999,7 +3155,7 @@ parentheses, no more than ovector[0] to ovector[2n+1] are set by
 pcre2_match(). The other elements retain whatever values they previously
 had. After a failed match attempt, the contents of the ovector are unchanged.
 
    
-
    OTHER INFORMATION ABOUT A MATCH
    
+
    OTHER INFORMATION ABOUT A MATCH
    
 
    
 PCRE2_SPTR pcre2_get_mark(pcre2_match_data *match_data);
 
    
@@ -3062,7 +3218,7 @@ the code unit offset of the invalid UTF character. Details are given in the
 pcre2unicode
 page.
 
    
-
    ERROR RETURNS FROM pcre2_match()
    
+
    ERROR RETURNS FROM pcre2_match()
    
 
    
 If pcre2_match() fails, it returns a negative number. This can be
 converted to a text string by calling the pcre2_get_error_message()
@@ -3148,7 +3304,7 @@ The backtracking match limit was reached.
 
       PCRE2_ERROR_NOMEMORY
 
    
-Heap memory is used to remember backgracking points. This error is given when
+Heap memory is used to remember backtracking points. This error is given when
 the memory allocation function (default or custom) fails. Note that a different
 error, PCRE2_ERROR_HEAPLIMIT, is given if the amount of memory needed exceeds
 the heap limit. PCRE2_ERROR_NOMEMORY is also returned if
@@ -3169,7 +3325,7 @@ detected and faulted at compile time, but more complicated cases, in particular
 mutual recursions between two different groups, cannot be detected until
 matching is attempted.
 
    
-
    OBTAINING A TEXTUAL ERROR MESSAGE
    
+
    OBTAINING A TEXTUAL ERROR MESSAGE
    
 
    
 int pcre2_get_error_message(int errorcode, PCRE2_UCHAR *buffer,
   PCRE2_SIZE bufflen);
@@ -3190,7 +3346,7 @@ returned. If the buffer is too small, the message is truncated (but still with
 a trailing zero), and the negative error code PCRE2_ERROR_NOMEMORY is returned.
 None of the messages are very long; a buffer size of 120 code units is ample.
 
    
-
    EXTRACTING CAPTURED SUBSTRINGS BY NUMBER
    
+
    EXTRACTING CAPTURED SUBSTRINGS BY NUMBER
    
 
    
 int pcre2_substring_length_bynumber(pcre2_match_data *match_data,
   uint32_t number, PCRE2_SIZE *length);
@@ -3287,13 +3443,13 @@ The substring did not participate in the match. For example, if the pattern is
 (abc)|(def) and the subject is "def", and the ovector contains at least two
 capturing slots, substring number 1 is unset.
 
    
-
    EXTRACTING A LIST OF ALL CAPTURED SUBSTRINGS
    
+
    EXTRACTING A LIST OF ALL CAPTURED SUBSTRINGS
    
 
    
 int pcre2_substring_list_get(pcre2_match_data *match_data,
 "  PCRE2_UCHAR ***listptr, PCRE2_SIZE **lengthsptr);
 
    
 
    
-void pcre2_substring_list_free(PCRE2_SPTR *list);
+void pcre2_substring_list_free(PCRE2_UCHAR **list);
 
    
 
    
 The pcre2_substring_list_get() function extracts all available substrings
@@ -3326,7 +3482,7 @@ distinguished from a genuine zero-length substring by inspecting the
 appropriate offset in the ovector, which contain PCRE2_UNSET for unset
 substrings, or by calling pcre2_substring_length_bynumber().
 
    
-
    EXTRACTING CAPTURED SUBSTRINGS BY NAME
    
+
    EXTRACTING CAPTURED SUBSTRINGS BY NAME
    
 
    
 int pcre2_substring_number_from_name(const pcre2_code *code,
   PCRE2_SPTR name);
@@ -3386,7 +3542,7 @@ names are not included in the compiled code. The matching process uses only
 numbers. For this reason, the use of different names for groups with the
 same number causes an error at compile time.
 
    
-
    CREATING A NEW STRING WITH SUBSTITUTIONS
    
+
    CREATING A NEW STRING WITH SUBSTITUTIONS
    
 
    
 int pcre2_substitute(const pcre2_code *code, PCRE2_SPTR subject,
   PCRE2_SIZE length, PCRE2_SIZE startoffset,
@@ -3510,7 +3666,8 @@ replacement string causes an immediate return with the relevant UTF error code.
 If PCRE2_SUBSTITUTE_LITERAL is set, the replacement string is not interpreted
 in any way. By default, however, a dollar character is an escape character that
 can specify the insertion of characters from capture groups and names from
-(*MARK) or other control verbs in the pattern. The following forms are always
+(*MARK) or other control verbs in the pattern. Dollar is the only escape
+character (backslash is treated as literal). The following forms are always
 recognized:
 
       $$                  insert a dollar character
@@ -3742,11 +3899,11 @@ PCRE2_SUBSTITUTE_GLOBAL is set, processing continues with a search for the next
 match. If the value is not zero, the current replacement is not accepted. If
 the value is greater than zero, processing continues when
 PCRE2_SUBSTITUTE_GLOBAL is set. Otherwise (the value is less than zero or
-PCRE2_SUBSTITUTE_GLOBAL is not set), the the rest of the input is copied to the
+PCRE2_SUBSTITUTE_GLOBAL is not set), the rest of the input is copied to the
 output and the call to pcre2_substitute() exits, returning the number of
 matches so far.
 
    
-
    DUPLICATE CAPTURE GROUP NAMES
    
+
    DUPLICATE CAPTURE GROUP NAMES
    
 
    
 int pcre2_substring_nametable_scan(const pcre2_code *code,
   PCRE2_SPTR name, PCRE2_SPTR *first, PCRE2_SPTR *last);
@@ -3792,7 +3949,7 @@ in the section entitled Information about a pattern. Given all the
 relevant entries for the name, you can extract each of their numbers, and hence
 the captured data.
 
    
-
    FINDING ALL POSSIBLE MATCHES AT ONE POSITION
    
+
    FINDING ALL POSSIBLE MATCHES AT ONE POSITION
    
 
    
 The traditional matching function uses a similar algorithm to Perl, which stops
 when it finds the first match at a given point in the subject. If you want to
@@ -3810,7 +3967,7 @@ substring. Then return 1, which forces pcre2_match() to backtrack and try
 other alternatives. Ultimately, when it runs out of matches,
 pcre2_match() will yield PCRE2_ERROR_NOMATCH.
 
    
-
    MATCHING A PATTERN: THE ALTERNATIVE FUNCTION
    
+
    MATCHING A PATTERN: THE ALTERNATIVE FUNCTION
    
 
    
 int pcre2_dfa_match(const pcre2_code *code, PCRE2_SPTR subject,
   PCRE2_SIZE length, PCRE2_SIZE startoffset,
@@ -4003,13 +4160,13 @@ some plausibility checks are made on the contents of the workspace, which
 should contain data about the previous partial match. If any of these checks
 fail, this error is given.
 
    
-
    SEE ALSO
    
+
    SEE ALSO
    
 
    
 pcre2build(3), pcre2callout(3), pcre2demo(3),
 pcre2matching(3), pcre2partial(3), pcre2posix(3),
 pcre2sample(3), pcre2unicode(3).
 
    
-
    AUTHOR
    
+
    AUTHOR
    
 
    
 Philip Hazel
 
    
@@ -4018,11 +4175,11 @@ Retired from University Computing Service
 Cambridge, England.
 
    
 
    
-
    REVISION
    
+
    REVISION
    
 
    
-Last updated: 27 July 2022
+Last updated: 24 April 2024
 
    
-Copyright © 1997-2022 University of Cambridge.
+Copyright © 1997-2024 University of Cambridge.
 
    
 
    
 Return to the PCRE2 index page.
diff --git a/pcre2/doc/html/pcre2build.html b/pcre2/doc/html/pcre2build.html
index 07472d1..d4b0d33 100644
--- a/pcre2/doc/html/pcre2build.html
+++ b/pcre2/doc/html/pcre2build.html
@@ -24,21 +24,22 @@ please consult the man page, in case the conversion went wrong.
 
  • WHAT \R MATCHES
 
  • HANDLING VERY LARGE PATTERNS
 
  • LIMITING PCRE2 RESOURCE USAGE
-
  • CREATING CHARACTER TABLES AT BUILD TIME
-
  • USING EBCDIC CODE
-
  • PCRE2GREP SUPPORT FOR EXTERNAL SCRIPTS
-
  • PCRE2GREP OPTIONS FOR COMPRESSED FILE SUPPORT
-
  • PCRE2GREP BUFFER SIZE
-
  • PCRE2TEST OPTION FOR LIBREADLINE SUPPORT
-
  • INCLUDING DEBUGGING CODE
-
  • DEBUGGING WITH VALGRIND SUPPORT
-
  • CODE COVERAGE REPORTING
-
  • DISABLING THE Z AND T FORMATTING MODIFIERS
-
  • SUPPORT FOR FUZZERS
-
  • OBSOLETE OPTION
-
  • SEE ALSO
-
  • AUTHOR
-
  • REVISION
+
  • LIMITING VARIABLE-LENGTH LOOKBEHIND ASSERTIONS
+
  • CREATING CHARACTER TABLES AT BUILD TIME
+
  • USING EBCDIC CODE
+
  • PCRE2GREP SUPPORT FOR EXTERNAL SCRIPTS
+
  • PCRE2GREP OPTIONS FOR COMPRESSED FILE SUPPORT
+
  • PCRE2GREP BUFFER SIZE
+
  • PCRE2TEST OPTION FOR LIBREADLINE SUPPORT
+
  • INCLUDING DEBUGGING CODE
+
  • DEBUGGING WITH VALGRIND SUPPORT
+
  • CODE COVERAGE REPORTING
+
  • DISABLING THE Z AND T FORMATTING MODIFIERS
+
  • SUPPORT FOR FUZZERS
+
  • OBSOLETE OPTION
+
  • SEE ALSO
+
  • AUTHOR
+
  • REVISION
 
 
    BUILDING PCRE2
    
 
    
@@ -49,7 +50,8 @@ Autotools. Also in the distribution are files to support building using
 README
 contains general information about building with Autotools (some of which is
 repeated below), and also has some comments about building on various operating
-systems. There is a lot more information about building PCRE2 without using
+systems. The files in the vms directory support building under OpenVMS.
+There is a lot more information about building PCRE2 without using
 Autotools (including information about using CMake and building "by
 hand") in the text file called
 NON-AUTOTOOLS-BUILD.
@@ -118,7 +120,19 @@ one of
   --disable-shared
   --disable-static
 
    • 
-to the configure command.
+to the configure command. Setting --disable-shared ensures that PCRE2
+libraries are built as static libraries. The binaries that are then created as
+part of the build process (for example, pcre2test and pcre2grep)
+are linked statically with one or more PCRE2 libraries, but may also be
+dynamically linked with other libraries such as libc. If you want these
+binaries to be fully statically linked, you can set LDFLAGS like this:
+
    
+
    
+LDFLAGS=--static ./configure --disable-shared
+
    
+
    
+Note the two hyphens in --static. Of course, this works only if static versions
+of all the relevant libraries are available for linking.
 
    
 
    UNICODE AND UTF SUPPORT
    
 
    
@@ -321,8 +335,22 @@ As well as applying to pcre2_match(), the depth limit also controls
 the depth of recursive function calls in pcre2_dfa_match(). These are
 used for lookaround assertions, atomic groups, and recursion within patterns.
 The limit does not apply to JIT matching.
+
    
+
    LIMITING VARIABLE-LENGTH LOOKBEHIND ASSERTIONS
    
+
    
+Lookbehind assertions in which one or more branches can match a variable number
+of characters are supported only if there is a maximum matching length for each
+top-level branch. There is a limit to this maximum that defaults to 255
+characters. You can alter this default by a setting such as
+
    +  --with-max-varlookbehind=100
+
    
+The limit can be changed at runtime by calling
+pcre2_set_max_varlookbehind(). Lookbehind assertions in which every
+branch matches a fixed number of characters (not necessarily all the same) are
+not constrained by this limit.
 
    
-
    CREATING CHARACTER TABLES AT BUILD TIME
    
+
    CREATING CHARACTER TABLES AT BUILD TIME
    
 
    
 PCRE2 uses fixed tables for processing characters whose code points are less
 than 256. By default, PCRE2 is built with a set of tables that are distributed
@@ -361,7 +389,7 @@ just a string of bytes, independent of hardware characteristics such as
 endianness. This means they can be bundled with an application that runs in
 different environments, to ensure consistent behaviour.
 
    
-
    USING EBCDIC CODE
    
+
    USING EBCDIC CODE
    
 
    
 PCRE2 assumes by default that it will run in an environment where the character
 code is ASCII or Unicode, which is a superset of ASCII. This is the case for
@@ -396,7 +424,7 @@ The options that select newline behaviour, such as --enable-newline-is-cr,
 and equivalent run-time options, refer to these character values in an EBCDIC
 environment.
 
    
-
    PCRE2GREP SUPPORT FOR EXTERNAL SCRIPTS
    
+
    PCRE2GREP SUPPORT FOR EXTERNAL SCRIPTS
    
 
    
 By default pcre2grep supports the use of callouts with string arguments
 within the patterns it is matching. There are two kinds: one that generates
@@ -408,7 +436,7 @@ callouts, see the
 pcre2grep
 documentation.
 
    
-
    PCRE2GREP OPTIONS FOR COMPRESSED FILE SUPPORT
    
+
    PCRE2GREP OPTIONS FOR COMPRESSED FILE SUPPORT
    
 
    
 By default, pcre2grep reads all files as plain text. You can build it so
 that it recognizes files whose names end in .gz or .bz2, and reads
@@ -421,7 +449,7 @@ to the configure command. These options naturally require that the
 relevant libraries are installed on your system. Configuration will fail if
 they are not.
 
    
-
    PCRE2GREP BUFFER SIZE
    
+
    PCRE2GREP BUFFER SIZE
    
 
    
 pcre2grep uses an internal buffer to hold a "window" on the file it is
 scanning, in order to be able to output "before" and "after" lines when it
@@ -439,7 +467,7 @@ default parameter values by adding, for example,
 to the configure command. The caller of pcre2grep can override
 these values by using --buffer-size and --max-buffer-size on the command line.
 
    
-
    PCRE2TEST OPTION FOR LIBREADLINE SUPPORT
    
+
    PCRE2TEST OPTION FOR LIBREADLINE SUPPORT
    
 
    
 If you add one of
 
    @@ -457,7 +485,7 @@ with libedit, which has a BSD licence.
 
    
 Setting --enable-pcre2test-libreadline causes the -lreadline option to be
 added to the pcre2test build. In many operating environments with a
-sytem-installed readline library this is sufficient. However, in some
+system-installed readline library this is sufficient. However, in some
 environments (e.g. if an unmodified distribution version of readline is in
 use), some extra configuration may be necessary. The INSTALL file for
 libreadline says this:
@@ -473,7 +501,7 @@ automatically included, you may need to add something like
 
    
 immediately before the configure command.
 
    
-
    INCLUDING DEBUGGING CODE
    
+
    INCLUDING DEBUGGING CODE
    
 
    
 If you add
 
    @@ -482,7 +510,7 @@ If you add
 to the configure command, additional debugging code is included in the
 build. This feature is intended for use by the PCRE2 maintainers.
 
    
-
    DEBUGGING WITH VALGRIND SUPPORT
    
+
    DEBUGGING WITH VALGRIND SUPPORT
    
 
    
 If you add
 
    @@ -492,7 +520,7 @@ to the configure command, PCRE2 will use valgrind annotations to mark
 certain memory regions as unaddressable. This allows it to detect invalid
 memory accesses, and is mostly useful for debugging PCRE2 itself.
 
    
-
    CODE COVERAGE REPORTING
    
+
    CODE COVERAGE REPORTING
    
 
    
 If your C compiler is gcc, you can build a version of PCRE2 that can generate a
 code coverage report for its test suite. To enable this, you must install
@@ -549,7 +577,7 @@ This cleans all coverage data including the generated coverage report. For more
 information about code coverage, see the gcov and lcov
 documentation.
 
    
-
    DISABLING THE Z AND T FORMATTING MODIFIERS
    
+
    DISABLING THE Z AND T FORMATTING MODIFIERS
    
 
    
 The C99 standard defines formatting modifiers z and t for size_t and
 ptrdiff_t values, respectively. By default, PCRE2 uses these modifiers in
@@ -564,7 +592,7 @@ support these modifiers. If
 is specified, no use is made of the z or t modifiers. Instead of %td or %zu,
 a suitable format is used depending in the size of long for the platform.
 
    
-
    SUPPORT FOR FUZZERS
    
+
    SUPPORT FOR FUZZERS
    
 
    
 There is a special option for use by people who want to run fuzzing tests on
 PCRE2:
@@ -588,7 +616,7 @@ arguments: if an argument starts with "=" the rest of it is a literal input
 string. Otherwise, it is assumed to be a file name, and the contents of the
 file are the test string.
 
    
-
    OBSOLETE OPTION
    
+
    OBSOLETE OPTION
    
 
    
 In versions of PCRE2 prior to 10.30, there were two ways of handling
 backtracking in the pcre2_match() function. The default was to use the
@@ -600,11 +628,11 @@ was set, memory on the heap was used. From release 10.30 onwards this has
 changed (the stack is no longer used) and this option now does nothing except
 give a warning.
 
    
-
    SEE ALSO
    
+
    SEE ALSO
    
 
    
 pcre2api(3), pcre2-config(3).
 
    
-
    AUTHOR
    
+
    AUTHOR
    
 
    
 Philip Hazel
 
    
@@ -613,11 +641,11 @@ Retired from University Computing Service
 Cambridge, England.
 
    
 
    
-
    REVISION
    
+
    REVISION
    
 
    
-Last updated: 27 July 2022
+Last updated: 15 April 2024
 
    
-Copyright © 1997-2022 University of Cambridge.
+Copyright © 1997-2024 University of Cambridge.
 
    
 
    
 Return to the PCRE2 index page.
diff --git a/pcre2/doc/html/pcre2callout.html b/pcre2/doc/html/pcre2callout.html
index 65db933..cdb65ad 100644
--- a/pcre2/doc/html/pcre2callout.html
+++ b/pcre2/doc/html/pcre2callout.html
@@ -350,12 +350,12 @@ The next_item_length field contains the length of the next item to be
 processed in the pattern string. When the callout is at the end of the pattern,
 the length is zero. When the callout precedes an opening parenthesis, the
 length includes meta characters that follow the parenthesis. For example, in a
-callout before an assertion such as (?=ab) the length is 3. For an an
-alternation bar or a closing parenthesis, the length is one, unless a closing
-parenthesis is followed by a quantifier, in which case its length is included.
-(This changed in release 10.23. In earlier releases, before an opening
-parenthesis the length was that of the entire group, and before an alternation
-bar or a closing parenthesis the length was zero.)
+callout before an assertion such as (?=ab) the length is 3. For an alternation
+bar or a closing parenthesis, the length is one, unless a closing parenthesis
+is followed by a quantifier, in which case its length is included. (This
+changed in release 10.23. In earlier releases, before an opening parenthesis
+the length was that of the entire group, and before an alternation bar or a
+closing parenthesis the length was zero.)
 
    
 
    
 The pattern_position and next_item_length fields are intended to
@@ -464,16 +464,16 @@ value, scanning the pattern stops, and that value is returned from
 
    
 Philip Hazel
 
    
-University Computing Service
+Retired from University Computing Service
 
    
 Cambridge, England.
 
    
 
    
 
    REVISION
    
 
    
-Last updated: 03 February 2019
+Last updated: 19 January 2024
 
    
-Copyright © 1997-2019 University of Cambridge.
+Copyright © 1997-2024 University of Cambridge.
 
    
 
    
 Return to the PCRE2 index page.
diff --git a/pcre2/doc/html/pcre2compat.html b/pcre2/doc/html/pcre2compat.html
index 5f390c1..d60182e 100644
--- a/pcre2/doc/html/pcre2compat.html
+++ b/pcre2/doc/html/pcre2compat.html
@@ -16,10 +16,10 @@ please consult the man page, in case the conversion went wrong.
 DIFFERENCES BETWEEN PCRE2 AND PERL
 
    
 
    
-This document describes some of the differences in the ways that PCRE2 and Perl
-handle regular expressions. The differences described here are with respect to
-Perl version 5.34.0, but as both Perl and PCRE2 are continually changing, the
-information may at times be out of date.
+This document describes some of the known differences in the ways that PCRE2
+and Perl handle regular expressions. The differences described here are with
+respect to Perl version 5.38.0, but as both Perl and PCRE2 are continually
+changing, the information may at times be out of date.
 
    
 
    
 1. When PCRE2_DOTALL (equivalent to Perl's /s qualifier) is not set, the
@@ -46,13 +46,18 @@ for example, \b* , but these do not seem to have any use. PCRE2 does not allow
 any kind of quantifier on non-lookaround assertions.
 
    
 
    
-4. Capture groups that occur inside negative lookaround assertions are counted,
+4. If a braced quantifier such as {1,2} appears where there is nothing to
+repeat (for example, at the start of a branch), PCRE2 raises an error whereas
+Perl treats the quantifier characters as literal.
+
    
+
    
+5. Capture groups that occur inside negative lookaround assertions are counted,
 but their entries in the offsets vector are set only when a negative assertion
 is a condition that has a matching branch (that is, the condition is false).
 Perl may set such capture groups in other circumstances.
 
    
 
    
-5. The following Perl escape sequences are not supported: \F, \l, \L, \u,
+6. The following Perl escape sequences are not supported: \F, \l, \L, \u,
 \U, and \N when followed by a character name. \N on its own, matching a
 non-newline character, and \N{U+dd..}, matching a Unicode code point, are
 supported. The escapes that modify the case of following letters are
@@ -63,19 +68,20 @@ PCRE2_EXTRA_ALT_BSUX options is set, \U and \u are interpreted as ECMAScript
 interprets them.
 
    
 
    
-6. The Perl escape sequences \p, \P, and \X are supported only if PCRE2 is
+7. The Perl escape sequences \p, \P, and \X are supported only if PCRE2 is
 built with Unicode support (the default). The properties that can be tested
 with \p and \P are limited to the general category properties such as Lu and
-Nd, script names such as Greek or Han, Bidi_Class, Bidi_Control, and the
-derived properties Any and LC (synonym L&). Both PCRE2 and Perl support the Cs
-(surrogate) property, but in PCRE2 its use is limited. See the
+Nd, the derived properties Any and LC (synonym L&), script names such as Greek
+or Han, Bidi_Class, Bidi_Control, and a few binary properties. Both PCRE2 and
+Perl support the Cs (surrogate) property, but in PCRE2 its use is limited. See
+the
 pcre2pattern
 documentation for details. The long synonyms for property names that Perl
 supports (such as \p{Letter}) are not supported by PCRE2, nor is it permitted
 to prefix any of these properties with "Is".
 
    
 
    
-7. PCRE2 supports the \Q...\E escape for quoting substrings. Characters
+8. PCRE2 supports the \Q...\E escape for quoting substrings. Characters
 in between are treated as literals. However, this is slightly different from
 Perl in that $ and @ are also handled as literals inside the quotes. In Perl,
 they cause variable interpolation (PCRE2 does not have variables). Also, Perl
@@ -96,19 +102,19 @@ The \Q...\E sequence is recognized both inside and outside character classes
 by both PCRE2 and Perl.
 
    
 
    
-8. Fairly obviously, PCRE2 does not support the (?{code}) and (??{code})
+9. Fairly obviously, PCRE2 does not support the (?{code}) and (??{code})
 constructions. However, PCRE2 does have a "callout" feature, which allows an
 external function to be called during pattern matching. See the
 pcre2callout
 documentation for details.
 
    
 
    
-9. Subroutine calls (whether recursive or not) were treated as atomic groups up
-to PCRE2 release 10.23, but from release 10.30 this changed, and backtracking
-into subroutine calls is now supported, as in Perl.
+10. Subroutine calls (whether recursive or not) were treated as atomic groups
+up to PCRE2 release 10.23, but from release 10.30 this changed, and
+backtracking into subroutine calls is now supported, as in Perl.
 
    
 
    
-10. In PCRE2, if any of the backtracking control verbs are used in a group that
+11. In PCRE2, if any of the backtracking control verbs are used in a group that
 is called as a subroutine (whether or not recursively), their effect is
 confined to that group; it does not extend to the surrounding pattern. This is
 not always the case in Perl. In particular, if (*THEN) is present in a group
@@ -117,20 +123,20 @@ the group does not contain any | characters. Note that such groups are
 processed as anchored at the point where they are tested.
 
    
 
    
-11. If a pattern contains more than one backtracking control verb, the first
+12. If a pattern contains more than one backtracking control verb, the first
 one that is backtracked onto acts. For example, in the pattern
 A(*COMMIT)B(*PRUNE)C a failure in B triggers (*COMMIT), but a failure in C
 triggers (*PRUNE). Perl's behaviour is more complex; in many cases it is the
 same as PCRE2, but there are cases where it differs.
 
    
 
    
-12. There are some differences that are concerned with the settings of captured
+13. There are some differences that are concerned with the settings of captured
 strings when part of a pattern is repeated. For example, matching "aba" against
 the pattern /^(a(b)?)+$/ in Perl leaves $2 unset, but in PCRE2 it is set to
 "b".
 
    
 
    
-13. PCRE2's handling of duplicate capture group numbers and names is not as
+14. PCRE2's handling of duplicate capture group numbers and names is not as
 general as Perl's. This is a consequence of the fact the PCRE2 works internally
 just with numbers, using an external table to translate between numbers and
 names. In particular, a pattern such as (?|(?<a>A)|(?<b>B)), where the two
@@ -140,99 +146,91 @@ to distinguish which group matched, because both names map to capture group
 number 1. To avoid this confusing situation, an error is given at compile time.
 
    
 
    
-14. Perl used to recognize comments in some places that PCRE2 does not, for
+15. Perl used to recognize comments in some places that PCRE2 does not, for
 example, between the ( and ? at the start of a group. If the /x modifier is
 set, Perl allowed white space between ( and ? though the latest Perls give an
 error (for a while it was just deprecated). There may still be some cases where
 Perl behaves differently.
 
    
 
    
-15. Perl, when in warning mode, gives warnings for character classes such as
+16. Perl, when in warning mode, gives warnings for character classes such as
 [A-\d] or [a-[:digit:]]. It then treats the hyphens as literals. PCRE2 has no
 warning features, so it gives an error in these cases because they are almost
 certainly user mistakes.
 
    
 
    
-16. In PCRE2, the upper/lower case character properties Lu and Ll are not
+17. In PCRE2, the upper/lower case character properties Lu and Ll are not
 affected when case-independent matching is specified. For example, \p{Lu}
 always matches an upper case letter. I think Perl has changed in this respect;
-in the release at the time of writing (5.34), \p{Lu} and \p{Ll} match all
+in the release at the time of writing (5.38), \p{Lu} and \p{Ll} match all
 letters, regardless of case, when case independence is specified.
 
    
 
    
-17. From release 5.32.0, Perl locks out the use of \K in lookaround
+18. From release 5.32.0, Perl locks out the use of \K in lookaround
 assertions. From release 10.38 PCRE2 does the same by default. However, there
 is an option for re-enabling the previous behaviour. When this option is set,
 \K is acted on when it occurs in positive assertions, but is ignored in
 negative assertions.
 
    
 
    
-18. PCRE2 provides some extensions to the Perl regular expression facilities.
+19. PCRE2 provides some extensions to the Perl regular expression facilities.
 Perl 5.10 included new features that were not in earlier versions of Perl, some
 of which (such as named parentheses) were in PCRE2 for some time before. This
-list is with respect to Perl 5.34:
-
    
-
    
-(a) Although lookbehind assertions in PCRE2 must match fixed length strings,
-each alternative toplevel branch of a lookbehind assertion can match a
-different length of string. Perl used to require them all to have the same
-length, but the latest version has some variable length support.
+list is with respect to Perl 5.38:
 
    
 
    
-(b) From PCRE2 10.23, backreferences to groups of fixed length are supported
-in lookbehinds, provided that there is no possibility of referencing a
-non-unique number or name. Perl does not support backreferences in lookbehinds.
-
    
-
    
-(c) If PCRE2_DOLLAR_ENDONLY is set and PCRE2_MULTILINE is not set, the $
+(a) If PCRE2_DOLLAR_ENDONLY is set and PCRE2_MULTILINE is not set, the $
 meta-character matches only at the very end of the string.
 
    
 
    
-(d) A backslash followed by a letter with no special meaning is faulted. (Perl
+(b) A backslash followed by a letter with no special meaning is faulted. (Perl
 can be made to issue a warning.)
 
    
 
    
-(e) If PCRE2_UNGREEDY is set, the greediness of the repetition quantifiers is
+(c) If PCRE2_UNGREEDY is set, the greediness of the repetition quantifiers is
 inverted, that is, by default they are not greedy, but if followed by a
 question mark they are.
 
    
 
    
-(f) PCRE2_ANCHORED can be used at matching time to force a pattern to be tried
+(d) PCRE2_ANCHORED can be used at matching time to force a pattern to be tried
 only at the first matching position in the subject string.
 
    
 
    
-(g) The PCRE2_NOTBOL, PCRE2_NOTEOL, PCRE2_NOTEMPTY and PCRE2_NOTEMPTY_ATSTART
+(e) The PCRE2_NOTBOL, PCRE2_NOTEOL, PCRE2_NOTEMPTY and PCRE2_NOTEMPTY_ATSTART
 options have no Perl equivalents.
 
    
 
    
-(h) The \R escape sequence can be restricted to match only CR, LF, or CRLF
+(f) The \R escape sequence can be restricted to match only CR, LF, or CRLF
 by the PCRE2_BSR_ANYCRLF option.
 
    
 
    
-(i) The callout facility is PCRE2-specific. Perl supports codeblocks and
+(g) The callout facility is PCRE2-specific. Perl supports codeblocks and
 variable interpolation, but not general hooks on every match.
 
    
 
    
-(j) The partial matching facility is PCRE2-specific.
+(h) The partial matching facility is PCRE2-specific.
 
    
 
    
-(k) The alternative matching function (pcre2_dfa_match() matches in a
+(i) The alternative matching function (pcre2_dfa_match() matches in a
 different way and is not Perl-compatible.
 
    
 
    
-(l) PCRE2 recognizes some special sequences such as (*CR) or (*NO_JIT) at
+(j) PCRE2 recognizes some special sequences such as (*CR) or (*NO_JIT) at
 the start of a pattern. These set overall options that cannot be changed within
 the pattern.
 
    
 
    
-(m) PCRE2 supports non-atomic positive lookaround assertions. This is an
+(k) PCRE2 supports non-atomic positive lookaround assertions. This is an
 extension to the lookaround facilities. The default, Perl-compatible
 lookarounds are atomic.
-
    
-
    
-19. The Perl /a modifier restricts /d numbers to pure ascii, and the /aa
-modifier restricts /i case-insensitive matching to pure ascii, ignoring Unicode
-rules. This separation cannot be represented with PCRE2_UCP.
+
    
+
    
+(l) There are three syntactical items in patterns that can refer to a capturing
+group by number: back references such as \g{2}, subroutine calls such as (?3),
+and condition references such as (?(4)...). PCRE2 supports relative group
+numbers such as +2 and -4 in all three cases. Perl supports both plus and minus
+for subroutine calls, but only minus for back references, and no relative
+numbering at all for conditions.
 
    
 
    
 20. Perl has different limits than PCRE2. See the
@@ -242,6 +240,18 @@ keeping the intermediate matches on the heap, which is ~10% slower but does not
 fall into any stack-overflow limit. PCRE2 made a similar change at release
 10.30, and also has many build-time and run-time customizable limits.
 
    
+
    
+21. Unlike Perl, PCRE2 doesn't have character set modifiers and specially no way
+to set characters by context just like Perl's "/d". A regular expression using
+PCRE2_UTF and PCRE2_UCP will use similar rules to Perl's "/u"; something closer
+to "/a" could be selected by adding other PCRE2_EXTRA_ASCII* options on top.
+
    
+
    
+22. Some recursive patterns that Perl diagnoses as infinite recursions can be
+handled by PCRE2, either by the interpreter or the JIT. An example is
+/(?:|(?0)abcd)(?(R)|\z)/, which matches a sequence of any number of repeated
+"abcd" substrings at the end of the subject.
+
    
 
    
 AUTHOR
 
    
@@ -257,9 +267,9 @@ Cambridge, England.
 REVISION
 
    
 
    
-Last updated: 08 December 2021
+Last updated: 30 November 2023
 
    
-Copyright © 1997-2021 University of Cambridge.
+Copyright © 1997-2023 University of Cambridge.
 
    
 
    
 Return to the PCRE2 index page.
diff --git a/pcre2/doc/html/pcre2convert.html b/pcre2/doc/html/pcre2convert.html
index c3d4cac..6b9fea5 100644
--- a/pcre2/doc/html/pcre2convert.html
+++ b/pcre2/doc/html/pcre2convert.html
@@ -175,7 +175,7 @@ neither do POSIX extended patterns).
 
    
 Philip Hazel
 
    
-University Computing Service
+Retired from University Computing Service
 
    
 Cambridge, England.
 
    
diff --git a/pcre2/doc/html/pcre2demo.html b/pcre2/doc/html/pcre2demo.html
index 1f84373..1cb7e0a 100644
--- a/pcre2/doc/html/pcre2demo.html
+++ b/pcre2/doc/html/pcre2demo.html
@@ -12,8 +12,9 @@ This page is part of the PCRE2 HTML documentation. It was generated
 automatically from the original man page. If there is any nonsense in it,
 please consult the man page, in case the conversion went wrong.
 
    
-
      
-
    
+
    
+SOURCE CODE
+
    
 
     /*************************************************
 *           PCRE2 DEMONSTRATION PROGRAM          *
diff --git a/pcre2/doc/html/pcre2grep.html b/pcre2/doc/html/pcre2grep.html
index 29ab031..bd12246 100644
--- a/pcre2/doc/html/pcre2grep.html
+++ b/pcre2/doc/html/pcre2grep.html
@@ -21,7 +21,7 @@ please consult the man page, in case the conversion went wrong.
 
  • OPTIONS
 
  • ENVIRONMENT VARIABLES
 
  • NEWLINES
-
  • OPTIONS COMPATIBILITY
+
  • OPTIONS COMPATIBILITY WITH GNU GREP
 
  • OPTIONS WITH DATA
 
  • USING PCRE2'S CALLOUT FACILITY
 
  • MATCHING ERRORS
@@ -71,15 +71,16 @@ For example:
 
       pcre2grep some-pattern file1 - file3
 
    
-By default, input files are searched line by line. Each line that matches a
-pattern is copied to the standard output, and if there is more than one file,
-the file name is output at the start of each line, followed by a colon.
-However, there are options that can change how pcre2grep behaves. For
-example, the -M option makes it possible to search for strings that span
-line boundaries. What defines a line boundary is controlled by the -N
-(--newline) option. The -h and -H options control whether or
-not file names are shown, and the -Z option changes the file name
-terminator to a zero byte.
+By default, input files are searched line by line, so pattern assertions about
+the beginning and end of a subject string (^, $, \A, \Z, and \z) match at
+the beginning and end of each line. When a line matches a pattern, it is copied
+to the standard output, and if there is more than one file, the file name is
+output at the start of each line, followed by a colon. However, there are
+options that can change how pcre2grep behaves. For example, the -M
+option makes it possible to search for strings that span line boundaries. What
+defines a line boundary is controlled by the -N (--newline) option.
+The -h and -H options control whether or not file names are shown,
+and the -Z option changes the file name terminator to a zero byte.
 
    
 
    
 The amount of memory used for buffering files that are being scanned is
@@ -99,6 +100,10 @@ allow for buffering "before" and "after" lines. If the buffer size is too
 small, fewer than requested "before" and "after" lines may be output.
 
    
 
    
+When matching with a multiline pattern, the size of the buffer must be at least
+half of the maximum match expected or the pattern might fail to match.
+
    
+
    
 Patterns can be no longer than 8KiB or BUFSIZ bytes, whichever is the greater.
 BUFSIZ is defined in <stdio.h>. When there is more than one pattern
 (specified by the use of -e and/or -f), each pattern is applied to
@@ -249,7 +254,7 @@ exactly the same as the number of lines that would have been output, but if the
 suppressed lines than the count (that is, the number of matches).
 
    
 
    
-If no lines are selected, the number zero is output. If several files are are
+If no lines are selected, the number zero is output. If several files are
 being scanned, a count is output for each of them and the -t option can
 be used to cause a total to be output at the end. However, if the
 --files-with-matches option is also used, only those files whose counts
@@ -314,6 +319,14 @@ end-of-file; in others it may provoke an error.
 See --match-limit below.
 
    
 
    
+-E, --case-restrict
+When case distinctions are being ignored in Unicode mode, two ASCII letters (K
+and S) will by default match Unicode characters U+212A (Kelvin sign) and U+017F
+(long S) respectively, as well as their lower case ASCII counterparts. When
+this option is set, case equivalences are restricted such that no ASCII
+character matches a non-ASCII character, and vice versa.
+
    
+
    
 -e pattern, --regex=pattern, --regexp=pattern
 Specify a pattern to be matched. This option can be used multiple times in
 order to specify several patterns. It can also be used as a way of specifying a
@@ -413,6 +426,11 @@ match in a line, each of them is shown separately. This option is mutually
 exclusive with --output, --line-offsets, and --only-matching.
 
    
 
    
+--group-separator=text
+Output this text string instead of two hyphens between groups of lines when
+-A, -B, or -C is in use. See also --no-group-separator.
+
    
+
    
 -H, --with-filename
 Force the inclusion of the file name at the start of output lines when
 searching a single file. The file name is not normally shown in this case.
@@ -449,7 +467,9 @@ Ignore binary files. This is equivalent to
 
    
 
    
 -i, --ignore-case
-Ignore upper/lower case distinctions during comparisons.
+Ignore upper/lower case distinctions when pattern matching. This applies when
+matching path names for inclusion or exclusion as well as when matching lines
+in files.
 
    
 
    
 --include=pattern
@@ -544,16 +564,24 @@ used. There is no short form for this option.
 
    
 -M, --multiline
 Allow patterns to match more than one line. When this option is set, the PCRE2
-library is called in "multiline" mode. This allows a matched string to extend
-past the end of a line and continue on one or more subsequent lines. Patterns
-used with -M may usefully contain literal newline characters and internal
-occurrences of ^ and $ characters. The output for a successful match may
-consist of more than one line. The first line is the line in which the match
-started, and the last line is the line in which the match ended. If the matched
-string ends with a newline sequence, the output ends at the end of that line.
-If -v is set, none of the lines in a multi-line match are output. Once a
-match has been handled, scanning restarts at the beginning of the line after
-the one in which the match ended.
+library is called in "multiline" mode, and a match is allowed to continue past
+the end of the initial line and onto one or more subsequent lines.
+
    
+
    
+Patterns used with -M may usefully contain literal newline characters and
+internal occurrences of ^ and $ characters, because in multiline mode these can
+match at internal newlines. Because pcre2grep is scanning multiple lines,
+the \Z and \z assertions match only at the end of the last line in the file.
+The \A assertion matches at the start of the first line of a match. This can
+be any line in the file; it is not anchored to the first line.
+
    
+
    
+The output for a successful match may consist of more than one line. The first
+line is the line in which the match started, and the last line is the line in
+which the match ended. If the matched string ends with a newline sequence, the
+output ends at the end of that line. If -v is set, none of the lines in a
+multi-line match are output. Once a match has been handled, scanning restarts
+at the beginning of the line after the one in which the match ended.
 
    
 
    
 The newline sequence that separates multiple lines must be matched as part of
@@ -570,8 +598,11 @@ well as possibly handling a two-character newline sequence.
 
    
 There is a limit to the number of lines that can be matched, imposed by the way
 that pcre2grep buffers the input file as it scans it. With a sufficiently
-large processing buffer, this should not be a problem, but the -M option
-does not work when input is read line by line (see --line-buffered.)
+large processing buffer, this should not be a problem.
+
    
+
    
+The -M option does not work when input is read line by line (see
+--line-buffered.)
 
    
 
    
 -m number, --max-count=number
@@ -661,11 +692,17 @@ pattern to match more than one line, only the first is preceded by its line
 number. This option is forced if --line-offsets is used.
 
    
 
    
+--no-group-separator
+Do not output a separator between groups of lines when -A, -B, or
+-C is in use. The default is to output a line containing two hyphens. See
+also --group-separator.
+
    
+
    
 --no-jit
 If the PCRE2 library is built with support for just-in-time compiling (which
 speeds up matching), pcre2grep automatically makes use of this, unless it
 was explicitly disabled at build time. This option can be used to disable the
-use of JIT at run time. It is provided for testing and working round problems.
+use of JIT at run time. It is provided for testing and working around problems.
 It should never be needed in normal use.
 
    
 
    
@@ -759,6 +796,18 @@ Specify a separating string for multiple occurrences of -o. The default
 is an empty string. Separating strings are never coloured.
 
    
 
    
+-P, --no-ucp
+Starting from release 10.43, when UTF/Unicode mode is specified with -u
+or -U, the PCRE2_UCP option is used by default. This means that the
+POSIX classes in patterns match more than just ASCII characters. For example,
+[:digit:] matches any Unicode decimal digit. The --no-ucp option
+suppresses PCRE2_UCP, thus restricting the POSIX classes to ASCII characters,
+as was the case in earlier releases. Note that there are now more fine-grained
+option settings within patterns that affect individual classes. For example,
+when in UCP mode, the sequence (?aP) restricts [:word:] to ASCII letters, while
+allowing \w to match Unicode letters and digits.
+
    
+
    
 -q, --quiet
 Work quietly, that is, display nothing except error messages. The exit
 status indicates whether or not any matches were found.
@@ -796,11 +845,11 @@ total would always be zero.
 
    
 
    
 -u, --utf
-Operate in UTF-8 mode. This option is available only if PCRE2 has been compiled
-with UTF-8 support. All patterns (including those for any --exclude and
---include options) and all lines that are scanned must be valid strings
-of UTF-8 characters. If an invalid UTF-8 string is encountered, an error
-occurs.
+Operate in UTF/Unicode mode. This option is available only if PCRE2 has been
+compiled with UTF-8 support. All patterns (including those for any
+--exclude and --include options) and all lines that are scanned
+must be valid strings of UTF-8 characters. If an invalid UTF-8 string is
+encountered, an error occurs.
 
    
 
    
 -U, --utf-allow-invalid
@@ -883,25 +932,27 @@ ends of output lines that are copied from the input is not converted to
 standard output must end with "\r\n". For all other operating systems, and
 for all messages to the standard error stream, "\n" is used.
 
    
-
    OPTIONS COMPATIBILITY
    
+
    OPTIONS COMPATIBILITY WITH GNU GREP
    
 
    
-Many of the short and long forms of pcre2grep's options are the same
-as in the GNU grep program. Any long option of the form
---xxx-regexp (GNU terminology) is also available as --xxx-regex
-(PCRE2 terminology). However, the --depth-limit, --file-list,
---file-offsets, --heap-limit, --include-dir,
---line-offsets, --locale, --match-limit, -M,
---multiline, -N, --newline, --om-separator,
---output, -u, --utf, -U, and --utf-allow-invalid
-options are specific to pcre2grep, as is the use of the
---only-matching option with a capturing parentheses number.
+Many of the short and long forms of pcre2grep's options are the same as
+in the GNU grep program. Any long option of the form --xxx-regexp
+(GNU terminology) is also available as --xxx-regex (PCRE2 terminology).
+However, the --case-restrict, --depth-limit, -E,
+--file-list, --file-offsets, --heap-limit,
+--include-dir, --line-offsets, --locale, --match-limit,
+-M, --multiline, -N, --newline, --no-ucp,
+--om-separator, --output, -P, -u, --utf,
+-U, and --utf-allow-invalid options are specific to
+pcre2grep, as is the use of the --only-matching option with a
+capturing parentheses number.
 
    
 
    
 Although most of the common options work the same way, a few are different in
 pcre2grep. For example, the --include option's argument is a glob
-for GNU grep, but a regular expression for pcre2grep. If both the
--c and -l options are given, GNU grep lists only file names,
-without counts, but pcre2grep gives the counts as well.
+for GNU grep, but in pcre2grep it is a regular expression to which
+the -i option applies. If both the -c and -l options are
+given, GNU grep lists only file names, without counts, but pcre2grep
+gives the counts as well.
 
    
 
    OPTIONS WITH DATA
    
 
    
@@ -1065,9 +1116,9 @@ Cambridge, England.
 
    
 
    REVISION
    
 
    
-Last updated: 21 November 2022
+Last updated: 22 December 2023
 
    
-Copyright © 1997-2022 University of Cambridge.
+Copyright © 1997-2023 University of Cambridge.
 
    
 
    
 Return to the PCRE2 index page.
diff --git a/pcre2/doc/html/pcre2jit.html b/pcre2/doc/html/pcre2jit.html
index d89fa23..d97d800 100644
--- a/pcre2/doc/html/pcre2jit.html
+++ b/pcre2/doc/html/pcre2jit.html
@@ -43,7 +43,7 @@ one-off matches. JIT support is available for all of the 8-bit, 16-bit and
 
    
 JIT support applies only to the traditional Perl-compatible matching function.
 It does not apply when the DFA matching function is being used. The code for
-this support was written by Zoltan Herczeg.
+JIT support was written by Zoltan Herczeg.
 
    
 
    AVAILABILITY OF JIT SUPPORT
    
 
    
@@ -52,23 +52,37 @@ JIT support is an optional feature of PCRE2. The "configure" option
 you want to use JIT. The support is limited to the following hardware
 platforms:
 
    -  ARM 32-bit (v5, v7, and Thumb2)
+  ARM 32-bit (v7, and Thumb2)
   ARM 64-bit
   IBM s390x 64 bit
   Intel x86 32-bit and 64-bit
+  LoongArch 64 bit
   MIPS 32-bit and 64-bit
   Power PC 32-bit and 64-bit
-  SPARC 32-bit
+  RISC-V 32-bit and 64-bit
 
    
 If --enable-jit is set on an unsupported platform, compilation fails.
 
    
 
    
-A program can tell if JIT support is available by calling pcre2_config()
-with the PCRE2_CONFIG_JIT option. The result is 1 when JIT is available, and 0
-otherwise. However, a simple program does not need to check this in order to
-use JIT. The API is implemented in a way that falls back to the interpretive
-code if JIT is not available. For programs that need the best possible
-performance, there is also a "fast path" API that is JIT-specific.
+A client program can tell if JIT support is available by calling
+pcre2_config() with the PCRE2_CONFIG_JIT option. The result is one if
+PCRE2 was built with JIT support, and zero otherwise. However, having the JIT
+code available does not guarantee that it will be used for any particular
+match. One reason for this is that there are a number of options and pattern
+items that are
+not supported by JIT
+(see below). Another reason is that in some environments JIT is unable to get
+memory in which to build its compiled code. The only guarantee from
+pcre2_config() is that if it returns zero, JIT will definitely not
+be used.
+
    
+
    
+A simple program does not need to check availability in order to use JIT when
+possible. The API is implemented in a way that falls back to the interpretive
+code if JIT is not available or cannot be used for a given match. For programs
+that need the best possible performance, there is a
+"fast path"
+API that is JIT-specific.
 
    
 
    SIMPLE USE OF JIT
    
 
    
@@ -127,9 +141,10 @@ below.
 
    
 There are some pcre2_match() options that are not supported by JIT, and
 there are also some pattern items that JIT cannot handle. Details are given
-below. In both cases, matching automatically falls back to the interpretive
-code. If you want to know whether JIT was actually used for a particular match,
-you should arrange for a JIT callback function to be set up as described in the
+below.
+In both cases, matching automatically falls back to the interpretive code. If
+you want to know whether JIT was actually used for a particular match, you
+should arrange for a JIT callback function to be set up as described in the
 section entitled
 "Controlling the JIT stack"
 below, even if you do not need to supply a non-default JIT stack. Such a
@@ -139,12 +154,14 @@ not obeyed.
 
    
 
    
 If the JIT compiler finds an unsupported item, no JIT data is generated. You
-can find out if JIT matching is available after compiling a pattern by calling
-pcre2_pattern_info() with the PCRE2_INFO_JITSIZE option. A non-zero
-result means that JIT compilation was successful. A result of 0 means that JIT
-support is not available, or the pattern was not processed by
+can find out if JIT compilation was successful for a compiled pattern by
+calling pcre2_pattern_info() with the PCRE2_INFO_JITSIZE option. A
+non-zero result means that JIT compilation was successful. A result of 0 means
+that JIT support is not available, or the pattern was not processed by
 pcre2_jit_compile(), or the JIT compiler was not able to handle the
-pattern.
+pattern. Successful JIT compilation does not, however, guarantee the use of JIT
+at match time because there are some match time options that are not supported
+by JIT.
 
    
 
    MATCHING SUBJECTS CONTAINING INVALID UTF
    
 
    
@@ -154,15 +171,16 @@ checked at the start of matching and an error is generated if invalid UTF is
 detected. The PCRE2_NO_UTF_CHECK option can be passed to pcre2_match() to
 skip the check (for improved performance) if you are sure that a subject string
 is valid. If this option is used with an invalid string, the result is
-undefined.
+undefined. The calling program may crash or loop or otherwise misbehave.
 
    
 
    
 However, a way of running matches on strings that may contain invalid UTF
 sequences is available. Calling pcre2_compile() with the
 PCRE2_MATCH_INVALID_UTF option has two effects: it tells the interpreter in
 pcre2_match() to support invalid UTF, and, if pcre2_jit_compile()
-is called, the compiled JIT code also supports invalid UTF. Details of how this
-support works, in both the JIT and the interpretive cases, is given in the
+is subsequently called, the compiled JIT code also supports invalid UTF.
+Details of how this support works, in both the JIT and the interpretive cases,
+is given in the
 pcre2unicode
 documentation.
 
    
@@ -171,7 +189,7 @@ There is also an obsolete option for pcre2_jit_compile() called
 PCRE2_JIT_INVALID_UTF, which currently exists only for backward compatibility.
 It is superseded by the pcre2_compile() option PCRE2_MATCH_INVALID_UTF
 and should no longer be used. It may be removed in future.
-
    
+
    
 
    UNSUPPORTED OPTIONS AND PATTERN ITEMS
    
 
    
 The pcre2_match() options that are supported for JIT matching are
@@ -191,10 +209,10 @@ in a conditional group.
 
    
 
    RETURN VALUES FROM JIT MATCHING
    
 
    
-When a pattern is matched using JIT matching, the return values are the same
-as those given by the interpretive pcre2_match() code, with the addition
-of one new error code: PCRE2_ERROR_JIT_STACKLIMIT. This means that the memory
-used for the JIT stack was insufficient. See
+When a pattern is matched using JIT, the return values are the same as those
+given by the interpretive pcre2_match() code, with the addition of one
+new error code: PCRE2_ERROR_JIT_STACKLIMIT. This means that the memory used for
+the JIT stack was insufficient. See
 "Controlling the JIT stack"
 below for a discussion of JIT stack usage.
 
    
@@ -363,7 +381,7 @@ pattern causes stack overflow with a stack of 1MiB? Is that 1MiB kept until the
 stack is freed?
 
    
 
    
-Especially on embedded sytems, it might be a good idea to release memory
+Especially on embedded systems, it might be a good idea to release memory
 sometimes without freeing the stack. There is no API for this at the moment.
 Probably a function call which returns with the currently allocated memory for
 any stack and another which allows releasing memory (shrinking the stack) would
@@ -416,7 +434,7 @@ calls.
   pcre2_match_context_free(mcontext);
   pcre2_jit_stack_free(jit_stack);
 
-
    • 
+
    
 
    
 
    JIT FAST PATH API
    
 
    
@@ -433,11 +451,10 @@ processed by pcre2_jit_compile()).
 The fast path function is called pcre2_jit_match(), and it takes exactly
 the same arguments as pcre2_match(). However, the subject string must be
 specified with a length; PCRE2_ZERO_TERMINATED is not supported. Unsupported
-option bits (for example, PCRE2_ANCHORED, PCRE2_ENDANCHORED and
-PCRE2_COPY_MATCHED_SUBJECT) are ignored, as is the PCRE2_NO_JIT option. The
-return values are also the same as for pcre2_match(), plus
-PCRE2_ERROR_JIT_BADOPTION if a matching mode (partial or complete) is requested
-that was not compiled.
+option bits (for example, PCRE2_ANCHORED and PCRE2_ENDANCHORED) are ignored, as
+is the PCRE2_NO_JIT option. The return values are also the same as for
+pcre2_match(), plus PCRE2_ERROR_JIT_BADOPTION if a matching mode (partial
+or complete) is requested that was not compiled.
 
    
 
    
 When you call pcre2_match(), as well as testing for invalid options, a
@@ -445,7 +462,11 @@ number of other sanity checks are performed on the arguments. For example, if
 the subject pointer is NULL but the length is non-zero, an immediate error is
 given. Also, unless PCRE2_NO_UTF_CHECK is set, a UTF subject string is tested
 for validity. In the interests of speed, these checks do not happen on the JIT
-fast path, and if invalid data is passed, the result is undefined.
+fast path. If invalid UTF data is passed when PCRE2_MATCH_INVALID_UTF was not
+set for pcre2_compile(), the result is undefined. The program may crash
+or loop or give wrong results. In the absence of PCRE2_MATCH_INVALID_UTF you
+should call pcre2_jit_match() in UTF mode only if you are sure the
+subject is valid.
 
    
 
    
 Bypassing the sanity checks and the pcre2_match() wrapping can give
@@ -453,22 +474,22 @@ speedups of more than 10%.
 
    
 
    SEE ALSO
    
 
    
-pcre2api(3)
+pcre2api(3), pcre2unicode(3)
 
    
 
    AUTHOR
    
 
    
 Philip Hazel (FAQ by Zoltan Herczeg)
 
    
-University Computing Service
+Retired from University Computing Service
 
    
 Cambridge, England.
 
    
 
    
 
    REVISION
    
 
    
-Last updated: 30 November 2021
+Last updated: 21 February 2024
 
    
-Copyright © 1997-2021 University of Cambridge.
+Copyright © 1997-2024 University of Cambridge.
 
    
 
    
 Return to the PCRE2 index page.
diff --git a/pcre2/doc/html/pcre2limits.html b/pcre2/doc/html/pcre2limits.html
index fca5e89..8152ed2 100644
--- a/pcre2/doc/html/pcre2limits.html
+++ b/pcre2/doc/html/pcre2limits.html
@@ -47,7 +47,12 @@ and unset offsets.
 All values in repeating quantifiers must be less than 65536.
 
    
 
    
-The maximum length of a lookbehind assertion is 65535 characters.
+There are two different limits that apply to branches of lookbehind assertions.
+If every branch in such an assertion matches a fixed number of characters,
+the maximum length of any branch is 65535 characters. If any branch matches a
+variable number of characters, then the maximum matching length for every
+branch is limited. The default limit is set at compile time, defaulting to 255,
+but can be changed by the calling program.
 
    
 
    
 There is no limit to the number of parenthesized groups, but there can be no
@@ -91,9 +96,9 @@ Cambridge, England.
 REVISION
 
    
 
    
-Last updated: 26 July 2022
+Last updated: August 2023
 
    
-Copyright © 1997-2022 University of Cambridge.
+Copyright © 1997-2023 University of Cambridge.
 
    
 
    
 Return to the PCRE2 index page.
diff --git a/pcre2/doc/html/pcre2matching.html b/pcre2/doc/html/pcre2matching.html
index ed92caf..3b8b629 100644
--- a/pcre2/doc/html/pcre2matching.html
+++ b/pcre2/doc/html/pcre2matching.html
@@ -27,7 +27,7 @@ please consult the man page, in case the conversion went wrong.
 This document describes the two different algorithms that are available in
 PCRE2 for matching a compiled regular expression against a given subject
 string. The "standard" algorithm is the one provided by the pcre2_match()
-function. This works in the same as as Perl's matching function, and provide a
+function. This works in the same as Perl's matching function, and provide a
 Perl-compatible matching operation. The just-in-time (JIT) optimization that is
 described in the
 pcre2jit
@@ -244,9 +244,9 @@ Cambridge, England.
 
    
 
    REVISION
    
 
    
-Last updated: 28 August 2021
+Last updated: 19 January 2024
 
    
-Copyright © 1997-2021 University of Cambridge.
+Copyright © 1997-2024 University of Cambridge.
 
    
 
    
 Return to the PCRE2 index page.
diff --git a/pcre2/doc/html/pcre2partial.html b/pcre2/doc/html/pcre2partial.html
index bb73b1d..64116c4 100644
--- a/pcre2/doc/html/pcre2partial.html
+++ b/pcre2/doc/html/pcre2partial.html
@@ -392,7 +392,7 @@ can then try a new match starting at offset n+1 in the first buffer.
 
    
 Philip Hazel
 
    
-University Computing Service
+Retired from University Computing Service
 
    
 Cambridge, England.
 
    
diff --git a/pcre2/doc/html/pcre2pattern.html b/pcre2/doc/html/pcre2pattern.html
index 2c24301..cf50c1a 100644
--- a/pcre2/doc/html/pcre2pattern.html
+++ b/pcre2/doc/html/pcre2pattern.html
@@ -116,6 +116,9 @@ such as \d and \w to use Unicode properties to determine character types,
 instead of recognizing only characters with codes less than 256 via a lookup
 table. If also causes upper/lower casing operations to use Unicode properties
 for characters with code points greater than 127, even when UTF is not set.
+These behaviours can be changed within the pattern; see the section entitled
+"Internal Option Setting"
+below.
 
    
 
    
 Some applications that allow their users to supply patterns may wish to
@@ -293,7 +296,9 @@ caseless matching is specified (the PCRE2_CASELESS option or (?i) within the
 pattern), letters are matched independently of case. Note that there are two
 ASCII characters, K and S, that, in addition to their lower case ASCII
 equivalents, are case-equivalent with Unicode U+212A (Kelvin sign) and U+017F
-(long S) respectively when either PCRE2_UTF or PCRE2_UCP is set.
+(long S) respectively when either PCRE2_UTF or PCRE2_UCP is set, unless the
+PCRE2_EXTRA_CASELESS_RESTRICT option is in force (either passed to
+pcre2_compile() or set by (?r) within the pattern).
 
    
 
    
 The power of regular expressions comes from the ability to include wild cards,
@@ -318,8 +323,18 @@ are as follows:
   *      0 or more quantifier
   +      1 or more quantifier; also "possessive quantifier"
   ?      0 or 1 quantifier; also quantifier minimizer
-  {      start min/max quantifier
+  {      potential start of min/max quantifier
 
    
+Brace characters { and } are also used to enclose data for constructions such
+as \g{2} or \k{name}. In almost all uses of braces, space and/or horizontal
+tab characters that follow { or precede } are allowed and are ignored. In the
+case of quantifiers, they may also appear before or after the comma. The
+exception to this is \u{...} which is an ECMAScript compatibility feature
+that is recognized only when the PCRE2_EXTRA_ALT_BSUX option is set. ECMAScript
+does not ignore such white space; it causes the item to be interpreted as
+literal.
+
    
+
    
 Part of a pattern that is in square brackets is called a "character class". In
 a character class the only metacharacters are:
 
    @@ -330,11 +345,11 @@ a character class the only metacharacters are:
   ]      terminates the character class
 
    
 If a pattern is compiled with the PCRE2_EXTENDED option, most white space in
-the pattern, other than in a character class, and characters between a #
-outside a character class and the next newline, inclusive, are ignored. An
-escaping backslash can be used to include a white space or a # character as
-part of the pattern. If the PCRE2_EXTENDED_MORE option is set, the same
-applies, but in addition unescaped space and horizontal tab characters are
+the pattern, other than in a character class, within a \Q...\E sequence, or
+between a # outside a character class and the next newline, inclusive, are
+ignored. An escaping backslash can be used to include a white space or a #
+character as part of the pattern. If the PCRE2_EXTENDED_MORE option is set, the
+same applies, but in addition unescaped space and horizontal tab characters are
 ignored inside a character class. Note: only these two characters are ignored,
 not the full set of pattern white space characters that are ignored outside a
 character class. Option settings can be changed within a pattern; see the
@@ -366,12 +381,14 @@ are treated as literals.
 
    
 
    
 If you want to treat all characters in a sequence as literals, you can do so by
-putting them between \Q and \E. This is different from Perl in that $ and @
-are handled as literals in \Q...\E sequences in PCRE2, whereas in Perl, $ and
-@ cause variable interpolation. Also, Perl does "double-quotish backslash
-interpolation" on any backslashes between \Q and \E which, its documentation
-says, "may lead to confusing results". PCRE2 treats a backslash between \Q and
-\E just like any other character. Note the following examples:
+putting them between \Q and \E. Note that this includes white space even when
+the PCRE2_EXTENDED option is set so that most other white space is ignored. The
+behaviour is different from Perl in that $ and @ are handled as literals in
+\Q...\E sequences in PCRE2, whereas in Perl, $ and @ cause variable
+interpolation. Also, Perl does "double-quotish backslash interpolation" on any
+backslashes between \Q and \E which, its documentation says, "may lead to
+confusing results". PCRE2 treats a backslash between \Q and \E just like any
+other character. Note the following examples:
 
       Pattern            PCRE2 matches   Perl matches
 
@@ -385,8 +402,8 @@ The \Q...\E sequence is recognized both inside and outside character classes.
 An isolated \E that is not preceded by \Q is ignored. If \Q is not followed
 by \E later in the pattern, the literal interpretation continues to the end of
 the pattern (that is, \E is assumed at the end). If the isolated \Q is inside
-a character class, this causes an error, because the character class is not
-terminated by a closing square bracket.
+a character class, this causes an error, because the character class is then
+not terminated by a closing square bracket.
 
    
 
    
 Non-printing characters
@@ -400,7 +417,7 @@ instead of the binary character it represents. In an ASCII or Unicode
 environment, these escapes are as follows:
 
       \a          alarm, that is, the BEL character (hex 07)
-  \cx         "control-x", where x is any printable ASCII character
+  \cx         "control-x", where x is a non-control ASCII character
   \e          escape (hex 1B)
   \f          form feed (hex 0C)
   \n          linefeed (hex 0A)
@@ -437,8 +454,9 @@ interpreted as a literal "u" character.
 
    
 PCRE2_EXTRA_ALT_BSUX has the same effect as PCRE2_ALT_BSUX and, in addition,
 \u{hhh..} is recognized as the character specified by hexadecimal code point.
-There may be any number of hexadecimal digits. This syntax is from ECMAScript
-6.
+There may be any number of hexadecimal digits, but unlike other places that
+also use curly brackets, spaces are not allowed and would result in the string
+being interpreted as a literal. This syntax is from ECMAScript 6.
 
    
 
    
 The \N{U+hhh..} escape sequence is recognized only when PCRE2 is operating in
@@ -454,12 +472,13 @@ pattern is converted to \n so that it matches a LF (linefeed) instead of a CR
 (carriage return) character.
 
    
 
    
-The precise effect of \cx on ASCII characters is as follows: if x is a lower
-case letter, it is converted to upper case. Then bit 6 of the character (hex
-40) is inverted. Thus \cA to \cZ become hex 01 to hex 1A (A is 41, Z is 5A),
-but \c{ becomes hex 3B ({ is 7B), and \c; becomes hex 7B (; is 3B). If the
-code unit following \c has a value less than 32 or greater than 126, a
-compile-time error occurs.
+An error occurs if \c is not followed by a character whose ASCII code point
+is in the range 32 to 126. The precise effect of \cx is as follows: if x is a
+lower case letter, it is converted to upper case. Then bit 6 of the character
+(hex 40) is inverted. Thus \cA to \cZ become hex 01 to hex 1A (A is 41, Z is
+5A), but \c{ becomes hex 3B ({ is 7B), and \c; becomes hex 7B (; is 3B). If
+the code unit following \c has a code point less than 32 or greater than 126,
+a compile-time error occurs.
 
    
 
    
 When PCRE2 is compiled in EBCDIC mode, \N{U+hhh..} is not supported. \a, \e,
@@ -501,8 +520,8 @@ to be unambiguously specified.
 
    
 
    
 For greater clarity and unambiguity, it is best to avoid following \ by a
-digit greater than zero. Instead, use \o{} or \x{} to specify numerical
-character code points, and \g{} to specify backreferences. The following
+digit greater than zero. Instead, use \o{...} or \x{...} to specify numerical
+character code points, and \g{...} to specify backreferences. The following
 paragraphs describe the old, ambiguous syntax.
 
    
 
    
@@ -673,15 +692,27 @@ determine character types, as follows:
 
       \d  any character that matches \p{Nd} (decimal digit)
   \s  any character that matches \p{Z} or \h or \v
-  \w  any character that matches \p{L} or \p{N}, plus underscore
+  \w  any character that matches \p{L}, \p{N}, \p{Mn}, or \p{Pc}
 
    
+The addition of \p{Mn} (non-spacing mark) and the replacement of an explicit
+test for underscore with a test for \p{Pc} (connector punctuation) happened in
+PCRE2 release 10.43. This brings PCRE2 into line with Perl.
+
    
+
    
 The upper case escapes match the inverse sets of characters. Note that \d
 matches only decimal digits, whereas \w matches any Unicode digit, as well as
-any Unicode letter, and underscore. Note also that PCRE2_UCP affects \b, and
+other character categories. Note also that PCRE2_UCP affects \b, and
 \B because they are defined in terms of \w and \W. Matching these sequences
 is noticeably slower when PCRE2_UCP is set.
 
    
 
    
+The effect of PCRE2_UCP on any one of these escape sequences can be negated by
+the options PCRE2_EXTRA_ASCII_BSD, PCRE2_EXTRA_ASCII_BSS, and
+PCRE2_EXTRA_ASCII_BSW, respectively. These options can be set and reset within
+a pattern by means of an internal option setting
+(see below).
+
    
+
    
 The sequences \h, \H, \v, and \V, in contrast to the other sequences, which
 match only ASCII characters by default, always match a specific list of code
 points, whether or not PCRE2_UCP is set. The horizontal space characters are:
@@ -1003,17 +1034,19 @@ L, V, LV, or LVT character; an LV or V character may be followed by a V or T
 character; an LVT or T character may be followed only by a T character.
 
    
 
    
-4. Do not end before extending characters or spacing marks or the "zero-width
-joiner" character. Characters with the "mark" property always have the
+4. Do not end before extending characters or spacing marks or the zero-width
+joiner (ZWJ) character. Characters with the "mark" property always have the
 "extend" grapheme breaking property.
 
    
 
    
 5. Do not end after prepend characters.
 
    
 
    
-6. Do not break within emoji modifier sequences or emoji zwj sequences. That
-is, do not break between characters with the Extended_Pictographic property.
-Extend and ZWJ characters are allowed between the characters.
+6. Do not end within emoji modifier sequences or emoji ZWJ (zero-width
+joiner) sequences. An emoji ZWJ sequence consists of a character with the
+Extended_Pictographic property, optionally followed by one or more characters
+with the Extend property, followed by the ZWJ character, followed by another
+Extended_Pictographic character.
 
    
 
    
 7. Do not break within emoji flag sequences. That is, do not break between
@@ -1043,7 +1076,8 @@ property. Xps matches the characters tab, linefeed, vertical tab, form feed, or
 carriage return, and any other character that has the Z (separator) property.
 Xsp is the same as Xps; in PCRE1 it used to exclude vertical tab, for Perl
 compatibility, but Perl changed. Xwd matches the same characters as Xan, plus
-underscore.
+those that match Mn (non-spacing mark) or Pc (connector punctuation, which
+includes underscore).
 
    
 
    
 There is another non-standard property, Xuc, which matches any character that
@@ -1073,10 +1107,10 @@ with anchoring in any way. The pattern:
 matches only when the subject begins with "foobar" (in single line mode),
 though it again reports the matched string as "bar". This feature is similar to
 a lookbehind assertion
-(described below).
-However, in this case, the part of the subject before the real match does not
-have to be of fixed length, as lookbehind assertions do. The use of \K does
-not interfere with the setting of
+(described below),
+but the part of the pattern that precedes \K is not constrained to match a
+limited number of characters, as is required for a lookbehind assertion. The
+use of \K does not interfere with the setting of
 captured substrings.
 For example, when the pattern
 
    @@ -1254,7 +1288,7 @@ above).
 Dot never matches a single line-ending character. When the two-character
 sequence CRLF is the only line ending, dot does not match CR if it is
 immediately followed by LF, but otherwise it matches all characters (including
-isolated CRs and LFs). When ANYCRLF is selected for line endings, no occurences
+isolated CRs and LFs). When ANYCRLF is selected for line endings, no occurrences
 of CR of LF match dot. When all Unicode line endings are being recognized, dot
 does not match CR or LF or any of the other line ending characters.
 
    
@@ -1404,7 +1438,7 @@ b to d, a hyphen character, or z.
 
    
 
    
 Perl treats a hyphen as a literal if it appears before or after a POSIX class
-(see below) or before or after a character type escape such as as \d or \H.
+(see below) or before or after a character type escape such as \d or \H.
 However, unless the hyphen is the last character in the class, Perl outputs a
 warning in its warning mode, as this is most likely a user error. As PCRE2 has
 no facility for warning, an error is given in these cases.
@@ -1489,7 +1523,7 @@ are:
 The default "space" characters are HT (9), LF (10), VT (11), FF (12), CR (13),
 and space (32). If locale-specific matching is taking place, the list of space
 characters may be different; there may be fewer or more of them. "Space" and
-\s match the same set of characters.
+\s match the same set of characters, as do "word" and \w.
 
    
 
    
 The name "word" is a Perl extension, and "blank" is a GNU extension from Perl
@@ -1505,10 +1539,10 @@ supported, and an error is given if they are encountered.
 
    
 By default, characters with values greater than 127 do not match any of the
 POSIX character classes, although this may be different for characters in the
-range 128-255 when locale-specific matching is happening. However, if the
-PCRE2_UCP option is passed to pcre2_compile(), some of the classes are
-changed so that Unicode character properties are used. This is achieved by
-replacing certain POSIX classes with other sequences, as follows:
+range 128-255 when locale-specific matching is happening. However, in UCP mode,
+unless certain options are set (see below), some of the classes are changed so
+that Unicode character properties are used. This is achieved by replacing
+POSIX classes with other sequences, as follows:
 
       [:alnum:]  becomes  \p{Xan}
   [:alpha:]  becomes  \p{L}
@@ -1520,7 +1554,7 @@ replacing certain POSIX classes with other sequences, as follows:
   [:upper:]  becomes  \p{Lu}
   [:word:]   becomes  \p{Xwd}
 
    
-Negated versions, such as [:^alpha:] use \P instead of \p. Three other POSIX
+Negated versions, such as [:^alpha:] use \P instead of \p. Four other POSIX
 classes are handled specially in UCP mode:
 
    
 
    
@@ -1547,8 +1581,22 @@ plus those characters with code points less than 256 that have the S (Symbol)
 property.
 
    
 
    
-The other POSIX classes are unchanged, and match only characters with code
-points less than 256.
+[:xdigit:]
+In addition to the ASCII hexadecimal digits, this also matches the "fullwidth"
+versions of those characters, whose Unicode code points start at U+FF10. This
+is a change that was made in PCRE release 10.43 for Perl compatibility.
+
    
+
    
+The other POSIX classes are unchanged by PCRE2_UCP, and match only characters
+with code points less than 256.
+
    
+
    
+There are two options that can be used to restrict the POSIX classes to ASCII
+characters when PCRE2_UCP is set. The option PCRE2_EXTRA_ASCII_DIGIT affects
+just [:digit:] and [:xdigit:]. Within a pattern, this can be set and unset by
+(?aT) and (?-aT). The PCRE2_EXTRA_ASCII_POSIX option disables UCP processing
+for all POSIX classes, including [:digit:] and [:xdigit:]. Within a pattern,
+(?aP) and (?-aP) set and unset both these options for consistency.
 
    
 
    COMPATIBILITY FEATURE FOR WORD BOUNDARIES
    
 
    
@@ -1567,7 +1615,9 @@ at the start and the end of a word (see
 "Simple assertions"
 above), and in a Perl-style pattern the preceding or following character
 normally shows which is wanted, without the need for the assertions that are
-used above in order to give exactly the POSIX behaviour.
+used above in order to give exactly the POSIX behaviour. Note also that the
+PCRE2_UCP option changes the meaning of \w (and therefore \b) by default, so
+it also affects these POSIX sequences.
 
    
 
    VERTICAL BAR
    
 
    
@@ -1586,10 +1636,9 @@ alternative in the group.
 
    
 
    INTERNAL OPTION SETTING
    
 
    
-The settings of the PCRE2_CASELESS, PCRE2_MULTILINE, PCRE2_DOTALL,
-PCRE2_EXTENDED, PCRE2_EXTENDED_MORE, and PCRE2_NO_AUTO_CAPTURE options can be
-changed from within the pattern by a sequence of letters enclosed between "(?"
-and ")". These options are Perl-compatible, and are described in detail in the
+The settings of several options can be changed within a pattern by a sequence
+of letters enclosed between "(?" and ")". The following are Perl-compatible,
+and are described in detail in the
 pcre2api
 documentation. The option letters are:
 
    @@ -1602,8 +1651,8 @@ documentation. The option letters are:
 
    
 For example, (?im) sets caseless, multiline matching. It is also possible to
 unset these options by preceding the relevant letters with a hyphen, for
-example (?-im). The two "extended" options are not independent; unsetting either
-one cancels the effects of both of them.
+example (?-im). The two "extended" options are not independent; unsetting
+either one cancels the effects of both of them.
 
    
 
    
 A combined setting and unsetting such as (?im-sx), which sets PCRE2_CASELESS
@@ -1614,27 +1663,44 @@ setting "(?)" is allowed. Needless to say, it has no effect.
 
    
 
    
 If the first character following (? is a circumflex, it causes all of the above
-options to be unset. Thus, (?^) is equivalent to (?-imnsx). Letters may follow
-the circumflex to cause some options to be re-instated, but a hyphen may not
-appear.
+options to be unset. Letters may follow the circumflex to cause some options to
+be re-instated, but a hyphen may not appear.
 
    
 
    
-The PCRE2-specific options PCRE2_DUPNAMES and PCRE2_UNGREEDY can be changed in
-the same way as the Perl-compatible options by using the characters J and U
-respectively. However, these are not unset by (?^).
+Some PCRE2-specific options can be changed by the same mechanism using these
+pairs or individual letters:
+
    +  aD for PCRE2_EXTRA_ASCII_BSD
+  aS for PCRE2_EXTRA_ASCII_BSS
+  aW for PCRE2_EXTRA_ASCII_BSW
+  aP for PCRE2_EXTRA_ASCII_POSIX and PCRE2_EXTRA_ASCII_DIGIT
+  aT for PCRE2_EXTRA_ASCII_DIGIT
+  r  for PCRE2_EXTRA_CASELESS_RESTRICT
+  J  for PCRE2_DUPNAMES
+  U  for PCRE2_UNGREEDY
+
    
+However, except for 'r', these are not unset by (?^), which is equivalent to
+(?-imnrsx). If 'a' is not followed by any of the upper case letters shown
+above, it sets (or unsets) all the ASCII options.
 
    
 
    
-When one of these option changes occurs at top level (that is, not inside
-group parentheses), the change applies to the remainder of the pattern
-that follows. An option change within a group (see below for a description
-of groups) affects only that part of the group that follows it, so
+PCRE2_EXTRA_ASCII_DIGIT has no additional effect when PCRE2_EXTRA_ASCII_POSIX
+is set, but including it in (?aP) means that (?-aP) suppresses all ASCII
+restrictions for POSIX classes.
+
    
+
    
+When one of these option changes occurs at top level (that is, not inside group
+parentheses), the change applies until a subsequent change, or the end of the
+pattern. An option change within a group (see below for a description of
+groups) affects only that part of the group that follows it. At the end of the
+group these options are reset to the state they were before the group. For
+example,
 
       (a(?i)b)c
 
    
-matches abc and aBc and no other strings (assuming PCRE2_CASELESS is not used).
-By this means, options can be made to have different settings in different
-parts of the pattern. Any changes made in one alternative do carry on
-into subsequent branches within the same group. For example,
+matches abc and aBc and no other strings (assuming PCRE2_CASELESS is not set
+externally). Any changes made in one alternative do carry on into subsequent
+branches within the same group. For example,
 
       (a(?i)b|c)
 
    
@@ -1663,7 +1729,7 @@ Details are given in the section entitled
 above. There are also the (*UTF) and (*UCP) leading sequences that can be used
 to set UTF and Unicode property modes; they are equivalent to setting the
 PCRE2_UTF and PCRE2_UCP options, respectively. However, the application can set
-the PCRE2_NEVER_UTF and PCRE2_NEVER_UCP options, which lock out the use of the
+the PCRE2_NEVER_UTF or PCRE2_NEVER_UCP options, which lock out the use of the
 (*UTF) and (*UCP) sequences.
 
    
 
    GROUPS
    
@@ -1779,7 +1845,7 @@ using the Python syntax. PCRE2 supports both the Perl and the Python syntax.
 
    
 
    
 In PCRE2, a capture group can be named in one of three ways: (?<name>...) or
-(?'name'...) as in Perl, or (?P<name>...) as in Python. Names may be up to 32
+(?'name'...) as in Perl, or (?P<name>...) as in Python. Names may be up to 128
 code units long. When PCRE2_UTF is not set, they may contain only ASCII
 alphanumeric characters and underscores, but must start with a non-digit. When
 PCRE2_UTF is set, the syntax of group names is extended to allow any Unicode
@@ -1890,7 +1956,7 @@ documentation.
 
    
 
    REPETITION
    
 
    
-Repetition is specified by quantifiers, which can follow any of the following
+Repetition is specified by quantifiers, which may follow any one of these
 items:
 
       a literal data character
@@ -1898,16 +1964,17 @@ items:
   the \C escape sequence
   the \R escape sequence
   the \X escape sequence
-  an escape such as \d or \pL that matches a single character
+  any escape sequence that matches a single character
   a character class
   a backreference
   a parenthesized group (including lookaround assertions)
   a subroutine call (recursive or otherwise)
 
    
-The general repetition quantifier specifies a minimum and maximum number of
-permitted matches, by giving the two numbers in curly brackets (braces),
-separated by a comma. The numbers must be less than 65536, and the first must
-be less than or equal to the second. For example,
+If a quantifier does not follow a repeatable item, an error occurs. The
+general repetition quantifier specifies a minimum and maximum number of
+permitted matches by giving two numbers in curly brackets (braces), separated
+by a comma. The numbers must be less than 65536, and the first must be less
+than or equal to the second. For example,
 
       z{2,4}
 
    
@@ -1922,10 +1989,23 @@ matches at least 3 successive vowels, but may match many more, whereas
 
       \d{8}
 
    
-matches exactly 8 digits. An opening curly bracket that appears in a position
-where a quantifier is not allowed, or one that does not match the syntax of a
-quantifier, is taken as a literal character. For example, {,6} is not a
-quantifier, but a literal string of four characters.
+matches exactly 8 digits. If the first number is omitted, the lower limit is
+taken as zero; in this case the upper limit must be present.
+
    +  X{,4} is interpreted as X{0,4}
+
    
+This is a change in behaviour that happened in Perl 5.34.0 and PCRE2 10.43. In
+earlier versions such a sequence was not interpreted as a quantifier. Other
+regular expression engines may behave either way.
+
    
+
    
+If the characters that follow an opening brace do not match the syntax of a
+quantifier, the brace is taken as a literal character. In particular, this
+means that {,} is a literal string of three characters.
+
    
+
    
+Note that not every opening brace is potentially the start of a quantifier
+because braces are used in other items such as \N{U+345} or \k{name}.
 
    
 
    
 In UTF modes, quantifiers apply to characters rather than to individual code
@@ -1966,11 +2046,11 @@ any of the iterations if a subsequent item fails to match.
 
    
 
    
 By default, quantifiers are "greedy", that is, they match as much as possible
-(up to the maximum number of permitted times), without causing the rest of the
-pattern to fail. The classic example of where this gives problems is in trying
-to match comments in C programs. These appear between /* and */ and within the
-comment, individual * and / characters may appear. An attempt to match C
-comments by applying the pattern
+(up to the maximum number of permitted repetitions), without causing the rest
+of the pattern to fail. The classic example of where this gives problems is in
+trying to match comments in C programs. These appear between /* and */ and
+within the comment, individual * and / characters may appear. An attempt to
+match C comments by applying the pattern
 
       /\*.*\*/
 
    
@@ -1985,10 +2065,10 @@ pattern
 
       /\*.*?\*/
 
    
-does the right thing with the C comments. The meaning of the various
-quantifiers is not otherwise changed, just the preferred number of matches.
-Do not confuse this use of question mark with its use as a quantifier in its
-own right. Because it has two uses, it can sometimes appear doubled, as in
+does the right thing with C comments. The meaning of the various quantifiers is
+not otherwise changed, just the preferred number of matches. Do not confuse
+this use of question mark with its use as a quantifier in its own right.
+Because it has two uses, it can sometimes appear doubled, as in
 
       \d??\d
 
    
@@ -2206,16 +2286,24 @@ the reference. A signed number is a relative reference. Consider this example:
 
       (abc(def)ghi)\g{-1}
 
    
-The sequence \g{-1} is a reference to the most recently started capture group
-before \g, that is, is it equivalent to \2 in this example. Similarly,
-\g{-2} would be equivalent to \1. The use of relative references can be
-helpful in long patterns, and also in patterns that are created by joining
-together fragments that contain references within themselves.
+The sequence \g{-1} is a reference to the capture group whose number is one
+less than the number of the next group to be started, so in this example (where
+the next group would be numbered 3) is it equivalent to \2, and \g{-2} would
+be equivalent to \1. Note that if this construct is inside a capture group,
+that group is included in the count, so in this example \g{-2} also refers to
+group 1:
+
    +  (A)(\g{-2}B)
+
    
+The use of relative references can be helpful in long patterns, and also in
+patterns that are created by joining together fragments that contain references
+within themselves.
 
    
 
    
-The sequence \g{+1} is a reference to the next capture group. This kind of
-forward reference can be useful in patterns that repeat. Perl does not support
-the use of + in this way.
+The sequence \g{+1} is a reference to the next capture group that is started
+after this item, and \g{+2} refers to the one after that, and so on. This kind
+of forward reference can be useful in patterns that repeat. Perl does not
+support the use of + in this way.
 
    
 
    
 A backreference matches whatever actually most recently matched the capture
@@ -2237,11 +2325,11 @@ capture group is matched caselessly.
 
    
 
    
 There are several different ways of writing backreferences to named capture
-groups. The .NET syntax \k{name} and the Perl syntax \k<name> or \k'name'
-are supported, as is the Python syntax (?P=name). Perl 5.10's unified
-backreference syntax, in which \g can be used for both numeric and named
-references, is also supported. We could rewrite the above example in any of the
-following ways:
+groups. The .NET syntax is \k{name}, the Python syntax is (?=name), and the
+original Perl syntax is \k<name> or \k'name'. All of these are now supported
+by both Perl and PCRE2. Perl 5.10's unified backreference syntax, in which \g
+can be used for both numeric and named references, is also supported by PCRE2.
+We could rewrite the above example in any of the following ways:
 
       (?<p1>(?i)rah)\s+\k<p1>
   (?'p1'(?i)rah)\s+\k{p1}
@@ -2420,39 +2508,32 @@ negative assertions. For example,
   (?<!foo)bar
 
    
 does find an occurrence of "bar" that is not preceded by "foo". The contents of
-a lookbehind assertion are restricted such that all the strings it matches must
-have a fixed length. However, if there are several top-level alternatives, they
-do not all have to have the same fixed length. Thus
-
    -  (?<=bullock|donkey)
-
    
-is permitted, but
-
    -  (?<!dogs?|cats?)
-
    
-causes an error at compile time. Branches that match different length strings
-are permitted only at the top level of a lookbehind assertion. This is an
-extension compared with Perl, which requires all branches to match the same
-length of string. An assertion such as
+a lookbehind assertion are restricted such that there must be a known maximum
+to the lengths of all the strings it matches. There are two cases:
+
    
+
    
+If every top-level alternative matches a fixed length, for example
 
    -  (?<=ab(c|de))
+  (?<=colour|color)
 
    
-is not permitted, because its single top-level branch can match two different
-lengths, but it is acceptable to PCRE2 if rewritten to use two top-level
-branches:
+there is a limit of 65535 characters to the lengths, which do not have to be
+the same, as this example demonstrates. This is the only kind of lookbehind
+supported by PCRE2 versions earlier than 10.43 and by the alternative matching
+function pcre2_dfa_match().
+
    
+
    
+In PCRE2 10.43 and later, pcre2_match() supports lookbehind assertions in
+which one or more top-level alternatives can match more than one string length,
+for example
 
    -  (?<=abc|abde)
+  (?<=colou?r)
 
    
-In some cases, the escape sequence \K
+The maximum matching length for any branch of the lookbehind is limited to a
+value set by the calling program (default 255 characters). Unlimited repetition
+(for example \d*) is not supported. In some cases, the escape sequence \K
 (see above)
-can be used instead of a lookbehind assertion to get round the fixed-length
-restriction.
-
    
-
    
-The implementation of lookbehind assertions is, for each alternative, to
-temporarily move the current position back by the fixed length and then try to
-match. If there are insufficient characters before the current position, the
-assertion fails.
+can be used instead of a lookbehind assertion at the start of a pattern to get
+round the length limit restriction.
 
    
 
    
 In UTF-8 and UTF-16 modes, PCRE2 does not allow the \C escape (which matches a
@@ -2464,27 +2545,27 @@ permitted in lookbehinds.
 
    
 "Subroutine"
 calls (see below) such as (?2) or (?&X) are permitted in lookbehinds, as long
-as the called capture group matches a fixed-length string. However,
+as the called capture group matches a limited-length string. However,
 recursion,
 that is, a "subroutine" call into a group that is already active,
 is not supported.
 
    
 
    
-Perl does not support backreferences in lookbehinds. PCRE2 does support them,
-but only if certain conditions are met. The PCRE2_MATCH_UNSET_BACKREF option
-must not be set, there must be no use of (?| in the pattern (it creates
-duplicate group numbers), and if the backreference is by name, the name
-must be unique. Of course, the referenced group must itself match a fixed
-length substring. The following pattern matches words containing at least two
-characters that begin and end with the same character:
+PCRE2 supports backreferences in lookbehinds, but only if certain conditions
+are met. The PCRE2_MATCH_UNSET_BACKREF option must not be set, there must be no
+use of (?| in the pattern (it creates duplicate group numbers), and if the
+backreference is by name, the name must be unique. Of course, the referenced
+group must itself match a limited length substring. The following pattern
+matches words containing at least two characters that begin and end with the
+same character:
 
        \b(\w)\w++(?<=\1)
 
    
 
    
 
    
 Possessive quantifiers can be used in conjunction with lookbehind assertions to
-specify efficient matching of fixed-length strings at the end of subject
-strings. Consider a simple pattern such as
+specify efficient matching at the end of subject strings. Consider a simple
+pattern such as
 
       abcd$
 
    
@@ -2545,11 +2626,10 @@ characters that are not "999".
 
    
 
    NON-ATOMIC ASSERTIONS
    
 
    
-The traditional Perl-compatible lookaround assertions are atomic. That is, if
-an assertion is true, but there is a subsequent matching failure, there is no
-backtracking into the assertion. However, there are some cases where non-atomic
-positive assertions can be useful. PCRE2 provides these using the following
-syntax:
+Traditional lookaround assertions are atomic. That is, if an assertion is true,
+but there is a subsequent matching failure, there is no backtracking into the
+assertion. However, there are some cases where non-atomic positive assertions
+can be useful. PCRE2 provides these using the following syntax:
 
       (*non_atomic_positive_lookahead:  or (*napla: or (?*
   (*non_atomic_positive_lookbehind: or (*naplb: or (?<*
@@ -2573,7 +2653,7 @@ The current matching point is then reset to the start of the subject, and the
 rest of the pattern match checks for two occurrences of the captured word,
 using an ungreedy .*? to scan from the left. If this succeeds, we are done, but
 if the last word in the string does not occur twice, this part of the pattern
-fails. If a traditional atomic lookhead (?= or (*pla: had been used, the
+fails. If a traditional atomic lookahead (?= or (*pla: had been used, the
 assertion could not be re-entered, and the whole match would fail. The pattern
 would succeed only if the very last word in the subject was found twice.
 
    
@@ -2700,13 +2780,14 @@ If the text between the parentheses consists of a sequence of digits, the
 condition is true if a capture group of that number has previously matched. If
 there is more than one capture group with the same number (see the earlier
 section about duplicate group numbers),
-the condition is true if any of them have matched. An alternative notation is
-to precede the digits with a plus or minus sign. In this case, the group number
-is relative rather than absolute. The most recently opened capture group can be
-referenced by (?(-1), the next most recent by (?(-2), and so on. Inside loops
-it can also make sense to refer to subsequent groups. The next capture group
-can be referenced as (?(+1), and so on. (The value zero in any of these forms
-is not used; it provokes a compile-time error.)
+the condition is true if any of them have matched. An alternative notation,
+which is a PCRE2 extension, not supported by Perl, is to precede the digits
+with a plus or minus sign. In this case, the group number is relative rather
+than absolute. The most recently opened capture group (which could be enclosing
+this condition) can be referenced by (?(-1), the next most recent by (?(-2),
+and so on. Inside loops it can also make sense to refer to subsequent groups.
+The next capture group to be opened can be referenced as (?(+1), and so on. The
+value zero in any of these forms is not used; it provokes a compile-time error.
 
    
 
    
 Consider the following pattern, which contains non-significant white space to
@@ -2843,7 +2924,6 @@ Assertion conditions
 If the condition is not in any of the above formats, it must be a parenthesized
 assertion. This may be a positive or negative lookahead or lookbehind
 assertion. However, it must be a traditional atomic assertion, not one of the
-PCRE2-specific
 non-atomic assertions.
 
    
 
    
@@ -3650,7 +3730,7 @@ If A matches but B fails, the backtrack to (*COMMIT) causes the entire match to
 fail. However, if A and B match, but C fails, the backtrack to (*THEN) causes
 the next alternative (ABD) to be tried. This behaviour is consistent, but is
 not always the same as Perl's. It means that if two or more backtracking verbs
-appear in succession, all the the last of them has no effect. Consider this
+appear in succession, all but the last of them has no effect. Consider this
 example:
 
       ...(*COMMIT)(*PRUNE)...
@@ -3766,9 +3846,9 @@ Cambridge, England.
 
    
 
    REVISION
    
 
    
-Last updated: 12 January 2022
+Last updated: 04 June 2024
 
    
-Copyright © 1997-2022 University of Cambridge.
+Copyright © 1997-2024 University of Cambridge.
 
    
 
    
 Return to the PCRE2 index page.
diff --git a/pcre2/doc/html/pcre2posix.html b/pcre2/doc/html/pcre2posix.html
index 0ad6f9e..6e7abd9 100644
--- a/pcre2/doc/html/pcre2posix.html
+++ b/pcre2/doc/html/pcre2posix.html
@@ -53,9 +53,14 @@ documentation for a description of PCRE2's native API, which contains much
 additional functionality.
 
    
 
    
-The functions described here are wrapper functions that ultimately call the
-PCRE2 native API. Their prototypes are defined in the pcre2posix.h header
-file, and they all have unique names starting with pcre2_. However, the
+IMPORTANT NOTE: The functions described here are NOT thread-safe, and
+should not be used in multi-threaded applications. They are also limited to
+processing subjects that are not bigger than 2GB. Use the native API instead.
+
    
+
    
+These functions are wrapper functions that ultimately call the PCRE2 native
+API. Their prototypes are defined in the pcre2posix.h header file, and
+they all have unique names starting with pcre2_. However, the
 pcre2posix.h header also contains macro definitions that convert the
 standard POSIX names such regcomp() into pcre2_regcomp() etc. This
 means that a program can use the usual POSIX names without running the risk of
@@ -68,7 +73,13 @@ application. Because the POSIX functions call the native ones, it is also
 necessary to add -lpcre2-8.
 
    
 
    
-Although they were not defined as protypes in pcre2posix.h, releases
+On Windows systems, if you are linking to a DLL version of the library, it is
+recommended that PCRE2POSIX_SHARED is defined before including the
+pcre2posix.h header, as it will allow for a more efficient way to
+invoke the functions by adding the __declspec(dllimport) decorator.
+
    
+
    
+Although they were not defined as prototypes in pcre2posix.h, releases
 10.33 to 10.36 of the library contained functions with the POSIX names
 regcomp() etc. These simply passed their arguments to the PCRE2
 functions. These functions were provided for backwards compatibility with
@@ -87,6 +98,11 @@ captured substrings. It also defines some constants whose names start with
 
    
 
    USING THE POSIX FUNCTIONS
    
 
    
+Note that these functions are just POSIX-style wrappers for PCRE2's native API.
+They do not give POSIX regular expression behaviour, and they are not
+thread-safe or even POSIX compatible.
+
    
+
    
 Those POSIX option bits that can reasonably be mapped to PCRE2 native options
 have been implemented. In addition, the option REG_EXTENDED is defined with the
 value zero. This has no effect, but since programs that are written to the
@@ -117,8 +133,10 @@ The function pcre2_regcomp() is called to compile a pattern into an
 internal form. By default, the pattern is a C string terminated by a binary
 zero (but see REG_PEND below). The preg argument is a pointer to a
 regex_t structure that is used as a base for storing information about
-the compiled regular expression. (It is also used for input when REG_PEND is
-set.)
+the compiled regular expression. It is also used for input when REG_PEND is
+set. The regex_t structure used by pcre2_regcomp() is defined in
+pcre2posix.h and is not the same as the structure used by other libraries
+that provide POSIX-style matching.
 
    
 
    
 The argument cflags is either zero, or contains one or more of the bits
@@ -171,7 +189,7 @@ caution in software intended to be portable to other systems.
 
    
 The PCRE2_UCP option is set when the regular expression is passed for
 compilation to the native function. This causes PCRE2 to use Unicode properties
-when matchine \d, \w, etc., instead of just recognizing ASCII values. Note
+when matching \d, \w, etc., instead of just recognizing ASCII values. Note
 that REG_UCP is not part of the POSIX standard.
 
       REG_UNGREEDY
@@ -189,7 +207,7 @@ is not part of the POSIX standard.
 
    
 
    
 In the absence of these flags, no options are passed to the native function.
-This means the the regex is compiled with PCRE2 default semantics. In
+This means that the regex is compiled with PCRE2 default semantics. In
 particular, the way it handles newline characters in the subject string is the
 Perl way, not the POSIX way. Note that setting PCRE2_MULTILINE has only
 some of the effects specified for REG_NEWLINE. It does not affect the way
@@ -315,6 +333,11 @@ the capturing subpatterns of the regular expression. Unused entries in the
 array have both structure members set to -1.
 
    
 
    
+regmatch_t as well as the regoff_t typedef it uses are defined in
+pcre2posix.h and are not warranted to have the same size or layout as other
+similarly named types from other libraries that provide POSIX-style matching.
+
    
+
    
 A successful match yields a zero return; various error codes are defined in the
 header file, of which REG_NOMATCH is the "expected" failure code.
 
    
@@ -340,16 +363,16 @@ expression.
 
    
 Philip Hazel
 
    
-University Computing Service
+Retired from University Computing Service
 
    
 Cambridge, England.
 
    
 
    
 
    REVISION
    
 
    
-Last updated: 26 April 2021
+Last updated: 19 January 2024
 
    
-Copyright © 1997-2021 University of Cambridge.
+Copyright © 1997-2024 University of Cambridge.
 
    
 
    
 Return to the PCRE2 index page.
diff --git a/pcre2/doc/html/pcre2sample.html b/pcre2/doc/html/pcre2sample.html
index 2b36f1f..345df03 100644
--- a/pcre2/doc/html/pcre2sample.html
+++ b/pcre2/doc/html/pcre2sample.html
@@ -92,7 +92,7 @@ AUTHOR
 
    
 Philip Hazel
 
    
-University Computing Service
+Retired from University Computing Service
 
    
 Cambridge, England.
 
    
diff --git a/pcre2/doc/html/pcre2serialize.html b/pcre2/doc/html/pcre2serialize.html
index a492305..19418a8 100644
--- a/pcre2/doc/html/pcre2serialize.html
+++ b/pcre2/doc/html/pcre2serialize.html
@@ -88,7 +88,7 @@ being a pointer to a vector of pointers to compiled patterns, and the length of
 the vector. The third and fourth arguments point to variables which are set to
 point to the created byte stream and its length, respectively. The final
 argument is a pointer to a general context, which can be used to specify custom
-memory mangagement functions. If this argument is NULL, malloc() is used
+memory management functions. If this argument is NULL, malloc() is used
 to obtain memory for the byte stream. The yield of the function is the number
 of serialized patterns, or one of the following negative error codes:
 
    @@ -150,7 +150,7 @@ the compiled patterns in new memory blocks, setting pointers to them in a
 vector. The first two arguments are a pointer to a suitable vector and its
 length, and the third argument points to a byte stream. The final argument is a
 pointer to a general context, which can be used to specify custom memory
-mangagement functions for the decoded patterns. If this argument is NULL,
+management functions for the decoded patterns. If this argument is NULL,
 malloc() and free() are used. After deserialization, the byte
 stream is no longer needed and can be discarded.
 
    @@ -196,7 +196,7 @@ save/restore cycle. You can, however, process a restored pattern with
 
    
 Philip Hazel
 
    
-University Computing Service
+Retired from University Computing Service
 
    
 Cambridge, England.
 
    
diff --git a/pcre2/doc/html/pcre2syntax.html b/pcre2/doc/html/pcre2syntax.html
index 8364c52..1c0ccb0 100644
--- a/pcre2/doc/html/pcre2syntax.html
+++ b/pcre2/doc/html/pcre2syntax.html
@@ -15,35 +15,36 @@ please consult the man page, in case the conversion went wrong.
 
    
 
    PCRE2 REGULAR EXPRESSION SYNTAX SUMMARY
    
 
    
@@ -57,15 +58,27 @@ documentation. This document contains a quick-reference summary of the syntax.
 
       \x         where x is non-alphanumeric is a literal x
   \Q...\E    treat enclosed characters as literal
-
    
+
    
+Note that white space inside \Q...\E is always treated as literal, even if
+PCRE2_EXTENDED is set, causing most other white space to be ignored.
+
    
+
    BRACED ITEMS
    
+
    
+With one exception, wherever brace characters { and } are required to enclose
+data for constructions such as \g{2} or \k{name}, space and/or horizontal tab
+characters that follow { or precede } are allowed and are ignored. In the case
+of quantifiers, they may also appear before or after the comma. The exception
+is \u{...} which is not Perl-compatible and is recognized only when
+PCRE2_EXTRA_ALT_BSUX is set. This is an ECMAScript compatibility feature, and
+follows ECMAScript's behaviour.
 
    
-
    ESCAPED CHARACTERS
    
+
    ESCAPED CHARACTERS
    
 
    
 This table applies to ASCII and Unicode environments. An unrecognized escape
 sequence causes an error.
 
       \a         alarm, that is, the BEL character (hex 07)
-  \cx        "control-x", where x is any ASCII printing character
+  \cx        "control-x", where x is a non-control ASCII character
   \e         escape (hex 1B)
   \f         form feed (hex 0C)
   \n         newline (hex 0A)
@@ -103,7 +116,7 @@ also given. \N{U+hh..} is synonymous with \x{hh..} in PCRE2 but is not
 supported in EBCDIC environments. Note that \N not followed by an opening
 curly bracket has a different meaning (see below).
 
    
-
    CHARACTER TYPES
    
+
    CHARACTER TYPES
    
 
    
 
       .          any character except newline;
@@ -136,14 +149,15 @@ or in the 16-bit and 32-bit libraries. However, if locale-specific matching is
 happening, \s and \w may also match characters with code points in the range
 128-255. If the PCRE2_UCP option is set, the behaviour of these escape
 sequences is changed to use Unicode properties and they match many more
-characters.
+characters, but there are some option settings that can restrict individual
+sequences to matching only ASCII characters.
 
    
 
    
 Property descriptions in \p and \P are matched caselessly; hyphens,
 underscores, and white space are ignored, in accordance with Unicode's "loose
 matching" rules.
 
    
-
    GENERAL CATEGORY PROPERTIES FOR \p and \P
    
+
    GENERAL CATEGORY PROPERTIES FOR \p and \P
    
 
    
 
       C          Other
@@ -193,20 +207,20 @@ matching" rules.
   Zs         Space separator
 
    
 
    
-
    PCRE2 SPECIAL CATEGORY PROPERTIES FOR \p and \P
    
+
    PCRE2 SPECIAL CATEGORY PROPERTIES FOR \p and \P
    
 
    
 
       Xan        Alphanumeric: union of properties L and N
   Xps        POSIX space: property Z or tab, NL, VT, FF, CR
   Xsp        Perl space: property Z or tab, NL, VT, FF, CR
-  Xuc        Univerally-named character: one that can be
+  Xuc        Universally-named character: one that can be
                represented by a Universal Character Name
   Xwd        Perl word: property Xan or underscore
 
    
 Perl and POSIX space are now the same. Perl added VT to its space character set
 at release 5.18.
 
    
-
    BINARY PROPERTIES FOR \p AND \P
    
+
    BINARY PROPERTIES FOR \p AND \P
    
 
    
 Unicode defines a number of binary properties, that is, properties whose only
 values are true or false. You can obtain a list of those that are recognized by
@@ -215,7 +229,7 @@ values are true or false. You can obtain a list of those that are recognized by
   pcre2test -LP
 
    
 
    
-
    SCRIPT MATCHING WITH \p AND \P
    
+
    SCRIPT MATCHING WITH \p AND \P
    
 
    
 Many script names and their 4-letter abbreviations are recognized in
 \p{sc:...} or \p{scx:...} items, or on their own with \p (and also \P of
@@ -224,7 +238,7 @@ course). You can obtain a list of these scripts by running this command:
   pcre2test -LS
 
    
 
    
-
    THE BIDI_CLASS PROPERTY FOR \p AND \P
    
+
    THE BIDI_CLASS PROPERTY FOR \p AND \P
    
 
    
 
       \p{Bidi_Class:<class>}   matches a character with the given class
@@ -257,7 +271,7 @@ The recognized classes are:
   WS          which space
 
    
 
    
-
    CHARACTER CLASSES
    
+
    CHARACTER CLASSES
    
 
    
 
       [...]       positive character class
@@ -285,7 +299,7 @@ In PCRE2, POSIX character set names recognize only ASCII characters by default,
 but some of them use Unicode properties if PCRE2_UCP is set. You can use
 \Q...\E inside a character class.
 
    
-
    QUANTIFIERS
    
+
    QUANTIFIERS
    
 
    
 
       ?           0 or 1, greedy
@@ -304,9 +318,12 @@ but some of them use Unicode properties if PCRE2_UCP is set. You can use
   {n,}        n or more, greedy
   {n,}+       n or more, possessive
   {n,}?       n or more, lazy
+  {,m}        zero up to m, greedy
+  {,m}+       zero up to m, possessive
+  {,m}?       zero up to m, lazy
 
    
 
    
-
    ANCHORS AND SIMPLE ASSERTIONS
    
+
    ANCHORS AND SIMPLE ASSERTIONS
    
 
    
 
       \b          word boundary
@@ -324,7 +341,7 @@ but some of them use Unicode properties if PCRE2_UCP is set. You can use
   \G          first matching position in subject
 
    
 
    
-
    REPORTED MATCH POINT SETTING
    
+
    REPORTED MATCH POINT SETTING
    
 
    
 
       \K          set reported start of match
@@ -334,13 +351,13 @@ for compatibility with Perl. However, if the PCRE2_EXTRA_ALLOW_LOOKAROUND_BSK
 option is set, the previous behaviour is re-enabled. When this option is set,
 \K is honoured in positive assertions, but ignored in negative ones.
 
    
-
    ALTERNATION
    
+
    ALTERNATION
    
 
    
 
       expr|expr|expr...
 
    
 
    
-
    CAPTURING
    
+
    CAPTURING
    
 
    
 
       (...)           capture group
@@ -355,35 +372,47 @@ In non-UTF modes, names may contain underscores and ASCII letters and digits;
 in UTF modes, any Unicode letters and Unicode decimal digits are permitted. In
 both cases, a name must not start with a digit.
 
    
-
    ATOMIC GROUPS
    
+
    ATOMIC GROUPS
    
 
    
 
       (?>...)         atomic non-capture group
   (*atomic:...)   atomic non-capture group
 
    
 
    
-
    COMMENT
    
+
    COMMENT
    
 
    
 
       (?#....)        comment (not nestable)
 
    
 
    
-
    OPTION SETTING
    
+
    OPTION SETTING
    
 
    
 Changes of these options within a group are automatically cancelled at the end
 of the group.
 
    +  (?a)            all ASCII options
+  (?aD)           restrict \d to ASCII in UCP mode
+  (?aS)           restrict \s to ASCII in UCP mode
+  (?aW)           restrict \w to ASCII in UCP mode
+  (?aP)           restrict all POSIX classes to ASCII in UCP mode
+  (?aT)           restrict POSIX digit classes to ASCII in UCP mode
   (?i)            caseless
   (?J)            allow duplicate named groups
   (?m)            multiline
   (?n)            no auto capture
+  (?r)            restrict caseless to either ASCII or non-ASCII
   (?s)            single line (dotall)
   (?U)            default ungreedy (lazy)
-  (?x)            extended: ignore white space except in classes
+  (?x)            ignore white space except in classes or \Q...\E
   (?xx)           as (?x) but also ignore space and tab in classes
-  (?-...)         unset option(s)
-  (?^)            unset imnsx options
+  (?-...)         unset the given option(s)
+  (?^)            unset imnrsx options
 
    
+(?aP) implies (?aT) as well, though this has no additional effect. However, it
+means that (?-aP) is really (?-PT) which disables all ASCII restrictions for
+POSIX classes.
+
    
+
    
 Unsetting x or xx unsets both. Several options may be set at once, and a
 mixture of setting and unsetting such as (?i-x) is allowed, but there may be
 only one hyphen. Setting (but no unsetting) is allowed after (?^ for example
@@ -413,7 +442,7 @@ not increase them. LIMIT_RECURSION is an obsolete synonym for LIMIT_DEPTH. The
 application can lock out the use of (*UTF) and (*UCP) by setting the
 PCRE2_NEVER_UTF or PCRE2_NEVER_UCP options, respectively, at compile time.
 
    
-
    NEWLINE CONVENTION
    
+
    NEWLINE CONVENTION
    
 
    
 These are recognized only at the very start of the pattern or after option
 settings with a similar syntax.
@@ -426,7 +455,7 @@ settings with a similar syntax.
   (*NUL)          the NUL character (binary zero)
 
    
 
    
-
    WHAT \R MATCHES
    
+
    WHAT \R MATCHES
    
 
    
 These are recognized only at the very start of the pattern or after option
 setting with a similar syntax.
@@ -435,7 +464,7 @@ setting with a similar syntax.
   (*BSR_UNICODE)  any Unicode newline sequence
 
    
 
    
-
    LOOKAHEAD AND LOOKBEHIND ASSERTIONS
    
+
    LOOKAHEAD AND LOOKBEHIND ASSERTIONS
    
 
    
 
       (?=...)                     )
@@ -454,9 +483,14 @@ setting with a similar syntax.
   (*nlb:...)                  ) negative lookbehind
   (*negative_lookbehind:...)  )
 
    
-Each top-level branch of a lookbehind must be of a fixed length.
+Each top-level branch of a lookbehind must have a limit for the number of
+characters it matches. If any branch can match a variable number of characters,
+the maximum for each branch is limited to a value set by the caller of
+pcre2_compile() or defaulted. The default is set when PCRE2 is built
+(ultimate default 255). If every branch matches a fixed number of characters,
+the limit for each branch is 65535 characters.
 
    
-
    NON-ATOMIC LOOKAROUND ASSERTIONS
    
+
    NON-ATOMIC LOOKAROUND ASSERTIONS
    
 
    
 These assertions are specific to PCRE2 and are not Perl-compatible.
 
    @@ -469,7 +503,7 @@ These assertions are specific to PCRE2 and are not Perl-compatible.
   (*non_atomic_positive_lookbehind:...)  )
 
    
 
    
-
    SCRIPT RUNS
    
+
    SCRIPT RUNS
    
 
    
 
       (*script_run:...)           ) script run, can be backtracked into
@@ -479,7 +513,7 @@ These assertions are specific to PCRE2 and are not Perl-compatible.
   (*asr:...)                  )
 
    
 
    
-
    BACKREFERENCES
    
+
    BACKREFERENCES
    
 
    
 
       \n              reference by number (can be ambiguous)
@@ -496,7 +530,7 @@ These assertions are specific to PCRE2 and are not Perl-compatible.
   (?P=name)       reference by name (Python)
 
    
 
    
-
    SUBROUTINE REFERENCES (POSSIBLY RECURSIVE)
    
+
    SUBROUTINE REFERENCES (POSSIBLY RECURSIVE)
    
 
    
 
       (?R)            recurse whole pattern
@@ -515,15 +549,15 @@ These assertions are specific to PCRE2 and are not Perl-compatible.
   \g'-n'          call subroutine by relative number (PCRE2 extension)
 
    
 
    
-
    CONDITIONAL PATTERNS
    
+
    CONDITIONAL PATTERNS
    
 
    
 
       (?(condition)yes-pattern)
   (?(condition)yes-pattern|no-pattern)
 
   (?(n)               absolute reference condition
-  (?(+n)              relative reference condition
-  (?(-n)              relative reference condition
+  (?(+n)              relative reference condition (PCRE2 extension)
+  (?(-n)              relative reference condition (PCRE2 extension)
   (?(<name>)          named reference condition (Perl)
   (?('name')          named reference condition (Perl)
   (?(name)            named reference condition (PCRE2, deprecated)
@@ -538,7 +572,7 @@ Note the ambiguity of (?(R) and (?(Rn) which might be named reference
 conditions or recursion tests. Such a condition is interpreted as a reference
 condition if the relevant named group exists.
 
    
-
    BACKTRACKING CONTROL
    
+
    BACKTRACKING CONTROL
    
 
    
 All backtracking control verbs may be in the form (*VERB:NAME). For (*MARK) the
 name is mandatory, for the others it is optional. (*SKIP) changes its behaviour
@@ -565,7 +599,7 @@ pattern is not anchored.
 The effect of one of these verbs in a group called as a subroutine is confined
 to the subroutine call.
 
    
-
    CALLOUTS
    
+
    CALLOUTS
    
 
    
 
       (?C)            callout (assumed number 0)
@@ -576,12 +610,12 @@ The allowed string delimiters are ` ' " ^ % # $ (which are the same for the
 start and the end), and the starting delimiter { matched with the ending
 delimiter }. To encode the ending delimiter within the string, double it.
 
    
-
    SEE ALSO
    
+
    SEE ALSO
    
 
    
 pcre2pattern(3), pcre2api(3), pcre2callout(3),
 pcre2matching(3), pcre2(3).
 
    
-
    AUTHOR
    
+
    AUTHOR
    
 
    
 Philip Hazel
 
    
@@ -590,11 +624,11 @@ Retired from University Computing Service
 Cambridge, England.
 
    
 
    
-
    REVISION
    
+
    REVISION
    
 
    
-Last updated: 12 January 2022
+Last updated: 12 October 2023
 
    
-Copyright © 1997-2022 University of Cambridge.
+Copyright © 1997-2023 University of Cambridge.
 
    
 
    
 Return to the PCRE2 index page.
diff --git a/pcre2/doc/html/pcre2test.html b/pcre2/doc/html/pcre2test.html
index 587ea59..6cc3cc3 100644
--- a/pcre2/doc/html/pcre2test.html
+++ b/pcre2/doc/html/pcre2test.html
@@ -90,14 +90,14 @@ end of file, and no further data is read, so this character should be avoided
 unless you really want that action.
 
    
 
    
-The input is processed using using C's string functions, so must not
-contain binary zeros, even though in Unix-like environments, fgets()
-treats any bytes other than newline as data characters. An error is generated
-if a binary zero is encountered. By default subject lines are processed for
-backslash escapes, which makes it possible to include any data value in strings
-that are passed to the library for matching. For patterns, there is a facility
-for specifying some or all of the 8-bit input characters as hexadecimal pairs,
-which makes it possible to include binary zeros.
+The input is processed using C's string functions, so must not contain binary
+zeros, even though in Unix-like environments, fgets() treats any bytes
+other than newline as data characters. An error is generated if a binary zero
+is encountered. By default subject lines are processed for backslash escapes,
+which makes it possible to include any data value in strings that are passed to
+the library for matching. For patterns, there is a facility for specifying some
+or all of the 8-bit input characters as hexadecimal pairs, which makes it
+possible to include binary zeros.
 
    
 
    
 Input for the 16-bit and 32-bit libraries
@@ -138,15 +138,15 @@ error.
 
    
 
    
 -16
-If the 16-bit library has been built, this option causes it to be used. If only
-the 16-bit library has been built, this is the default. If the 16-bit library
+If the 16-bit library has been built, this option causes it to be used. If the
+8-bit library has not been built, this is the default. If the 16-bit library
 has not been built, this option causes an error.
 
    
 
    
 -32
-If the 32-bit library has been built, this option causes it to be used. If only
-the 32-bit library has been built, this is the default. If the 32-bit library
-has not been built, this option causes an error.
+If the 32-bit library has been built, this option causes it to be used. If no
+other library has been built, this is the default. If the 32-bit library has
+not been built, this option causes an error.
 
    
 
    
 -ac
@@ -507,8 +507,8 @@ followed by a backslash, for example,
 
       /abc/\
 
    
-then a backslash is added to the end of the pattern. This is done to provide a
-way of testing the error condition that arises if a pattern finishes with a
+a backslash is added to the end of the pattern. This is done to provide a way
+of testing the error condition that arises if a pattern finishes with a
 backslash, because
 
       /abc\/
@@ -612,12 +612,11 @@ Setting compilation options
 
    
 The following modifiers set options for pcre2_compile(). Most of them set
 bits in the options argument of that function, but those whose names start with
-PCRE2_EXTRA are additional options that are set in the compile context. For the
-main options, there are some single-letter abbreviations that are the same as
-Perl options. There is special handling for /x: if a second x is present,
-PCRE2_EXTENDED is converted into PCRE2_EXTENDED_MORE as in Perl. A third
-appearance adds PCRE2_EXTENDED as well, though this makes no difference to the
-way pcre2_compile() behaves. See
+PCRE2_EXTRA are additional options that are set in the compile context.
+Some of these options have single-letter abbreviations. There is special
+handling for /x: if a second x is present, PCRE2_EXTENDED is converted into
+PCRE2_EXTENDED_MORE as in Perl. A third appearance adds PCRE2_EXTENDED as well,
+though this makes no difference to the way pcre2_compile() behaves. See
 pcre2api
 for a description of the effects of these options.
 
    @@ -628,9 +627,16 @@ for a description of the effects of these options.
       alt_circumflex            set PCRE2_ALT_CIRCUMFLEX
       alt_verbnames             set PCRE2_ALT_VERBNAMES
       anchored                  set PCRE2_ANCHORED
+  /a  ascii_all                 set all ASCII options
+      ascii_bsd                 set PCRE2_EXTRA_ASCII_BSD
+      ascii_bss                 set PCRE2_EXTRA_ASCII_BSS
+      ascii_bsw                 set PCRE2_EXTRA_ASCII_BSW
+      ascii_digit               set PCRE2_EXTRA_ASCII_DIGIT
+      ascii_posix               set PCRE2_EXTRA_ASCII_POSIX
       auto_callout              set PCRE2_AUTO_CALLOUT
       bad_escape_is_literal     set PCRE2_EXTRA_BAD_ESCAPE_IS_LITERAL
   /i  caseless                  set PCRE2_CASELESS
+  /r  caseless_restrict         set PCRE2_EXTRA_CASELESS_RESTRICT
       dollar_endonly            set PCRE2_DOLLAR_ENDONLY
   /s  dotall                    set PCRE2_DOTALL
       dupnames                  set PCRE2_DUPNAMES
@@ -690,10 +696,14 @@ heavily used in the test files.
       jitfast                   use JIT fast path
       jitverify                 verify JIT use
       locale=<name>             use this locale
-      max_pattern_length=<n>    set the maximum pattern length
+      max_pattern_compiled      ) set maximum compiled pattern
+                 _length=<n>    )   length (bytes)
+      max_pattern_length=<n>    set maximum pattern length (code units)
+      max_varlookbehind=<n>     set maximum variable lookbehind length
       memory                    show memory used
       newline=<type>            set newline type
       null_context              compile with a NULL context
+      null_pattern              pass pattern as NULL
       parens_nest_limit=<n>     set maximum parentheses depth
       posix                     use the POSIX API
       posix_nosub               use the POSIX API with REG_NOSUB
@@ -773,9 +783,11 @@ ending code units are recorded. The subject length line is omitted when
 when it can never be used.
 
    
 
    
-The framesize modifier shows the size, in bytes, of the storage frames
+The framesize modifier shows the size, in bytes, of each storage frame
 used by pcre2_match() for handling backtracking. The size depends on the
-number of capturing parentheses in the pattern.
+number of capturing parentheses in the pattern. A vector of these frames is
+used at matching time; its overall size is shown when the heaframes_size
+subject modifier is set.
 
    
 
    
 The callout_info modifier requests information about all the callouts in
@@ -793,6 +805,15 @@ testing that pcre2_compile() behaves correctly in this case (it uses
 default values).
 
    
 
    
+Passing a NULL pattern
+
    
+
    
+The null_pattern modifier is for testing the behaviour of
+pcre2_compile() when the pattern argument is NULL. The length value
+passed is the default PCRE2_ZERO_TERMINATED unless use_length is set.
+Any length other than zero causes an error.
+
    
+
    
 Specifying pattern characters in hexadecimal
 
    
 
    
@@ -830,6 +851,17 @@ If hex or use_length is used with the POSIX wrapper API (see
 below), the REG_PEND extension is used to pass the pattern's length.
 
    
 
    
+Specifying a maximum for variable lookbehinds
+
    
+
    
+Variable lookbehind assertions are supported only if, for each one, there is a
+maximum length (in characters) that it can match. There is a limit on this,
+whose default can be set at build time, with an ultimate default of 255. The
+max_varlookbehind modifier uses the pcre2_set_max_varlookbehind()
+function to change the limit. Lookbehinds whose branches each match a fixed
+length are limited to 65535 characters per branch.
+
    
+
    
 Specifying wide characters in 16-bit and 32-bit modes
 
    
 
    
@@ -989,6 +1021,15 @@ The max_pattern_length modifier sets a limit, in code units, to the
 length of pattern that pcre2_compile() will accept. Breaching the limit
 causes a compilation error. The default is the largest number a PCRE2_SIZE
 variable can hold (essentially unlimited).
+
    
+
    
+Limiting the size of a compiled pattern
+
    
+
    
+The max_pattern_compiled_length modifier sets a limit, in bytes, to the
+amount of memory used by a compiled pattern. Breaching the limit causes a
+compilation error. The default is the largest number a PCRE2_SIZE variable can
+hold (essentially unlimited).
 
    
 
    
 Using the POSIX wrapper API
@@ -1081,6 +1122,7 @@ process.
       allusedtext                 show all consulted text
       altglobal                   alternative global matching
   /g  global                      global matching
+      heapframes_size             show match data heapframes size
       jitstack=<n>                set size of JIT stack
       mark                        show mark values
       replace=<string>            specify a replacement string
@@ -1178,18 +1220,19 @@ The following modifiers set options for pcre2_match() or
 pcreapi
 for a description of their effects.
 
    -      anchored                  set PCRE2_ANCHORED
-      endanchored               set PCRE2_ENDANCHORED
-      dfa_restart               set PCRE2_DFA_RESTART
-      dfa_shortest              set PCRE2_DFA_SHORTEST
-      no_jit                    set PCRE2_NO_JIT
-      no_utf_check              set PCRE2_NO_UTF_CHECK
-      notbol                    set PCRE2_NOTBOL
-      notempty                  set PCRE2_NOTEMPTY
-      notempty_atstart          set PCRE2_NOTEMPTY_ATSTART
-      noteol                    set PCRE2_NOTEOL
-      partial_hard (or ph)      set PCRE2_PARTIAL_HARD
-      partial_soft (or ps)      set PCRE2_PARTIAL_SOFT
+      anchored                   set PCRE2_ANCHORED
+      endanchored                set PCRE2_ENDANCHORED
+      dfa_restart                set PCRE2_DFA_RESTART
+      dfa_shortest               set PCRE2_DFA_SHORTEST
+      disable_recurseloop_check  set PCRE2_DISABLE_RECURSELOOP_CHECK
+      no_jit                     set PCRE2_NO_JIT
+      no_utf_check               set PCRE2_NO_UTF_CHECK
+      notbol                     set PCRE2_NOTBOL
+      notempty                   set PCRE2_NOTEMPTY
+      notempty_atstart           set PCRE2_NOTEMPTY_ATSTART
+      noteol                     set PCRE2_NOTEOL
+      partial_hard (or ph)       set PCRE2_PARTIAL_HARD
+      partial_soft (or ps)       set PCRE2_PARTIAL_SOFT
 
    
 The partial matching modifiers are provided with abbreviations because they
 appear frequently in tests.
@@ -1246,6 +1289,7 @@ pattern, but can be overridden by modifiers on the subject.
       get=<number or name>       extract captured substring
       getall                     extract all captured substrings
   /g  global                     global matching
+      heapframes_size            show match data heapframes size
       heap_limit=<n>             set a limit on heap memory (Kbytes)
       jitstack=<n>               set size of JIT stack
       mark                       show mark values
@@ -1511,7 +1555,7 @@ Testing substitute callouts
 If the substitute_callout modifier is set, a substitution callout
 function is set up. The null_context modifier must not be set, because
 the address of the callout function is passed in a match context. When the
-callout function is called (after each substitution), details of the the input
+callout function is called (after each substitution), details of the input
 and output strings are output. For example:
 
       /abc/g,replace=<$0>,substitute_callout
@@ -1634,6 +1678,24 @@ memory is allocated during matching with JIT. For this modifier to work, the
 subject, though it can be set on one or the other.
 
    
 
    
+Showing the heap frame overall vector size
+
    
+
    
+The heapframes_size modifier is relevant for matches using
+pcre2_match() without JIT. After a match has run (whether successful or
+not) the size, in bytes, of the allocated heap frames vector that is left
+attached to the match data block is shown. If the matching action involved
+several calls to pcre2_match() (for example, global matching or for
+timing) only the final value is shown.
+
    
+
    
+This modifier is ignored, with a warning, for POSIX or DFA matching. JIT
+matching does not use the heap frames vector, so the size is always zero,
+unless there was a previous non-JIT match. Note that specifing a size of zero
+for the output vector (see below) causes pcre2test to free its match data
+block (and associated heap frames vector) and allocate a new one.
+
    
+
    
 Setting a starting offset
 
    
 
    
@@ -1664,9 +1726,9 @@ A value of zero is useful when testing the POSIX API because it causes
 regexec() to be called with a NULL capture vector. When not testing the
 POSIX API, a value of zero is used to cause
 pcre2_match_data_create_from_pattern() to be called, in order to create a
-match block of exactly the right size for the pattern. (It is not possible to
-create a match block with a zero-length ovector; there is always at least one
-pair of offsets.)
+new match block of exactly the right size for the pattern. (It is not possible
+to create a match block with a zero-length ovector; there is always at least
+one pair of offsets.) The old match data block is freed.
 
    
 
    
 Passing the subject as zero-terminated
@@ -1764,9 +1826,8 @@ unset substring is shown as "<unset>", as for the second data line.
 If the strings contain any non-printing characters, they are output as \xhh
 escapes if the value is less than 256 and UTF mode is not set. Otherwise they
 are output as \x{hh...} escapes. See below for the definition of non-printing
-characters. If the aftertext modifier is set, the output for substring
-0 is followed by the the rest of the subject string, identified by "0+" like
-this:
+characters. If the aftertext modifier is set, the output for substring 0
+is followed by the rest of the subject string, identified by "0+" like this:
 
         re> /cat/aftertext
   data> cataract
@@ -2143,9 +2204,9 @@ Cambridge, England.
 
    
 
    REVISION
    
 
    
-Last updated: 27 July 2022
+Last updated: 24 April 2024
 
    
-Copyright © 1997-2022 University of Cambridge.
+Copyright © 1997-2024 University of Cambridge.
 
    
 
    
 Return to the PCRE2 index page.
diff --git a/pcre2/doc/html/pcre2unicode.html b/pcre2/doc/html/pcre2unicode.html
index a0d4270..6f0972e 100644
--- a/pcre2/doc/html/pcre2unicode.html
+++ b/pcre2/doc/html/pcre2unicode.html
@@ -52,9 +52,12 @@ When PCRE2 is built with Unicode support, the escape sequences \p{..},
 \P{..}, and \X can be used. This is not dependent on the PCRE2_UTF setting.
 The Unicode properties that can be tested are a subset of those that Perl
 supports. Currently they are limited to the general category properties such as
-Lu for an upper case letter or Nd for a decimal number, the Unicode script
-names such as Arabic or Han, Bidi_Class, Bidi_Control, and the derived
-properties Any and LC (synonym L&). Full lists are given in the
+Lu for an upper case letter or Nd for a decimal number, the derived properties
+Any and LC (synonym L&), the Unicode script names such as Arabic or Han,
+Bidi_Class, Bidi_Control, and a few binary properties.
+
    
+
    
+The full lists are given in the
 pcre2pattern
 and
 pcre2syntax
@@ -118,21 +121,22 @@ and \B, because they are defined in terms of \w and \W. If you want
 to test for a wider sense of, say, "digit", you can use explicit Unicode
 property tests such as \p{Nd}. Alternatively, if you set the PCRE2_UCP option,
 the way that the character escapes work is changed so that Unicode properties
-are used to determine which characters match. There are more details in the
-section on
+are used to determine which characters match, though there are some options
+that suppress this for individual escapes. For details see the section on
 generic character types
 in the
 pcre2pattern
 documentation.
 
    
 
    
-Similarly, characters that match the POSIX named character classes are all
-low-valued characters, unless the PCRE2_UCP option is set.
+Like the escapes, characters that match the POSIX named character classes are
+all low-valued characters unless the PCRE2_UCP option is set, but there is an
+option to override this.
 
    
 
    
-However, the special horizontal and vertical white space matching escapes (\h,
-\H, \v, and \V) do match all the appropriate Unicode characters, whether or
-not PCRE2_UCP is set.
+In contrast to the character escapes and character classes, the special
+horizontal and vertical white space escapes (\h, \H, \v, and \V) do match
+all the appropriate Unicode characters, whether or not PCRE2_UCP is set.
 
    
 
    
 UNICODE CASE-EQUIVALENCE
@@ -145,6 +149,14 @@ lookup is used for speed. A few Unicode characters such as Greek sigma have
 more than two code points that are case-equivalent, and these are treated
 specially. Setting PCRE2_UCP without PCRE2_UTF allows Unicode-style case
 processing for non-UTF character encodings such as UCS-2.
+
    
+
    
+There are two ASCII characters (S and K) that, in addition to their ASCII lower
+case equivalents, have a non-ASCII one as well (long S and Kelvin sign).
+Recognition of these non-ASCII characters as case-equivalent to their ASCII
+counterparts can be disabled by setting the PCRE2_EXTRA_CASELESS_RESTRICT
+option. When this is set, all characters in a case equivalence must either be
+ASCII or non-ASCII; there can be no mixing.
 
    
 
    
 SCRIPT RUNS
@@ -432,6 +444,14 @@ PCRE2_UTF to be set as well. Note, however, that the pattern itself must be a
 valid UTF string.
 
    
 
    
+If you do not set PCRE2_MATCH_INVALID_UTF when calling pcre2_compile, and
+you are not certain that your subject strings are valid UTF sequences, you
+should not make use of the JIT "fast path" function pcre2_jit_match()
+because it bypasses sanity checks, including the one for UTF validity. An
+invalid string may cause undefined behaviour, including looping, crashing, or
+giving the wrong answer.
+
    
+
    
 Setting PCRE2_MATCH_INVALID_UTF does not affect what pcre2_compile()
 generates, but if pcre2_jit_compile() is subsequently called, it does
 generate different code. If JIT is not used, the option affects the behaviour
@@ -472,6 +492,12 @@ Using PCRE2_MATCH_INVALID_UTF, an application can run matches on arbitrary
 data, knowing that any matched strings that are returned are valid UTF. This
 can be useful when searching for UTF text in executable or other binary files.
 
    
+
    
+Note, however, that the 16-bit and 32-bit PCRE2 libraries process strings as
+sequences of uint16_t or uint32_t code points. They cannot find valid UTF
+sequences within an arbitrary string of bytes unless such sequences are
+suitably aligned.
+
    
 
    
 AUTHOR
 
    
@@ -487,9 +513,9 @@ Cambridge, England.
 REVISION
 
    
 
    
-Last updated: 22 December 2021
+Last updated: 12 October 2023
 
    
-Copyright © 1997-2021 University of Cambridge.
+Copyright © 1997-2023 University of Cambridge.
 
    
 
    
 Return to the PCRE2 index page.
diff --git a/pcre2/doc/index.html.src b/pcre2/doc/index.html.src
index 2c7c5fb..e4dc786 100644
--- a/pcre2/doc/index.html.src
+++ b/pcre2/doc/index.html.src
@@ -252,8 +252,14 @@ in the library.
 pcre2_set_match_limit
       Set the match limit
 
+pcre2_set_max_pattern_compiled_length
+      Set the maximum length of a compiled pattern
+
 pcre2_set_max_pattern_length
-      Set the maximum length of pattern
+      Set the maximum length of a pattern
+
+pcre2_set_max_varlookbehind
+      Set the maximum match length for a variable-length lookbehind
 
 pcre2_set_newline
       Set the newline convention
diff --git a/pcre2/doc/pcre2-config.txt b/pcre2/doc/pcre2-config.txt
index 33785f4..dc8cf8f 100644
--- a/pcre2/doc/pcre2-config.txt
+++ b/pcre2/doc/pcre2-config.txt
@@ -1,10 +1,11 @@
-PCRE2-CONFIG(1)             General Commands Manual            PCRE2-CONFIG(1)
 
+PCRE2-CONFIG(1)             General Commands Manual            PCRE2-CONFIG(1)
 
 
 NAME
        pcre2-config - program to return PCRE2 configuration
 
+
 SYNOPSIS
 
        pcre2-config [--prefix] [--exec-prefix] [--version]
@@ -15,9 +16,9 @@ SYNOPSIS
 DESCRIPTION
 
        pcre2-config returns the configuration of the installed PCRE2 libraries
-       and the options required to compile a program to use them. Some of  the
-       options  apply  only  to the 8-bit, or 16-bit, or 32-bit libraries, re-
-       spectively, and are not available for  libraries  that  have  not  been
+       and  the options required to compile a program to use them. Some of the
+       options apply only to the 8-bit, or 16-bit, or  32-bit  libraries,  re-
+       spectively,  and  are  not  available  for libraries that have not been
        built. If an unavailable option is encountered, the "usage" information
        is output.
 
@@ -58,9 +59,9 @@ OPTIONS
                  -I options, but is blank on many systems).
 
        --cflags-posix
-                 Writes  to  the  standard output the command line options re-
-                 quired to compile files that use PCRE2's  POSIX  API  wrapper
-                 library  (this  may  include some -I options, but is blank on
+                 Writes to the standard output the command  line  options  re-
+                 quired  to  compile  files that use PCRE2's POSIX API wrapper
+                 library (this may include some -I options, but  is  blank  on
                  many systems).
 
 
@@ -71,11 +72,14 @@ SEE ALSO
 
 AUTHOR
 
-       This manual page was originally written by Mark Baker  for  the  Debian
-       GNU/Linux  system.  It has been subsequently revised as a generic PCRE2
+       This  manual  page  was originally written by Mark Baker for the Debian
+       GNU/Linux system. It has been subsequently revised as a  generic  PCRE2
        man page.
 
 
 REVISION
 
        Last updated: 28 September 2014
+
+
+PCRE2 10.00                    28 September 2014               PCRE2-CONFIG(1)
diff --git a/pcre2/doc/pcre2.txt b/pcre2/doc/pcre2.txt
index a997f73..85eead6 100644
--- a/pcre2/doc/pcre2.txt
+++ b/pcre2/doc/pcre2.txt
@@ -8,17 +8,18 @@ pcre2test commands.
 -----------------------------------------------------------------------------
 
 
-PCRE2(3)                   Library Functions Manual                   PCRE2(3)
 
+PCRE2(3)                   Library Functions Manual                   PCRE2(3)
 
 
 NAME
        PCRE2 - Perl-compatible regular expressions (revised API)
 
+
 INTRODUCTION
 
        PCRE2 is the name used for a revised API for the PCRE library, which is
-       a set of functions, written in C,  that  implement  regular  expression
+       a  set  of  functions,  written in C, that implement regular expression
        pattern matching using the same syntax and semantics as Perl, with just
        a few differences. After nearly two decades,  the  limitations  of  the
        original  API  were  making development increasingly difficult. The new
@@ -32,8 +33,8 @@ INTRODUCTION
        appeared  in  Python and the original PCRE before they appeared in Perl
        are available using the Python syntax. There is also some  support  for
        one  or  two .NET and Oniguruma syntax items, and there are options for
-       requesting some minor changes that give better  ECMAScript  (aka  Java-
-       Script) compatibility.
+       requesting  some  minor  changes  that  give  better  ECMAScript   (aka
+       JavaScript) compatibility.
 
        The  source code for PCRE2 can be compiled to support strings of 8-bit,
        16-bit, or 32-bit code units, which means that up to three separate li-
@@ -44,7 +45,7 @@ INTRODUCTION
 
        The original work to extend PCRE to 16-bit and 32-bit  code  units  was
        done by Zoltan Herczeg and Christian Persch, respectively. In all three
-       cases, strings can be interpreted either  as  one  character  per  code
+       cases,  strings  can  be  interpreted  either as one character per code
        unit, or as UTF-encoded Unicode, with support for Unicode general cate-
        gory properties. Unicode support is optional at build time (but is  the
        default). However, processing strings as UTF code units must be enabled
@@ -63,17 +64,17 @@ INTRODUCTION
        In addition to the Perl-compatible matching function, PCRE2 contains an
        alternative  function that matches the same compiled patterns in a dif-
        ferent way. In certain circumstances, the alternative function has some
-       advantages.   For  a discussion of the two matching algorithms, see the
+       advantages.  For a discussion of the two matching algorithms,  see  the
        pcre2matching page.
 
-       Details of exactly which Perl regular expression features are  and  are
-       not  supported  by  PCRE2  are  given  in  separate  documents. See the
-       pcre2pattern and pcre2compat pages. There is a syntax  summary  in  the
+       Details  of  exactly which Perl regular expression features are and are
+       not supported by  PCRE2  are  given  in  separate  documents.  See  the
+       pcre2pattern  and  pcre2compat  pages. There is a syntax summary in the
        pcre2syntax page.
 
-       Some  features  of PCRE2 can be included, excluded, or changed when the
-       library is built. The pcre2_config() function makes it possible  for  a
-       client  to  discover  which  features are available. The features them-
+       Some features of PCRE2 can be included, excluded, or changed  when  the
+       library  is  built. The pcre2_config() function makes it possible for a
+       client to discover which features are  available.  The  features  them-
        selves are described in the pcre2build page. Documentation about build-
        ing  PCRE2 for various operating systems can be found in the README and
        NON-AUTOTOOLS_BUILD files in the source distribution.
@@ -83,50 +84,50 @@ INTRODUCTION
        functions, but which are not intended  for  use  by  external  callers.
        Their  names  all begin with "_pcre2", which hopefully will not provoke
        any name clashes. In some environments, it is possible to control which
-       external  symbols  are  exported when a shared library is built, and in
+       external symbols are exported when a shared library is  built,  and  in
        these cases the undocumented symbols are not exported.
 
 
 SECURITY CONSIDERATIONS
 
-       If you are using PCRE2 in a non-UTF application that permits  users  to
-       supply  arbitrary  patterns  for  compilation, you should be aware of a
+       If  you  are using PCRE2 in a non-UTF application that permits users to
+       supply arbitrary patterns for compilation, you should  be  aware  of  a
        feature that allows users to turn on UTF support from within a pattern.
        For  example, an 8-bit pattern that begins with "(*UTF)" turns on UTF-8
        mode, which interprets patterns and subjects as strings of  UTF-8  code
        units instead of individual 8-bit characters. This causes both the pat-
-       tern and any data against which it is matched to be checked  for  UTF-8
-       validity.  If the data string is very long, such a check might use suf-
-       ficiently many resources as to cause your application to  lose  perfor-
+       tern  and  any data against which it is matched to be checked for UTF-8
+       validity. If the data string is very long, such a check might use  suf-
+       ficiently  many  resources as to cause your application to lose perfor-
        mance.
 
-       One  way  of guarding against this possibility is to use the pcre2_pat-
-       tern_info() function  to  check  the  compiled  pattern's  options  for
-       PCRE2_UTF.  Alternatively,  you can set the PCRE2_NEVER_UTF option when
-       calling pcre2_compile(). This causes a compile time error if  the  pat-
+       One way of guarding against this possibility is to use  the  pcre2_pat-
+       tern_info()  function  to  check  the  compiled  pattern's  options for
+       PCRE2_UTF. Alternatively, you can set the PCRE2_NEVER_UTF  option  when
+       calling  pcre2_compile().  This causes a compile time error if the pat-
        tern contains a UTF-setting sequence.
 
-       The  use  of Unicode properties for character types such as \d can also
-       be enabled from within the pattern, by specifying "(*UCP)".  This  fea-
+       The use of Unicode properties for character types such as \d  can  also
+       be  enabled  from within the pattern, by specifying "(*UCP)". This fea-
        ture can be disallowed by setting the PCRE2_NEVER_UCP option.
 
-       If  your  application  is one that supports UTF, be aware that validity
-       checking can take time. If the same data string is to be  matched  many
-       times,  you  can  use  the PCRE2_NO_UTF_CHECK option for the second and
+       If your application is one that supports UTF, be  aware  that  validity
+       checking  can  take time. If the same data string is to be matched many
+       times, you can use the PCRE2_NO_UTF_CHECK option  for  the  second  and
        subsequent matches to avoid running redundant checks.
 
        The use of the \C escape sequence in a UTF-8 or UTF-16 pattern can lead
        to  problems,  because  it  may leave the current matching point in the
        middle of a multi-code-unit character. The PCRE2_NEVER_BACKSLASH_C  op-
        tion can be used by an application to lock out the use of \C, causing a
-       compile-time error if it is encountered. It is also possible  to  build
+       compile-time  error  if it is encountered. It is also possible to build
        PCRE2 with the use of \C permanently disabled.
 
-       Another  way  that  performance can be hit is by running a pattern that
-       has a very large search tree against a string that  will  never  match.
-       Nested  unlimited repeats in a pattern are a common example. PCRE2 pro-
-       vides some protection against  this:  see  the  pcre2_set_match_limit()
-       function  in  the  pcre2api  page.  There  is a similar function called
+       Another way that performance can be hit is by running  a  pattern  that
+       has  a  very  large search tree against a string that will never match.
+       Nested unlimited repeats in a pattern are a common example. PCRE2  pro-
+       vides  some  protection  against  this: see the pcre2_set_match_limit()
+       function in the pcre2api page.  There  is  a  similar  function  called
        pcre2_set_depth_limit() that can be used to restrict the amount of mem-
        ory that is used.
 
@@ -138,9 +139,9 @@ USER DOCUMENTATION
        the  HTML  format, each is a separate page, linked from the index page.
        In the plain  text  format,  the  descriptions  of  the  pcre2grep  and
        pcre2test programs are in files called pcre2grep.txt and pcre2test.txt,
-       respectively. The remaining sections, except for the pcre2demo  section
-       (which  is a program listing), and the short pages for individual func-
-       tions, are concatenated in pcre2.txt, for ease of searching.  The  sec-
+       respectively.  The remaining sections, except for the pcre2demo section
+       (which is a program listing), and the short pages for individual  func-
+       tions,  are  concatenated in pcre2.txt, for ease of searching. The sec-
        tions are as follows:
 
          pcre2              this document
@@ -166,7 +167,7 @@ USER DOCUMENTATION
          pcre2test          description of the pcre2test command
          pcre2unicode       discussion of Unicode and UTF support
 
-       In  the  "man"  and HTML formats, there is also a short page for each C
+       In the "man" and HTML formats, there is also a short page  for  each  C
        library function, listing its arguments and results.
 
 
@@ -176,7 +177,7 @@ AUTHOR
        Retired from University Computing Service
        Cambridge, England.
 
-       Putting an actual email address here is a spam magnet. If you  want  to
+       Putting  an  actual email address here is a spam magnet. If you want to
        email me, use my two names separated by a dot at gmail.com.
 
 
@@ -184,11 +185,14 @@ REVISION
 
        Last updated: 27 August 2021
        Copyright (c) 1997-2021 University of Cambridge.
+
+
+PCRE2 10.38                     27 August 2021                        PCRE2(3)
 ------------------------------------------------------------------------------
 
 
-PCRE2API(3)                Library Functions Manual                PCRE2API(3)
 
+PCRE2API(3)                Library Functions Manual                PCRE2API(3)
 
 
 NAME
@@ -233,6 +237,11 @@ PCRE2 NATIVE API AUXILIARY MATCH FUNCTIONS
 
        PCRE2_SPTR pcre2_get_mark(pcre2_match_data *match_data);
 
+       PCRE2_SIZE pcre2_get_match_data_size(pcre2_match_data *match_data);
+
+       PCRE2_SIZE pcre2_get_match_data_heapframes_size(
+         pcre2_match_data *match_data);
+
        uint32_t pcre2_get_ovector_count(pcre2_match_data *match_data);
 
        PCRE2_SIZE *pcre2_get_ovector_pointer(pcre2_match_data *match_data);
@@ -274,6 +283,12 @@ PCRE2 NATIVE API COMPILE CONTEXT FUNCTIONS
        int pcre2_set_max_pattern_length(pcre2_compile_context *ccontext,
          PCRE2_SIZE value);
 
+       int pcre2_set_max_pattern_compiled_length(
+         pcre2_compile_context *ccontext, PCRE2_SIZE value);
+
+       int pcre2_set_max_varlookbehind(pcre2_compile_contest *ccontext,
+         uint32_t value);
+
        int pcre2_set_newline(pcre2_compile_context *ccontext,
          uint32_t value);
 
@@ -345,7 +360,7 @@ PCRE2 NATIVE API STRING EXTRACTION FUNCTIONS
        int pcre2_substring_number_from_name(const pcre2_code *code,
          PCRE2_SPTR name);
 
-       void pcre2_substring_list_free(PCRE2_SPTR *list);
+       void pcre2_substring_list_free(PCRE2_UCHAR **list);
 
        int pcre2_substring_list_get(pcre2_match_data *match_data,
          PCRE2_UCHAR ***listptr, PCRE2_SIZE **lengthsptr);
@@ -372,8 +387,8 @@ PCRE2 NATIVE API JIT FUNCTIONS
 
        void pcre2_jit_free_unused_memory(pcre2_general_context *gcontext);
 
-       pcre2_jit_stack *pcre2_jit_stack_create(PCRE2_SIZE startsize,
-         PCRE2_SIZE maxsize, pcre2_general_context *gcontext);
+       pcre2_jit_stack *pcre2_jit_stack_create(size_t startsize,
+         size_t maxsize, pcre2_general_context *gcontext);
 
        void pcre2_jit_stack_assign(pcre2_match_context *mcontext,
          pcre2_jit_callback callback_function, void *callback_data);
@@ -427,12 +442,12 @@ PCRE2 NATIVE API OBSOLETE FUNCTIONS
 
        int pcre2_set_recursion_memory_management(
          pcre2_match_context *mcontext,
-         void *(*private_malloc)(PCRE2_SIZE, void *),
+         void *(*private_malloc)(size_t, void *),
          void (*private_free)(void *, void *), void *memory_data);
 
-       These  functions became obsolete at release 10.30 and are retained only
-       for backward compatibility. They should not be used in  new  code.  The
-       first  is  replaced by pcre2_set_depth_limit(); the second is no longer
+       These functions became obsolete at release 10.30 and are retained  only
+       for  backward  compatibility.  They should not be used in new code. The
+       first is replaced by pcre2_set_depth_limit(); the second is  no  longer
        needed and has no effect (it always returns zero).
 
 
@@ -458,7 +473,7 @@ PCRE2 EXPERIMENTAL PATTERN CONVERSION FUNCTIONS
 
        void pcre2_converted_pattern_free(PCRE2_UCHAR *converted_pattern);
 
-       These functions provide a way of  converting  non-PCRE2  patterns  into
+       These  functions  provide  a  way of converting non-PCRE2 patterns into
        patterns that can be processed by pcre2_compile(). This facility is ex-
        perimental and may be changed in future releases. At  present,  "globs"
        and  POSIX  basic  and  extended patterns can be converted. Details are
@@ -471,14 +486,10 @@ PCRE2 8-BIT, 16-BIT, AND 32-BIT LIBRARIES
        code  units,  respectively.  However,  there  is  just one header file,
        pcre2.h.  This contains the function prototypes and  other  definitions
        for all three libraries. One, two, or all three can be installed simul-
-       taneously. On Unix-like systems the libraries  are  called  libpcre2-8,
+       taneously.  On  Unix-like  systems the libraries are called libpcre2-8,
        libpcre2-16, and libpcre2-32, and they can also co-exist with the orig-
-       inal PCRE libraries.
-
-       Character strings are passed to and from a PCRE2 library as a  sequence
-       of  unsigned  integers  in  code  units of the appropriate width. Every
-       PCRE2 function comes in three different forms, one  for  each  library,
-       for example:
+       inal PCRE libraries.  Every PCRE2 function  comes  in  three  different
+       forms, one for each library, for example:
 
          pcre2_compile_8()
          pcre2_compile_16()
@@ -491,22 +502,27 @@ PCRE2 8-BIT, 16-BIT, AND 32-BIT LIBRARIES
 
        The  UCHAR  types define unsigned code units of the appropriate widths.
        For example, PCRE2_UCHAR16 is usually defined as `uint16_t'.  The  SPTR
-       types  are  constant  pointers  to the equivalent UCHAR types, that is,
+       types are pointers to constants of the equivalent UCHAR types, that is,
        they are pointers to vectors of unsigned code units.
 
-       Many applications use only one code unit width. For their  convenience,
+       Character  strings  are  passed  to a PCRE2 library as sequences of un-
+       signed integers in code units of the appropriate width. The length of a
+       string may be given as a number of code units, or  the  string  may  be
+       specified as zero-terminated.
+
+       Many  applications use only one code unit width. For their convenience,
        macros are defined whose names are the generic forms such as pcre2_com-
        pile() and  PCRE2_SPTR.  These  macros  use  the  value  of  the  macro
        PCRE2_CODE_UNIT_WIDTH  to generate the appropriate width-specific func-
        tion and macro names.  PCRE2_CODE_UNIT_WIDTH is not defined by default.
-       An  application  must  define  it  to  be 8, 16, or 32 before including
+       An application must define it to be  8,  16,  or  32  before  including
        pcre2.h in order to make use of the generic names.
 
-       Applications that use more than one code unit width can be linked  with
-       more  than  one PCRE2 library, but must define PCRE2_CODE_UNIT_WIDTH to
-       be 0 before including pcre2.h, and then use the  real  function  names.
-       Any  code  that  is to be included in an environment where the value of
-       PCRE2_CODE_UNIT_WIDTH is unknown should  also  use  the  real  function
+       Applications  that use more than one code unit width can be linked with
+       more than one PCRE2 library, but must define  PCRE2_CODE_UNIT_WIDTH  to
+       be  0  before  including pcre2.h, and then use the real function names.
+       Any code that is to be included in an environment where  the  value  of
+       PCRE2_CODE_UNIT_WIDTH  is  unknown  should  also  use the real function
        names. (Unfortunately, it is not possible in C code to save and restore
        the value of a macro.)
 
@@ -528,14 +544,15 @@ PCRE2 API OVERVIEW
 
        PCRE2  has  its  own  native  API, which is described in this document.
        There are also some wrapper functions for the 8-bit library that corre-
-       spond  to the POSIX regular expression API, but they do not give access
-       to all the functionality of PCRE2. They are described in the pcre2posix
-       documentation. Both these APIs define a set of C function calls.
+       spond to the POSIX regular expression API, but they do not give  access
+       to  all  the  functionality of PCRE2 and they are not thread-safe. They
+       are described in the pcre2posix documentation. Both these APIs define a
+       set of C function calls.
 
-       The  native  API  C data types, function prototypes, option values, and
+       The native API C data types, function prototypes,  option  values,  and
        error codes are defined in the header file pcre2.h, which also contains
        definitions of PCRE2_MAJOR and PCRE2_MINOR, the major and minor release
-       numbers for the library. Applications can use these to include  support
+       numbers  for the library. Applications can use these to include support
        for different releases of PCRE2.
 
        In a Windows environment, if you want to statically link an application
@@ -560,30 +577,30 @@ PCRE2 API OVERVIEW
        that can be built in  appropriate  hardware  environments.  It  greatly
        speeds  up  the matching performance of many patterns. Programs can re-
        quest that it be used if available by calling pcre2_jit_compile() after
-       a  pattern has been successfully compiled by pcre2_compile(). This does
+       a pattern has been successfully compiled by pcre2_compile(). This  does
        nothing if JIT support is not available.
 
-       More complicated programs might need to  make  use  of  the  specialist
-       functions    pcre2_jit_stack_create(),    pcre2_jit_stack_free(),   and
-       pcre2_jit_stack_assign() in order to control the JIT code's memory  us-
+       More  complicated  programs  might  need  to make use of the specialist
+       functions   pcre2_jit_stack_create(),    pcre2_jit_stack_free(),    and
+       pcre2_jit_stack_assign()  in order to control the JIT code's memory us-
        age.
 
        JIT matching is automatically used by pcre2_match() if it is available,
        unless the PCRE2_NO_JIT option is set. There is also a direct interface
-       for  JIT  matching,  which gives improved performance at the expense of
-       less sanity checking. The JIT-specific functions are discussed  in  the
+       for JIT matching, which gives improved performance at  the  expense  of
+       less  sanity  checking. The JIT-specific functions are discussed in the
        pcre2jit documentation.
 
-       A  second  matching function, pcre2_dfa_match(), which is not Perl-com-
-       patible, is also provided. This uses  a  different  algorithm  for  the
-       matching.  The  alternative  algorithm finds all possible matches (at a
-       given point in the subject), and scans the subject  just  once  (unless
-       there  are lookaround assertions). However, this algorithm does not re-
-       turn captured substrings. A description of the two matching  algorithms
-       and  their  advantages  and disadvantages is given in the pcre2matching
+       A second matching function, pcre2_dfa_match(), which is  not  Perl-com-
+       patible,  is  also  provided.  This  uses a different algorithm for the
+       matching. The alternative algorithm finds all possible  matches  (at  a
+       given  point  in  the subject), and scans the subject just once (unless
+       there are lookaround assertions). However, this algorithm does not  re-
+       turn  captured substrings. A description of the two matching algorithms
+       and their advantages and disadvantages is given  in  the  pcre2matching
        documentation. There is no JIT support for pcre2_dfa_match().
 
-       In addition to the main compiling and  matching  functions,  there  are
+       In  addition  to  the  main compiling and matching functions, there are
        convenience functions for extracting captured substrings from a subject
        string that has been matched by pcre2_match(). They are:
 
@@ -626,7 +643,9 @@ STRING LENGTHS AND OFFSETS
        The  largest  value  that  can  be  stored  in  such  a  type  (that is
        ~(PCRE2_SIZE)0) is reserved as a special indicator for  zero-terminated
        strings  and  unset offsets.  Therefore, the longest string that can be
-       handled is one less than this maximum.
+       handled is one less than this maximum. Note that string lengths are al-
+       ways given in code units. Only in the 8-bit library is  such  a  length
+       the same as the number of bytes in the string.
 
 
 NEWLINES
@@ -634,8 +653,8 @@ NEWLINES
        PCRE2 supports five different conventions for indicating line breaks in
        strings:  a  single  CR (carriage return) character, a single LF (line-
        feed) character, the two-character sequence CRLF, any of the three pre-
-       ceding,  or any Unicode newline sequence. The Unicode newline sequences
-       are the three just mentioned, plus the single characters  VT  (vertical
+       ceding, or any Unicode newline sequence. The Unicode newline  sequences
+       are  the  three just mentioned, plus the single characters VT (vertical
        tab, U+000B), FF (form feed, U+000C), NEL (next line, U+0085), LS (line
        separator, U+2028), and PS (paragraph separator, U+2029).
 
@@ -643,16 +662,16 @@ NEWLINES
        system as its standard newline sequence. When PCRE2 is built, a default
        can be specified.  If it is not, the default is set to LF, which is the
        Unix standard. However, the newline convention can be changed by an ap-
-       plication when calling pcre2_compile(), or it can be specified by  spe-
-       cial  text at the start of the pattern itself; this overrides any other
-       settings. See the pcre2pattern page for details of the special  charac-
+       plication  when calling pcre2_compile(), or it can be specified by spe-
+       cial text at the start of the pattern itself; this overrides any  other
+       settings.  See the pcre2pattern page for details of the special charac-
        ter sequences.
 
-       In  the  PCRE2  documentation  the  word "newline" is used to mean "the
+       In the PCRE2 documentation the word "newline"  is  used  to  mean  "the
        character or pair of characters that indicate a line break". The choice
        of  newline convention affects the handling of the dot, circumflex, and
        dollar metacharacters, the handling of #-comments in /x mode, and, when
-       CRLF  is a recognized line ending sequence, the match position advance-
+       CRLF is a recognized line ending sequence, the match position  advance-
        ment for a non-anchored pattern. There is more detail about this in the
        section on pcre2_match() options below.
 
@@ -663,9 +682,9 @@ NEWLINES
 
 MULTITHREADING
 
-       In  a multithreaded application it is important to keep thread-specific
-       data separate from data that can be shared between threads.  The  PCRE2
-       library  code  itself  is  thread-safe: it contains no static or global
+       In a multithreaded application it is important to keep  thread-specific
+       data  separate  from data that can be shared between threads. The PCRE2
+       library code itself is thread-safe: it contains  no  static  or  global
        variables. The API is designed to be fairly simple for non-threaded ap-
        plications  while at the same time ensuring that multithreaded applica-
        tions can use it.
@@ -675,7 +694,7 @@ MULTITHREADING
 
    The compiled pattern
 
-       A  pointer  to  the  compiled form of a pattern is returned to the user
+       A pointer to the compiled form of a pattern is  returned  to  the  user
        when pcre2_compile() is successful. The data in the compiled pattern is
        fixed,  and  does not change when the pattern is matched. Therefore, it
        is thread-safe, that is, the same compiled pattern can be used by  more
@@ -707,9 +726,9 @@ MULTITHREADING
        The  reason  for checking the pointer a second time is as follows: Sev-
        eral threads may have acquired the shared lock and tested  the  pointer
        for being NULL, but only one of them will be given the write lock, with
-       the rest kept waiting. The winning thread will compile the pattern  and
-       store  the  result.  After this thread releases the write lock, another
-       thread will get it, and if it does not retest pointer for  being  NULL,
+       the  rest kept waiting. The winning thread will compile the pattern and
+       store the result.  After this thread releases the write  lock,  another
+       thread  will  get it, and if it does not retest pointer for being NULL,
        will recompile the pattern and overwrite the pointer, creating a memory
        leak and possibly causing other issues.
 
@@ -748,8 +767,8 @@ MULTITHREADING
        PCRE2 functions are called. A context is nothing more than a collection
        of parameters that control the way PCRE2 operates. Grouping a number of
        parameters together in a context is a convenient way of passing them to
-       a PCRE2 function without using lots of arguments. The  parameters  that
-       are  stored  in  contexts  are in some sense "advanced features" of the
+       a  PCRE2  function without using lots of arguments. The parameters that
+       are stored in contexts are in some sense  "advanced  features"  of  the
        API. Many straightforward applications will not need to use contexts.
 
        In a multithreaded application, if the parameters in a context are val-
@@ -759,7 +778,7 @@ MULTITHREADING
 
    Match blocks
 
-       The  matching  functions need a block of memory for storing the results
+       The matching functions need a block of memory for storing  the  results
        of a match. This includes details of what was matched, as well as addi-
        tional  information  such as the name of a (*MARK) setting. Each thread
        must provide its own copy of this memory.
@@ -777,25 +796,25 @@ PCRE2 CONTEXTS
        just any of the context parameters can pass NULL when a context pointer
        is required.
 
-       There are three different types of context: a general context  that  is
-       relevant  for  several  PCRE2 operations, a compile-time context, and a
+       There  are  three different types of context: a general context that is
+       relevant for several PCRE2 operations, a compile-time  context,  and  a
        match-time context.
 
    The general context
 
-       At present, this context just contains pointers to (and data  for)  ex-
-       ternal  memory management functions that are called from several places
-       in the PCRE2 library.  The  context  is  named  `general'  rather  than
-       specifically  `memory'  because in future other fields may be added. If
-       you do not want to supply your own custom memory management  functions,
-       you  do not need to bother with a general context. A general context is
+       At  present,  this context just contains pointers to (and data for) ex-
+       ternal memory management functions that are called from several  places
+       in  the  PCRE2  library.  The  context  is  named `general' rather than
+       specifically `memory' because in future other fields may be  added.  If
+       you  do not want to supply your own custom memory management functions,
+       you do not need to bother with a general context. A general context  is
        created by:
 
        pcre2_general_context *pcre2_general_context_create(
          void *(*private_malloc)(PCRE2_SIZE, void *),
          void (*private_free)(void *, void *), void *memory_data);
 
-       The two function pointers specify custom memory  management  functions,
+       The  two  function pointers specify custom memory management functions,
        whose prototypes are:
 
          void *private_malloc(PCRE2_SIZE, void *);
@@ -803,16 +822,16 @@ PCRE2 CONTEXTS
 
        Whenever code in PCRE2 calls these functions, the final argument is the
        value of memory_data. Either of the first two arguments of the creation
-       function  may be NULL, in which case the system memory management func-
-       tions malloc() and free() are used. (This is not currently  useful,  as
-       there  are  no  other  fields in a general context, but in future there
-       might be.)  The private_malloc() function is used (if supplied) to  ob-
-       tain  memory for storing the context, and all three values are saved as
+       function may be NULL, in which case the system memory management  func-
+       tions  malloc()  and free() are used. (This is not currently useful, as
+       there are no other fields in a general context,  but  in  future  there
+       might  be.)  The private_malloc() function is used (if supplied) to ob-
+       tain memory for storing the context, and all three values are saved  as
        part of the context.
 
-       Whenever PCRE2 creates a data block of any kind, the block  contains  a
-       pointer  to the free() function that matches the malloc() function that
-       was used. When the time comes to  free  the  block,  this  function  is
+       Whenever  PCRE2  creates a data block of any kind, the block contains a
+       pointer to the free() function that matches the malloc() function  that
+       was  used.  When  the  time  comes  to free the block, this function is
        called.
 
        A general context can be copied by calling:
@@ -824,13 +843,13 @@ PCRE2 CONTEXTS
 
        void pcre2_general_context_free(pcre2_general_context *gcontext);
 
-       If  this  function  is  passed  a NULL argument, it returns immediately
+       If this function is passed a  NULL  argument,  it  returns  immediately
        without doing anything.
 
    The compile context
 
-       A compile context is required if you want to provide an external  func-
-       tion  for  stack  checking  during compilation or to change the default
+       A  compile context is required if you want to provide an external func-
+       tion for stack checking during compilation or  to  change  the  default
        values of any of the following compile-time parameters:
 
          What \R matches (Unicode newlines or CR, LF, CRLF only)
@@ -840,11 +859,11 @@ PCRE2 CONTEXTS
          The maximum length of the pattern string
          The extra options bits (none set by default)
 
-       A compile context is also required if you are using custom memory  man-
-       agement.   If  none of these apply, just pass NULL as the context argu-
+       A  compile context is also required if you are using custom memory man-
+       agement.  If none of these apply, just pass NULL as the  context  argu-
        ment of pcre2_compile().
 
-       A compile context is created, copied, and freed by the following  func-
+       A  compile context is created, copied, and freed by the following func-
        tions:
 
        pcre2_compile_context *pcre2_compile_context_create(
@@ -855,7 +874,7 @@ PCRE2 CONTEXTS
 
        void pcre2_compile_context_free(pcre2_compile_context *ccontext);
 
-       A  compile  context  is created with default values for its parameters.
+       A compile context is created with default values  for  its  parameters.
        These can be changed by calling the following functions, which return 0
        on success, or PCRE2_ERROR_BADDATA if invalid data is detected.
 
@@ -865,13 +884,13 @@ PCRE2 CONTEXTS
        The  value  must  be PCRE2_BSR_ANYCRLF, to specify that \R matches only
        CR, LF, or CRLF, or PCRE2_BSR_UNICODE, to specify that \R  matches  any
        Unicode line ending sequence. The value is used by the JIT compiler and
-       by  the  two  interpreted   matching   functions,   pcre2_match()   and
+       by   the   two   interpreted   matching  functions,  pcre2_match()  and
        pcre2_dfa_match().
 
        int pcre2_set_character_tables(pcre2_compile_context *ccontext,
          const uint8_t *tables);
 
-       The  value  must  be  the result of a call to pcre2_maketables(), whose
+       The value must be the result of a  call  to  pcre2_maketables(),  whose
        only argument is a general context. This function builds a set of char-
        acter tables in the current locale.
 
@@ -893,14 +912,33 @@ PCRE2 CONTEXTS
        is compiled with this context. If the pattern is longer,  an  error  is
        generated.   This facility is provided so that applications that accept
        patterns from external sources can limit their size. The default is the
-       largest  number  that  a  PCRE2_SIZE variable can hold, which is effec-
+       largest number that a PCRE2_SIZE variable can  hold,  which  is  effec-
+       tively unlimited.
+
+       int pcre2_set_max_pattern_compiled_length(
+         pcre2_compile_context *ccontext, PCRE2_SIZE value);
+
+       This  sets  a maximum size, in bytes, for the memory needed to hold the
+       compiled version of a pattern that is compiled with  this  context.  If
+       the  pattern needs more memory, an error is generated. This facility is
+       provided so  that  applications  that  accept  patterns  from  external
+       sources  can  limit  the  amount of memory they use. The default is the
+       largest number that a PCRE2_SIZE variable can  hold,  which  is  effec-
        tively unlimited.
 
+       int pcre2_set_max_varlookbehind(pcre2_compile_contest *ccontext,
+         uint32_t value);
+
+       This  sets  a  maximum length for the number of characters matched by a
+       variable-length lookbehind assertion. The default is set when PCRE2  is
+       built,  with  the ultimate default being 255, the same as Perl. Lookbe-
+       hind assertions without a bounding length are not supported.
+
        int pcre2_set_newline(pcre2_compile_context *ccontext,
          uint32_t value);
 
        This specifies which characters or character sequences are to be recog-
-       nized  as newlines. The value must be one of PCRE2_NEWLINE_CR (carriage
+       nized as newlines. The value must be one of PCRE2_NEWLINE_CR  (carriage
        return only), PCRE2_NEWLINE_LF (linefeed only), PCRE2_NEWLINE_CRLF (the
        two-character  sequence  CR followed by LF), PCRE2_NEWLINE_ANYCRLF (any
        of the above), PCRE2_NEWLINE_ANY (any  Unicode  newline  sequence),  or
@@ -909,37 +947,37 @@ PCRE2 CONTEXTS
        A pattern can override the value set in the compile context by starting
        with a sequence such as (*CRLF). See the pcre2pattern page for details.
 
-       When a  pattern  is  compiled  with  the  PCRE2_EXTENDED  or  PCRE2_EX-
-       TENDED_MORE  option,  the newline convention affects the recognition of
-       the end of internal comments starting with #. The value is  saved  with
-       the  compiled pattern for subsequent use by the JIT compiler and by the
-       two    interpreted    matching     functions,     pcre2_match()     and
+       When  a  pattern  is  compiled  with  the  PCRE2_EXTENDED  or PCRE2_EX-
+       TENDED_MORE option, the newline convention affects the  recognition  of
+       the  end  of internal comments starting with #. The value is saved with
+       the compiled pattern for subsequent use by the JIT compiler and by  the
+       two     interpreted     matching     functions,    pcre2_match()    and
        pcre2_dfa_match().
 
        int pcre2_set_parens_nest_limit(pcre2_compile_context *ccontext,
          uint32_t value);
 
-       This  parameter  adjusts  the  limit,  set when PCRE2 is built (default
-       250), on the depth of parenthesis nesting  in  a  pattern.  This  limit
-       stops  rogue  patterns  using  up too much system stack when being com-
-       piled. The limit applies to parentheses of all kinds, not just  captur-
+       This parameter adjusts the limit, set  when  PCRE2  is  built  (default
+       250),  on  the  depth  of  parenthesis nesting in a pattern. This limit
+       stops rogue patterns using up too much system  stack  when  being  com-
+       piled.  The limit applies to parentheses of all kinds, not just captur-
        ing parentheses.
 
        int pcre2_set_compile_recursion_guard(pcre2_compile_context *ccontext,
          int (*guard_function)(uint32_t, void *), void *user_data);
 
-       There  is at least one application that runs PCRE2 in threads with very
-       limited system stack, where running out of stack is to  be  avoided  at
-       all  costs. The parenthesis limit above cannot take account of how much
-       stack is actually available during compilation. For  a  finer  control,
-       you  can  supply  a  function  that  is called whenever pcre2_compile()
-       starts to compile a parenthesized part of a pattern. This function  can
-       check  the  actual  stack  size  (or anything else that it wants to, of
+       There is at least one application that runs PCRE2 in threads with  very
+       limited  system  stack,  where running out of stack is to be avoided at
+       all costs. The parenthesis limit above cannot take account of how  much
+       stack  is  actually  available during compilation. For a finer control,
+       you can supply a  function  that  is  called  whenever  pcre2_compile()
+       starts  to compile a parenthesized part of a pattern. This function can
+       check the actual stack size (or anything else  that  it  wants  to,  of
        course).
 
-       The first argument to the callout function gives the current  depth  of
-       nesting,  and  the second is user data that is set up by the last argu-
-       ment  of  pcre2_set_compile_recursion_guard().  The  callout   function
+       The  first  argument to the callout function gives the current depth of
+       nesting, and the second is user data that is set up by the  last  argu-
+       ment   of  pcre2_set_compile_recursion_guard().  The  callout  function
        should return zero if all is well, or non-zero to force an error.
 
    The match context
@@ -953,10 +991,10 @@ PCRE2 CONTEXTS
          Change the backtracking depth limit
          Set custom memory management specifically for the match
 
-       If  none  of  these  apply,  just  pass NULL as the context argument of
+       If none of these apply, just pass  NULL  as  the  context  argument  of
        pcre2_match(), pcre2_dfa_match(), or pcre2_jit_match().
 
-       A match context is created, copied, and freed by  the  following  func-
+       A  match  context  is created, copied, and freed by the following func-
        tions:
 
        pcre2_match_context *pcre2_match_context_create(
@@ -967,7 +1005,7 @@ PCRE2 CONTEXTS
 
        void pcre2_match_context_free(pcre2_match_context *mcontext);
 
-       A  match  context  is  created  with default values for its parameters.
+       A match context is created with  default  values  for  its  parameters.
        These can be changed by calling the following functions, which return 0
        on success, or PCRE2_ERROR_BADDATA if invalid data is detected.
 
@@ -983,7 +1021,7 @@ PCRE2 CONTEXTS
          int (*callout_function)(pcre2_substitute_callout_block *, void *),
          void *callout_data);
 
-       This  sets up a callout function for PCRE2 to call after each substitu-
+       This sets up a callout function for PCRE2 to call after each  substitu-
        tion made by pcre2_substitute(). Details are given in the section enti-
        tled "Creating a new string with substitutions" below.
 
@@ -996,13 +1034,13 @@ PCRE2 CONTEXTS
        MATCH if a match with a starting point before or at the given offset is
        not found. The pcre2_substitute() function makes no more substitutions.
 
-       For  example,  if the pattern /abc/ is matched against "123abc" with an
-       offset limit less than 3, the result is  PCRE2_ERROR_NOMATCH.  A  match
-       can  never  be  found  if  the  startoffset  argument of pcre2_match(),
-       pcre2_dfa_match(), or pcre2_substitute() is  greater  than  the  offset
+       For example, if the pattern /abc/ is matched against "123abc"  with  an
+       offset  limit  less  than 3, the result is PCRE2_ERROR_NOMATCH. A match
+       can never be  found  if  the  startoffset  argument  of  pcre2_match(),
+       pcre2_dfa_match(),  or  pcre2_substitute()  is  greater than the offset
        limit set in the match context.
 
-       When  using  this facility, you must set the PCRE2_USE_OFFSET_LIMIT op-
+       When using this facility, you must set the  PCRE2_USE_OFFSET_LIMIT  op-
        tion when calling pcre2_compile() so that when JIT is in use, different
        code  can  be  compiled. If a match is started with a non-default match
        limit when PCRE2_USE_OFFSET_LIMIT is not set, an error is generated.
@@ -1012,8 +1050,8 @@ PCRE2 CONTEXTS
        See also the PCRE2_FIRSTLINE option, which requires a  match  to  start
        before  or  at  the first newline that follows the start of matching in
        the subject. If this is set with an offset limit, a match must occur in
-       the first line and also within the offset limit. In other words, which-
-       ever limit comes first is used.
+       the first line and also  within  the  offset  limit.  In  other  words,
+       whichever limit comes first is used.
 
        int pcre2_set_heap_limit(pcre2_match_context *mcontext,
          uint32_t value);
@@ -1024,10 +1062,10 @@ PCRE2 CONTEXTS
        also applies to pcre2_dfa_match(), which may use the heap when process-
        ing patterns with a lot of nested pattern recursion or  lookarounds  or
        atomic groups. This limit does not apply to matching with the JIT opti-
-       mization, which has  its  own  memory  control  arrangements  (see  the
-       pcre2jit  documentation for more details). If the limit is reached, the
-       negative error code  PCRE2_ERROR_HEAPLIMIT  is  returned.  The  default
-       limit  can be set when PCRE2 is built; if it is not, the default is set
+       mization,  which  has  its  own  memory  control  arrangements (see the
+       pcre2jit documentation for more details). If the limit is reached,  the
+       negative  error  code  PCRE2_ERROR_HEAPLIMIT  is  returned. The default
+       limit can be set when PCRE2 is built; if it is not, the default is  set
        very large and is essentially unlimited.
 
        A value for the heap limit may also be supplied by an item at the start
@@ -1053,7 +1091,7 @@ PCRE2 CONTEXTS
          uint32_t value);
 
        The match_limit parameter provides a means of preventing PCRE2 from us-
-       ing up too many computing resources when processing patterns  that  are
+       ing  up  too many computing resources when processing patterns that are
        not going to match, but which have a very large number of possibilities
        in their search trees. The classic  example  is  a  pattern  that  uses
        nested unlimited repeats.
@@ -1061,36 +1099,36 @@ PCRE2 CONTEXTS
        There  is an internal counter in pcre2_match() that is incremented each
        time round its main matching loop. If  this  value  reaches  the  match
        limit, pcre2_match() returns the negative value PCRE2_ERROR_MATCHLIMIT.
-       This has the effect of limiting the amount  of  backtracking  that  can
+       This  has  the  effect  of limiting the amount of backtracking that can
        take place. For patterns that are not anchored, the count restarts from
        zero for each position in the subject string. This limit  also  applies
        to pcre2_dfa_match(), though the counting is done in a different way.
 
-       When  pcre2_match() is called with a pattern that was successfully pro-
-       cessed by pcre2_jit_compile(), the way in which matching is executed is
-       entirely  different. However, there is still the possibility of runaway
-       matching that goes on for a very long  time,  and  so  the  match_limit
+       When  pcre2_match()  is  called  with  a  pattern that was successfully
+       processed by pcre2_jit_compile(), the way in which matching is executed
+       is entirely different. However, there is still the possibility of  run-
+       away matching that goes on for a very long time, and so the match_limit
        value  is  also used in this case (but in a different way) to limit how
        long the matching can continue.
 
        The default value for the limit can be set when PCRE2 is built; the de-
-       fault  default  is  10  million, which handles all but the most extreme
-       cases. A value for the match limit may also be supplied by an  item  at
-       the start of a pattern of the form
+       fault is 10 million, which handles all but the most  extreme  cases.  A
+       value  for the match limit may also be supplied by an item at the start
+       of a pattern of the form
 
          (*LIMIT_MATCH=ddd)
 
-       where  ddd  is a decimal number. However, such a setting is ignored un-
-       less ddd is less than the limit set by the caller of  pcre2_match()  or
+       where ddd is a decimal number. However, such a setting is  ignored  un-
+       less  ddd  is less than the limit set by the caller of pcre2_match() or
        pcre2_dfa_match() or, if no such limit is set, less than the default.
 
        int pcre2_set_depth_limit(pcre2_match_context *mcontext,
          uint32_t value);
 
-       This   parameter   limits   the   depth   of   nested  backtracking  in
-       pcre2_match().  Each time a nested backtracking point is passed, a  new
-       memory  frame  is used to remember the state of matching at that point.
-       Thus, this parameter indirectly limits the amount  of  memory  that  is
+       This  parameter  limits   the   depth   of   nested   backtracking   in
+       pcre2_match().   Each time a nested backtracking point is passed, a new
+       memory frame is used to remember the state of matching at  that  point.
+       Thus,  this  parameter  indirectly  limits the amount of memory that is
        used in a match. However, because the size of each memory frame depends
        on the number of capturing parentheses, the actual memory limit  varies
        from  pattern to pattern. This limit was more useful in versions before
@@ -1098,12 +1136,12 @@ PCRE2 CONTEXTS
 
        The depth limit is not relevant, and is ignored, when matching is  done
        using JIT compiled code. However, it is supported by pcre2_dfa_match(),
-       which uses it to limit the depth of nested internal recursive  function
-       calls  that implement atomic groups, lookaround assertions, and pattern
+       which  uses it to limit the depth of nested internal recursive function
+       calls that implement atomic groups, lookaround assertions, and  pattern
        recursions. This limits, indirectly, the amount of system stack that is
        used.  It  was  more useful in versions before 10.32, when stack memory
        was used for local workspace vectors for recursive function calls. From
-       version  10.32,  only local variables are allocated on the stack and as
+       version 10.32, only local variables are allocated on the stack  and  as
        each call uses only a few hundred bytes, even a small stack can support
        quite a lot of recursion.
 
@@ -1111,13 +1149,13 @@ PCRE2 CONTEXTS
        cal workspace vectors are allocated on the heap from version 10.32  on-
        wards,  so  the  depth  limit also indirectly limits the amount of heap
        memory that is used. A recursive pattern such as /(.(?2))((?1)|)/, when
-       matched  to a very long string using pcre2_dfa_match(), can use a great
-       deal of memory. However, it is probably better to limit heap usage  di-
+       matched to a very long string using pcre2_dfa_match(), can use a  great
+       deal  of memory. However, it is probably better to limit heap usage di-
        rectly by calling pcre2_set_heap_limit().
 
-       The  default  value for the depth limit can be set when PCRE2 is built;
-       if it is not, the default is set to the same value as the  default  for
-       the   match   limit.   If  the  limit  is  exceeded,  pcre2_match()  or
+       The default value for the depth limit can be set when PCRE2  is  built;
+       if  it  is not, the default is set to the same value as the default for
+       the  match  limit.   If  the  limit  is  exceeded,   pcre2_match()   or
        pcre2_dfa_match() returns PCRE2_ERROR_DEPTHLIMIT. A value for the depth
        limit  may also be supplied by an item at the start of a pattern of the
        form
@@ -1162,39 +1200,42 @@ CHECKING BUILD-TIME OPTIONS
 
          PCRE2_CONFIG_COMPILED_WIDTHS
 
-       The  output  is a uint32_t integer whose lower bits indicate which code
-       unit widths were selected when PCRE2 was  built.  The  1-bit  indicates
-       8-bit  support, and the 2-bit and 4-bit indicate 16-bit and 32-bit sup-
+       The output is a uint32_t integer whose lower bits indicate  which  code
+       unit  widths  were  selected  when PCRE2 was built. The 1-bit indicates
+       8-bit support, and the 2-bit and 4-bit indicate 16-bit and 32-bit  sup-
        port, respectively.
 
          PCRE2_CONFIG_DEPTHLIMIT
 
-       The output is a uint32_t integer that gives the default limit  for  the
-       depth  of  nested  backtracking in pcre2_match() or the depth of nested
-       recursions, lookarounds, and atomic groups in  pcre2_dfa_match().  Fur-
+       The  output  is a uint32_t integer that gives the default limit for the
+       depth of nested backtracking in pcre2_match() or the  depth  of  nested
+       recursions,  lookarounds,  and atomic groups in pcre2_dfa_match(). Fur-
        ther details are given with pcre2_set_depth_limit() above.
 
          PCRE2_CONFIG_HEAPLIMIT
 
-       The  output is a uint32_t integer that gives, in kibibytes, the default
-       limit  for  the  amount  of  heap  memory  used  by  pcre2_match()   or
-       pcre2_dfa_match().      Further      details     are     given     with
+       The output is a uint32_t integer that gives, in kibibytes, the  default
+       limit   for  the  amount  of  heap  memory  used  by  pcre2_match()  or
+       pcre2_dfa_match().     Further     details     are      given      with
        pcre2_set_heap_limit() above.
 
          PCRE2_CONFIG_JIT
 
-       The output is a uint32_t integer that is set  to  one  if  support  for
-       just-in-time compiling is available; otherwise it is set to zero.
+       The  output  is  a  uint32_t  integer that is set to one if support for
+       just-in-time compiling is included in the library; otherwise it is  set
+       to zero. Note that having the support in the library does not guarantee
+       that  JIT will be used for any given match. See the pcre2jit documenta-
+       tion for more details.
 
          PCRE2_CONFIG_JITTARGET
 
-       The  where  argument  should point to a buffer that is at least 48 code
-       units long.  (The  exact  length  required  can  be  found  by  calling
-       pcre2_config()  with  where  set  to NULL.) The buffer is filled with a
-       string that contains the name of the architecture  for  which  the  JIT
-       compiler  is  configured,  for  example "x86 32bit (little endian + un-
-       aligned)". If JIT support is not  available,  PCRE2_ERROR_BADOPTION  is
-       returned,  otherwise the number of code units used is returned. This is
+       The where argument should point to a buffer that is at  least  48  code
+       units  long.  (The  exact  length  required  can  be  found  by calling
+       pcre2_config() with where set to NULL.) The buffer  is  filled  with  a
+       string  that  contains  the  name of the architecture for which the JIT
+       compiler is configured, for example "x86 32bit  (little  endian  +  un-
+       aligned)".  If  JIT  support is not available, PCRE2_ERROR_BADOPTION is
+       returned, otherwise the number of code units used is returned. This  is
        the length of the string, plus one unit for the terminating zero.
 
          PCRE2_CONFIG_LINKSIZE
@@ -1208,9 +1249,9 @@ CHECKING BUILD-TIME OPTIONS
        bytes, so the configured value is not relevant.
 
        The default value of 2 for the 8-bit and 16-bit libraries is sufficient
-       for  all but the most massive patterns, since it allows the size of the
-       compiled pattern to be up to 65535  code  units.  Larger  values  allow
-       larger  regular  expressions to be compiled by those two libraries, but
+       for all but the most massive patterns, since it allows the size of  the
+       compiled  pattern  to  be  up  to 65535 code units. Larger values allow
+       larger regular expressions to be compiled by those two  libraries,  but
        at the expense of slower matching.
 
          PCRE2_CONFIG_MATCHLIMIT
@@ -1245,8 +1286,8 @@ CHECKING BUILD-TIME OPTIONS
 
        The  output is a uint32_t integer that gives the maximum depth of nest-
        ing of parentheses (of any kind) in a pattern. This limit is imposed to
-       cap  the  amount of system stack used when a pattern is compiled. It is
-       specified when PCRE2 is built; the default is 250. This limit does  not
+       cap the amount of system stack used when a pattern is compiled.  It  is
+       specified  when PCRE2 is built; the default is 250. This limit does not
        take into account the stack that may already be used by the calling ap-
        plication.  For  finer  control  over  compilation  stack  usage,   see
        pcre2_set_compile_recursion_guard().
@@ -1302,10 +1343,12 @@ COMPILING A PATTERN
 
        The  pcre2_compile() function compiles a pattern into an internal form.
        The pattern is defined by a pointer to a string of  code  units  and  a
-       length  (in  code units). If the pattern is zero-terminated, the length
-       can be specified  as  PCRE2_ZERO_TERMINATED.  The  function  returns  a
-       pointer to a block of memory that contains the compiled pattern and re-
-       lated data, or NULL if an error occurred.
+       length in code units. If the pattern is zero-terminated, the length can
+       be  specified  as  PCRE2_ZERO_TERMINATED. A NULL pattern pointer with a
+       length of zero is treated as an empty  string  (NULL  with  a  non-zero
+       length  causes  an  error  return). The function returns a pointer to a
+       block of memory that contains the compiled pattern and related data, or
+       NULL if an error occurred.
 
        If the compile context argument ccontext is NULL, memory for  the  com-
        piled  pattern  is  obtained  by calling malloc(). Otherwise, it is ob-
@@ -1323,12 +1366,12 @@ COMPILING A PATTERN
        pcre2_code_copy() is called with a NULL argument, it returns NULL.
 
        The pcre2_code_copy() function provides a way for individual threads in
-       a multithreaded application to acquire a private copy  of  shared  com-
-       piled  code.   However, it does not make a copy of the character tables
-       used by the compiled pattern; the new pattern code points to  the  same
-       tables  as  the original code.  (See "Locale Support" below for details
-       of these character tables.) In many applications the  same  tables  are
-       used  throughout, so this behaviour is appropriate. Nevertheless, there
+       a  multithreaded  application  to acquire a private copy of shared com-
+       piled code.  However, it does not make a copy of the  character  tables
+       used  by  the compiled pattern; the new pattern code points to the same
+       tables as the original code.  (See "Locale Support" below  for  details
+       of  these  character  tables.) In many applications the same tables are
+       used throughout, so this behaviour is appropriate. Nevertheless,  there
        are occasions when a copy of a compiled pattern and the relevant tables
        are  needed.  The pcre2_code_copy_with_tables() provides this facility.
        Copies of both the code and the tables are  made,  with  the  new  code
@@ -1339,49 +1382,49 @@ COMPILING A PATTERN
 
        NOTE: When one of the matching functions is  called,  pointers  to  the
        compiled pattern and the subject string are set in the match data block
-       so that they can be referenced by the  substring  extraction  functions
-       after  a  successful match.  After running a match, you must not free a
-       compiled pattern or a subject string until after all operations on  the
-       match  data  block have taken place, unless, in the case of the subject
-       string, you have used the PCRE2_COPY_MATCHED_SUBJECT option,  which  is
-       described  in  the section entitled "Option bits for pcre2_match()" be-
+       so  that  they  can be referenced by the substring extraction functions
+       after a successful match.  After running a match, you must not  free  a
+       compiled  pattern or a subject string until after all operations on the
+       match data block have taken place, unless, in the case of  the  subject
+       string,  you  have used the PCRE2_COPY_MATCHED_SUBJECT option, which is
+       described in the section entitled "Option bits for  pcre2_match()"  be-
        low.
 
-       The options argument for pcre2_compile() contains various bit  settings
-       that  affect the compilation. It should be zero if none of them are re-
-       quired. The available options are described below.  Some  of  them  (in
-       particular,  those  that  are  compatible with Perl, but some others as
-       well) can also be set and unset from within the pattern  (see  the  de-
+       The  options argument for pcre2_compile() contains various bit settings
+       that affect the compilation. It should be zero if none of them are  re-
+       quired.  The  available  options  are described below. Some of them (in
+       particular, those that are compatible with Perl,  but  some  others  as
+       well)  can  also  be set and unset from within the pattern (see the de-
        tailed description in the pcre2pattern documentation).
 
-       For  those options that can be different in different parts of the pat-
-       tern, the contents of the options argument specifies their settings  at
-       the  start  of  compilation. The PCRE2_ANCHORED, PCRE2_ENDANCHORED, and
-       PCRE2_NO_UTF_CHECK options can be set at the time of matching  as  well
+       For those options that can be different in different parts of the  pat-
+       tern,  the contents of the options argument specifies their settings at
+       the start of compilation. The  PCRE2_ANCHORED,  PCRE2_ENDANCHORED,  and
+       PCRE2_NO_UTF_CHECK  options  can be set at the time of matching as well
        as at compile time.
 
-       Some  additional  options and less frequently required compile-time pa-
-       rameters (for example, the newline setting) can be provided in  a  com-
-       pile context (as described above).
+       Some additional options and less frequently required compile-time para-
+       meters (for example, the newline setting) can be provided in a  compile
+       context (as described above).
 
        If errorcode or erroroffset is NULL, pcre2_compile() returns NULL imme-
-       diately. Otherwise, the variables to which these point are  set  to  an
+       diately.  Otherwise,  the  variables to which these point are set to an
        error code and an offset (number of code units) within the pattern, re-
        spectively, when pcre2_compile() returns NULL because a compilation er-
        ror has occurred.
 
-       There  are nearly 100 positive error codes that pcre2_compile() may re-
-       turn if it finds an error in the pattern. There are also some  negative
-       error  codes that are used for invalid UTF strings when validity check-
-       ing is in force. These are the  same  as  given  by  pcre2_match()  and
+       There are nearly 100 positive error codes that pcre2_compile() may  re-
+       turn  if it finds an error in the pattern. There are also some negative
+       error codes that are used for invalid UTF strings when validity  check-
+       ing  is  in  force.  These  are  the same as given by pcre2_match() and
        pcre2_dfa_match(), and are described in the pcre2unicode documentation.
        There is no separate documentation for the positive  error  codes,  be-
        cause  the  textual  error  messages  that  are obtained by calling the
        pcre2_get_error_message() function (see "Obtaining a textual error mes-
-       sage"  below)  should  be  self-explanatory.  Macro names starting with
-       PCRE2_ERROR_ are defined for both positive and negative error codes  in
-       pcre2.h.  When  compilation  is  successful errorcode is set to a value
-       that returns the message "no error" if passed  to  pcre2_get_error_mes-
+       sage" below) should be  self-explanatory.  Macro  names  starting  with
+       PCRE2_ERROR_  are defined for both positive and negative error codes in
+       pcre2.h. When compilation is successful errorcode is  set  to  a  value
+       that  returns  the message "no error" if passed to pcre2_get_error_mes-
        sage().
 
        The value returned in erroroffset is an indication of where in the pat-
@@ -1392,9 +1435,9 @@ COMPILING A PATTERN
        assertion. For an invalid UTF-8 or UTF-16 string, the offset is that of
        the first code unit of the failing character.
 
-       Some  errors are not detected until the whole pattern has been scanned;
-       in these cases, the offset passed back is the length  of  the  pattern.
-       Note  that  the  offset is in code units, not characters, even in a UTF
+       Some errors are not detected until the whole pattern has been  scanned;
+       in  these  cases,  the offset passed back is the length of the pattern.
+       Note that the offset is in code units, not characters, even  in  a  UTF
        mode. It may sometimes point into the middle of a UTF-8 or UTF-16 char-
        acter.
 
@@ -1421,40 +1464,40 @@ COMPILING A PATTERN
          PCRE2_ANCHORED
 
        If this bit is set, the pattern is forced to be "anchored", that is, it
-       is constrained to match only at the first matching point in the  string
-       that  is being searched (the "subject string"). This effect can also be
-       achieved by appropriate constructs in the pattern itself, which is  the
+       is  constrained to match only at the first matching point in the string
+       that is being searched (the "subject string"). This effect can also  be
+       achieved  by appropriate constructs in the pattern itself, which is the
        only way to do it in Perl.
 
          PCRE2_ALLOW_EMPTY_CLASS
 
-       By  default, for compatibility with Perl, a closing square bracket that
-       immediately follows an opening one is treated as a data  character  for
-       the  class.  When  PCRE2_ALLOW_EMPTY_CLASS  is  set,  it terminates the
+       By default, for compatibility with Perl, a closing square bracket  that
+       immediately  follows  an opening one is treated as a data character for
+       the class. When  PCRE2_ALLOW_EMPTY_CLASS  is  set,  it  terminates  the
        class, which therefore contains no characters and so can never match.
 
          PCRE2_ALT_BSUX
 
-       This option request alternative handling  of  three  escape  sequences,
-       which  makes  PCRE2's  behaviour more like ECMAscript (aka JavaScript).
+       This  option  request  alternative  handling of three escape sequences,
+       which makes PCRE2's behaviour more like  ECMAscript  (aka  JavaScript).
        When it is set:
 
        (1) \U matches an upper case "U" character; by default \U causes a com-
        pile time error (Perl uses \U to upper case subsequent characters).
 
        (2) \u matches a lower case "u" character unless it is followed by four
-       hexadecimal digits, in which case the hexadecimal  number  defines  the
-       code  point  to match. By default, \u causes a compile time error (Perl
+       hexadecimal  digits,  in  which case the hexadecimal number defines the
+       code point to match. By default, \u causes a compile time  error  (Perl
        uses it to upper case the following character).
 
-       (3) \x matches a lower case "x" character unless it is followed by  two
-       hexadecimal  digits,  in  which case the hexadecimal number defines the
-       code point to match. By default, as in Perl, a  hexadecimal  number  is
+       (3)  \x matches a lower case "x" character unless it is followed by two
+       hexadecimal digits, in which case the hexadecimal  number  defines  the
+       code  point  to  match. By default, as in Perl, a hexadecimal number is
        always expected after \x, but it may have zero, one, or two digits (so,
        for example, \xz matches a binary zero character followed by z).
 
        ECMAscript 6 added additional functionality to \u. This can be accessed
-       using  the  PCRE2_EXTRA_ALT_BSUX  extra  option (see "Extra compile op-
+       using the PCRE2_EXTRA_ALT_BSUX extra option  (see  "Extra  compile  op-
        tions" below).  Note that this alternative escape handling applies only
        to  patterns.  Neither  of  these options affects the processing of re-
        placement strings passed to pcre2_substitute().
@@ -1465,62 +1508,65 @@ COMPILING A PATTERN
        metacharacter  matches at the start of the subject (unless PCRE2_NOTBOL
        is set), and also after any internal  newline.  However,  it  does  not
        match after a newline at the end of the subject, for compatibility with
-       Perl. If you want a multiline circumflex also to match after  a  termi-
+       Perl.  If  you want a multiline circumflex also to match after a termi-
        nating newline, you must set PCRE2_ALT_CIRCUMFLEX.
 
          PCRE2_ALT_VERBNAMES
 
-       By  default, for compatibility with Perl, the name in any verb sequence
-       such as (*MARK:NAME) is any sequence of characters that  does  not  in-
-       clude  a closing parenthesis. The name is not processed in any way, and
-       it is not possible to include a closing parenthesis in the  name.  How-
-       ever,  if  the PCRE2_ALT_VERBNAMES option is set, normal backslash pro-
-       cessing is applied to verb names and only an unescaped  closing  paren-
-       thesis  terminates the name. A closing parenthesis can be included in a
-       name either as \) or between  \Q  and  \E.  If  the  PCRE2_EXTENDED  or
-       PCRE2_EXTENDED_MORE  option  is set with PCRE2_ALT_VERBNAMES, unescaped
-       whitespace in verb names is skipped and #-comments are recognized,  ex-
+       By default, for compatibility with Perl, the name in any verb  sequence
+       such  as  (*MARK:NAME)  is any sequence of characters that does not in-
+       clude a closing parenthesis. The name is not processed in any way,  and
+       it  is  not possible to include a closing parenthesis in the name. How-
+       ever, if the PCRE2_ALT_VERBNAMES option is set, normal  backslash  pro-
+       cessing  is  applied to verb names and only an unescaped closing paren-
+       thesis terminates the name. A closing parenthesis can be included in  a
+       name  either  as  \)  or  between  \Q  and \E. If the PCRE2_EXTENDED or
+       PCRE2_EXTENDED_MORE option is set with  PCRE2_ALT_VERBNAMES,  unescaped
+       whitespace  in verb names is skipped and #-comments are recognized, ex-
        actly as in the rest of the pattern.
 
          PCRE2_AUTO_CALLOUT
 
-       If  this  bit  is  set,  pcre2_compile()  automatically inserts callout
-       items, all with number 255, before each pattern  item,  except  immedi-
-       ately  before  or after an explicit callout in the pattern. For discus-
+       If this bit  is  set,  pcre2_compile()  automatically  inserts  callout
+       items,  all  with  number 255, before each pattern item, except immedi-
+       ately before or after an explicit callout in the pattern.  For  discus-
        sion of the callout facility, see the pcre2callout documentation.
 
          PCRE2_CASELESS
 
-       If this bit is set, letters in the pattern match both upper  and  lower
-       case  letters in the subject. It is equivalent to Perl's /i option, and
-       it can be changed within a pattern by a (?i) option setting. If  either
-       PCRE2_UTF  or  PCRE2_UCP  is  set,  Unicode properties are used for all
-       characters with more than one other case, and for all characters  whose
-       code  points  are  greater  than  U+007F. Note that there are two ASCII
+       If  this  bit is set, letters in the pattern match both upper and lower
+       case letters in the subject. It is equivalent to Perl's /i option,  and
+       it  can be changed within a pattern by a (?i) option setting. If either
+       PCRE2_UTF or PCRE2_UCP is set, Unicode  properties  are  used  for  all
+       characters  with more than one other case, and for all characters whose
+       code points are greater than U+007F. Note  that  there  are  two  ASCII
        characters, K and S, that, in addition to their lower case ASCII equiv-
        alents,  are case-equivalent with U+212A (Kelvin sign) and U+017F (long
-       S) respectively. For lower valued characters with only one other  case,
-       a  lookup table is used for speed. When neither PCRE2_UTF nor PCRE2_UCP
-       is set, a lookup table is used for all code points less than  256,  and
-       higher  code  points  (available  only  in  16-bit  or 32-bit mode) are
-       treated as not having another case.
+       S) respectively. If you do not want this case equivalence, you can sup-
+       press it by setting PCRE2_EXTRA_CASELESS_RESTRICT.
+
+       For lower valued characters with only one other case, a lookup table is
+       used for speed. When neither PCRE2_UTF nor PCRE2_UCP is set,  a  lookup
+       table is used for all code points less than 256, and higher code points
+       (available only in 16-bit or 32-bit mode) are treated as not having an-
+       other case.
 
          PCRE2_DOLLAR_ENDONLY
 
-       If this bit is set, a dollar metacharacter in the pattern matches  only
-       at  the  end  of the subject string. Without this option, a dollar also
-       matches immediately before a newline at the end of the string (but  not
-       before  any other newlines). The PCRE2_DOLLAR_ENDONLY option is ignored
-       if PCRE2_MULTILINE is set. There is no equivalent  to  this  option  in
+       If  this bit is set, a dollar metacharacter in the pattern matches only
+       at the end of the subject string. Without this option,  a  dollar  also
+       matches  immediately before a newline at the end of the string (but not
+       before any other newlines). The PCRE2_DOLLAR_ENDONLY option is  ignored
+       if  PCRE2_MULTILINE  is  set.  There is no equivalent to this option in
        Perl, and no way to set it within a pattern.
 
          PCRE2_DOTALL
 
-       If  this  bit  is  set,  a dot metacharacter in the pattern matches any
-       character, including one that indicates a  newline.  However,  it  only
+       If this bit is set, a dot metacharacter  in  the  pattern  matches  any
+       character,  including  one  that  indicates a newline. However, it only
        ever matches one character, even if newlines are coded as CRLF. Without
        this option, a dot does not match when the current position in the sub-
-       ject  is  at  a newline. This option is equivalent to Perl's /s option,
+       ject is at a newline. This option is equivalent to  Perl's  /s  option,
        and it can be changed within a pattern by a (?s) option setting. A neg-
        ative  class such as [^a] always matches newline characters, and the \N
        escape sequence always matches a non-newline character, independent  of
@@ -1542,15 +1588,15 @@ COMPILING A PATTERN
        subject, the match fails at the current starting point. For  unanchored
        patterns,  a  new  match is then tried at the next starting point. How-
        ever, if the match succeeds by reaching the end of the pattern, but not
-       the  end  of  the subject, backtracking occurs and an alternative match
+       the end of the subject, backtracking occurs and  an  alternative  match
        may be found. Consider these two patterns:
 
          .(*ACCEPT)|..
          .|..
 
-       If matched against "abc" with PCRE2_ENDANCHORED set, the first  matches
-       "c"  whereas  the  second matches "bc". The effect of PCRE2_ENDANCHORED
-       can also be achieved by appropriate constructs in the  pattern  itself,
+       If  matched against "abc" with PCRE2_ENDANCHORED set, the first matches
+       "c" whereas the second matches "bc". The  effect  of  PCRE2_ENDANCHORED
+       can  also  be achieved by appropriate constructs in the pattern itself,
        which is the only way to do it in Perl.
 
        For DFA matching with pcre2_dfa_match(), PCRE2_ENDANCHORED applies only
@@ -1561,52 +1607,53 @@ COMPILING A PATTERN
          PCRE2_EXTENDED
 
        If this bit is set, most white space characters in the pattern are  to-
-       tally ignored except when escaped or inside a character class. However,
-       white space is not allowed within sequences such as (?> that  introduce
-       various  parenthesized groups, nor within numerical quantifiers such as
-       {1,3}. Ignorable white space is permitted between an item and a follow-
-       ing  quantifier  and  between a quantifier and a following + that indi-
-       cates possessiveness. PCRE2_EXTENDED is equivalent to Perl's /x option,
-       and it can be changed within a pattern by a (?x) option setting.
-
-       When  PCRE2  is compiled without Unicode support, PCRE2_EXTENDED recog-
-       nizes as white space only those characters with code points  less  than
+       tally  ignored except when escaped, inside a character class, or inside
+       a \Q...\E sequence. However, white space  is  not  allowed  within  se-
+       quences  such  as  (?> that introduce various parenthesized groups, nor
+       within numerical quantifiers such as {1,3}. Ignorable  white  space  is
+       permitted  between  an  item  and  a following quantifier and between a
+       quantifier and a following + that indicates  possessiveness.  PCRE2_EX-
+       TENDED  is equivalent to Perl's /x option, and it can be changed within
+       a pattern by a (?x) option setting.
+
+       When PCRE2 is compiled without Unicode support,  PCRE2_EXTENDED  recog-
+       nizes  as  white space only those characters with code points less than
        256 that are flagged as white space in its low-character table. The ta-
        ble is normally created by pcre2_maketables(), which uses the isspace()
-       function  to identify space characters. In most ASCII environments, the
-       relevant characters are those with code  points  0x0009  (tab),  0x000A
-       (linefeed),  0x000B (vertical tab), 0x000C (formfeed), 0x000D (carriage
+       function to identify space characters. In most ASCII environments,  the
+       relevant  characters  are  those  with code points 0x0009 (tab), 0x000A
+       (linefeed), 0x000B (vertical tab), 0x000C (formfeed), 0x000D  (carriage
        return), and 0x0020 (space).
 
        When PCRE2 is compiled with Unicode support, in addition to these char-
        acters,  five  more Unicode "Pattern White Space" characters are recog-
        nized by PCRE2_EXTENDED. These are U+0085 (next line), U+200E (left-to-
-       right  mark), U+200F (right-to-left mark), U+2028 (line separator), and
-       U+2029 (paragraph separator). This set of characters  is  the  same  as
-       recognized  by  Perl's /x option. Note that the horizontal and vertical
-       space characters that are matched by the \h and \v escapes in  patterns
+       right mark), U+200F (right-to-left mark), U+2028 (line separator),  and
+       U+2029  (paragraph  separator).  This  set of characters is the same as
+       recognized by Perl's /x option. Note that the horizontal  and  vertical
+       space  characters that are matched by the \h and \v escapes in patterns
        are a much bigger set.
 
-       As  well as ignoring most white space, PCRE2_EXTENDED also causes char-
-       acters between an unescaped # outside a character class  and  the  next
-       newline,  inclusive,  to be ignored, which makes it possible to include
+       As well as ignoring most white space, PCRE2_EXTENDED also causes  char-
+       acters  between  an  unescaped # outside a character class and the next
+       newline, inclusive, to be ignored, which makes it possible  to  include
        comments inside complicated patterns. Note that the end of this type of
        comment  is a literal newline sequence in the pattern; escape sequences
        that happen to represent a newline do not count.
 
        Which characters are interpreted as newlines can be specified by a set-
-       ting  in  the compile context that is passed to pcre2_compile() or by a
-       special sequence at the start of the pattern, as described in the  sec-
-       tion  entitled "Newline conventions" in the pcre2pattern documentation.
+       ting in the compile context that is passed to pcre2_compile() or  by  a
+       special  sequence at the start of the pattern, as described in the sec-
+       tion entitled "Newline conventions" in the pcre2pattern  documentation.
        A default is defined when PCRE2 is built.
 
          PCRE2_EXTENDED_MORE
 
-       This option has the effect of PCRE2_EXTENDED,  but,  in  addition,  un-
-       escaped  space and horizontal tab characters are ignored inside a char-
-       acter class. Note: only these two characters are ignored, not the  full
-       set  of pattern white space characters that are ignored outside a char-
-       acter class. PCRE2_EXTENDED_MORE is equivalent to  Perl's  /xx  option,
+       This  option  has  the  effect of PCRE2_EXTENDED, but, in addition, un-
+       escaped space and horizontal tab characters are ignored inside a  char-
+       acter  class. Note: only these two characters are ignored, not the full
+       set of pattern white space characters that are ignored outside a  char-
+       acter  class.  PCRE2_EXTENDED_MORE  is equivalent to Perl's /xx option,
        and it can be changed within a pattern by a (?xx) option setting.
 
          PCRE2_FIRSTLINE
@@ -1615,18 +1662,19 @@ COMPILING A PATTERN
        before or at the first newline in  the  subject  string  following  the
        start  of  matching, though the matched text may continue over the new-
        line. If startoffset is non-zero, the limiting newline is not necessar-
-       ily  the  first  newline  in  the  subject. For example, if the subject
+       ily the first newline in the  subject.  For  example,  if  the  subject
        string is "abc\nxyz" (where \n represents a single-character newline) a
        pattern  match for "yz" succeeds with PCRE2_FIRSTLINE if startoffset is
        greater than 3. See also PCRE2_USE_OFFSET_LIMIT, which provides a  more
        general  limiting  facility.  If  PCRE2_FIRSTLINE is set with an offset
        limit, a match must occur in the first line and also within the  offset
-       limit. In other words, whichever limit comes first is used.
+       limit. In other words, whichever limit comes first is used. This option
+       has no effect for anchored patterns.
 
          PCRE2_LITERAL
 
        If this option is set, all meta-characters in the pattern are disabled,
-       and it is treated as a literal string. Matching literal strings with  a
+       and  it is treated as a literal string. Matching literal strings with a
        regular expression engine is not the most efficient way of doing it. If
        you are doing a lot of literal matching and  are  worried  about  effi-
        ciency, you should consider using other approaches. The only other main
@@ -1639,28 +1687,32 @@ COMPILING A PATTERN
 
          PCRE2_MATCH_INVALID_UTF
 
-       This  option  forces PCRE2_UTF (see below) and also enables support for
-       matching by pcre2_match() in subject strings that contain  invalid  UTF
-       sequences.   This  facility  is not supported for DFA matching. For de-
-       tails, see the pcre2unicode documentation.
+       This option forces PCRE2_UTF (see below) and also enables  support  for
+       matching  by  pcre2_match() in subject strings that contain invalid UTF
+       sequences.  Note, however, that the 16-bit and 32-bit  PCRE2  libraries
+       process  strings as sequences of uint16_t or uint32_t code points. They
+       cannot find valid UTF sequences within an arbitrary string of bytes un-
+       less such sequences are suitably aligned. This  facility  is  not  sup-
+       ported  for  DFA matching. For details, see the pcre2unicode documenta-
+       tion.
 
          PCRE2_MATCH_UNSET_BACKREF
 
        If this option is set,  a  backreference  to  an  unset  capture  group
        matches  an  empty  string (by default this causes the current matching
        alternative to fail).  A pattern such as (\1)(a) succeeds when this op-
-       tion  is  set  (assuming it can find an "a" in the subject), whereas it
-       fails by default, for Perl compatibility.  Setting  this  option  makes
+       tion is set (assuming it can find an "a" in the  subject),  whereas  it
+       fails  by  default,  for  Perl compatibility. Setting this option makes
        PCRE2 behave more like ECMAscript (aka JavaScript).
 
          PCRE2_MULTILINE
 
-       By  default,  for  the purposes of matching "start of line" and "end of
-       line", PCRE2 treats the subject string as consisting of a  single  line
-       of  characters,  even  if  it actually contains newlines. The "start of
-       line" metacharacter (^) matches only at the start of  the  string,  and
-       the  "end  of  line"  metacharacter  ($) matches only at the end of the
-       string, or before a terminating newline (except  when  PCRE2_DOLLAR_EN-
+       By default, for the purposes of matching "start of line"  and  "end  of
+       line",  PCRE2  treats the subject string as consisting of a single line
+       of characters, even if it actually contains  newlines.  The  "start  of
+       line"  metacharacter  (^)  matches only at the start of the string, and
+       the "end of line" metacharacter ($) matches only  at  the  end  of  the
+       string,  or  before a terminating newline (except when PCRE2_DOLLAR_EN-
        DONLY is set). Note, however, that unless PCRE2_DOTALL is set, the "any
        character" metacharacter (.) does not match at a newline.  This  behav-
        iour (for ^, $, and dot) is the same as Perl.
@@ -1689,9 +1741,9 @@ COMPILING A PATTERN
 
        This  option  locks  out the use of Unicode properties for handling \B,
        \b, \D, \d, \S, \s, \W, \w, and some of the POSIX character classes, as
-       described  for  the  PCRE2_UCP option below. In particular, it prevents
-       the creator of the pattern from enabling this facility by starting  the
-       pattern  with  (*UCP).  This  option may be useful in applications that
+       described for the PCRE2_UCP option below. In  particular,  it  prevents
+       the  creator of the pattern from enabling this facility by starting the
+       pattern with (*UCP). This option may be  useful  in  applications  that
        process patterns from external sources. The option combination PCRE_UCP
        and PCRE_NEVER_UCP causes an error.
 
@@ -1699,16 +1751,16 @@ COMPILING A PATTERN
 
        This  option  locks out interpretation of the pattern as UTF-8, UTF-16,
        or UTF-32, depending on which library is in use. In particular, it pre-
-       vents  the  creator of the pattern from switching to UTF interpretation
-       by starting the pattern with (*UTF). This option may be useful  in  ap-
+       vents the creator of the pattern from switching to  UTF  interpretation
+       by  starting  the pattern with (*UTF). This option may be useful in ap-
        plications that process patterns from external sources. The combination
        of PCRE2_UTF and PCRE2_NEVER_UTF causes an error.
 
          PCRE2_NO_AUTO_CAPTURE
 
        If this option is set, it disables the use of numbered capturing paren-
-       theses  in the pattern. Any opening parenthesis that is not followed by
-       ? behaves as if it were followed by ?: but named parentheses can  still
+       theses in the pattern. Any opening parenthesis that is not followed  by
+       ?  behaves as if it were followed by ?: but named parentheses can still
        be used for capturing (and they acquire numbers in the usual way). This
        is the same as Perl's /n option.  Note that, when this option  is  set,
        references  to  capture  groups (backreferences or recursion/subroutine
@@ -1718,9 +1770,9 @@ COMPILING A PATTERN
          PCRE2_NO_AUTO_POSSESS
 
        If this option is set, it disables "auto-possessification", which is an
-       optimization that, for example, turns a+b into a++b in order  to  avoid
-       backtracks  into  a+ that can never be successful. However, if callouts
-       are in use, auto-possessification means that some  callouts  are  never
+       optimization  that,  for example, turns a+b into a++b in order to avoid
+       backtracks into a+ that can never be successful. However,  if  callouts
+       are  in  use,  auto-possessification means that some callouts are never
        taken. You can set this option if you want the matching functions to do
        a full unoptimized search and run all the callouts, but  it  is  mainly
        provided for testing purposes.
@@ -1728,20 +1780,20 @@ COMPILING A PATTERN
          PCRE2_NO_DOTSTAR_ANCHOR
 
        If this option is set, it disables an optimization that is applied when
-       .* is the first significant item in a top-level branch  of  a  pattern,
-       and  all  the  other branches also start with .* or with \A or \G or ^.
-       The optimization is automatically disabled for .* if it  is  inside  an
+       .*  is  the  first significant item in a top-level branch of a pattern,
+       and all the other branches also start with .* or with \A or  \G  or  ^.
+       The  optimization  is  automatically disabled for .* if it is inside an
        atomic group or a capture group that is the subject of a backreference,
        or if the pattern contains (*PRUNE) or (*SKIP). When  the  optimization
        is   not   disabled,  such  a  pattern  is  automatically  anchored  if
        PCRE2_DOTALL is set for all the .* items and PCRE2_MULTILINE is not set
-       for  any  ^ items. Otherwise, the fact that any match must start either
-       at the start of the subject or following a newline is remembered.  Like
+       for any ^ items. Otherwise, the fact that any match must  start  either
+       at  the start of the subject or following a newline is remembered. Like
        other optimizations, this can cause callouts to be skipped.
 
          PCRE2_NO_START_OPTIMIZE
 
-       This  is  an  option whose main effect is at matching time. It does not
+       This is an option whose main effect is at matching time.  It  does  not
        change what pcre2_compile() generates, but it does affect the output of
        the JIT compiler.
 
@@ -1759,8 +1811,8 @@ COMPILING A PATTERN
        the pattern is run.
 
        The PCRE2_NO_START_OPTIMIZE option disables the start-up optimizations,
-       possibly  causing  performance  to  suffer,  but ensuring that in cases
-       where the result is "no match", the callouts do occur, and  that  items
+       possibly causing performance to suffer,  but  ensuring  that  in  cases
+       where  the  result is "no match", the callouts do occur, and that items
        such as (*COMMIT) and (*MARK) are considered at every possible starting
        position in the subject string.
 
@@ -1787,14 +1839,14 @@ COMPILING A PATTERN
 
        The  minimum  length  for  a match is two characters. If the subject is
        "XXBB", the "starting character" optimization skips "XX", then tries to
-       match  "BB", which is long enough. In the process, (*MARK:2) is encoun-
-       tered and remembered. When the match attempt fails,  the  next  "B"  is
-       found,  but  there is only one character left, so there are no more at-
-       tempts, and "no match" is returned with the "last  mark  seen"  set  to
-       "2".  If  NO_START_OPTIMIZE is set, however, matches are tried at every
-       possible starting position, including at the end of the subject,  where
-       (*MARK:1)  is encountered, but there is no "B", so the "last mark seen"
-       that is returned is "1". In this case, the optimizations do not  affect
+       match "BB", which is long enough. In the process, (*MARK:2) is  encoun-
+       tered  and  remembered.  When  the match attempt fails, the next "B" is
+       found, but there is only one character left, so there are no  more  at-
+       tempts,  and  "no  match"  is returned with the "last mark seen" set to
+       "2". If NO_START_OPTIMIZE is set, however, matches are tried  at  every
+       possible  starting position, including at the end of the subject, where
+       (*MARK:1) is encountered, but there is no "B", so the "last mark  seen"
+       that  is returned is "1". In this case, the optimizations do not affect
        the overall match result, which is still "no match", but they do affect
        the auxiliary information that is returned.
 
@@ -1809,11 +1861,11 @@ COMPILING A PATTERN
        If you know that your pattern is a valid UTF string, and  you  want  to
        skip   this   check   for   performance   reasons,   you  can  set  the
        PCRE2_NO_UTF_CHECK option. When it is set, the effect of passing an in-
-       valid  UTF  string as a pattern is undefined. It may cause your program
+       valid UTF string as a pattern is undefined. It may cause  your  program
        to crash or loop.
 
        Note  that  this  option  can  also  be  passed  to  pcre2_match()  and
-       pcre2_dfa_match(),  to  suppress  UTF  validity checking of the subject
+       pcre2_dfa_match(), to suppress UTF validity  checking  of  the  subject
        string.
 
        Note also that setting PCRE2_NO_UTF_CHECK at compile time does not dis-
@@ -1831,17 +1883,19 @@ COMPILING A PATTERN
        This option has two effects. Firstly, it change the way PCRE2 processes
        \B,  \b,  \D,  \d,  \S,  \s,  \W,  \w,  and some of the POSIX character
        classes. By default, only  ASCII  characters  are  recognized,  but  if
-       PCRE2_UCP is set, Unicode properties are used instead to classify char-
-       acters. More details are given in  the  section  on  generic  character
-       types  in  the pcre2pattern page. If you set PCRE2_UCP, matching one of
-       the items it affects takes much longer.
+       PCRE2_UCP  is  set, Unicode properties are used to classify characters.
+       There are some PCRE2_EXTRA options (see below) that add  finer  control
+       to  this  behaviour.  More  details are given in the section on generic
+       character types in the pcre2pattern page.
 
        The second effect of PCRE2_UCP is to force the use of  Unicode  proper-
-       ties  for  upper/lower casing operations on characters with code points
-       greater than 127, even when PCRE2_UTF is not set. This makes it  possi-
-       ble, for example, to process strings in the 16-bit UCS-2 code. This op-
-       tion is available only if PCRE2 has been compiled with Unicode  support
-       (which is the default).
+       ties for upper/lower casing operations, even when PCRE2_UTF is not set.
+       This  makes  it  possible  to process strings in the 16-bit UCS-2 code.
+       This option is available only if PCRE2 has been compiled  with  Unicode
+       support  (which is the default).  The PCRE2_EXTRA_CASELESS_RESTRICT op-
+       tion (see below) restricts caseless matching such that ASCII characters
+       match only ASCII characters and non-ASCII characters  match  only  non-
+       ASCII characters.
 
          PCRE2_UNGREEDY
 
@@ -1853,22 +1907,22 @@ COMPILING A PATTERN
          PCRE2_USE_OFFSET_LIMIT
 
        This option must be set for pcre2_compile() if pcre2_set_offset_limit()
-       is  going  to be used to set a non-default offset limit in a match con-
-       text for matches that use this pattern. An error  is  generated  if  an
-       offset  limit is set without this option. For more details, see the de-
-       scription of pcre2_set_offset_limit() in  the  section  that  describes
+       is going to be used to set a non-default offset limit in a  match  con-
+       text  for  matches  that  use this pattern. An error is generated if an
+       offset limit is set without this option. For more details, see the  de-
+       scription  of  pcre2_set_offset_limit()  in  the section that describes
        match contexts. See also the PCRE2_FIRSTLINE option above.
 
          PCRE2_UTF
 
-       This  option  causes  PCRE2  to regard both the pattern and the subject
-       strings that are subsequently processed as strings  of  UTF  characters
-       instead  of  single-code-unit  strings.  It  is available when PCRE2 is
-       built to include Unicode support (which is  the  default).  If  Unicode
+       This option causes PCRE2 to regard both the  pattern  and  the  subject
+       strings  that  are  subsequently processed as strings of UTF characters
+       instead of single-code-unit strings. It  is  available  when  PCRE2  is
+       built  to  include  Unicode  support (which is the default). If Unicode
        support is not available, the use of this option provokes an error. De-
        tails of how PCRE2_UTF changes the behaviour of PCRE2 are given in  the
        pcre2unicode  page.  In  particular,  note  that  it  changes  the  way
-       PCRE2_CASELESS handles characters with code points greater than 127.
+       PCRE2_CASELESS works.
 
    Extra compile options
 
@@ -1884,41 +1938,73 @@ COMPILING A PATTERN
 
          PCRE2_EXTRA_ALLOW_SURROGATE_ESCAPES
 
-       This option applies when compiling a pattern in UTF-8 or  UTF-32  mode.
-       It  is  forbidden in UTF-16 mode, and ignored in non-UTF modes. Unicode
+       This  option  applies when compiling a pattern in UTF-8 or UTF-32 mode.
+       It is forbidden in UTF-16 mode, and ignored in non-UTF  modes.  Unicode
        "surrogate" code points in the range 0xd800 to 0xdfff are used in pairs
        in  UTF-16  to  encode  code points with values in the range 0x10000 to
        0x10ffff. The surrogates cannot therefore  be  represented  in  UTF-16.
        They can be represented in UTF-8 and UTF-32, but are defined as invalid
-       code points, and cause errors if  encountered  in  a  UTF-8  or  UTF-32
+       code  points,  and  cause  errors  if  encountered in a UTF-8 or UTF-32
        string that is being checked for validity by PCRE2.
 
-       These  values also cause errors if encountered in escape sequences such
+       These values also cause errors if encountered in escape sequences  such
        as \x{d912} within a pattern. However, it seems that some applications,
        when using PCRE2 to check for unwanted characters in UTF-8 strings, ex-
-       plicitly  test  for  the  surrogates  using   escape   sequences.   The
-       PCRE2_NO_UTF_CHECK  option  does not disable the error that occurs, be-
+       plicitly   test   for   the  surrogates  using  escape  sequences.  The
+       PCRE2_NO_UTF_CHECK option does not disable the error that  occurs,  be-
        cause it applies only to the testing of input strings for UTF validity.
 
-       If the extra option PCRE2_EXTRA_ALLOW_SURROGATE_ESCAPES is set,  surro-
-       gate  code  point values in UTF-8 and UTF-32 patterns no longer provoke
-       errors and are incorporated in the compiled pattern. However, they  can
-       only  match  subject characters if the matching function is called with
+       If  the extra option PCRE2_EXTRA_ALLOW_SURROGATE_ESCAPES is set, surro-
+       gate code point values in UTF-8 and UTF-32 patterns no  longer  provoke
+       errors  and are incorporated in the compiled pattern. However, they can
+       only match subject characters if the matching function is  called  with
        PCRE2_NO_UTF_CHECK set.
 
          PCRE2_EXTRA_ALT_BSUX
 
-       The original option PCRE2_ALT_BSUX causes PCRE2 to process \U, \u,  and
-       \x  in  the way that ECMAscript (aka JavaScript) does. Additional func-
+       The  original option PCRE2_ALT_BSUX causes PCRE2 to process \U, \u, and
+       \x in the way that ECMAscript (aka JavaScript) does.  Additional  func-
        tionality was defined by ECMAscript 6; setting PCRE2_EXTRA_ALT_BSUX has
        the  effect  of PCRE2_ALT_BSUX, but in addition it recognizes \u{hhh..}
        as a hexadecimal character code, where hhh.. is any number of hexadeci-
        mal digits.
 
+         PCRE2_EXTRA_ASCII_BSD
+
+       This option forces \d to match only ASCII digits, even  when  PCRE2_UCP
+       is  set.   It can be changed within a pattern by means of the (?aD) op-
+       tion setting.
+
+         PCRE2_EXTRA_ASCII_BSS
+
+       This option forces \s to match only ASCII space characters,  even  when
+       PCRE2_UCP  is  set.  It can be changed within a pattern by means of the
+       (?aS) option setting.
+
+         PCRE2_EXTRA_ASCII_BSW
+
+       This option forces \w to match only ASCII word  characters,  even  when
+       PCRE2_UCP  is  set.  It can be changed within a pattern by means of the
+       (?aW) option setting.
+
+         PCRE2_EXTRA_ASCII_DIGIT
+
+       This option forces the POSIX character classes [:digit:] and [:xdigit:]
+       to match only ASCII digits, even when  PCRE2_UCP  is  set.  It  can  be
+       changed within a pattern by means of the (?aT) option setting.
+
+         PCRE2_EXTRA_ASCII_POSIX
+
+       This option forces all the POSIX character classes, including [:digit:]
+       and  [:xdigit:], to match only ASCII characters, even when PCRE2_UCP is
+       set. It can be changed within a pattern by means of  the  (?aP)  option
+       setting,  but note that this also sets PCRE2_EXTRA_ASCII_DIGIT in order
+       to ensure that (?-aP) unsets all ASCII restrictions for POSIX classes.
+
          PCRE2_EXTRA_BAD_ESCAPE_IS_LITERAL
 
-       This  is a dangerous option. Use with care. By default, an unrecognized
-       escape such as \j or a malformed one such as \x{2z} causes  a  compile-
+       This is a dangerous option. Use with care. By default, an  unrecognized
+       escape  such  as \j or a malformed one such as \x{2z} causes a compile-
        time error when detected by pcre2_compile(). Perl is somewhat inconsis-
        tent in handling such items: for example, \j is treated  as  a  literal
        "j",  and non-hexadecimal digits in \x{} are just ignored, though warn-
@@ -1931,37 +2017,49 @@ COMPILING A PATTERN
        treated as single-character escapes. For example, \j is a  literal  "j"
        and  \x{2z}  is treated as the literal string "x{2z}". Setting this op-
        tion means that typos in patterns may go undetected and have unexpected
-       results.  Also  note  that a sequence such as [\N{] is interpreted as a
-       malformed attempt at [\N{...}] and so is treated as [N{]  whereas  [\N]
+       results. Also note that a sequence such as [\N{] is  interpreted  as  a
+       malformed  attempt  at [\N{...}] and so is treated as [N{] whereas [\N]
        gives an error because an unqualified \N is a valid escape sequence but
        is not supported in a character class. To reiterate: this is a  danger-
        ous option. Use with great care.
 
+         PCRE2_EXTRA_CASELESS_RESTRICT
+
+       When  either  PCRE2_UCP  or PCRE2_UTF is set, caseless matching follows
+       Unicode rules, which allow for more than two cases per character. There
+       are two case-equivalent character sets that contain both ASCII and non-
+       ASCII characters. The ASCII letter S is case-equivalent to U+017f (long
+       S) and the ASCII letter K is case-equivalent to U+212a  (Kelvin  sign).
+       This  option  disables  recognition of case-equivalences that cross the
+       ASCII/non-ASCII boundary. In a caseless match, both characters must ei-
+       ther be ASCII or non-ASCII. The option can be changed with a pattern by
+       the (?r) option setting.
+
          PCRE2_EXTRA_ESCAPED_CR_IS_LF
 
-       There  are  some  legacy applications where the escape sequence \r in a
-       pattern is expected to match a newline. If this option is set, \r in  a
-       pattern  is  converted to \n so that it matches a LF (linefeed) instead
-       of a CR (carriage return) character. The option does not affect a  lit-
-       eral  CR in the pattern, nor does it affect CR specified as an explicit
+       There are some legacy applications where the escape sequence  \r  in  a
+       pattern  is expected to match a newline. If this option is set, \r in a
+       pattern is converted to \n so that it matches a LF  (linefeed)  instead
+       of  a CR (carriage return) character. The option does not affect a lit-
+       eral CR in the pattern, nor does it affect CR specified as an  explicit
        code point such as \x{0D}.
 
          PCRE2_EXTRA_MATCH_LINE
 
-       This option is provided for use by  the  -x  option  of  pcre2grep.  It
-       causes  the  pattern  only to match complete lines. This is achieved by
-       automatically inserting the code for "^(?:" at the start  of  the  com-
-       piled  pattern  and ")$" at the end. Thus, when PCRE2_MULTILINE is set,
-       the matched line may be in the middle of the subject string.  This  op-
+       This  option  is  provided  for  use  by the -x option of pcre2grep. It
+       causes the pattern only to match complete lines. This  is  achieved  by
+       automatically  inserting  the  code for "^(?:" at the start of the com-
+       piled pattern and ")$" at the end. Thus, when PCRE2_MULTILINE  is  set,
+       the  matched  line may be in the middle of the subject string. This op-
        tion can be used with PCRE2_LITERAL.
 
          PCRE2_EXTRA_MATCH_WORD
 
-       This  option  is  provided  for  use  by the -w option of pcre2grep. It
-       causes the pattern only to match strings that have a word  boundary  at
-       the  start and the end. This is achieved by automatically inserting the
-       code for "\b(?:" at the start of the compiled pattern and ")\b" at  the
-       end.  The option may be used with PCRE2_LITERAL. However, it is ignored
+       This option is provided for use by  the  -w  option  of  pcre2grep.  It
+       causes  the  pattern only to match strings that have a word boundary at
+       the start and the end. This is achieved by automatically inserting  the
+       code  for "\b(?:" at the start of the compiled pattern and ")\b" at the
+       end. The option may be used with PCRE2_LITERAL. However, it is  ignored
        if PCRE2_EXTRA_MATCH_LINE is also set.
 
 
@@ -1976,16 +2074,16 @@ JUST-IN-TIME (JIT) COMPILATION
 
        void pcre2_jit_free_unused_memory(pcre2_general_context *gcontext);
 
-       pcre2_jit_stack *pcre2_jit_stack_create(PCRE2_SIZE startsize,
-         PCRE2_SIZE maxsize, pcre2_general_context *gcontext);
+       pcre2_jit_stack *pcre2_jit_stack_create(size_t startsize,
+         size_t maxsize, pcre2_general_context *gcontext);
 
        void pcre2_jit_stack_assign(pcre2_match_context *mcontext,
          pcre2_jit_callback callback_function, void *callback_data);
 
        void pcre2_jit_stack_free(pcre2_jit_stack *jit_stack);
 
-       These functions provide support for  JIT  compilation,  which,  if  the
-       just-in-time  compiler  is available, further processes a compiled pat-
+       These  functions  provide  support  for  JIT compilation, which, if the
+       just-in-time compiler is available, further processes a  compiled  pat-
        tern into machine code that executes much faster than the pcre2_match()
        interpretive  matching function. Full details are given in the pcre2jit
        documentation.
@@ -2007,34 +2105,36 @@ LOCALE SUPPORT
        PCRE2 handles caseless matching, and determines whether characters  are
        letters,  digits, or whatever, by reference to a set of tables, indexed
        by character code point. However, this applies only to characters whose
-       code  points  are  less than 256. By default, higher-valued code points
+       code points are less than 256. By default,  higher-valued  code  points
        never match escapes such as \w or \d.
 
        When PCRE2 is built with Unicode support (the default), certain Unicode
        character  properties  can be tested with \p and \P, or, alternatively,
        the PCRE2_UCP option can be set when a pattern is compiled; this causes
-       \w  and friends to use Unicode property support instead of the built-in
+       \w and friends to use Unicode property support instead of the  built-in
        tables.  PCRE2_UCP also causes upper/lower casing operations on charac-
        ters with code points greater than 127 to use Unicode properties. These
-       effects apply even when PCRE2_UTF is not set.
+       effects  apply even when PCRE2_UTF is not set. There are, however, some
+       PCRE2_EXTRA options (see above) that can be used to modify or  suppress
+       them.
 
-       The use of locales with Unicode is discouraged.  If  you  are  handling
-       characters  with  code  points  greater than 127, you should either use
+       The  use  of  locales  with Unicode is discouraged. If you are handling
+       characters with code points greater than 127,  you  should  either  use
        Unicode support, or use locales, but not try to mix the two.
 
-       PCRE2 contains a built-in set of character tables that are used by  de-
-       fault.   These  are sufficient for many applications. Normally, the in-
-       ternal tables recognize only ASCII characters. However, when  PCRE2  is
+       PCRE2  contains a built-in set of character tables that are used by de-
+       fault.  These are sufficient for many applications. Normally,  the  in-
+       ternal  tables  recognize only ASCII characters. However, when PCRE2 is
        built, it is possible to cause the internal tables to be rebuilt in the
        default "C" locale of the local system, which may cause them to be dif-
        ferent.
 
-       The  built-in tables can be overridden by tables supplied by the appli-
-       cation that calls PCRE2. These may be created  in  a  different  locale
-       from  the  default.  As more and more applications change to using Uni-
+       The built-in tables can be overridden by tables supplied by the  appli-
+       cation  that  calls  PCRE2.  These may be created in a different locale
+       from the default.  As more and more applications change to  using  Uni-
        code, the need for this locale support is expected to die away.
 
-       External tables are built by calling the  pcre2_maketables()  function,
+       External  tables  are built by calling the pcre2_maketables() function,
        in the relevant locale. The only argument to this function is a general
        context, which can be used to pass a custom memory  allocator.  If  the
        argument is NULL, the system malloc() is used. The result can be passed
@@ -2063,20 +2163,20 @@ LOCALE SUPPORT
 
        It  is the caller's responsibility to ensure that the memory containing
        the tables remains available while they are still in use. When they are
-       no  longer  needed, you can discard them using pcre2_maketables_free(),
-       which should pass as its first parameter the same global  context  that
+       no longer needed, you can discard them  using  pcre2_maketables_free(),
+       which  should  pass as its first parameter the same global context that
        was used to create the tables.
 
    Saving locale tables
 
-       The  tables  described above are just a sequence of binary bytes, which
-       makes them independent of hardware characteristics such  as  endianness
-       or  whether  the processor is 32-bit or 64-bit. A copy of the result of
-       pcre2_maketables() can therefore be saved in a file  or  elsewhere  and
-       re-used  later, even in a different program or on another computer. The
-       size of the tables (number  of  bytes)  must  be  obtained  by  calling
-       pcre2_config()   with  the  PCRE2_CONFIG_TABLES_LENGTH  option  because
-       pcre2_maketables()  does  not  return  this  value.   Note   that   the
+       The tables described above are just a sequence of binary  bytes,  which
+       makes  them  independent of hardware characteristics such as endianness
+       or whether the processor is 32-bit or 64-bit. A copy of the  result  of
+       pcre2_maketables()  can  therefore  be saved in a file or elsewhere and
+       re-used later, even in a different program or on another computer.  The
+       size  of  the  tables  (number  of  bytes)  must be obtained by calling
+       pcre2_config()  with  the  PCRE2_CONFIG_TABLES_LENGTH  option   because
+       pcre2_maketables()   does   not   return  this  value.  Note  that  the
        pcre2_dftables program, which is part of the PCRE2 build system, can be
        used stand-alone to create a file that contains a set of binary tables.
        See the pcre2build documentation for details.
@@ -2086,13 +2186,13 @@ INFORMATION ABOUT A COMPILED PATTERN
 
        int pcre2_pattern_info(const pcre2 *code, uint32_t what, void *where);
 
-       The  pcre2_pattern_info()  function returns general information about a
+       The pcre2_pattern_info() function returns general information  about  a
        compiled pattern. For information about callouts, see the next section.
        The  first  argument  for pcre2_pattern_info() is a pointer to the com-
        piled pattern. The second argument specifies which piece of information
-       is  required,  and the third argument is a pointer to a variable to re-
-       ceive the data. If the third argument is NULL, the  first  argument  is
-       ignored,  and  the  function  returns the size in bytes of the variable
+       is required, and the third argument is a pointer to a variable  to  re-
+       ceive  the  data.  If the third argument is NULL, the first argument is
+       ignored, and the function returns the size in  bytes  of  the  variable
        that is required for the information requested. Otherwise, the yield of
        the function is zero for success, or one of the following negative num-
        bers:
@@ -2134,10 +2234,10 @@ INFORMATION ABOUT A COMPILED PATTERN
        TENDED option, the result for PCRE2_INFO_ALLOPTIONS  is  PCRE2_EXTENDED
        and  PCRE2_UTF.   Option settings such as (?i) that can change within a
        pattern do not affect the result of PCRE2_INFO_ALLOPTIONS, even if they
-       appear  right  at the start of the pattern. (This was different in some
+       appear right at the start of the pattern. (This was different  in  some
        earlier releases.)
 
-       A pattern compiled without PCRE2_ANCHORED is automatically anchored  by
+       A  pattern compiled without PCRE2_ANCHORED is automatically anchored by
        PCRE2 if the first significant item in every top-level branch is one of
        the following:
 
@@ -2184,23 +2284,23 @@ INFORMATION ABOUT A COMPILED PATTERN
 
          PCRE2_INFO_DEPTHLIMIT
 
-       If  the  pattern set a backtracking depth limit by including an item of
-       the form (*LIMIT_DEPTH=nnnn) at the start, the value is  returned.  The
+       If the pattern set a backtracking depth limit by including an  item  of
+       the  form  (*LIMIT_DEPTH=nnnn) at the start, the value is returned. The
        third argument should point to a uint32_t integer. If no such value has
        been set, the call to pcre2_pattern_info() returns the error  PCRE2_ER-
        ROR_UNSET. Note that this limit will only be used during matching if it
-       is less than the limit set or defaulted by  the  caller  of  the  match
+       is  less  than  the  limit  set or defaulted by the caller of the match
        function.
 
          PCRE2_INFO_FIRSTBITMAP
 
-       In  the absence of a single first code unit for a non-anchored pattern,
-       pcre2_compile() may construct a 256-bit table that defines a fixed  set
-       of  values for the first code unit in any match. For example, a pattern
-       that starts with [abc] results in a table with  three  bits  set.  When
-       code  unit  values greater than 255 are supported, the flag bit for 255
-       means "any code unit of value 255 or above". If such a table  was  con-
-       structed,  a pointer to it is returned. Otherwise NULL is returned. The
+       In the absence of a single first code unit for a non-anchored  pattern,
+       pcre2_compile()  may construct a 256-bit table that defines a fixed set
+       of values for the first code unit in any match. For example, a  pattern
+       that  starts  with  [abc]  results in a table with three bits set. When
+       code unit values greater than 255 are supported, the flag bit  for  255
+       means  "any  code unit of value 255 or above". If such a table was con-
+       structed, a pointer to it is returned. Otherwise NULL is returned.  The
        third argument should point to a const uint8_t * variable.
 
          PCRE2_INFO_FIRSTCODETYPE
@@ -2251,39 +2351,39 @@ INFORMATION ABOUT A COMPILED PATTERN
        If the pattern set a heap memory limit by including an item of the form
        (*LIMIT_HEAP=nnnn) at the start, the value is returned. The third argu-
        ment should point to a uint32_t integer. If no such value has been set,
-       the call to pcre2_pattern_info() returns the  error  PCRE2_ERROR_UNSET.
-       Note  that  this  limit will only be used during matching if it is less
+       the  call  to pcre2_pattern_info() returns the error PCRE2_ERROR_UNSET.
+       Note that this limit will only be used during matching if  it  is  less
        than the limit set or defaulted by the caller of the match function.
 
          PCRE2_INFO_JCHANGED
 
-       Return 1 if the (?J) or (?-J) option setting is used  in  the  pattern,
-       otherwise  0.  The  third argument should point to a uint32_t variable.
-       (?J) and (?-J) set and unset the local PCRE2_DUPNAMES  option,  respec-
+       Return  1  if  the (?J) or (?-J) option setting is used in the pattern,
+       otherwise 0. The third argument should point to  a  uint32_t  variable.
+       (?J)  and  (?-J) set and unset the local PCRE2_DUPNAMES option, respec-
        tively.
 
          PCRE2_INFO_JITSIZE
 
-       If  the  compiled  pattern was successfully processed by pcre2_jit_com-
-       pile(), return the size of the  JIT  compiled  code,  otherwise  return
+       If the compiled pattern was successfully  processed  by  pcre2_jit_com-
+       pile(),  return  the  size  of  the JIT compiled code, otherwise return
        zero. The third argument should point to a size_t variable.
 
          PCRE2_INFO_LASTCODETYPE
 
-       Returns  1 if there is a rightmost literal code unit that must exist in
-       any matched string, other than at its start. The third argument  should
+       Returns 1 if there is a rightmost literal code unit that must exist  in
+       any  matched string, other than at its start. The third argument should
        point to a uint32_t variable. If there is no such value, 0 is returned.
        When 1 is returned, the code unit value itself can be  retrieved  using
        PCRE2_INFO_LASTCODEUNIT. For anchored patterns, a last literal value is
-       recorded only if it follows something of variable length. For  example,
-       for  the pattern /^a\d+z\d+/ the returned value is 1 (with "z" returned
-       from PCRE2_INFO_LASTCODEUNIT), but for /^a\dz\d/ the returned value  is
+       recorded  only if it follows something of variable length. For example,
+       for the pattern /^a\d+z\d+/ the returned value is 1 (with "z"  returned
+       from  PCRE2_INFO_LASTCODEUNIT), but for /^a\dz\d/ the returned value is
        0.
 
          PCRE2_INFO_LASTCODEUNIT
 
-       Return  the value of the rightmost literal code unit that must exist in
-       any matched string, other than  at  its  start,  for  a  pattern  where
+       Return the value of the rightmost literal code unit that must exist  in
+       any  matched  string,  other  than  at  its  start, for a pattern where
        PCRE2_INFO_LASTCODETYPE returns 1. Otherwise, return 0. The third argu-
        ment should point to a uint32_t variable.
 
@@ -2297,9 +2397,9 @@ INFORMATION ABOUT A COMPILED PATTERN
 
          PCRE2_INFO_MATCHLIMIT
 
-       If the pattern set a match limit by  including  an  item  of  the  form
-       (*LIMIT_MATCH=nnnn)  at the start, the value is returned. The third ar-
-       gument should point to a uint32_t integer. If no such  value  has  been
+       If  the  pattern  set  a  match  limit by including an item of the form
+       (*LIMIT_MATCH=nnnn) at the start, the value is returned. The third  ar-
+       gument  should  point  to a uint32_t integer. If no such value has been
        set, the call to pcre2_pattern_info() returns the error PCRE2_ERROR_UN-
        SET. Note that this limit will only be used during matching  if  it  is
        less  than  the limit set or defaulted by the caller of the match func-
@@ -2311,30 +2411,30 @@ INFORMATION ABOUT A COMPILED PATTERN
        code  units)  when  it starts to process each of its branches. This re-
        quest returns the largest of these backward moves. The  third  argument
        should point to a uint32_t integer. The simple assertions \b and \B re-
-       quire a one-character lookbehind and cause PCRE2_INFO_MAXLOOKBEHIND  to
-       return  1  in  the absence of anything longer. \A also registers a one-
-       character lookbehind, though it does not actually inspect the  previous
+       quire  a one-character lookbehind and cause PCRE2_INFO_MAXLOOKBEHIND to
+       return 1 in the absence of anything longer. \A also  registers  a  one-
+       character  lookbehind, though it does not actually inspect the previous
        character.
 
        Note that this information is useful for multi-segment matching only if
        the pattern contains no nested lookbehinds. For  example,  the  pattern
-       (?<=a(?<=ba)c)  returns  a maximum lookbehind of 2, but when it is pro-
-       cessed, the first lookbehind moves back by two characters, matches  one
-       character,  then  the  nested lookbehind also moves back by two charac-
-       ters. This puts the matching point three characters earlier than it was
-       at  the start.  PCRE2_INFO_MAXLOOKBEHIND is really only useful as a de-
-       bugging tool. See the pcre2partial documentation for  a  discussion  of
+       (?<=a(?<=ba)c)  returns  a  maximum  lookbehind  of  2,  but when it is
+       processed, the first lookbehind moves back by two  characters,  matches
+       one  character, then the nested lookbehind also moves back by two char-
+       acters. This puts the matching point three characters earlier  than  it
+       was  at the start.  PCRE2_INFO_MAXLOOKBEHIND is really only useful as a
+       debugging tool. See the pcre2partial documentation for a discussion  of
        multi-segment matching.
 
          PCRE2_INFO_MINLENGTH
 
        If  a  minimum  length  for  matching subject strings was computed, its
        value is returned. Otherwise the returned value is 0. This value is not
-       computed  when PCRE2_NO_START_OPTIMIZE is set. The value is a number of
-       characters, which in UTF mode may be different from the number of  code
-       units.  The  third  argument  should  point to a uint32_t variable. The
-       value is a lower bound to the length of any matching string. There  may
-       not  be  any  strings  of that length that do actually match, but every
+       computed when PCRE2_NO_START_OPTIMIZE is set. The value is a number  of
+       characters,  which in UTF mode may be different from the number of code
+       units. The third argument should point  to  a  uint32_t  variable.  The
+       value  is a lower bound to the length of any matching string. There may
+       not be any strings of that length that do  actually  match,  but  every
        string that does match is at least that long.
 
          PCRE2_INFO_NAMECOUNT
@@ -2344,10 +2444,10 @@ INFORMATION ABOUT A COMPILED PATTERN
        PCRE2 supports the use of named as well as numbered capturing parenthe-
        ses.  The names are just an additional way of identifying the parenthe-
        ses, which still acquire numbers. Several convenience functions such as
-       pcre2_substring_get_byname()  are provided for extracting captured sub-
-       strings by name. It is also possible to extract the data  directly,  by
-       first  converting  the  name to a number in order to access the correct
-       pointers in the output vector (described with pcre2_match() below).  To
+       pcre2_substring_get_byname() are provided for extracting captured  sub-
+       strings  by  name. It is also possible to extract the data directly, by
+       first converting the name to a number in order to  access  the  correct
+       pointers  in the output vector (described with pcre2_match() below). To
        do the conversion, you need to use the name-to-number map, which is de-
        scribed by these three values.
 
@@ -2373,13 +2473,13 @@ INFORMATION ABOUT A COMPILED PATTERN
 
        Duplicate names for capture groups with different numbers  are  permit-
        ted, but only if PCRE2_DUPNAMES is set. They appear in the table in the
-       order in which they were found in the pattern. In the  absence  of  (?|
-       this  is  the  order of increasing number; when (?| is used this is not
-       necessarily the case because later capture groups may have  lower  num-
+       order  in  which  they were found in the pattern. In the absence of (?|
+       this is the order of increasing number; when (?| is used  this  is  not
+       necessarily  the  case because later capture groups may have lower num-
        bers.
 
-       As  a  simple  example of the name/number table, consider the following
-       pattern after compilation by the 8-bit library  (assume  PCRE2_EXTENDED
+       As a simple example of the name/number table,  consider  the  following
+       pattern  after  compilation by the 8-bit library (assume PCRE2_EXTENDED
        is set, so white space - including newlines - is ignored):
 
          (? (?(\d\d)?\d\d) -
@@ -2395,8 +2495,8 @@ INFORMATION ABOUT A COMPILED PATTERN
          00 04 m  o  n  t  h  00
          00 02 y  e  a  r  00 ??
 
-       When writing code to extract data from named capture groups  using  the
-       name-to-number  map,  remember that the length of the entries is likely
+       When  writing  code to extract data from named capture groups using the
+       name-to-number map, remember that the length of the entries  is  likely
        to be different for each compiled pattern.
 
          PCRE2_INFO_NEWLINE
@@ -2421,8 +2521,8 @@ INFORMATION ABOUT A COMPILED PATTERN
        code units of the compiled pattern itself. The value that is used  when
        pcre2_compile()  is  getting memory in which to place the compiled pat-
        tern may be slightly larger than the value returned by this option, be-
-       cause  there  are  cases where the code that calculates the size has to
-       over-estimate. Processing a pattern with the JIT compiler does not  al-
+       cause there are cases where the code that calculates the  size  has  to
+       over-estimate.  Processing a pattern with the JIT compiler does not al-
        ter the value returned by this option.
 
 
@@ -2435,9 +2535,9 @@ INFORMATION ABOUT A PATTERN'S CALLOUTS
        A script language that supports the use of string arguments in callouts
        might like to scan all the callouts in a  pattern  before  running  the
        match. This can be done by calling pcre2_callout_enumerate(). The first
-       argument is a pointer to a compiled pattern, the  second  points  to  a
-       callback  function,  and the third is arbitrary user data. The callback
-       function is called for every callout in the pattern  in  the  order  in
+       argument  is  a  pointer  to a compiled pattern, the second points to a
+       callback function, and the third is arbitrary user data.  The  callback
+       function  is  called  for  every callout in the pattern in the order in
        which they appear. Its first argument is a pointer to a callout enumer-
        ation block, and its second argument is the user_data  value  that  was
        passed  to  pcre2_callout_enumerate(). The contents of the callout enu-
@@ -2447,17 +2547,17 @@ INFORMATION ABOUT A PATTERN'S CALLOUTS
 
 SERIALIZATION AND PRECOMPILING
 
-       It  is  possible  to  save  compiled patterns on disc or elsewhere, and
-       reload them later, subject to a number of  restrictions.  The  host  on
-       which  the  patterns  are  reloaded must be running the same version of
-       PCRE2, with the same code unit width, and must also have the same endi-
-       anness,  pointer  width,  and PCRE2_SIZE type. Before compiled patterns
-       can be saved, they must be converted to a "serialized" form,  which  in
-       the  case of PCRE2 is really just a bytecode dump.  The functions whose
-       names begin with pcre2_serialize_ are used for converting to  and  from
-       the  serialized form. They are described in the pcre2serialize documen-
-       tation. Note that PCRE2 serialization does not  convert  compiled  pat-
-       terns to an abstract format like Java or .NET serialization.
+       It  is possible to save compiled patterns on disc or elsewhere, and re-
+       load them later, subject to a number of restrictions. The host on which
+       the patterns are reloaded must be running the same  version  of  PCRE2,
+       with  the same code unit width, and must also have the same endianness,
+       pointer width, and PCRE2_SIZE type. Before  compiled  patterns  can  be
+       saved, they must be converted to a "serialized" form, which in the case
+       of PCRE2 is really just a bytecode dump.  The functions whose names be-
+       gin with pcre2_serialize_ are used for converting to and from the seri-
+       alized  form.  They  are described in the pcre2serialize documentation.
+       Note that PCRE2 serialization does not convert compiled patterns to  an
+       abstract format like Java or .NET serialization.
 
 
 THE MATCH DATA BLOCK
@@ -2476,7 +2576,7 @@ THE MATCH DATA BLOCK
        of offsets into the subject string that define the matched parts of the
        subject. This is known as the ovector.
 
-       Before  calling  pcre2_match(), pcre2_dfa_match(), or pcre2_jit_match()
+       Before calling pcre2_match(), pcre2_dfa_match(),  or  pcre2_jit_match()
        you must create a match data block by calling one of the creation func-
        tions  above.  For pcre2_match_data_create(), the first argument is the
        number of pairs of offsets in the ovector.
@@ -2484,47 +2584,47 @@ THE MATCH DATA BLOCK
        When using pcre2_match(), one pair of offsets is required  to  identify
        the  string that matched the whole pattern, with an additional pair for
        each captured substring. For example, a value of 4 creates enough space
-       to  record  the matched portion of the subject plus three captured sub-
+       to record the matched portion of the subject plus three  captured  sub-
        strings.
 
-       When using pcre2_dfa_match() there may be multiple  matched  substrings
-       of  different  lengths  at  the  same point in the subject. The ovector
+       When  using  pcre2_dfa_match() there may be multiple matched substrings
+       of different lengths at the same point  in  the  subject.  The  ovector
        should be made large enough to hold as many as are expected.
 
-       A minimum of at least 1 pair is imposed  by  pcre2_match_data_create(),
-       so  it  is  always possible to return the overall matched string in the
-       case  of  pcre2_match()  or  the  longest  match   in   the   case   of
-       pcre2_dfa_match().  The  maximum  number  of pairs is 65535; if the the
-       first argument of pcre2_match_data_create() is greater than this, 65535
-       is used.
+       A  minimum  of at least 1 pair is imposed by pcre2_match_data_create(),
+       so it is always possible to return the overall matched  string  in  the
+       case   of   pcre2_match()   or   the  longest  match  in  the  case  of
+       pcre2_dfa_match(). The maximum number of pairs is 65535; if  the  first
+       argument  of  pcre2_match_data_create()  is greater than this, 65535 is
+       used.
 
        The second argument of pcre2_match_data_create() is a pointer to a gen-
        eral context, which can specify custom memory management for  obtaining
        the memory for the match data block. If you are not using custom memory
        management, pass NULL, which causes malloc() to be used.
 
-       For pcre2_match_data_create_from_pattern(), the  first  argument  is  a
+       For  pcre2_match_data_create_from_pattern(),  the  first  argument is a
        pointer to a compiled pattern. The ovector is created to be exactly the
        right size to hold all the substrings  a  pattern  might  capture  when
        matched using pcre2_match(). You should not use this call when matching
-       with pcre2_dfa_match(). The second argument is again  a  pointer  to  a
-       general  context, but in this case if NULL is passed, the memory is ob-
-       tained using the same allocator that was used for the compiled  pattern
+       with  pcre2_dfa_match().  The  second  argument is again a pointer to a
+       general context, but in this case if NULL is passed, the memory is  ob-
+       tained  using the same allocator that was used for the compiled pattern
        (custom or default).
 
-       A  match  data block can be used many times, with the same or different
-       compiled patterns. You can extract information from a match data  block
-       after  a  match  operation  has  finished, using functions that are de-
+       A match data block can be used many times, with the same  or  different
+       compiled  patterns. You can extract information from a match data block
+       after a match operation has finished,  using  functions  that  are  de-
        scribed in the sections on matched strings and other match data below.
 
-       When a call of pcre2_match() fails, valid  data  is  available  in  the
-       match  block  only  when  the  error  is PCRE2_ERROR_NOMATCH, PCRE2_ER-
-       ROR_PARTIAL, or one of the error codes for an invalid UTF  string.  Ex-
+       When  a  call  of  pcre2_match()  fails, valid data is available in the
+       match block only  when  the  error  is  PCRE2_ERROR_NOMATCH,  PCRE2_ER-
+       ROR_PARTIAL,  or  one of the error codes for an invalid UTF string. Ex-
        actly what is available depends on the error, and is detailed below.
 
-       When  one of the matching functions is called, pointers to the compiled
-       pattern and the subject string are set in the match data block so  that
-       they  can  be referenced by the extraction functions after a successful
+       When one of the matching functions is called, pointers to the  compiled
+       pattern  and the subject string are set in the match data block so that
+       they can be referenced by the extraction functions after  a  successful
        match. After running a match, you must not free a compiled pattern or a
        subject  string until after all operations on the match data block (for
        that match) have taken place,  unless,  in  the  case  of  the  subject
@@ -2537,6 +2637,39 @@ THE MATCH DATA BLOCK
        NULL argument, it returns immediately, without doing anything.
 
 
+MEMORY USE FOR MATCH DATA BLOCKS
+
+       PCRE2_SIZE pcre2_get_match_data_size(pcre2_match_data *match_data);
+
+       PCRE2_SIZE pcre2_get_match_data_heapframes_size(
+         pcre2_match_data *match_data);
+
+       The  size of a match data block depends on the size of the ovector that
+       it contains. The function pcre2_get_match_data_size() returns the size,
+       in bytes, of the block that is its argument.
+
+       When pcre2_match() runs interpretively (that is, without using JIT), it
+       makes use of a vector of data frames for remembering backtracking posi-
+       tions.  The size of each individual frame depends on the number of cap-
+       turing parentheses in the  pattern  and  can  be  obtained  by  calling
+       pcre2_pattern_info() with the PCRE2_INFO_FRAMESIZE option (see the sec-
+       tion entitled "Information about a compiled pattern" above).
+
+       Heap  memory is used for the frames vector; if the initial memory block
+       turns out to be too small during  matching,  it  is  automatically  ex-
+       panded.  When  pcre2_match()  returns, the memory is not freed, but re-
+       mains attached to the match data  block,  for  use  by  any  subsequent
+       matches  that  use  the  same block. It is automatically freed when the
+       match data block itself is freed.
+
+       You can find the current size of the frames vector that  a  match  data
+       block  owns  by  calling  pcre2_get_match_data_heapframes_size(). For a
+       newly created match data block the size will be  zero.  Some  types  of
+       match may require a lot of frames and thus a large vector; applications
+       that run in environments where memory is constrained can check this and
+       free the match data block if the heap frames vector has become too big.
+
+
 MATCHING A PATTERN: THE TRADITIONAL FUNCTION
 
        int pcre2_match(const pcre2_code *code, PCRE2_SPTR subject,
@@ -2547,12 +2680,12 @@ MATCHING A PATTERN: THE TRADITIONAL FUNCTION
        The  function pcre2_match() is called to match a subject string against
        a compiled pattern, which is passed in the code argument. You can  call
        pcre2_match() with the same code argument as many times as you like, in
-       order to find multiple matches in the subject string or to  match  dif-
+       order  to  find multiple matches in the subject string or to match dif-
        ferent subject strings with the same pattern.
 
-       This  function is the main matching facility of the library, and it op-
-       erates in a Perl-like manner. For specialist use there is also  an  al-
-       ternative  matching  function,  which is described below in the section
+       This function is the main matching facility of the library, and it  op-
+       erates  in  a Perl-like manner. For specialist use there is also an al-
+       ternative matching function, which is described below  in  the  section
        about the pcre2_dfa_match() function.
 
        Here is an example of a simple call to pcre2_match():
@@ -2567,25 +2700,25 @@ MATCHING A PATTERN: THE TRADITIONAL FUNCTION
            md,             /* the match data block */
            NULL);          /* a match context; NULL means use defaults */
 
-       If the subject string is zero-terminated, the length can  be  given  as
+       If  the  subject  string is zero-terminated, the length can be given as
        PCRE2_ZERO_TERMINATED. A match context must be provided if certain less
        common matching parameters are to be changed. For details, see the sec-
        tion on the match context above.
 
    The string to be matched by pcre2_match()
 
-       The  subject string is passed to pcre2_match() as a pointer in subject,
-       a length in length, and a starting offset in  startoffset.  The  length
-       and  offset  are  in  code units, not characters.  That is, they are in
-       bytes for the 8-bit library, 16-bit code units for the 16-bit  library,
-       and  32-bit  code units for the 32-bit library, whether or not UTF pro-
+       The subject string is passed to pcre2_match() as a pointer in  subject,
+       a  length  in  length, and a starting offset in startoffset. The length
+       and offset are in code units, not characters.  That  is,  they  are  in
+       bytes  for the 8-bit library, 16-bit code units for the 16-bit library,
+       and 32-bit code units for the 32-bit library, whether or not  UTF  pro-
        cessing is enabled. As a special case, if subject is NULL and length is
        zero,  the  subject is assumed to be an empty string. If length is non-
        zero, an error occurs if subject is NULL.
 
        If startoffset is greater than the length of the subject, pcre2_match()
-       returns  PCRE2_ERROR_BADOFFSET.  When  the starting offset is zero, the
-       search for a match starts at the beginning of the subject, and this  is
+       returns PCRE2_ERROR_BADOFFSET. When the starting offset  is  zero,  the
+       search  for a match starts at the beginning of the subject, and this is
        by far the most common case. In UTF-8 or UTF-16 mode, the starting off-
        set must point to the start of a character, or to the end of  the  sub-
        ject  (in  UTF-32 mode, one code unit equals one character, so all off-
@@ -2605,44 +2738,45 @@ MATCHING A PATTERN: THE TRADITIONAL FUNCTION
        When   applied   to   the   string  "Mississippi"  the  first  call  to
        pcre2_match() finds the first occurrence. If  pcre2_match()  is  called
        again with just the remainder of the subject, namely "issippi", it does
-       not match, because \B is always false at  the  start  of  the  subject,
-       which  is  deemed  to  be a word boundary. However, if pcre2_match() is
+       not  match,  because  \B  is  always false at the start of the subject,
+       which is deemed to be a word boundary.  However,  if  pcre2_match()  is
        passed the entire string again, but with startoffset set to 4, it finds
        the  second  occurrence  of "iss" because it is able to look behind the
        starting point to discover that it is preceded by a letter.
 
        Finding all the matches in a subject is tricky  when  the  pattern  can
        match an empty string. It is possible to emulate Perl's /g behaviour by
-       first  trying  the  match  again  at  the   same   offset,   with   the
-       PCRE2_NOTEMPTY_ATSTART  and  PCRE2_ANCHORED  options,  and then if that
-       fails, advancing the starting  offset  and  trying  an  ordinary  match
-       again.  There  is  some  code  that  demonstrates how to do this in the
-       pcre2demo sample program. In the most general case, you have  to  check
-       to  see  if the newline convention recognizes CRLF as a newline, and if
-       so, and the current character is CR followed by LF, advance the  start-
+       first   trying   the   match   again  at  the  same  offset,  with  the
+       PCRE2_NOTEMPTY_ATSTART and PCRE2_ANCHORED options,  and  then  if  that
+       fails,  advancing  the  starting  offset  and  trying an ordinary match
+       again. There is some code that demonstrates  how  to  do  this  in  the
+       pcre2demo  sample  program. In the most general case, you have to check
+       to see if the newline convention recognizes CRLF as a newline,  and  if
+       so,  and the current character is CR followed by LF, advance the start-
        ing offset by two characters instead of one.
 
        If a non-zero starting offset is passed when the pattern is anchored, a
        single attempt to match at the given offset is made. This can only suc-
-       ceed  if  the  pattern does not require the match to be at the start of
-       the subject. In other words, the anchoring must be the result  of  set-
-       ting  the PCRE2_ANCHORED option or the use of .* with PCRE2_DOTALL, not
+       ceed if the pattern does not require the match to be at  the  start  of
+       the  subject.  In other words, the anchoring must be the result of set-
+       ting the PCRE2_ANCHORED option or the use of .* with PCRE2_DOTALL,  not
        by starting the pattern with ^ or \A.
 
    Option bits for pcre2_match()
 
        The unused bits of the options argument for pcre2_match() must be zero.
        The    only    bits    that    may    be    set   are   PCRE2_ANCHORED,
-       PCRE2_COPY_MATCHED_SUBJECT, PCRE2_ENDANCHORED, PCRE2_NOTBOL,  PCRE2_NO-
-       TEOL,     PCRE2_NOTEMPTY,     PCRE2_NOTEMPTY_ATSTART,     PCRE2_NO_JIT,
-       PCRE2_NO_UTF_CHECK, PCRE2_PARTIAL_HARD, and  PCRE2_PARTIAL_SOFT.  Their
-       action is described below.
+       PCRE2_COPY_MATCHED_SUBJECT, PCRE2_DISABLE_RECURSELOOP_CHECK,  PCRE2_EN-
+       DANCHORED,       PCRE2_NOTBOL,       PCRE2_NOTEOL,      PCRE2_NOTEMPTY,
+       PCRE2_NOTEMPTY_ATSTART,  PCRE2_NO_JIT,  PCRE2_NO_UTF_CHECK,  PCRE2_PAR-
+       TIAL_HARD, and PCRE2_PARTIAL_SOFT.  Their action is described below.
 
        Setting  PCRE2_ANCHORED  or PCRE2_ENDANCHORED at match time is not sup-
        ported by the just-in-time (JIT) compiler. If it is set,  JIT  matching
-       is  disabled  and  the interpretive code in pcre2_match() is run. Apart
-       from PCRE2_NO_JIT (obviously), the remaining options are supported  for
-       JIT matching.
+       is  disabled  and  the  interpretive  code  in  pcre2_match()  is  run.
+       PCRE2_DISABLE_RECURSELOOP_CHECK is  ignored  by  JIT,  but  apart  from
+       PCRE2_NO_JIT  (obviously),  the remaining options are supported for JIT
+       matching.
 
          PCRE2_ANCHORED
 
@@ -2669,6 +2803,25 @@ MATCHING A PATTERN: THE TRADITIONAL FUNCTION
        also automatically freed if the match data block is re-used for another
        match operation.
 
+         PCRE2_DISABLE_RECURSELOOP_CHECK
+
+       This  option  is relevant only to pcre2_match() for interpretive match-
+       ing.   It  is  ignored  when  JIT  is  used,  and  is   forbidden   for
+       pcre2_dfa_match().
+
+       The use of recursion in patterns can lead to infinite loops. In the in-
+       terpretive  matcher  these  would  be eventually caught by the match or
+       heap limits, but this could take a long time and/or use a lot of memory
+       if the limits are large. There is therefore a check  at  the  start  of
+       each  recursion.   If  the  same  group is still active from a previous
+       call, and the current subject pointer is the same  as  it  was  at  the
+       start  of  that group, and the furthest inspected character of the sub-
+       ject has not changed, an error is generated.
+
+       There are rare cases of matches that would complete,  but  nevertheless
+       trigger  this  error.  This  option  disables the check. It is provided
+       mainly for testing when comparing JIT and interpretive behaviour.
+
          PCRE2_ENDANCHORED
 
        If the PCRE2_ENDANCHORED option is set, any string  that  pcre2_match()
@@ -2678,30 +2831,30 @@ MATCHING A PATTERN: THE TRADITIONAL FUNCTION
          PCRE2_NOTBOL
 
        This option specifies that first character of the subject string is not
-       the  beginning  of  a  line, so the circumflex metacharacter should not
-       match before it. Setting this without  having  set  PCRE2_MULTILINE  at
+       the beginning of a line, so the  circumflex  metacharacter  should  not
+       match  before  it.  Setting  this without having set PCRE2_MULTILINE at
        compile time causes circumflex never to match. This option affects only
        the behaviour of the circumflex metacharacter. It does not affect \A.
 
          PCRE2_NOTEOL
 
        This option specifies that the end of the subject string is not the end
-       of  a line, so the dollar metacharacter should not match it nor (except
-       in multiline mode) a newline immediately before it. Setting this  with-
-       out  having  set PCRE2_MULTILINE at compile time causes dollar never to
+       of a line, so the dollar metacharacter should not match it nor  (except
+       in  multiline mode) a newline immediately before it. Setting this with-
+       out having set PCRE2_MULTILINE at compile time causes dollar  never  to
        match. This option affects only the behaviour of the dollar metacharac-
        ter. It does not affect \Z or \z.
 
          PCRE2_NOTEMPTY
 
        An empty string is not considered to be a valid match if this option is
-       set. If there are alternatives in the pattern, they are tried.  If  all
-       the  alternatives  match  the empty string, the entire match fails. For
+       set.  If  there are alternatives in the pattern, they are tried. If all
+       the alternatives match the empty string, the entire  match  fails.  For
        example, if the pattern
 
          a?b?
 
-       is applied to a string not beginning with "a" or  "b",  it  matches  an
+       is  applied  to  a  string not beginning with "a" or "b", it matches an
        empty string at the start of the subject. With PCRE2_NOTEMPTY set, this
        match is not valid, so pcre2_match() searches further into  the  string
        for occurrences of "a" or "b".
@@ -2710,7 +2863,7 @@ MATCHING A PATTERN: THE TRADITIONAL FUNCTION
 
        This  is  like PCRE2_NOTEMPTY, except that it locks out an empty string
        match only at the first matching position, that is, at the start of the
-       subject  plus  the  starting offset. An empty string match later in the
+       subject plus the starting offset. An empty string match  later  in  the
        subject is permitted.  If the pattern is anchored, such a match can oc-
        cur only if the pattern contains \K.
 
@@ -2724,36 +2877,36 @@ MATCHING A PATTERN: THE TRADITIONAL FUNCTION
          PCRE2_NO_UTF_CHECK
 
        When PCRE2_UTF is set at compile time, the validity of the subject as a
-       UTF   string   is   checked  unless  PCRE2_NO_UTF_CHECK  is  passed  to
+       UTF  string  is  checked  unless  PCRE2_NO_UTF_CHECK   is   passed   to
        pcre2_match() or PCRE2_MATCH_INVALID_UTF was passed to pcre2_compile().
        The latter special case is discussed in detail in the pcre2unicode doc-
        umentation.
 
-       In the default case, if a non-zero starting offset is given, the  check
-       is  applied  only  to  that part of the subject that could be inspected
-       during matching, and there is a check that the starting  offset  points
-       to  the first code unit of a character or to the end of the subject. If
-       there are no lookbehind assertions in the pattern, the check starts  at
+       In  the default case, if a non-zero starting offset is given, the check
+       is applied only to that part of the subject  that  could  be  inspected
+       during  matching,  and there is a check that the starting offset points
+       to the first code unit of a character or to the end of the subject.  If
+       there  are no lookbehind assertions in the pattern, the check starts at
        the starting offset.  Otherwise, it starts at the length of the longest
        lookbehind before the starting offset, or at the start of  the  subject
        if  there are not that many characters before the starting offset. Note
        that the sequences \b and \B are one-character lookbehinds.
 
        The check is carried out before any other processing takes place, and a
-       negative  error  code is returned if the check fails. There are several
-       UTF error codes for each code unit width,  corresponding  to  different
-       problems  with  the code unit sequence. There are discussions about the
-       validity of UTF-8 strings, UTF-16 strings, and UTF-32  strings  in  the
+       negative error code is returned if the check fails. There  are  several
+       UTF  error  codes  for each code unit width, corresponding to different
+       problems with the code unit sequence. There are discussions  about  the
+       validity  of  UTF-8  strings, UTF-16 strings, and UTF-32 strings in the
        pcre2unicode documentation.
 
        If you know that your subject is valid, and you want to skip this check
        for performance reasons, you can set the PCRE2_NO_UTF_CHECK option when
-       calling  pcre2_match().  You  might  want to do this for the second and
-       subsequent calls to pcre2_match() if you are making repeated  calls  to
+       calling pcre2_match(). You might want to do this  for  the  second  and
+       subsequent  calls  to pcre2_match() if you are making repeated calls to
        find multiple matches in the same subject string.
 
-       Warning:  Unless  PCRE2_MATCH_INVALID_UTF was set at compile time, when
-       PCRE2_NO_UTF_CHECK is set at match time the effect of  passing  an  in-
+       Warning: Unless PCRE2_MATCH_INVALID_UTF was set at compile  time,  when
+       PCRE2_NO_UTF_CHECK  is  set  at match time the effect of passing an in-
        valid string as a subject, or an invalid value of startoffset, is unde-
        fined.  Your program may crash or loop indefinitely or give  wrong  re-
        sults.
@@ -2762,7 +2915,7 @@ MATCHING A PATTERN: THE TRADITIONAL FUNCTION
          PCRE2_PARTIAL_SOFT
 
        These options turn on the partial matching feature. A partial match oc-
-       curs if the end of the subject  string  is  reached  successfully,  but
+       curs  if  the  end  of  the subject string is reached successfully, but
        there are not enough subject characters to complete the match. In addi-
        tion, either at least one character must have  been  inspected  or  the
        pattern  must  contain  a  lookbehind,  or the pattern must be one that
@@ -2770,14 +2923,14 @@ MATCHING A PATTERN: THE TRADITIONAL FUNCTION
 
        If this situation arises when PCRE2_PARTIAL_SOFT  (but  not  PCRE2_PAR-
        TIAL_HARD) is set, matching continues by testing any remaining alterna-
-       tives. Only if no complete match can be  found  is  PCRE2_ERROR_PARTIAL
-       returned  instead  of  PCRE2_ERROR_NOMATCH.  In other words, PCRE2_PAR-
-       TIAL_SOFT specifies that the caller is prepared  to  handle  a  partial
+       tives.  Only  if  no complete match can be found is PCRE2_ERROR_PARTIAL
+       returned instead of PCRE2_ERROR_NOMATCH.  In  other  words,  PCRE2_PAR-
+       TIAL_SOFT  specifies  that  the  caller is prepared to handle a partial
        match, but only if no complete match can be found.
 
-       If  PCRE2_PARTIAL_HARD is set, it overrides PCRE2_PARTIAL_SOFT. In this
-       case, if a partial match is found,  pcre2_match()  immediately  returns
-       PCRE2_ERROR_PARTIAL,  without  considering  any  other alternatives. In
+       If PCRE2_PARTIAL_HARD is set, it overrides PCRE2_PARTIAL_SOFT. In  this
+       case,  if  a  partial match is found, pcre2_match() immediately returns
+       PCRE2_ERROR_PARTIAL, without considering  any  other  alternatives.  In
        other words, when PCRE2_PARTIAL_HARD is set, a partial match is consid-
        ered to be more important that an alternative complete match.
 
@@ -2787,21 +2940,21 @@ MATCHING A PATTERN: THE TRADITIONAL FUNCTION
 
 NEWLINE HANDLING WHEN MATCHING
 
-       When PCRE2 is built, a default newline convention is set; this is  usu-
-       ally  the standard convention for the operating system. The default can
-       be overridden in a compile context by calling  pcre2_set_newline().  It
-       can  also be overridden by starting a pattern string with, for example,
-       (*CRLF), as described in the section  on  newline  conventions  in  the
-       pcre2pattern  page. During matching, the newline choice affects the be-
-       haviour of the dot, circumflex, and dollar metacharacters. It may  also
-       alter  the  way  the  match starting position is advanced after a match
+       When  PCRE2 is built, a default newline convention is set; this is usu-
+       ally the standard convention for the operating system. The default  can
+       be  overridden  in a compile context by calling pcre2_set_newline(). It
+       can also be overridden by starting a pattern string with, for  example,
+       (*CRLF),  as  described  in  the  section on newline conventions in the
+       pcre2pattern page. During matching, the newline choice affects the  be-
+       haviour  of the dot, circumflex, and dollar metacharacters. It may also
+       alter the way the match starting position is  advanced  after  a  match
        failure for an unanchored pattern.
 
        When PCRE2_NEWLINE_CRLF, PCRE2_NEWLINE_ANYCRLF, or PCRE2_NEWLINE_ANY is
        set  as  the  newline convention, and a match attempt for an unanchored
        pattern fails when the current starting position is at a CRLF sequence,
-       and  the  pattern contains no explicit matches for CR or LF characters,
-       the match position is advanced by two characters  instead  of  one,  in
+       and the pattern contains no explicit matches for CR or  LF  characters,
+       the  match  position  is  advanced by two characters instead of one, in
        other words, to after the CRLF.
 
        The above rule is a compromise that makes the most common cases work as
@@ -2815,10 +2968,10 @@ NEWLINE HANDLING WHEN MATCHING
        An explicit match for CR of LF is either a literal appearance of one of
        those characters in the pattern, or one of the \r or \n  or  equivalent
        octal or hexadecimal escape sequences. Implicit matches such as [^X] do
-       not count, nor does \s, even though it includes CR and LF in the  char-
+       not  count, nor does \s, even though it includes CR and LF in the char-
        acters that it matches.
 
-       Notwithstanding  the above, anomalous effects may still occur when CRLF
+       Notwithstanding the above, anomalous effects may still occur when  CRLF
        is a valid newline sequence and explicit \r or \n escapes appear in the
        pattern.
 
@@ -2836,10 +2989,10 @@ HOW PCRE2_MATCH() RETURNS A STRING AND CAPTURED SUBSTRINGS
        phrase  "capture  group" (Perl terminology) is used for a fragment of a
        pattern that picks out a substring. PCRE2 supports several other  kinds
        of parenthesized group that do not cause substrings to be captured. The
-       pcre2_pattern_info() function can be used to find out how many  capture
+       pcre2_pattern_info()  function can be used to find out how many capture
        groups there are in a compiled pattern.
 
-       You  can  use  auxiliary functions for accessing captured substrings by
+       You can use auxiliary functions for accessing  captured  substrings  by
        number or by name, as described in sections below.
 
        Alternatively, you can make direct use of the vector of PCRE2_SIZE val-
@@ -2851,8 +3004,8 @@ HOW PCRE2_MATCH() RETURNS A STRING AND CAPTURED SUBSTRINGS
 
        Within the ovector, the first in each pair of values is set to the off-
        set of the first code unit of a substring, and the second is set to the
-       offset  of the first code unit after the end of a substring. These val-
-       ues are always code unit offsets, not character offsets. That is,  they
+       offset of the first code unit after the end of a substring. These  val-
+       ues  are always code unit offsets, not character offsets. That is, they
        are byte offsets in the 8-bit library, 16-bit offsets in the 16-bit li-
        brary, and 32-bit offsets in the 32-bit library.
 
@@ -2870,7 +3023,7 @@ HOW PCRE2_MATCH() RETURNS A STRING AND CAPTURED SUBSTRINGS
        strings, the return value from a successful match is 1, indicating that
        just the first pair of offsets has been set.
 
-       If a pattern uses the \K escape sequence within a  positive  assertion,
+       If  a  pattern uses the \K escape sequence within a positive assertion,
        the reported start of a successful match can be greater than the end of
        the match.  For example, if the pattern  (?=ab\K)  is  matched  against
        "ab", the start and end offset values for the match are 2 and 0.
@@ -2885,8 +3038,8 @@ HOW PCRE2_MATCH() RETURNS A STRING AND CAPTURED SUBSTRINGS
        called with a match data block whose ovector is of minimum length (that
        is, one pair).
 
-       It  is  possible for capture group number n+1 to match some part of the
-       subject when group n has not been used at  all.  For  example,  if  the
+       It is possible for capture group number n+1 to match some part  of  the
+       subject  when  group  n  has  not been used at all. For example, if the
        string "abc" is matched against the pattern (a|(z))(bc) the return from
        the function is 4, and groups 1 and 3 are matched, but 2 is  not.  When
        this  happens,  both values in the offset pairs corresponding to unused
@@ -2896,9 +3049,9 @@ HOW PCRE2_MATCH() RETURNS A STRING AND CAPTURED SUBSTRINGS
        pression  are also set to PCRE2_UNSET. For example, if the string "abc"
        is matched against the pattern (abc)(x(yz)?)? groups 2 and  3  are  not
        matched.  The  return  from the function is 2, because the highest used
-       capture group number is 1. The offsets for for  the  second  and  third
-       capture  groupss  (assuming  the vector is large enough, of course) are
-       set to PCRE2_UNSET.
+       capture group number is 1. The offsets for the second and third capture
+       groups (assuming the vector is large enough,  of  course)  are  set  to
+       PCRE2_UNSET.
 
        Elements in the ovector that do not correspond to capturing parentheses
        in the pattern are never changed. That is, if a pattern contains n cap-
@@ -2926,11 +3079,11 @@ OTHER INFORMATION ABOUT A MATCH
        verbs, not just (*MARK). The same function applies to all the verbs. It
        returns a pointer to the zero-terminated name, which is within the com-
        piled pattern. If no name is available, NULL is returned. The length of
-       the  name  (excluding  the terminating zero) is stored in the code unit
-       that precedes the name. You should use this length instead  of  relying
+       the name (excluding the terminating zero) is stored in  the  code  unit
+       that  precedes  the name. You should use this length instead of relying
        on the terminating zero if the name might contain a binary zero.
 
-       After  a  successful  match, the name that is returned is the last mark
+       After a successful match, the name that is returned is  the  last  mark
        name encountered on the matching path through the pattern. Instances of
        backtracking  verbs  without  names do not count. Thus, for example, if
        the matching path contains (*MARK:A)(*PRUNE), the name "A" is returned.
@@ -2949,12 +3102,12 @@ OTHER INFORMATION ABOUT A MATCH
        anchoring  is removed from the pattern above, there is an initial check
        for the presence of "c" in the subject before running the matching  en-
        gine. This check fails for "bx", causing a match failure without seeing
-       any marks. You can disable the start-of-match optimizations by  setting
-       the  PCRE2_NO_START_OPTIMIZE  option for pcre2_compile() or by starting
+       any  marks. You can disable the start-of-match optimizations by setting
+       the PCRE2_NO_START_OPTIMIZE option for pcre2_compile() or  by  starting
        the pattern with (*NO_START_OPT).
 
-       After a successful match, a partial match, or one of  the  invalid  UTF
-       errors  (for example, PCRE2_ERROR_UTF8_ERR5), pcre2_get_startchar() can
+       After  a  successful  match, a partial match, or one of the invalid UTF
+       errors (for example, PCRE2_ERROR_UTF8_ERR5), pcre2_get_startchar()  can
        be called. After a successful or partial match it returns the code unit
        offset  of  the character at which the match started. For a non-partial
        match, this can be different to the value of ovector[0] if the  pattern
@@ -2969,11 +3122,11 @@ OTHER INFORMATION ABOUT A MATCH
 
 ERROR RETURNS FROM pcre2_match()
 
-       If  pcre2_match() fails, it returns a negative number. This can be con-
-       verted to a text string by calling the pcre2_get_error_message()  func-
-       tion  (see  "Obtaining a textual error message" below).  Negative error
-       codes are also returned by other functions,  and  are  documented  with
-       them.  The codes are given names in the header file. If UTF checking is
+       If pcre2_match() fails, it returns a negative number. This can be  con-
+       verted  to a text string by calling the pcre2_get_error_message() func-
+       tion (see "Obtaining a textual error message" below).   Negative  error
+       codes  are  also  returned  by other functions, and are documented with
+       them. The codes are given names in the header file. If UTF checking  is
        in force and an invalid UTF subject string is detected, one of a number
        of  UTF-specific negative error codes is returned. Details are given in
        the pcre2unicode page. The following are the other errors that  may  be
@@ -2991,14 +3144,14 @@ ERROR RETURNS FROM pcre2_match()
          PCRE2_ERROR_BADMAGIC
 
        PCRE2 stores a 4-byte "magic number" at the start of the compiled code,
-       to  catch  the case when it is passed a junk pointer. This is the error
+       to catch the case when it is passed a junk pointer. This is  the  error
        that is returned when the magic number is not present.
 
          PCRE2_ERROR_BADMODE
 
-       This error is given when a compiled pattern is passed to a function  in
-       a  library  of a different code unit width, for example, a pattern com-
-       piled by the 8-bit library is passed to  a  16-bit  or  32-bit  library
+       This  error is given when a compiled pattern is passed to a function in
+       a library of a different code unit width, for example, a  pattern  com-
+       piled  by  the  8-bit  library  is passed to a 16-bit or 32-bit library
        function.
 
          PCRE2_ERROR_BADOFFSET
@@ -3049,11 +3202,11 @@ ERROR RETURNS FROM pcre2_match()
 
          PCRE2_ERROR_NOMEMORY
 
-       Heap  memory  is  used  to  remember backgracking points. This error is
+       Heap  memory  is  used  to  remember backtracking points. This error is
        given when the memory allocation function (default  or  custom)  fails.
        Note  that  a  different  error, PCRE2_ERROR_HEAPLIMIT, is given if the
        amount of memory needed exceeds the heap limit. PCRE2_ERROR_NOMEMORY is
-       also  returned  if PCRE2_COPY_MATCHED_SUBJECT is set and memory alloca-
+       also returned if PCRE2_COPY_MATCHED_SUBJECT is set and  memory  alloca-
        tion fails.
 
          PCRE2_ERROR_NULL
@@ -3062,8 +3215,8 @@ ERROR RETURNS FROM pcre2_match()
 
          PCRE2_ERROR_RECURSELOOP
 
-       This error is returned when  pcre2_match()  detects  a  recursion  loop
-       within  the  pattern. Specifically, it means that either the whole pat-
+       This  error  is  returned  when  pcre2_match() detects a recursion loop
+       within the pattern. Specifically, it means that either the  whole  pat-
        tern or a capture group has been called recursively for the second time
        at  the  same position in the subject string. Some simple patterns that
        might do this are detected and faulted at compile time, but  more  com-
@@ -3087,7 +3240,7 @@ OBTAINING A TEXTUAL ERROR MESSAGE
        The returned message is terminated with a trailing zero, and the  func-
        tion  returns  the  number  of  code units used, excluding the trailing
        zero. If the error number is unknown, the negative error code PCRE2_ER-
-       ROR_BADDATA  is  returned.  If  the buffer is too small, the message is
+       ROR_BADDATA is returned. If the buffer is too  small,  the  message  is
        truncated (but still with a trailing zero), and the negative error code
        PCRE2_ERROR_NOMEMORY  is returned.  None of the messages are very long;
        a buffer size of 120 code units is ample.
@@ -3110,7 +3263,7 @@ EXTRACTING CAPTURED SUBSTRINGS BY NUMBER
 
        Captured substrings can be accessed directly by using  the  ovector  as
        described above.  For convenience, auxiliary functions are provided for
-       extracting  captured  substrings  as  new,  separate,   zero-terminated
+       extracting   captured  substrings  as  new,  separate,  zero-terminated
        strings. A substring that contains a binary zero is correctly extracted
        and has a further zero added on the end, but  the  result  is  not,  of
        course, a C string.
@@ -3124,23 +3277,23 @@ EXTRACTING CAPTURED SUBSTRINGS BY NUMBER
 
        If a pattern uses the \K escape sequence within a  positive  assertion,
        the reported start of a successful match can be greater than the end of
-       the match.  For example, if the pattern  (?=ab\K)  is  matched  against
-       "ab",  the  start  and  end offset values for the match are 2 and 0. In
-       this situation, calling these functions with a  zero  substring  number
+       the  match.   For  example,  if the pattern (?=ab\K) is matched against
+       "ab", the start and end offset values for the match are  2  and  0.  In
+       this  situation,  calling  these functions with a zero substring number
        extracts a zero-length empty string.
 
-       You  can  find the length in code units of a captured substring without
-       extracting it by calling pcre2_substring_length_bynumber().  The  first
-       argument  is a pointer to the match data block, the second is the group
-       number, and the third is a pointer to a variable into which the  length
-       is  placed.  If  you just want to know whether or not the substring has
+       You can find the length in code units of a captured  substring  without
+       extracting  it  by calling pcre2_substring_length_bynumber(). The first
+       argument is a pointer to the match data block, the second is the  group
+       number,  and the third is a pointer to a variable into which the length
+       is placed. If you just want to know whether or not  the  substring  has
        been captured, you can pass the third argument as NULL.
 
-       The pcre2_substring_copy_bynumber() function  copies  a  captured  sub-
-       string  into  a supplied buffer, whereas pcre2_substring_get_bynumber()
-       copies it into new memory, obtained using the  same  memory  allocation
-       function  that  was  used for the match data block. The first two argu-
-       ments of these functions are a pointer to the match data  block  and  a
+       The  pcre2_substring_copy_bynumber()  function  copies  a captured sub-
+       string into a supplied buffer,  whereas  pcre2_substring_get_bynumber()
+       copies  it  into  new memory, obtained using the same memory allocation
+       function that was used for the match data block. The  first  two  argu-
+       ments  of  these  functions are a pointer to the match data block and a
        capture group number.
 
        The final arguments of pcre2_substring_copy_bynumber() are a pointer to
@@ -3149,25 +3302,25 @@ EXTRACTING CAPTURED SUBSTRINGS BY NUMBER
        for the extracted substring, excluding the terminating zero.
 
        For pcre2_substring_get_bynumber() the third and fourth arguments point
-       to  variables that are updated with a pointer to the new memory and the
-       number of code units that comprise the substring, again  excluding  the
-       terminating  zero.  When  the substring is no longer needed, the memory
+       to variables that are updated with a pointer to the new memory and  the
+       number  of  code units that comprise the substring, again excluding the
+       terminating zero. When the substring is no longer  needed,  the  memory
        should be freed by calling pcre2_substring_free().
 
-       The return value from all these functions is zero  for  success,  or  a
-       negative  error  code.  If  the pattern match failed, the match failure
-       code is returned.  If a substring number greater than zero is used  af-
-       ter  a  partial  match, PCRE2_ERROR_PARTIAL is returned. Other possible
+       The  return  value  from  all these functions is zero for success, or a
+       negative error code. If the pattern match  failed,  the  match  failure
+       code  is returned.  If a substring number greater than zero is used af-
+       ter a partial match, PCRE2_ERROR_PARTIAL is  returned.  Other  possible
        error codes are:
 
          PCRE2_ERROR_NOMEMORY
 
-       The buffer was too small for  pcre2_substring_copy_bynumber(),  or  the
+       The  buffer  was  too small for pcre2_substring_copy_bynumber(), or the
        attempt to get memory failed for pcre2_substring_get_bynumber().
 
          PCRE2_ERROR_NOSUBSTRING
 
-       There  is  no  substring  with that number in the pattern, that is, the
+       There is no substring with that number in the  pattern,  that  is,  the
        number is greater than the number of capturing parentheses.
 
          PCRE2_ERROR_UNAVAILABLE
@@ -3178,8 +3331,8 @@ EXTRACTING CAPTURED SUBSTRINGS BY NUMBER
 
          PCRE2_ERROR_UNSET
 
-       The substring did not participate in the match.  For  example,  if  the
-       pattern  is  (abc)|(def) and the subject is "def", and the ovector con-
+       The  substring  did  not  participate in the match. For example, if the
+       pattern is (abc)|(def) and the subject is "def", and the  ovector  con-
        tains at least two capturing slots, substring number 1 is unset.
 
 
@@ -3188,12 +3341,12 @@ EXTRACTING A LIST OF ALL CAPTURED SUBSTRINGS
        int pcre2_substring_list_get(pcre2_match_data *match_data,
          PCRE2_UCHAR ***listptr, PCRE2_SIZE **lengthsptr);
 
-       void pcre2_substring_list_free(PCRE2_SPTR *list);
+       void pcre2_substring_list_free(PCRE2_UCHAR **list);
 
-       The pcre2_substring_list_get() function  extracts  all  available  sub-
-       strings  and  builds  a  list of pointers to them. It also (optionally)
-       builds a second list that contains their lengths (in code  units),  ex-
-       cluding  a  terminating zero that is added to each of them. All this is
+       The  pcre2_substring_list_get()  function  extracts  all available sub-
+       strings and builds a list of pointers to  them.  It  also  (optionally)
+       builds  a  second list that contains their lengths (in code units), ex-
+       cluding a terminating zero that is added to each of them. All  this  is
        done in a single block of memory that is obtained using the same memory
        allocation function that was used to get the match data block.
 
@@ -3202,8 +3355,8 @@ EXTRACTING A LIST OF ALL CAPTURED SUBSTRINGS
 
        The address of the memory block is returned via listptr, which is  also
        the start of the list of string pointers. The end of the list is marked
-       by a NULL pointer. The address of the list of lengths is  returned  via
-       lengthsptr.  If your strings do not contain binary zeros and you do not
+       by  a  NULL pointer. The address of the list of lengths is returned via
+       lengthsptr. If your strings do not contain binary zeros and you do  not
        therefore need the lengths, you may supply NULL as the lengthsptr argu-
        ment  to  disable  the  creation of a list of lengths. The yield of the
        function is zero if all went well, or PCRE2_ERROR_NOMEMORY if the  mem-
@@ -3211,8 +3364,8 @@ EXTRACTING A LIST OF ALL CAPTURED SUBSTRINGS
        should be freed by calling pcre2_substring_list_free().
 
        If this function encounters a substring that is unset, which can happen
-       when  capture  group  number  n+1 matches some part of the subject, but
-       group n has not been used at all, it returns an empty string. This  can
+       when capture group number n+1 matches some part  of  the  subject,  but
+       group  n has not been used at all, it returns an empty string. This can
        be distinguished from a genuine zero-length substring by inspecting the
        appropriate offset in the ovector, which contain PCRE2_UNSET for  unset
        substrings, or by calling pcre2_substring_length_bynumber().
@@ -3242,28 +3395,28 @@ EXTRACTING CAPTURED SUBSTRINGS BY NAME
        the number of the capture group called "xxx" is 2. If the name is known
        to be unique (PCRE2_DUPNAMES was not set), you can find the number from
        the name by calling pcre2_substring_number_from_name(). The first argu-
-       ment  is the compiled pattern, and the second is the name. The yield of
-       the function is the group number, PCRE2_ERROR_NOSUBSTRING if  there  is
-       no  group  with that name, or PCRE2_ERROR_NOUNIQUESUBSTRING if there is
-       more than one group with that name.  Given the number, you can  extract
-       the  substring  directly from the ovector, or use one of the "bynumber"
+       ment is the compiled pattern, and the second is the name. The yield  of
+       the  function  is the group number, PCRE2_ERROR_NOSUBSTRING if there is
+       no group with that name, or PCRE2_ERROR_NOUNIQUESUBSTRING if  there  is
+       more  than one group with that name.  Given the number, you can extract
+       the substring directly from the ovector, or use one of  the  "bynumber"
        functions described above.
 
-       For convenience, there are also "byname" functions that  correspond  to
+       For  convenience,  there are also "byname" functions that correspond to
        the "bynumber" functions, the only difference being that the second ar-
        gument is a name instead of a number.  If  PCRE2_DUPNAMES  is  set  and
        there are duplicate names, these functions scan all the groups with the
-       given name, and return the captured  substring  from  the  first  named
+       given  name,  and  return  the  captured substring from the first named
        group that is set.
 
-       If  there are no groups with the given name, PCRE2_ERROR_NOSUBSTRING is
-       returned. If all groups with the name have  numbers  that  are  greater
+       If there are no groups with the given name, PCRE2_ERROR_NOSUBSTRING  is
+       returned.  If  all  groups  with the name have numbers that are greater
        than the number of slots in the ovector, PCRE2_ERROR_UNAVAILABLE is re-
        turned. If there is at least one group with a slot in the ovector,  but
        no group is found to be set, PCRE2_ERROR_UNSET is returned.
 
        Warning: If the pattern uses the (?| feature to set up multiple capture
-       groups with the same number, as described in the section  on  duplicate
+       groups  with  the same number, as described in the section on duplicate
        group numbers in the pcre2pattern page, you cannot use names to distin-
        guish the different capture groups, because names are not  included  in
        the  compiled  code.  The  matching process uses only numbers. For this
@@ -3283,9 +3436,9 @@ CREATING A NEW STRING WITH SUBSTITUTIONS
        This  function  optionally calls pcre2_match() and then makes a copy of
        the subject string in outputbuffer, replacing parts that  were  matched
        with the replacement string, whose length is supplied in rlength, which
-       can be given as PCRE2_ZERO_TERMINATED for a zero-terminated string.  As
-       a  special  case,  if  replacement is NULL and rlength is zero, the re-
-       placement is assumed to be an empty string. If rlength is non-zero,  an
+       can  be given as PCRE2_ZERO_TERMINATED for a zero-terminated string. As
+       a special case, if replacement is NULL and rlength  is  zero,  the  re-
+       placement  is assumed to be an empty string. If rlength is non-zero, an
        error occurs if replacement is NULL.
 
        There is an option (see PCRE2_SUBSTITUTE_REPLACEMENT_ONLY below) to re-
@@ -3302,10 +3455,10 @@ CREATING A NEW STRING WITH SUBSTITUTIONS
        Matches in which a \K item in a lookahead in  the  pattern  causes  the
        match  to  end  before it starts are not supported, and give rise to an
        error return. For global replacements, matches in which \K in a lookbe-
-       hind  causes the match to start earlier than the point that was reached
+       hind causes the match to start earlier than the point that was  reached
        in the previous iteration are also not supported.
 
-       The first seven arguments of pcre2_substitute() are  the  same  as  for
+       The  first  seven  arguments  of pcre2_substitute() are the same as for
        pcre2_match(), except that the partial matching options are not permit-
        ted, and match_data may be passed as NULL, in which case a  match  data
        block  is obtained and freed within this function, using memory manage-
@@ -3314,7 +3467,7 @@ CREATING A NEW STRING WITH SUBSTITUTIONS
 
        If  match_data is not NULL and PCRE2_SUBSTITUTE_MATCHED is not set, the
        provided block is used for all calls to pcre2_match(), and its contents
-       afterwards  are  the result of the final call. For global changes, this
+       afterwards are the result of the final call. For global  changes,  this
        will always be a no-match error. The contents of the ovector within the
        match data block may or may not have been changed.
 
@@ -3323,9 +3476,9 @@ CREATING A NEW STRING WITH SUBSTITUTIONS
        such  option is PCRE2_SUBSTITUTE_MATCHED. When this is set, an external
        match_data block must be provided, and it must have already  been  used
        for an external call to pcre2_match() with the same pattern and subject
-       arguments. The data in the match_data block (return code,  offset  vec-
-       tor)  is  then  used  for  the  first  substitution  instead of calling
-       pcre2_match() from within pcre2_substitute(). This allows  an  applica-
+       arguments.  The  data in the match_data block (return code, offset vec-
+       tor) is then  used  for  the  first  substitution  instead  of  calling
+       pcre2_match()  from  within pcre2_substitute(). This allows an applica-
        tion to check for a match before choosing to substitute, without having
        to repeat the match.
 
@@ -3342,37 +3495,37 @@ CREATING A NEW STRING WITH SUBSTITUTIONS
        formation such as the UTF setting and the number of capturing parenthe-
        ses in the pattern.
 
-       The  default  action  of  pcre2_substitute() is to return a copy of the
+       The default action of pcre2_substitute() is to return  a  copy  of  the
        subject string with matched substrings replaced. However, if PCRE2_SUB-
        STITUTE_REPLACEMENT_ONLY  is  set,  only the replacement substrings are
        returned. In the global case, multiple replacements are concatenated in
-       the  output  buffer.  Substitution  callouts (see below) can be used to
+       the output buffer. Substitution callouts (see below)  can  be  used  to
        separate them if necessary.
 
-       The outlengthptr argument of pcre2_substitute() must point to  a  vari-
-       able  that contains the length, in code units, of the output buffer. If
-       the function is successful, the value is updated to contain the  length
-       in  code  units  of the new string, excluding the trailing zero that is
+       The  outlengthptr  argument of pcre2_substitute() must point to a vari-
+       able that contains the length, in code units, of the output buffer.  If
+       the  function is successful, the value is updated to contain the length
+       in code units of the new string, excluding the trailing  zero  that  is
        automatically added.
 
-       If the function is not successful, the value set via  outlengthptr  de-
-       pends  on  the  type  of  error.  For  syntax errors in the replacement
+       If  the  function is not successful, the value set via outlengthptr de-
+       pends on the type of  error.  For  syntax  errors  in  the  replacement
        string, the value is the offset in the replacement string where the er-
        ror  was  detected.  For  other errors, the value is PCRE2_UNSET by de-
        fault. This includes the case of the output buffer being too small, un-
        less PCRE2_SUBSTITUTE_OVERFLOW_LENGTH is set.
 
-       PCRE2_SUBSTITUTE_OVERFLOW_LENGTH  changes  what happens when the output
+       PCRE2_SUBSTITUTE_OVERFLOW_LENGTH changes what happens when  the  output
        buffer is too small. The default action is to return PCRE2_ERROR_NOMEM-
        ORY  immediately.  If  this  option is set, however, pcre2_substitute()
        continues to go through the motions of matching and substituting (with-
-       out,  of course, writing anything) in order to compute the size of buf-
-       fer that is needed. This value is  passed  back  via  the  outlengthptr
-       variable,  with  the  result  of  the  function  still  being PCRE2_ER-
+       out, of course, writing anything) in  order  to  compute  the  size  of
+       buffer  that  is needed. This value is passed back via the outlengthptr
+       variable, with  the  result  of  the  function  still  being  PCRE2_ER-
        ROR_NOMEMORY.
 
-       Passing a buffer size of zero is a permitted way  of  finding  out  how
-       much  memory  is needed for given substitution. However, this does mean
+       Passing  a  buffer  size  of zero is a permitted way of finding out how
+       much memory is needed for given substitution. However, this  does  mean
        that the entire operation is carried out twice. Depending on the appli-
        cation,  it  may  be more efficient to allocate a large buffer and free
        the  excess  afterwards,  instead   of   using   PCRE2_SUBSTITUTE_OVER-
@@ -3383,11 +3536,12 @@ CREATING A NEW STRING WITH SUBSTITUTIONS
        invalid UTF replacement string causes an immediate return with the rel-
        evant UTF error code.
 
-       If PCRE2_SUBSTITUTE_LITERAL is set, the replacement string is  not  in-
+       If  PCRE2_SUBSTITUTE_LITERAL  is set, the replacement string is not in-
        terpreted in any way. By default, however, a dollar character is an es-
        cape character that can specify the insertion of characters  from  cap-
        ture  groups  and names from (*MARK) or other control verbs in the pat-
-       tern. The following forms are always recognized:
+       tern. Dollar is the only escape character (backslash is treated as lit-
+       eral). The following forms are always recognized:
 
          $$                  insert a dollar character
          $ or ${}      insert the contents of group 
@@ -3396,13 +3550,13 @@ CREATING A NEW STRING WITH SUBSTITUTIONS
        Either a group number or a group name  can  be  given  for  .  Curly
        brackets  are  required only if the following character would be inter-
        preted as part of the number or name. The number may be zero to include
-       the  entire  matched  string.   For  example,  if  the pattern a(b)c is
-       matched with "=abc=" and the replacement string "+$1$0$1+", the  result
+       the entire matched string.   For  example,  if  the  pattern  a(b)c  is
+       matched  with "=abc=" and the replacement string "+$1$0$1+", the result
        is "=+babcb+=".
 
-       $*MARK  inserts the name from the last encountered backtracking control
-       verb on the matching path that has a name. (*MARK) must always  include
-       a  name,  but  the  other  verbs  need not. For example, in the case of
+       $*MARK inserts the name from the last encountered backtracking  control
+       verb  on the matching path that has a name. (*MARK) must always include
+       a name, but the other verbs need not.  For  example,  in  the  case  of
        (*MARK:A)(*PRUNE) the name inserted is "A", but for (*MARK:A)(*PRUNE:B)
        the  relevant  name is "B". This facility can be used to perform simple
        simultaneous substitutions, as this pcre2test example shows:
@@ -3412,11 +3566,11 @@ CREATING A NEW STRING WITH SUBSTITUTIONS
           2: pear orange
 
        PCRE2_SUBSTITUTE_GLOBAL causes the function to iterate over the subject
-       string,  replacing every matching substring. If this option is not set,
-       only the first matching substring is replaced. The search  for  matches
-       takes  place in the original subject string (that is, previous replace-
-       ments do not affect it).  Iteration is  implemented  by  advancing  the
-       startoffset  value  for  each search, which is always passed the entire
+       string, replacing every matching substring. If this option is not  set,
+       only  the  first matching substring is replaced. The search for matches
+       takes place in the original subject string (that is, previous  replace-
+       ments  do  not  affect  it).  Iteration is implemented by advancing the
+       startoffset value for each search, which is always  passed  the  entire
        subject string. If an offset limit is set in the match context, search-
        ing stops when that limit is reached.
 
@@ -3428,7 +3582,7 @@ CREATING A NEW STRING WITH SUBSTITUTIONS
          ABC ABC ABC ABC\=offset=3,offset_limit=12
           2: ABC A!C A!C ABC
 
-       When  continuing  with  global substitutions after matching a substring
+       When continuing with global substitutions after  matching  a  substring
        with zero length, an attempt to find a non-empty match at the same off-
        set is performed.  If this is not successful, the offset is advanced by
        one character except when CRLF is a valid newline sequence and the next
@@ -3441,8 +3595,8 @@ CREATING A NEW STRING WITH SUBSTITUTIONS
        or number no longer causes the PCRE2_ERROR_NOSUBSTRING error.
 
        PCRE2_SUBSTITUTE_UNSET_EMPTY causes unset capture groups (including un-
-       known groups when PCRE2_SUBSTITUTE_UNKNOWN_UNSET is set) to be  treated
-       as  empty  strings  when inserted as described above. If this option is
+       known  groups when PCRE2_SUBSTITUTE_UNKNOWN_UNSET is set) to be treated
+       as empty strings when inserted as described above. If  this  option  is
        not set, an attempt to insert an unset group causes the PCRE2_ERROR_UN-
        SET  error.  This  option  does not influence the extended substitution
        syntax described below.
@@ -3454,17 +3608,17 @@ CREATING A NEW STRING WITH SUBSTITUTIONS
 
        Firstly,  backslash in a replacement string is interpreted as an escape
        character. The usual forms such as \n or \x{ddd} can be used to specify
-       particular  character codes, and backslash followed by any non-alphanu-
-       meric character quotes that character. Extended quoting  can  be  coded
+       particular character codes, and backslash followed by any  non-alphanu-
+       meric  character  quotes  that character. Extended quoting can be coded
        using \Q...\E, exactly as in pattern strings.
 
-       There  are  also four escape sequences for forcing the case of inserted
-       letters.  The insertion mechanism has three states:  no  case  forcing,
+       There are also four escape sequences for forcing the case  of  inserted
+       letters.   The  insertion  mechanism has three states: no case forcing,
        force upper case, and force lower case. The escape sequences change the
        current state: \U and \L change to upper or lower case forcing, respec-
-       tively,  and  \E (when not terminating a \Q quoted sequence) reverts to
-       no case forcing. The sequences \u and \l force the next  character  (if
-       it  is  a  letter)  to  upper or lower case, respectively, and then the
+       tively, and \E (when not terminating a \Q quoted sequence)  reverts  to
+       no  case  forcing. The sequences \u and \l force the next character (if
+       it is a letter) to upper or lower  case,  respectively,  and  then  the
        state automatically reverts to no case forcing. Case forcing applies to
        all  inserted  characters, including those from capture groups and let-
        ters within \Q...\E quoted sequences. If either PCRE2_UTF or  PCRE2_UCP
@@ -3472,29 +3626,29 @@ CREATING A NEW STRING WITH SUBSTITUTIONS
        case forcing characters whose code points are greater than 127.
 
        Note that case forcing sequences such as \U...\E do not nest. For exam-
-       ple,  the  result of processing "\Uaa\LBB\Ecc\E" is "AAbbcc"; the final
-       \E has no effect. Note  also  that  the  PCRE2_ALT_BSUX  and  PCRE2_EX-
+       ple, the result of processing "\Uaa\LBB\Ecc\E" is "AAbbcc";  the  final
+       \E  has  no  effect.  Note  also  that the PCRE2_ALT_BSUX and PCRE2_EX-
        TRA_ALT_BSUX options do not apply to replacement strings.
 
-       The  second  effect of setting PCRE2_SUBSTITUTE_EXTENDED is to add more
-       flexibility to capture group substitution. The  syntax  is  similar  to
+       The second effect of setting PCRE2_SUBSTITUTE_EXTENDED is to  add  more
+       flexibility  to  capture  group  substitution. The syntax is similar to
        that used by Bash:
 
          ${:-}
          ${:+:}
 
-       As  before,   may be a group number or a name. The first form speci-
-       fies a default value. If group  is set, its value  is  inserted;  if
-       not,    is  expanded  and  the result inserted. The second form
-       specifies strings that are expanded and inserted when group  is  set
-       or  unset,  respectively. The first form is just a convenient shorthand
+       As before,  may be a group number or a name. The first  form  speci-
+       fies  a  default  value. If group  is set, its value is inserted; if
+       not,  is expanded and the  result  inserted.  The  second  form
+       specifies  strings that are expanded and inserted when group  is set
+       or unset, respectively. The first form is just a  convenient  shorthand
        for
 
          ${:+${}:}
 
-       Backslash can be used to escape colons and closing  curly  brackets  in
-       the  replacement  strings.  A change of the case forcing state within a
-       replacement string remains  in  force  afterwards,  as  shown  in  this
+       Backslash  can  be  used to escape colons and closing curly brackets in
+       the replacement strings. A change of the case forcing  state  within  a
+       replacement  string  remains  in  force  afterwards,  as  shown in this
        pcre2test example:
 
          /(some)?(body)/substitute_extended,replace=${1:+\U:\L}HeLLo
@@ -3503,8 +3657,8 @@ CREATING A NEW STRING WITH SUBSTITUTIONS
              somebody
           1: HELLO
 
-       The  PCRE2_SUBSTITUTE_UNSET_EMPTY option does not affect these extended
-       substitutions. However, PCRE2_SUBSTITUTE_UNKNOWN_UNSET does  cause  un-
+       The PCRE2_SUBSTITUTE_UNSET_EMPTY option does not affect these  extended
+       substitutions.  However,  PCRE2_SUBSTITUTE_UNKNOWN_UNSET does cause un-
        known groups in the extended syntax forms to be treated as unset.
 
        If  PCRE2_SUBSTITUTE_LITERAL  is  set,  PCRE2_SUBSTITUTE_UNKNOWN_UNSET,
@@ -3527,7 +3681,7 @@ CREATING A NEW STRING WITH SUBSTITUTIONS
 
        PCRE2_ERROR_NOMEMORY  is  returned  if  the  output  buffer  is not big
        enough. If the PCRE2_SUBSTITUTE_OVERFLOW_LENGTH option is set, the size
-       of  buffer  that is needed is returned via outlengthptr. Note that this
+       of buffer that is needed is returned via outlengthptr. Note  that  this
        does not happen by default.
 
        PCRE2_ERROR_NULL is returned if PCRE2_SUBSTITUTE_MATCHED is set but the
@@ -3538,14 +3692,14 @@ CREATING A NEW STRING WITH SUBSTITUTIONS
        PCRE2_ERROR_BADREPLACEMENT  is  used for miscellaneous syntax errors in
        the replacement string, with more  particular  errors  being  PCRE2_ER-
        ROR_BADREPESCAPE (invalid escape sequence), PCRE2_ERROR_REPMISSINGBRACE
-       (closing curly bracket not found), PCRE2_ERROR_BADSUBSTITUTION  (syntax
-       error  in  extended group substitution), and PCRE2_ERROR_BADSUBSPATTERN
+       (closing  curly bracket not found), PCRE2_ERROR_BADSUBSTITUTION (syntax
+       error in extended group substitution),  and  PCRE2_ERROR_BADSUBSPATTERN
        (the pattern match ended before it started or the match started earlier
        than  the  current  position  in the subject, which can happen if \K is
        used in an assertion).
 
        As for all PCRE2 errors, a text message that describes the error can be
-       obtained  by  calling  the pcre2_get_error_message() function (see "Ob-
+       obtained by calling the pcre2_get_error_message()  function  (see  "Ob-
        taining a textual error message" above).
 
    Substitution callouts
@@ -3554,11 +3708,11 @@ CREATING A NEW STRING WITH SUBSTITUTIONS
          int (*callout_function)(pcre2_substitute_callout_block *, void *),
          void *callout_data);
 
-       The pcre2_set_substitution_callout() function can be used to specify  a
-       callout  function for pcre2_substitute(). This information is passed in
+       The  pcre2_set_substitution_callout() function can be used to specify a
+       callout function for pcre2_substitute(). This information is passed  in
        a match context. The callout function is called after each substitution
        has been processed, but it can cause the replacement not to happen. The
-       callout function is not called for simulated substitutions that  happen
+       callout  function is not called for simulated substitutions that happen
        as a result of the PCRE2_SUBSTITUTE_OVERFLOW_LENGTH option.
 
        The first argument of the callout function is a pointer to a substitute
@@ -3586,22 +3740,22 @@ CREATING A NEW STRING WITH SUBSTITUTIONS
        the most recent match. The oveccount field contains the number of pairs
        that are set in the ovector, and is always greater than zero.
 
-       The output_offsets vector contains the offsets of  the  replacement  in
-       the  output  string. This has already been processed for dollar and (if
+       The  output_offsets  vector  contains the offsets of the replacement in
+       the output string. This has already been processed for dollar  and  (if
        requested) backslash substitutions as described above.
 
-       The second argument of the callout function  is  the  value  passed  as
-       callout_data  when  the  function was registered. The value returned by
+       The  second  argument  of  the  callout function is the value passed as
+       callout_data when the function was registered. The  value  returned  by
        the callout function is interpreted as follows:
 
-       If the value is zero, the replacement is accepted, and,  if  PCRE2_SUB-
-       STITUTE_GLOBAL  is set, processing continues with a search for the next
-       match. If the value is not zero, the current  replacement  is  not  ac-
-       cepted.  If  the  value is greater than zero, processing continues when
-       PCRE2_SUBSTITUTE_GLOBAL is set. Otherwise (the value is less than  zero
-       or  PCRE2_SUBSTITUTE_GLOBAL  is  not set), the the rest of the input is
-       copied to the output and the call to pcre2_substitute() exits,  return-
-       ing the number of matches so far.
+       If  the  value is zero, the replacement is accepted, and, if PCRE2_SUB-
+       STITUTE_GLOBAL is set, processing continues with a search for the  next
+       match.  If  the  value  is not zero, the current replacement is not ac-
+       cepted. If the value is greater than zero,  processing  continues  when
+       PCRE2_SUBSTITUTE_GLOBAL  is set. Otherwise (the value is less than zero
+       or PCRE2_SUBSTITUTE_GLOBAL is not set), the rest of the input is copied
+       to the output and the call to pcre2_substitute() exits,  returning  the
+       number of matches so far.
 
 
 DUPLICATE CAPTURE GROUP NAMES
@@ -3615,28 +3769,28 @@ DUPLICATE CAPTURE GROUP NAMES
        feature. Indeed, if such groups are named, they are required to use the
        same names.
 
-       Normally,  patterns  that  use duplicate names are such that in any one
-       match, only one of each set of identically-named  groups  participates.
+       Normally, patterns that use duplicate names are such that  in  any  one
+       match,  only  one of each set of identically-named groups participates.
        An example is shown in the pcre2pattern documentation.
 
-       When   duplicates   are   present,   pcre2_substring_copy_byname()  and
-       pcre2_substring_get_byname() return the first  substring  corresponding
-       to  the given name that is set. Only if none are set is PCRE2_ERROR_UN-
-       SET is returned. The  pcre2_substring_number_from_name()  function  re-
-       turns  the error PCRE2_ERROR_NOUNIQUESUBSTRING when there are duplicate
+       When  duplicates   are   present,   pcre2_substring_copy_byname()   and
+       pcre2_substring_get_byname()  return  the first substring corresponding
+       to the given name that is set. Only if none are set is  PCRE2_ERROR_UN-
+       SET  is  returned.  The pcre2_substring_number_from_name() function re-
+       turns the error PCRE2_ERROR_NOUNIQUESUBSTRING when there are  duplicate
        names.
 
-       If you want to get full details of all captured substrings for a  given
-       name,  you  must use the pcre2_substring_nametable_scan() function. The
-       first argument is the compiled pattern, and the second is the name.  If
-       the  third  and fourth arguments are NULL, the function returns a group
+       If  you want to get full details of all captured substrings for a given
+       name, you must use the pcre2_substring_nametable_scan()  function.  The
+       first  argument is the compiled pattern, and the second is the name. If
+       the third and fourth arguments are NULL, the function returns  a  group
        number for a unique name, or PCRE2_ERROR_NOUNIQUESUBSTRING otherwise.
 
        When the third and fourth arguments are not NULL, they must be pointers
        to  variables  that are updated by the function. After it has run, they
        point to the first and last entries in the name-to-number table for the
-       given  name,  and the function returns the length of each entry in code
-       units. In both cases, PCRE2_ERROR_NOSUBSTRING is returned if there  are
+       given name, and the function returns the length of each entry  in  code
+       units.  In both cases, PCRE2_ERROR_NOSUBSTRING is returned if there are
        no entries for the given name.
 
        The format of the name table is described above in the section entitled
@@ -3650,15 +3804,15 @@ FINDING ALL POSSIBLE MATCHES AT ONE POSITION
        The traditional matching function uses a  similar  algorithm  to  Perl,
        which  stops when it finds the first match at a given point in the sub-
        ject. If you want to find all possible matches, or the longest possible
-       match  at  a  given  position,  consider using the alternative matching
-       function (see below) instead. If you cannot use the  alternative  func-
+       match at a given position,  consider  using  the  alternative  matching
+       function  (see  below) instead. If you cannot use the alternative func-
        tion, you can kludge it up by making use of the callout facility, which
        is described in the pcre2callout documentation.
 
        What you have to do is to insert a callout right at the end of the pat-
-       tern.   When your callout function is called, extract and save the cur-
-       rent matched substring. Then return 1, which  forces  pcre2_match()  to
-       backtrack  and  try other alternatives. Ultimately, when it runs out of
+       tern.  When your callout function is called, extract and save the  cur-
+       rent  matched  substring.  Then return 1, which forces pcre2_match() to
+       backtrack and try other alternatives. Ultimately, when it runs  out  of
        matches, pcre2_match() will yield PCRE2_ERROR_NOMATCH.
 
 
@@ -3670,14 +3824,14 @@ MATCHING A PATTERN: THE ALTERNATIVE FUNCTION
          pcre2_match_context *mcontext,
          int *workspace, PCRE2_SIZE wscount);
 
-       The function pcre2_dfa_match() is called  to  match  a  subject  string
-       against  a  compiled pattern, using a matching algorithm that scans the
+       The  function  pcre2_dfa_match()  is  called  to match a subject string
+       against a compiled pattern, using a matching algorithm that  scans  the
        subject string just once (not counting lookaround assertions), and does
        not  backtrack (except when processing lookaround assertions). This has
        different characteristics to the normal algorithm, and is not  compati-
        ble  with  Perl.  Some  of  the features of PCRE2 patterns are not sup-
        ported. Nevertheless, there are times when this kind of matching can be
-       useful.  For a discussion of the two matching algorithms, and a list of
+       useful. For a discussion of the two matching algorithms, and a list  of
        features that pcre2_dfa_match() does not support, see the pcre2matching
        documentation.
 
@@ -3689,9 +3843,9 @@ MATCHING A PATTERN: THE ALTERNATIVE FUNCTION
 
        The  two  additional  arguments provide workspace for the function. The
        workspace vector should contain at least 20 elements. It  is  used  for
-       keeping  track  of  multiple  paths  through  the  pattern  tree.  More
-       workspace is needed for patterns and subjects where there are a lot  of
-       potential matches.
+       keeping  track  of  multiple paths through the pattern tree. More work-
+       space is needed for patterns and subjects where there are a lot of  po-
+       tential matches.
 
        Here is an example of a simple call to pcre2_dfa_match():
 
@@ -3730,7 +3884,7 @@ MATCHING A PATTERN: THE ALTERNATIVE FUNCTION
        return  code  PCRE2_ERROR_NOMATCH is converted into PCRE2_ERROR_PARTIAL
        if the end of the subject is  reached,  there  have  been  no  complete
        matches, but there is still at least one matching possibility. The por-
-       tion of the string that was inspected when the  longest  partial  match
+       tion  of  the  string that was inspected when the longest partial match
        was found is set as the first matching string in both cases. There is a
        more detailed discussion of partial and  multi-segment  matching,  with
        examples, in the pcre2partial documentation.
@@ -3739,16 +3893,16 @@ MATCHING A PATTERN: THE ALTERNATIVE FUNCTION
 
        Setting  the PCRE2_DFA_SHORTEST option causes the matching algorithm to
        stop as soon as it has found one match. Because of the way the alterna-
-       tive  algorithm  works, this is necessarily the shortest possible match
+       tive algorithm works, this is necessarily the shortest  possible  match
        at the first possible matching point in the subject string.
 
          PCRE2_DFA_RESTART
 
-       When pcre2_dfa_match() returns a partial match, it is possible to  call
+       When  pcre2_dfa_match() returns a partial match, it is possible to call
        it again, with additional subject characters, and have it continue with
        the same match. The PCRE2_DFA_RESTART option requests this action; when
-       it  is  set,  the workspace and wscount options must reference the same
-       vector as before because data about the match so far is  left  in  them
+       it is set, the workspace and wscount options must  reference  the  same
+       vector  as  before  because data about the match so far is left in them
        after a partial match. There is more discussion of this facility in the
        pcre2partial documentation.
 
@@ -3781,18 +3935,18 @@ MATCHING A PATTERN: THE ALTERNATIVE FUNCTION
 
        Calls  to the convenience functions that extract substrings by name re-
        turn the error PCRE2_ERROR_DFA_UFUNC (unsupported function) if used af-
-       ter  a  DFA match. The convenience functions that extract substrings by
+       ter a DFA match. The convenience functions that extract  substrings  by
        number never return PCRE2_ERROR_NOSUBSTRING.
 
-       The matched strings are stored in  the  ovector  in  reverse  order  of
-       length;  that  is,  the longest matching string is first. If there were
-       too many matches to fit into the ovector, the yield of the function  is
+       The  matched  strings  are  stored  in  the ovector in reverse order of
+       length; that is, the longest matching string is first.  If  there  were
+       too  many matches to fit into the ovector, the yield of the function is
        zero, and the vector is filled with the longest matches.
 
-       NOTE:  PCRE2's  "auto-possessification" optimization usually applies to
-       character repeats at the end of a pattern (as well as internally).  For
-       example,  the pattern "a\d+" is compiled as if it were "a\d++". For DFA
-       matching, this means that only one possible match is found. If you  re-
+       NOTE: PCRE2's "auto-possessification" optimization usually  applies  to
+       character  repeats at the end of a pattern (as well as internally). For
+       example, the pattern "a\d+" is compiled as if it were "a\d++". For  DFA
+       matching,  this means that only one possible match is found. If you re-
        ally do want multiple matches in such cases, either use an ungreedy re-
        peat such as "a\d+?" or set the PCRE2_NO_AUTO_POSSESS option when  com-
        piling.
@@ -3800,7 +3954,7 @@ MATCHING A PATTERN: THE ALTERNATIVE FUNCTION
    Error returns from pcre2_dfa_match()
 
        The pcre2_dfa_match() function returns a negative number when it fails.
-       Many of the errors are the same  as  for  pcre2_match(),  as  described
+       Many  of  the  errors  are  the same as for pcre2_match(), as described
        above.  There are in addition the following errors that are specific to
        pcre2_dfa_match():
 
@@ -3818,13 +3972,13 @@ MATCHING A PATTERN: THE ALTERNATIVE FUNCTION
 
          PCRE2_ERROR_DFA_UINVALID_UTF
 
-       This return is given if pcre2_dfa_match() is called for a pattern  that
-       was  compiled  with  PCRE2_MATCH_INVALID_UTF. This is not supported for
+       This  return is given if pcre2_dfa_match() is called for a pattern that
+       was compiled with PCRE2_MATCH_INVALID_UTF. This is  not  supported  for
        DFA matching.
 
          PCRE2_ERROR_DFA_WSSIZE
 
-       This return is given if pcre2_dfa_match() runs  out  of  space  in  the
+       This  return  is  given  if  pcre2_dfa_match() runs out of space in the
        workspace vector.
 
          PCRE2_ERROR_DFA_RECURSE
@@ -3858,31 +4012,36 @@ AUTHOR
 
 REVISION
 
-       Last updated: 27 July 2022
-       Copyright (c) 1997-2022 University of Cambridge.
+       Last updated: 24 April 2024
+       Copyright (c) 1997-2024 University of Cambridge.
+
+
+PCRE2 10.44                      24 April 2024                     PCRE2API(3)
 ------------------------------------------------------------------------------
 
 
-PCRE2BUILD(3)              Library Functions Manual              PCRE2BUILD(3)
 
+PCRE2BUILD(3)              Library Functions Manual              PCRE2BUILD(3)
 
 
 NAME
        PCRE2 - Perl-compatible regular expressions (revised API)
 
+
 BUILDING PCRE2
 
        PCRE2  is distributed with a configure script that can be used to build
        the library in Unix-like environments using the applications  known  as
        Autotools. Also in the distribution are files to support building using
-       CMake instead of configure. The text file README contains  general  in-
-       formation  about building with Autotools (some of which is repeated be-
-       low), and also has some comments about building  on  various  operating
-       systems.  There  is a lot more information about building PCRE2 without
-       using Autotools (including information about using CMake  and  building
-       "by  hand")  in  the  text file called NON-AUTOTOOLS-BUILD.  You should
-       consult this file as well as the README file if you are building  in  a
-       non-Unix-like environment.
+       CMake  instead  of configure. The text file README contains general in-
+       formation about building with Autotools (some of which is repeated  be-
+       low),  and  also  has some comments about building on various operating
+       systems. The files in the vms directory support building under OpenVMS.
+       There is a lot more information about building PCRE2 without using  Au-
+       totools  (including  information  about  using  CMake  and building "by
+       hand") in the text file called NON-AUTOTOOLS-BUILD.  You should consult
+       this file as well as the README file if you are building in a non-Unix-
+       like environment.
 
 
 PCRE2 BUILD-TIME OPTIONS
@@ -3900,12 +4059,12 @@ PCRE2 BUILD-TIME OPTIONS
        compiler, as described in NON-AUTOTOOLS-BUILD.
 
        The complete list of options for configure (which includes the standard
-       ones such as the selection of the installation directory)  can  be  ob-
+       ones  such  as  the selection of the installation directory) can be ob-
        tained by running
 
          ./configure --help
 
-       The  following  sections include descriptions of "on/off" options whose
+       The following sections include descriptions of "on/off"  options  whose
        names begin with --enable or --disable. Because of the way that config-
        ure  works, --enable and --disable always come in pairs, so the comple-
        mentary option always exists as well, but as it specifies the  default,
@@ -3922,7 +4081,7 @@ BUILDING 8-BIT, 16-BIT AND 32-BIT LIBRARIES
        two other libraries, called libpcre2-16 and libpcre2-32, which  process
        strings  that  are contained in arrays of 16-bit and 32-bit code units,
        respectively. These can be interpreted either as single-unit characters
-       or  UTF-16/UTF-32 strings. To build these additional libraries, add one
+       or UTF-16/UTF-32 strings. To build these additional libraries, add  one
        or both of the following to the configure command:
 
          --enable-pcre2-16
@@ -3932,22 +4091,33 @@ BUILDING 8-BIT, 16-BIT AND 32-BIT LIBRARIES
 
          --disable-pcre2-8
 
-       as well. At least one of the three libraries must be built.  Note  that
-       the  POSIX wrapper is for the 8-bit library only, and that pcre2grep is
-       an 8-bit program. Neither of these are built if  you  select  only  the
+       as  well.  At least one of the three libraries must be built. Note that
+       the POSIX wrapper is for the 8-bit library only, and that pcre2grep  is
+       an  8-bit  program.  Neither  of these are built if you select only the
        16-bit or 32-bit libraries.
 
 
 BUILDING SHARED AND STATIC LIBRARIES
 
-       The  Autotools PCRE2 building process uses libtool to build both shared
-       and static libraries by default. You can suppress an  unwanted  library
+       The Autotools PCRE2 building process uses libtool to build both  shared
+       and  static  libraries by default. You can suppress an unwanted library
        by adding one of
 
          --disable-shared
          --disable-static
 
-       to the configure command.
+       to the configure command. Setting --disable-shared ensures  that  PCRE2
+       libraries  are  built  as  static libraries. The binaries that are then
+       created as part of  the  build  process  (for  example,  pcre2test  and
+       pcre2grep)  are linked statically with one or more PCRE2 libraries, but
+       may also be dynamically linked with other libraries such  as  libc.  If
+       you  want these binaries to be fully statically linked, you can set LD-
+       FLAGS like this:
+
+       LDFLAGS=--static ./configure --disable-shared
+
+       Note the two hyphens in --static. Of course, this works only if  static
+       versions of all the relevant libraries are available for linking.
 
 
 UNICODE AND UTF SUPPORT
@@ -3963,8 +4133,8 @@ UNICODE AND UTF SUPPORT
 
        Of itself, Unicode support does not make PCRE2 treat strings as  UTF-8,
        UTF-16 or UTF-32. To do that, applications that use the library can set
-       the PCRE2_UTF option when they call pcre2_compile() to compile  a  pat-
-       tern.   Alternatively,  patterns  may be started with (*UTF) unless the
+       the  PCRE2_UTF  option when they call pcre2_compile() to compile a pat-
+       tern.  Alternatively, patterns may be started with  (*UTF)  unless  the
        application has locked this out by setting PCRE2_NEVER_UTF.
 
        UTF support allows the libraries to process character code points up to
@@ -3975,8 +4145,8 @@ UNICODE AND UTF SUPPORT
        Details are given in the pcre2pattern documentation.
 
        Pattern escapes such as \d and \w do not by default make use of Unicode
-       properties. The application can request that they  do  by  setting  the
-       PCRE2_UCP  option.  Unless  the  application has set PCRE2_NEVER_UCP, a
+       properties.  The  application  can  request that they do by setting the
+       PCRE2_UCP option. Unless the application  has  set  PCRE2_NEVER_UCP,  a
        pattern may also request this by starting with (*UCP).
 
 
@@ -4014,8 +4184,8 @@ JUST-IN-TIME COMPILER SUPPORT
          --enable-jit-sealloc
 
        which enables the use of an execmem allocator in JIT that is compatible
-       with  SELinux.  This  has  no  effect  if  JIT  is not enabled. See the
-       pcre2jit documentation for a discussion of JIT usage. When JIT  support
+       with SELinux. This has no  effect  if  JIT  is  not  enabled.  See  the
+       pcre2jit  documentation for a discussion of JIT usage. When JIT support
        is enabled, pcre2grep automatically makes use of it, unless you add
 
          --disable-pcre2grep-jit
@@ -4025,14 +4195,14 @@ JUST-IN-TIME COMPILER SUPPORT
 
 NEWLINE RECOGNITION
 
-       By  default, PCRE2 interprets the linefeed (LF) character as indicating
-       the end of a line. This is the normal newline  character  on  Unix-like
-       systems.  You can compile PCRE2 to use carriage return (CR) instead, by
+       By default, PCRE2 interprets the linefeed (LF) character as  indicating
+       the  end  of  a line. This is the normal newline character on Unix-like
+       systems. You can compile PCRE2 to use carriage return (CR) instead,  by
        adding
 
          --enable-newline-is-cr
 
-       to the configure command. There is also an  --enable-newline-is-lf  op-
+       to  the  configure command. There is also an --enable-newline-is-lf op-
        tion, which explicitly specifies linefeed as the newline character.
 
        Alternatively, you can specify that line endings are to be indicated by
@@ -4045,20 +4215,20 @@ NEWLINE RECOGNITION
 
          --enable-newline-is-anycrlf
 
-       which  causes  PCRE2 to recognize any of the three sequences CR, LF, or
+       which causes PCRE2 to recognize any of the three sequences CR,  LF,  or
        CRLF as indicating a line ending. A fifth option, specified by
 
          --enable-newline-is-any
 
-       causes PCRE2 to recognize any Unicode  newline  sequence.  The  Unicode
+       causes  PCRE2  to  recognize  any Unicode newline sequence. The Unicode
        newline sequences are the three just mentioned, plus the single charac-
        ters VT (vertical tab, U+000B), FF (form feed, U+000C), NEL (next line,
-       U+0085),  LS  (line  separator,  U+2028),  and PS (paragraph separator,
+       U+0085), LS (line separator,  U+2028),  and  PS  (paragraph  separator,
        U+2029). The final option is
 
          --enable-newline-is-nul
 
-       which causes NUL (binary zero) to be set  as  the  default  line-ending
+       which  causes  NUL  (binary  zero) to be set as the default line-ending
        character.
 
        Whatever default line ending convention is selected when PCRE2 is built
@@ -4086,7 +4256,7 @@ HANDLING VERY LARGE PATTERNS
        nation  metacharacter).  By default, in the 8-bit and 16-bit libraries,
        two-byte values are used for these offsets, leading to a  maximum  size
        for a compiled pattern of around 64 thousand code units. This is suffi-
-       cient to handle all but the most gigantic patterns. Nevertheless,  some
+       cient  to handle all but the most gigantic patterns. Nevertheless, some
        people do want to process truly enormous patterns, so it is possible to
        compile PCRE2 to use three-byte or four-byte offsets by adding  a  set-
        ting such as
@@ -4104,8 +4274,8 @@ HANDLING VERY LARGE PATTERNS
 LIMITING PCRE2 RESOURCE USAGE
 
        The pcre2_match() function increments a counter each time it goes round
-       its  main  loop. Putting a limit on this counter controls the amount of
-       computing resource used by a single call to  pcre2_match().  The  limit
+       its main loop. Putting a limit on this counter controls the  amount  of
+       computing  resource  used  by a single call to pcre2_match(). The limit
        can be changed at run time, as described in the pcre2api documentation.
        The default is 10 million, but this can be changed by adding a  setting
        such as
@@ -4128,11 +4298,11 @@ LIMITING PCRE2 RESOURCE USAGE
 
        which  limits the amount of heap to 500 KiB. This limit applies only to
        interpretive matching in pcre2_match() and pcre2_dfa_match(), which may
-       also  use  the  heap for internal workspace when processing complicated
-       patterns. This limit does not apply when JIT (which has its own  memory
+       also use the heap for internal workspace  when  processing  complicated
+       patterns.  This limit does not apply when JIT (which has its own memory
        arrangements) is used.
 
-       You  can  also explicitly limit the depth of nested backtracking in the
+       You can also explicitly limit the depth of nested backtracking  in  the
        pcre2_match() interpreter. This limit defaults to the value that is set
        for  --with-match-limit.  You  can set a lower default limit by adding,
        for example,
@@ -4153,25 +4323,41 @@ LIMITING PCRE2 RESOURCE USAGE
        terns.  The limit does not apply to JIT matching.
 
 
+LIMITING VARIABLE-LENGTH LOOKBEHIND ASSERTIONS
+
+       Lookbehind  assertions  in which one or more branches can match a vari-
+       able number of characters are supported only  if  there  is  a  maximum
+       matching  length  for  each  top-level branch. There is a limit to this
+       maximum that defaults to 255 characters. You can alter this default  by
+       a setting such as
+
+         --with-max-varlookbehind=100
+
+       The limit can be changed at runtime by calling pcre2_set_max_varlookbe-
+       hind().  Lookbehind  assertions  in  which every branch matches a fixed
+       number of characters (not necessarily all the same) are not constrained
+       by this limit.
+
+
 CREATING CHARACTER TABLES AT BUILD TIME
 
        PCRE2 uses fixed tables for processing characters whose code points are
        less than 256. By default, PCRE2 is built with a set of tables that are
-       distributed  in  the file src/pcre2_chartables.c.dist. These tables are
+       distributed in the file src/pcre2_chartables.c.dist. These  tables  are
        for ASCII codes only. If you add
 
          --enable-rebuild-chartables
 
-       to the configure command, the distributed tables are  no  longer  used.
+       to  the  configure  command, the distributed tables are no longer used.
        Instead, a program called pcre2_dftables is compiled and run. This out-
        puts the source for new set of tables, created in the default locale of
-       your  C  run-time  system. This method of replacing the tables does not
+       your C run-time system. This method of replacing the  tables  does  not
        work if you are cross compiling, because pcre2_dftables needs to be run
        on the local host and therefore not compiled with the cross compiler.
 
        If you need to create alternative tables when cross compiling, you will
-       have to do so "by hand". There may also be other reasons  for  creating
-       tables  manually.   To  cause  pcre2_dftables  to be built on the local
+       have  to  do so "by hand". There may also be other reasons for creating
+       tables manually.  To cause pcre2_dftables to  be  built  on  the  local
        host, run a normal compiling command, and then run the program with the
        output file as its argument, for example:
 
@@ -4184,8 +4370,8 @@ CREATING CHARACTER TABLES AT BUILD TIME
          LC_ALL=fr_FR ./pcre2_dftables -L src/pcre2_chartables.c
 
        You can also specify -b (with or without -L). This causes the tables to
-       be  written in binary instead of as source code. A set of binary tables
-       can be loaded into memory by an application and  passed  to  pcre2_com-
+       be written in binary instead of as source code. A set of binary  tables
+       can  be  loaded  into memory by an application and passed to pcre2_com-
        pile() in the same way as tables created by calling pcre2_maketables().
        The tables are just a string of bytes, independent of hardware  charac-
        teristics  such  as  endianness. This means they can be bundled with an
@@ -4211,7 +4397,7 @@ USING EBCDIC CODE
        ebcdic are mutually exclusive.
 
        The EBCDIC character that corresponds to an ASCII LF is assumed to have
-       the  value  0x15 by default. However, in some EBCDIC environments, 0x25
+       the value 0x15 by default. However, in some EBCDIC  environments,  0x25
        is used. In such an environment you should use
 
          --enable-ebcdic-nl25
@@ -4231,17 +4417,17 @@ PCRE2GREP SUPPORT FOR EXTERNAL SCRIPTS
        By default pcre2grep supports the use of callouts with string arguments
        within the patterns it is matching. There are two kinds: one that  gen-
        erates output using local code, and another that calls an external pro-
-       gram or script.  If --disable-pcre2grep-callout-fork is  added  to  the
-       configure  command,  only  the  first  kind of callout is supported; if
-       --disable-pcre2grep-callout is used, all callouts  are  completely  ig-
-       nored.  For more details of pcre2grep callouts, see the pcre2grep docu-
+       gram  or  script.   If --disable-pcre2grep-callout-fork is added to the
+       configure command, only the first kind  of  callout  is  supported;  if
+       --disable-pcre2grep-callout  is  used,  all callouts are completely ig-
+       nored. For more details of pcre2grep callouts, see the pcre2grep  docu-
        mentation.
 
 
 PCRE2GREP OPTIONS FOR COMPRESSED FILE SUPPORT
 
-       By default, pcre2grep reads all files as plain text. You can  build  it
-       so  that  it recognizes files whose names end in .gz or .bz2, and reads
+       By  default,  pcre2grep reads all files as plain text. You can build it
+       so that it recognizes files whose names end in .gz or .bz2,  and  reads
        them with libz or libbz2, respectively, by adding one or both of
 
          --enable-pcre2grep-libz
@@ -4288,9 +4474,9 @@ PCRE2TEST OPTION FOR LIBREADLINE SUPPORT
        licensing issues. These can be avoided by linking instead with libedit,
        which has a BSD licence.
 
-       Setting  --enable-pcre2test-libreadline causes the -lreadline option to
-       be added to the pcre2test build. In many operating environments with  a
-       sytem-installed  readline  library this is sufficient. However, in some
+       Setting --enable-pcre2test-libreadline causes the -lreadline option  to
+       be  added to the pcre2test build. In many operating environments with a
+       system-installed readline library this is sufficient. However, in  some
        environments (e.g. if an unmodified distribution version of readline is
        in  use),  some  extra configuration may be necessary. The INSTALL file
        for libreadline says this:
@@ -4389,21 +4575,21 @@ DISABLING THE Z AND T FORMATTING MODIFIERS
        The  C99  standard  defines formatting modifiers z and t for size_t and
        ptrdiff_t values, respectively. By default, PCRE2 uses these  modifiers
        in environments other than old versions of Microsoft Visual Studio when
-       __STDC_VERSION__ is defined and has a value greater than  or  equal  to
-       199901L  (indicating  support for C99).  However, there is at least one
+       __STDC_VERSION__  is  defined  and has a value greater than or equal to
+       199901L (indicating support for C99).  However, there is at  least  one
        environment that claims to be C99 but does not support these modifiers.
        If
 
          --disable-percent-zt
 
        is specified, no use is made of the z or t modifiers. Instead of %td or
-       %zu, a suitable format is used depending in the size of  long  for  the
+       %zu,  a  suitable  format is used depending in the size of long for the
        platform.
 
 
 SUPPORT FOR FUZZERS
 
-       There  is  a  special  option for use by people who want to run fuzzing
+       There is a special option for use by people who  want  to  run  fuzzing
        tests on PCRE2:
 
          --enable-fuzz-support
@@ -4420,22 +4606,22 @@ SUPPORT FOR FUZZERS
        Setting  --enable-fuzz-support  also  causes  a binary called pcre2fuz-
        zcheck to be created. This is normally run under valgrind or used  when
        PCRE2 is compiled with address sanitizing enabled. It calls the fuzzing
-       function and outputs information about what  it  is  doing.  The  input
-       strings  are specified by arguments: if an argument starts with "=" the
-       rest of it is a literal input string. Otherwise, it is assumed to be  a
+       function  and  outputs  information  about  what it is doing. The input
+       strings are specified by arguments: if an argument starts with "="  the
+       rest  of it is a literal input string. Otherwise, it is assumed to be a
        file name, and the contents of the file are the test string.
 
 
 OBSOLETE OPTION
 
-       In  versions  of  PCRE2 prior to 10.30, there were two ways of handling
-       backtracking in the pcre2_match() function. The default was to use  the
+       In versions of PCRE2 prior to 10.30, there were two  ways  of  handling
+       backtracking  in the pcre2_match() function. The default was to use the
        system stack, but if
 
          --disable-stack-for-recursion
 
-       was  set,  memory on the heap was used. From release 10.30 onwards this
-       has changed (the stack is no longer used)  and  this  option  now  does
+       was set, memory on the heap was used. From release 10.30  onwards  this
+       has  changed  (the  stack  is  no longer used) and this option now does
        nothing except give a warning.
 
 
@@ -4453,18 +4639,22 @@ AUTHOR
 
 REVISION
 
-       Last updated: 27 July 2022
-       Copyright (c) 1997-2022 University of Cambridge.
+       Last updated: 15 April 2024
+       Copyright (c) 1997-2024 University of Cambridge.
+
+
+PCRE2 10.44                      15 April 2024                   PCRE2BUILD(3)
 ------------------------------------------------------------------------------
 
 
-PCRE2CALLOUT(3)            Library Functions Manual            PCRE2CALLOUT(3)
 
+PCRE2CALLOUT(3)            Library Functions Manual            PCRE2CALLOUT(3)
 
 
 NAME
        PCRE2 - Perl-compatible regular expressions (revised API)
 
+
 SYNOPSIS
 
        #include 
@@ -4478,11 +4668,11 @@ SYNOPSIS
 
 DESCRIPTION
 
-       PCRE2  provides  a feature called "callout", which is a means of tempo-
-       rarily passing control to the caller of PCRE2 in the middle of  pattern
-       matching.  The caller of PCRE2 provides an external function by putting
-       its entry point in a match  context  (see  pcre2_set_callout()  in  the
-       pcre2api documentation).
+       PCRE2  provides  a  feature  called "callout", which is a means of tem-
+       porarily passing control to the caller of PCRE2 in the middle  of  pat-
+       tern  matching.  The  caller  of PCRE2 provides an external function by
+       putting its entry point in a match context (see pcre2_set_callout()  in
+       the pcre2api documentation).
 
        When  using the pcre2_substitute() function, an additional callout fea-
        ture is available. This does a callout after each change to the subject
@@ -4495,8 +4685,8 @@ DESCRIPTION
        default  value is zero.  Alternatively, the argument may be a delimited
        string. The starting delimiter must be one of ` ' " ^ % # $ {  and  the
        ending delimiter is the same as the start, except for {, where the end-
-       ing delimiter is }. If  the  ending  delimiter  is  needed  within  the
-       string,  it  must be doubled. For example, this pattern has two callout
+       ing  delimiter  is  }.  If  the  ending  delimiter is needed within the
+       string, it must be doubled. For example, this pattern has  two  callout
        points:
 
          (?C1)abc(?C"some ""arbitrary"" text")def
@@ -4522,16 +4712,16 @@ DESCRIPTION
 
        Notice  that  there  is a callout before and after each parenthesis and
        alternation bar. If the pattern contains a conditional group whose con-
-       dition  is  an  assertion, an automatic callout is inserted immediately
-       before the condition. Such a callout may also be  inserted  explicitly,
+       dition is an assertion, an automatic callout  is  inserted  immediately
+       before  the  condition. Such a callout may also be inserted explicitly,
        for example:
 
          (?(?C9)(?=a)ab|de)  (?(?C%text%)(?!=d)ab|de)
 
-       This  applies only to assertion conditions (because they are themselves
+       This applies only to assertion conditions (because they are  themselves
        independent groups).
 
-       Callouts can be useful for tracking the progress of  pattern  matching.
+       Callouts  can  be useful for tracking the progress of pattern matching.
        The pcre2test program has a pattern qualifier (/auto_callout) that sets
        automatic callouts.  When any callouts are  present,  the  output  from
        pcre2test  indicates  how  the pattern is being matched. This is useful
@@ -4558,7 +4748,7 @@ MISSING CALLOUTS
           +2 ^   ^    [bc]
          No match
 
-       This  indicates that when matching [bc] fails, there is no backtracking
+       This indicates that when matching [bc] fails, there is no  backtracking
        into a+ (because it is being treated as a++) and therefore the callouts
        that  would  be  taken for the backtracks do not occur. You can disable
        the  auto-possessify  feature  by  passing   PCRE2_NO_AUTO_POSSESS   to
@@ -4583,15 +4773,15 @@ MISSING CALLOUTS
        any  character,  the pattern is automatically anchored. If PCRE2_DOTALL
        is not set, a match can start only after an internal newline or at  the
        beginning of the subject, and pcre2_compile() remembers this. If a pat-
-       tern has more than one top-level branch, automatic anchoring occurs  if
+       tern  has more than one top-level branch, automatic anchoring occurs if
        all branches are anchorable.
 
-       This  optimization is disabled, however, if .* is in an atomic group or
-       if there is a backreference to the capture group in which  it  appears.
-       It  is  also disabled if the pattern contains (*PRUNE) or (*SKIP). How-
+       This optimization is disabled, however, if .* is in an atomic group  or
+       if  there  is a backreference to the capture group in which it appears.
+       It is also disabled if the pattern contains (*PRUNE) or  (*SKIP).  How-
        ever, the presence of callouts does not affect it.
 
-       For example, if the pattern .*\d is  compiled  with  PCRE2_AUTO_CALLOUT
+       For  example,  if  the pattern .*\d is compiled with PCRE2_AUTO_CALLOUT
        and applied to the string "aa", the pcre2test output is:
 
          --->aa
@@ -4601,7 +4791,7 @@ MISSING CALLOUTS
           +2 ^      \d
          No match
 
-       This  shows  that all match attempts start at the beginning of the sub-
+       This shows that all match attempts start at the beginning of  the  sub-
        ject. In other words, the pattern is anchored. You can disable this op-
        timization  by  passing  PCRE2_NO_DOTSTAR_ANCHOR to pcre2_compile(), or
        starting the pattern with (*NO_DOTSTAR_ANCHOR). In this case, the  out-
@@ -4639,20 +4829,20 @@ MISSING CALLOUTS
        patterns, if it has been scanned far enough.
 
        You can disable these optimizations by passing the PCRE2_NO_START_OPTI-
-       MIZE  option  to  pcre2_compile(),  or  by  starting  the  pattern with
-       (*NO_START_OPT). This slows down the matching process, but does  ensure
+       MIZE option  to  pcre2_compile(),  or  by  starting  the  pattern  with
+       (*NO_START_OPT).  This slows down the matching process, but does ensure
        that callouts such as the example above are obeyed.
 
 
 THE CALLOUT INTERFACE
 
-       During  matching,  when  PCRE2  reaches a callout point, if an external
-       function is provided in the match context, it is called.  This  applies
-       to  both normal, DFA, and JIT matching. The first argument to the call-
+       During matching, when PCRE2 reaches a callout  point,  if  an  external
+       function  is  provided in the match context, it is called. This applies
+       to both normal, DFA, and JIT matching. The first argument to the  call-
        out function is a pointer to a pcre2_callout block. The second argument
        is  the  void * callout data that was supplied when the callout was set
        up by calling pcre2_set_callout() (see the pcre2api documentation). The
-       callout  block structure contains the following fields, not necessarily
+       callout block structure contains the following fields, not  necessarily
        in this order:
 
          uint32_t      version;
@@ -4672,25 +4862,25 @@ THE CALLOUT INTERFACE
          PCRE2_SIZE    callout_string_length;
          PCRE2_SPTR    callout_string;
 
-       The version field contains the version number of the block format.  The
-       current  version  is  2; the three callout string fields were added for
-       version 1, and the callout_flags field for version 2. If you are  writ-
-       ing  an  application  that  might  use an earlier release of PCRE2, you
-       should check the version number before accessing any of  these  fields.
-       The  version  number  will increase in future if more fields are added,
+       The  version field contains the version number of the block format. The
+       current version is 2; the three callout string fields  were  added  for
+       version  1, and the callout_flags field for version 2. If you are writ-
+       ing an application that might use an  earlier  release  of  PCRE2,  you
+       should  check  the version number before accessing any of these fields.
+       The version number will increase in future if more  fields  are  added,
        but the intention is never to remove any of the existing fields.
 
    Fields for numerical callouts
 
-       For a numerical callout, callout_string  is  NULL,  and  callout_number
-       contains  the  number  of  the callout, in the range 0-255. This is the
-       number that follows (?C for callouts that part of the  pattern;  it  is
+       For  a  numerical  callout,  callout_string is NULL, and callout_number
+       contains the number of the callout, in the range  0-255.  This  is  the
+       number  that  follows  (?C for callouts that part of the pattern; it is
        255 for automatically generated callouts.
 
    Fields for string callouts
 
-       For  callouts with string arguments, callout_number is always zero, and
-       callout_string points to the string that is contained within  the  com-
+       For callouts with string arguments, callout_number is always zero,  and
+       callout_string  points  to the string that is contained within the com-
        piled pattern. Its length is given by callout_string_length. Duplicated
        ending delimiters that were present in the original pattern string have
        been turned into single characters, but there is no other processing of
@@ -4714,10 +4904,10 @@ THE CALLOUT INTERFACE
        (the "ovector"). You may read the elements in this vector, but you must
        not change any of them.
 
-       For calls to pcre2_match(), the offset_vector field is not  (since  re-
-       lease  10.30)  a  pointer  to the actual ovector that was passed to the
-       matching function in the match data block. Instead it points to an  in-
-       ternal  ovector  of  a  size large enough to hold all possible captured
+       For  calls  to pcre2_match(), the offset_vector field is not (since re-
+       lease 10.30) a pointer to the actual ovector that  was  passed  to  the
+       matching  function in the match data block. Instead it points to an in-
+       ternal ovector of a size large enough to  hold  all  possible  captured
        substrings in the pattern. Note that whenever a recursion or subroutine
        call  within  a pattern completes, the capturing state is reset to what
        it was before.
@@ -4741,9 +4931,9 @@ THE CALLOUT INTERFACE
        For DFA matching, the offset_vector field points to  the  ovector  that
        was  passed  to the matching function in the match data block for call-
        outs at the top level, but to an internal ovector during the processing
-       of  pattern  recursions, lookarounds, and atomic groups. However, these
-       ovectors hold no useful information because pcre2_dfa_match() does  not
-       support  substring  capturing. The value of capture_top is always 1 and
+       of pattern recursions, lookarounds, and atomic groups.  However,  these
+       ovectors  hold no useful information because pcre2_dfa_match() does not
+       support substring capturing. The value of capture_top is always  1  and
        the value of capture_last is always 0 for DFA matching.
 
        The subject and subject_length fields contain copies of the values that
@@ -4756,7 +4946,7 @@ THE CALLOUT INTERFACE
        function may be called several times from the same point in the pattern
        for different starting points in the subject.
 
-       The current_position field contains the offset within  the  subject  of
+       The  current_position  field  contains the offset within the subject of
        the current match pointer.
 
        The pattern_position field contains the offset in the pattern string to
@@ -4766,24 +4956,24 @@ THE CALLOUT INTERFACE
        processed  in the pattern string. When the callout is at the end of the
        pattern, the length is zero.  When  the  callout  precedes  an  opening
        parenthesis, the length includes meta characters that follow the paren-
-       thesis. For example, in a callout before an assertion  such  as  (?=ab)
-       the  length  is  3. For an an alternation bar or a closing parenthesis,
-       the length is one, unless a closing parenthesis is followed by a  quan-
-       tifier, in which case its length is included.  (This changed in release
-       10.23. In earlier releases, before an opening  parenthesis  the  length
-       was  that of the entire group, and before an alternation bar or a clos-
+       thesis.  For  example,  in a callout before an assertion such as (?=ab)
+       the length is 3. For an alternation bar or a closing  parenthesis,  the
+       length  is  one,  unless a closing parenthesis is followed by a quanti-
+       fier, in which case its length is included. (This  changed  in  release
+       10.23.  In  earlier  releases, before an opening parenthesis the length
+       was that of the entire group, and before an alternation bar or a  clos-
        ing parenthesis the length was zero.)
 
-       The pattern_position and next_item_length fields are intended  to  help
-       in  distinguishing between different automatic callouts, which all have
-       the same callout number. However, they are set for  all  callouts,  and
+       The  pattern_position  and next_item_length fields are intended to help
+       in distinguishing between different automatic callouts, which all  have
+       the  same  callout  number. However, they are set for all callouts, and
        are used by pcre2test to show the next item to be matched when display-
        ing callout information.
 
        In callouts from pcre2_match() the mark field contains a pointer to the
-       zero-terminated  name of the most recently passed (*MARK), (*PRUNE), or
-       (*THEN) item in the match, or NULL if no such items have  been  passed.
-       Instances  of  (*PRUNE)  or  (*THEN) without a name do not obliterate a
+       zero-terminated name of the most recently passed (*MARK), (*PRUNE),  or
+       (*THEN)  item  in the match, or NULL if no such items have been passed.
+       Instances of (*PRUNE) or (*THEN) without a name  do  not  obliterate  a
        previous (*MARK). In callouts from the DFA matching function this field
        always contains NULL.
 
@@ -4793,18 +4983,18 @@ THE CALLOUT INTERFACE
 
          PCRE2_CALLOUT_STARTMATCH
 
-       This  is set for the first callout after the start of matching for each
+       This is set for the first callout after the start of matching for  each
        new starting position in the subject.
 
          PCRE2_CALLOUT_BACKTRACK
 
-       This is set if there has been a matching backtrack since  the  previous
-       callout,  or  since  the start of matching if this is the first callout
+       This  is  set if there has been a matching backtrack since the previous
+       callout, or since the start of matching if this is  the  first  callout
        from a pcre2_match() run.
 
-       Both bits are set when a backtrack has caused a "bumpalong"  to  a  new
-       starting  position in the subject. Output from pcre2test does not indi-
-       cate the presence of these bits unless the  callout_extra  modifier  is
+       Both  bits  are  set when a backtrack has caused a "bumpalong" to a new
+       starting position in the subject. Output from pcre2test does not  indi-
+       cate  the  presence  of these bits unless the callout_extra modifier is
        set.
 
        The information in the callout_flags field is provided so that applica-
@@ -4838,14 +5028,14 @@ CALLOUT ENUMERATION
          void *user_data);
 
        A script language that supports the use of string arguments in callouts
-       might like to scan all the callouts in a  pattern  before  running  the
+       might  like  to  scan  all the callouts in a pattern before running the
        match. This can be done by calling pcre2_callout_enumerate(). The first
        argument is a pointer to a compiled pattern, the  second  points  to  a
        callback  function,  and the third is arbitrary user data. The callback
        function is called for every callout in the pattern  in  the  order  in
        which they appear. Its first argument is a pointer to a callout enumer-
-       ation block, and its second argument is the user_data  value  that  was
-       passed  to  pcre2_callout_enumerate(). The data block contains the fol-
+       ation  block,  and  its second argument is the user_data value that was
+       passed to pcre2_callout_enumerate(). The data block contains  the  fol-
        lowing fields:
 
          version                Block version number
@@ -4856,13 +5046,13 @@ CALLOUT ENUMERATION
          callout_string_length  Length of callout string
          callout_string         Points to callout string or is NULL
 
-       The version number is currently 0. It will increase if new  fields  are
-       ever  added  to  the  block. The remaining fields are the same as their
-       namesakes in the pcre2_callout block that is used for  callouts  during
+       The  version  number is currently 0. It will increase if new fields are
+       ever added to the block. The remaining fields are  the  same  as  their
+       namesakes  in  the pcre2_callout block that is used for callouts during
        matching, as described above.
 
-       Note  that  the  value  of pattern_position is unique for each callout.
-       However, if a callout occurs inside a group that is quantified  with  a
+       Note that the value of pattern_position is  unique  for  each  callout.
+       However,  if  a callout occurs inside a group that is quantified with a
        non-zero minimum or a fixed maximum, the group is replicated inside the
        compiled pattern. For example, a pattern such as /(a){2}/  is  compiled
        as  if it were /(a)(a)/. This means that the callout will be enumerated
@@ -4877,32 +5067,37 @@ CALLOUT ENUMERATION
 AUTHOR
 
        Philip Hazel
-       University Computing Service
+       Retired from University Computing Service
        Cambridge, England.
 
 
 REVISION
 
-       Last updated: 03 February 2019
-       Copyright (c) 1997-2019 University of Cambridge.
+       Last updated: 19 January 2024
+       Copyright (c) 1997-2024 University of Cambridge.
+
+
+PCRE2 10.43                     19 January 2024                PCRE2CALLOUT(3)
 ------------------------------------------------------------------------------
 
 
-PCRE2COMPAT(3)             Library Functions Manual             PCRE2COMPAT(3)
 
+PCRE2COMPAT(3)             Library Functions Manual             PCRE2COMPAT(3)
 
 
 NAME
        PCRE2 - Perl-compatible regular expressions (revised API)
 
+
 DIFFERENCES BETWEEN PCRE2 AND PERL
 
-       This  document describes some of the differences in the ways that PCRE2
-       and Perl handle regular expressions. The differences described here are
-       with  respect  to  Perl  version 5.34.0, but as both Perl and PCRE2 are
-       continually changing, the information may at times be out of date.
+       This  document describes some of the known differences in the ways that
+       PCRE2 and Perl handle regular expressions.  The  differences  described
+       here  are  with  respect  to  Perl version 5.38.0, but as both Perl and
+       PCRE2 are continually changing, the information may at times be out  of
+       date.
 
-       1. When PCRE2_DOTALL (equivalent to Perl's /s qualifier)  is  not  set,
+       1.  When  PCRE2_DOTALL  (equivalent to Perl's /s qualifier) is not set,
        the behaviour of the '.' metacharacter differs from Perl. In PCRE2, '.'
        matches the next character unless it is the  start  of  a  newline  se-
        quence.  This  means  that, if the newline setting is CR, CRLF, or NUL,
@@ -4919,37 +5114,41 @@ DIFFERENCES BETWEEN PCRE2 AND PERL
        serts that the next character is not "a"  three  times  (in  principle;
        PCRE2  optimizes this to run the assertion just once). Perl allows some
        repeat quantifiers on other assertions, for example, \b* , but these do
-       not  seem  to have any use. PCRE2 does not allow any kind of quantifier
+       not seem to have any use. PCRE2 does not allow any kind  of  quantifier
        on non-lookaround assertions.
 
-       4. Capture groups that occur inside negative lookaround assertions  are
-       counted,  but  their  entries in the offsets vector are set only when a
-       negative assertion is a condition that has a matching branch (that  is,
-       the  condition  is  false).   Perl may set such capture groups in other
+       4.  If a braced quantifier such as {1,2} appears where there is nothing
+       to repeat (for example, at the start of a branch), PCRE2 raises an  er-
+       ror whereas Perl treats the quantifier characters as literal.
+
+       5.  Capture groups that occur inside negative lookaround assertions are
+       counted, but their entries in the offsets vector are set  only  when  a
+       negative  assertion is a condition that has a matching branch (that is,
+       the condition is false).  Perl may set such  capture  groups  in  other
        circumstances.
 
-       5. The following Perl escape sequences are not supported: \F,  \l,  \L,
+       6.  The  following Perl escape sequences are not supported: \F, \l, \L,
        \u, \U, and \N when followed by a character name. \N on its own, match-
        ing a non-newline character, and \N{U+dd..}, matching  a  Unicode  code
        point,  are  supported.  The  escapes that modify the case of following
        letters are implemented by Perl's general string-handling and  are  not
        part of its pattern matching engine. If any of these are encountered by
-       PCRE2, an error is generated by default.  However,  if  either  of  the
-       PCRE2_ALT_BSUX  or  PCRE2_EXTRA_ALT_BSUX  options is set, \U and \u are
+       PCRE2,  an  error  is  generated  by default. However, if either of the
+       PCRE2_ALT_BSUX or PCRE2_EXTRA_ALT_BSUX options is set, \U  and  \u  are
        interpreted as ECMAScript interprets them.
 
-       6. The Perl escape sequences \p, \P, and \X are supported only if PCRE2
+       7. The Perl escape sequences \p, \P, and \X are supported only if PCRE2
        is built with Unicode support (the default). The properties that can be
-       tested with \p and \P are limited to the  general  category  properties
-       such  as  Lu  and  Nd,  script  names such as Greek or Han, Bidi_Class,
-       Bidi_Control, and the derived properties Any and LC (synonym L&).  Both
-       PCRE2  and  Perl  support the Cs (surrogate) property, but in PCRE2 its
-       use is limited. See the pcre2pattern  documentation  for  details.  The
-       long  synonyms  for  property names that Perl supports (such as \p{Let-
-       ter}) are not supported by PCRE2, nor is it permitted to prefix any  of
-       these properties with "Is".
-
-       7. PCRE2 supports the \Q...\E escape for quoting substrings. Characters
+       tested  with  \p  and \P are limited to the general category properties
+       such as Lu and Nd, the derived properties  Any  and  LC  (synonym  L&),
+       script  names such as Greek or Han, Bidi_Class, Bidi_Control, and a few
+       binary properties. Both PCRE2 and Perl support the Cs (surrogate) prop-
+       erty, but in PCRE2 its use is limited. See the pcre2pattern  documenta-
+       tion  for  details. The long synonyms for property names that Perl sup-
+       ports (such as \p{Letter}) are not supported by PCRE2, nor is  it  per-
+       mitted to prefix any of these properties with "Is".
+
+       8. PCRE2 supports the \Q...\E escape for quoting substrings. Characters
        in between are treated as literals. However, this is slightly different
        from  Perl  in  that  $  and  @ are also handled as literals inside the
        quotes. In Perl, they cause variable interpolation (PCRE2 does not have
@@ -4970,124 +5169,115 @@ DIFFERENCES BETWEEN PCRE2 AND PERL
        The \Q...\E sequence is recognized both inside  and  outside  character
        classes by both PCRE2 and Perl.
 
-       8.   Fairly  obviously,  PCRE2  does  not  support  the  (?{code})  and
+       9.   Fairly  obviously,  PCRE2  does  not  support  the  (?{code})  and
        (??{code}) constructions. However, PCRE2 does have a "callout" feature,
        which allows an external function to be called during pattern matching.
        See the pcre2callout documentation for details.
 
-       9. Subroutine calls (whether recursive or not) were treated  as  atomic
+       10. Subroutine calls (whether recursive or not) were treated as  atomic
        groups  up to PCRE2 release 10.23, but from release 10.30 this changed,
        and backtracking into subroutine calls is now supported, as in Perl.
 
-       10. In PCRE2, if any of the backtracking control verbs are  used  in  a
+       11. In PCRE2, if any of the backtracking control verbs are  used  in  a
        group  that  is  called  as  a subroutine (whether or not recursively),
        their effect is confined to that group; it does not extend to the  sur-
        rounding  pattern.  This is not always the case in Perl. In particular,
        if (*THEN) is present in a group that is called as  a  subroutine,  its
        action is limited to that group, even if the group does not contain any
-       | characters. Note that such groups are processed as  anchored  at  the
+       |  characters.  Note  that such groups are processed as anchored at the
        point where they are tested.
 
-       11.  If a pattern contains more than one backtracking control verb, the
-       first one that is backtracked onto acts. For example,  in  the  pattern
-       A(*COMMIT)B(*PRUNE)C  a  failure in B triggers (*COMMIT), but a failure
+       12. If a pattern contains more than one backtracking control verb,  the
+       first  one  that  is backtracked onto acts. For example, in the pattern
+       A(*COMMIT)B(*PRUNE)C a failure in B triggers (*COMMIT), but  a  failure
        in C triggers (*PRUNE). Perl's behaviour is more complex; in many cases
        it is the same as PCRE2, but there are cases where it differs.
 
-       12.  There are some differences that are concerned with the settings of
+       13.  There are some differences that are concerned with the settings of
        captured strings when part of  a  pattern  is  repeated.  For  example,
        matching  "aba"  against the pattern /^(a(b)?)+$/ in Perl leaves $2 un-
        set, but in PCRE2 it is set to "b".
 
-       13. PCRE2's handling of duplicate capture group numbers  and  names  is
+       14. PCRE2's handling of duplicate capture group numbers  and  names  is
        not  as  general as Perl's. This is a consequence of the fact the PCRE2
        works internally just with numbers, using an external table  to  trans-
        late  between  numbers  and  names.  In  particular,  a pattern such as
        (?|(?A)|(?B)), where the two capture groups have the same  number
        but  different  names, is not supported, and causes an error at compile
        time. If it were allowed, it would not be possible to distinguish which
-       group  matched,  because  both  names map to capture group number 1. To
+       group matched, because both names map to capture  group  number  1.  To
        avoid this confusing situation, an error is given at compile time.
 
-       14. Perl used to recognize comments in some places that PCRE2 does not,
+       15. Perl used to recognize comments in some places that PCRE2 does not,
        for  example,  between  the  ( and ? at the start of a group. If the /x
        modifier is set, Perl allowed white space between ( and  ?  though  the
        latest  Perls give an error (for a while it was just deprecated). There
        may still be some cases where Perl behaves differently.
 
-       15. Perl, when in warning mode, gives warnings  for  character  classes
+       16. Perl, when in warning mode, gives warnings  for  character  classes
        such  as  [A-\d] or [a-[:digit:]]. It then treats the hyphens as liter-
        als. PCRE2 has no warning features, so it gives an error in these cases
        because they are almost certainly user mistakes.
 
-       16.  In  PCRE2, the upper/lower case character properties Lu and Ll are
-       not affected when case-independent matching is specified. For  example,
+       17. In PCRE2, the upper/lower case character properties Lu and  Ll  are
+       not  affected when case-independent matching is specified. For example,
        \p{Lu} always matches an upper case letter. I think Perl has changed in
-       this respect; in the release at the time of writing (5.34), \p{Lu}  and
+       this respect; in the release at the time of writing (5.38), \p{Lu}  and
        \p{Ll} match all letters, regardless of case, when case independence is
        specified.
 
-       17. From release 5.32.0, Perl locks out the use of \K in lookaround as-
+       18. From release 5.32.0, Perl locks out the use of \K in lookaround as-
        sertions.  From  release 10.38 PCRE2 does the same by default. However,
        there is an option for re-enabling the previous  behaviour.  When  this
        option  is  set,  \K is acted on when it occurs in positive assertions,
        but is ignored in negative assertions.
 
-       18. PCRE2 provides some extensions to the Perl regular  expression  fa-
+       19. PCRE2 provides some extensions to the Perl regular  expression  fa-
        cilities.   Perl  5.10  included  new features that were not in earlier
        versions of Perl, some of which (such as  named  parentheses)  were  in
-       PCRE2 for some time before. This list is with respect to Perl 5.34:
+       PCRE2 for some time before. This list is with respect to Perl 5.38:
 
-       (a)  Although  lookbehind  assertions  in PCRE2 must match fixed length
-       strings, each alternative toplevel branch of a lookbehind assertion can
-       match  a  different  length of string. Perl used to require them all to
-       have the same length, but the latest version has some  variable  length
-       support.
-
-       (b) From PCRE2 10.23, backreferences to groups of fixed length are sup-
-       ported in lookbehinds, provided that there is no possibility of  refer-
-       encing  a  non-unique  number or name. Perl does not support backrefer-
-       ences in lookbehinds.
-
-       (c) If PCRE2_DOLLAR_ENDONLY is set and PCRE2_MULTILINE is not set,  the
+       (a)  If PCRE2_DOLLAR_ENDONLY is set and PCRE2_MULTILINE is not set, the
        $ meta-character matches only at the very end of the string.
 
-       (d)  A  backslash  followed  by  a  letter  with  no special meaning is
+       (b) A backslash followed  by  a  letter  with  no  special  meaning  is
        faulted. (Perl can be made to issue a warning.)
 
-       (e) If PCRE2_UNGREEDY is set, the greediness of the repetition  quanti-
+       (c)  If PCRE2_UNGREEDY is set, the greediness of the repetition quanti-
        fiers is inverted, that is, by default they are not greedy, but if fol-
        lowed by a question mark they are.
 
-       (f) PCRE2_ANCHORED can be used at matching time to force a  pattern  to
+       (d) PCRE2_ANCHORED can be used at matching time to force a  pattern  to
        be tried only at the first matching position in the subject string.
 
-       (g)     The     PCRE2_NOTBOL,    PCRE2_NOTEOL,    PCRE2_NOTEMPTY    and
+       (e)     The     PCRE2_NOTBOL,    PCRE2_NOTEOL,    PCRE2_NOTEMPTY    and
        PCRE2_NOTEMPTY_ATSTART options have no Perl equivalents.
 
-       (h) The \R escape sequence can be restricted to match only CR,  LF,  or
+       (f) The \R escape sequence can be restricted to match only CR,  LF,  or
        CRLF by the PCRE2_BSR_ANYCRLF option.
 
-       (i)  The  callout  facility is PCRE2-specific. Perl supports codeblocks
+       (g)  The  callout  facility is PCRE2-specific. Perl supports codeblocks
        and variable interpolation, but not general hooks on every match.
 
-       (j) The partial matching facility is PCRE2-specific.
+       (h) The partial matching facility is PCRE2-specific.
 
-       (k) The alternative matching function (pcre2_dfa_match() matches  in  a
+       (i) The alternative matching function (pcre2_dfa_match() matches  in  a
        different way and is not Perl-compatible.
 
-       (l)  PCRE2 recognizes some special sequences such as (*CR) or (*NO_JIT)
+       (j)  PCRE2 recognizes some special sequences such as (*CR) or (*NO_JIT)
        at the start of a pattern. These set overall  options  that  cannot  be
        changed within the pattern.
 
-       (m)  PCRE2  supports non-atomic positive lookaround assertions. This is
+       (k)  PCRE2  supports non-atomic positive lookaround assertions. This is
        an extension to the lookaround facilities. The default, Perl-compatible
        lookarounds are atomic.
 
-       19.  The  Perl  /a modifier restricts /d numbers to pure ascii, and the
-       /aa modifier restricts /i case-insensitive matching to pure ascii,  ig-
-       noring  Unicode  rules.  This  separation  cannot  be  represented with
-       PCRE2_UCP.
+       (l) There are three syntactical items in patterns that can refer  to  a
+       capturing  group  by  number: back references such as \g{2}, subroutine
+       calls such as (?3), and condition references such as  (?(4)...).  PCRE2
+       supports  relative  group numbers such as +2 and -4 in all three cases.
+       Perl supports both plus and minus for subroutine calls, but only  minus
+       for back references, and no relative numbering at all for conditions.
 
        20. Perl has different limits than PCRE2. See the pcre2limit documenta-
        tion for details. Perl went with 5.10 from recursion to iteration keep-
@@ -5096,6 +5286,17 @@ DIFFERENCES BETWEEN PCRE2 AND PERL
        release 10.30, and also has many build-time and  run-time  customizable
        limits.
 
+       21.  Unlike  Perl,  PCRE2 doesn't have character set modifiers and spe-
+       cially no way to set characters by context just  like  Perl's  "/d".  A
+       regular expression using PCRE2_UTF and PCRE2_UCP will use similar rules
+       to  Perl's  "/u";  something closer to "/a" could be selected by adding
+       other PCRE2_EXTRA_ASCII* options on top.
+
+       22. Some recursive patterns that Perl diagnoses as infinite  recursions
+       can be handled by PCRE2, either by the interpreter or the JIT. An exam-
+       ple is /(?:|(?0)abcd)(?(R)|\z)/, which matches a sequence of any number
+       of repeated "abcd" substrings at the end of the subject.
+
 
 AUTHOR
 
@@ -5106,18 +5307,22 @@ AUTHOR
 
 REVISION
 
-       Last updated: 08 December 2021
-       Copyright (c) 1997-2021 University of Cambridge.
+       Last updated: 30 November 2023
+       Copyright (c) 1997-2023 University of Cambridge.
+
+
+PCRE2 10.43                    30 November 2023                 PCRE2COMPAT(3)
 ------------------------------------------------------------------------------
 
 
-PCRE2JIT(3)                Library Functions Manual                PCRE2JIT(3)
 
+PCRE2JIT(3)                Library Functions Manual                PCRE2JIT(3)
 
 
 NAME
        PCRE2 - Perl-compatible regular expressions (revised API)
 
+
 PCRE2 JUST-IN-TIME COMPILER SUPPORT
 
        Just-in-time  compiling  is a heavyweight optimization that can greatly
@@ -5127,45 +5332,54 @@ PCRE2 JUST-IN-TIME COMPILER SUPPORT
        essarily  mean many calls of a matching function; if the pattern is not
        anchored, matching attempts may take place many times at various  posi-
        tions in the subject, even for a single call. Therefore, if the subject
-       string is very long, it may still pay  to  use  JIT  even  for  one-off
-       matches.  JIT  support  is  available  for all of the 8-bit, 16-bit and
+       string  is  very  long,  it  may  still pay to use JIT even for one-off
+       matches. JIT support is available for all  of  the  8-bit,  16-bit  and
        32-bit PCRE2 libraries.
 
-       JIT support applies only to the  traditional  Perl-compatible  matching
-       function.   It  does  not apply when the DFA matching function is being
-       used. The code for this support was written by Zoltan Herczeg.
+       JIT  support  applies  only to the traditional Perl-compatible matching
+       function.  It does not apply when the DFA matching  function  is  being
+       used. The code for JIT support was written by Zoltan Herczeg.
 
 
 AVAILABILITY OF JIT SUPPORT
 
-       JIT support is an optional feature of  PCRE2.  The  "configure"  option
-       --enable-jit  (or  equivalent  CMake  option) must be set when PCRE2 is
-       built if you want to use JIT. The support is limited to  the  following
+       JIT  support  is  an  optional feature of PCRE2. The "configure" option
+       --enable-jit (or equivalent CMake option) must be  set  when  PCRE2  is
+       built  if  you want to use JIT. The support is limited to the following
        hardware platforms:
 
-         ARM 32-bit (v5, v7, and Thumb2)
+         ARM 32-bit (v7, and Thumb2)
          ARM 64-bit
          IBM s390x 64 bit
          Intel x86 32-bit and 64-bit
+         LoongArch 64 bit
          MIPS 32-bit and 64-bit
          Power PC 32-bit and 64-bit
-         SPARC 32-bit
+         RISC-V 32-bit and 64-bit
 
        If --enable-jit is set on an unsupported platform, compilation fails.
 
-       A  program  can  tell if JIT support is available by calling pcre2_con-
-       fig() with the PCRE2_CONFIG_JIT option. The result is  1  when  JIT  is
-       available,  and 0 otherwise. However, a simple program does not need to
-       check this in order to use JIT. The API is implemented in  a  way  that
-       falls  back  to the interpretive code if JIT is not available. For pro-
-       grams that need the best possible performance, there is  also  a  "fast
-       path" API that is JIT-specific.
+       A client program can tell  if  JIT  support  is  available  by  calling
+       pcre2_config()  with  the PCRE2_CONFIG_JIT option. The result is one if
+       PCRE2 was built with JIT support, and zero otherwise.  However,  having
+       the  JIT code available does not guarantee that it will be used for any
+       particular match. One reason for this is that there are a number of op-
+       tions and pattern items that are not supported by JIT (see below).  An-
+       other  reason  is that in some environments JIT is unable to get memory
+       in which to build its compiled code. The only guarantee from pcre2_con-
+       fig() is that if it returns zero, JIT will definitely not be used.
+
+       A simple program does not need to check availability in  order  to  use
+       JIT  when  possible. The API is implemented in a way that falls back to
+       the interpretive code if JIT is not available or cannot be used  for  a
+       given  match.  For  programs  that  need the best possible performance,
+       there is a "fast path" API that is JIT-specific.
 
 
 SIMPLE USE OF JIT
 
-       To  make use of the JIT support in the simplest way, all you have to do
-       is to call pcre2_jit_compile() after successfully compiling  a  pattern
+       To make use of the JIT support in the simplest way, all you have to  do
+       is  to  call pcre2_jit_compile() after successfully compiling a pattern
        with pcre2_compile(). This function has two arguments: the first is the
        compiled pattern pointer that was returned by pcre2_compile(), and  the
        second  is  zero  or  more of the following option bits: PCRE2_JIT_COM-
@@ -5181,13 +5395,13 @@ SIMPLE USE OF JIT
        There  is  a limit to the size of pattern that JIT supports, imposed by
        the size of machine stack that it uses. The exact rules are  not  docu-
        mented because they may change at any time, in particular, when new op-
-       timizations are introduced.  If  a  pattern  is  too  big,  a  call  to
+       timizations  are  introduced.   If  a  pattern  is  too  big, a call to
        pcre2_jit_compile() returns PCRE2_ERROR_NOMEMORY.
 
-       PCRE2_JIT_COMPLETE  requests the JIT compiler to generate code for com-
-       plete matches. If you want to run partial matches using the  PCRE2_PAR-
-       TIAL_HARD  or  PCRE2_PARTIAL_SOFT  options of pcre2_match(), you should
-       set one or both of  the  other  options  as  well  as,  or  instead  of
+       PCRE2_JIT_COMPLETE requests the JIT compiler to generate code for  com-
+       plete  matches. If you want to run partial matches using the PCRE2_PAR-
+       TIAL_HARD or PCRE2_PARTIAL_SOFT options of  pcre2_match(),  you  should
+       set  one  or  both  of  the  other  options  as  well as, or instead of
        PCRE2_JIT_COMPLETE. The JIT compiler generates different optimized code
        for each of the three modes (normal, soft partial, hard partial).  When
        pcre2_match()  is  called,  the appropriate code is run if it is avail-
@@ -5203,31 +5417,33 @@ SIMPLE USE OF JIT
        diately returns zero. This is an alternative way of testing whether JIT
        is available.
 
-       At present, it is not possible to free JIT compiled  code  except  when
+       At  present,  it  is not possible to free JIT compiled code except when
        the entire compiled pattern is freed by calling pcre2_code_free().
 
-       In  some circumstances you may need to call additional functions. These
-       are described in the section entitled "Controlling the JIT  stack"  be-
+       In some circumstances you may need to call additional functions.  These
+       are  described  in the section entitled "Controlling the JIT stack" be-
        low.
 
        There are some pcre2_match() options that are not supported by JIT, and
        there are also some pattern items that JIT cannot handle.  Details  are
-       given  below.  In  both cases, matching automatically falls back to the
+       given  below.   In both cases, matching automatically falls back to the
        interpretive code. If you want to know whether JIT  was  actually  used
        for  a particular match, you should arrange for a JIT callback function
        to be set up as described in the section entitled "Controlling the  JIT
        stack"  below,  even  if  you  do  not need to supply a non-default JIT
        stack. Such a callback function is called whenever JIT code is about to
-       be  obeyed.  If the match-time options are not right for JIT execution,
+       be obeyed. If the match-time options are not right for  JIT  execution,
        the callback function is not obeyed.
 
-       If the JIT compiler finds an unsupported item, no JIT  data  is  gener-
-       ated.  You  can find out if JIT matching is available after compiling a
+       If  the  JIT  compiler finds an unsupported item, no JIT data is gener-
+       ated. You can find out if JIT compilation was successful for a compiled
        pattern by calling pcre2_pattern_info() with the PCRE2_INFO_JITSIZE op-
-       tion.  A  non-zero  result means that JIT compilation was successful. A
+       tion. A non-zero result means that JIT compilation  was  successful.  A
        result of 0 means that JIT support is not available, or the pattern was
        not  processed by pcre2_jit_compile(), or the JIT compiler was not able
-       to handle the pattern.
+       to handle the pattern. Successful JIT compilation  does  not,  however,
+       guarantee  the  use  of  JIT at match time because there are some match
+       time options that are not supported by JIT.
 
 
 MATCHING SUBJECTS CONTAINING INVALID UTF
@@ -5237,20 +5453,21 @@ MATCHING SUBJECTS CONTAINING INVALID UTF
        fault, this is checked at the start of matching and an error is  gener-
        ated  if  invalid UTF is detected. The PCRE2_NO_UTF_CHECK option can be
        passed to pcre2_match() to skip the check (for improved performance) if
-       you  are  sure  that  a subject string is valid. If this option is used
-       with an invalid string, the result is undefined.
+       you are sure that a subject string is valid. If  this  option  is  used
+       with  an  invalid  string, the result is undefined. The calling program
+       may crash or loop or otherwise misbehave.
 
        However, a way of running matches on strings that may  contain  invalid
        UTF   sequences   is   available.   Calling  pcre2_compile()  with  the
        PCRE2_MATCH_INVALID_UTF option has two effects:  it  tells  the  inter-
        preter  in pcre2_match() to support invalid UTF, and, if pcre2_jit_com-
-       pile() is called, the compiled JIT code also supports invalid UTF.  De-
-       tails  of  how this support works, in both the JIT and the interpretive
-       cases, is given in the pcre2unicode documentation.
+       pile() is subsequently called, the compiled JIT code also supports  in-
+       valid  UTF.  Details of how this support works, in both the JIT and the
+       interpretive cases, is given in the pcre2unicode documentation.
 
        There  is  also  an  obsolete  option  for  pcre2_jit_compile()  called
        PCRE2_JIT_INVALID_UTF, which currently exists only for backward compat-
-       ibility.    It   is   superseded   by   the   pcre2_compile()    option
+       ibility.     It   is   superseded   by   the   pcre2_compile()   option
        PCRE2_MATCH_INVALID_UTF and should no longer be used. It may be removed
        in future.
 
@@ -5259,29 +5476,29 @@ UNSUPPORTED OPTIONS AND PATTERN ITEMS
 
        The pcre2_match() options that  are  supported  for  JIT  matching  are
        PCRE2_COPY_MATCHED_SUBJECT, PCRE2_NOTBOL, PCRE2_NOTEOL, PCRE2_NOTEMPTY,
-       PCRE2_NOTEMPTY_ATSTART,  PCRE2_NO_UTF_CHECK,  PCRE2_PARTIAL_HARD,   and
-       PCRE2_PARTIAL_SOFT.  The  PCRE2_ANCHORED  and PCRE2_ENDANCHORED options
+       PCRE2_NOTEMPTY_ATSTART,   PCRE2_NO_UTF_CHECK,  PCRE2_PARTIAL_HARD,  and
+       PCRE2_PARTIAL_SOFT. The PCRE2_ANCHORED  and  PCRE2_ENDANCHORED  options
        are not supported at match time.
 
-       If the PCRE2_NO_JIT option is passed to pcre2_match() it  disables  the
+       If  the  PCRE2_NO_JIT option is passed to pcre2_match() it disables the
        use of JIT, forcing matching by the interpreter code.
 
-       The  only  unsupported  pattern items are \C (match a single data unit)
-       when running in a UTF mode, and a callout immediately before an  asser-
+       The only unsupported pattern items are \C (match a  single  data  unit)
+       when  running in a UTF mode, and a callout immediately before an asser-
        tion condition in a conditional group.
 
 
 RETURN VALUES FROM JIT MATCHING
 
-       When a pattern is matched using JIT matching, the return values are the
-       same as those given by the interpretive pcre2_match()  code,  with  the
-       addition  of one new error code: PCRE2_ERROR_JIT_STACKLIMIT. This means
-       that the memory used for the JIT stack was insufficient. See  "Control-
-       ling the JIT stack" below for a discussion of JIT stack usage.
+       When a pattern is matched using JIT, the return values are the same  as
+       those  given  by the interpretive pcre2_match() code, with the addition
+       of one new error code: PCRE2_ERROR_JIT_STACKLIMIT. This means that  the
+       memory  used  for  the JIT stack was insufficient. See "Controlling the
+       JIT stack" below for a discussion of JIT stack usage.
 
-       The  error  code  PCRE2_ERROR_MATCHLIMIT is returned by the JIT code if
-       searching a very large pattern tree goes on for too long, as it  is  in
-       the  same circumstance when JIT is not used, but the details of exactly
+       The error code PCRE2_ERROR_MATCHLIMIT is returned by the  JIT  code  if
+       searching  a  very large pattern tree goes on for too long, as it is in
+       the same circumstance when JIT is not used, but the details of  exactly
        what is counted are not the same. The PCRE2_ERROR_DEPTHLIMIT error code
        is never returned when JIT matching is used.
 
@@ -5289,25 +5506,25 @@ RETURN VALUES FROM JIT MATCHING
 CONTROLLING THE JIT STACK
 
        When the compiled JIT code runs, it needs a block of memory to use as a
-       stack.  By default, it uses 32KiB on the machine stack.  However,  some
-       large  or complicated patterns need more than this. The error PCRE2_ER-
+       stack.   By  default, it uses 32KiB on the machine stack. However, some
+       large or complicated patterns need more than this. The error  PCRE2_ER-
        ROR_JIT_STACKLIMIT is given when there is not enough stack. Three func-
        tions are provided for managing blocks of memory for use as JIT stacks.
-       There is further discussion about the use of JIT stacks in the  section
+       There  is further discussion about the use of JIT stacks in the section
        entitled "JIT stack FAQ" below.
 
-       The  pcre2_jit_stack_create()  function  creates a JIT stack. Its argu-
-       ments are a starting size, a maximum size, and a general  context  (for
-       memory  allocation  functions, or NULL for standard memory allocation).
+       The pcre2_jit_stack_create() function creates a JIT  stack.  Its  argu-
+       ments  are  a starting size, a maximum size, and a general context (for
+       memory allocation functions, or NULL for standard  memory  allocation).
        It returns a pointer to an opaque structure of type pcre2_jit_stack, or
        NULL  if there is an error. The pcre2_jit_stack_free() function is used
        to free a stack that is no longer needed. If its argument is NULL, this
-       function  returns immediately, without doing anything. (For the techni-
-       cally minded: the address space is allocated by mmap or  VirtualAlloc.)
-       A  maximum  stack size of 512KiB to 1MiB should be more than enough for
+       function returns immediately, without doing anything. (For the  techni-
+       cally  minded: the address space is allocated by mmap or VirtualAlloc.)
+       A maximum stack size of 512KiB to 1MiB should be more than  enough  for
        any pattern.
 
-       The pcre2_jit_stack_assign() function specifies which  stack  JIT  code
+       The  pcre2_jit_stack_assign()  function  specifies which stack JIT code
        should use. Its arguments are as follows:
 
          pcre2_match_context  *mcontext
@@ -5337,20 +5554,20 @@ CONTROLLING THE JIT STACK
 
        A  callback function is obeyed whenever JIT code is about to be run; it
        is not obeyed when pcre2_match() is called with options that are incom-
-       patible  for JIT matching. A callback function can therefore be used to
-       determine whether a match operation was executed by JIT or by  the  in-
+       patible for JIT matching. A callback function can therefore be used  to
+       determine  whether  a match operation was executed by JIT or by the in-
        terpreter.
 
        You may safely use the same JIT stack for more than one pattern (either
        by assigning directly or by callback), as  long  as  the  patterns  are
        matched sequentially in the same thread. Currently, the only way to set
-       up non-sequential matches in one thread is to use callouts: if a  call-
-       out  function starts another match, that match must use a different JIT
+       up  non-sequential matches in one thread is to use callouts: if a call-
+       out function starts another match, that match must use a different  JIT
        stack to the one used for currently suspended match(es).
 
-       In a multithread application, if you do not specify a JIT stack, or  if
-       you  assign or pass back NULL from a callback, that is thread-safe, be-
-       cause each thread has its own machine stack. However, if you assign  or
+       In  a multithread application, if you do not specify a JIT stack, or if
+       you assign or pass back NULL from a callback, that is thread-safe,  be-
+       cause  each thread has its own machine stack. However, if you assign or
        pass back a non-NULL JIT stack, this must be a different stack for each
        thread so that the application is thread-safe.
 
@@ -5362,7 +5579,7 @@ CONTROLLING THE JIT STACK
        is available for use. However, this is an inefficient solution, and not
        recommended.
 
-       This is a suggestion for how a multithreaded program that needs to  set
+       This  is a suggestion for how a multithreaded program that needs to set
        up non-default JIT stacks might operate:
 
          During thread initialization
@@ -5374,7 +5591,7 @@ CONTROLLING THE JIT STACK
          Use a one-line callback function
            return thread_local_var
 
-       All  the  functions  described in this section do nothing if JIT is not
+       All the functions described in this section do nothing if  JIT  is  not
        available.
 
 
@@ -5404,8 +5621,8 @@ JIT STACK FAQ
        The owner of the stack is the user program, not the JIT studied pattern
        or anything else. The user program must ensure that if a stack is being
        used by pcre2_match(), (that is, it is assigned to a match context that
-       is passed to the pattern currently running), that  stack  must  not  be
-       used  by any other threads (to avoid overwriting the same memory area).
+       is  passed  to  the  pattern currently running), that stack must not be
+       used by any other threads (to avoid overwriting the same memory  area).
        The best practice for multithreaded programs is to allocate a stack for
        each thread, and return this stack through the JIT callback function.
 
@@ -5415,7 +5632,7 @@ JIT STACK FAQ
        pcre2_match() again. When you assign the stack to a match context, only
        a  pointer  is  set. There is no reference counting or any other magic.
        You can free compiled patterns, contexts, and stacks in any order, any-
-       time.   Just do not call pcre2_match() with a match context pointing to
+       time.  Just do not call pcre2_match() with a match context pointing  to
        an already freed stack, as that will cause SEGFAULT. (Also, do not free
        a  stack  currently  used  by pcre2_match() in another thread). You can
        also replace the stack in a context at any time when it is not in  use.
@@ -5433,10 +5650,10 @@ JIT STACK FAQ
        if a pattern causes stack overflow with a stack of 1MiB? Is  that  1MiB
        kept until the stack is freed?
 
-       Especially  on embedded sytems, it might be a good idea to release mem-
-       ory sometimes without freeing the stack. There is no API  for  this  at
-       the  moment.  Probably a function call which returns with the currently
-       allocated memory for any stack and another which allows releasing  mem-
+       Especially on embedded systems, it might be a good idea to release mem-
+       ory  sometimes  without  freeing the stack. There is no API for this at
+       the moment.  Probably a function call which returns with the  currently
+       allocated  memory for any stack and another which allows releasing mem-
        ory (shrinking the stack) would be a good idea if someone needs this.
 
        (7) This is too much of a headache. Isn't there any better solution for
@@ -5451,10 +5668,10 @@ FREEING JIT SPECULATIVE MEMORY
        void pcre2_jit_free_unused_memory(pcre2_general_context *gcontext);
 
        The JIT executable allocator does not free all memory when it is possi-
-       ble. It expects new allocations, and keeps some free memory  around  to
-       improve  allocation  speed. However, in low memory conditions, it might
-       be better to free all possible memory. You can cause this to happen  by
-       calling  pcre2_jit_free_unused_memory(). Its argument is a general con-
+       ble.  It  expects new allocations, and keeps some free memory around to
+       improve allocation speed. However, in low memory conditions,  it  might
+       be  better to free all possible memory. You can cause this to happen by
+       calling pcre2_jit_free_unused_memory(). Its argument is a general  con-
        text, for custom memory management, or NULL for standard memory manage-
        ment.
 
@@ -5490,7 +5707,7 @@ EXAMPLE CODE
 JIT FAST PATH API
 
        Because the API described above falls back to interpreted matching when
-       JIT is not available, it is convenient for programs  that  are  written
+       JIT  is  not  available, it is convenient for programs that are written
        for  general  use  in  many  environments.  However,  calling  JIT  via
        pcre2_match() does have a performance impact. Programs that are written
        for  use  where  JIT  is known to be available, and which need the best
@@ -5501,68 +5718,76 @@ JIT FAST PATH API
        The fast path function is called pcre2_jit_match(), and  it  takes  ex-
        actly  the same arguments as pcre2_match(). However, the subject string
        must be specified with a  length;  PCRE2_ZERO_TERMINATED  is  not  sup-
-       ported. Unsupported option bits (for example, PCRE2_ANCHORED, PCRE2_EN-
-       DANCHORED  and  PCRE2_COPY_MATCHED_SUBJECT)  are  ignored,  as  is  the
-       PCRE2_NO_JIT  option.  The  return  values  are  also  the  same as for
-       pcre2_match(), plus PCRE2_ERROR_JIT_BADOPTION if a matching mode  (par-
-       tial or complete) is requested that was not compiled.
+       ported.  Unsupported  option  bits  (for  example,  PCRE2_ANCHORED  and
+       PCRE2_ENDANCHORED) are ignored, as is the PCRE2_NO_JIT option. The  re-
+       turn  values  are  also  the  same as for pcre2_match(), plus PCRE2_ER-
+       ROR_JIT_BADOPTION if a matching mode (partial or complete) is requested
+       that was not compiled.
 
-       When  you call pcre2_match(), as well as testing for invalid options, a
+       When you call pcre2_match(), as well as testing for invalid options,  a
        number of other sanity checks are performed on the arguments. For exam-
        ple,  if the subject pointer is NULL but the length is non-zero, an im-
        mediate error is given. Also, unless PCRE2_NO_UTF_CHECK is set,  a  UTF
        subject string is tested for validity. In the interests of speed, these
-       checks do not happen on the JIT fast  path,  and  if  invalid  data  is
-       passed, the result is undefined.
-
-       Bypassing  the  sanity  checks  and the pcre2_match() wrapping can give
+       checks  do  not  happen  on  the  JIT fast path. If invalid UTF data is
+       passed when PCRE2_MATCH_INVALID_UTF was not  set  for  pcre2_compile(),
+       the  result  is  undefined. The program may crash or loop or give wrong
+       results. In the absence  of  PCRE2_MATCH_INVALID_UTF  you  should  call
+       pcre2_jit_match()  in  UTF  mode  only  if  you are sure the subject is
+       valid.
+
+       Bypassing the sanity checks and the  pcre2_match()  wrapping  can  give
        speedups of more than 10%.
 
 
 SEE ALSO
 
-       pcre2api(3)
+       pcre2api(3), pcre2unicode(3)
 
 
 AUTHOR
 
        Philip Hazel (FAQ by Zoltan Herczeg)
-       University Computing Service
+       Retired from University Computing Service
        Cambridge, England.
 
 
 REVISION
 
-       Last updated: 30 November 2021
-       Copyright (c) 1997-2021 University of Cambridge.
+       Last updated: 21 February 2024
+       Copyright (c) 1997-2024 University of Cambridge.
+
+
+PCRE2 10.43                    21 February 2024                    PCRE2JIT(3)
 ------------------------------------------------------------------------------
 
 
-PCRE2LIMITS(3)             Library Functions Manual             PCRE2LIMITS(3)
 
+PCRE2LIMITS(3)             Library Functions Manual             PCRE2LIMITS(3)
 
 
 NAME
        PCRE2 - Perl-compatible regular expressions (revised API)
 
+
 SIZE AND OTHER LIMITATIONS
 
        There are some size limitations in PCRE2 but it is hoped that they will
        never in practice be relevant.
 
-       The maximum size of a compiled pattern  is  approximately  64  thousand
+       The  maximum  size  of  a compiled pattern is approximately 64 thousand
        code units for the 8-bit and 16-bit libraries if PCRE2 is compiled with
        the default internal linkage size, which  is  2  bytes  for  these  li-
        braries.  If  you  want  to  process regular expressions that are truly
        enormous, you can compile PCRE2 with an internal linkage size of 3 or 4
-       (when  building  the  16-bit  library,  3  is rounded up to 4). See the
+       (when building the 16-bit library, 3 is  rounded  up  to  4).  See  the
        README file in the source distribution and the pcre2build documentation
        for  details.  In  these cases the limit is substantially larger.  How-
        ever, the speed of execution is slower. In the 32-bit library, the  in-
        ternal linkage size is always 4.
 
        The maximum length of a source pattern string is essentially unlimited;
-       it is the largest number a PCRE2_SIZE variable can hold.  However,  the
+       it  is  the largest number a PCRE2_SIZE variable can hold. However, the
        program that calls pcre2_compile() can specify a smaller limit.
 
        The maximum length (in code units) of a subject string is one less than
@@ -5573,12 +5798,18 @@ SIZE AND OTHER LIMITATIONS
 
        All values in repeating quantifiers must be less than 65536.
 
-       The maximum length of a lookbehind assertion is 65535 characters.
+       There are two different limits that apply to branches of lookbehind as-
+       sertions.   If every branch in such an assertion matches a fixed number
+       of characters, the maximum length of any branch is 65535 characters. If
+       any branch matches a variable number of characters,  then  the  maximum
+       matching  length  for every branch is limited. The default limit is set
+       at compile time, defaulting to 255, but can be changed by  the  calling
+       program.
 
        There  is no limit to the number of parenthesized groups, but there can
        be no more than 65535 capture groups, and there is a limit to the depth
-       of  nesting  of parenthesized subpatterns of all kinds. This is imposed
-       in order to limit the amount of system stack used at compile time.  The
+       of nesting of parenthesized subpatterns of all kinds. This  is  imposed
+       in  order to limit the amount of system stack used at compile time. The
        default limit can be specified when PCRE2 is built; if not, the default
        is set to  250.  An  application  can  change  this  limit  by  calling
        pcre2_set_parens_nest_limit() to set the limit in a compile context.
@@ -5607,31 +5838,35 @@ AUTHOR
 
 REVISION
 
-       Last updated: 26 July 2022
-       Copyright (c) 1997-2022 University of Cambridge.
+       Last updated: August 2023
+       Copyright (c) 1997-2023 University of Cambridge.
+
+
+PCRE2 10.43                      1 August 2023                  PCRE2LIMITS(3)
 ------------------------------------------------------------------------------
 
 
-PCRE2MATCHING(3)           Library Functions Manual           PCRE2MATCHING(3)
 
+PCRE2MATCHING(3)           Library Functions Manual           PCRE2MATCHING(3)
 
 
 NAME
        PCRE2 - Perl-compatible regular expressions (revised API)
 
+
 PCRE2 MATCHING ALGORITHMS
 
        This document describes the two different algorithms that are available
-       in PCRE2 for matching a compiled regular  expression  against  a  given
-       subject  string.  The  "standard"  algorithm is the one provided by the
-       pcre2_match() function. This works in the same as  as  Perl's  matching
-       function,  and  provide a Perl-compatible matching operation. The just-
-       in-time (JIT) optimization that is described in the pcre2jit documenta-
-       tion is compatible with this function.
+       in  PCRE2  for  matching  a compiled regular expression against a given
+       subject string. The "standard" algorithm is the  one  provided  by  the
+       pcre2_match() function. This works in the same as Perl's matching func-
+       tion,  and  provide  a Perl-compatible matching operation. The just-in-
+       time (JIT) optimization that is described in the pcre2jit documentation
+       is compatible with this function.
 
        An alternative algorithm is provided by the pcre2_dfa_match() function;
        it operates in a different way, and is not Perl-compatible. This alter-
-       native  has advantages and disadvantages compared with the standard al-
+       native has advantages and disadvantages compared with the standard  al-
        gorithm, and these are described below.
 
        When there is only one possible way in which a given subject string can
@@ -5652,19 +5887,19 @@ PCRE2 MATCHING ALGORITHMS
 REGULAR EXPRESSIONS AS TREES
 
        The set of strings that are matched by a regular expression can be rep-
-       resented  as  a  tree structure. An unlimited repetition in the pattern
-       makes the tree of infinite size, but it is still a tree.  Matching  the
-       pattern  to a given subject string (from a given starting point) can be
-       thought of as a search of the tree.  There are two  ways  to  search  a
-       tree:  depth-first  and  breadth-first, and these correspond to the two
+       resented as a tree structure. An unlimited repetition  in  the  pattern
+       makes  the  tree of infinite size, but it is still a tree. Matching the
+       pattern to a given subject string (from a given starting point) can  be
+       thought  of  as  a  search of the tree.  There are two ways to search a
+       tree: depth-first and breadth-first, and these correspond  to  the  two
        matching algorithms provided by PCRE2.
 
 
 THE STANDARD MATCHING ALGORITHM
 
-       In the terminology of Jeffrey Friedl's book "Mastering Regular  Expres-
-       sions",  the  standard  algorithm  is an "NFA algorithm". It conducts a
-       depth-first search of the pattern tree. That is, it  proceeds  along  a
+       In  the terminology of Jeffrey Friedl's book "Mastering Regular Expres-
+       sions", the standard algorithm is an "NFA  algorithm".  It  conducts  a
+       depth-first  search  of  the pattern tree. That is, it proceeds along a
        single path through the tree, checking that the subject matches what is
        required. When there is a mismatch, the algorithm  tries  any  alterna-
        tives  at  the  current point, and if they all fail, it backs up to the
@@ -5681,16 +5916,16 @@ THE STANDARD MATCHING ALGORITHM
        on the way the alternations and the greedy or ungreedy repetition quan-
        tifiers are specified in the pattern.
 
-       Because  it  ends  up  with a single path through the tree, it is rela-
-       tively straightforward for this algorithm to keep  track  of  the  sub-
-       strings  that  are  matched  by portions of the pattern in parentheses.
+       Because it ends up with a single path through the  tree,  it  is  rela-
+       tively  straightforward  for  this  algorithm to keep track of the sub-
+       strings that are matched by portions of  the  pattern  in  parentheses.
        This provides support for capturing parentheses and backreferences.
 
 
 THE ALTERNATIVE MATCHING ALGORITHM
 
-       This algorithm conducts a breadth-first search of  the  tree.  Starting
-       from  the  first  matching  point  in the subject, it scans the subject
+       This  algorithm  conducts  a breadth-first search of the tree. Starting
+       from the first matching point in the  subject,  it  scans  the  subject
        string from left to right, once, character by character, and as it does
        this,  it remembers all the paths through the tree that represent valid
        matches. In Friedl's terminology, this is a kind  of  "DFA  algorithm",
@@ -5707,44 +5942,44 @@ THE ALTERNATIVE MATCHING ALGORITHM
        there  are  no more unterminated paths. At this point, terminated paths
        represent the different matching possibilities (if there are none,  the
        match  has  failed).   Thus,  if there is more than one possible match,
-       this algorithm finds all of them, and in particular, it finds the long-
-       est.  The matches are returned in the output vector in decreasing order
-       of length. There is an option to stop the  algorithm  after  the  first
-       match (which is necessarily the shortest) is found.
+       this algorithm finds all of them,  and  in  particular,  it  finds  the
+       longest.  The  matches  are returned in the output vector in decreasing
+       order of length. There is an option to stop  the  algorithm  after  the
+       first match (which is necessarily the shortest) is found.
 
        Note  that the size of vector needed to contain all the results depends
        on the number of simultaneous matches, not on the number of parentheses
-       in  the pattern. Using pcre2_match_data_create_from_pattern() to create
-       the match data block is therefore not advisable when doing  DFA  match-
+       in the pattern. Using pcre2_match_data_create_from_pattern() to  create
+       the  match  data block is therefore not advisable when doing DFA match-
        ing.
 
-       Note  also  that all the matches that are found start at the same point
+       Note also that all the matches that are found start at the  same  point
        in the subject. If the pattern
 
          cat(er(pillar)?)?
 
-       is matched against the string "the caterpillar catchment",  the  result
-       is  the  three  strings "caterpillar", "cater", and "cat" that start at
-       the fifth character of the subject. The algorithm  does  not  automati-
+       is  matched  against the string "the caterpillar catchment", the result
+       is the three strings "caterpillar", "cater", and "cat"  that  start  at
+       the  fifth  character  of the subject. The algorithm does not automati-
        cally move on to find matches that start at later positions.
 
        PCRE2's "auto-possessification" optimization usually applies to charac-
        ter repeats at the end of a pattern (as well as internally). For  exam-
        ple, the pattern "a\d+" is compiled as if it were "a\d++" because there
-       is no point even considering the possibility of backtracking  into  the
-       repeated  digits.  For  DFA matching, this means that only one possible
-       match is found. If you really do want multiple matches in  such  cases,
-       either  use  an ungreedy repeat ("a\d+?") or set the PCRE2_NO_AUTO_POS-
+       is  no  point even considering the possibility of backtracking into the
+       repeated digits. For DFA matching, this means that  only  one  possible
+       match  is  found. If you really do want multiple matches in such cases,
+       either use an ungreedy repeat ("a\d+?") or set  the  PCRE2_NO_AUTO_POS-
        SESS option when compiling.
 
-       There are a number of features of PCRE2 regular  expressions  that  are
-       not  supported  or behave differently in the alternative matching func-
+       There  are  a  number of features of PCRE2 regular expressions that are
+       not supported or behave differently in the alternative  matching  func-
        tion. Those that are not supported cause an error if encountered.
 
-       1. Because the algorithm finds all possible matches, the greedy or  un-
-       greedy  nature of repetition quantifiers is not relevant (though it may
-       affect auto-possessification,  as  just  described).  During  matching,
-       greedy  and  ungreedy  quantifiers are treated in exactly the same way.
+       1.  Because the algorithm finds all possible matches, the greedy or un-
+       greedy nature of repetition quantifiers is not relevant (though it  may
+       affect  auto-possessification,  as  just  described).  During matching,
+       greedy and ungreedy quantifiers are treated in exactly  the  same  way.
        However, possessive quantifiers can make a difference when what follows
        could  also  match  what  is  quantified, for example in a pattern like
        this:
@@ -5758,8 +5993,8 @@ THE ALTERNATIVE MATCHING ALGORITHM
        pattern.
 
        2. When dealing with multiple paths through the tree simultaneously, it
-       is  not  straightforward  to  keep track of captured substrings for the
-       different matching possibilities, and PCRE2's  implementation  of  this
+       is not straightforward to keep track of  captured  substrings  for  the
+       different  matching  possibilities,  and PCRE2's implementation of this
        algorithm does not attempt to do this. This means that no captured sub-
        strings are available.
 
@@ -5773,29 +6008,29 @@ THE ALTERNATIVE MATCHING ALGORITHM
        5. Again for the same reason, script runs are not supported.
 
        6. Because many paths through the tree may be active, the \K escape se-
-       quence, which resets the start of the match when encountered  (but  may
+       quence,  which  resets the start of the match when encountered (but may
        be on some paths and not on others), is not supported.
 
-       7.  Callouts  are  supported, but the value of the capture_top field is
+       7. Callouts are supported, but the value of the  capture_top  field  is
        always 1, and the value of the capture_last field is always 0.
 
-       8. The \C escape sequence, which (in  the  standard  algorithm)  always
-       matches  a  single  code  unit, even in a UTF mode, is not supported in
-       these modes, because the alternative algorithm moves through  the  sub-
-       ject  string  one  character  (not code unit) at a time, for all active
+       8.  The  \C  escape  sequence, which (in the standard algorithm) always
+       matches a single code unit, even in a UTF mode,  is  not  supported  in
+       these  modes,  because the alternative algorithm moves through the sub-
+       ject string one character (not code unit) at a  time,  for  all  active
        paths through the tree.
 
-       9. Except for (*FAIL), the backtracking control verbs such as  (*PRUNE)
-       are  not  supported.  (*FAIL)  is supported, and behaves like a failing
+       9.  Except for (*FAIL), the backtracking control verbs such as (*PRUNE)
+       are not supported. (*FAIL) is supported, and  behaves  like  a  failing
        negative assertion.
 
-       10. The PCRE2_MATCH_INVALID_UTF option for pcre2_compile() is not  sup-
+       10.  The PCRE2_MATCH_INVALID_UTF option for pcre2_compile() is not sup-
        ported by pcre2_dfa_match().
 
 
 ADVANTAGES OF THE ALTERNATIVE ALGORITHM
 
-       The  main  advantage  of the alternative algorithm is that all possible
+       The main advantage of the alternative algorithm is  that  all  possible
        matches (at a single point in the subject) are automatically found, and
        in  particular, the longest match is found. To find more than one match
        at the same point using the standard algorithm, you have to  do  kludgy
@@ -5832,18 +6067,22 @@ AUTHOR
 
 REVISION
 
-       Last updated: 28 August 2021
-       Copyright (c) 1997-2021 University of Cambridge.
+       Last updated: 19 January 2024
+       Copyright (c) 1997-2024 University of Cambridge.
+
+
+PCRE2 10.43                     19 January 2024               PCRE2MATCHING(3)
 ------------------------------------------------------------------------------
 
 
-PCRE2PARTIAL(3)            Library Functions Manual            PCRE2PARTIAL(3)
 
+PCRE2PARTIAL(3)            Library Functions Manual            PCRE2PARTIAL(3)
 
 
 NAME
        PCRE2 - Perl-compatible regular expressions
 
+
 PARTIAL MATCHING IN PCRE2
 
        In  normal use of PCRE2, if there is a match up to the end of a subject
@@ -5854,61 +6093,61 @@ PARTIAL MATCHING IN PCRE2
 
        One  example  is  an application where the subject string is very long,
        and not all available at once. The requirement here is to be able to do
-       the  matching  segment  by segment, but special action is needed when a
+       the matching segment by segment, but special action is  needed  when  a
        matched substring spans the boundary between two segments.
 
-       Another example is checking a user input string as it is typed, to  en-
-       sure  that  it conforms to a required format. Invalid characters can be
+       Another  example is checking a user input string as it is typed, to en-
+       sure that it conforms to a required format. Invalid characters  can  be
        immediately diagnosed and rejected, giving instant feedback.
 
-       Partial matching is a PCRE2-specific feature; it is  not  Perl-compati-
-       ble.  It  is  requested  by  setting  one  of the PCRE2_PARTIAL_HARD or
-       PCRE2_PARTIAL_SOFT options when calling a matching function.  The  dif-
-       ference  between  the  two options is whether or not a partial match is
-       preferred to an alternative complete match, though the  details  differ
-       between  the  two  types of matching function. If both options are set,
+       Partial  matching  is a PCRE2-specific feature; it is not Perl-compati-
+       ble. It is requested  by  setting  one  of  the  PCRE2_PARTIAL_HARD  or
+       PCRE2_PARTIAL_SOFT  options  when calling a matching function. The dif-
+       ference between the two options is whether or not a  partial  match  is
+       preferred  to  an alternative complete match, though the details differ
+       between the two types of matching function. If both  options  are  set,
        PCRE2_PARTIAL_HARD takes precedence.
 
-       If you want to use partial matching with just-in-time  optimized  code,
-       as  well  as  setting a partial match option for the matching function,
-       you must also call pcre2_jit_compile() with one or both  of  these  op-
+       If  you  want to use partial matching with just-in-time optimized code,
+       as well as setting a partial match option for  the  matching  function,
+       you  must  also  call pcre2_jit_compile() with one or both of these op-
        tions:
 
          PCRE2_JIT_PARTIAL_HARD
          PCRE2_JIT_PARTIAL_SOFT
 
-       PCRE2_JIT_COMPLETE  should also be set if you are going to run non-par-
-       tial matches on the same pattern. Separate code is  compiled  for  each
-       mode.  If  the appropriate JIT mode has not been compiled, interpretive
+       PCRE2_JIT_COMPLETE should also be set if you are going to run  non-par-
+       tial  matches  on  the same pattern. Separate code is compiled for each
+       mode. If the appropriate JIT mode has not been  compiled,  interpretive
        matching code is used.
 
-       Setting a partial matching option disables two of PCRE2's standard  op-
-       timization  hints. PCRE2 remembers the last literal code unit in a pat-
-       tern, and abandons matching immediately if it is  not  present  in  the
-       subject  string.  This optimization cannot be used for a subject string
-       that might match only partially. PCRE2 also remembers a minimum  length
-       of  a matching string, and does not bother to run the matching function
-       on shorter strings. This optimization  is  also  disabled  for  partial
+       Setting  a partial matching option disables two of PCRE2's standard op-
+       timization hints. PCRE2 remembers the last literal code unit in a  pat-
+       tern,  and  abandons  matching  immediately if it is not present in the
+       subject string.  This optimization cannot be used for a subject  string
+       that  might match only partially. PCRE2 also remembers a minimum length
+       of a matching string, and does not bother to run the matching  function
+       on  shorter  strings.  This  optimization  is also disabled for partial
        matching.
 
 
 REQUIREMENTS FOR A PARTIAL MATCH
 
-       A  possible  partial  match  occurs during matching when the end of the
-       subject string is reached successfully, but either more characters  are
-       needed  to complete the match, or the addition of more characters might
+       A possible partial match occurs during matching when  the  end  of  the
+       subject  string is reached successfully, but either more characters are
+       needed to complete the match, or the addition of more characters  might
        change what is matched.
 
-       Example 1: if the pattern is /abc/ and the subject is "ab", more  char-
-       acters  are  definitely  needed  to complete a match. In this case both
+       Example  1: if the pattern is /abc/ and the subject is "ab", more char-
+       acters are definitely needed to complete a match.  In  this  case  both
        hard and soft matching options yield a partial match.
 
-       Example 2: if the pattern is /ab+/ and the subject is "ab", a  complete
-       match  can  be  found, but the addition of more characters might change
-       what is matched. In this case, only PCRE2_PARTIAL_HARD returns  a  par-
+       Example  2: if the pattern is /ab+/ and the subject is "ab", a complete
+       match can be found, but the addition of more  characters  might  change
+       what  is  matched. In this case, only PCRE2_PARTIAL_HARD returns a par-
        tial match; PCRE2_PARTIAL_SOFT returns the complete match.
 
-       On  reaching the end of the subject, when PCRE2_PARTIAL_HARD is set, if
+       On reaching the end of the subject, when PCRE2_PARTIAL_HARD is set,  if
        the next pattern item is \z, \Z, \b, \B, or $ there is always a partial
        match.   Otherwise, for both options, the next pattern item must be one
        that inspects a character, and at least one of the  following  must  be
@@ -5920,16 +6159,16 @@ REQUIREMENTS FOR A PARTIAL MATCH
        acters before the start of a matched string.
 
        (2) The pattern contains one or more lookbehind assertions. This condi-
-       tion  exists in case there is a lookbehind that inspects characters be-
+       tion exists in case there is a lookbehind that inspects characters  be-
        fore the start of the match.
 
-       (3) There is a special case when the whole pattern can match  an  empty
-       string.   When  the  starting  point  is at the end of the subject, the
-       empty string match is a possibility, and if PCRE2_PARTIAL_SOFT  is  set
-       and  neither  of the above conditions is true, it is returned. However,
-       because adding more characters  might  result  in  a  non-empty  match,
-       PCRE2_PARTIAL_HARD  returns  a  partial match, which in this case means
-       "there is going to be a match at this point, but until some more  char-
+       (3)  There  is a special case when the whole pattern can match an empty
+       string.  When the starting point is at the  end  of  the  subject,  the
+       empty  string  match is a possibility, and if PCRE2_PARTIAL_SOFT is set
+       and neither of the above conditions is true, it is  returned.  However,
+       because  adding  more  characters  might  result  in a non-empty match,
+       PCRE2_PARTIAL_HARD returns a partial match, which in  this  case  means
+       "there  is going to be a match at this point, but until some more char-
        acters are added, we do not know if it will be an empty string or some-
        thing longer".
 
@@ -5947,7 +6186,7 @@ PARTIAL MATCHING USING pcre2_match()
          No match can start anywhere in this subject.
 
        PCRE2_ERROR_PARTIAL
-         Adding more characters may result in a complete match that  uses  one
+         Adding  more  characters may result in a complete match that uses one
          or more characters from the end of this subject.
 
        When a partial match is returned, the first two elements in the ovector
@@ -5958,22 +6197,22 @@ PARTIAL MATCHING USING pcre2_match()
          /abc\K123/
 
        If it is matched against "456abc123xyz" the result is a complete match,
-       and  the ovector defines the matched string as "123", because \K resets
-       the "start of match" point. However, if a partial  match  is  requested
-       and  the subject string is "456abc12", a partial match is found for the
-       string "abc12", because all these characters are needed  for  a  subse-
+       and the ovector defines the matched string as "123", because \K  resets
+       the  "start  of  match" point. However, if a partial match is requested
+       and the subject string is "456abc12", a partial match is found for  the
+       string  "abc12",  because  all these characters are needed for a subse-
        quent re-match with additional characters.
 
-       If  there  is more than one partial match, the first one that was found
+       If there is more than one partial match, the first one that  was  found
        provides the data that is returned. Consider this pattern:
 
          /123\w+X|dogY/
 
-       If this is matched against the subject string "abc123dog", both  alter-
-       natives  fail  to  match,  but the end of the subject is reached during
-       matching, so PCRE2_ERROR_PARTIAL is returned. The offsets are set to  3
-       and  9, identifying "123dog" as the first partial match. (In this exam-
-       ple, there are two partial matches, because "dog" on its own  partially
+       If  this is matched against the subject string "abc123dog", both alter-
+       natives fail to match, but the end of the  subject  is  reached  during
+       matching,  so PCRE2_ERROR_PARTIAL is returned. The offsets are set to 3
+       and 9, identifying "123dog" as the first partial match. (In this  exam-
+       ple,  there are two partial matches, because "dog" on its own partially
        matches the second alternative.)
 
    How a partial match is processed by pcre2_match()
@@ -5985,11 +6224,11 @@ PARTIAL MATCHING USING pcre2_match()
        as  a partial match is found, without continuing to search for possible
        complete matches. This option is "hard" because it prefers  an  earlier
        partial match over a later complete match. For this reason, the assump-
-       tion is made that the end of the supplied subject  string  is  not  the
-       true  end of the available data, which is why \z, \Z, \b, \B, and $ al-
+       tion  is  made  that  the end of the supplied subject string is not the
+       true end of the available data, which is why \z, \Z, \b, \B, and $  al-
        ways give a partial match.
 
-       If PCRE2_PARTIAL_SOFT is set, the  partial  match  is  remembered,  but
+       If  PCRE2_PARTIAL_SOFT  is  set,  the  partial match is remembered, but
        matching continues as normal, and other alternatives in the pattern are
        tried. If no complete match can be found,  PCRE2_ERROR_PARTIAL  is  re-
        turned instead of PCRE2_ERROR_NOMATCH. This option is "soft" because it
@@ -6020,14 +6259,14 @@ PARTIAL MATCHING USING pcre2_match()
          /dog(sbody)?/    is the same as  /dogsbody|dog/
          /dog(sbody)??/   is the same as  /dog|dogsbody/
 
-       The second pattern will never match "dogsbody", because it will  always
+       The  second pattern will never match "dogsbody", because it will always
        find the shorter match first.
 
    Example of partial matching using pcre2test
 
-       The  pcre2test data modifiers partial_hard (or ph) and partial_soft (or
-       ps) set PCRE2_PARTIAL_HARD and PCRE2_PARTIAL_SOFT,  respectively,  when
-       calling  pcre2_match(). Here is a run of pcre2test using a pattern that
+       The pcre2test data modifiers partial_hard (or ph) and partial_soft  (or
+       ps)  set  PCRE2_PARTIAL_HARD and PCRE2_PARTIAL_SOFT, respectively, when
+       calling pcre2_match(). Here is a run of pcre2test using a pattern  that
        matches the whole subject in the form of a date:
 
            re> /^\d?\d(jan|feb|mar|apr|may|jun|jul|aug|sep|oct|nov|dec)\d\d$/
@@ -6038,7 +6277,7 @@ PARTIAL MATCHING USING pcre2_match()
          data> 3juj\=ph
          No match
 
-       This example gives the same results for  both  hard  and  soft  partial
+       This  example  gives  the  same  results for both hard and soft partial
        matching options. Here is an example where there is a difference:
 
            re> /^\d?\d(jan|feb|mar|apr|may|jun|jul|aug|sep|oct|nov|dec)\d\d$/
@@ -6048,7 +6287,7 @@ PARTIAL MATCHING USING pcre2_match()
          data> 25jun04\=ph
          Partial match: 25jun04
 
-       With   PCRE2_PARTIAL_SOFT,  the  subject  is  matched  completely.  For
+       With  PCRE2_PARTIAL_SOFT,  the  subject  is  matched  completely.   For
        PCRE2_PARTIAL_HARD, however, the subject is assumed not to be complete,
        so there is only a partial match.
 
@@ -6058,7 +6297,7 @@ MULTI-SEGMENT MATCHING WITH pcre2_match()
        PCRE  was  not originally designed with multi-segment matching in mind.
        However, over time, features (including  partial  matching)  that  make
        multi-segment matching possible have been added. A very long string can
-       be searched segment by segment  by  calling  pcre2_match()  repeatedly,
+       be  searched  segment  by  segment by calling pcre2_match() repeatedly,
        with the aim of achieving the same results that would happen if the en-
        tire string was available for searching all  the  time.  Normally,  the
        strings  that  are  being  sought are much shorter than each individual
@@ -6067,8 +6306,8 @@ MULTI-SEGMENT MATCHING WITH pcre2_match()
 
        Special  logic  must  be implemented to handle a matched substring that
        spans a segment boundary. PCRE2_PARTIAL_HARD should be used, because it
-       returns  a  partial match at the end of a segment whenever there is the
-       possibility of changing  the  match  by  adding  more  characters.  The
+       returns a partial match at the end of a segment whenever there  is  the
+       possibility  of  changing  the  match  by  adding  more characters. The
        PCRE2_NOTBOL option should also be set for all but the first segment.
 
        When a partial match occurs, the next segment must be added to the cur-
@@ -6085,21 +6324,21 @@ MULTI-SEGMENT MATCHING WITH pcre2_match()
 
        Note the use of the offset modifier to start the new  match  where  the
        partial match was found. In this example, the next segment was added to
-       the one in which  the  partial  match  was  found.  This  is  the  most
+       the  one  in  which  the  partial  match  was  found.  This is the most
        straightforward approach, typically using a memory buffer that is twice
        the size of each segment. After a partial match, the first half of  the
-       buffer  is discarded, the second half is moved to the start of the buf-
-       fer, and a new segment is added before repeating the match  as  in  the
+       buffer  is  discarded,  the  second  half  is moved to the start of the
+       buffer, and a new segment is added before repeating the match as in the
        example above. After a no match, the entire buffer can be discarded.
 
        If there are memory constraints, you may want to discard text that pre-
        cedes a partial match before adding the  next  segment.  Unfortunately,
        this  is  not  at  present straightforward. In cases such as the above,
        where the pattern does not contain any lookbehinds, it is sufficient to
-       retain  only  the  partially matched substring. However, if the pattern
-       contains a lookbehind assertion, characters that precede the  start  of
-       the  partial match may have been inspected during the matching process.
-       When pcre2test displays a partial match, it indicates these  characters
+       retain only the partially matched substring. However,  if  the  pattern
+       contains  a  lookbehind assertion, characters that precede the start of
+       the partial match may have been inspected during the matching  process.
+       When  pcre2test displays a partial match, it indicates these characters
        with '<' if the allusedtext modifier is set:
 
            re> "(?<=123)abc"
@@ -6107,8 +6346,8 @@ MULTI-SEGMENT MATCHING WITH pcre2_match()
          Partial match: 123ab
                         <<<
 
-       However,  the  allusedtext  modifier is not available for JIT matching,
-       because JIT matching does not record  the  first  (or  last)  consulted
+       However, the allusedtext modifier is not available  for  JIT  matching,
+       because  JIT  matching  does  not  record the first (or last) consulted
        characters.  For this reason, this information is not available via the
        API. It is therefore not possible in general to obtain the exact number
        of characters that must be retained in order to get the right match re-
@@ -6122,12 +6361,12 @@ MULTI-SEGMENT MATCHING WITH pcre2_match()
        if  there  are  nested  lookbehinds.  The  value  returned  by  calling
        pcre2_pattern_info() with the PCRE2_INFO_MAXLOOKBEHIND  option  is  the
        maximum number of characters (not code units) that any individual look-
-       behind  moves  back  when  it  is  processed.   A   pattern   such   as
-       "(?<=(?\r\n|\n|\x0b|\f|\r|\x85)
 
        This is an example of an "atomic group", details of which are given be-
-       low.  This particular group matches either the  two-character  sequence
-       CR  followed  by  LF,  or  one  of  the single characters LF (linefeed,
-       U+000A), VT (vertical tab, U+000B), FF (form feed,  U+000C),  CR  (car-
-       riage  return,  U+000D), or NEL (next line, U+0085). Because this is an
-       atomic group, the two-character sequence is treated as  a  single  unit
+       low.   This  particular group matches either the two-character sequence
+       CR followed by LF, or  one  of  the  single  characters  LF  (linefeed,
+       U+000A),  VT  (vertical  tab, U+000B), FF (form feed, U+000C), CR (car-
+       riage return, U+000D), or NEL (next line, U+0085). Because this  is  an
+       atomic  group,  the  two-character sequence is treated as a single unit
        that cannot be split.
 
        In other modes, two additional characters whose code points are greater
        than 255 are added: LS (line separator, U+2028) and PS (paragraph sepa-
-       rator,  U+2029).  Unicode support is not needed for these characters to
+       rator, U+2029).  Unicode support is not needed for these characters  to
        be recognized.
 
        It is possible to restrict \R to match only CR, LF, or CRLF (instead of
        the  complete  set  of  Unicode  line  endings)  by  setting the option
        PCRE2_BSR_ANYCRLF at compile time. (BSR is an abbreviation  for  "back-
        slash R".) This can be made the default when PCRE2 is built; if this is
-       the case, the other behaviour can be requested via  the  PCRE2_BSR_UNI-
-       CODE  option. It is also possible to specify these settings by starting
+       the  case,  the other behaviour can be requested via the PCRE2_BSR_UNI-
+       CODE option. It is also possible to specify these settings by  starting
        a pattern string with one of the following sequences:
 
          (*BSR_ANYCRLF)   CR, LF, or CRLF only
@@ -6872,8 +7144,8 @@ BACKSLASH
 
        These override the default and the options given to the compiling func-
        tion.  Note that these special settings, which are not Perl-compatible,
-       are recognized only at the very start of a pattern, and that they  must
-       be  in upper case. If more than one of them is present, the last one is
+       are  recognized only at the very start of a pattern, and that they must
+       be in upper case. If more than one of them is present, the last one  is
        used. They can be combined with a change of newline convention; for ex-
        ample, a pattern can start with:
 
@@ -6888,14 +7160,14 @@ BACKSLASH
        When  PCRE2  is  built  with Unicode support (the default), three addi-
        tional escape sequences that match characters with specific  properties
        are available. They can be used in any mode, though in 8-bit and 16-bit
-       non-UTF modes these sequences are of course limited to testing  charac-
-       ters  whose code points are less than U+0100 and U+10000, respectively.
-       In 32-bit non-UTF mode, code points greater than 0x10ffff (the  Unicode
-       limit)  may  be  encountered. These are all treated as being in the Un-
+       non-UTF  modes these sequences are of course limited to testing charac-
+       ters whose code points are less than U+0100 and U+10000,  respectively.
+       In  32-bit non-UTF mode, code points greater than 0x10ffff (the Unicode
+       limit) may be encountered. These are all treated as being  in  the  Un-
        known script and with an unassigned type.
 
-       Matching characters by Unicode property is not fast, because PCRE2  has
-       to  do  a  multistage table lookup in order to find a character's prop-
+       Matching  characters by Unicode property is not fast, because PCRE2 has
+       to do a multistage table lookup in order to find  a  character's  prop-
        erty. That is why the traditional escape sequences such as \d and \w do
        not  use  Unicode  properties  in PCRE2 by default, though you can make
        them do so by setting the PCRE2_UCP option or by starting  the  pattern
@@ -6920,20 +7192,20 @@ BACKSLASH
    Script properties for \p and \P
 
        There are three different syntax forms for matching a script. Each Uni-
-       code character has a basic script and,  optionally,  a  list  of  other
+       code  character  has  a  basic  script and, optionally, a list of other
        scripts ("Script Extensions") with which it is commonly used. Using the
        Adlam script as an example, \p{sc:Adlam} matches characters whose basic
        script is Adlam, whereas \p{scx:Adlam} matches, in addition, characters
        that have Adlam in their extensions list. The full names  "script"  and
        "script extensions" for the property types are recognized, and a equals
-       sign is an alternative to the colon. If a script name is given  without
-       a  property  type,  for example, \p{Adlam}, it is treated as \p{scx:Ad-
-       lam}. Perl changed to this interpretation at  release  5.26  and  PCRE2
+       sign  is an alternative to the colon. If a script name is given without
+       a property type, for example, \p{Adlam}, it is  treated  as  \p{scx:Ad-
+       lam}.  Perl  changed  to  this interpretation at release 5.26 and PCRE2
        changed at release 10.40.
 
        Unassigned characters (and in non-UTF 32-bit mode, characters with code
        points greater than 0x10FFFF) are assigned the "Unknown" script. Others
-       that  are not part of an identified script are lumped together as "Com-
+       that are not part of an identified script are lumped together as  "Com-
        mon". The current list of recognized script names and their 4-character
        abbreviations can be obtained by running this command:
 
@@ -6943,9 +7215,9 @@ BACKSLASH
    The general category property for \p and \P
 
        Each character has exactly one Unicode general category property, spec-
-       ified by a two-letter abbreviation. For compatibility with Perl,  nega-
-       tion  can  be  specified  by including a circumflex between the opening
-       brace and the property name.  For  example,  \p{^Lu}  is  the  same  as
+       ified  by a two-letter abbreviation. For compatibility with Perl, nega-
+       tion can be specified by including a  circumflex  between  the  opening
+       brace  and  the  property  name.  For  example,  \p{^Lu} is the same as
        \P{Lu}.
 
        If only one letter is specified with \p or \P, it includes all the gen-
@@ -7011,26 +7283,26 @@ BACKSLASH
        ferent to any other character when PCRE2 is not in UTF mode (using  the
        16-bit  or  32-bit  library).   However,  they are not valid in Unicode
        strings and so cannot be tested by PCRE2 in UTF mode, unless UTF valid-
-       ity   checking   has   been   turned   off   (see   the  discussion  of
+       ity  checking  has   been   turned   off   (see   the   discussion   of
        PCRE2_NO_UTF_CHECK in the pcre2api page).
 
-       The long synonyms for  property  names  that  Perl  supports  (such  as
-       \p{Letter})  are  not supported by PCRE2, nor is it permitted to prefix
+       The  long  synonyms  for  property  names  that  Perl supports (such as
+       \p{Letter}) are not supported by PCRE2, nor is it permitted  to  prefix
        any of these properties with "Is".
 
        No character that is in the Unicode table has the Cn (unassigned) prop-
        erty.  Instead, this property is assumed for any code point that is not
        in the Unicode table.
 
-       Specifying caseless matching does not affect  these  escape  sequences.
-       For  example,  \p{Lu}  always  matches only upper case letters. This is
+       Specifying  caseless  matching  does not affect these escape sequences.
+       For example, \p{Lu} always matches only upper  case  letters.  This  is
        different from the behaviour of current versions of Perl.
 
    Binary (yes/no) properties for \p and \P
 
-       Unicode defines a number of  binary  properties,  that  is,  properties
-       whose  only  values  are  true or false. You can obtain a list of those
-       that are recognized by \p and \P, along with  their  abbreviations,  by
+       Unicode  defines  a  number  of  binary properties, that is, properties
+       whose only values are true or false. You can obtain  a  list  of  those
+       that  are  recognized  by \p and \P, along with their abbreviations, by
        running this command:
 
          pcre2test -LP
@@ -7067,23 +7339,23 @@ BACKSLASH
          S           segment separator
          WS          which space
 
-       An  equals  sign  may  be  used instead of a colon. The class names are
+       An equals sign may be used instead of a  colon.  The  class  names  are
        case-insensitive; only the short names listed above are recognized.
 
    Extended grapheme clusters
 
-       The \X escape matches any number of Unicode  characters  that  form  an
+       The  \X  escape  matches  any number of Unicode characters that form an
        "extended grapheme cluster", and treats the sequence as an atomic group
        (see below).  Unicode supports various kinds of composite character  by
        giving  each  character  a grapheme breaking property, and having rules
        that use these properties to define the boundaries of extended grapheme
-       clusters.  The rules are defined in Unicode Standard Annex 29, "Unicode
-       Text Segmentation". Unicode 11.0.0 abandoned the use of  some  previous
-       properties  that had been used for emojis.  Instead it introduced vari-
-       ous emoji-specific properties. PCRE2  uses  only  the  Extended  Picto-
+       clusters. The rules are defined in Unicode Standard Annex 29,  "Unicode
+       Text  Segmentation".  Unicode 11.0.0 abandoned the use of some previous
+       properties that had been used for emojis.  Instead it introduced  vari-
+       ous  emoji-specific  properties.  PCRE2  uses  only the Extended Picto-
        graphic property.
 
-       \X  always  matches  at least one character. Then it decides whether to
+       \X always matches at least one character. Then it  decides  whether  to
        add additional characters according to the following rules for ending a
        cluster:
 
@@ -7098,16 +7370,17 @@ BACKSLASH
        be  followed  by  a V or T character; an LVT or T character may be fol-
        lowed only by a T character.
 
-       4. Do not end before extending  characters  or  spacing  marks  or  the
-       "zero-width  joiner" character. Characters with the "mark" property al-
+       4. Do not end before extending characters or spacing marks or the zero-
+       width joiner (ZWJ) character. Characters with the "mark"  property  al-
        ways have the "extend" grapheme breaking property.
 
        5. Do not end after prepend characters.
 
-       6. Do not break within emoji modifier sequences or emoji zwj sequences.
-       That is, do not break between characters with the Extended_Pictographic
-       property.  Extend and ZWJ characters are allowed  between  the  charac-
-       ters.
+       6.  Do not end within emoji modifier sequences or emoji ZWJ (zero-width
+       joiner) sequences. An emoji ZWJ sequence consists of a  character  with
+       the  Extended_Pictographic property, optionally followed by one or more
+       characters with the Extend property, followed  by  the  ZWJ  character,
+       followed by another Extended_Pictographic character.
 
        7.  Do not break within emoji flag sequences. That is, do not break be-
        tween regional indicator (RI) characters if there are an odd number  of
@@ -7119,8 +7392,8 @@ BACKSLASH
 
        As  well as the standard Unicode properties described above, PCRE2 sup-
        ports four more that make it possible to convert traditional escape se-
-       quences  such  as \w and \s to use Unicode properties. PCRE2 uses these
-       non-standard, non-Perl properties internally  when  PCRE2_UCP  is  set.
+       quences such as \w and \s to use Unicode properties. PCRE2  uses  these
+       non-standard,  non-Perl  properties  internally  when PCRE2_UCP is set.
        However, they may also be used explicitly. These properties are:
 
          Xan   Any alphanumeric character
@@ -7128,20 +7401,21 @@ BACKSLASH
          Xsp   Any Perl space character
          Xwd   Any Perl "word" character
 
-       Xan  matches  characters that have either the L (letter) or the N (num-
-       ber) property. Xps matches the characters tab, linefeed, vertical  tab,
-       form  feed,  or carriage return, and any other character that has the Z
-       (separator) property.  Xsp is the same as Xps; in PCRE1 it used to  ex-
-       clude  vertical  tab,  for  Perl  compatibility,  but Perl changed. Xwd
-       matches the same characters as Xan, plus underscore.
-
-       There is another non-standard property, Xuc, which matches any  charac-
-       ter  that  can  be represented by a Universal Character Name in C++ and
-       other programming languages. These are the characters $,  @,  `  (grave
-       accent),  and  all  characters with Unicode code points greater than or
-       equal to U+00A0, except for the surrogates U+D800 to U+DFFF. Note  that
-       most  base  (ASCII) characters are excluded. (Universal Character Names
-       are of the form \uHHHH or \UHHHHHHHH where H is  a  hexadecimal  digit.
+       Xan matches characters that have either the L (letter) or the  N  (num-
+       ber)  property. Xps matches the characters tab, linefeed, vertical tab,
+       form feed, or carriage return, and any other character that has  the  Z
+       (separator)  property.  Xsp is the same as Xps; in PCRE1 it used to ex-
+       clude vertical tab, for  Perl  compatibility,  but  Perl  changed.  Xwd
+       matches the same characters as Xan, plus those that match Mn (non-spac-
+       ing mark) or Pc (connector punctuation, which includes underscore).
+
+       There  is another non-standard property, Xuc, which matches any charac-
+       ter that can be represented by a Universal Character Name  in  C++  and
+       other  programming  languages.  These are the characters $, @, ` (grave
+       accent), and all characters with Unicode code points  greater  than  or
+       equal  to U+00A0, except for the surrogates U+D800 to U+DFFF. Note that
+       most base (ASCII) characters are excluded. (Universal  Character  Names
+       are  of  the  form \uHHHH or \UHHHHHHHH where H is a hexadecimal digit.
        Note that the Xuc property does not match these sequences but the char-
        acters that they represent.)
 
@@ -7153,18 +7427,18 @@ BACKSLASH
 
          foo\Kbar
 
-       matches "foobar", but reports that it has matched "bar".  \K  does  not
+       matches  "foobar",  but  reports that it has matched "bar". \K does not
        interact with anchoring in any way. The pattern:
 
          ^foo\Kbar
 
-       matches  only  when  the  subject  begins with "foobar" (in single line
-       mode), though it again reports the matched string as "bar".  This  fea-
-       ture  is similar to a lookbehind assertion (described below).  However,
-       in this case, the part of the subject before the real  match  does  not
-       have  to be of fixed length, as lookbehind assertions do. The use of \K
-       does not interfere with the setting of captured substrings.  For  exam-
-       ple, when the pattern
+       matches only when the subject begins  with  "foobar"  (in  single  line
+       mode),  though  it again reports the matched string as "bar". This fea-
+       ture is similar to a lookbehind assertion (described  below),  but  the
+       part of the pattern that precedes \K is not constrained to match a lim-
+       ited  number  of characters, as is required for a lookbehind assertion.
+       The use of \K does not interfere with  the  setting  of  captured  sub-
+       strings.  For example, when the pattern
 
          (foo)\Kbar
 
@@ -7175,25 +7449,25 @@ BACKSLASH
        the  PCRE2_EXTRA_ALLOW_LOOKAROUND_BSK  option  can be used when calling
        pcre2_compile() to re-enable the previous behaviour. When  this  option
        is set, \K is acted upon when it occurs inside positive assertions, but
-       is ignored in negative assertions. Note that when  a  pattern  such  as
-       (?=ab\K)  matches,  the reported start of the match can be greater than
-       the end of the match. Using \K in a lookbehind assertion at  the  start
-       of  a  pattern can also lead to odd effects. For example, consider this
+       is  ignored  in  negative  assertions. Note that when a pattern such as
+       (?=ab\K) matches, the reported start of the match can be  greater  than
+       the  end  of the match. Using \K in a lookbehind assertion at the start
+       of a pattern can also lead to odd effects. For example,  consider  this
        pattern:
 
          (?<=\Kfoo)bar
 
-       If the subject is "foobar", a call to  pcre2_match()  with  a  starting
-       offset  of 3 succeeds and reports the matching string as "foobar", that
-       is, the start of the reported match is earlier  than  where  the  match
+       If  the  subject  is  "foobar", a call to pcre2_match() with a starting
+       offset of 3 succeeds and reports the matching string as "foobar",  that
+       is,  the  start  of  the reported match is earlier than where the match
        started.
 
    Simple assertions
 
-       The  final use of backslash is for certain simple assertions. An asser-
-       tion specifies a condition that has to be met at a particular point  in
-       a  match, without consuming any characters from the subject string. The
-       use of groups for more complicated assertions is described below.   The
+       The final use of backslash is for certain simple assertions. An  asser-
+       tion  specifies a condition that has to be met at a particular point in
+       a match, without consuming any characters from the subject string.  The
+       use  of groups for more complicated assertions is described below.  The
        backslashed assertions are:
 
          \b     matches at a word boundary
@@ -7204,15 +7478,15 @@ BACKSLASH
          \z     matches only at the end of the subject
          \G     matches at the first matching position in the subject
 
-       Inside  a  character  class, \b has a different meaning; it matches the
-       backspace character. If any other of  these  assertions  appears  in  a
+       Inside a character class, \b has a different meaning;  it  matches  the
+       backspace  character.  If  any  other  of these assertions appears in a
        character class, an "invalid escape sequence" error is generated.
 
-       A  word  boundary is a position in the subject string where the current
-       character and the previous character do not both match \w or  \W  (i.e.
-       one  matches  \w  and the other matches \W), or the start or end of the
-       string if the first or last character matches  \w,  respectively.  When
-       PCRE2  is  built with Unicode support, the meanings of \w and \W can be
+       A word boundary is a position in the subject string where  the  current
+       character  and  the previous character do not both match \w or \W (i.e.
+       one matches \w and the other matches \W), or the start or  end  of  the
+       string  if  the  first or last character matches \w, respectively. When
+       PCRE2 is built with Unicode support, the meanings of \w and \W  can  be
        changed by setting the PCRE2_UCP option. When this is done, it also af-
        fects  \b and \B. Neither PCRE2 nor Perl has a separate "start of word"
        or "end of word" metasequence. However, whatever  follows  \b  normally
@@ -7221,27 +7495,27 @@ BACKSLASH
 
        The \A, \Z, and \z assertions differ from  the  traditional  circumflex
        and dollar (described in the next section) in that they only ever match
-       at the very start and end of the subject string, whatever  options  are
-       set.  Thus,  they are independent of multiline mode. These three asser-
-       tions are not affected by the  PCRE2_NOTBOL  or  PCRE2_NOTEOL  options,
-       which  affect only the behaviour of the circumflex and dollar metachar-
-       acters. However, if the startoffset argument of pcre2_match()  is  non-
-       zero,  indicating  that  matching is to start at a point other than the
-       beginning of the subject, \A can never match.  The  difference  between
-       \Z  and \z is that \Z matches before a newline at the end of the string
+       at  the  very start and end of the subject string, whatever options are
+       set. Thus, they are independent of multiline mode. These  three  asser-
+       tions  are  not  affected  by the PCRE2_NOTBOL or PCRE2_NOTEOL options,
+       which affect only the behaviour of the circumflex and dollar  metachar-
+       acters.  However,  if the startoffset argument of pcre2_match() is non-
+       zero, indicating that matching is to start at a point  other  than  the
+       beginning  of  the subject, \A can never match.  The difference between
+       \Z and \z is that \Z matches before a newline at the end of the  string
        as well as at the very end, whereas \z matches only at the end.
 
-       The \G assertion is true only when the current matching position is  at
-       the  start point of the matching process, as specified by the startoff-
-       set argument of pcre2_match(). It differs from \A  when  the  value  of
-       startoffset  is  non-zero. By calling pcre2_match() multiple times with
-       appropriate arguments, you can mimic Perl's /g option,  and  it  is  in
+       The  \G assertion is true only when the current matching position is at
+       the start point of the matching process, as specified by the  startoff-
+       set  argument  of  pcre2_match().  It differs from \A when the value of
+       startoffset is non-zero. By calling pcre2_match() multiple  times  with
+       appropriate  arguments,  you  can  mimic Perl's /g option, and it is in
        this kind of implementation where \G can be useful.
 
-       Note,  however,  that  PCRE2's  implementation of \G, being true at the
-       starting character of the matching process, is  subtly  different  from
-       Perl's,  which  defines it as true at the end of the previous match. In
-       Perl, these can be different when the  previously  matched  string  was
+       Note, however, that PCRE2's implementation of \G,  being  true  at  the
+       starting  character  of  the matching process, is subtly different from
+       Perl's, which defines it as true at the end of the previous  match.  In
+       Perl,  these  can  be  different when the previously matched string was
        empty. Because PCRE2 does just one match at a time, it cannot reproduce
        this behaviour.
 
@@ -7252,8 +7526,8 @@ BACKSLASH
 
 CIRCUMFLEX AND DOLLAR
 
-       The circumflex and dollar  metacharacters  are  zero-width  assertions.
-       That  is,  they test for a particular condition being true without con-
+       The  circumflex  and  dollar  metacharacters are zero-width assertions.
+       That is, they test for a particular condition being true  without  con-
        suming any characters from the subject string. These two metacharacters
        are  concerned  with matching the starts and ends of lines. If the new-
        line convention is set so that only the two-character sequence CRLF  is
@@ -7261,32 +7535,32 @@ CIRCUMFLEX AND DOLLAR
        ordinary data characters, and are not recognized as newlines.
 
        Outside a character class, in the default matching mode, the circumflex
-       character  is  an  assertion  that is true only if the current matching
-       point is at the start of the subject string. If the  startoffset  argu-
-       ment  of  pcre2_match() is non-zero, or if PCRE2_NOTBOL is set, circum-
-       flex can never match if the PCRE2_MULTILINE option is unset.  Inside  a
-       character  class, circumflex has an entirely different meaning (see be-
+       character is an assertion that is true only  if  the  current  matching
+       point  is  at the start of the subject string. If the startoffset argu-
+       ment of pcre2_match() is non-zero, or if PCRE2_NOTBOL is  set,  circum-
+       flex  can  never match if the PCRE2_MULTILINE option is unset. Inside a
+       character class, circumflex has an entirely different meaning (see  be-
        low).
 
-       Circumflex need not be the first character of the pattern if  a  number
-       of  alternatives are involved, but it should be the first thing in each
-       alternative in which it appears if the pattern is ever  to  match  that
-       branch.  If all possible alternatives start with a circumflex, that is,
-       if the pattern is constrained to match only at the start  of  the  sub-
-       ject,  it  is  said  to be an "anchored" pattern. (There are also other
+       Circumflex  need  not be the first character of the pattern if a number
+       of alternatives are involved, but it should be the first thing in  each
+       alternative  in  which  it appears if the pattern is ever to match that
+       branch. If all possible alternatives start with a circumflex, that  is,
+       if  the  pattern  is constrained to match only at the start of the sub-
+       ject, it is said to be an "anchored" pattern.  (There  are  also  other
        constructs that can cause a pattern to be anchored.)
 
-       The dollar character is an assertion that is true only if  the  current
-       matching  point is at the end of the subject string, or immediately be-
-       fore a newline at the end of the string (by default), unless  PCRE2_NO-
-       TEOL  is  set.  Note, however, that it does not actually match the new-
-       line. Dollar need not be the last character of the pattern if a  number
-       of  alternatives  are  involved,  but it should be the last item in any
-       branch in which it appears. Dollar has no special meaning in a  charac-
+       The  dollar  character is an assertion that is true only if the current
+       matching point is at the end of the subject string, or immediately  be-
+       fore  a newline at the end of the string (by default), unless PCRE2_NO-
+       TEOL is set. Note, however, that it does not actually  match  the  new-
+       line.  Dollar need not be the last character of the pattern if a number
+       of alternatives are involved, but it should be the  last  item  in  any
+       branch  in which it appears. Dollar has no special meaning in a charac-
        ter class.
 
-       The  meaning  of  dollar  can be changed so that it matches only at the
-       very end of the string, by setting the PCRE2_DOLLAR_ENDONLY  option  at
+       The meaning of dollar can be changed so that it  matches  only  at  the
+       very  end  of the string, by setting the PCRE2_DOLLAR_ENDONLY option at
        compile time. This does not affect the \Z assertion.
 
        The meanings of the circumflex and dollar metacharacters are changed if
@@ -7322,7 +7596,7 @@ CIRCUMFLEX AND DOLLAR
 FULL STOP (PERIOD, DOT) AND \N
 
        Outside a character class, a dot in the pattern matches any one charac-
-       ter  in  the subject string except (by default) a character that signi-
+       ter in the subject string except (by default) a character  that  signi-
        fies the end of a line. One or more characters may be specified as line
        terminators (see "Newline conventions" above).
 
@@ -7330,22 +7604,22 @@ FULL STOP (PERIOD, DOT) AND \N
        ter sequence CRLF is the only line ending, dot does not match CR if  it
        is  immediately followed by LF, but otherwise it matches all characters
        (including isolated CRs and LFs). When ANYCRLF  is  selected  for  line
-       endings,  no  occurences  of  CR of LF match dot. When all Unicode line
+       endings,  no  occurrences  of CR of LF match dot. When all Unicode line
        endings are being recognized, dot does not match CR or LF or any of the
        other line ending characters.
 
-       The  behaviour  of  dot  with regard to newlines can be changed. If the
-       PCRE2_DOTALL option is set, a dot matches any  one  character,  without
-       exception.   If  the two-character sequence CRLF is present in the sub-
+       The behaviour of dot with regard to newlines can  be  changed.  If  the
+       PCRE2_DOTALL  option  is  set, a dot matches any one character, without
+       exception.  If the two-character sequence CRLF is present in  the  sub-
        ject string, it takes two dots to match it.
 
-       The handling of dot is entirely independent of the handling of  circum-
-       flex  and  dollar,  the  only relationship being that they both involve
+       The  handling of dot is entirely independent of the handling of circum-
+       flex and dollar, the only relationship being  that  they  both  involve
        newlines. Dot has no special meaning in a character class.
 
-       The escape sequence \N when not followed by an  opening  brace  behaves
-       like  a dot, except that it is not affected by the PCRE2_DOTALL option.
-       In other words, it matches any character except one that signifies  the
+       The  escape  sequence  \N when not followed by an opening brace behaves
+       like a dot, except that it is not affected by the PCRE2_DOTALL  option.
+       In  other words, it matches any character except one that signifies the
        end of a line.
 
        When \N is followed by an opening brace it has a different meaning. See
@@ -7364,8 +7638,8 @@ MATCHING A SINGLE CODE UNIT
        match individual bytes in UTF-8 mode, but it is unclear how it can use-
        fully be used.
 
-       Because \C breaks up characters into individual  code  units,  matching
-       one  unit  with  \C  in UTF-8 or UTF-16 mode means that the rest of the
+       Because  \C  breaks  up characters into individual code units, matching
+       one unit with \C in UTF-8 or UTF-16 mode means that  the  rest  of  the
        string may start with a malformed UTF character. This has undefined re-
        sults, because PCRE2 assumes that it is matching character by character
        in a valid UTF string (by default it checks the subject string's valid-
@@ -7388,9 +7662,9 @@ MATCHING A SINGLE CODE UNIT
        whether or not UTF-32 is specified.
 
        In general, the \C escape sequence is best avoided. However, one way of
-       using it that avoids the problem of malformed UTF-8 or  UTF-16  charac-
-       ters  is  to use a lookahead to check the length of the next character,
-       as in this pattern, which could be used with  a  UTF-8  string  (ignore
+       using  it  that avoids the problem of malformed UTF-8 or UTF-16 charac-
+       ters is to use a lookahead to check the length of the  next  character,
+       as  in  this  pattern,  which could be used with a UTF-8 string (ignore
        white space and line breaks):
 
          (?| (?=[\x00-\x7f])(\C) |
@@ -7398,8 +7672,8 @@ MATCHING A SINGLE CODE UNIT
              (?=[\x{800}-\x{ffff}])(\C)(\C)(\C) |
              (?=[\x{10000}-\x{1fffff}])(\C)(\C)(\C)(\C))
 
-       In  this  example,  a  group  that starts with (?| resets the capturing
-       parentheses numbers in each alternative (see "Duplicate Group  Numbers"
+       In this example, a group that starts  with  (?|  resets  the  capturing
+       parentheses  numbers in each alternative (see "Duplicate Group Numbers"
        below). The assertions at the start of each branch check the next UTF-8
        character for values whose encoding uses 1, 2, 3, or 4  bytes,  respec-
        tively.  The  character's individual bytes are then captured by the ap-
@@ -7412,20 +7686,20 @@ SQUARE BRACKETS AND CHARACTER CLASSES
        closing square bracket. A closing square bracket on its own is not spe-
        cial by default.  If a closing square bracket is required as  a  member
        of the class, it should be the first data character in the class (after
-       an initial circumflex, if present) or escaped with  a  backslash.  This
-       means  that,  by default, an empty class cannot be defined. However, if
-       the PCRE2_ALLOW_EMPTY_CLASS option is set, a closing square bracket  at
+       an  initial  circumflex,  if present) or escaped with a backslash. This
+       means that, by default, an empty class cannot be defined.  However,  if
+       the  PCRE2_ALLOW_EMPTY_CLASS option is set, a closing square bracket at
        the start does end the (empty) class.
 
-       A  character class matches a single character in the subject. A matched
+       A character class matches a single character in the subject. A  matched
        character must be in the set of characters defined by the class, unless
        the  first  character in the class definition is a circumflex, in which
        case the subject character must not be in the set defined by the class.
-       If  a  circumflex is actually required as a member of the class, ensure
+       If a circumflex is actually required as a member of the  class,  ensure
        it is not the first character, or escape it with a backslash.
 
-       For example, the character class [aeiou] matches any lower case  vowel,
-       while  [^aeiou]  matches  any character that is not a lower case vowel.
+       For  example, the character class [aeiou] matches any lower case vowel,
+       while [^aeiou] matches any character that is not a  lower  case  vowel.
        Note that a circumflex is just a convenient notation for specifying the
        characters  that  are in the class by enumerating those that are not. A
        class that starts with a circumflex is not an assertion; it still  con-
@@ -7449,40 +7723,40 @@ SQUARE BRACKETS AND CHARACTER CLASSES
        one of these characters.
 
        The generic character type escape sequences \d, \D, \h, \H, \p, \P, \s,
-       \S,  \v,  \V,  \w,  and \W may appear in a character class, and add the
-       characters that they  match  to  the  class.  For  example,  [\dABCDEF]
-       matches  any  hexadecimal digit. In UTF modes, the PCRE2_UCP option af-
+       \S, \v, \V, \w, and \W may appear in a character  class,  and  add  the
+       characters  that  they  match  to  the  class.  For example, [\dABCDEF]
+       matches any hexadecimal digit. In UTF modes, the PCRE2_UCP  option  af-
        fects the meanings of \d, \s, \w and their upper case partners, just as
        it does when they appear outside a character class, as described in the
-       section entitled "Generic character types" above. The  escape  sequence
-       \b  has  a  different  meaning inside a character class; it matches the
-       backspace character. The sequences \B, \R, and \X are not  special  in-
-       side  a  character class. Like any other unrecognized escape sequences,
-       they cause an error. The same is true for \N when not  followed  by  an
+       section  entitled  "Generic character types" above. The escape sequence
+       \b has a different meaning inside a character  class;  it  matches  the
+       backspace  character.  The sequences \B, \R, and \X are not special in-
+       side a character class. Like any other unrecognized  escape  sequences,
+       they  cause  an  error. The same is true for \N when not followed by an
        opening brace.
 
-       The  minus (hyphen) character can be used to specify a range of charac-
-       ters in a character class. For example, [d-m] matches  any  letter  be-
-       tween  d and m, inclusive. If a minus character is required in a class,
-       it must be escaped with a backslash or appear in a  position  where  it
-       cannot  be interpreted as indicating a range, typically as the first or
+       The minus (hyphen) character can be used to specify a range of  charac-
+       ters  in  a  character class. For example, [d-m] matches any letter be-
+       tween d and m, inclusive. If a minus character is required in a  class,
+       it  must  be  escaped with a backslash or appear in a position where it
+       cannot be interpreted as indicating a range, typically as the first  or
        last character in the class, or immediately after a range. For example,
        [b-d-z] matches letters in the range b to d, a hyphen character, or z.
 
        Perl treats a hyphen as a literal if it appears before or after a POSIX
-       class (see below) or before or after a character type escape such as as
-       \d  or  \H.   However,  unless  the hyphen is the last character in the
-       class, Perl outputs a warning in its warning  mode,  as  this  is  most
-       likely  a user error. As PCRE2 has no facility for warning, an error is
-       given in these cases.
+       class (see below) or before or after a character type escape such as \d
+       or  \H.  However, unless the hyphen is the last character in the class,
+       Perl outputs a warning in its warning mode, as this is  most  likely  a
+       user  error. As PCRE2 has no facility for warning, an error is given in
+       these cases.
 
        It is not possible to have the literal character "]" as the end charac-
-       ter  of a range. A pattern such as [W-]46] is interpreted as a class of
-       two characters ("W" and "-") followed by a literal string "46]", so  it
-       would  match  "W46]"  or  "-46]". However, if the "]" is escaped with a
-       backslash it is interpreted as the end of range, so [W-\]46] is  inter-
-       preted  as a class containing a range followed by two other characters.
-       The octal or hexadecimal representation of "]" can also be used to  end
+       ter of a range. A pattern such as [W-]46] is interpreted as a class  of
+       two  characters ("W" and "-") followed by a literal string "46]", so it
+       would match "W46]" or "-46]". However, if the "]"  is  escaped  with  a
+       backslash  it is interpreted as the end of range, so [W-\]46] is inter-
+       preted as a class containing a range followed by two other  characters.
+       The  octal or hexadecimal representation of "]" can also be used to end
        a range.
 
        Ranges normally include all code points between the start and end char-
@@ -7495,33 +7769,33 @@ SQUARE BRACKETS AND CHARACTER CLASSES
        ever, ranges such as [\x{d7ff}-\x{e000}], which include the surrogates,
        are always permitted.
 
-       There  is  a  special  case in EBCDIC environments for ranges whose end
+       There is a special case in EBCDIC environments  for  ranges  whose  end
        points are both specified as literal letters in the same case. For com-
        patibility  with Perl, EBCDIC code points within the range that are not
        letters are omitted. For example, [h-k] matches only  four  characters,
        even though the codes for h and k are 0x88 and 0x92, a range of 11 code
-       points. However, if the range is specified  numerically,  for  example,
+       points.  However,  if  the range is specified numerically, for example,
        [\x88-\x92] or [h-\x92], all code points are included.
 
        If a range that includes letters is used when caseless matching is set,
        it matches the letters in either case. For example, [W-c] is equivalent
-       to  [][\\^_`wxyzabc],  matched  caselessly,  and  in a non-UTF mode, if
-       character tables for a French locale are in  use,  [\xc8-\xcb]  matches
+       to [][\\^_`wxyzabc], matched caselessly, and  in  a  non-UTF  mode,  if
+       character  tables  for  a French locale are in use, [\xc8-\xcb] matches
        accented E characters in both cases.
 
-       A  circumflex  can  conveniently  be used with the upper case character
-       types to specify a more restricted set of characters than the  matching
-       lower  case  type.  For example, the class [^\W_] matches any letter or
+       A circumflex can conveniently be used with  the  upper  case  character
+       types  to specify a more restricted set of characters than the matching
+       lower case type.  For example, the class [^\W_] matches any  letter  or
        digit, but not underscore, whereas [\w] includes underscore. A positive
        character class should be read as "something OR something OR ..." and a
        negative class as "NOT something AND NOT something AND NOT ...".
 
-       The only metacharacters that are recognized in  character  classes  are
-       backslash,  hyphen  (only  where  it can be interpreted as specifying a
-       range), circumflex (only at the start), opening  square  bracket  (only
-       when  it can be interpreted as introducing a POSIX class name, or for a
-       special compatibility feature - see the next  two  sections),  and  the
-       terminating  closing  square  bracket.  However, escaping other non-al-
+       The  only  metacharacters  that are recognized in character classes are
+       backslash, hyphen (only where it can be  interpreted  as  specifying  a
+       range),  circumflex  (only  at the start), opening square bracket (only
+       when it can be interpreted as introducing a POSIX class name, or for  a
+       special  compatibility  feature  -  see the next two sections), and the
+       terminating closing square bracket.  However,  escaping  other  non-al-
        phanumeric characters does no harm.
 
 
@@ -7551,10 +7825,11 @@ POSIX CHARACTER CLASSES
          word     "word" characters (same as \w)
          xdigit   hexadecimal digits
 
-       The  default  "space" characters are HT (9), LF (10), VT (11), FF (12),
-       CR (13), and space (32). If locale-specific matching is  taking  place,
-       the  list  of  space characters may be different; there may be fewer or
-       more of them. "Space" and \s match the same set of characters.
+       The default "space" characters are HT (9), LF (10), VT (11),  FF  (12),
+       CR  (13),  and space (32). If locale-specific matching is taking place,
+       the list of space characters may be different; there may  be  fewer  or
+       more  of  them.  "Space" and \s match the same set of characters, as do
+       "word" and \w.
 
        The name "word" is a Perl extension, and "blank"  is  a  GNU  extension
        from  Perl  5.8. Another Perl extension is negation, which is indicated
@@ -7569,10 +7844,10 @@ POSIX CHARACTER CLASSES
        By default, characters with values greater than 127 do not match any of
        the POSIX character classes, although this may be different for charac-
        ters in the range 128-255 when locale-specific matching  is  happening.
-       However,  if the PCRE2_UCP option is passed to pcre2_compile(), some of
-       the classes are changed so that Unicode character properties are  used.
-       This  is  achieved  by  replacing  certain POSIX classes with other se-
-       quences, as follows:
+       However,  in UCP mode, unless certain options are set (see below), some
+       of the classes are changed so that  Unicode  character  properties  are
+       used. This is achieved by replacing POSIX classes with other sequences,
+       as follows:
 
          [:alnum:]  becomes  \p{Xan}
          [:alpha:]  becomes  \p{L}
@@ -7584,10 +7859,10 @@ POSIX CHARACTER CLASSES
          [:upper:]  becomes  \p{Lu}
          [:word:]   becomes  \p{Xwd}
 
-       Negated versions, such as [:^alpha:] use \P instead of \p. Three  other
+       Negated  versions,  such as [:^alpha:] use \P instead of \p. Four other
        POSIX classes are handled specially in UCP mode:
 
-       [:graph:] This  matches  characters that have glyphs that mark the page
+       [:graph:] This matches characters that have glyphs that mark  the  page
                  when printed. In Unicode property terms, it matches all char-
                  acters with the L, M, N, P, S, or Cf properties, except for:
 
@@ -7601,17 +7876,31 @@ POSIX CHARACTER CLASSES
                  the Zs property.
 
        [:punct:] This matches all characters that have the Unicode P (punctua-
-                 tion) property, plus those characters with code  points  less
+                 tion)  property,  plus those characters with code points less
                  than 256 that have the S (Symbol) property.
 
-       The  other  POSIX classes are unchanged, and match only characters with
-       code points less than 256.
+       [:xdigit:]
+                 In addition  to  the  ASCII  hexadecimal  digits,  this  also
+                 matches  the  "fullwidth" versions of those characters, whose
+                 Unicode code points start at U+FF10. This is  a  change  that
+                 was made in PCRE release 10.43 for Perl compatibility.
+
+       The  other  POSIX  classes  are  unchanged by PCRE2_UCP, and match only
+       characters with code points less than 256.
+
+       There are two options that can be used to restrict the POSIX classes to
+       ASCII  characters  when  PCRE2_UCP  is  set.   The   option   PCRE2_EX-
+       TRA_ASCII_DIGIT  affects  just  [:digit:] and [:xdigit:]. Within a pat-
+       tern, this can be set and unset by  (?aT)  and  (?-aT).  The  PCRE2_EX-
+       TRA_ASCII_POSIX  option  disables UCP processing for all POSIX classes,
+       including [:digit:] and [:xdigit:]. Within a pattern, (?aP) and  (?-aP)
+       set and unset both these options for consistency.
 
 
 COMPATIBILITY FEATURE FOR WORD BOUNDARIES
 
-       In the POSIX.2 compliant library that was included in 4.4BSD Unix,  the
-       ugly  syntax  [[:<:]]  and [[:>:]] is used for matching "start of word"
+       In  the POSIX.2 compliant library that was included in 4.4BSD Unix, the
+       ugly syntax [[:<:]] and [[:>:]] is used for matching  "start  of  word"
        and "end of word". PCRE2 treats these items as follows:
 
          [[:<:]]  is converted to  \b(?=\w)
@@ -7621,22 +7910,24 @@ COMPATIBILITY FEATURE FOR WORD BOUNDARIES
        [a[:<:]b]  provokes  error  for  an unrecognized POSIX class name. This
        support is not compatible with Perl. It is provided to help  migrations
        from other environments, and is best not used in any new patterns. Note
-       that \b matches at the start and the end of a word (see "Simple  asser-
-       tions"  above),  and in a Perl-style pattern the preceding or following
-       character normally shows which is wanted, without the need for the  as-
-       sertions  that are used above in order to give exactly the POSIX behav-
-       iour.
+       that  \b matches at the start and the end of a word (see "Simple asser-
+       tions" above), and in a Perl-style pattern the preceding  or  following
+       character  normally shows which is wanted, without the need for the as-
+       sertions that are used above in order to give exactly the POSIX  behav-
+       iour.  Note  also  that  the PCRE2_UCP option changes the meaning of \w
+       (and therefore \b) by default, so  it  also  affects  these  POSIX  se-
+       quences.
 
 
 VERTICAL BAR
 
-       Vertical bar characters are used to separate alternative patterns.  For
+       Vertical  bar characters are used to separate alternative patterns. For
        example, the pattern
 
          gilbert|sullivan
 
-       matches  either "gilbert" or "sullivan". Any number of alternatives may
-       appear, and an empty  alternative  is  permitted  (matching  the  empty
+       matches either "gilbert" or "sullivan". Any number of alternatives  may
+       appear,  and  an  empty  alternative  is  permitted (matching the empty
        string). The matching process tries each alternative in turn, from left
        to right, and the first one that succeeds is used. If the  alternatives
        are  within a group (defined below), "succeeds" means matching the rest
@@ -7645,12 +7936,10 @@ VERTICAL BAR
 
 INTERNAL OPTION SETTING
 
-       The settings  of  the  PCRE2_CASELESS,  PCRE2_MULTILINE,  PCRE2_DOTALL,
-       PCRE2_EXTENDED,  PCRE2_EXTENDED_MORE, and PCRE2_NO_AUTO_CAPTURE options
-       can be changed from within the pattern by a  sequence  of  letters  en-
-       closed  between  "(?"   and ")". These options are Perl-compatible, and
-       are described in detail in the pcre2api documentation. The option  let-
-       ters are:
+       The settings of several options can be changed within a  pattern  by  a
+       sequence  of  letters  enclosed between "(?" and ")". The following are
+       Perl-compatible, and are described in detail in the pcre2api documenta-
+       tion. The option letters are:
 
          i  for PCRE2_CASELESS
          m  for PCRE2_MULTILINE
@@ -7661,38 +7950,52 @@ INTERNAL OPTION SETTING
 
        For example, (?im) sets caseless, multiline matching. It is also possi-
        ble to unset these options by preceding the relevant letters with a hy-
-       phen,  for  example (?-im). The two "extended" options are not indepen-
+       phen, for example (?-im). The two "extended" options are  not  indepen-
        dent; unsetting either one cancels the effects of both of them.
 
-       A  combined  setting  and  unsetting  such  as  (?im-sx),  which   sets
-       PCRE2_CASELESS  and  PCRE2_MULTILINE  while  unsetting PCRE2_DOTALL and
-       PCRE2_EXTENDED, is also permitted. Only one hyphen may  appear  in  the
-       options  string.  If a letter appears both before and after the hyphen,
-       the option is unset. An empty options setting "(?)" is  allowed.  Need-
+       A   combined  setting  and  unsetting  such  as  (?im-sx),  which  sets
+       PCRE2_CASELESS and PCRE2_MULTILINE  while  unsetting  PCRE2_DOTALL  and
+       PCRE2_EXTENDED,  is  also  permitted. Only one hyphen may appear in the
+       options string. If a letter appears both before and after  the  hyphen,
+       the  option  is unset. An empty options setting "(?)" is allowed. Need-
        less to say, it has no effect.
 
-       If  the  first character following (? is a circumflex, it causes all of
-       the above options to be unset. Thus, (?^) is equivalent  to  (?-imnsx).
-       Letters  may  follow  the circumflex to cause some options to be re-in-
-       stated, but a hyphen may not appear.
-
-       The PCRE2-specific options PCRE2_DUPNAMES  and  PCRE2_UNGREEDY  can  be
-       changed  in  the  same  way as the Perl-compatible options by using the
-       characters J and U respectively. However, these are not unset by (?^).
-
-       When one of these option changes occurs at top level (that is, not  in-
-       side  group  parentheses),  the  change applies to the remainder of the
-       pattern that follows. An option change within a group (see below for  a
-       description of groups) affects only that part of the group that follows
-       it, so
+       If the first character following (? is a circumflex, it causes  all  of
+       the  above  options  to  be unset. Letters may follow the circumflex to
+       cause some options to be re-instated, but a hyphen may not appear.
+
+       Some PCRE2-specific options can be changed by the same mechanism  using
+       these pairs or individual letters:
+
+         aD for PCRE2_EXTRA_ASCII_BSD
+         aS for PCRE2_EXTRA_ASCII_BSS
+         aW for PCRE2_EXTRA_ASCII_BSW
+         aP for PCRE2_EXTRA_ASCII_POSIX and PCRE2_EXTRA_ASCII_DIGIT
+         aT for PCRE2_EXTRA_ASCII_DIGIT
+         r  for PCRE2_EXTRA_CASELESS_RESTRICT
+         J  for PCRE2_DUPNAMES
+         U  for PCRE2_UNGREEDY
+
+       However,  except for 'r', these are not unset by (?^), which is equiva-
+       lent to (?-imnrsx). If 'a' is not followed by any  of  the  upper  case
+       letters shown above, it sets (or unsets) all the ASCII options.
+
+       PCRE2_EXTRA_ASCII_DIGIT   has   no  additional  effect  when  PCRE2_EX-
+       TRA_ASCII_POSIX is set, but including it in  (?aP)  means  that  (?-aP)
+       suppresses all ASCII restrictions for POSIX classes.
+
+       When  one of these option changes occurs at top level (that is, not in-
+       side group parentheses), the change applies until a subsequent  change,
+       or  the  end of the pattern. An option change within a group (see below
+       for a description of groups) affects only that part of the  group  that
+       follows  it.  At  the  end  of the group these options are reset to the
+       state they were before the group. For example,
 
          (a(?i)b)c
 
        matches abc and aBc and no other strings  (assuming  PCRE2_CASELESS  is
-       not  used).   By this means, options can be made to have different set-
-       tings in different parts of the pattern. Any changes made in one alter-
-       native  do carry on into subsequent branches within the same group. For
-       example,
+       not  set  externally).  Any changes made in one alternative do carry on
+       into subsequent branches within the same group. For example,
 
          (a(?i)b|c)
 
@@ -7716,29 +8019,29 @@ INTERNAL OPTION SETTING
        sequences such as (*CRLF) to override what the application has  set  or
        what  has  been  defaulted.   Details are given in the section entitled
        "Newline sequences" above. There are also the (*UTF) and (*UCP) leading
-       sequences  that can be used to set UTF and Unicode property modes; they
-       are equivalent to setting the PCRE2_UTF and PCRE2_UCP options,  respec-
-       tively.  However,  the  application  can  set  the  PCRE2_NEVER_UTF and
-       PCRE2_NEVER_UCP options, which lock out  the  use  of  the  (*UTF)  and
+       sequences that can be used to set UTF and Unicode property modes;  they
+       are  equivalent to setting the PCRE2_UTF and PCRE2_UCP options, respec-
+       tively.  However,  the  application  can  set  the  PCRE2_NEVER_UTF  or
+       PCRE2_NEVER_UCP  options,  which  lock  out  the  use of the (*UTF) and
        (*UCP) sequences.
 
 
 GROUPS
 
-       Groups  are  delimited  by  parentheses  (round brackets), which can be
+       Groups are delimited by parentheses  (round  brackets),  which  can  be
        nested.  Turning part of a pattern into a group does two things:
 
        1. It localizes a set of alternatives. For example, the pattern
 
          cat(aract|erpillar|)
 
-       matches "cataract", "caterpillar", or "cat". Without  the  parentheses,
+       matches  "cataract",  "caterpillar", or "cat". Without the parentheses,
        it would match "cataract", "erpillar" or an empty string.
 
-       2.  It  creates a "capture group". This means that, when the whole pat-
-       tern matches, the portion of the subject string that matched the  group
-       is  passed back to the caller, separately from the portion that matched
-       the whole pattern.  (This applies  only  to  the  traditional  matching
+       2. It creates a "capture group". This means that, when the  whole  pat-
+       tern  matches, the portion of the subject string that matched the group
+       is passed back to the caller, separately from the portion that  matched
+       the  whole  pattern.   (This  applies  only to the traditional matching
        function; the DFA matching function does not support capturing.)
 
        Opening parentheses are counted from left to right (starting from 1) to
@@ -7750,11 +8053,11 @@ GROUPS
        the captured substrings are "red king", "red", and "king", and are num-
        bered 1, 2, and 3, respectively.
 
-       The fact that plain parentheses fulfil  two  functions  is  not  always
-       helpful.   There are often times when grouping is required without cap-
-       turing. If an opening parenthesis is followed by a question mark and  a
-       colon,  the  group  does  not do any capturing, and is not counted when
-       computing the number of any subsequent capture groups. For example,  if
+       The  fact  that  plain  parentheses  fulfil two functions is not always
+       helpful.  There are often times when grouping is required without  cap-
+       turing.  If an opening parenthesis is followed by a question mark and a
+       colon, the group does not do any capturing, and  is  not  counted  when
+       computing  the number of any subsequent capture groups. For example, if
        the string "the white queen" is matched against the pattern
 
          the ((?:red|white) (king|queen))
@@ -7770,8 +8073,8 @@ GROUPS
          (?:(?i)saturday|sunday)
 
        match exactly the same set of strings. Because alternative branches are
-       tried  from  left  to right, and options are not reset until the end of
-       the group is reached, an option setting in one branch does affect  sub-
+       tried from left to right, and options are not reset until  the  end  of
+       the  group is reached, an option setting in one branch does affect sub-
        sequent branches, so the above patterns match "SUNDAY" as well as "Sat-
        urday".
 
@@ -7779,16 +8082,16 @@ GROUPS
 DUPLICATE GROUP NUMBERS
 
        Perl 5.10 introduced a feature whereby each alternative in a group uses
-       the  same  numbers  for  its capturing parentheses. Such a group starts
-       with (?| and is itself a non-capturing  group.  For  example,  consider
+       the same numbers for its capturing parentheses.  Such  a  group  starts
+       with  (?|  and  is  itself a non-capturing group. For example, consider
        this pattern:
 
          (?|(Sat)ur|(Sun))day
 
-       Because  the two alternatives are inside a (?| group, both sets of cap-
-       turing parentheses are numbered one. Thus, when  the  pattern  matches,
-       you  can  look  at captured substring number one, whichever alternative
-       matched. This construct is useful when you want to  capture  part,  but
+       Because the two alternatives are inside a (?| group, both sets of  cap-
+       turing  parentheses  are  numbered one. Thus, when the pattern matches,
+       you can look at captured substring number  one,  whichever  alternative
+       matched.  This  construct  is useful when you want to capture part, but
        not all, of one of a number of alternatives. Inside a (?| group, paren-
        theses are numbered as usual, but the number is reset at the  start  of
        each  branch.  The numbers of any capturing parentheses that follow the
@@ -7824,17 +8127,17 @@ DUPLICATE GROUP NUMBERS
 NAMED CAPTURE GROUPS
 
        Identifying capture groups by number is simple, but it can be very hard
-       to  keep  track of the numbers in complicated patterns. Furthermore, if
-       an expression is modified, the numbers may change. To  help  with  this
-       difficulty,  PCRE2  supports the naming of capture groups. This feature
-       was not added to Perl until release 5.10. Python had the  feature  ear-
-       lier,  and PCRE1 introduced it at release 4.0, using the Python syntax.
+       to keep track of the numbers in complicated patterns.  Furthermore,  if
+       an  expression  is  modified, the numbers may change. To help with this
+       difficulty, PCRE2 supports the naming of capture groups.  This  feature
+       was  not  added to Perl until release 5.10. Python had the feature ear-
+       lier, and PCRE1 introduced it at release 4.0, using the Python  syntax.
        PCRE2 supports both the Perl and the Python syntax.
 
-       In PCRE2,  a  capture  group  can  be  named  in  one  of  three  ways:
+       In  PCRE2,  a  capture  group  can  be  named  in  one  of  three ways:
        (?...) or (?'name'...) as in Perl, or (?P...) as in Python.
-       Names may be up to 32 code units long. When PCRE2_UTF is not set,  they
-       may  contain  only  ASCII  alphanumeric characters and underscores, but
+       Names may be up to 128 code units long. When PCRE2_UTF is not set, they
+       may contain only ASCII alphanumeric  characters  and  underscores,  but
        must start with a non-digit. When PCRE2_UTF is set, the syntax of group
        names is extended to allow any Unicode letter or Unicode decimal digit.
        In other words, group names must match one of these patterns:
@@ -7842,19 +8145,19 @@ NAMED CAPTURE GROUPS
          ^[_A-Za-z][_A-Za-z0-9]*\z   when PCRE2_UTF is not set
          ^[_\p{L}][_\p{L}\p{Nd}]*\z  when PCRE2_UTF is set
 
-       References to capture groups from other parts of the pattern,  such  as
-       backreferences,  recursion,  and conditions, can all be made by name as
+       References  to  capture groups from other parts of the pattern, such as
+       backreferences, recursion, and conditions, can all be made by  name  as
        well as by number.
 
        Named capture groups are allocated numbers as well as names, exactly as
        if  the  names were not present. In both PCRE2 and Perl, capture groups
        are primarily identified by numbers; any names  are  just  aliases  for
        these numbers. The PCRE2 API provides function calls for extracting the
-       complete name-to-number translation table from a compiled  pattern,  as
-       well  as  convenience  functions  for extracting captured substrings by
+       complete  name-to-number  translation table from a compiled pattern, as
+       well as convenience functions for  extracting  captured  substrings  by
        name.
 
-       Warning: When more than one capture group has the same number,  as  de-
+       Warning:  When  more than one capture group has the same number, as de-
        scribed in the previous section, a name given to one of them applies to
        all of them. Perl allows identically numbered groups to have  different
        names.  Consider this pattern, where there are two capture groups, both
@@ -7862,13 +8165,13 @@ NAMED CAPTURE GROUPS
 
          (?|(?aa)|(?bb))
 
-       Perl allows this, with both names AA and BB  as  aliases  of  group  1.
+       Perl  allows  this,  with  both  names AA and BB as aliases of group 1.
        Thus, after a successful match, both names yield the same value (either
        "aa" or "bb").
 
        In an attempt to reduce confusion, PCRE2 does not allow the same  group
        number to be associated with more than one name. The example above pro-
-       vokes a compile-time error. However, there is still  scope  for  confu-
+       vokes  a  compile-time  error. However, there is still scope for confu-
        sion. Consider this pattern:
 
          (?|(?aa)|(bb))
@@ -7903,13 +8206,13 @@ NAMED CAPTURE GROUPS
        The  convenience  functions for extracting the data by name returns the
        substring for the first (and in this example, the only) group  of  that
        name that matched. This saves searching to find which numbered group it
-       was. (An alternative way of solving this problem is to  use  a  "branch
+       was.  (An  alternative  way of solving this problem is to use a "branch
        reset" group, as described in the previous section.)
 
-       If  you make a backreference to a non-unique named group from elsewhere
-       in the pattern, the groups to which the name refers are checked in  the
-       order  in  which they appear in the overall pattern. The first one that
-       is set is used for the reference. For  example,  this  pattern  matches
+       If you make a backreference to a non-unique named group from  elsewhere
+       in  the pattern, the groups to which the name refers are checked in the
+       order in which they appear in the overall pattern. The first  one  that
+       is  set  is  used  for the reference. For example, this pattern matches
        both "foofoo" and "barbar" but not "foobar" or "barfoo":
 
          (?J)(?:(?foo)|(?bar))\k
@@ -7930,31 +8233,32 @@ NAMED CAPTURE GROUPS
 
 REPETITION
 
-       Repetition  is  specified  by  quantifiers, which can follow any of the
-       following items:
+       Repetition  is  specified  by  quantifiers, which may follow any one of
+       these items:
 
          a literal data character
          the dot metacharacter
          the \C escape sequence
          the \R escape sequence
          the \X escape sequence
-         an escape such as \d or \pL that matches a single character
+         any escape sequence that matches a single character
          a character class
          a backreference
          a parenthesized group (including lookaround assertions)
          a subroutine call (recursive or otherwise)
 
-       The general repetition quantifier specifies a minimum and maximum  num-
-       ber  of  permitted matches, by giving the two numbers in curly brackets
-       (braces), separated by a comma. The numbers must be  less  than  65536,
-       and the first must be less than or equal to the second. For example,
+       If a quantifier does not follow a repeatable item, an error occurs. The
+       general repetition quantifier specifies a minimum and maximum number of
+       permitted matches by giving two numbers  in  curly  brackets  (braces),
+       separated  by  a  comma.  The  numbers must be less than 65536, and the
+       first must be less than or equal to the second. For example,
 
          z{2,4}
 
-       matches  "zz",  "zzz",  or  "zzzz". A closing brace on its own is not a
-       special character. If the second number is omitted, but  the  comma  is
-       present,  there  is  no upper limit; if the second number and the comma
-       are both omitted, the quantifier specifies an exact number of  required
+       matches "zz", "zzz", or "zzzz". A closing brace on its  own  is  not  a
+       special  character.  If  the second number is omitted, but the comma is
+       present, there is no upper limit; if the second number  and  the  comma
+       are  both omitted, the quantifier specifies an exact number of required
        matches. Thus
 
          [aeiou]{3,}
@@ -7963,22 +8267,34 @@ REPETITION
 
          \d{8}
 
-       matches  exactly  8  digits. An opening curly bracket that appears in a
-       position where a quantifier is not allowed, or one that does not  match
-       the  syntax of a quantifier, is taken as a literal character. For exam-
-       ple, {,6} is not a quantifier, but a literal string of four characters.
+       matches exactly 8 digits. If the first number  is  omitted,  the  lower
+       limit is taken as zero; in this case the upper limit must be present.
+
+         X{,4} is interpreted as X{0,4}
+
+       This  is  a  change in behaviour that happened in Perl 5.34.0 and PCRE2
+       10.43. In earlier versions such a sequence was  not  interpreted  as  a
+       quantifier. Other regular expression engines may behave either way.
+
+       If  the characters that follow an opening brace do not match the syntax
+       of a quantifier, the brace is taken as a literal character. In particu-
+       lar, this means that {,} is a literal string of three characters.
+
+       Note that not every opening brace is potentially the start of a quanti-
+       fier because braces are used  in  other  items  such  as  \N{U+345}  or
+       \k{name}.
 
        In UTF modes, quantifiers apply to characters rather than to individual
        code  units. Thus, for example, \x{100}{2} matches two characters, each
        of which is represented by a two-byte sequence in a UTF-8 string. Simi-
-       larly,  \X{3} matches three Unicode extended grapheme clusters, each of
-       which may be several code units long (and  they  may  be  of  different
+       larly, \X{3} matches three Unicode extended grapheme clusters, each  of
+       which  may  be  several  code  units long (and they may be of different
        lengths).
 
        The quantifier {0} is permitted, causing the expression to behave as if
        the previous item and the quantifier were not present. This may be use-
-       ful  for  capture  groups that are referenced as subroutines from else-
-       where in the pattern (but see also the section entitled "Defining  cap-
+       ful for capture groups that are referenced as  subroutines  from  else-
+       where  in the pattern (but see also the section entitled "Defining cap-
        ture groups for use by reference only" below). Except for parenthesized
        groups, items that have a {0} quantifier are omitted from the  compiled
        pattern.
@@ -8005,12 +8321,12 @@ REPETITION
        quent item fails to match.
 
        By default, quantifiers are "greedy", that is, they match  as  much  as
-       possible (up to the maximum number of permitted times), without causing
-       the rest of the pattern to fail. The  classic  example  of  where  this
-       gives  problems is in trying to match comments in C programs. These ap-
-       pear between /* and */ and within the comment, individual * and / char-
-       acters  may appear. An attempt to match C comments by applying the pat-
-       tern
+       possible  (up  to the maximum number of permitted repetitions), without
+       causing the rest of the pattern to fail. The classic example  of  where
+       this gives problems is in trying to match comments in C programs. These
+       appear  between  /*  and  */ and within the comment, individual * and /
+       characters may appear. An attempt to match C comments by  applying  the
+       pattern
 
          /\*.*\*/
 
@@ -8018,18 +8334,18 @@ REPETITION
 
          /* first comment */  not comment  /* second comment */
 
-       fails, because it matches the entire string owing to the greediness  of
-       the  .*  item. However, if a quantifier is followed by a question mark,
+       fails,  because it matches the entire string owing to the greediness of
+       the .*  item. However, if a quantifier is followed by a question  mark,
        it ceases to be greedy, and instead matches the minimum number of times
        possible, so the pattern
 
          /\*.*?\*/
 
-       does  the  right  thing with the C comments. The meaning of the various
-       quantifiers is not otherwise changed,  just  the  preferred  number  of
-       matches.   Do  not  confuse this use of question mark with its use as a
-       quantifier in its own right. Because it has two uses, it can  sometimes
-       appear doubled, as in
+       does  the right thing with C comments. The meaning of the various quan-
+       tifiers is not otherwise changed, just the preferred number of matches.
+       Do not confuse this use of question mark with its use as  a  quantifier
+       in  its  own  right.   Because it has two uses, it can sometimes appear
+       doubled, as in
 
          \d??\d
 
@@ -8037,12 +8353,12 @@ REPETITION
        only way the rest of the pattern matches.
 
        If the PCRE2_UNGREEDY option is set (an option that is not available in
-       Perl),  the  quantifiers are not greedy by default, but individual ones
-       can be made greedy by following them with a  question  mark.  In  other
+       Perl), the quantifiers are not greedy by default, but  individual  ones
+       can  be  made  greedy  by following them with a question mark. In other
        words, it inverts the default behaviour.
 
-       When  a  parenthesized  group is quantified with a minimum repeat count
-       that is greater than 1 or with a limited maximum, more  memory  is  re-
+       When a parenthesized group is quantified with a  minimum  repeat  count
+       that  is  greater  than 1 or with a limited maximum, more memory is re-
        quired for the compiled pattern, in proportion to the size of the mini-
        mum or maximum.
 
@@ -8084,8 +8400,8 @@ REPETITION
          (tweedle[dume]{3}\s*)+
 
        has matched "tweedledum tweedledee" the value of the captured substring
-       is "tweedledee". However, if there are nested capture groups, the  cor-
-       responding  captured  values  may have been set in previous iterations.
+       is  "tweedledee". However, if there are nested capture groups, the cor-
+       responding captured values may have been set  in  previous  iterations.
        For example, after
 
          (a|(b))+
@@ -8095,15 +8411,15 @@ REPETITION
 
 ATOMIC GROUPING AND POSSESSIVE QUANTIFIERS
 
-       With both maximizing ("greedy") and minimizing ("ungreedy"  or  "lazy")
-       repetition,  failure  of what follows normally causes the repeated item
-       to be re-evaluated to see if a different number of repeats  allows  the
-       rest  of  the pattern to match. Sometimes it is useful to prevent this,
-       either to change the nature of the match, or to cause it  fail  earlier
-       than  it otherwise might, when the author of the pattern knows there is
+       With  both  maximizing ("greedy") and minimizing ("ungreedy" or "lazy")
+       repetition, failure of what follows normally causes the  repeated  item
+       to  be  re-evaluated to see if a different number of repeats allows the
+       rest of the pattern to match. Sometimes it is useful to  prevent  this,
+       either  to  change the nature of the match, or to cause it fail earlier
+       than it otherwise might, when the author of the pattern knows there  is
        no point in carrying on.
 
-       Consider, for example, the pattern \d+foo when applied to  the  subject
+       Consider,  for  example, the pattern \d+foo when applied to the subject
        line
 
          123456bar
@@ -8115,33 +8431,33 @@ ATOMIC GROUPING AND POSSESSIVE QUANTIFIERS
        the means for specifying that once a group has matched, it is not to be
        re-evaluated in this way.
 
-       If we use atomic grouping for the previous example, the  matcher  gives
-       up  immediately  on failing to match "foo" the first time. The notation
+       If  we  use atomic grouping for the previous example, the matcher gives
+       up immediately on failing to match "foo" the first time.  The  notation
        is a kind of special parenthesis, starting with (?> as in this example:
 
          (?>\d+)foo
 
-       Perl 5.28 introduced an experimental alphabetic form starting  with  (*
+       Perl  5.28  introduced an experimental alphabetic form starting with (*
        which may be easier to remember:
 
          (*atomic:\d+)foo
 
-       This  kind of parenthesized group "locks up" the part of the pattern it
+       This kind of parenthesized group "locks up" the part of the pattern  it
        contains once it has matched, and a failure further into the pattern is
        prevented  from  backtracking into it. Backtracking past it to previous
        items, however, works as normal.
 
        An alternative description is that a group of this type matches exactly
-       the  string  of  characters  that an identical standalone pattern would
+       the string of characters that an  identical  standalone  pattern  would
        match, if anchored at the current point in the subject string.
 
-       Atomic groups are not capture groups. Simple cases such  as  the  above
-       example  can be thought of as a maximizing repeat that must swallow ev-
-       erything it can.  So, while both \d+ and \d+? are  prepared  to  adjust
-       the  number  of digits they match in order to make the rest of the pat-
+       Atomic  groups  are  not capture groups. Simple cases such as the above
+       example can be thought of as a  maximizing  repeat  that  must  swallow
+       everything  it can.  So, while both \d+ and \d+? are prepared to adjust
+       the number of digits they match in order to make the rest of  the  pat-
        tern match, (?>\d+) can only match an entire sequence of digits.
 
-       Atomic groups in general can of course contain arbitrarily  complicated
+       Atomic  groups in general can of course contain arbitrarily complicated
        expressions, and can be nested. However, when the contents of an atomic
        group is just a single repeated item, as in the example above,  a  sim-
        pler  notation, called a "possessive quantifier" can be used. This con-
@@ -8155,15 +8471,15 @@ ATOMIC GROUPING AND POSSESSIVE QUANTIFIERS
 
          (abc|xyz){2,3}+
 
-       Possessive quantifiers are always greedy; the setting of the  PCRE2_UN-
-       GREEDY  option  is ignored. They are a convenient notation for the sim-
-       pler forms of atomic group. However, there  is  no  difference  in  the
-       meaning  of  a  possessive  quantifier and the equivalent atomic group,
-       though there may be a performance  difference;  possessive  quantifiers
+       Possessive  quantifiers are always greedy; the setting of the PCRE2_UN-
+       GREEDY option is ignored. They are a convenient notation for  the  sim-
+       pler  forms  of  atomic  group.  However, there is no difference in the
+       meaning of a possessive quantifier and  the  equivalent  atomic  group,
+       though  there  may  be a performance difference; possessive quantifiers
        should be slightly faster.
 
-       The  possessive  quantifier syntax is an extension to the Perl 5.8 syn-
-       tax.  Jeffrey Friedl originated the idea (and the name)  in  the  first
+       The possessive quantifier syntax is an extension to the Perl  5.8  syn-
+       tax.   Jeffrey  Friedl  originated the idea (and the name) in the first
        edition of his book. Mike McCloskey liked it, so implemented it when he
        built Sun's Java package, and PCRE1 copied it from there. It found  its
        way into Perl at release 5.10.
@@ -8205,7 +8521,7 @@ ATOMIC GROUPING AND POSSESSIVE QUANTIFIERS
 BACKREFERENCES
 
        Outside a character class, a backslash followed by a digit greater than
-       0  (and  possibly further digits) is a backreference to a capture group
+       0 (and possibly further digits) is a backreference to a  capture  group
        earlier (that is, to its left) in the pattern, provided there have been
        that many previous capture groups.
 
@@ -8213,7 +8529,7 @@ BACKREFERENCES
        it is always taken as a backreference, and  causes  an  error  only  if
        there  are not that many capture groups in the entire pattern. In other
        words, the group that is referenced need not be to the left of the ref-
-       erence  for numbers less than 8. A "forward backreference" of this type
+       erence for numbers less than 8. A "forward backreference" of this  type
        can make sense when a repetition is involved and the group to the right
        has participated in an earlier iteration.
 
@@ -8221,12 +8537,12 @@ BACKREFERENCES
        group whose number is 8 or more using this syntax  because  a  sequence
        such  as  \50  is  interpreted as a character defined in octal. See the
        subsection entitled "Non-printing characters" above for further details
-       of  the  handling of digits following a backslash. Other forms of back-
-       referencing do not suffer from this restriction. In  particular,  there
+       of the handling of digits following a backslash. Other forms  of  back-
+       referencing  do  not suffer from this restriction. In particular, there
        is no problem when named capture groups are used (see below).
 
-       Another  way  of  avoiding  the ambiguity inherent in the use of digits
-       following a backslash is to use the \g  escape  sequence.  This  escape
+       Another way of avoiding the ambiguity inherent in  the  use  of  digits
+       following  a  backslash  is  to use the \g escape sequence. This escape
        must be followed by a signed or unsigned number, optionally enclosed in
        braces. These examples are all identical:
 
@@ -8236,24 +8552,31 @@ BACKREFERENCES
 
        An unsigned number specifies an absolute reference without the  ambigu-
        ity that is present in the older syntax. It is also useful when literal
-       digits follow the reference. A signed number is a  relative  reference.
+       digits  follow  the reference. A signed number is a relative reference.
        Consider this example:
 
          (abc(def)ghi)\g{-1}
 
-       The sequence \g{-1} is a reference to the most recently started capture
-       group before \g, that is, is it equivalent to \2 in this example. Simi-
-       larly, \g{-2} would be equivalent to \1. The use of relative references
-       can be helpful in long patterns, and also in patterns that are  created
-       by  joining  together  fragments  that  contain references within them-
-       selves.
+       The sequence \g{-1} is a reference to the capture group whose number is
+       one less than the number of the next group to be started,  so  in  this
+       example  (where the next group would be numbered 3) is it equivalent to
+       \2, and \g{-2} would be equivalent to \1. Note that if  this  construct
+       is  inside  a capture group, that group is included in the count, so in
+       this example \g{-2} also refers to group 1:
+
+         (A)(\g{-2}B)
+
+       The use of relative references can be helpful  in  long  patterns,  and
+       also  in  patterns  that are created by joining together fragments that
+       contain references within themselves.
 
-       The sequence \g{+1} is a reference to the next capture group. This kind
-       of  forward  reference can be useful in patterns that repeat. Perl does
-       not support the use of + in this way.
+       The sequence \g{+1} is a reference to the next capture  group  that  is
+       started  after  this item, and \g{+2} refers to the one after that, and
+       so on. This kind of forward reference can be useful  in  patterns  that
+       repeat. Perl does not support the use of + in this way.
 
-       A backreference matches whatever actually  most  recently  matched  the
-       capture  group  in  the current subject string, rather than anything at
+       A  backreference  matches  whatever  actually most recently matched the
+       capture group in the current subject string, rather  than  anything  at
        all that matches the group (see "Groups as subroutines" below for a way
        of doing that). So the pattern
 
@@ -8270,10 +8593,11 @@ BACKREFERENCES
        original capture group is matched caselessly.
 
        There  are  several  different  ways of writing backreferences to named
-       capture groups. The .NET syntax \k{name} and the Perl  syntax  \k
-       or  \k'name'  are  supported,  as  is the Python syntax (?P=name). Perl
-       5.10's unified backreference syntax, in which \g can be used  for  both
-       numeric  and  named references, is also supported. We could rewrite the
+       capture groups. The .NET syntax  is  \k{name},  the  Python  syntax  is
+       (?=name),  and the original Perl syntax is \k or \k'name'. All of
+       these are now supported by both Perl and  PCRE2.  Perl  5.10's  unified
+       backreference  syntax,  in  which  \g  can be used for both numeric and
+       named references, is also supported by PCRE2.   We  could  rewrite  the
        above example in any of the following ways:
 
          (?(?i)rah)\s+\k
@@ -8281,16 +8605,16 @@ BACKREFERENCES
          (?P(?i)rah)\s+(?P=p1)
          (?(?i)rah)\s+\g{p1}
 
-       A capture group that is referenced by name may appear  in  the  pattern
+       A  capture  group  that is referenced by name may appear in the pattern
        before or after the reference.
 
-       There  may be more than one backreference to the same group. If a group
-       has not actually been used in a particular match, backreferences to  it
+       There may be more than one backreference to the same group. If a  group
+       has  not actually been used in a particular match, backreferences to it
        always fail by default. For example, the pattern
 
          (a|(bc))\2
 
-       always  fails  if  it starts to match "a" rather than "bc". However, if
+       always fails if it starts to match "a" rather than  "bc".  However,  if
        the PCRE2_MATCH_UNSET_BACKREF option is set at compile time, a backref-
        erence to an unset value matches an empty string.
 
@@ -8318,14 +8642,14 @@ BACKREFERENCES
        ple above, or by a quantifier with a minimum of zero.
 
        For versions of PCRE2 less than 10.25, backreferences of this type used
-       to  cause  the  group  that  they  reference to be treated as an atomic
-       group.  This restriction no longer applies, and backtracking into  such
+       to cause the group that they reference  to  be  treated  as  an  atomic
+       group.   This restriction no longer applies, and backtracking into such
        groups can occur as normal.
 
 
 ASSERTIONS
 
-       An  assertion  is  a  test on the characters following or preceding the
+       An assertion is a test on the characters  following  or  preceding  the
        current matching point that does not consume any characters. The simple
        assertions  coded  as  \b,  \B,  \A,  \G, \Z, \z, ^ and $ are described
        above.
@@ -8336,13 +8660,13 @@ ASSERTIONS
        sertion  may  be  positive (must match for the assertion to be true) or
        negative (must not match for the assertion to be  true).  An  assertion
        group is matched in the normal way, and if it is true, matching contin-
-       ues after it, but with the matching position in the subject string  re-
+       ues  after it, but with the matching position in the subject string re-
        set to what it was before the assertion was processed.
 
-       The  Perl-compatible  lookaround assertions are atomic. If an assertion
-       is true, but there is a subsequent matching failure, there is no  back-
-       tracking  into  the assertion. However, there are some cases where non-
-       atomic assertions can be useful. PCRE2 has some support for these,  de-
+       The Perl-compatible lookaround assertions are atomic. If  an  assertion
+       is  true, but there is a subsequent matching failure, there is no back-
+       tracking into the assertion. However, there are some cases  where  non-
+       atomic  assertions can be useful. PCRE2 has some support for these, de-
        scribed in the section entitled "Non-atomic assertions" below, but they
        are not Perl-compatible.
 
@@ -8361,32 +8685,32 @@ ASSERTIONS
        were captured are discarded (as happens with any  pattern  branch  that
        fails  to  match).  A  negative  assertion  is  true  only when all its
        branches fail to match; this means that no captured substrings are ever
-       retained  after a successful negative assertion. When an assertion con-
+       retained after a successful negative assertion. When an assertion  con-
        tains a matching branch, what happens depends on the type of assertion.
 
-       For a positive assertion, internally captured substrings  in  the  suc-
-       cessful  branch are retained, and matching continues with the next pat-
-       tern item after the assertion. For a  negative  assertion,  a  matching
-       branch  means  that  the assertion is not true. If such an assertion is
-       being used as a condition in a conditional group (see below),  captured
-       substrings  are  retained,  because  matching  continues  with the "no"
+       For  a  positive  assertion, internally captured substrings in the suc-
+       cessful branch are retained, and matching continues with the next  pat-
+       tern  item  after  the  assertion. For a negative assertion, a matching
+       branch means that the assertion is not true. If such  an  assertion  is
+       being  used as a condition in a conditional group (see below), captured
+       substrings are retained,  because  matching  continues  with  the  "no"
        branch of the condition. For other failing negative assertions, control
        passes to the previous backtracking point, thus discarding any captured
        strings within the assertion.
 
-       Most assertion groups may be repeated; though it makes no sense to  as-
+       Most  assertion groups may be repeated; though it makes no sense to as-
        sert the same thing several times, the side effect of capturing in pos-
        itive assertions may occasionally be useful. However, an assertion that
-       forms  the  condition  for  a  conditional group may not be quantified.
-       PCRE2 used to restrict the repetition of assertions, but  from  release
-       10.35  the  only restriction is that an unlimited maximum repetition is
-       changed to be one more than the minimum. For example, {3,}  is  treated
+       forms the condition for a conditional  group  may  not  be  quantified.
+       PCRE2  used  to restrict the repetition of assertions, but from release
+       10.35 the only restriction is that an unlimited maximum  repetition  is
+       changed  to  be one more than the minimum. For example, {3,} is treated
        as {3,4}.
 
    Alphabetic assertion names
 
-       Traditionally,  symbolic  sequences such as (?= and (?<= have been used
-       to specify lookaround assertions. Perl 5.28 introduced some  experimen-
+       Traditionally, symbolic sequences such as (?= and (?<= have  been  used
+       to  specify lookaround assertions. Perl 5.28 introduced some experimen-
        tal alphabetic alternatives which might be easier to remember. They all
        start with (* instead of (? and must be written using lower  case  let-
        ters. PCRE2 supports the following synonyms:
@@ -8407,24 +8731,24 @@ ASSERTIONS
 
          \w+(?=;)
 
-       matches a word followed by a semicolon, but does not include the  semi-
+       matches  a word followed by a semicolon, but does not include the semi-
        colon in the match, and
 
          foo(?!bar)
 
-       matches  any  occurrence  of  "foo" that is not followed by "bar". Note
+       matches any occurrence of "foo" that is not  followed  by  "bar".  Note
        that the apparently similar pattern
 
          (?!foo)bar
 
-       does not find an occurrence of "bar"  that  is  preceded  by  something
-       other  than "foo"; it finds any occurrence of "bar" whatsoever, because
+       does  not  find  an  occurrence  of "bar" that is preceded by something
+       other than "foo"; it finds any occurrence of "bar" whatsoever,  because
        the assertion (?!foo) is always true when the next three characters are
        "bar". A lookbehind assertion is needed to achieve the other effect.
 
        If you want to force a matching failure at some point in a pattern, the
-       most convenient way to do it is with (?!) because an empty  string  al-
-       ways  matches,  so  an assertion that requires there not to be an empty
+       most  convenient  way to do it is with (?!) because an empty string al-
+       ways matches, so an assertion that requires there not to  be  an  empty
        string must always fail.  The backtracking control verb (*FAIL) or (*F)
        is a synonym for (?!).
 
@@ -8436,63 +8760,56 @@ ASSERTIONS
          (? .*? \b\1\b ){2}
 
-       For a subject such as "word1 word2 word3 word2 word3 word4" the  result
-       is  "word3".  How does it work? At the start, ^(?x) anchors the pattern
+       For  a subject such as "word1 word2 word3 word2 word3 word4" the result
+       is "word3". How does it work? At the start, ^(?x) anchors  the  pattern
        and sets the "x" option, which causes white space (introduced for read-
        ability)  to  be  ignored. Inside the assertion, the greedy .* at first
        consumes the entire string, but then has to backtrack until the rest of
-       the  assertion can match a word, which is captured by group 1. In other
-       words, when the assertion first succeeds, it  captures  the  right-most
+       the assertion can match a word, which is captured by group 1. In  other
+       words,  when  the  assertion first succeeds, it captures the right-most
        word in the string.
 
-       The  current  matching point is then reset to the start of the subject,
-       and the rest of the pattern match checks for  two  occurrences  of  the
-       captured  word,  using  an  ungreedy .*? to scan from the left. If this
-       succeeds, we are done, but if the last word in the string does not  oc-
-       cur  twice,  this  part  of  the pattern fails. If a traditional atomic
-       lookhead (?= or (*pla: had been used, the assertion could not be re-en-
-       tered,  and  the whole match would fail. The pattern would succeed only
+       The current matching point is then reset to the start of  the  subject,
+       and  the  rest  of  the pattern match checks for two occurrences of the
+       captured word, using an ungreedy .*? to scan from  the  left.  If  this
+       succeeds,  we are done, but if the last word in the string does not oc-
+       cur twice, this part of the pattern  fails.  If  a  traditional  atomic
+       lookahead  (?=  or (*pla: had been used, the assertion could not be re-
+       entered, and the whole match would fail. The pattern would succeed only
        if the very last word in the subject was found twice.
 
        Using a non-atomic lookahead, however, means that when  the  last  word
@@ -8593,18 +8910,18 @@ NON-ATOMIC ASSERTIONS
        or all words have been tested.
 
        Two conditions must be met for a non-atomic assertion to be useful: the
-       contents of one or more capturing groups must change after a  backtrack
-       into  the  assertion,  and  there  must be a backreference to a changed
-       group later in the pattern. If this is not the case, the  rest  of  the
-       pattern  match  fails exactly as before because nothing has changed, so
+       contents  of one or more capturing groups must change after a backtrack
+       into the assertion, and there must be  a  backreference  to  a  changed
+       group  later  in  the pattern. If this is not the case, the rest of the
+       pattern match fails exactly as before because nothing has  changed,  so
        using a non-atomic assertion just wastes resources.
 
-       There is one exception to backtracking into a non-atomic assertion.  If
-       an  (*ACCEPT)  control verb is triggered, the assertion succeeds atomi-
-       cally. That is, a subsequent match failure cannot  backtrack  into  the
+       There  is one exception to backtracking into a non-atomic assertion. If
+       an (*ACCEPT) control verb is triggered, the assertion  succeeds  atomi-
+       cally.  That  is,  a subsequent match failure cannot backtrack into the
        assertion.
 
-       Non-atomic  assertions  are  not  supported by the alternative matching
+       Non-atomic assertions are not supported  by  the  alternative  matching
        function pcre2_dfa_match(). They are supported by JIT, but only if they
        do not contain any control verbs such as (*ACCEPT). (This may change in
        future). Note that assertions that appear as conditions for conditional
@@ -8620,19 +8937,19 @@ SCRIPT RUNS
        There is a full description of the rules that PCRE2 uses in the section
        entitled "Script Runs" in the pcre2unicode documentation.
 
-       If part of a pattern is enclosed between (*script_run: or (*sr:  and  a
-       closing  parenthesis,  it  fails  if the sequence of characters that it
-       matches are not a script run. After a failure, normal backtracking  oc-
-       curs.  Script runs can be used to detect spoofing attacks using charac-
-       ters that look the same, but are from  different  scripts.  The  string
-       "paypal.com"  is an infamous example, where the letters could be a mix-
+       If  part  of a pattern is enclosed between (*script_run: or (*sr: and a
+       closing parenthesis, it fails if the sequence  of  characters  that  it
+       matches  are not a script run. After a failure, normal backtracking oc-
+       curs. Script runs can be used to detect spoofing attacks using  charac-
+       ters  that  look  the  same, but are from different scripts. The string
+       "paypal.com" is an infamous example, where the letters could be a  mix-
        ture of Latin and Cyrillic. This pattern ensures that the matched char-
        acters in a sequence of non-spaces that follow white space are a script
        run:
 
          \s+(*sr:\S+)
 
-       To be sure that they are all from the Latin  script  (for  example),  a
+       To  be  sure  that  they are all from the Latin script (for example), a
        lookahead can be used:
 
          \s+(?=\p{Latin})(*sr:\S+)
@@ -8656,7 +8973,7 @@ SCRIPT RUNS
        Note that the atomic group is inside the script run. Putting it outside
        would not prevent backtracking into the script run pattern.
 
-       Support  for  script runs is not available if PCRE2 is compiled without
+       Support for script runs is not available if PCRE2 is  compiled  without
        Unicode support. A compile-time error is given if any of the above con-
        structs  is encountered. Script runs are not supported by the alternate
        matching function, pcre2_dfa_match() because they use the  same  mecha-
@@ -8671,16 +8988,16 @@ CONDITIONAL GROUPS
 
        It is possible to cause the matching process to obey a pattern fragment
        conditionally or to choose between two alternative fragments, depending
-       on  the result of an assertion, or whether a specific capture group has
+       on the result of an assertion, or whether a specific capture group  has
        already been matched. The two possible forms of conditional group are:
 
          (?(condition)yes-pattern)
          (?(condition)yes-pattern|no-pattern)
 
-       If the condition is satisfied, the yes-pattern is used;  otherwise  the
-       no-pattern  (if present) is used. An absent no-pattern is equivalent to
-       an empty string (it always matches). If there are more than two  alter-
-       natives  in the group, a compile-time error occurs. Each of the two al-
+       If  the  condition is satisfied, the yes-pattern is used; otherwise the
+       no-pattern (if present) is used. An absent no-pattern is equivalent  to
+       an  empty string (it always matches). If there are more than two alter-
+       natives in the group, a compile-time error occurs. Each of the two  al-
        ternatives may itself contain nested groups of any form, including con-
        ditional  groups;  the  restriction to two alternatives applies only at
        the level of the condition itself. This pattern fragment is an  example
@@ -8690,31 +9007,32 @@ CONDITIONAL GROUPS
 
 
        There are five kinds of condition: references to capture groups, refer-
-       ences to recursion, two pseudo-conditions called  DEFINE  and  VERSION,
+       ences  to  recursion,  two pseudo-conditions called DEFINE and VERSION,
        and assertions.
 
    Checking for a used capture group by number
 
-       If  the  text between the parentheses consists of a sequence of digits,
-       the condition is true if a capture group of that number has  previously
-       matched.  If  there is more than one capture group with the same number
-       (see the earlier section about duplicate group numbers), the  condition
-       is true if any of them have matched. An alternative notation is to pre-
-       cede the digits with a plus or minus sign. In this case, the group num-
-       ber  is relative rather than absolute. The most recently opened capture
-       group can be referenced by (?(-1), the next most recent by (?(-2),  and
-       so  on.  Inside  loops  it  can  also make sense to refer to subsequent
-       groups. The next capture group can be referenced as (?(+1), and so  on.
-       (The  value  zero in any of these forms is not used; it provokes a com-
-       pile-time error.)
-
-       Consider the following pattern, which  contains  non-significant  white
-       space  to  make it more readable (assume the PCRE2_EXTENDED option) and
+       If the text between the parentheses consists of a sequence  of  digits,
+       the  condition is true if a capture group of that number has previously
+       matched. If there is more than one capture group with the  same  number
+       (see  the earlier section about duplicate group numbers), the condition
+       is true if any of them have matched. An alternative notation, which  is
+       a PCRE2 extension, not supported by Perl, is to precede the digits with
+       a plus or minus sign. In this case, the group number is relative rather
+       than  absolute.  The most recently opened capture group (which could be
+       enclosing this condition) can be referenced by (?(-1),  the  next  most
+       recent by (?(-2), and so on. Inside loops it can also make sense to re-
+       fer  to  subsequent groups.  The next capture group to be opened can be
+       referenced as (?(+1), and so on. The value zero in any of  these  forms
+       is not used; it provokes a compile-time error.
+
+       Consider  the  following  pattern, which contains non-significant white
+       space to make it more readable (assume the PCRE2_EXTENDED  option)  and
        to divide it into three parts for ease of discussion:
 
          ( \( )?    [^()]+    (?(1) \) )
 
-       The first part matches an optional opening  parenthesis,  and  if  that
+       The  first  part  matches  an optional opening parenthesis, and if that
        character is present, sets it as the first captured substring. The sec-
        ond part matches one or more characters that are not  parentheses.  The
        third  part  is a conditional group that tests whether or not the first
@@ -8722,60 +9040,60 @@ CONDITIONAL GROUPS
        opening  parenthesis,  the condition is true, and so the yes-pattern is
        executed and a closing parenthesis is required.  Otherwise,  since  no-
        pattern is not present, the conditional group matches nothing. In other
-       words, this pattern matches a sequence of  non-parentheses,  optionally
+       words,  this  pattern matches a sequence of non-parentheses, optionally
        enclosed in parentheses.
 
-       If  you  were  embedding  this pattern in a larger one, you could use a
+       If you were embedding this pattern in a larger one,  you  could  use  a
        relative reference:
 
          ...other stuff... ( \( )?    [^()]+    (?(-1) \) ) ...
 
-       This makes the fragment independent of the parentheses  in  the  larger
+       This  makes  the  fragment independent of the parentheses in the larger
        pattern.
 
    Checking for a used capture group by name
 
-       Perl  uses  the  syntax  (?()...) or (?('name')...) to test for a
-       used capture group by name. For compatibility with earlier versions  of
-       PCRE1,  which had this facility before Perl, the syntax (?(name)...) is
-       also recognized.  Note, however, that undelimited names  consisting  of
-       the  letter  R followed by digits are ambiguous (see the following sec-
+       Perl uses the syntax (?()...) or (?('name')...)  to  test  for  a
+       used  capture group by name. For compatibility with earlier versions of
+       PCRE1, which had this facility before Perl, the syntax (?(name)...)  is
+       also  recognized.   Note, however, that undelimited names consisting of
+       the letter R followed by digits are ambiguous (see the  following  sec-
        tion). Rewriting the above example to use a named group gives this:
 
          (? \( )?    [^()]+    (?() \) )
 
-       If the name used in a condition of this kind is a duplicate,  the  test
-       is  applied  to  all groups of the same name, and is true if any one of
+       If  the  name used in a condition of this kind is a duplicate, the test
+       is applied to all groups of the same name, and is true if  any  one  of
        them has matched.
 
    Checking for pattern recursion
 
-       "Recursion" in this sense refers to any subroutine-like call  from  one
-       part  of  the  pattern to another, whether or not it is actually recur-
-       sive. See the sections entitled "Recursive  patterns"  and  "Groups  as
+       "Recursion"  in  this sense refers to any subroutine-like call from one
+       part of the pattern to another, whether or not it  is  actually  recur-
+       sive.  See  the  sections  entitled "Recursive patterns" and "Groups as
        subroutines" below for details of recursion and subroutine calls.
 
-       If  a  condition  is the string (R), and there is no capture group with
-       the name R, the condition is true if matching is currently in a  recur-
-       sion  or  subroutine call to the whole pattern or any capture group. If
-       digits follow the letter R, and there is no group with that  name,  the
-       condition  is  true  if  the  most recent call is into a group with the
-       given number, which must exist somewhere in the overall  pattern.  This
+       If a condition is the string (R), and there is no  capture  group  with
+       the  name R, the condition is true if matching is currently in a recur-
+       sion or subroutine call to the whole pattern or any capture  group.  If
+       digits  follow  the letter R, and there is no group with that name, the
+       condition is true if the most recent call is  into  a  group  with  the
+       given  number,  which must exist somewhere in the overall pattern. This
        is a contrived example that is equivalent to a+b:
 
          ((?(R1)a+|(?1)b))
 
-       However,  in  both  cases,  if there is a capture group with a matching
-       name, the condition tests for its being set, as described in  the  sec-
-       tion  above,  instead of testing for recursion. For example, creating a
-       group with the name R1 by adding (?)  to  the  above  pattern  com-
+       However, in both cases, if there is a capture  group  with  a  matching
+       name,  the  condition tests for its being set, as described in the sec-
+       tion above, instead of testing for recursion. For example,  creating  a
+       group  with  the  name  R1  by adding (?) to the above pattern com-
        pletely changes its meaning.
 
        If a name preceded by ampersand follows the letter R, for example:
 
          (?(R&name)...)
 
-       the  condition  is true if the most recent recursion is into a group of
+       the condition is true if the most recent recursion is into a  group  of
        that name (which must exist within the pattern).
 
        This condition does not check the entire recursion stack. It tests only
@@ -8788,7 +9106,7 @@ CONDITIONAL GROUPS
    Defining capture groups for use by reference only
 
        If the condition is the string (DEFINE), the condition is always false,
-       even if there is a group with the name DEFINE. In this case, there  may
+       even  if there is a group with the name DEFINE. In this case, there may
        be only one alternative in the rest of the conditional group. It is al-
        ways skipped if control reaches this point in the pattern; the idea  of
        DEFINE  is that it can be used to define subroutines that can be refer-
@@ -8814,34 +9132,34 @@ CONDITIONAL GROUPS
        that do not have access to the underlying code cannot do this.  A  spe-
        cial  "condition" called VERSION exists to allow such users to discover
        which version of PCRE2 they are dealing with by using this condition to
-       match  a string such as "yesno". VERSION must be followed either by "="
+       match a string such as "yesno". VERSION must be followed either by  "="
        or ">=" and a version number.  For example:
 
          (?(VERSION>=10.4)yes|no)
 
-       This pattern matches "yes" if the PCRE2 version is greater or equal  to
-       10.4,  or "no" otherwise. The fractional part of the version number may
+       This  pattern matches "yes" if the PCRE2 version is greater or equal to
+       10.4, or "no" otherwise. The fractional part of the version number  may
        not contain more than two digits.
 
    Assertion conditions
 
-       If the condition is not in any of the  above  formats,  it  must  be  a
-       parenthesized  assertion.  This may be a positive or negative lookahead
-       or lookbehind assertion. However, it must be a traditional  atomic  as-
-       sertion, not one of the PCRE2-specific non-atomic assertions.
+       If  the  condition  is  not  in  any of the above formats, it must be a
+       parenthesized assertion. This may be a positive or  negative  lookahead
+       or  lookbehind  assertion. However, it must be a traditional atomic as-
+       sertion, not one of the non-atomic assertions.
 
-       Consider  this  pattern,  again containing non-significant white space,
+       Consider this pattern, again containing  non-significant  white  space,
        and with the two alternatives on the second line:
 
          (?(?=[^a-z]*[a-z])
          \d{2}-[a-z]{3}-\d{2}  |  \d{2}-\d{2}-\d{2} )
 
-       The condition is a positive lookahead assertion  that  matches  an  op-
+       The  condition  is  a  positive lookahead assertion that matches an op-
        tional sequence of non-letters followed by a letter. In other words, it
        tests for the presence of at least one letter in the subject. If a let-
-       ter  is  found,  the  subject is matched against the first alternative;
-       otherwise it is  matched  against  the  second.  This  pattern  matches
-       strings  in  one  of the two forms dd-aaa-dd or dd-dd-dd, where aaa are
+       ter is found, the subject is matched  against  the  first  alternative;
+       otherwise  it  is  matched  against  the  second.  This pattern matches
+       strings in one of the two forms dd-aaa-dd or dd-dd-dd,  where  aaa  are
        letters and dd are digits.
 
        When an assertion that is a condition contains capture groups, any cap-
@@ -8855,39 +9173,39 @@ CONDITIONAL GROUPS
 COMMENTS
 
        There are two ways of including comments in patterns that are processed
-       by PCRE2. In both cases, the start of the comment  must  not  be  in  a
-       character  class,  nor  in  the middle of any other sequence of related
-       characters such as (?: or a group name or number. The  characters  that
+       by  PCRE2.  In  both  cases,  the start of the comment must not be in a
+       character class, nor in the middle of any  other  sequence  of  related
+       characters  such  as (?: or a group name or number. The characters that
        make up a comment play no part in the pattern matching.
 
-       The  sequence (?# marks the start of a comment that continues up to the
-       next closing parenthesis. Nested parentheses are not permitted. If  the
-       PCRE2_EXTENDED  or  PCRE2_EXTENDED_MORE  option  is set, an unescaped #
-       character also introduces a comment, which in this  case  continues  to
-       immediately  after  the next newline character or character sequence in
+       The sequence (?# marks the start of a comment that continues up to  the
+       next  closing parenthesis. Nested parentheses are not permitted. If the
+       PCRE2_EXTENDED or PCRE2_EXTENDED_MORE option is  set,  an  unescaped  #
+       character  also  introduces  a comment, which in this case continues to
+       immediately after the next newline character or character  sequence  in
        the pattern. Which characters are interpreted as newlines is controlled
        by  an option passed to the compiling function or by a special sequence
        at the start of the pattern, as described in the section entitled "New-
        line conventions" above. Note that the end of this type of comment is a
        literal newline sequence in the pattern; escape sequences  that  happen
        to represent a newline do not count. For example, consider this pattern
-       when PCRE2_EXTENDED is set, and the default newline convention (a  sin-
+       when  PCRE2_EXTENDED is set, and the default newline convention (a sin-
        gle linefeed character) is in force:
 
          abc #comment \n still comment
 
-       On  encountering  the # character, pcre2_compile() skips along, looking
-       for a newline in the pattern. The sequence \n is still literal at  this
-       stage,  so  it does not terminate the comment. Only an actual character
+       On encountering the # character, pcre2_compile() skips  along,  looking
+       for  a newline in the pattern. The sequence \n is still literal at this
+       stage, so it does not terminate the comment. Only an  actual  character
        with the code value 0x0a (the default newline) does so.
 
 
 RECURSIVE PATTERNS
 
-       Consider the problem of matching a string in parentheses, allowing  for
-       unlimited  nested  parentheses.  Without the use of recursion, the best
-       that can be done is to use a pattern that  matches  up  to  some  fixed
-       depth  of  nesting.  It  is not possible to handle an arbitrary nesting
+       Consider  the problem of matching a string in parentheses, allowing for
+       unlimited nested parentheses. Without the use of  recursion,  the  best
+       that  can  be  done  is  to use a pattern that matches up to some fixed
+       depth of nesting. It is not possible to  handle  an  arbitrary  nesting
        depth.
 
        For some time, Perl has provided a facility that allows regular expres-
@@ -8914,13 +9232,13 @@ RECURSIVE PATTERNS
        scribed in the next section.) The special item (?R) or (?0) is a recur-
        sive call of the entire regular expression.
 
-       This PCRE2 pattern solves the nested parentheses  problem  (assume  the
+       This  PCRE2  pattern  solves the nested parentheses problem (assume the
        PCRE2_EXTENDED option is set so that white space is ignored):
 
          \( ( [^()]++ | (?R) )* \)
 
-       First  it matches an opening parenthesis. Then it matches any number of
-       substrings which can either be a sequence of non-parentheses, or a  re-
+       First it matches an opening parenthesis. Then it matches any number  of
+       substrings  which can either be a sequence of non-parentheses, or a re-
        cursive match of the pattern itself (that is, a correctly parenthesized
        substring).  Finally there is a closing parenthesis. Note the use of  a
        possessive  quantifier  to  avoid  backtracking  into sequences of non-
@@ -8937,12 +9255,12 @@ RECURSIVE PATTERNS
        In a larger pattern,  keeping  track  of  parenthesis  numbers  can  be
        tricky.  This is made easier by the use of relative references. Instead
        of (?1) in the pattern above you can write (?-2) to refer to the second
-       most  recently  opened  parentheses  preceding  the recursion. In other
-       words, a negative number counts capturing  parentheses  leftwards  from
+       most recently opened parentheses  preceding  the  recursion.  In  other
+       words,  a  negative  number counts capturing parentheses leftwards from
        the point at which it is encountered.
 
-       Be  aware  however, that if duplicate capture group numbers are in use,
-       relative references refer to the earliest group  with  the  appropriate
+       Be aware however, that if duplicate capture group numbers are  in  use,
+       relative  references  refer  to the earliest group with the appropriate
        number. Consider, for example:
 
          (?|(a)|(b)) (c) (?-2)
@@ -8951,17 +9269,17 @@ RECURSIVE PATTERNS
        (c) is number 2. When the reference (?-2) is  encountered,  the  second
        most  recently opened parentheses has the number 1, but it is the first
        such group (the (a) group) to which the recursion refers. This would be
-       the  same if an absolute reference (?1) was used. In other words, rela-
+       the same if an absolute reference (?1) was used. In other words,  rela-
        tive references are just a shorthand for computing a group number.
 
-       It is also possible to refer to subsequent capture groups,  by  writing
-       references  such  as  (?+2). However, these cannot be recursive because
-       the reference is not inside the parentheses that are  referenced.  They
-       are  always  non-recursive  subroutine  calls, as described in the next
+       It  is  also possible to refer to subsequent capture groups, by writing
+       references such as (?+2). However, these cannot  be  recursive  because
+       the  reference  is not inside the parentheses that are referenced. They
+       are always non-recursive subroutine calls, as  described  in  the  next
        section.
 
-       An alternative approach is to use named parentheses.  The  Perl  syntax
-       for  this  is  (?&name);  PCRE1's earlier syntax (?P>name) is also sup-
+       An  alternative  approach  is to use named parentheses. The Perl syntax
+       for this is (?&name); PCRE1's earlier syntax  (?P>name)  is  also  sup-
        ported. We could rewrite the above example as follows:
 
          (? \( ( [^()]++ | (?&pn) )* \) )
@@ -8970,19 +9288,19 @@ RECURSIVE PATTERNS
        used.
 
        The example pattern that we have been looking at contains nested unlim-
-       ited repeats, and so the use of a possessive  quantifier  for  matching
-       strings  of  non-parentheses  is important when applying the pattern to
+       ited  repeats,  and  so the use of a possessive quantifier for matching
+       strings of non-parentheses is important when applying  the  pattern  to
        strings that do not match. For example, when this pattern is applied to
 
          (aaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaa()
 
-       it yields "no match" quickly. However, if a  possessive  quantifier  is
-       not  used, the match runs for a very long time indeed because there are
-       so many different ways the + and * repeats can carve  up  the  subject,
+       it  yields  "no  match" quickly. However, if a possessive quantifier is
+       not used, the match runs for a very long time indeed because there  are
+       so  many  different  ways the + and * repeats can carve up the subject,
        and all have to be tested before failure can be reported.
 
-       At  the  end  of a match, the values of capturing parentheses are those
-       from the outermost level. If you want to obtain intermediate values,  a
+       At the end of a match, the values of capturing  parentheses  are  those
+       from  the outermost level. If you want to obtain intermediate values, a
        callout function can be used (see below and the pcre2callout documenta-
        tion). If the pattern above is matched against
 
@@ -9019,8 +9337,8 @@ RECURSIVE PATTERNS
 
        Starting  with  release 10.30, recursive subroutine calls are no longer
        treated as atomic. That is, they can be re-entered to try unused alter-
-       natives  if  there  is a matching failure later in the pattern. This is
-       now compatible with the way Perl works. If you want a  subroutine  call
+       natives if there is a matching failure later in the  pattern.  This  is
+       now  compatible  with the way Perl works. If you want a subroutine call
        to be atomic, you must explicitly enclose it in an atomic group.
 
        Supporting backtracking into recursions simplifies certain types of re-
@@ -9033,14 +9351,14 @@ RECURSIVE PATTERNS
        when there are an even number of characters, but in order  to  work  it
        has  to  be  able  to  try the second case when the rest of the pattern
        match fails. If you want to match typical palindromic phrases, the pat-
-       tern  has  to  ignore  all  non-word characters, which can be done like
+       tern has to ignore all non-word characters,  which  can  be  done  like
        this:
 
          ^\W*+((.)\W*+(?1)\W*+\2|\W*+.?)\W*+$
 
-       If run with the PCRE2_CASELESS option,  this  pattern  matches  phrases
-       such  as "A man, a plan, a canal: Panama!". Note the use of the posses-
-       sive quantifier *+ to avoid backtracking  into  sequences  of  non-word
+       If  run  with  the  PCRE2_CASELESS option, this pattern matches phrases
+       such as "A man, a plan, a canal: Panama!". Note the use of the  posses-
+       sive  quantifier  *+  to  avoid backtracking into sequences of non-word
        characters. Without this, PCRE2 takes a great deal longer (ten times or
        more) to match typical phrases, and Perl takes so long that  you  think
        it has gone into a loop.
@@ -9049,27 +9367,27 @@ RECURSIVE PATTERNS
        processing is in the handling of captured  values.  Formerly  in  Perl,
        when  a  group  was called recursively or as a subroutine (see the next
        section), it had no access to any values that were captured outside the
-       recursion,  whereas  in  PCRE2 these values can be referenced. Consider
+       recursion, whereas in PCRE2 these values can  be  referenced.  Consider
        this pattern:
 
          ^(.)(\1|a(?2))
 
-       This pattern matches "bab". The first capturing parentheses match  "b",
+       This  pattern matches "bab". The first capturing parentheses match "b",
        then in the second group, when the backreference \1 fails to match "b",
        the second alternative matches "a" and then recurses. In the recursion,
-       \1  does now match "b" and so the whole match succeeds. This match used
+       \1 does now match "b" and so the whole match succeeds. This match  used
        to fail in Perl, but in later versions (I tried 5.024) it now works.
 
 
 GROUPS AS SUBROUTINES
 
-       If the syntax for a recursive group call (either by number or by  name)
-       is  used  outside the parentheses to which it refers, it operates a bit
-       like a subroutine in a programming  language.  More  accurately,  PCRE2
+       If  the syntax for a recursive group call (either by number or by name)
+       is used outside the parentheses to which it refers, it operates  a  bit
+       like  a  subroutine  in  a programming language. More accurately, PCRE2
        treats the referenced group as an independent subpattern which it tries
        to match at the current matching position. The called group may be  de-
-       fined  before or after the reference. A numbered reference can be abso-
-       lute or relative, as in these examples:
+       fined  before  or  after the reference. A numbered reference can be ab-
+       solute or relative, as in these examples:
 
          (...(absolute)...)...(?2)...
          (...(relative)...)...(?-1)...
@@ -9109,22 +9427,22 @@ GROUPS AS SUBROUTINES
 
 ONIGURUMA SUBROUTINE SYNTAX
 
-       For  compatibility with Oniguruma, the non-Perl syntax \g followed by a
+       For compatibility with Oniguruma, the non-Perl syntax \g followed by  a
        name or a number enclosed either in angle brackets or single quotes, is
        an alternative syntax for calling a group as a subroutine, possibly re-
-       cursively. Here are two of the examples  used  above,  rewritten  using
+       cursively.  Here  are  two  of the examples used above, rewritten using
        this syntax:
 
          (? \( ( (?>[^()]+) | \g )* \) )
          (sens|respons)e and \g'1'ibility
 
-       PCRE2  supports an extension to Oniguruma: if a number is preceded by a
+       PCRE2 supports an extension to Oniguruma: if a number is preceded by  a
        plus or a minus sign it is taken as a relative reference. For example:
 
          (abc)(?i:\g<-1>)
 
-       Note that \g{...} (Perl syntax) and \g<...> (Oniguruma syntax) are  not
-       synonymous.  The  former is a backreference; the latter is a subroutine
+       Note  that \g{...} (Perl syntax) and \g<...> (Oniguruma syntax) are not
+       synonymous. The former is a backreference; the latter is  a  subroutine
        call.
 
 
@@ -9144,13 +9462,13 @@ CALLOUTS
        passed, or if the callout entry point is set to NULL, callouts are dis-
        abled.
 
-       Within a regular expression, (?C) indicates a point at  which  the
-       external  function  is  to  be  called. There are two kinds of callout:
-       those with a numerical argument and those with a string argument.  (?C)
-       on  its  own with no argument is treated as (?C0). A numerical argument
-       allows the  application  to  distinguish  between  different  callouts.
-       String  arguments  were added for release 10.20 to make it possible for
-       script languages that use PCRE2 to embed short scripts within  patterns
+       Within  a  regular expression, (?C) indicates a point at which the
+       external function is to be called. There  are  two  kinds  of  callout:
+       those  with a numerical argument and those with a string argument. (?C)
+       on its own with no argument is treated as (?C0). A  numerical  argument
+       allows  the  application  to  distinguish  between  different callouts.
+       String arguments were added for release 10.20 to make it  possible  for
+       script  languages that use PCRE2 to embed short scripts within patterns
        in a similar way to Perl.
 
        During matching, when PCRE2 reaches a callout point, the external func-
@@ -9159,24 +9477,24 @@ CALLOUTS
        also set in the match block. The callout function may cause matching to
        proceed, to backtrack, or to fail.
 
-       By  default,  PCRE2  implements  a  number of optimizations at matching
-       time, and one side-effect is that sometimes callouts  are  skipped.  If
-       you  need all possible callouts to happen, you need to set options that
-       disable the relevant optimizations. More details, including a  complete
-       description  of  the programming interface to the callout function, are
+       By default, PCRE2 implements a  number  of  optimizations  at  matching
+       time,  and  one  side-effect is that sometimes callouts are skipped. If
+       you need all possible callouts to happen, you need to set options  that
+       disable  the relevant optimizations. More details, including a complete
+       description of the programming interface to the callout  function,  are
        given in the pcre2callout documentation.
 
    Callouts with numerical arguments
 
-       If you just want to have  a  means  of  identifying  different  callout
-       points,  put  a  number  less than 256 after the letter C. For example,
+       If  you  just  want  to  have  a means of identifying different callout
+       points, put a number less than 256 after the  letter  C.  For  example,
        this pattern has two callout points:
 
          (?C1)abc(?C2)def
 
-       If the PCRE2_AUTO_CALLOUT flag is passed to pcre2_compile(),  numerical
-       callouts  are  automatically installed before each item in the pattern.
-       They are all numbered 255. If there is a conditional group in the  pat-
+       If  the PCRE2_AUTO_CALLOUT flag is passed to pcre2_compile(), numerical
+       callouts are automatically installed before each item in  the  pattern.
+       They  are all numbered 255. If there is a conditional group in the pat-
        tern whose condition is an assertion, an additional callout is inserted
        just before the condition. An explicit callout may also be set at  this
        position, as in this example:
@@ -9188,8 +9506,8 @@ CALLOUTS
 
    Callouts with string arguments
 
-       A delimited string may be used instead of a number as a  callout  argu-
-       ment.  The  starting  delimiter  must be one of ` ' " ^ % # $ { and the
+       A  delimited  string may be used instead of a number as a callout argu-
+       ment. The starting delimiter must be one of ` ' " ^ % #  $  {  and  the
        ending delimiter is the same as the start, except for {, where the end-
        ing  delimiter  is  }.  If  the  ending  delimiter is needed within the
        string, it must be doubled. For example:
@@ -9206,10 +9524,10 @@ BACKTRACKING CONTROL
        Perl's terminology) that modify the behaviour  of  backtracking  during
        matching.  They are generally of the form (*VERB) or (*VERB:NAME). Some
        verbs take either form, and may behave differently depending on whether
-       or  not  a  name  argument is present. The names are not required to be
+       or not a name argument is present. The names are  not  required  to  be
        unique within the pattern.
 
-       By default, for compatibility with Perl, a  name  is  any  sequence  of
+       By  default,  for  compatibility  with  Perl, a name is any sequence of
        characters that does not include a closing parenthesis. The name is not
        processed in any way, and it is  not  possible  to  include  a  closing
        parenthesis   in  the  name.   This  can  be  changed  by  setting  the
@@ -9223,22 +9541,22 @@ BACKTRACKING CONTROL
        acter type escapes such as \d are faulted.
 
        A closing parenthesis can be included in a name either as \) or between
-       \Q and \E. In addition to backslash processing, if  the  PCRE2_EXTENDED
+       \Q  and  \E. In addition to backslash processing, if the PCRE2_EXTENDED
        or PCRE2_EXTENDED_MORE option is also set, unescaped whitespace in verb
        names is skipped, and #-comments are recognized, exactly as in the rest
-       of  the  pattern.  PCRE2_EXTENDED and PCRE2_EXTENDED_MORE do not affect
+       of the pattern.  PCRE2_EXTENDED and PCRE2_EXTENDED_MORE do  not  affect
        verb names unless PCRE2_ALT_VERBNAMES is also set.
 
-       The maximum length of a name is 255 in the 8-bit library and  65535  in
-       the  16-bit and 32-bit libraries. If the name is empty, that is, if the
-       closing parenthesis immediately follows the colon, the effect is as  if
+       The  maximum  length of a name is 255 in the 8-bit library and 65535 in
+       the 16-bit and 32-bit libraries. If the name is empty, that is, if  the
+       closing  parenthesis immediately follows the colon, the effect is as if
        the colon were not there. Any number of these verbs may occur in a pat-
        tern. Except for (*ACCEPT), they may not be quantified.
 
        Since these verbs are specifically related  to  backtracking,  most  of
        them  can be used only when the pattern is to be matched using the tra-
        ditional matching function, because that uses a backtracking algorithm.
-       With  the  exception  of (*FAIL), which behaves like a failing negative
+       With the exception of (*FAIL), which behaves like  a  failing  negative
        assertion, the backtracking control verbs cause an error if encountered
        by the DFA matching function.
 
@@ -9252,14 +9570,14 @@ BACKTRACKING CONTROL
        running some checks at the start of each match attempt. For example, it
        may  know  the minimum length of matching subject, or that a particular
        character must be present. When one of these optimizations bypasses the
-       running  of  a  match,  any  included  backtracking  verbs will not, of
+       running of a match,  any  included  backtracking  verbs  will  not,  of
        course, be processed. You can suppress the start-of-match optimizations
        by  setting  the PCRE2_NO_START_OPTIMIZE option when calling pcre2_com-
        pile(), or by starting the pattern with (*NO_START_OPT). There is  more
        discussion of this option in the section entitled "Compiling a pattern"
        in the pcre2api documentation.
 
-       Experiments with Perl suggest that it too  has  similar  optimizations,
+       Experiments  with  Perl  suggest that it too has similar optimizations,
        and like PCRE2, turning them off can change the result of a match.
 
    Verbs that act immediately
@@ -9268,70 +9586,70 @@ BACKTRACKING CONTROL
 
           (*ACCEPT) or (*ACCEPT:NAME)
 
-       This  verb causes the match to end successfully, skipping the remainder
-       of the pattern. However, when it is inside  a  capture  group  that  is
+       This verb causes the match to end successfully, skipping the  remainder
+       of  the  pattern.  However,  when  it is inside a capture group that is
        called as a subroutine, only that group is ended successfully. Matching
        then continues at the outer level. If (*ACCEPT) in triggered in a posi-
-       tive  assertion,  the  assertion succeeds; in a negative assertion, the
+       tive assertion, the assertion succeeds; in a  negative  assertion,  the
        assertion fails.
 
-       If (*ACCEPT) is inside capturing parentheses, the data so far  is  cap-
+       If  (*ACCEPT)  is inside capturing parentheses, the data so far is cap-
        tured. For example:
 
          A((?:A|B(*ACCEPT)|C)D)
 
-       This  matches  "AB", "AAD", or "ACD"; when it matches "AB", "B" is cap-
+       This matches "AB", "AAD", or "ACD"; when it matches "AB", "B"  is  cap-
        tured by the outer parentheses.
 
-       (*ACCEPT) is the only backtracking verb that is allowed to  be  quanti-
-       fied  because  an  ungreedy  quantification with a minimum of zero acts
+       (*ACCEPT)  is  the only backtracking verb that is allowed to be quanti-
+       fied because an ungreedy quantification with a  minimum  of  zero  acts
        only when a backtrack happens. Consider, for example,
 
          (A(*ACCEPT)??B)C
 
-       where A, B, and C may be complex expressions. After matching  "A",  the
-       matcher  processes  "BC"; if that fails, causing a backtrack, (*ACCEPT)
-       is triggered and the match succeeds. In both cases, all but C  is  cap-
-       tured.  Whereas  (*COMMIT) (see below) means "fail on backtrack", a re-
+       where  A,  B, and C may be complex expressions. After matching "A", the
+       matcher processes "BC"; if that fails, causing a  backtrack,  (*ACCEPT)
+       is  triggered  and the match succeeds. In both cases, all but C is cap-
+       tured. Whereas (*COMMIT) (see below) means "fail on backtrack",  a  re-
        peated (*ACCEPT) of this type means "succeed on backtrack".
 
-       Warning: (*ACCEPT) should not be used within a script  run  group,  be-
-       cause  it causes an immediate exit from the group, bypassing the script
+       Warning:  (*ACCEPT)  should  not be used within a script run group, be-
+       cause it causes an immediate exit from the group, bypassing the  script
        run checking.
 
          (*FAIL) or (*FAIL:NAME)
 
-       This verb causes a matching failure, forcing backtracking to occur.  It
-       may  be  abbreviated  to  (*F).  It is equivalent to (?!) but easier to
+       This  verb causes a matching failure, forcing backtracking to occur. It
+       may be abbreviated to (*F). It is equivalent  to  (?!)  but  easier  to
        read. The Perl documentation notes that it is probably useful only when
        combined with (?{}) or (??{}). Those are, of course, Perl features that
-       are not present in PCRE2. The nearest equivalent is  the  callout  fea-
+       are  not  present  in PCRE2. The nearest equivalent is the callout fea-
        ture, as for example in this pattern:
 
          a+(?C)(*FAIL)
 
-       A  match  with the string "aaaa" always fails, but the callout is taken
+       A match with the string "aaaa" always fails, but the callout  is  taken
        before each backtrack happens (in this example, 10 times).
 
-       (*ACCEPT:NAME) and (*FAIL:NAME) behave the  same  as  (*MARK:NAME)(*AC-
-       CEPT)  and  (*MARK:NAME)(*FAIL),  respectively,  that  is, a (*MARK) is
+       (*ACCEPT:NAME)  and  (*FAIL:NAME)  behave the same as (*MARK:NAME)(*AC-
+       CEPT) and (*MARK:NAME)(*FAIL), respectively,  that  is,  a  (*MARK)  is
        recorded just before the verb acts.
 
    Recording which path was taken
 
-       There is one verb whose main purpose is to track how a  match  was  ar-
-       rived  at,  though  it also has a secondary use in conjunction with ad-
+       There  is  one  verb whose main purpose is to track how a match was ar-
+       rived at, though it also has a secondary use in  conjunction  with  ad-
        vancing the match starting point (see (*SKIP) below).
 
          (*MARK:NAME) or (*:NAME)
 
-       A name is always required with this verb. For all the other  backtrack-
+       A  name is always required with this verb. For all the other backtrack-
        ing control verbs, a NAME argument is optional.
 
-       When  a  match  succeeds, the name of the last-encountered mark name on
+       When a match succeeds, the name of the last-encountered  mark  name  on
        the matching path is passed back to the caller as described in the sec-
        tion entitled "Other information about the match" in the pcre2api docu-
-       mentation. This applies to all instances of (*MARK)  and  other  verbs,
+       mentation.  This  applies  to all instances of (*MARK) and other verbs,
        including those inside assertions and atomic groups. However, there are
        differences in those cases when (*MARK) is  used  in  conjunction  with
        (*SKIP) as described below.
@@ -9350,12 +9668,12 @@ BACKTRACKING CONTROL
          MK: B
 
        The (*MARK) name is tagged with "MK:" in this output, and in this exam-
-       ple  it indicates which of the two alternatives matched. This is a more
-       efficient way of obtaining this information than putting each  alterna-
+       ple it indicates which of the two alternatives matched. This is a  more
+       efficient  way of obtaining this information than putting each alterna-
        tive in its own capturing parentheses.
 
-       If  a  verb  with a name is encountered in a positive assertion that is
-       true, the name is recorded and passed back if it  is  the  last-encoun-
+       If a verb with a name is encountered in a positive  assertion  that  is
+       true,  the  name  is recorded and passed back if it is the last-encoun-
        tered. This does not happen for negative assertions or failing positive
        assertions.
 
@@ -9378,23 +9696,23 @@ BACKTRACKING CONTROL
    Verbs that act after backtracking
 
        The following verbs do nothing when they are encountered. Matching con-
-       tinues  with  what follows, but if there is a subsequent match failure,
-       causing a backtrack to the verb, a failure is forced.  That  is,  back-
-       tracking  cannot  pass  to  the  left of the verb. However, when one of
+       tinues with what follows, but if there is a subsequent  match  failure,
+       causing  a  backtrack  to the verb, a failure is forced. That is, back-
+       tracking cannot pass to the left of the  verb.  However,  when  one  of
        these verbs appears inside an atomic group or in a lookaround assertion
        that  is  true,  its effect is confined to that group, because once the
        group has been matched, there is never any backtracking into it.  Back-
        tracking from beyond an assertion or an atomic group ignores the entire
        group, and seeks a preceding backtracking point.
 
-       These verbs differ in exactly what kind of failure  occurs  when  back-
-       tracking  reaches  them.  The behaviour described below is what happens
-       when the verb is not in a subroutine or an assertion.  Subsequent  sec-
+       These  verbs  differ  in exactly what kind of failure occurs when back-
+       tracking reaches them. The behaviour described below  is  what  happens
+       when  the  verb is not in a subroutine or an assertion. Subsequent sec-
        tions cover these special cases.
 
          (*COMMIT) or (*COMMIT:NAME)
 
-       This  verb  causes the whole match to fail outright if there is a later
+       This verb causes the whole match to fail outright if there is  a  later
        matching failure that causes backtracking to reach it. Even if the pat-
        tern  is  unanchored,  no further attempts to find a match by advancing
        the starting point take place. If (*COMMIT) is  the  only  backtracking
@@ -9413,13 +9731,13 @@ BACKTRACKING CONTROL
        that are set with (*MARK), ignoring those set by any of the other back-
        tracking verbs.
 
-       If there is more than one backtracking verb in a pattern,  a  different
-       one  that  follows  (*COMMIT) may be triggered first, so merely passing
+       If  there  is more than one backtracking verb in a pattern, a different
+       one that follows (*COMMIT) may be triggered first,  so  merely  passing
        (*COMMIT) during a match does not always guarantee that a match must be
        at this starting point.
 
        Note that (*COMMIT) at the start of a pattern is not the same as an an-
-       chor, unless PCRE2's start-of-match optimizations are  turned  off,  as
+       chor,  unless  PCRE2's  start-of-match optimizations are turned off, as
        shown in this output from pcre2test:
 
            re> /(*COMMIT)abc/
@@ -9430,17 +9748,17 @@ BACKTRACKING CONTROL
          data> xyzabc
          No match
 
-       For  the first pattern, PCRE2 knows that any match must start with "a",
-       so the optimization skips along the subject to "a" before applying  the
-       pattern  to the first set of data. The match attempt then succeeds. The
-       second pattern disables the optimization that skips along to the  first
-       character.  The  pattern  is  now  applied  starting at "x", and so the
-       (*COMMIT) causes the match to fail without trying  any  other  starting
+       For the first pattern, PCRE2 knows that any match must start with  "a",
+       so  the optimization skips along the subject to "a" before applying the
+       pattern to the first set of data. The match attempt then succeeds.  The
+       second  pattern disables the optimization that skips along to the first
+       character. The pattern is now applied  starting  at  "x",  and  so  the
+       (*COMMIT)  causes  the  match to fail without trying any other starting
        points.
 
          (*PRUNE) or (*PRUNE:NAME)
 
-       This  verb causes the match to fail at the current starting position in
+       This verb causes the match to fail at the current starting position  in
        the subject if there is a later matching failure that causes backtrack-
        ing  to  reach it. If the pattern is unanchored, the normal "bumpalong"
        advance to the next starting character then happens.  Backtracking  can
@@ -9449,18 +9767,18 @@ BACKTRACKING CONTROL
        right,  backtracking cannot cross (*PRUNE). In simple cases, the use of
        (*PRUNE) is just an alternative to an atomic group or possessive  quan-
        tifier, but there are some uses of (*PRUNE) that cannot be expressed in
-       any other way. In an anchored pattern (*PRUNE) has the same  effect  as
+       any  other  way. In an anchored pattern (*PRUNE) has the same effect as
        (*COMMIT).
 
        The behaviour of (*PRUNE:NAME) is not the same as (*MARK:NAME)(*PRUNE).
        It is like (*MARK:NAME) in that the name is remembered for passing back
-       to  the  caller. However, (*SKIP:NAME) searches only for names set with
+       to the caller. However, (*SKIP:NAME) searches only for names  set  with
        (*MARK), ignoring those set by other backtracking verbs.
 
          (*SKIP)
 
-       This verb, when given without a name, is like (*PRUNE), except that  if
-       the  pattern  is unanchored, the "bumpalong" advance is not to the next
+       This  verb, when given without a name, is like (*PRUNE), except that if
+       the pattern is unanchored, the "bumpalong" advance is not to  the  next
        character, but to the position in the subject where (*SKIP) was encoun-
        tered.  (*SKIP)  signifies that whatever text was matched leading up to
        it cannot be part of a successful match if there is a  later  mismatch.
@@ -9505,13 +9823,13 @@ BACKTRACKING CONTROL
           0: b
           1: b
 
-       In the first example, the (*MARK) setting is in an atomic group, so  it
+       In  the first example, the (*MARK) setting is in an atomic group, so it
        is not seen when (*SKIP:X) triggers, causing the (*SKIP) to be ignored.
        This allows the second branch of the pattern to be tried at  the  first
        character  position.  In the second example, the (*MARK) setting is not
        in an atomic group. This allows (*SKIP:X) to find the (*MARK)  when  it
        backtracks, and this causes a new matching attempt to start at the sec-
-       ond character. This time, the (*MARK) is never seen  because  "a"  does
+       ond  character.  This  time, the (*MARK) is never seen because "a" does
        not match "b", so the matcher immediately jumps to the second branch of
        the pattern.
 
@@ -9537,11 +9855,11 @@ BACKTRACKING CONTROL
 
        The behaviour of (*THEN:NAME) is not the same  as  (*MARK:NAME)(*THEN).
        It is like (*MARK:NAME) in that the name is remembered for passing back
-       to the caller. However, (*SKIP:NAME) searches only for names  set  with
+       to  the  caller. However, (*SKIP:NAME) searches only for names set with
        (*MARK), ignoring those set by other backtracking verbs.
 
-       A  group  that does not contain a | character is just a part of the en-
-       closing alternative; it is not a nested alternation with only  one  al-
+       A group that does not contain a | character is just a part of  the  en-
+       closing  alternative;  it is not a nested alternation with only one al-
        ternative. The effect of (*THEN) extends beyond such a group to the en-
        closing alternative.  Consider this pattern, where A, B, etc. are  com-
        plex  pattern  fragments  that  do not contain any | characters at this
@@ -9551,7 +9869,7 @@ BACKTRACKING CONTROL
 
        If A and B are matched, but there is a failure in C, matching does  not
        backtrack into A; instead it moves to the next alternative, that is, D.
-       However, if the group containing (*THEN) is given  an  alternative,  it
+       However,  if  the  group containing (*THEN) is given an alternative, it
        behaves differently:
 
          A (B(*THEN)C | (*FAIL)) | D
@@ -9569,15 +9887,15 @@ BACKTRACKING CONTROL
          ^.*? (?(?=a) a | b(*THEN)c )
 
        If the subject is "ba", this pattern does not match. Because .*? is un-
-       greedy, it initially matches zero characters. The condition (?=a)  then
-       fails,  the  character  "b"  is matched, but "c" is not. At this point,
-       matching does not backtrack to .*? as might perhaps  be  expected  from
-       the  presence  of the | character. The conditional group is part of the
-       single alternative that comprises the whole pattern, and so  the  match
-       fails.  (If  there  was a backtrack into .*?, allowing it to match "b",
+       greedy,  it initially matches zero characters. The condition (?=a) then
+       fails, the character "b" is matched, but "c" is  not.  At  this  point,
+       matching  does  not  backtrack to .*? as might perhaps be expected from
+       the presence of the | character. The conditional group is part  of  the
+       single  alternative  that comprises the whole pattern, and so the match
+       fails. (If there was a backtrack into .*?, allowing it  to  match  "b",
        the match would succeed.)
 
-       The verbs just described provide four different "strengths" of  control
+       The  verbs just described provide four different "strengths" of control
        when subsequent matching fails. (*THEN) is the weakest, carrying on the
        match at the next alternative. (*PRUNE) comes next, failing  the  match
        at  the  current starting position, but allowing an advance to the next
@@ -9587,23 +9905,23 @@ BACKTRACKING CONTROL
 
    More than one backtracking verb
 
-       If more than one backtracking verb is present in  a  pattern,  the  one
-       that  is  backtracked  onto first acts. For example, consider this pat-
+       If  more  than  one  backtracking verb is present in a pattern, the one
+       that is backtracked onto first acts. For example,  consider  this  pat-
        tern, where A, B, etc. are complex pattern fragments:
 
          (A(*COMMIT)B(*THEN)C|ABD)
 
-       If A matches but B fails, the backtrack to (*COMMIT) causes the  entire
+       If  A matches but B fails, the backtrack to (*COMMIT) causes the entire
        match to fail. However, if A and B match, but C fails, the backtrack to
        (*THEN) causes the next alternative (ABD) to be tried.  This  behaviour
        is  consistent,  but is not always the same as Perl's. It means that if
-       two or more backtracking verbs appear in succession, all the  the  last
+       two or more backtracking verbs appear in succession, all but  the  last
        of them has no effect. Consider this example:
 
          ...(*COMMIT)(*PRUNE)...
 
        If there is a matching failure to the right, backtracking onto (*PRUNE)
-       causes it to be triggered, and its action is taken. There can never  be
+       causes  it to be triggered, and its action is taken. There can never be
        a backtrack onto (*COMMIT).
 
    Backtracking verbs in repeated groups
@@ -9630,8 +9948,8 @@ BACKTRACKING CONTROL
        CEPT) causes the assertion to fail without any further processing; cap-
        tured substrings and any mark name are discarded.
 
-       If  the  assertion is a condition, (*ACCEPT) causes the condition to be
-       true for a positive assertion and false for a  negative  one;  captured
+       If the assertion is a condition, (*ACCEPT) causes the condition  to  be
+       true  for  a  positive assertion and false for a negative one; captured
        substrings are retained in both cases.
 
        The remaining verbs act only when a later failure causes a backtrack to
@@ -9656,7 +9974,7 @@ BACKTRACKING CONTROL
        The other backtracking verbs are not treated specially if  they  appear
        in  a  standalone  positive assertion. In a conditional positive asser-
        tion, backtracking (from within the assertion) into (*COMMIT), (*SKIP),
-       or  (*PRUNE) causes the condition to be false. However, for both stand-
+       or (*PRUNE) causes the condition to be false. However, for both  stand-
        alone and conditional negative assertions, backtracking into (*COMMIT),
        (*SKIP), or (*PRUNE) causes the assertion to be true, without consider-
        ing any further alternative branches.
@@ -9678,7 +9996,7 @@ BACKTRACKING CONTROL
        tine. There is then a backtrack at the outer level.
 
        (*THEN), when triggered, skips to the next alternative in the innermost
-       enclosing  group that has alternatives (its normal behaviour). However,
+       enclosing group that has alternatives (its normal behaviour).  However,
        if there is no such group within the subroutine's group, the subroutine
        match fails and there is a backtrack at the outer level.
 
@@ -9698,18 +10016,22 @@ AUTHOR
 
 REVISION
 
-       Last updated: 12 January 2022
-       Copyright (c) 1997-2022 University of Cambridge.
+       Last updated: 04 June 2024
+       Copyright (c) 1997-2024 University of Cambridge.
+
+
+PCRE2 10.44                      04 June 2024                  PCRE2PATTERN(3)
 ------------------------------------------------------------------------------
 
 
-PCRE2PERFORM(3)            Library Functions Manual            PCRE2PERFORM(3)
 
+PCRE2PERFORM(3)            Library Functions Manual            PCRE2PERFORM(3)
 
 
 NAME
        PCRE2 - Perl-compatible regular expressions (revised API)
 
+
 PCRE2 PERFORMANCE
 
        Two  aspects  of performance are discussed below: memory usage and pro-
@@ -9720,7 +10042,7 @@ PCRE2 PERFORMANCE
 COMPILED PATTERN MEMORY USAGE
 
        Patterns are compiled by PCRE2 into a reasonably efficient interpretive
-       code, so that most simple patterns do not use much memory  for  storing
+       code,  so  that most simple patterns do not use much memory for storing
        the compiled version. However, there is one case where the memory usage
        of a compiled pattern can be unexpectedly  large.  If  a  parenthesized
        group  has  a quantifier with a minimum greater than 1 and/or a limited
@@ -9733,31 +10055,31 @@ COMPILED PATTERN MEMORY USAGE
 
          (abc|def)(abc|def)((abc|def)(abc|def)?)?
 
-       (Technical  aside:  It is done this way so that backtrack points within
+       (Technical aside: It is done this way so that backtrack  points  within
        each of the repetitions can be independently maintained.)
 
-       For regular expressions whose quantifiers use only small numbers,  this
-       is  not  usually a problem. However, if the numbers are large, and par-
-       ticularly if such repetitions are nested, the memory usage  can  become
+       For  regular expressions whose quantifiers use only small numbers, this
+       is not usually a problem. However, if the numbers are large,  and  par-
+       ticularly  if  such repetitions are nested, the memory usage can become
        an embarrassment. For example, the very simple pattern
 
          ((ab){1,1000}c){1,3}
 
-       uses  over  50KiB  when compiled using the 8-bit library. When PCRE2 is
-       compiled with its default internal pointer size of two bytes, the  size
+       uses over 50KiB when compiled using the 8-bit library.  When  PCRE2  is
+       compiled  with its default internal pointer size of two bytes, the size
        limit on a compiled pattern is 65535 code units in the 8-bit and 16-bit
        libraries, and this is reached with the above pattern if the outer rep-
-       etition  is  increased from 3 to 4. PCRE2 can be compiled to use larger
-       internal pointers and thus handle larger compiled patterns, but  it  is
+       etition is increased from 3 to 4. PCRE2 can be compiled to  use  larger
+       internal  pointers  and thus handle larger compiled patterns, but it is
        better to try to rewrite your pattern to use less memory if you can.
 
-       One  way  of reducing the memory usage for such patterns is to make use
+       One way of reducing the memory usage for such patterns is to  make  use
        of PCRE2's "subroutine" facility. Re-writing the above pattern as
 
          ((ab)(?2){0,999}c)(?1){0,2}
 
-       reduces the memory requirements to around 16KiB, and indeed it  remains
-       under  20KiB  even with the outer repetition increased to 100. However,
+       reduces  the memory requirements to around 16KiB, and indeed it remains
+       under 20KiB even with the outer repetition increased to  100.  However,
        this kind of pattern is not always exactly equivalent, because any cap-
        tures  within  subroutine calls are lost when the subroutine completes.
        If this is not a problem, this kind of  rewriting  will  allow  you  to
@@ -9770,10 +10092,10 @@ COMPILED PATTERN MEMORY USAGE
 STACK AND HEAP USAGE AT RUN TIME
 
        From release 10.30, the interpretive (non-JIT) version of pcre2_match()
-       uses  very  little system stack at run time. In earlier releases recur-
-       sive function calls could use a great deal of  stack,  and  this  could
-       cause  problems, but this usage has been eliminated. Backtracking posi-
-       tions are now explicitly remembered in memory frames controlled by  the
+       uses very little system stack at run time. In earlier  releases  recur-
+       sive  function  calls  could  use a great deal of stack, and this could
+       cause problems, but this usage has been eliminated. Backtracking  posi-
+       tions  are now explicitly remembered in memory frames controlled by the
        code.
 
        The size of each frame depends on the size of pointer variables and the
@@ -9781,10 +10103,10 @@ STACK AND HEAP USAGE AT RUN TIME
        On a 64-bit system the frame size for a pattern with no captures is 128
        bytes. For each capturing group the size increases by 16 bytes.
 
-       Until release 10.41, an initial 20KiB frames vector  was  allocated  on
-       the  system  stack,  but this still caused some issues for multi-thread
-       applications where each thread has a very  small  stack.  From  release
-       10.41  backtracking  memory  frames  are always held in heap memory. An
+       Until  release  10.41,  an initial 20KiB frames vector was allocated on
+       the system stack, but this still caused some  issues  for  multi-thread
+       applications  where  each  thread  has a very small stack. From release
+       10.41 backtracking memory frames are always held  in  heap  memory.  An
        initial heap allocation is obtained the first time any match data block
        is  passed  to  pcre2_match().  This  is remembered with the match data
        block and re-used if that block is used for another match. It is  freed
@@ -9792,7 +10114,7 @@ STACK AND HEAP USAGE AT RUN TIME
 
        The  size  of the initial block is the larger of 20KiB or ten times the
        pattern's frame size, unless the heap limit is less than this, in which
-       case  the  heap  limit  is  used. If the initial block proves to be too
+       case the heap limit is used. If the initial  block  proves  to  be  too
        small during matching, it is replaced by a larger block, subject to the
        heap  limit.  The  heap limit is checked only when a new block is to be
        allocated. Reducing the heap limit between calls to pcre2_match()  with
@@ -9801,26 +10123,26 @@ STACK AND HEAP USAGE AT RUN TIME
        In  contrast  to  pcre2_match(),  pcre2_dfa_match()  does use recursive
        function calls, but only for processing atomic groups,  lookaround  as-
        sertions, and recursion within the pattern. The original version of the
-       code used to allocate quite large internal  workspace  vectors  on  the
-       stack,  which  caused  some  problems for some patterns in environments
-       with small stacks. From release 10.32 the  code  for  pcre2_dfa_match()
-       has  been  re-factored  to  use heap memory when necessary for internal
-       workspace when recursing, though recursive  function  calls  are  still
+       code  used  to  allocate  quite large internal workspace vectors on the
+       stack, which caused some problems for  some  patterns  in  environments
+       with  small  stacks.  From release 10.32 the code for pcre2_dfa_match()
+       has been re-factored to use heap memory  when  necessary  for  internal
+       workspace  when  recursing,  though  recursive function calls are still
        used.
 
-       The  "match depth" parameter can be used to limit the depth of function
-       recursion, and the "match heap"  parameter  to  limit  heap  memory  in
+       The "match depth" parameter can be used to limit the depth of  function
+       recursion,  and  the  "match  heap"  parameter  to limit heap memory in
        pcre2_dfa_match().
 
 
 PROCESSING TIME
 
-       Certain  items  in regular expression patterns are processed more effi-
+       Certain items in regular expression patterns are processed  more  effi-
        ciently than others. It is more efficient to use a character class like
        [aeiou]   than   a   set   of  single-character  alternatives  such  as
        (a|e|i|o|u). In general, the simplest construction  that  provides  the
        required behaviour is usually the most efficient. Jeffrey Friedl's book
-       contains a lot of useful general discussion  about  optimizing  regular
+       contains  a  lot  of useful general discussion about optimizing regular
        expressions for efficient performance. This document contains a few ob-
        servations about PCRE2.
 
@@ -9832,16 +10154,16 @@ PROCESSING TIME
        By  default,  the  escape  sequences  \b, \d, \s, and \w, and the POSIX
        character classes such as [:alpha:]  do  not  use  Unicode  properties,
        partly for backwards compatibility, and partly for performance reasons.
-       However, you can set the PCRE2_UCP option or  start  the  pattern  with
-       (*UCP)  if  you  want Unicode character properties to be used. This can
-       double the matching time for  items  such  as  \d,  when  matched  with
-       pcre2_match();  the  performance loss is less with a DFA matching func-
+       However,  you  can  set  the PCRE2_UCP option or start the pattern with
+       (*UCP) if you want Unicode character properties to be  used.  This  can
+       double  the  matching  time  for  items  such  as \d, when matched with
+       pcre2_match(); the performance loss is less with a DFA  matching  func-
        tion, and in both cases there is not much difference for \b.
 
-       When a pattern begins with .* not in atomic parentheses, nor in  paren-
-       theses  that  are  the subject of a backreference, and the PCRE2_DOTALL
-       option is set, the pattern is implicitly anchored by  PCRE2,  since  it
-       can  match  only  at  the start of a subject string. If the pattern has
+       When  a pattern begins with .* not in atomic parentheses, nor in paren-
+       theses that are the subject of a backreference,  and  the  PCRE2_DOTALL
+       option  is  set,  the pattern is implicitly anchored by PCRE2, since it
+       can match only at the start of a subject string.  If  the  pattern  has
        multiple top-level branches, they must all be anchorable. The optimiza-
        tion  can be disabled by the PCRE2_NO_DOTSTAR_ANCHOR option, and is au-
        tomatically disabled if the pattern contains (*PRUNE) or (*SKIP).
@@ -9854,45 +10176,45 @@ PROCESSING TIME
 
          .*second
 
-       matches the subject "first\nand second" (where \n stands for a  newline
-       character),  with the match starting at the seventh character. In order
-       to do this, PCRE2 has to retry the match starting after  every  newline
+       matches  the subject "first\nand second" (where \n stands for a newline
+       character), with the match starting at the seventh character. In  order
+       to  do  this, PCRE2 has to retry the match starting after every newline
        in the subject.
 
-       If  you  are using such a pattern with subject strings that do not con-
-       tain  newlines,  the  best   performance   is   obtained   by   setting
-       PCRE2_DOTALL,  or starting the pattern with ^.* or ^.*? to indicate ex-
-       plicit anchoring. That saves PCRE2 from having to scan along  the  sub-
+       If you are using such a pattern with subject strings that do  not  con-
+       tain   newlines,   the   best   performance   is  obtained  by  setting
+       PCRE2_DOTALL, or starting the pattern with ^.* or ^.*? to indicate  ex-
+       plicit  anchoring.  That saves PCRE2 from having to scan along the sub-
        ject looking for a newline to restart at.
 
-       Beware  of  patterns  that contain nested indefinite repeats. These can
-       take a long time to run when applied to a string that does  not  match.
+       Beware of patterns that contain nested indefinite  repeats.  These  can
+       take  a  long time to run when applied to a string that does not match.
        Consider the pattern fragment
 
          ^(a+)*
 
-       This  can  match "aaaa" in 16 different ways, and this number increases
-       very rapidly as the string gets longer. (The * repeat can match  0,  1,
-       2,  3, or 4 times, and for each of those cases other than 0 or 4, the +
-       repeats can match different numbers of times.) When  the  remainder  of
-       the  pattern  is such that the entire match is going to fail, PCRE2 has
-       in principle to try every possible variation, and this can take an  ex-
+       This can match "aaaa" in 16 different ways, and this  number  increases
+       very  rapidly  as the string gets longer. (The * repeat can match 0, 1,
+       2, 3, or 4 times, and for each of those cases other than 0 or 4, the  +
+       repeats  can  match  different numbers of times.) When the remainder of
+       the pattern is such that the entire match is going to fail,  PCRE2  has
+       in  principle to try every possible variation, and this can take an ex-
        tremely long time, even for relatively short strings.
 
        An optimization catches some of the more simple cases such as
 
          (a+)*b
 
-       where  a  literal  character  follows. Before embarking on the standard
-       matching procedure, PCRE2 checks that there is a "b" later in the  sub-
-       ject  string, and if there is not, it fails the match immediately. How-
-       ever, when there is no following literal this  optimization  cannot  be
+       where a literal character follows. Before  embarking  on  the  standard
+       matching  procedure, PCRE2 checks that there is a "b" later in the sub-
+       ject string, and if there is not, it fails the match immediately.  How-
+       ever,  when  there  is no following literal this optimization cannot be
        used. You can see the difference by comparing the behaviour of
 
          (a+)*\d
 
-       with  the  pattern  above.  The former gives a failure almost instantly
-       when applied to a whole line of  "a"  characters,  whereas  the  latter
+       with the pattern above. The former gives  a  failure  almost  instantly
+       when  applied  to  a  whole  line of "a" characters, whereas the latter
        takes an appreciable time with strings longer than about 20 characters.
 
        In many cases, the solution to this kind of performance issue is to use
@@ -9904,9 +10226,9 @@ PROCESSING TIME
        It  matches  from wherever it starts until it encounters "
@@ -9982,38 +10308,48 @@ DESCRIPTION
 
        This  set of functions provides a POSIX-style API for the PCRE2 regular
        expression 8-bit library. There are no POSIX-style wrappers for PCRE2's
-       16-bit  and  32-bit libraries. See the pcre2api documentation for a de-
-       scription of PCRE2's native API, which contains much  additional  func-
+       16-bit and 32-bit libraries. See the pcre2api documentation for  a  de-
+       scription  of  PCRE2's native API, which contains much additional func-
        tionality.
 
-       The functions described here are wrapper functions that ultimately call
-       the PCRE2 native API. Their prototypes are defined in the  pcre2posix.h
-       header  file, and they all have unique names starting with pcre2_. How-
-       ever, the pcre2posix.h header also contains macro definitions that con-
-       vert  the standard POSIX names such regcomp() into pcre2_regcomp() etc.
-       This means that a program can use the usual POSIX names without running
-       the  risk of accidentally linking with POSIX functions from a different
-       library.
-
-       On Unix-like systems the PCRE2 POSIX library is called  libpcre2-posix,
-       so  can  be accessed by adding -lpcre2-posix to the command for linking
+       IMPORTANT NOTE: The functions described here are NOT  thread-safe,  and
+       should  not  be used in multi-threaded applications. They are also lim-
+       ited to processing subjects that are not bigger than 2GB. Use  the  na-
+       tive API instead.
+
+       These  functions  are  wrapper functions that ultimately call the PCRE2
+       native API. Their prototypes are defined  in  the  pcre2posix.h  header
+       file, and they all have unique names starting with pcre2_. However, the
+       pcre2posix.h  header  also  contains macro definitions that convert the
+       standard POSIX names such  regcomp()  into  pcre2_regcomp()  etc.  This
+       means  that a program can use the usual POSIX names without running the
+       risk of accidentally linking with POSIX functions from a different  li-
+       brary.
+
+       On  Unix-like systems the PCRE2 POSIX library is called libpcre2-posix,
+       so can be accessed by adding -lpcre2-posix to the command  for  linking
        an application. Because the POSIX functions call the native ones, it is
        also necessary to add -lpcre2-8.
 
-       Although  they  were  not defined as protypes in pcre2posix.h, releases
+       On Windows systems, if you are linking to a DLL version of the library,
+       it  is  recommended  that PCRE2POSIX_SHARED is defined before including
+       the pcre2posix.h header, as it will allow for a more efficient  way  to
+       invoke the functions by adding the __declspec(dllimport) decorator.
+
+       Although  they were not defined as prototypes in pcre2posix.h, releases
        10.33 to 10.36 of the library contained functions with the POSIX  names
        regcomp()  etc.  These simply passed their arguments to the PCRE2 func-
        tions. These functions were provided for backwards  compatibility  with
        earlier  versions  of  PCRE2, which had only POSIX names. However, this
        has proved troublesome in situations where a program links with several
-       libraries,  some  of which use PCRE2's POSIX interface while others use
-       the real POSIX functions.  For this reason, the POSIX names  have  been
+       libraries, some of which use PCRE2's POSIX interface while  others  use
+       the  real  POSIX functions.  For this reason, the POSIX names have been
        removed since release 10.37.
 
-       Calling  the  header  file  pcre2posix.h avoids any conflict with other
-       POSIX libraries. It can, of course, be renamed or aliased  as  regex.h,
-       which  is  the  "correct"  name,  if there is no clash. It provides two
-       structure types, regex_t for compiled internal  forms,  and  regmatch_t
+       Calling the header file pcre2posix.h avoids  any  conflict  with  other
+       POSIX  libraries.  It can, of course, be renamed or aliased as regex.h,
+       which is the "correct" name, if there is  no  clash.  It  provides  two
+       structure  types,  regex_t  for compiled internal forms, and regmatch_t
        for returning captured substrings. It also defines some constants whose
        names start with "REG_"; these are used for setting options and identi-
        fying error codes.
@@ -10021,6 +10357,10 @@ DESCRIPTION
 
 USING THE POSIX FUNCTIONS
 
+       Note that these functions are just POSIX-style wrappers for PCRE2's na-
+       tive API.  They do not give POSIX  regular  expression  behaviour,  and
+       they are not thread-safe or even POSIX compatible.
+
        Those  POSIX  option bits that can reasonably be mapped to PCRE2 native
        options have been implemented. In addition, the option REG_EXTENDED  is
        defined  with  the  value  zero. This has no effect, but since programs
@@ -10049,24 +10389,26 @@ USING THE POSIX FUNCTIONS
 COMPILING A PATTERN
 
        The function pcre2_regcomp() is called to compile a pattern into an in-
-       ternal form. By default, the pattern is a C string terminated by a  bi-
+       ternal  form. By default, the pattern is a C string terminated by a bi-
        nary zero (but see REG_PEND below). The preg argument is a pointer to a
        regex_t structure that is used as a base for storing information  about
-       the  compiled  regular  expression.  (It  is  also  used for input when
-       REG_PEND is set.)
+       the  compiled  regular  expression.  It  is  also  used  for input when
+       REG_PEND is set. The regex_t structure used by pcre2_regcomp()  is  de-
+       fined  in  pcre2posix.h  and  is  not the same as the structure used by
+       other libraries that provide POSIX-style matching.
 
        The argument cflags is either zero, or contains one or more of the bits
        defined by the following macros:
 
          REG_DOTALL
 
-       The  PCRE2_DOTALL  option  is set when the regular expression is passed
-       for compilation to the native function. Note  that  REG_DOTALL  is  not
+       The PCRE2_DOTALL option is set when the regular  expression  is  passed
+       for  compilation  to  the  native function. Note that REG_DOTALL is not
        part of the POSIX standard.
 
          REG_ICASE
 
-       The  PCRE2_CASELESS option is set when the regular expression is passed
+       The PCRE2_CASELESS option is set when the regular expression is  passed
        for compilation to the native function.
 
          REG_NEWLINE
@@ -10098,9 +10440,9 @@ COMPILING A PATTERN
 
        If  this option is set, the reg_endp field in the preg structure (which
        has the type const char *) must be set to point to the character beyond
-       the  end of the pattern before calling pcre2_regcomp(). The pattern it-
-       self may now contain binary zeros, which are treated  as  data  charac-
-       ters.  Without  REG_PEND,  a binary zero terminates the pattern and the
+       the end of the pattern before calling pcre2_regcomp(). The pattern  it-
+       self  may  now  contain binary zeros, which are treated as data charac-
+       ters. Without REG_PEND, a binary zero terminates the  pattern  and  the
        re_endp field is ignored. This is a GNU extension to the POSIX standard
        and  should be used with caution in software intended to be portable to
        other systems.
@@ -10109,7 +10451,7 @@ COMPILING A PATTERN
 
        The PCRE2_UCP option is set when the regular expression is  passed  for
        compilation  to  the  native function. This causes PCRE2 to use Unicode
-       properties when matchine \d, \w,  etc.,  instead  of  just  recognizing
+       properties when matching \d, \w,  etc.,  instead  of  just  recognizing
        ASCII values. Note that REG_UCP is not part of the POSIX standard.
 
          REG_UNGREEDY
@@ -10126,22 +10468,22 @@ COMPILING A PATTERN
        Note that REG_UTF is not part of the POSIX standard.
 
        In the absence of these flags, no options  are  passed  to  the  native
-       function.   This means the the regex is compiled with PCRE2 default se-
-       mantics. In particular, the way it handles newline  characters  in  the
-       subject  string  is  the Perl way, not the POSIX way. Note that setting
+       function.  This means that the regex is compiled with PCRE2 default se-
+       mantics.  In  particular,  the way it handles newline characters in the
+       subject string is the Perl way, not the POSIX way.  Note  that  setting
        PCRE2_MULTILINE has only some of the effects specified for REG_NEWLINE.
        It  does not affect the way newlines are matched by the dot metacharac-
        ter (they are not) or by a negative class such as [^a] (they are).
 
        The yield of pcre2_regcomp() is zero on success,  and  non-zero  other-
        wise.  The preg structure is filled in on success, and one other member
-       of the structure (as well as re_endp) is public: re_nsub  contains  the
-       number  of capturing subpatterns in the regular expression. Various er-
+       of  the  structure (as well as re_endp) is public: re_nsub contains the
+       number of capturing subpatterns in the regular expression. Various  er-
        ror codes are defined in the header file.
 
        NOTE: If the yield of pcre2_regcomp() is non-zero, you must not attempt
        to use the contents of the preg structure. If, for example, you pass it
-       to pcre2_regexec(), the result is undefined and your program is  likely
+       to  pcre2_regexec(), the result is undefined and your program is likely
        to crash.
 
 
@@ -10150,7 +10492,7 @@ MATCHING NEWLINE CHARACTERS
        This area is not simple, because POSIX and Perl take different views of
        things.  It is not possible to get PCRE2 to obey POSIX  semantics,  but
        then PCRE2 was never intended to be a POSIX engine. The following table
-       lists the different possibilities for matching  newline  characters  in
+       lists  the  different  possibilities for matching newline characters in
        Perl and PCRE2:
 
                                  Default   Change with
@@ -10171,13 +10513,13 @@ MATCHING NEWLINE CHARACTERS
          $ matches \n in middle     no     REG_NEWLINE
          ^ matches \n in middle     no     REG_NEWLINE
 
-       This  behaviour  is not what happens when PCRE2 is called via its POSIX
-       API. By default, PCRE2's behaviour is the same as Perl's,  except  that
-       there  is no equivalent for PCRE2_DOLLAR_ENDONLY in Perl. In both PCRE2
+       This behaviour is not what happens when PCRE2 is called via  its  POSIX
+       API.  By  default, PCRE2's behaviour is the same as Perl's, except that
+       there is no equivalent for PCRE2_DOLLAR_ENDONLY in Perl. In both  PCRE2
        and Perl, there is no way to stop newline from matching [^a].
 
-       Default POSIX newline handling can be obtained by setting  PCRE2_DOTALL
-       and  PCRE2_DOLLAR_ENDONLY  when  calling  pcre2_compile() directly, but
+       Default  POSIX newline handling can be obtained by setting PCRE2_DOTALL
+       and PCRE2_DOLLAR_ENDONLY when  calling  pcre2_compile()  directly,  but
        there is no way to make PCRE2 behave exactly as for the REG_NEWLINE ac-
        tion.  When  using  the  POSIX  API,  passing  REG_NEWLINE  to  PCRE2's
        pcre2_regcomp()  function  causes  PCRE2_MULTILINE  to  be  passed   to
@@ -10199,9 +10541,9 @@ MATCHING A PATTERN
 
          REG_NOTEMPTY
 
-       The PCRE2_NOTEMPTY option is set  when  calling  the  underlying  PCRE2
-       matching  function.  Note  that  REG_NOTEMPTY  is not part of the POSIX
-       standard. However, setting this option can give more POSIX-like  behav-
+       The  PCRE2_NOTEMPTY  option  is  set  when calling the underlying PCRE2
+       matching function. Note that REG_NOTEMPTY is  not  part  of  the  POSIX
+       standard.  However, setting this option can give more POSIX-like behav-
        iour in some situations.
 
          REG_NOTEOL
@@ -10214,55 +10556,60 @@ MATCHING A PATTERN
        When this option  is  set,  the  subject  string  starts  at  string  +
        pmatch[0].rm_so  and  ends  at  string  + pmatch[0].rm_eo, which should
        point to the first character beyond the string. There may be binary ze-
-       ros  within  the  subject string, and indeed, using REG_STARTEND is the
+       ros within the subject string, and indeed, using  REG_STARTEND  is  the
        only way to pass a subject string that contains a binary zero.
 
-       Whatever the value of  pmatch[0].rm_so,  the  offsets  of  the  matched
-       string  and  any  captured  substrings  are still given relative to the
-       start of string itself. (Before PCRE2 release 10.30  these  were  given
-       relative  to  string + pmatch[0].rm_so, but this differs from other im-
+       Whatever  the  value  of  pmatch[0].rm_so,  the  offsets of the matched
+       string and any captured substrings are  still  given  relative  to  the
+       start  of  string  itself. (Before PCRE2 release 10.30 these were given
+       relative to string + pmatch[0].rm_so, but this differs from  other  im-
        plementations.)
 
-       This is a BSD extension, compatible with  but  not  specified  by  IEEE
-       Standard  1003.2 (POSIX.2), and should be used with caution in software
-       intended to be portable to other systems. Note that  a  non-zero  rm_so
-       does  not  imply REG_NOTBOL; REG_STARTEND affects only the location and
-       length of the string, not how it is matched. Setting  REG_STARTEND  and
-       passing  pmatch as NULL are mutually exclusive; the error REG_INVARG is
+       This  is  a  BSD  extension,  compatible with but not specified by IEEE
+       Standard 1003.2 (POSIX.2), and should be used with caution in  software
+       intended  to  be  portable to other systems. Note that a non-zero rm_so
+       does not imply REG_NOTBOL; REG_STARTEND affects only the  location  and
+       length  of  the string, not how it is matched. Setting REG_STARTEND and
+       passing pmatch as NULL are mutually exclusive; the error REG_INVARG  is
        returned.
 
-       If the pattern was compiled with the REG_NOSUB flag, no data about  any
-       matched  strings  is  returned.  The  nmatch  and  pmatch  arguments of
-       pcre2_regexec() are ignored (except possibly  as  input  for  REG_STAR-
+       If  the pattern was compiled with the REG_NOSUB flag, no data about any
+       matched strings  is  returned.  The  nmatch  and  pmatch  arguments  of
+       pcre2_regexec()  are  ignored  (except  possibly as input for REG_STAR-
        TEND).
 
-       The  value of nmatch may be zero, and the value pmatch may be NULL (un-
-       less REG_STARTEND is set); in  both  these  cases  no  data  about  any
+       The value of nmatch may be zero, and the value pmatch may be NULL  (un-
+       less  REG_STARTEND  is  set);  in  both  these  cases no data about any
        matched strings is returned.
 
-       Otherwise,  the  portion  of  the string that was matched, and also any
+       Otherwise, the portion of the string that was  matched,  and  also  any
        captured substrings, are returned via the pmatch argument, which points
        to  an  array  of  nmatch structures of type regmatch_t, containing the
        members rm_so and rm_eo. These contain the byte  offset  to  the  first
        character of each substring and the offset to the first character after
-       the end of each substring, respectively. The 0th element of the  vector
-       relates  to  the  entire portion of string that was matched; subsequent
+       the  end of each substring, respectively. The 0th element of the vector
+       relates to the entire portion of string that  was  matched;  subsequent
        elements relate to the capturing subpatterns of the regular expression.
        Unused entries in the array have both structure members set to -1.
 
-       A  successful  match  yields a zero return; various error codes are de-
-       fined in the header file, of which REG_NOMATCH is the "expected"  fail-
+       regmatch_t  as  well  as  the  regoff_t  typedef it uses are defined in
+       pcre2posix.h and are not warranted to have the same size or  layout  as
+       other  similarly  named  types from other libraries that provide POSIX-
+       style matching.
+
+       A successful match yields a zero return; various error  codes  are  de-
+       fined  in the header file, of which REG_NOMATCH is the "expected" fail-
        ure code.
 
 
 ERROR MESSAGES
 
-       The  pcre2_regerror()  function  maps  a non-zero errorcode from either
-       pcre2_regcomp() or pcre2_regexec() to a printable message. If  preg  is
-       not  NULL, the error should have arisen from the use of that structure.
-       A message terminated by a binary zero is placed in errbuf. If the  buf-
-       fer  is too short, only the first errbuf_size - 1 characters of the er-
-       ror message are used. The yield of the function is the size  of  buffer
+       The pcre2_regerror() function maps a  non-zero  errorcode  from  either
+       pcre2_regcomp()  or  pcre2_regexec() to a printable message. If preg is
+       not NULL, the error should have arisen from the use of that  structure.
+       A  message  terminated  by  a  binary  zero is placed in errbuf. If the
+       buffer is too short, only the first errbuf_size - 1 characters  of  the
+       error message are used. The yield of the function is the size of buffer
        needed  to hold the whole message, including the terminating zero. This
        value is greater than errbuf_size if the message was truncated.
 
@@ -10278,24 +10625,28 @@ MEMORY USAGE
 AUTHOR
 
        Philip Hazel
-       University Computing Service
+       Retired from University Computing Service
        Cambridge, England.
 
 
 REVISION
 
-       Last updated: 26 April 2021
-       Copyright (c) 1997-2021 University of Cambridge.
+       Last updated: 19 January 2024
+       Copyright (c) 1997-2024 University of Cambridge.
+
+
+PCRE2 10.43                     19 January 2024                  PCRE2POSIX(3)
 ------------------------------------------------------------------------------
 
 
-PCRE2SAMPLE(3)             Library Functions Manual             PCRE2SAMPLE(3)
 
+PCRE2SAMPLE(3)             Library Functions Manual             PCRE2SAMPLE(3)
 
 
 NAME
        PCRE2 - Perl-compatible regular expressions (revised API)
 
+
 PCRE2 SAMPLE PROGRAM
 
        A  simple, complete demonstration program to get you started with using
@@ -10306,7 +10657,7 @@ PCRE2 SAMPLE PROGRAM
 
        The  demonstration  program compiles the regular expression that is its
        first argument, and matches it against the subject string in its second
-       argument.  No  PCRE2  options are set, and default character tables are
+       argument. No PCRE2 options are set, and default  character  tables  are
        used. If matching succeeds, the program outputs the portion of the sub-
        ject  that  matched,  together  with  the contents of any captured sub-
        strings.
@@ -10344,10 +10695,10 @@ PCRE2 SAMPLE PROGRAM
          ./pcre2demo 'cat|dog' 'the cat sat on the mat'
          ./pcre2demo -g 'cat|dog' 'the dog sat on the cat'
 
-       Note  that  there  is  a  much  more comprehensive test program, called
-       pcre2test, which supports many more facilities for testing regular  ex-
-       pressions  using  all three PCRE2 libraries (8-bit, 16-bit, and 32-bit,
-       though not all three need be installed). The pcre2demo program is  pro-
+       Note that there is a  much  more  comprehensive  test  program,  called
+       pcre2test,  which supports many more facilities for testing regular ex-
+       pressions using all three PCRE2 libraries (8-bit, 16-bit,  and  32-bit,
+       though  not all three need be installed). The pcre2demo program is pro-
        vided as a relatively simple coding example.
 
        If you try to run pcre2demo when PCRE2 is not installed in the standard
@@ -10357,7 +10708,7 @@ PCRE2 SAMPLE PROGRAM
          ld.so.1: pcre2demo: fatal: libpcre2-8.so.0: open failed: No such file
        or directory
 
-       This is caused by the way shared library support works  on  those  sys-
+       This  is  caused  by the way shared library support works on those sys-
        tems. You need to add
 
          -R/usr/local/lib
@@ -10368,7 +10719,7 @@ PCRE2 SAMPLE PROGRAM
 AUTHOR
 
        Philip Hazel
-       University Computing Service
+       Retired from University Computing Service
        Cambridge, England.
 
 
@@ -10376,14 +10727,18 @@ REVISION
 
        Last updated: 02 February 2016
        Copyright (c) 1997-2016 University of Cambridge.
+
+
+PCRE2 10.22                    02 February 2016                 PCRE2SAMPLE(3)
 ------------------------------------------------------------------------------
-PCRE2SERIALIZE(3)          Library Functions Manual          PCRE2SERIALIZE(3)
 
+PCRE2SERIALIZE(3)          Library Functions Manual          PCRE2SERIALIZE(3)
 
 
 NAME
        PCRE2 - Perl-compatible regular expressions (revised API)
 
+
 SAVING AND RE-USING PRECOMPILED PCRE2 PATTERNS
 
        int32_t pcre2_serialize_decode(pcre2_code **codes,
@@ -10403,17 +10758,17 @@ SAVING AND RE-USING PRECOMPILED PCRE2 PATTERNS
        form  instead  of  having to compile them every time the application is
        run. However, if you are using the just-in-time  optimization  feature,
        it is not possible to save and reload the JIT data, because it is posi-
-       tion-dependent. The host on which the patterns  are  reloaded  must  be
-       running  the  same version of PCRE2, with the same code unit width, and
-       must also have the same endianness, pointer width and PCRE2_SIZE  type.
-       For  example, patterns compiled on a 32-bit system using PCRE2's 16-bit
+       tion-dependent.  The  host  on  which the patterns are reloaded must be
+       running the same version of PCRE2, with the same code unit  width,  and
+       must  also have the same endianness, pointer width and PCRE2_SIZE type.
+       For example, patterns compiled on a 32-bit system using PCRE2's  16-bit
        library cannot be reloaded on a 64-bit system, nor can they be reloaded
        using the 8-bit library.
 
        Note  that  "serialization" in PCRE2 does not convert compiled patterns
        to an abstract format like Java or .NET serialization.  The  serialized
-       output  is  really  just  a  bytecode dump, which is why it can only be
-       reloaded in the same environment as the one that created it. Hence  the
+       output  is really just a bytecode dump, which is why it can only be re-
+       loaded in the same environment as the one that created  it.  Hence  the
        restrictions  mentioned  above.   Applications  that are not statically
        linked with a fixed version of PCRE2 must be prepared to recompile pat-
        terns from their sources, in order to be immune to PCRE2 upgrades.
@@ -10446,9 +10801,9 @@ SAVING COMPILED PATTERNS
        list, being a pointer to a vector of pointers to compiled patterns, and
        the length of the vector. The third and fourth arguments point to vari-
        ables which are set to point to the created byte stream and its length,
-       respectively.  The  final  argument  is a pointer to a general context,
-       which can be used to specify custom memory  mangagement  functions.  If
-       this  argument  is NULL, malloc() is used to obtain memory for the byte
+       respectively. The final argument is a pointer  to  a  general  context,
+       which  can  be  used  to specify custom memory management functions. If
+       this argument is NULL, malloc() is used to obtain memory for  the  byte
        stream. The yield of the function is the number of serialized patterns,
        or one of the following negative error codes:
 
@@ -10463,7 +10818,7 @@ SAVING COMPILED PATTERNS
        tern.
 
        Once a set of patterns has been serialized you can save the data in any
-       appropriate manner. Here is sample code that compiles two patterns  and
+       appropriate  manner. Here is sample code that compiles two patterns and
        writes them to a file. It assumes that the variable fd refers to a file
        that is open for output. The error checking that should be present in a
        real application has been omitted for simplicity.
@@ -10481,26 +10836,26 @@ SAVING COMPILED PATTERNS
            &bytescount, NULL);
          errorcode = fwrite(bytes, 1, bytescount, fd);
 
-       Note  that  the  serialized data is binary data that may contain any of
-       the 256 possible byte values. On systems that make  a  distinction  be-
-       tween  binary  and non-binary data, be sure that the file is opened for
+       Note that the serialized data is binary data that may  contain  any  of
+       the  256  possible  byte values. On systems that make a distinction be-
+       tween binary and non-binary data, be sure that the file is  opened  for
        binary output.
 
-       Serializing a set of patterns leaves the original  data  untouched,  so
-       they  can  still  be used for matching. Their memory must eventually be
+       Serializing  a  set  of patterns leaves the original data untouched, so
+       they can still be used for matching. Their memory  must  eventually  be
        freed in the usual way by calling pcre2_code_free(). When you have fin-
        ished with the byte stream, it too must be freed by calling pcre2_seri-
-       alize_free(). If this function is called with a NULL argument,  it  re-
+       alize_free().  If  this function is called with a NULL argument, it re-
        turns immediately without doing anything.
 
 
 RE-USING PRECOMPILED PATTERNS
 
-       In  order to re-use a set of saved patterns you must first make the se-
-       rialized byte stream available in main memory (for example, by  reading
+       In order to re-use a set of saved patterns you must first make the  se-
+       rialized  byte stream available in main memory (for example, by reading
        from a file). The management of this memory block is up to the applica-
        tion. You can use the pcre2_serialize_get_number_of_codes() function to
-       find  out how many compiled patterns are in the serialized data without
+       find out how many compiled patterns are in the serialized data  without
        actually decoding the patterns:
 
          uint8_t *bytes = ;
@@ -10508,12 +10863,12 @@ RE-USING PRECOMPILED PATTERNS
 
        The pcre2_serialize_decode() function reads a byte stream and recreates
        the compiled patterns in new memory blocks, setting pointers to them in
-       a vector. The first two arguments are a pointer to  a  suitable  vector
+       a  vector.  The  first two arguments are a pointer to a suitable vector
        and its length, and the third argument points to a byte stream. The fi-
        nal argument is a pointer to a general context, which can  be  used  to
-       specify  custom  memory mangagement functions for the decoded patterns.
-       If this argument is NULL, malloc() and free() are used. After deserial-
-       ization, the byte stream is no longer needed and can be discarded.
+       specify custom memory management functions for the decoded patterns. If
+       this argument is NULL, malloc() and free() are used. After deserializa-
+       tion, the byte stream is no longer needed and can be discarded.
 
          pcre2_code *list_of_codes[2];
          uint8_t *bytes = ;
@@ -10536,10 +10891,10 @@ RE-USING PRECOMPILED PATTERNS
        compiled on a system with different endianness.
 
        Decoded patterns can be used for matching in the usual way, and must be
-       freed by calling pcre2_code_free(). However, be aware that there  is  a
-       potential  race  issue if you are using multiple patterns that were de-
-       coded from a single byte stream in a multithreaded application. A  sin-
-       gle  copy  of  the character tables is used by all the decoded patterns
+       freed  by  calling pcre2_code_free(). However, be aware that there is a
+       potential race issue if you are using multiple patterns that  were  de-
+       coded  from a single byte stream in a multithreaded application. A sin-
+       gle copy of the character tables is used by all  the  decoded  patterns
        and a reference count is used to arrange for its memory to be automati-
        cally  freed when the last pattern is freed, but there is no locking on
        this reference count. Therefore, if you want to call  pcre2_code_free()
@@ -10556,7 +10911,7 @@ RE-USING PRECOMPILED PATTERNS
 AUTHOR
 
        Philip Hazel
-       University Computing Service
+       Retired from University Computing Service
        Cambridge, England.
 
 
@@ -10564,16 +10919,20 @@ REVISION
 
        Last updated: 27 June 2018
        Copyright (c) 1997-2018 University of Cambridge.
+
+
+PCRE2 10.32                      27 June 2018                PCRE2SERIALIZE(3)
 ------------------------------------------------------------------------------
 
 
-PCRE2SYNTAX(3)             Library Functions Manual             PCRE2SYNTAX(3)
 
+PCRE2SYNTAX(3)             Library Functions Manual             PCRE2SYNTAX(3)
 
 
 NAME
        PCRE2 - Perl-compatible regular expressions (revised API)
 
+
 PCRE2 REGULAR EXPRESSION SYNTAX SUMMARY
 
        The  full syntax and semantics of the regular expressions that are sup-
@@ -10586,6 +10945,20 @@ QUOTING
          \x         where x is non-alphanumeric is a literal x
          \Q...\E    treat enclosed characters as literal
 
+       Note that white space inside \Q...\E is always treated as literal, even
+       if PCRE2_EXTENDED is set, causing most other white space to be ignored.
+
+
+BRACED ITEMS
+
+       With  one  exception, wherever brace characters { and } are required to
+       enclose data for constructions such as \g{2} or \k{name}, space  and/or
+       horizontal  tab  characters  that follow { or precede } are allowed and
+       are ignored. In the case of quantifiers, they may also appear before or
+       after the comma. The exception is \u{...} which is not  Perl-compatible
+       and is recognized only when PCRE2_EXTRA_ALT_BSUX is set. This is an EC-
+       MAScript compatibility feature, and follows ECMAScript's behaviour.
+
 
 ESCAPED CHARACTERS
 
@@ -10593,7 +10966,7 @@ ESCAPED CHARACTERS
        escape sequence causes an error.
 
          \a         alarm, that is, the BEL character (hex 07)
-         \cx        "control-x", where x is any ASCII printing character
+         \cx        "control-x", where x is a non-control ASCII character
          \e         escape (hex 1B)
          \f         form feed (hex 0C)
          \n         newline (hex 0A)
@@ -10613,11 +10986,11 @@ ESCAPED CHARACTERS
          \uhhhh     character with hex code hhhh
          \u{hh..}   character with hex code hh.. but only for EXTRA_ALT_BSUX
 
-       When  \x  is not followed by {, from zero to two hexadecimal digits are
-       read, but in ALT_BSUX mode \x must be followed by two hexadecimal  dig-
-       its  to  be  recognized as a hexadecimal escape; otherwise it matches a
-       literal "x".  Likewise, if \u (in ALT_BSUX mode)  is  not  followed  by
-       four  hexadecimal  digits or (in EXTRA_ALT_BSUX mode) a sequence of hex
+       When \x is not followed by {, from zero to two hexadecimal  digits  are
+       read,  but in ALT_BSUX mode \x must be followed by two hexadecimal dig-
+       its to be recognized as a hexadecimal escape; otherwise  it  matches  a
+       literal  "x".   Likewise,  if  \u (in ALT_BSUX mode) is not followed by
+       four hexadecimal digits or (in EXTRA_ALT_BSUX mode) a sequence  of  hex
        digits in curly brackets, it matches a literal "u".
 
        Note that \0dd is always an octal code. The treatment of backslash fol-
@@ -10625,7 +10998,7 @@ ESCAPED CHARACTERS
        "Non-printing characters" in the pcre2pattern documentation, where  de-
        tails  of  escape  processing  in  EBCDIC  environments are also given.
        \N{U+hh..} is synonymous with \x{hh..} in PCRE2 but is not supported in
-       EBCDIC  environments.  Note  that  \N  not followed by an opening curly
+       EBCDIC environments. Note that \N not  followed  by  an  opening  curly
        bracket has a different meaning (see below).
 
 
@@ -10650,17 +11023,19 @@ CHARACTER TYPES
          \W         a "non-word" character
          \X         a Unicode extended grapheme cluster
 
-       \C is dangerous because it may leave the current matching point in  the
+       \C  is dangerous because it may leave the current matching point in the
        middle of a UTF-8 or UTF-16 character. The application can lock out the
        use of \C by setting the PCRE2_NEVER_BACKSLASH_C  option.  It  is  also
        possible to build PCRE2 with the use of \C permanently disabled.
 
        By  default,  \d, \s, and \w match only ASCII characters, even in UTF-8
        mode or in the 16-bit and 32-bit libraries. However, if locale-specific
-       matching  is  happening,  \s and \w may also match characters with code
+       matching is happening, \s and \w may also match  characters  with  code
        points in the range 128-255. If the PCRE2_UCP option is set, the behav-
        iour of these escape sequences is changed to use Unicode properties and
-       they match many more characters.
+       they  match  many  more  characters, but there are some option settings
+       that can restrict individual sequences to matching only  ASCII  charac-
+       ters.
 
        Property descriptions in \p and \P are matched caselessly; hyphens, un-
        derscores,  and  white  space are ignored, in accordance with Unicode's
@@ -10721,7 +11096,7 @@ PCRE2 SPECIAL CATEGORY PROPERTIES FOR \p and \P
          Xan        Alphanumeric: union of properties L and N
          Xps        POSIX space: property Z or tab, NL, VT, FF, CR
          Xsp        Perl space: property Z or tab, NL, VT, FF, CR
-         Xuc        Univerally-named character: one that can be
+         Xuc        Universally-named character: one that can be
                       represented by a Universal Character Name
          Xwd        Perl word: property Xan or underscore
 
@@ -10731,9 +11106,9 @@ PCRE2 SPECIAL CATEGORY PROPERTIES FOR \p and \P
 
 BINARY PROPERTIES FOR \p AND \P
 
-       Unicode  defines  a  number  of  binary properties, that is, properties
-       whose only values are true or false. You can obtain  a  list  of  those
-       that  are  recognized  by \p and \P, along with their abbreviations, by
+       Unicode defines a number of  binary  properties,  that  is,  properties
+       whose  only  values  are  true or false. You can obtain a list of those
+       that are recognized by \p and \P, along with  their  abbreviations,  by
        running this command:
 
          pcre2test -LP
@@ -10741,8 +11116,8 @@ BINARY PROPERTIES FOR \p AND \P
 
 SCRIPT MATCHING WITH \p AND \P
 
-       Many script names and their 4-letter abbreviations  are  recognized  in
-       \p{sc:...}  or  \p{scx:...} items, or on their own with \p (and also \P
+       Many  script  names  and their 4-letter abbreviations are recognized in
+       \p{sc:...} or \p{scx:...} items, or on their own with \p (and  also  \P
        of course). You can obtain a list of these scripts by running this com-
        mand:
 
@@ -10827,6 +11202,9 @@ QUANTIFIERS
          {n,}        n or more, greedy
          {n,}+       n or more, possessive
          {n,}?       n or more, lazy
+         {,m}        zero up to m, greedy
+         {,m}+       zero up to m, possessive
+         {,m}?       zero up to m, lazy
 
 
 ANCHORS AND SIMPLE ASSERTIONS
@@ -10892,18 +11270,29 @@ OPTION SETTING
        Changes  of these options within a group are automatically cancelled at
        the end of the group.
 
+         (?a)            all ASCII options
+         (?aD)           restrict \d to ASCII in UCP mode
+         (?aS)           restrict \s to ASCII in UCP mode
+         (?aW)           restrict \w to ASCII in UCP mode
+         (?aP)           restrict all POSIX classes to ASCII in UCP mode
+         (?aT)           restrict POSIX digit classes to ASCII in UCP mode
          (?i)            caseless
          (?J)            allow duplicate named groups
          (?m)            multiline
          (?n)            no auto capture
+         (?r)            restrict caseless to either ASCII or non-ASCII
          (?s)            single line (dotall)
          (?U)            default ungreedy (lazy)
-         (?x)            extended: ignore white space except in classes
+         (?x)            ignore white space except in classes or \Q...\E
          (?xx)           as (?x) but also ignore space and tab in classes
-         (?-...)         unset option(s)
-         (?^)            unset imnsx options
+         (?-...)         unset the given option(s)
+         (?^)            unset imnrsx options
+
+       (?aP) implies (?aT) as well, though this has no additional effect. How-
+       ever, it means that (?-aP) is really (?-PT) which  disables  all  ASCII
+       restrictions for POSIX classes.
 
-       Unsetting x or xx unsets both. Several options may be set at once,  and
+       Unsetting  x or xx unsets both. Several options may be set at once, and
        a mixture of setting and unsetting such as (?i-x) is allowed, but there
        may be only one hyphen. Setting (but no unsetting) is allowed after (?^
        for example (?^in). An option setting may appear at the start of a non-
@@ -10929,7 +11318,7 @@ OPTION SETTING
        value   of   the   limits   set  by  the  caller  of  pcre2_match()  or
        pcre2_dfa_match(), not increase them. LIMIT_RECURSION  is  an  obsolete
        synonym for LIMIT_DEPTH. The application can lock out the use of (*UTF)
-       and (*UCP) by setting the PCRE2_NEVER_UTF or  PCRE2_NEVER_UCP  options,
+       and  (*UCP)  by setting the PCRE2_NEVER_UTF or PCRE2_NEVER_UCP options,
        respectively, at compile time.
 
 
@@ -10973,7 +11362,12 @@ LOOKAHEAD AND LOOKBEHIND ASSERTIONS
          (*nlb:...)                  ) negative lookbehind
          (*negative_lookbehind:...)  )
 
-       Each top-level branch of a lookbehind must be of a fixed length.
+       Each top-level branch of a lookbehind must have a limit for the  number
+       of  characters it matches. If any branch can match a variable number of
+       characters, the maximum for each branch is limited to a  value  set  by
+       the  caller  of  pcre2_compile()  or defaulted. The default is set when
+       PCRE2 is built (ultimate default 255). If every branch matches a  fixed
+       number of characters, the limit for each branch is 65535 characters.
 
 
 NON-ATOMIC LOOKAROUND ASSERTIONS
@@ -11038,8 +11432,8 @@ CONDITIONAL PATTERNS
          (?(condition)yes-pattern|no-pattern)
 
          (?(n)               absolute reference condition
-         (?(+n)              relative reference condition
-         (?(-n)              relative reference condition
+         (?(+n)              relative reference condition (PCRE2 extension)
+         (?(-n)              relative reference condition (PCRE2 extension)
          (?()          named reference condition (Perl)
          (?('name')          named reference condition (Perl)
          (?(name)            named reference condition (PCRE2, deprecated)
@@ -11067,7 +11461,7 @@ BACKTRACKING CONTROL
          (*FAIL)         force backtrack; synonym (*F)
          (*MARK:NAME)    set name to be passed back; synonym (*:NAME)
 
-       The  following  act only when a subsequent match failure causes a back-
+       The following act only when a subsequent match failure causes  a  back-
        track to reach them. They all force a match failure, but they differ in
        what happens afterwards. Those that advance the start-of-match point do
        so only if the pattern is not anchored.
@@ -11079,7 +11473,7 @@ BACKTRACKING CONTROL
                          (*MARK:NAME); if not found, the (*SKIP) is ignored
          (*THEN)         local failure, backtrack to next alternation
 
-       The effect of one of these verbs in a group called as a  subroutine  is
+       The  effect  of one of these verbs in a group called as a subroutine is
        confined to the subroutine call.
 
 
@@ -11110,22 +11504,26 @@ AUTHOR
 
 REVISION
 
-       Last updated: 12 January 2022
-       Copyright (c) 1997-2022 University of Cambridge.
+       Last updated: 12 October 2023
+       Copyright (c) 1997-2023 University of Cambridge.
+
+
+PCRE2 10.43                     12 October 2023                 PCRE2SYNTAX(3)
 ------------------------------------------------------------------------------
 
 
-PCRE2UNICODE(3)            Library Functions Manual            PCRE2UNICODE(3)
 
+PCRE2UNICODE(3)            Library Functions Manual            PCRE2UNICODE(3)
 
 
 NAME
        PCRE - Perl-compatible regular expressions (revised API)
 
+
 UNICODE AND UTF SUPPORT
 
        PCRE2 is normally built with Unicode support, though if you do not need
-       it, you can build it  without,  in  which  case  the  library  will  be
+       it,  you  can  build  it  without,  in  which  case the library will be
        smaller. With Unicode support, PCRE2 has knowledge of Unicode character
        properties and can process strings of text in UTF-8, UTF-16, and UTF-32
        format (depending on the code unit width), but this is not the default.
@@ -11135,49 +11533,51 @@ UNICODE AND UTF SUPPORT
        There  are two ways of telling PCRE2 to switch to UTF mode, where char-
        acters may consist of more than one code unit and the range  of  values
        is constrained. The program can call pcre2_compile() with the PCRE2_UTF
-       option, or the pattern may start with the  sequence  (*UTF).   However,
-       the  latter  facility  can be locked out by the PCRE2_NEVER_UTF option.
-       That is, the programmer can prevent the supplier of  the  pattern  from
+       option,  or  the  pattern may start with the sequence (*UTF).  However,
+       the latter facility can be locked out by  the  PCRE2_NEVER_UTF  option.
+       That  is,  the  programmer can prevent the supplier of the pattern from
        switching to UTF mode.
 
-       Note   that  the  PCRE2_MATCH_INVALID_UTF  option  (see  below)  forces
+       Note  that  the  PCRE2_MATCH_INVALID_UTF  option  (see  below)   forces
        PCRE2_UTF to be set.
 
-       In UTF mode, both the pattern and any subject strings that are  matched
-       against  it are treated as UTF strings instead of strings of individual
-       one-code-unit characters. There are also some other changes to the  way
+       In  UTF mode, both the pattern and any subject strings that are matched
+       against it are treated as UTF strings instead of strings of  individual
+       one-code-unit  characters. There are also some other changes to the way
        characters are handled, as documented below.
 
 
 UNICODE PROPERTY SUPPORT
 
-       When  PCRE2 is built with Unicode support, the escape sequences \p{..},
+       When PCRE2 is built with Unicode support, the escape sequences  \p{..},
        \P{..}, and \X can be used. This is not dependent on the PCRE2_UTF set-
        ting.   The Unicode properties that can be tested are a subset of those
        that Perl supports. Currently they are limited to the general  category
        properties such as Lu for an upper case letter or Nd for a decimal num-
-       ber, the Unicode script  names  such  as  Arabic  or  Han,  Bidi_Class,
-       Bidi_Control,  and the derived properties Any and LC (synonym L&). Full
-       lists are given in the pcre2pattern and pcre2syntax  documentation.  In
-       general,  only the short names for properties are supported.  For exam-
-       ple, \p{L} matches a letter. Its longer  synonym,  \p{Letter},  is  not
-       supported. Furthermore, in Perl, many properties may optionally be pre-
-       fixed by "Is", for compatibility with Perl 5.6. PCRE2 does not  support
-       this.
+       ber, the derived properties Any and LC (synonym L&), the Unicode script
+       names such as Arabic or Han, Bidi_Class, Bidi_Control, and a few binary
+       properties.
+
+       The full lists are given in the pcre2pattern and pcre2syntax documenta-
+       tion.  In  general,  only the short names for properties are supported.
+       For example, \p{L} matches a letter. Its longer synonym, \p{Letter}, is
+       not supported. Furthermore, in Perl, many properties may optionally  be
+       prefixed  by "Is", for compatibility with Perl 5.6. PCRE2 does not sup-
+       port this.
 
 
 WIDE CHARACTERS AND UTF MODES
 
        Code points less than 256 can be specified in patterns by either braced
        or unbraced hexadecimal escape sequences (for example, \x{b3} or \xb3).
-       Larger  values have to use braced sequences. Unbraced octal code points
+       Larger values have to use braced sequences. Unbraced octal code  points
        up to \777 are also recognized; larger ones can be coded using \o{...}.
 
-       The escape sequence \N{U+} is recognized as another way  of
-       specifying  a  Unicode character by code point in a UTF mode. It is not
+       The  escape sequence \N{U+} is recognized as another way of
+       specifying a Unicode character by code point in a UTF mode. It  is  not
        allowed in non-UTF mode.
 
-       In UTF mode, repeat quantifiers apply to complete UTF  characters,  not
+       In  UTF  mode, repeat quantifiers apply to complete UTF characters, not
        to individual code units.
 
        In UTF mode, the dot metacharacter matches one UTF character instead of
@@ -11188,7 +11588,7 @@ WIDE CHARACTERS AND UTF MODES
 
        The  escape  sequence \C can be used to match a single code unit in UTF
        mode, but its use can lead to some strange effects because it breaks up
-       multi-unit  characters  (see  the description of \C in the pcre2pattern
+       multi-unit characters (see the description of \C  in  the  pcre2pattern
        documentation). For this reason, there is a build-time option that dis-
        ables  support  for  \C completely. There is also a less draconian com-
        pile-time option for locking out the use of \C when a pattern  is  com-
@@ -11196,8 +11596,8 @@ WIDE CHARACTERS AND UTF MODES
 
        The  use  of  \C  is not supported by the alternative matching function
        pcre2_dfa_match() when in UTF-8 or UTF-16 mode, that is, when a charac-
-       ter  may  consist  of  more  than one code unit. The use of \C in these
-       modes provokes a match-time error. Also, the JIT optimization does  not
+       ter may consist of more than one code unit. The  use  of  \C  in  these
+       modes  provokes a match-time error. Also, the JIT optimization does not
        support \C in these modes. If JIT optimization is requested for a UTF-8
        or UTF-16 pattern that contains \C, it will not succeed,  and  so  when
        pcre2_match() is called, the matching will be carried out by the inter-
@@ -11208,21 +11608,24 @@ WIDE CHARACTERS AND UTF MODES
        PCRE2 recognizes as digits, spaces, or word characters remain the  same
        set  as  in  non-UTF mode, all with code points less than 256. This re-
        mains true even when PCRE2 is built to include Unicode support, because
-       to  do  otherwise  would  slow down matching in many common cases. Note
-       that this also applies to \b and \B, because they are defined in  terms
-       of  \w  and \W. If you want to test for a wider sense of, say, "digit",
-       you can use explicit Unicode property tests such  as  \p{Nd}.  Alterna-
+       to do otherwise would slow down matching in  many  common  cases.  Note
+       that  this also applies to \b and \B, because they are defined in terms
+       of \w and \W. If you want to test for a wider sense of,  say,  "digit",
+       you  can  use  explicit Unicode property tests such as \p{Nd}. Alterna-
        tively, if you set the PCRE2_UCP option, the way that the character es-
        capes work is changed so that Unicode properties are used to  determine
-       which  characters  match.  There  are  more  details  in the section on
-       generic character types in the pcre2pattern documentation.
+       which  characters  match,  though  there are some options that suppress
+       this for individual escapes. For details see  the  section  on  generic
+       character types in the pcre2pattern documentation.
 
-       Similarly, characters that match the POSIX named character classes  are
-       all low-valued characters, unless the PCRE2_UCP option is set.
+       Like  the  escapes,  characters  that  match  the POSIX named character
+       classes are all low-valued characters unless the  PCRE2_UCP  option  is
+       set, but there is an option to override this.
 
-       However,  the  special horizontal and vertical white space matching es-
-       capes (\h, \H, \v, and \V) do match all the appropriate Unicode charac-
-       ters, whether or not PCRE2_UCP is set.
+       In contrast to the character escapes and character classes, the special
+       horizontal  and  vertical  white  space escapes (\h, \H, \v, and \V) do
+       match all the appropriate Unicode characters, whether or not  PCRE2_UCP
+       is set.
 
 
 UNICODE CASE-EQUIVALENCE
@@ -11236,19 +11639,27 @@ UNICODE CASE-EQUIVALENCE
        PCRE2_UTF  allows  Unicode-style  case processing for non-UTF character
        encodings such as UCS-2.
 
+       There are two ASCII characters (S and K) that,  in  addition  to  their
+       ASCII  lower case equivalents, have a non-ASCII one as well (long S and
+       Kelvin sign).  Recognition of these non-ASCII characters as case-equiv-
+       alent to their ASCII  counterparts  can  be  disabled  by  setting  the
+       PCRE2_EXTRA_CASELESS_RESTRICT  option. When this is set, all characters
+       in a case equivalence must either be ASCII or non-ASCII; there  can  be
+       no mixing.
+
 
 SCRIPT RUNS
 
-       The pattern constructs (*script_run:...) and  (*atomic_script_run:...),
-       with  synonyms (*sr:...) and (*asr:...), verify that the string matched
-       within the parentheses is a script run. In concept, a script run  is  a
-       sequence  of characters that are all from the same Unicode script. How-
+       The  pattern constructs (*script_run:...) and (*atomic_script_run:...),
+       with synonyms (*sr:...) and (*asr:...), verify that the string  matched
+       within  the  parentheses is a script run. In concept, a script run is a
+       sequence of characters that are all from the same Unicode script.  How-
        ever, because some scripts are commonly used together, and because some
        diacritical  and  other marks are used with multiple scripts, it is not
        that simple.
 
        Every Unicode character has a Script property, mostly with a value cor-
-       responding  to the name of a script, such as Latin, Greek, or Cyrillic.
+       responding to the name of a script, such as Latin, Greek, or  Cyrillic.
        There are also three special values:
 
        "Unknown" is used for code points that have not been assigned, and also
@@ -11265,8 +11676,8 @@ SCRIPT RUNS
        ify a previous character. These are considered to take on the script of
        the character that they modify.
 
-       Some Inherited characters are used with many scripts, but many of  them
-       are  only  normally  used  with a small number of scripts. For example,
+       Some  Inherited characters are used with many scripts, but many of them
+       are only normally used with a small number  of  scripts.  For  example,
        U+102E0 (Coptic Epact thousands mark) is used only with Arabic and Cop-
        tic.  In  order  to  make it possible to check this, a Unicode property
        called Script Extension exists. Its value is a list of scripts that ap-
@@ -11277,9 +11688,9 @@ SCRIPT RUNS
        their Script Extension list.
 
        The next section describes the basic rules for deciding whether a given
-       string of characters is a script run. Note,  however,  that  there  are
-       some  special cases involving the Chinese Han script, and an additional
-       constraint for decimal digits. These are  covered  in  subsequent  sec-
+       string  of  characters  is  a script run. Note, however, that there are
+       some special cases involving the Chinese Han script, and an  additional
+       constraint  for  decimal  digits.  These are covered in subsequent sec-
        tions.
 
    Basic script run rules
@@ -11291,81 +11702,81 @@ SCRIPT RUNS
 
        If a character's Script Extension property is the single value  "Inher-
        ited", it is always accepted as part of a script run. This is also true
-       for the property "Common", subject to the checking  of  decimal  digits
+       for  the  property  "Common", subject to the checking of decimal digits
        described below. All the remaining characters in a script run must have
        at least one script in common in their Script Extension lists. In  set-
        theoretic terminology, the intersection of all the sets of scripts must
        not be empty.
 
-       A simple example is an Internet name such as "google.com". The  letters
+       A  simple example is an Internet name such as "google.com". The letters
        are all in the Latin script, and the dot is Common, so this string is a
        script run.  However, the Cyrillic letter "o" looks exactly the same as
-       the  Latin "o"; a string that looks the same, but with Cyrillic "o"s is
+       the Latin "o"; a string that looks the same, but with Cyrillic "o"s  is
        not a script run.
 
-       More interesting examples involve characters with more than one  script
+       More  interesting examples involve characters with more than one script
        in their Script Extension. Consider the following characters:
 
          U+060C  Arabic comma
          U+06D4  Arabic full stop
 
-       The  first  has the Script Extension list Arabic, Hanifi Rohingya, Syr-
-       iac, and Thaana; the second has just Arabic and Hanifi  Rohingya.  Both
-       of  them  could  appear  in  script runs of either Arabic or Hanifi Ro-
-       hingya. The first could also appear in Syriac or  Thaana  script  runs,
+       The first has the Script Extension list Arabic, Hanifi  Rohingya,  Syr-
+       iac,  and  Thaana; the second has just Arabic and Hanifi Rohingya. Both
+       of them could appear in script runs of  either  Arabic  or  Hanifi  Ro-
+       hingya.  The  first  could also appear in Syriac or Thaana script runs,
        but the second could not.
 
    The Chinese Han script
 
-       The  Chinese  Han  script  is  commonly  used in conjunction with other
-       scripts for writing certain languages. Japanese uses the  Hiragana  and
-       Katakana  scripts  together  with Han; Korean uses Hangul and Han; Tai-
-       wanese Mandarin uses Bopomofo and Han.  These  three  combinations  are
-       treated  as special cases when checking script runs and are, in effect,
-       "virtual scripts". Thus, a script run may contain a  mixture  of  Hira-
-       gana,  Katakana,  and Han, or a mixture of Hangul and Han, or a mixture
-       of Bopomofo and Han, but not, for example,  a  mixture  of  Hangul  and
-       Bopomofo  and  Han. PCRE2 (like Perl) follows Unicode's Technical Stan-
-       dard  39   ("Unicode   Security   Mechanisms",   http://unicode.org/re-
+       The Chinese Han script is  commonly  used  in  conjunction  with  other
+       scripts  for  writing certain languages. Japanese uses the Hiragana and
+       Katakana scripts together with Han; Korean uses Hangul  and  Han;  Tai-
+       wanese  Mandarin  uses  Bopomofo  and Han. These three combinations are
+       treated as special cases when checking script runs and are, in  effect,
+       "virtual  scripts".  Thus,  a script run may contain a mixture of Hira-
+       gana, Katakana, and Han, or a mixture of Hangul and Han, or  a  mixture
+       of  Bopomofo  and  Han,  but  not, for example, a mixture of Hangul and
+       Bopomofo and Han. PCRE2 (like Perl) follows Unicode's  Technical  Stan-
+       dard   39   ("Unicode   Security   Mechanisms",  http://unicode.org/re-
        ports/tr39/) in allowing such mixtures.
 
    Decimal digits
 
-       Unicode  contains  many sets of 10 decimal digits in different scripts,
-       and some scripts (including the Common script) contain  more  than  one
-       set.  Some  of these decimal digits them are visually indistinguishable
-       from the common ASCII digits. In addition to the  script  checking  de-
-       scribed  above,  if a script run contains any decimal digits, they must
+       Unicode contains many sets of 10 decimal digits in  different  scripts,
+       and  some  scripts  (including the Common script) contain more than one
+       set. Some of these decimal digits them are  visually  indistinguishable
+       from  the  common  ASCII digits. In addition to the script checking de-
+       scribed above, if a script run contains any decimal digits,  they  must
        all come from the same set of 10 adjacent characters.
 
 
 VALIDITY OF UTF STRINGS
 
-       When the PCRE2_UTF option is set, the strings passed  as  patterns  and
+       When  the  PCRE2_UTF  option is set, the strings passed as patterns and
        subjects are (by default) checked for validity on entry to the relevant
        functions. If an invalid UTF string is passed, a negative error code is
-       returned.  The  code  unit offset to the offending character can be ex-
-       tracted from the match data  block  by  calling  pcre2_get_startchar(),
+       returned. The code unit offset to the offending character  can  be  ex-
+       tracted  from  the  match  data block by calling pcre2_get_startchar(),
        which is used for this purpose after a UTF error.
 
-       In  some  situations, you may already know that your strings are valid,
-       and therefore want to skip these checks in  order  to  improve  perfor-
-       mance,  for  example in the case of a long subject string that is being
-       scanned repeatedly.  If you set the PCRE2_NO_UTF_CHECK option  at  com-
-       pile  time  or at match time, PCRE2 assumes that the pattern or subject
+       In some situations, you may already know that your strings  are  valid,
+       and  therefore  want  to  skip these checks in order to improve perfor-
+       mance, for example in the case of a long subject string that  is  being
+       scanned  repeatedly.   If you set the PCRE2_NO_UTF_CHECK option at com-
+       pile time or at match time, PCRE2 assumes that the pattern  or  subject
        it is given (respectively) contains only valid UTF code unit sequences.
 
-       If you pass an invalid UTF string when PCRE2_NO_UTF_CHECK is  set,  the
-       result  is undefined and your program may crash or loop indefinitely or
-       give incorrect results. There is, however, one mode  of  matching  that
-       can  handle  invalid  UTF  subject  strings. This is enabled by passing
-       PCRE2_MATCH_INVALID_UTF to pcre2_compile() and is  discussed  below  in
-       the  next  section.  The  rest  of  this  section  covers the case when
+       If  you  pass an invalid UTF string when PCRE2_NO_UTF_CHECK is set, the
+       result is undefined and your program may crash or loop indefinitely  or
+       give  incorrect  results.  There is, however, one mode of matching that
+       can handle invalid UTF subject strings.  This  is  enabled  by  passing
+       PCRE2_MATCH_INVALID_UTF  to  pcre2_compile()  and is discussed below in
+       the next section. The  rest  of  this  section  covers  the  case  when
        PCRE2_MATCH_INVALID_UTF is not set.
 
-       Passing PCRE2_NO_UTF_CHECK to pcre2_compile()  just  disables  the  UTF
-       check  for  the  pattern; it does not also apply to subject strings. If
-       you want to disable the check for a subject string you must  pass  this
+       Passing  PCRE2_NO_UTF_CHECK  to  pcre2_compile()  just disables the UTF
+       check for the pattern; it does not also apply to  subject  strings.  If
+       you  want  to disable the check for a subject string you must pass this
        same option to pcre2_match() or pcre2_dfa_match().
 
        UTF-16 and UTF-32 strings can indicate their endianness by special code
@@ -11376,33 +11787,33 @@ VALIDITY OF UTF STRINGS
        other  processing  takes  place.  In  the  case  of  pcre2_match()  and
        pcre2_dfa_match()  calls  with a non-zero starting offset, the check is
        applied only to that part of the subject that could be inspected during
-       matching,  and  there is a check that the starting offset points to the
-       first code unit of a character or to the end of the subject.  If  there
-       are  no  lookbehind  assertions in the pattern, the check starts at the
-       starting offset.  Otherwise, it starts at the  length  of  the  longest
-       lookbehind  before  the starting offset, or at the start of the subject
-       if there are not that many characters before the starting offset.  Note
+       matching, and there is a check that the starting offset points  to  the
+       first  code  unit of a character or to the end of the subject. If there
+       are no lookbehind assertions in the pattern, the check  starts  at  the
+       starting  offset.   Otherwise,  it  starts at the length of the longest
+       lookbehind before the starting offset, or at the start of  the  subject
+       if  there are not that many characters before the starting offset. Note
        that the sequences \b and \B are one-character lookbehinds.
 
-       In  addition  to checking the format of the string, there is a check to
+       In addition to checking the format of the string, there is a  check  to
        ensure that all code points lie in the range U+0 to U+10FFFF, excluding
        the  surrogate  area. The so-called "non-character" code points are not
        excluded because Unicode corrigendum #9 makes it clear that they should
        not be.
 
-       Characters  in  the "Surrogate Area" of Unicode are reserved for use by
-       UTF-16, where they are used in pairs to encode code points with  values
-       greater  than  0xFFFF. The code points that are encoded by UTF-16 pairs
-       are available independently in the  UTF-8  and  UTF-32  encodings.  (In
-       other  words, the whole surrogate thing is a fudge for UTF-16 which un-
+       Characters in the "Surrogate Area" of Unicode are reserved for  use  by
+       UTF-16,  where they are used in pairs to encode code points with values
+       greater than 0xFFFF. The code points that are encoded by  UTF-16  pairs
+       are  available  independently  in  the  UTF-8 and UTF-32 encodings. (In
+       other words, the whole surrogate thing is a fudge for UTF-16 which  un-
        fortunately messes up UTF-8 and UTF-32.)
 
-       Setting PCRE2_NO_UTF_CHECK at compile time does not disable  the  error
-       that  is  given if an escape sequence for an invalid Unicode code point
-       is encountered in the pattern. If you want to  allow  escape  sequences
-       such  as  \x{d800}  (a  surrogate code point) you can set the PCRE2_EX-
-       TRA_ALLOW_SURROGATE_ESCAPES extra option.  However,  this  is  possible
-       only  in  UTF-8  and  UTF-32 modes, because these values are not repre-
+       Setting  PCRE2_NO_UTF_CHECK  at compile time does not disable the error
+       that is given if an escape sequence for an invalid Unicode  code  point
+       is  encountered  in  the pattern. If you want to allow escape sequences
+       such as \x{d800} (a surrogate code point) you  can  set  the  PCRE2_EX-
+       TRA_ALLOW_SURROGATE_ESCAPES  extra  option.  However,  this is possible
+       only in UTF-8 and UTF-32 modes, because these  values  are  not  repre-
        sentable in UTF-16.
 
    Errors in UTF-8 strings
@@ -11415,10 +11826,10 @@ VALIDITY OF UTF STRINGS
          PCRE2_ERROR_UTF8_ERR4
          PCRE2_ERROR_UTF8_ERR5
 
-       The string ends with a truncated UTF-8 character;  the  code  specifies
-       how  many bytes are missing (1 to 5). Although RFC 3629 restricts UTF-8
-       characters to be no longer than 4 bytes, the  encoding  scheme  (origi-
-       nally  defined  by  RFC  2279)  allows  for  up to 6 bytes, and this is
+       The  string  ends  with a truncated UTF-8 character; the code specifies
+       how many bytes are missing (1 to 5). Although RFC 3629 restricts  UTF-8
+       characters  to  be  no longer than 4 bytes, the encoding scheme (origi-
+       nally defined by RFC 2279) allows for  up  to  6  bytes,  and  this  is
        checked first; hence the possibility of 4 or 5 missing bytes.
 
          PCRE2_ERROR_UTF8_ERR6
@@ -11444,8 +11855,8 @@ VALIDITY OF UTF STRINGS
 
          PCRE2_ERROR_UTF8_ERR14
 
-       A 3-byte character has a value in the  range  0xd800  to  0xdfff;  this
-       range  of code points are reserved by RFC 3629 for use with UTF-16, and
+       A  3-byte  character  has  a  value in the range 0xd800 to 0xdfff; this
+       range of code points are reserved by RFC 3629 for use with UTF-16,  and
        so are excluded from UTF-8.
 
          PCRE2_ERROR_UTF8_ERR15
@@ -11454,9 +11865,9 @@ VALIDITY OF UTF STRINGS
          PCRE2_ERROR_UTF8_ERR18
          PCRE2_ERROR_UTF8_ERR19
 
-       A 2-, 3-, 4-, 5-, or 6-byte character is "overlong", that is, it  codes
-       for  a  value that can be represented by fewer bytes, which is invalid.
-       For example, the two bytes 0xc0, 0xae give the value 0x2e,  whose  cor-
+       A  2-, 3-, 4-, 5-, or 6-byte character is "overlong", that is, it codes
+       for a value that can be represented by fewer bytes, which  is  invalid.
+       For  example,  the two bytes 0xc0, 0xae give the value 0x2e, whose cor-
        rect coding uses just one byte.
 
          PCRE2_ERROR_UTF8_ERR20
@@ -11493,24 +11904,31 @@ VALIDITY OF UTF STRINGS
 MATCHING IN INVALID UTF STRINGS
 
        You can run pattern matches on subject strings that may contain invalid
-       UTF sequences if you  call  pcre2_compile()  with  the  PCRE2_MATCH_IN-
-       VALID_UTF  option.  This  is  supported by pcre2_match(), including JIT
+       UTF  sequences  if  you  call  pcre2_compile() with the PCRE2_MATCH_IN-
+       VALID_UTF option. This is supported  by  pcre2_match(),  including  JIT
        matching, but not by pcre2_dfa_match(). When PCRE2_MATCH_INVALID_UTF is
        set,  it  forces  PCRE2_UTF  to be set as well. Note, however, that the
        pattern itself must be a valid UTF string.
 
-       Setting PCRE2_MATCH_INVALID_UTF does not  affect  what  pcre2_compile()
-       generates,  but  if pcre2_jit_compile() is subsequently called, it does
+       If you do not set PCRE2_MATCH_INVALID_UTF when  calling  pcre2_compile,
+       and  you  are  not  certain that your subject strings are valid UTF se-
+       quences, you should not make  use  of  the  JIT  "fast  path"  function
+       pcre2_jit_match()  because it bypasses sanity checks, including the one
+       for UTF validity. An invalid string may cause undefined behaviour,  in-
+       cluding looping, crashing, or giving the wrong answer.
+
+       Setting  PCRE2_MATCH_INVALID_UTF  does  not affect what pcre2_compile()
+       generates, but if pcre2_jit_compile() is subsequently called,  it  does
        generate different code. If JIT is not used, the option affects the be-
        haviour of the interpretive code in pcre2_match(). When PCRE2_MATCH_IN-
-       VALID_UTF is set at compile  time,  PCRE2_NO_UTF_CHECK  is  ignored  at
+       VALID_UTF  is  set  at  compile  time, PCRE2_NO_UTF_CHECK is ignored at
        match time.
 
-       In  this  mode,  an  invalid  code  unit  sequence in the subject never
-       matches any pattern item. It does not match  dot,  it  does  not  match
-       \p{Any},  it does not even match negative items such as [^X]. A lookbe-
-       hind assertion fails if it encounters an invalid sequence while  moving
-       the  current  point backwards. In other words, an invalid UTF code unit
+       In this mode, an invalid  code  unit  sequence  in  the  subject  never
+       matches  any  pattern  item.  It  does not match dot, it does not match
+       \p{Any}, it does not even match negative items such as [^X]. A  lookbe-
+       hind  assertion fails if it encounters an invalid sequence while moving
+       the current point backwards. In other words, an invalid UTF  code  unit
        sequence acts as a barrier which no match can cross.
 
        You can also think of this as the subject being split up into fragments
@@ -11528,15 +11946,20 @@ MATCHING IN INVALID UTF STRINGS
        next valid UTF character, or the end of the subject.
 
        At internal fragment boundaries, \b and \B behave in the same way as at
-       the  beginning  and end of the subject. For example, a sequence such as
-       \bWORD\b would match an instance of WORD that is surrounded by  invalid
+       the beginning and end of the subject. For example, a sequence  such  as
+       \bWORD\b  would match an instance of WORD that is surrounded by invalid
        UTF code units.
 
-       Using  PCRE2_MATCH_INVALID_UTF, an application can run matches on arbi-
-       trary data, knowing that any matched  strings  that  are  returned  are
+       Using PCRE2_MATCH_INVALID_UTF, an application can run matches on  arbi-
+       trary  data,  knowing  that  any  matched strings that are returned are
        valid UTF. This can be useful when searching for UTF text in executable
        or other binary files.
 
+       Note, however, that the  16-bit  and  32-bit  PCRE2  libraries  process
+       strings  as  sequences of uint16_t or uint32_t code points. They cannot
+       find valid UTF sequences within an arbitrary  string  of  bytes  unless
+       such sequences are suitably aligned.
+
 
 AUTHOR
 
@@ -11547,8 +11970,11 @@ AUTHOR
 
 REVISION
 
-       Last updated: 22 December 2021
-       Copyright (c) 1997-2021 University of Cambridge.
+       Last updated: 12 October 2023
+       Copyright (c) 1997-2023 University of Cambridge.
+
+
+PCRE2 10.43                    04 February 2023                PCRE2UNICODE(3)
 ------------------------------------------------------------------------------
 
 
diff --git a/pcre2/doc/pcre2_compile.3 b/pcre2/doc/pcre2_compile.3
index 5a07b8b..151a703 100644
--- a/pcre2/doc/pcre2_compile.3
+++ b/pcre2/doc/pcre2_compile.3
@@ -1,4 +1,4 @@
-.TH PCRE2_COMPILE 3 "22 April 2022" "PCRE2 10.41"
+.TH PCRE2_COMPILE 3 "19 January 2024" "PCRE2 10.43"
 .SH NAME
 PCRE2 - Perl-compatible regular expressions (revised API)
 .SH SYNOPSIS
@@ -20,24 +20,26 @@ arguments are:
 .sp
   \fIpattern\fP       A string containing expression to be compiled
   \fIlength\fP        The length of the string or PCRE2_ZERO_TERMINATED
-  \fIoptions\fP       Option bits
+  \fIoptions\fP       Primary option bits
   \fIerrorcode\fP     Where to put an error code
   \fIerroffset\fP     Where to put an error offset
   \fIccontext\fP      Pointer to a compile context or NULL
 .sp
 The length of the pattern and any error offset that is returned are in code
-units, not characters. A compile context is needed only if you want to provide
-custom memory allocation functions, or to provide an external function for
-system stack size checking, or to change one or more of these parameters:
+units, not characters. A NULL pattern with zero length is treated as an empty
+string. A compile context is needed only if you want to provide custom memory
+allocation functions, or to provide an external function for system stack size
+checking (see \fBpcre2_set_compile_recursion_guard()\fP), or to change one or
+more of these parameters:
 .sp
   What \eR matches (Unicode newlines, or CR, LF, CRLF only);
   PCRE2's character tables;
   The newline character sequence;
   The compile time nested parentheses limit;
-  The maximum pattern length (in code units) that is allowed.
-  The additional options bits (see pcre2_set_compile_extra_options())
+  The maximum pattern length (in code units) that is allowed;
+  The additional options bits.
 .sp
-The option bits are:
+The primary option bits are:
 .sp
   PCRE2_ANCHORED           Force pattern anchoring
   PCRE2_ALLOW_EMPTY_CLASS  Allow empty classes
@@ -84,7 +86,7 @@ If either of \fIerrorcode\fP or \fIerroroffset\fP is NULL, the function returns
 NULL immediately. Otherwise, the yield of this function is a pointer to a
 private data structure that contains the compiled pattern, or NULL if an error
 was detected. In the error case, a text error message can be obtained by
-passing the value returned via the \fIerrorcode\fP argument to the the
+passing the value returned via the \fIerrorcode\fP argument to the
 \fBpcre2_get_error_message()\fP function. The offset (in code units) where the
 error was encountered is returned via the \fIerroroffset\fP argument.
 .P
diff --git a/pcre2/doc/pcre2_general_context_create.3 b/pcre2/doc/pcre2_general_context_create.3
index a3e6c10..e204a95 100644
--- a/pcre2/doc/pcre2_general_context_create.3
+++ b/pcre2/doc/pcre2_general_context_create.3
@@ -8,7 +8,7 @@ PCRE2 - Perl-compatible regular expressions (revised API)
 .PP
 .nf
 .B pcre2_general_context *pcre2_general_context_create(
-.B "  void *(*\fIprivate_malloc\fP)(PCRE2_SIZE, void *),"
+.B "  void *(*\fIprivate_malloc\fP)(size_t, void *),"
 .B "  void (*\fIprivate_free\fP)(void *, void *), void *\fImemory_data\fP);"
 .fi
 .
diff --git a/pcre2/doc/pcre2_get_match_data_heapframes_size.3 b/pcre2/doc/pcre2_get_match_data_heapframes_size.3
new file mode 100644
index 0000000..1eba42b
--- /dev/null
+++ b/pcre2/doc/pcre2_get_match_data_heapframes_size.3
@@ -0,0 +1,28 @@
+.TH PCRE2_GET_MATCH_DATA_HEAPFRAMES_SIZE 3 "13 January 2023" "PCRE2 10.43"
+.SH NAME
+PCRE2 - Perl-compatible regular expressions (revised API)
+.SH SYNOPSIS
+.rs
+.sp
+.B #include 
+.PP
+.nf
+.B PCRE2_SIZE pcre2_get_match_data_heapframes_size(
+.B "  pcre2_match_data *\fImatch_data\fP);"
+.fi
+.
+.SH DESCRIPTION
+.rs
+.sp
+This function returns the size, in bytes, of the heapframes data block that is
+owned by its argument.
+.P
+There is a complete description of the PCRE2 native API in the
+.\" HREF
+\fBpcre2api\fP
+.\"
+page and a description of the POSIX API in the
+.\" HREF
+\fBpcre2posix\fP
+.\"
+page.
diff --git a/pcre2/doc/pcre2_jit_match.3 b/pcre2/doc/pcre2_jit_match.3
index 5877fcb..72c4bc1 100644
--- a/pcre2/doc/pcre2_jit_match.3
+++ b/pcre2/doc/pcre2_jit_match.3
@@ -1,4 +1,4 @@
-.TH PCRE2_JIT_MATCH 3 "11 February 2020" "PCRE2 10.35"
+.TH PCRE2_JIT_MATCH 3 "20 January 2023" "PCRE2 10.43"
 .SH NAME
 PCRE2 - Perl-compatible regular expressions (revised API)
 .SH SYNOPSIS
@@ -20,7 +20,15 @@ This function matches a compiled regular expression that has been successfully
 processed by the JIT compiler against a given subject string, using a matching
 algorithm that is similar to Perl's. It is a "fast path" interface to JIT, and
 it bypasses some of the sanity checks that \fBpcre2_match()\fP applies.
-Its arguments are exactly the same as for
+.P
+In UTF mode, the subject string is not checked for UTF validity. Unless
+PCRE2_MATCH_INVALID_UTF was set when the pattern was compiled, passing an
+invalid UTF string results in undefined behaviour. Your program may crash or
+loop or give wrong results. In the absence of PCRE2_MATCH_INVALID_UTF you
+should only call \fBpcre2_jit_match()\fP in UTF mode if you are sure the
+subject is valid.
+.P
+The arguments for \fBpcre2_jit_match()\fP are exactly the same as for
 .\" HREF
 \fBpcre2_match()\fP,
 .\"
@@ -29,7 +37,7 @@ PCRE2_ZERO_TERMINATED is not supported.
 .P
 The supported options are PCRE2_NOTBOL, PCRE2_NOTEOL, PCRE2_NOTEMPTY,
 PCRE2_NOTEMPTY_ATSTART, PCRE2_PARTIAL_HARD, and PCRE2_PARTIAL_SOFT. Unsupported
-options are ignored. The subject string is not checked for UTF validity.
+options are ignored.
 .P
 The return values are the same as for \fBpcre2_match()\fP plus
 PCRE2_ERROR_JIT_BADOPTION if a matching mode (partial or complete) is requested
diff --git a/pcre2/doc/pcre2_jit_stack_create.3 b/pcre2/doc/pcre2_jit_stack_create.3
index d332b72..74cdb1d 100644
--- a/pcre2/doc/pcre2_jit_stack_create.3
+++ b/pcre2/doc/pcre2_jit_stack_create.3
@@ -7,8 +7,8 @@ PCRE2 - Perl-compatible regular expressions (revised API)
 .B #include 
 .PP
 .nf
-.B pcre2_jit_stack *pcre2_jit_stack_create(PCRE2_SIZE \fIstartsize\fP,
-.B "  PCRE2_SIZE \fImaxsize\fP, pcre2_general_context *\fIgcontext\fP);"
+.B pcre2_jit_stack *pcre2_jit_stack_create(size_t \fIstartsize\fP,
+.B "  size_t \fImaxsize\fP, pcre2_general_context *\fIgcontext\fP);"
 .fi
 .
 .SH DESCRIPTION
diff --git a/pcre2/doc/pcre2_match.3 b/pcre2/doc/pcre2_match.3
index 2be2dd0..efdd892 100644
--- a/pcre2/doc/pcre2_match.3
+++ b/pcre2/doc/pcre2_match.3
@@ -1,4 +1,4 @@
-.TH PCRE2_MATCH 3 "16 October 2018" "PCRE2 10.33"
+.TH PCRE2_MATCH 3 "27 January 2024" "PCRE2 10.43"
 .SH NAME
 PCRE2 - Perl-compatible regular expressions (revised API)
 .SH SYNOPSIS
@@ -50,6 +50,8 @@ terminated by a binary zero code unit. The options are:
   PCRE2_ANCHORED          Match only at the first position
   PCRE2_COPY_MATCHED_SUBJECT
                           On success, make a private subject copy
+  PCRE2_DISABLE_RECURSELOOP_CHECK
+                          Only useful in rare cases; use with care
   PCRE2_ENDANCHORED       Pattern can match only at end of subject
   PCRE2_NOTBOL            Subject string is not the beginning of a line
   PCRE2_NOTEOL            Subject string is not the end of a line
diff --git a/pcre2/doc/pcre2_match_data_free.3 b/pcre2/doc/pcre2_match_data_free.3
index cebdef9..202035a 100644
--- a/pcre2/doc/pcre2_match_data_free.3
+++ b/pcre2/doc/pcre2_match_data_free.3
@@ -1,4 +1,4 @@
-.TH PCRE2_MATCH_DATA_FREE 3 "16 October 2018" "PCRE2 10.33"
+.TH PCRE2_MATCH_DATA_FREE 3 "18 January 2023" "PCRE2 10.43"
 .SH NAME
 PCRE2 - Perl-compatible regular expressions (revised API)
 .SH SYNOPSIS
@@ -16,11 +16,13 @@ PCRE2 - Perl-compatible regular expressions (revised API)
 If \fImatch_data\fP is NULL, this function does nothing. Otherwise,
 \fImatch_data\fP must point to a match data block, which this function frees,
 using the memory freeing function from the general context or compiled pattern
-with which it was created, or \fBfree()\fP if that was not set.
+with which it was created, or \fBfree()\fP if that was not set. If the match
+data block was previously passed to \fBpcre2_match()\fP, it will have an
+attached heapframe vector; this is also freed.
 .P
 If the PCRE2_COPY_MATCHED_SUBJECT was used for a successful match using this
-match data block, the copy of the subject that was remembered with the block is
-also freed.
+match data block, the copy of the subject that was referenced within the block
+is also freed.
 .P
 There is a complete description of the PCRE2 native API in the
 .\" HREF
diff --git a/pcre2/doc/pcre2_set_compile_extra_options.3 b/pcre2/doc/pcre2_set_compile_extra_options.3
index 0dcc8de..a1e07e9 100644
--- a/pcre2/doc/pcre2_set_compile_extra_options.3
+++ b/pcre2/doc/pcre2_set_compile_extra_options.3
@@ -1,4 +1,4 @@
-.TH PCRE2_SET_COMPILE_EXTRA_OPTIONS 3 "31 August 2021" "PCRE2 10.38"
+.TH PCRE2_SET_COMPILE_EXTRA_OPTIONS 3 "03 February 2023" "PCRE2 10.43"
 .SH NAME
 PCRE2 - Perl-compatible regular expressions (revised API)
 .SH SYNOPSIS
@@ -25,9 +25,21 @@ options are:
 .\" JOIN
   PCRE2_EXTRA_ALT_BSUX                 Extended alternate \eu, \eU, and
                                          \ex handling
+  PCRE2_EXTRA_ASCII_BSD                \ed remains ASCII in UCP mode
+  PCRE2_EXTRA_ASCII_BSS                \es remains ASCII in UCP mode
+  PCRE2_EXTRA_ASCII_BSW                \ew remains ASCII in UCP mode
+.\" JOIN
+  PCRE2_EXTRA_ASCII_DIGIT              [:digit:] and [:xdigit:] POSIX classes
+                                         remain ASCII in UCP mode
+.\" JOIN
+  PCRE2_EXTRA_ASCII_POSIX              POSIX classes remain ASCII in
+                                         UCP mode
 .\" JOIN
   PCRE2_EXTRA_BAD_ESCAPE_IS_LITERAL    Treat all invalid escapes as
                                          a literal following character
+.\" JOIN
+  PCRE2_EXTRA_CASELESS_RESTRICT        Disable mixed ASCII/non-ASCII
+                                         case folding
   PCRE2_EXTRA_ESCAPED_CR_IS_LF         Interpret \er as \en
   PCRE2_EXTRA_MATCH_LINE               Pattern matches whole lines
   PCRE2_EXTRA_MATCH_WORD               Pattern matches "words"
diff --git a/pcre2/doc/pcre2_set_max_pattern_compiled_length.3 b/pcre2/doc/pcre2_set_max_pattern_compiled_length.3
new file mode 100644
index 0000000..472a7bb
--- /dev/null
+++ b/pcre2/doc/pcre2_set_max_pattern_compiled_length.3
@@ -0,0 +1,32 @@
+.TH PCRE2_SET_MAX_PATTERN_COMPILED_LENGTH 3 "24 April 2024" "PCRE2 10.44"
+.SH NAME
+PCRE2 - Perl-compatible regular expressions (revised API)
+.SH SYNOPSIS
+.rs
+.sp
+.B #include 
+.PP
+.nf
+.B int pcre2_set_max_pattern_compiled_length(
+.B "  pcre2_compile_context *\fIccontext\fP, PCRE2_SIZE \fIvalue\fP);"
+.fi
+.
+.SH DESCRIPTION
+.rs
+.sp
+This function sets, in a compile context, the maximum size (in bytes) for the
+memory needed to hold the compiled version of a pattern that is compiled with
+this context. The result is always zero. If a pattern that is passed to
+\fBpcre2_compile()\fP with this context needs more memory, an error is
+generated. The default is the largest number that a PCRE2_SIZE variable can
+hold, which is effectively unlimited.
+.P
+There is a complete description of the PCRE2 native API in the
+.\" HREF
+\fBpcre2api\fP
+.\"
+page and a description of the POSIX API in the
+.\" HREF
+\fBpcre2posix\fP
+.\"
+page.
diff --git a/pcre2/doc/pcre2_set_max_varlookbehind.3 b/pcre2/doc/pcre2_set_max_varlookbehind.3
new file mode 100644
index 0000000..84639d9
--- /dev/null
+++ b/pcre2/doc/pcre2_set_max_varlookbehind.3
@@ -0,0 +1,30 @@
+.TH PCRE2_SET_NEWLINE 3 "09 August 2023" "PCRE2 10.43"
+.SH NAME
+PCRE2 - Perl-compatible regular expressions (revised API)
+.SH SYNOPSIS
+.rs
+.sp
+.B #include 
+.PP
+.nf
+.B int pcre2_set_max_varlookbehind(pcre2_compile_context *\fIccontext\fP,
+.B "  uint32_t \fIvalue\fP);"
+.fi
+.
+.SH DESCRIPTION
+.rs
+.sp
+This sets a maximum length for the number of characters matched by a
+variable-length lookbehind assertion. The default is set when PCRE2 is built,
+with the ultimate default being 255, the same as Perl. Lookbehind assertions
+without a bounding length are not supported. The result is always zero.
+.P
+There is a complete description of the PCRE2 native API in the
+.\" HREF
+\fBpcre2api\fP
+.\"
+page and a description of the POSIX API in the
+.\" HREF
+\fBpcre2posix\fP
+.\"
+page.
diff --git a/pcre2/doc/pcre2_set_recursion_memory_management.3 b/pcre2/doc/pcre2_set_recursion_memory_management.3
index 12f175d..743c288 100644
--- a/pcre2/doc/pcre2_set_recursion_memory_management.3
+++ b/pcre2/doc/pcre2_set_recursion_memory_management.3
@@ -9,7 +9,7 @@ PCRE2 - Perl-compatible regular expressions (revised API)
 .nf
 .B int pcre2_set_recursion_memory_management(
 .B "  pcre2_match_context *\fImcontext\fP,"
-.B "  void *(*\fIprivate_malloc\fP)(PCRE2_SIZE, void *),"
+.B "  void *(*\fIprivate_malloc\fP)(size_t, void *),"
 .B "  void (*\fIprivate_free\fP)(void *, void *), void *\fImemory_data\fP);"
 .fi
 .
diff --git a/pcre2/doc/pcre2_substring_list_free.3 b/pcre2/doc/pcre2_substring_list_free.3
index d977ed5..2c6fb02 100644
--- a/pcre2/doc/pcre2_substring_list_free.3
+++ b/pcre2/doc/pcre2_substring_list_free.3
@@ -1,4 +1,4 @@
-.TH PCRE2_SUBSTRING_LIST_FREE 3 "28 June 2018" "PCRE2 10.32"
+.TH PCRE2_SUBSTRING_LIST_FREE 3 "02 December 2023" "PCRE2 10.43"
 .SH NAME
 PCRE2 - Perl-compatible regular expressions (revised API)
 .SH SYNOPSIS
@@ -7,7 +7,7 @@ PCRE2 - Perl-compatible regular expressions (revised API)
 .B #include 
 .PP
 .SM
-.B void pcre2_substring_list_free(PCRE2_SPTR *\fIlist\fP);
+.B void pcre2_substring_list_free(PCRE2_UCHAR **\fIlist\fP);
 .
 .SH DESCRIPTION
 .rs
diff --git a/pcre2/doc/pcre2api.3 b/pcre2/doc/pcre2api.3
index 28c6033..6028d62 100644
--- a/pcre2/doc/pcre2api.3
+++ b/pcre2/doc/pcre2api.3
@@ -1,4 +1,4 @@
-.TH PCRE2API 3 "27 July 2022" "PCRE2 10.41"
+.TH PCRE2API 3 "24 April 2024" "PCRE2 10.44"
 .SH NAME
 PCRE2 - Perl-compatible regular expressions (revised API)
 .sp
@@ -49,6 +49,11 @@ document for an overview of all the PCRE2 documentation.
 .nf
 .B PCRE2_SPTR pcre2_get_mark(pcre2_match_data *\fImatch_data\fP);
 .sp
+.B PCRE2_SIZE pcre2_get_match_data_size(pcre2_match_data *\fImatch_data\fP);
+.sp
+.B PCRE2_SIZE pcre2_get_match_data_heapframes_size(
+.B "  pcre2_match_data *\fImatch_data\fP);"
+.sp
 .B uint32_t pcre2_get_ovector_count(pcre2_match_data *\fImatch_data\fP);
 .sp
 .B PCRE2_SIZE *pcre2_get_ovector_pointer(pcre2_match_data *\fImatch_data\fP);
@@ -96,6 +101,12 @@ document for an overview of all the PCRE2 documentation.
 .B int pcre2_set_max_pattern_length(pcre2_compile_context *\fIccontext\fP,
 .B "  PCRE2_SIZE \fIvalue\fP);"
 .sp
+.B int pcre2_set_max_pattern_compiled_length(
+.B "  pcre2_compile_context *\fIccontext\fP, PCRE2_SIZE \fIvalue\fP);"
+.sp
+.B int pcre2_set_max_varlookbehind(pcre2_compile_contest *\fIccontext\fP,
+.B "  uint32_t \fIvalue\fP);
+.sp
 .B int pcre2_set_newline(pcre2_compile_context *\fIccontext\fP,
 .B "  uint32_t \fIvalue\fP);"
 .sp
@@ -173,7 +184,7 @@ document for an overview of all the PCRE2 documentation.
 .B int pcre2_substring_number_from_name(const pcre2_code *\fIcode\fP,
 .B "  PCRE2_SPTR \fIname\fP);"
 .sp
-.B void pcre2_substring_list_free(PCRE2_SPTR *\fIlist\fP);
+.B void pcre2_substring_list_free(PCRE2_UCHAR **\fIlist\fP);
 .sp
 .B int pcre2_substring_list_get(pcre2_match_data *\fImatch_data\fP,
 .B "  PCRE2_UCHAR ***\fIlistptr\fP, PCRE2_SIZE **\fIlengthsptr\fP);
@@ -206,8 +217,8 @@ document for an overview of all the PCRE2 documentation.
 .sp
 .B void pcre2_jit_free_unused_memory(pcre2_general_context *\fIgcontext\fP);
 .sp
-.B pcre2_jit_stack *pcre2_jit_stack_create(PCRE2_SIZE \fIstartsize\fP,
-.B "  PCRE2_SIZE \fImaxsize\fP, pcre2_general_context *\fIgcontext\fP);"
+.B pcre2_jit_stack *pcre2_jit_stack_create(size_t \fIstartsize\fP,
+.B "  size_t \fImaxsize\fP, pcre2_general_context *\fIgcontext\fP);"
 .sp
 .B void pcre2_jit_stack_assign(pcre2_match_context *\fImcontext\fP,
 .B "  pcre2_jit_callback \fIcallback_function\fP, void *\fIcallback_data\fP);"
@@ -270,7 +281,7 @@ document for an overview of all the PCRE2 documentation.
 .sp
 .B int pcre2_set_recursion_memory_management(
 .B "  pcre2_match_context *\fImcontext\fP,"
-.B "  void *(*\fIprivate_malloc\fP)(PCRE2_SIZE, void *),"
+.B "  void *(*\fIprivate_malloc\fP)(size_t, void *),"
 .B "  void (*\fIprivate_free\fP)(void *, void *), void *\fImemory_data\fP);"
 .fi
 .sp
@@ -324,10 +335,8 @@ This contains the function prototypes and other definitions for all three
 libraries. One, two, or all three can be installed simultaneously. On Unix-like
 systems the libraries are called \fBlibpcre2-8\fP, \fBlibpcre2-16\fP, and
 \fBlibpcre2-32\fP, and they can also co-exist with the original PCRE libraries.
-.P
-Character strings are passed to and from a PCRE2 library as a sequence of
-unsigned integers in code units of the appropriate width. Every PCRE2 function
-comes in three different forms, one for each library, for example:
+Every PCRE2 function comes in three different forms, one for each library, for
+example:
 .sp
   \fBpcre2_compile_8()\fP
   \fBpcre2_compile_16()\fP
@@ -338,10 +347,15 @@ There are also three different sets of data types:
   \fBPCRE2_UCHAR8, PCRE2_UCHAR16, PCRE2_UCHAR32\fP
   \fBPCRE2_SPTR8,  PCRE2_SPTR16,  PCRE2_SPTR32\fP
 .sp
-The UCHAR types define unsigned code units of the appropriate widths. For
-example, PCRE2_UCHAR16 is usually defined as `uint16_t'. The SPTR types are
-constant pointers to the equivalent UCHAR types, that is, they are pointers to
-vectors of unsigned code units.
+The UCHAR types define unsigned code units of the appropriate widths.
+For example, PCRE2_UCHAR16 is usually defined as `uint16_t'.
+The SPTR types are pointers to constants of the equivalent UCHAR types,
+that is, they are pointers to vectors of unsigned code units.
+.P
+Character strings are passed to a PCRE2 library as sequences of unsigned
+integers in code units of the appropriate width. The length of a string may
+be given as a number of code units, or the string may be specified as
+zero-terminated.
 .P
 Many applications use only one code unit width. For their convenience, macros
 are defined whose names are the generic forms such as \fBpcre2_compile()\fP and
@@ -378,7 +392,7 @@ names, without the _8, _16, or _32 suffix.
 PCRE2 has its own native API, which is described in this document. There are
 also some wrapper functions for the 8-bit library that correspond to the
 POSIX regular expression API, but they do not give access to all the
-functionality of PCRE2. They are described in the
+functionality of PCRE2 and they are not thread-safe. They are described in the
 .\" HREF
 \fBpcre2posix\fP
 .\"
@@ -490,7 +504,8 @@ unsigned integer type, currently always defined as \fIsize_t\fP. The largest
 value that can be stored in such a type (that is ~(PCRE2_SIZE)0) is reserved
 as a special indicator for zero-terminated strings and unset offsets.
 Therefore, the longest string that can be handled is one less than this
-maximum.
+maximum. Note that string lengths are always given in code units. Only in the
+8-bit library is such a length the same as the number of bytes in the string.
 .
 .
 .\" HTML 
@@ -793,6 +808,28 @@ external sources can limit their size. The default is the largest number that a
 PCRE2_SIZE variable can hold, which is effectively unlimited.
 .sp
 .nf
+.B int pcre2_set_max_pattern_compiled_length(
+.B "  pcre2_compile_context *\fIccontext\fP, PCRE2_SIZE \fIvalue\fP);"
+.fi
+.sp
+This sets a maximum size, in bytes, for the memory needed to hold the compiled
+version of a pattern that is compiled with this context. If the pattern needs
+more memory, an error is generated. This facility is provided so that
+applications that accept patterns from external sources can limit the amount of
+memory they use. The default is the largest number that a PCRE2_SIZE variable
+can hold, which is effectively unlimited.
+.sp
+.nf
+.B int pcre2_set_max_varlookbehind(pcre2_compile_contest *\fIccontext\fP,
+.B "  uint32_t \fIvalue\fP);
+.fi
+.sp
+This sets a maximum length for the number of characters matched by a
+variable-length lookbehind assertion. The default is set when PCRE2 is built,
+with the ultimate default being 255, the same as Perl. Lookbehind assertions
+without a bounding length are not supported.
+.sp
+.nf
 .B int pcre2_set_newline(pcre2_compile_context *\fIccontext\fP,
 .B "  uint32_t \fIvalue\fP);"
 .fi
@@ -1002,10 +1039,9 @@ matching that goes on for a very long time, and so the \fImatch_limit\fP value
 is also used in this case (but in a different way) to limit how long the
 matching can continue.
 .P
-The default value for the limit can be set when PCRE2 is built; the default
-default is 10 million, which handles all but the most extreme cases. A value
-for the match limit may also be supplied by an item at the start of a pattern
-of the form
+The default value for the limit can be set when PCRE2 is built; the default is
+10 million, which handles all but the most extreme cases. A value for the match
+limit may also be supplied by an item at the start of a pattern of the form
 .sp
   (*LIMIT_MATCH=ddd)
 .sp
@@ -1115,7 +1151,13 @@ for the amount of heap memory used by \fBpcre2_match()\fP or
   PCRE2_CONFIG_JIT
 .sp
 The output is a uint32_t integer that is set to one if support for just-in-time
-compiling is available; otherwise it is set to zero.
+compiling is included in the library; otherwise it is set to zero. Note that
+having the support in the library does not guarantee that JIT will be used for
+any given match. See the
+.\" HREF
+\fBpcre2jit\fP
+.\"
+documentation for more details.
 .sp
   PCRE2_CONFIG_JITTARGET
 .sp
@@ -1235,10 +1277,12 @@ zero.
 .fi
 .P
 The \fBpcre2_compile()\fP function compiles a pattern into an internal form.
-The pattern is defined by a pointer to a string of code units and a length (in
-code units). If the pattern is zero-terminated, the length can be specified as
-PCRE2_ZERO_TERMINATED. The function returns a pointer to a block of memory that
-contains the compiled pattern and related data, or NULL if an error occurred.
+The pattern is defined by a pointer to a string of code units and a length in
+code units. If the pattern is zero-terminated, the length can be specified as
+PCRE2_ZERO_TERMINATED. A NULL pattern pointer with a length of zero is treated
+as an empty string (NULL with a non-zero length causes an error return). The
+function returns a pointer to a block of memory that contains the compiled
+pattern and related data, or NULL if an error occurred.
 .P
 If the compile context argument \fIccontext\fP is NULL, memory for the compiled
 pattern is obtained by calling \fBmalloc()\fP. Otherwise, it is obtained from
@@ -1467,11 +1511,13 @@ PCRE2_UCP is set, Unicode properties are used for all characters with more than
 one other case, and for all characters whose code points are greater than
 U+007F. Note that there are two ASCII characters, K and S, that, in addition to
 their lower case ASCII equivalents, are case-equivalent with U+212A (Kelvin
-sign) and U+017F (long S) respectively. For lower valued characters with only
-one other case, a lookup table is used for speed. When neither PCRE2_UTF nor
-PCRE2_UCP is set, a lookup table is used for all code points less than 256, and
-higher code points (available only in 16-bit or 32-bit mode) are treated as not
-having another case.
+sign) and U+017F (long S) respectively. If you do not want this case
+equivalence, you can suppress it by setting PCRE2_EXTRA_CASELESS_RESTRICT.
+.P
+For lower valued characters with only one other case, a lookup table is used
+for speed. When neither PCRE2_UTF nor PCRE2_UCP is set, a lookup table is used
+for all code points less than 256, and higher code points (available only in
+16-bit or 32-bit mode) are treated as not having another case.
 .sp
   PCRE2_DOLLAR_ENDONLY
 .sp
@@ -1530,13 +1576,13 @@ the end of the subject.
   PCRE2_EXTENDED
 .sp
 If this bit is set, most white space characters in the pattern are totally
-ignored except when escaped or inside a character class. However, white space
-is not allowed within sequences such as (?> that introduce various
-parenthesized groups, nor within numerical quantifiers such as {1,3}. Ignorable
-white space is permitted between an item and a following quantifier and between
-a quantifier and a following + that indicates possessiveness. PCRE2_EXTENDED is
-equivalent to Perl's /x option, and it can be changed within a pattern by a
-(?x) option setting.
+ignored except when escaped, inside a character class, or inside a \eQ...\eE
+sequence. However, white space is not allowed within sequences such as (?> that
+introduce various parenthesized groups, nor within numerical quantifiers such
+as {1,3}. Ignorable white space is permitted between an item and a following
+quantifier and between a quantifier and a following + that indicates
+possessiveness. PCRE2_EXTENDED is equivalent to Perl's /x option, and it can be
+changed within a pattern by a (?x) option setting.
 .P
 When PCRE2 is compiled without Unicode support, PCRE2_EXTENDED recognizes as
 white space only those characters with code points less than 256 that are
@@ -1596,7 +1642,7 @@ PCRE2_FIRSTLINE if \fIstartoffset\fP is greater than 3. See also
 PCRE2_USE_OFFSET_LIMIT, which provides a more general limiting facility. If
 PCRE2_FIRSTLINE is set with an offset limit, a match must occur in the first
 line and also within the offset limit. In other words, whichever limit comes
-first is used.
+first is used. This option has no effect for anchored patterns.
 .sp
   PCRE2_LITERAL
 .sp
@@ -1615,7 +1661,11 @@ PCRE2_EXTRA_MATCH_WORD are also supported. Any other options cause an error.
 .sp
 This option forces PCRE2_UTF (see below) and also enables support for matching
 by \fBpcre2_match()\fP in subject strings that contain invalid UTF sequences.
-This facility is not supported for DFA matching. For details, see the
+Note, however, that the 16-bit and 32-bit PCRE2 libraries process strings as
+sequences of uint16_t or uint32_t code points. They cannot find valid UTF
+sequences within an arbitrary string of bytes unless such sequences are
+suitably aligned. This facility is not supported for DFA matching. For details,
+see the
 .\" HREF
 \fBpcre2unicode\fP
 .\"
@@ -1817,8 +1867,9 @@ are not representable in UTF-16.
 This option has two effects. Firstly, it change the way PCRE2 processes \eB,
 \eb, \eD, \ed, \eS, \es, \eW, \ew, and some of the POSIX character classes. By
 default, only ASCII characters are recognized, but if PCRE2_UCP is set, Unicode
-properties are used instead to classify characters. More details are given in
-the section on
+properties are used to classify characters. There are some PCRE2_EXTRA
+options (see below) that add finer control to this behaviour. More details are
+given in the section on
 .\" HTML 
 .\" 
 generic character types
@@ -1827,14 +1878,15 @@ in the
 .\" HREF
 \fBpcre2pattern\fP
 .\"
-page. If you set PCRE2_UCP, matching one of the items it affects takes much
-longer.
+page.
 .P
 The second effect of PCRE2_UCP is to force the use of Unicode properties for
-upper/lower casing operations on characters with code points greater than 127,
-even when PCRE2_UTF is not set. This makes it possible, for example, to process
-strings in the 16-bit UCS-2 code. This option is available only if PCRE2 has
-been compiled with Unicode support (which is the default).
+upper/lower casing operations, even when PCRE2_UTF is not set. This makes it
+possible to process strings in the 16-bit UCS-2 code. This option is available
+only if PCRE2 has been compiled with Unicode support (which is the default).
+The PCRE2_EXTRA_CASELESS_RESTRICT option (see below) restricts caseless
+matching such that ASCII characters match only ASCII characters and non-ASCII
+characters match only non-ASCII characters.
 .sp
   PCRE2_UNGREEDY
 .sp
@@ -1867,8 +1919,7 @@ behaviour of PCRE2 are given in the
 .\" HREF
 \fBpcre2unicode\fP
 .\"
-page. In particular, note that it changes the way PCRE2_CASELESS handles
-characters with code points greater than 127.
+page. In particular, note that it changes the way PCRE2_CASELESS works.
 .
 .
 .\" HTML 
@@ -1914,6 +1965,37 @@ the way that ECMAscript (aka JavaScript) does. Additional functionality was
 defined by ECMAscript 6; setting PCRE2_EXTRA_ALT_BSUX has the effect of
 PCRE2_ALT_BSUX, but in addition it recognizes \eu{hhh..} as a hexadecimal
 character code, where hhh.. is any number of hexadecimal digits.
+.sp
+  PCRE2_EXTRA_ASCII_BSD
+.sp
+This option forces \ed to match only ASCII digits, even when PCRE2_UCP is set.
+It can be changed within a pattern by means of the (?aD) option setting.
+.sp
+  PCRE2_EXTRA_ASCII_BSS
+.sp
+This option forces \es to match only ASCII space characters, even when
+PCRE2_UCP is set. It can be changed within a pattern by means of the (?aS)
+option setting.
+.sp
+  PCRE2_EXTRA_ASCII_BSW
+.sp
+This option forces \ew to match only ASCII word characters, even when PCRE2_UCP
+is set. It can be changed within a pattern by means of the (?aW) option
+setting.
+.sp
+  PCRE2_EXTRA_ASCII_DIGIT
+.sp
+This option forces the POSIX character classes [:digit:] and [:xdigit:] to
+match only ASCII digits, even when PCRE2_UCP is set. It can be changed within
+a pattern by means of the (?aT) option setting.
+.sp
+  PCRE2_EXTRA_ASCII_POSIX
+.sp
+This option forces all the POSIX character classes, including [:digit:] and
+[:xdigit:], to match only ASCII characters, even when PCRE2_UCP is set. It can
+be changed within a pattern by means of the (?aP) option setting, but note that
+this also sets PCRE2_EXTRA_ASCII_DIGIT in order to ensure that (?-aP) unsets
+all ASCII restrictions for POSIX classes.
 .sp
   PCRE2_EXTRA_BAD_ESCAPE_IS_LITERAL
 .sp
@@ -1934,6 +2016,17 @@ that a sequence such as [\eN{] is interpreted as a malformed attempt at
 [\eN{...}] and so is treated as [N{] whereas [\eN] gives an error because an
 unqualified \eN is a valid escape sequence but is not supported in a character
 class. To reiterate: this is a dangerous option. Use with great care.
+.sp
+  PCRE2_EXTRA_CASELESS_RESTRICT
+.sp
+When either PCRE2_UCP or PCRE2_UTF is set, caseless matching follows Unicode
+rules, which allow for more than two cases per character. There are two
+case-equivalent character sets that contain both ASCII and non-ASCII
+characters. The ASCII letter S is case-equivalent to U+017f (long S) and the
+ASCII letter K is case-equivalent to U+212a (Kelvin sign). This option disables
+recognition of case-equivalences that cross the ASCII/non-ASCII boundary. In a
+caseless match, both characters must either be ASCII or non-ASCII. The option
+can be changed with a pattern by the (?r) option setting.
 .sp
   PCRE2_EXTRA_ESCAPED_CR_IS_LF
 .sp
@@ -1976,8 +2069,8 @@ also set.
 .sp
 .B void pcre2_jit_free_unused_memory(pcre2_general_context *\fIgcontext\fP);
 .sp
-.B pcre2_jit_stack *pcre2_jit_stack_create(PCRE2_SIZE \fIstartsize\fP,
-.B "  PCRE2_SIZE \fImaxsize\fP, pcre2_general_context *\fIgcontext\fP);"
+.B pcre2_jit_stack *pcre2_jit_stack_create(size_t \fIstartsize\fP,
+.B "  size_t \fImaxsize\fP, pcre2_general_context *\fIgcontext\fP);"
 .sp
 .B void pcre2_jit_stack_assign(pcre2_match_context *\fImcontext\fP,
 .B "  pcre2_jit_callback \fIcallback_function\fP, void *\fIcallback_data\fP);"
@@ -2023,7 +2116,8 @@ PCRE2_UCP option can be set when a pattern is compiled; this causes \ew and
 friends to use Unicode property support instead of the built-in tables.
 PCRE2_UCP also causes upper/lower casing operations on characters with code
 points greater than 127 to use Unicode properties. These effects apply even
-when PCRE2_UTF is not set.
+when PCRE2_UTF is not set. There are, however, some PCRE2_EXTRA options (see
+above) that can be used to modify or suppress them.
 .P
 The use of locales with Unicode is discouraged. If you are handling characters
 with code points greater than 127, you should either use Unicode support, or
@@ -2519,7 +2613,7 @@ large enough to hold as many as are expected.
 A minimum of at least 1 pair is imposed by \fBpcre2_match_data_create()\fP, so
 it is always possible to return the overall matched string in the case of
 \fBpcre2_match()\fP or the longest match in the case of
-\fBpcre2_dfa_match()\fP. The maximum number of pairs is 65535; if the the first
+\fBpcre2_dfa_match()\fP. The maximum number of pairs is 65535; if the first
 argument of \fBpcre2_match_data_create()\fP is greater than this, 65535 is
 used.
 .P
@@ -2573,6 +2667,45 @@ calling \fBpcre2_match_data_free()\fP. If this function is called with a NULL
 argument, it returns immediately, without doing anything.
 .
 .
+.SH "MEMORY USE FOR MATCH DATA BLOCKS"
+.rs
+.sp
+.nf
+.B PCRE2_SIZE pcre2_get_match_data_size(pcre2_match_data *\fImatch_data\fP);
+.sp
+.B PCRE2_SIZE pcre2_get_match_data_heapframes_size(
+.B "  pcre2_match_data *\fImatch_data\fP);"
+.fi
+.P
+The size of a match data block depends on the size of the ovector that it
+contains. The function \fBpcre2_get_match_data_size()\fP returns the size, in
+bytes, of the block that is its argument.
+.P
+When \fBpcre2_match()\fP runs interpretively (that is, without using JIT), it
+makes use of a vector of data frames for remembering backtracking positions.
+The size of each individual frame depends on the number of capturing
+parentheses in the pattern and can be obtained by calling
+\fBpcre2_pattern_info()\fP with the PCRE2_INFO_FRAMESIZE option (see the
+section entitled "Information about a compiled pattern"
+.\" HTML 
+.\" 
+above).
+.\"
+.P
+Heap memory is used for the frames vector; if the initial memory block turns
+out to be too small during matching, it is automatically expanded. When
+\fBpcre2_match()\fP returns, the memory is not freed, but remains attached to
+the match data block, for use by any subsequent matches that use the same
+block. It is automatically freed when the match data block itself is freed.
+.P
+You can find the current size of the frames vector that a match data block owns
+by calling \fBpcre2_get_match_data_heapframes_size()\fP. For a newly created
+match data block the size will be zero. Some types of match may require a lot
+of frames and thus a large vector; applications that run in environments where
+memory is constrained can check this and free the match data block if the heap
+frames vector has become too big.
+.
+.
 .SH "MATCHING A PATTERN: THE TRADITIONAL FUNCTION"
 .rs
 .sp
@@ -2686,13 +2819,15 @@ the use of .* with PCRE2_DOTALL, not by starting the pattern with ^ or \eA.
 .sp
 The unused bits of the \fIoptions\fP argument for \fBpcre2_match()\fP must be
 zero. The only bits that may be set are PCRE2_ANCHORED,
-PCRE2_COPY_MATCHED_SUBJECT, PCRE2_ENDANCHORED, PCRE2_NOTBOL, PCRE2_NOTEOL,
-PCRE2_NOTEMPTY, PCRE2_NOTEMPTY_ATSTART, PCRE2_NO_JIT, PCRE2_NO_UTF_CHECK,
-PCRE2_PARTIAL_HARD, and PCRE2_PARTIAL_SOFT. Their action is described below.
+PCRE2_COPY_MATCHED_SUBJECT, PCRE2_DISABLE_RECURSELOOP_CHECK, PCRE2_ENDANCHORED,
+PCRE2_NOTBOL, PCRE2_NOTEOL, PCRE2_NOTEMPTY, PCRE2_NOTEMPTY_ATSTART,
+PCRE2_NO_JIT, PCRE2_NO_UTF_CHECK, PCRE2_PARTIAL_HARD, and PCRE2_PARTIAL_SOFT.
+Their action is described below.
 .P
 Setting PCRE2_ANCHORED or PCRE2_ENDANCHORED at match time is not supported by
 the just-in-time (JIT) compiler. If it is set, JIT matching is disabled and the
-interpretive code in \fBpcre2_match()\fP is run. Apart from PCRE2_NO_JIT
+interpretive code in \fBpcre2_match()\fP is run.
+PCRE2_DISABLE_RECURSELOOP_CHECK is ignored by JIT, but apart from PCRE2_NO_JIT
 (obviously), the remaining options are supported for JIT matching.
 .sp
   PCRE2_ANCHORED
@@ -2718,6 +2853,23 @@ the match block itself is used. The copy is automatically freed when
 \fBpcre2_match_data_free()\fP is called to free the match data block. It is also
 automatically freed if the match data block is re-used for another match
 operation.
+.sp
+  PCRE2_DISABLE_RECURSELOOP_CHECK
+.sp
+This option is relevant only to \fBpcre2_match()\fP for interpretive matching.
+It is ignored when JIT is used, and is forbidden for \fBpcre2_dfa_match()\fP.
+.P
+The use of recursion in patterns can lead to infinite loops. In the
+interpretive matcher these would be eventually caught by the match or heap
+limits, but this could take a long time and/or use a lot of memory if the
+limits are large. There is therefore a check at the start of each recursion.
+If the same group is still active from a previous call, and the current subject
+pointer is the same as it was at the start of that group, and the furthest
+inspected character of the subject has not changed, an error is generated.
+.P
+There are rare cases of matches that would complete, but nevertheless trigger
+this error. This option disables the check. It is provided mainly for testing
+when comparing JIT and interpretive behaviour.
 .sp
   PCRE2_ENDANCHORED
 .sp
@@ -2992,8 +3144,8 @@ Offset values that correspond to unused groups at the end of the expression are
 also set to PCRE2_UNSET. For example, if the string "abc" is matched against
 the pattern (abc)(x(yz)?)? groups 2 and 3 are not matched. The return from the
 function is 2, because the highest used capture group number is 1. The offsets
-for for the second and third capture groupss (assuming the vector is large
-enough, of course) are set to PCRE2_UNSET.
+for the second and third capture groups (assuming the vector is large enough,
+of course) are set to PCRE2_UNSET.
 .P
 Elements in the ovector that do not correspond to capturing parentheses in the
 pattern are never changed. That is, if a pattern contains \fIn\fP capturing
@@ -3164,7 +3316,7 @@ The backtracking match limit was reached.
 .sp
   PCRE2_ERROR_NOMEMORY
 .sp
-Heap memory is used to remember backgracking points. This error is given when
+Heap memory is used to remember backtracking points. This error is given when
 the memory allocation function (default or custom) fails. Note that a different
 error, PCRE2_ERROR_HEAPLIMIT, is given if the amount of memory needed exceeds
 the heap limit. PCRE2_ERROR_NOMEMORY is also returned if
@@ -3311,7 +3463,7 @@ capturing slots, substring number 1 is unset.
 .B int pcre2_substring_list_get(pcre2_match_data *\fImatch_data\fP,
 .B "  PCRE2_UCHAR ***\fIlistptr\fP, PCRE2_SIZE **\fIlengthsptr\fP);
 .sp
-.B void pcre2_substring_list_free(PCRE2_SPTR *\fIlist\fP);
+.B void pcre2_substring_list_free(PCRE2_UCHAR **\fIlist\fP);
 .fi
 .P
 The \fBpcre2_substring_list_get()\fP function extracts all available substrings
@@ -3519,7 +3671,8 @@ replacement string causes an immediate return with the relevant UTF error code.
 If PCRE2_SUBSTITUTE_LITERAL is set, the replacement string is not interpreted
 in any way. By default, however, a dollar character is an escape character that
 can specify the insertion of characters from capture groups and names from
-(*MARK) or other control verbs in the pattern. The following forms are always
+(*MARK) or other control verbs in the pattern. Dollar is the only escape
+character (backslash is treated as literal). The following forms are always
 recognized:
 .sp
   $$                  insert a dollar character
@@ -3734,7 +3887,7 @@ PCRE2_SUBSTITUTE_GLOBAL is set, processing continues with a search for the next
 match. If the value is not zero, the current replacement is not accepted. If
 the value is greater than zero, processing continues when
 PCRE2_SUBSTITUTE_GLOBAL is set. Otherwise (the value is less than zero or
-PCRE2_SUBSTITUTE_GLOBAL is not set), the the rest of the input is copied to the
+PCRE2_SUBSTITUTE_GLOBAL is not set), the rest of the input is copied to the
 output and the call to \fBpcre2_substitute()\fP exits, returning the number of
 matches so far.
 .
@@ -4029,6 +4182,6 @@ Cambridge, England.
 .rs
 .sp
 .nf
-Last updated: 27 July 2022
-Copyright (c) 1997-2022 University of Cambridge.
+Last updated: 24 April 2024
+Copyright (c) 1997-2024 University of Cambridge.
 .fi
diff --git a/pcre2/doc/pcre2build.3 b/pcre2/doc/pcre2build.3
index 36728c8..1df4ebd 100644
--- a/pcre2/doc/pcre2build.3
+++ b/pcre2/doc/pcre2build.3
@@ -1,4 +1,4 @@
-.TH PCRE2BUILD 3 "27 July 2022" "PCRE2 10.41"
+.TH PCRE2BUILD 3 "15 April 2024" "PCRE2 10.44"
 .SH NAME
 PCRE2 - Perl-compatible regular expressions (revised API)
 .
@@ -16,7 +16,8 @@ Autotools. Also in the distribution are files to support building using
 .\"
 contains general information about building with Autotools (some of which is
 repeated below), and also has some comments about building on various operating
-systems. There is a lot more information about building PCRE2 without using
+systems. The files in the \fBvms\fP directory support building under OpenVMS.
+There is a lot more information about building PCRE2 without using
 Autotools (including information about using \fBCMake\fP and building "by
 hand") in the text file called
 .\" HTML 
@@ -98,7 +99,17 @@ one of
   --disable-shared
   --disable-static
 .sp
-to the \fBconfigure\fP command.
+to the \fBconfigure\fP command. Setting --disable-shared ensures that PCRE2
+libraries are built as static libraries. The binaries that are then created as
+part of the build process (for example, \fBpcre2test\fP and \fBpcre2grep\fP)
+are linked statically with one or more PCRE2 libraries, but may also be
+dynamically linked with other libraries such as \fBlibc\fP. If you want these
+binaries to be fully statically linked, you can set LDFLAGS like this:
+.sp
+LDFLAGS=--static ./configure --disable-shared
+.sp
+Note the two hyphens in --static. Of course, this works only if static versions
+of all the relevant libraries are available for linking.
 .
 .
 .SH "UNICODE AND UTF SUPPORT"
@@ -317,6 +328,22 @@ used for lookaround assertions, atomic groups, and recursion within patterns.
 The limit does not apply to JIT matching.
 .
 .
+.SH "LIMITING VARIABLE-LENGTH LOOKBEHIND ASSERTIONS"
+.rs
+.sp
+Lookbehind assertions in which one or more branches can match a variable number
+of characters are supported only if there is a maximum matching length for each
+top-level branch. There is a limit to this maximum that defaults to 255
+characters. You can alter this default by a setting such as
+.sp
+  --with-max-varlookbehind=100
+.sp
+The limit can be changed at runtime by calling
+\fBpcre2_set_max_varlookbehind()\fP. Lookbehind assertions in which every
+branch matches a fixed number of characters (not necessarily all the same) are
+not constrained by this limit.
+.
+.
 .\" HTML 
 .SH "CREATING CHARACTER TABLES AT BUILD TIME"
 .rs
@@ -461,7 +488,7 @@ with \fBlibedit\fP, which has a BSD licence.
 .P
 Setting --enable-pcre2test-libreadline causes the \fB-lreadline\fP option to be
 added to the \fBpcre2test\fP build. In many operating environments with a
-sytem-installed readline library this is sufficient. However, in some
+system-installed readline library this is sufficient. However, in some
 environments (e.g. if an unmodified distribution version of readline is in
 use), some extra configuration may be necessary. The INSTALL file for
 \fBlibreadline\fP says this:
@@ -633,6 +660,6 @@ Cambridge, England.
 .rs
 .sp
 .nf
-Last updated: 27 July 2022
-Copyright (c) 1997-2022 University of Cambridge.
+Last updated: 15 April 2024
+Copyright (c) 1997-2024 University of Cambridge.
 .fi
diff --git a/pcre2/doc/pcre2callout.3 b/pcre2/doc/pcre2callout.3
index adb411b..86a1c54 100644
--- a/pcre2/doc/pcre2callout.3
+++ b/pcre2/doc/pcre2callout.3
@@ -1,4 +1,4 @@
-.TH PCRE2CALLOUT 3 "03 February 2019" "PCRE2 10.33"
+.TH PCRE2CALLOUT 3 "19 January 2024" "PCRE2 10.43"
 .SH NAME
 PCRE2 - Perl-compatible regular expressions (revised API)
 .SH SYNOPSIS
@@ -327,12 +327,12 @@ The \fInext_item_length\fP field contains the length of the next item to be
 processed in the pattern string. When the callout is at the end of the pattern,
 the length is zero. When the callout precedes an opening parenthesis, the
 length includes meta characters that follow the parenthesis. For example, in a
-callout before an assertion such as (?=ab) the length is 3. For an an
-alternation bar or a closing parenthesis, the length is one, unless a closing
-parenthesis is followed by a quantifier, in which case its length is included.
-(This changed in release 10.23. In earlier releases, before an opening
-parenthesis the length was that of the entire group, and before an alternation
-bar or a closing parenthesis the length was zero.)
+callout before an assertion such as (?=ab) the length is 3. For an alternation
+bar or a closing parenthesis, the length is one, unless a closing parenthesis
+is followed by a quantifier, in which case its length is included. (This
+changed in release 10.23. In earlier releases, before an opening parenthesis
+the length was that of the entire group, and before an alternation bar or a
+closing parenthesis the length was zero.)
 .P
 The \fIpattern_position\fP and \fInext_item_length\fP fields are intended to
 help in distinguishing between different automatic callouts, which all have the
@@ -443,7 +443,7 @@ value, scanning the pattern stops, and that value is returned from
 .sp
 .nf
 Philip Hazel
-University Computing Service
+Retired from University Computing Service
 Cambridge, England.
 .fi
 .
@@ -452,6 +452,6 @@ Cambridge, England.
 .rs
 .sp
 .nf
-Last updated: 03 February 2019
-Copyright (c) 1997-2019 University of Cambridge.
+Last updated: 19 January 2024
+Copyright (c) 1997-2024 University of Cambridge.
 .fi
diff --git a/pcre2/doc/pcre2compat.3 b/pcre2/doc/pcre2compat.3
index 8333d3e..8313e03 100644
--- a/pcre2/doc/pcre2compat.3
+++ b/pcre2/doc/pcre2compat.3
@@ -1,13 +1,13 @@
-.TH PCRE2COMPAT 3 "08 December 2021" "PCRE2 10.40"
+.TH PCRE2COMPAT 3 "30 November 2023" "PCRE2 10.43"
 .SH NAME
 PCRE2 - Perl-compatible regular expressions (revised API)
 .SH "DIFFERENCES BETWEEN PCRE2 AND PERL"
 .rs
 .sp
-This document describes some of the differences in the ways that PCRE2 and Perl
-handle regular expressions. The differences described here are with respect to
-Perl version 5.34.0, but as both Perl and PCRE2 are continually changing, the
-information may at times be out of date.
+This document describes some of the known differences in the ways that PCRE2
+and Perl handle regular expressions. The differences described here are with
+respect to Perl version 5.38.0, but as both Perl and PCRE2 are continually
+changing, the information may at times be out of date.
 .P
 1. When PCRE2_DOTALL (equivalent to Perl's /s qualifier) is not set, the
 behaviour of the '.' metacharacter differs from Perl. In PCRE2, '.' matches the
@@ -32,12 +32,16 @@ assertion just once). Perl allows some repeat quantifiers on other assertions,
 for example, \eb* , but these do not seem to have any use. PCRE2 does not allow
 any kind of quantifier on non-lookaround assertions.
 .P
-4. Capture groups that occur inside negative lookaround assertions are counted,
+4. If a braced quantifier such as {1,2} appears where there is nothing to
+repeat (for example, at the start of a branch), PCRE2 raises an error whereas
+Perl treats the quantifier characters as literal.
+.P
+5. Capture groups that occur inside negative lookaround assertions are counted,
 but their entries in the offsets vector are set only when a negative assertion
 is a condition that has a matching branch (that is, the condition is false).
 Perl may set such capture groups in other circumstances.
 .P
-5. The following Perl escape sequences are not supported: \eF, \el, \eL, \eu,
+6. The following Perl escape sequences are not supported: \eF, \el, \eL, \eu,
 \eU, and \eN when followed by a character name. \eN on its own, matching a
 non-newline character, and \eN{U+dd..}, matching a Unicode code point, are
 supported. The escapes that modify the case of following letters are
@@ -47,12 +51,13 @@ generated by default. However, if either of the PCRE2_ALT_BSUX or
 PCRE2_EXTRA_ALT_BSUX options is set, \eU and \eu are interpreted as ECMAScript
 interprets them.
 .P
-6. The Perl escape sequences \ep, \eP, and \eX are supported only if PCRE2 is
+7. The Perl escape sequences \ep, \eP, and \eX are supported only if PCRE2 is
 built with Unicode support (the default). The properties that can be tested
 with \ep and \eP are limited to the general category properties such as Lu and
-Nd, script names such as Greek or Han, Bidi_Class, Bidi_Control, and the
-derived properties Any and LC (synonym L&). Both PCRE2 and Perl support the Cs
-(surrogate) property, but in PCRE2 its use is limited. See the
+Nd, the derived properties Any and LC (synonym L&), script names such as Greek
+or Han, Bidi_Class, Bidi_Control, and a few binary properties. Both PCRE2 and
+Perl support the Cs (surrogate) property, but in PCRE2 its use is limited. See
+the
 .\" HREF
 \fBpcre2pattern\fP
 .\"
@@ -60,7 +65,7 @@ documentation for details. The long synonyms for property names that Perl
 supports (such as \ep{Letter}) are not supported by PCRE2, nor is it permitted
 to prefix any of these properties with "Is".
 .P
-7. PCRE2 supports the \eQ...\eE escape for quoting substrings. Characters
+8. PCRE2 supports the \eQ...\eE escape for quoting substrings. Characters
 in between are treated as literals. However, this is slightly different from
 Perl in that $ and @ are also handled as literals inside the quotes. In Perl,
 they cause variable interpolation (PCRE2 does not have variables). Also, Perl
@@ -82,7 +87,7 @@ following examples:
 The \eQ...\eE sequence is recognized both inside and outside character classes
 by both PCRE2 and Perl.
 .P
-8. Fairly obviously, PCRE2 does not support the (?{code}) and (??{code})
+9. Fairly obviously, PCRE2 does not support the (?{code}) and (??{code})
 constructions. However, PCRE2 does have a "callout" feature, which allows an
 external function to be called during pattern matching. See the
 .\" HREF
@@ -90,11 +95,11 @@ external function to be called during pattern matching. See the
 .\"
 documentation for details.
 .P
-9. Subroutine calls (whether recursive or not) were treated as atomic groups up
-to PCRE2 release 10.23, but from release 10.30 this changed, and backtracking
-into subroutine calls is now supported, as in Perl.
+10. Subroutine calls (whether recursive or not) were treated as atomic groups
+up to PCRE2 release 10.23, but from release 10.30 this changed, and
+backtracking into subroutine calls is now supported, as in Perl.
 .P
-10. In PCRE2, if any of the backtracking control verbs are used in a group that
+11. In PCRE2, if any of the backtracking control verbs are used in a group that
 is called as a subroutine (whether or not recursively), their effect is
 confined to that group; it does not extend to the surrounding pattern. This is
 not always the case in Perl. In particular, if (*THEN) is present in a group
@@ -102,18 +107,18 @@ that is called as a subroutine, its action is limited to that group, even if
 the group does not contain any | characters. Note that such groups are
 processed as anchored at the point where they are tested.
 .P
-11. If a pattern contains more than one backtracking control verb, the first
+12. If a pattern contains more than one backtracking control verb, the first
 one that is backtracked onto acts. For example, in the pattern
 A(*COMMIT)B(*PRUNE)C a failure in B triggers (*COMMIT), but a failure in C
 triggers (*PRUNE). Perl's behaviour is more complex; in many cases it is the
 same as PCRE2, but there are cases where it differs.
 .P
-12. There are some differences that are concerned with the settings of captured
+13. There are some differences that are concerned with the settings of captured
 strings when part of a pattern is repeated. For example, matching "aba" against
 the pattern /^(a(b)?)+$/ in Perl leaves $2 unset, but in PCRE2 it is set to
 "b".
 .P
-13. PCRE2's handling of duplicate capture group numbers and names is not as
+14. PCRE2's handling of duplicate capture group numbers and names is not as
 general as Perl's. This is a consequence of the fact the PCRE2 works internally
 just with numbers, using an external table to translate between numbers and
 names. In particular, a pattern such as (?|(?A)|(?B)), where the two
@@ -122,81 +127,75 @@ causes an error at compile time. If it were allowed, it would not be possible
 to distinguish which group matched, because both names map to capture group
 number 1. To avoid this confusing situation, an error is given at compile time.
 .P
-14. Perl used to recognize comments in some places that PCRE2 does not, for
+15. Perl used to recognize comments in some places that PCRE2 does not, for
 example, between the ( and ? at the start of a group. If the /x modifier is
 set, Perl allowed white space between ( and ? though the latest Perls give an
 error (for a while it was just deprecated). There may still be some cases where
 Perl behaves differently.
 .P
-15. Perl, when in warning mode, gives warnings for character classes such as
+16. Perl, when in warning mode, gives warnings for character classes such as
 [A-\ed] or [a-[:digit:]]. It then treats the hyphens as literals. PCRE2 has no
 warning features, so it gives an error in these cases because they are almost
 certainly user mistakes.
 .P
-16. In PCRE2, the upper/lower case character properties Lu and Ll are not
+17. In PCRE2, the upper/lower case character properties Lu and Ll are not
 affected when case-independent matching is specified. For example, \ep{Lu}
 always matches an upper case letter. I think Perl has changed in this respect;
-in the release at the time of writing (5.34), \ep{Lu} and \ep{Ll} match all
+in the release at the time of writing (5.38), \ep{Lu} and \ep{Ll} match all
 letters, regardless of case, when case independence is specified.
 .P
-17. From release 5.32.0, Perl locks out the use of \eK in lookaround
+18. From release 5.32.0, Perl locks out the use of \eK in lookaround
 assertions. From release 10.38 PCRE2 does the same by default. However, there
 is an option for re-enabling the previous behaviour. When this option is set,
 \eK is acted on when it occurs in positive assertions, but is ignored in
 negative assertions.
 .P
-18. PCRE2 provides some extensions to the Perl regular expression facilities.
+19. PCRE2 provides some extensions to the Perl regular expression facilities.
 Perl 5.10 included new features that were not in earlier versions of Perl, some
 of which (such as named parentheses) were in PCRE2 for some time before. This
-list is with respect to Perl 5.34:
-.sp
-(a) Although lookbehind assertions in PCRE2 must match fixed length strings,
-each alternative toplevel branch of a lookbehind assertion can match a
-different length of string. Perl used to require them all to have the same
-length, but the latest version has some variable length support.
+list is with respect to Perl 5.38:
 .sp
-(b) From PCRE2 10.23, backreferences to groups of fixed length are supported
-in lookbehinds, provided that there is no possibility of referencing a
-non-unique number or name. Perl does not support backreferences in lookbehinds.
-.sp
-(c) If PCRE2_DOLLAR_ENDONLY is set and PCRE2_MULTILINE is not set, the $
+(a) If PCRE2_DOLLAR_ENDONLY is set and PCRE2_MULTILINE is not set, the $
 meta-character matches only at the very end of the string.
 .sp
-(d) A backslash followed by a letter with no special meaning is faulted. (Perl
+(b) A backslash followed by a letter with no special meaning is faulted. (Perl
 can be made to issue a warning.)
 .sp
-(e) If PCRE2_UNGREEDY is set, the greediness of the repetition quantifiers is
+(c) If PCRE2_UNGREEDY is set, the greediness of the repetition quantifiers is
 inverted, that is, by default they are not greedy, but if followed by a
 question mark they are.
 .sp
-(f) PCRE2_ANCHORED can be used at matching time to force a pattern to be tried
+(d) PCRE2_ANCHORED can be used at matching time to force a pattern to be tried
 only at the first matching position in the subject string.
 .sp
-(g) The PCRE2_NOTBOL, PCRE2_NOTEOL, PCRE2_NOTEMPTY and PCRE2_NOTEMPTY_ATSTART
+(e) The PCRE2_NOTBOL, PCRE2_NOTEOL, PCRE2_NOTEMPTY and PCRE2_NOTEMPTY_ATSTART
 options have no Perl equivalents.
 .sp
-(h) The \eR escape sequence can be restricted to match only CR, LF, or CRLF
+(f) The \eR escape sequence can be restricted to match only CR, LF, or CRLF
 by the PCRE2_BSR_ANYCRLF option.
 .sp
-(i) The callout facility is PCRE2-specific. Perl supports codeblocks and
+(g) The callout facility is PCRE2-specific. Perl supports codeblocks and
 variable interpolation, but not general hooks on every match.
 .sp
-(j) The partial matching facility is PCRE2-specific.
+(h) The partial matching facility is PCRE2-specific.
 .sp
-(k) The alternative matching function (\fBpcre2_dfa_match()\fP matches in a
+(i) The alternative matching function (\fBpcre2_dfa_match()\fP matches in a
 different way and is not Perl-compatible.
 .sp
-(l) PCRE2 recognizes some special sequences such as (*CR) or (*NO_JIT) at
+(j) PCRE2 recognizes some special sequences such as (*CR) or (*NO_JIT) at
 the start of a pattern. These set overall options that cannot be changed within
 the pattern.
 .sp
-(m) PCRE2 supports non-atomic positive lookaround assertions. This is an
+(k) PCRE2 supports non-atomic positive lookaround assertions. This is an
 extension to the lookaround facilities. The default, Perl-compatible
 lookarounds are atomic.
-.P
-19. The Perl /a modifier restricts /d numbers to pure ascii, and the /aa
-modifier restricts /i case-insensitive matching to pure ascii, ignoring Unicode
-rules. This separation cannot be represented with PCRE2_UCP.
+.sp
+(l) There are three syntactical items in patterns that can refer to a capturing
+group by number: back references such as \eg{2}, subroutine calls such as (?3),
+and condition references such as (?(4)...). PCRE2 supports relative group
+numbers such as +2 and -4 in all three cases. Perl supports both plus and minus
+for subroutine calls, but only minus for back references, and no relative
+numbering at all for conditions.
 .P
 20. Perl has different limits than PCRE2. See the
 .\" HREF
@@ -206,6 +205,16 @@ documentation for details. Perl went with 5.10 from recursion to iteration
 keeping the intermediate matches on the heap, which is ~10% slower but does not
 fall into any stack-overflow limit. PCRE2 made a similar change at release
 10.30, and also has many build-time and run-time customizable limits.
+.P
+21. Unlike Perl, PCRE2 doesn't have character set modifiers and specially no way
+to set characters by context just like Perl's "/d". A regular expression using
+PCRE2_UTF and PCRE2_UCP will use similar rules to Perl's "/u"; something closer
+to "/a" could be selected by adding other PCRE2_EXTRA_ASCII* options on top.
+.P
+22. Some recursive patterns that Perl diagnoses as infinite recursions can be
+handled by PCRE2, either by the interpreter or the JIT. An example is
+/(?:|(?0)abcd)(?(R)|\ez)/, which matches a sequence of any number of repeated
+"abcd" substrings at the end of the subject.
 .
 .
 .SH AUTHOR
@@ -222,6 +231,6 @@ Cambridge, England.
 .rs
 .sp
 .nf
-Last updated: 08 December 2021
-Copyright (c) 1997-2021 University of Cambridge.
+Last updated: 30 November 2023
+Copyright (c) 1997-2023 University of Cambridge.
 .fi
diff --git a/pcre2/doc/pcre2convert.3 b/pcre2/doc/pcre2convert.3
index 4ed6ea5..62c7ebb 100644
--- a/pcre2/doc/pcre2convert.3
+++ b/pcre2/doc/pcre2convert.3
@@ -150,7 +150,7 @@ neither do POSIX extended patterns).
 .sp
 .nf
 Philip Hazel
-University Computing Service
+Retired from University Computing Service
 Cambridge, England.
 .fi
 .
diff --git a/pcre2/doc/pcre2demo.3 b/pcre2/doc/pcre2demo.3
index 89c9497..0453a94 100644
--- a/pcre2/doc/pcre2demo.3
+++ b/pcre2/doc/pcre2demo.3
@@ -1,22 +1,30 @@
+.TH PCRE2DEMO 3 " 7 June 2024" "PCRE2 10.44"
+.\"AUTOMATICALLY GENERATED BY PrepareRelease - do not EDIT!
 .SH NAME
-// - A demonstration C program for PCRE2 - //
+PCRE2DEMO - A demonstration C program for PCRE2
+.SH "SOURCE CODE"
+.rs
 .sp
 .\" Start example.
 .de EX
+.	do ds mF \\n[.fam]
 .  nr mE \\n(.f
 .  nf
 .  nh
+.	do fam C
 .  ft CW
 ..
 .
 .
 .\" End example.
 .de EE
+.	do fam \\*(mF
 .  ft \\n(mE
 .  fi
 .  hy \\n(HY
 ..
 .
+.RS -7
 .EX
 /*************************************************
 *           PCRE2 DEMONSTRATION PROGRAM          *
diff --git a/pcre2/doc/pcre2grep.1 b/pcre2/doc/pcre2grep.1
index 956633d..ffe9d39 100644
--- a/pcre2/doc/pcre2grep.1
+++ b/pcre2/doc/pcre2grep.1
@@ -1,4 +1,4 @@
-.TH PCRE2GREP 1 "21 November 2022" "PCRE2 10.41"
+.TH PCRE2GREP 1 "22 December 2023" "PCRE2 10.43"
 .SH NAME
 pcre2grep - a grep with Perl-compatible regular expressions.
 .SH SYNOPSIS
@@ -43,15 +43,16 @@ For example:
 .sp
   pcre2grep some-pattern file1 - file3
 .sp
-By default, input files are searched line by line. Each line that matches a
-pattern is copied to the standard output, and if there is more than one file,
-the file name is output at the start of each line, followed by a colon.
-However, there are options that can change how \fBpcre2grep\fP behaves. For
-example, the \fB-M\fP option makes it possible to search for strings that span
-line boundaries. What defines a line boundary is controlled by the \fB-N\fP
-(\fB--newline\fP) option. The \fB-h\fP and \fB-H\fP options control whether or
-not file names are shown, and the \fB-Z\fP option changes the file name
-terminator to a zero byte.
+By default, input files are searched line by line, so pattern assertions about
+the beginning and end of a subject string (^, $, \eA, \eZ, and \ez) match at
+the beginning and end of each line. When a line matches a pattern, it is copied
+to the standard output, and if there is more than one file, the file name is
+output at the start of each line, followed by a colon. However, there are
+options that can change how \fBpcre2grep\fP behaves. For example, the \fB-M\fP
+option makes it possible to search for strings that span line boundaries. What
+defines a line boundary is controlled by the \fB-N\fP (\fB--newline\fP) option.
+The \fB-h\fP and \fB-H\fP options control whether or not file names are shown,
+and the \fB-Z\fP option changes the file name terminator to a zero byte.
 .P
 The amount of memory used for buffering files that are being scanned is
 controlled by parameters that can be set by the \fB--buffer-size\fP and
@@ -68,6 +69,9 @@ The block of memory that is actually used is three times the "buffer size", to
 allow for buffering "before" and "after" lines. If the buffer size is too
 small, fewer than requested "before" and "after" lines may be output.
 .P
+When matching with a multiline pattern, the size of the buffer must be at least
+half of the maximum match expected or the pattern might fail to match.
+.P
 Patterns can be no longer than 8KiB or BUFSIZ bytes, whichever is the greater.
 BUFSIZ is defined in \fB\fP. When there is more than one pattern
 (specified by the use of \fB-e\fP and/or \fB-f\fP), each pattern is applied to
@@ -211,7 +215,7 @@ exactly the same as the number of lines that would have been output, but if the
 \fB-M\fP (multiline) option is used (without \fB-v\fP), there may be more
 suppressed lines than the count (that is, the number of matches).
 .sp
-If no lines are selected, the number zero is output. If several files are are
+If no lines are selected, the number zero is output. If several files are
 being scanned, a count is output for each of them and the \fB-t\fP option can
 be used to cause a total to be output at the end. However, if the
 \fB--files-with-matches\fP option is also used, only those files whose counts
@@ -268,6 +272,13 @@ end-of-file; in others it may provoke an error.
 \fB--depth-limit\fP=\fInumber\fP
 See \fB--match-limit\fP below.
 .TP
+\fB-E\fP, \fB--case-restrict\fP
+When case distinctions are being ignored in Unicode mode, two ASCII letters (K
+and S) will by default match Unicode characters U+212A (Kelvin sign) and U+017F
+(long S) respectively, as well as their lower case ASCII counterparts. When
+this option is set, case equivalences are restricted such that no ASCII
+character matches a non-ASCII character, and vice versa.
+.TP
 \fB-e\fP \fIpattern\fP, \fB--regex=\fP\fIpattern\fP, \fB--regexp=\fP\fIpattern\fP
 Specify a pattern to be matched. This option can be used multiple times in
 order to specify several patterns. It can also be used as a way of specifying a
@@ -357,6 +368,10 @@ mode, \fB--colour\fP has no effect, and no context is shown. That is, the
 match in a line, each of them is shown separately. This option is mutually
 exclusive with \fB--output\fP, \fB--line-offsets\fP, and \fB--only-matching\fP.
 .TP
+\fB--group-separator\fP=\fItext\fP
+Output this text string instead of two hyphens between groups of lines when
+\fB-A\fP, \fB-B\fP, or \fB-C\fP is in use. See also \fB--no-group-separator\fP.
+.TP
 \fB-H\fP, \fB--with-filename\fP
 Force the inclusion of the file name at the start of output lines when
 searching a single file. The file name is not normally shown in this case.
@@ -388,7 +403,9 @@ Ignore binary files. This is equivalent to
 \fB--binary-files\fP=\fIwithout-match\fP.
 .TP
 \fB-i\fP, \fB--ignore-case\fP
-Ignore upper/lower case distinctions during comparisons.
+Ignore upper/lower case distinctions when pattern matching. This applies when
+matching path names for inclusion or exclusion as well as when matching lines
+in files.
 .TP
 \fB--include\fP=\fIpattern\fP
 If any \fB--include\fP patterns are specified, the only files that are
@@ -473,16 +490,22 @@ used. There is no short form for this option.
 .TP
 \fB-M\fP, \fB--multiline\fP
 Allow patterns to match more than one line. When this option is set, the PCRE2
-library is called in "multiline" mode. This allows a matched string to extend
-past the end of a line and continue on one or more subsequent lines. Patterns
-used with \fB-M\fP may usefully contain literal newline characters and internal
-occurrences of ^ and $ characters. The output for a successful match may
-consist of more than one line. The first line is the line in which the match
-started, and the last line is the line in which the match ended. If the matched
-string ends with a newline sequence, the output ends at the end of that line.
-If \fB-v\fP is set, none of the lines in a multi-line match are output. Once a
-match has been handled, scanning restarts at the beginning of the line after
-the one in which the match ended.
+library is called in "multiline" mode, and a match is allowed to continue past
+the end of the initial line and onto one or more subsequent lines.
+.sp
+Patterns used with \fB-M\fP may usefully contain literal newline characters and
+internal occurrences of ^ and $ characters, because in multiline mode these can
+match at internal newlines. Because \fBpcre2grep\fP is scanning multiple lines,
+the \eZ and \ez assertions match only at the end of the last line in the file.
+The \eA assertion matches at the start of the first line of a match. This can
+be any line in the file; it is not anchored to the first line.
+.sp
+The output for a successful match may consist of more than one line. The first
+line is the line in which the match started, and the last line is the line in
+which the match ended. If the matched string ends with a newline sequence, the
+output ends at the end of that line. If \fB-v\fP is set, none of the lines in a
+multi-line match are output. Once a match has been handled, scanning restarts
+at the beginning of the line after the one in which the match ended.
 .sp
 The newline sequence that separates multiple lines must be matched as part of
 the pattern. For example, to find the phrase "regular expression" in a file
@@ -497,8 +520,10 @@ well as possibly handling a two-character newline sequence.
 .sp
 There is a limit to the number of lines that can be matched, imposed by the way
 that \fBpcre2grep\fP buffers the input file as it scans it. With a sufficiently
-large processing buffer, this should not be a problem, but the \fB-M\fP option
-does not work when input is read line by line (see \fB--line-buffered\fP.)
+large processing buffer, this should not be a problem.
+.sp
+The \fB-M\fP option does not work when input is read line by line (see
+\fB--line-buffered\fP.)
 .TP
 \fB-m\fP \fInumber\fP, \fB--max-count\fP=\fInumber\fP
 Stop processing after finding \fInumber\fP matching lines, or non-matching
@@ -576,11 +601,16 @@ being output, it precedes the line number. When the \fB-M\fP option causes a
 pattern to match more than one line, only the first is preceded by its line
 number. This option is forced if \fB--line-offsets\fP is used.
 .TP
+\fB--no-group-separator\fP
+Do not output a separator between groups of lines when \fB-A\fP, \fB-B\fP, or
+\fB-C\fP is in use. The default is to output a line containing two hyphens. See
+also \fB--group-separator\fP.
+.TP
 \fB--no-jit\fP
 If the PCRE2 library is built with support for just-in-time compiling (which
 speeds up matching), \fBpcre2grep\fP automatically makes use of this, unless it
 was explicitly disabled at build time. This option can be used to disable the
-use of JIT at run time. It is provided for testing and working round problems.
+use of JIT at run time. It is provided for testing and working around problems.
 It should never be needed in normal use.
 .TP
 \fB-O\fP \fItext\fP, \fB--output\fP=\fItext\fP
@@ -660,6 +690,17 @@ default is 50.
 Specify a separating string for multiple occurrences of \fB-o\fP. The default
 is an empty string. Separating strings are never coloured.
 .TP
+\fB-P\fP, \fB--no-ucp\fP
+Starting from release 10.43, when UTF/Unicode mode is specified with \fB-u\fP
+or \fB-U\fP, the PCRE2_UCP option is used by default. This means that the
+POSIX classes in patterns match more than just ASCII characters. For example,
+[:digit:] matches any Unicode decimal digit. The \fB--no-ucp\fP option
+suppresses PCRE2_UCP, thus restricting the POSIX classes to ASCII characters,
+as was the case in earlier releases. Note that there are now more fine-grained
+option settings within patterns that affect individual classes. For example,
+when in UCP mode, the sequence (?aP) restricts [:word:] to ASCII letters, while
+allowing \ew to match Unicode letters and digits.
+.TP
 \fB-q\fP, \fB--quiet\fP
 Work quietly, that is, display nothing except error messages. The exit
 status indicates whether or not any matches were found.
@@ -692,11 +733,11 @@ ignored when used with \fB-L\fP (list files without matches), because the grand
 total would always be zero.
 .TP
 \fB-u\fP, \fB--utf\fP
-Operate in UTF-8 mode. This option is available only if PCRE2 has been compiled
-with UTF-8 support. All patterns (including those for any \fB--exclude\fP and
-\fB--include\fP options) and all lines that are scanned must be valid strings
-of UTF-8 characters. If an invalid UTF-8 string is encountered, an error
-occurs.
+Operate in UTF/Unicode mode. This option is available only if PCRE2 has been
+compiled with UTF-8 support. All patterns (including those for any
+\fB--exclude\fP and \fB--include\fP options) and all lines that are scanned
+must be valid strings of UTF-8 characters. If an invalid UTF-8 string is
+encountered, an error occurs.
 .TP
 \fB-U\fP, \fB--utf-allow-invalid\fP
 As \fB--utf\fP, but in addition subject lines may contain invalid UTF-8 code
@@ -778,25 +819,27 @@ standard output must end with "\er\en". For all other operating systems, and
 for all messages to the standard error stream, "\en" is used.
 .
 .
-.SH "OPTIONS COMPATIBILITY"
+.SH "OPTIONS COMPATIBILITY WITH GNU GREP"
 .rs
 .sp
-Many of the short and long forms of \fBpcre2grep\fP's options are the same
-as in the GNU \fBgrep\fP program. Any long option of the form
-\fB--xxx-regexp\fP (GNU terminology) is also available as \fB--xxx-regex\fP
-(PCRE2 terminology). However, the \fB--depth-limit\fP, \fB--file-list\fP,
-\fB--file-offsets\fP, \fB--heap-limit\fP, \fB--include-dir\fP,
-\fB--line-offsets\fP, \fB--locale\fP, \fB--match-limit\fP, \fB-M\fP,
-\fB--multiline\fP, \fB-N\fP, \fB--newline\fP, \fB--om-separator\fP,
-\fB--output\fP, \fB-u\fP, \fB--utf\fP, \fB-U\fP, and \fB--utf-allow-invalid\fP
-options are specific to \fBpcre2grep\fP, as is the use of the
-\fB--only-matching\fP option with a capturing parentheses number.
+Many of the short and long forms of \fBpcre2grep\fP's options are the same as
+in the GNU \fBgrep\fP program. Any long option of the form \fB--xxx-regexp\fP
+(GNU terminology) is also available as \fB--xxx-regex\fP (PCRE2 terminology).
+However, the \fB--case-restrict\fP, \fB--depth-limit\fP, \fB-E\fP,
+\fB--file-list\fP, \fB--file-offsets\fP, \fB--heap-limit\fP,
+\fB--include-dir\fP, \fB--line-offsets\fP, \fB--locale\fP, \fB--match-limit\fP,
+\fB-M\fP, \fB--multiline\fP, \fB-N\fP, \fB--newline\fP, \fB--no-ucp\fP,
+\fB--om-separator\fP, \fB--output\fP, \fB-P\fP, \fB-u\fP, \fB--utf\fP,
+\fB-U\fP, and \fB--utf-allow-invalid\fP options are specific to
+\fBpcre2grep\fP, as is the use of the \fB--only-matching\fP option with a
+capturing parentheses number.
 .P
 Although most of the common options work the same way, a few are different in
 \fBpcre2grep\fP. For example, the \fB--include\fP option's argument is a glob
-for GNU \fBgrep\fP, but a regular expression for \fBpcre2grep\fP. If both the
-\fB-c\fP and \fB-l\fP options are given, GNU grep lists only file names,
-without counts, but \fBpcre2grep\fP gives the counts as well.
+for GNU \fBgrep\fP, but in \fBpcre2grep\fP it is a regular expression to which
+the \fB-i\fP option applies. If both the \fB-c\fP and \fB-l\fP options are
+given, GNU grep lists only file names, without counts, but \fBpcre2grep\fP
+gives the counts as well.
 .
 .
 .SH "OPTIONS WITH DATA"
@@ -970,6 +1013,6 @@ Cambridge, England.
 .rs
 .sp
 .nf
-Last updated: 21 November 2022
-Copyright (c) 1997-2022 University of Cambridge.
+Last updated: 22 December 2023
+Copyright (c) 1997-2023 University of Cambridge.
 .fi
diff --git a/pcre2/doc/pcre2grep.txt b/pcre2/doc/pcre2grep.txt
index adc1d89..7914c45 100644
--- a/pcre2/doc/pcre2grep.txt
+++ b/pcre2/doc/pcre2grep.txt
@@ -1,10 +1,11 @@
-PCRE2GREP(1)                General Commands Manual               PCRE2GREP(1)
 
+PCRE2GREP(1)                General Commands Manual               PCRE2GREP(1)
 
 
 NAME
        pcre2grep - a grep with Perl-compatible regular expressions.
 
+
 SYNOPSIS
        pcre2grep [options] [long options] [pattern] [path1 path2 ...]
 
@@ -18,7 +19,7 @@ DESCRIPTION
        pattern syntax, or pcre2pattern(3) for a full description of the syntax
        and semantics of the regular expressions that PCRE2 supports.
 
-       Patterns, whether supplied on the command line or in a  separate  file,
+       Patterns,  whether  supplied on the command line or in a separate file,
        are given without delimiters. For example:
 
          pcre2grep Thursday /etc/motd
@@ -36,20 +37,22 @@ DESCRIPTION
        terns, all arguments are treated as path names. At least one of -e, -f,
        or an argument pattern must be provided.
 
-       If no files are specified, pcre2grep  reads  the  standard  input.  The
-       standard  input can also be referenced by a name consisting of a single
+       If  no  files  are  specified,  pcre2grep reads the standard input. The
+       standard input can also be referenced by a name consisting of a  single
        hyphen.  For example:
 
          pcre2grep some-pattern file1 - file3
 
-       By default, input files are searched  line  by  line.  Each  line  that
-       matches  a  pattern  is  copied to the standard output, and if there is
+       By  default,  input  files are searched line by line, so pattern asser-
+       tions about the beginning and end of a subject string (^,  $,  \A,  \Z,
+       and  \z)  match  at  the  beginning  and  end of each line. When a line
+       matches a pattern, it is copied to the standard output, and if there is
        more than one file, the file name is output at the start of each  line,
        followed  by  a  colon.  However, there are options that can change how
        pcre2grep behaves. For example, the -M  option  makes  it  possible  to
        search  for  strings  that  span  line  boundaries. What defines a line
-       boundary is controlled by the -N (--newline) option. The -h and -H  op-
-       tions  control  whether  or not file names are shown, and the -Z option
+       boundary is controlled by the -N (--newline) option.  The -h and -H op-
+       tions control whether or not file names are shown, and  the  -Z  option
        changes the file name terminator to a zero byte.
 
        The amount of memory used for buffering files that are being scanned is
@@ -65,11 +68,15 @@ DESCRIPTION
 
        The  block  of  memory that is actually used is three times the "buffer
        size", to allow for buffering "before" and "after" lines. If the buffer
-       size  is too small, fewer than requested "before" and "after" lines may
+       size is too small, fewer than requested "before" and "after" lines  may
        be output.
 
-       Patterns can be no longer than 8KiB or BUFSIZ bytes, whichever  is  the
-       greater.   BUFSIZ  is defined in . When there is more than one
+       When  matching with a multiline pattern, the size of the buffer must be
+       at least half of the maximum match expected or the pattern  might  fail
+       to match.
+
+       Patterns  can  be no longer than 8KiB or BUFSIZ bytes, whichever is the
+       greater.  BUFSIZ is defined in . When there is more  than  one
        pattern (specified by the use of -e and/or -f), each pattern is applied
        to  each  line  in the order in which they are defined, except that all
        the -e patterns are tried before the -f patterns.
@@ -80,11 +87,11 @@ DESCRIPTION
        sets,  or  --output  is  used  to output only the part of the line that
        matched (either shown literally, or as an  offset),  the  behaviour  is
        different. In this situation, all the patterns are applied to the line.
-       If there is more than one match, the one that  begins  nearest  to  the
-       start  of  the subject is processed; if there is more than one match at
-       that position, the one with the  longest  matching  substring  is  pro-
-       cessed;  if the matching substrings are equal, the first match found is
-       processed.
+       If  there  is  more  than one match, the one that begins nearest to the
+       start of the subject is processed; if there is more than one  match  at
+       that   position,  the  one  with  the  longest  matching  substring  is
+       processed; if the matching substrings are equal, the first match  found
+       is processed.
 
        Scanning with all the patterns resumes immediately following the match,
        so  that  later  matches  on the same line can be found. Note, however,
@@ -95,14 +102,14 @@ DESCRIPTION
        with GNU grep. In earlier releases, pcre2grep did not recognize matches
        from later patterns that were earlier in the subject.
 
-       Patterns  that can match an empty string are accepted, but empty string
-       matches  are  never  recognized.  An  example  is  the  pattern   "(su-
-       per)?(man)?",  in which all components are optional. This pattern finds
-       all occurrences of both "super" and  "man";  the  output  differs  from
-       matching  with  "super|man" when only the matching substrings are being
+       Patterns that can match an empty string are accepted, but empty  string
+       matches   are  never  recognized.  An  example  is  the  pattern  "(su-
+       per)?(man)?", in which all components are optional. This pattern  finds
+       all  occurrences  of  both  "super"  and "man"; the output differs from
+       matching with "super|man" when only the matching substrings  are  being
        shown.
 
-       If the LC_ALL or LC_CTYPE environment variable is set,  pcre2grep  uses
+       If  the  LC_ALL or LC_CTYPE environment variable is set, pcre2grep uses
        the value to set a locale when calling the PCRE2 library.  The --locale
        option can be used to override this.
 
@@ -126,25 +133,25 @@ BINARY FILES
        1024  bytes is identified as a binary file, and is processed specially.
        However, if the newline type is specified as NUL,  that  is,  the  line
        terminator is a binary zero, the test for a binary file is not applied.
-       See the --binary-files option for a means of changing  the  way  binary
+       See  the  --binary-files  option for a means of changing the way binary
        files are handled.
 
 
 BINARY ZEROS IN PATTERNS
 
-       Patterns  passed  from the command line are strings that are terminated
-       by a binary zero, so cannot contain internal zeros.  However,  patterns
+       Patterns passed from the command line are strings that  are  terminated
+       by  a  binary zero, so cannot contain internal zeros. However, patterns
        that are read from a file via the -f option may contain binary zeros.
 
 
 OPTIONS
 
-       The  order  in  which some of the options appear can affect the output.
-       For example, both the -H and -l options affect  the  printing  of  file
-       names.  Whichever  comes later in the command line will be the one that
-       takes effect. Similarly, except where noted  below,  if  an  option  is
-       given  twice,  the  later setting is used. Numerical values for options
-       may be followed by K  or  M,  to  signify  multiplication  by  1024  or
+       The order in which some of the options appear can  affect  the  output.
+       For  example,  both  the  -H and -l options affect the printing of file
+       names. Whichever comes later in the command line will be the  one  that
+       takes  effect.  Similarly,  except  where  noted below, if an option is
+       given twice, the later setting is used. Numerical  values  for  options
+       may  be  followed  by  K  or  M,  to  signify multiplication by 1024 or
        1024*1024 respectively.
 
        --        This terminates the list of options. It is useful if the next
@@ -162,11 +169,11 @@ OPTIONS
                  file name terminator to a zero byte). A line containing  "--"
                  is  output  between  each  group of lines, unless they are in
                  fact contiguous in the input file. The value of number is ex-
-                 pected  to  be  relatively  small. When -c is used, -A is ig-
+                 pected to be relatively small. When -c is  used,  -A  is  ig-
                  nored.
 
        -a, --text
-                 Treat binary files as text. This is equivalent  to  --binary-
+                 Treat  binary  files as text. This is equivalent to --binary-
                  files=text.
 
        --allow-lookaround-bsk
@@ -181,23 +188,23 @@ OPTIONS
                  start of the file is within number lines, or if the  process-
                  ing  buffer size has been set too small. If file names and/or
                  line numbers are being output, a hyphen separator is used in-
-                 stead  of a colon for the context lines (the -Z option can be
-                 used to change the file name terminator to a  zero  byte).  A
-                 line  containing  "--" is output between each group of lines,
-                 unless they are in fact contiguous in  the  input  file.  The
-                 value  of  number is expected to be relatively small. When -c
+                 stead of a colon for the context lines (the -Z option can  be
+                 used  to  change  the file name terminator to a zero byte). A
+                 line containing "--" is output between each group  of  lines,
+                 unless  they  are  in  fact contiguous in the input file. The
+                 value of number is expected to be relatively small.  When  -c
                  is used, -B is ignored.
 
        --binary-files=word
-                 Specify how binary files are to be processed. If the word  is
-                 "binary"  (the default), pattern matching is performed on bi-
-                 nary files, but  the  only  output  is  "Binary  file  
-                 matches"  when a match succeeds. If the word is "text", which
-                 is equivalent to the -a or --text option,  binary  files  are
-                 processed  in  the  same way as any other file. In this case,
-                 when a match succeeds, the  output  may  be  binary  garbage,
-                 which  can  have  nasty effects if sent to a terminal. If the
-                 word is "without-match", which is equivalent to  the  -I  op-
+                 Specify  how binary files are to be processed. If the word is
+                 "binary" (the default), pattern matching is performed on  bi-
+                 nary  files,  but  the  only  output  is  "Binary file 
+                 matches" when a match succeeds. If the word is "text",  which
+                 is  equivalent  to  the -a or --text option, binary files are
+                 processed in the same way as any other file.  In  this  case,
+                 when  a  match  succeeds,  the  output may be binary garbage,
+                 which can have nasty effects if sent to a  terminal.  If  the
+                 word  is  "without-match",  which is equivalent to the -I op-
                  tion, binary files are not processed at all; they are assumed
                  not to be of interest and are  skipped  without  causing  any
                  output or affecting the return code.
@@ -208,13 +215,13 @@ OPTIONS
                  scanned. See also --max-buffer-size below.
 
        -C number, --context=number
-                 Output  number  lines  of  context both before and after each
-                 matching line.  This is equivalent to setting both -A and  -B
+                 Output number lines of context both  before  and  after  each
+                 matching  line.  This is equivalent to setting both -A and -B
                  to the same value.
 
        -c, --count
-                 Do  not  output  lines from the files that are being scanned;
-                 instead output the number  of  lines  that  would  have  been
+                 Do not output lines from the files that  are  being  scanned;
+                 instead  output  the  number  of  lines  that would have been
                  shown, either because they matched, or, if -v is set, because
                  they failed to match. By default, this count is  exactly  the
                  same  as the number of lines that would have been output, but
@@ -223,8 +230,8 @@ OPTIONS
                  of matches).
 
                  If no lines are selected, the number zero is output. If  sev-
-                 eral  files are are being scanned, a count is output for each
-                 of them and the -t option can be used to cause a total to  be
+                 eral  files  are being scanned, a count is output for each of
+                 them and the -t option can be used to cause  a  total  to  be
                  output  at  the end. However, if the --files-with-matches op-
                  tion is also used, only those files whose counts are  greater
                  than zero are listed. When -c is used, the -A, -B, and -C op-
@@ -241,25 +248,25 @@ OPTIONS
                  It is ignored if --file-offsets, --line-offsets, or  --output
                  is set. By default, output is not coloured. The value for the
                  --colour  option  (which  is  optional,  see  above)  may  be
-                 "never",  "always",  or "auto". In the latter case, colouring
-                 happens only if the standard output is connected to a  termi-
-                 nal.   More resources are used when colouring is enabled, be-
-                 cause pcre2grep has to search for all possible matches  in  a
+                 "never", "always", or "auto". In the latter  case,  colouring
+                 happens  only if the standard output is connected to a termi-
+                 nal.  More resources are used when colouring is enabled,  be-
+                 cause  pcre2grep  has to search for all possible matches in a
                  line, not just one, in order to colour them all.
 
-                 The  colour  that  is used can be specified by setting one of
-                 the environment variables PCRE2GREP_COLOUR,  PCRE2GREP_COLOR,
+                 The colour that is used can be specified by  setting  one  of
+                 the  environment variables PCRE2GREP_COLOUR, PCRE2GREP_COLOR,
                  PCREGREP_COLOUR, or PCREGREP_COLOR, which are checked in that
                  order.  If  none  of  these  are  set,  pcre2grep  looks  for
                  GREP_COLORS  or  GREP_COLOR (in that order). The value of the
                  variable should be a string of two numbers,  separated  by  a
                  semicolon,  except  in  the  case  of GREP_COLORS, which must
                  start with "ms=" or "mt=" followed by two semicolon-separated
-                 colours,  terminated  by the end of the string or by a colon.
-                 If GREP_COLORS does not start with "ms=" or "mt=" it  is  ig-
+                 colours, terminated by the end of the string or by  a  colon.
+                 If  GREP_COLORS  does not start with "ms=" or "mt=" it is ig-
                  nored, and GREP_COLOR is checked.
 
-                 If  the  string obtained from one of the above variables con-
+                 If the string obtained from one of the above  variables  con-
                  tains any characters other than semicolon or digits, the set-
                  ting is ignored and the default colour is used. The string is
                  copied directly into the control string for setting colour on
@@ -274,18 +281,27 @@ OPTIONS
 
        -d action, --directories=action
                  If an input path is a directory, "action" specifies how it is
-                 to be processed.  Valid values are  "read"  (the  default  in
-                 non-Windows  environments,  for compatibility with GNU grep),
-                 "recurse" (equivalent to the -r option), or "skip"  (silently
-                 skip  the  path, the default in Windows environments). In the
-                 "read" case, directories are read as if  they  were  ordinary
-                 files.  In some operating systems the effect of reading a di-
-                 rectory like this is an immediate end-of-file; in  others  it
+                 to  be  processed.   Valid  values are "read" (the default in
+                 non-Windows environments, for compatibility with  GNU  grep),
+                 "recurse"  (equivalent to the -r option), or "skip" (silently
+                 skip the path, the default in Windows environments).  In  the
+                 "read"  case,  directories  are read as if they were ordinary
+                 files. In some operating systems the effect of reading a  di-
+                 rectory  like  this is an immediate end-of-file; in others it
                  may provoke an error.
 
        --depth-limit=number
                  See --match-limit below.
 
+       -E, --case-restrict
+                 When case distinctions are being ignored in Unicode mode, two
+                 ASCII letters (K and S) will by default match Unicode charac-
+                 ters U+212A (Kelvin sign) and U+017F (long  S)  respectively,
+                 as well as their lower case ASCII counterparts. When this op-
+                 tion  is  set,  case equivalences are restricted such that no
+                 ASCII character  matches  a  non-ASCII  character,  and  vice
+                 versa.
+
        -e pattern, --regex=pattern, --regexp=pattern
                  Specify a pattern to be matched. This option can be used mul-
                  tiple times in order to specify several patterns. It can also
@@ -304,15 +320,15 @@ OPTIONS
                  skipped without being processed. This applies to  all  files,
                  whether  listed  on  the  command line, obtained from --file-
                  list, or by scanning a directory. The pattern is a PCRE2 reg-
-                 ular  expression,  and is matched against the final component
+                 ular expression, and is matched against the  final  component
                  of the file name, not the entire path. The -F, -w, and -x op-
                  tions  do  not apply to this pattern. The option may be given
                  any number of times in order to specify multiple patterns. If
-                 a  file  name matches both an --include and an --exclude pat-
+                 a file name matches both an --include and an  --exclude  pat-
                  tern, it is excluded. There is no short form for this option.
 
        --exclude-from=filename
-                 Treat each non-empty line of the file  as  the  data  for  an
+                 Treat  each  non-empty  line  of  the file as the data for an
                  --exclude option. What constitutes a newline when reading the
                  file is the operating system's default. The --newline  option
                  has  no  effect on this option. This option may be given more
@@ -320,24 +336,24 @@ OPTIONS
 
        --exclude-dir=pattern
                  Directories whose names match the pattern are skipped without
-                 being  processed, whatever the setting of the --recursive op-
-                 tion. This applies to all directories, whether listed on  the
-                 command  line,  obtained  from  --file-list, or by scanning a
-                 parent directory. The pattern is a PCRE2 regular  expression,
-                 and  is  matched against the final component of the directory
-                 name, not the entire path. The -F, -w, and -x options do  not
-                 apply  to this pattern. The option may be given any number of
-                 times in order to specify more than one pattern. If a  direc-
-                 tory  matches both --include-dir and --exclude-dir, it is ex-
+                 being processed, whatever the setting of the --recursive  op-
+                 tion.  This applies to all directories, whether listed on the
+                 command line, obtained from --file-list,  or  by  scanning  a
+                 parent  directory. The pattern is a PCRE2 regular expression,
+                 and is matched against the final component of  the  directory
+                 name,  not the entire path. The -F, -w, and -x options do not
+                 apply to this pattern. The option may be given any number  of
+                 times  in order to specify more than one pattern. If a direc-
+                 tory matches both --include-dir and --exclude-dir, it is  ex-
                  cluded. There is no short form for this option.
 
        -F, --fixed-strings
-                 Interpret each data-matching  pattern  as  a  list  of  fixed
-                 strings,  separated  by newlines, instead of as a regular ex-
+                 Interpret  each  data-matching  pattern  as  a  list of fixed
+                 strings, separated by newlines, instead of as a  regular  ex-
                  pression. What constitutes a newline for this purpose is con-
                  trolled by the --newline option. The -w (match as a word) and
-                 -x (match whole line) options can be used with -F.  They  ap-
-                 ply  to  each of the fixed strings. A line is selected if any
+                 -x  (match whole line) options can be used with -F.  They ap-
+                 ply to each of the fixed strings. A line is selected  if  any
                  of the fixed strings are found in it (subject to -w or -x, if
                  present).  This  option applies only to the patterns that are
                  matched against the contents of files; it does not  apply  to
@@ -348,8 +364,8 @@ OPTIONS
                  Read patterns from the file, one per line.  As  is  the  case
                  with  patterns  on  the command line, no delimiters should be
                  used. What constitutes a newline when reading the file is the
-                 operating  system's  default interpretation of \n. The --new-
-                 line option has no effect  on  this  option.  Trailing  white
+                 operating system's default interpretation of \n.  The  --new-
+                 line  option  has  no  effect  on this option. Trailing white
                  space is removed from each line, and blank lines are ignored.
                  An empty file contains  no  patterns  and  therefore  matches
                  nothing.  Patterns  read  from a file in this way may contain
@@ -361,20 +377,20 @@ OPTIONS
                  standard  input.  When  -f is used, patterns specified on the
                  command line using -e may also be present; they  are  matched
                  before the file's patterns. However, no pattern is taken from
-                 the command line; all arguments are treated as the  names  of
+                 the  command  line; all arguments are treated as the names of
                  paths to be searched.
 
        --file-list=filename
-                 Read  a  list  of  files  and/or  directories  that are to be
+                 Read a list of  files  and/or  directories  that  are  to  be
                  scanned from the given file, one per line. What constitutes a
                  newline  when  reading the file is the operating system's de-
                  fault. Trailing white space is removed from  each  line,  and
                  blank lines are ignored. These paths are processed before any
-                 that are listed on the command line. The  file  name  can  be
-                 given  as  "-"  to refer to the standard input. If --file and
-                 --file-list are both specified  as  "-",  patterns  are  read
-                 first.  This is useful only when the standard input is a ter-
-                 minal, from which further lines (the list of  files)  can  be
+                 that  are  listed  on  the command line. The file name can be
+                 given as "-" to refer to the standard input.  If  --file  and
+                 --file-list  are  both  specified  as  "-", patterns are read
+                 first. This is useful only when the standard input is a  ter-
+                 minal,  from  which  further lines (the list of files) can be
                  read after an end-of-file indication. If this option is given
                  more than once, all the specified files are read.
 
@@ -388,16 +404,21 @@ OPTIONS
                  ally exclusive with  --output,  --line-offsets,  and  --only-
                  matching.
 
+       --group-separator=text
+                 Output this text string instead of two hyphens between groups
+                 of  lines  when -A, -B, or -C is in use. See also --no-group-
+                 separator.
+
        -H, --with-filename
-                 Force  the  inclusion of the file name at the start of output
+                 Force the inclusion of the file name at the start  of  output
                  lines when searching a single file. The file name is not nor-
                  mally  shown  in  this case.  By default, for matching lines,
                  the file name is followed by a colon; for  context  lines,  a
                  hyphen separator is used. The -Z option can be used to change
                  the terminator to a zero byte. If a line number is also being
                  output, it follows the file name. When the -M option causes a
-                 pattern to match more than one line, only the first  is  pre-
-                 ceded  by  the  file name. This option overrides any previous
+                 pattern  to  match more than one line, only the first is pre-
+                 ceded by the file name. This option  overrides  any  previous
                  -h, -l, or -L options.
 
        -h, --no-filename
@@ -413,46 +434,48 @@ OPTIONS
        --heap-limit=number
                  See --match-limit below.
 
-       --help    Output  a  help  message, giving brief details of the command
-                 options and file type support, and then exit.  Anything  else
+       --help    Output a help message, giving brief details  of  the  command
+                 options  and  file type support, and then exit. Anything else
                  on the command line is ignored.
 
-       -I        Ignore   binary   files.  This  is  equivalent  to  --binary-
+       -I        Ignore  binary  files.  This  is  equivalent   to   --binary-
                  files=without-match.
 
        -i, --ignore-case
-                 Ignore upper/lower case distinctions during comparisons.
+                 Ignore  upper/lower  case distinctions when pattern matching.
+                 This applies when matching path names for inclusion or exclu-
+                 sion as well as when matching lines in files.
 
        --include=pattern
                  If any --include patterns are specified, the only files  that
                  are processed are those whose names match one of the patterns
-                 and do not match an --exclude pattern. This option  does  not
-                 affect  directories,  but  it  applies  to all files, whether
-                 listed on the command line, obtained from --file-list, or  by
-                 scanning  a directory. The pattern is a PCRE2 regular expres-
-                 sion, and is matched against the final component of the  file
-                 name,  not the entire path. The -F, -w, and -x options do not
-                 apply to this pattern. The option may be given any number  of
-                 times.  If a file name matches both an --include and an --ex-
-                 clude pattern, it is excluded.  There is no  short  form  for
+                 and  do  not match an --exclude pattern. This option does not
+                 affect directories, but it  applies  to  all  files,  whether
+                 listed  on the command line, obtained from --file-list, or by
+                 scanning a directory. The pattern is a PCRE2 regular  expres-
+                 sion,  and is matched against the final component of the file
+                 name, not the entire path. The -F, -w, and -x options do  not
+                 apply  to this pattern. The option may be given any number of
+                 times. If a file name matches both an --include and an  --ex-
+                 clude  pattern,  it  is excluded.  There is no short form for
                  this option.
 
        --include-from=filename
-                 Treat  each  non-empty  line  of  the file as the data for an
+                 Treat each non-empty line of the file  as  the  data  for  an
                  --include option. What constitutes a newline for this purpose
                  is  the  operating system's default. The --newline option has
                  no effect on this option. This option may be given any number
                  of times; all the files are read.
 
        --include-dir=pattern
-                 If  any --include-dir patterns are specified, the only direc-
-                 tories that are processed are those whose names match one  of
-                 the  patterns and do not match an --exclude-dir pattern. This
-                 applies to all directories, whether  listed  on  the  command
-                 line,  obtained from --file-list, or by scanning a parent di-
-                 rectory. The pattern is a PCRE2 regular  expression,  and  is
-                 matched  against  the  final component of the directory name,
-                 not the entire path. The -F, -w, and -x options do not  apply
+                 If any --include-dir patterns are specified, the only  direc-
+                 tories  that are processed are those whose names match one of
+                 the patterns and do not match an --exclude-dir pattern.  This
+                 applies  to  all  directories,  whether listed on the command
+                 line, obtained from --file-list, or by scanning a parent  di-
+                 rectory.  The  pattern  is a PCRE2 regular expression, and is
+                 matched against the final component of  the  directory  name,
+                 not  the entire path. The -F, -w, and -x options do not apply
                  to this pattern. The option may be given any number of times.
                  If a directory matches both --include-dir and  --exclude-dir,
                  it is excluded. There is no short form for this option.
@@ -468,7 +491,7 @@ OPTIONS
        -l, --files-with-matches
                  Instead of outputting lines from the files, just  output  the
                  names of the files containing lines that would have been out-
-                 put. Each file name is output once, on a separate  line,  but
+                 put.  Each  file name is output once, on a separate line, but
                  if the -Z option is set, they are separated by zero bytes in-
                  stead of newlines. Searching normally  stops  as  soon  as  a
                  matching  line is found in a file. However, if the -c (count)
@@ -485,21 +508,21 @@ OPTIONS
                  input)" is used. There is no short form for this option.
 
        --line-buffered
-                 When  this  option is given, non-compressed input is read and
-                 processed line by line, and the output is flushed after  each
-                 write.  By  default,  input  is  read in large chunks, unless
-                 pcre2grep can determine that it is reading from  a  terminal,
+                 When this option is given, non-compressed input is  read  and
+                 processed  line by line, and the output is flushed after each
+                 write. By default, input is  read  in  large  chunks,  unless
+                 pcre2grep  can  determine that it is reading from a terminal,
                  which is currently possible only in Unix-like environments or
                  Windows. Output to terminal is normally automatically flushed
-                 by  the  operating system. This option can be useful when the
-                 input or output is attached to a pipe and  you  do  not  want
-                 pcre2grep  to  buffer up large amounts of data.  However, its
-                 use will affect performance, and the  -M  (multiline)  option
-                 ceases  to  work. When input is from a compressed .gz or .bz2
+                 by the operating system. This option can be useful  when  the
+                 input  or  output  is  attached to a pipe and you do not want
+                 pcre2grep to buffer up large amounts of data.   However,  its
+                 use  will  affect  performance, and the -M (multiline) option
+                 ceases to work. When input is from a compressed .gz  or  .bz2
                  file, --line-buffered is ignored.
 
        --line-offsets
-                 Instead of showing lines or parts of lines that  match,  show
+                 Instead  of  showing lines or parts of lines that match, show
                  each match as a line number, the offset from the start of the
                  line, and a length. The line number is terminated by a  colon
                  (as  usual; see the -n option), and the offset and length are
@@ -517,20 +540,28 @@ OPTIONS
                  short form for this option.
 
        -M, --multiline
-                 Allow patterns to match more than one line. When this  option
-                 is set, the PCRE2 library is called in "multiline" mode. This
-                 allows a matched string to extend past the end of a line  and
-                 continue  on one or more subsequent lines. Patterns used with
-                 -M may usefully contain literal newline characters and inter-
-                 nal  occurrences of ^ and $ characters. The output for a suc-
-                 cessful match may consist of more than one  line.  The  first
-                 line  is  the  line  in which the match started, and the last
-                 line is the line in which the match  ended.  If  the  matched
-                 string  ends  with a newline sequence, the output ends at the
-                 end of that line.  If -v is set,  none  of  the  lines  in  a
-                 multi-line  match  are output. Once a match has been handled,
-                 scanning restarts at the beginning of the line after the  one
-                 in which the match ended.
+                 Allow  patterns to match more than one line. When this option
+                 is set, the PCRE2 library is called in "multiline" mode,  and
+                 a  match  is  allowed to continue past the end of the initial
+                 line and onto one or more subsequent lines.
+
+                 Patterns used with -M may usefully  contain  literal  newline
+                 characters  and  internal  occurrences of ^ and $ characters,
+                 because in multiline mode these can match  at  internal  new-
+                 lines.  Because  pcre2grep is scanning multiple lines, the \Z
+                 and \z assertions match only at the end of the last  line  in
+                 the file.  The \A assertion matches at the start of the first
+                 line  of a match. This can be any line in the file; it is not
+                 anchored to the first line.
+
+                 The output for a successful match may consist  of  more  than
+                 one  line.  The  first  line  is  the line in which the match
+                 started, and the last line is the line  in  which  the  match
+                 ended.  If  the  matched string ends with a newline sequence,
+                 the output ends at the end of that line. If -v is  set,  none
+                 of  the  lines in a multi-line match are output. Once a match
+                 has been handled, scanning restarts at the beginning  of  the
+                 line after the one in which the match ended.
 
                  The  newline  sequence  that separates multiple lines must be
                  matched as part of the pattern.  For  example,  to  find  the
@@ -541,22 +572,24 @@ OPTIONS
                    pcre2grep -M 'regular\s+expression' 
 
                  The \s escape sequence matches any white space character, in-
-                 cluding newlines, and is followed by + so as to match  trail-
-                 ing  white  space  on the first line as well as possibly han-
+                 cluding  newlines, and is followed by + so as to match trail-
+                 ing white space on the first line as well  as  possibly  han-
                  dling a two-character newline sequence.
 
-                 There is a limit to the number of lines that can be  matched,
-                 imposed  by  the way that pcre2grep buffers the input file as
-                 it scans it. With a  sufficiently  large  processing  buffer,
-                 this should not be a problem, but the -M option does not work
-                 when input is read line by line (see --line-buffered.)
+                 There  is a limit to the number of lines that can be matched,
+                 imposed by the way that pcre2grep buffers the input  file  as
+                 it  scans  it.  With  a sufficiently large processing buffer,
+                 this should not be a problem.
+
+                 The -M option does not work when input is read line  by  line
+                 (see --line-buffered.)
 
        -m number, --max-count=number
-                 Stop processing after finding number matching lines, or  non-
-                 matching  lines if -v is also set. Any trailing context lines
-                 are output after the final match.  In  multiline  mode,  each
-                 multiline  match counts as just one line for this purpose. If
-                 this limit is reached when reading the standard input from  a
+                 Stop  processing after finding number matching lines, or non-
+                 matching lines if -v is also set. Any trailing context  lines
+                 are  output  after  the  final match. In multiline mode, each
+                 multiline match counts as just one line for this purpose.  If
+                 this  limit is reached when reading the standard input from a
                  regular file, the file is left positioned just after the last
                  matching line.  If -c is also set, the count that  is  output
                  is  never  greater  than number. This option has no effect if
@@ -564,21 +597,21 @@ OPTIONS
                  a binary file.
 
        --match-limit=number
-                 Processing  some  regular expression patterns may take a very
+                 Processing some regular expression patterns may take  a  very
                  long time to search for all possible matching strings. Others
                  may  require  a  very large amount of memory. There are three
                  options that set resource limits for matching.
 
                  The --match-limit option provides a means of limiting comput-
-                 ing  resource usage when processing patterns that are not go-
+                 ing resource usage when processing patterns that are not  go-
                  ing to match, but which have a very large number of possibil-
                  ities in their search trees. The classic example is a pattern
-                 that uses nested unlimited repeats. Internally, PCRE2  has  a
-                 counter  that  is  incremented each time around its main pro-
-                 cessing loop. If the value set by --match-limit  is  reached,
+                 that  uses  nested unlimited repeats. Internally, PCRE2 has a
+                 counter that is incremented each time around  its  main  pro-
+                 cessing  loop.  If the value set by --match-limit is reached,
                  an error occurs.
 
-                 The  --heap-limit  option specifies, as a number of kibibytes
+                 The --heap-limit option specifies, as a number  of  kibibytes
                  (units of 1024 bytes), the maximum amount of heap memory that
                  may be used for matching.
 
@@ -587,18 +620,18 @@ OPTIONS
                  that is used. The amount of memory needed for each backtrack-
                  ing point depends on the number of capturing  parentheses  in
                  the pattern, so the amount of memory that is used before this
-                 limit acts varies from pattern to pattern. This limit  is  of
+                 limit  acts  varies from pattern to pattern. This limit is of
                  use only if it is set smaller than --match-limit.
 
-                 There  are no short forms for these options. The default lim-
-                 its can be set when the PCRE2 library is  compiled;  if  they
-                 are  not specified, the defaults are very large and so effec-
+                 There are no short forms for these options. The default  lim-
+                 its  can  be  set when the PCRE2 library is compiled; if they
+                 are not specified, the defaults are very large and so  effec-
                  tively unlimited.
 
        --max-buffer-size=number
-                 This limits the expansion of  the  processing  buffer,  whose
-                 initial  size can be set by --buffer-size. The maximum buffer
-                 size is silently forced to be no smaller  than  the  starting
+                 This  limits  the  expansion  of the processing buffer, whose
+                 initial size can be set by --buffer-size. The maximum  buffer
+                 size  is  silently  forced to be no smaller than the starting
                  buffer size.
 
        -N newline-type, --newline=newline-type
@@ -626,45 +659,50 @@ OPTIONS
 
                  This  option makes it possible to use pcre2grep to scan files
                  that have come from other environments without having to mod-
-                 ify  their  line  endings.  If the data that is being scanned
-                 does not agree  with  the  convention  set  by  this  option,
-                 pcre2grep  may  behave in strange ways. Note that this option
-                 does not apply to files specified by the -f,  --exclude-from,
-                 or  --include-from options, which are expected to use the op-
+                 ify their line endings. If the data  that  is  being  scanned
+                 does  not  agree  with  the  convention  set  by this option,
+                 pcre2grep may behave in strange ways. Note that  this  option
+                 does  not apply to files specified by the -f, --exclude-from,
+                 or --include-from options, which are expected to use the  op-
                  erating system's standard newline sequence.
 
        -n, --line-number
                  Precede each output line by its line number in the file, fol-
                  lowed  by  a colon for matching lines or a hyphen for context
                  lines. If the file name is also being output, it precedes the
-                 line  number.  When  the  -M option causes a pattern to match
-                 more than one line, only the first is preceded  by  its  line
+                 line number. When the -M option causes  a  pattern  to  match
+                 more  than  one  line, only the first is preceded by its line
                  number. This option is forced if --line-offsets is used.
 
+       --no-group-separator
+                 Do not output a separator between groups of  lines  when  -A,
+                 -B, or -C is in use. The default is to output a line contain-
+                 ing two hyphens. See also --group-separator.
+
        --no-jit  If  the  PCRE2 library is built with support for just-in-time
                  compiling (which speeds up matching), pcre2grep automatically
                  makes use of this, unless it was explicitly disabled at build
                  time. This option can be used to disable the use  of  JIT  at
-                 run  time. It is provided for testing and working round prob-
+                 run time. It is provided for testing and working around prob-
                  lems.  It should never be needed in normal use.
 
        -O text, --output=text
-                 When there is a match, instead of outputting  the  line  that
-                 matched,  output just the text specified in this option, fol-
-                 lowed by an operating-system standard newline. In this  mode,
-                 --colour  has  no  effect, and no context is shown.  That is,
-                 the -A, -B, and -C options are ignored. The --newline  option
-                 has  no  effect  on  this option, which is mutually exclusive
+                 When  there  is  a match, instead of outputting the line that
+                 matched, output just the text specified in this option,  fol-
+                 lowed  by an operating-system standard newline. In this mode,
+                 --colour has no effect, and no context is  shown.   That  is,
+                 the  -A, -B, and -C options are ignored. The --newline option
+                 has no effect on this option,  which  is  mutually  exclusive
                  with  --only-matching,  --file-offsets,  and  --line-offsets.
-                 However,  like  --only-matching,  if  there  is more than one
+                 However, like --only-matching, if  there  is  more  than  one
                  match in a line, each of them causes a line of output.
 
                  Escape sequences starting with a dollar character may be used
                  to insert the contents of the matched part of the line and/or
                  captured substrings into the text.
 
-                 $ or ${} is replaced  by  the  captured  sub-
-                 string  of  the  given  decimal  number; zero substitutes the
+                 $  or  ${}  is  replaced by the captured sub-
+                 string of the given  decimal  number;  zero  substitutes  the
                  whole match. If the number is greater than the number of cap-
                  turing  substrings,  or if the capture is unset, the replace-
                  ment is empty.
@@ -674,18 +712,18 @@ OPTIONS
                  $v by vertical tab.
 
                  $o or $o{} is replaced by the character whose
-                 code  point  is the given octal number. In the first form, up
-                 to three octal digits are processed.  When  more  digits  are
-                 needed  in Unicode mode to specify a wide character, the sec-
+                 code point is the given octal number. In the first  form,  up
+                 to  three  octal  digits are processed.  When more digits are
+                 needed in Unicode mode to specify a wide character, the  sec-
                  ond form must be used.
 
-                 $x or $x{} is replaced by the character  rep-
-                 resented  by the given hexadecimal number. In the first form,
-                 up to two hexadecimal digits are processed. When more  digits
-                 are  needed  in Unicode mode to specify a wide character, the
+                 $x  or $x{} is replaced by the character rep-
+                 resented by the given hexadecimal number. In the first  form,
+                 up  to two hexadecimal digits are processed. When more digits
+                 are needed in Unicode mode to specify a wide  character,  the
                  second form must be used.
 
-                 Any other character is substituted by itself. In  particular,
+                 Any  other character is substituted by itself. In particular,
                  $$ is replaced by a single dollar.
 
        -o, --only-matching
@@ -705,10 +743,10 @@ OPTIONS
        -onumber, --only-matching=number
                  Show only the part of the line  that  matched  the  capturing
                  parentheses of the given number. Up to 50 capturing parenthe-
-                 ses are supported by default. This limit can be  changed  via
-                 the  --om-capture option. A pattern may contain any number of
-                 capturing parentheses, but only those whose number is  within
-                 the  limit can be accessed by -o. An error occurs if the num-
+                 ses  are  supported by default. This limit can be changed via
+                 the --om-capture option. A pattern may contain any number  of
+                 capturing  parentheses, but only those whose number is within
+                 the limit can be accessed by -o. An error occurs if the  num-
                  ber specified by -o is greater than the limit.
 
                  -o0 is the same as -o without a number. Because these options
@@ -736,32 +774,45 @@ OPTIONS
                  The default is an empty string. Separating strings are  never
                  coloured.
 
+       -P, --no-ucp
+                 Starting  from release 10.43, when UTF/Unicode mode is speci-
+                 fied with -u or -U, the PCRE2_UCP option is used by  default.
+                 This means that the POSIX classes in patterns match more than
+                 just  ASCII  characters.  For  example, [:digit:] matches any
+                 Unicode  decimal  digit.  The  --no-ucp   option   suppresses
+                 PCRE2_UCP,  thus restricting the POSIX classes to ASCII char-
+                 acters, as was the case in earlier releases. Note that  there
+                 are  now  more  fine-grained  option settings within patterns
+                 that affect individual classes.  For  example,  when  in  UCP
+                 mode, the sequence (?aP) restricts [:word:] to ASCII letters,
+                 while allowing \w to match Unicode letters and digits.
+
        -q, --quiet
                  Work quietly, that is, display nothing except error messages.
-                 The exit status indicates whether or  not  any  matches  were
+                 The  exit  status  indicates  whether or not any matches were
                  found.
 
        -r, --recursive
-                 If  any given path is a directory, recursively scan the files
-                 it contains, taking note of any --include and --exclude  set-
-                 tings.  By  default, a directory is read as a normal file; in
-                 some operating systems this gives an  immediate  end-of-file.
-                 This  option is a shorthand for setting the -d option to "re-
+                 If any given path is a directory, recursively scan the  files
+                 it  contains, taking note of any --include and --exclude set-
+                 tings. By default, a directory is read as a normal  file;  in
+                 some  operating  systems this gives an immediate end-of-file.
+                 This option is a shorthand for setting the -d option to  "re-
                  curse".
 
        --recursion-limit=number
-                 This is an obsolete synonym for --depth-limit.  See  --match-
+                 This  is  an obsolete synonym for --depth-limit. See --match-
                  limit above for details.
 
        -s, --no-messages
-                 Suppress  error  messages  about  non-existent  or unreadable
-                 files. Such files are quietly skipped.  However,  the  return
+                 Suppress error  messages  about  non-existent  or  unreadable
+                 files.  Such  files  are quietly skipped. However, the return
                  code is still 2, even if matches were found in other files.
 
        -t, --total-count
-                 This  option  is  useful when scanning more than one file. If
-                 used on its own, -t suppresses all output except for a  grand
-                 total  number  of matching lines (or non-matching lines if -v
+                 This option is useful when scanning more than  one  file.  If
+                 used  on its own, -t suppresses all output except for a grand
+                 total number of matching lines (or non-matching lines  if  -v
                  is used) in all the files. If -t is used with -c, a grand to-
                  tal  is  output  except  when the previous output is just one
                  line. In other words, it is not output when just  one  file's
@@ -771,11 +822,12 @@ OPTIONS
                  (list files without matches), because the grand  total  would
                  always be zero.
 
-       -u, --utf Operate in UTF-8 mode. This option is available only if PCRE2
-                 has been compiled with UTF-8 support. All patterns (including
-                 those  for any --exclude and --include options) and all lines
-                 that are scanned must be valid strings of  UTF-8  characters.
-                 If an invalid UTF-8 string is encountered, an error occurs.
+       -u, --utf Operate in UTF/Unicode mode. This option is available only if
+                 PCRE2 has been compiled with UTF-8 support. All patterns (in-
+                 cluding  those  for  any --exclude and --include options) and
+                 all lines that are scanned must be  valid  strings  of  UTF-8
+                 characters. If an invalid UTF-8 string is encountered, an er-
+                 ror occurs.
 
        -U, --utf-allow-invalid
                  As  --utf,  but in addition subject lines may contain invalid
@@ -800,28 +852,28 @@ OPTIONS
 
        -w, --word-regex, --word-regexp
                  Force the patterns only to match "words". That is, there must
-                 be a word boundary at the  start  and  end  of  each  matched
-                 string.  This is equivalent to having "\b(?:" at the start of
-                 each pattern, and ")\b" at the end. This option applies  only
-                 to  the  patterns  that  are  matched against the contents of
-                 files; it does not apply to patterns specified by any of  the
+                 be  a  word  boundary  at  the  start and end of each matched
+                 string. This is equivalent to having "\b(?:" at the start  of
+                 each  pattern, and ")\b" at the end. This option applies only
+                 to the patterns that are  matched  against  the  contents  of
+                 files;  it does not apply to patterns specified by any of the
                  --include or --exclude options.
 
        -x, --line-regex, --line-regexp
-                 Force  the  patterns to start matching only at the beginnings
-                 of lines, and in  addition,  require  them  to  match  entire
+                 Force the patterns to start matching only at  the  beginnings
+                 of  lines,  and  in  addition,  require  them to match entire
                  lines. In multiline mode the match may be more than one line.
                  This is equivalent to having "^(?:" at the start of each pat-
-                 tern  and  ")$"  at  the end. This option applies only to the
-                 patterns that are matched against the contents of  files;  it
-                 does  not apply to patterns specified by any of the --include
+                 tern and ")$" at the end. This option  applies  only  to  the
+                 patterns  that  are matched against the contents of files; it
+                 does not apply to patterns specified by any of the  --include
                  or --exclude options.
 
        -Z, --null
-                 Terminate files names in the regular output with a zero  byte
-                 (the  NUL  character)  instead of what would normally appear.
-                 This is useful when file  names  contain  unusual  characters
-                 such  as  colons,  hyphens, or even newlines. The option does
+                 Terminate  files names in the regular output with a zero byte
+                 (the NUL character) instead of what  would  normally  appear.
+                 This  is  useful  when  file names contain unusual characters
+                 such as colons, hyphens, or even newlines.  The  option  does
                  not apply to file names in error messages.
 
 
@@ -858,22 +910,24 @@ NEWLINES
        stream, "\n" is used.
 
 
-OPTIONS COMPATIBILITY
+OPTIONS COMPATIBILITY WITH GNU GREP
 
        Many of the short and long forms of pcre2grep's options are the same as
-       in the GNU grep program. Any long option of the form --xxx-regexp  (GNU
-       terminology) is also available as --xxx-regex (PCRE2 terminology). How-
-       ever, the  --depth-limit,  --file-list,  --file-offsets,  --heap-limit,
-       --include-dir,  --line-offsets,  --locale,  --match-limit, -M, --multi-
-       line, -N, --newline,  --om-separator,  --output,  -u,  --utf,  -U,  and
-       --utf-allow-invalid options are specific to pcre2grep, as is the use of
-       the --only-matching option with a capturing parentheses number.
-
-       Although most of the common options work the same way, a few  are  dif-
-       ferent  in pcre2grep. For example, the --include option's argument is a
-       glob for GNU grep, but a regular expression for pcre2grep. If both  the
-       -c  and  -l  options are given, GNU grep lists only file names, without
-       counts, but pcre2grep gives the counts as well.
+       in  the GNU grep program. Any long option of the form --xxx-regexp (GNU
+       terminology) is also  available  as  --xxx-regex  (PCRE2  terminology).
+       However,  the  --case-restrict, --depth-limit, -E, --file-list, --file-
+       offsets,   --heap-limit,   --include-dir,   --line-offsets,   --locale,
+       --match-limit,  -M,  --multiline, -N, --newline, --no-ucp, --om-separa-
+       tor, --output, -P, -u, --utf, -U, and --utf-allow-invalid  options  are
+       specific to pcre2grep, as is the use of the --only-matching option with
+       a capturing parentheses number.
+
+       Although  most  of the common options work the same way, a few are dif-
+       ferent in pcre2grep. For example, the --include option's argument is  a
+       glob for GNU grep, but in pcre2grep it is a regular expression to which
+       the  -i  option  applies.  If both the -c and -l options are given, GNU
+       grep lists only file names, without counts,  but  pcre2grep  gives  the
+       counts as well.
 
 
 OPTIONS WITH DATA
@@ -886,36 +940,36 @@ OPTIONS WITH DATA
          -f/some/file
          -f /some/file
 
-       The  exception is the -o option, which may appear with or without data.
-       Because of this, if data is present, it must follow immediately in  the
+       The exception is the -o option, which may appear with or without  data.
+       Because  of this, if data is present, it must follow immediately in the
        same item, for example -o3.
 
-       If  a long form option is used, the data may appear in the same command
-       line item, separated by an equals character, or (with  two  exceptions)
+       If a long form option is used, the data may appear in the same  command
+       line  item,  separated by an equals character, or (with two exceptions)
        it may appear in the next command line item. For example:
 
          --file=/some/file
          --file /some/file
 
-       Note,  however, that if you want to supply a file name beginning with ~
-       as data in a shell command, and have the shell expand ~ to a  home  di-
-       rectory,  you  must separate the file name from the option, because the
+       Note, however, that if you want to supply a file name beginning with  ~
+       as  data  in a shell command, and have the shell expand ~ to a home di-
+       rectory, you must separate the file name from the option,  because  the
        shell does not treat ~ specially unless it is at the start of an item.
 
-       The exceptions to the above are the --colour (or --color)  and  --only-
-       matching  options,  for which the data is optional. If one of these op-
-       tions does have data, it must be given in  the  first  form,  using  an
+       The  exceptions  to the above are the --colour (or --color) and --only-
+       matching options, for which the data is optional. If one of  these  op-
+       tions  does  have  data,  it  must be given in the first form, using an
        equals character. Otherwise pcre2grep will assume that it has no data.
 
 
 USING PCRE2'S CALLOUT FACILITY
 
-       pcre2grep  has,  by  default,  support for calling external programs or
-       scripts or echoing specific strings during matching by  making  use  of
-       PCRE2's  callout  facility.  However, this support can be completely or
-       partially disabled when pcre2grep is built. You can  find  out  whether
-       your  binary has support for callouts by running it with the --help op-
-       tion. If callout support is completely disabled, all callouts  in  pat-
+       pcre2grep has, by default, support for  calling  external  programs  or
+       scripts  or  echoing  specific strings during matching by making use of
+       PCRE2's callout facility. However, this support can  be  completely  or
+       partially  disabled  when  pcre2grep is built. You can find out whether
+       your binary has support for callouts by running it with the --help  op-
+       tion.  If  callout support is completely disabled, all callouts in pat-
        terns are ignored by pcre2grep.  If the facility is partially disabled,
        calling external programs is not supported, and callouts  that  request
        it are ignored.
@@ -929,23 +983,23 @@ USING PCRE2'S CALLOUT FACILITY
 
        Starting the callout string with a pipe character  invokes  an  echoing
        facility that avoids calling an external program or script. This facil-
-       ity is always available, provided that  callouts  were  not  completely
-       disabled  when  pcre2grep  was built. The rest of the callout string is
-       processed as a zero-terminated string, which means it should  not  con-
-       tain  any  internal  binary  zeros. It is written to the output, having
-       first been passed through the same escape processing as text  from  the
-       --output  (-O) option (see above). However, $0 cannot be used to insert
-       a matched substring because the match is still  in  progress.  Instead,
-       the  single  character '0' is inserted. Any syntax errors in the string
-       (for example, a dollar not followed by another  character)  causes  the
-       callout  to be ignored. No terminator is added to the output string, so
-       if you want a newline, you must include it explicitly using the  escape
+       ity  is  always  available,  provided that callouts were not completely
+       disabled when pcre2grep was built. The rest of the  callout  string  is
+       processed  as  a zero-terminated string, which means it should not con-
+       tain any internal binary zeros. It is written  to  the  output,  having
+       first  been  passed through the same escape processing as text from the
+       --output (-O) option (see above). However, $0 cannot be used to  insert
+       a  matched  substring  because the match is still in progress. Instead,
+       the single character '0' is inserted. Any syntax errors in  the  string
+       (for  example,  a  dollar not followed by another character) causes the
+       callout to be ignored. No terminator is added to the output string,  so
+       if  you want a newline, you must include it explicitly using the escape
        $n. For example:
 
          pcre2grep '(.)(..(.))(?C"|[$1] [$2] [$3]$n")' 
 
-       Matching  continues normally after the string is output. If you want to
-       see only the callout output but not any output from  an  actual  match,
+       Matching continues normally after the string is output. If you want  to
+       see  only  the  callout output but not any output from an actual match,
        you should end the pattern with (*FAIL).
 
    Calling external programs or scripts
@@ -956,14 +1010,14 @@ USING PCRE2'S CALLOUT FACILITY
        fork() and execv() are available.
 
        If the callout string does not start with a pipe (vertical bar) charac-
-       ter,  it  is parsed into a list of substrings separated by pipe charac-
-       ters. The first substring must be an executable name, with the  follow-
+       ter, it is parsed into a list of substrings separated by  pipe  charac-
+       ters.  The first substring must be an executable name, with the follow-
        ing substrings specifying arguments:
 
          executable_name|arg1|arg2|...
 
-       Any  substring  (including  the executable name) may contain escape se-
-       quences started by a dollar character. These are the same  as  for  the
+       Any substring (including the executable name) may  contain  escape  se-
+       quences  started  by  a dollar character. These are the same as for the
        --output (-O) option documented above, except that $0 cannot insert the
        matched string because the match is still  in  progress.  Instead,  the
        character '0' is inserted. If you need a literal dollar or pipe charac-
@@ -980,30 +1034,30 @@ USING PCRE2'S CALLOUT FACILITY
            Arg1: [1] [234] [4] Arg2: |1| ()
            12345
 
-       The parameters for the system call that is used to run the  program  or
+       The  parameters  for the system call that is used to run the program or
        script are zero-terminated strings. This means that binary zero charac-
        ters in the callout argument will cause premature termination of  their
        substrings,  and  therefore should not be present. Any syntax errors in
        the string (for example, a dollar not followed  by  another  character)
        causes the callout to be ignored.  If running the program fails for any
-       reason (including the non-existence of the executable), a local  match-
+       reason  (including the non-existence of the executable), a local match-
        ing failure occurs and the matcher backtracks in the normal way.
 
 
 MATCHING ERRORS
 
-       It  is  possible  to supply a regular expression that takes a very long
-       time to fail to match certain lines.  Such  patterns  normally  involve
-       nested  indefinite repeats, for example: (a+)*\d when matched against a
-       line of a's with no final digit. The PCRE2 matching function has a  re-
-       source  limit  that  causes it to abort in these circumstances. If this
-       happens, pcre2grep outputs an error message and the  line  that  caused
-       the  problem  to  the  standard error stream. If there are more than 20
+       It is possible to supply a regular expression that takes  a  very  long
+       time  to  fail  to  match certain lines. Such patterns normally involve
+       nested indefinite repeats, for example: (a+)*\d when matched against  a
+       line  of a's with no final digit. The PCRE2 matching function has a re-
+       source limit that causes it to abort in these  circumstances.  If  this
+       happens,  pcre2grep  outputs  an error message and the line that caused
+       the problem to the standard error stream. If there  are  more  than  20
        such errors, pcre2grep gives up.
 
-       The --match-limit option of pcre2grep can be used to  set  the  overall
-       resource  limit.  There are also other limits that affect the amount of
-       memory used during matching; see the  discussion  of  --heap-limit  and
+       The  --match-limit  option  of pcre2grep can be used to set the overall
+       resource limit. There are also other limits that affect the  amount  of
+       memory  used  during  matching;  see the discussion of --heap-limit and
        --depth-limit above.
 
 
@@ -1015,8 +1069,8 @@ DIAGNOSTICS
        errors. Using the -s option to suppress error messages about inaccessi-
        ble files does not affect the return code.
 
-       When   run  under  VMS,  the  return  code  is  placed  in  the  symbol
-       PCRE2GREP_RC because VMS  does  not  distinguish  between  exit(0)  and
+       When  run  under  VMS,  the  return  code  is  placed  in  the   symbol
+       PCRE2GREP_RC  because  VMS  does  not  distinguish  between exit(0) and
        exit(1).
 
 
@@ -1034,5 +1088,8 @@ AUTHOR
 
 REVISION
 
-       Last updated: 21 November 2022
-       Copyright (c) 1997-2022 University of Cambridge.
+       Last updated: 22 December 2023
+       Copyright (c) 1997-2023 University of Cambridge.
+
+
+PCRE2 10.43                    22 December 2023                   PCRE2GREP(1)
diff --git a/pcre2/doc/pcre2jit.3 b/pcre2/doc/pcre2jit.3
index f0b3b15..8798089 100644
--- a/pcre2/doc/pcre2jit.3
+++ b/pcre2/doc/pcre2jit.3
@@ -1,4 +1,4 @@
-.TH PCRE2JIT 3 "30 November 2021" "PCRE2 10.40"
+.TH PCRE2JIT 3 "21 February 2024" "PCRE2 10.43"
 .SH NAME
 PCRE2 - Perl-compatible regular expressions (revised API)
 .SH "PCRE2 JUST-IN-TIME COMPILER SUPPORT"
@@ -16,7 +16,7 @@ one-off matches. JIT support is available for all of the 8-bit, 16-bit and
 .P
 JIT support applies only to the traditional Perl-compatible matching function.
 It does not apply when the DFA matching function is being used. The code for
-this support was written by Zoltan Herczeg.
+JIT support was written by Zoltan Herczeg.
 .
 .
 .SH "AVAILABILITY OF JIT SUPPORT"
@@ -27,22 +27,41 @@ JIT support is an optional feature of PCRE2. The "configure" option
 you want to use JIT. The support is limited to the following hardware
 platforms:
 .sp
-  ARM 32-bit (v5, v7, and Thumb2)
+  ARM 32-bit (v7, and Thumb2)
   ARM 64-bit
   IBM s390x 64 bit
   Intel x86 32-bit and 64-bit
+  LoongArch 64 bit
   MIPS 32-bit and 64-bit
   Power PC 32-bit and 64-bit
-  SPARC 32-bit
+  RISC-V 32-bit and 64-bit
 .sp
 If --enable-jit is set on an unsupported platform, compilation fails.
 .P
-A program can tell if JIT support is available by calling \fBpcre2_config()\fP
-with the PCRE2_CONFIG_JIT option. The result is 1 when JIT is available, and 0
-otherwise. However, a simple program does not need to check this in order to
-use JIT. The API is implemented in a way that falls back to the interpretive
-code if JIT is not available. For programs that need the best possible
-performance, there is also a "fast path" API that is JIT-specific.
+A client program can tell if JIT support is available by calling
+\fBpcre2_config()\fP with the PCRE2_CONFIG_JIT option. The result is one if
+PCRE2 was built with JIT support, and zero otherwise. However, having the JIT
+code available does not guarantee that it will be used for any particular
+match. One reason for this is that there are a number of options and pattern
+items that are
+.\" HTML 
+.\" 
+not supported by JIT
+.\"
+(see below). Another reason is that in some environments JIT is unable to get
+memory in which to build its compiled code. The only guarantee from
+\fBpcre2_config()\fP is that if it returns zero, JIT will definitely \fInot\fP
+be used.
+.P
+A simple program does not need to check availability in order to use JIT when
+possible. The API is implemented in a way that falls back to the interpretive
+code if JIT is not available or cannot be used for a given match. For programs
+that need the best possible performance, there is a
+.\" HTML 
+.\" 
+"fast path"
+.\"
+API that is JIT-specific.
 .
 .
 .SH "SIMPLE USE OF JIT"
@@ -99,9 +118,13 @@ below.
 .P
 There are some \fBpcre2_match()\fP options that are not supported by JIT, and
 there are also some pattern items that JIT cannot handle. Details are given
-below. In both cases, matching automatically falls back to the interpretive
-code. If you want to know whether JIT was actually used for a particular match,
-you should arrange for a JIT callback function to be set up as described in the
+.\" HTML 
+.\" 
+below.
+.\"
+In both cases, matching automatically falls back to the interpretive code. If
+you want to know whether JIT was actually used for a particular match, you
+should arrange for a JIT callback function to be set up as described in the
 section entitled
 .\" HTML 
 .\" 
@@ -113,12 +136,14 @@ match-time options are not right for JIT execution, the callback function is
 not obeyed.
 .P
 If the JIT compiler finds an unsupported item, no JIT data is generated. You
-can find out if JIT matching is available after compiling a pattern by calling
-\fBpcre2_pattern_info()\fP with the PCRE2_INFO_JITSIZE option. A non-zero
-result means that JIT compilation was successful. A result of 0 means that JIT
-support is not available, or the pattern was not processed by
+can find out if JIT compilation was successful for a compiled pattern by
+calling \fBpcre2_pattern_info()\fP with the PCRE2_INFO_JITSIZE option. A
+non-zero result means that JIT compilation was successful. A result of 0 means
+that JIT support is not available, or the pattern was not processed by
 \fBpcre2_jit_compile()\fP, or the JIT compiler was not able to handle the
-pattern.
+pattern. Successful JIT compilation does not, however, guarantee the use of JIT
+at match time because there are some match time options that are not supported
+by JIT.
 .
 .
 .SH "MATCHING SUBJECTS CONTAINING INVALID UTF"
@@ -130,14 +155,15 @@ checked at the start of matching and an error is generated if invalid UTF is
 detected. The PCRE2_NO_UTF_CHECK option can be passed to \fBpcre2_match()\fP to
 skip the check (for improved performance) if you are sure that a subject string
 is valid. If this option is used with an invalid string, the result is
-undefined.
+undefined. The calling program may crash or loop or otherwise misbehave.
 .P
 However, a way of running matches on strings that may contain invalid UTF
 sequences is available. Calling \fBpcre2_compile()\fP with the
 PCRE2_MATCH_INVALID_UTF option has two effects: it tells the interpreter in
 \fBpcre2_match()\fP to support invalid UTF, and, if \fBpcre2_jit_compile()\fP
-is called, the compiled JIT code also supports invalid UTF. Details of how this
-support works, in both the JIT and the interpretive cases, is given in the
+is subsequently called, the compiled JIT code also supports invalid UTF.
+Details of how this support works, in both the JIT and the interpretive cases,
+is given in the
 .\" HREF
 \fBpcre2unicode\fP
 .\"
@@ -149,6 +175,7 @@ It is superseded by the \fBpcre2_compile()\fP option PCRE2_MATCH_INVALID_UTF
 and should no longer be used. It may be removed in future.
 .
 .
+.\" HTML 
 .SH "UNSUPPORTED OPTIONS AND PATTERN ITEMS"
 .rs
 .sp
@@ -169,10 +196,10 @@ in a conditional group.
 .SH "RETURN VALUES FROM JIT MATCHING"
 .rs
 .sp
-When a pattern is matched using JIT matching, the return values are the same
-as those given by the interpretive \fBpcre2_match()\fP code, with the addition
-of one new error code: PCRE2_ERROR_JIT_STACKLIMIT. This means that the memory
-used for the JIT stack was insufficient. See
+When a pattern is matched using JIT, the return values are the same as those
+given by the interpretive \fBpcre2_match()\fP code, with the addition of one
+new error code: PCRE2_ERROR_JIT_STACKLIMIT. This means that the memory used for
+the JIT stack was insufficient. See
 .\" HTML 
 .\" 
 "Controlling the JIT stack"
@@ -335,7 +362,7 @@ list of patterns.
 pattern causes stack overflow with a stack of 1MiB? Is that 1MiB kept until the
 stack is freed?
 .sp
-Especially on embedded sytems, it might be a good idea to release memory
+Especially on embedded systems, it might be a good idea to release memory
 sometimes without freeing the stack. There is no API for this at the moment.
 Probably a function call which returns with the currently allocated memory for
 any stack and another which allows releasing memory (shrinking the stack) would
@@ -393,6 +420,7 @@ calls.
 .sp
 .
 .
+.\" HTML 
 .SH "JIT FAST PATH API"
 .rs
 .sp
@@ -408,18 +436,21 @@ processed by \fBpcre2_jit_compile()\fP).
 The fast path function is called \fBpcre2_jit_match()\fP, and it takes exactly
 the same arguments as \fBpcre2_match()\fP. However, the subject string must be
 specified with a length; PCRE2_ZERO_TERMINATED is not supported. Unsupported
-option bits (for example, PCRE2_ANCHORED, PCRE2_ENDANCHORED and
-PCRE2_COPY_MATCHED_SUBJECT) are ignored, as is the PCRE2_NO_JIT option. The
-return values are also the same as for \fBpcre2_match()\fP, plus
-PCRE2_ERROR_JIT_BADOPTION if a matching mode (partial or complete) is requested
-that was not compiled.
+option bits (for example, PCRE2_ANCHORED and PCRE2_ENDANCHORED) are ignored, as
+is the PCRE2_NO_JIT option. The return values are also the same as for
+\fBpcre2_match()\fP, plus PCRE2_ERROR_JIT_BADOPTION if a matching mode (partial
+or complete) is requested that was not compiled.
 .P
 When you call \fBpcre2_match()\fP, as well as testing for invalid options, a
 number of other sanity checks are performed on the arguments. For example, if
 the subject pointer is NULL but the length is non-zero, an immediate error is
 given. Also, unless PCRE2_NO_UTF_CHECK is set, a UTF subject string is tested
 for validity. In the interests of speed, these checks do not happen on the JIT
-fast path, and if invalid data is passed, the result is undefined.
+fast path. If invalid UTF data is passed when PCRE2_MATCH_INVALID_UTF was not
+set for \fBpcre2_compile()\fP, the result is undefined. The program may crash
+or loop or give wrong results. In the absence of PCRE2_MATCH_INVALID_UTF you
+should call \fBpcre2_jit_match()\fP in UTF mode only if you are sure the
+subject is valid.
 .P
 Bypassing the sanity checks and the \fBpcre2_match()\fP wrapping can give
 speedups of more than 10%.
@@ -428,7 +459,7 @@ speedups of more than 10%.
 .SH "SEE ALSO"
 .rs
 .sp
-\fBpcre2api\fP(3)
+\fBpcre2api\fP(3), \fBpcre2unicode\fP(3)
 .
 .
 .SH AUTHOR
@@ -436,7 +467,7 @@ speedups of more than 10%.
 .sp
 .nf
 Philip Hazel (FAQ by Zoltan Herczeg)
-University Computing Service
+Retired from University Computing Service
 Cambridge, England.
 .fi
 .
@@ -445,6 +476,6 @@ Cambridge, England.
 .rs
 .sp
 .nf
-Last updated: 30 November 2021
-Copyright (c) 1997-2021 University of Cambridge.
+Last updated: 21 February 2024
+Copyright (c) 1997-2024 University of Cambridge.
 .fi
diff --git a/pcre2/doc/pcre2limits.3 b/pcre2/doc/pcre2limits.3
index 9281aa6..a1ea3ea 100644
--- a/pcre2/doc/pcre2limits.3
+++ b/pcre2/doc/pcre2limits.3
@@ -1,4 +1,4 @@
-.TH PCRE2LIMITS 3 "26 July 2022" "PCRE2 10.41"
+.TH PCRE2LIMITS 3 "1 August 2023" "PCRE2 10.43"
 .SH NAME
 PCRE2 - Perl-compatible regular expressions (revised API)
 .SH "SIZE AND OTHER LIMITATIONS"
@@ -32,7 +32,12 @@ and unset offsets.
 .P
 All values in repeating quantifiers must be less than 65536.
 .P
-The maximum length of a lookbehind assertion is 65535 characters.
+There are two different limits that apply to branches of lookbehind assertions.
+If every branch in such an assertion matches a fixed number of characters,
+the maximum length of any branch is 65535 characters. If any branch matches a
+variable number of characters, then the maximum matching length for every
+branch is limited. The default limit is set at compile time, defaulting to 255,
+but can be changed by the calling program.
 .P
 There is no limit to the number of parenthesized groups, but there can be no
 more than 65535 capture groups, and there is a limit to the depth of nesting of
@@ -71,6 +76,6 @@ Cambridge, England.
 .rs
 .sp
 .nf
-Last updated: 26 July 2022
-Copyright (c) 1997-2022 University of Cambridge.
+Last updated: August 2023
+Copyright (c) 1997-2023 University of Cambridge.
 .fi
diff --git a/pcre2/doc/pcre2matching.3 b/pcre2/doc/pcre2matching.3
index 673952d..96800ef 100644
--- a/pcre2/doc/pcre2matching.3
+++ b/pcre2/doc/pcre2matching.3
@@ -1,4 +1,4 @@
-.TH PCRE2MATCHING 3 "28 August 2021" "PCRE2 10.38"
+.TH PCRE2MATCHING 3 "19 January 2024" "PCRE2 10.43"
 .SH NAME
 PCRE2 - Perl-compatible regular expressions (revised API)
 .SH "PCRE2 MATCHING ALGORITHMS"
@@ -7,7 +7,7 @@ PCRE2 - Perl-compatible regular expressions (revised API)
 This document describes the two different algorithms that are available in
 PCRE2 for matching a compiled regular expression against a given subject
 string. The "standard" algorithm is the one provided by the \fBpcre2_match()\fP
-function. This works in the same as as Perl's matching function, and provide a
+function. This works in the same as Perl's matching function, and provide a
 Perl-compatible matching operation. The just-in-time (JIT) optimization that is
 described in the
 .\" HREF
@@ -217,6 +217,6 @@ Cambridge, England.
 .rs
 .sp
 .nf
-Last updated: 28 August 2021
-Copyright (c) 1997-2021 University of Cambridge.
+Last updated: 19 January 2024
+Copyright (c) 1997-2024 University of Cambridge.
 .fi
diff --git a/pcre2/doc/pcre2partial.3 b/pcre2/doc/pcre2partial.3
index 892906a..cf8006d 100644
--- a/pcre2/doc/pcre2partial.3
+++ b/pcre2/doc/pcre2partial.3
@@ -359,7 +359,7 @@ can then try a new match starting at offset \fIn+1\fP in the first buffer.
 .sp
 .nf
 Philip Hazel
-University Computing Service
+Retired from University Computing Service
 Cambridge, England.
 .fi
 .
diff --git a/pcre2/doc/pcre2pattern.3 b/pcre2/doc/pcre2pattern.3
index 3088ec0..c3ccb0b 100644
--- a/pcre2/doc/pcre2pattern.3
+++ b/pcre2/doc/pcre2pattern.3
@@ -1,4 +1,4 @@
-.TH PCRE2PATTERN 3 "12 January 2022" "PCRE2 10.40"
+.TH PCRE2PATTERN 3 "04 June 2024" "PCRE2 10.44"
 .SH NAME
 PCRE2 - Perl-compatible regular expressions (revised API)
 .SH "PCRE2 REGULAR EXPRESSION DETAILS"
@@ -77,6 +77,12 @@ such as \ed and \ew to use Unicode properties to determine character types,
 instead of recognizing only characters with codes less than 256 via a lookup
 table. If also causes upper/lower casing operations to use Unicode properties
 for characters with code points greater than 127, even when UTF is not set.
+These behaviours can be changed within the pattern; see the section entitled
+.\" HTML 
+.\" 
+"Internal Option Setting"
+.\"
+below.
 .P
 Some applications that allow their users to supply patterns may wish to
 restrict them for security reasons. If the PCRE2_NEVER_UCP option is passed to
@@ -267,7 +273,9 @@ caseless matching is specified (the PCRE2_CASELESS option or (?i) within the
 pattern), letters are matched independently of case. Note that there are two
 ASCII characters, K and S, that, in addition to their lower case ASCII
 equivalents, are case-equivalent with Unicode U+212A (Kelvin sign) and U+017F
-(long S) respectively when either PCRE2_UTF or PCRE2_UCP is set.
+(long S) respectively when either PCRE2_UTF or PCRE2_UCP is set, unless the
+PCRE2_EXTRA_CASELESS_RESTRICT option is in force (either passed to
+\fBpcre2_compile()\fP or set by (?r) within the pattern).
 .P
 The power of regular expressions comes from the ability to include wild cards,
 character classes, alternatives, and repetitions in the pattern. These are
@@ -290,8 +298,17 @@ are as follows:
   *      0 or more quantifier
   +      1 or more quantifier; also "possessive quantifier"
   ?      0 or 1 quantifier; also quantifier minimizer
-  {      start min/max quantifier
+  {      potential start of min/max quantifier
 .sp
+Brace characters { and } are also used to enclose data for constructions such
+as \eg{2} or \ek{name}. In almost all uses of braces, space and/or horizontal
+tab characters that follow { or precede } are allowed and are ignored. In the
+case of quantifiers, they may also appear before or after the comma. The
+exception to this is \eu{...} which is an ECMAScript compatibility feature
+that is recognized only when the PCRE2_EXTRA_ALT_BSUX option is set. ECMAScript
+does not ignore such white space; it causes the item to be interpreted as
+literal.
+.P
 Part of a pattern that is in square brackets is called a "character class". In
 a character class the only metacharacters are:
 .sp
@@ -302,11 +319,11 @@ a character class the only metacharacters are:
   ]      terminates the character class
 .sp
 If a pattern is compiled with the PCRE2_EXTENDED option, most white space in
-the pattern, other than in a character class, and characters between a #
-outside a character class and the next newline, inclusive, are ignored. An
-escaping backslash can be used to include a white space or a # character as
-part of the pattern. If the PCRE2_EXTENDED_MORE option is set, the same
-applies, but in addition unescaped space and horizontal tab characters are
+the pattern, other than in a character class, within a \eQ...\eE sequence, or
+between a # outside a character class and the next newline, inclusive, are
+ignored. An escaping backslash can be used to include a white space or a #
+character as part of the pattern. If the PCRE2_EXTENDED_MORE option is set, the
+same applies, but in addition unescaped space and horizontal tab characters are
 ignored inside a character class. Note: only these two characters are ignored,
 not the full set of pattern white space characters that are ignored outside a
 character class. Option settings can be changed within a pattern; see the
@@ -339,12 +356,14 @@ other characters (in particular, those whose code points are greater than 127)
 are treated as literals.
 .P
 If you want to treat all characters in a sequence as literals, you can do so by
-putting them between \eQ and \eE. This is different from Perl in that $ and @
-are handled as literals in \eQ...\eE sequences in PCRE2, whereas in Perl, $ and
-@ cause variable interpolation. Also, Perl does "double-quotish backslash
-interpolation" on any backslashes between \eQ and \eE which, its documentation
-says, "may lead to confusing results". PCRE2 treats a backslash between \eQ and
-\eE just like any other character. Note the following examples:
+putting them between \eQ and \eE. Note that this includes white space even when
+the PCRE2_EXTENDED option is set so that most other white space is ignored. The
+behaviour is different from Perl in that $ and @ are handled as literals in
+\eQ...\eE sequences in PCRE2, whereas in Perl, $ and @ cause variable
+interpolation. Also, Perl does "double-quotish backslash interpolation" on any
+backslashes between \eQ and \eE which, its documentation says, "may lead to
+confusing results". PCRE2 treats a backslash between \eQ and \eE just like any
+other character. Note the following examples:
 .sp
   Pattern            PCRE2 matches   Perl matches
 .sp
@@ -360,8 +379,8 @@ The \eQ...\eE sequence is recognized both inside and outside character classes.
 An isolated \eE that is not preceded by \eQ is ignored. If \eQ is not followed
 by \eE later in the pattern, the literal interpretation continues to the end of
 the pattern (that is, \eE is assumed at the end). If the isolated \eQ is inside
-a character class, this causes an error, because the character class is not
-terminated by a closing square bracket.
+a character class, this causes an error, because the character class is then
+not terminated by a closing square bracket.
 .
 .
 .\" HTML 
@@ -376,7 +395,7 @@ instead of the binary character it represents. In an ASCII or Unicode
 environment, these escapes are as follows:
 .sp
   \ea          alarm, that is, the BEL character (hex 07)
-  \ecx         "control-x", where x is any printable ASCII character
+  \ecx         "control-x", where x is a non-control ASCII character
   \ee          escape (hex 1B)
   \ef          form feed (hex 0C)
   \en          linefeed (hex 0A)
@@ -410,8 +429,9 @@ interpreted as a literal "u" character.
 .P
 PCRE2_EXTRA_ALT_BSUX has the same effect as PCRE2_ALT_BSUX and, in addition,
 \eu{hhh..} is recognized as the character specified by hexadecimal code point.
-There may be any number of hexadecimal digits. This syntax is from ECMAScript
-6.
+There may be any number of hexadecimal digits, but unlike other places that
+also use curly brackets, spaces are not allowed and would result in the string
+being interpreted as a literal. This syntax is from ECMAScript 6.
 .P
 The \eN{U+hhh..} escape sequence is recognized only when PCRE2 is operating in
 UTF mode. Perl also uses \eN{name} to specify characters by Unicode name; PCRE2
@@ -424,12 +444,13 @@ match a newline. If the PCRE2_EXTRA_ESCAPED_CR_IS_LF option is set, \er in a
 pattern is converted to \en so that it matches a LF (linefeed) instead of a CR
 (carriage return) character.
 .P
-The precise effect of \ecx on ASCII characters is as follows: if x is a lower
-case letter, it is converted to upper case. Then bit 6 of the character (hex
-40) is inverted. Thus \ecA to \ecZ become hex 01 to hex 1A (A is 41, Z is 5A),
-but \ec{ becomes hex 3B ({ is 7B), and \ec; becomes hex 7B (; is 3B). If the
-code unit following \ec has a value less than 32 or greater than 126, a
-compile-time error occurs.
+An error occurs if \ec is not followed by a character whose ASCII code point
+is in the range 32 to 126. The precise effect of \ecx is as follows: if x is a
+lower case letter, it is converted to upper case. Then bit 6 of the character
+(hex 40) is inverted. Thus \ecA to \ecZ become hex 01 to hex 1A (A is 41, Z is
+5A), but \ec{ becomes hex 3B ({ is 7B), and \ec; becomes hex 7B (; is 3B). If
+the code unit following \ec has a code point less than 32 or greater than 126,
+a compile-time error occurs.
 .P
 When PCRE2 is compiled in EBCDIC mode, \eN{U+hhh..} is not supported. \ea, \ee,
 \ef, \en, \er, and \et generate the appropriate EBCDIC code values. The \ec
@@ -465,8 +486,8 @@ numbers greater than 0777, and it also allows octal numbers and backreferences
 to be unambiguously specified.
 .P
 For greater clarity and unambiguity, it is best to avoid following \e by a
-digit greater than zero. Instead, use \eo{} or \ex{} to specify numerical
-character code points, and \eg{} to specify backreferences. The following
+digit greater than zero. Instead, use \eo{...} or \ex{...} to specify numerical
+character code points, and \eg{...} to specify backreferences. The following
 paragraphs describe the old, ambiguous syntax.
 .P
 The handling of a backslash followed by a digit other than 0 is complicated,
@@ -667,14 +688,27 @@ determine character types, as follows:
 .sp
   \ed  any character that matches \ep{Nd} (decimal digit)
   \es  any character that matches \ep{Z} or \eh or \ev
-  \ew  any character that matches \ep{L} or \ep{N}, plus underscore
+  \ew  any character that matches \ep{L}, \ep{N}, \ep{Mn}, or \ep{Pc}
 .sp
+The addition of \ep{Mn} (non-spacing mark) and the replacement of an explicit
+test for underscore with a test for \ep{Pc} (connector punctuation) happened in
+PCRE2 release 10.43. This brings PCRE2 into line with Perl.
+.P
 The upper case escapes match the inverse sets of characters. Note that \ed
 matches only decimal digits, whereas \ew matches any Unicode digit, as well as
-any Unicode letter, and underscore. Note also that PCRE2_UCP affects \eb, and
+other character categories. Note also that PCRE2_UCP affects \eb, and
 \eB because they are defined in terms of \ew and \eW. Matching these sequences
 is noticeably slower when PCRE2_UCP is set.
 .P
+The effect of PCRE2_UCP on any one of these escape sequences can be negated by
+the options PCRE2_EXTRA_ASCII_BSD, PCRE2_EXTRA_ASCII_BSS, and
+PCRE2_EXTRA_ASCII_BSW, respectively. These options can be set and reset within
+a pattern by means of an internal option setting
+.\" HTML 
+.\" 
+(see below).
+.\"
+.P
 The sequences \eh, \eH, \ev, and \eV, in contrast to the other sequences, which
 match only ASCII characters by default, always match a specific list of code
 points, whether or not PCRE2_UCP is set. The horizontal space characters are:
@@ -993,15 +1027,17 @@ are of five types: L, V, T, LV, and LVT. An L character may be followed by an
 L, V, LV, or LVT character; an LV or V character may be followed by a V or T
 character; an LVT or T character may be followed only by a T character.
 .P
-4. Do not end before extending characters or spacing marks or the "zero-width
-joiner" character. Characters with the "mark" property always have the
+4. Do not end before extending characters or spacing marks or the zero-width
+joiner (ZWJ) character. Characters with the "mark" property always have the
 "extend" grapheme breaking property.
 .P
 5. Do not end after prepend characters.
 .P
-6. Do not break within emoji modifier sequences or emoji zwj sequences. That
-is, do not break between characters with the Extended_Pictographic property.
-Extend and ZWJ characters are allowed between the characters.
+6. Do not end within emoji modifier sequences or emoji ZWJ (zero-width
+joiner) sequences. An emoji ZWJ sequence consists of a character with the
+Extended_Pictographic property, optionally followed by one or more characters
+with the Extend property, followed by the ZWJ character, followed by another
+Extended_Pictographic character.
 .P
 7. Do not break within emoji flag sequences. That is, do not break between
 regional indicator (RI) characters if there are an odd number of RI characters
@@ -1030,7 +1066,8 @@ property. Xps matches the characters tab, linefeed, vertical tab, form feed, or
 carriage return, and any other character that has the Z (separator) property.
 Xsp is the same as Xps; in PCRE1 it used to exclude vertical tab, for Perl
 compatibility, but Perl changed. Xwd matches the same characters as Xan, plus
-underscore.
+those that match Mn (non-spacing mark) or Pc (connector punctuation, which
+includes underscore).
 .P
 There is another non-standard property, Xuc, which matches any character that
 can be represented by a Universal Character Name in C++ and other programming
@@ -1062,11 +1099,11 @@ though it again reports the matched string as "bar". This feature is similar to
 a lookbehind assertion
 .\" HTML 
 .\" 
-(described below).
+(described below),
 .\"
-However, in this case, the part of the subject before the real match does not
-have to be of fixed length, as lookbehind assertions do. The use of \eK does
-not interfere with the setting of
+but the part of the pattern that precedes \eK is not constrained to match a
+limited number of characters, as is required for a lookbehind assertion. The
+use of \eK does not interfere with the setting of
 .\" HTML 
 .\" 
 captured substrings.
@@ -1250,7 +1287,7 @@ above).
 Dot never matches a single line-ending character. When the two-character
 sequence CRLF is the only line ending, dot does not match CR if it is
 immediately followed by LF, but otherwise it matches all characters (including
-isolated CRs and LFs). When ANYCRLF is selected for line endings, no occurences
+isolated CRs and LFs). When ANYCRLF is selected for line endings, no occurrences
 of CR of LF match dot. When all Unicode line endings are being recognized, dot
 does not match CR or LF or any of the other line ending characters.
 .P
@@ -1401,7 +1438,7 @@ or immediately after a range. For example, [b-d-z] matches letters in the range
 b to d, a hyphen character, or z.
 .P
 Perl treats a hyphen as a literal if it appears before or after a POSIX class
-(see below) or before or after a character type escape such as as \ed or \eH.
+(see below) or before or after a character type escape such as \ed or \eH.
 However, unless the hyphen is the last character in the class, Perl outputs a
 warning in its warning mode, as this is most likely a user error. As PCRE2 has
 no facility for warning, an error is given in these cases.
@@ -1482,7 +1519,7 @@ are:
 The default "space" characters are HT (9), LF (10), VT (11), FF (12), CR (13),
 and space (32). If locale-specific matching is taking place, the list of space
 characters may be different; there may be fewer or more of them. "Space" and
-\es match the same set of characters.
+\es match the same set of characters, as do "word" and \ew.
 .P
 The name "word" is a Perl extension, and "blank" is a GNU extension from Perl
 5.8. Another Perl extension is negation, which is indicated by a ^ character
@@ -1496,10 +1533,10 @@ supported, and an error is given if they are encountered.
 .P
 By default, characters with values greater than 127 do not match any of the
 POSIX character classes, although this may be different for characters in the
-range 128-255 when locale-specific matching is happening. However, if the
-PCRE2_UCP option is passed to \fBpcre2_compile()\fP, some of the classes are
-changed so that Unicode character properties are used. This is achieved by
-replacing certain POSIX classes with other sequences, as follows:
+range 128-255 when locale-specific matching is happening. However, in UCP mode,
+unless certain options are set (see below), some of the classes are changed so
+that Unicode character properties are used. This is achieved by replacing
+POSIX classes with other sequences, as follows:
 .sp
   [:alnum:]  becomes  \ep{Xan}
   [:alpha:]  becomes  \ep{L}
@@ -1511,7 +1548,7 @@ replacing certain POSIX classes with other sequences, as follows:
   [:upper:]  becomes  \ep{Lu}
   [:word:]   becomes  \ep{Xwd}
 .sp
-Negated versions, such as [:^alpha:] use \eP instead of \ep. Three other POSIX
+Negated versions, such as [:^alpha:] use \eP instead of \ep. Four other POSIX
 classes are handled specially in UCP mode:
 .TP 10
 [:graph:]
@@ -1532,9 +1569,21 @@ not controls, that is, characters with the Zs property.
 This matches all characters that have the Unicode P (punctuation) property,
 plus those characters with code points less than 256 that have the S (Symbol)
 property.
+.TP 10
+[:xdigit:]
+In addition to the ASCII hexadecimal digits, this also matches the "fullwidth"
+versions of those characters, whose Unicode code points start at U+FF10. This
+is a change that was made in PCRE release 10.43 for Perl compatibility.
+.P
+The other POSIX classes are unchanged by PCRE2_UCP, and match only characters
+with code points less than 256.
 .P
-The other POSIX classes are unchanged, and match only characters with code
-points less than 256.
+There are two options that can be used to restrict the POSIX classes to ASCII
+characters when PCRE2_UCP is set. The option PCRE2_EXTRA_ASCII_DIGIT affects
+just [:digit:] and [:xdigit:]. Within a pattern, this can be set and unset by
+(?aT) and (?-aT). The PCRE2_EXTRA_ASCII_POSIX option disables UCP processing
+for all POSIX classes, including [:digit:] and [:xdigit:]. Within a pattern,
+(?aP) and (?-aP) set and unset both these options for consistency.
 .
 .
 .SH "COMPATIBILITY FEATURE FOR WORD BOUNDARIES"
@@ -1558,7 +1607,9 @@ at the start and the end of a word (see
 .\"
 above), and in a Perl-style pattern the preceding or following character
 normally shows which is wanted, without the need for the assertions that are
-used above in order to give exactly the POSIX behaviour.
+used above in order to give exactly the POSIX behaviour. Note also that the
+PCRE2_UCP option changes the meaning of \ew (and therefore \eb) by default, so
+it also affects these POSIX sequences.
 .
 .
 .SH "VERTICAL BAR"
@@ -1585,10 +1636,9 @@ alternative in the group.
 .SH "INTERNAL OPTION SETTING"
 .rs
 .sp
-The settings of the PCRE2_CASELESS, PCRE2_MULTILINE, PCRE2_DOTALL,
-PCRE2_EXTENDED, PCRE2_EXTENDED_MORE, and PCRE2_NO_AUTO_CAPTURE options can be
-changed from within the pattern by a sequence of letters enclosed between "(?"
-and ")". These options are Perl-compatible, and are described in detail in the
+The settings of several options can be changed within a pattern by a sequence
+of letters enclosed between "(?" and ")". The following are Perl-compatible,
+and are described in detail in the
 .\" HREF
 \fBpcre2api\fP
 .\"
@@ -1603,8 +1653,8 @@ documentation. The option letters are:
 .sp
 For example, (?im) sets caseless, multiline matching. It is also possible to
 unset these options by preceding the relevant letters with a hyphen, for
-example (?-im). The two "extended" options are not independent; unsetting either
-one cancels the effects of both of them.
+example (?-im). The two "extended" options are not independent; unsetting
+either one cancels the effects of both of them.
 .P
 A combined setting and unsetting such as (?im-sx), which sets PCRE2_CASELESS
 and PCRE2_MULTILINE while unsetting PCRE2_DOTALL and PCRE2_EXTENDED, is also
@@ -1613,25 +1663,41 @@ appears both before and after the hyphen, the option is unset. An empty options
 setting "(?)" is allowed. Needless to say, it has no effect.
 .P
 If the first character following (? is a circumflex, it causes all of the above
-options to be unset. Thus, (?^) is equivalent to (?-imnsx). Letters may follow
-the circumflex to cause some options to be re-instated, but a hyphen may not
-appear.
-.P
-The PCRE2-specific options PCRE2_DUPNAMES and PCRE2_UNGREEDY can be changed in
-the same way as the Perl-compatible options by using the characters J and U
-respectively. However, these are not unset by (?^).
-.P
-When one of these option changes occurs at top level (that is, not inside
-group parentheses), the change applies to the remainder of the pattern
-that follows. An option change within a group (see below for a description
-of groups) affects only that part of the group that follows it, so
+options to be unset. Letters may follow the circumflex to cause some options to
+be re-instated, but a hyphen may not appear.
+.P
+Some PCRE2-specific options can be changed by the same mechanism using these
+pairs or individual letters:
+.sp
+  aD for PCRE2_EXTRA_ASCII_BSD
+  aS for PCRE2_EXTRA_ASCII_BSS
+  aW for PCRE2_EXTRA_ASCII_BSW
+  aP for PCRE2_EXTRA_ASCII_POSIX and PCRE2_EXTRA_ASCII_DIGIT
+  aT for PCRE2_EXTRA_ASCII_DIGIT
+  r  for PCRE2_EXTRA_CASELESS_RESTRICT
+  J  for PCRE2_DUPNAMES
+  U  for PCRE2_UNGREEDY
+.sp
+However, except for 'r', these are not unset by (?^), which is equivalent to
+(?-imnrsx). If 'a' is not followed by any of the upper case letters shown
+above, it sets (or unsets) all the ASCII options.
+.P
+PCRE2_EXTRA_ASCII_DIGIT has no additional effect when PCRE2_EXTRA_ASCII_POSIX
+is set, but including it in (?aP) means that (?-aP) suppresses all ASCII
+restrictions for POSIX classes.
+.P
+When one of these option changes occurs at top level (that is, not inside group
+parentheses), the change applies until a subsequent change, or the end of the
+pattern. An option change within a group (see below for a description of
+groups) affects only that part of the group that follows it. At the end of the
+group these options are reset to the state they were before the group. For
+example,
 .sp
   (a(?i)b)c
 .sp
-matches abc and aBc and no other strings (assuming PCRE2_CASELESS is not used).
-By this means, options can be made to have different settings in different
-parts of the pattern. Any changes made in one alternative do carry on
-into subsequent branches within the same group. For example,
+matches abc and aBc and no other strings (assuming PCRE2_CASELESS is not set
+externally). Any changes made in one alternative do carry on into subsequent
+branches within the same group. For example,
 .sp
   (a(?i)b|c)
 .sp
@@ -1661,7 +1727,7 @@ Details are given in the section entitled
 above. There are also the (*UTF) and (*UCP) leading sequences that can be used
 to set UTF and Unicode property modes; they are equivalent to setting the
 PCRE2_UTF and PCRE2_UCP options, respectively. However, the application can set
-the PCRE2_NEVER_UTF and PCRE2_NEVER_UCP options, which lock out the use of the
+the PCRE2_NEVER_UTF or PCRE2_NEVER_UCP options, which lock out the use of the
 (*UTF) and (*UCP) sequences.
 .
 .
@@ -1780,7 +1846,7 @@ the naming of capture groups. This feature was not added to Perl until release
 using the Python syntax. PCRE2 supports both the Perl and the Python syntax.
 .P
 In PCRE2, a capture group can be named in one of three ways: (?...) or
-(?'name'...) as in Perl, or (?P...) as in Python. Names may be up to 32
+(?'name'...) as in Perl, or (?P...) as in Python. Names may be up to 128
 code units long. When PCRE2_UTF is not set, they may contain only ASCII
 alphanumeric characters and underscores, but must start with a non-digit. When
 PCRE2_UTF is set, the syntax of group names is extended to allow any Unicode
@@ -1902,7 +1968,7 @@ documentation.
 .SH REPETITION
 .rs
 .sp
-Repetition is specified by quantifiers, which can follow any of the following
+Repetition is specified by quantifiers, which may follow any one of these
 items:
 .sp
   a literal data character
@@ -1910,16 +1976,17 @@ items:
   the \eC escape sequence
   the \eR escape sequence
   the \eX escape sequence
-  an escape such as \ed or \epL that matches a single character
+  any escape sequence that matches a single character
   a character class
   a backreference
   a parenthesized group (including lookaround assertions)
   a subroutine call (recursive or otherwise)
 .sp
-The general repetition quantifier specifies a minimum and maximum number of
-permitted matches, by giving the two numbers in curly brackets (braces),
-separated by a comma. The numbers must be less than 65536, and the first must
-be less than or equal to the second. For example,
+If a quantifier does not follow a repeatable item, an error occurs. The
+general repetition quantifier specifies a minimum and maximum number of
+permitted matches by giving two numbers in curly brackets (braces), separated
+by a comma. The numbers must be less than 65536, and the first must be less
+than or equal to the second. For example,
 .sp
   z{2,4}
 .sp
@@ -1934,10 +2001,21 @@ matches at least 3 successive vowels, but may match many more, whereas
 .sp
   \ed{8}
 .sp
-matches exactly 8 digits. An opening curly bracket that appears in a position
-where a quantifier is not allowed, or one that does not match the syntax of a
-quantifier, is taken as a literal character. For example, {,6} is not a
-quantifier, but a literal string of four characters.
+matches exactly 8 digits. If the first number is omitted, the lower limit is
+taken as zero; in this case the upper limit must be present.
+.sp
+  X{,4} is interpreted as X{0,4}
+.sp
+This is a change in behaviour that happened in Perl 5.34.0 and PCRE2 10.43. In
+earlier versions such a sequence was not interpreted as a quantifier. Other
+regular expression engines may behave either way.
+.P
+If the characters that follow an opening brace do not match the syntax of a
+quantifier, the brace is taken as a literal character. In particular, this
+means that {,} is a literal string of three characters.
+.P
+Note that not every opening brace is potentially the start of a quantifier
+because braces are used in other items such as \eN{U+345} or \ek{name}.
 .P
 In UTF modes, quantifiers apply to characters rather than to individual code
 units. Thus, for example, \ex{100}{2} matches two characters, each of
@@ -1980,11 +2058,11 @@ repeatedly matching an empty string. This does not prevent backtracking into
 any of the iterations if a subsequent item fails to match.
 .P
 By default, quantifiers are "greedy", that is, they match as much as possible
-(up to the maximum number of permitted times), without causing the rest of the
-pattern to fail. The classic example of where this gives problems is in trying
-to match comments in C programs. These appear between /* and */ and within the
-comment, individual * and / characters may appear. An attempt to match C
-comments by applying the pattern
+(up to the maximum number of permitted repetitions), without causing the rest
+of the pattern to fail. The classic example of where this gives problems is in
+trying to match comments in C programs. These appear between /* and */ and
+within the comment, individual * and / characters may appear. An attempt to
+match C comments by applying the pattern
 .sp
   /\e*.*\e*/
 .sp
@@ -1999,10 +2077,10 @@ pattern
 .sp
   /\e*.*?\e*/
 .sp
-does the right thing with the C comments. The meaning of the various
-quantifiers is not otherwise changed, just the preferred number of matches.
-Do not confuse this use of question mark with its use as a quantifier in its
-own right. Because it has two uses, it can sometimes appear doubled, as in
+does the right thing with C comments. The meaning of the various quantifiers is
+not otherwise changed, just the preferred number of matches. Do not confuse
+this use of question mark with its use as a quantifier in its own right.
+Because it has two uses, it can sometimes appear doubled, as in
 .sp
   \ed??\ed
 .sp
@@ -2211,15 +2289,23 @@ the reference. A signed number is a relative reference. Consider this example:
 .sp
   (abc(def)ghi)\eg{-1}
 .sp
-The sequence \eg{-1} is a reference to the most recently started capture group
-before \eg, that is, is it equivalent to \e2 in this example. Similarly,
-\eg{-2} would be equivalent to \e1. The use of relative references can be
-helpful in long patterns, and also in patterns that are created by joining
-together fragments that contain references within themselves.
+The sequence \eg{-1} is a reference to the capture group whose number is one
+less than the number of the next group to be started, so in this example (where
+the next group would be numbered 3) is it equivalent to \e2, and \eg{-2} would
+be equivalent to \e1. Note that if this construct is inside a capture group,
+that group is included in the count, so in this example \eg{-2} also refers to
+group 1:
+.sp
+  (A)(\eg{-2}B)
+.sp
+The use of relative references can be helpful in long patterns, and also in
+patterns that are created by joining together fragments that contain references
+within themselves.
 .P
-The sequence \eg{+1} is a reference to the next capture group. This kind of
-forward reference can be useful in patterns that repeat. Perl does not support
-the use of + in this way.
+The sequence \eg{+1} is a reference to the next capture group that is started
+after this item, and \eg{+2} refers to the one after that, and so on. This kind
+of forward reference can be useful in patterns that repeat. Perl does not
+support the use of + in this way.
 .P
 A backreference matches whatever actually most recently matched the capture
 group in the current subject string, rather than anything at all that matches
@@ -2242,11 +2328,11 @@ matches "rah rah" and "RAH RAH", but not "RAH rah", even though the original
 capture group is matched caselessly.
 .P
 There are several different ways of writing backreferences to named capture
-groups. The .NET syntax \ek{name} and the Perl syntax \ek or \ek'name'
-are supported, as is the Python syntax (?P=name). Perl 5.10's unified
-backreference syntax, in which \eg can be used for both numeric and named
-references, is also supported. We could rewrite the above example in any of the
-following ways:
+groups. The .NET syntax is \ek{name}, the Python syntax is (?=name), and the
+original Perl syntax is \ek or \ek'name'. All of these are now supported
+by both Perl and PCRE2. Perl 5.10's unified backreference syntax, in which \eg
+can be used for both numeric and named references, is also supported by PCRE2.
+We could rewrite the above example in any of the following ways:
 .sp
   (?(?i)rah)\es+\ek
   (?'p1'(?i)rah)\es+\ek{p1}
@@ -2436,41 +2522,33 @@ negative assertions. For example,
   (?
 .\" 
 (see above)
 .\"
-can be used instead of a lookbehind assertion to get round the fixed-length
-restriction.
-.P
-The implementation of lookbehind assertions is, for each alternative, to
-temporarily move the current position back by the fixed length and then try to
-match. If there are insufficient characters before the current position, the
-assertion fails.
+can be used instead of a lookbehind assertion at the start of a pattern to get
+round the length limit restriction.
 .P
 In UTF-8 and UTF-16 modes, PCRE2 does not allow the \eC escape (which matches a
 single code unit even in a UTF mode) to appear in lookbehind assertions,
@@ -2483,7 +2561,7 @@ permitted in lookbehinds.
 "Subroutine"
 .\"
 calls (see below) such as (?2) or (?&X) are permitted in lookbehinds, as long
-as the called capture group matches a fixed-length string. However,
+as the called capture group matches a limited-length string. However,
 .\" HTML 
 .\" 
 recursion,
@@ -2491,19 +2569,19 @@ recursion,
 that is, a "subroutine" call into a group that is already active,
 is not supported.
 .P
-Perl does not support backreferences in lookbehinds. PCRE2 does support them,
-but only if certain conditions are met. The PCRE2_MATCH_UNSET_BACKREF option
-must not be set, there must be no use of (?| in the pattern (it creates
-duplicate group numbers), and if the backreference is by name, the name
-must be unique. Of course, the referenced group must itself match a fixed
-length substring. The following pattern matches words containing at least two
-characters that begin and end with the same character:
+PCRE2 supports backreferences in lookbehinds, but only if certain conditions
+are met. The PCRE2_MATCH_UNSET_BACKREF option must not be set, there must be no
+use of (?| in the pattern (it creates duplicate group numbers), and if the
+backreference is by name, the name must be unique. Of course, the referenced
+group must itself match a limited length substring. The following pattern
+matches words containing at least two characters that begin and end with the
+same character:
 .sp
    \eb(\ew)\ew++(?<=\e1)
 .P
 Possessive quantifiers can be used in conjunction with lookbehind assertions to
-specify efficient matching of fixed-length strings at the end of subject
-strings. Consider a simple pattern such as
+specify efficient matching at the end of subject strings. Consider a simple
+pattern such as
 .sp
   abcd$
 .sp
@@ -2566,11 +2644,10 @@ characters that are not "999".
 .SH "NON-ATOMIC ASSERTIONS"
 .rs
 .sp
-The traditional Perl-compatible lookaround assertions are atomic. That is, if
-an assertion is true, but there is a subsequent matching failure, there is no
-backtracking into the assertion. However, there are some cases where non-atomic
-positive assertions can be useful. PCRE2 provides these using the following
-syntax:
+Traditional lookaround assertions are atomic. That is, if an assertion is true,
+but there is a subsequent matching failure, there is no backtracking into the
+assertion. However, there are some cases where non-atomic positive assertions
+can be useful. PCRE2 provides these using the following syntax:
 .sp
   (*non_atomic_positive_lookahead:  or (*napla: or (?*
   (*non_atomic_positive_lookbehind: or (*naplb: or (?<*
@@ -2593,7 +2670,7 @@ The current matching point is then reset to the start of the subject, and the
 rest of the pattern match checks for two occurrences of the captured word,
 using an ungreedy .*? to scan from the left. If this succeeds, we are done, but
 if the last word in the string does not occur twice, this part of the pattern
-fails. If a traditional atomic lookhead (?= or (*pla: had been used, the
+fails. If a traditional atomic lookahead (?= or (*pla: had been used, the
 assertion could not be re-entered, and the whole match would fail. The pattern
 would succeed only if the very last word in the subject was found twice.
 .P
@@ -2729,13 +2806,14 @@ there is more than one capture group with the same number (see the earlier
 .\" 
 section about duplicate group numbers),
 .\"
-the condition is true if any of them have matched. An alternative notation is
-to precede the digits with a plus or minus sign. In this case, the group number
-is relative rather than absolute. The most recently opened capture group can be
-referenced by (?(-1), the next most recent by (?(-2), and so on. Inside loops
-it can also make sense to refer to subsequent groups. The next capture group
-can be referenced as (?(+1), and so on. (The value zero in any of these forms
-is not used; it provokes a compile-time error.)
+the condition is true if any of them have matched. An alternative notation,
+which is a PCRE2 extension, not supported by Perl, is to precede the digits
+with a plus or minus sign. In this case, the group number is relative rather
+than absolute. The most recently opened capture group (which could be enclosing
+this condition) can be referenced by (?(-1), the next most recent by (?(-2),
+and so on. Inside loops it can also make sense to refer to subsequent groups.
+The next capture group to be opened can be referenced as (?(+1), and so on. The
+value zero in any of these forms is not used; it provokes a compile-time error.
 .P
 Consider the following pattern, which contains non-significant white space to
 make it more readable (assume the PCRE2_EXTENDED option) and to divide it into
@@ -2876,7 +2954,6 @@ than two digits.
 If the condition is not in any of the above formats, it must be a parenthesized
 assertion. This may be a positive or negative lookahead or lookbehind
 assertion. However, it must be a traditional atomic assertion, not one of the
-PCRE2-specific
 .\" HTML 
 .\" 
 non-atomic assertions.
@@ -3696,7 +3773,7 @@ If A matches but B fails, the backtrack to (*COMMIT) causes the entire match to
 fail. However, if A and B match, but C fails, the backtrack to (*THEN) causes
 the next alternative (ABD) to be tried. This behaviour is consistent, but is
 not always the same as Perl's. It means that if two or more backtracking verbs
-appear in succession, all the the last of them has no effect. Consider this
+appear in succession, all but the last of them has no effect. Consider this
 example:
 .sp
   ...(*COMMIT)(*PRUNE)...
@@ -3814,6 +3891,6 @@ Cambridge, England.
 .rs
 .sp
 .nf
-Last updated: 12 January 2022
-Copyright (c) 1997-2022 University of Cambridge.
+Last updated: 04 June 2024
+Copyright (c) 1997-2024 University of Cambridge.
 .fi
diff --git a/pcre2/doc/pcre2posix.3 b/pcre2/doc/pcre2posix.3
index 6cfede7..3709299 100644
--- a/pcre2/doc/pcre2posix.3
+++ b/pcre2/doc/pcre2posix.3
@@ -1,4 +1,4 @@
-.TH PCRE2POSIX 3 "26 April 2021" "PCRE2 10.37"
+.TH PCRE2POSIX 3 "19 January 2024" "PCRE2 10.43"
 .SH NAME
 PCRE2 - Perl-compatible regular expressions (revised API)
 .SH "SYNOPSIS"
@@ -31,9 +31,13 @@ and 32-bit libraries. See the
 documentation for a description of PCRE2's native API, which contains much
 additional functionality.
 .P
-The functions described here are wrapper functions that ultimately call the
-PCRE2 native API. Their prototypes are defined in the \fBpcre2posix.h\fP header
-file, and they all have unique names starting with \fBpcre2_\fP. However, the
+\fBIMPORTANT NOTE\fP: The functions described here are NOT thread-safe, and
+should not be used in multi-threaded applications. They are also limited to
+processing subjects that are not bigger than 2GB. Use the native API instead.
+.P
+These functions are wrapper functions that ultimately call the PCRE2 native
+API. Their prototypes are defined in the \fBpcre2posix.h\fP header file, and
+they all have unique names starting with \fBpcre2_\fP. However, the
 \fBpcre2posix.h\fP header also contains macro definitions that convert the
 standard POSIX names such \fBregcomp()\fP into \fBpcre2_regcomp()\fP etc. This
 means that a program can use the usual POSIX names without running the risk of
@@ -44,7 +48,12 @@ can be accessed by adding \fB-lpcre2-posix\fP to the command for linking an
 application. Because the POSIX functions call the native ones, it is also
 necessary to add \fB-lpcre2-8\fP.
 .P
-Although they were not defined as protypes in \fBpcre2posix.h\fP, releases
+On Windows systems, if you are linking to a DLL version of the library, it is
+recommended that \fBPCRE2POSIX_SHARED\fP is defined before including the
+\fBpcre2posix.h\fP header, as it will allow for a more efficient way to
+invoke the functions by adding the \fB__declspec(dllimport)\fP decorator.
+.P
+Although they were not defined as prototypes in \fBpcre2posix.h\fP, releases
 10.33 to 10.36 of the library contained functions with the POSIX names
 \fBregcomp()\fP etc. These simply passed their arguments to the PCRE2
 functions. These functions were provided for backwards compatibility with
@@ -64,6 +73,10 @@ captured substrings. It also defines some constants whose names start with
 .SH "USING THE POSIX FUNCTIONS"
 .rs
 .sp
+Note that these functions are just POSIX-style wrappers for PCRE2's native API.
+They do not give POSIX regular expression behaviour, and they are not
+thread-safe or even POSIX compatible.
+.P
 Those POSIX option bits that can reasonably be mapped to PCRE2 native options
 have been implemented. In addition, the option REG_EXTENDED is defined with the
 value zero. This has no effect, but since programs that are written to the
@@ -93,8 +106,10 @@ The function \fBpcre2_regcomp()\fP is called to compile a pattern into an
 internal form. By default, the pattern is a C string terminated by a binary
 zero (but see REG_PEND below). The \fIpreg\fP argument is a pointer to a
 \fBregex_t\fP structure that is used as a base for storing information about
-the compiled regular expression. (It is also used for input when REG_PEND is
-set.)
+the compiled regular expression. It is also used for input when REG_PEND is
+set. The \fBregex_t\fP structure used by \fBpcre2_regcomp()\fP is defined in
+\fBpcre2posix.h\fP and is not the same as the structure used by other libraries
+that provide POSIX-style matching.
 .P
 The argument \fIcflags\fP is either zero, or contains one or more of the bits
 defined by the following macros:
@@ -146,7 +161,7 @@ caution in software intended to be portable to other systems.
 .sp
 The PCRE2_UCP option is set when the regular expression is passed for
 compilation to the native function. This causes PCRE2 to use Unicode properties
-when matchine \ed, \ew, etc., instead of just recognizing ASCII values. Note
+when matching \ed, \ew, etc., instead of just recognizing ASCII values. Note
 that REG_UCP is not part of the POSIX standard.
 .sp
   REG_UNGREEDY
@@ -163,7 +178,7 @@ strings used for matching it to be treated as UTF-8 strings. Note that REG_UTF
 is not part of the POSIX standard.
 .P
 In the absence of these flags, no options are passed to the native function.
-This means the the regex is compiled with PCRE2 default semantics. In
+This means that the regex is compiled with PCRE2 default semantics. In
 particular, the way it handles newline characters in the subject string is the
 Perl way, not the POSIX way. Note that setting PCRE2_MULTILINE has only
 \fIsome\fP of the effects specified for REG_NEWLINE. It does not affect the way
@@ -284,6 +299,10 @@ entire portion of \fIstring\fP that was matched; subsequent elements relate to
 the capturing subpatterns of the regular expression. Unused entries in the
 array have both structure members set to -1.
 .P
+\fIregmatch_t\fP as well as the \fIregoff_t\fP typedef it uses are defined in
+\fBpcre2posix.h\fP and are not warranted to have the same size or layout as other
+similarly named types from other libraries that provide POSIX-style matching.
+.P
 A successful match yields a zero return; various error codes are defined in the
 header file, of which REG_NOMATCH is the "expected" failure code.
 .
@@ -315,7 +334,7 @@ expression.
 .sp
 .nf
 Philip Hazel
-University Computing Service
+Retired from University Computing Service
 Cambridge, England.
 .fi
 .
@@ -324,6 +343,6 @@ Cambridge, England.
 .rs
 .sp
 .nf
-Last updated: 26 April 2021
-Copyright (c) 1997-2021 University of Cambridge.
+Last updated: 19 January 2024
+Copyright (c) 1997-2024 University of Cambridge.
 .fi
diff --git a/pcre2/doc/pcre2sample.3 b/pcre2/doc/pcre2sample.3
index 661e392..1e93ba4 100644
--- a/pcre2/doc/pcre2sample.3
+++ b/pcre2/doc/pcre2sample.3
@@ -85,7 +85,7 @@ need to add
 .sp
 .nf
 Philip Hazel
-University Computing Service
+Retired from University Computing Service
 Cambridge, England.
 .fi
 .
diff --git a/pcre2/doc/pcre2serialize.3 b/pcre2/doc/pcre2serialize.3
index a94f13b..6fe2c64 100644
--- a/pcre2/doc/pcre2serialize.3
+++ b/pcre2/doc/pcre2serialize.3
@@ -75,7 +75,7 @@ being a pointer to a vector of pointers to compiled patterns, and the length of
 the vector. The third and fourth arguments point to variables which are set to
 point to the created byte stream and its length, respectively. The final
 argument is a pointer to a general context, which can be used to specify custom
-memory mangagement functions. If this argument is NULL, \fBmalloc()\fP is used
+memory management functions. If this argument is NULL, \fBmalloc()\fP is used
 to obtain memory for the byte stream. The yield of the function is the number
 of serialized patterns, or one of the following negative error codes:
 .sp
@@ -137,7 +137,7 @@ the compiled patterns in new memory blocks, setting pointers to them in a
 vector. The first two arguments are a pointer to a suitable vector and its
 length, and the third argument points to a byte stream. The final argument is a
 pointer to a general context, which can be used to specify custom memory
-mangagement functions for the decoded patterns. If this argument is NULL,
+management functions for the decoded patterns. If this argument is NULL,
 \fBmalloc()\fP and \fBfree()\fP are used. After deserialization, the byte
 stream is no longer needed and can be discarded.
 .sp
@@ -184,7 +184,7 @@ save/restore cycle. You can, however, process a restored pattern with
 .sp
 .nf
 Philip Hazel
-University Computing Service
+Retired from University Computing Service
 Cambridge, England.
 .fi
 .
diff --git a/pcre2/doc/pcre2syntax.3 b/pcre2/doc/pcre2syntax.3
index c0a496f..6f4f7aa 100644
--- a/pcre2/doc/pcre2syntax.3
+++ b/pcre2/doc/pcre2syntax.3
@@ -1,4 +1,4 @@
-.TH PCRE2SYNTAX 3 "12 January 2022" "PCRE2 10.40"
+.TH PCRE2SYNTAX 3 "12 October 2023" "PCRE2 10.43"
 .SH NAME
 PCRE2 - Perl-compatible regular expressions (revised API)
 .SH "PCRE2 REGULAR EXPRESSION SYNTAX SUMMARY"
@@ -17,6 +17,21 @@ documentation. This document contains a quick-reference summary of the syntax.
 .sp
   \ex         where x is non-alphanumeric is a literal x
   \eQ...\eE    treat enclosed characters as literal
+.sp
+Note that white space inside \eQ...\eE is always treated as literal, even if
+PCRE2_EXTENDED is set, causing most other white space to be ignored.
+.
+.
+.SH "BRACED ITEMS"
+.rs
+.sp
+With one exception, wherever brace characters { and } are required to enclose
+data for constructions such as \eg{2} or \ek{name}, space and/or horizontal tab
+characters that follow { or precede } are allowed and are ignored. In the case
+of quantifiers, they may also appear before or after the comma. The exception
+is \eu{...} which is not Perl-compatible and is recognized only when
+PCRE2_EXTRA_ALT_BSUX is set. This is an ECMAScript compatibility feature, and
+follows ECMAScript's behaviour.
 .
 .
 .SH "ESCAPED CHARACTERS"
@@ -26,7 +41,7 @@ This table applies to ASCII and Unicode environments. An unrecognized escape
 sequence causes an error.
 .sp
   \ea         alarm, that is, the BEL character (hex 07)
-  \ecx        "control-x", where x is any ASCII printing character
+  \ecx        "control-x", where x is a non-control ASCII character
   \ee         escape (hex 1B)
   \ef         form feed (hex 0C)
   \en         newline (hex 0A)
@@ -101,7 +116,8 @@ or in the 16-bit and 32-bit libraries. However, if locale-specific matching is
 happening, \es and \ew may also match characters with code points in the range
 128-255. If the PCRE2_UCP option is set, the behaviour of these escape
 sequences is changed to use Unicode properties and they match many more
-characters.
+characters, but there are some option settings that can restrict individual
+sequences to matching only ASCII characters.
 .P
 Property descriptions in \ep and \eP are matched caselessly; hyphens,
 underscores, and white space are ignored, in accordance with Unicode's "loose
@@ -164,7 +180,7 @@ matching" rules.
   Xan        Alphanumeric: union of properties L and N
   Xps        POSIX space: property Z or tab, NL, VT, FF, CR
   Xsp        Perl space: property Z or tab, NL, VT, FF, CR
-  Xuc        Univerally-named character: one that can be
+  Xuc        Universally-named character: one that can be
                represented by a Universal Character Name
   Xwd        Perl word: property Xan or underscore
 .sp
@@ -275,6 +291,9 @@ but some of them use Unicode properties if PCRE2_UCP is set. You can use
   {n,}        n or more, greedy
   {n,}+       n or more, possessive
   {n,}?       n or more, lazy
+  {,m}        zero up to m, greedy
+  {,m}+       zero up to m, possessive
+  {,m}?       zero up to m, lazy
 .
 .
 .SH "ANCHORS AND SIMPLE ASSERTIONS"
@@ -346,17 +365,28 @@ both cases, a name must not start with a digit.
 Changes of these options within a group are automatically cancelled at the end
 of the group.
 .sp
+  (?a)            all ASCII options
+  (?aD)           restrict \ed to ASCII in UCP mode
+  (?aS)           restrict \es to ASCII in UCP mode
+  (?aW)           restrict \ew to ASCII in UCP mode
+  (?aP)           restrict all POSIX classes to ASCII in UCP mode
+  (?aT)           restrict POSIX digit classes to ASCII in UCP mode
   (?i)            caseless
   (?J)            allow duplicate named groups
   (?m)            multiline
   (?n)            no auto capture
+  (?r)            restrict caseless to either ASCII or non-ASCII
   (?s)            single line (dotall)
   (?U)            default ungreedy (lazy)
-  (?x)            extended: ignore white space except in classes
+  (?x)            ignore white space except in classes or \eQ...\eE
   (?xx)           as (?x) but also ignore space and tab in classes
-  (?-...)         unset option(s)
-  (?^)            unset imnsx options
+  (?-...)         unset the given option(s)
+  (?^)            unset imnrsx options
 .sp
+(?aP) implies (?aT) as well, though this has no additional effect. However, it
+means that (?-aP) is really (?-PT) which disables all ASCII restrictions for
+POSIX classes.
+.P
 Unsetting x or xx unsets both. Several options may be set at once, and a
 mixture of setting and unsetting such as (?i-x) is allowed, but there may be
 only one hyphen. Setting (but no unsetting) is allowed after (?^ for example
@@ -429,7 +459,12 @@ setting with a similar syntax.
   (*nlb:...)                  ) negative lookbehind
   (*negative_lookbehind:...)  )
 .sp
-Each top-level branch of a lookbehind must be of a fixed length.
+Each top-level branch of a lookbehind must have a limit for the number of
+characters it matches. If any branch can match a variable number of characters,
+the maximum for each branch is limited to a value set by the caller of
+\fBpcre2_compile()\fP or defaulted. The default is set when PCRE2 is built
+(ultimate default 255). If every branch matches a fixed number of characters,
+the limit for each branch is 65535 characters.
 .
 .
 .SH "NON-ATOMIC LOOKAROUND ASSERTIONS"
@@ -499,8 +534,8 @@ These assertions are specific to PCRE2 and are not Perl-compatible.
   (?(condition)yes-pattern|no-pattern)
 .sp
   (?(n)               absolute reference condition
-  (?(+n)              relative reference condition
-  (?(-n)              relative reference condition
+  (?(+n)              relative reference condition (PCRE2 extension)
+  (?(-n)              relative reference condition (PCRE2 extension)
   (?()          named reference condition (Perl)
   (?('name')          named reference condition (Perl)
   (?(name)            named reference condition (PCRE2, deprecated)
@@ -578,6 +613,6 @@ Cambridge, England.
 .rs
 .sp
 .nf
-Last updated: 12 January 2022
-Copyright (c) 1997-2022 University of Cambridge.
+Last updated: 12 October 2023
+Copyright (c) 1997-2023 University of Cambridge.
 .fi
diff --git a/pcre2/doc/pcre2test.1 b/pcre2/doc/pcre2test.1
index 3ac42e0..c7df418 100644
--- a/pcre2/doc/pcre2test.1
+++ b/pcre2/doc/pcre2test.1
@@ -1,4 +1,4 @@
-.TH PCRE2TEST 1 "27 July 2022" "PCRE 10.41"
+.TH PCRE2TEST 1 "24 April 2024" "PCRE 10.44"
 .SH NAME
 pcre2test - a program for testing Perl-compatible regular expressions.
 .SH SYNOPSIS
@@ -61,14 +61,14 @@ library. In some Windows environments character 26 (hex 1A) causes an immediate
 end of file, and no further data is read, so this character should be avoided
 unless you really want that action.
 .P
-The input is processed using using C's string functions, so must not
-contain binary zeros, even though in Unix-like environments, \fBfgets()\fP
-treats any bytes other than newline as data characters. An error is generated
-if a binary zero is encountered. By default subject lines are processed for
-backslash escapes, which makes it possible to include any data value in strings
-that are passed to the library for matching. For patterns, there is a facility
-for specifying some or all of the 8-bit input characters as hexadecimal pairs,
-which makes it possible to include binary zeros.
+The input is processed using C's string functions, so must not contain binary
+zeros, even though in Unix-like environments, \fBfgets()\fP treats any bytes
+other than newline as data characters. An error is generated if a binary zero
+is encountered. By default subject lines are processed for backslash escapes,
+which makes it possible to include any data value in strings that are passed to
+the library for matching. For patterns, there is a facility for specifying some
+or all of the 8-bit input characters as hexadecimal pairs, which makes it
+possible to include binary zeros.
 .
 .
 .SS "Input for the 16-bit and 32-bit libraries"
@@ -111,14 +111,14 @@ the default). If the 8-bit library has not been built, this option causes an
 error.
 .TP 10
 \fB-16\fP
-If the 16-bit library has been built, this option causes it to be used. If only
-the 16-bit library has been built, this is the default. If the 16-bit library
+If the 16-bit library has been built, this option causes it to be used. If the
+8-bit library has not been built, this is the default. If the 16-bit library
 has not been built, this option causes an error.
 .TP 10
 \fB-32\fP
-If the 32-bit library has been built, this option causes it to be used. If only
-the 32-bit library has been built, this is the default. If the 32-bit library
-has not been built, this option causes an error.
+If the 32-bit library has been built, this option causes it to be used. If no
+other library has been built, this is the default. If the 32-bit library has
+not been built, this option causes an error.
 .TP 10
 \fB-ac\fP
 Behave as if each pattern has the \fBauto_callout\fP modifier, that is, insert
@@ -462,8 +462,8 @@ followed by a backslash, for example,
 .sp
   /abc/\e
 .sp
-then a backslash is added to the end of the pattern. This is done to provide a
-way of testing the error condition that arises if a pattern finishes with a
+a backslash is added to the end of the pattern. This is done to provide a way
+of testing the error condition that arises if a pattern finishes with a
 backslash, because
 .sp
   /abc\e/
@@ -565,12 +565,11 @@ by a previous \fB#pattern\fP command.
 .sp
 The following modifiers set options for \fBpcre2_compile()\fP. Most of them set
 bits in the options argument of that function, but those whose names start with
-PCRE2_EXTRA are additional options that are set in the compile context. For the
-main options, there are some single-letter abbreviations that are the same as
-Perl options. There is special handling for /x: if a second x is present,
-PCRE2_EXTENDED is converted into PCRE2_EXTENDED_MORE as in Perl. A third
-appearance adds PCRE2_EXTENDED as well, though this makes no difference to the
-way \fBpcre2_compile()\fP behaves. See
+PCRE2_EXTRA are additional options that are set in the compile context.
+Some of these options have single-letter abbreviations. There is special
+handling for /x: if a second x is present, PCRE2_EXTENDED is converted into
+PCRE2_EXTENDED_MORE as in Perl. A third appearance adds PCRE2_EXTENDED as well,
+though this makes no difference to the way \fBpcre2_compile()\fP behaves. See
 .\" HREF
 \fBpcre2api\fP
 .\"
@@ -583,9 +582,16 @@ for a description of the effects of these options.
       alt_circumflex            set PCRE2_ALT_CIRCUMFLEX
       alt_verbnames             set PCRE2_ALT_VERBNAMES
       anchored                  set PCRE2_ANCHORED
+  /a  ascii_all                 set all ASCII options
+      ascii_bsd                 set PCRE2_EXTRA_ASCII_BSD
+      ascii_bss                 set PCRE2_EXTRA_ASCII_BSS
+      ascii_bsw                 set PCRE2_EXTRA_ASCII_BSW
+      ascii_digit               set PCRE2_EXTRA_ASCII_DIGIT
+      ascii_posix               set PCRE2_EXTRA_ASCII_POSIX
       auto_callout              set PCRE2_AUTO_CALLOUT
       bad_escape_is_literal     set PCRE2_EXTRA_BAD_ESCAPE_IS_LITERAL
   /i  caseless                  set PCRE2_CASELESS
+  /r  caseless_restrict         set PCRE2_EXTRA_CASELESS_RESTRICT
       dollar_endonly            set PCRE2_DOLLAR_ENDONLY
   /s  dotall                    set PCRE2_DOTALL
       dupnames                  set PCRE2_DUPNAMES
@@ -646,10 +652,14 @@ heavily used in the test files.
       jitfast                   use JIT fast path
       jitverify                 verify JIT use
       locale=             use this locale
-      max_pattern_length=    set the maximum pattern length
+      max_pattern_compiled      ) set maximum compiled pattern
+                 _length=    )   length (bytes)
+      max_pattern_length=    set maximum pattern length (code units)
+      max_varlookbehind=     set maximum variable lookbehind length
       memory                    show memory used
       newline=            set newline type
       null_context              compile with a NULL context
+      null_pattern              pass pattern as NULL
       parens_nest_limit=     set maximum parentheses depth
       posix                     use the POSIX API
       posix_nosub               use the POSIX API with REG_NOSUB
@@ -724,9 +734,11 @@ ending code units are recorded. The subject length line is omitted when
 \fBno_start_optimize\fP is set because the minimum length is not calculated
 when it can never be used.
 .P
-The \fBframesize\fP modifier shows the size, in bytes, of the storage frames
+The \fBframesize\fP modifier shows the size, in bytes, of each storage frame
 used by \fBpcre2_match()\fP for handling backtracking. The size depends on the
-number of capturing parentheses in the pattern.
+number of capturing parentheses in the pattern. A vector of these frames is
+used at matching time; its overall size is shown when the \fBheaframes_size\fP
+subject modifier is set.
 .P
 The \fBcallout_info\fP modifier requests information about all the callouts in
 the pattern. A list of them is output at the end of any other information that
@@ -743,6 +755,15 @@ testing that \fBpcre2_compile()\fP behaves correctly in this case (it uses
 default values).
 .
 .
+.SS "Passing a NULL pattern"
+.rs
+.sp
+The \fBnull_pattern\fP modifier is for testing the behaviour of
+\fBpcre2_compile()\fP when the pattern argument is NULL. The length value
+passed is the default PCRE2_ZERO_TERMINATED unless \fBuse_length\fP is set.
+Any length other than zero causes an error.
+.
+.
 .SS "Specifying pattern characters in hexadecimal"
 .rs
 .sp
@@ -782,6 +803,17 @@ If \fBhex\fP or \fBuse_length\fP is used with the POSIX wrapper API (see
 below), the REG_PEND extension is used to pass the pattern's length.
 .
 .
+.SS "Specifying a maximum for variable lookbehinds"
+.rs
+.sp
+Variable lookbehind assertions are supported only if, for each one, there is a
+maximum length (in characters) that it can match. There is a limit on this,
+whose default can be set at build time, with an ultimate default of 255. The
+\fBmax_varlookbehind\fP modifier uses the \fBpcre2_set_max_varlookbehind()\fP
+function to change the limit. Lookbehinds whose branches each match a fixed
+length are limited to 65535 characters per branch.
+.
+.
 .SS "Specifying wide characters in 16-bit and 32-bit modes"
 .rs
 .sp
@@ -946,6 +978,15 @@ causes a compilation error. The default is the largest number a PCRE2_SIZE
 variable can hold (essentially unlimited).
 .
 .
+.SS "Limiting the size of a compiled pattern"
+.rs
+.sp
+The \fBmax_pattern_compiled_length\fP modifier sets a limit, in bytes, to the
+amount of memory used by a compiled pattern. Breaching the limit causes a
+compilation error. The default is the largest number a PCRE2_SIZE variable can
+hold (essentially unlimited).
+.
+.
 .\" HTML 
 .SS "Using the POSIX wrapper API"
 .rs
@@ -1039,6 +1080,7 @@ process.
       allusedtext                 show all consulted text
       altglobal                   alternative global matching
   /g  global                      global matching
+      heapframes_size             show match data heapframes size
       jitstack=                set size of JIT stack
       mark                        show mark values
       replace=            specify a replacement string
@@ -1143,18 +1185,19 @@ The following modifiers set options for \fBpcre2_match()\fP or
 .\"
 for a description of their effects.
 .sp
-      anchored                  set PCRE2_ANCHORED
-      endanchored               set PCRE2_ENDANCHORED
-      dfa_restart               set PCRE2_DFA_RESTART
-      dfa_shortest              set PCRE2_DFA_SHORTEST
-      no_jit                    set PCRE2_NO_JIT
-      no_utf_check              set PCRE2_NO_UTF_CHECK
-      notbol                    set PCRE2_NOTBOL
-      notempty                  set PCRE2_NOTEMPTY
-      notempty_atstart          set PCRE2_NOTEMPTY_ATSTART
-      noteol                    set PCRE2_NOTEOL
-      partial_hard (or ph)      set PCRE2_PARTIAL_HARD
-      partial_soft (or ps)      set PCRE2_PARTIAL_SOFT
+      anchored                   set PCRE2_ANCHORED
+      endanchored                set PCRE2_ENDANCHORED
+      dfa_restart                set PCRE2_DFA_RESTART
+      dfa_shortest               set PCRE2_DFA_SHORTEST
+      disable_recurseloop_check  set PCRE2_DISABLE_RECURSELOOP_CHECK
+      no_jit                     set PCRE2_NO_JIT
+      no_utf_check               set PCRE2_NO_UTF_CHECK
+      notbol                     set PCRE2_NOTBOL
+      notempty                   set PCRE2_NOTEMPTY
+      notempty_atstart           set PCRE2_NOTEMPTY_ATSTART
+      noteol                     set PCRE2_NOTEOL
+      partial_hard (or ph)       set PCRE2_PARTIAL_HARD
+      partial_soft (or ps)       set PCRE2_PARTIAL_SOFT
 .sp
 The partial matching modifiers are provided with abbreviations because they
 appear frequently in tests.
@@ -1211,6 +1254,7 @@ pattern, but can be overridden by modifiers on the subject.
       get=       extract captured substring
       getall                     extract all captured substrings
   /g  global                     global matching
+      heapframes_size            show match data heapframes size
       heap_limit=             set a limit on heap memory (Kbytes)
       jitstack=               set size of JIT stack
       mark                       show mark values
@@ -1476,7 +1520,7 @@ matching provokes an error return ("bad option value") from
 If the \fBsubstitute_callout\fP modifier is set, a substitution callout
 function is set up. The \fBnull_context\fP modifier must not be set, because
 the address of the callout function is passed in a match context. When the
-callout function is called (after each substitution), details of the the input
+callout function is called (after each substitution), details of the input
 and output strings are output. For example:
 .sp
   /abc/g,replace=<$0>,substitute_callout
@@ -1595,6 +1639,23 @@ memory is allocated during matching with JIT. For this modifier to work, the
 subject, though it can be set on one or the other.
 .
 .
+.SS "Showing the heap frame overall vector size"
+.rs
+.sp
+The \fBheapframes_size\fP modifier is relevant for matches using
+\fBpcre2_match()\fP without JIT. After a match has run (whether successful or
+not) the size, in bytes, of the allocated heap frames vector that is left
+attached to the match data block is shown. If the matching action involved
+several calls to \fBpcre2_match()\fP (for example, global matching or for
+timing) only the final value is shown.
+.P
+This modifier is ignored, with a warning, for POSIX or DFA matching. JIT
+matching does not use the heap frames vector, so the size is always zero,
+unless there was a previous non-JIT match. Note that specifing a size of zero
+for the output vector (see below) causes \fBpcre2test\fP to free its match data
+block (and associated heap frames vector) and allocate a new one.
+.
+.
 .SS "Setting a starting offset"
 .rs
 .sp
@@ -1624,9 +1685,9 @@ A value of zero is useful when testing the POSIX API because it causes
 \fBregexec()\fP to be called with a NULL capture vector. When not testing the
 POSIX API, a value of zero is used to cause
 \fBpcre2_match_data_create_from_pattern()\fP to be called, in order to create a
-match block of exactly the right size for the pattern. (It is not possible to
-create a match block with a zero-length ovector; there is always at least one
-pair of offsets.)
+new match block of exactly the right size for the pattern. (It is not possible
+to create a match block with a zero-length ovector; there is always at least
+one pair of offsets.) The old match data block is freed.
 .
 .
 .SS "Passing the subject as zero-terminated"
@@ -1725,9 +1786,8 @@ unset substring is shown as "", as for the second data line.
 If the strings contain any non-printing characters, they are output as \exhh
 escapes if the value is less than 256 and UTF mode is not set. Otherwise they
 are output as \ex{hh...} escapes. See below for the definition of non-printing
-characters. If the \fBaftertext\fP modifier is set, the output for substring
-0 is followed by the the rest of the subject string, identified by "0+" like
-this:
+characters. If the \fBaftertext\fP modifier is set, the output for substring 0
+is followed by the rest of the subject string, identified by "0+" like this:
 .sp
     re> /cat/aftertext
   data> cataract
@@ -2121,6 +2181,6 @@ Cambridge, England.
 .rs
 .sp
 .nf
-Last updated: 27 July 2022
-Copyright (c) 1997-2022 University of Cambridge.
+Last updated: 24 April 2024
+Copyright (c) 1997-2024 University of Cambridge.
 .fi
diff --git a/pcre2/doc/pcre2test.txt b/pcre2/doc/pcre2test.txt
index b03b11f..ddb491d 100644
--- a/pcre2/doc/pcre2test.txt
+++ b/pcre2/doc/pcre2test.txt
@@ -1,23 +1,24 @@
-PCRE2TEST(1)                General Commands Manual               PCRE2TEST(1)
 
+PCRE2TEST(1)                General Commands Manual               PCRE2TEST(1)
 
 
 NAME
        pcre2test - a program for testing Perl-compatible regular expressions.
 
+
 SYNOPSIS
 
        pcre2test [options] [input file [output file]]
 
        pcre2test is a test program for the PCRE2 regular expression libraries,
-       but it can also be used for  experimenting  with  regular  expressions.
-       This  document  describes the features of the test program; for details
-       of the regular expressions themselves, see the pcre2pattern  documenta-
-       tion.  For  details  of  the PCRE2 library function calls and their op-
+       but  it  can  also  be used for experimenting with regular expressions.
+       This document describes the features of the test program;  for  details
+       of  the regular expressions themselves, see the pcre2pattern documenta-
+       tion. For details of the PCRE2 library function  calls  and  their  op-
        tions, see the pcre2api documentation.
 
-       The input for pcre2test is a sequence of  regular  expression  patterns
-       and  subject  strings  to  be matched. There are also command lines for
+       The  input  for  pcre2test is a sequence of regular expression patterns
+       and subject strings to be matched. There are  also  command  lines  for
        setting defaults and controlling some special actions. The output shows
        the  result  of  each  match attempt. Modifiers on external or internal
        command lines, the patterns, and the subject lines specify PCRE2  func-
@@ -40,7 +41,7 @@ PCRE2's 8-BIT, 16-BIT AND 32-BIT LIBRARIES
        However, its own input and output are  always  in  8-bit  format.  When
        testing  the  16-bit  or 32-bit libraries, patterns and subject strings
        are converted to 16-bit or 32-bit format before being passed to the li-
-       brary  functions.  Results  are  converted back to 8-bit code units for
+       brary functions. Results are converted back to  8-bit  code  units  for
        output.
 
        In the rest of this document, the names of library functions and struc-
@@ -57,30 +58,30 @@ INPUT ENCODING
        end of file, and no further data is read, so this character  should  be
        avoided unless you really want that action.
 
-       The  input  is  processed using using C's string functions, so must not
-       contain binary zeros, even though in  Unix-like  environments,  fgets()
-       treats  any  bytes  other  than newline as data characters. An error is
-       generated if a binary zero is encountered. By default subject lines are
-       processed for backslash escapes, which makes it possible to include any
-       data value in strings that are passed to the library for matching.  For
-       patterns,  there  is a facility for specifying some or all of the 8-bit
-       input characters as hexadecimal pairs, which makes it possible  to  in-
-       clude binary zeros.
+       The  input is processed using C's string functions, so must not contain
+       binary zeros, even though in Unix-like environments, fgets() treats any
+       bytes other than newline as data characters. An error is generated if a
+       binary zero is encountered. By default subject lines are processed  for
+       backslash escapes, which makes it possible to include any data value in
+       strings  that  are  passed  to  the library for matching. For patterns,
+       there is a facility for specifying some or all of the 8-bit input char-
+       acters as hexadecimal pairs, which makes it possible to include  binary
+       zeros.
 
    Input for the 16-bit and 32-bit libraries
 
        When testing the 16-bit or 32-bit libraries, there is a need to be able
-       to generate character code points greater than 255 in the strings  that
-       are  passed to the library. For subject lines, backslash escapes can be
-       used. In addition, when the utf modifier (see "Setting compilation  op-
-       tions"  below)  is set, the pattern and any following subject lines are
-       interpreted as UTF-8 strings and translated to UTF-16 or UTF-32 as  ap-
+       to  generate character code points greater than 255 in the strings that
+       are passed to the library. For subject lines, backslash escapes can  be
+       used.  In addition, when the utf modifier (see "Setting compilation op-
+       tions" below) is set, the pattern and any following subject  lines  are
+       interpreted  as UTF-8 strings and translated to UTF-16 or UTF-32 as ap-
        propriate.
 
-       For  non-UTF testing of wide characters, the utf8_input modifier can be
-       used. This is mutually exclusive with  utf,  and  is  allowed  only  in
-       16-bit  or  32-bit  mode.  It  causes the pattern and following subject
-       lines to be treated as UTF-8 according to the original definition  (RFC
+       For non-UTF testing of wide characters, the utf8_input modifier can  be
+       used.  This  is  mutually  exclusive  with  utf, and is allowed only in
+       16-bit or 32-bit mode. It causes  the  pattern  and  following  subject
+       lines  to be treated as UTF-8 according to the original definition (RFC
        2279), which allows for character values up to 0x7fffffff. Each charac-
        ter is placed in one 16-bit or 32-bit code unit (in  the  16-bit  case,
        values greater than 0xffff cause an error to occur).
@@ -97,28 +98,28 @@ INPUT ENCODING
 COMMAND LINE OPTIONS
 
        -8        If the 8-bit library has been built, this option causes it to
-                 be used (this is the default). If the 8-bit library  has  not
+                 be  used  (this is the default). If the 8-bit library has not
                  been built, this option causes an error.
 
-       -16       If  the  16-bit library has been built, this option causes it
-                 to be used. If only the 16-bit library has been  built,  this
-                 is  the  default.  If  the 16-bit library has not been built,
-                 this option causes an error.
+       -16       If the 16-bit library has been built, this option  causes  it
+                 to  be used. If the 8-bit library has not been built, this is
+                 the default. If the 16-bit library has not been  built,  this
+                 option causes an error.
 
-       -32       If the 32-bit library has been built, this option  causes  it
-                 to  be  used. If only the 32-bit library has been built, this
-                 is the default. If the 32-bit library  has  not  been  built,
-                 this option causes an error.
+       -32       If  the  32-bit library has been built, this option causes it
+                 to be used. If no other library has been built, this  is  the
+                 default.  If  the 32-bit library has not been built, this op-
+                 tion causes an error.
 
        -ac       Behave as if each pattern has the auto_callout modifier, that
                  is, insert automatic callouts into every pattern that is com-
                  piled.
 
-       -AC       As  for  -ac,  but in addition behave as if each subject line
-                 has the callout_extra modifier, that is, show additional  in-
+       -AC       As for -ac, but in addition behave as if  each  subject  line
+                 has  the callout_extra modifier, that is, show additional in-
                  formation from callouts.
 
-       -b        Behave  as  if each pattern has the fullbincode modifier; the
+       -b        Behave as if each pattern has the fullbincode  modifier;  the
                  full internal binary form of the pattern is output after com-
                  pilation.
 
@@ -190,9 +191,9 @@ COMMAND LINE OPTIONS
                  passed directly to the JIT matcher via its "fast path".
 
        -jitverify
-                 Behave as if each pattern line has  the  jitverify  modifier;
-                 after  successful  compilation, each pattern is passed to the
-                 just-in-time compiler, if available, and the use of  JIT  for
+                 Behave  as  if  each pattern line has the jitverify modifier;
+                 after successful compilation, each pattern is passed  to  the
+                 just-in-time  compiler,  if available, and the use of JIT for
                  matching is verified.
 
        -LM       List modifiers: write a list of available pattern and subject
@@ -233,8 +234,8 @@ COMMAND LINE OPTIONS
        -tm       This is like -t except that it times only the matching phase,
                  not the compile phase.
 
-       -T -TM    These  behave like -t and -tm, but in addition, at the end of
-                 a run, the total times for all compiles and matches are  out-
+       -T -TM    These behave like -t and -tm, but in addition, at the end  of
+                 a  run, the total times for all compiles and matches are out-
                  put.
 
        -version  Output the PCRE2 version number and then exit.
@@ -242,15 +243,15 @@ COMMAND LINE OPTIONS
 
 DESCRIPTION
 
-       If  pcre2test  is given two filename arguments, it reads from the first
+       If pcre2test is given two filename arguments, it reads from  the  first
        and writes to the second. If the first name is "-", input is taken from
        the  standard  input. If pcre2test is given only one argument, it reads
        from that file and writes to stdout. Otherwise, it reads from stdin and
        writes to stdout.
 
-       When  pcre2test  is  built,  a configuration option can specify that it
-       should be linked with the libreadline or libedit library. When this  is
-       done,  if the input is from a terminal, it is read using the readline()
+       When pcre2test is built, a configuration option  can  specify  that  it
+       should  be linked with the libreadline or libedit library. When this is
+       done, if the input is from a terminal, it is read using the  readline()
        function. This provides line-editing and history facilities. The output
        from the -help option states whether or not readline() will be used.
 
@@ -259,17 +260,17 @@ DESCRIPTION
        followed by any number of subject lines to be matched against that pat-
        tern. In between sets of test data, command lines that begin with # may
        appear. This file format, with some restrictions, can also be processed
-       by the perltest.sh script that is distributed with PCRE2 as a means  of
+       by  the perltest.sh script that is distributed with PCRE2 as a means of
        checking that the behaviour of PCRE2 and Perl is the same. For a speci-
        fication of perltest.sh, see the comments near its beginning. See  also
        the #perltest command below.
 
        When the input is a terminal, pcre2test prompts for each line of input,
-       using "re>" to prompt for regular expression patterns, and  "data>"  to
-       prompt  for subject lines. Command lines starting with # can be entered
+       using  "re>"  to prompt for regular expression patterns, and "data>" to
+       prompt for subject lines. Command lines starting with # can be  entered
        only in response to the "re>" prompt.
 
-       Each subject line is matched separately and independently. If you  want
+       Each  subject line is matched separately and independently. If you want
        to do multi-line matches, you have to use the \n escape sequence (or \r
        or \r\n, etc., depending on the newline setting) in a  single  line  of
        input  to encode the newline sequences. There is no limit on the length
@@ -287,25 +288,25 @@ COMMAND LINES
 
        In  between sets of test data, a line that begins with # is interpreted
        as a command line. If the first character is followed by white space or
-       an  exclamation  mark,  the  line is treated as a comment, and ignored.
+       an exclamation mark, the line is treated as  a  comment,  and  ignored.
        Otherwise, the following commands are recognized:
 
          #forbid_utf
 
-       Subsequent  patterns  automatically  have   the   PCRE2_NEVER_UTF   and
-       PCRE2_NEVER_UCP  options  set, which locks out the use of the PCRE2_UTF
-       and PCRE2_UCP options and the use of (*UTF) and (*UCP) at the start  of
-       patterns.  This  command  also  forces an error if a subsequent pattern
-       contains any occurrences of \P, \p, or \X, which  are  still  supported
-       when  PCRE2_UTF  is not set, but which require Unicode property support
+       Subsequent   patterns   automatically   have  the  PCRE2_NEVER_UTF  and
+       PCRE2_NEVER_UCP options set, which locks out the use of  the  PCRE2_UTF
+       and  PCRE2_UCP options and the use of (*UTF) and (*UCP) at the start of
+       patterns. This command also forces an error  if  a  subsequent  pattern
+       contains  any  occurrences  of \P, \p, or \X, which are still supported
+       when PCRE2_UTF is not set, but which require Unicode  property  support
        to be included in the library.
 
-       This is a trigger guard that is used in test files to ensure  that  UTF
-       or  Unicode property tests are not accidentally added to files that are
-       used when Unicode support is  not  included  in  the  library.  Setting
-       PCRE2_NEVER_UTF  and  PCRE2_NEVER_UCP as a default can also be obtained
-       by the use of #pattern; the difference is that  #forbid_utf  cannot  be
-       unset,  and the automatic options are not displayed in pattern informa-
+       This  is  a trigger guard that is used in test files to ensure that UTF
+       or Unicode property tests are not accidentally added to files that  are
+       used  when  Unicode  support  is  not  included in the library. Setting
+       PCRE2_NEVER_UTF and PCRE2_NEVER_UCP as a default can also  be  obtained
+       by  the  use  of #pattern; the difference is that #forbid_utf cannot be
+       unset, and the automatic options are not displayed in pattern  informa-
        tion, to avoid cluttering up test output.
 
          #load 
@@ -325,10 +326,10 @@ COMMAND LINES
        When PCRE2 is built, a default newline  convention  can  be  specified.
        This  determines which characters and/or character pairs are recognized
        as indicating a newline in a pattern or subject string. The default can
-       be  overridden when a pattern is compiled. The standard test files con-
-       tain tests of various newline conventions,  but  the  majority  of  the
-       tests  expect  a  single  linefeed to be recognized as a newline by de-
-       fault. Without special action the tests would fail when PCRE2  is  com-
+       be overridden when a pattern is compiled. The standard test files  con-
+       tain  tests  of  various  newline  conventions, but the majority of the
+       tests expect a single linefeed to be recognized as  a  newline  by  de-
+       fault.  Without  special action the tests would fail when PCRE2 is com-
        piled with either CR or CRLF as the default newline.
 
        The #newline_default command specifies a list of newline types that are
@@ -338,13 +339,13 @@ COMMAND LINES
          #newline_default LF Any anyCRLF
 
        If the default newline is in the list, this command has no effect. Oth-
-       erwise, except when testing the POSIX  API,  a  newline  modifier  that
+       erwise,  except  when  testing  the  POSIX API, a newline modifier that
        specifies the first newline convention in the list (LF in the above ex-
        ample) is added to any pattern that does not  already  have  a  newline
        modifier. If the newline list is empty, the feature is turned off. This
        command is present in a number of the standard test input files.
 
-       When the POSIX API is being tested there is no way to override the  de-
+       When  the POSIX API is being tested there is no way to override the de-
        fault newline convention, though it is possible to set the newline con-
        vention from within the pattern. A warning is given  if  the  posix  or
        posix_nosub  modifier is used when #newline_default would set a default
@@ -367,28 +368,28 @@ COMMAND LINES
        that set or unset "mark" are recognized and acted  on.  The  #perltest,
        #forbid_utf,  and  #newline_default  commands,  which are needed in the
        relevant pcre2test files, are silently ignored. All other command lines
-       are  ignored,  but  give a warning message. The #perltest command helps
-       detect tests that are accidentally put in the wrong  file  or  use  the
-       wrong  delimiter.  For  more  details of the perltest.sh script see the
+       are ignored, but give a warning message. The  #perltest  command  helps
+       detect  tests  that  are  accidentally put in the wrong file or use the
+       wrong delimiter. For more details of the  perltest.sh  script  see  the
        comments it contains.
 
          #pop []
          #popcopy []
 
-       These commands are used to manipulate the stack of  compiled  patterns,
-       as  described  in  the  section entitled "Saving and restoring compiled
+       These  commands  are used to manipulate the stack of compiled patterns,
+       as described in the section entitled  "Saving  and  restoring  compiled
        patterns" below.
 
          #save 
 
-       This command is used to save a set of compiled patterns to a  file,  as
-       described  in  the section entitled "Saving and restoring compiled pat-
+       This  command  is used to save a set of compiled patterns to a file, as
+       described in the section entitled "Saving and restoring  compiled  pat-
        terns" below.
 
          #subject 
 
-       This command sets a default modifier list that applies  to  all  subse-
-       quent  subject lines. Modifiers on a subject line can change these set-
+       This  command  sets  a default modifier list that applies to all subse-
+       quent subject lines. Modifiers on a subject line can change these  set-
        tings.
 
 
@@ -396,38 +397,38 @@ MODIFIER SYNTAX
 
        Modifier lists are used with both pattern and subject lines. Items in a
        list are separated by commas followed by optional white space. Trailing
-       whitespace in a modifier list is ignored. Some modifiers may  be  given
-       for  both patterns and subject lines, whereas others are valid only for
-       one or the other. Each modifier has  a  long  name,  for  example  "an-
-       chored",  and  some  of  them  must be followed by an equals sign and a
-       value, for example, "offset=12". Values cannot  contain  comma  charac-
-       ters,  but may contain spaces. Modifiers that do not take values may be
+       whitespace  in  a modifier list is ignored. Some modifiers may be given
+       for both patterns and subject lines, whereas others are valid only  for
+       one  or  the  other.  Each  modifier  has a long name, for example "an-
+       chored", and some of them must be followed by  an  equals  sign  and  a
+       value,  for  example,  "offset=12". Values cannot contain comma charac-
+       ters, but may contain spaces. Modifiers that do not take values may  be
        preceded by a minus sign to turn off a previous setting.
 
        A few of the more common modifiers can also be specified as single let-
        ters,  for  example "i" for "caseless". In documentation, following the
        Perl convention, these are written with a slash ("the /i modifier") for
-       clarity.  Abbreviated  modifiers  must all be concatenated in the first
-       item of a modifier list. If the first item is not recognized as a  long
-       modifier  name, it is interpreted as a sequence of these abbreviations.
+       clarity. Abbreviated modifiers must all be concatenated  in  the  first
+       item  of a modifier list. If the first item is not recognized as a long
+       modifier name, it is interpreted as a sequence of these  abbreviations.
        For example:
 
          /abc/ig,newline=cr,jit=3
 
-       This is a pattern line whose modifier list starts with  two  one-letter
-       modifiers  (/i  and  /g).  The lower-case abbreviated modifiers are the
+       This  is  a pattern line whose modifier list starts with two one-letter
+       modifiers (/i and /g). The lower-case  abbreviated  modifiers  are  the
        same as used in Perl.
 
 
 PATTERN SYNTAX
 
-       A pattern line must start with one of the following characters  (common
+       A  pattern line must start with one of the following characters (common
        symbols, excluding pattern meta-characters):
 
          / ! " ' ` - = _ : ; , % & @ ~
 
-       This  is  interpreted  as the pattern's delimiter. A regular expression
-       may be continued over several input lines, in which  case  the  newline
+       This is interpreted as the pattern's delimiter.  A  regular  expression
+       may  be  continued  over several input lines, in which case the newline
        characters are included within it. It is possible to include the delim-
        iter as a literal within the pattern by escaping it with  a  backslash,
        for example
@@ -436,16 +437,16 @@ PATTERN SYNTAX
 
        If  you do this, the escape and the delimiter form part of the pattern,
        but since the delimiters are all non-alphanumeric, the inclusion of the
-       backslash  does not affect the pattern's interpretation. Note, however,
+       backslash does not affect the pattern's interpretation. Note,  however,
        that this trick does not work within \Q...\E literal bracketing because
        the backslash will itself be interpreted as a literal. If the terminat-
        ing delimiter is immediately followed by a backslash, for example,
 
          /abc/\
 
-       then a backslash is added to the end of the pattern. This  is  done  to
-       provide  a  way of testing the error condition that arises if a pattern
-       finishes with a backslash, because
+       a backslash is added to the end of the pattern. This is done to provide
+       a  way of testing the error condition that arises if a pattern finishes
+       with a backslash, because
 
          /abc\/
 
@@ -459,9 +460,9 @@ PATTERN SYNTAX
 SUBJECT LINE SYNTAX
 
        Before each subject line is passed to pcre2_match(), pcre2_dfa_match(),
-       or  pcre2_jit_match(), leading and trailing white space is removed, and
-       the line is scanned for backslash escapes, unless  the  subject_literal
-       modifier  was set for the pattern. The following provide a means of en-
+       or pcre2_jit_match(), leading and trailing white space is removed,  and
+       the  line  is scanned for backslash escapes, unless the subject_literal
+       modifier was set for the pattern. The following provide a means of  en-
        coding non-printing characters in a visible way:
 
          \a         alarm (BEL, \x07)
@@ -503,31 +504,31 @@ SUBJECT LINE SYNTAX
 
          \[]{}
 
-       This  makes  it possible to test long strings without having to provide
+       This makes it possible to test long strings without having  to  provide
        them as part of the file. For example:
 
          \[abc]{4}
 
-       is converted to "abcabcabcabc". This feature does not support  nesting.
+       is  converted to "abcabcabcabc". This feature does not support nesting.
        To include a closing square bracket in the characters, code it as \x5D.
 
-       A  backslash  followed  by  an equals sign marks the end of the subject
+       A backslash followed by an equals sign marks the  end  of  the  subject
        string and the start of a modifier list. For example:
 
          abc\=notbol,notempty
 
-       If the subject string is empty and \= is followed  by  whitespace,  the
-       line  is  treated  as a comment line, and is not used for matching. For
+       If  the  subject  string is empty and \= is followed by whitespace, the
+       line is treated as a comment line, and is not used  for  matching.  For
        example:
 
          \= This is a comment.
          abc\= This is an invalid modifier list.
 
-       A backslash followed by any other non-alphanumeric character  just  es-
-       capes  that  character. A backslash followed by anything else causes an
-       error. However, if the very last character in the line is  a  backslash
-       (and  there  is  no  modifier list), it is ignored. This gives a way of
-       passing an empty line as data, since a real empty line  terminates  the
+       A  backslash  followed by any other non-alphanumeric character just es-
+       capes that character. A backslash followed by anything else  causes  an
+       error.  However,  if the very last character in the line is a backslash
+       (and there is no modifier list), it is ignored. This  gives  a  way  of
+       passing  an  empty line as data, since a real empty line terminates the
        data input.
 
        If the subject_literal modifier is set for a pattern, all subject lines
@@ -540,21 +541,20 @@ PATTERN MODIFIERS
 
        There are several types of modifier that can appear in  pattern  lines.
        Except where noted below, they may also be used in #pattern commands. A
-       pattern's modifier list can add to or override default  modifiers  that
+       pattern's  modifier  list can add to or override default modifiers that
        were set by a previous #pattern command.
 
    Setting compilation options
 
-       The  following  modifiers set options for pcre2_compile(). Most of them
-       set bits in the options argument of  that  function,  but  those  whose
+       The following modifiers set options for pcre2_compile(). Most  of  them
+       set  bits  in  the  options  argument of that function, but those whose
        names start with PCRE2_EXTRA are additional options that are set in the
-       compile context. For the main options, there are some single-letter ab-
-       breviations  that  are  the same as Perl options. There is special han-
-       dling for /x: if a second x is  present,  PCRE2_EXTENDED  is  converted
-       into  PCRE2_EXTENDED_MORE as in Perl. A third appearance adds PCRE2_EX-
-       TENDED as well, though this makes no difference to the  way  pcre2_com-
-       pile()  behaves. See pcre2api for a description of the effects of these
-       options.
+       compile context.  Some of these options  have  single-letter  abbrevia-
+       tions.  There  is  special  handling  for /x: if a second x is present,
+       PCRE2_EXTENDED is converted into  PCRE2_EXTENDED_MORE  as  in  Perl.  A
+       third appearance adds PCRE2_EXTENDED as well, though this makes no dif-
+       ference to the way pcre2_compile() behaves. See pcre2api for a descrip-
+       tion of the effects of these options.
 
              allow_empty_class         set PCRE2_ALLOW_EMPTY_CLASS
              allow_lookaround_bsk      set PCRE2_EXTRA_ALLOW_LOOKAROUND_BSK
@@ -563,9 +563,16 @@ PATTERN MODIFIERS
              alt_circumflex            set PCRE2_ALT_CIRCUMFLEX
              alt_verbnames             set PCRE2_ALT_VERBNAMES
              anchored                  set PCRE2_ANCHORED
+         /a  ascii_all                 set all ASCII options
+             ascii_bsd                 set PCRE2_EXTRA_ASCII_BSD
+             ascii_bss                 set PCRE2_EXTRA_ASCII_BSS
+             ascii_bsw                 set PCRE2_EXTRA_ASCII_BSW
+             ascii_digit               set PCRE2_EXTRA_ASCII_DIGIT
+             ascii_posix               set PCRE2_EXTRA_ASCII_POSIX
              auto_callout              set PCRE2_AUTO_CALLOUT
              bad_escape_is_literal     set PCRE2_EXTRA_BAD_ESCAPE_IS_LITERAL
          /i  caseless                  set PCRE2_CASELESS
+         /r  caseless_restrict         set PCRE2_EXTRA_CASELESS_RESTRICT
              dollar_endonly            set PCRE2_DOLLAR_ENDONLY
          /s  dotall                    set PCRE2_DOTALL
              dupnames                  set PCRE2_DUPNAMES
@@ -623,10 +630,14 @@ PATTERN MODIFIERS
              jitfast                   use JIT fast path
              jitverify                 verify JIT use
              locale=             use this locale
-             max_pattern_length=    set the maximum pattern length
+             max_pattern_compiled      ) set maximum compiled pattern
+                        _length=    )   length (bytes)
+             max_pattern_length=    set maximum pattern length (code units)
+             max_varlookbehind=     set maximum variable lookbehind length
              memory                    show memory used
              newline=            set newline type
              null_context              compile with a NULL context
+             null_pattern              pass pattern as NULL
              parens_nest_limit=     set maximum parentheses depth
              posix                     use the POSIX API
              posix_nosub               use the POSIX API with REG_NOSUB
@@ -648,7 +659,7 @@ PATTERN MODIFIERS
        specified when PCRE2 is built; if it is not, the default is set to Uni-
        code.
 
-       The  newline  modifier specifies which characters are to be interpreted
+       The newline modifier specifies which characters are to  be  interpreted
        as newlines, both in the pattern and in subject lines. The type must be
        one of CR, LF, CRLF, ANYCRLF, ANY, or NUL (in upper or lower case).
 
@@ -658,7 +669,7 @@ PATTERN MODIFIERS
        available information.
 
        The bincode modifier causes a representation of the compiled code to be
-       output  after compilation. This information does not contain length and
+       output after compilation. This information does not contain length  and
        offset values, which ensures that the same output is generated for dif-
        ferent  internal  link  sizes  and different code unit widths. By using
        bincode, the same regression tests can be used  in  different  environ-
@@ -700,9 +711,11 @@ PATTERN MODIFIERS
        no_start_optimize  is  set because the minimum length is not calculated
        when it can never be used.
 
-       The framesize modifier shows the size, in bytes, of the storage  frames
+       The framesize modifier shows the size, in bytes, of each storage  frame
        used  by  pcre2_match()  for handling backtracking. The size depends on
-       the number of capturing parentheses in the pattern.
+       the number of capturing parentheses in the pattern. A vector  of  these
+       frames  is  used  at  matching time; its overall size is shown when the
+       heaframes_size subject modifier is set.
 
        The callout_info modifier requests information about all  the  callouts
        in the pattern. A list of them is output at the end of any other infor-
@@ -716,25 +729,32 @@ PATTERN MODIFIERS
        testing  that  pcre2_compile()  behaves correctly in this case (it uses
        default values).
 
+   Passing a NULL pattern
+
+       The null_pattern modifier is for testing the  behaviour  of  pcre2_com-
+       pile()  when  the  pattern argument is NULL. The length value passed is
+       the default PCRE2_ZERO_TERMINATED unless use_length is set.  Any length
+       other than zero causes an error.
+
    Specifying pattern characters in hexadecimal
 
        The hex modifier specifies that the characters of the  pattern,  except
        for  substrings  enclosed  in single or double quotes, are to be inter-
        preted as pairs of hexadecimal digits. This feature is  provided  as  a
        way of creating patterns that contain binary zeros and other non-print-
-       ing characters. White space is permitted between pairs of  digits.  For
+       ing  characters.  White space is permitted between pairs of digits. For
        example, this pattern contains three characters:
 
          /ab 32 59/hex
 
-       Parts  of  such  a  pattern are taken literally if quoted. This pattern
-       contains nine characters, only two of which are specified in  hexadeci-
+       Parts of such a pattern are taken literally  if  quoted.  This  pattern
+       contains  nine characters, only two of which are specified in hexadeci-
        mal:
 
          /ab "literal" 32/hex
 
-       Either  single or double quotes may be used. There is no way of includ-
-       ing the delimiter within a substring. The hex and expand modifiers  are
+       Either single or double quotes may be used. There is no way of  includ-
+       ing  the delimiter within a substring. The hex and expand modifiers are
        mutually exclusive.
 
    Specifying the pattern's length
@@ -747,13 +767,23 @@ PATTERN MODIFIERS
        ros.
 
        If hex or use_length is used with the POSIX wrapper API (see "Using the
-       POSIX  wrapper  API" below), the REG_PEND extension is used to pass the
+       POSIX wrapper API" below), the REG_PEND extension is used to  pass  the
        pattern's length.
 
+   Specifying a maximum for variable lookbehinds
+
+       Variable  lookbehind  assertions  are  supported only if, for each one,
+       there is a maximum length (in characters) that it can match. There is a
+       limit on this, whose default can be set at build time, with an ultimate
+       default   of   255.   The   max_varlookbehind   modifier    uses    the
+       pcre2_set_max_varlookbehind() function to change the limit. Lookbehinds
+       whose  branches  each match a fixed length are limited to 65535 charac-
+       ters per branch.
+
    Specifying wide characters in 16-bit and 32-bit modes
 
        In 16-bit and 32-bit modes, all input is automatically treated as UTF-8
-       and  translated  to  UTF-16 or UTF-32 when the utf modifier is set. For
+       and translated to UTF-16 or UTF-32 when the utf modifier  is  set.  For
        testing the 16-bit and 32-bit libraries in non-UTF mode, the utf8_input
        modifier  can  be  used. It is mutually exclusive with utf. Input lines
        are interpreted as UTF-8 as a means of specifying wide characters. More
@@ -761,18 +791,18 @@ PATTERN MODIFIERS
 
    Generating long repetitive patterns
 
-       Some  tests use long patterns that are very repetitive. Instead of cre-
-       ating a very long input line for such a pattern, you can use a  special
-       repetition  feature,  similar  to  the  one described for subject lines
-       above. If the expand modifier is present on a  pattern,  parts  of  the
+       Some tests use long patterns that are very repetitive. Instead of  cre-
+       ating  a very long input line for such a pattern, you can use a special
+       repetition feature, similar to the  one  described  for  subject  lines
+       above.  If  the  expand  modifier is present on a pattern, parts of the
        pattern that have the form
 
          \[]{}
 
        are expanded before the pattern is passed to pcre2_compile(). For exam-
        ple, \[AB]{6000} is expanded to "ABAB..." 6000 times. This construction
-       cannot  be  nested. An initial "\[" sequence is recognized only if "]{"
-       followed by decimal digits and "}" is found later in  the  pattern.  If
+       cannot be nested. An initial "\[" sequence is recognized only  if  "]{"
+       followed  by  decimal  digits and "}" is found later in the pattern. If
        not, the characters remain in the pattern unaltered. The expand and hex
        modifiers are mutually exclusive.
 
@@ -797,8 +827,8 @@ PATTERN MODIFIERS
        options are specified for each match attempt.
 
        JIT compilation is requested by the jit pattern modifier, which may op-
-       tionally  be  followed by an equals sign and a number in the range 0 to
-       7.  The three bits that make up the number specify which of  the  three
+       tionally be followed by an equals sign and a number in the range  0  to
+       7.   The  three bits that make up the number specify which of the three
        JIT operating modes are to be compiled:
 
          1  compile JIT code for non-partial matching
@@ -815,16 +845,16 @@ PATTERN MODIFIERS
          6  soft and hard partial matching only
          7  all three modes
 
-       If  no  number  is  given,  7 is assumed. The phrase "partial matching"
+       If no number is given, 7 is  assumed.  The  phrase  "partial  matching"
        means a call to pcre2_match() with either the PCRE2_PARTIAL_SOFT or the
        PCRE2_PARTIAL_HARD  option set. Note that such a call may return a com-
        plete match; the options enable the possibility of a partial match, but
-       do  not  require it. Note also that if you request JIT compilation only
-       for partial matching (for example, jit=2) but do not  set  the  partial
-       modifier  on  a  subject line, that match will not use JIT code because
+       do not require it. Note also that if you request JIT  compilation  only
+       for  partial  matching  (for example, jit=2) but do not set the partial
+       modifier on a subject line, that match will not use  JIT  code  because
        none was compiled for non-partial matching.
 
-       If JIT compilation is successful, the compiled JIT code will  automati-
+       If  JIT compilation is successful, the compiled JIT code will automati-
        cally be used when an appropriate type of match is run, except when in-
        compatible run-time options are specified. For more  details,  see  the
        pcre2jit  documentation. See also the jitstack modifier below for a way
@@ -854,7 +884,7 @@ PATTERN MODIFIERS
        pile()  when compiling the regular expression. The same tables are used
        when matching the following subject lines. The locale modifier  applies
        only to the pattern on which it appears, but can be given in a #pattern
-       command if a default is needed. Setting a locale and alternate  charac-
+       command  if a default is needed. Setting a locale and alternate charac-
        ter tables are mutually exclusive.
 
    Showing pattern memory
@@ -882,9 +912,16 @@ PATTERN MODIFIERS
 
        The  max_pattern_length  modifier  sets  a limit, in code units, to the
        length of pattern that pcre2_compile() will accept. Breaching the limit
-       causes  a  compilation  error.  The  default  is  the  largest number a
+       causes a compilation  error.  The  default  is  the  largest  number  a
        PCRE2_SIZE variable can hold (essentially unlimited).
 
+   Limiting the size of a compiled pattern
+
+       The max_pattern_compiled_length modifier sets a limit, in bytes, to the
+       amount of memory used by a compiled pattern. Breaching the limit causes
+       a  compilation  error.  The  default is the largest number a PCRE2_SIZE
+       variable can hold (essentially unlimited).
+
    Using the POSIX wrapper API
 
        The posix and posix_nosub modifiers cause pcre2test to call  PCRE2  via
@@ -892,7 +929,7 @@ PATTERN MODIFIERS
        used, the POSIX option REG_NOSUB is  passed  to  regcomp().  The  POSIX
        wrapper  supports  only  the 8-bit library. Note that it does not imply
        POSIX matching semantics; for more detail see the pcre2posix documenta-
-       tion.  The  following  pattern  modifiers set options for the regcomp()
+       tion. The following pattern modifiers set  options  for  the  regcomp()
        function:
 
          caseless           REG_ICASE
@@ -902,17 +939,17 @@ PATTERN MODIFIERS
          ucp                REG_UCP        )   the POSIX standard
          utf                REG_UTF8       )
 
-       The regerror_buffsize modifier specifies a size for  the  error  buffer
-       that  is  passed to regerror() in the event of a compilation error. For
+       The  regerror_buffsize  modifier  specifies a size for the error buffer
+       that is passed to regerror() in the event of a compilation  error.  For
        example:
 
          /abc/posix,regerror_buffsize=20
 
-       This provides a means of testing the behaviour of regerror()  when  the
-       buffer  is  too  small  for the error message. If this modifier has not
+       This  provides  a means of testing the behaviour of regerror() when the
+       buffer is too small for the error message. If  this  modifier  has  not
        been set, a large buffer is used.
 
-       The aftertext and allaftertext subject modifiers work as described  be-
+       The  aftertext and allaftertext subject modifiers work as described be-
        low. All other modifiers are either ignored, with a warning message, or
        cause an error.
 
@@ -922,10 +959,10 @@ PATTERN MODIFIERS
 
    Testing the stack guard feature
 
-       The stackguard modifier is used  to  test  the  use  of  pcre2_set_com-
-       pile_recursion_guard(),  a  function  that  is provided to enable stack
-       availability to be checked during compilation (see the  pcre2api  docu-
-       mentation  for  details).  If  the  number specified by the modifier is
+       The  stackguard  modifier  is  used  to  test the use of pcre2_set_com-
+       pile_recursion_guard(), a function that is  provided  to  enable  stack
+       availability  to  be checked during compilation (see the pcre2api docu-
+       mentation for details). If the number  specified  by  the  modifier  is
        greater than zero, pcre2_set_compile_recursion_guard() is called to set
        up  callback  from pcre2_compile() to a local function. The argument it
        receives is the current nesting parenthesis depth; if this  is  greater
@@ -934,7 +971,7 @@ PATTERN MODIFIERS
 
    Using alternative character tables
 
-       The value specified for the tables modifier must be one of  the  digits
+       The  value  specified for the tables modifier must be one of the digits
        0, 1, 2, or 3. It causes a specific set of built-in character tables to
        be passed to pcre2_compile(). This is used in the PCRE2 tests to  check
        behaviour  with different character tables. The digit specifies the ta-
@@ -954,9 +991,9 @@ PATTERN MODIFIERS
    Setting certain match controls
 
        The following modifiers are really subject modifiers, and are described
-       under "Subject Modifiers" below. However, they may  be  included  in  a
-       pattern's  modifier  list, in which case they are applied to every sub-
-       ject line that is processed with that pattern. These modifiers  do  not
+       under  "Subject  Modifiers"  below.  However, they may be included in a
+       pattern's modifier list, in which case they are applied to  every  sub-
+       ject  line  that is processed with that pattern. These modifiers do not
        affect the compilation process.
 
              aftertext                   show text after match
@@ -966,6 +1003,7 @@ PATTERN MODIFIERS
              allusedtext                 show all consulted text
              altglobal                   alternative global matching
          /g  global                      global matching
+             heapframes_size             show match data heapframes size
              jitstack=                set size of JIT stack
              mark                        show mark values
              replace=            specify a replacement string
@@ -981,12 +1019,12 @@ PATTERN MODIFIERS
              substitute_unknown_unset    use PCRE2_SUBSTITUTE_UNKNOWN_UNSET
              substitute_unset_empty      use PCRE2_SUBSTITUTE_UNSET_EMPTY
 
-       These  modifiers may not appear in a #pattern command. If you want them
+       These modifiers may not appear in a #pattern command. If you want  them
        as defaults, set them in a #subject command.
 
    Specifying literal subject lines
 
-       If the subject_literal modifier is present on a pattern, all  the  sub-
+       If  the  subject_literal modifier is present on a pattern, all the sub-
        ject lines that it matches are taken as literal strings, with no inter-
        pretation of backslashes. It is not possible to set  subject  modifiers
        on  such  lines, but any that are set as defaults by a #subject command
@@ -998,12 +1036,12 @@ PATTERN MODIFIERS
        pushed  onto  a  stack  of compiled patterns, and pcre2test expects the
        next line to contain a new pattern (or a command) instead of a  subject
        line. This facility is used when saving compiled patterns to a file, as
-       described in the section entitled "Saving and restoring  compiled  pat-
-       terns"  below.  If pushcopy is used instead of push, a copy of the com-
-       piled pattern is stacked, leaving the original  as  current,  ready  to
-       match  the  following  input  lines. This provides a way of testing the
-       pcre2_code_copy() function.  The push and pushcopy  modifiers  are  in-
-       compatible  with compilation modifiers such as global that act at match
+       described  in  the section entitled "Saving and restoring compiled pat-
+       terns" below.  If pushcopy is used instead of push, a copy of the  com-
+       piled  pattern  is  stacked,  leaving the original as current, ready to
+       match the following input lines. This provides a  way  of  testing  the
+       pcre2_code_copy()  function.   The push and pushcopy  modifiers are in-
+       compatible with compilation modifiers such as global that act at  match
        time. Any that are specified are ignored (for the stacked copy), with a
        warning  message,  except for replace, which causes an error. Note that
        jitverify, which is allowed, does not carry through to  any  subsequent
@@ -1028,7 +1066,7 @@ PATTERN MODIFIERS
        tern is passed to pcre2_pattern_convert(). If the  conversion  is  suc-
        cessful,  the  result  is  reflected  in  the output and then passed to
        pcre2_compile(). The normal utf and no_utf_check options, if set, cause
-       the  PCRE2_CONVERT_UTF  and  PCRE2_CONVERT_NO_UTF_CHECK  options  to be
+       the PCRE2_CONVERT_UTF  and  PCRE2_CONVERT_NO_UTF_CHECK  options  to  be
        passed to pcre2_pattern_convert().
 
        By default, the conversion function is allowed to allocate a buffer for
@@ -1048,42 +1086,43 @@ SUBJECT MODIFIERS
 
    Setting match options
 
-       The   following   modifiers   set   options   for   pcre2_match()    or
+       The    following   modifiers   set   options   for   pcre2_match()   or
        pcre2_dfa_match(). See pcreapi for a description of their effects.
 
-             anchored                  set PCRE2_ANCHORED
-             endanchored               set PCRE2_ENDANCHORED
-             dfa_restart               set PCRE2_DFA_RESTART
-             dfa_shortest              set PCRE2_DFA_SHORTEST
-             no_jit                    set PCRE2_NO_JIT
-             no_utf_check              set PCRE2_NO_UTF_CHECK
-             notbol                    set PCRE2_NOTBOL
-             notempty                  set PCRE2_NOTEMPTY
-             notempty_atstart          set PCRE2_NOTEMPTY_ATSTART
-             noteol                    set PCRE2_NOTEOL
-             partial_hard (or ph)      set PCRE2_PARTIAL_HARD
-             partial_soft (or ps)      set PCRE2_PARTIAL_SOFT
-
-       The  partial matching modifiers are provided with abbreviations because
+             anchored                   set PCRE2_ANCHORED
+             endanchored                set PCRE2_ENDANCHORED
+             dfa_restart                set PCRE2_DFA_RESTART
+             dfa_shortest               set PCRE2_DFA_SHORTEST
+             disable_recurseloop_check  set PCRE2_DISABLE_RECURSELOOP_CHECK
+             no_jit                     set PCRE2_NO_JIT
+             no_utf_check               set PCRE2_NO_UTF_CHECK
+             notbol                     set PCRE2_NOTBOL
+             notempty                   set PCRE2_NOTEMPTY
+             notempty_atstart           set PCRE2_NOTEMPTY_ATSTART
+             noteol                     set PCRE2_NOTEOL
+             partial_hard (or ph)       set PCRE2_PARTIAL_HARD
+             partial_soft (or ps)       set PCRE2_PARTIAL_SOFT
+
+       The partial matching modifiers are provided with abbreviations  because
        they appear frequently in tests.
 
-       If the posix or posix_nosub modifier was present on the pattern,  caus-
+       If  the posix or posix_nosub modifier was present on the pattern, caus-
        ing the POSIX wrapper API to be used, the only option-setting modifiers
        that have any effect are notbol, notempty, and noteol, causing REG_NOT-
-       BOL,  REG_NOTEMPTY,  and  REG_NOTEOL,  respectively,  to  be  passed to
+       BOL, REG_NOTEMPTY,  and  REG_NOTEOL,  respectively,  to  be  passed  to
        regexec(). The other modifiers are ignored, with a warning message.
 
-       There is one additional modifier that can be used with the POSIX  wrap-
+       There  is one additional modifier that can be used with the POSIX wrap-
        per. It is ignored (with a warning) if used for non-POSIX matching.
 
              posix_startend=[:]
 
-       This  causes  the  subject  string  to be passed to regexec() using the
-       REG_STARTEND option, which uses offsets to specify which  part  of  the
-       string  is  searched.  If  only  one number is given, the end offset is
-       passed as the end of the subject string. For more detail  of  REG_STAR-
-       TEND,  see the pcre2posix documentation. If the subject string contains
-       binary zeros (coded as escapes such as \x{00}  because  pcre2test  does
+       This causes the subject string to be  passed  to  regexec()  using  the
+       REG_STARTEND  option,  which  uses offsets to specify which part of the
+       string is searched. If only one number is  given,  the  end  offset  is
+       passed  as  the end of the subject string. For more detail of REG_STAR-
+       TEND, see the pcre2posix documentation. If the subject string  contains
+       binary  zeros  (coded  as escapes such as \x{00} because pcre2test does
        not support actual binary zeros in its input), you must use posix_star-
        tend to specify its length.
 
@@ -1116,6 +1155,7 @@ SUBJECT MODIFIERS
              get=       extract captured substring
              getall                     extract all captured substrings
          /g  global                     global matching
+             heapframes_size            show match data heapframes size
              heap_limit=             set a limit on heap memory (Kbytes)
              jitstack=               set size of JIT stack
              mark                       show mark values
@@ -1144,13 +1184,13 @@ SUBJECT MODIFIERS
              zero_terminate             pass the subject as zero-terminated
 
        The effects of these modifiers are described in the following sections.
-       When  matching  via the POSIX wrapper API, the aftertext, allaftertext,
-       and ovector subject modifiers work as described below. All other  modi-
+       When matching via the POSIX wrapper API, the  aftertext,  allaftertext,
+       and  ovector subject modifiers work as described below. All other modi-
        fiers are either ignored, with a warning message, or cause an error.
 
    Showing more text
 
-       The  aftertext modifier requests that as well as outputting the part of
+       The aftertext modifier requests that as well as outputting the part  of
        the subject string that matched the entire pattern, pcre2test should in
        addition output the remainder of the subject string. This is useful for
        tests where the subject contains multiple copies of the same substring.
@@ -1166,7 +1206,7 @@ SUBJECT MODIFIERS
        message). Setting this modifier affects the output if there is a  look-
        behind  at  the start of a match, or, for a complete match, a lookahead
        at the end, or if \K is used in the pattern. Characters that precede or
-       follow  the start and end of the actual match are indicated in the out-
+       follow the start and end of the actual match are indicated in the  out-
        put by '<' or '>' characters underneath them.  Here is an example:
 
            re> /(?<=pqr)abc(?=xyz)/
@@ -1177,16 +1217,16 @@ SUBJECT MODIFIERS
          Partial match: pqrabcxy
                         <<<
 
-       The first, complete match shows that the matched string is "abc",  with
-       the  preceding  and  following strings "pqr" and "xyz" having been con-
-       sulted during the match (when processing the assertions).  The  partial
+       The  first, complete match shows that the matched string is "abc", with
+       the preceding and following strings "pqr" and "xyz"  having  been  con-
+       sulted  during  the match (when processing the assertions). The partial
        match can indicate only the preceding string.
 
-       The  startchar  modifier  requests  that the starting character for the
-       match be indicated, if it is different to  the  start  of  the  matched
+       The startchar modifier requests that the  starting  character  for  the
+       match  be  indicated,  if  it  is different to the start of the matched
        string. The only time when this occurs is when \K has been processed as
        part of the match. In this situation, the output for the matched string
-       is  displayed  from  the  starting  character instead of from the match
+       is displayed from the starting character  instead  of  from  the  match
        point, with circumflex characters under the earlier characters. For ex-
        ample:
 
@@ -1203,35 +1243,35 @@ SUBJECT MODIFIERS
        The allcaptures modifier requests that the values of all potential cap-
        tured parentheses be output after a match. By default, only those up to
        the highest one actually used in the match are output (corresponding to
-       the  return  code from pcre2_match()). Groups that did not take part in
-       the match are output as "". This modifier is  not  relevant  for
-       DFA  matching (which does no capturing) and does not apply when replace
+       the return code from pcre2_match()). Groups that did not take  part  in
+       the  match  are  output as "". This modifier is not relevant for
+       DFA matching (which does no capturing) and does not apply when  replace
        is specified; it is ignored, with a warning message, if present.
 
    Showing the entire ovector, for all outcomes
 
        The allvector modifier requests that the entire ovector be shown, what-
        ever the outcome of the match. Compare allcaptures, which shows only up
-       to the maximum number of capture groups for the pattern, and then  only
-       for  a successful complete non-DFA match. This modifier, which acts af-
-       ter any match result, and also for DFA matching, provides  a  means  of
-       checking  that there are no unexpected modifications to ovector fields.
-       Before each match attempt, the ovector is filled with a special  value,
-       and  if  this  is  found  in  both  elements of a capturing pair, "" is output. After a successful  match,  this  applies  to  all
-       groups  after the maximum capture group for the pattern. In other cases
-       it applies to the entire ovector. After a partial match, the first  two
-       elements  are  the only ones that should be set. After a DFA match, the
-       amount of ovector that is used depends on the number  of  matches  that
+       to  the maximum number of capture groups for the pattern, and then only
+       for a successful complete non-DFA match. This modifier, which acts  af-
+       ter  any  match  result, and also for DFA matching, provides a means of
+       checking that there are no unexpected modifications to ovector  fields.
+       Before  each match attempt, the ovector is filled with a special value,
+       and if this is found in  both  elements  of  a  capturing  pair,  ""  is  output.  After  a  successful match, this applies to all
+       groups after the maximum capture group for the pattern. In other  cases
+       it  applies to the entire ovector. After a partial match, the first two
+       elements are the only ones that should be set. After a DFA  match,  the
+       amount  of  ovector  that is used depends on the number of matches that
        were found.
 
    Testing pattern callouts
 
-       A  callout function is supplied when pcre2test calls the library match-
-       ing functions, unless callout_none is specified. Its behaviour  can  be
-       controlled  by  various  modifiers  listed above whose names begin with
-       callout_. Details are given in the section entitled  "Callouts"  below.
-       Testing  callouts  from  pcre2_substitute()  is described separately in
+       A callout function is supplied when pcre2test calls the library  match-
+       ing  functions,  unless callout_none is specified. Its behaviour can be
+       controlled by various modifiers listed above  whose  names  begin  with
+       callout_.  Details  are given in the section entitled "Callouts" below.
+       Testing callouts from pcre2_substitute()  is  described  separately  in
        "Testing the substitution function" below.
 
    Finding all matches in a string
@@ -1281,26 +1321,26 @@ SUBJECT MODIFIERS
 
    Testing the substitution function
 
-       If  the  replace  modifier  is  set, the pcre2_substitute() function is
-       called instead of one of the matching functions (or after one  call  of
-       pcre2_match()  in  the case of PCRE2_SUBSTITUTE_MATCHED). Note that re-
-       placement strings cannot contain commas, because a comma signifies  the
-       end  of  a  modifier. This is not thought to be an issue in a test pro-
+       If the replace modifier is  set,  the  pcre2_substitute()  function  is
+       called  instead  of one of the matching functions (or after one call of
+       pcre2_match() in the case of PCRE2_SUBSTITUTE_MATCHED). Note  that  re-
+       placement  strings cannot contain commas, because a comma signifies the
+       end of a modifier. This is not thought to be an issue in  a  test  pro-
        gram.
 
-       Specifying a completely empty replacement string  disables  this  modi-
-       fier.   However, it is possible to specify an empty replacement by pro-
-       viding a buffer length, as described below, for an otherwise empty  re-
+       Specifying  a  completely  empty replacement string disables this modi-
+       fier.  However, it is possible to specify an empty replacement by  pro-
+       viding  a buffer length, as described below, for an otherwise empty re-
        placement.
 
-       Unlike  subject strings, pcre2test does not process replacement strings
-       for escape sequences. In UTF mode, a replacement string is  checked  to
-       see  if it is a valid UTF-8 string. If so, it is correctly converted to
-       a UTF string of the appropriate code unit width. If it is not  a  valid
-       UTF-8  string, the individual code units are copied directly. This pro-
+       Unlike subject strings, pcre2test does not process replacement  strings
+       for  escape  sequences. In UTF mode, a replacement string is checked to
+       see if it is a valid UTF-8 string. If so, it is correctly converted  to
+       a  UTF  string of the appropriate code unit width. If it is not a valid
+       UTF-8 string, the individual code units are copied directly. This  pro-
        vides a means of passing an invalid UTF-8 string for testing purposes.
 
-       The following modifiers set options (in additional to the normal  match
+       The  following modifiers set options (in additional to the normal match
        options) for pcre2_substitute():
 
          global                      PCRE2_SUBSTITUTE_GLOBAL
@@ -1314,8 +1354,8 @@ SUBJECT MODIFIERS
 
        See the pcre2api documentation for details of these options.
 
-       After  a  successful  substitution, the modified string is output, pre-
-       ceded by the number of replacements. This may be zero if there were  no
+       After a successful substitution, the modified string  is  output,  pre-
+       ceded  by the number of replacements. This may be zero if there were no
        matches. Here is a simple example of a substitution test:
 
          /abc/replace=xxx
@@ -1324,12 +1364,12 @@ SUBJECT MODIFIERS
              =abc=abc=\=global
           2: =xxx=xxx=
 
-       Subject  and replacement strings should be kept relatively short (fewer
-       than 256 characters) for substitution tests, as fixed-size buffers  are
-       used.  To  make it easy to test for buffer overflow, if the replacement
-       string starts with a number in square brackets, that number  is  passed
-       to  pcre2_substitute()  as  the size of the output buffer, with the re-
-       placement string starting at the next character.  Here  is  an  example
+       Subject and replacement strings should be kept relatively short  (fewer
+       than  256 characters) for substitution tests, as fixed-size buffers are
+       used. To make it easy to test for buffer overflow, if  the  replacement
+       string  starts  with a number in square brackets, that number is passed
+       to pcre2_substitute() as the size of the output buffer,  with  the  re-
+       placement  string  starting  at  the next character. Here is an example
        that tests the edge case:
 
          /abc/
@@ -1339,12 +1379,12 @@ SUBJECT MODIFIERS
          Failed: error -47: no more memory
 
        The  default  action  of  pcre2_substitute()  is  to  return  PCRE2_ER-
-       ROR_NOMEMORY when the output buffer  is  too  small.  However,  if  the
-       PCRE2_SUBSTITUTE_OVERFLOW_LENGTH  option  is  set (by using the substi-
+       ROR_NOMEMORY  when  the  output  buffer  is  too small. However, if the
+       PCRE2_SUBSTITUTE_OVERFLOW_LENGTH option is set (by  using  the  substi-
        tute_overflow_length  modifier),  pcre2_substitute()  continues  to  go
-       through  the  motions  of  matching and substituting (but not doing any
-       callouts), in order to compute the size of  buffer  that  is  required.
-       When  this  happens,  pcre2test shows the required buffer length (which
+       through the motions of matching and substituting  (but  not  doing  any
+       callouts),  in  order  to  compute the size of buffer that is required.
+       When this happens, pcre2test shows the required  buffer  length  (which
        includes space for the trailing zero) as part of the error message. For
        example:
 
@@ -1353,7 +1393,7 @@ SUBJECT MODIFIERS
          Failed: error -47: no more memory: 10 code units are needed
 
        A replacement string is ignored with POSIX and DFA matching. Specifying
-       partial matching provokes an error return  ("bad  option  value")  from
+       partial  matching  provokes  an  error return ("bad option value") from
        pcre2_substitute().
 
    Testing substitute callouts
@@ -1362,7 +1402,7 @@ SUBJECT MODIFIERS
        tion is set up. The null_context modifier must not be set, because  the
        address  of the callout function is passed in a match context. When the
        callout function is called (after each substitution),  details  of  the
-       the input and output strings are output. For example:
+       input and output strings are output. For example:
 
          /abc/g,replace=<$0>,substitute_callout
              abcdefabcpqr
@@ -1372,7 +1412,7 @@ SUBJECT MODIFIERS
 
        The  first  number  on  each  callout line is the count of matches. The
        parenthesized number is the number of pairs that are set in the ovector
-       (that  is, one more than the number of capturing groups that were set).
+       (that is, one more than the number of capturing groups that were  set).
        Then are listed the offsets of the old substring, its contents, and the
        same for the replacement.
 
@@ -1405,35 +1445,35 @@ SUBJECT MODIFIERS
        JIT optimization is not being used. The value is a number of  kibibytes
        (units  of  1024  bytes). Setting zero reverts to the default of 32KiB.
        Providing a stack that is larger than the default is necessary only for
-       very  complicated  patterns.  If  jitstack is set non-zero on a subject
+       very complicated patterns. If jitstack is set  non-zero  on  a  subject
        line it overrides any value that was set on the pattern.
 
    Setting heap, match, and depth limits
 
-       The heap_limit, match_limit, and depth_limit modifiers set  the  appro-
-       priate  limits  in the match context. These values are ignored when the
+       The  heap_limit,  match_limit, and depth_limit modifiers set the appro-
+       priate limits in the match context. These values are ignored  when  the
        find_limits or find_limits_noheap modifier is specified.
 
    Finding minimum limits
 
-       If the find_limits modifier is present on  a  subject  line,  pcre2test
-       calls  the  relevant matching function several times, setting different
-       values   in   the    match    context    via    pcre2_set_heap_limit(),
-       pcre2_set_match_limit(),  or pcre2_set_depth_limit() until it finds the
-       smallest value for each parameter that allows  the  match  to  complete
+       If  the  find_limits  modifier  is present on a subject line, pcre2test
+       calls the relevant matching function several times,  setting  different
+       values    in    the    match    context   via   pcre2_set_heap_limit(),
+       pcre2_set_match_limit(), or pcre2_set_depth_limit() until it finds  the
+       smallest  value  for  each  parameter that allows the match to complete
        without a "limit exceeded" error. The match itself may succeed or fail.
        An alternative modifier, find_limits_noheap, omits the heap limit. This
-       is  used  in  the standard tests, because the minimum heap limit varies
-       between systems. If JIT is being used, only the match  limit  is  rele-
+       is used in the standard tests, because the minimum  heap  limit  varies
+       between  systems.  If  JIT is being used, only the match limit is rele-
        vant, and the other two are automatically omitted.
 
        When using this modifier, the pattern should not contain any limit set-
        tings such as (*LIMIT_MATCH=...)  within  it.  If  such  a  setting  is
        present and is lower than the minimum matching value, the minimum value
-       cannot be found because pcre2_set_match_limit() etc. are only  able  to
+       cannot  be  found because pcre2_set_match_limit() etc. are only able to
        reduce the value of an in-pattern limit; they cannot increase it.
 
-       For  non-DFA  matching,  the minimum depth_limit number is a measure of
+       For non-DFA matching, the minimum depth_limit number is  a  measure  of
        how much nested backtracking happens (that is, how deeply the pattern's
        tree  is  searched).  In the case of DFA matching, depth_limit controls
        the depth of recursive calls of the internal function that is used  for
@@ -1457,22 +1497,38 @@ SUBJECT MODIFIERS
 
 
        The mark modifier causes the names from backtracking control verbs that
-       are returned from calls to pcre2_match() to be displayed. If a mark  is
-       returned  for a match, non-match, or partial match, pcre2test shows it.
-       For a match, it is on a line by itself, tagged with  "MK:".  Otherwise,
+       are  returned from calls to pcre2_match() to be displayed. If a mark is
+       returned for a match, non-match, or partial match, pcre2test shows  it.
+       For  a  match, it is on a line by itself, tagged with "MK:". Otherwise,
        it is added to the non-match message.
 
    Showing memory usage
 
-       The  memory modifier causes pcre2test to log the sizes of all heap mem-
-       ory  allocation  and  freeing  calls  that  occur  during  a  call   to
-       pcre2_match()  or pcre2_dfa_match(). In the latter case, heap memory is
-       used only when a match requires more internal workspace  that  the  de-
-       fault  allocation  on the stack, so in many cases there will be no out-
-       put. No heap memory is allocated during matching  with  JIT.  For  this
+       The memory modifier causes pcre2test to log the sizes of all heap  mem-
+       ory   allocation  and  freeing  calls  that  occur  during  a  call  to
+       pcre2_match() or pcre2_dfa_match(). In the latter case, heap memory  is
+       used  only  when  a match requires more internal workspace that the de-
+       fault allocation on the stack, so in many cases there will be  no  out-
+       put.  No  heap  memory  is allocated during matching with JIT. For this
        modifier to work, the null_context modifier must not be set on both the
        pattern and the subject, though it can be set on one or the other.
 
+   Showing the heap frame overall vector size
+
+       The  heapframes_size   modifier   is   relevant   for   matches   using
+       pcre2_match() without JIT. After a match has run (whether successful or
+       not)  the  size,  in bytes, of the allocated heap frames vector that is
+       left attached to the match data block is shown. If the matching  action
+       involved  several  calls to pcre2_match() (for example, global matching
+       or for timing) only the final value is shown.
+
+       This modifier is ignored, with a warning, for POSIX  or  DFA  matching.
+       JIT matching does not use the heap frames vector, so the size is always
+       zero,  unless there was a previous non-JIT match. Note that specifing a
+       size of zero for the output vector (see below) causes pcre2test to free
+       its match data block (and associated heap frames vector) and allocate a
+       new one.
+
    Setting a starting offset
 
        The offset modifier sets an offset  in  the  subject  string  at  which
@@ -1490,16 +1546,16 @@ SUBJECT MODIFIERS
 
        The  ovector  modifier applies only to the subject line in which it ap-
        pears, though of course it can also be used to set a default in a #sub-
-       ject  command.  It  specifies  the  number of pairs of offsets that are
+       ject command. It specifies the number of  pairs  of  offsets  that  are
        available for storing matching information. The default is 15.
 
-       A value of zero is useful when testing the POSIX API because it  causes
+       A  value of zero is useful when testing the POSIX API because it causes
        regexec() to be called with a NULL capture vector. When not testing the
        POSIX API, a value of  zero  is  used  to  cause  pcre2_match_data_cre-
-       ate_from_pattern()  to  be  called, in order to create a match block of
-       exactly the right size for the pattern. (It is not possible to create a
-       match  block  with  a zero-length ovector; there is always at least one
-       pair of offsets.)
+       ate_from_pattern()  to  be called, in order to create a new match block
+       of exactly the right size for the pattern. (It is not possible to  cre-
+       ate  a match block with a zero-length ovector; there is always at least
+       one pair of offsets.) The old match data block is freed.
 
    Passing the subject as zero-terminated
 
@@ -1531,24 +1587,24 @@ THE ALTERNATIVE MATCHING FUNCTION
 
        By  default,  pcre2test  uses  the  standard  PCRE2  matching function,
        pcre2_match() to match each subject line. PCRE2 also supports an alter-
-       native  matching  function, pcre2_dfa_match(), which operates in a dif-
-       ferent way, and has some restrictions. The differences between the  two
+       native matching function, pcre2_dfa_match(), which operates in  a  dif-
+       ferent  way, and has some restrictions. The differences between the two
        functions are described in the pcre2matching documentation.
 
-       If  the dfa modifier is set, the alternative matching function is used.
-       This function finds all possible matches at a given point in  the  sub-
-       ject.  If,  however, the dfa_shortest modifier is set, processing stops
-       after the first match is found. This is always  the  shortest  possible
+       If the dfa modifier is set, the alternative matching function is  used.
+       This  function  finds all possible matches at a given point in the sub-
+       ject. If, however, the dfa_shortest modifier is set,  processing  stops
+       after  the  first  match is found. This is always the shortest possible
        match.
 
 
 DEFAULT OUTPUT FROM pcre2test
 
-       This  section  describes  the output when the normal matching function,
+       This section describes the output when the  normal  matching  function,
        pcre2_match(), is being used.
 
-       When a match succeeds, pcre2test outputs  the  list  of  captured  sub-
-       strings,  starting  with number 0 for the string that matched the whole
+       When  a  match  succeeds,  pcre2test  outputs the list of captured sub-
+       strings, starting with number 0 for the string that matched  the  whole
        pattern.  Otherwise, it outputs "No match" when the return is PCRE2_ER-
        ROR_NOMATCH,  or  "Partial  match:"  followed by the partially matching
        substring when the return is PCRE2_ERROR_PARTIAL. (Note  that  this  is
@@ -1557,8 +1613,8 @@ DEFAULT OUTPUT FROM pcre2test
        assertion, \K, \b, or \B was involved.)
 
        For any other return, pcre2test outputs the PCRE2 negative error number
-       and a short descriptive phrase. If the error is  a  failed  UTF  string
-       check,  the  code  unit offset of the start of the failing character is
+       and  a  short  descriptive  phrase. If the error is a failed UTF string
+       check, the code unit offset of the start of the  failing  character  is
        also output. Here is an example of an interactive pcre2test run.
 
          $ pcre2test
@@ -1590,8 +1646,8 @@ DEFAULT OUTPUT FROM pcre2test
        If  the strings contain any non-printing characters, they are output as
        \xhh escapes if the value is less than 256 and UTF  mode  is  not  set.
        Otherwise they are output as \x{hh...} escapes. See below for the defi-
-       nition of non-printing characters. If the aftertext  modifier  is  set,
-       the  output  for substring 0 is followed by the the rest of the subject
+       nition  of  non-printing  characters. If the aftertext modifier is set,
+       the output for substring 0 is followed  by  the  rest  of  the  subject
        string, identified by "0+" like this:
 
            re> /cat/aftertext
@@ -1620,7 +1676,7 @@ DEFAULT OUTPUT FROM pcre2test
          Error -24 (bad offset value)
 
        Note that whereas patterns can be continued over several lines (a plain
-       ">" prompt is used for continuations), subject lines may  not.  However
+       ">"  prompt  is used for continuations), subject lines may not. However
        newlines can be included in a subject by means of the \n escape (or \r,
        \r\n, etc., depending on the newline sequence setting).
 
@@ -1628,7 +1684,7 @@ DEFAULT OUTPUT FROM pcre2test
 OUTPUT FROM THE ALTERNATIVE MATCHING FUNCTION
 
        When the alternative matching function, pcre2_dfa_match(), is used, the
-       output  consists  of  a list of all the matches that start at the first
+       output consists of a list of all the matches that start  at  the  first
        point in the subject where there is at least one match. For example:
 
            re> /(tang|tangerine|tan)/
@@ -1637,9 +1693,9 @@ OUTPUT FROM THE ALTERNATIVE MATCHING FUNCTION
           1: tang
           2: tan
 
-       Using the normal matching function on this data finds only "tang".  The
-       longest  matching string is always given first (and numbered zero). Af-
-       ter a PCRE2_ERROR_PARTIAL return, the output is "Partial match:",  fol-
+       Using  the normal matching function on this data finds only "tang". The
+       longest matching string is always given first (and numbered zero).  Af-
+       ter  a PCRE2_ERROR_PARTIAL return, the output is "Partial match:", fol-
        lowed by the partially matching substring. Note that this is the entire
        substring that was inspected during the partial match; it  may  include
        characters before the actual match start if a lookbehind assertion, \b,
@@ -1666,7 +1722,7 @@ RESTARTING AFTER A PARTIAL MATCH
 
        When  the  alternative matching function has given the PCRE2_ERROR_PAR-
        TIAL return, indicating that the subject partially matched the pattern,
-       you  can restart the match with additional subject data by means of the
+       you can restart the match with additional subject data by means of  the
        dfa_restart modifier. For example:
 
            re> /^\d?\d(jan|feb|mar|apr|may|jun|jul|aug|sep|oct|nov|dec)\d\d$/
@@ -1675,7 +1731,7 @@ RESTARTING AFTER A PARTIAL MATCH
          data> n05\=dfa,dfa_restart
           0: n05
 
-       For further information about partial matching,  see  the  pcre2partial
+       For  further  information  about partial matching, see the pcre2partial
        documentation.
 
 
@@ -1684,7 +1740,7 @@ CALLOUTS
        If the pattern contains any callout requests, pcre2test's callout func-
        tion is called during matching unless callout_none is  specified.  This
        works with both matching functions, and with JIT, though there are some
-       differences in behaviour. The output for callouts with numerical  argu-
+       differences  in behaviour. The output for callouts with numerical argu-
        ments and those with string arguments is slightly different.
 
    Callouts with numerical arguments
@@ -1705,7 +1761,7 @@ CALLOUTS
 
        Callouts numbered 255 are assumed to be automatic callouts, inserted as
        a result of the auto_callout pattern modifier. In this case, instead of
-       showing the callout number, the offset in the pattern,  preceded  by  a
+       showing  the  callout  number, the offset in the pattern, preceded by a
        plus, is output. For example:
 
            re> /\d?[A-E]\*/auto_callout
@@ -1732,9 +1788,9 @@ CALLOUTS
          +12 ^  ^
           0: abc
 
-       The  mark  changes between matching "a" and "b", but stays the same for
-       the rest of the match, so nothing more is output. If, as  a  result  of
-       backtracking,  the  mark  reverts to being unset, the text "" is
+       The mark changes between matching "a" and "b", but stays the  same  for
+       the  rest  of  the match, so nothing more is output. If, as a result of
+       backtracking, the mark reverts to being unset, the  text  ""  is
        output.
 
    Callouts with string arguments
@@ -1768,14 +1824,14 @@ CALLOUTS
        ever shown.
 
        The normal callout output, showing the callout number or pattern offset
-       (as described above) is suppressed if the callout_no_where modifier  is
+       (as  described above) is suppressed if the callout_no_where modifier is
        set.
 
-       When  using  the  interpretive  matching function pcre2_match() without
-       JIT, setting the callout_extra modifier causes additional  output  from
-       pcre2test's  callout function to be generated. For the first callout in
-       a match attempt at a new starting position in the subject,  "New  match
-       attempt"  is output. If there has been a backtrack since the last call-
+       When using the interpretive  matching  function  pcre2_match()  without
+       JIT,  setting  the callout_extra modifier causes additional output from
+       pcre2test's callout function to be generated. For the first callout  in
+       a  match  attempt at a new starting position in the subject, "New match
+       attempt" is output. If there has been a backtrack since the last  call-
        out (or start of matching if this is the first callout), "Backtrack" is
        output,  followed  by  "No other matching paths" if the backtrack ended
        the previous match attempt. For example:
@@ -1831,8 +1887,8 @@ CALLOUTS
        matching to continue. The callout_fail modifier can be given one or two
        numbers. If there is only one number, 1 is returned instead of 0 (caus-
        ing matching to backtrack) when a callout of that number is reached. If
-       two  numbers  (:)  are  given,  1 is returned when callout  is
-       reached and there have been at least   callouts.  The  callout_error
+       two numbers (:) are given, 1 is  returned  when  callout    is
+       reached  and  there  have been at least  callouts. The callout_error
        modifier is similar, except that PCRE2_ERROR_CALLOUT is returned, caus-
        ing the entire matching process to be aborted. If both these  modifiers
        are  set  for  the same callout number, callout_error takes precedence.
@@ -1846,7 +1902,7 @@ CALLOUTS
        function.
 
        Inserting callouts can be helpful when using pcre2test to check compli-
-       cated regular expressions. For further information about callouts,  see
+       cated  regular expressions. For further information about callouts, see
        the pcre2callout documentation.
 
 
@@ -1865,9 +1921,9 @@ NON-PRINTING CHARACTERS
 
 SAVING AND RESTORING COMPILED PATTERNS
 
-       It  is  possible  to  save  compiled patterns on disc or elsewhere, and
-       reload them later, subject to a number of restrictions. JIT data cannot
-       be  saved.  The host on which the patterns are reloaded must be running
+       It is possible to save compiled patterns on disc or elsewhere, and  re-
+       load  them  later, subject to a number of restrictions. JIT data cannot
+       be saved. The host on which the patterns are reloaded must  be  running
        the same version of PCRE2, with the same code unit width, and must also
        have  the  same  endianness,  pointer width and PCRE2_SIZE type. Before
        compiled patterns can be saved they must be serialized, that  is,  con-
@@ -1889,9 +1945,9 @@ SAVING AND RESTORING COMPILED PATTERNS
        piled, it is pushed onto a stack of compiled  patterns,  and  pcre2test
        expects  the next line to contain a new pattern (or command) instead of
        a subject line. By contrast, the pushcopy modifier causes a copy of the
-       compiled  pattern to be stacked, leaving the original available for im-
-       mediate matching. By using push and/or pushcopy, a number  of  patterns
-       can  be  compiled  and  retained. These modifiers are incompatible with
+       compiled pattern to be stacked, leaving the original available for  im-
+       mediate  matching.  By using push and/or pushcopy, a number of patterns
+       can be compiled and retained. These  modifiers  are  incompatible  with
        posix, and control modifiers that act at match time are ignored (with a
        message)  for the stacked patterns. The jitverify modifier applies only
        at compile time.
@@ -1901,21 +1957,21 @@ SAVING AND RESTORING COMPILED PATTERNS
          #save 
 
        causes all the stacked patterns to be serialized and the result written
-       to  the named file. Afterwards, all the stacked patterns are freed. The
+       to the named file. Afterwards, all the stacked patterns are freed.  The
        command
 
          #load 
 
-       reads the data in the file, and then arranges for it to  be  de-serial-
-       ized,  with the resulting compiled patterns added to the pattern stack.
-       The pattern on the top of the stack can be retrieved by the  #pop  com-
-       mand,  which  must  be  followed  by  lines  of subjects that are to be
-       matched with the pattern, terminated as usual by an empty line  or  end
-       of  file.  This  command  may be followed by a modifier list containing
-       only control modifiers that act after a pattern has been  compiled.  In
-       particular,  hex,  posix,  posix_nosub,  push, and pushcopy are not al-
-       lowed, nor are any option-setting modifiers.  The  JIT  modifiers  are,
-       however  permitted.  Here is an example that saves and reloads two pat-
+       reads  the  data in the file, and then arranges for it to be de-serial-
+       ized, with the resulting compiled patterns added to the pattern  stack.
+       The  pattern  on the top of the stack can be retrieved by the #pop com-
+       mand, which must be followed by  lines  of  subjects  that  are  to  be
+       matched  with  the pattern, terminated as usual by an empty line or end
+       of file. This command may be followed by  a  modifier  list  containing
+       only  control  modifiers that act after a pattern has been compiled. In
+       particular, hex, posix, posix_nosub, push, and  pushcopy  are  not  al-
+       lowed,  nor  are  any option-setting modifiers.  The JIT modifiers are,
+       however permitted. Here is an example that saves and reloads  two  pat-
        terns.
 
          /abc/push
@@ -1928,10 +1984,10 @@ SAVING AND RESTORING COMPILED PATTERNS
          #pop jit,bincode
          abc
 
-       If jitverify is used with #pop, it does not  automatically  imply  jit,
+       If  jitverify  is  used with #pop, it does not automatically imply jit,
        which is different behaviour from when it is used on a pattern.
 
-       The  #popcopy  command is analogous to the pushcopy modifier in that it
+       The #popcopy command is analogous to the pushcopy modifier in  that  it
        makes current a copy of the topmost stack pattern, leaving the original
        still on the stack.
 
@@ -1951,5 +2007,8 @@ AUTHOR
 
 REVISION
 
-       Last updated: 27 July 2022
-       Copyright (c) 1997-2022 University of Cambridge.
+       Last updated: 24 April 2024
+       Copyright (c) 1997-2024 University of Cambridge.
+
+
+PCRE 10.44                       24 April 2024                    PCRE2TEST(1)
diff --git a/pcre2/doc/pcre2unicode.3 b/pcre2/doc/pcre2unicode.3
index e7e37a3..eb613f4 100644
--- a/pcre2/doc/pcre2unicode.3
+++ b/pcre2/doc/pcre2unicode.3
@@ -1,4 +1,4 @@
-.TH PCRE2UNICODE 3 "22 December 2021" "PCRE2 10.40"
+.TH PCRE2UNICODE 3 "04 February 2023" "PCRE2 10.43"
 .SH NAME
 PCRE - Perl-compatible regular expressions (revised API)
 .SH "UNICODE AND UTF SUPPORT"
@@ -42,9 +42,11 @@ When PCRE2 is built with Unicode support, the escape sequences \ep{..},
 \eP{..}, and \eX can be used. This is not dependent on the PCRE2_UTF setting.
 The Unicode properties that can be tested are a subset of those that Perl
 supports. Currently they are limited to the general category properties such as
-Lu for an upper case letter or Nd for a decimal number, the Unicode script
-names such as Arabic or Han, Bidi_Class, Bidi_Control, and the derived
-properties Any and LC (synonym L&). Full lists are given in the
+Lu for an upper case letter or Nd for a decimal number, the derived properties
+Any and LC (synonym L&), the Unicode script names such as Arabic or Han,
+Bidi_Class, Bidi_Control, and a few binary properties.
+.P
+The full lists are given in the
 .\" HREF
 \fBpcre2pattern\fP
 .\"
@@ -107,8 +109,8 @@ and \eB, because they are defined in terms of \ew and \eW. If you want
 to test for a wider sense of, say, "digit", you can use explicit Unicode
 property tests such as \ep{Nd}. Alternatively, if you set the PCRE2_UCP option,
 the way that the character escapes work is changed so that Unicode properties
-are used to determine which characters match. There are more details in the
-section on
+are used to determine which characters match, though there are some options
+that suppress this for individual escapes. For details see the section on
 .\" HTML 
 .\" 
 generic character types
@@ -119,12 +121,13 @@ in the
 .\"
 documentation.
 .P
-Similarly, characters that match the POSIX named character classes are all
-low-valued characters, unless the PCRE2_UCP option is set.
+Like the escapes, characters that match the POSIX named character classes are
+all low-valued characters unless the PCRE2_UCP option is set, but there is an
+option to override this.
 .P
-However, the special horizontal and vertical white space matching escapes (\eh,
-\eH, \ev, and \eV) do match all the appropriate Unicode characters, whether or
-not PCRE2_UCP is set.
+In contrast to the character escapes and character classes, the special
+horizontal and vertical white space escapes (\eh, \eH, \ev, and \eV) do match
+all the appropriate Unicode characters, whether or not PCRE2_UCP is set.
 .
 .
 .SH "UNICODE CASE-EQUIVALENCE"
@@ -137,6 +140,13 @@ lookup is used for speed. A few Unicode characters such as Greek sigma have
 more than two code points that are case-equivalent, and these are treated
 specially. Setting PCRE2_UCP without PCRE2_UTF allows Unicode-style case
 processing for non-UTF character encodings such as UCS-2.
+.P
+There are two ASCII characters (S and K) that, in addition to their ASCII lower
+case equivalents, have a non-ASCII one as well (long S and Kelvin sign).
+Recognition of these non-ASCII characters as case-equivalent to their ASCII
+counterparts can be disabled by setting the PCRE2_EXTRA_CASELESS_RESTRICT
+option. When this is set, all characters in a case equivalence must either be
+ASCII or non-ASCII; there can be no mixing.
 .
 .
 .\" HTML 
@@ -409,6 +419,13 @@ not by \fBpcre2_dfa_match()\fP. When PCRE2_MATCH_INVALID_UTF is set, it forces
 PCRE2_UTF to be set as well. Note, however, that the pattern itself must be a
 valid UTF string.
 .P
+If you do not set PCRE2_MATCH_INVALID_UTF when calling \fBpcre2_compile\fP, and
+you are not certain that your subject strings are valid UTF sequences, you
+should not make use of the JIT "fast path" function \fBpcre2_jit_match()\fP
+because it bypasses sanity checks, including the one for UTF validity. An
+invalid string may cause undefined behaviour, including looping, crashing, or
+giving the wrong answer.
+.P
 Setting PCRE2_MATCH_INVALID_UTF does not affect what \fBpcre2_compile()\fP
 generates, but if \fBpcre2_jit_compile()\fP is subsequently called, it does
 generate different code. If JIT is not used, the option affects the behaviour
@@ -442,6 +459,11 @@ would match an instance of WORD that is surrounded by invalid UTF code units.
 Using PCRE2_MATCH_INVALID_UTF, an application can run matches on arbitrary
 data, knowing that any matched strings that are returned are valid UTF. This
 can be useful when searching for UTF text in executable or other binary files.
+.P
+Note, however, that the 16-bit and 32-bit PCRE2 libraries process strings as
+sequences of uint16_t or uint32_t code points. They cannot find valid UTF
+sequences within an arbitrary string of bytes unless such sequences are
+suitably aligned.
 .
 .
 .SH AUTHOR
@@ -458,6 +480,6 @@ Cambridge, England.
 .rs
 .sp
 .nf
-Last updated: 22 December 2021
-Copyright (c) 1997-2021 University of Cambridge.
+Last updated: 12 October 2023
+Copyright (c) 1997-2023 University of Cambridge.
 .fi
diff --git a/pcre2/libpcre2-posix.pc.in b/pcre2/libpcre2-posix.pc.in
index 758c306..2f1e8f1 100644
--- a/pcre2/libpcre2-posix.pc.in
+++ b/pcre2/libpcre2-posix.pc.in
@@ -9,5 +9,5 @@ Name: libpcre2-posix
 Description: Posix compatible interface to libpcre2-8
 Version: @PACKAGE_VERSION@
 Libs: -L${libdir} -lpcre2-posix@LIB_POSTFIX@
-Cflags: -I${includedir} @PCRE2_STATIC_CFLAG@
+Cflags: -I${includedir} @PCRE2POSIX_CFLAG@
 Requires.private: libpcre2-8
diff --git a/pcre2/m4/pcre2_visibility.m4 b/pcre2/m4/pcre2_visibility.m4
index 480f2ee..c025d5f 100644
--- a/pcre2/m4/pcre2_visibility.m4
+++ b/pcre2/m4/pcre2_visibility.m4
@@ -73,11 +73,12 @@ AC_DEFUN([PCRE2_VISIBILITY],
       VISIBILITY_CFLAGS="-fvisibility=hidden"
       VISIBILITY_CXXFLAGS="-fvisibility=hidden -fvisibility-inlines-hidden"
       HAVE_VISIBILITY=1
-      AC_DEFINE(PCRE2_EXP_DECL, [extern __attribute__ ((visibility ("default")))], [to make a symbol visible])
-      AC_DEFINE(PCRE2_EXP_DEFN, [__attribute__ ((visibility ("default")))], [to make a symbol visible])
-      AC_DEFINE(PCRE2POSIX_EXP_DECL, [extern __attribute__ ((visibility ("default")))], [to make a symbol visible])
-      AC_DEFINE(PCRE2POSIX_EXP_DEFN, [extern __attribute__ ((visibility ("default")))], [to make a symbol visible])
+      AC_DEFINE(PCRE2_EXPORT, [__attribute__ ((visibility ("default")))], [to make a symbol visible])
+    else
+      AC_DEFINE(PCRE2_EXPORT, [], [to make a symbol visible])
     fi
+  else
+    AC_DEFINE(PCRE2_EXPORT, [], [to make a symbol visible])
   fi
   AC_SUBST([VISIBILITY_CFLAGS])
   AC_SUBST([VISIBILITY_CXXFLAGS])
diff --git a/pcre2/maint/GenerateCommon.py b/pcre2/maint/GenerateCommon.py
index 03f9ac5..b1e61ba 100644
--- a/pcre2/maint/GenerateCommon.py
+++ b/pcre2/maint/GenerateCommon.py
@@ -16,32 +16,32 @@ import re
 #                             DATA LISTS
 # ---------------------------------------------------------------------------
 
-# BIDI classes in the DerivedBidiClass.txt file, with comments.
+# BIDI classes in the DerivedBidiClass.txt file, short and long identifiers.
 
 bidi_classes = [
-  'AL',  'Arabic letter',
-  'AN',  'Arabic number',
-  'B',   'Paragraph separator',
-  'BN',  'Boundary neutral',
-  'CS',  'Common separator',
-  'EN',  'European number',
-  'ES',  'European separator',
-  'ET',  'European terminator',
-  'FSI', 'First strong isolate',
-  'L',   'Left to right',
-  'LRE', 'Left to right embedding',
-  'LRI', 'Left to right isolate',
-  'LRO', 'Left to right override',
-  'NSM', 'Non-spacing mark',
-  'ON',  'Other neutral',
-  'PDF', 'Pop directional format',
-  'PDI', 'Pop directional isolate',
-  'R',   'Right to left',
-  'RLE', 'Right to left embedding',
-  'RLI', 'Right to left isolate',
-  'RLO', 'Right to left override',
-  'S',   'Segment separator',
-  'WS',  'White space'
+  'AL',  'Arabic_Letter',
+  'AN',  'Arabic_Number',
+  'B',   'Paragraph_Separator',
+  'BN',  'Boundary_Neutral',
+  'CS',  'Common_Separator',
+  'EN',  'European_Number',
+  'ES',  'European_Separator',
+  'ET',  'European_Terminator',
+  'FSI', 'First_Strong_Isolate',
+  'L',   'Left_To_Right',
+  'LRE', 'Left_To_Right_Embedding',
+  'LRI', 'Left_To_Right_Isolate',
+  'LRO', 'Left_To_Right_Override',
+  'NSM', 'Nonspacing_Mark',
+  'ON',  'Other_Neutral',
+  'PDF', 'Pop_Directional_Format',
+  'PDI', 'Pop_Directional_Isolate',
+  'R',   'Right_To_Left',
+  'RLE', 'Right_To_Left_Embedding',
+  'RLI', 'Right_To_Left_Isolate',
+  'RLO', 'Right_To_Left_Override',
+  'S',   'Segment_Separator',
+  'WS',  'White_Space'
   ]
 
 # Particular category property names, with comments. NOTE: If ever this list
@@ -139,7 +139,8 @@ def getbpropslist():
         if re.match(pat, bplast) != None:
           break
       else:
-        bplist.append(bplast)
+        if bplast not in bplist:
+          bplist.append(bplast)
 
     file.close()
 
@@ -204,7 +205,7 @@ def collect_property_names():
       if match_obj == None:
         continue
 
-      if match_obj.group(2) in bool_properties:
+      if match_obj.group(2) != match_obj.group(1) and match_obj.group(2) in bool_properties:
         if match_obj.group(3) == None:
           abbreviations[match_obj.group(2)] = (match_obj.group(1),)
         else:
@@ -294,7 +295,7 @@ def open_output(default):
   try:
     file = open(output_name, "w")
   except IOError:
-    print ("** Couldn't open %s" % output_name)
+    print("** Couldn't open %s" % output_name)
     sys.exit(1)
 
   script_name = sys.argv[0]
diff --git a/pcre2/maint/GenerateTest26.py b/pcre2/maint/GenerateTest26.py
index 2afdf25..64d5720 100755
--- a/pcre2/maint/GenerateTest26.py
+++ b/pcre2/maint/GenerateTest26.py
@@ -40,7 +40,7 @@ try:
   input_file = open(output_directory + "testinput26", "w")
   output_file = open(output_directory + "testoutput26", "w")
 except IOError:
-  print ("** Couldn't open output files")
+  print("** Couldn't open output files")
   sys.exit(1)
 
 write_both("# These tests are generated by maint/GenerateTest26.py, do not edit.\n\n")
diff --git a/pcre2/maint/GenerateUcd.py b/pcre2/maint/GenerateUcd.py
index 6081800..1bde718 100755
--- a/pcre2/maint/GenerateUcd.py
+++ b/pcre2/maint/GenerateUcd.py
@@ -109,6 +109,8 @@
 # 10-January-2022:   Addition of general Boolean property support
 # 12-January-2022:   Merge scriptx and bidiclass fields
 # 14-January-2022:   Enlarge Boolean property offset to 12 bits
+# 28-January-2023:   Remove ASCII "other case" from non-ASCII character that
+#                      are present in caseless sets.
 #
 # ----------------------------------------------------------------------------
 #
@@ -269,19 +271,27 @@ NOTACHAR = 0xffffffff
 # ---------------------------------------------------------------------------
 
 
-# Parse a line of Scripts.txt, GraphemeBreakProperty.txt, DerivedBidiClass.txt
-# or DerivedGeneralCategory.txt
+# Parse a line of Scripts.txt, GraphemeBreakProperty.txt or DerivedGeneralCategory.txt
 
 def make_get_names(enum):
   return lambda chardata: enum.index(chardata[1])
 
 
+# Parse a line of DerivedBidiClass.txt
+
+def get_bidi(chardata):
+  if len(chardata[1]) > 3:
+    return bidi_classes_long.index(chardata[1])
+  else:
+    return bidi_classes_short.index(chardata[1])
+
+
 # Parse a line of CaseFolding.txt
 
 def get_other_case(chardata):
   if chardata[1] == 'C' or chardata[1] == 'S':
     return int(chardata[2], 16) - int(chardata[0], 16)
-  return 0
+  return None
 
 
 # Parse a line of ScriptExtensions.txt
@@ -316,11 +326,16 @@ def read_table(file_name, get_value, default_value):
 
   table = [default_value] * MAX_UNICODE
   for line in file:
+    if file_base == 'DerivedBidiClass':
+      line = re.sub(r'# @missing: ', '', line)
+
     line = re.sub(r'#.*', '', line)
     chardata = list(map(str.strip, line.split(';')))
     if len(chardata) <= 1:
       continue
     value = get_value(chardata)
+    if value is None:
+      continue
     m = re.match(r'([0-9a-fA-F]+)(\.\.([0-9a-fA-F]+))?$', chardata[0])
     char = int(m.group(1), 16)
     if m.group(3) is None:
@@ -328,11 +343,8 @@ def read_table(file_name, get_value, default_value):
     else:
       last = int(m.group(3), 16)
     for i in range(char, last + 1):
-      # It is important not to overwrite a previously set value because in the
-      # CaseFolding file there are lines to be ignored (returning the default
-      # value of 0) which often come after a line which has already set data.
-      if table[i] == default_value:
-        table[i] = value
+      table[i] = value
+
   file.close()
   return table
 
@@ -506,7 +518,8 @@ unicode_version = ""
 # strings for use by GenerateUcpHeader. The comments are not wanted here, so
 # remove them.
 
-bidi_classes = bidi_classes[::2]
+bidi_classes_short = bidi_classes[::2]
+bidi_classes_long = bidi_classes[1::2]
 break_properties = break_properties[::2]
 category_names = category_names[::2]
 
@@ -516,7 +529,7 @@ script = read_table('Unicode.tables/Scripts.txt', make_get_names(script_names),
 category = read_table('Unicode.tables/DerivedGeneralCategory.txt', make_get_names(category_names), category_names.index('Cn'))
 break_props = read_table('Unicode.tables/GraphemeBreakProperty.txt', make_get_names(break_properties), break_properties.index('Other'))
 other_case = read_table('Unicode.tables/CaseFolding.txt', get_other_case, 0)
-bidi_class = read_table('Unicode.tables/DerivedBidiClass.txt', make_get_names(bidi_classes), bidi_classes.index('L'))
+bidi_class = read_table('Unicode.tables/DerivedBidiClass.txt', get_bidi, bidi_classes_short.index('L'))
 
 # The grapheme breaking rules were changed for Unicode 11.0.0 (June 2018). Now
 # we need to find the Extended_Pictographic property for emoji characters. This
@@ -710,6 +723,16 @@ for s in caseless_sets:
 
 # End of block of code for creating offsets for caseless matching sets.
 
+# Scan the caseless sets, and for any non-ASCII character that has an ASCII
+# character as its "base" other case, remove the other case. This makes it
+# easier to handle those characters when the PCRE2 option for not mixing ASCII
+# and non-ASCII is enabled. In principle one should perhaps scan for a 
+# non-ASCII alternative, but in practice these don't exist.
+
+for s in caseless_sets:
+  for x in s:
+    if x > 127 and x + other_case[x] < 128:
+      other_case[x] = 0  
 
 # Combine all the tables
 
@@ -728,7 +751,7 @@ for block_size in [2 ** i for i in range(5,10)]:
   size = len(records) * record_size
   stage1, stage2 = compress_table(table, block_size)
   size += get_tables_size(stage1, stage2)
-  #print "/* block size %5d  => %5d bytes */" % (block_size, size)
+  #print("/* block size {:3d} => {:5d} bytes */".format(block_size, size))
   if size < min_size:
     min_size = size
     min_stage1, min_stage2 = stage1, stage2
diff --git a/pcre2/maint/GenerateUcpTables.py b/pcre2/maint/GenerateUcpTables.py
index 528ff91..db79bc5 100755
--- a/pcre2/maint/GenerateUcpTables.py
+++ b/pcre2/maint/GenerateUcpTables.py
@@ -114,7 +114,7 @@ utt_table += list(zip(std_bidi_class_names, bidi_class_names, ['PT_BIDICL'] * le
 
 for name in bool_properties:
   utt_table.append((stdname(name), name, 'PT_BOOL'))
-  if name in abbreviations: 
+  if name in abbreviations:
     for abbrev in abbreviations[name]:
       utt_table.append((stdname(abbrev), name, 'PT_BOOL'))
 
diff --git a/pcre2/maint/ManyConfigTests b/pcre2/maint/ManyConfigTests
index d82613f..afac18e 100755
--- a/pcre2/maint/ManyConfigTests
+++ b/pcre2/maint/ManyConfigTests
@@ -1,6 +1,6 @@
 #! /bin/sh
 
-# This is a script for the use of PCRE2 maintainers. It configures and rebuilds
+# This is a script for the use of PCRE2 maintainers. It configures and builds
 # PCRE2 with a variety of configuration options, and in each case runs the
 # tests to ensure that all goes well. Every possible combination would take far
 # too long, so we use a representative sample. This script should be run in the
@@ -18,7 +18,8 @@
 # -nojitvalgrind  skip JIT tests with valgrind
 # -nomain         skip all the main (non-JIT) set of tests
 # -nomainvalgrind skip the main (non-JIT) valgrind tests
-# -notmp          skip the test in a temporary directory
+# -notmp          skip the tests in a temporary directory
+# -notmpjit       skip the JIT test in a temporary directory
 # -novalgrind     skip all the valgrind tests
 
 # Alternatively, if any of those names are given with '+' instead of '-no',
@@ -36,6 +37,7 @@ usejitvalgrind=1
 usemain=1
 usemainvalgrind=1
 usetmp=1
+usetmpjit=1
 usevalgrind=1
 
 dummy=0
@@ -53,6 +55,8 @@ while [ $# -gt 0 ] ; do
           usemain=0
           usemainvalgrind=0
           usetmp=0
+          usetmpjit=0 
+          usevalgrind=0 
           seenplus=1
         fi;;
   esac
@@ -63,22 +67,24 @@ while [ $# -gt 0 ] ; do
     -noasan)         useasan=0;;
     -nousan)         useusan=0;;
     -nodebug)        usedebug=0;;
-    -nojit)          usejit=0; usejitvalgrind=0;;
+    -nojit)          usejit=0; usejitvalgrind=0; usetmpjit=0;;
     -nojitmain)      usejit=0;;
     -nojitvalgrind)  usejitvalgrind=0;;
     -nomain)         usemain=0; usemainvalgrind=0;;
     -nomainvalgrind) usemainvalgrind=0;;
-    -notmp)          usetmp=0;;
+    -notmp)          usetmp=0; usetmpjit=0;;
+    -notmpjit)       usetmpjit=0;;
     -novalgrind)     usevalgrind=0;;
     +asan)           useasan=1;;
     +usan)           useusan=1;;
     +debug)          usedebug=1;;
-    +jit)            usejit=1; usejitvalgrind=1;;
+    +jit)            usejit=1; usejitvalgrind=1; usetmpjit=1;;
     +jitmain)        usejit=1;;
     +jitvalgrind)    usejitvalgrind=1;;
     +main)           usemain=1; usemainvalgrind=1;;
     +mainvalgrind)   usemainvalgrind=1;;
     +tmp)            usetmp=1;;
+    +tmpjit)         usetmpjit=1;;
     +valgrind)       usevalgrind=1; usejitvalgrind=1; usemainvalgrind=1;;
     *)               echo "Unknown option '$1'"; exit 1;;
   esac
@@ -124,9 +130,11 @@ if [ $? -eq 0 ] && grep GCC /tmp/pcre2ccversion >/dev/null; then
   CFLAGS="$CFLAGS -Wnested-externs"
   CFLAGS="$CFLAGS -pedantic"
   CFLAGS="$CFLAGS -Wuninitialized"
-  CFLAGS="$CFLAGS -Wmaybe-uninitialized" 
+  CFLAGS="$CFLAGS -Wmaybe-uninitialized"
   CFLAGS="$CFLAGS -Wmissing-prototypes"
   CFLAGS="$CFLAGS -Wstrict-prototypes"
+  CFKAGS="$CFLAGS -Warray-bounds"
+  CFLAGS="$CFLAGS -Wformat-overflow=2"
 fi
 rm -f /tmp/pcre2ccversion
 
@@ -137,7 +145,7 @@ rm -f /tmp/pcre2ccversion
 
 runtest()
   {
-  rm -f $srcdir/pcre2test $srcdir/pcre2grep $srcdir/pcre2_jit_test
+  rm -f $srcdir/pcre2test $srcdir/pcre2grep $srcdir/pcre2_jit_test $srcdir/pcre2posix_test
   testcount=`expr $testcount + 1`
 
   if [ "$opts" = "" ] ; then
@@ -218,13 +226,21 @@ runtest()
       cat teststdoutM
       exit 1
     fi
+    echo "Running pcre2posix test $withvalgrind"
+    $valgrind ./pcre2posix_test >teststdoutM 2>teststderrM
+
+    if [ $? -ne 0 ]; then
+      echo " "
+      echo "**** Test failed ****"
+      exit 1
+    fi
   else
-    echo "Skipping pcre2grep tests: 8-bit library not compiled"
+    echo "Skipping pcre2grep and pcre2posix tests: 8-bit library not compiled"
   fi
 
   if [ "$jit" -gt 0 ]; then
     echo "Running JIT regression tests $withvalgrind"
-    $jrvalgrind $srcdir/pcre2_jit_test >teststdoutM 2>teststderrM
+    $jrvalgrind ./pcre2_jit_test >teststdoutM 2>teststderrM
     if [ $? -ne 0 -o -s teststderrM ]; then
       echo " "
       echo "**** Test failed ****"
@@ -242,7 +258,7 @@ runtest()
 
 testtotal=`expr 17 \* $usemain + \
   1 \* $usemain \* $usedebug + \
-  1 \* $usetmp + \
+  1 \* $usetmp + 1 \* $usetmpjit + \
   1 \* $ISGCC \* $usemain + \
   1 \* $ISGCC \* $usemain \* $useasan + \
   1 \* $ISGCC \* $usemain \* $useusan + \
@@ -273,9 +289,7 @@ fi
 # throw up warnings that are not detected with -O0. Then run a second test with
 # -fsanitize=address, which also may throw up new warnings as well as checking
 # things at runtime. Finally, run another test using -fsanitize=undefined
-# -std-gnu99 to check for runtime actions that are not well defined. However,
-# we also use -fno-sanitize=shift to avoid warnings for shifts of negative
-# numbers, which occur in src/pcre2_jit_compile.c.
+# -std-gnu99 to check for runtime actions that are not well defined.
 
 if [ $ISGCC -ne 0 -a $usemain -ne 0 ]; then
   echo "---------- Maximally configured test with -O2 ----------"
@@ -293,15 +307,15 @@ if [ $ISGCC -ne 0 -a $usemain -ne 0 ]; then
     opts="--disable-shared $enable_jit --enable-pcre2-16 --enable-pcre2-32"
     runtest
   fi
-# This also seems to be the case for sanitize undefined.   
+# This also seems to be the case for sanitize undefined.
   if [ $useusan -ne 0 ]; then
-    echo "------- Maximally configured test with -fsanitize=undefined -fno-sanitize=shift -fno-sanitize=alignment -std=gnu99 -------"
-    CFLAGS="$OFLAGS $SAVECFLAGS -no-pie -fno-PIE -fsanitize=undefined -fno-sanitize=shift -fno-sanitize=alignment -std=gnu99"
+    echo "------- Maximally configured test with -fsanitize=undefined -fno-sanitize=alignment -std=gnu99 -------"
+    CFLAGS="$OFLAGS $SAVECFLAGS -no-pie -fno-PIE -fsanitize=undefined -fno-sanitize=alignment -std=gnu99"
     echo "CFLAGS=$CFLAGS"
     opts="--disable-shared $enable_jit --enable-pcre2-16 --enable-pcre2-32"
     runtest
   fi
-  CFLAGS="$OFLAGS $SAVECFLAGS"
+  CFLAGS="$SAVECFLAGS"
 fi
 
 # This set of tests builds PCRE2 and runs the tests with a variety of configure
@@ -312,6 +326,7 @@ fi
 # library for the subsequent tests.
 
 echo "---------- CFLAGS for the remaining tests ----------"
+CFLAGS="$OFLAGS $CFLAGS"
 echo "CFLAGS=$CFLAGS"
 
 if [ $usemain -ne 0 ]; then
@@ -386,7 +401,7 @@ if [ $usevalgrind -ne 0 ]; then
   fi
 
   if [ $usejitvalgrind -ne 0 ]; then
-    jrvalgrind="valgrind --tool=memcheck -q --smc-check=all-non-file --suppressions=$srcdir/testdata/valgrind-jit.supp" 
+    jrvalgrind="valgrind --tool=memcheck -q --smc-check=all-non-file --suppressions=$srcdir/testdata/valgrind-jit.supp"
     for opts in \
       "--enable-jit --disable-shared" \
       "--enable-jit --enable-pcre2-16 --enable-pcre2-32"
@@ -418,8 +433,7 @@ echo "---------- End of tests in the source directory ----------"
 echo "Removing teststdoutM and teststderrM"
 rm -rf teststdoutM teststderrM
 
-if [ $usetmp -ne 0 ]; then
-  echo "---------- Tests in the $tmp directory ----------"
+if [ $usetmp -ne 0 -o $usetmpjit -ne 0 ]; then
   srcdir=`pwd`
   export srcdir
 
@@ -438,11 +452,23 @@ if [ $usetmp -ne 0 ]; then
     exit 1
   fi
 
-  for opts in \
-    "--disable-shared"
-  do
-    runtest
-  done
+  if [ $usetmp -ne 0 ]; then
+    echo "---------- Tests in the $tmp directory ----------"
+    for opts in \
+      "--disable-shared"
+    do
+      runtest
+    done
+  fi   
+  
+  if [ $usetmpjit -ne 0 ]; then
+    echo "---------- JIT tests in the $tmp directory ----------"
+    for opts in \
+      "--enable-jit --disable-shared"
+    do
+      runtest
+    done
+  fi
 
   echo "Removing $tmp"
   rm -rf $tmp
diff --git a/pcre2/maint/README b/pcre2/maint/README
index 3d341b8..e451a1a 100644
--- a/pcre2/maint/README
+++ b/pcre2/maint/README
@@ -156,12 +156,10 @@ release.
 
 . Run tests with two or more different compilers (e.g. clang and gcc), and
   make use of -fsanitize=address and friends where possible. For gcc,
-  -fsanitize=undefined -std=gnu99 picks up undefined behaviour at runtime, but
-  needs -fno-sanitize=shift to get rid of warnings for shifts of negative
-  numbers in the JIT compiler. For clang, -fsanitize=address,undefined,integer
-  can be used but -fno-sanitize=alignment,shift,unsigned-integer-overflow must
-  be added when compiling with JIT. Another useful clang option is
-  -fsanitize=signed-integer-overflow
+  -fsanitize=undefined -std=gnu99 picks up undefined behaviour at runtime.
+  For clang, -fsanitize=address,undefined,integer can be used but
+  -fno-sanitize=unsigned-integer-overflow must be added when compiling with JIT.
+  Another useful clang option is -fsanitize=signed-integer-overflow
 
 . Do a test build using CMake. Remove src/config.h first, lest it override the
   version that CMake creates. Also do a CMake unity build to check that it 
@@ -450,11 +448,17 @@ years.
   gigabyte memory, but perhaps another implementation might be considered.
   Needs coordination between the interpreters and JIT.
 
-. There are regular requests for variable-length lookbehinds.
+. The POSIX interface is no longer POSIX compatible, because regoff_t is still
+  defined as an int.
+
+. The POSIX interface is not thread safe because it modifies a pcre2_match
+  inside its regex_t while doing matching. A thread safe version that uses
+  a thread local object has been proposed but it will require that the code
+  requires at least C11 compatibility.
 
 . See also any suggestions in the GitHub issues.
 
 Philip Hazel
 Email local part: Philip.Hazel
 Email domain: gmail.com
-Last updated: 25 April 2022
+Last updated: 30 November 2023
diff --git a/pcre2/maint/Unicode.tables/BidiMirroring.txt b/pcre2/maint/Unicode.tables/BidiMirroring.txt
index bd8e2c5..5861d6e 100644
--- a/pcre2/maint/Unicode.tables/BidiMirroring.txt
+++ b/pcre2/maint/Unicode.tables/BidiMirroring.txt
@@ -1,6 +1,6 @@
-# BidiMirroring-14.0.0.txt
-# Date: 2021-08-08, 22:55:00 GMT [KW, RP]
-# © 2021 Unicode®, Inc.
+# BidiMirroring-15.0.0.txt
+# Date: 2022-05-03, 18:47:00 GMT [KW, RP]
+# © 2022 Unicode®, Inc.
 # For terms of use, see https://www.unicode.org/terms_of_use.html
 #
 # Unicode Character Database
@@ -15,7 +15,7 @@
 # value, for which there is another Unicode character that typically has a glyph
 # that is the mirror image of the original character's glyph.
 #
-# The repertoire covered by the file is Unicode 14.0.0.
+# The repertoire covered by the file is Unicode 15.0.0.
 #
 # The file contains a list of lines with mappings from one code point
 # to another one for character-based mirroring.
diff --git a/pcre2/maint/Unicode.tables/CaseFolding.txt b/pcre2/maint/Unicode.tables/CaseFolding.txt
index 932ace2..65aa0fc 100644
--- a/pcre2/maint/Unicode.tables/CaseFolding.txt
+++ b/pcre2/maint/Unicode.tables/CaseFolding.txt
@@ -1,11 +1,11 @@
-# CaseFolding-14.0.0.txt
-# Date: 2021-03-08, 19:35:41 GMT
-# © 2021 Unicode®, Inc.
+# CaseFolding-15.0.0.txt
+# Date: 2022-02-02, 23:35:35 GMT
+# © 2022 Unicode®, Inc.
 # Unicode and the Unicode Logo are registered trademarks of Unicode, Inc. in the U.S. and other countries.
-# For terms of use, see http://www.unicode.org/terms_of_use.html
+# For terms of use, see https://www.unicode.org/terms_of_use.html
 #
 # Unicode Character Database
-#   For documentation, see http://www.unicode.org/reports/tr44/
+#   For documentation, see https://www.unicode.org/reports/tr44/
 #
 # Case Folding Properties
 #
diff --git a/pcre2/maint/Unicode.tables/DerivedBidiClass.txt b/pcre2/maint/Unicode.tables/DerivedBidiClass.txt
index 4012dc2..55b30a6 100644
--- a/pcre2/maint/Unicode.tables/DerivedBidiClass.txt
+++ b/pcre2/maint/Unicode.tables/DerivedBidiClass.txt
@@ -1,36 +1,19 @@
-# DerivedBidiClass-14.0.0.txt
-# Date: 2021-07-10, 00:35:02 GMT
-# © 2021 Unicode®, Inc.
+# DerivedBidiClass-15.0.0.txt
+# Date: 2022-08-05, 17:39:24 GMT
+# © 2022 Unicode®, Inc.
 # Unicode and the Unicode Logo are registered trademarks of Unicode, Inc. in the U.S. and other countries.
-# For terms of use, see http://www.unicode.org/terms_of_use.html
+# For terms of use, see https://www.unicode.org/terms_of_use.html
 #
 # Unicode Character Database
-#   For documentation, see http://www.unicode.org/reports/tr44/
+#   For documentation, see https://www.unicode.org/reports/tr44/
 
 # ================================================
 
 # Bidi Class (listing UnicodeData.txt, field 4: see UAX #44: https://www.unicode.org/reports/tr44/)
 # Unlike other properties, unassigned code points in blocks
-# reserved for right-to-left scripts are given either types R or AL.
-#
-# The unassigned code points that default to AL are in the ranges:
-#     [\u0600-\u07BF \u0860-\u08FF \uFB50-\uFDCF \uFDF0-\uFDFF \uFE70-\uFEFF
-#      \U00010D00-\U00010D3F \U00010F30-\U00010F6F
-#      \U0001EC70-\U0001ECBF \U0001ED00-\U0001ED4F \U0001EE00-\U0001EEFF]
-#
-#     This includes code points in the Arabic, Syriac, and Thaana blocks, among others.
-#
-# The unassigned code points that default to R are in the ranges:
-#     [\u0590-\u05FF \u07C0-\u085F \uFB1D-\uFB4F
-#      \U00010800-\U00010CFF \U00010D40-\U00010F2F \U00010F70-\U00010FFF
-#      \U0001E800-\U0001EC6F \U0001ECC0-\U0001ECFF \U0001ED50-\U0001EDFF \U0001EF00-\U0001EFFF]
-#
-#     This includes code points in the Hebrew, NKo, and Phoenician blocks, among others.
-#
-# The unassigned code points that default to ET are in the range:
-#     [\u20A0-\u20CF]
-#
-#     This consists of code points in the Currency Symbols block.
+# reserved for right-to-left scripts are given either values R or AL,
+# and unassigned code points in the Currency Symbols block are given the value ET.
+# For details see the @missing lines below.
 #
 # The unassigned code points that default to BN have one of the following properties:
 #     Default_Ignorable_Code_Point
@@ -43,6 +26,101 @@
 
 # @missing: 0000..10FFFF; Left_To_Right
 
+# 0590..05FF Hebrew
+# @missing: 0590..05FF; Right_To_Left
+
+# 0600..06FF Arabic
+# 0700..074F Syriac
+# 0750..077F Arabic_Supplement
+# 0780..07BF Thaana
+# @missing: 0600..07BF; Arabic_Letter
+
+# 07C0..07FF NKo
+# 0800..083F Samaritan
+# 0840..085F Mandaic
+# @missing: 07C0..085F; Right_To_Left
+
+# 0860..086F Syriac_Supplement
+# 0870..089F Arabic_Extended_B
+# 08A0..08FF Arabic_Extended_A
+# @missing: 0860..08FF; Arabic_Letter
+
+# 20A0..20CF Currency_Symbols
+# @missing: 20A0..20CF; European_Terminator
+
+# FB00..FB4F Alphabetic_Presentation_Forms (partial)
+# @missing: FB1D..FB4F; Right_To_Left
+
+# FB50..FDFF Arabic_Presentation_Forms_A (partial)
+# @missing: FB50..FDCF; Arabic_Letter
+
+# FB50..FDFF Arabic_Presentation_Forms_A (partial)
+# @missing: FDF0..FDFF; Arabic_Letter
+
+# FE70..FEFF Arabic_Presentation_Forms_B
+# @missing: FE70..FEFF; Arabic_Letter
+
+# 10800..1083F Cypriot_Syllabary
+# 10840..1085F Imperial_Aramaic
+# 10860..1087F Palmyrene
+# 10880..108AF Nabataean
+# 108E0..108FF Hatran
+# 10900..1091F Phoenician
+# 10920..1093F Lydian
+# 10980..1099F Meroitic_Hieroglyphs
+# 109A0..109FF Meroitic_Cursive
+# 10A00..10A5F Kharoshthi
+# 10A60..10A7F Old_South_Arabian
+# 10A80..10A9F Old_North_Arabian
+# 10AC0..10AFF Manichaean
+# 10B00..10B3F Avestan
+# 10B40..10B5F Inscriptional_Parthian
+# 10B60..10B7F Inscriptional_Pahlavi
+# 10B80..10BAF Psalter_Pahlavi
+# 10C00..10C4F Old_Turkic
+# 10C80..10CFF Old_Hungarian
+# @missing: 10800..10CFF; Right_To_Left
+
+# 10D00..10D3F Hanifi_Rohingya
+# @missing: 10D00..10D3F; Arabic_Letter
+
+# 10E60..10E7F Rumi_Numeral_Symbols
+# 10E80..10EBF Yezidi
+# @missing: 10D40..10EBF; Right_To_Left
+
+# 10EC0..10EFF Arabic_Extended_C
+# @missing: 10EC0..10EFF; Arabic_Letter
+
+# 10F00..10F2F Old_Sogdian
+# @missing: 10F00..10F2F; Right_To_Left
+
+# 10F30..10F6F Sogdian
+# @missing: 10F30..10F6F; Arabic_Letter
+
+# 10F70..10FAF Old_Uyghur
+# 10FB0..10FDF Chorasmian
+# 10FE0..10FFF Elymaic
+# @missing: 10F70..10FFF; Right_To_Left
+
+# 1E800..1E8DF Mende_Kikakui
+# 1E900..1E95F Adlam
+# @missing: 1E800..1EC6F; Right_To_Left
+
+# 1EC70..1ECBF Indic_Siyaq_Numbers
+# @missing: 1EC70..1ECBF; Arabic_Letter
+
+# @missing: 1ECC0..1ECFF; Right_To_Left
+
+# 1ED00..1ED4F Ottoman_Siyaq_Numbers
+# @missing: 1ED00..1ED4F; Arabic_Letter
+
+# @missing: 1ED50..1EDFF; Right_To_Left
+
+# 1EE00..1EEFF Arabic_Mathematical_Alphabetic_Symbols
+# @missing: 1EE00..1EEFF; Arabic_Letter
+
+# @missing: 1EF00..1EFFF; Right_To_Left
+
 # ================================================
 
 # Bidi_Class=Left_To_Right
@@ -219,6 +297,7 @@
 0CE0..0CE1    ; L # Lo   [2] KANNADA LETTER VOCALIC RR..KANNADA LETTER VOCALIC LL
 0CE6..0CEF    ; L # Nd  [10] KANNADA DIGIT ZERO..KANNADA DIGIT NINE
 0CF1..0CF2    ; L # Lo   [2] KANNADA SIGN JIHVAMULIYA..KANNADA SIGN UPADHMANIYA
+0CF3          ; L # Mc       KANNADA SIGN COMBINING ANUSVARA ABOVE RIGHT
 0D02..0D03    ; L # Mc   [2] MALAYALAM SIGN ANUSVARA..MALAYALAM SIGN VISARGA
 0D04..0D0C    ; L # Lo   [9] MALAYALAM LETTER VEDIC ANUSVARA..MALAYALAM LETTER VOCALIC L
 0D0E..0D10    ; L # Lo   [3] MALAYALAM LETTER E..MALAYALAM LETTER AI
@@ -795,6 +874,7 @@ FFDA..FFDC    ; L # Lo   [3] HALFWIDTH HANGUL LETTER EU..HALFWIDTH HANGUL LETTER
 11232..11233  ; L # Mc   [2] KHOJKI VOWEL SIGN O..KHOJKI VOWEL SIGN AU
 11235         ; L # Mc       KHOJKI SIGN VIRAMA
 11238..1123D  ; L # Po   [6] KHOJKI DANDA..KHOJKI ABBREVIATION SIGN
+1123F..11240  ; L # Lo   [2] KHOJKI LETTER QA..KHOJKI LETTER SHORT I
 11280..11286  ; L # Lo   [7] MULTANI LETTER A..MULTANI LETTER GA
 11288         ; L # Lo       MULTANI LETTER GHA
 1128A..1128D  ; L # Lo   [4] MULTANI LETTER CA..MULTANI LETTER JJA
@@ -910,6 +990,7 @@ FFDA..FFDC    ; L # Lo   [3] HALFWIDTH HANGUL LETTER EU..HALFWIDTH HANGUL LETTER
 11A9D         ; L # Lo       SOYOMBO MARK PLUTA
 11A9E..11AA2  ; L # Po   [5] SOYOMBO HEAD MARK WITH MOON AND SUN AND TRIPLE FLAME..SOYOMBO TERMINAL MARK-2
 11AB0..11AF8  ; L # Lo  [73] CANADIAN SYLLABICS NATTILIK HI..PAU CIN HAU GLOTTAL STOP FINAL
+11B00..11B09  ; L # Po  [10] DEVANAGARI HEAD MARK..DEVANAGARI SIGN MINDU
 11C00..11C08  ; L # Lo   [9] BHAIKSUKI LETTER A..BHAIKSUKI LETTER VOCALIC L
 11C0A..11C2E  ; L # Lo  [37] BHAIKSUKI LETTER E..BHAIKSUKI LETTER HA
 11C2F         ; L # Mc       BHAIKSUKI VOWEL SIGN AA
@@ -940,6 +1021,15 @@ FFDA..FFDC    ; L # Lo   [3] HALFWIDTH HANGUL LETTER EU..HALFWIDTH HANGUL LETTER
 11EE0..11EF2  ; L # Lo  [19] MAKASAR LETTER KA..MAKASAR ANGKA
 11EF5..11EF6  ; L # Mc   [2] MAKASAR VOWEL SIGN E..MAKASAR VOWEL SIGN O
 11EF7..11EF8  ; L # Po   [2] MAKASAR PASSIMBANG..MAKASAR END OF SECTION
+11F02         ; L # Lo       KAWI SIGN REPHA
+11F03         ; L # Mc       KAWI SIGN VISARGA
+11F04..11F10  ; L # Lo  [13] KAWI LETTER A..KAWI LETTER O
+11F12..11F33  ; L # Lo  [34] KAWI LETTER KA..KAWI LETTER JNYA
+11F34..11F35  ; L # Mc   [2] KAWI VOWEL SIGN AA..KAWI VOWEL SIGN ALTERNATE AA
+11F3E..11F3F  ; L # Mc   [2] KAWI VOWEL SIGN E..KAWI VOWEL SIGN AI
+11F41         ; L # Mc       KAWI SIGN KILLER
+11F43..11F4F  ; L # Po  [13] KAWI DANDA..KAWI PUNCTUATION CLOSING SPIRAL
+11F50..11F59  ; L # Nd  [10] KAWI DIGIT ZERO..KAWI DIGIT NINE
 11FB0         ; L # Lo       LISU LETTER YHA
 11FC0..11FD4  ; L # No  [21] TAMIL FRACTION ONE THREE-HUNDRED-AND-TWENTIETH..TAMIL FRACTION DOWNSCALING FACTOR KIIZH
 11FFF         ; L # Po       TAMIL PUNCTUATION END OF TEXT
@@ -949,8 +1039,9 @@ FFDA..FFDC    ; L # Lo   [3] HALFWIDTH HANGUL LETTER EU..HALFWIDTH HANGUL LETTER
 12480..12543  ; L # Lo [196] CUNEIFORM SIGN AB TIMES NUN TENU..CUNEIFORM SIGN ZU5 TIMES THREE DISH TENU
 12F90..12FF0  ; L # Lo  [97] CYPRO-MINOAN SIGN CM001..CYPRO-MINOAN SIGN CM114
 12FF1..12FF2  ; L # Po   [2] CYPRO-MINOAN SIGN CM301..CYPRO-MINOAN SIGN CM302
-13000..1342E  ; L # Lo [1071] EGYPTIAN HIEROGLYPH A001..EGYPTIAN HIEROGLYPH AA032
-13430..13438  ; L # Cf   [9] EGYPTIAN HIEROGLYPH VERTICAL JOINER..EGYPTIAN HIEROGLYPH END SEGMENT
+13000..1342F  ; L # Lo [1072] EGYPTIAN HIEROGLYPH A001..EGYPTIAN HIEROGLYPH V011D
+13430..1343F  ; L # Cf  [16] EGYPTIAN HIEROGLYPH VERTICAL JOINER..EGYPTIAN HIEROGLYPH END WALLED ENCLOSURE
+13441..13446  ; L # Lo   [6] EGYPTIAN HIEROGLYPH FULL BLANK..EGYPTIAN HIEROGLYPH WIDE LOST SIGN
 14400..14646  ; L # Lo [583] ANATOLIAN HIEROGLYPH A001..ANATOLIAN HIEROGLYPH A530
 16800..16A38  ; L # Lo [569] BAMUM LETTER PHASE-A NGKUE MFON..BAMUM LETTER PHASE-F VUEQ
 16A40..16A5E  ; L # Lo  [31] MRO LETTER TA..MRO LETTER TEK
@@ -987,7 +1078,9 @@ FFDA..FFDC    ; L # Lo   [3] HALFWIDTH HANGUL LETTER EU..HALFWIDTH HANGUL LETTER
 1AFF5..1AFFB  ; L # Lm   [7] KATAKANA LETTER MINNAN TONE-7..KATAKANA LETTER MINNAN NASALIZED TONE-5
 1AFFD..1AFFE  ; L # Lm   [2] KATAKANA LETTER MINNAN NASALIZED TONE-7..KATAKANA LETTER MINNAN NASALIZED TONE-8
 1B000..1B122  ; L # Lo [291] KATAKANA LETTER ARCHAIC E..KATAKANA LETTER ARCHAIC WU
+1B132         ; L # Lo       HIRAGANA LETTER SMALL KO
 1B150..1B152  ; L # Lo   [3] HIRAGANA LETTER SMALL WI..HIRAGANA LETTER SMALL WO
+1B155         ; L # Lo       KATAKANA LETTER SMALL KO
 1B164..1B167  ; L # Lo   [4] KATAKANA LETTER SMALL WI..KATAKANA LETTER SMALL N
 1B170..1B2FB  ; L # Lo [396] NUSHU CHARACTER-1B170..NUSHU CHARACTER-1B2FB
 1BC00..1BC6A  ; L # Lo [107] DUPLOYAN LETTER H..DUPLOYAN LETTER VOCALIC M
@@ -1006,6 +1099,7 @@ FFDA..FFDC    ; L # Lo   [3] HALFWIDTH HANGUL LETTER EU..HALFWIDTH HANGUL LETTER
 1D183..1D184  ; L # So   [2] MUSICAL SYMBOL ARPEGGIATO UP..MUSICAL SYMBOL ARPEGGIATO DOWN
 1D18C..1D1A9  ; L # So  [30] MUSICAL SYMBOL RINFORZANDO..MUSICAL SYMBOL DEGREE SLASH
 1D1AE..1D1E8  ; L # So  [59] MUSICAL SYMBOL PEDAL MARK..MUSICAL SYMBOL KIEVAN FLAT SIGN
+1D2C0..1D2D3  ; L # No  [20] KAKTOVIK NUMERAL ZERO..KAKTOVIK NUMERAL NINETEEN
 1D2E0..1D2F3  ; L # No  [20] MAYAN NUMERAL ZERO..MAYAN NUMERAL NINETEEN
 1D360..1D378  ; L # No  [25] COUNTING ROD UNIT DIGIT ONE..TALLY MARK FIVE
 1D400..1D454  ; L # L&  [85] MATHEMATICAL BOLD CAPITAL A..MATHEMATICAL ITALIC SMALL G
@@ -1052,6 +1146,8 @@ FFDA..FFDC    ; L # Lo   [3] HALFWIDTH HANGUL LETTER EU..HALFWIDTH HANGUL LETTER
 1DF00..1DF09  ; L # L&  [10] LATIN SMALL LETTER FENG DIGRAPH WITH TRILL..LATIN SMALL LETTER T WITH HOOK AND RETROFLEX HOOK
 1DF0A         ; L # Lo       LATIN LETTER RETROFLEX CLICK WITH RETROFLEX HOOK
 1DF0B..1DF1E  ; L # L&  [20] LATIN SMALL LETTER ESH WITH DOUBLE BAR..LATIN SMALL LETTER S WITH CURL
+1DF25..1DF2A  ; L # L&   [6] LATIN SMALL LETTER D WITH MID-HEIGHT LEFT HOOK..LATIN SMALL LETTER T WITH MID-HEIGHT LEFT HOOK
+1E030..1E06D  ; L # Lm  [62] MODIFIER LETTER CYRILLIC SMALL A..MODIFIER LETTER CYRILLIC SMALL STRAIGHT U WITH STROKE
 1E100..1E12C  ; L # Lo  [45] NYIAKENG PUACHUE HMONG LETTER MA..NYIAKENG PUACHUE HMONG LETTER W
 1E137..1E13D  ; L # Lm   [7] NYIAKENG PUACHUE HMONG SIGN FOR PERSON..NYIAKENG PUACHUE HMONG SYLLABLE LENGTHENER
 1E140..1E149  ; L # Nd  [10] NYIAKENG PUACHUE HMONG DIGIT ZERO..NYIAKENG PUACHUE HMONG DIGIT NINE
@@ -1060,6 +1156,9 @@ FFDA..FFDC    ; L # Lo   [3] HALFWIDTH HANGUL LETTER EU..HALFWIDTH HANGUL LETTER
 1E290..1E2AD  ; L # Lo  [30] TOTO LETTER PA..TOTO LETTER A
 1E2C0..1E2EB  ; L # Lo  [44] WANCHO LETTER AA..WANCHO LETTER YIH
 1E2F0..1E2F9  ; L # Nd  [10] WANCHO DIGIT ZERO..WANCHO DIGIT NINE
+1E4D0..1E4EA  ; L # Lo  [27] NAG MUNDARI LETTER O..NAG MUNDARI LETTER ELL
+1E4EB         ; L # Lm       NAG MUNDARI SIGN OJOD
+1E4F0..1E4F9  ; L # Nd  [10] NAG MUNDARI DIGIT ZERO..NAG MUNDARI DIGIT NINE
 1E7E0..1E7E6  ; L # Lo   [7] ETHIOPIC SYLLABLE HHYA..ETHIOPIC SYLLABLE HHYO
 1E7E8..1E7EB  ; L # Lo   [4] ETHIOPIC SYLLABLE GURAGE HHWA..ETHIOPIC SYLLABLE HHWE
 1E7ED..1E7EE  ; L # Lo   [2] ETHIOPIC SYLLABLE GURAGE MWI..ETHIOPIC SYLLABLE GURAGE MWEE
@@ -1072,188 +1171,124 @@ FFDA..FFDC    ; L # Lo   [3] HALFWIDTH HANGUL LETTER EU..HALFWIDTH HANGUL LETTER
 1F240..1F248  ; L # So   [9] TORTOISE SHELL BRACKETED CJK UNIFIED IDEOGRAPH-672C..TORTOISE SHELL BRACKETED CJK UNIFIED IDEOGRAPH-6557
 1F250..1F251  ; L # So   [2] CIRCLED IDEOGRAPH ADVANTAGE..CIRCLED IDEOGRAPH ACCEPT
 20000..2A6DF  ; L # Lo [42720] CJK UNIFIED IDEOGRAPH-20000..CJK UNIFIED IDEOGRAPH-2A6DF
-2A700..2B738  ; L # Lo [4153] CJK UNIFIED IDEOGRAPH-2A700..CJK UNIFIED IDEOGRAPH-2B738
+2A700..2B739  ; L # Lo [4154] CJK UNIFIED IDEOGRAPH-2A700..CJK UNIFIED IDEOGRAPH-2B739
 2B740..2B81D  ; L # Lo [222] CJK UNIFIED IDEOGRAPH-2B740..CJK UNIFIED IDEOGRAPH-2B81D
 2B820..2CEA1  ; L # Lo [5762] CJK UNIFIED IDEOGRAPH-2B820..CJK UNIFIED IDEOGRAPH-2CEA1
 2CEB0..2EBE0  ; L # Lo [7473] CJK UNIFIED IDEOGRAPH-2CEB0..CJK UNIFIED IDEOGRAPH-2EBE0
 2F800..2FA1D  ; L # Lo [542] CJK COMPATIBILITY IDEOGRAPH-2F800..CJK COMPATIBILITY IDEOGRAPH-2FA1D
 30000..3134A  ; L # Lo [4939] CJK UNIFIED IDEOGRAPH-30000..CJK UNIFIED IDEOGRAPH-3134A
+31350..323AF  ; L # Lo [4192] CJK UNIFIED IDEOGRAPH-31350..CJK UNIFIED IDEOGRAPH-323AF
 F0000..FFFFD  ; L # Co [65534] ..
 100000..10FFFD; L # Co [65534] ..
 
-# The above property value applies to 825575 code points not listed here.
-# Total code points: 1096333
+# The above property value applies to 821089 code points not listed here.
+# Total code points: 1096272
 
 # ================================================
 
 # Bidi_Class=Right_To_Left
 
-0590          ; R # Cn       
 05BE          ; R # Pd       HEBREW PUNCTUATION MAQAF
 05C0          ; R # Po       HEBREW PUNCTUATION PASEQ
 05C3          ; R # Po       HEBREW PUNCTUATION SOF PASUQ
 05C6          ; R # Po       HEBREW PUNCTUATION NUN HAFUKHA
-05C8..05CF    ; R # Cn   [8] ..
 05D0..05EA    ; R # Lo  [27] HEBREW LETTER ALEF..HEBREW LETTER TAV
-05EB..05EE    ; R # Cn   [4] ..
 05EF..05F2    ; R # Lo   [4] HEBREW YOD TRIANGLE..HEBREW LIGATURE YIDDISH DOUBLE YOD
 05F3..05F4    ; R # Po   [2] HEBREW PUNCTUATION GERESH..HEBREW PUNCTUATION GERSHAYIM
-05F5..05FF    ; R # Cn  [11] ..
 07C0..07C9    ; R # Nd  [10] NKO DIGIT ZERO..NKO DIGIT NINE
 07CA..07EA    ; R # Lo  [33] NKO LETTER A..NKO LETTER JONA RA
 07F4..07F5    ; R # Lm   [2] NKO HIGH TONE APOSTROPHE..NKO LOW TONE APOSTROPHE
 07FA          ; R # Lm       NKO LAJANYALAN
-07FB..07FC    ; R # Cn   [2] ..
 07FE..07FF    ; R # Sc   [2] NKO DOROME SIGN..NKO TAMAN SIGN
 0800..0815    ; R # Lo  [22] SAMARITAN LETTER ALAF..SAMARITAN LETTER TAAF
 081A          ; R # Lm       SAMARITAN MODIFIER LETTER EPENTHETIC YUT
 0824          ; R # Lm       SAMARITAN MODIFIER LETTER SHORT A
 0828          ; R # Lm       SAMARITAN MODIFIER LETTER I
-082E..082F    ; R # Cn   [2] ..
 0830..083E    ; R # Po  [15] SAMARITAN PUNCTUATION NEQUDAA..SAMARITAN PUNCTUATION ANNAAU
-083F          ; R # Cn       
 0840..0858    ; R # Lo  [25] MANDAIC LETTER HALQA..MANDAIC LETTER AIN
-085C..085D    ; R # Cn   [2] ..
 085E          ; R # Po       MANDAIC PUNCTUATION
-085F          ; R # Cn       
 200F          ; R # Cf       RIGHT-TO-LEFT MARK
 FB1D          ; R # Lo       HEBREW LETTER YOD WITH HIRIQ
 FB1F..FB28    ; R # Lo  [10] HEBREW LIGATURE YIDDISH YOD YOD PATAH..HEBREW LETTER WIDE TAV
 FB2A..FB36    ; R # Lo  [13] HEBREW LETTER SHIN WITH SHIN DOT..HEBREW LETTER ZAYIN WITH DAGESH
-FB37          ; R # Cn       
 FB38..FB3C    ; R # Lo   [5] HEBREW LETTER TET WITH DAGESH..HEBREW LETTER LAMED WITH DAGESH
-FB3D          ; R # Cn       
 FB3E          ; R # Lo       HEBREW LETTER MEM WITH DAGESH
-FB3F          ; R # Cn       
 FB40..FB41    ; R # Lo   [2] HEBREW LETTER NUN WITH DAGESH..HEBREW LETTER SAMEKH WITH DAGESH
-FB42          ; R # Cn       
 FB43..FB44    ; R # Lo   [2] HEBREW LETTER FINAL PE WITH DAGESH..HEBREW LETTER PE WITH DAGESH
-FB45          ; R # Cn       
 FB46..FB4F    ; R # Lo  [10] HEBREW LETTER TSADI WITH DAGESH..HEBREW LIGATURE ALEF LAMED
 10800..10805  ; R # Lo   [6] CYPRIOT SYLLABLE A..CYPRIOT SYLLABLE JA
-10806..10807  ; R # Cn   [2] ..
 10808         ; R # Lo       CYPRIOT SYLLABLE JO
-10809         ; R # Cn       
 1080A..10835  ; R # Lo  [44] CYPRIOT SYLLABLE KA..CYPRIOT SYLLABLE WO
-10836         ; R # Cn       
 10837..10838  ; R # Lo   [2] CYPRIOT SYLLABLE XA..CYPRIOT SYLLABLE XE
-10839..1083B  ; R # Cn   [3] ..
 1083C         ; R # Lo       CYPRIOT SYLLABLE ZA
-1083D..1083E  ; R # Cn   [2] ..
 1083F..10855  ; R # Lo  [23] CYPRIOT SYLLABLE ZO..IMPERIAL ARAMAIC LETTER TAW
-10856         ; R # Cn       
 10857         ; R # Po       IMPERIAL ARAMAIC SECTION SIGN
 10858..1085F  ; R # No   [8] IMPERIAL ARAMAIC NUMBER ONE..IMPERIAL ARAMAIC NUMBER TEN THOUSAND
 10860..10876  ; R # Lo  [23] PALMYRENE LETTER ALEPH..PALMYRENE LETTER TAW
 10877..10878  ; R # So   [2] PALMYRENE LEFT-POINTING FLEURON..PALMYRENE RIGHT-POINTING FLEURON
 10879..1087F  ; R # No   [7] PALMYRENE NUMBER ONE..PALMYRENE NUMBER TWENTY
 10880..1089E  ; R # Lo  [31] NABATAEAN LETTER FINAL ALEPH..NABATAEAN LETTER TAW
-1089F..108A6  ; R # Cn   [8] ..
 108A7..108AF  ; R # No   [9] NABATAEAN NUMBER ONE..NABATAEAN NUMBER ONE HUNDRED
-108B0..108DF  ; R # Cn  [48] ..
 108E0..108F2  ; R # Lo  [19] HATRAN LETTER ALEPH..HATRAN LETTER QOPH
-108F3         ; R # Cn       
 108F4..108F5  ; R # Lo   [2] HATRAN LETTER SHIN..HATRAN LETTER TAW
-108F6..108FA  ; R # Cn   [5] ..
 108FB..108FF  ; R # No   [5] HATRAN NUMBER ONE..HATRAN NUMBER ONE HUNDRED
 10900..10915  ; R # Lo  [22] PHOENICIAN LETTER ALF..PHOENICIAN LETTER TAU
 10916..1091B  ; R # No   [6] PHOENICIAN NUMBER ONE..PHOENICIAN NUMBER THREE
-1091C..1091E  ; R # Cn   [3] ..
 10920..10939  ; R # Lo  [26] LYDIAN LETTER A..LYDIAN LETTER C
-1093A..1093E  ; R # Cn   [5] ..
 1093F         ; R # Po       LYDIAN TRIANGULAR MARK
-10940..1097F  ; R # Cn  [64] ..
 10980..109B7  ; R # Lo  [56] MEROITIC HIEROGLYPHIC LETTER A..MEROITIC CURSIVE LETTER DA
-109B8..109BB  ; R # Cn   [4] ..
 109BC..109BD  ; R # No   [2] MEROITIC CURSIVE FRACTION ELEVEN TWELFTHS..MEROITIC CURSIVE FRACTION ONE HALF
 109BE..109BF  ; R # Lo   [2] MEROITIC CURSIVE LOGOGRAM RMT..MEROITIC CURSIVE LOGOGRAM IMN
 109C0..109CF  ; R # No  [16] MEROITIC CURSIVE NUMBER ONE..MEROITIC CURSIVE NUMBER SEVENTY
-109D0..109D1  ; R # Cn   [2] ..
 109D2..109FF  ; R # No  [46] MEROITIC CURSIVE NUMBER ONE HUNDRED..MEROITIC CURSIVE FRACTION TEN TWELFTHS
 10A00         ; R # Lo       KHAROSHTHI LETTER A
-10A04         ; R # Cn       
-10A07..10A0B  ; R # Cn   [5] ..
 10A10..10A13  ; R # Lo   [4] KHAROSHTHI LETTER KA..KHAROSHTHI LETTER GHA
-10A14         ; R # Cn       
 10A15..10A17  ; R # Lo   [3] KHAROSHTHI LETTER CA..KHAROSHTHI LETTER JA
-10A18         ; R # Cn       
 10A19..10A35  ; R # Lo  [29] KHAROSHTHI LETTER NYA..KHAROSHTHI LETTER VHA
-10A36..10A37  ; R # Cn   [2] ..
-10A3B..10A3E  ; R # Cn   [4] ..
 10A40..10A48  ; R # No   [9] KHAROSHTHI DIGIT ONE..KHAROSHTHI FRACTION ONE HALF
-10A49..10A4F  ; R # Cn   [7] ..
 10A50..10A58  ; R # Po   [9] KHAROSHTHI PUNCTUATION DOT..KHAROSHTHI PUNCTUATION LINES
-10A59..10A5F  ; R # Cn   [7] ..
 10A60..10A7C  ; R # Lo  [29] OLD SOUTH ARABIAN LETTER HE..OLD SOUTH ARABIAN LETTER THETH
 10A7D..10A7E  ; R # No   [2] OLD SOUTH ARABIAN NUMBER ONE..OLD SOUTH ARABIAN NUMBER FIFTY
 10A7F         ; R # Po       OLD SOUTH ARABIAN NUMERIC INDICATOR
 10A80..10A9C  ; R # Lo  [29] OLD NORTH ARABIAN LETTER HEH..OLD NORTH ARABIAN LETTER ZAH
 10A9D..10A9F  ; R # No   [3] OLD NORTH ARABIAN NUMBER ONE..OLD NORTH ARABIAN NUMBER TWENTY
-10AA0..10ABF  ; R # Cn  [32] ..
 10AC0..10AC7  ; R # Lo   [8] MANICHAEAN LETTER ALEPH..MANICHAEAN LETTER WAW
 10AC8         ; R # So       MANICHAEAN SIGN UD
 10AC9..10AE4  ; R # Lo  [28] MANICHAEAN LETTER ZAYIN..MANICHAEAN LETTER TAW
-10AE7..10AEA  ; R # Cn   [4] ..
 10AEB..10AEF  ; R # No   [5] MANICHAEAN NUMBER ONE..MANICHAEAN NUMBER ONE HUNDRED
 10AF0..10AF6  ; R # Po   [7] MANICHAEAN PUNCTUATION STAR..MANICHAEAN PUNCTUATION LINE FILLER
-10AF7..10AFF  ; R # Cn   [9] ..
 10B00..10B35  ; R # Lo  [54] AVESTAN LETTER A..AVESTAN LETTER HE
-10B36..10B38  ; R # Cn   [3] ..
 10B40..10B55  ; R # Lo  [22] INSCRIPTIONAL PARTHIAN LETTER ALEPH..INSCRIPTIONAL PARTHIAN LETTER TAW
-10B56..10B57  ; R # Cn   [2] ..
 10B58..10B5F  ; R # No   [8] INSCRIPTIONAL PARTHIAN NUMBER ONE..INSCRIPTIONAL PARTHIAN NUMBER ONE THOUSAND
 10B60..10B72  ; R # Lo  [19] INSCRIPTIONAL PAHLAVI LETTER ALEPH..INSCRIPTIONAL PAHLAVI LETTER TAW
-10B73..10B77  ; R # Cn   [5] ..
 10B78..10B7F  ; R # No   [8] INSCRIPTIONAL PAHLAVI NUMBER ONE..INSCRIPTIONAL PAHLAVI NUMBER ONE THOUSAND
 10B80..10B91  ; R # Lo  [18] PSALTER PAHLAVI LETTER ALEPH..PSALTER PAHLAVI LETTER TAW
-10B92..10B98  ; R # Cn   [7] ..
 10B99..10B9C  ; R # Po   [4] PSALTER PAHLAVI SECTION MARK..PSALTER PAHLAVI FOUR DOTS WITH DOT
-10B9D..10BA8  ; R # Cn  [12] ..
 10BA9..10BAF  ; R # No   [7] PSALTER PAHLAVI NUMBER ONE..PSALTER PAHLAVI NUMBER ONE HUNDRED
-10BB0..10BFF  ; R # Cn  [80] ..
 10C00..10C48  ; R # Lo  [73] OLD TURKIC LETTER ORKHON A..OLD TURKIC LETTER ORKHON BASH
-10C49..10C7F  ; R # Cn  [55] ..
 10C80..10CB2  ; R # L&  [51] OLD HUNGARIAN CAPITAL LETTER A..OLD HUNGARIAN CAPITAL LETTER US
-10CB3..10CBF  ; R # Cn  [13] ..
 10CC0..10CF2  ; R # L&  [51] OLD HUNGARIAN SMALL LETTER A..OLD HUNGARIAN SMALL LETTER US
-10CF3..10CF9  ; R # Cn   [7] ..
 10CFA..10CFF  ; R # No   [6] OLD HUNGARIAN NUMBER ONE..OLD HUNGARIAN NUMBER ONE THOUSAND
-10D40..10E5F  ; R # Cn [288] ..
-10E7F         ; R # Cn       
 10E80..10EA9  ; R # Lo  [42] YEZIDI LETTER ELIF..YEZIDI LETTER ET
-10EAA         ; R # Cn       
 10EAD         ; R # Pd       YEZIDI HYPHENATION MARK
-10EAE..10EAF  ; R # Cn   [2] ..
 10EB0..10EB1  ; R # Lo   [2] YEZIDI LETTER LAM WITH DOT ABOVE..YEZIDI LETTER YOT WITH CIRCUMFLEX ABOVE
-10EB2..10EFF  ; R # Cn  [78] ..
 10F00..10F1C  ; R # Lo  [29] OLD SOGDIAN LETTER ALEPH..OLD SOGDIAN LETTER FINAL TAW WITH VERTICAL TAIL
 10F1D..10F26  ; R # No  [10] OLD SOGDIAN NUMBER ONE..OLD SOGDIAN FRACTION ONE HALF
 10F27         ; R # Lo       OLD SOGDIAN LIGATURE AYIN-DALETH
-10F28..10F2F  ; R # Cn   [8] ..
 10F70..10F81  ; R # Lo  [18] OLD UYGHUR LETTER ALEPH..OLD UYGHUR LETTER LESH
 10F86..10F89  ; R # Po   [4] OLD UYGHUR PUNCTUATION BAR..OLD UYGHUR PUNCTUATION FOUR DOTS
-10F8A..10FAF  ; R # Cn  [38] ..
 10FB0..10FC4  ; R # Lo  [21] CHORASMIAN LETTER ALEPH..CHORASMIAN LETTER TAW
 10FC5..10FCB  ; R # No   [7] CHORASMIAN NUMBER ONE..CHORASMIAN NUMBER ONE HUNDRED
-10FCC..10FDF  ; R # Cn  [20] ..
 10FE0..10FF6  ; R # Lo  [23] ELYMAIC LETTER ALEPH..ELYMAIC LIGATURE ZAYIN-YODH
-10FF7..10FFF  ; R # Cn   [9] ..
 1E800..1E8C4  ; R # Lo [197] MENDE KIKAKUI SYLLABLE M001 KI..MENDE KIKAKUI SYLLABLE M060 NYON
-1E8C5..1E8C6  ; R # Cn   [2] ..
 1E8C7..1E8CF  ; R # No   [9] MENDE KIKAKUI DIGIT ONE..MENDE KIKAKUI DIGIT NINE
-1E8D7..1E8FF  ; R # Cn  [41] ..
 1E900..1E943  ; R # L&  [68] ADLAM CAPITAL LETTER ALIF..ADLAM SMALL LETTER SHA
 1E94B         ; R # Lm       ADLAM NASALIZATION MARK
-1E94C..1E94F  ; R # Cn   [4] ..
 1E950..1E959  ; R # Nd  [10] ADLAM DIGIT ZERO..ADLAM DIGIT NINE
-1E95A..1E95D  ; R # Cn   [4] ..
 1E95E..1E95F  ; R # Po   [2] ADLAM INITIAL EXCLAMATION MARK..ADLAM INITIAL QUESTION MARK
-1E960..1EC6F  ; R # Cn [784] ..
-1ECC0..1ECFF  ; R # Cn  [64] ..
-1ED50..1EDFF  ; R # Cn [176] ..
-1EF00..1EFFF  ; R # Cn [256] ..
 
-# Total code points: 3711
+# The above property value applies to 2156 code points not listed here.
+# Total code points: 3647
 
 # ================================================
 
@@ -1313,7 +1348,6 @@ FF0D          ; ES # Pd       FULLWIDTH HYPHEN-MINUS
 17DB          ; ET # Sc       KHMER CURRENCY SYMBOL RIEL
 2030..2034    ; ET # Po   [5] PER MILLE SIGN..TRIPLE PRIME
 20A0..20C0    ; ET # Sc  [33] EURO-CURRENCY SIGN..SOM SIGN
-20C1..20CF    ; ET # Cn  [15] ..
 212E          ; ET # So       ESTIMATED SYMBOL
 2213          ; ET # Sm       MINUS-OR-PLUS SIGN
 A838          ; ET # Sc       NORTH INDIC RUPEE MARK
@@ -1329,6 +1363,7 @@ FFE5..FFE6    ; ET # Sc   [2] FULLWIDTH YEN SIGN..FULLWIDTH WON SIGN
 11FDD..11FE0  ; ET # Sc   [4] TAMIL SIGN KAACU..TAMIL SIGN VARAAKAN
 1E2FF         ; ET # Sc       WANCHO NGUN SIGN
 
+# The above property value applies to 15 code points not listed here.
 # Total code points: 92
 
 # ================================================
@@ -1887,10 +1922,10 @@ FFFC..FFFD    ; ON # So   [2] OBJECT REPLACEMENT CHARACTER..REPLACEMENT CHARACTE
 1F300..1F3FA  ; ON # So [251] CYCLONE..AMPHORA
 1F3FB..1F3FF  ; ON # Sk   [5] EMOJI MODIFIER FITZPATRICK TYPE-1-2..EMOJI MODIFIER FITZPATRICK TYPE-6
 1F400..1F6D7  ; ON # So [728] RAT..ELEVATOR
-1F6DD..1F6EC  ; ON # So  [16] PLAYGROUND SLIDE..AIRPLANE ARRIVING
+1F6DC..1F6EC  ; ON # So  [17] WIRELESS..AIRPLANE ARRIVING
 1F6F0..1F6FC  ; ON # So  [13] SATELLITE..ROLLER SKATE
-1F700..1F773  ; ON # So [116] ALCHEMICAL SYMBOL FOR QUINTESSENCE..ALCHEMICAL SYMBOL FOR HALF OUNCE
-1F780..1F7D8  ; ON # So  [89] BLACK LEFT-POINTING ISOSCELES RIGHT TRIANGLE..NEGATIVE CIRCLED SQUARE
+1F700..1F776  ; ON # So [119] ALCHEMICAL SYMBOL FOR QUINTESSENCE..LUNAR ECLIPSE
+1F77B..1F7D9  ; ON # So  [95] HAUMEA..NINE POINTED WHITE STAR
 1F7E0..1F7EB  ; ON # So  [12] LARGE ORANGE CIRCLE..LARGE BROWN SQUARE
 1F7F0         ; ON # So       HEAVY EQUALS SIGN
 1F800..1F80B  ; ON # So  [12] LEFTWARDS ARROW WITH SMALL TRIANGLE ARROWHEAD..DOWNWARDS ARROW WITH LARGE TRIANGLE ARROWHEAD
@@ -1901,19 +1936,17 @@ FFFC..FFFD    ; ON # So   [2] OBJECT REPLACEMENT CHARACTER..REPLACEMENT CHARACTE
 1F8B0..1F8B1  ; ON # So   [2] ARROW POINTING UPWARDS THEN NORTH WEST..ARROW POINTING RIGHTWARDS THEN CURVING SOUTH WEST
 1F900..1FA53  ; ON # So [340] CIRCLED CROSS FORMEE WITH FOUR DOTS..BLACK CHESS KNIGHT-BISHOP
 1FA60..1FA6D  ; ON # So  [14] XIANGQI RED GENERAL..XIANGQI BLACK SOLDIER
-1FA70..1FA74  ; ON # So   [5] BALLET SHOES..THONG SANDAL
-1FA78..1FA7C  ; ON # So   [5] DROP OF BLOOD..CRUTCH
-1FA80..1FA86  ; ON # So   [7] YO-YO..NESTING DOLLS
-1FA90..1FAAC  ; ON # So  [29] RINGED PLANET..HAMSA
-1FAB0..1FABA  ; ON # So  [11] FLY..NEST WITH EGGS
-1FAC0..1FAC5  ; ON # So   [6] ANATOMICAL HEART..PERSON WITH CROWN
-1FAD0..1FAD9  ; ON # So  [10] BLUEBERRIES..JAR
-1FAE0..1FAE7  ; ON # So   [8] MELTING FACE..BUBBLES
-1FAF0..1FAF6  ; ON # So   [7] HAND WITH INDEX FINGER AND THUMB CROSSED..HEART HANDS
+1FA70..1FA7C  ; ON # So  [13] BALLET SHOES..CRUTCH
+1FA80..1FA88  ; ON # So   [9] YO-YO..FLUTE
+1FA90..1FABD  ; ON # So  [46] RINGED PLANET..WING
+1FABF..1FAC5  ; ON # So   [7] GOOSE..PERSON WITH CROWN
+1FACE..1FADB  ; ON # So  [14] MOOSE..PEA POD
+1FAE0..1FAE8  ; ON # So   [9] MELTING FACE..SHAKING FACE
+1FAF0..1FAF8  ; ON # So   [9] HAND WITH INDEX FINGER AND THUMB CROSSED..RIGHTWARDS PUSHING HAND
 1FB00..1FB92  ; ON # So [147] BLOCK SEXTANT-1..UPPER HALF INVERSE MEDIUM SHADE AND LOWER HALF BLOCK
 1FB94..1FBCA  ; ON # So  [55] LEFT HALF INVERSE MEDIUM SHADE AND RIGHT HALF BLOCK..WHITE UP-POINTING CHEVRON
 
-# Total code points: 6000
+# Total code points: 6029
 
 # ================================================
 
@@ -2054,7 +2087,7 @@ FFFFE..FFFFF  ; BN # Cn   [2] ..
 0E47..0E4E    ; NSM # Mn   [8] THAI CHARACTER MAITAIKHU..THAI CHARACTER YAMAKKAN
 0EB1          ; NSM # Mn       LAO VOWEL SIGN MAI KAN
 0EB4..0EBC    ; NSM # Mn   [9] LAO VOWEL SIGN I..LAO SEMIVOWEL SIGN LO
-0EC8..0ECD    ; NSM # Mn   [6] LAO TONE MAI EK..LAO NIGGAHITA
+0EC8..0ECE    ; NSM # Mn   [7] LAO TONE MAI EK..LAO YAMAKKAN
 0F18..0F19    ; NSM # Mn   [2] TIBETAN ASTROLOGICAL SIGN -KHYUD PA..TIBETAN ASTROLOGICAL SIGN SDONG TSHUGS
 0F35          ; NSM # Mn       TIBETAN MARK NGAS BZUNG NYI ZLA
 0F37          ; NSM # Mn       TIBETAN MARK NGAS BZUNG SGOR RTAGS
@@ -2189,6 +2222,7 @@ FE20..FE2F    ; NSM # Mn  [16] COMBINING LIGATURE LEFT HALF..COMBINING CYRILLIC
 10AE5..10AE6  ; NSM # Mn   [2] MANICHAEAN ABBREVIATION MARK ABOVE..MANICHAEAN ABBREVIATION MARK BELOW
 10D24..10D27  ; NSM # Mn   [4] HANIFI ROHINGYA SIGN HARBAHAY..HANIFI ROHINGYA SIGN TASSI
 10EAB..10EAC  ; NSM # Mn   [2] YEZIDI COMBINING HAMZA MARK..YEZIDI COMBINING MADDA MARK
+10EFD..10EFF  ; NSM # Mn   [3] ARABIC SMALL LOW WORD SAKTA..ARABIC SMALL LOW WORD MADDA
 10F46..10F50  ; NSM # Mn  [11] SOGDIAN COMBINING DOT BELOW..SOGDIAN COMBINING STROKE BELOW
 10F82..10F85  ; NSM # Mn   [4] OLD UYGHUR COMBINING DOT ABOVE..OLD UYGHUR COMBINING TWO DOTS BELOW
 11001         ; NSM # Mn       BRAHMI SIGN ANUSVARA
@@ -2211,6 +2245,7 @@ FE20..FE2F    ; NSM # Mn  [16] COMBINING LIGATURE LEFT HALF..COMBINING CYRILLIC
 11234         ; NSM # Mn       KHOJKI SIGN ANUSVARA
 11236..11237  ; NSM # Mn   [2] KHOJKI SIGN NUKTA..KHOJKI SIGN SHADDA
 1123E         ; NSM # Mn       KHOJKI SIGN SUKUN
+11241         ; NSM # Mn       KHOJKI VOWEL SIGN VOCALIC R
 112DF         ; NSM # Mn       KHUDAWADI SIGN ANUSVARA
 112E3..112EA  ; NSM # Mn   [8] KHUDAWADI VOWEL SIGN U..KHUDAWADI SIGN VIRAMA
 11300..11301  ; NSM # Mn   [2] GRANTHA SIGN COMBINING ANUSVARA ABOVE..GRANTHA SIGN CANDRABINDU
@@ -2272,6 +2307,12 @@ FE20..FE2F    ; NSM # Mn  [16] COMBINING LIGATURE LEFT HALF..COMBINING CYRILLIC
 11D95         ; NSM # Mn       GUNJALA GONDI SIGN ANUSVARA
 11D97         ; NSM # Mn       GUNJALA GONDI VIRAMA
 11EF3..11EF4  ; NSM # Mn   [2] MAKASAR VOWEL SIGN I..MAKASAR VOWEL SIGN U
+11F00..11F01  ; NSM # Mn   [2] KAWI SIGN CANDRABINDU..KAWI SIGN ANUSVARA
+11F36..11F3A  ; NSM # Mn   [5] KAWI VOWEL SIGN I..KAWI VOWEL SIGN VOCALIC R
+11F40         ; NSM # Mn       KAWI VOWEL SIGN EU
+11F42         ; NSM # Mn       KAWI CONJOINER
+13440         ; NSM # Mn       EGYPTIAN HIEROGLYPH MIRROR HORIZONTALLY
+13447..13455  ; NSM # Mn  [15] EGYPTIAN HIEROGLYPH MODIFIER DAMAGED AT TOP START..EGYPTIAN HIEROGLYPH MODIFIER DAMAGED
 16AF0..16AF4  ; NSM # Mn   [5] BASSA VAH COMBINING HIGH TONE..BASSA VAH COMBINING HIGH-LOW TONE
 16B30..16B36  ; NSM # Mn   [7] PAHAWH HMONG MARK CIM TUB..PAHAWH HMONG MARK CIM TAUM
 16F4F         ; NSM # Mn       MIAO SIGN CONSONANT MODIFIER BAR
@@ -2296,14 +2337,16 @@ FE20..FE2F    ; NSM # Mn  [16] COMBINING LIGATURE LEFT HALF..COMBINING CYRILLIC
 1E01B..1E021  ; NSM # Mn   [7] COMBINING GLAGOLITIC LETTER SHTA..COMBINING GLAGOLITIC LETTER YATI
 1E023..1E024  ; NSM # Mn   [2] COMBINING GLAGOLITIC LETTER YU..COMBINING GLAGOLITIC LETTER SMALL YUS
 1E026..1E02A  ; NSM # Mn   [5] COMBINING GLAGOLITIC LETTER YO..COMBINING GLAGOLITIC LETTER FITA
+1E08F         ; NSM # Mn       COMBINING CYRILLIC SMALL LETTER BYELORUSSIAN-UKRAINIAN I
 1E130..1E136  ; NSM # Mn   [7] NYIAKENG PUACHUE HMONG TONE-B..NYIAKENG PUACHUE HMONG TONE-D
 1E2AE         ; NSM # Mn       TOTO SIGN RISING TONE
 1E2EC..1E2EF  ; NSM # Mn   [4] WANCHO TONE TUP..WANCHO TONE KOINI
+1E4EC..1E4EF  ; NSM # Mn   [4] NAG MUNDARI SIGN MUHOR..NAG MUNDARI SIGN SUTUH
 1E8D0..1E8D6  ; NSM # Mn   [7] MENDE KIKAKUI COMBINING NUMBER TEENS..MENDE KIKAKUI COMBINING NUMBER MILLIONS
 1E944..1E94A  ; NSM # Mn   [7] ADLAM ALIF LENGTHENER..ADLAM NUKTA
 E0100..E01EF  ; NSM # Mn [240] VARIATION SELECTOR-17..VARIATION SELECTOR-256
 
-# Total code points: 1958
+# Total code points: 1993
 
 # ================================================
 
@@ -2329,125 +2372,74 @@ E0100..E01EF  ; NSM # Mn [240] VARIATION SELECTOR-17..VARIATION SELECTOR-256
 06FD..06FE    ; AL # So   [2] ARABIC SIGN SINDHI AMPERSAND..ARABIC SIGN SINDHI POSTPOSITION MEN
 06FF          ; AL # Lo       ARABIC LETTER HEH WITH INVERTED V
 0700..070D    ; AL # Po  [14] SYRIAC END OF PARAGRAPH..SYRIAC HARKLEAN ASTERISCUS
-070E          ; AL # Cn       
 070F          ; AL # Cf       SYRIAC ABBREVIATION MARK
 0710          ; AL # Lo       SYRIAC LETTER ALAPH
 0712..072F    ; AL # Lo  [30] SYRIAC LETTER BETH..SYRIAC LETTER PERSIAN DHALATH
-074B..074C    ; AL # Cn   [2] ..
 074D..07A5    ; AL # Lo  [89] SYRIAC LETTER SOGDIAN ZHAIN..THAANA LETTER WAAVU
 07B1          ; AL # Lo       THAANA LETTER NAA
-07B2..07BF    ; AL # Cn  [14] ..
 0860..086A    ; AL # Lo  [11] SYRIAC LETTER MALAYALAM NGA..SYRIAC LETTER MALAYALAM SSA
-086B..086F    ; AL # Cn   [5] ..
 0870..0887    ; AL # Lo  [24] ARABIC LETTER ALEF WITH ATTACHED FATHA..ARABIC BASELINE ROUND DOT
 0888          ; AL # Sk       ARABIC RAISED ROUND DOT
 0889..088E    ; AL # Lo   [6] ARABIC LETTER NOON WITH INVERTED SMALL V..ARABIC VERTICAL TAIL
-088F          ; AL # Cn       
-0892..0897    ; AL # Cn   [6] ..
 08A0..08C8    ; AL # Lo  [41] ARABIC LETTER BEH WITH SMALL V BELOW..ARABIC LETTER GRAF
 08C9          ; AL # Lm       ARABIC SMALL FARSI YEH
 FB50..FBB1    ; AL # Lo  [98] ARABIC LETTER ALEF WASLA ISOLATED FORM..ARABIC LETTER YEH BARREE WITH HAMZA ABOVE FINAL FORM
 FBB2..FBC2    ; AL # Sk  [17] ARABIC SYMBOL DOT ABOVE..ARABIC SYMBOL WASLA ABOVE
-FBC3..FBD2    ; AL # Cn  [16] ..
 FBD3..FD3D    ; AL # Lo [363] ARABIC LETTER NG ISOLATED FORM..ARABIC LIGATURE ALEF WITH FATHATAN ISOLATED FORM
 FD50..FD8F    ; AL # Lo  [64] ARABIC LIGATURE TEH WITH JEEM WITH MEEM INITIAL FORM..ARABIC LIGATURE MEEM WITH KHAH WITH MEEM INITIAL FORM
-FD90..FD91    ; AL # Cn   [2] ..
 FD92..FDC7    ; AL # Lo  [54] ARABIC LIGATURE MEEM WITH JEEM WITH KHAH INITIAL FORM..ARABIC LIGATURE NOON WITH JEEM WITH YEH FINAL FORM
-FDC8..FDCE    ; AL # Cn   [7] ..
 FDF0..FDFB    ; AL # Lo  [12] ARABIC LIGATURE SALLA USED AS KORANIC STOP SIGN ISOLATED FORM..ARABIC LIGATURE JALLAJALALOUHOU
 FDFC          ; AL # Sc       RIAL SIGN
 FE70..FE74    ; AL # Lo   [5] ARABIC FATHATAN ISOLATED FORM..ARABIC KASRATAN ISOLATED FORM
-FE75          ; AL # Cn       
 FE76..FEFC    ; AL # Lo [135] ARABIC FATHA ISOLATED FORM..ARABIC LIGATURE LAM WITH ALEF FINAL FORM
-FEFD..FEFE    ; AL # Cn   [2] ..
 10D00..10D23  ; AL # Lo  [36] HANIFI ROHINGYA LETTER A..HANIFI ROHINGYA MARK NA KHONNA
-10D28..10D2F  ; AL # Cn   [8] ..
-10D3A..10D3F  ; AL # Cn   [6] ..
 10F30..10F45  ; AL # Lo  [22] SOGDIAN LETTER ALEPH..SOGDIAN INDEPENDENT SHIN
 10F51..10F54  ; AL # No   [4] SOGDIAN NUMBER ONE..SOGDIAN NUMBER ONE HUNDRED
 10F55..10F59  ; AL # Po   [5] SOGDIAN PUNCTUATION TWO VERTICAL BARS..SOGDIAN PUNCTUATION HALF CIRCLE WITH DOT
-10F5A..10F6F  ; AL # Cn  [22] ..
-1EC70         ; AL # Cn       
 1EC71..1ECAB  ; AL # No  [59] INDIC SIYAQ NUMBER ONE..INDIC SIYAQ NUMBER PREFIXED NINE
 1ECAC         ; AL # So       INDIC SIYAQ PLACEHOLDER
 1ECAD..1ECAF  ; AL # No   [3] INDIC SIYAQ FRACTION ONE QUARTER..INDIC SIYAQ FRACTION THREE QUARTERS
 1ECB0         ; AL # Sc       INDIC SIYAQ RUPEE MARK
 1ECB1..1ECB4  ; AL # No   [4] INDIC SIYAQ NUMBER ALTERNATE ONE..INDIC SIYAQ ALTERNATE LAKH MARK
-1ECB5..1ECBF  ; AL # Cn  [11] ..
-1ED00         ; AL # Cn       
 1ED01..1ED2D  ; AL # No  [45] OTTOMAN SIYAQ NUMBER ONE..OTTOMAN SIYAQ NUMBER NINETY THOUSAND
 1ED2E         ; AL # So       OTTOMAN SIYAQ MARRATAN
 1ED2F..1ED3D  ; AL # No  [15] OTTOMAN SIYAQ ALTERNATE NUMBER TWO..OTTOMAN SIYAQ FRACTION ONE SIXTH
-1ED3E..1ED4F  ; AL # Cn  [18] ..
 1EE00..1EE03  ; AL # Lo   [4] ARABIC MATHEMATICAL ALEF..ARABIC MATHEMATICAL DAL
-1EE04         ; AL # Cn       
 1EE05..1EE1F  ; AL # Lo  [27] ARABIC MATHEMATICAL WAW..ARABIC MATHEMATICAL DOTLESS QAF
-1EE20         ; AL # Cn       
 1EE21..1EE22  ; AL # Lo   [2] ARABIC MATHEMATICAL INITIAL BEH..ARABIC MATHEMATICAL INITIAL JEEM
-1EE23         ; AL # Cn       
 1EE24         ; AL # Lo       ARABIC MATHEMATICAL INITIAL HEH
-1EE25..1EE26  ; AL # Cn   [2] ..
 1EE27         ; AL # Lo       ARABIC MATHEMATICAL INITIAL HAH
-1EE28         ; AL # Cn       
 1EE29..1EE32  ; AL # Lo  [10] ARABIC MATHEMATICAL INITIAL YEH..ARABIC MATHEMATICAL INITIAL QAF
-1EE33         ; AL # Cn       
 1EE34..1EE37  ; AL # Lo   [4] ARABIC MATHEMATICAL INITIAL SHEEN..ARABIC MATHEMATICAL INITIAL KHAH
-1EE38         ; AL # Cn       
 1EE39         ; AL # Lo       ARABIC MATHEMATICAL INITIAL DAD
-1EE3A         ; AL # Cn       
 1EE3B         ; AL # Lo       ARABIC MATHEMATICAL INITIAL GHAIN
-1EE3C..1EE41  ; AL # Cn   [6] ..
 1EE42         ; AL # Lo       ARABIC MATHEMATICAL TAILED JEEM
-1EE43..1EE46  ; AL # Cn   [4] ..
 1EE47         ; AL # Lo       ARABIC MATHEMATICAL TAILED HAH
-1EE48         ; AL # Cn       
 1EE49         ; AL # Lo       ARABIC MATHEMATICAL TAILED YEH
-1EE4A         ; AL # Cn       
 1EE4B         ; AL # Lo       ARABIC MATHEMATICAL TAILED LAM
-1EE4C         ; AL # Cn       
 1EE4D..1EE4F  ; AL # Lo   [3] ARABIC MATHEMATICAL TAILED NOON..ARABIC MATHEMATICAL TAILED AIN
-1EE50         ; AL # Cn       
 1EE51..1EE52  ; AL # Lo   [2] ARABIC MATHEMATICAL TAILED SAD..ARABIC MATHEMATICAL TAILED QAF
-1EE53         ; AL # Cn       
 1EE54         ; AL # Lo       ARABIC MATHEMATICAL TAILED SHEEN
-1EE55..1EE56  ; AL # Cn   [2] ..
 1EE57         ; AL # Lo       ARABIC MATHEMATICAL TAILED KHAH
-1EE58         ; AL # Cn       
 1EE59         ; AL # Lo       ARABIC MATHEMATICAL TAILED DAD
-1EE5A         ; AL # Cn       
 1EE5B         ; AL # Lo       ARABIC MATHEMATICAL TAILED GHAIN
-1EE5C         ; AL # Cn       
 1EE5D         ; AL # Lo       ARABIC MATHEMATICAL TAILED DOTLESS NOON
-1EE5E         ; AL # Cn       
 1EE5F         ; AL # Lo       ARABIC MATHEMATICAL TAILED DOTLESS QAF
-1EE60         ; AL # Cn       
 1EE61..1EE62  ; AL # Lo   [2] ARABIC MATHEMATICAL STRETCHED BEH..ARABIC MATHEMATICAL STRETCHED JEEM
-1EE63         ; AL # Cn       
 1EE64         ; AL # Lo       ARABIC MATHEMATICAL STRETCHED HEH
-1EE65..1EE66  ; AL # Cn   [2] ..
 1EE67..1EE6A  ; AL # Lo   [4] ARABIC MATHEMATICAL STRETCHED HAH..ARABIC MATHEMATICAL STRETCHED KAF
-1EE6B         ; AL # Cn       
 1EE6C..1EE72  ; AL # Lo   [7] ARABIC MATHEMATICAL STRETCHED MEEM..ARABIC MATHEMATICAL STRETCHED QAF
-1EE73         ; AL # Cn       
 1EE74..1EE77  ; AL # Lo   [4] ARABIC MATHEMATICAL STRETCHED SHEEN..ARABIC MATHEMATICAL STRETCHED KHAH
-1EE78         ; AL # Cn       
 1EE79..1EE7C  ; AL # Lo   [4] ARABIC MATHEMATICAL STRETCHED DAD..ARABIC MATHEMATICAL STRETCHED DOTLESS BEH
-1EE7D         ; AL # Cn       
 1EE7E         ; AL # Lo       ARABIC MATHEMATICAL STRETCHED DOTLESS FEH
-1EE7F         ; AL # Cn       
 1EE80..1EE89  ; AL # Lo  [10] ARABIC MATHEMATICAL LOOPED ALEF..ARABIC MATHEMATICAL LOOPED YEH
-1EE8A         ; AL # Cn       
 1EE8B..1EE9B  ; AL # Lo  [17] ARABIC MATHEMATICAL LOOPED LAM..ARABIC MATHEMATICAL LOOPED GHAIN
-1EE9C..1EEA0  ; AL # Cn   [5] ..
 1EEA1..1EEA3  ; AL # Lo   [3] ARABIC MATHEMATICAL DOUBLE-STRUCK BEH..ARABIC MATHEMATICAL DOUBLE-STRUCK DAL
-1EEA4         ; AL # Cn       
 1EEA5..1EEA9  ; AL # Lo   [5] ARABIC MATHEMATICAL DOUBLE-STRUCK WAW..ARABIC MATHEMATICAL DOUBLE-STRUCK YEH
-1EEAA         ; AL # Cn       
 1EEAB..1EEBB  ; AL # Lo  [17] ARABIC MATHEMATICAL DOUBLE-STRUCK LAM..ARABIC MATHEMATICAL DOUBLE-STRUCK GHAIN
-1EEBC..1EEEF  ; AL # Cn  [52] ..
-1EEF2..1EEFF  ; AL # Cn  [14] ..
 
-# Total code points: 1708
+# The above property value applies to 298 code points not listed here.
+# Total code points: 1769
 
 # ================================================
 
diff --git a/pcre2/maint/Unicode.tables/DerivedCoreProperties.txt b/pcre2/maint/Unicode.tables/DerivedCoreProperties.txt
index afc2abd..8b482b5 100644
--- a/pcre2/maint/Unicode.tables/DerivedCoreProperties.txt
+++ b/pcre2/maint/Unicode.tables/DerivedCoreProperties.txt
@@ -1,11 +1,11 @@
-# DerivedCoreProperties-14.0.0.txt
-# Date: 2021-08-12, 23:12:53 GMT
-# © 2021 Unicode®, Inc.
+# DerivedCoreProperties-15.0.0.txt
+# Date: 2022-08-05, 22:17:05 GMT
+# © 2022 Unicode®, Inc.
 # Unicode and the Unicode Logo are registered trademarks of Unicode, Inc. in the U.S. and other countries.
-# For terms of use, see http://www.unicode.org/terms_of_use.html
+# For terms of use, see https://www.unicode.org/terms_of_use.html
 #
 # Unicode Character Database
-#   For documentation, see http://www.unicode.org/reports/tr44/
+#   For documentation, see https://www.unicode.org/reports/tr44/
 
 # ================================================
 
@@ -462,6 +462,7 @@ FFE9..FFEC    ; Math # Sm   [4] HALFWIDTH LEFTWARDS ARROW..HALFWIDTH DOWNWARDS A
 0BD7          ; Alphabetic # Mc       TAMIL AU LENGTH MARK
 0C00          ; Alphabetic # Mn       TELUGU SIGN COMBINING CANDRABINDU ABOVE
 0C01..0C03    ; Alphabetic # Mc   [3] TELUGU SIGN CANDRABINDU..TELUGU SIGN VISARGA
+0C04          ; Alphabetic # Mn       TELUGU SIGN COMBINING ANUSVARA ABOVE
 0C05..0C0C    ; Alphabetic # Lo   [8] TELUGU LETTER A..TELUGU LETTER VOCALIC L
 0C0E..0C10    ; Alphabetic # Lo   [3] TELUGU LETTER E..TELUGU LETTER AI
 0C12..0C28    ; Alphabetic # Lo  [23] TELUGU LETTER O..TELUGU LETTER NA
@@ -497,6 +498,7 @@ FFE9..FFEC    ; Math # Sm   [4] HALFWIDTH LEFTWARDS ARROW..HALFWIDTH DOWNWARDS A
 0CE0..0CE1    ; Alphabetic # Lo   [2] KANNADA LETTER VOCALIC RR..KANNADA LETTER VOCALIC LL
 0CE2..0CE3    ; Alphabetic # Mn   [2] KANNADA VOWEL SIGN VOCALIC L..KANNADA VOWEL SIGN VOCALIC LL
 0CF1..0CF2    ; Alphabetic # Lo   [2] KANNADA SIGN JIHVAMULIYA..KANNADA SIGN UPADHMANIYA
+0CF3          ; Alphabetic # Mc       KANNADA SIGN COMBINING ANUSVARA ABOVE RIGHT
 0D00..0D01    ; Alphabetic # Mn   [2] MALAYALAM SIGN COMBINING ANUSVARA ABOVE..MALAYALAM SIGN CANDRABINDU
 0D02..0D03    ; Alphabetic # Mc   [2] MALAYALAM SIGN ANUSVARA..MALAYALAM SIGN VISARGA
 0D04..0D0C    ; Alphabetic # Lo   [9] MALAYALAM LETTER VEDIC ANUSVARA..MALAYALAM LETTER VOCALIC L
@@ -552,7 +554,7 @@ FFE9..FFEC    ; Math # Sm   [4] HALFWIDTH LEFTWARDS ARROW..HALFWIDTH DOWNWARDS A
 0F49..0F6C    ; Alphabetic # Lo  [36] TIBETAN LETTER NYA..TIBETAN LETTER RRA
 0F71..0F7E    ; Alphabetic # Mn  [14] TIBETAN VOWEL SIGN AA..TIBETAN SIGN RJES SU NGA RO
 0F7F          ; Alphabetic # Mc       TIBETAN SIGN RNAM BCAD
-0F80..0F81    ; Alphabetic # Mn   [2] TIBETAN VOWEL SIGN REVERSED I..TIBETAN VOWEL SIGN REVERSED II
+0F80..0F83    ; Alphabetic # Mn   [4] TIBETAN VOWEL SIGN REVERSED I..TIBETAN SIGN SNA LDAN
 0F88..0F8C    ; Alphabetic # Lo   [5] TIBETAN SIGN LCE TSA CAN..TIBETAN SIGN INVERTED MCHU CAN
 0F8D..0F97    ; Alphabetic # Mn  [11] TIBETAN SUBJOINED SIGN LCE TSA CAN..TIBETAN SUBJOINED LETTER JA
 0F99..0FBC    ; Alphabetic # Mn  [36] TIBETAN SUBJOINED LETTER NYA..TIBETAN SUBJOINED LETTER FIXED-FORM RA
@@ -1053,6 +1055,7 @@ FFDA..FFDC    ; Alphabetic # Lo   [3] HALFWIDTH HANGUL LETTER EU..HALFWIDTH HANG
 11071..11072  ; Alphabetic # Lo   [2] BRAHMI LETTER OLD TAMIL SHORT E..BRAHMI LETTER OLD TAMIL SHORT O
 11073..11074  ; Alphabetic # Mn   [2] BRAHMI VOWEL SIGN OLD TAMIL SHORT E..BRAHMI VOWEL SIGN OLD TAMIL SHORT O
 11075         ; Alphabetic # Lo       BRAHMI LETTER OLD TAMIL LLA
+11080..11081  ; Alphabetic # Mn   [2] KAITHI SIGN CANDRABINDU..KAITHI SIGN ANUSVARA
 11082         ; Alphabetic # Mc       KAITHI SIGN VISARGA
 11083..110AF  ; Alphabetic # Lo  [45] KAITHI LETTER A..KAITHI LETTER HA
 110B0..110B2  ; Alphabetic # Mc   [3] KAITHI VOWEL SIGN AA..KAITHI VOWEL SIGN II
@@ -1089,6 +1092,8 @@ FFDA..FFDC    ; Alphabetic # Lo   [3] HALFWIDTH HANGUL LETTER EU..HALFWIDTH HANG
 11234         ; Alphabetic # Mn       KHOJKI SIGN ANUSVARA
 11237         ; Alphabetic # Mn       KHOJKI SIGN SHADDA
 1123E         ; Alphabetic # Mn       KHOJKI SIGN SUKUN
+1123F..11240  ; Alphabetic # Lo   [2] KHOJKI LETTER QA..KHOJKI LETTER SHORT I
+11241         ; Alphabetic # Mn       KHOJKI VOWEL SIGN VOCALIC R
 11280..11286  ; Alphabetic # Lo   [7] MULTANI LETTER A..MULTANI LETTER GA
 11288         ; Alphabetic # Lo       MULTANI LETTER GHA
 1128A..1128D  ; Alphabetic # Lo   [4] MULTANI LETTER CA..MULTANI LETTER JJA
@@ -1243,12 +1248,22 @@ FFDA..FFDC    ; Alphabetic # Lo   [3] HALFWIDTH HANGUL LETTER EU..HALFWIDTH HANG
 11EE0..11EF2  ; Alphabetic # Lo  [19] MAKASAR LETTER KA..MAKASAR ANGKA
 11EF3..11EF4  ; Alphabetic # Mn   [2] MAKASAR VOWEL SIGN I..MAKASAR VOWEL SIGN U
 11EF5..11EF6  ; Alphabetic # Mc   [2] MAKASAR VOWEL SIGN E..MAKASAR VOWEL SIGN O
+11F00..11F01  ; Alphabetic # Mn   [2] KAWI SIGN CANDRABINDU..KAWI SIGN ANUSVARA
+11F02         ; Alphabetic # Lo       KAWI SIGN REPHA
+11F03         ; Alphabetic # Mc       KAWI SIGN VISARGA
+11F04..11F10  ; Alphabetic # Lo  [13] KAWI LETTER A..KAWI LETTER O
+11F12..11F33  ; Alphabetic # Lo  [34] KAWI LETTER KA..KAWI LETTER JNYA
+11F34..11F35  ; Alphabetic # Mc   [2] KAWI VOWEL SIGN AA..KAWI VOWEL SIGN ALTERNATE AA
+11F36..11F3A  ; Alphabetic # Mn   [5] KAWI VOWEL SIGN I..KAWI VOWEL SIGN VOCALIC R
+11F3E..11F3F  ; Alphabetic # Mc   [2] KAWI VOWEL SIGN E..KAWI VOWEL SIGN AI
+11F40         ; Alphabetic # Mn       KAWI VOWEL SIGN EU
 11FB0         ; Alphabetic # Lo       LISU LETTER YHA
 12000..12399  ; Alphabetic # Lo [922] CUNEIFORM SIGN A..CUNEIFORM SIGN U U
 12400..1246E  ; Alphabetic # Nl [111] CUNEIFORM NUMERIC SIGN TWO ASH..CUNEIFORM NUMERIC SIGN NINE U VARIANT FORM
 12480..12543  ; Alphabetic # Lo [196] CUNEIFORM SIGN AB TIMES NUN TENU..CUNEIFORM SIGN ZU5 TIMES THREE DISH TENU
 12F90..12FF0  ; Alphabetic # Lo  [97] CYPRO-MINOAN SIGN CM001..CYPRO-MINOAN SIGN CM114
-13000..1342E  ; Alphabetic # Lo [1071] EGYPTIAN HIEROGLYPH A001..EGYPTIAN HIEROGLYPH AA032
+13000..1342F  ; Alphabetic # Lo [1072] EGYPTIAN HIEROGLYPH A001..EGYPTIAN HIEROGLYPH V011D
+13441..13446  ; Alphabetic # Lo   [6] EGYPTIAN HIEROGLYPH FULL BLANK..EGYPTIAN HIEROGLYPH WIDE LOST SIGN
 14400..14646  ; Alphabetic # Lo [583] ANATOLIAN HIEROGLYPH A001..ANATOLIAN HIEROGLYPH A530
 16800..16A38  ; Alphabetic # Lo [569] BAMUM LETTER PHASE-A NGKUE MFON..BAMUM LETTER PHASE-F VUEQ
 16A40..16A5E  ; Alphabetic # Lo  [31] MRO LETTER TA..MRO LETTER TEK
@@ -1275,7 +1290,9 @@ FFDA..FFDC    ; Alphabetic # Lo   [3] HALFWIDTH HANGUL LETTER EU..HALFWIDTH HANG
 1AFF5..1AFFB  ; Alphabetic # Lm   [7] KATAKANA LETTER MINNAN TONE-7..KATAKANA LETTER MINNAN NASALIZED TONE-5
 1AFFD..1AFFE  ; Alphabetic # Lm   [2] KATAKANA LETTER MINNAN NASALIZED TONE-7..KATAKANA LETTER MINNAN NASALIZED TONE-8
 1B000..1B122  ; Alphabetic # Lo [291] KATAKANA LETTER ARCHAIC E..KATAKANA LETTER ARCHAIC WU
+1B132         ; Alphabetic # Lo       HIRAGANA LETTER SMALL KO
 1B150..1B152  ; Alphabetic # Lo   [3] HIRAGANA LETTER SMALL WI..HIRAGANA LETTER SMALL WO
+1B155         ; Alphabetic # Lo       KATAKANA LETTER SMALL KO
 1B164..1B167  ; Alphabetic # Lo   [4] KATAKANA LETTER SMALL WI..KATAKANA LETTER SMALL N
 1B170..1B2FB  ; Alphabetic # Lo [396] NUSHU CHARACTER-1B170..NUSHU CHARACTER-1B2FB
 1BC00..1BC6A  ; Alphabetic # Lo [107] DUPLOYAN LETTER H..DUPLOYAN LETTER VOCALIC M
@@ -1316,16 +1333,21 @@ FFDA..FFDC    ; Alphabetic # Lo   [3] HALFWIDTH HANGUL LETTER EU..HALFWIDTH HANG
 1DF00..1DF09  ; Alphabetic # L&  [10] LATIN SMALL LETTER FENG DIGRAPH WITH TRILL..LATIN SMALL LETTER T WITH HOOK AND RETROFLEX HOOK
 1DF0A         ; Alphabetic # Lo       LATIN LETTER RETROFLEX CLICK WITH RETROFLEX HOOK
 1DF0B..1DF1E  ; Alphabetic # L&  [20] LATIN SMALL LETTER ESH WITH DOUBLE BAR..LATIN SMALL LETTER S WITH CURL
+1DF25..1DF2A  ; Alphabetic # L&   [6] LATIN SMALL LETTER D WITH MID-HEIGHT LEFT HOOK..LATIN SMALL LETTER T WITH MID-HEIGHT LEFT HOOK
 1E000..1E006  ; Alphabetic # Mn   [7] COMBINING GLAGOLITIC LETTER AZU..COMBINING GLAGOLITIC LETTER ZHIVETE
 1E008..1E018  ; Alphabetic # Mn  [17] COMBINING GLAGOLITIC LETTER ZEMLJA..COMBINING GLAGOLITIC LETTER HERU
 1E01B..1E021  ; Alphabetic # Mn   [7] COMBINING GLAGOLITIC LETTER SHTA..COMBINING GLAGOLITIC LETTER YATI
 1E023..1E024  ; Alphabetic # Mn   [2] COMBINING GLAGOLITIC LETTER YU..COMBINING GLAGOLITIC LETTER SMALL YUS
 1E026..1E02A  ; Alphabetic # Mn   [5] COMBINING GLAGOLITIC LETTER YO..COMBINING GLAGOLITIC LETTER FITA
+1E030..1E06D  ; Alphabetic # Lm  [62] MODIFIER LETTER CYRILLIC SMALL A..MODIFIER LETTER CYRILLIC SMALL STRAIGHT U WITH STROKE
+1E08F         ; Alphabetic # Mn       COMBINING CYRILLIC SMALL LETTER BYELORUSSIAN-UKRAINIAN I
 1E100..1E12C  ; Alphabetic # Lo  [45] NYIAKENG PUACHUE HMONG LETTER MA..NYIAKENG PUACHUE HMONG LETTER W
 1E137..1E13D  ; Alphabetic # Lm   [7] NYIAKENG PUACHUE HMONG SIGN FOR PERSON..NYIAKENG PUACHUE HMONG SYLLABLE LENGTHENER
 1E14E         ; Alphabetic # Lo       NYIAKENG PUACHUE HMONG LOGOGRAM NYAJ
 1E290..1E2AD  ; Alphabetic # Lo  [30] TOTO LETTER PA..TOTO LETTER A
 1E2C0..1E2EB  ; Alphabetic # Lo  [44] WANCHO LETTER AA..WANCHO LETTER YIH
+1E4D0..1E4EA  ; Alphabetic # Lo  [27] NAG MUNDARI LETTER O..NAG MUNDARI LETTER ELL
+1E4EB         ; Alphabetic # Lm       NAG MUNDARI SIGN OJOD
 1E7E0..1E7E6  ; Alphabetic # Lo   [7] ETHIOPIC SYLLABLE HHYA..ETHIOPIC SYLLABLE HHYO
 1E7E8..1E7EB  ; Alphabetic # Lo   [4] ETHIOPIC SYLLABLE GURAGE HHWA..ETHIOPIC SYLLABLE HHWE
 1E7ED..1E7EE  ; Alphabetic # Lo   [2] ETHIOPIC SYLLABLE GURAGE MWI..ETHIOPIC SYLLABLE GURAGE MWEE
@@ -1371,14 +1393,15 @@ FFDA..FFDC    ; Alphabetic # Lo   [3] HALFWIDTH HANGUL LETTER EU..HALFWIDTH HANG
 1F150..1F169  ; Alphabetic # So  [26] NEGATIVE CIRCLED LATIN CAPITAL LETTER A..NEGATIVE CIRCLED LATIN CAPITAL LETTER Z
 1F170..1F189  ; Alphabetic # So  [26] NEGATIVE SQUARED LATIN CAPITAL LETTER A..NEGATIVE SQUARED LATIN CAPITAL LETTER Z
 20000..2A6DF  ; Alphabetic # Lo [42720] CJK UNIFIED IDEOGRAPH-20000..CJK UNIFIED IDEOGRAPH-2A6DF
-2A700..2B738  ; Alphabetic # Lo [4153] CJK UNIFIED IDEOGRAPH-2A700..CJK UNIFIED IDEOGRAPH-2B738
+2A700..2B739  ; Alphabetic # Lo [4154] CJK UNIFIED IDEOGRAPH-2A700..CJK UNIFIED IDEOGRAPH-2B739
 2B740..2B81D  ; Alphabetic # Lo [222] CJK UNIFIED IDEOGRAPH-2B740..CJK UNIFIED IDEOGRAPH-2B81D
 2B820..2CEA1  ; Alphabetic # Lo [5762] CJK UNIFIED IDEOGRAPH-2B820..CJK UNIFIED IDEOGRAPH-2CEA1
 2CEB0..2EBE0  ; Alphabetic # Lo [7473] CJK UNIFIED IDEOGRAPH-2CEB0..CJK UNIFIED IDEOGRAPH-2EBE0
 2F800..2FA1D  ; Alphabetic # Lo [542] CJK COMPATIBILITY IDEOGRAPH-2F800..CJK COMPATIBILITY IDEOGRAPH-2FA1D
 30000..3134A  ; Alphabetic # Lo [4939] CJK UNIFIED IDEOGRAPH-30000..CJK UNIFIED IDEOGRAPH-3134A
+31350..323AF  ; Alphabetic # Lo [4192] CJK UNIFIED IDEOGRAPH-31350..CJK UNIFIED IDEOGRAPH-323AF
 
-# Total code points: 133396
+# Total code points: 137765
 
 # ================================================
 
@@ -1663,6 +1686,7 @@ FFDA..FFDC    ; Alphabetic # Lo   [3] HALFWIDTH HANGUL LETTER EU..HALFWIDTH HANG
 052F          ; Lowercase # L&       CYRILLIC SMALL LETTER EL WITH DESCENDER
 0560..0588    ; Lowercase # L&  [41] ARMENIAN SMALL LETTER TURNED AYB..ARMENIAN SMALL LETTER YI WITH STROKE
 10D0..10FA    ; Lowercase # L&  [43] GEORGIAN LETTER AN..GEORGIAN LETTER AIN
+10FC          ; Lowercase # Lm       MODIFIER LETTER GEORGIAN NAR
 10FD..10FF    ; Lowercase # L&   [3] GEORGIAN LETTER AEN..GEORGIAN LETTER LABIAL SIGN
 13F8..13FD    ; Lowercase # L&   [6] CHEROKEE SMALL LETTER YE..CHEROKEE SMALL LETTER MV
 1C80..1C88    ; Lowercase # L&   [9] CYRILLIC SMALL LETTER ROUNDED VE..CYRILLIC SMALL LETTER UNBLENDED UK
@@ -2012,12 +2036,14 @@ A7D3          ; Lowercase # L&       LATIN SMALL LETTER DOUBLE THORN
 A7D5          ; Lowercase # L&       LATIN SMALL LETTER DOUBLE WYNN
 A7D7          ; Lowercase # L&       LATIN SMALL LETTER MIDDLE SCOTS S
 A7D9          ; Lowercase # L&       LATIN SMALL LETTER SIGMOID S
+A7F2..A7F4    ; Lowercase # Lm   [3] MODIFIER LETTER CAPITAL C..MODIFIER LETTER CAPITAL Q
 A7F6          ; Lowercase # L&       LATIN SMALL LETTER REVERSED HALF H
 A7F8..A7F9    ; Lowercase # Lm   [2] MODIFIER LETTER CAPITAL H WITH STROKE..MODIFIER LETTER SMALL LIGATURE OE
 A7FA          ; Lowercase # L&       LATIN LETTER SMALL CAPITAL TURNED M
 AB30..AB5A    ; Lowercase # L&  [43] LATIN SMALL LETTER BARRED ALPHA..LATIN SMALL LETTER Y WITH SHORT RIGHT LEG
 AB5C..AB5F    ; Lowercase # Lm   [4] MODIFIER LETTER SMALL HENG..MODIFIER LETTER SMALL U WITH LEFT HOOK
 AB60..AB68    ; Lowercase # L&   [9] LATIN SMALL LETTER SAKHA YAT..LATIN SMALL LETTER TURNED R WITH MIDDLE TILDE
+AB69          ; Lowercase # Lm       MODIFIER LETTER SMALL TURNED W
 AB70..ABBF    ; Lowercase # L&  [80] CHEROKEE SMALL LETTER A..CHEROKEE SMALL LETTER YA
 FB00..FB06    ; Lowercase # L&   [7] LATIN SMALL LIGATURE FF..LATIN SMALL LIGATURE ST
 FB13..FB17    ; Lowercase # L&   [5] ARMENIAN SMALL LIGATURE MEN NOW..ARMENIAN SMALL LIGATURE MEN XEH
@@ -2065,9 +2091,11 @@ FF41..FF5A    ; Lowercase # L&  [26] FULLWIDTH LATIN SMALL LETTER A..FULLWIDTH L
 1D7CB         ; Lowercase # L&       MATHEMATICAL BOLD SMALL DIGAMMA
 1DF00..1DF09  ; Lowercase # L&  [10] LATIN SMALL LETTER FENG DIGRAPH WITH TRILL..LATIN SMALL LETTER T WITH HOOK AND RETROFLEX HOOK
 1DF0B..1DF1E  ; Lowercase # L&  [20] LATIN SMALL LETTER ESH WITH DOUBLE BAR..LATIN SMALL LETTER S WITH CURL
+1DF25..1DF2A  ; Lowercase # L&   [6] LATIN SMALL LETTER D WITH MID-HEIGHT LEFT HOOK..LATIN SMALL LETTER T WITH MID-HEIGHT LEFT HOOK
+1E030..1E06D  ; Lowercase # Lm  [62] MODIFIER LETTER CYRILLIC SMALL A..MODIFIER LETTER CYRILLIC SMALL STRAIGHT U WITH STROKE
 1E922..1E943  ; Lowercase # L&  [34] ADLAM SMALL LETTER ALIF..ADLAM SMALL LETTER SHA
 
-# Total code points: 2471
+# Total code points: 2544
 
 # ================================================
 
@@ -2767,6 +2795,7 @@ FF21..FF3A    ; Uppercase # L&  [26] FULLWIDTH LATIN CAPITAL LETTER A..FULLWIDTH
 10C7          ; Cased # L&       GEORGIAN CAPITAL LETTER YN
 10CD          ; Cased # L&       GEORGIAN CAPITAL LETTER AEN
 10D0..10FA    ; Cased # L&  [43] GEORGIAN LETTER AN..GEORGIAN LETTER AIN
+10FC          ; Cased # Lm       MODIFIER LETTER GEORGIAN NAR
 10FD..10FF    ; Cased # L&   [3] GEORGIAN LETTER AEN..GEORGIAN LETTER LABIAL SIGN
 13A0..13F5    ; Cased # L&  [86] CHEROKEE LETTER A..CHEROKEE LETTER MV
 13F8..13FD    ; Cased # L&   [6] CHEROKEE SMALL LETTER YE..CHEROKEE SMALL LETTER MV
@@ -2837,12 +2866,14 @@ A790..A7CA    ; Cased # L&  [59] LATIN CAPITAL LETTER N WITH DESCENDER..LATIN SM
 A7D0..A7D1    ; Cased # L&   [2] LATIN CAPITAL LETTER CLOSED INSULAR G..LATIN SMALL LETTER CLOSED INSULAR G
 A7D3          ; Cased # L&       LATIN SMALL LETTER DOUBLE THORN
 A7D5..A7D9    ; Cased # L&   [5] LATIN SMALL LETTER DOUBLE WYNN..LATIN SMALL LETTER SIGMOID S
+A7F2..A7F4    ; Cased # Lm   [3] MODIFIER LETTER CAPITAL C..MODIFIER LETTER CAPITAL Q
 A7F5..A7F6    ; Cased # L&   [2] LATIN CAPITAL LETTER REVERSED HALF H..LATIN SMALL LETTER REVERSED HALF H
 A7F8..A7F9    ; Cased # Lm   [2] MODIFIER LETTER CAPITAL H WITH STROKE..MODIFIER LETTER SMALL LIGATURE OE
 A7FA          ; Cased # L&       LATIN LETTER SMALL CAPITAL TURNED M
 AB30..AB5A    ; Cased # L&  [43] LATIN SMALL LETTER BARRED ALPHA..LATIN SMALL LETTER Y WITH SHORT RIGHT LEG
 AB5C..AB5F    ; Cased # Lm   [4] MODIFIER LETTER SMALL HENG..MODIFIER LETTER SMALL U WITH LEFT HOOK
 AB60..AB68    ; Cased # L&   [9] LATIN SMALL LETTER SAKHA YAT..LATIN SMALL LETTER TURNED R WITH MIDDLE TILDE
+AB69          ; Cased # Lm       MODIFIER LETTER SMALL TURNED W
 AB70..ABBF    ; Cased # L&  [80] CHEROKEE SMALL LETTER A..CHEROKEE SMALL LETTER YA
 FB00..FB06    ; Cased # L&   [7] LATIN SMALL LIGATURE FF..LATIN SMALL LIGATURE ST
 FB13..FB17    ; Cased # L&   [5] ARMENIAN SMALL LIGATURE MEN NOW..ARMENIAN SMALL LIGATURE MEN XEH
@@ -2899,12 +2930,14 @@ FF41..FF5A    ; Cased # L&  [26] FULLWIDTH LATIN SMALL LETTER A..FULLWIDTH LATIN
 1D7C4..1D7CB  ; Cased # L&   [8] MATHEMATICAL SANS-SERIF BOLD ITALIC EPSILON SYMBOL..MATHEMATICAL BOLD SMALL DIGAMMA
 1DF00..1DF09  ; Cased # L&  [10] LATIN SMALL LETTER FENG DIGRAPH WITH TRILL..LATIN SMALL LETTER T WITH HOOK AND RETROFLEX HOOK
 1DF0B..1DF1E  ; Cased # L&  [20] LATIN SMALL LETTER ESH WITH DOUBLE BAR..LATIN SMALL LETTER S WITH CURL
+1DF25..1DF2A  ; Cased # L&   [6] LATIN SMALL LETTER D WITH MID-HEIGHT LEFT HOOK..LATIN SMALL LETTER T WITH MID-HEIGHT LEFT HOOK
+1E030..1E06D  ; Cased # Lm  [62] MODIFIER LETTER CYRILLIC SMALL A..MODIFIER LETTER CYRILLIC SMALL STRAIGHT U WITH STROKE
 1E900..1E943  ; Cased # L&  [68] ADLAM CAPITAL LETTER ALIF..ADLAM SMALL LETTER SHA
 1F130..1F149  ; Cased # So  [26] SQUARED LATIN CAPITAL LETTER A..SQUARED LATIN CAPITAL LETTER Z
 1F150..1F169  ; Cased # So  [26] NEGATIVE CIRCLED LATIN CAPITAL LETTER A..NEGATIVE CIRCLED LATIN CAPITAL LETTER Z
 1F170..1F189  ; Cased # So  [26] NEGATIVE SQUARED LATIN CAPITAL LETTER A..NEGATIVE SQUARED LATIN CAPITAL LETTER Z
 
-# Total code points: 4453
+# Total code points: 4526
 
 # ================================================
 
@@ -3054,7 +3087,7 @@ FF41..FF5A    ; Cased # L&  [26] FULLWIDTH LATIN SMALL LETTER A..FULLWIDTH LATIN
 0EB1          ; Case_Ignorable # Mn       LAO VOWEL SIGN MAI KAN
 0EB4..0EBC    ; Case_Ignorable # Mn   [9] LAO VOWEL SIGN I..LAO SEMIVOWEL SIGN LO
 0EC6          ; Case_Ignorable # Lm       LAO KO LA
-0EC8..0ECD    ; Case_Ignorable # Mn   [6] LAO TONE MAI EK..LAO NIGGAHITA
+0EC8..0ECE    ; Case_Ignorable # Mn   [7] LAO TONE MAI EK..LAO YAMAKKAN
 0F18..0F19    ; Case_Ignorable # Mn   [2] TIBETAN ASTROLOGICAL SIGN -KHYUD PA..TIBETAN ASTROLOGICAL SIGN SDONG TSHUGS
 0F35          ; Case_Ignorable # Mn       TIBETAN MARK NGAS BZUNG NYI ZLA
 0F37          ; Case_Ignorable # Mn       TIBETAN MARK NGAS BZUNG SGOR RTAGS
@@ -3263,6 +3296,7 @@ FFF9..FFFB    ; Case_Ignorable # Cf   [3] INTERLINEAR ANNOTATION ANCHOR..INTERLI
 10AE5..10AE6  ; Case_Ignorable # Mn   [2] MANICHAEAN ABBREVIATION MARK ABOVE..MANICHAEAN ABBREVIATION MARK BELOW
 10D24..10D27  ; Case_Ignorable # Mn   [4] HANIFI ROHINGYA SIGN HARBAHAY..HANIFI ROHINGYA SIGN TASSI
 10EAB..10EAC  ; Case_Ignorable # Mn   [2] YEZIDI COMBINING HAMZA MARK..YEZIDI COMBINING MADDA MARK
+10EFD..10EFF  ; Case_Ignorable # Mn   [3] ARABIC SMALL LOW WORD SAKTA..ARABIC SMALL LOW WORD MADDA
 10F46..10F50  ; Case_Ignorable # Mn  [11] SOGDIAN COMBINING DOT BELOW..SOGDIAN COMBINING STROKE BELOW
 10F82..10F85  ; Case_Ignorable # Mn   [4] OLD UYGHUR COMBINING DOT ABOVE..OLD UYGHUR COMBINING TWO DOTS BELOW
 11001         ; Case_Ignorable # Mn       BRAHMI SIGN ANUSVARA
@@ -3287,6 +3321,7 @@ FFF9..FFFB    ; Case_Ignorable # Cf   [3] INTERLINEAR ANNOTATION ANCHOR..INTERLI
 11234         ; Case_Ignorable # Mn       KHOJKI SIGN ANUSVARA
 11236..11237  ; Case_Ignorable # Mn   [2] KHOJKI SIGN NUKTA..KHOJKI SIGN SHADDA
 1123E         ; Case_Ignorable # Mn       KHOJKI SIGN SUKUN
+11241         ; Case_Ignorable # Mn       KHOJKI VOWEL SIGN VOCALIC R
 112DF         ; Case_Ignorable # Mn       KHUDAWADI SIGN ANUSVARA
 112E3..112EA  ; Case_Ignorable # Mn   [8] KHUDAWADI VOWEL SIGN U..KHUDAWADI SIGN VIRAMA
 11300..11301  ; Case_Ignorable # Mn   [2] GRANTHA SIGN COMBINING ANUSVARA ABOVE..GRANTHA SIGN CANDRABINDU
@@ -3348,7 +3383,13 @@ FFF9..FFFB    ; Case_Ignorable # Cf   [3] INTERLINEAR ANNOTATION ANCHOR..INTERLI
 11D95         ; Case_Ignorable # Mn       GUNJALA GONDI SIGN ANUSVARA
 11D97         ; Case_Ignorable # Mn       GUNJALA GONDI VIRAMA
 11EF3..11EF4  ; Case_Ignorable # Mn   [2] MAKASAR VOWEL SIGN I..MAKASAR VOWEL SIGN U
-13430..13438  ; Case_Ignorable # Cf   [9] EGYPTIAN HIEROGLYPH VERTICAL JOINER..EGYPTIAN HIEROGLYPH END SEGMENT
+11F00..11F01  ; Case_Ignorable # Mn   [2] KAWI SIGN CANDRABINDU..KAWI SIGN ANUSVARA
+11F36..11F3A  ; Case_Ignorable # Mn   [5] KAWI VOWEL SIGN I..KAWI VOWEL SIGN VOCALIC R
+11F40         ; Case_Ignorable # Mn       KAWI VOWEL SIGN EU
+11F42         ; Case_Ignorable # Mn       KAWI CONJOINER
+13430..1343F  ; Case_Ignorable # Cf  [16] EGYPTIAN HIEROGLYPH VERTICAL JOINER..EGYPTIAN HIEROGLYPH END WALLED ENCLOSURE
+13440         ; Case_Ignorable # Mn       EGYPTIAN HIEROGLYPH MIRROR HORIZONTALLY
+13447..13455  ; Case_Ignorable # Mn  [15] EGYPTIAN HIEROGLYPH MODIFIER DAMAGED AT TOP START..EGYPTIAN HIEROGLYPH MODIFIER DAMAGED
 16AF0..16AF4  ; Case_Ignorable # Mn   [5] BASSA VAH COMBINING HIGH TONE..BASSA VAH COMBINING HIGH-LOW TONE
 16B30..16B36  ; Case_Ignorable # Mn   [7] PAHAWH HMONG MARK CIM TUB..PAHAWH HMONG MARK CIM TAUM
 16B40..16B43  ; Case_Ignorable # Lm   [4] PAHAWH HMONG SIGN VOS SEEV..PAHAWH HMONG SIGN IB YAM
@@ -3382,10 +3423,14 @@ FFF9..FFFB    ; Case_Ignorable # Cf   [3] INTERLINEAR ANNOTATION ANCHOR..INTERLI
 1E01B..1E021  ; Case_Ignorable # Mn   [7] COMBINING GLAGOLITIC LETTER SHTA..COMBINING GLAGOLITIC LETTER YATI
 1E023..1E024  ; Case_Ignorable # Mn   [2] COMBINING GLAGOLITIC LETTER YU..COMBINING GLAGOLITIC LETTER SMALL YUS
 1E026..1E02A  ; Case_Ignorable # Mn   [5] COMBINING GLAGOLITIC LETTER YO..COMBINING GLAGOLITIC LETTER FITA
+1E030..1E06D  ; Case_Ignorable # Lm  [62] MODIFIER LETTER CYRILLIC SMALL A..MODIFIER LETTER CYRILLIC SMALL STRAIGHT U WITH STROKE
+1E08F         ; Case_Ignorable # Mn       COMBINING CYRILLIC SMALL LETTER BYELORUSSIAN-UKRAINIAN I
 1E130..1E136  ; Case_Ignorable # Mn   [7] NYIAKENG PUACHUE HMONG TONE-B..NYIAKENG PUACHUE HMONG TONE-D
 1E137..1E13D  ; Case_Ignorable # Lm   [7] NYIAKENG PUACHUE HMONG SIGN FOR PERSON..NYIAKENG PUACHUE HMONG SYLLABLE LENGTHENER
 1E2AE         ; Case_Ignorable # Mn       TOTO SIGN RISING TONE
 1E2EC..1E2EF  ; Case_Ignorable # Mn   [4] WANCHO TONE TUP..WANCHO TONE KOINI
+1E4EB         ; Case_Ignorable # Lm       NAG MUNDARI SIGN OJOD
+1E4EC..1E4EF  ; Case_Ignorable # Mn   [4] NAG MUNDARI SIGN MUHOR..NAG MUNDARI SIGN SUTUH
 1E8D0..1E8D6  ; Case_Ignorable # Mn   [7] MENDE KIKAKUI COMBINING NUMBER TEENS..MENDE KIKAKUI COMBINING NUMBER MILLIONS
 1E944..1E94A  ; Case_Ignorable # Mn   [7] ADLAM ALIF LENGTHENER..ADLAM NUKTA
 1E94B         ; Case_Ignorable # Lm       ADLAM NASALIZATION MARK
@@ -3394,7 +3439,7 @@ E0001         ; Case_Ignorable # Cf       LANGUAGE TAG
 E0020..E007F  ; Case_Ignorable # Cf  [96] TAG SPACE..CANCEL TAG
 E0100..E01EF  ; Case_Ignorable # Mn [240] VARIATION SELECTOR-17..VARIATION SELECTOR-256
 
-# Total code points: 2602
+# Total code points: 2707
 
 # ================================================
 
@@ -6617,6 +6662,7 @@ FFDA..FFDC    ; ID_Start # Lo   [3] HALFWIDTH HANGUL LETTER EU..HALFWIDTH HANGUL
 111DC         ; ID_Start # Lo       SHARADA HEADSTROKE
 11200..11211  ; ID_Start # Lo  [18] KHOJKI LETTER A..KHOJKI LETTER JJA
 11213..1122B  ; ID_Start # Lo  [25] KHOJKI LETTER NYA..KHOJKI LETTER LLA
+1123F..11240  ; ID_Start # Lo   [2] KHOJKI LETTER QA..KHOJKI LETTER SHORT I
 11280..11286  ; ID_Start # Lo   [7] MULTANI LETTER A..MULTANI LETTER GA
 11288         ; ID_Start # Lo       MULTANI LETTER GHA
 1128A..1128D  ; ID_Start # Lo   [4] MULTANI LETTER CA..MULTANI LETTER JJA
@@ -6679,12 +6725,16 @@ FFDA..FFDC    ; ID_Start # Lo   [3] HALFWIDTH HANGUL LETTER EU..HALFWIDTH HANGUL
 11D6A..11D89  ; ID_Start # Lo  [32] GUNJALA GONDI LETTER OO..GUNJALA GONDI LETTER SA
 11D98         ; ID_Start # Lo       GUNJALA GONDI OM
 11EE0..11EF2  ; ID_Start # Lo  [19] MAKASAR LETTER KA..MAKASAR ANGKA
+11F02         ; ID_Start # Lo       KAWI SIGN REPHA
+11F04..11F10  ; ID_Start # Lo  [13] KAWI LETTER A..KAWI LETTER O
+11F12..11F33  ; ID_Start # Lo  [34] KAWI LETTER KA..KAWI LETTER JNYA
 11FB0         ; ID_Start # Lo       LISU LETTER YHA
 12000..12399  ; ID_Start # Lo [922] CUNEIFORM SIGN A..CUNEIFORM SIGN U U
 12400..1246E  ; ID_Start # Nl [111] CUNEIFORM NUMERIC SIGN TWO ASH..CUNEIFORM NUMERIC SIGN NINE U VARIANT FORM
 12480..12543  ; ID_Start # Lo [196] CUNEIFORM SIGN AB TIMES NUN TENU..CUNEIFORM SIGN ZU5 TIMES THREE DISH TENU
 12F90..12FF0  ; ID_Start # Lo  [97] CYPRO-MINOAN SIGN CM001..CYPRO-MINOAN SIGN CM114
-13000..1342E  ; ID_Start # Lo [1071] EGYPTIAN HIEROGLYPH A001..EGYPTIAN HIEROGLYPH AA032
+13000..1342F  ; ID_Start # Lo [1072] EGYPTIAN HIEROGLYPH A001..EGYPTIAN HIEROGLYPH V011D
+13441..13446  ; ID_Start # Lo   [6] EGYPTIAN HIEROGLYPH FULL BLANK..EGYPTIAN HIEROGLYPH WIDE LOST SIGN
 14400..14646  ; ID_Start # Lo [583] ANATOLIAN HIEROGLYPH A001..ANATOLIAN HIEROGLYPH A530
 16800..16A38  ; ID_Start # Lo [569] BAMUM LETTER PHASE-A NGKUE MFON..BAMUM LETTER PHASE-F VUEQ
 16A40..16A5E  ; ID_Start # Lo  [31] MRO LETTER TA..MRO LETTER TEK
@@ -6707,7 +6757,9 @@ FFDA..FFDC    ; ID_Start # Lo   [3] HALFWIDTH HANGUL LETTER EU..HALFWIDTH HANGUL
 1AFF5..1AFFB  ; ID_Start # Lm   [7] KATAKANA LETTER MINNAN TONE-7..KATAKANA LETTER MINNAN NASALIZED TONE-5
 1AFFD..1AFFE  ; ID_Start # Lm   [2] KATAKANA LETTER MINNAN NASALIZED TONE-7..KATAKANA LETTER MINNAN NASALIZED TONE-8
 1B000..1B122  ; ID_Start # Lo [291] KATAKANA LETTER ARCHAIC E..KATAKANA LETTER ARCHAIC WU
+1B132         ; ID_Start # Lo       HIRAGANA LETTER SMALL KO
 1B150..1B152  ; ID_Start # Lo   [3] HIRAGANA LETTER SMALL WI..HIRAGANA LETTER SMALL WO
+1B155         ; ID_Start # Lo       KATAKANA LETTER SMALL KO
 1B164..1B167  ; ID_Start # Lo   [4] KATAKANA LETTER SMALL WI..KATAKANA LETTER SMALL N
 1B170..1B2FB  ; ID_Start # Lo [396] NUSHU CHARACTER-1B170..NUSHU CHARACTER-1B2FB
 1BC00..1BC6A  ; ID_Start # Lo [107] DUPLOYAN LETTER H..DUPLOYAN LETTER VOCALIC M
@@ -6747,11 +6799,15 @@ FFDA..FFDC    ; ID_Start # Lo   [3] HALFWIDTH HANGUL LETTER EU..HALFWIDTH HANGUL
 1DF00..1DF09  ; ID_Start # L&  [10] LATIN SMALL LETTER FENG DIGRAPH WITH TRILL..LATIN SMALL LETTER T WITH HOOK AND RETROFLEX HOOK
 1DF0A         ; ID_Start # Lo       LATIN LETTER RETROFLEX CLICK WITH RETROFLEX HOOK
 1DF0B..1DF1E  ; ID_Start # L&  [20] LATIN SMALL LETTER ESH WITH DOUBLE BAR..LATIN SMALL LETTER S WITH CURL
+1DF25..1DF2A  ; ID_Start # L&   [6] LATIN SMALL LETTER D WITH MID-HEIGHT LEFT HOOK..LATIN SMALL LETTER T WITH MID-HEIGHT LEFT HOOK
+1E030..1E06D  ; ID_Start # Lm  [62] MODIFIER LETTER CYRILLIC SMALL A..MODIFIER LETTER CYRILLIC SMALL STRAIGHT U WITH STROKE
 1E100..1E12C  ; ID_Start # Lo  [45] NYIAKENG PUACHUE HMONG LETTER MA..NYIAKENG PUACHUE HMONG LETTER W
 1E137..1E13D  ; ID_Start # Lm   [7] NYIAKENG PUACHUE HMONG SIGN FOR PERSON..NYIAKENG PUACHUE HMONG SYLLABLE LENGTHENER
 1E14E         ; ID_Start # Lo       NYIAKENG PUACHUE HMONG LOGOGRAM NYAJ
 1E290..1E2AD  ; ID_Start # Lo  [30] TOTO LETTER PA..TOTO LETTER A
 1E2C0..1E2EB  ; ID_Start # Lo  [44] WANCHO LETTER AA..WANCHO LETTER YIH
+1E4D0..1E4EA  ; ID_Start # Lo  [27] NAG MUNDARI LETTER O..NAG MUNDARI LETTER ELL
+1E4EB         ; ID_Start # Lm       NAG MUNDARI SIGN OJOD
 1E7E0..1E7E6  ; ID_Start # Lo   [7] ETHIOPIC SYLLABLE HHYA..ETHIOPIC SYLLABLE HHYO
 1E7E8..1E7EB  ; ID_Start # Lo   [4] ETHIOPIC SYLLABLE GURAGE HHWA..ETHIOPIC SYLLABLE HHWE
 1E7ED..1E7EE  ; ID_Start # Lo   [2] ETHIOPIC SYLLABLE GURAGE MWI..ETHIOPIC SYLLABLE GURAGE MWEE
@@ -6793,14 +6849,15 @@ FFDA..FFDC    ; ID_Start # Lo   [3] HALFWIDTH HANGUL LETTER EU..HALFWIDTH HANGUL
 1EEA5..1EEA9  ; ID_Start # Lo   [5] ARABIC MATHEMATICAL DOUBLE-STRUCK WAW..ARABIC MATHEMATICAL DOUBLE-STRUCK YEH
 1EEAB..1EEBB  ; ID_Start # Lo  [17] ARABIC MATHEMATICAL DOUBLE-STRUCK LAM..ARABIC MATHEMATICAL DOUBLE-STRUCK GHAIN
 20000..2A6DF  ; ID_Start # Lo [42720] CJK UNIFIED IDEOGRAPH-20000..CJK UNIFIED IDEOGRAPH-2A6DF
-2A700..2B738  ; ID_Start # Lo [4153] CJK UNIFIED IDEOGRAPH-2A700..CJK UNIFIED IDEOGRAPH-2B738
+2A700..2B739  ; ID_Start # Lo [4154] CJK UNIFIED IDEOGRAPH-2A700..CJK UNIFIED IDEOGRAPH-2B739
 2B740..2B81D  ; ID_Start # Lo [222] CJK UNIFIED IDEOGRAPH-2B740..CJK UNIFIED IDEOGRAPH-2B81D
 2B820..2CEA1  ; ID_Start # Lo [5762] CJK UNIFIED IDEOGRAPH-2B820..CJK UNIFIED IDEOGRAPH-2CEA1
 2CEB0..2EBE0  ; ID_Start # Lo [7473] CJK UNIFIED IDEOGRAPH-2CEB0..CJK UNIFIED IDEOGRAPH-2EBE0
 2F800..2FA1D  ; ID_Start # Lo [542] CJK COMPATIBILITY IDEOGRAPH-2F800..CJK COMPATIBILITY IDEOGRAPH-2FA1D
 30000..3134A  ; ID_Start # Lo [4939] CJK UNIFIED IDEOGRAPH-30000..CJK UNIFIED IDEOGRAPH-3134A
+31350..323AF  ; ID_Start # Lo [4192] CJK UNIFIED IDEOGRAPH-31350..CJK UNIFIED IDEOGRAPH-323AF
 
-# Total code points: 131997
+# Total code points: 136345
 
 # ================================================
 
@@ -7083,6 +7140,7 @@ FFDA..FFDC    ; ID_Start # Lo   [3] HALFWIDTH HANGUL LETTER EU..HALFWIDTH HANGUL
 0CE2..0CE3    ; ID_Continue # Mn   [2] KANNADA VOWEL SIGN VOCALIC L..KANNADA VOWEL SIGN VOCALIC LL
 0CE6..0CEF    ; ID_Continue # Nd  [10] KANNADA DIGIT ZERO..KANNADA DIGIT NINE
 0CF1..0CF2    ; ID_Continue # Lo   [2] KANNADA SIGN JIHVAMULIYA..KANNADA SIGN UPADHMANIYA
+0CF3          ; ID_Continue # Mc       KANNADA SIGN COMBINING ANUSVARA ABOVE RIGHT
 0D00..0D01    ; ID_Continue # Mn   [2] MALAYALAM SIGN COMBINING ANUSVARA ABOVE..MALAYALAM SIGN CANDRABINDU
 0D02..0D03    ; ID_Continue # Mc   [2] MALAYALAM SIGN ANUSVARA..MALAYALAM SIGN VISARGA
 0D04..0D0C    ; ID_Continue # Lo   [9] MALAYALAM LETTER VEDIC ANUSVARA..MALAYALAM LETTER VOCALIC L
@@ -7136,7 +7194,7 @@ FFDA..FFDC    ; ID_Start # Lo   [3] HALFWIDTH HANGUL LETTER EU..HALFWIDTH HANGUL
 0EBD          ; ID_Continue # Lo       LAO SEMIVOWEL SIGN NYO
 0EC0..0EC4    ; ID_Continue # Lo   [5] LAO VOWEL SIGN E..LAO VOWEL SIGN AI
 0EC6          ; ID_Continue # Lm       LAO KO LA
-0EC8..0ECD    ; ID_Continue # Mn   [6] LAO TONE MAI EK..LAO NIGGAHITA
+0EC8..0ECE    ; ID_Continue # Mn   [7] LAO TONE MAI EK..LAO YAMAKKAN
 0ED0..0ED9    ; ID_Continue # Nd  [10] LAO DIGIT ZERO..LAO DIGIT NINE
 0EDC..0EDF    ; ID_Continue # Lo   [4] LAO HO NO..LAO LETTER KHMU NYO
 0F00          ; ID_Continue # Lo       TIBETAN SYLLABLE OM
@@ -7719,6 +7777,7 @@ FFDA..FFDC    ; ID_Continue # Lo   [3] HALFWIDTH HANGUL LETTER EU..HALFWIDTH HAN
 10E80..10EA9  ; ID_Continue # Lo  [42] YEZIDI LETTER ELIF..YEZIDI LETTER ET
 10EAB..10EAC  ; ID_Continue # Mn   [2] YEZIDI COMBINING HAMZA MARK..YEZIDI COMBINING MADDA MARK
 10EB0..10EB1  ; ID_Continue # Lo   [2] YEZIDI LETTER LAM WITH DOT ABOVE..YEZIDI LETTER YOT WITH CIRCUMFLEX ABOVE
+10EFD..10EFF  ; ID_Continue # Mn   [3] ARABIC SMALL LOW WORD SAKTA..ARABIC SMALL LOW WORD MADDA
 10F00..10F1C  ; ID_Continue # Lo  [29] OLD SOGDIAN LETTER ALEPH..OLD SOGDIAN LETTER FINAL TAW WITH VERTICAL TAIL
 10F27         ; ID_Continue # Lo       OLD SOGDIAN LIGATURE AYIN-DALETH
 10F30..10F45  ; ID_Continue # Lo  [22] SOGDIAN LETTER ALEPH..SOGDIAN INDEPENDENT SHIN
@@ -7781,6 +7840,8 @@ FFDA..FFDC    ; ID_Continue # Lo   [3] HALFWIDTH HANGUL LETTER EU..HALFWIDTH HAN
 11235         ; ID_Continue # Mc       KHOJKI SIGN VIRAMA
 11236..11237  ; ID_Continue # Mn   [2] KHOJKI SIGN NUKTA..KHOJKI SIGN SHADDA
 1123E         ; ID_Continue # Mn       KHOJKI SIGN SUKUN
+1123F..11240  ; ID_Continue # Lo   [2] KHOJKI LETTER QA..KHOJKI LETTER SHORT I
+11241         ; ID_Continue # Mn       KHOJKI VOWEL SIGN VOCALIC R
 11280..11286  ; ID_Continue # Lo   [7] MULTANI LETTER A..MULTANI LETTER GA
 11288         ; ID_Continue # Lo       MULTANI LETTER GHA
 1128A..1128D  ; ID_Continue # Lo   [4] MULTANI LETTER CA..MULTANI LETTER JJA
@@ -7963,12 +8024,27 @@ FFDA..FFDC    ; ID_Continue # Lo   [3] HALFWIDTH HANGUL LETTER EU..HALFWIDTH HAN
 11EE0..11EF2  ; ID_Continue # Lo  [19] MAKASAR LETTER KA..MAKASAR ANGKA
 11EF3..11EF4  ; ID_Continue # Mn   [2] MAKASAR VOWEL SIGN I..MAKASAR VOWEL SIGN U
 11EF5..11EF6  ; ID_Continue # Mc   [2] MAKASAR VOWEL SIGN E..MAKASAR VOWEL SIGN O
+11F00..11F01  ; ID_Continue # Mn   [2] KAWI SIGN CANDRABINDU..KAWI SIGN ANUSVARA
+11F02         ; ID_Continue # Lo       KAWI SIGN REPHA
+11F03         ; ID_Continue # Mc       KAWI SIGN VISARGA
+11F04..11F10  ; ID_Continue # Lo  [13] KAWI LETTER A..KAWI LETTER O
+11F12..11F33  ; ID_Continue # Lo  [34] KAWI LETTER KA..KAWI LETTER JNYA
+11F34..11F35  ; ID_Continue # Mc   [2] KAWI VOWEL SIGN AA..KAWI VOWEL SIGN ALTERNATE AA
+11F36..11F3A  ; ID_Continue # Mn   [5] KAWI VOWEL SIGN I..KAWI VOWEL SIGN VOCALIC R
+11F3E..11F3F  ; ID_Continue # Mc   [2] KAWI VOWEL SIGN E..KAWI VOWEL SIGN AI
+11F40         ; ID_Continue # Mn       KAWI VOWEL SIGN EU
+11F41         ; ID_Continue # Mc       KAWI SIGN KILLER
+11F42         ; ID_Continue # Mn       KAWI CONJOINER
+11F50..11F59  ; ID_Continue # Nd  [10] KAWI DIGIT ZERO..KAWI DIGIT NINE
 11FB0         ; ID_Continue # Lo       LISU LETTER YHA
 12000..12399  ; ID_Continue # Lo [922] CUNEIFORM SIGN A..CUNEIFORM SIGN U U
 12400..1246E  ; ID_Continue # Nl [111] CUNEIFORM NUMERIC SIGN TWO ASH..CUNEIFORM NUMERIC SIGN NINE U VARIANT FORM
 12480..12543  ; ID_Continue # Lo [196] CUNEIFORM SIGN AB TIMES NUN TENU..CUNEIFORM SIGN ZU5 TIMES THREE DISH TENU
 12F90..12FF0  ; ID_Continue # Lo  [97] CYPRO-MINOAN SIGN CM001..CYPRO-MINOAN SIGN CM114
-13000..1342E  ; ID_Continue # Lo [1071] EGYPTIAN HIEROGLYPH A001..EGYPTIAN HIEROGLYPH AA032
+13000..1342F  ; ID_Continue # Lo [1072] EGYPTIAN HIEROGLYPH A001..EGYPTIAN HIEROGLYPH V011D
+13440         ; ID_Continue # Mn       EGYPTIAN HIEROGLYPH MIRROR HORIZONTALLY
+13441..13446  ; ID_Continue # Lo   [6] EGYPTIAN HIEROGLYPH FULL BLANK..EGYPTIAN HIEROGLYPH WIDE LOST SIGN
+13447..13455  ; ID_Continue # Mn  [15] EGYPTIAN HIEROGLYPH MODIFIER DAMAGED AT TOP START..EGYPTIAN HIEROGLYPH MODIFIER DAMAGED
 14400..14646  ; ID_Continue # Lo [583] ANATOLIAN HIEROGLYPH A001..ANATOLIAN HIEROGLYPH A530
 16800..16A38  ; ID_Continue # Lo [569] BAMUM LETTER PHASE-A NGKUE MFON..BAMUM LETTER PHASE-F VUEQ
 16A40..16A5E  ; ID_Continue # Lo  [31] MRO LETTER TA..MRO LETTER TEK
@@ -8001,7 +8077,9 @@ FFDA..FFDC    ; ID_Continue # Lo   [3] HALFWIDTH HANGUL LETTER EU..HALFWIDTH HAN
 1AFF5..1AFFB  ; ID_Continue # Lm   [7] KATAKANA LETTER MINNAN TONE-7..KATAKANA LETTER MINNAN NASALIZED TONE-5
 1AFFD..1AFFE  ; ID_Continue # Lm   [2] KATAKANA LETTER MINNAN NASALIZED TONE-7..KATAKANA LETTER MINNAN NASALIZED TONE-8
 1B000..1B122  ; ID_Continue # Lo [291] KATAKANA LETTER ARCHAIC E..KATAKANA LETTER ARCHAIC WU
+1B132         ; ID_Continue # Lo       HIRAGANA LETTER SMALL KO
 1B150..1B152  ; ID_Continue # Lo   [3] HIRAGANA LETTER SMALL WI..HIRAGANA LETTER SMALL WO
+1B155         ; ID_Continue # Lo       KATAKANA LETTER SMALL KO
 1B164..1B167  ; ID_Continue # Lo   [4] KATAKANA LETTER SMALL WI..KATAKANA LETTER SMALL N
 1B170..1B2FB  ; ID_Continue # Lo [396] NUSHU CHARACTER-1B170..NUSHU CHARACTER-1B2FB
 1BC00..1BC6A  ; ID_Continue # Lo [107] DUPLOYAN LETTER H..DUPLOYAN LETTER VOCALIC M
@@ -8058,11 +8136,14 @@ FFDA..FFDC    ; ID_Continue # Lo   [3] HALFWIDTH HANGUL LETTER EU..HALFWIDTH HAN
 1DF00..1DF09  ; ID_Continue # L&  [10] LATIN SMALL LETTER FENG DIGRAPH WITH TRILL..LATIN SMALL LETTER T WITH HOOK AND RETROFLEX HOOK
 1DF0A         ; ID_Continue # Lo       LATIN LETTER RETROFLEX CLICK WITH RETROFLEX HOOK
 1DF0B..1DF1E  ; ID_Continue # L&  [20] LATIN SMALL LETTER ESH WITH DOUBLE BAR..LATIN SMALL LETTER S WITH CURL
+1DF25..1DF2A  ; ID_Continue # L&   [6] LATIN SMALL LETTER D WITH MID-HEIGHT LEFT HOOK..LATIN SMALL LETTER T WITH MID-HEIGHT LEFT HOOK
 1E000..1E006  ; ID_Continue # Mn   [7] COMBINING GLAGOLITIC LETTER AZU..COMBINING GLAGOLITIC LETTER ZHIVETE
 1E008..1E018  ; ID_Continue # Mn  [17] COMBINING GLAGOLITIC LETTER ZEMLJA..COMBINING GLAGOLITIC LETTER HERU
 1E01B..1E021  ; ID_Continue # Mn   [7] COMBINING GLAGOLITIC LETTER SHTA..COMBINING GLAGOLITIC LETTER YATI
 1E023..1E024  ; ID_Continue # Mn   [2] COMBINING GLAGOLITIC LETTER YU..COMBINING GLAGOLITIC LETTER SMALL YUS
 1E026..1E02A  ; ID_Continue # Mn   [5] COMBINING GLAGOLITIC LETTER YO..COMBINING GLAGOLITIC LETTER FITA
+1E030..1E06D  ; ID_Continue # Lm  [62] MODIFIER LETTER CYRILLIC SMALL A..MODIFIER LETTER CYRILLIC SMALL STRAIGHT U WITH STROKE
+1E08F         ; ID_Continue # Mn       COMBINING CYRILLIC SMALL LETTER BYELORUSSIAN-UKRAINIAN I
 1E100..1E12C  ; ID_Continue # Lo  [45] NYIAKENG PUACHUE HMONG LETTER MA..NYIAKENG PUACHUE HMONG LETTER W
 1E130..1E136  ; ID_Continue # Mn   [7] NYIAKENG PUACHUE HMONG TONE-B..NYIAKENG PUACHUE HMONG TONE-D
 1E137..1E13D  ; ID_Continue # Lm   [7] NYIAKENG PUACHUE HMONG SIGN FOR PERSON..NYIAKENG PUACHUE HMONG SYLLABLE LENGTHENER
@@ -8073,6 +8154,10 @@ FFDA..FFDC    ; ID_Continue # Lo   [3] HALFWIDTH HANGUL LETTER EU..HALFWIDTH HAN
 1E2C0..1E2EB  ; ID_Continue # Lo  [44] WANCHO LETTER AA..WANCHO LETTER YIH
 1E2EC..1E2EF  ; ID_Continue # Mn   [4] WANCHO TONE TUP..WANCHO TONE KOINI
 1E2F0..1E2F9  ; ID_Continue # Nd  [10] WANCHO DIGIT ZERO..WANCHO DIGIT NINE
+1E4D0..1E4EA  ; ID_Continue # Lo  [27] NAG MUNDARI LETTER O..NAG MUNDARI LETTER ELL
+1E4EB         ; ID_Continue # Lm       NAG MUNDARI SIGN OJOD
+1E4EC..1E4EF  ; ID_Continue # Mn   [4] NAG MUNDARI SIGN MUHOR..NAG MUNDARI SIGN SUTUH
+1E4F0..1E4F9  ; ID_Continue # Nd  [10] NAG MUNDARI DIGIT ZERO..NAG MUNDARI DIGIT NINE
 1E7E0..1E7E6  ; ID_Continue # Lo   [7] ETHIOPIC SYLLABLE HHYA..ETHIOPIC SYLLABLE HHYO
 1E7E8..1E7EB  ; ID_Continue # Lo   [4] ETHIOPIC SYLLABLE GURAGE HHWA..ETHIOPIC SYLLABLE HHWE
 1E7ED..1E7EE  ; ID_Continue # Lo   [2] ETHIOPIC SYLLABLE GURAGE MWI..ETHIOPIC SYLLABLE GURAGE MWEE
@@ -8118,15 +8203,16 @@ FFDA..FFDC    ; ID_Continue # Lo   [3] HALFWIDTH HANGUL LETTER EU..HALFWIDTH HAN
 1EEAB..1EEBB  ; ID_Continue # Lo  [17] ARABIC MATHEMATICAL DOUBLE-STRUCK LAM..ARABIC MATHEMATICAL DOUBLE-STRUCK GHAIN
 1FBF0..1FBF9  ; ID_Continue # Nd  [10] SEGMENTED DIGIT ZERO..SEGMENTED DIGIT NINE
 20000..2A6DF  ; ID_Continue # Lo [42720] CJK UNIFIED IDEOGRAPH-20000..CJK UNIFIED IDEOGRAPH-2A6DF
-2A700..2B738  ; ID_Continue # Lo [4153] CJK UNIFIED IDEOGRAPH-2A700..CJK UNIFIED IDEOGRAPH-2B738
+2A700..2B739  ; ID_Continue # Lo [4154] CJK UNIFIED IDEOGRAPH-2A700..CJK UNIFIED IDEOGRAPH-2B739
 2B740..2B81D  ; ID_Continue # Lo [222] CJK UNIFIED IDEOGRAPH-2B740..CJK UNIFIED IDEOGRAPH-2B81D
 2B820..2CEA1  ; ID_Continue # Lo [5762] CJK UNIFIED IDEOGRAPH-2B820..CJK UNIFIED IDEOGRAPH-2CEA1
 2CEB0..2EBE0  ; ID_Continue # Lo [7473] CJK UNIFIED IDEOGRAPH-2CEB0..CJK UNIFIED IDEOGRAPH-2EBE0
 2F800..2FA1D  ; ID_Continue # Lo [542] CJK COMPATIBILITY IDEOGRAPH-2F800..CJK COMPATIBILITY IDEOGRAPH-2FA1D
 30000..3134A  ; ID_Continue # Lo [4939] CJK UNIFIED IDEOGRAPH-30000..CJK UNIFIED IDEOGRAPH-3134A
+31350..323AF  ; ID_Continue # Lo [4192] CJK UNIFIED IDEOGRAPH-31350..CJK UNIFIED IDEOGRAPH-323AF
 E0100..E01EF  ; ID_Continue # Mn [240] VARIATION SELECTOR-17..VARIATION SELECTOR-256
 
-# Total code points: 135072
+# Total code points: 139482
 
 # ================================================
 
@@ -8685,6 +8771,7 @@ FFDA..FFDC    ; XID_Start # Lo   [3] HALFWIDTH HANGUL LETTER EU..HALFWIDTH HANGU
 111DC         ; XID_Start # Lo       SHARADA HEADSTROKE
 11200..11211  ; XID_Start # Lo  [18] KHOJKI LETTER A..KHOJKI LETTER JJA
 11213..1122B  ; XID_Start # Lo  [25] KHOJKI LETTER NYA..KHOJKI LETTER LLA
+1123F..11240  ; XID_Start # Lo   [2] KHOJKI LETTER QA..KHOJKI LETTER SHORT I
 11280..11286  ; XID_Start # Lo   [7] MULTANI LETTER A..MULTANI LETTER GA
 11288         ; XID_Start # Lo       MULTANI LETTER GHA
 1128A..1128D  ; XID_Start # Lo   [4] MULTANI LETTER CA..MULTANI LETTER JJA
@@ -8747,12 +8834,16 @@ FFDA..FFDC    ; XID_Start # Lo   [3] HALFWIDTH HANGUL LETTER EU..HALFWIDTH HANGU
 11D6A..11D89  ; XID_Start # Lo  [32] GUNJALA GONDI LETTER OO..GUNJALA GONDI LETTER SA
 11D98         ; XID_Start # Lo       GUNJALA GONDI OM
 11EE0..11EF2  ; XID_Start # Lo  [19] MAKASAR LETTER KA..MAKASAR ANGKA
+11F02         ; XID_Start # Lo       KAWI SIGN REPHA
+11F04..11F10  ; XID_Start # Lo  [13] KAWI LETTER A..KAWI LETTER O
+11F12..11F33  ; XID_Start # Lo  [34] KAWI LETTER KA..KAWI LETTER JNYA
 11FB0         ; XID_Start # Lo       LISU LETTER YHA
 12000..12399  ; XID_Start # Lo [922] CUNEIFORM SIGN A..CUNEIFORM SIGN U U
 12400..1246E  ; XID_Start # Nl [111] CUNEIFORM NUMERIC SIGN TWO ASH..CUNEIFORM NUMERIC SIGN NINE U VARIANT FORM
 12480..12543  ; XID_Start # Lo [196] CUNEIFORM SIGN AB TIMES NUN TENU..CUNEIFORM SIGN ZU5 TIMES THREE DISH TENU
 12F90..12FF0  ; XID_Start # Lo  [97] CYPRO-MINOAN SIGN CM001..CYPRO-MINOAN SIGN CM114
-13000..1342E  ; XID_Start # Lo [1071] EGYPTIAN HIEROGLYPH A001..EGYPTIAN HIEROGLYPH AA032
+13000..1342F  ; XID_Start # Lo [1072] EGYPTIAN HIEROGLYPH A001..EGYPTIAN HIEROGLYPH V011D
+13441..13446  ; XID_Start # Lo   [6] EGYPTIAN HIEROGLYPH FULL BLANK..EGYPTIAN HIEROGLYPH WIDE LOST SIGN
 14400..14646  ; XID_Start # Lo [583] ANATOLIAN HIEROGLYPH A001..ANATOLIAN HIEROGLYPH A530
 16800..16A38  ; XID_Start # Lo [569] BAMUM LETTER PHASE-A NGKUE MFON..BAMUM LETTER PHASE-F VUEQ
 16A40..16A5E  ; XID_Start # Lo  [31] MRO LETTER TA..MRO LETTER TEK
@@ -8775,7 +8866,9 @@ FFDA..FFDC    ; XID_Start # Lo   [3] HALFWIDTH HANGUL LETTER EU..HALFWIDTH HANGU
 1AFF5..1AFFB  ; XID_Start # Lm   [7] KATAKANA LETTER MINNAN TONE-7..KATAKANA LETTER MINNAN NASALIZED TONE-5
 1AFFD..1AFFE  ; XID_Start # Lm   [2] KATAKANA LETTER MINNAN NASALIZED TONE-7..KATAKANA LETTER MINNAN NASALIZED TONE-8
 1B000..1B122  ; XID_Start # Lo [291] KATAKANA LETTER ARCHAIC E..KATAKANA LETTER ARCHAIC WU
+1B132         ; XID_Start # Lo       HIRAGANA LETTER SMALL KO
 1B150..1B152  ; XID_Start # Lo   [3] HIRAGANA LETTER SMALL WI..HIRAGANA LETTER SMALL WO
+1B155         ; XID_Start # Lo       KATAKANA LETTER SMALL KO
 1B164..1B167  ; XID_Start # Lo   [4] KATAKANA LETTER SMALL WI..KATAKANA LETTER SMALL N
 1B170..1B2FB  ; XID_Start # Lo [396] NUSHU CHARACTER-1B170..NUSHU CHARACTER-1B2FB
 1BC00..1BC6A  ; XID_Start # Lo [107] DUPLOYAN LETTER H..DUPLOYAN LETTER VOCALIC M
@@ -8815,11 +8908,15 @@ FFDA..FFDC    ; XID_Start # Lo   [3] HALFWIDTH HANGUL LETTER EU..HALFWIDTH HANGU
 1DF00..1DF09  ; XID_Start # L&  [10] LATIN SMALL LETTER FENG DIGRAPH WITH TRILL..LATIN SMALL LETTER T WITH HOOK AND RETROFLEX HOOK
 1DF0A         ; XID_Start # Lo       LATIN LETTER RETROFLEX CLICK WITH RETROFLEX HOOK
 1DF0B..1DF1E  ; XID_Start # L&  [20] LATIN SMALL LETTER ESH WITH DOUBLE BAR..LATIN SMALL LETTER S WITH CURL
+1DF25..1DF2A  ; XID_Start # L&   [6] LATIN SMALL LETTER D WITH MID-HEIGHT LEFT HOOK..LATIN SMALL LETTER T WITH MID-HEIGHT LEFT HOOK
+1E030..1E06D  ; XID_Start # Lm  [62] MODIFIER LETTER CYRILLIC SMALL A..MODIFIER LETTER CYRILLIC SMALL STRAIGHT U WITH STROKE
 1E100..1E12C  ; XID_Start # Lo  [45] NYIAKENG PUACHUE HMONG LETTER MA..NYIAKENG PUACHUE HMONG LETTER W
 1E137..1E13D  ; XID_Start # Lm   [7] NYIAKENG PUACHUE HMONG SIGN FOR PERSON..NYIAKENG PUACHUE HMONG SYLLABLE LENGTHENER
 1E14E         ; XID_Start # Lo       NYIAKENG PUACHUE HMONG LOGOGRAM NYAJ
 1E290..1E2AD  ; XID_Start # Lo  [30] TOTO LETTER PA..TOTO LETTER A
 1E2C0..1E2EB  ; XID_Start # Lo  [44] WANCHO LETTER AA..WANCHO LETTER YIH
+1E4D0..1E4EA  ; XID_Start # Lo  [27] NAG MUNDARI LETTER O..NAG MUNDARI LETTER ELL
+1E4EB         ; XID_Start # Lm       NAG MUNDARI SIGN OJOD
 1E7E0..1E7E6  ; XID_Start # Lo   [7] ETHIOPIC SYLLABLE HHYA..ETHIOPIC SYLLABLE HHYO
 1E7E8..1E7EB  ; XID_Start # Lo   [4] ETHIOPIC SYLLABLE GURAGE HHWA..ETHIOPIC SYLLABLE HHWE
 1E7ED..1E7EE  ; XID_Start # Lo   [2] ETHIOPIC SYLLABLE GURAGE MWI..ETHIOPIC SYLLABLE GURAGE MWEE
@@ -8861,14 +8958,15 @@ FFDA..FFDC    ; XID_Start # Lo   [3] HALFWIDTH HANGUL LETTER EU..HALFWIDTH HANGU
 1EEA5..1EEA9  ; XID_Start # Lo   [5] ARABIC MATHEMATICAL DOUBLE-STRUCK WAW..ARABIC MATHEMATICAL DOUBLE-STRUCK YEH
 1EEAB..1EEBB  ; XID_Start # Lo  [17] ARABIC MATHEMATICAL DOUBLE-STRUCK LAM..ARABIC MATHEMATICAL DOUBLE-STRUCK GHAIN
 20000..2A6DF  ; XID_Start # Lo [42720] CJK UNIFIED IDEOGRAPH-20000..CJK UNIFIED IDEOGRAPH-2A6DF
-2A700..2B738  ; XID_Start # Lo [4153] CJK UNIFIED IDEOGRAPH-2A700..CJK UNIFIED IDEOGRAPH-2B738
+2A700..2B739  ; XID_Start # Lo [4154] CJK UNIFIED IDEOGRAPH-2A700..CJK UNIFIED IDEOGRAPH-2B739
 2B740..2B81D  ; XID_Start # Lo [222] CJK UNIFIED IDEOGRAPH-2B740..CJK UNIFIED IDEOGRAPH-2B81D
 2B820..2CEA1  ; XID_Start # Lo [5762] CJK UNIFIED IDEOGRAPH-2B820..CJK UNIFIED IDEOGRAPH-2CEA1
 2CEB0..2EBE0  ; XID_Start # Lo [7473] CJK UNIFIED IDEOGRAPH-2CEB0..CJK UNIFIED IDEOGRAPH-2EBE0
 2F800..2FA1D  ; XID_Start # Lo [542] CJK COMPATIBILITY IDEOGRAPH-2F800..CJK COMPATIBILITY IDEOGRAPH-2FA1D
 30000..3134A  ; XID_Start # Lo [4939] CJK UNIFIED IDEOGRAPH-30000..CJK UNIFIED IDEOGRAPH-3134A
+31350..323AF  ; XID_Start # Lo [4192] CJK UNIFIED IDEOGRAPH-31350..CJK UNIFIED IDEOGRAPH-323AF
 
-# Total code points: 131974
+# Total code points: 136322
 
 # ================================================
 
@@ -9147,6 +9245,7 @@ FFDA..FFDC    ; XID_Start # Lo   [3] HALFWIDTH HANGUL LETTER EU..HALFWIDTH HANGU
 0CE2..0CE3    ; XID_Continue # Mn   [2] KANNADA VOWEL SIGN VOCALIC L..KANNADA VOWEL SIGN VOCALIC LL
 0CE6..0CEF    ; XID_Continue # Nd  [10] KANNADA DIGIT ZERO..KANNADA DIGIT NINE
 0CF1..0CF2    ; XID_Continue # Lo   [2] KANNADA SIGN JIHVAMULIYA..KANNADA SIGN UPADHMANIYA
+0CF3          ; XID_Continue # Mc       KANNADA SIGN COMBINING ANUSVARA ABOVE RIGHT
 0D00..0D01    ; XID_Continue # Mn   [2] MALAYALAM SIGN COMBINING ANUSVARA ABOVE..MALAYALAM SIGN CANDRABINDU
 0D02..0D03    ; XID_Continue # Mc   [2] MALAYALAM SIGN ANUSVARA..MALAYALAM SIGN VISARGA
 0D04..0D0C    ; XID_Continue # Lo   [9] MALAYALAM LETTER VEDIC ANUSVARA..MALAYALAM LETTER VOCALIC L
@@ -9200,7 +9299,7 @@ FFDA..FFDC    ; XID_Start # Lo   [3] HALFWIDTH HANGUL LETTER EU..HALFWIDTH HANGU
 0EBD          ; XID_Continue # Lo       LAO SEMIVOWEL SIGN NYO
 0EC0..0EC4    ; XID_Continue # Lo   [5] LAO VOWEL SIGN E..LAO VOWEL SIGN AI
 0EC6          ; XID_Continue # Lm       LAO KO LA
-0EC8..0ECD    ; XID_Continue # Mn   [6] LAO TONE MAI EK..LAO NIGGAHITA
+0EC8..0ECE    ; XID_Continue # Mn   [7] LAO TONE MAI EK..LAO YAMAKKAN
 0ED0..0ED9    ; XID_Continue # Nd  [10] LAO DIGIT ZERO..LAO DIGIT NINE
 0EDC..0EDF    ; XID_Continue # Lo   [4] LAO HO NO..LAO LETTER KHMU NYO
 0F00          ; XID_Continue # Lo       TIBETAN SYLLABLE OM
@@ -9788,6 +9887,7 @@ FFDA..FFDC    ; XID_Continue # Lo   [3] HALFWIDTH HANGUL LETTER EU..HALFWIDTH HA
 10E80..10EA9  ; XID_Continue # Lo  [42] YEZIDI LETTER ELIF..YEZIDI LETTER ET
 10EAB..10EAC  ; XID_Continue # Mn   [2] YEZIDI COMBINING HAMZA MARK..YEZIDI COMBINING MADDA MARK
 10EB0..10EB1  ; XID_Continue # Lo   [2] YEZIDI LETTER LAM WITH DOT ABOVE..YEZIDI LETTER YOT WITH CIRCUMFLEX ABOVE
+10EFD..10EFF  ; XID_Continue # Mn   [3] ARABIC SMALL LOW WORD SAKTA..ARABIC SMALL LOW WORD MADDA
 10F00..10F1C  ; XID_Continue # Lo  [29] OLD SOGDIAN LETTER ALEPH..OLD SOGDIAN LETTER FINAL TAW WITH VERTICAL TAIL
 10F27         ; XID_Continue # Lo       OLD SOGDIAN LIGATURE AYIN-DALETH
 10F30..10F45  ; XID_Continue # Lo  [22] SOGDIAN LETTER ALEPH..SOGDIAN INDEPENDENT SHIN
@@ -9850,6 +9950,8 @@ FFDA..FFDC    ; XID_Continue # Lo   [3] HALFWIDTH HANGUL LETTER EU..HALFWIDTH HA
 11235         ; XID_Continue # Mc       KHOJKI SIGN VIRAMA
 11236..11237  ; XID_Continue # Mn   [2] KHOJKI SIGN NUKTA..KHOJKI SIGN SHADDA
 1123E         ; XID_Continue # Mn       KHOJKI SIGN SUKUN
+1123F..11240  ; XID_Continue # Lo   [2] KHOJKI LETTER QA..KHOJKI LETTER SHORT I
+11241         ; XID_Continue # Mn       KHOJKI VOWEL SIGN VOCALIC R
 11280..11286  ; XID_Continue # Lo   [7] MULTANI LETTER A..MULTANI LETTER GA
 11288         ; XID_Continue # Lo       MULTANI LETTER GHA
 1128A..1128D  ; XID_Continue # Lo   [4] MULTANI LETTER CA..MULTANI LETTER JJA
@@ -10032,12 +10134,27 @@ FFDA..FFDC    ; XID_Continue # Lo   [3] HALFWIDTH HANGUL LETTER EU..HALFWIDTH HA
 11EE0..11EF2  ; XID_Continue # Lo  [19] MAKASAR LETTER KA..MAKASAR ANGKA
 11EF3..11EF4  ; XID_Continue # Mn   [2] MAKASAR VOWEL SIGN I..MAKASAR VOWEL SIGN U
 11EF5..11EF6  ; XID_Continue # Mc   [2] MAKASAR VOWEL SIGN E..MAKASAR VOWEL SIGN O
+11F00..11F01  ; XID_Continue # Mn   [2] KAWI SIGN CANDRABINDU..KAWI SIGN ANUSVARA
+11F02         ; XID_Continue # Lo       KAWI SIGN REPHA
+11F03         ; XID_Continue # Mc       KAWI SIGN VISARGA
+11F04..11F10  ; XID_Continue # Lo  [13] KAWI LETTER A..KAWI LETTER O
+11F12..11F33  ; XID_Continue # Lo  [34] KAWI LETTER KA..KAWI LETTER JNYA
+11F34..11F35  ; XID_Continue # Mc   [2] KAWI VOWEL SIGN AA..KAWI VOWEL SIGN ALTERNATE AA
+11F36..11F3A  ; XID_Continue # Mn   [5] KAWI VOWEL SIGN I..KAWI VOWEL SIGN VOCALIC R
+11F3E..11F3F  ; XID_Continue # Mc   [2] KAWI VOWEL SIGN E..KAWI VOWEL SIGN AI
+11F40         ; XID_Continue # Mn       KAWI VOWEL SIGN EU
+11F41         ; XID_Continue # Mc       KAWI SIGN KILLER
+11F42         ; XID_Continue # Mn       KAWI CONJOINER
+11F50..11F59  ; XID_Continue # Nd  [10] KAWI DIGIT ZERO..KAWI DIGIT NINE
 11FB0         ; XID_Continue # Lo       LISU LETTER YHA
 12000..12399  ; XID_Continue # Lo [922] CUNEIFORM SIGN A..CUNEIFORM SIGN U U
 12400..1246E  ; XID_Continue # Nl [111] CUNEIFORM NUMERIC SIGN TWO ASH..CUNEIFORM NUMERIC SIGN NINE U VARIANT FORM
 12480..12543  ; XID_Continue # Lo [196] CUNEIFORM SIGN AB TIMES NUN TENU..CUNEIFORM SIGN ZU5 TIMES THREE DISH TENU
 12F90..12FF0  ; XID_Continue # Lo  [97] CYPRO-MINOAN SIGN CM001..CYPRO-MINOAN SIGN CM114
-13000..1342E  ; XID_Continue # Lo [1071] EGYPTIAN HIEROGLYPH A001..EGYPTIAN HIEROGLYPH AA032
+13000..1342F  ; XID_Continue # Lo [1072] EGYPTIAN HIEROGLYPH A001..EGYPTIAN HIEROGLYPH V011D
+13440         ; XID_Continue # Mn       EGYPTIAN HIEROGLYPH MIRROR HORIZONTALLY
+13441..13446  ; XID_Continue # Lo   [6] EGYPTIAN HIEROGLYPH FULL BLANK..EGYPTIAN HIEROGLYPH WIDE LOST SIGN
+13447..13455  ; XID_Continue # Mn  [15] EGYPTIAN HIEROGLYPH MODIFIER DAMAGED AT TOP START..EGYPTIAN HIEROGLYPH MODIFIER DAMAGED
 14400..14646  ; XID_Continue # Lo [583] ANATOLIAN HIEROGLYPH A001..ANATOLIAN HIEROGLYPH A530
 16800..16A38  ; XID_Continue # Lo [569] BAMUM LETTER PHASE-A NGKUE MFON..BAMUM LETTER PHASE-F VUEQ
 16A40..16A5E  ; XID_Continue # Lo  [31] MRO LETTER TA..MRO LETTER TEK
@@ -10070,7 +10187,9 @@ FFDA..FFDC    ; XID_Continue # Lo   [3] HALFWIDTH HANGUL LETTER EU..HALFWIDTH HA
 1AFF5..1AFFB  ; XID_Continue # Lm   [7] KATAKANA LETTER MINNAN TONE-7..KATAKANA LETTER MINNAN NASALIZED TONE-5
 1AFFD..1AFFE  ; XID_Continue # Lm   [2] KATAKANA LETTER MINNAN NASALIZED TONE-7..KATAKANA LETTER MINNAN NASALIZED TONE-8
 1B000..1B122  ; XID_Continue # Lo [291] KATAKANA LETTER ARCHAIC E..KATAKANA LETTER ARCHAIC WU
+1B132         ; XID_Continue # Lo       HIRAGANA LETTER SMALL KO
 1B150..1B152  ; XID_Continue # Lo   [3] HIRAGANA LETTER SMALL WI..HIRAGANA LETTER SMALL WO
+1B155         ; XID_Continue # Lo       KATAKANA LETTER SMALL KO
 1B164..1B167  ; XID_Continue # Lo   [4] KATAKANA LETTER SMALL WI..KATAKANA LETTER SMALL N
 1B170..1B2FB  ; XID_Continue # Lo [396] NUSHU CHARACTER-1B170..NUSHU CHARACTER-1B2FB
 1BC00..1BC6A  ; XID_Continue # Lo [107] DUPLOYAN LETTER H..DUPLOYAN LETTER VOCALIC M
@@ -10127,11 +10246,14 @@ FFDA..FFDC    ; XID_Continue # Lo   [3] HALFWIDTH HANGUL LETTER EU..HALFWIDTH HA
 1DF00..1DF09  ; XID_Continue # L&  [10] LATIN SMALL LETTER FENG DIGRAPH WITH TRILL..LATIN SMALL LETTER T WITH HOOK AND RETROFLEX HOOK
 1DF0A         ; XID_Continue # Lo       LATIN LETTER RETROFLEX CLICK WITH RETROFLEX HOOK
 1DF0B..1DF1E  ; XID_Continue # L&  [20] LATIN SMALL LETTER ESH WITH DOUBLE BAR..LATIN SMALL LETTER S WITH CURL
+1DF25..1DF2A  ; XID_Continue # L&   [6] LATIN SMALL LETTER D WITH MID-HEIGHT LEFT HOOK..LATIN SMALL LETTER T WITH MID-HEIGHT LEFT HOOK
 1E000..1E006  ; XID_Continue # Mn   [7] COMBINING GLAGOLITIC LETTER AZU..COMBINING GLAGOLITIC LETTER ZHIVETE
 1E008..1E018  ; XID_Continue # Mn  [17] COMBINING GLAGOLITIC LETTER ZEMLJA..COMBINING GLAGOLITIC LETTER HERU
 1E01B..1E021  ; XID_Continue # Mn   [7] COMBINING GLAGOLITIC LETTER SHTA..COMBINING GLAGOLITIC LETTER YATI
 1E023..1E024  ; XID_Continue # Mn   [2] COMBINING GLAGOLITIC LETTER YU..COMBINING GLAGOLITIC LETTER SMALL YUS
 1E026..1E02A  ; XID_Continue # Mn   [5] COMBINING GLAGOLITIC LETTER YO..COMBINING GLAGOLITIC LETTER FITA
+1E030..1E06D  ; XID_Continue # Lm  [62] MODIFIER LETTER CYRILLIC SMALL A..MODIFIER LETTER CYRILLIC SMALL STRAIGHT U WITH STROKE
+1E08F         ; XID_Continue # Mn       COMBINING CYRILLIC SMALL LETTER BYELORUSSIAN-UKRAINIAN I
 1E100..1E12C  ; XID_Continue # Lo  [45] NYIAKENG PUACHUE HMONG LETTER MA..NYIAKENG PUACHUE HMONG LETTER W
 1E130..1E136  ; XID_Continue # Mn   [7] NYIAKENG PUACHUE HMONG TONE-B..NYIAKENG PUACHUE HMONG TONE-D
 1E137..1E13D  ; XID_Continue # Lm   [7] NYIAKENG PUACHUE HMONG SIGN FOR PERSON..NYIAKENG PUACHUE HMONG SYLLABLE LENGTHENER
@@ -10142,6 +10264,10 @@ FFDA..FFDC    ; XID_Continue # Lo   [3] HALFWIDTH HANGUL LETTER EU..HALFWIDTH HA
 1E2C0..1E2EB  ; XID_Continue # Lo  [44] WANCHO LETTER AA..WANCHO LETTER YIH
 1E2EC..1E2EF  ; XID_Continue # Mn   [4] WANCHO TONE TUP..WANCHO TONE KOINI
 1E2F0..1E2F9  ; XID_Continue # Nd  [10] WANCHO DIGIT ZERO..WANCHO DIGIT NINE
+1E4D0..1E4EA  ; XID_Continue # Lo  [27] NAG MUNDARI LETTER O..NAG MUNDARI LETTER ELL
+1E4EB         ; XID_Continue # Lm       NAG MUNDARI SIGN OJOD
+1E4EC..1E4EF  ; XID_Continue # Mn   [4] NAG MUNDARI SIGN MUHOR..NAG MUNDARI SIGN SUTUH
+1E4F0..1E4F9  ; XID_Continue # Nd  [10] NAG MUNDARI DIGIT ZERO..NAG MUNDARI DIGIT NINE
 1E7E0..1E7E6  ; XID_Continue # Lo   [7] ETHIOPIC SYLLABLE HHYA..ETHIOPIC SYLLABLE HHYO
 1E7E8..1E7EB  ; XID_Continue # Lo   [4] ETHIOPIC SYLLABLE GURAGE HHWA..ETHIOPIC SYLLABLE HHWE
 1E7ED..1E7EE  ; XID_Continue # Lo   [2] ETHIOPIC SYLLABLE GURAGE MWI..ETHIOPIC SYLLABLE GURAGE MWEE
@@ -10187,15 +10313,16 @@ FFDA..FFDC    ; XID_Continue # Lo   [3] HALFWIDTH HANGUL LETTER EU..HALFWIDTH HA
 1EEAB..1EEBB  ; XID_Continue # Lo  [17] ARABIC MATHEMATICAL DOUBLE-STRUCK LAM..ARABIC MATHEMATICAL DOUBLE-STRUCK GHAIN
 1FBF0..1FBF9  ; XID_Continue # Nd  [10] SEGMENTED DIGIT ZERO..SEGMENTED DIGIT NINE
 20000..2A6DF  ; XID_Continue # Lo [42720] CJK UNIFIED IDEOGRAPH-20000..CJK UNIFIED IDEOGRAPH-2A6DF
-2A700..2B738  ; XID_Continue # Lo [4153] CJK UNIFIED IDEOGRAPH-2A700..CJK UNIFIED IDEOGRAPH-2B738
+2A700..2B739  ; XID_Continue # Lo [4154] CJK UNIFIED IDEOGRAPH-2A700..CJK UNIFIED IDEOGRAPH-2B739
 2B740..2B81D  ; XID_Continue # Lo [222] CJK UNIFIED IDEOGRAPH-2B740..CJK UNIFIED IDEOGRAPH-2B81D
 2B820..2CEA1  ; XID_Continue # Lo [5762] CJK UNIFIED IDEOGRAPH-2B820..CJK UNIFIED IDEOGRAPH-2CEA1
 2CEB0..2EBE0  ; XID_Continue # Lo [7473] CJK UNIFIED IDEOGRAPH-2CEB0..CJK UNIFIED IDEOGRAPH-2EBE0
 2F800..2FA1D  ; XID_Continue # Lo [542] CJK COMPATIBILITY IDEOGRAPH-2F800..CJK COMPATIBILITY IDEOGRAPH-2FA1D
 30000..3134A  ; XID_Continue # Lo [4939] CJK UNIFIED IDEOGRAPH-30000..CJK UNIFIED IDEOGRAPH-3134A
+31350..323AF  ; XID_Continue # Lo [4192] CJK UNIFIED IDEOGRAPH-31350..CJK UNIFIED IDEOGRAPH-323AF
 E0100..E01EF  ; XID_Continue # Mn [240] VARIATION SELECTOR-17..VARIATION SELECTOR-256
 
-# Total code points: 135053
+# Total code points: 139463
 
 # ================================================
 
@@ -10206,7 +10333,7 @@ E0100..E01EF  ; XID_Continue # Mn [240] VARIATION SELECTOR-17..VARIATION SELECTO
 #  + Variation_Selector
 #  - White_Space
 #  - FFF9..FFFB (Interlinear annotation format characters)
-#  - 13430..13438 (Egyptian hieroglyph format characters)
+#  - 13430..13440 (Egyptian hieroglyph format characters)
 #  - Prepended_Concatenation_Mark (Exceptional format characters that should be visible)
 
 00AD          ; Default_Ignorable_Code_Point # Cf       SOFT HYPHEN
@@ -10351,7 +10478,7 @@ E01F0..E0FFF  ; Default_Ignorable_Code_Point # Cn [3600] ..
 0CE4..0CE5    ; Cn #   [2] ..
 0CF0          ; Cn #       
-0CF3..0CFF    ; Cn #  [13] ..
+0CF4..0CFF    ; Cn #  [12] ..
 0D0D          ; Cn #       
 0D11          ; Cn #       
 0D45          ; Cn #       
@@ -166,7 +166,7 @@
 0EBE..0EBF    ; Cn #   [2] ..
 0EC5          ; Cn #       
 0EC7          ; Cn #       
-0ECE..0ECF    ; Cn #   [2] ..
+0ECF          ; Cn #       
 0EDA..0EDB    ; Cn #   [2] ..
 0EE0..0EFF    ; Cn #  [32] ..
 0F48          ; Cn #       
@@ -436,7 +436,7 @@ FFFE..FFFF    ; Cn #   [2] ..
 10E7F         ; Cn #       
 10EAA         ; Cn #       
 10EAE..10EAF  ; Cn #   [2] ..
-10EB2..10EFF  ; Cn #  [78] ..
+10EB2..10EFC  ; Cn #  [75] ..
 10F28..10F2F  ; Cn #   [8] ..
 10F5A..10F6F  ; Cn #  [22] ..
 10F8A..10FAF  ; Cn #  [38] ..
@@ -454,7 +454,7 @@ FFFE..FFFF    ; Cn #   [2] ..
 111E0         ; Cn #       
 111F5..111FF  ; Cn #  [11] ..
 11212         ; Cn #       
-1123F..1127F  ; Cn #  [65] ..
+11242..1127F  ; Cn #  [62] ..
 11287         ; Cn #       
 11289         ; Cn #       
 1128E         ; Cn #       
@@ -506,7 +506,8 @@ FFFE..FFFF    ; Cn #   [2] ..
 119E5..119FF  ; Cn #  [27] ..
 11A48..11A4F  ; Cn #   [8] ..
 11AA3..11AAF  ; Cn #  [13] ..
-11AF9..11BFF  ; Cn # [263] ..
+11AF9..11AFF  ; Cn #   [7] ..
+11B0A..11BFF  ; Cn # [246] ..
 11C09         ; Cn #       
 11C37         ; Cn #       
 11C46..11C4F  ; Cn #  [10] ..
@@ -527,7 +528,10 @@ FFFE..FFFF    ; Cn #   [2] ..
 11D92         ; Cn #       
 11D99..11D9F  ; Cn #   [7] ..
 11DAA..11EDF  ; Cn # [310] ..
-11EF9..11FAF  ; Cn # [183] ..
+11EF9..11EFF  ; Cn #   [7] ..
+11F11         ; Cn #       
+11F3B..11F3D  ; Cn #   [3] ..
+11F5A..11FAF  ; Cn #  [86] ..
 11FB1..11FBF  ; Cn #  [15] ..
 11FF2..11FFE  ; Cn #  [13] ..
 1239A..123FF  ; Cn # [102] ..
@@ -535,8 +539,7 @@ FFFE..FFFF    ; Cn #   [2] ..
 12475..1247F  ; Cn #  [11] ..
 12544..12F8F  ; Cn # [2636] ..
 12FF3..12FFF  ; Cn #  [13] ..
-1342F         ; Cn #       
-13439..143FF  ; Cn # [4039] ..
+13456..143FF  ; Cn # [4010] ..
 14647..167FF  ; Cn # [8633] ..
 16A39..16A3F  ; Cn #   [7] ..
 16A5F         ; Cn #       
@@ -562,8 +565,10 @@ FFFE..FFFF    ; Cn #   [2] ..
 1AFF4         ; Cn #       
 1AFFC         ; Cn #       
 1AFFF         ; Cn #       
-1B123..1B14F  ; Cn #  [45] ..
-1B153..1B163  ; Cn #  [17] ..
+1B123..1B131  ; Cn #  [15] ..
+1B133..1B14F  ; Cn #  [29] ..
+1B153..1B154  ; Cn #   [2] ..
+1B156..1B163  ; Cn #  [14] ..
 1B168..1B16F  ; Cn #   [8] ..
 1B2FC..1BBFF  ; Cn # [2308] ..
 1BC6B..1BC6F  ; Cn #   [5] ..
@@ -577,7 +582,8 @@ FFFE..FFFF    ; Cn #   [2] ..
 1D0F6..1D0FF  ; Cn #  [10] ..
 1D127..1D128  ; Cn #   [2] ..
 1D1EB..1D1FF  ; Cn #  [21] ..
-1D246..1D2DF  ; Cn # [154] ..
+1D246..1D2BF  ; Cn # [122] ..
+1D2D4..1D2DF  ; Cn #  [12] ..
 1D2F4..1D2FF  ; Cn #  [12] ..
 1D357..1D35F  ; Cn #   [9] ..
 1D379..1D3FF  ; Cn # [135] ..
@@ -604,19 +610,23 @@ FFFE..FFFF    ; Cn #   [2] ..
 1DA8C..1DA9A  ; Cn #  [15] ..
 1DAA0         ; Cn #       
 1DAB0..1DEFF  ; Cn # [1104] ..
-1DF1F..1DFFF  ; Cn # [225] ..
+1DF1F..1DF24  ; Cn #   [6] ..
+1DF2B..1DFFF  ; Cn # [213] ..
 1E007         ; Cn #       
 1E019..1E01A  ; Cn #   [2] ..
 1E022         ; Cn #       
 1E025         ; Cn #       
-1E02B..1E0FF  ; Cn # [213] ..
+1E02B..1E02F  ; Cn #   [5] ..
+1E06E..1E08E  ; Cn #  [33] ..
+1E090..1E0FF  ; Cn # [112] ..
 1E12D..1E12F  ; Cn #   [3] ..
 1E13E..1E13F  ; Cn #   [2] ..
 1E14A..1E14D  ; Cn #   [4] ..
 1E150..1E28F  ; Cn # [320] ..
 1E2AF..1E2BF  ; Cn #  [17] ..
 1E2FA..1E2FE  ; Cn #   [5] ..
-1E300..1E7DF  ; Cn # [1248] ..
+1E300..1E4CF  ; Cn # [464] ..
+1E4FA..1E7DF  ; Cn # [742] ..
 1E7E7         ; Cn #       
 1E7EC         ; Cn #       
 1E7EF         ; Cn #       
@@ -674,11 +684,11 @@ FFFE..FFFF    ; Cn #   [2] ..
 1F249..1F24F  ; Cn #   [7] ..
 1F252..1F25F  ; Cn #  [14] ..
 1F266..1F2FF  ; Cn # [154] ..
-1F6D8..1F6DC  ; Cn #   [5] ..
+1F6D8..1F6DB  ; Cn #   [4] ..
 1F6ED..1F6EF  ; Cn #   [3] ..
 1F6FD..1F6FF  ; Cn #   [3] ..
-1F774..1F77F  ; Cn #  [12] ..
-1F7D9..1F7DF  ; Cn #   [7] ..
+1F777..1F77A  ; Cn #   [4] ..
+1F7DA..1F7DF  ; Cn #   [6] ..
 1F7EC..1F7EF  ; Cn #   [4] ..
 1F7F1..1F7FF  ; Cn #  [15] ..
 1F80C..1F80F  ; Cn #   [4] ..
@@ -689,32 +699,31 @@ FFFE..FFFF    ; Cn #   [2] ..
 1F8B2..1F8FF  ; Cn #  [78] ..
 1FA54..1FA5F  ; Cn #  [12] ..
 1FA6E..1FA6F  ; Cn #   [2] ..
-1FA75..1FA77  ; Cn #   [3] ..
 1FA7D..1FA7F  ; Cn #   [3] ..
-1FA87..1FA8F  ; Cn #   [9] ..
-1FAAD..1FAAF  ; Cn #   [3] ..
-1FABB..1FABF  ; Cn #   [5] ..
-1FAC6..1FACF  ; Cn #  [10] ..
-1FADA..1FADF  ; Cn #   [6] ..
-1FAE8..1FAEF  ; Cn #   [8] ..
-1FAF7..1FAFF  ; Cn #   [9] ..
+1FA89..1FA8F  ; Cn #   [7] ..
+1FABE         ; Cn #       
+1FAC6..1FACD  ; Cn #   [8] ..
+1FADC..1FADF  ; Cn #   [4] ..
+1FAE9..1FAEF  ; Cn #   [7] ..
+1FAF9..1FAFF  ; Cn #   [7] ..
 1FB93         ; Cn #       
 1FBCB..1FBEF  ; Cn #  [37] ..
 1FBFA..1FFFF  ; Cn # [1030] ..
 2A6E0..2A6FF  ; Cn #  [32] ..
-2B739..2B73F  ; Cn #   [7] ..
+2B73A..2B73F  ; Cn #   [6] ..
 2B81E..2B81F  ; Cn #   [2] ..
 2CEA2..2CEAF  ; Cn #  [14] ..
 2EBE1..2F7FF  ; Cn # [3103] ..
 2FA1E..2FFFF  ; Cn # [1506] ..
-3134B..E0000  ; Cn # [715958] ..
+3134B..3134F  ; Cn #   [5] ..
+323B0..E0000  ; Cn # [711761] ..
 E0002..E001F  ; Cn #  [30] ..
 E0080..E00FF  ; Cn # [128] ..
 E01F0..EFFFF  ; Cn # [65040] ..
 FFFFE..FFFFF  ; Cn #   [2] ..
 10FFFE..10FFFF; Cn #   [2] ..
 
-# Total code points: 829834
+# Total code points: 825345
 
 # ================================================
 
@@ -2029,9 +2038,10 @@ FF41..FF5A    ; Ll #  [26] FULLWIDTH LATIN SMALL LETTER A..FULLWIDTH LATIN SMALL
 1D7CB         ; Ll #       MATHEMATICAL BOLD SMALL DIGAMMA
 1DF00..1DF09  ; Ll #  [10] LATIN SMALL LETTER FENG DIGRAPH WITH TRILL..LATIN SMALL LETTER T WITH HOOK AND RETROFLEX HOOK
 1DF0B..1DF1E  ; Ll #  [20] LATIN SMALL LETTER ESH WITH DOUBLE BAR..LATIN SMALL LETTER S WITH CURL
+1DF25..1DF2A  ; Ll #   [6] LATIN SMALL LETTER D WITH MID-HEIGHT LEFT HOOK..LATIN SMALL LETTER T WITH MID-HEIGHT LEFT HOOK
 1E922..1E943  ; Ll #  [34] ADLAM SMALL LETTER ALIF..ADLAM SMALL LETTER SHA
 
-# Total code points: 2227
+# Total code points: 2233
 
 # ================================================
 
@@ -2121,10 +2131,12 @@ FF9E..FF9F    ; Lm #   [2] HALFWIDTH KATAKANA VOICED SOUND MARK..HALFWIDTH KATAK
 1AFF0..1AFF3  ; Lm #   [4] KATAKANA LETTER MINNAN TONE-2..KATAKANA LETTER MINNAN TONE-5
 1AFF5..1AFFB  ; Lm #   [7] KATAKANA LETTER MINNAN TONE-7..KATAKANA LETTER MINNAN NASALIZED TONE-5
 1AFFD..1AFFE  ; Lm #   [2] KATAKANA LETTER MINNAN NASALIZED TONE-7..KATAKANA LETTER MINNAN NASALIZED TONE-8
+1E030..1E06D  ; Lm #  [62] MODIFIER LETTER CYRILLIC SMALL A..MODIFIER LETTER CYRILLIC SMALL STRAIGHT U WITH STROKE
 1E137..1E13D  ; Lm #   [7] NYIAKENG PUACHUE HMONG SIGN FOR PERSON..NYIAKENG PUACHUE HMONG SYLLABLE LENGTHENER
+1E4EB         ; Lm #       NAG MUNDARI SIGN OJOD
 1E94B         ; Lm #       ADLAM NASALIZATION MARK
 
-# Total code points: 334
+# Total code points: 397
 
 # ================================================
 
@@ -2494,6 +2506,7 @@ FFDA..FFDC    ; Lo #   [3] HALFWIDTH HANGUL LETTER EU..HALFWIDTH HANGUL LETTER I
 111DC         ; Lo #       SHARADA HEADSTROKE
 11200..11211  ; Lo #  [18] KHOJKI LETTER A..KHOJKI LETTER JJA
 11213..1122B  ; Lo #  [25] KHOJKI LETTER NYA..KHOJKI LETTER LLA
+1123F..11240  ; Lo #   [2] KHOJKI LETTER QA..KHOJKI LETTER SHORT I
 11280..11286  ; Lo #   [7] MULTANI LETTER A..MULTANI LETTER GA
 11288         ; Lo #       MULTANI LETTER GHA
 1128A..1128D  ; Lo #   [4] MULTANI LETTER CA..MULTANI LETTER JJA
@@ -2555,11 +2568,15 @@ FFDA..FFDC    ; Lo #   [3] HALFWIDTH HANGUL LETTER EU..HALFWIDTH HANGUL LETTER I
 11D6A..11D89  ; Lo #  [32] GUNJALA GONDI LETTER OO..GUNJALA GONDI LETTER SA
 11D98         ; Lo #       GUNJALA GONDI OM
 11EE0..11EF2  ; Lo #  [19] MAKASAR LETTER KA..MAKASAR ANGKA
+11F02         ; Lo #       KAWI SIGN REPHA
+11F04..11F10  ; Lo #  [13] KAWI LETTER A..KAWI LETTER O
+11F12..11F33  ; Lo #  [34] KAWI LETTER KA..KAWI LETTER JNYA
 11FB0         ; Lo #       LISU LETTER YHA
 12000..12399  ; Lo # [922] CUNEIFORM SIGN A..CUNEIFORM SIGN U U
 12480..12543  ; Lo # [196] CUNEIFORM SIGN AB TIMES NUN TENU..CUNEIFORM SIGN ZU5 TIMES THREE DISH TENU
 12F90..12FF0  ; Lo #  [97] CYPRO-MINOAN SIGN CM001..CYPRO-MINOAN SIGN CM114
-13000..1342E  ; Lo # [1071] EGYPTIAN HIEROGLYPH A001..EGYPTIAN HIEROGLYPH AA032
+13000..1342F  ; Lo # [1072] EGYPTIAN HIEROGLYPH A001..EGYPTIAN HIEROGLYPH V011D
+13441..13446  ; Lo #   [6] EGYPTIAN HIEROGLYPH FULL BLANK..EGYPTIAN HIEROGLYPH WIDE LOST SIGN
 14400..14646  ; Lo # [583] ANATOLIAN HIEROGLYPH A001..ANATOLIAN HIEROGLYPH A530
 16800..16A38  ; Lo # [569] BAMUM LETTER PHASE-A NGKUE MFON..BAMUM LETTER PHASE-F VUEQ
 16A40..16A5E  ; Lo #  [31] MRO LETTER TA..MRO LETTER TEK
@@ -2574,7 +2591,9 @@ FFDA..FFDC    ; Lo #   [3] HALFWIDTH HANGUL LETTER EU..HALFWIDTH HANGUL LETTER I
 18800..18CD5  ; Lo # [1238] TANGUT COMPONENT-001..KHITAN SMALL SCRIPT CHARACTER-18CD5
 18D00..18D08  ; Lo #   [9] TANGUT IDEOGRAPH-18D00..TANGUT IDEOGRAPH-18D08
 1B000..1B122  ; Lo # [291] KATAKANA LETTER ARCHAIC E..KATAKANA LETTER ARCHAIC WU
+1B132         ; Lo #       HIRAGANA LETTER SMALL KO
 1B150..1B152  ; Lo #   [3] HIRAGANA LETTER SMALL WI..HIRAGANA LETTER SMALL WO
+1B155         ; Lo #       KATAKANA LETTER SMALL KO
 1B164..1B167  ; Lo #   [4] KATAKANA LETTER SMALL WI..KATAKANA LETTER SMALL N
 1B170..1B2FB  ; Lo # [396] NUSHU CHARACTER-1B170..NUSHU CHARACTER-1B2FB
 1BC00..1BC6A  ; Lo # [107] DUPLOYAN LETTER H..DUPLOYAN LETTER VOCALIC M
@@ -2586,6 +2605,7 @@ FFDA..FFDC    ; Lo #   [3] HALFWIDTH HANGUL LETTER EU..HALFWIDTH HANGUL LETTER I
 1E14E         ; Lo #       NYIAKENG PUACHUE HMONG LOGOGRAM NYAJ
 1E290..1E2AD  ; Lo #  [30] TOTO LETTER PA..TOTO LETTER A
 1E2C0..1E2EB  ; Lo #  [44] WANCHO LETTER AA..WANCHO LETTER YIH
+1E4D0..1E4EA  ; Lo #  [27] NAG MUNDARI LETTER O..NAG MUNDARI LETTER ELL
 1E7E0..1E7E6  ; Lo #   [7] ETHIOPIC SYLLABLE HHYA..ETHIOPIC SYLLABLE HHYO
 1E7E8..1E7EB  ; Lo #   [4] ETHIOPIC SYLLABLE GURAGE HHWA..ETHIOPIC SYLLABLE HHWE
 1E7ED..1E7EE  ; Lo #   [2] ETHIOPIC SYLLABLE GURAGE MWI..ETHIOPIC SYLLABLE GURAGE MWEE
@@ -2625,14 +2645,15 @@ FFDA..FFDC    ; Lo #   [3] HALFWIDTH HANGUL LETTER EU..HALFWIDTH HANGUL LETTER I
 1EEA5..1EEA9  ; Lo #   [5] ARABIC MATHEMATICAL DOUBLE-STRUCK WAW..ARABIC MATHEMATICAL DOUBLE-STRUCK YEH
 1EEAB..1EEBB  ; Lo #  [17] ARABIC MATHEMATICAL DOUBLE-STRUCK LAM..ARABIC MATHEMATICAL DOUBLE-STRUCK GHAIN
 20000..2A6DF  ; Lo # [42720] CJK UNIFIED IDEOGRAPH-20000..CJK UNIFIED IDEOGRAPH-2A6DF
-2A700..2B738  ; Lo # [4153] CJK UNIFIED IDEOGRAPH-2A700..CJK UNIFIED IDEOGRAPH-2B738
+2A700..2B739  ; Lo # [4154] CJK UNIFIED IDEOGRAPH-2A700..CJK UNIFIED IDEOGRAPH-2B739
 2B740..2B81D  ; Lo # [222] CJK UNIFIED IDEOGRAPH-2B740..CJK UNIFIED IDEOGRAPH-2B81D
 2B820..2CEA1  ; Lo # [5762] CJK UNIFIED IDEOGRAPH-2B820..CJK UNIFIED IDEOGRAPH-2CEA1
 2CEB0..2EBE0  ; Lo # [7473] CJK UNIFIED IDEOGRAPH-2CEB0..CJK UNIFIED IDEOGRAPH-2EBE0
 2F800..2FA1D  ; Lo # [542] CJK COMPATIBILITY IDEOGRAPH-2F800..CJK COMPATIBILITY IDEOGRAPH-2FA1D
 30000..3134A  ; Lo # [4939] CJK UNIFIED IDEOGRAPH-30000..CJK UNIFIED IDEOGRAPH-3134A
+31350..323AF  ; Lo # [4192] CJK UNIFIED IDEOGRAPH-31350..CJK UNIFIED IDEOGRAPH-323AF
 
-# Total code points: 127333
+# Total code points: 131612
 
 # ================================================
 
@@ -2730,7 +2751,7 @@ FFDA..FFDC    ; Lo #   [3] HALFWIDTH HANGUL LETTER EU..HALFWIDTH HANGUL LETTER I
 0E47..0E4E    ; Mn #   [8] THAI CHARACTER MAITAIKHU..THAI CHARACTER YAMAKKAN
 0EB1          ; Mn #       LAO VOWEL SIGN MAI KAN
 0EB4..0EBC    ; Mn #   [9] LAO VOWEL SIGN I..LAO SEMIVOWEL SIGN LO
-0EC8..0ECD    ; Mn #   [6] LAO TONE MAI EK..LAO NIGGAHITA
+0EC8..0ECE    ; Mn #   [7] LAO TONE MAI EK..LAO YAMAKKAN
 0F18..0F19    ; Mn #   [2] TIBETAN ASTROLOGICAL SIGN -KHYUD PA..TIBETAN ASTROLOGICAL SIGN SDONG TSHUGS
 0F35          ; Mn #       TIBETAN MARK NGAS BZUNG NYI ZLA
 0F37          ; Mn #       TIBETAN MARK NGAS BZUNG SGOR RTAGS
@@ -2861,6 +2882,7 @@ FE20..FE2F    ; Mn #  [16] COMBINING LIGATURE LEFT HALF..COMBINING CYRILLIC TITL
 10AE5..10AE6  ; Mn #   [2] MANICHAEAN ABBREVIATION MARK ABOVE..MANICHAEAN ABBREVIATION MARK BELOW
 10D24..10D27  ; Mn #   [4] HANIFI ROHINGYA SIGN HARBAHAY..HANIFI ROHINGYA SIGN TASSI
 10EAB..10EAC  ; Mn #   [2] YEZIDI COMBINING HAMZA MARK..YEZIDI COMBINING MADDA MARK
+10EFD..10EFF  ; Mn #   [3] ARABIC SMALL LOW WORD SAKTA..ARABIC SMALL LOW WORD MADDA
 10F46..10F50  ; Mn #  [11] SOGDIAN COMBINING DOT BELOW..SOGDIAN COMBINING STROKE BELOW
 10F82..10F85  ; Mn #   [4] OLD UYGHUR COMBINING DOT ABOVE..OLD UYGHUR COMBINING TWO DOTS BELOW
 11001         ; Mn #       BRAHMI SIGN ANUSVARA
@@ -2883,6 +2905,7 @@ FE20..FE2F    ; Mn #  [16] COMBINING LIGATURE LEFT HALF..COMBINING CYRILLIC TITL
 11234         ; Mn #       KHOJKI SIGN ANUSVARA
 11236..11237  ; Mn #   [2] KHOJKI SIGN NUKTA..KHOJKI SIGN SHADDA
 1123E         ; Mn #       KHOJKI SIGN SUKUN
+11241         ; Mn #       KHOJKI VOWEL SIGN VOCALIC R
 112DF         ; Mn #       KHUDAWADI SIGN ANUSVARA
 112E3..112EA  ; Mn #   [8] KHUDAWADI VOWEL SIGN U..KHUDAWADI SIGN VIRAMA
 11300..11301  ; Mn #   [2] GRANTHA SIGN COMBINING ANUSVARA ABOVE..GRANTHA SIGN CANDRABINDU
@@ -2944,6 +2967,12 @@ FE20..FE2F    ; Mn #  [16] COMBINING LIGATURE LEFT HALF..COMBINING CYRILLIC TITL
 11D95         ; Mn #       GUNJALA GONDI SIGN ANUSVARA
 11D97         ; Mn #       GUNJALA GONDI VIRAMA
 11EF3..11EF4  ; Mn #   [2] MAKASAR VOWEL SIGN I..MAKASAR VOWEL SIGN U
+11F00..11F01  ; Mn #   [2] KAWI SIGN CANDRABINDU..KAWI SIGN ANUSVARA
+11F36..11F3A  ; Mn #   [5] KAWI VOWEL SIGN I..KAWI VOWEL SIGN VOCALIC R
+11F40         ; Mn #       KAWI VOWEL SIGN EU
+11F42         ; Mn #       KAWI CONJOINER
+13440         ; Mn #       EGYPTIAN HIEROGLYPH MIRROR HORIZONTALLY
+13447..13455  ; Mn #  [15] EGYPTIAN HIEROGLYPH MODIFIER DAMAGED AT TOP START..EGYPTIAN HIEROGLYPH MODIFIER DAMAGED
 16AF0..16AF4  ; Mn #   [5] BASSA VAH COMBINING HIGH TONE..BASSA VAH COMBINING HIGH-LOW TONE
 16B30..16B36  ; Mn #   [7] PAHAWH HMONG MARK CIM TUB..PAHAWH HMONG MARK CIM TAUM
 16F4F         ; Mn #       MIAO SIGN CONSONANT MODIFIER BAR
@@ -2968,14 +2997,16 @@ FE20..FE2F    ; Mn #  [16] COMBINING LIGATURE LEFT HALF..COMBINING CYRILLIC TITL
 1E01B..1E021  ; Mn #   [7] COMBINING GLAGOLITIC LETTER SHTA..COMBINING GLAGOLITIC LETTER YATI
 1E023..1E024  ; Mn #   [2] COMBINING GLAGOLITIC LETTER YU..COMBINING GLAGOLITIC LETTER SMALL YUS
 1E026..1E02A  ; Mn #   [5] COMBINING GLAGOLITIC LETTER YO..COMBINING GLAGOLITIC LETTER FITA
+1E08F         ; Mn #       COMBINING CYRILLIC SMALL LETTER BYELORUSSIAN-UKRAINIAN I
 1E130..1E136  ; Mn #   [7] NYIAKENG PUACHUE HMONG TONE-B..NYIAKENG PUACHUE HMONG TONE-D
 1E2AE         ; Mn #       TOTO SIGN RISING TONE
 1E2EC..1E2EF  ; Mn #   [4] WANCHO TONE TUP..WANCHO TONE KOINI
+1E4EC..1E4EF  ; Mn #   [4] NAG MUNDARI SIGN MUHOR..NAG MUNDARI SIGN SUTUH
 1E8D0..1E8D6  ; Mn #   [7] MENDE KIKAKUI COMBINING NUMBER TEENS..MENDE KIKAKUI COMBINING NUMBER MILLIONS
 1E944..1E94A  ; Mn #   [7] ADLAM ALIF LENGTHENER..ADLAM NUKTA
 E0100..E01EF  ; Mn # [240] VARIATION SELECTOR-17..VARIATION SELECTOR-256
 
-# Total code points: 1950
+# Total code points: 1985
 
 # ================================================
 
@@ -3028,6 +3059,7 @@ A670..A672    ; Me #   [3] COMBINING CYRILLIC TEN MILLIONS SIGN..COMBINING CYRIL
 0CC7..0CC8    ; Mc #   [2] KANNADA VOWEL SIGN EE..KANNADA VOWEL SIGN AI
 0CCA..0CCB    ; Mc #   [2] KANNADA VOWEL SIGN O..KANNADA VOWEL SIGN OO
 0CD5..0CD6    ; Mc #   [2] KANNADA LENGTH MARK..KANNADA AI LENGTH MARK
+0CF3          ; Mc #       KANNADA SIGN COMBINING ANUSVARA ABOVE RIGHT
 0D02..0D03    ; Mc #   [2] MALAYALAM SIGN ANUSVARA..MALAYALAM SIGN VISARGA
 0D3E..0D40    ; Mc #   [3] MALAYALAM VOWEL SIGN AA..MALAYALAM VOWEL SIGN II
 0D46..0D48    ; Mc #   [3] MALAYALAM VOWEL SIGN E..MALAYALAM VOWEL SIGN AI
@@ -3166,12 +3198,16 @@ ABEC          ; Mc #       MEETEI MAYEK LUM IYEK
 11D93..11D94  ; Mc #   [2] GUNJALA GONDI VOWEL SIGN OO..GUNJALA GONDI VOWEL SIGN AU
 11D96         ; Mc #       GUNJALA GONDI SIGN VISARGA
 11EF5..11EF6  ; Mc #   [2] MAKASAR VOWEL SIGN E..MAKASAR VOWEL SIGN O
+11F03         ; Mc #       KAWI SIGN VISARGA
+11F34..11F35  ; Mc #   [2] KAWI VOWEL SIGN AA..KAWI VOWEL SIGN ALTERNATE AA
+11F3E..11F3F  ; Mc #   [2] KAWI VOWEL SIGN E..KAWI VOWEL SIGN AI
+11F41         ; Mc #       KAWI SIGN KILLER
 16F51..16F87  ; Mc #  [55] MIAO SIGN ASPIRATION..MIAO VOWEL SIGN UI
 16FF0..16FF1  ; Mc #   [2] VIETNAMESE ALTERNATE READING MARK CA..VIETNAMESE ALTERNATE READING MARK NHAY
 1D165..1D166  ; Mc #   [2] MUSICAL SYMBOL COMBINING STEM..MUSICAL SYMBOL COMBINING SPRECHGESANG STEM
 1D16D..1D172  ; Mc #   [6] MUSICAL SYMBOL COMBINING AUGMENTATION DOT..MUSICAL SYMBOL COMBINING FLAG-5
 
-# Total code points: 445
+# Total code points: 452
 
 # ================================================
 
@@ -3231,16 +3267,18 @@ FF10..FF19    ; Nd #  [10] FULLWIDTH DIGIT ZERO..FULLWIDTH DIGIT NINE
 11C50..11C59  ; Nd #  [10] BHAIKSUKI DIGIT ZERO..BHAIKSUKI DIGIT NINE
 11D50..11D59  ; Nd #  [10] MASARAM GONDI DIGIT ZERO..MASARAM GONDI DIGIT NINE
 11DA0..11DA9  ; Nd #  [10] GUNJALA GONDI DIGIT ZERO..GUNJALA GONDI DIGIT NINE
+11F50..11F59  ; Nd #  [10] KAWI DIGIT ZERO..KAWI DIGIT NINE
 16A60..16A69  ; Nd #  [10] MRO DIGIT ZERO..MRO DIGIT NINE
 16AC0..16AC9  ; Nd #  [10] TANGSA DIGIT ZERO..TANGSA DIGIT NINE
 16B50..16B59  ; Nd #  [10] PAHAWH HMONG DIGIT ZERO..PAHAWH HMONG DIGIT NINE
 1D7CE..1D7FF  ; Nd #  [50] MATHEMATICAL BOLD DIGIT ZERO..MATHEMATICAL MONOSPACE DIGIT NINE
 1E140..1E149  ; Nd #  [10] NYIAKENG PUACHUE HMONG DIGIT ZERO..NYIAKENG PUACHUE HMONG DIGIT NINE
 1E2F0..1E2F9  ; Nd #  [10] WANCHO DIGIT ZERO..WANCHO DIGIT NINE
+1E4F0..1E4F9  ; Nd #  [10] NAG MUNDARI DIGIT ZERO..NAG MUNDARI DIGIT NINE
 1E950..1E959  ; Nd #  [10] ADLAM DIGIT ZERO..ADLAM DIGIT NINE
 1FBF0..1FBF9  ; Nd #  [10] SEGMENTED DIGIT ZERO..SEGMENTED DIGIT NINE
 
-# Total code points: 660
+# Total code points: 680
 
 # ================================================
 
@@ -3327,6 +3365,7 @@ A830..A835    ; No #   [6] NORTH INDIC FRACTION ONE QUARTER..NORTH INDIC FRACTIO
 11FC0..11FD4  ; No #  [21] TAMIL FRACTION ONE THREE-HUNDRED-AND-TWENTIETH..TAMIL FRACTION DOWNSCALING FACTOR KIIZH
 16B5B..16B61  ; No #   [7] PAHAWH HMONG NUMBER TENS..PAHAWH HMONG NUMBER TRILLIONS
 16E80..16E96  ; No #  [23] MEDEFAIDRIN DIGIT ZERO..MEDEFAIDRIN DIGIT THREE ALTERNATE FORM
+1D2C0..1D2D3  ; No #  [20] KAKTOVIK NUMERAL ZERO..KAKTOVIK NUMERAL NINETEEN
 1D2E0..1D2F3  ; No #  [20] MAYAN NUMERAL ZERO..MAYAN NUMERAL NINETEEN
 1D360..1D378  ; No #  [25] COUNTING ROD UNIT DIGIT ONE..TALLY MARK FIVE
 1E8C7..1E8CF  ; No #   [9] MENDE KIKAKUI DIGIT ONE..MENDE KIKAKUI DIGIT NINE
@@ -3337,7 +3376,7 @@ A830..A835    ; No #   [6] NORTH INDIC FRACTION ONE QUARTER..NORTH INDIC FRACTIO
 1ED2F..1ED3D  ; No #  [15] OTTOMAN SIYAQ ALTERNATE NUMBER TWO..OTTOMAN SIYAQ FRACTION ONE SIXTH
 1F100..1F10C  ; No #  [13] DIGIT ZERO FULL STOP..DINGBAT NEGATIVE CIRCLED SANS-SERIF DIGIT ZERO
 
-# Total code points: 895
+# Total code points: 915
 
 # ================================================
 
@@ -3398,13 +3437,13 @@ FEFF          ; Cf #       ZERO WIDTH NO-BREAK SPACE
 FFF9..FFFB    ; Cf #   [3] INTERLINEAR ANNOTATION ANCHOR..INTERLINEAR ANNOTATION TERMINATOR
 110BD         ; Cf #       KAITHI NUMBER SIGN
 110CD         ; Cf #       KAITHI NUMBER SIGN ABOVE
-13430..13438  ; Cf #   [9] EGYPTIAN HIEROGLYPH VERTICAL JOINER..EGYPTIAN HIEROGLYPH END SEGMENT
+13430..1343F  ; Cf #  [16] EGYPTIAN HIEROGLYPH VERTICAL JOINER..EGYPTIAN HIEROGLYPH END WALLED ENCLOSURE
 1BCA0..1BCA3  ; Cf #   [4] SHORTHAND FORMAT LETTER OVERLAP..SHORTHAND FORMAT UP STEP
 1D173..1D17A  ; Cf #   [8] MUSICAL SYMBOL BEGIN BEAM..MUSICAL SYMBOL END PHRASE
 E0001         ; Cf #       LANGUAGE TAG
 E0020..E007F  ; Cf #  [96] TAG SPACE..CANCEL TAG
 
-# Total code points: 163
+# Total code points: 170
 
 # ================================================
 
@@ -3806,9 +3845,11 @@ FF64..FF65    ; Po #   [2] HALFWIDTH IDEOGRAPHIC COMMA..HALFWIDTH KATAKANA MIDDL
 11A3F..11A46  ; Po #   [8] ZANABAZAR SQUARE INITIAL HEAD MARK..ZANABAZAR SQUARE CLOSING DOUBLE-LINED HEAD MARK
 11A9A..11A9C  ; Po #   [3] SOYOMBO MARK TSHEG..SOYOMBO MARK DOUBLE SHAD
 11A9E..11AA2  ; Po #   [5] SOYOMBO HEAD MARK WITH MOON AND SUN AND TRIPLE FLAME..SOYOMBO TERMINAL MARK-2
+11B00..11B09  ; Po #  [10] DEVANAGARI HEAD MARK..DEVANAGARI SIGN MINDU
 11C41..11C45  ; Po #   [5] BHAIKSUKI DANDA..BHAIKSUKI GAP FILLER-2
 11C70..11C71  ; Po #   [2] MARCHEN HEAD MARK..MARCHEN MARK SHAD
 11EF7..11EF8  ; Po #   [2] MAKASAR PASSIMBANG..MAKASAR END OF SECTION
+11F43..11F4F  ; Po #  [13] KAWI DANDA..KAWI PUNCTUATION CLOSING SPIRAL
 11FFF         ; Po #       TAMIL PUNCTUATION END OF TEXT
 12470..12474  ; Po #   [5] CUNEIFORM PUNCTUATION SIGN OLD ASSYRIAN WORD DIVIDER..CUNEIFORM PUNCTUATION SIGN DIAGONAL QUADCOLON
 12FF1..12FF2  ; Po #   [2] CYPRO-MINOAN SIGN CM301..CYPRO-MINOAN SIGN CM302
@@ -3822,7 +3863,7 @@ FF64..FF65    ; Po #   [2] HALFWIDTH IDEOGRAPHIC COMMA..HALFWIDTH KATAKANA MIDDL
 1DA87..1DA8B  ; Po #   [5] SIGNWRITING COMMA..SIGNWRITING PARENTHESIS
 1E95E..1E95F  ; Po #   [2] ADLAM INITIAL EXCLAMATION MARK..ADLAM INITIAL QUESTION MARK
 
-# Total code points: 605
+# Total code points: 628
 
 # ================================================
 
@@ -4126,10 +4167,10 @@ FFFC..FFFD    ; So #   [2] OBJECT REPLACEMENT CHARACTER..REPLACEMENT CHARACTER
 1F260..1F265  ; So #   [6] ROUNDED SYMBOL FOR FU..ROUNDED SYMBOL FOR CAI
 1F300..1F3FA  ; So # [251] CYCLONE..AMPHORA
 1F400..1F6D7  ; So # [728] RAT..ELEVATOR
-1F6DD..1F6EC  ; So #  [16] PLAYGROUND SLIDE..AIRPLANE ARRIVING
+1F6DC..1F6EC  ; So #  [17] WIRELESS..AIRPLANE ARRIVING
 1F6F0..1F6FC  ; So #  [13] SATELLITE..ROLLER SKATE
-1F700..1F773  ; So # [116] ALCHEMICAL SYMBOL FOR QUINTESSENCE..ALCHEMICAL SYMBOL FOR HALF OUNCE
-1F780..1F7D8  ; So #  [89] BLACK LEFT-POINTING ISOSCELES RIGHT TRIANGLE..NEGATIVE CIRCLED SQUARE
+1F700..1F776  ; So # [119] ALCHEMICAL SYMBOL FOR QUINTESSENCE..LUNAR ECLIPSE
+1F77B..1F7D9  ; So #  [95] HAUMEA..NINE POINTED WHITE STAR
 1F7E0..1F7EB  ; So #  [12] LARGE ORANGE CIRCLE..LARGE BROWN SQUARE
 1F7F0         ; So #       HEAVY EQUALS SIGN
 1F800..1F80B  ; So #  [12] LEFTWARDS ARROW WITH SMALL TRIANGLE ARROWHEAD..DOWNWARDS ARROW WITH LARGE TRIANGLE ARROWHEAD
@@ -4140,19 +4181,17 @@ FFFC..FFFD    ; So #   [2] OBJECT REPLACEMENT CHARACTER..REPLACEMENT CHARACTER
 1F8B0..1F8B1  ; So #   [2] ARROW POINTING UPWARDS THEN NORTH WEST..ARROW POINTING RIGHTWARDS THEN CURVING SOUTH WEST
 1F900..1FA53  ; So # [340] CIRCLED CROSS FORMEE WITH FOUR DOTS..BLACK CHESS KNIGHT-BISHOP
 1FA60..1FA6D  ; So #  [14] XIANGQI RED GENERAL..XIANGQI BLACK SOLDIER
-1FA70..1FA74  ; So #   [5] BALLET SHOES..THONG SANDAL
-1FA78..1FA7C  ; So #   [5] DROP OF BLOOD..CRUTCH
-1FA80..1FA86  ; So #   [7] YO-YO..NESTING DOLLS
-1FA90..1FAAC  ; So #  [29] RINGED PLANET..HAMSA
-1FAB0..1FABA  ; So #  [11] FLY..NEST WITH EGGS
-1FAC0..1FAC5  ; So #   [6] ANATOMICAL HEART..PERSON WITH CROWN
-1FAD0..1FAD9  ; So #  [10] BLUEBERRIES..JAR
-1FAE0..1FAE7  ; So #   [8] MELTING FACE..BUBBLES
-1FAF0..1FAF6  ; So #   [7] HAND WITH INDEX FINGER AND THUMB CROSSED..HEART HANDS
+1FA70..1FA7C  ; So #  [13] BALLET SHOES..CRUTCH
+1FA80..1FA88  ; So #   [9] YO-YO..FLUTE
+1FA90..1FABD  ; So #  [46] RINGED PLANET..WING
+1FABF..1FAC5  ; So #   [7] GOOSE..PERSON WITH CROWN
+1FACE..1FADB  ; So #  [14] MOOSE..PEA POD
+1FAE0..1FAE8  ; So #   [9] MELTING FACE..SHAKING FACE
+1FAF0..1FAF8  ; So #   [9] HAND WITH INDEX FINGER AND THUMB CROSSED..RIGHTWARDS PUSHING HAND
 1FB00..1FB92  ; So # [147] BLOCK SEXTANT-1..UPPER HALF INVERSE MEDIUM SHADE AND LOWER HALF BLOCK
 1FB94..1FBCA  ; So #  [55] LEFT HALF INVERSE MEDIUM SHADE AND RIGHT HALF BLOCK..WHITE UP-POINTING CHEVRON
 
-# Total code points: 6605
+# Total code points: 6634
 
 # ================================================
 
diff --git a/pcre2/maint/Unicode.tables/GraphemeBreakProperty.txt b/pcre2/maint/Unicode.tables/GraphemeBreakProperty.txt
index dd25690..a12b5ee 100644
--- a/pcre2/maint/Unicode.tables/GraphemeBreakProperty.txt
+++ b/pcre2/maint/Unicode.tables/GraphemeBreakProperty.txt
@@ -1,11 +1,11 @@
-# GraphemeBreakProperty-14.0.0.txt
-# Date: 2021-08-12, 23:13:02 GMT
-# © 2021 Unicode®, Inc.
+# GraphemeBreakProperty-15.0.0.txt
+# Date: 2022-04-27, 17:07:38 GMT
+# © 2022 Unicode®, Inc.
 # Unicode and the Unicode Logo are registered trademarks of Unicode, Inc. in the U.S. and other countries.
-# For terms of use, see http://www.unicode.org/terms_of_use.html
+# For terms of use, see https://www.unicode.org/terms_of_use.html
 #
 # Unicode Character Database
-#   For documentation, see http://www.unicode.org/reports/tr44/
+#   For documentation, see https://www.unicode.org/reports/tr44/
 
 # ================================================
 
@@ -32,8 +32,9 @@
 11A3A         ; Prepend # Lo       ZANABAZAR SQUARE CLUSTER-INITIAL LETTER RA
 11A84..11A89  ; Prepend # Lo   [6] SOYOMBO SIGN JIHVAMULIYA..SOYOMBO CLUSTER-INITIAL LETTER SA
 11D46         ; Prepend # Lo       MASARAM GONDI REPHA
+11F02         ; Prepend # Lo       KAWI SIGN REPHA
 
-# Total code points: 26
+# Total code points: 27
 
 # ================================================
 
@@ -67,7 +68,7 @@
 FEFF          ; Control # Cf       ZERO WIDTH NO-BREAK SPACE
 FFF0..FFF8    ; Control # Cn   [9] ..
 FFF9..FFFB    ; Control # Cf   [3] INTERLINEAR ANNOTATION ANCHOR..INTERLINEAR ANNOTATION TERMINATOR
-13430..13438  ; Control # Cf   [9] EGYPTIAN HIEROGLYPH VERTICAL JOINER..EGYPTIAN HIEROGLYPH END SEGMENT
+13430..1343F  ; Control # Cf  [16] EGYPTIAN HIEROGLYPH VERTICAL JOINER..EGYPTIAN HIEROGLYPH END WALLED ENCLOSURE
 1BCA0..1BCA3  ; Control # Cf   [4] SHORTHAND FORMAT LETTER OVERLAP..SHORTHAND FORMAT UP STEP
 1D173..1D17A  ; Control # Cf   [8] MUSICAL SYMBOL BEGIN BEAM..MUSICAL SYMBOL END PHRASE
 E0000         ; Control # Cn       
@@ -76,7 +77,7 @@ E0002..E001F  ; Control # Cn  [30] ..
 E0080..E00FF  ; Control # Cn [128] ..
 E01F0..E0FFF  ; Control # Cn [3600] ..
 
-# Total code points: 3886
+# Total code points: 3893
 
 # ================================================
 
@@ -185,7 +186,7 @@ E01F0..E0FFF  ; Control # Cn [3600] ..
 0E47..0E4E    ; Extend # Mn   [8] THAI CHARACTER MAITAIKHU..THAI CHARACTER YAMAKKAN
 0EB1          ; Extend # Mn       LAO VOWEL SIGN MAI KAN
 0EB4..0EBC    ; Extend # Mn   [9] LAO VOWEL SIGN I..LAO SEMIVOWEL SIGN LO
-0EC8..0ECD    ; Extend # Mn   [6] LAO TONE MAI EK..LAO NIGGAHITA
+0EC8..0ECE    ; Extend # Mn   [7] LAO TONE MAI EK..LAO YAMAKKAN
 0F18..0F19    ; Extend # Mn   [2] TIBETAN ASTROLOGICAL SIGN -KHYUD PA..TIBETAN ASTROLOGICAL SIGN SDONG TSHUGS
 0F35          ; Extend # Mn       TIBETAN MARK NGAS BZUNG NYI ZLA
 0F37          ; Extend # Mn       TIBETAN MARK NGAS BZUNG SGOR RTAGS
@@ -324,6 +325,7 @@ FF9E..FF9F    ; Extend # Lm   [2] HALFWIDTH KATAKANA VOICED SOUND MARK..HALFWIDT
 10AE5..10AE6  ; Extend # Mn   [2] MANICHAEAN ABBREVIATION MARK ABOVE..MANICHAEAN ABBREVIATION MARK BELOW
 10D24..10D27  ; Extend # Mn   [4] HANIFI ROHINGYA SIGN HARBAHAY..HANIFI ROHINGYA SIGN TASSI
 10EAB..10EAC  ; Extend # Mn   [2] YEZIDI COMBINING HAMZA MARK..YEZIDI COMBINING MADDA MARK
+10EFD..10EFF  ; Extend # Mn   [3] ARABIC SMALL LOW WORD SAKTA..ARABIC SMALL LOW WORD MADDA
 10F46..10F50  ; Extend # Mn  [11] SOGDIAN COMBINING DOT BELOW..SOGDIAN COMBINING STROKE BELOW
 10F82..10F85  ; Extend # Mn   [4] OLD UYGHUR COMBINING DOT ABOVE..OLD UYGHUR COMBINING TWO DOTS BELOW
 11001         ; Extend # Mn       BRAHMI SIGN ANUSVARA
@@ -346,6 +348,7 @@ FF9E..FF9F    ; Extend # Lm   [2] HALFWIDTH KATAKANA VOICED SOUND MARK..HALFWIDT
 11234         ; Extend # Mn       KHOJKI SIGN ANUSVARA
 11236..11237  ; Extend # Mn   [2] KHOJKI SIGN NUKTA..KHOJKI SIGN SHADDA
 1123E         ; Extend # Mn       KHOJKI SIGN SUKUN
+11241         ; Extend # Mn       KHOJKI VOWEL SIGN VOCALIC R
 112DF         ; Extend # Mn       KHUDAWADI SIGN ANUSVARA
 112E3..112EA  ; Extend # Mn   [8] KHUDAWADI VOWEL SIGN U..KHUDAWADI SIGN VIRAMA
 11300..11301  ; Extend # Mn   [2] GRANTHA SIGN COMBINING ANUSVARA ABOVE..GRANTHA SIGN CANDRABINDU
@@ -413,6 +416,12 @@ FF9E..FF9F    ; Extend # Lm   [2] HALFWIDTH KATAKANA VOICED SOUND MARK..HALFWIDT
 11D95         ; Extend # Mn       GUNJALA GONDI SIGN ANUSVARA
 11D97         ; Extend # Mn       GUNJALA GONDI VIRAMA
 11EF3..11EF4  ; Extend # Mn   [2] MAKASAR VOWEL SIGN I..MAKASAR VOWEL SIGN U
+11F00..11F01  ; Extend # Mn   [2] KAWI SIGN CANDRABINDU..KAWI SIGN ANUSVARA
+11F36..11F3A  ; Extend # Mn   [5] KAWI VOWEL SIGN I..KAWI VOWEL SIGN VOCALIC R
+11F40         ; Extend # Mn       KAWI VOWEL SIGN EU
+11F42         ; Extend # Mn       KAWI CONJOINER
+13440         ; Extend # Mn       EGYPTIAN HIEROGLYPH MIRROR HORIZONTALLY
+13447..13455  ; Extend # Mn  [15] EGYPTIAN HIEROGLYPH MODIFIER DAMAGED AT TOP START..EGYPTIAN HIEROGLYPH MODIFIER DAMAGED
 16AF0..16AF4  ; Extend # Mn   [5] BASSA VAH COMBINING HIGH TONE..BASSA VAH COMBINING HIGH-LOW TONE
 16B30..16B36  ; Extend # Mn   [7] PAHAWH HMONG MARK CIM TUB..PAHAWH HMONG MARK CIM TAUM
 16F4F         ; Extend # Mn       MIAO SIGN CONSONANT MODIFIER BAR
@@ -439,16 +448,18 @@ FF9E..FF9F    ; Extend # Lm   [2] HALFWIDTH KATAKANA VOICED SOUND MARK..HALFWIDT
 1E01B..1E021  ; Extend # Mn   [7] COMBINING GLAGOLITIC LETTER SHTA..COMBINING GLAGOLITIC LETTER YATI
 1E023..1E024  ; Extend # Mn   [2] COMBINING GLAGOLITIC LETTER YU..COMBINING GLAGOLITIC LETTER SMALL YUS
 1E026..1E02A  ; Extend # Mn   [5] COMBINING GLAGOLITIC LETTER YO..COMBINING GLAGOLITIC LETTER FITA
+1E08F         ; Extend # Mn       COMBINING CYRILLIC SMALL LETTER BYELORUSSIAN-UKRAINIAN I
 1E130..1E136  ; Extend # Mn   [7] NYIAKENG PUACHUE HMONG TONE-B..NYIAKENG PUACHUE HMONG TONE-D
 1E2AE         ; Extend # Mn       TOTO SIGN RISING TONE
 1E2EC..1E2EF  ; Extend # Mn   [4] WANCHO TONE TUP..WANCHO TONE KOINI
+1E4EC..1E4EF  ; Extend # Mn   [4] NAG MUNDARI SIGN MUHOR..NAG MUNDARI SIGN SUTUH
 1E8D0..1E8D6  ; Extend # Mn   [7] MENDE KIKAKUI COMBINING NUMBER TEENS..MENDE KIKAKUI COMBINING NUMBER MILLIONS
 1E944..1E94A  ; Extend # Mn   [7] ADLAM ALIF LENGTHENER..ADLAM NUKTA
 1F3FB..1F3FF  ; Extend # Sk   [5] EMOJI MODIFIER FITZPATRICK TYPE-1-2..EMOJI MODIFIER FITZPATRICK TYPE-6
 E0020..E007F  ; Extend # Cf  [96] TAG SPACE..CANCEL TAG
 E0100..E01EF  ; Extend # Mn [240] VARIATION SELECTOR-17..VARIATION SELECTOR-256
 
-# Total code points: 2095
+# Total code points: 2130
 
 # ================================================
 
@@ -489,6 +500,7 @@ E0100..E01EF  ; Extend # Mn [240] VARIATION SELECTOR-17..VARIATION SELECTOR-256
 0CC3..0CC4    ; SpacingMark # Mc   [2] KANNADA VOWEL SIGN VOCALIC R..KANNADA VOWEL SIGN VOCALIC RR
 0CC7..0CC8    ; SpacingMark # Mc   [2] KANNADA VOWEL SIGN EE..KANNADA VOWEL SIGN AI
 0CCA..0CCB    ; SpacingMark # Mc   [2] KANNADA VOWEL SIGN O..KANNADA VOWEL SIGN OO
+0CF3          ; SpacingMark # Mc       KANNADA SIGN COMBINING ANUSVARA ABOVE RIGHT
 0D02..0D03    ; SpacingMark # Mc   [2] MALAYALAM SIGN ANUSVARA..MALAYALAM SIGN VISARGA
 0D3F..0D40    ; SpacingMark # Mc   [2] MALAYALAM VOWEL SIGN I..MALAYALAM VOWEL SIGN II
 0D46..0D48    ; SpacingMark # Mc   [3] MALAYALAM VOWEL SIGN E..MALAYALAM VOWEL SIGN AI
@@ -614,12 +626,16 @@ ABEC          ; SpacingMark # Mc       MEETEI MAYEK LUM IYEK
 11D93..11D94  ; SpacingMark # Mc   [2] GUNJALA GONDI VOWEL SIGN OO..GUNJALA GONDI VOWEL SIGN AU
 11D96         ; SpacingMark # Mc       GUNJALA GONDI SIGN VISARGA
 11EF5..11EF6  ; SpacingMark # Mc   [2] MAKASAR VOWEL SIGN E..MAKASAR VOWEL SIGN O
+11F03         ; SpacingMark # Mc       KAWI SIGN VISARGA
+11F34..11F35  ; SpacingMark # Mc   [2] KAWI VOWEL SIGN AA..KAWI VOWEL SIGN ALTERNATE AA
+11F3E..11F3F  ; SpacingMark # Mc   [2] KAWI VOWEL SIGN E..KAWI VOWEL SIGN AI
+11F41         ; SpacingMark # Mc       KAWI SIGN KILLER
 16F51..16F87  ; SpacingMark # Mc  [55] MIAO SIGN ASPIRATION..MIAO VOWEL SIGN UI
 16FF0..16FF1  ; SpacingMark # Mc   [2] VIETNAMESE ALTERNATE READING MARK CA..VIETNAMESE ALTERNATE READING MARK NHAY
 1D166         ; SpacingMark # Mc       MUSICAL SYMBOL COMBINING SPRECHGESANG STEM
 1D16D         ; SpacingMark # Mc       MUSICAL SYMBOL COMBINING AUGMENTATION DOT
 
-# Total code points: 388
+# Total code points: 395
 
 # ================================================
 
diff --git a/pcre2/maint/Unicode.tables/PropList.txt b/pcre2/maint/Unicode.tables/PropList.txt
index 0a5a934..b49d646 100644
--- a/pcre2/maint/Unicode.tables/PropList.txt
+++ b/pcre2/maint/Unicode.tables/PropList.txt
@@ -1,11 +1,11 @@
-# PropList-14.0.0.txt
-# Date: 2021-08-12, 23:13:05 GMT
-# © 2021 Unicode®, Inc.
+# PropList-15.0.0.txt
+# Date: 2022-08-05, 22:17:16 GMT
+# © 2022 Unicode®, Inc.
 # Unicode and the Unicode Logo are registered trademarks of Unicode, Inc. in the U.S. and other countries.
-# For terms of use, see http://www.unicode.org/terms_of_use.html
+# For terms of use, see https://www.unicode.org/terms_of_use.html
 #
 # Unicode Character Database
-#   For documentation, see http://www.unicode.org/reports/tr44/
+#   For documentation, see https://www.unicode.org/reports/tr44/
 
 # ================================================
 
@@ -215,6 +215,7 @@ FF64          ; Terminal_Punctuation # Po       HALFWIDTH IDEOGRAPHIC COMMA
 11C41..11C43  ; Terminal_Punctuation # Po   [3] BHAIKSUKI DANDA..BHAIKSUKI WORD SEPARATOR
 11C71         ; Terminal_Punctuation # Po       MARCHEN MARK SHAD
 11EF7..11EF8  ; Terminal_Punctuation # Po   [2] MAKASAR PASSIMBANG..MAKASAR END OF SECTION
+11F43..11F44  ; Terminal_Punctuation # Po   [2] KAWI DANDA..KAWI DOUBLE DANDA
 12470..12474  ; Terminal_Punctuation # Po   [5] CUNEIFORM PUNCTUATION SIGN OLD ASSYRIAN WORD DIVIDER..CUNEIFORM PUNCTUATION SIGN DIAGONAL QUADCOLON
 16A6E..16A6F  ; Terminal_Punctuation # Po   [2] MRO DANDA..MRO DOUBLE DANDA
 16AF5         ; Terminal_Punctuation # Po       BASSA VAH FULL STOP
@@ -224,7 +225,7 @@ FF64          ; Terminal_Punctuation # Po       HALFWIDTH IDEOGRAPHIC COMMA
 1BC9F         ; Terminal_Punctuation # Po       DUPLOYAN PUNCTUATION CHINOOK FULL STOP
 1DA87..1DA8A  ; Terminal_Punctuation # Po   [4] SIGNWRITING COMMA..SIGNWRITING COLON
 
-# Total code points: 276
+# Total code points: 278
 
 # ================================================
 
@@ -507,6 +508,7 @@ FF41..FF46    ; Hex_Digit # L&   [6] FULLWIDTH LATIN SMALL LETTER A..FULLWIDTH L
 0BD7          ; Other_Alphabetic # Mc       TAMIL AU LENGTH MARK
 0C00          ; Other_Alphabetic # Mn       TELUGU SIGN COMBINING CANDRABINDU ABOVE
 0C01..0C03    ; Other_Alphabetic # Mc   [3] TELUGU SIGN CANDRABINDU..TELUGU SIGN VISARGA
+0C04          ; Other_Alphabetic # Mn       TELUGU SIGN COMBINING ANUSVARA ABOVE
 0C3E..0C40    ; Other_Alphabetic # Mn   [3] TELUGU VOWEL SIGN AA..TELUGU VOWEL SIGN II
 0C41..0C44    ; Other_Alphabetic # Mc   [4] TELUGU VOWEL SIGN U..TELUGU VOWEL SIGN VOCALIC RR
 0C46..0C48    ; Other_Alphabetic # Mn   [3] TELUGU VOWEL SIGN E..TELUGU VOWEL SIGN AI
@@ -524,6 +526,7 @@ FF41..FF46    ; Hex_Digit # L&   [6] FULLWIDTH LATIN SMALL LETTER A..FULLWIDTH L
 0CCC          ; Other_Alphabetic # Mn       KANNADA VOWEL SIGN AU
 0CD5..0CD6    ; Other_Alphabetic # Mc   [2] KANNADA LENGTH MARK..KANNADA AI LENGTH MARK
 0CE2..0CE3    ; Other_Alphabetic # Mn   [2] KANNADA VOWEL SIGN VOCALIC L..KANNADA VOWEL SIGN VOCALIC LL
+0CF3          ; Other_Alphabetic # Mc       KANNADA SIGN COMBINING ANUSVARA ABOVE RIGHT
 0D00..0D01    ; Other_Alphabetic # Mn   [2] MALAYALAM SIGN COMBINING ANUSVARA ABOVE..MALAYALAM SIGN CANDRABINDU
 0D02..0D03    ; Other_Alphabetic # Mc   [2] MALAYALAM SIGN ANUSVARA..MALAYALAM SIGN VISARGA
 0D3E..0D40    ; Other_Alphabetic # Mc   [3] MALAYALAM VOWEL SIGN AA..MALAYALAM VOWEL SIGN II
@@ -548,7 +551,7 @@ FF41..FF46    ; Hex_Digit # L&   [6] FULLWIDTH LATIN SMALL LETTER A..FULLWIDTH L
 0ECD          ; Other_Alphabetic # Mn       LAO NIGGAHITA
 0F71..0F7E    ; Other_Alphabetic # Mn  [14] TIBETAN VOWEL SIGN AA..TIBETAN SIGN RJES SU NGA RO
 0F7F          ; Other_Alphabetic # Mc       TIBETAN SIGN RNAM BCAD
-0F80..0F81    ; Other_Alphabetic # Mn   [2] TIBETAN VOWEL SIGN REVERSED I..TIBETAN VOWEL SIGN REVERSED II
+0F80..0F83    ; Other_Alphabetic # Mn   [4] TIBETAN VOWEL SIGN REVERSED I..TIBETAN SIGN SNA LDAN
 0F8D..0F97    ; Other_Alphabetic # Mn  [11] TIBETAN SUBJOINED SIGN LCE TSA CAN..TIBETAN SUBJOINED LETTER JA
 0F99..0FBC    ; Other_Alphabetic # Mn  [36] TIBETAN SUBJOINED LETTER NYA..TIBETAN SUBJOINED LETTER FIXED-FORM RA
 102B..102C    ; Other_Alphabetic # Mc   [2] MYANMAR VOWEL SIGN TALL AA..MYANMAR VOWEL SIGN AA
@@ -692,6 +695,7 @@ FB1E          ; Other_Alphabetic # Mn       HEBREW POINT JUDEO-SPANISH VARIKA
 11002         ; Other_Alphabetic # Mc       BRAHMI SIGN VISARGA
 11038..11045  ; Other_Alphabetic # Mn  [14] BRAHMI VOWEL SIGN AA..BRAHMI VOWEL SIGN AU
 11073..11074  ; Other_Alphabetic # Mn   [2] BRAHMI VOWEL SIGN OLD TAMIL SHORT E..BRAHMI VOWEL SIGN OLD TAMIL SHORT O
+11080..11081  ; Other_Alphabetic # Mn   [2] KAITHI SIGN CANDRABINDU..KAITHI SIGN ANUSVARA
 11082         ; Other_Alphabetic # Mc       KAITHI SIGN VISARGA
 110B0..110B2  ; Other_Alphabetic # Mc   [3] KAITHI VOWEL SIGN AA..KAITHI VOWEL SIGN II
 110B3..110B6  ; Other_Alphabetic # Mn   [4] KAITHI VOWEL SIGN U..KAITHI VOWEL SIGN AI
@@ -715,6 +719,7 @@ FB1E          ; Other_Alphabetic # Mn       HEBREW POINT JUDEO-SPANISH VARIKA
 11234         ; Other_Alphabetic # Mn       KHOJKI SIGN ANUSVARA
 11237         ; Other_Alphabetic # Mn       KHOJKI SIGN SHADDA
 1123E         ; Other_Alphabetic # Mn       KHOJKI SIGN SUKUN
+11241         ; Other_Alphabetic # Mn       KHOJKI VOWEL SIGN VOCALIC R
 112DF         ; Other_Alphabetic # Mn       KHUDAWADI SIGN ANUSVARA
 112E0..112E2  ; Other_Alphabetic # Mc   [3] KHUDAWADI VOWEL SIGN AA..KHUDAWADI VOWEL SIGN II
 112E3..112E8  ; Other_Alphabetic # Mn   [6] KHUDAWADI VOWEL SIGN U..KHUDAWADI VOWEL SIGN AU
@@ -807,6 +812,12 @@ FB1E          ; Other_Alphabetic # Mn       HEBREW POINT JUDEO-SPANISH VARIKA
 11D96         ; Other_Alphabetic # Mc       GUNJALA GONDI SIGN VISARGA
 11EF3..11EF4  ; Other_Alphabetic # Mn   [2] MAKASAR VOWEL SIGN I..MAKASAR VOWEL SIGN U
 11EF5..11EF6  ; Other_Alphabetic # Mc   [2] MAKASAR VOWEL SIGN E..MAKASAR VOWEL SIGN O
+11F00..11F01  ; Other_Alphabetic # Mn   [2] KAWI SIGN CANDRABINDU..KAWI SIGN ANUSVARA
+11F03         ; Other_Alphabetic # Mc       KAWI SIGN VISARGA
+11F34..11F35  ; Other_Alphabetic # Mc   [2] KAWI VOWEL SIGN AA..KAWI VOWEL SIGN ALTERNATE AA
+11F36..11F3A  ; Other_Alphabetic # Mn   [5] KAWI VOWEL SIGN I..KAWI VOWEL SIGN VOCALIC R
+11F3E..11F3F  ; Other_Alphabetic # Mc   [2] KAWI VOWEL SIGN E..KAWI VOWEL SIGN AI
+11F40         ; Other_Alphabetic # Mn       KAWI VOWEL SIGN EU
 16F4F         ; Other_Alphabetic # Mn       MIAO SIGN CONSONANT MODIFIER BAR
 16F51..16F87  ; Other_Alphabetic # Mc  [55] MIAO SIGN ASPIRATION..MIAO VOWEL SIGN UI
 16F8F..16F92  ; Other_Alphabetic # Mn   [4] MIAO TONE RIGHT..MIAO TONE BELOW
@@ -817,12 +828,13 @@ FB1E          ; Other_Alphabetic # Mn       HEBREW POINT JUDEO-SPANISH VARIKA
 1E01B..1E021  ; Other_Alphabetic # Mn   [7] COMBINING GLAGOLITIC LETTER SHTA..COMBINING GLAGOLITIC LETTER YATI
 1E023..1E024  ; Other_Alphabetic # Mn   [2] COMBINING GLAGOLITIC LETTER YU..COMBINING GLAGOLITIC LETTER SMALL YUS
 1E026..1E02A  ; Other_Alphabetic # Mn   [5] COMBINING GLAGOLITIC LETTER YO..COMBINING GLAGOLITIC LETTER FITA
+1E08F         ; Other_Alphabetic # Mn       COMBINING CYRILLIC SMALL LETTER BYELORUSSIAN-UKRAINIAN I
 1E947         ; Other_Alphabetic # Mn       ADLAM HAMZA
 1F130..1F149  ; Other_Alphabetic # So  [26] SQUARED LATIN CAPITAL LETTER A..SQUARED LATIN CAPITAL LETTER Z
 1F150..1F169  ; Other_Alphabetic # So  [26] NEGATIVE CIRCLED LATIN CAPITAL LETTER A..NEGATIVE CIRCLED LATIN CAPITAL LETTER Z
 1F170..1F189  ; Other_Alphabetic # So  [26] NEGATIVE SQUARED LATIN CAPITAL LETTER A..NEGATIVE SQUARED LATIN CAPITAL LETTER Z
 
-# Total code points: 1404
+# Total code points: 1425
 
 # ================================================
 
@@ -840,14 +852,15 @@ FA70..FAD9    ; Ideographic # Lo [106] CJK COMPATIBILITY IDEOGRAPH-FA70..CJK COM
 18D00..18D08  ; Ideographic # Lo   [9] TANGUT IDEOGRAPH-18D00..TANGUT IDEOGRAPH-18D08
 1B170..1B2FB  ; Ideographic # Lo [396] NUSHU CHARACTER-1B170..NUSHU CHARACTER-1B2FB
 20000..2A6DF  ; Ideographic # Lo [42720] CJK UNIFIED IDEOGRAPH-20000..CJK UNIFIED IDEOGRAPH-2A6DF
-2A700..2B738  ; Ideographic # Lo [4153] CJK UNIFIED IDEOGRAPH-2A700..CJK UNIFIED IDEOGRAPH-2B738
+2A700..2B739  ; Ideographic # Lo [4154] CJK UNIFIED IDEOGRAPH-2A700..CJK UNIFIED IDEOGRAPH-2B739
 2B740..2B81D  ; Ideographic # Lo [222] CJK UNIFIED IDEOGRAPH-2B740..CJK UNIFIED IDEOGRAPH-2B81D
 2B820..2CEA1  ; Ideographic # Lo [5762] CJK UNIFIED IDEOGRAPH-2B820..CJK UNIFIED IDEOGRAPH-2CEA1
 2CEB0..2EBE0  ; Ideographic # Lo [7473] CJK UNIFIED IDEOGRAPH-2CEB0..CJK UNIFIED IDEOGRAPH-2EBE0
 2F800..2FA1D  ; Ideographic # Lo [542] CJK COMPATIBILITY IDEOGRAPH-2F800..CJK COMPATIBILITY IDEOGRAPH-2FA1D
 30000..3134A  ; Ideographic # Lo [4939] CJK UNIFIED IDEOGRAPH-30000..CJK UNIFIED IDEOGRAPH-3134A
+31350..323AF  ; Ideographic # Lo [4192] CJK UNIFIED IDEOGRAPH-31350..CJK UNIFIED IDEOGRAPH-323AF
 
-# Total code points: 101661
+# Total code points: 105854
 
 # ================================================
 
@@ -1028,6 +1041,7 @@ FFE3          ; Diacritic # Sk       FULLWIDTH MACRON
 10AE5..10AE6  ; Diacritic # Mn   [2] MANICHAEAN ABBREVIATION MARK ABOVE..MANICHAEAN ABBREVIATION MARK BELOW
 10D22..10D23  ; Diacritic # Lo   [2] HANIFI ROHINGYA MARK SAKIN..HANIFI ROHINGYA MARK NA KHONNA
 10D24..10D27  ; Diacritic # Mn   [4] HANIFI ROHINGYA SIGN HARBAHAY..HANIFI ROHINGYA SIGN TASSI
+10EFD..10EFF  ; Diacritic # Mn   [3] ARABIC SMALL LOW WORD SAKTA..ARABIC SMALL LOW WORD MADDA
 10F46..10F50  ; Diacritic # Mn  [11] SOGDIAN COMBINING DOT BELOW..SOGDIAN COMBINING STROKE BELOW
 10F82..10F85  ; Diacritic # Mn   [4] OLD UYGHUR COMBINING DOT ABOVE..OLD UYGHUR COMBINING TWO DOTS BELOW
 11046         ; Diacritic # Mn       BRAHMI VIRAMA
@@ -1064,6 +1078,7 @@ FFE3          ; Diacritic # Sk       FULLWIDTH MACRON
 11D42         ; Diacritic # Mn       MASARAM GONDI SIGN NUKTA
 11D44..11D45  ; Diacritic # Mn   [2] MASARAM GONDI SIGN HALANTA..MASARAM GONDI VIRAMA
 11D97         ; Diacritic # Mn       GUNJALA GONDI VIRAMA
+13447..13455  ; Diacritic # Mn  [15] EGYPTIAN HIEROGLYPH MODIFIER DAMAGED AT TOP START..EGYPTIAN HIEROGLYPH MODIFIER DAMAGED
 16AF0..16AF4  ; Diacritic # Mn   [5] BASSA VAH COMBINING HIGH TONE..BASSA VAH COMBINING HIGH-LOW TONE
 16B30..16B36  ; Diacritic # Mn   [7] PAHAWH HMONG MARK CIM TUB..PAHAWH HMONG MARK CIM TAUM
 16F8F..16F92  ; Diacritic # Mn   [4] MIAO TONE RIGHT..MIAO TONE BELOW
@@ -1079,6 +1094,7 @@ FFE3          ; Diacritic # Sk       FULLWIDTH MACRON
 1D17B..1D182  ; Diacritic # Mn   [8] MUSICAL SYMBOL COMBINING ACCENT..MUSICAL SYMBOL COMBINING LOURE
 1D185..1D18B  ; Diacritic # Mn   [7] MUSICAL SYMBOL COMBINING DOIT..MUSICAL SYMBOL COMBINING TRIPLE TONGUE
 1D1AA..1D1AD  ; Diacritic # Mn   [4] MUSICAL SYMBOL COMBINING DOWN BOW..MUSICAL SYMBOL COMBINING SNAP PIZZICATO
+1E030..1E06D  ; Diacritic # Lm  [62] MODIFIER LETTER CYRILLIC SMALL A..MODIFIER LETTER CYRILLIC SMALL STRAIGHT U WITH STROKE
 1E130..1E136  ; Diacritic # Mn   [7] NYIAKENG PUACHUE HMONG TONE-B..NYIAKENG PUACHUE HMONG TONE-D
 1E2AE         ; Diacritic # Mn       TOTO SIGN RISING TONE
 1E2EC..1E2EF  ; Diacritic # Mn   [4] WANCHO TONE TUP..WANCHO TONE KOINI
@@ -1086,7 +1102,7 @@ FFE3          ; Diacritic # Sk       FULLWIDTH MACRON
 1E944..1E946  ; Diacritic # Mn   [3] ADLAM ALIF LENGTHENER..ADLAM GEMINATION MARK
 1E948..1E94A  ; Diacritic # Mn   [3] ADLAM CONSONANT MODIFIER..ADLAM NUKTA
 
-# Total code points: 1064
+# Total code points: 1144
 
 # ================================================
 
@@ -1135,6 +1151,7 @@ FF70          ; Extender # Lm       HALFWIDTH KATAKANA-HIRAGANA PROLONGED SOUND
 02E0..02E4    ; Other_Lowercase # Lm   [5] MODIFIER LETTER SMALL GAMMA..MODIFIER LETTER SMALL REVERSED GLOTTAL STOP
 0345          ; Other_Lowercase # Mn       COMBINING GREEK YPOGEGRAMMENI
 037A          ; Other_Lowercase # Lm       GREEK YPOGEGRAMMENI
+10FC          ; Other_Lowercase # Lm       MODIFIER LETTER GEORGIAN NAR
 1D2C..1D6A    ; Other_Lowercase # Lm  [63] MODIFIER LETTER CAPITAL A..GREEK SUBSCRIPT SMALL LETTER CHI
 1D78          ; Other_Lowercase # Lm       MODIFIER LETTER CYRILLIC EN
 1D9B..1DBF    ; Other_Lowercase # Lm  [37] MODIFIER LETTER SMALL TURNED ALPHA..MODIFIER LETTER SMALL THETA
@@ -1146,14 +1163,17 @@ FF70          ; Extender # Lm       HALFWIDTH KATAKANA-HIRAGANA PROLONGED SOUND
 2C7C..2C7D    ; Other_Lowercase # Lm   [2] LATIN SUBSCRIPT SMALL LETTER J..MODIFIER LETTER CAPITAL V
 A69C..A69D    ; Other_Lowercase # Lm   [2] MODIFIER LETTER CYRILLIC HARD SIGN..MODIFIER LETTER CYRILLIC SOFT SIGN
 A770          ; Other_Lowercase # Lm       MODIFIER LETTER US
+A7F2..A7F4    ; Other_Lowercase # Lm   [3] MODIFIER LETTER CAPITAL C..MODIFIER LETTER CAPITAL Q
 A7F8..A7F9    ; Other_Lowercase # Lm   [2] MODIFIER LETTER CAPITAL H WITH STROKE..MODIFIER LETTER SMALL LIGATURE OE
 AB5C..AB5F    ; Other_Lowercase # Lm   [4] MODIFIER LETTER SMALL HENG..MODIFIER LETTER SMALL U WITH LEFT HOOK
+AB69          ; Other_Lowercase # Lm       MODIFIER LETTER SMALL TURNED W
 10780         ; Other_Lowercase # Lm       MODIFIER LETTER SMALL CAPITAL AA
 10783..10785  ; Other_Lowercase # Lm   [3] MODIFIER LETTER SMALL AE..MODIFIER LETTER SMALL B WITH HOOK
 10787..107B0  ; Other_Lowercase # Lm  [42] MODIFIER LETTER SMALL DZ DIGRAPH..MODIFIER LETTER SMALL V WITH RIGHT HOOK
 107B2..107BA  ; Other_Lowercase # Lm   [9] MODIFIER LETTER SMALL CAPITAL Y..MODIFIER LETTER SMALL S WITH CURL
+1E030..1E06D  ; Other_Lowercase # Lm  [62] MODIFIER LETTER CYRILLIC SMALL A..MODIFIER LETTER CYRILLIC SMALL STRAIGHT U WITH STROKE
 
-# Total code points: 244
+# Total code points: 311
 
 # ================================================
 
@@ -1251,13 +1271,14 @@ FA21          ; Unified_Ideograph # Lo       CJK COMPATIBILITY IDEOGRAPH-FA21
 FA23..FA24    ; Unified_Ideograph # Lo   [2] CJK COMPATIBILITY IDEOGRAPH-FA23..CJK COMPATIBILITY IDEOGRAPH-FA24
 FA27..FA29    ; Unified_Ideograph # Lo   [3] CJK COMPATIBILITY IDEOGRAPH-FA27..CJK COMPATIBILITY IDEOGRAPH-FA29
 20000..2A6DF  ; Unified_Ideograph # Lo [42720] CJK UNIFIED IDEOGRAPH-20000..CJK UNIFIED IDEOGRAPH-2A6DF
-2A700..2B738  ; Unified_Ideograph # Lo [4153] CJK UNIFIED IDEOGRAPH-2A700..CJK UNIFIED IDEOGRAPH-2B738
+2A700..2B739  ; Unified_Ideograph # Lo [4154] CJK UNIFIED IDEOGRAPH-2A700..CJK UNIFIED IDEOGRAPH-2B739
 2B740..2B81D  ; Unified_Ideograph # Lo [222] CJK UNIFIED IDEOGRAPH-2B740..CJK UNIFIED IDEOGRAPH-2B81D
 2B820..2CEA1  ; Unified_Ideograph # Lo [5762] CJK UNIFIED IDEOGRAPH-2B820..CJK UNIFIED IDEOGRAPH-2CEA1
 2CEB0..2EBE0  ; Unified_Ideograph # Lo [7473] CJK UNIFIED IDEOGRAPH-2CEB0..CJK UNIFIED IDEOGRAPH-2EBE0
 30000..3134A  ; Unified_Ideograph # Lo [4939] CJK UNIFIED IDEOGRAPH-30000..CJK UNIFIED IDEOGRAPH-3134A
+31350..323AF  ; Unified_Ideograph # Lo [4192] CJK UNIFIED IDEOGRAPH-31350..CJK UNIFIED IDEOGRAPH-323AF
 
-# Total code points: 92865
+# Total code points: 97058
 
 # ================================================
 
@@ -1323,8 +1344,10 @@ E0001         ; Deprecated # Cf       LANGUAGE TAG
 1D65E..1D65F  ; Soft_Dotted # L&   [2] MATHEMATICAL SANS-SERIF BOLD ITALIC SMALL I..MATHEMATICAL SANS-SERIF BOLD ITALIC SMALL J
 1D692..1D693  ; Soft_Dotted # L&   [2] MATHEMATICAL MONOSPACE SMALL I..MATHEMATICAL MONOSPACE SMALL J
 1DF1A         ; Soft_Dotted # L&       LATIN SMALL LETTER I WITH STROKE AND RETROFLEX HOOK
+1E04C..1E04D  ; Soft_Dotted # Lm   [2] MODIFIER LETTER CYRILLIC SMALL BYELORUSSIAN-UKRAINIAN I..MODIFIER LETTER CYRILLIC SMALL JE
+1E068         ; Soft_Dotted # Lm       CYRILLIC SUBSCRIPT SMALL LETTER BYELORUSSIAN-UKRAINIAN I
 
-# Total code points: 47
+# Total code points: 50
 
 # ================================================
 
@@ -1430,6 +1453,7 @@ FF61          ; Sentence_Terminal # Po       HALFWIDTH IDEOGRAPHIC FULL STOP
 11A9B..11A9C  ; Sentence_Terminal # Po   [2] SOYOMBO MARK SHAD..SOYOMBO MARK DOUBLE SHAD
 11C41..11C42  ; Sentence_Terminal # Po   [2] BHAIKSUKI DANDA..BHAIKSUKI DOUBLE DANDA
 11EF7..11EF8  ; Sentence_Terminal # Po   [2] MAKASAR PASSIMBANG..MAKASAR END OF SECTION
+11F43..11F44  ; Sentence_Terminal # Po   [2] KAWI DANDA..KAWI DOUBLE DANDA
 16A6E..16A6F  ; Sentence_Terminal # Po   [2] MRO DANDA..MRO DOUBLE DANDA
 16AF5         ; Sentence_Terminal # Po       BASSA VAH FULL STOP
 16B37..16B38  ; Sentence_Terminal # Po   [2] PAHAWH HMONG SIGN VOS THOM..PAHAWH HMONG SIGN VOS TSHAB CEEB
@@ -1438,7 +1462,7 @@ FF61          ; Sentence_Terminal # Po       HALFWIDTH IDEOGRAPHIC FULL STOP
 1BC9F         ; Sentence_Terminal # Po       DUPLOYAN PUNCTUATION CHINOOK FULL STOP
 1DA88         ; Sentence_Terminal # Po       SIGNWRITING FULL STOP
 
-# Total code points: 152
+# Total code points: 154
 
 # ================================================
 
diff --git a/pcre2/maint/Unicode.tables/PropertyAliases.txt b/pcre2/maint/Unicode.tables/PropertyAliases.txt
index 3e4b429..2de24e2 100644
--- a/pcre2/maint/Unicode.tables/PropertyAliases.txt
+++ b/pcre2/maint/Unicode.tables/PropertyAliases.txt
@@ -1,11 +1,11 @@
-# PropertyAliases-14.0.0.txt
-# Date: 2021-03-08, 19:35:48 GMT
-# © 2021 Unicode®, Inc.
+# PropertyAliases-15.0.0.txt
+# Date: 2022-02-02, 23:35:44 GMT
+# © 2022 Unicode®, Inc.
 # Unicode and the Unicode Logo are registered trademarks of Unicode, Inc. in the U.S. and other countries.
-# For terms of use, see http://www.unicode.org/terms_of_use.html
+# For terms of use, see https://www.unicode.org/terms_of_use.html
 #
 # Unicode Character Database
-#   For documentation, see http://www.unicode.org/reports/tr44/
+#   For documentation, see https://www.unicode.org/reports/tr44/
 #
 # This file contains aliases for properties used in the UCD.
 # These names can be used for XML formats of UCD data, for regular-expression
diff --git a/pcre2/maint/Unicode.tables/PropertyValueAliases.txt b/pcre2/maint/Unicode.tables/PropertyValueAliases.txt
index f0cb26b..863301b 100644
--- a/pcre2/maint/Unicode.tables/PropertyValueAliases.txt
+++ b/pcre2/maint/Unicode.tables/PropertyValueAliases.txt
@@ -1,11 +1,11 @@
-# PropertyValueAliases-14.0.0.txt
-# Date: 2021-05-10, 21:08:53 GMT
-# © 2021 Unicode®, Inc.
+# PropertyValueAliases-15.0.0.txt
+# Date: 2022-08-05, 23:42:17 GMT
+# © 2022 Unicode®, Inc.
 # Unicode and the Unicode Logo are registered trademarks of Unicode, Inc. in the U.S. and other countries.
-# For terms of use, see http://www.unicode.org/terms_of_use.html
+# For terms of use, see https://www.unicode.org/terms_of_use.html
 #
 # Unicode Character Database
-#   For documentation, see http://www.unicode.org/reports/tr44/
+#   For documentation, see https://www.unicode.org/reports/tr44/
 #
 # This file contains aliases for property values used in the UCD.
 # These names can be used for XML formats of UCD data, for regular-expression
@@ -90,6 +90,7 @@ age; 12.0                             ; V12_0
 age; 12.1                             ; V12_1
 age; 13.0                             ; V13_0
 age; 14.0                             ; V14_0
+age; 15.0                             ; V15_0
 age; NA                               ; Unassigned
 
 # Alphabetic (Alpha)
@@ -135,7 +136,6 @@ Bidi_M; Y                             ; Yes                              ; T
 
 # Bidi_Mirroring_Glyph (bmg)
 
-# @missing: 0000..10FFFF; Bidi_Mirroring_Glyph; 
 
 # Bidi_Paired_Bracket (bpb)
 
@@ -162,6 +162,7 @@ blk; Ancient_Symbols                  ; Ancient_Symbols
 blk; Arabic                           ; Arabic
 blk; Arabic_Ext_A                     ; Arabic_Extended_A
 blk; Arabic_Ext_B                     ; Arabic_Extended_B
+blk; Arabic_Ext_C                     ; Arabic_Extended_C
 blk; Arabic_Math                      ; Arabic_Mathematical_Alphabetic_Symbols
 blk; Arabic_PF_A                      ; Arabic_Presentation_Forms_A      ; Arabic_Presentation_Forms-A
 blk; Arabic_PF_B                      ; Arabic_Presentation_Forms_B
@@ -206,6 +207,7 @@ blk; CJK_Ext_D                        ; CJK_Unified_Ideographs_Extension_D
 blk; CJK_Ext_E                        ; CJK_Unified_Ideographs_Extension_E
 blk; CJK_Ext_F                        ; CJK_Unified_Ideographs_Extension_F
 blk; CJK_Ext_G                        ; CJK_Unified_Ideographs_Extension_G
+blk; CJK_Ext_H                        ; CJK_Unified_Ideographs_Extension_H
 blk; CJK_Radicals_Sup                 ; CJK_Radicals_Supplement
 blk; CJK_Strokes                      ; CJK_Strokes
 blk; CJK_Symbols                      ; CJK_Symbols_And_Punctuation
@@ -223,10 +225,12 @@ blk; Cyrillic                         ; Cyrillic
 blk; Cyrillic_Ext_A                   ; Cyrillic_Extended_A
 blk; Cyrillic_Ext_B                   ; Cyrillic_Extended_B
 blk; Cyrillic_Ext_C                   ; Cyrillic_Extended_C
+blk; Cyrillic_Ext_D                   ; Cyrillic_Extended_D
 blk; Cyrillic_Sup                     ; Cyrillic_Supplement              ; Cyrillic_Supplementary
 blk; Deseret                          ; Deseret
 blk; Devanagari                       ; Devanagari
 blk; Devanagari_Ext                   ; Devanagari_Extended
+blk; Devanagari_Ext_A                 ; Devanagari_Extended_A
 blk; Diacriticals                     ; Combining_Diacritical_Marks
 blk; Diacriticals_Ext                 ; Combining_Diacritical_Marks_Extended
 blk; Diacriticals_For_Symbols         ; Combining_Diacritical_Marks_For_Symbols; Combining_Marks_For_Symbols
@@ -288,6 +292,7 @@ blk; Jamo_Ext_A                       ; Hangul_Jamo_Extended_A
 blk; Jamo_Ext_B                       ; Hangul_Jamo_Extended_B
 blk; Javanese                         ; Javanese
 blk; Kaithi                           ; Kaithi
+blk; Kaktovik_Numerals                ; Kaktovik_Numerals
 blk; Kana_Ext_A                       ; Kana_Extended_A
 blk; Kana_Ext_B                       ; Kana_Extended_B
 blk; Kana_Sup                         ; Kana_Supplement
@@ -296,6 +301,7 @@ blk; Kangxi                           ; Kangxi_Radicals
 blk; Kannada                          ; Kannada
 blk; Katakana                         ; Katakana
 blk; Katakana_Ext                     ; Katakana_Phonetic_Extensions
+blk; Kawi                             ; Kawi
 blk; Kayah_Li                         ; Kayah_Li
 blk; Kharoshthi                       ; Kharoshthi
 blk; Khitan_Small_Script              ; Khitan_Small_Script
@@ -360,6 +366,7 @@ blk; Myanmar                          ; Myanmar
 blk; Myanmar_Ext_A                    ; Myanmar_Extended_A
 blk; Myanmar_Ext_B                    ; Myanmar_Extended_B
 blk; Nabataean                        ; Nabataean
+blk; Nag_Mundari                      ; Nag_Mundari
 blk; Nandinagari                      ; Nandinagari
 blk; NB                               ; No_Block
 blk; New_Tai_Lue                      ; New_Tai_Lue
@@ -663,7 +670,6 @@ EPres; Y                              ; Yes                              ; T
 
 # Equivalent_Unified_Ideograph (EqUIdeo)
 
-# @missing: 0000..10FFFF; Equivalent_Unified_Ideograph; 
 
 # Expands_On_NFC (XO_NFC)
 
@@ -1143,7 +1149,6 @@ NFD_QC; Y                             ; Yes
 
 # NFKC_Casefold (NFKC_CF)
 
-# @missing: 0000..10FFFF; NFKC_Casefold; 
 
 # NFKC_Quick_Check (NFKC_QC)
 
@@ -1313,6 +1318,7 @@ sc ; Ital                             ; Old_Italic
 sc ; Java                             ; Javanese
 sc ; Kali                             ; Kayah_Li
 sc ; Kana                             ; Katakana
+sc ; Kawi                             ; Kawi
 sc ; Khar                             ; Kharoshthi
 sc ; Khmr                             ; Khmer
 sc ; Khoj                             ; Khojki
@@ -1345,6 +1351,7 @@ sc ; Mroo                             ; Mro
 sc ; Mtei                             ; Meetei_Mayek
 sc ; Mult                             ; Multani
 sc ; Mymr                             ; Myanmar
+sc ; Nagm                             ; Nag_Mundari
 sc ; Nand                             ; Nandinagari
 sc ; Narb                             ; Old_North_Arabian
 sc ; Nbat                             ; Nabataean
@@ -1418,7 +1425,6 @@ sc ; Zzzz                             ; Unknown
 
 # Script_Extensions (scx)
 
-# @missing: 0000..10FFFF; Script_Extensions;