From ec95f3e2df797dc906f365884d53902a05394609 Mon Sep 17 00:00:00 2001 From: sunyaozu Date: Sat, 7 Dec 2024 16:27:06 +0800 Subject: [PATCH] provide string&text process ndk function Signed-off-by: sunyaozu --- third_party/icu4c/BUILD.gn | 6 + third_party/icu4c/libicu.ndk.json | 268 ++++ third_party/icu4c/ndk_headers/unicode/putil.h | 70 + .../icu4c/ndk_headers/unicode/ustring.h | 1354 +++++++++++++++++ third_party/icu4c/ndk_headers/unicode/utext.h | 582 +++++++ .../icu4c/ndk_headers/unicode/utypes.h | 8 + 6 files changed, 2288 insertions(+) create mode 100644 third_party/icu4c/ndk_headers/unicode/putil.h create mode 100644 third_party/icu4c/ndk_headers/unicode/ustring.h create mode 100644 third_party/icu4c/ndk_headers/unicode/utext.h diff --git a/third_party/icu4c/BUILD.gn b/third_party/icu4c/BUILD.gn index d3466f1eb..a4fa3d8c5 100644 --- a/third_party/icu4c/BUILD.gn +++ b/third_party/icu4c/BUILD.gn @@ -23,6 +23,7 @@ ohos_ndk_library("libicu_ndk") { "unicode/parseerr.h", "unicode/platform.h", "unicode/ptypes.h", + "unicode/putil.h", "unicode/stringoptions.h", "unicode/ubidi.h", "unicode/ubrk.h", @@ -45,6 +46,8 @@ ohos_ndk_library("libicu_ndk") { "unicode/unumberformatter.h", "unicode/uscript.h", "unicode/uset.h", + "unicode/ustring.h", + "unicode/utext.h", "unicode/utrans.h", "unicode/utypes.h", ] @@ -57,6 +60,7 @@ ohos_ndk_headers("icu_unicode_header") { "ndk_headers/unicode/parseerr.h", "ndk_headers/unicode/platform.h", "ndk_headers/unicode/ptypes.h", + "ndk_headers/unicode/putil.h", "ndk_headers/unicode/stringoptions.h", "ndk_headers/unicode/ubidi.h", "ndk_headers/unicode/ubrk.h", @@ -79,6 +83,8 @@ ohos_ndk_headers("icu_unicode_header") { "ndk_headers/unicode/unumberformatter.h", "ndk_headers/unicode/uscript.h", "ndk_headers/unicode/uset.h", + "ndk_headers/unicode/ustring.h", + "ndk_headers/unicode/utext.h", "ndk_headers/unicode/utrans.h", "ndk_headers/unicode/utypes.h", ] diff --git a/third_party/icu4c/libicu.ndk.json b/third_party/icu4c/libicu.ndk.json index 5fc158cad..34bf1aa98 100644 --- a/third_party/icu4c/libicu.ndk.json +++ b/third_party/icu4c/libicu.ndk.json @@ -1814,5 +1814,273 @@ { "first_introduced": "12", "name":"uidna_nameToUnicodeUTF8" + }, + { + "first_introduced": "15", + "name":"utext_close" + }, + { + "first_introduced": "15", + "name":"utext_openUTF8" + }, + { + "first_introduced": "15", + "name":"utext_openUChars" + }, + { + "first_introduced": "15", + "name":"utext_clone" + }, + { + "first_introduced": "15", + "name":"utext_equals" + }, + { + "first_introduced": "15", + "name":"utext_nativeLength" + }, + { + "first_introduced": "15", + "name":"utext_char32At" + }, + { + "first_introduced": "15", + "name":"utext_current32" + }, + { + "first_introduced": "15", + "name":"utext_next32" + }, + { + "first_introduced": "15", + "name":"utext_previous32" + }, + { + "first_introduced": "15", + "name":"utext_next32From" + }, + { + "first_introduced": "15", + "name":"utext_previous32From" + }, + { + "first_introduced": "15", + "name":"utext_getNativeIndex" + }, + { + "first_introduced": "15", + "name":"utext_setNativeIndex" + }, + { + "first_introduced": "15", + "name":"utext_moveIndex32" + }, + { + "first_introduced": "15", + "name":"utext_getPreviousNativeIndex" + }, + { + "first_introduced": "15", + "name":"utext_extract" + }, + { + "first_introduced": "15", + "name":"u_strlen" + }, + { + "first_introduced": "15", + "name":"u_countChar32" + }, + { + "first_introduced": "15", + "name":"u_strHasMoreChar32Than" + }, + { + "first_introduced": "15", + "name":"u_strcat" + }, + { + "first_introduced": "15", + "name":"u_strncat" + }, + { + "first_introduced": "15", + "name":"u_strstr" + }, + { + "first_introduced": "15", + "name":"u_strFindFirst" + }, + { + "first_introduced": "15", + "name":"u_strchr" + }, + { + "first_introduced": "15", + "name":"u_strchr32" + }, + { + "first_introduced": "15", + "name":"u_strrstr" + }, + { + "first_introduced": "15", + "name":"u_strFindLast" + }, + { + "first_introduced": "15", + "name":"u_strrchr" + }, + { + "first_introduced": "15", + "name":"u_strrchr32" + }, + { + "first_introduced": "15", + "name":"u_strpbrk" + }, + { + "first_introduced": "15", + "name":"u_strcspn" + }, + { + "first_introduced": "15", + "name":"u_strspn" + }, + { + "first_introduced": "15", + "name":"u_strtok_r" + }, + { + "first_introduced": "15", + "name":"u_strcmp" + }, + { + "first_introduced": "15", + "name":"u_strcmpCodePointOrder" + }, + { + "first_introduced": "15", + "name":"u_strCompare" + }, + { + "first_introduced": "15", + "name":"u_strCaseCompare" + }, + { + "first_introduced": "15", + "name":"u_strncmp" + }, + { + "first_introduced": "15", + "name":"u_strncmpCodePointOrder" + }, + { + "first_introduced": "15", + "name":"u_strcasecmp" + }, + { + "first_introduced": "15", + "name":"u_strncasecmp" + }, + { + "first_introduced": "15", + "name":"u_memcasecmp" + }, + { + "first_introduced": "15", + "name":"u_strcpy" + }, + { + "first_introduced": "15", + "name":"u_strncpy" + }, + { + "first_introduced": "15", + "name":"u_memcpy" + }, + { + "first_introduced": "15", + "name":"u_memmove" + }, + { + "first_introduced": "15", + "name":"u_memset" + }, + { + "first_introduced": "15", + "name":"u_memcmp" + }, + { + "first_introduced": "15", + "name":"u_memcmpCodePointOrder" + }, + { + "first_introduced": "15", + "name":"u_memchr" + }, + { + "first_introduced": "15", + "name":"u_memchr32" + }, + { + "first_introduced": "15", + "name":"u_memrchr" + }, + { + "first_introduced": "15", + "name":"u_memrchr32" + }, + { + "first_introduced": "15", + "name":"u_strToUpper" + }, + { + "first_introduced": "15", + "name":"u_strToLower" + }, + { + "first_introduced": "15", + "name":"u_strToTitle" + }, + { + "first_introduced": "15", + "name":"u_strFoldCase" + }, + { + "first_introduced": "15", + "name":"u_strToUTF8" + }, + { + "first_introduced": "15", + "name":"u_strFromUTF8" + }, + { + "first_introduced": "15", + "name":"u_strToUTF8WithSub" + }, + { + "first_introduced": "15", + "name":"u_strFromUTF8WithSub" + }, + { + "first_introduced": "15", + "name":"u_strFromUTF8Lenient" + }, + { + "first_introduced": "15", + "name":"u_strToUTF32" + }, + { + "first_introduced": "15", + "name":"u_strFromUTF32" + }, + { + "first_introduced": "15", + "name":"u_strToUTF32WithSub" + }, + { + "first_introduced": "15", + "name":"u_strFromUTF32WithSub" } ] diff --git a/third_party/icu4c/ndk_headers/unicode/putil.h b/third_party/icu4c/ndk_headers/unicode/putil.h new file mode 100644 index 000000000..a8dca9321 --- /dev/null +++ b/third_party/icu4c/ndk_headers/unicode/putil.h @@ -0,0 +1,70 @@ +// © 2016 and later: Unicode, Inc. and others. +// License & terms of use: http://www.unicode.org/copyright.html +/* +****************************************************************************** +* +* Copyright (C) 1997-2014, International Business Machines +* Corporation and others. All Rights Reserved. +* +****************************************************************************** +* +* FILE NAME : putil.h +* +* Date Name Description +* 05/14/98 nos Creation (content moved here from utypes.h). +* 06/17/99 erm Added IEEE_754 +* 07/22/98 stephen Added IEEEremainder, max, min, trunc +* 08/13/98 stephen Added isNegativeInfinity, isPositiveInfinity +* 08/24/98 stephen Added longBitsFromDouble +* 03/02/99 stephen Removed openFile(). Added AS400 support. +* 04/15/99 stephen Converted to C +* 11/15/99 helena Integrated S/390 changes for IEEE support. +* 01/11/00 helena Added u_getVersion. +****************************************************************************** +*/ + +#ifndef PUTIL_H +#define PUTIL_H + +#include "unicode/utypes.h" + /** + * \file + * \brief C API: Platform Utilities + */ + +/*==========================================================================*/ +/* Platform utilities */ +/*==========================================================================*/ + +/** + * Platform utilities isolates the platform dependencies of the + * library. For each platform which this code is ported to, these + * functions may have to be re-implemented. + */ + +/** + * @{ + * Filesystem file and path separator characters. + * Example: '/' and ':' on Unix, '\\' and ';' on Windows. + * @stable ICU 2.0 + */ +#if U_PLATFORM_USES_ONLY_WIN32_API +# define U_FILE_SEP_CHAR '\\' +# define U_FILE_ALT_SEP_CHAR '/' +# define U_PATH_SEP_CHAR ';' +# define U_FILE_SEP_STRING "\\" +# define U_FILE_ALT_SEP_STRING "/" +# define U_PATH_SEP_STRING ";" +#else +# define U_FILE_SEP_CHAR '/' +# define U_FILE_ALT_SEP_CHAR '/' +# define U_PATH_SEP_CHAR ':' +# define U_FILE_SEP_STRING "/" +# define U_FILE_ALT_SEP_STRING "/" +# define U_PATH_SEP_STRING ":" +#endif + +/** @} */ + + +#endif diff --git a/third_party/icu4c/ndk_headers/unicode/ustring.h b/third_party/icu4c/ndk_headers/unicode/ustring.h new file mode 100644 index 000000000..3d5731226 --- /dev/null +++ b/third_party/icu4c/ndk_headers/unicode/ustring.h @@ -0,0 +1,1354 @@ +// © 2016 and later: Unicode, Inc. and others. +// License & terms of use: http://www.unicode.org/copyright.html +/* +********************************************************************** +* Copyright (C) 1998-2014, International Business Machines +* Corporation and others. All Rights Reserved. +********************************************************************** +* +* File ustring.h +* +* Modification History: +* +* Date Name Description +* 12/07/98 bertrand Creation. +****************************************************************************** +*/ + +#ifndef USTRING_H +#define USTRING_H + +#include "unicode/utypes.h" +#include "unicode/putil.h" + +/** + * \def UBRK_TYPEDEF_UBREAK_ITERATOR + * @internal + */ + +#ifndef UBRK_TYPEDEF_UBREAK_ITERATOR +# define UBRK_TYPEDEF_UBREAK_ITERATOR +/** Simple declaration for u_strToTitle() to avoid including unicode/ubrk.h. @stable ICU 2.1*/ + typedef struct UBreakIterator UBreakIterator; +#endif + +/** + * \file + * \brief C API: Unicode string handling functions + * + * These C API functions provide general Unicode string handling. + * + * Some functions are equivalent in name, signature, and behavior to the ANSI C + * functions. (For example, they do not check for bad arguments like NULL string pointers.) + * In some cases, only the thread-safe variant of such a function is implemented here + * (see u_strtok_r()). + * + * Other functions provide more Unicode-specific functionality like locale-specific + * upper/lower-casing and string comparison in code point order. + * + * ICU uses 16-bit Unicode (UTF-16) in the form of arrays of UChar code units. + * UTF-16 encodes each Unicode code point with either one or two UChar code units. + * (This is the default form of Unicode, and a forward-compatible extension of the original, + * fixed-width form that was known as UCS-2. UTF-16 superseded UCS-2 with Unicode 2.0 + * in 1996.) + * + * Some APIs accept a 32-bit UChar32 value for a single code point. + * + * ICU also handles 16-bit Unicode text with unpaired surrogates. + * Such text is not well-formed UTF-16. + * Code-point-related functions treat unpaired surrogates as surrogate code points, + * i.e., as separate units. + * + * Although UTF-16 is a variable-width encoding form (like some legacy multi-byte encodings), + * it is much more efficient even for random access because the code unit values + * for single-unit characters vs. lead units vs. trail units are completely disjoint. + * This means that it is easy to determine character (code point) boundaries from + * random offsets in the string. + * + * Unicode (UTF-16) string processing is optimized for the single-unit case. + * Although it is important to support supplementary characters + * (which use pairs of lead/trail code units called "surrogates"), + * their occurrence is rare. Almost all characters in modern use require only + * a single UChar code unit (i.e., their code point values are <=0xffff). + * + * For more details see the User Guide Strings chapter (https://unicode-org.github.io/icu/userguide/strings/). + * For a discussion of the handling of unpaired surrogates see also + * Jitterbug 2145 and its icu mailing list proposal on 2002-sep-18. + */ + +/** + * \defgroup ustring_ustrlen String Length + * \ingroup ustring_strlen + */ +/*@{*/ +/** + * Determine the length of an array of UChar. + * + * @param s The array of UChars, NULL (U+0000) terminated. + * @return The number of UChars in chars, minus the terminator. + * @stable ICU 2.0 + */ +U_CAPI int32_t U_EXPORT2 +u_strlen(const UChar *s); +/*@}*/ + +/** + * Count Unicode code points in the length UChar code units of the string. + * A code point may occupy either one or two UChar code units. + * Counting code points involves reading all code units. + * + * This functions is basically the inverse of the U16_FWD_N() macro (see utf.h). + * + * @param s The input string. + * @param length The number of UChar code units to be checked, or -1 to count all + * code points before the first NUL (U+0000). + * @return The number of code points in the specified code units. + * @stable ICU 2.0 + */ +U_CAPI int32_t U_EXPORT2 +u_countChar32(const UChar *s, int32_t length); + +/** + * Check if the string contains more Unicode code points than a certain number. + * This is more efficient than counting all code points in the entire string + * and comparing that number with a threshold. + * This function may not need to scan the string at all if the length is known + * (not -1 for NUL-termination) and falls within a certain range, and + * never needs to count more than 'number+1' code points. + * Logically equivalent to (u_countChar32(s, length)>number). + * A Unicode code point may occupy either one or two UChar code units. + * + * @param s The input string. + * @param length The length of the string, or -1 if it is NUL-terminated. + * @param number The number of code points in the string is compared against + * the 'number' parameter. + * @return Boolean value for whether the string contains more Unicode code points + * than 'number'. Same as (u_countChar32(s, length)>number). + * @stable ICU 2.4 + */ +U_CAPI UBool U_EXPORT2 +u_strHasMoreChar32Than(const UChar *s, int32_t length, int32_t number); + +/** + * Concatenate two ustrings. Appends a copy of src, + * including the null terminator, to dst. The initial copied + * character from src overwrites the null terminator in dst. + * + * @param dst The destination string. + * @param src The source string. + * @return A pointer to dst. + * @stable ICU 2.0 + */ +U_CAPI UChar* U_EXPORT2 +u_strcat(UChar *dst, + const UChar *src); + +/** + * Concatenate two ustrings. + * Appends at most n characters from src to dst. + * Adds a terminating NUL. + * If src is too long, then only n-1 characters will be copied + * before the terminating NUL. + * If n<=0 then dst is not modified. + * + * @param dst The destination string. + * @param src The source string (can be NULL/invalid if n<=0). + * @param n The maximum number of characters to append; no-op if <=0. + * @return A pointer to dst. + * @stable ICU 2.0 + */ +U_CAPI UChar* U_EXPORT2 +u_strncat(UChar *dst, + const UChar *src, + int32_t n); + +/** + * Find the first occurrence of a substring in a string. + * The substring is found at code point boundaries. + * That means that if the substring begins with + * a trail surrogate or ends with a lead surrogate, + * then it is found only if these surrogates stand alone in the text. + * Otherwise, the substring edge units would be matched against + * halves of surrogate pairs. + * + * @param s The string to search (NUL-terminated). + * @param substring The substring to find (NUL-terminated). + * @return A pointer to the first occurrence of substring in s, + * or s itself if the substring is empty, + * or NULL if substring is not in s. + * @stable ICU 2.0 + * + * @see u_strrstr + * @see u_strFindFirst + * @see u_strFindLast + */ +U_CAPI UChar * U_EXPORT2 +u_strstr(const UChar *s, const UChar *substring); + +/** + * Find the first occurrence of a substring in a string. + * The substring is found at code point boundaries. + * That means that if the substring begins with + * a trail surrogate or ends with a lead surrogate, + * then it is found only if these surrogates stand alone in the text. + * Otherwise, the substring edge units would be matched against + * halves of surrogate pairs. + * + * @param s The string to search. + * @param length The length of s (number of UChars), or -1 if it is NUL-terminated. + * @param substring The substring to find (NUL-terminated). + * @param subLength The length of substring (number of UChars), or -1 if it is NUL-terminated. + * @return A pointer to the first occurrence of substring in s, + * or s itself if the substring is empty, + * or NULL if substring is not in s. + * @stable ICU 2.4 + * + * @see u_strstr + * @see u_strFindLast + */ +U_CAPI UChar * U_EXPORT2 +u_strFindFirst(const UChar *s, int32_t length, const UChar *substring, int32_t subLength); + +/** + * Find the first occurrence of a BMP code point in a string. + * A surrogate code point is found only if its match in the text is not + * part of a surrogate pair. + * A NUL character is found at the string terminator. + * + * @param s The string to search (NUL-terminated). + * @param c The BMP code point to find. + * @return A pointer to the first occurrence of c in s + * or NULL if c is not in s. + * @stable ICU 2.0 + * + * @see u_strchr32 + * @see u_memchr + * @see u_strstr + * @see u_strFindFirst + */ +U_CAPI UChar * U_EXPORT2 +u_strchr(const UChar *s, UChar c); + +/** + * Find the first occurrence of a code point in a string. + * A surrogate code point is found only if its match in the text is not + * part of a surrogate pair. + * A NUL character is found at the string terminator. + * + * @param s The string to search (NUL-terminated). + * @param c The code point to find. + * @return A pointer to the first occurrence of c in s + * or NULL if c is not in s. + * @stable ICU 2.0 + * + * @see u_strchr + * @see u_memchr32 + * @see u_strstr + * @see u_strFindFirst + */ +U_CAPI UChar * U_EXPORT2 +u_strchr32(const UChar *s, UChar32 c); + +/** + * Find the last occurrence of a substring in a string. + * The substring is found at code point boundaries. + * That means that if the substring begins with + * a trail surrogate or ends with a lead surrogate, + * then it is found only if these surrogates stand alone in the text. + * Otherwise, the substring edge units would be matched against + * halves of surrogate pairs. + * + * @param s The string to search (NUL-terminated). + * @param substring The substring to find (NUL-terminated). + * @return A pointer to the last occurrence of substring in s, + * or s itself if the substring is empty, + * or NULL if substring is not in s. + * @stable ICU 2.4 + * + * @see u_strstr + * @see u_strFindFirst + * @see u_strFindLast + */ +U_CAPI UChar * U_EXPORT2 +u_strrstr(const UChar *s, const UChar *substring); + +/** + * Find the last occurrence of a substring in a string. + * The substring is found at code point boundaries. + * That means that if the substring begins with + * a trail surrogate or ends with a lead surrogate, + * then it is found only if these surrogates stand alone in the text. + * Otherwise, the substring edge units would be matched against + * halves of surrogate pairs. + * + * @param s The string to search. + * @param length The length of s (number of UChars), or -1 if it is NUL-terminated. + * @param substring The substring to find (NUL-terminated). + * @param subLength The length of substring (number of UChars), or -1 if it is NUL-terminated. + * @return A pointer to the last occurrence of substring in s, + * or s itself if the substring is empty, + * or NULL if substring is not in s. + * @stable ICU 2.4 + * + * @see u_strstr + * @see u_strFindLast + */ +U_CAPI UChar * U_EXPORT2 +u_strFindLast(const UChar *s, int32_t length, const UChar *substring, int32_t subLength); + +/** + * Find the last occurrence of a BMP code point in a string. + * A surrogate code point is found only if its match in the text is not + * part of a surrogate pair. + * A NUL character is found at the string terminator. + * + * @param s The string to search (NUL-terminated). + * @param c The BMP code point to find. + * @return A pointer to the last occurrence of c in s + * or NULL if c is not in s. + * @stable ICU 2.4 + * + * @see u_strrchr32 + * @see u_memrchr + * @see u_strrstr + * @see u_strFindLast + */ +U_CAPI UChar * U_EXPORT2 +u_strrchr(const UChar *s, UChar c); + +/** + * Find the last occurrence of a code point in a string. + * A surrogate code point is found only if its match in the text is not + * part of a surrogate pair. + * A NUL character is found at the string terminator. + * + * @param s The string to search (NUL-terminated). + * @param c The code point to find. + * @return A pointer to the last occurrence of c in s + * or NULL if c is not in s. + * @stable ICU 2.4 + * + * @see u_strrchr + * @see u_memchr32 + * @see u_strrstr + * @see u_strFindLast + */ +U_CAPI UChar * U_EXPORT2 +u_strrchr32(const UChar *s, UChar32 c); + +/** + * Locates the first occurrence in the string string of any of the characters + * in the string matchSet. + * Works just like C's strpbrk but with Unicode. + * + * @param string The string in which to search, NUL-terminated. + * @param matchSet A NUL-terminated string defining a set of code points + * for which to search in the text string. + * @return A pointer to the character in string that matches one of the + * characters in matchSet, or NULL if no such character is found. + * @stable ICU 2.0 + */ +U_CAPI UChar * U_EXPORT2 +u_strpbrk(const UChar *string, const UChar *matchSet); + +/** + * Returns the number of consecutive characters in string, + * beginning with the first, that do not occur somewhere in matchSet. + * Works just like C's strcspn but with Unicode. + * + * @param string The string in which to search, NUL-terminated. + * @param matchSet A NUL-terminated string defining a set of code points + * for which to search in the text string. + * @return The number of initial characters in string that do not + * occur in matchSet. + * @see u_strspn + * @stable ICU 2.0 + */ +U_CAPI int32_t U_EXPORT2 +u_strcspn(const UChar *string, const UChar *matchSet); + +/** + * Returns the number of consecutive characters in string, + * beginning with the first, that occur somewhere in matchSet. + * Works just like C's strspn but with Unicode. + * + * @param string The string in which to search, NUL-terminated. + * @param matchSet A NUL-terminated string defining a set of code points + * for which to search in the text string. + * @return The number of initial characters in string that do + * occur in matchSet. + * @see u_strcspn + * @stable ICU 2.0 + */ +U_CAPI int32_t U_EXPORT2 +u_strspn(const UChar *string, const UChar *matchSet); + +/** + * The string tokenizer API allows an application to break a string into + * tokens. Unlike strtok(), the saveState (the current pointer within the + * original string) is maintained in saveState. In the first call, the + * argument src is a pointer to the string. In subsequent calls to + * return successive tokens of that string, src must be specified as + * NULL. The value saveState is set by this function to maintain the + * function's position within the string, and on each subsequent call + * you must give this argument the same variable. This function does + * handle surrogate pairs. This function is similar to the strtok_r() + * the POSIX Threads Extension (1003.1c-1995) version. + * + * @param src String containing token(s). This string will be modified. + * After the first call to u_strtok_r(), this argument must + * be NULL to get to the next token. + * @param delim Set of delimiter characters (Unicode code points). + * @param saveState The current pointer within the original string, + * which is set by this function. The saveState + * parameter should the address of a local variable of type + * UChar *. (i.e. defined "UChar *myLocalSaveState" and use + * &myLocalSaveState for this parameter). + * @return A pointer to the next token found in src, or NULL + * when there are no more tokens. + * @stable ICU 2.0 + */ +U_CAPI UChar * U_EXPORT2 +u_strtok_r(UChar *src, + const UChar *delim, + UChar **saveState); + +/** + * Compare two Unicode strings for bitwise equality (code unit order). + * + * @param s1 A string to compare. + * @param s2 A string to compare. + * @return 0 if s1 and s2 are bitwise equal; a negative + * value if s1 is bitwise less than s2,; a positive + * value if s1 is bitwise greater than s2. + * @stable ICU 2.0 + */ +U_CAPI int32_t U_EXPORT2 +u_strcmp(const UChar *s1, + const UChar *s2); + +/** + * Compare two Unicode strings in code point order. + * See u_strCompare for details. + * + * @param s1 A string to compare. + * @param s2 A string to compare. + * @return a negative/zero/positive integer corresponding to whether + * the first string is less than/equal to/greater than the second one + * in code point order + * @stable ICU 2.0 + */ +U_CAPI int32_t U_EXPORT2 +u_strcmpCodePointOrder(const UChar *s1, const UChar *s2); + +/** + * Compare two Unicode strings (binary order). + * + * The comparison can be done in code unit order or in code point order. + * They differ only in UTF-16 when + * comparing supplementary code points (U+10000..U+10ffff) + * to BMP code points near the end of the BMP (i.e., U+e000..U+ffff). + * In code unit order, high BMP code points sort after supplementary code points + * because they are stored as pairs of surrogates which are at U+d800..U+dfff. + * + * This functions works with strings of different explicitly specified lengths + * unlike the ANSI C-like u_strcmp() and u_memcmp() etc. + * NUL-terminated strings are possible with length arguments of -1. + * + * @param s1 First source string. + * @param length1 Length of first source string, or -1 if NUL-terminated. + * + * @param s2 Second source string. + * @param length2 Length of second source string, or -1 if NUL-terminated. + * + * @param codePointOrder Choose between code unit order (false) + * and code point order (true). + * + * @return <0 or 0 or >0 as usual for string comparisons + * + * @stable ICU 2.2 + */ +U_CAPI int32_t U_EXPORT2 +u_strCompare(const UChar *s1, int32_t length1, + const UChar *s2, int32_t length2, + UBool codePointOrder); + + +/** + * Compare two strings case-insensitively using full case folding. + * This is equivalent to + * u_strCompare(u_strFoldCase(s1, options), + * u_strFoldCase(s2, options), + * (options&U_COMPARE_CODE_POINT_ORDER)!=0). + * + * The comparison can be done in UTF-16 code unit order or in code point order. + * They differ only when comparing supplementary code points (U+10000..U+10ffff) + * to BMP code points near the end of the BMP (i.e., U+e000..U+ffff). + * In code unit order, high BMP code points sort after supplementary code points + * because they are stored as pairs of surrogates which are at U+d800..U+dfff. + * + * This functions works with strings of different explicitly specified lengths + * unlike the ANSI C-like u_strcmp() and u_memcmp() etc. + * NUL-terminated strings are possible with length arguments of -1. + * + * @param s1 First source string. + * @param length1 Length of first source string, or -1 if NUL-terminated. + * + * @param s2 Second source string. + * @param length2 Length of second source string, or -1 if NUL-terminated. + * + * @param options A bit set of options: + * - U_FOLD_CASE_DEFAULT or 0 is used for default options: + * Comparison in code unit order with default case folding. + * + * - U_COMPARE_CODE_POINT_ORDER + * Set to choose code point order instead of code unit order + * (see u_strCompare for details). + * + * - U_FOLD_CASE_EXCLUDE_SPECIAL_I + * + * @param pErrorCode Must be a valid pointer to an error code value, + * which must not indicate a failure before the function call. + * + * @return <0 or 0 or >0 as usual for string comparisons + * + * @stable ICU 2.2 + */ +U_CAPI int32_t U_EXPORT2 +u_strCaseCompare(const UChar *s1, int32_t length1, + const UChar *s2, int32_t length2, + uint32_t options, + UErrorCode *pErrorCode); + +/** + * Compare two ustrings for bitwise equality. + * Compares at most n characters. + * + * @param ucs1 A string to compare (can be NULL/invalid if n<=0). + * @param ucs2 A string to compare (can be NULL/invalid if n<=0). + * @param n The maximum number of characters to compare; always returns 0 if n<=0. + * @return 0 if s1 and s2 are bitwise equal; a negative + * value if s1 is bitwise less than s2; a positive + * value if s1 is bitwise greater than s2. + * @stable ICU 2.0 + */ +U_CAPI int32_t U_EXPORT2 +u_strncmp(const UChar *ucs1, + const UChar *ucs2, + int32_t n); + +/** + * Compare two Unicode strings in code point order. + * This is different in UTF-16 from u_strncmp() if supplementary characters are present. + * For details, see u_strCompare(). + * + * @param s1 A string to compare. + * @param s2 A string to compare. + * @param n The maximum number of characters to compare. + * @return a negative/zero/positive integer corresponding to whether + * the first string is less than/equal to/greater than the second one + * in code point order + * @stable ICU 2.0 + */ +U_CAPI int32_t U_EXPORT2 +u_strncmpCodePointOrder(const UChar *s1, const UChar *s2, int32_t n); + +/** + * Compare two strings case-insensitively using full case folding. + * This is equivalent to u_strcmp(u_strFoldCase(s1, options), u_strFoldCase(s2, options)). + * + * @param s1 A string to compare. + * @param s2 A string to compare. + * @param options A bit set of options: + * - U_FOLD_CASE_DEFAULT or 0 is used for default options: + * Comparison in code unit order with default case folding. + * + * - U_COMPARE_CODE_POINT_ORDER + * Set to choose code point order instead of code unit order + * (see u_strCompare for details). + * + * - U_FOLD_CASE_EXCLUDE_SPECIAL_I + * + * @return A negative, zero, or positive integer indicating the comparison result. + * @stable ICU 2.0 + */ +U_CAPI int32_t U_EXPORT2 +u_strcasecmp(const UChar *s1, const UChar *s2, uint32_t options); + +/** + * Compare two strings case-insensitively using full case folding. + * This is equivalent to u_strcmp(u_strFoldCase(s1, at most n, options), + * u_strFoldCase(s2, at most n, options)). + * + * @param s1 A string to compare. + * @param s2 A string to compare. + * @param n The maximum number of characters each string to case-fold and then compare. + * @param options A bit set of options: + * - U_FOLD_CASE_DEFAULT or 0 is used for default options: + * Comparison in code unit order with default case folding. + * + * - U_COMPARE_CODE_POINT_ORDER + * Set to choose code point order instead of code unit order + * (see u_strCompare for details). + * + * - U_FOLD_CASE_EXCLUDE_SPECIAL_I + * + * @return A negative, zero, or positive integer indicating the comparison result. + * @stable ICU 2.0 + */ +U_CAPI int32_t U_EXPORT2 +u_strncasecmp(const UChar *s1, const UChar *s2, int32_t n, uint32_t options); + +/** + * Compare two strings case-insensitively using full case folding. + * This is equivalent to u_strcmp(u_strFoldCase(s1, n, options), + * u_strFoldCase(s2, n, options)). + * + * @param s1 A string to compare. + * @param s2 A string to compare. + * @param length The number of characters in each string to case-fold and then compare. + * @param options A bit set of options: + * - U_FOLD_CASE_DEFAULT or 0 is used for default options: + * Comparison in code unit order with default case folding. + * + * - U_COMPARE_CODE_POINT_ORDER + * Set to choose code point order instead of code unit order + * (see u_strCompare for details). + * + * - U_FOLD_CASE_EXCLUDE_SPECIAL_I + * + * @return A negative, zero, or positive integer indicating the comparison result. + * @stable ICU 2.0 + */ +U_CAPI int32_t U_EXPORT2 +u_memcasecmp(const UChar *s1, const UChar *s2, int32_t length, uint32_t options); + +/** + * Copy a ustring. Adds a null terminator. + * + * @param dst The destination string. + * @param src The source string. + * @return A pointer to dst. + * @stable ICU 2.0 + */ +U_CAPI UChar* U_EXPORT2 +u_strcpy(UChar *dst, + const UChar *src); + +/** + * Copy a ustring. + * Copies at most n characters. The result will be null terminated + * if the length of src is less than n. + * + * @param dst The destination string. + * @param src The source string (can be NULL/invalid if n<=0). + * @param n The maximum number of characters to copy; no-op if <=0. + * @return A pointer to dst. + * @stable ICU 2.0 + */ +U_CAPI UChar* U_EXPORT2 +u_strncpy(UChar *dst, + const UChar *src, + int32_t n); + + +/** + * Synonym for memcpy(), but with UChars only. + * @param dest The destination string + * @param src The source string (can be NULL/invalid if count<=0) + * @param count The number of characters to copy; no-op if <=0 + * @return A pointer to dest + * @stable ICU 2.0 + */ +U_CAPI UChar* U_EXPORT2 +u_memcpy(UChar *dest, const UChar *src, int32_t count); + +/** + * Synonym for memmove(), but with UChars only. + * @param dest The destination string + * @param src The source string (can be NULL/invalid if count<=0) + * @param count The number of characters to move; no-op if <=0 + * @return A pointer to dest + * @stable ICU 2.0 + */ +U_CAPI UChar* U_EXPORT2 +u_memmove(UChar *dest, const UChar *src, int32_t count); + +/** + * Initialize count characters of dest to c. + * + * @param dest The destination string. + * @param c The character to initialize the string. + * @param count The maximum number of characters to set. + * @return A pointer to dest. + * @stable ICU 2.0 + */ +U_CAPI UChar* U_EXPORT2 +u_memset(UChar *dest, UChar c, int32_t count); + +/** + * Compare the first count UChars of each buffer. + * + * @param buf1 The first string to compare. + * @param buf2 The second string to compare. + * @param count The maximum number of UChars to compare. + * @return When buf1 < buf2, a negative number is returned. + * When buf1 == buf2, 0 is returned. + * When buf1 > buf2, a positive number is returned. + * @stable ICU 2.0 + */ +U_CAPI int32_t U_EXPORT2 +u_memcmp(const UChar *buf1, const UChar *buf2, int32_t count); + +/** + * Compare two Unicode strings in code point order. + * This is different in UTF-16 from u_memcmp() if supplementary characters are present. + * For details, see u_strCompare(). + * + * @param s1 A string to compare. + * @param s2 A string to compare. + * @param count The maximum number of characters to compare. + * @return a negative/zero/positive integer corresponding to whether + * the first string is less than/equal to/greater than the second one + * in code point order + * @stable ICU 2.0 + */ +U_CAPI int32_t U_EXPORT2 +u_memcmpCodePointOrder(const UChar *s1, const UChar *s2, int32_t count); + +/** + * Find the first occurrence of a BMP code point in a string. + * A surrogate code point is found only if its match in the text is not + * part of a surrogate pair. + * A NUL character is found at the string terminator. + * + * @param s The string to search (contains count UChars). + * @param c The BMP code point to find. + * @param count The length of the string. + * @return A pointer to the first occurrence of c in s + * or NULL if c is not in s. + * @stable ICU 2.0 + * + * @see u_strchr + * @see u_memchr32 + * @see u_strFindFirst + */ +U_CAPI UChar* U_EXPORT2 +u_memchr(const UChar *s, UChar c, int32_t count); + +/** + * Find the first occurrence of a code point in a string. + * A surrogate code point is found only if its match in the text is not + * part of a surrogate pair. + * A NUL character is found at the string terminator. + * + * @param s The string to search (contains count UChars). + * @param c The code point to find. + * @param count The length of the string. + * @return A pointer to the first occurrence of c in s + * or NULL if c is not in s. + * @stable ICU 2.0 + * + * @see u_strchr32 + * @see u_memchr + * @see u_strFindFirst + */ +U_CAPI UChar* U_EXPORT2 +u_memchr32(const UChar *s, UChar32 c, int32_t count); + +/** + * Find the last occurrence of a BMP code point in a string. + * A surrogate code point is found only if its match in the text is not + * part of a surrogate pair. + * A NUL character is found at the string terminator. + * + * @param s The string to search (contains count UChars). + * @param c The BMP code point to find. + * @param count The length of the string. + * @return A pointer to the last occurrence of c in s + * or NULL if c is not in s. + * @stable ICU 2.4 + * + * @see u_strrchr + * @see u_memrchr32 + * @see u_strFindLast + */ +U_CAPI UChar* U_EXPORT2 +u_memrchr(const UChar *s, UChar c, int32_t count); + +/** + * Find the last occurrence of a code point in a string. + * A surrogate code point is found only if its match in the text is not + * part of a surrogate pair. + * A NUL character is found at the string terminator. + * + * @param s The string to search (contains count UChars). + * @param c The code point to find. + * @param count The length of the string. + * @return A pointer to the last occurrence of c in s + * or NULL if c is not in s. + * @stable ICU 2.4 + * + * @see u_strrchr32 + * @see u_memrchr + * @see u_strFindLast + */ +U_CAPI UChar* U_EXPORT2 +u_memrchr32(const UChar *s, UChar32 c, int32_t count); + +/** + * Unicode String literals in C. + * We need one macro to declare a variable for the string + * and to statically preinitialize it if possible, + * and a second macro to dynamically initialize such a string variable if necessary. + * + * The macros are defined for maximum performance. + * They work only for strings that contain "invariant characters", i.e., + * only latin letters, digits, and some punctuation. + * See utypes.h for details. + * + * A pair of macros for a single string must be used with the same + * parameters. + * The string parameter must be a C string literal. + * The length of the string, not including the terminating + * `NUL`, must be specified as a constant. + * The U_STRING_DECL macro should be invoked exactly once for one + * such string variable before it is used. + * + * Usage: + * + * U_STRING_DECL(ustringVar1, "Quick-Fox 2", 11); + * U_STRING_DECL(ustringVar2, "jumps 5%", 8); + * static UBool didInit=false; + * + * int32_t function() { + * if(!didInit) { + * U_STRING_INIT(ustringVar1, "Quick-Fox 2", 11); + * U_STRING_INIT(ustringVar2, "jumps 5%", 8); + * didInit=true; + * } + * return u_strcmp(ustringVar1, ustringVar2); + * } + * + * Note that the macros will NOT consistently work if their argument is another #`define`. + * The following will not work on all platforms, don't use it. + * + * #define GLUCK "Mr. Gluck" + * U_STRING_DECL(var, GLUCK, 9) + * U_STRING_INIT(var, GLUCK, 9) + * + * Instead, use the string literal "Mr. Gluck" as the argument to both macro + * calls. + * + * + * @stable ICU 2.0 + */ +#if defined(U_DECLARE_UTF16) +# define U_STRING_DECL(var, cs, length) static const UChar *var=(const UChar *)U_DECLARE_UTF16(cs) + /**@stable ICU 2.0 */ +# define U_STRING_INIT(var, cs, length) +#elif U_SIZEOF_WCHAR_T==U_SIZEOF_UCHAR && (U_CHARSET_FAMILY==U_ASCII_FAMILY || (U_SIZEOF_UCHAR == 2 && defined(U_WCHAR_IS_UTF16))) +# define U_STRING_DECL(var, cs, length) static const UChar var[(length)+1]=L ## cs + /**@stable ICU 2.0 */ +# define U_STRING_INIT(var, cs, length) +#elif U_SIZEOF_UCHAR==1 && U_CHARSET_FAMILY==U_ASCII_FAMILY +# define U_STRING_DECL(var, cs, length) static const UChar var[(length)+1]=cs + /**@stable ICU 2.0 */ +# define U_STRING_INIT(var, cs, length) +#else +# define U_STRING_DECL(var, cs, length) static UChar var[(length)+1] + /**@stable ICU 2.0 */ +# define U_STRING_INIT(var, cs, length) u_charsToUChars(cs, var, length+1) +#endif + + +/** + * Uppercase the characters in a string. + * Casing is locale-dependent and context-sensitive. + * The result may be longer or shorter than the original. + * The source string and the destination buffer are allowed to overlap. + * + * @param dest A buffer for the result string. The result will be zero-terminated if + * the buffer is large enough. + * @param destCapacity The size of the buffer (number of UChars). If it is 0, then + * dest may be NULL and the function will only return the length of the result + * without writing any of the result string. + * @param src The original string + * @param srcLength The length of the original string. If -1, then src must be zero-terminated. + * @param locale The locale to consider, or "" for the root locale or NULL for the default locale. + * @param pErrorCode Must be a valid pointer to an error code value, + * which must not indicate a failure before the function call. + * @return The length of the result string. It may be greater than destCapacity. In that case, + * only some of the result was written to the destination buffer. + * @stable ICU 2.0 + */ +U_CAPI int32_t U_EXPORT2 +u_strToUpper(UChar *dest, int32_t destCapacity, + const UChar *src, int32_t srcLength, + const char *locale, + UErrorCode *pErrorCode); + +/** + * Lowercase the characters in a string. + * Casing is locale-dependent and context-sensitive. + * The result may be longer or shorter than the original. + * The source string and the destination buffer are allowed to overlap. + * + * @param dest A buffer for the result string. The result will be zero-terminated if + * the buffer is large enough. + * @param destCapacity The size of the buffer (number of UChars). If it is 0, then + * dest may be NULL and the function will only return the length of the result + * without writing any of the result string. + * @param src The original string + * @param srcLength The length of the original string. If -1, then src must be zero-terminated. + * @param locale The locale to consider, or "" for the root locale or NULL for the default locale. + * @param pErrorCode Must be a valid pointer to an error code value, + * which must not indicate a failure before the function call. + * @return The length of the result string. It may be greater than destCapacity. In that case, + * only some of the result was written to the destination buffer. + * @stable ICU 2.0 + */ +U_CAPI int32_t U_EXPORT2 +u_strToLower(UChar *dest, int32_t destCapacity, + const UChar *src, int32_t srcLength, + const char *locale, + UErrorCode *pErrorCode); + +#if !UCONFIG_NO_BREAK_ITERATION + +/** + * Titlecase a string. + * Casing is locale-dependent and context-sensitive. + * Titlecasing uses a break iterator to find the first characters of words + * that are to be titlecased. It titlecases those characters and lowercases + * all others. + * + * The titlecase break iterator can be provided to customize for arbitrary + * styles, using rules and dictionaries beyond the standard iterators. + * It may be more efficient to always provide an iterator to avoid + * opening and closing one for each string. + * The standard titlecase iterator for the root locale implements the + * algorithm of Unicode TR 21. + * + * This function uses only the setText(), first() and next() methods of the + * provided break iterator. + * + * The result may be longer or shorter than the original. + * The source string and the destination buffer are allowed to overlap. + * + * @param dest A buffer for the result string. The result will be zero-terminated if + * the buffer is large enough. + * @param destCapacity The size of the buffer (number of UChars). If it is 0, then + * dest may be NULL and the function will only return the length of the result + * without writing any of the result string. + * @param src The original string + * @param srcLength The length of the original string. If -1, then src must be zero-terminated. + * @param titleIter A break iterator to find the first characters of words + * that are to be titlecased. + * If none is provided (NULL), then a standard titlecase + * break iterator is opened. + * @param locale The locale to consider, or "" for the root locale or NULL for the default locale. + * @param pErrorCode Must be a valid pointer to an error code value, + * which must not indicate a failure before the function call. + * @return The length of the result string. It may be greater than destCapacity. In that case, + * only some of the result was written to the destination buffer. + * @stable ICU 2.1 + */ +U_CAPI int32_t U_EXPORT2 +u_strToTitle(UChar *dest, int32_t destCapacity, + const UChar *src, int32_t srcLength, + UBreakIterator *titleIter, + const char *locale, + UErrorCode *pErrorCode); + +#endif + +/** + * Case-folds the characters in a string. + * + * Case-folding is locale-independent and not context-sensitive, + * but there is an option for whether to include or exclude mappings for dotted I + * and dotless i that are marked with 'T' in CaseFolding.txt. + * + * The result may be longer or shorter than the original. + * The source string and the destination buffer are allowed to overlap. + * + * @param dest A buffer for the result string. The result will be zero-terminated if + * the buffer is large enough. + * @param destCapacity The size of the buffer (number of UChars). If it is 0, then + * dest may be NULL and the function will only return the length of the result + * without writing any of the result string. + * @param src The original string + * @param srcLength The length of the original string. If -1, then src must be zero-terminated. + * @param options Either U_FOLD_CASE_DEFAULT or U_FOLD_CASE_EXCLUDE_SPECIAL_I + * @param pErrorCode Must be a valid pointer to an error code value, + * which must not indicate a failure before the function call. + * @return The length of the result string. It may be greater than destCapacity. In that case, + * only some of the result was written to the destination buffer. + * @stable ICU 2.0 + */ +U_CAPI int32_t U_EXPORT2 +u_strFoldCase(UChar *dest, int32_t destCapacity, + const UChar *src, int32_t srcLength, + uint32_t options, + UErrorCode *pErrorCode); + + +/** + * Convert a UTF-16 string to UTF-8. + * If the input string is not well-formed, then the U_INVALID_CHAR_FOUND error code is set. + * + * @param dest A buffer for the result string. The result will be zero-terminated if + * the buffer is large enough. + * @param destCapacity The size of the buffer (number of chars). If it is 0, then + * dest may be NULL and the function will only return the length of the + * result without writing any of the result string (pre-flighting). + * @param pDestLength A pointer to receive the number of units written to the destination. If + * pDestLength!=NULL then *pDestLength is always set to the + * number of output units corresponding to the transformation of + * all the input units, even in case of a buffer overflow. + * @param src The original source string + * @param srcLength The length of the original string. If -1, then src must be zero-terminated. + * @param pErrorCode Must be a valid pointer to an error code value, + * which must not indicate a failure before the function call. + * @return The pointer to destination buffer. + * @stable ICU 2.0 + * @see u_strToUTF8WithSub + * @see u_strFromUTF8 + */ +U_CAPI char* U_EXPORT2 +u_strToUTF8(char *dest, + int32_t destCapacity, + int32_t *pDestLength, + const UChar *src, + int32_t srcLength, + UErrorCode *pErrorCode); + +/** + * Convert a UTF-8 string to UTF-16. + * If the input string is not well-formed, then the U_INVALID_CHAR_FOUND error code is set. + * + * @param dest A buffer for the result string. The result will be zero-terminated if + * the buffer is large enough. + * @param destCapacity The size of the buffer (number of UChars). If it is 0, then + * dest may be NULL and the function will only return the length of the + * result without writing any of the result string (pre-flighting). + * @param pDestLength A pointer to receive the number of units written to the destination. If + * pDestLength!=NULL then *pDestLength is always set to the + * number of output units corresponding to the transformation of + * all the input units, even in case of a buffer overflow. + * @param src The original source string + * @param srcLength The length of the original string. If -1, then src must be zero-terminated. + * @param pErrorCode Must be a valid pointer to an error code value, + * which must not indicate a failure before the function call. + * @return The pointer to destination buffer. + * @stable ICU 2.0 + * @see u_strFromUTF8WithSub + * @see u_strFromUTF8Lenient + */ +U_CAPI UChar* U_EXPORT2 +u_strFromUTF8(UChar *dest, + int32_t destCapacity, + int32_t *pDestLength, + const char *src, + int32_t srcLength, + UErrorCode *pErrorCode); + +/** + * Convert a UTF-16 string to UTF-8. + * + * Same as u_strToUTF8() except for the additional subchar which is output for + * illegal input sequences, instead of stopping with the U_INVALID_CHAR_FOUND error code. + * With subchar==U_SENTINEL, this function behaves exactly like u_strToUTF8(). + * + * @param dest A buffer for the result string. The result will be zero-terminated if + * the buffer is large enough. + * @param destCapacity The size of the buffer (number of chars). If it is 0, then + * dest may be NULL and the function will only return the length of the + * result without writing any of the result string (pre-flighting). + * @param pDestLength A pointer to receive the number of units written to the destination. If + * pDestLength!=NULL then *pDestLength is always set to the + * number of output units corresponding to the transformation of + * all the input units, even in case of a buffer overflow. + * @param src The original source string + * @param srcLength The length of the original string. If -1, then src must be zero-terminated. + * @param subchar The substitution character to use in place of an illegal input sequence, + * or U_SENTINEL if the function is to return with U_INVALID_CHAR_FOUND instead. + * A substitution character can be any valid Unicode code point (up to U+10FFFF) + * except for surrogate code points (U+D800..U+DFFF). + * The recommended value is U+FFFD "REPLACEMENT CHARACTER". + * @param pNumSubstitutions Output parameter receiving the number of substitutions if subchar>=0. + * Set to 0 if no substitutions occur or subchar<0. + * pNumSubstitutions can be NULL. + * @param pErrorCode Pointer to a standard ICU error code. Its input value must + * pass the U_SUCCESS() test, or else the function returns + * immediately. Check for U_FAILURE() on output or use with + * function chaining. (See User Guide for details.) + * @return The pointer to destination buffer. + * @see u_strToUTF8 + * @see u_strFromUTF8WithSub + * @stable ICU 3.6 + */ +U_CAPI char* U_EXPORT2 +u_strToUTF8WithSub(char *dest, + int32_t destCapacity, + int32_t *pDestLength, + const UChar *src, + int32_t srcLength, + UChar32 subchar, int32_t *pNumSubstitutions, + UErrorCode *pErrorCode); + +/** + * Convert a UTF-8 string to UTF-16. + * + * Same as u_strFromUTF8() except for the additional subchar which is output for + * illegal input sequences, instead of stopping with the U_INVALID_CHAR_FOUND error code. + * With subchar==U_SENTINEL, this function behaves exactly like u_strFromUTF8(). + * + * @param dest A buffer for the result string. The result will be zero-terminated if + * the buffer is large enough. + * @param destCapacity The size of the buffer (number of UChars). If it is 0, then + * dest may be NULL and the function will only return the length of the + * result without writing any of the result string (pre-flighting). + * @param pDestLength A pointer to receive the number of units written to the destination. If + * pDestLength!=NULL then *pDestLength is always set to the + * number of output units corresponding to the transformation of + * all the input units, even in case of a buffer overflow. + * @param src The original source string + * @param srcLength The length of the original string. If -1, then src must be zero-terminated. + * @param subchar The substitution character to use in place of an illegal input sequence, + * or U_SENTINEL if the function is to return with U_INVALID_CHAR_FOUND instead. + * A substitution character can be any valid Unicode code point (up to U+10FFFF) + * except for surrogate code points (U+D800..U+DFFF). + * The recommended value is U+FFFD "REPLACEMENT CHARACTER". + * @param pNumSubstitutions Output parameter receiving the number of substitutions if subchar>=0. + * Set to 0 if no substitutions occur or subchar<0. + * pNumSubstitutions can be NULL. + * @param pErrorCode Pointer to a standard ICU error code. Its input value must + * pass the U_SUCCESS() test, or else the function returns + * immediately. Check for U_FAILURE() on output or use with + * function chaining. (See User Guide for details.) + * @return The pointer to destination buffer. + * @see u_strFromUTF8 + * @see u_strFromUTF8Lenient + * @see u_strToUTF8WithSub + * @stable ICU 3.6 + */ +U_CAPI UChar* U_EXPORT2 +u_strFromUTF8WithSub(UChar *dest, + int32_t destCapacity, + int32_t *pDestLength, + const char *src, + int32_t srcLength, + UChar32 subchar, int32_t *pNumSubstitutions, + UErrorCode *pErrorCode); + +/** + * Convert a UTF-8 string to UTF-16. + * + * Same as u_strFromUTF8() except that this function is designed to be very fast, + * which it achieves by being lenient about malformed UTF-8 sequences. + * This function is intended for use in environments where UTF-8 text is + * expected to be well-formed. + * + * Its semantics are: + * - Well-formed UTF-8 text is correctly converted to well-formed UTF-16 text. + * - The function will not read beyond the input string, nor write beyond + * the destCapacity. + * - Malformed UTF-8 results in "garbage" 16-bit Unicode strings which may not + * be well-formed UTF-16. + * The function will resynchronize to valid code point boundaries + * within a small number of code points after an illegal sequence. + * - Non-shortest forms are not detected and will result in "spoofing" output. + * + * For further performance improvement, if srcLength is given (>=0), + * then it must be destCapacity>=srcLength. + * + * There is no inverse u_strToUTF8Lenient() function because there is practically + * no performance gain from not checking that a UTF-16 string is well-formed. + * + * @param dest A buffer for the result string. The result will be zero-terminated if + * the buffer is large enough. + * @param destCapacity The size of the buffer (number of UChars). If it is 0, then + * dest may be NULL and the function will only return the length of the + * result without writing any of the result string (pre-flighting). + * Unlike for other ICU functions, if srcLength>=0 then it + * must be destCapacity>=srcLength. + * @param pDestLength A pointer to receive the number of units written to the destination. If + * pDestLength!=NULL then *pDestLength is always set to the + * number of output units corresponding to the transformation of + * all the input units, even in case of a buffer overflow. + * Unlike for other ICU functions, if srcLength>=0 but + * destCapacity=0. + * Set to 0 if no substitutions occur or subchar<0. + * pNumSubstitutions can be NULL. + * @param pErrorCode Pointer to a standard ICU error code. Its input value must + * pass the U_SUCCESS() test, or else the function returns + * immediately. Check for U_FAILURE() on output or use with + * function chaining. (See User Guide for details.) + * @return The pointer to destination buffer. + * @see u_strToUTF32 + * @see u_strFromUTF32WithSub + * @stable ICU 4.2 + */ +U_CAPI UChar32* U_EXPORT2 +u_strToUTF32WithSub(UChar32 *dest, + int32_t destCapacity, + int32_t *pDestLength, + const UChar *src, + int32_t srcLength, + UChar32 subchar, int32_t *pNumSubstitutions, + UErrorCode *pErrorCode); + +/** + * Convert a UTF-32 string to UTF-16. + * + * Same as u_strFromUTF32() except for the additional subchar which is output for + * illegal input sequences, instead of stopping with the U_INVALID_CHAR_FOUND error code. + * With subchar==U_SENTINEL, this function behaves exactly like u_strFromUTF32(). + * + * @param dest A buffer for the result string. The result will be zero-terminated if + * the buffer is large enough. + * @param destCapacity The size of the buffer (number of UChars). If it is 0, then + * dest may be NULL and the function will only return the length of the + * result without writing any of the result string (pre-flighting). + * @param pDestLength A pointer to receive the number of units written to the destination. If + * pDestLength!=NULL then *pDestLength is always set to the + * number of output units corresponding to the transformation of + * all the input units, even in case of a buffer overflow. + * @param src The original source string + * @param srcLength The length of the original string. If -1, then src must be zero-terminated. + * @param subchar The substitution character to use in place of an illegal input sequence, + * or U_SENTINEL if the function is to return with U_INVALID_CHAR_FOUND instead. + * A substitution character can be any valid Unicode code point (up to U+10FFFF) + * except for surrogate code points (U+D800..U+DFFF). + * The recommended value is U+FFFD "REPLACEMENT CHARACTER". + * @param pNumSubstitutions Output parameter receiving the number of substitutions if subchar>=0. + * Set to 0 if no substitutions occur or subchar<0. + * pNumSubstitutions can be NULL. + * @param pErrorCode Pointer to a standard ICU error code. Its input value must + * pass the U_SUCCESS() test, or else the function returns + * immediately. Check for U_FAILURE() on output or use with + * function chaining. (See User Guide for details.) + * @return The pointer to destination buffer. + * @see u_strFromUTF32 + * @see u_strToUTF32WithSub + * @stable ICU 4.2 + */ +U_CAPI UChar* U_EXPORT2 +u_strFromUTF32WithSub(UChar *dest, + int32_t destCapacity, + int32_t *pDestLength, + const UChar32 *src, + int32_t srcLength, + UChar32 subchar, int32_t *pNumSubstitutions, + UErrorCode *pErrorCode); + + +#endif diff --git a/third_party/icu4c/ndk_headers/unicode/utext.h b/third_party/icu4c/ndk_headers/unicode/utext.h new file mode 100644 index 000000000..66e557ccf --- /dev/null +++ b/third_party/icu4c/ndk_headers/unicode/utext.h @@ -0,0 +1,582 @@ +// © 2016 and later: Unicode, Inc. and others. +// License & terms of use: http://www.unicode.org/copyright.html +/* +******************************************************************************* +* +* Copyright (C) 2004-2012, International Business Machines +* Corporation and others. All Rights Reserved. +* +******************************************************************************* +* file name: utext.h +* encoding: UTF-8 +* tab size: 8 (not used) +* indentation:4 +* +* created on: 2004oct06 +* created by: Markus W. Scherer +*/ + +#ifndef __UTEXT_H__ +#define __UTEXT_H__ + +/** + * \file + * \brief C API: Abstract Unicode Text API + * + * The Text Access API provides a means to allow text that is stored in alternative + * formats to work with ICU services. ICU normally operates on text that is + * stored in UTF-16 format, in (UChar *) arrays for the C APIs or as type + * UnicodeString for C++ APIs. + * + * ICU Text Access allows other formats, such as UTF-8 or non-contiguous + * UTF-16 strings, to be placed in a UText wrapper and then passed to ICU services. + * + * There are three general classes of usage for UText: + * + * Application Level Use. This is the simplest usage - applications would + * use one of the utext_open() functions on their input text, and pass + * the resulting UText to the desired ICU service. + * + * Second is usage in ICU Services, such as break iteration, that will need to + * operate on input presented to them as a UText. These implementations + * will need to use the iteration and related UText functions to gain + * access to the actual text. + * + * The third class of UText users are "text providers." These are the + * UText implementations for the various text storage formats. An application + * or system with a unique text storage format can implement a set of + * UText provider functions for that format, which will then allow + * ICU services to operate on that format. + * + * + * Iterating over text + * + * Here is sample code for a forward iteration over the contents of a UText + * + * \code + * UChar32 c; + * UText *ut = whatever(); + * + * for (c=utext_next32From(ut, 0); c>=0; c=utext_next32(ut)) { + * // do whatever with the codepoint c here. + * } + * \endcode + * + * And here is similar code to iterate in the reverse direction, from the end + * of the text towards the beginning. + * + * \code + * UChar32 c; + * UText *ut = whatever(); + * int textLength = utext_nativeLength(ut); + * for (c=utext_previous32From(ut, textLength); c>=0; c=utext_previous32(ut)) { + * // do whatever with the codepoint c here. + * } + * \endcode + * + * Characters and Indexing + * + * Indexing into text by UText functions is nearly always in terms of the native + * indexing of the underlying text storage. The storage format could be UTF-8 + * or UTF-32, for example. When coding to the UText access API, no assumptions + * can be made regarding the size of characters, or how far an index + * may move when iterating between characters. + * + * All indices supplied to UText functions are pinned to the length of the + * text. An out-of-bounds index is not considered to be an error, but is + * adjusted to be in the range 0 <= index <= length of input text. + * + * + * When an index position is returned from a UText function, it will be + * a native index to the underlying text. In the case of multi-unit characters, + * it will always refer to the first position of the character, + * never to the interior. This is essentially the same thing as saying that + * a returned index will always point to a boundary between characters. + * + * When a native index is supplied to a UText function, all indices that + * refer to any part of a multi-unit character representation are considered + * to be equivalent. In the case of multi-unit characters, an incoming index + * will be logically normalized to refer to the start of the character. + * + * It is possible to test whether a native index is on a code point boundary + * by doing a utext_setNativeIndex() followed by a utext_getNativeIndex(). + * If the index is returned unchanged, it was on a code point boundary. If + * an adjusted index is returned, the original index referred to the + * interior of a character. + * + * Conventions for calling UText functions + * + * Most UText access functions have as their first parameter a (UText *) pointer, + * which specifies the UText to be used. Unless otherwise noted, the + * pointer must refer to a valid, open UText. Attempting to + * use a closed UText or passing a NULL pointer is a programming error and + * will produce undefined results or NULL pointer exceptions. + * + * The UText_Open family of functions can either open an existing (closed) + * UText, or heap allocate a new UText. Here is sample code for creating + * a stack-allocated UText. + * + * \code + * char *s = whatever(); // A utf-8 string + * U_ErrorCode status = U_ZERO_ERROR; + * UText ut = UTEXT_INITIALIZER; + * utext_openUTF8(ut, s, -1, &status); + * if (U_FAILURE(status)) { + * // error handling + * } else { + * // work with the UText + * } + * \endcode + * + * Any existing UText passed to an open function _must_ have been initialized, + * either by the UTEXT_INITIALIZER, or by having been originally heap-allocated + * by an open function. Passing NULL will cause the open function to + * heap-allocate and fully initialize a new UText. + * + */ + + + +#include "unicode/utypes.h" +#include "unicode/uchar.h" +#if U_SHOW_CPLUSPLUS_API +#include "unicode/localpointer.h" +#include "unicode/rep.h" +#include "unicode/unistr.h" +#include "unicode/chariter.h" +#endif + + +U_CDECL_BEGIN + +struct UText; +typedef struct UText UText; /**< C typedef for struct UText. @stable ICU 3.6 */ + + +/*************************************************************************************** + * + * C Functions for creating UText wrappers around various kinds of text strings. + * + ****************************************************************************************/ + + +/** + * Close function for UText instances. + * Cleans up, releases any resources being held by an open UText. + *

+ * If the UText was originally allocated by one of the utext_open functions, + * the storage associated with the utext will also be freed. + * If the UText storage originated with the application, as it would with + * a local or static instance, the storage will not be deleted. + * + * An open UText can be reset to refer to new string by using one of the utext_open() + * functions without first closing the UText. + * + * @param ut The UText to be closed. + * @return NULL if the UText struct was deleted by the close. If the UText struct + * was originally provided by the caller to the open function, it is + * returned by this function, and may be safely used again in + * a subsequent utext_open. + * + * @stable ICU 3.4 + */ +U_CAPI UText * U_EXPORT2 +utext_close(UText *ut); + +/** + * Open a read-only UText implementation for UTF-8 strings. + * + * \htmlonly + * Any invalid UTF-8 in the input will be handled in this way: + * a sequence of bytes that has the form of a truncated, but otherwise valid, + * UTF-8 sequence will be replaced by a single unicode replacement character, \uFFFD. + * Any other illegal bytes will each be replaced by a \uFFFD. + * \endhtmlonly + * + * @param ut Pointer to a UText struct. If NULL, a new UText will be created. + * If non-NULL, must refer to an initialized UText struct, which will then + * be reset to reference the specified UTF-8 string. + * @param s A UTF-8 string. Must not be NULL. + * @param length The length of the UTF-8 string in bytes, or -1 if the string is + * zero terminated. + * @param status Errors are returned here. + * @return A pointer to the UText. If a pre-allocated UText was provided, it + * will always be used and returned. + * @stable ICU 3.4 + */ +U_CAPI UText * U_EXPORT2 +utext_openUTF8(UText *ut, const char *s, int64_t length, UErrorCode *status); + + +/** + * Open a read-only UText for UChar * string. + * + * @param ut Pointer to a UText struct. If NULL, a new UText will be created. + * If non-NULL, must refer to an initialized UText struct, which will then + * be reset to reference the specified UChar string. + * @param s A UChar (UTF-16) string + * @param length The number of UChars in the input string, or -1 if the string is + * zero terminated. + * @param status Errors are returned here. + * @return A pointer to the UText. If a pre-allocated UText was provided, it + * will always be used and returned. + * @stable ICU 3.4 + */ +U_CAPI UText * U_EXPORT2 +utext_openUChars(UText *ut, const UChar *s, int64_t length, UErrorCode *status); + + +/** + * Clone a UText. This is much like opening a UText where the source text is itself + * another UText. + * + * A deep clone will copy both the UText data structures and the underlying text. + * The original and cloned UText will operate completely independently; modifications + * made to the text in one will not affect the other. Text providers are not + * required to support deep clones. The user of clone() must check the status return + * and be prepared to handle failures. + * + * The standard UText implementations for UTF8, UChar *, UnicodeString and + * Replaceable all support deep cloning. + * + * The UText returned from a deep clone will be writable, assuming that the text + * provider is able to support writing, even if the source UText had been made + * non-writable by means of UText_freeze(). + * + * A shallow clone replicates only the UText data structures; it does not make + * a copy of the underlying text. Shallow clones can be used as an efficient way to + * have multiple iterators active in a single text string that is not being + * modified. + * + * A shallow clone operation will not fail, barring truly exceptional conditions such + * as memory allocation failures. + * + * Shallow UText clones should be avoided if the UText functions that modify the + * text are expected to be used, either on the original or the cloned UText. + * Any such modifications can cause unpredictable behavior. Read Only + * shallow clones provide some protection against errors of this type by + * disabling text modification via the cloned UText. + * + * A shallow clone made with the readOnly parameter == false will preserve the + * utext_isWritable() state of the source object. Note, however, that + * write operations must be avoided while more than one UText exists that refer + * to the same underlying text. + * + * A UText and its clone may be safely concurrently accessed by separate threads. + * This is true for read access only with shallow clones, and for both read and + * write access with deep clones. + * It is the responsibility of the Text Provider to ensure that this thread safety + * constraint is met. + * + * @param dest A UText struct to be filled in with the result of the clone operation, + * or NULL if the clone function should heap-allocate a new UText struct. + * If non-NULL, must refer to an already existing UText, which will then + * be reset to become the clone. + * @param src The UText to be cloned. + * @param deep true to request a deep clone, false for a shallow clone. + * @param readOnly true to request that the cloned UText have read only access to the + * underlying text. + + * @param status Errors are returned here. For deep clones, U_UNSUPPORTED_ERROR + * will be returned if the text provider is unable to clone the + * original text. + * @return The newly created clone, or NULL if the clone operation failed. + * @stable ICU 3.4 + */ +U_CAPI UText * U_EXPORT2 +utext_clone(UText *dest, const UText *src, UBool deep, UBool readOnly, UErrorCode *status); + + +/** + * Compare two UText objects for equality. + * UTexts are equal if they are iterating over the same text, and + * have the same iteration position within the text. + * If either or both of the parameters are NULL, the comparison is false. + * + * @param a The first of the two UTexts to compare. + * @param b The other UText to be compared. + * @return true if the two UTexts are equal. + * @stable ICU 3.6 + */ +U_CAPI UBool U_EXPORT2 +utext_equals(const UText *a, const UText *b); + + +/***************************************************************************** + * + * Functions to work with the text represented by a UText wrapper + * + *****************************************************************************/ + +/** + * Get the length of the text. Depending on the characteristics + * of the underlying text representation, this may be expensive. + * @see utext_isLengthExpensive() + * + * + * @param ut the text to be accessed. + * @return the length of the text, expressed in native units. + * + * @stable ICU 3.4 + */ +U_CAPI int64_t U_EXPORT2 +utext_nativeLength(UText *ut); + +/** + * Returns the code point at the requested index, + * or U_SENTINEL (-1) if it is out of bounds. + * + * If the specified index points to the interior of a multi-unit + * character - one of the trail bytes of a UTF-8 sequence, for example - + * the complete code point will be returned. + * + * The iteration position will be set to the start of the returned code point. + * + * This function is roughly equivalent to the sequence + * utext_setNativeIndex(index); + * utext_current32(); + * (There is a subtle difference if the index is out of bounds by being less than zero - + * utext_setNativeIndex(negative value) sets the index to zero, after which utext_current() + * will return the char at zero. utext_char32At(negative index), on the other hand, will + * return the U_SENTINEL value of -1.) + * + * @param ut the text to be accessed + * @param nativeIndex the native index of the character to be accessed. If the index points + * to other than the first unit of a multi-unit character, it will be adjusted + * to the start of the character. + * @return the code point at the specified index. + * @stable ICU 3.4 + */ +U_CAPI UChar32 U_EXPORT2 +utext_char32At(UText *ut, int64_t nativeIndex); + + +/** + * + * Get the code point at the current iteration position, + * or U_SENTINEL (-1) if the iteration has reached the end of + * the input text. + * + * @param ut the text to be accessed. + * @return the Unicode code point at the current iterator position. + * @stable ICU 3.4 + */ +U_CAPI UChar32 U_EXPORT2 +utext_current32(UText *ut); + + +/** + * Get the code point at the current iteration position of the UText, and + * advance the position to the first index following the character. + * + * If the position is at the end of the text (the index following + * the last character, which is also the length of the text), + * return U_SENTINEL (-1) and do not advance the index. + * + * This is a post-increment operation. + * + * An inline macro version of this function, UTEXT_NEXT32(), + * is available for performance critical use. + * + * @param ut the text to be accessed. + * @return the Unicode code point at the iteration position. + * @see UTEXT_NEXT32 + * @stable ICU 3.4 + */ +U_CAPI UChar32 U_EXPORT2 +utext_next32(UText *ut); + + +/** + * Move the iterator position to the character (code point) whose + * index precedes the current position, and return that character. + * This is a pre-decrement operation. + * + * If the initial position is at the start of the text (index of 0) + * return U_SENTINEL (-1), and leave the position unchanged. + * + * An inline macro version of this function, UTEXT_PREVIOUS32(), + * is available for performance critical use. + * + * @param ut the text to be accessed. + * @return the previous UChar32 code point, or U_SENTINEL (-1) + * if the iteration has reached the start of the text. + * @see UTEXT_PREVIOUS32 + * @stable ICU 3.4 + */ +U_CAPI UChar32 U_EXPORT2 +utext_previous32(UText *ut); + + +/** + * Set the iteration index and return the code point at that index. + * Leave the iteration index at the start of the following code point. + * + * This function is the most efficient and convenient way to + * begin a forward iteration. The results are identical to the those + * from the sequence + * \code + * utext_setIndex(); + * utext_next32(); + * \endcode + * + * @param ut the text to be accessed. + * @param nativeIndex Iteration index, in the native units of the text provider. + * @return Code point which starts at or before index, + * or U_SENTINEL (-1) if it is out of bounds. + * @stable ICU 3.4 + */ +U_CAPI UChar32 U_EXPORT2 +utext_next32From(UText *ut, int64_t nativeIndex); + + + +/** + * Set the iteration index, and return the code point preceding the + * one specified by the initial index. Leave the iteration position + * at the start of the returned code point. + * + * This function is the most efficient and convenient way to + * begin a backwards iteration. + * + * @param ut the text to be accessed. + * @param nativeIndex Iteration index in the native units of the text provider. + * @return Code point preceding the one at the initial index, + * or U_SENTINEL (-1) if it is out of bounds. + * + * @stable ICU 3.4 + */ +U_CAPI UChar32 U_EXPORT2 +utext_previous32From(UText *ut, int64_t nativeIndex); + +/** + * Get the current iterator position, which can range from 0 to + * the length of the text. + * The position is a native index into the input text, in whatever format it + * may have (possibly UTF-8 for example), and may not always be the same as + * the corresponding UChar (UTF-16) index. + * The returned position will always be aligned to a code point boundary. + * + * @param ut the text to be accessed. + * @return the current index position, in the native units of the text provider. + * @stable ICU 3.4 + */ +U_CAPI int64_t U_EXPORT2 +utext_getNativeIndex(const UText *ut); + +/** + * Set the current iteration position to the nearest code point + * boundary at or preceding the specified index. + * The index is in the native units of the original input text. + * If the index is out of range, it will be pinned to be within + * the range of the input text. + *

+ * It will usually be more efficient to begin an iteration + * using the functions utext_next32From() or utext_previous32From() + * rather than setIndex(). + *

+ * Moving the index position to an adjacent character is best done + * with utext_next32(), utext_previous32() or utext_moveIndex32(). + * Attempting to do direct arithmetic on the index position is + * complicated by the fact that the size (in native units) of a + * character depends on the underlying representation of the character + * (UTF-8, UTF-16, UTF-32, arbitrary codepage), and is not + * easily knowable. + * + * @param ut the text to be accessed. + * @param nativeIndex the native unit index of the new iteration position. + * @stable ICU 3.4 + */ +U_CAPI void U_EXPORT2 +utext_setNativeIndex(UText *ut, int64_t nativeIndex); + +/** + * Move the iterator position by delta code points. The number of code points + * is a signed number; a negative delta will move the iterator backwards, + * towards the start of the text. + *

+ * The index is moved by delta code points + * forward or backward, but no further backward than to 0 and + * no further forward than to utext_nativeLength(). + * The resulting index value will be in between 0 and length, inclusive. + * + * @param ut the text to be accessed. + * @param delta the signed number of code points to move the iteration position. + * @return true if the position could be moved the requested number of positions while + * staying within the range [0 - text length]. + * @stable ICU 3.4 + */ +U_CAPI UBool U_EXPORT2 +utext_moveIndex32(UText *ut, int32_t delta); + +/** + * Get the native index of the character preceding the current position. + * If the iteration position is already at the start of the text, zero + * is returned. + * The value returned is the same as that obtained from the following sequence, + * but without the side effect of changing the iteration position. + * + * \code + * UText *ut = whatever; + * ... + * utext_previous(ut) + * utext_getNativeIndex(ut); + * \endcode + * + * This function is most useful during forwards iteration, where it will get the + * native index of the character most recently returned from utext_next(). + * + * @param ut the text to be accessed + * @return the native index of the character preceding the current index position, + * or zero if the current position is at the start of the text. + * @stable ICU 3.6 + */ +U_CAPI int64_t U_EXPORT2 +utext_getPreviousNativeIndex(UText *ut); + + +/** + * + * Extract text from a UText into a UChar buffer. The range of text to be extracted + * is specified in the native indices of the UText provider. These may not necessarily + * be UTF-16 indices. + *

+ * The size (number of 16 bit UChars) of the data to be extracted is returned. The + * full number of UChars is returned, even when the extracted text is truncated + * because the specified buffer size is too small. + *

+ * The extracted string will (if you are a user) / must (if you are a text provider) + * be NUL-terminated if there is sufficient space in the destination buffer. This + * terminating NUL is not included in the returned length. + *

+ * The iteration index is left at the position following the last extracted character. + * + * @param ut the UText from which to extract data. + * @param nativeStart the native index of the first character to extract.\ + * If the specified index is out of range, + * it will be pinned to be within 0 <= index <= textLength + * @param nativeLimit the native string index of the position following the last + * character to extract. If the specified index is out of range, + * it will be pinned to be within 0 <= index <= textLength. + * nativeLimit must be >= nativeStart. + * @param dest the UChar (UTF-16) buffer into which the extracted text is placed + * @param destCapacity The size, in UChars, of the destination buffer. May be zero + * for precomputing the required size. + * @param status receives any error status. + * U_BUFFER_OVERFLOW_ERROR: the extracted text was truncated because the + * buffer was too small. Returns number of UChars for preflighting. + * @return Number of UChars in the data to be extracted. Does not include a trailing NUL. + * + * @stable ICU 3.4 + */ +U_CAPI int32_t U_EXPORT2 +utext_extract(UText *ut, + int64_t nativeStart, int64_t nativeLimit, + UChar *dest, int32_t destCapacity, + UErrorCode *status); + + +U_CDECL_END + + +#endif diff --git a/third_party/icu4c/ndk_headers/unicode/utypes.h b/third_party/icu4c/ndk_headers/unicode/utypes.h index 5f6cac32a..8293ca70e 100644 --- a/third_party/icu4c/ndk_headers/unicode/utypes.h +++ b/third_party/icu4c/ndk_headers/unicode/utypes.h @@ -637,5 +637,13 @@ typedef enum UErrorCode { # define U_FAILURE(x) ((x)>U_ZERO_ERROR) #endif +/** + * Return a string for a UErrorCode value. + * The string will be the same as the name of the error code constant + * in the UErrorCode enum above. + * @stable ICU 2.0 + */ +U_CAPI const char * U_EXPORT2 +u_errorName(UErrorCode code); #endif /* _UTYPES */ -- Gitee