From bf59b0c54f559179c6773dd4697e9d88a2021503 Mon Sep 17 00:00:00 2001
From: gaoruoshu <gaoruoshu@huawei.com>
Date: Mon, 24 Apr 2023 19:25:21 +0800
Subject: [PATCH] grep:pcre use UCP in UTF mode

---
 backport-pcre-use-UCP-in-UTF-mode.patch | 88 +++++++++++++++++++++++++
 grep.spec                               |  8 ++-
 2 files changed, 95 insertions(+), 1 deletion(-)
 create mode 100644 backport-pcre-use-UCP-in-UTF-mode.patch

diff --git a/backport-pcre-use-UCP-in-UTF-mode.patch b/backport-pcre-use-UCP-in-UTF-mode.patch
new file mode 100644
index 0000000..706034d
--- /dev/null
+++ b/backport-pcre-use-UCP-in-UTF-mode.patch
@@ -0,0 +1,88 @@
+From 5e3b760f65f13856e5717e5b9d935f5b4a615be3 Mon Sep 17 00:00:00 2001
+From: =?UTF-8?q?Carlo=20Marcelo=20Arenas=20Bel=C3=B3n?= <carenas@gmail.com>
+Date: Fri, 6 Jan 2023 19:34:56 -0800
+Subject: [PATCH] pcre: use UCP in UTF mode
+ 
+This fixes a serious bug affecting word-boundary and word-constituent regular
+expressions when the desired match involves non-ASCII UTF8 characters.
+* src/pcresearch.c: Set PCRE2_UCP together with PCRE2_UTF
+* tests/pcre-utf8-w: New file.
+* tests/Makefile.am (TESTS): Add it.
+* NEWS (Bug fixes): Mention this.
+* THANKS.in: Add Gro-Tsen and Karl Petterson.
+Reported by Gro-Tsen https://twitter.com/gro_tsen/status/1610972356972875777
+via Karl Pettersson in https://github.com/PCRE2Project/pcre2/issues/185
+This bug was present from grep-2.5, when --perl-regexp (-P) support was added.
+ 
+Reference:https://git.savannah.gnu.org/cgit/grep.git/commit?id=5e3b760f65f13856e5717e5b9d935f5b4a615be3
+Conflict:delete NEWS,ThANKS.in and change src/pcresearch.c
+---
+ src/pcresearch.c  |  2 +-
+ tests/Makefile.am |  1 +
+ tests/pcre-utf8-w | 28 ++++++++++++++++++++++++++++
+ 3 files changed, 30 insertions(+), 1 deletion(-)
+ create mode 100755 tests/pcre-utf8-w
+
+diff --git a/src/pcresearch.c b/src/pcresearch.c
+index 577995f..0127073 100644
+--- a/src/pcresearch.c
++++ b/src/pcresearch.c
+@@ -136,7 +136,7 @@ Pcompile (char *pattern, size_t size, reg_syntax_t ignored, bool exact)
+     {
+       if (! localeinfo.using_utf8)
+         die (EXIT_TROUBLE, 0, _("-P supports only unibyte and UTF-8 locales"));
+-      flags |= PCRE_UTF8;
++      flags |= (PCRE_UTF8 | PCRE_UCP);
+     }
+ 
+   /* FIXME: Remove this restriction.  */
+diff --git a/tests/Makefile.am b/tests/Makefile.am
+index b05a126..d2968c6 100644
+--- a/tests/Makefile.am
++++ b/tests/Makefile.am
+@@ -143,6 +143,7 @@ TESTS =					\	
+   pcre-jitstack					\
+   pcre-o					\
+   pcre-utf8					\
++  pcre-utf8-w					\
+   pcre-w					\
+   pcre-wx-backref				\
+   pcre-z					\
+diff --git a/tests/pcre-utf8-w b/tests/pcre-utf8-w
+new file mode 100755
+index 0000000..4cd7db6
+--- /dev/null
++++ b/tests/pcre-utf8-w
+@@ -0,0 +1,28 @@
++#!/bin/sh
++# Ensure non-ASCII UTF-8 characters are correctly identified as word-consituent
++#
++# Copyright (C) 2023 Free Software Foundation, Inc.
++#
++# Copying and distribution of this file, with or without modification,
++# are permitted in any medium without royalty provided the copyright
++# notice and this notice are preserved.
++
++. "${srcdir=.}/init.sh"; path_prepend_ ../src
++require_en_utf8_locale_
++LC_ALL=en_US.UTF-8
++export LC_ALL
++require_pcre_
++
++fail=0
++
++echo 'Perú'> in || framework_failure_
++
++echo 'ú' > exp || framework_failure_
++grep -Po '.\b' in > out || fail=1
++compare exp out || fail=1
++
++echo 'rú' > exp || framework_failure_
++grep -Po 'r\w' in > out || fail=1
++compare exp out || fail=1
++
++Exit $fail
+-- 
+2.27.0
+
+
diff --git a/grep.spec b/grep.spec
index beaa8d9..03444be 100644
--- a/grep.spec
+++ b/grep.spec
@@ -1,6 +1,6 @@
 Name:    grep
 Version: 3.4
-Release: 2
+Release: 3
 Summary: A string search utility
 License: GPLv3+
 URL: http://www.gnu.org/software/grep/
@@ -10,6 +10,7 @@ Source2: colorgrep.csh
 Source3: grepconf.sh
 
 Patch1: backport-grep-avoid-sticky-problem-with-f-f.patch
+Patch6001: backport-pcre-use-UCP-in-UTF-mode.patch
 
 BuildRequires: gcc git pcre-devel >= 3.9-10 texinfo gettext
 Provides: /bin/egrep /bin/fgrep /bin/grep bundled(gnulib)
@@ -22,6 +23,7 @@ a specified pattern. By default, Grep outputs the matching lines.
 %autosetup -n %{name}-%{version} -p1
 
 %build
+autoreconf
 %configure --without-included-regex --disable-silent-rules \
 CPPFLAGS="-I%{_includedir}/pcre" CFLAGS="$RPM_OPT_FLAGS"
 %make_build
@@ -54,6 +56,10 @@ make check
 
 
 %changelog
+* Mon Apr 24 2023 gaoruoshu<gaoruoshu@huawei.com> - 3.4-3
+- Type:bugfix
+- DESC:pcre: use UCP in UTF mode
+
 * Tue Dec 20 2022 gaoruoshu<gaoruoshu@huawei.com> - 3.4-2
 - Type:bugfix
 - DESC:Added coloring aliases to fgrep egrep and grep
-- 
Gitee