Return-Path: X-Original-To: apmail-couchdb-commits-archive@www.apache.org Delivered-To: apmail-couchdb-commits-archive@www.apache.org Received: from mail.apache.org (hermes.apache.org [140.211.11.3]) by minotaur.apache.org (Postfix) with SMTP id CA5EA10982 for ; Thu, 6 Feb 2014 17:30:28 +0000 (UTC) Received: (qmail 12641 invoked by uid 500); 6 Feb 2014 17:28:34 -0000 Delivered-To: apmail-couchdb-commits-archive@couchdb.apache.org Received: (qmail 11711 invoked by uid 500); 6 Feb 2014 17:28:07 -0000 Mailing-List: contact commits-help@couchdb.apache.org; run by ezmlm Precedence: bulk List-Help: List-Unsubscribe: List-Post: List-Id: Reply-To: dev@couchdb.apache.org Delivered-To: mailing list commits@couchdb.apache.org Received: (qmail 10773 invoked by uid 99); 6 Feb 2014 17:27:44 -0000 Received: from tyr.zones.apache.org (HELO tyr.zones.apache.org) (140.211.11.114) by apache.org (qpsmtpd/0.29) with ESMTP; Thu, 06 Feb 2014 17:27:44 +0000 Received: by tyr.zones.apache.org (Postfix, from userid 65534) id AC4CB8A3452; Thu, 6 Feb 2014 17:27:43 +0000 (UTC) Content-Type: text/plain; charset="us-ascii" MIME-Version: 1.0 Content-Transfer-Encoding: 7bit From: davisp@apache.org To: commits@couchdb.apache.org Date: Thu, 06 Feb 2014 17:27:49 -0000 Message-Id: <0c5d25f582284f4facd5a9a2dcbc9044@git.apache.org> In-Reply-To: <24a97e2b76944cf6952863df43b7ba3e@git.apache.org> References: <24a97e2b76944cf6952863df43b7ba3e@git.apache.org> X-Mailer: ASF-Git Admin Mailer Subject: [07/46] support static build http://git-wip-us.apache.org/repos/asf/couchdb-couch-collate/blob/32ffa429/platform/osx/icu/unicode/ushape.h ---------------------------------------------------------------------- diff --git a/platform/osx/icu/unicode/ushape.h b/platform/osx/icu/unicode/ushape.h new file mode 100644 index 0000000..f165e14 --- /dev/null +++ b/platform/osx/icu/unicode/ushape.h @@ -0,0 +1,263 @@ +/* +****************************************************************************** +* +* Copyright (C) 2000-2007, International Business Machines +* Corporation and others. All Rights Reserved. +* +****************************************************************************** +* file name: ushape.h +* encoding: US-ASCII +* tab size: 8 (not used) +* indentation:4 +* +* created on: 2000jun29 +* created by: Markus W. Scherer +*/ + +#ifndef __USHAPE_H__ +#define __USHAPE_H__ + +#include "unicode/utypes.h" + +/** + * \file + * \brief C API: Arabic shaping + * + */ + +/** + * Shape Arabic text on a character basis. + * + *

This function performs basic operations for "shaping" Arabic text. It is most + * useful for use with legacy data formats and legacy display technology + * (simple terminals). All operations are performed on Unicode characters.

+ * + *

Text-based shaping means that some character code points in the text are + * replaced by others depending on the context. It transforms one kind of text + * into another. In comparison, modern displays for Arabic text select + * appropriate, context-dependent font glyphs for each text element, which means + * that they transform text into a glyph vector.

+ * + *

Text transformations are necessary when modern display technology is not + * available or when text needs to be transformed to or from legacy formats that + * use "shaped" characters. Since the Arabic script is cursive, connecting + * adjacent letters to each other, computers select images for each letter based + * on the surrounding letters. This usually results in four images per Arabic + * letter: initial, middle, final, and isolated forms. In Unicode, on the other + * hand, letters are normally stored abstract, and a display system is expected + * to select the necessary glyphs. (This makes searching and other text + * processing easier because the same letter has only one code.) It is possible + * to mimic this with text transformations because there are characters in + * Unicode that are rendered as letters with a specific shape + * (or cursive connectivity). They were included for interoperability with + * legacy systems and codepages, and for unsophisticated display systems.

+ * + *

A second kind of text transformations is supported for Arabic digits: + * For compatibility with legacy codepages that only include European digits, + * it is possible to replace one set of digits by another, changing the + * character code points. These operations can be performed for either + * Arabic-Indic Digits (U+0660...U+0669) or Eastern (Extended) Arabic-Indic + * digits (U+06f0...U+06f9).

+ * + *

Some replacements may result in more or fewer characters (code points). + * By default, this means that the destination buffer may receive text with a + * length different from the source length. Some legacy systems rely on the + * length of the text to be constant. They expect extra spaces to be added + * or consumed either next to the affected character or at the end of the + * text.

+ * + *

For details about the available operations, see the description of the + * U_SHAPE_... options.

+ * + * @param source The input text. + * + * @param sourceLength The number of UChars in source. + * + * @param dest The destination buffer that will receive the results of the + * requested operations. It may be NULL only if + * destSize is 0. The source and destination must not + * overlap. + * + * @param destSize The size (capacity) of the destination buffer in UChars. + * If destSize is 0, then no output is produced, + * but the necessary buffer size is returned ("preflighting"). + * + * @param options This is a 32-bit set of flags that specify the operations + * that are performed on the input text. If no error occurs, + * then the result will always be written to the destination + * buffer. + * + * @param pErrorCode must be a valid pointer to an error code value, + * which must not indicate a failure before the function call. + * + * @return The number of UChars written to the destination buffer. + * If an error occured, then no output was written, or it may be + * incomplete. If U_BUFFER_OVERFLOW_ERROR is set, then + * the return value indicates the necessary destination buffer size. + * @stable ICU 2.0 + */ +U_STABLE int32_t U_EXPORT2 +u_shapeArabic(const UChar *source, int32_t sourceLength, + UChar *dest, int32_t destSize, + uint32_t options, + UErrorCode *pErrorCode); + +/** + * Memory option: allow the result to have a different length than the source. + * @stable ICU 2.0 + */ +#define U_SHAPE_LENGTH_GROW_SHRINK 0 + +/** + * Memory option: the result must have the same length as the source. + * If more room is necessary, then try to consume spaces next to modified characters. + * @stable ICU 2.0 + */ +#define U_SHAPE_LENGTH_FIXED_SPACES_NEAR 1 + +/** + * Memory option: the result must have the same length as the source. + * If more room is necessary, then try to consume spaces at the end of the text. + * @stable ICU 2.0 + */ +#define U_SHAPE_LENGTH_FIXED_SPACES_AT_END 2 + +/** + * Memory option: the result must have the same length as the source. + * If more room is necessary, then try to consume spaces at the beginning of the text. + * @stable ICU 2.0 + */ +#define U_SHAPE_LENGTH_FIXED_SPACES_AT_BEGINNING 3 + +/** Bit mask for memory options. @stable ICU 2.0 */ +#define U_SHAPE_LENGTH_MASK 3 + + +/** Direction indicator: the source is in logical (keyboard) order. @stable ICU 2.0 */ +#define U_SHAPE_TEXT_DIRECTION_LOGICAL 0 + +/** + * Direction indicator: + * the source is in visual LTR order, + * the leftmost displayed character stored first. + * @stable ICU 2.0 + */ +#define U_SHAPE_TEXT_DIRECTION_VISUAL_LTR 4 + +/** Bit mask for direction indicators. @stable ICU 2.0 */ +#define U_SHAPE_TEXT_DIRECTION_MASK 4 + + +/** Letter shaping option: do not perform letter shaping. @stable ICU 2.0 */ +#define U_SHAPE_LETTERS_NOOP 0 + +/** Letter shaping option: replace abstract letter characters by "shaped" ones. @stable ICU 2.0 */ +#define U_SHAPE_LETTERS_SHAPE 8 + +/** Letter shaping option: replace "shaped" letter characters by abstract ones. @stable ICU 2.0 */ +#define U_SHAPE_LETTERS_UNSHAPE 0x10 + +/** + * Letter shaping option: replace abstract letter characters by "shaped" ones. + * The only difference with U_SHAPE_LETTERS_SHAPE is that Tashkeel letters + * are always "shaped" into the isolated form instead of the medial form + * (selecting code points from the Arabic Presentation Forms-B block). + * @stable ICU 2.0 + */ +#define U_SHAPE_LETTERS_SHAPE_TASHKEEL_ISOLATED 0x18 + +/** Bit mask for letter shaping options. @stable ICU 2.0 */ +#define U_SHAPE_LETTERS_MASK 0x18 + + +/** Digit shaping option: do not perform digit shaping. @stable ICU 2.0 */ +#define U_SHAPE_DIGITS_NOOP 0 + +/** + * Digit shaping option: + * Replace European digits (U+0030...) by Arabic-Indic digits. + * @stable ICU 2.0 + */ +#define U_SHAPE_DIGITS_EN2AN 0x20 + +/** + * Digit shaping option: + * Replace Arabic-Indic digits by European digits (U+0030...). + * @stable ICU 2.0 + */ +#define U_SHAPE_DIGITS_AN2EN 0x40 + +/** + * Digit shaping option: + * Replace European digits (U+0030...) by Arabic-Indic digits if the most recent + * strongly directional character is an Arabic letter + * (u_charDirection() result U_RIGHT_TO_LEFT_ARABIC [AL]).
+ * The direction of "preceding" depends on the direction indicator option. + * For the first characters, the preceding strongly directional character + * (initial state) is assumed to be not an Arabic letter + * (it is U_LEFT_TO_RIGHT [L] or U_RIGHT_TO_LEFT [R]). + * @stable ICU 2.0 + */ +#define U_SHAPE_DIGITS_ALEN2AN_INIT_LR 0x60 + +/** + * Digit shaping option: + * Replace European digits (U+0030...) by Arabic-Indic digits if the most recent + * strongly directional character is an Arabic letter + * (u_charDirection() result U_RIGHT_TO_LEFT_ARABIC [AL]).
+ * The direction of "preceding" depends on the direction indicator option. + * For the first characters, the preceding strongly directional character + * (initial state) is assumed to be an Arabic letter. + * @stable ICU 2.0 + */ +#define U_SHAPE_DIGITS_ALEN2AN_INIT_AL 0x80 + +/** Not a valid option value. May be replaced by a new option. @stable ICU 2.0 */ +#define U_SHAPE_DIGITS_RESERVED 0xa0 + +/** Bit mask for digit shaping options. @stable ICU 2.0 */ +#define U_SHAPE_DIGITS_MASK 0xe0 + + +/** Digit type option: Use Arabic-Indic digits (U+0660...U+0669). @stable ICU 2.0 */ +#define U_SHAPE_DIGIT_TYPE_AN 0 + +/** Digit type option: Use Eastern (Extended) Arabic-Indic digits (U+06f0...U+06f9). @stable ICU 2.0 */ +#define U_SHAPE_DIGIT_TYPE_AN_EXTENDED 0x100 + +/** Not a valid option value. May be replaced by a new option. @stable ICU 2.0 */ +#define U_SHAPE_DIGIT_TYPE_RESERVED 0x200 + +/** Bit mask for digit type options. @stable ICU 2.0 */ +#define U_SHAPE_DIGIT_TYPE_MASK 0x3f00 + +/** + * Tashkeel aggregation option: + * Replaces any combination of U+0651 with one of + * U+064C, U+064D, U+064E, U+064F, U+0650 with + * U+FC5E, U+FC5F, U+FC60, U+FC61, U+FC62 consecutively. + * @stable ICU 3.6 + */ +#define U_SHAPE_AGGREGATE_TASHKEEL 0x4000 +/** Tashkeel aggregation option: do not aggregate tashkeels. @stable ICU 3.6 */ +#define U_SHAPE_AGGREGATE_TASHKEEL_NOOP 0 +/** Bit mask for tashkeel aggregation. @stable ICU 3.6 */ +#define U_SHAPE_AGGREGATE_TASHKEEL_MASK 0x4000 + +/** + * Presentation form option: + * Don't replace Arabic Presentation Forms-A and Arabic Presentation Forms-B + * characters with 0+06xx characters, before shaping. + * @stable ICU 3.6 + */ +#define U_SHAPE_PRESERVE_PRESENTATION 0x8000 +/** Presentation form option: + * Replace Arabic Presentation Forms-A and Arabic Presentationo Forms-B with + * their unshaped correspondants in range 0+06xx, before shaping. + * @stable ICU 3.6 + */ +#define U_SHAPE_PRESERVE_PRESENTATION_NOOP 0 +/** Bit mask for preserve presentation form. @stable ICU 3.6 */ +#define U_SHAPE_PRESERVE_PRESENTATION_MASK 0x8000 + +#endif http://git-wip-us.apache.org/repos/asf/couchdb-couch-collate/blob/32ffa429/platform/osx/icu/unicode/usprep.h ---------------------------------------------------------------------- diff --git a/platform/osx/icu/unicode/usprep.h b/platform/osx/icu/unicode/usprep.h new file mode 100644 index 0000000..c7e75a5 --- /dev/null +++ b/platform/osx/icu/unicode/usprep.h @@ -0,0 +1,156 @@ +/* + ******************************************************************************* + * + * Copyright (C) 2003-2006, International Business Machines + * Corporation and others. All Rights Reserved. + * + ******************************************************************************* + * file name: usprep.h + * encoding: US-ASCII + * tab size: 8 (not used) + * indentation:4 + * + * created on: 2003jul2 + * created by: Ram Viswanadha + */ + +#ifndef __USPREP_H__ +#define __USPREP_H__ + +/** + * \file + * \brief C API: Implements the StringPrep algorithm. + */ + +#include "unicode/utypes.h" +/** + * + * StringPrep API implements the StingPrep framework as described by RFC 3454. + * StringPrep prepares Unicode strings for use in network protocols. + * Profiles of StingPrep are set of rules and data according to with the + * Unicode Strings are prepared. Each profiles contains tables which describe + * how a code point should be treated. The tables are broadly classied into + *
    + *
  • Unassinged Table: Contains code points that are unassigned + * in the Unicode Version supported by StringPrep. Currently + * RFC 3454 supports Unicode 3.2.
    • + *
  • Prohibited Table: Contains code points that are prohibted from + * the output of the StringPrep processing function.
    • + *
  • Mapping Table: Contains code ponts that are deleted from the output or case mapped.
    • + *
+ * + * The procedure for preparing Unicode strings: + *
    + *
  1. Map: For each character in the input, check if it has a mapping + * and, if so, replace it with its mapping.
    2. + *
  2. Normalize: Possibly normalize the result of step 1 using Unicode + * normalization.
    3. + *
  3. Prohibit: Check for any characters that are not allowed in the + * output. If any are found, return an error.
    4. + *
  4. Check bidi: Possibly check for right-to-left characters, and if + * any are found, make sure that the whole string satisfies the + * requirements for bidirectional strings. If the string does not + * satisfy the requirements for bidirectional strings, return an + * error.
    5. + *
+ * @author Ram Viswanadha + */ +#if !UCONFIG_NO_IDNA + +#include "unicode/parseerr.h" + +/** + * The StringPrep profile + * @stable ICU 2.8 + */ +typedef struct UStringPrepProfile UStringPrepProfile; + + +/** + * Option to prohibit processing of unassigned code points in the input + * + * @see usprep_prepare + * @stable ICU 2.8 + */ +#define USPREP_DEFAULT 0x0000 + +/** + * Option to allow processing of unassigned code points in the input + * + * @see usprep_prepare + * @stable ICU 2.8 + */ +#define USPREP_ALLOW_UNASSIGNED 0x0001 + + +/** + * Creates a StringPrep profile from the data file. + * + * @param path string containing the full path pointing to the directory + * where the profile reside followed by the package name + * e.g. "/usr/resource/my_app/profiles/mydata" on a Unix system. + * if NULL, ICU default data files will be used. + * @param fileName name of the profile file to be opened + * @param status ICU error code in/out parameter. Must not be NULL. + * Must fulfill U_SUCCESS before the function call. + * @return Pointer to UStringPrepProfile that is opened. Should be closed by + * calling usprep_close() + * @see usprep_close() + * @stable ICU 2.8 + */ +U_STABLE UStringPrepProfile* U_EXPORT2 +usprep_open(const char* path, + const char* fileName, + UErrorCode* status); + + +/** + * Closes the profile + * @param profile The profile to close + * @stable ICU 2.8 + */ +U_STABLE void U_EXPORT2 +usprep_close(UStringPrepProfile* profile); + + +/** + * Prepare the input buffer for use in applications with the given profile. This operation maps, normalizes(NFKC), + * checks for prohited and BiDi characters in the order defined by RFC 3454 + * depending on the options specified in the profile. + * + * @param prep The profile to use + * @param src Pointer to UChar buffer containing the string to prepare + * @param srcLength Number of characters in the source string + * @param dest Pointer to the destination buffer to receive the output + * @param destCapacity The capacity of destination array + * @param options A bit set of options: + * + * - USPREP_NONE Prohibit processing of unassigned code points in the input + * + * - USPREP_ALLOW_UNASSIGNED Treat the unassigned code points are in the input + * as normal Unicode code points. + * + * @param parseError Pointer to UParseError struct to receive information on position + * of error if an error is encountered. Can be NULL. + * @param status ICU in/out error code parameter. + * U_INVALID_CHAR_FOUND if src contains + * unmatched single surrogates. + * U_INDEX_OUTOFBOUNDS_ERROR if src contains + * too many code points. + * U_BUFFER_OVERFLOW_ERROR if destCapacity is not enough + * @return The number of UChars in the destination buffer + * @stable ICU 2.8 + */ + +U_STABLE int32_t U_EXPORT2 +usprep_prepare( const UStringPrepProfile* prep, + const UChar* src, int32_t srcLength, + UChar* dest, int32_t destCapacity, + int32_t options, + UParseError* parseError, + UErrorCode* status ); + + +#endif /* #if !UCONFIG_NO_IDNA */ + +#endif http://git-wip-us.apache.org/repos/asf/couchdb-couch-collate/blob/32ffa429/platform/osx/icu/unicode/ustring.h ---------------------------------------------------------------------- diff --git a/platform/osx/icu/unicode/ustring.h b/platform/osx/icu/unicode/ustring.h new file mode 100644 index 0000000..12411ef --- /dev/null +++ b/platform/osx/icu/unicode/ustring.h @@ -0,0 +1,1479 @@ +/* +********************************************************************** +* Copyright (C) 1998-2008, 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" +#include "unicode/uiter.h" + +/** Simple declaration for u_strToTitle() to avoid including unicode/ubrk.h. @stable ICU 2.1*/ +#ifndef UBRK_TYPEDEF_UBREAK_ITERATOR +# define UBRK_TYPEDEF_UBREAK_ITERATOR + typedef void 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 (http://icu-project.org/userguide/strings.html). + * 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_STABLE 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_STABLE 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_STABLE 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_STABLE 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. + * @param n The maximum number of characters to compare. + * @return A pointer to dst. + * @stable ICU 2.0 + */ +U_STABLE 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_STABLE 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_STABLE 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_STABLE 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_STABLE 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_STABLE 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_STABLE 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_STABLE 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_STABLE 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_STABLE 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_STABLE 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_STABLE 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 "Uhar *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_STABLE 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_STABLE 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_STABLE 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_STABLE int32_t U_EXPORT2 +u_strCompare(const UChar *s1, int32_t length1, + const UChar *s2, int32_t length2, + UBool codePointOrder); + +/** + * Compare two Unicode strings (binary order) + * as presented by UCharIterator objects. + * Works otherwise just like u_strCompare(). + * + * Both iterators are reset to their start positions. + * When the function returns, it is undefined where the iterators + * have stopped. + * + * @param iter1 First source string iterator. + * @param iter2 Second source string iterator. + * @param codePointOrder Choose between code unit order (FALSE) + * and code point order (TRUE). + * + * @return <0 or 0 or >0 as usual for string comparisons + * + * @see u_strCompare + * + * @stable ICU 2.6 + */ +U_STABLE int32_t U_EXPORT2 +u_strCompareIter(UCharIterator *iter1, UCharIterator *iter2, UBool codePointOrder); + +#ifndef U_COMPARE_CODE_POINT_ORDER +/* see also unistr.h and unorm.h */ +/** + * Option bit for u_strCaseCompare, u_strcasecmp, unorm_compare, etc: + * Compare strings in code point order instead of code unit order. + * @stable ICU 2.2 + */ +#define U_COMPARE_CODE_POINT_ORDER 0x8000 +#endif + +/** + * 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_STABLE 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. + * @param ucs2 A string to compare. + * @param n The maximum number of characters 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_STABLE 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_STABLE 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_STABLE 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_STABLE 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_STABLE 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_STABLE 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. + * @param n The maximum number of characters to copy. + * @return A pointer to dst. + * @stable ICU 2.0 + */ +U_STABLE UChar* U_EXPORT2 +u_strncpy(UChar *dst, + const UChar *src, + int32_t n); + +#if !UCONFIG_NO_CONVERSION + +/** + * Copy a byte string encoded in the default codepage to a ustring. + * Adds a null terminator. + * Performs a host byte to UChar conversion + * + * @param dst The destination string. + * @param src The source string. + * @return A pointer to dst. + * @stable ICU 2.0 + */ +U_STABLE UChar* U_EXPORT2 u_uastrcpy(UChar *dst, + const char *src ); + +/** + * Copy a byte string encoded in the default codepage to a ustring. + * Copies at most n characters. The result will be null terminated + * if the length of src is less than n. + * Performs a host byte to UChar conversion + * + * @param dst The destination string. + * @param src The source string. + * @param n The maximum number of characters to copy. + * @return A pointer to dst. + * @stable ICU 2.0 + */ +U_STABLE UChar* U_EXPORT2 u_uastrncpy(UChar *dst, + const char *src, + int32_t n); + +/** + * Copy ustring to a byte string encoded in the default codepage. + * Adds a null terminator. + * Performs a UChar to host byte conversion + * + * @param dst The destination string. + * @param src The source string. + * @return A pointer to dst. + * @stable ICU 2.0 + */ +U_STABLE char* U_EXPORT2 u_austrcpy(char *dst, + const UChar *src ); + +/** + * Copy ustring to a byte string encoded in the default codepage. + * Copies at most n characters. The result will be null terminated + * if the length of src is less than n. + * Performs a UChar to host byte conversion + * + * @param dst The destination string. + * @param src The source string. + * @param n The maximum number of characters to copy. + * @return A pointer to dst. + * @stable ICU 2.0 + */ +U_STABLE char* U_EXPORT2 u_austrncpy(char *dst, + const UChar *src, + int32_t n ); + +#endif + +/** + * Synonym for memcpy(), but with UChars only. + * @param dest The destination string + * @param src The source string + * @param count The number of characters to copy + * @return A pointer to dest + * @stable ICU 2.0 + */ +U_STABLE 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 + * @param count The number of characters to move + * @return A pointer to dest + * @stable ICU 2.0 + */ +U_STABLE 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_STABLE 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_STABLE 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_STABLE 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_STABLE 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_STABLE 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_STABLE 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_STABLE 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 intialize 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);
+ *    }
+ *
+ * @stable ICU 2.0 + */ +#if defined(U_DECLARE_UTF16) +# define U_STRING_DECL(var, cs, length) static const UChar var[(length)+1]=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 + +/** + * Unescape a string of characters and write the resulting + * Unicode characters to the destination buffer. The following escape + * sequences are recognized: + * + * \\uhhhh 4 hex digits; h in [0-9A-Fa-f] + * \\Uhhhhhhhh 8 hex digits + * \\xhh 1-2 hex digits + * \\x{h...} 1-8 hex digits + * \\ooo 1-3 octal digits; o in [0-7] + * \\cX control-X; X is masked with 0x1F + * + * as well as the standard ANSI C escapes: + * + * \\a => U+0007, \\b => U+0008, \\t => U+0009, \\n => U+000A, + * \\v => U+000B, \\f => U+000C, \\r => U+000D, \\e => U+001B, + * \\" => U+0022, \\' => U+0027, \\? => U+003F, \\\\ => U+005C + * + * Anything else following a backslash is generically escaped. For + * example, "[a\\-z]" returns "[a-z]". + * + * If an escape sequence is ill-formed, this method returns an empty + * string. An example of an ill-formed sequence is "\\u" followed by + * fewer than 4 hex digits. + * + * The above characters are recognized in the compiler's codepage, + * that is, they are coded as 'u', '\\', etc. Characters that are + * not parts of escape sequences are converted using u_charsToUChars(). + * + * This function is similar to UnicodeString::unescape() but not + * identical to it. The latter takes a source UnicodeString, so it + * does escape recognition but no conversion. + * + * @param src a zero-terminated string of invariant characters + * @param dest pointer to buffer to receive converted and unescaped + * text and, if there is room, a zero terminator. May be NULL for + * preflighting, in which case no UChars will be written, but the + * return value will still be valid. On error, an empty string is + * stored here (if possible). + * @param destCapacity the number of UChars that may be written at + * dest. Ignored if dest == NULL. + * @return the length of unescaped string. + * @see u_unescapeAt + * @see UnicodeString#unescape() + * @see UnicodeString#unescapeAt() + * @stable ICU 2.0 + */ +U_STABLE int32_t U_EXPORT2 +u_unescape(const char *src, + UChar *dest, int32_t destCapacity); + +U_CDECL_BEGIN +/** + * Callback function for u_unescapeAt() that returns a character of + * the source text given an offset and a context pointer. The context + * pointer will be whatever is passed into u_unescapeAt(). + * + * @param offset pointer to the offset that will be passed to u_unescapeAt(). + * @param context an opaque pointer passed directly into u_unescapeAt() + * @return the character represented by the escape sequence at + * offset + * @see u_unescapeAt + * @stable ICU 2.0 + */ +typedef UChar (U_CALLCONV *UNESCAPE_CHAR_AT)(int32_t offset, void *context); +U_CDECL_END + +/** + * Unescape a single sequence. The character at offset-1 is assumed + * (without checking) to be a backslash. This method takes a callback + * pointer to a function that returns the UChar at a given offset. By + * varying this callback, ICU functions are able to unescape char* + * strings, UnicodeString objects, and UFILE pointers. + * + * If offset is out of range, or if the escape sequence is ill-formed, + * (UChar32)0xFFFFFFFF is returned. See documentation of u_unescape() + * for a list of recognized sequences. + * + * @param charAt callback function that returns a UChar of the source + * text given an offset and a context pointer. + * @param offset pointer to the offset that will be passed to charAt. + * The offset value will be updated upon return to point after the + * last parsed character of the escape sequence. On error the offset + * is unchanged. + * @param length the number of characters in the source text. The + * last character of the source text is considered to be at offset + * length-1. + * @param context an opaque pointer passed directly into charAt. + * @return the character represented by the escape sequence at + * offset, or (UChar32)0xFFFFFFFF on error. + * @see u_unescape() + * @see UnicodeString#unescape() + * @see UnicodeString#unescapeAt() + * @stable ICU 2.0 + */ +U_STABLE UChar32 U_EXPORT2 +u_unescapeAt(UNESCAPE_CHAR_AT charAt, + int32_t *offset, + int32_t length, + void *context); + +/** + * 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_STABLE 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_STABLE 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_STABLE 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-fold 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 'I' 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_STABLE int32_t U_EXPORT2 +u_strFoldCase(UChar *dest, int32_t destCapacity, + const UChar *src, int32_t srcLength, + uint32_t options, + UErrorCode *pErrorCode); + +#if defined(U_WCHAR_IS_UTF16) || defined(U_WCHAR_IS_UTF32) || !UCONFIG_NO_CONVERSION +/** + * Converts a sequence of UChars to wchar_t units. + * + * @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 wchar_t's). 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 + */ +U_STABLE wchar_t* U_EXPORT2 +u_strToWCS(wchar_t *dest, + int32_t destCapacity, + int32_t *pDestLength, + const UChar *src, + int32_t srcLength, + UErrorCode *pErrorCode); +/** + * Converts a sequence of wchar_t units to UChars + * + * @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 + */ +U_STABLE UChar* U_EXPORT2 +u_strFromWCS(UChar *dest, + int32_t destCapacity, + int32_t *pDestLength, + const wchar_t *src, + int32_t srcLength, + UErrorCode *pErrorCode); +#endif /* defined(U_WCHAR_IS_UTF16) || defined(U_WCHAR_IS_UTF32) || !UCONFIG_NO_CONVERSION */ + +/** + * Converts a sequence of UChars (UTF-16) to UTF-8 bytes + * + * @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_STABLE char* U_EXPORT2 +u_strToUTF8(char *dest, + int32_t destCapacity, + int32_t *pDestLength, + const UChar *src, + int32_t srcLength, + UErrorCode *pErrorCode); + +/** + * Converts a sequence of UTF-8 bytes to UChars (UTF-16). + * + * @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_STABLE UChar* U_EXPORT2 +u_strFromUTF8(UChar *dest, + int32_t destCapacity, + int32_t *pDestLength, + const char *src, + int32_t srcLength, + UErrorCode *pErrorCode); + +/** + * Converts a sequence of UChars (UTF-16) to UTF-8 bytes. + * 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_STABLE 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); + +/** + * Converts a sequence of UTF-8 bytes to UChars (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_STABLE 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); + +/** + * Converts a sequence of UTF-8 bytes to UChars (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. + * + * @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