You are viewing a plain text version of this content. The canonical link for it is here.
Posted to commits@subversion.apache.org by br...@apache.org on 2017/09/21 10:49:13 UTC
svn commit: r1809147 [3/3] - in /subversion/branches/better-pristines: ./
subversion/libsvn_client/ subversion/libsvn_subr/
subversion/libsvn_subr/utf8proc/ subversion/tests/cmdline/
subversion/tests/libsvn_client/
Modified: subversion/branches/better-pristines/subversion/libsvn_subr/utf8proc/utf8proc_internal.h
URL: http://svn.apache.org/viewvc/subversion/branches/better-pristines/subversion/libsvn_subr/utf8proc/utf8proc_internal.h?rev=1809147&r1=1809146&r2=1809147&view=diff
==============================================================================
--- subversion/branches/better-pristines/subversion/libsvn_subr/utf8proc/utf8proc_internal.h (original)
+++ subversion/branches/better-pristines/subversion/libsvn_subr/utf8proc/utf8proc_internal.h Thu Sep 21 10:49:13 2017
@@ -1,60 +1,60 @@
-#include "svn_private_config.h"
-#if SVN_INTERNAL_UTF8PROC
/*
- * Copyright (c) 2009 Public Software Group e. V., Berlin, Germany
+ * Copyright (c) 2015 Steven G. Johnson, Jiahao Chen, Peter Colberg, Tony Kelman, Scott P. Jones, and other contributors.
+ * Copyright (c) 2009 Public Software Group e. V., Berlin, Germany
*
- * Permission is hereby granted, free of charge, to any person obtaining a
- * copy of this software and associated documentation files (the "Software"),
- * to deal in the Software without restriction, including without limitation
- * the rights to use, copy, modify, merge, publish, distribute, sublicense,
- * and/or sell copies of the Software, and to permit persons to whom the
- * Software is furnished to do so, subject to the following conditions:
- *
- * The above copyright notice and this permission notice shall be included in
- * all copies or substantial portions of the Software.
- *
- * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
- * IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
- * FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE
- * AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
- * LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING
- * FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER
- * DEALINGS IN THE SOFTWARE.
+ * Permission is hereby granted, free of charge, to any person obtaining a
+ * copy of this software and associated documentation files (the "Software"),
+ * to deal in the Software without restriction, including without limitation
+ * the rights to use, copy, modify, merge, publish, distribute, sublicense,
+ * and/or sell copies of the Software, and to permit persons to whom the
+ * Software is furnished to do so, subject to the following conditions:
+ *
+ * The above copyright notice and this permission notice shall be included in
+ * all copies or substantial portions of the Software.
+ *
+ * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
+ * IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
+ * FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE
+ * AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
+ * LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING
+ * FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER
+ * DEALINGS IN THE SOFTWARE.
*/
-/*
- * File name: utf8proc.h
+/**
+ * @mainpage
+ *
+ * utf8proc is a free/open-source (MIT/expat licensed) C library
+ * providing Unicode normalization, case-folding, and other operations
+ * for strings in the UTF-8 encoding, supporting Unicode version
+ * 8.0.0. See the utf8proc home page (http://julialang.org/utf8proc/)
+ * for downloads and other information, or the source code on github
+ * (https://github.com/JuliaLang/utf8proc).
*
- * Description:
- * Header files for libutf8proc, which is a mapping tool for UTF-8 strings
- * with following features:
- * - decomposing and composing of strings
- * - replacing compatibility characters with their equivalents
- * - stripping of "default ignorable characters"
- * like SOFT-HYPHEN or ZERO-WIDTH-SPACE
- * - folding of certain characters for string comparison
- * (e.g. HYPHEN U+2010 and MINUS U+2212 to ASCII "-")
- * (see "LUMP" option)
- * - optional rejection of strings containing non-assigned code points
- * - stripping of control characters
- * - stripping of character marks (accents, etc.)
- * - transformation of LF, CRLF, CR and NEL to line-feed (LF)
- * or to the unicode chararacters for paragraph separation (PS)
- * or line separation (LS).
- * - unicode case folding (for case insensitive string comparisons)
- * - rejection of illegal UTF-8 data
- * (i.e. UTF-8 encoded UTF-16 surrogates)
- * - support for korean hangul characters
- * Unicode Version 5.0.0 is supported.
+ * For the utf8proc API documentation, see: @ref utf8proc.h
+ *
+ * The features of utf8proc include:
+ *
+ * - Transformation of strings (@ref utf8proc_map) to:
+ * - decompose (@ref UTF8PROC_DECOMPOSE) or compose (@ref UTF8PROC_COMPOSE) Unicode combining characters (http://en.wikipedia.org/wiki/Combining_character)
+ * - canonicalize Unicode compatibility characters (@ref UTF8PROC_COMPAT)
+ * - strip "ignorable" (@ref UTF8PROC_IGNORE) characters, control characters (@ref UTF8PROC_STRIPCC), or combining characters such as accents (@ref UTF8PROC_STRIPMARK)
+ * - case-folding (@ref UTF8PROC_CASEFOLD)
+ * - Unicode normalization: @ref utf8proc_NFD, @ref utf8proc_NFC, @ref utf8proc_NFKD, @ref utf8proc_NFKC
+ * - Detecting grapheme boundaries (@ref utf8proc_grapheme_break and @ref UTF8PROC_CHARBOUND)
+ * - Character-width computation: @ref utf8proc_charwidth
+ * - Classification of characters by Unicode category: @ref utf8proc_category and @ref utf8proc_category_string
+ * - Encode (@ref utf8proc_encode_char) and decode (@ref utf8proc_iterate) Unicode codepoints to/from UTF-8.
*/
+/** @file */
#ifndef UTF8PROC_H
#define UTF8PROC_H
/** @name API version
- *
+ *
* The utf8proc API version MAJOR.MINOR.PATCH, following
* semantic-versioning rules (http://semver.org) based on API
* compatibility.
@@ -63,66 +63,81 @@
* runtime version may append a string like "-dev" to the version number
* for prerelease versions.
*
- * @note The shared-library version number in the Makefile may be different,
+ * @note The shared-library version number in the Makefile
+ * (and CMakeLists.txt, and MANIFEST) may be different,
* being based on ABI compatibility rather than API compatibility.
*/
/** @{ */
/** The MAJOR version number (increased when backwards API compatibility is broken). */
-#define UTF8PROC_VERSION_MAJOR 1
+#define UTF8PROC_VERSION_MAJOR 2
/** The MINOR version number (increased when new functionality is added in a backwards-compatible manner). */
#define UTF8PROC_VERSION_MINOR 1
/** The PATCH version (increased for fixes that do not change the API). */
-#define UTF8PROC_VERSION_PATCH 5
+#define UTF8PROC_VERSION_PATCH 0
/** @} */
-/*
- * Define UTF8PROC_INLINE and include utf8proc.c to embed a static
- * version of utf8proc in your program or library without exporting
- * any of its symbols.
- */
-#ifdef UTF8PROC_INLINE
-#define UTF8PROC_API static
-#undef UTF8PROC_DATA_EXPORT
-#define UTF8PROC_DATA static
-#else
-#define UTF8PROC_API
-#define UTF8PROC_DATA_EXPORT
-#define UTF8PROC_DATA
-#endif
-
-
#include <stdlib.h>
#include <sys/types.h>
-
-#ifdef HAVE_STDINT_H
-#include <stdint.h>
-#else
#include <apr.h>
+typedef char utf8proc_int8_t;
+typedef unsigned char utf8proc_uint8_t;
+typedef apr_int16_t utf8proc_int16_t;
+typedef apr_uint16_t utf8proc_uint16_t;
+typedef apr_int32_t utf8proc_int32_t;
+typedef apr_uint32_t utf8proc_uint32_t;
#ifdef _MSC_VER
-typedef apr_int8_t int8_t;
-typedef apr_uint8_t uint8_t;
-typedef apr_int16_t int16_t;
-typedef apr_uint16_t uint16_t;
-typedef apr_int32_t int32_t;
-typedef apr_uint32_t uint32_t;
+# ifdef _WIN64
+typedef apr_int64_t utf8proc_ssize_t;
+typedef apr_uint64_t utf8proc_size_t;
+# else
+typedef apr_int32_t utf8proc_ssize_t;
+typedef apr_uint32_t utf8proc_size_t;
+# endif
+#else
+typedef apr_size_t utf8proc_size_t;
+typedef apr_ssize_t utf8proc_ssize_t;
#endif
+#ifdef __cplusplus
+typedef bool utf8proc_bool;
+#elif defined HAVE_STDBOOL_H
+# include <stdbool.h>
+typedef bool utf8proc_bool;
+#else
+// emulate C99 bool
+# ifndef __bool_true_false_are_defined
+# define false 0
+# define true 1
+# define __bool_true_false_are_defined 1
+# endif
+typedef apr_byte_t utf8proc_bool;
#endif
+#include <limits.h>
-#ifdef HAVE_STDBOOL_H
-#include <stdbool.h>
-#elif !defined(__cplusplus)
-typedef uint8_t bool;
-enum { false, true };
-#endif
-#ifdef _MSC_VER
-# ifdef _WIN64
-# define ssize_t __int64
-# else
-# define ssize_t int
-# endif
+/*
+ * Define UTF8PROC_INLINE and include utf8proc.c to embed a static
+ * version of utf8proc in your program or library without exporting
+ * any of its symbols.
+ */
+#ifdef UTF8PROC_INLINE
+# define UTF8PROC_DATA static
+# undef UTF8PROC_DATA_EXPORT
+# define UTF8PROC_DLLEXPORT static
+#else
+# define UTF8PROC_DATA
+# define UTF8PROC_DATA_EXPORT
+# ifdef _WIN32
+# ifdef UTF8PROC_EXPORTS
+# define UTF8PROC_DLLEXPORT __declspec(dllexport)
+# else
+# define UTF8PROC_DLLEXPORT __declspec(dllimport)
+# endif
+# elif __GNUC__ >= 4
+# define UTF8PROC_DLLEXPORT __attribute__ ((visibility("default")))
+# else
+# define UTF8PROC_DLLEXPORT
+# endif
#endif
-#include <limits.h>
#ifdef __cplusplus
extern "C" {
@@ -132,321 +147,562 @@ extern "C" {
#define SSIZE_MAX ((size_t)SIZE_MAX/2)
#endif
-#define UTF8PROC_NULLTERM (1<<0)
-#define UTF8PROC_STABLE (1<<1)
-#define UTF8PROC_COMPAT (1<<2)
-#define UTF8PROC_COMPOSE (1<<3)
-#define UTF8PROC_DECOMPOSE (1<<4)
-#define UTF8PROC_IGNORE (1<<5)
-#define UTF8PROC_REJECTNA (1<<6)
-#define UTF8PROC_NLF2LS (1<<7)
-#define UTF8PROC_NLF2PS (1<<8)
-#define UTF8PROC_NLF2LF (UTF8PROC_NLF2LS | UTF8PROC_NLF2PS)
-#define UTF8PROC_STRIPCC (1<<9)
-#define UTF8PROC_CASEFOLD (1<<10)
-#define UTF8PROC_CHARBOUND (1<<11)
-#define UTF8PROC_LUMP (1<<12)
-#define UTF8PROC_STRIPMARK (1<<13)
-/*
- * Flags being regarded by several functions in the library:
- * NULLTERM: The given UTF-8 input is NULL terminated.
- * STABLE: Unicode Versioning Stability has to be respected.
- * COMPAT: Compatiblity decomposition
- * (i.e. formatting information is lost)
- * COMPOSE: Return a result with composed characters.
- * DECOMPOSE: Return a result with decomposed characters.
- * IGNORE: Strip "default ignorable characters"
- * REJECTNA: Return an error, if the input contains unassigned
- * code points.
- * NLF2LS: Indicating that NLF-sequences (LF, CRLF, CR, NEL) are
- * representing a line break, and should be converted to the
- * unicode character for line separation (LS).
- * NLF2PS: Indicating that NLF-sequences are representing a paragraph
- * break, and should be converted to the unicode character for
- * paragraph separation (PS).
- * NLF2LF: Indicating that the meaning of NLF-sequences is unknown.
- * STRIPCC: Strips and/or convers control characters.
- * NLF-sequences are transformed into space, except if one of
- * the NLF2LS/PS/LF options is given.
- * HorizontalTab (HT) and FormFeed (FF) are treated as a
- * NLF-sequence in this case.
- * All other control characters are simply removed.
- * CASEFOLD: Performs unicode case folding, to be able to do a
- * case-insensitive string comparison.
- * CHARBOUND: Inserts 0xFF bytes at the beginning of each sequence which
- * is representing a single grapheme cluster (see UAX#29).
- * LUMP: Lumps certain characters together
- * (e.g. HYPHEN U+2010 and MINUS U+2212 to ASCII "-").
- * (See lump.txt for details.)
- * If NLF2LF is set, this includes a transformation of
- * paragraph and line separators to ASCII line-feed (LF).
- * STRIPMARK: Strips all character markings
- * (non-spacing, spacing and enclosing) (i.e. accents)
- * NOTE: this option works only with COMPOSE or DECOMPOSE
+#ifndef UINT16_MAX
+# define UINT16_MAX 65535U
+#endif
+
+/**
+ * Option flags used by several functions in the library.
*/
+typedef enum {
+ /** The given UTF-8 input is NULL terminated. */
+ UTF8PROC_NULLTERM = (1<<0),
+ /** Unicode Versioning Stability has to be respected. */
+ UTF8PROC_STABLE = (1<<1),
+ /** Compatibility decomposition (i.e. formatting information is lost). */
+ UTF8PROC_COMPAT = (1<<2),
+ /** Return a result with decomposed characters. */
+ UTF8PROC_COMPOSE = (1<<3),
+ /** Return a result with decomposed characters. */
+ UTF8PROC_DECOMPOSE = (1<<4),
+ /** Strip "default ignorable characters" such as SOFT-HYPHEN or ZERO-WIDTH-SPACE. */
+ UTF8PROC_IGNORE = (1<<5),
+ /** Return an error, if the input contains unassigned codepoints. */
+ UTF8PROC_REJECTNA = (1<<6),
+ /**
+ * Indicating that NLF-sequences (LF, CRLF, CR, NEL) are representing a
+ * line break, and should be converted to the codepoint for line
+ * separation (LS).
+ */
+ UTF8PROC_NLF2LS = (1<<7),
+ /**
+ * Indicating that NLF-sequences are representing a paragraph break, and
+ * should be converted to the codepoint for paragraph separation
+ * (PS).
+ */
+ UTF8PROC_NLF2PS = (1<<8),
+ /** Indicating that the meaning of NLF-sequences is unknown. */
+ UTF8PROC_NLF2LF = (UTF8PROC_NLF2LS | UTF8PROC_NLF2PS),
+ /** Strips and/or convers control characters.
+ *
+ * NLF-sequences are transformed into space, except if one of the
+ * NLF2LS/PS/LF options is given. HorizontalTab (HT) and FormFeed (FF)
+ * are treated as a NLF-sequence in this case. All other control
+ * characters are simply removed.
+ */
+ UTF8PROC_STRIPCC = (1<<9),
+ /**
+ * Performs unicode case folding, to be able to do a case-insensitive
+ * string comparison.
+ */
+ UTF8PROC_CASEFOLD = (1<<10),
+ /**
+ * Inserts 0xFF bytes at the beginning of each sequence which is
+ * representing a single grapheme cluster (see UAX#29).
+ */
+ UTF8PROC_CHARBOUND = (1<<11),
+ /** Lumps certain characters together.
+ *
+ * E.g. HYPHEN U+2010 and MINUS U+2212 to ASCII "-". See lump.md for details.
+ *
+ * If NLF2LF is set, this includes a transformation of paragraph and
+ * line separators to ASCII line-feed (LF).
+ */
+ UTF8PROC_LUMP = (1<<12),
+ /** Strips all character markings.
+ *
+ * This includes non-spacing, spacing and enclosing (i.e. accents).
+ * @note This option works only with @ref UTF8PROC_COMPOSE or
+ * @ref UTF8PROC_DECOMPOSE
+ */
+ UTF8PROC_STRIPMARK = (1<<13),
+} utf8proc_option_t;
+/** @name Error codes
+ * Error codes being returned by almost all functions.
+ */
+/** @{ */
+/** Memory could not be allocated. */
#define UTF8PROC_ERROR_NOMEM -1
+/** The given string is too long to be processed. */
#define UTF8PROC_ERROR_OVERFLOW -2
+/** The given string is not a legal UTF-8 string. */
#define UTF8PROC_ERROR_INVALIDUTF8 -3
+/** The @ref UTF8PROC_REJECTNA flag was set and an unassigned codepoint was found. */
#define UTF8PROC_ERROR_NOTASSIGNED -4
+/** Invalid options have been used. */
#define UTF8PROC_ERROR_INVALIDOPTS -5
-/*
- * Error codes being returned by almost all functions:
- * ERROR_NOMEM: Memory could not be allocated.
- * ERROR_OVERFLOW: The given string is too long to be processed.
- * ERROR_INVALIDUTF8: The given string is not a legal UTF-8 string.
- * ERROR_NOTASSIGNED: The REJECTNA flag was set,
- * and an unassigned code point was found.
- * ERROR_INVALIDOPTS: Invalid options have been used.
- */
+/** @} */
+
+/* @name Types */
+
+/** Holds the value of a property. */
+typedef utf8proc_int16_t utf8proc_propval_t;
-typedef int16_t utf8proc_propval_t;
+/** Struct containing information about a codepoint. */
typedef struct utf8proc_property_struct {
+ /**
+ * Unicode category.
+ * @see utf8proc_category_t.
+ */
utf8proc_propval_t category;
utf8proc_propval_t combining_class;
+ /**
+ * Bidirectional class.
+ * @see utf8proc_bidi_class_t.
+ */
utf8proc_propval_t bidi_class;
+ /**
+ * @anchor Decomposition type.
+ * @see utf8proc_decomp_type_t.
+ */
utf8proc_propval_t decomp_type;
- const int32_t *decomp_mapping;
+ utf8proc_uint16_t decomp_seqindex;
+ utf8proc_uint16_t casefold_seqindex;
+ utf8proc_uint16_t uppercase_seqindex;
+ utf8proc_uint16_t lowercase_seqindex;
+ utf8proc_uint16_t titlecase_seqindex;
+ utf8proc_uint16_t comb_index;
unsigned bidi_mirrored:1;
- int32_t uppercase_mapping;
- int32_t lowercase_mapping;
- int32_t titlecase_mapping;
- int32_t comb1st_index;
- int32_t comb2nd_index;
unsigned comp_exclusion:1;
+ /**
+ * Can this codepoint be ignored?
+ *
+ * Used by @ref utf8proc_decompose_char when @ref UTF8PROC_IGNORE is
+ * passed as an option.
+ */
unsigned ignorable:1;
unsigned control_boundary:1;
- unsigned extend:1;
- const int32_t *casefold_mapping;
+ /** The width of the codepoint. */
+ unsigned charwidth:2;
+ unsigned pad:2;
+ /**
+ * Boundclass.
+ * @see utf8proc_boundclass_t.
+ */
+ unsigned boundclass:8;
} utf8proc_property_t;
-#define UTF8PROC_CATEGORY_LU 1
-#define UTF8PROC_CATEGORY_LL 2
-#define UTF8PROC_CATEGORY_LT 3
-#define UTF8PROC_CATEGORY_LM 4
-#define UTF8PROC_CATEGORY_LO 5
-#define UTF8PROC_CATEGORY_MN 6
-#define UTF8PROC_CATEGORY_MC 7
-#define UTF8PROC_CATEGORY_ME 8
-#define UTF8PROC_CATEGORY_ND 9
-#define UTF8PROC_CATEGORY_NL 10
-#define UTF8PROC_CATEGORY_NO 11
-#define UTF8PROC_CATEGORY_PC 12
-#define UTF8PROC_CATEGORY_PD 13
-#define UTF8PROC_CATEGORY_PS 14
-#define UTF8PROC_CATEGORY_PE 15
-#define UTF8PROC_CATEGORY_PI 16
-#define UTF8PROC_CATEGORY_PF 17
-#define UTF8PROC_CATEGORY_PO 18
-#define UTF8PROC_CATEGORY_SM 19
-#define UTF8PROC_CATEGORY_SC 20
-#define UTF8PROC_CATEGORY_SK 21
-#define UTF8PROC_CATEGORY_SO 22
-#define UTF8PROC_CATEGORY_ZS 23
-#define UTF8PROC_CATEGORY_ZL 24
-#define UTF8PROC_CATEGORY_ZP 25
-#define UTF8PROC_CATEGORY_CC 26
-#define UTF8PROC_CATEGORY_CF 27
-#define UTF8PROC_CATEGORY_CS 28
-#define UTF8PROC_CATEGORY_CO 29
-#define UTF8PROC_CATEGORY_CN 30
-#define UTF8PROC_BIDI_CLASS_L 1
-#define UTF8PROC_BIDI_CLASS_LRE 2
-#define UTF8PROC_BIDI_CLASS_LRO 3
-#define UTF8PROC_BIDI_CLASS_R 4
-#define UTF8PROC_BIDI_CLASS_AL 5
-#define UTF8PROC_BIDI_CLASS_RLE 6
-#define UTF8PROC_BIDI_CLASS_RLO 7
-#define UTF8PROC_BIDI_CLASS_PDF 8
-#define UTF8PROC_BIDI_CLASS_EN 9
-#define UTF8PROC_BIDI_CLASS_ES 10
-#define UTF8PROC_BIDI_CLASS_ET 11
-#define UTF8PROC_BIDI_CLASS_AN 12
-#define UTF8PROC_BIDI_CLASS_CS 13
-#define UTF8PROC_BIDI_CLASS_NSM 14
-#define UTF8PROC_BIDI_CLASS_BN 15
-#define UTF8PROC_BIDI_CLASS_B 16
-#define UTF8PROC_BIDI_CLASS_S 17
-#define UTF8PROC_BIDI_CLASS_WS 18
-#define UTF8PROC_BIDI_CLASS_ON 19
-#define UTF8PROC_DECOMP_TYPE_FONT 1
-#define UTF8PROC_DECOMP_TYPE_NOBREAK 2
-#define UTF8PROC_DECOMP_TYPE_INITIAL 3
-#define UTF8PROC_DECOMP_TYPE_MEDIAL 4
-#define UTF8PROC_DECOMP_TYPE_FINAL 5
-#define UTF8PROC_DECOMP_TYPE_ISOLATED 6
-#define UTF8PROC_DECOMP_TYPE_CIRCLE 7
-#define UTF8PROC_DECOMP_TYPE_SUPER 8
-#define UTF8PROC_DECOMP_TYPE_SUB 9
-#define UTF8PROC_DECOMP_TYPE_VERTICAL 10
-#define UTF8PROC_DECOMP_TYPE_WIDE 11
-#define UTF8PROC_DECOMP_TYPE_NARROW 12
-#define UTF8PROC_DECOMP_TYPE_SMALL 13
-#define UTF8PROC_DECOMP_TYPE_SQUARE 14
-#define UTF8PROC_DECOMP_TYPE_FRACTION 15
-#define UTF8PROC_DECOMP_TYPE_COMPAT 16
-
-#ifdef UTF8PROC_DATA_EXPORT
-extern const int8_t utf8proc_utf8class[256];
+/** Unicode categories. */
+typedef enum {
+ UTF8PROC_CATEGORY_CN = 0, /**< Other, not assigned */
+ UTF8PROC_CATEGORY_LU = 1, /**< Letter, uppercase */
+ UTF8PROC_CATEGORY_LL = 2, /**< Letter, lowercase */
+ UTF8PROC_CATEGORY_LT = 3, /**< Letter, titlecase */
+ UTF8PROC_CATEGORY_LM = 4, /**< Letter, modifier */
+ UTF8PROC_CATEGORY_LO = 5, /**< Letter, other */
+ UTF8PROC_CATEGORY_MN = 6, /**< Mark, nonspacing */
+ UTF8PROC_CATEGORY_MC = 7, /**< Mark, spacing combining */
+ UTF8PROC_CATEGORY_ME = 8, /**< Mark, enclosing */
+ UTF8PROC_CATEGORY_ND = 9, /**< Number, decimal digit */
+ UTF8PROC_CATEGORY_NL = 10, /**< Number, letter */
+ UTF8PROC_CATEGORY_NO = 11, /**< Number, other */
+ UTF8PROC_CATEGORY_PC = 12, /**< Punctuation, connector */
+ UTF8PROC_CATEGORY_PD = 13, /**< Punctuation, dash */
+ UTF8PROC_CATEGORY_PS = 14, /**< Punctuation, open */
+ UTF8PROC_CATEGORY_PE = 15, /**< Punctuation, close */
+ UTF8PROC_CATEGORY_PI = 16, /**< Punctuation, initial quote */
+ UTF8PROC_CATEGORY_PF = 17, /**< Punctuation, final quote */
+ UTF8PROC_CATEGORY_PO = 18, /**< Punctuation, other */
+ UTF8PROC_CATEGORY_SM = 19, /**< Symbol, math */
+ UTF8PROC_CATEGORY_SC = 20, /**< Symbol, currency */
+ UTF8PROC_CATEGORY_SK = 21, /**< Symbol, modifier */
+ UTF8PROC_CATEGORY_SO = 22, /**< Symbol, other */
+ UTF8PROC_CATEGORY_ZS = 23, /**< Separator, space */
+ UTF8PROC_CATEGORY_ZL = 24, /**< Separator, line */
+ UTF8PROC_CATEGORY_ZP = 25, /**< Separator, paragraph */
+ UTF8PROC_CATEGORY_CC = 26, /**< Other, control */
+ UTF8PROC_CATEGORY_CF = 27, /**< Other, format */
+ UTF8PROC_CATEGORY_CS = 28, /**< Other, surrogate */
+ UTF8PROC_CATEGORY_CO = 29, /**< Other, private use */
+} utf8proc_category_t;
+
+/** Bidirectional character classes. */
+typedef enum {
+ UTF8PROC_BIDI_CLASS_L = 1, /**< Left-to-Right */
+ UTF8PROC_BIDI_CLASS_LRE = 2, /**< Left-to-Right Embedding */
+ UTF8PROC_BIDI_CLASS_LRO = 3, /**< Left-to-Right Override */
+ UTF8PROC_BIDI_CLASS_R = 4, /**< Right-to-Left */
+ UTF8PROC_BIDI_CLASS_AL = 5, /**< Right-to-Left Arabic */
+ UTF8PROC_BIDI_CLASS_RLE = 6, /**< Right-to-Left Embedding */
+ UTF8PROC_BIDI_CLASS_RLO = 7, /**< Right-to-Left Override */
+ UTF8PROC_BIDI_CLASS_PDF = 8, /**< Pop Directional Format */
+ UTF8PROC_BIDI_CLASS_EN = 9, /**< European Number */
+ UTF8PROC_BIDI_CLASS_ES = 10, /**< European Separator */
+ UTF8PROC_BIDI_CLASS_ET = 11, /**< European Number Terminator */
+ UTF8PROC_BIDI_CLASS_AN = 12, /**< Arabic Number */
+ UTF8PROC_BIDI_CLASS_CS = 13, /**< Common Number Separator */
+ UTF8PROC_BIDI_CLASS_NSM = 14, /**< Nonspacing Mark */
+ UTF8PROC_BIDI_CLASS_BN = 15, /**< Boundary Neutral */
+ UTF8PROC_BIDI_CLASS_B = 16, /**< Paragraph Separator */
+ UTF8PROC_BIDI_CLASS_S = 17, /**< Segment Separator */
+ UTF8PROC_BIDI_CLASS_WS = 18, /**< Whitespace */
+ UTF8PROC_BIDI_CLASS_ON = 19, /**< Other Neutrals */
+ UTF8PROC_BIDI_CLASS_LRI = 20, /**< Left-to-Right Isolate */
+ UTF8PROC_BIDI_CLASS_RLI = 21, /**< Right-to-Left Isolate */
+ UTF8PROC_BIDI_CLASS_FSI = 22, /**< First Strong Isolate */
+ UTF8PROC_BIDI_CLASS_PDI = 23, /**< Pop Directional Isolate */
+} utf8proc_bidi_class_t;
+
+/** Decomposition type. */
+typedef enum {
+ UTF8PROC_DECOMP_TYPE_FONT = 1, /**< Font */
+ UTF8PROC_DECOMP_TYPE_NOBREAK = 2, /**< Nobreak */
+ UTF8PROC_DECOMP_TYPE_INITIAL = 3, /**< Initial */
+ UTF8PROC_DECOMP_TYPE_MEDIAL = 4, /**< Medial */
+ UTF8PROC_DECOMP_TYPE_FINAL = 5, /**< Final */
+ UTF8PROC_DECOMP_TYPE_ISOLATED = 6, /**< Isolated */
+ UTF8PROC_DECOMP_TYPE_CIRCLE = 7, /**< Circle */
+ UTF8PROC_DECOMP_TYPE_SUPER = 8, /**< Super */
+ UTF8PROC_DECOMP_TYPE_SUB = 9, /**< Sub */
+ UTF8PROC_DECOMP_TYPE_VERTICAL = 10, /**< Vertical */
+ UTF8PROC_DECOMP_TYPE_WIDE = 11, /**< Wide */
+ UTF8PROC_DECOMP_TYPE_NARROW = 12, /**< Narrow */
+ UTF8PROC_DECOMP_TYPE_SMALL = 13, /**< Small */
+ UTF8PROC_DECOMP_TYPE_SQUARE = 14, /**< Square */
+ UTF8PROC_DECOMP_TYPE_FRACTION = 15, /**< Fraction */
+ UTF8PROC_DECOMP_TYPE_COMPAT = 16, /**< Compat */
+} utf8proc_decomp_type_t;
+
+/** Boundclass property. (TR29) */
+typedef enum {
+ UTF8PROC_BOUNDCLASS_START = 0, /**< Start */
+ UTF8PROC_BOUNDCLASS_OTHER = 1, /**< Other */
+ UTF8PROC_BOUNDCLASS_CR = 2, /**< Cr */
+ UTF8PROC_BOUNDCLASS_LF = 3, /**< Lf */
+ UTF8PROC_BOUNDCLASS_CONTROL = 4, /**< Control */
+ UTF8PROC_BOUNDCLASS_EXTEND = 5, /**< Extend */
+ UTF8PROC_BOUNDCLASS_L = 6, /**< L */
+ UTF8PROC_BOUNDCLASS_V = 7, /**< V */
+ UTF8PROC_BOUNDCLASS_T = 8, /**< T */
+ UTF8PROC_BOUNDCLASS_LV = 9, /**< Lv */
+ UTF8PROC_BOUNDCLASS_LVT = 10, /**< Lvt */
+ UTF8PROC_BOUNDCLASS_REGIONAL_INDICATOR = 11, /**< Regional indicator */
+ UTF8PROC_BOUNDCLASS_SPACINGMARK = 12, /**< Spacingmark */
+ UTF8PROC_BOUNDCLASS_PREPEND = 13, /**< Prepend */
+ UTF8PROC_BOUNDCLASS_ZWJ = 14, /**< Zero Width Joiner */
+ UTF8PROC_BOUNDCLASS_E_BASE = 15, /**< Emoji Base */
+ UTF8PROC_BOUNDCLASS_E_MODIFIER = 16, /**< Emoji Modifier */
+ UTF8PROC_BOUNDCLASS_GLUE_AFTER_ZWJ = 17, /**< Glue_After_ZWJ */
+ UTF8PROC_BOUNDCLASS_E_BASE_GAZ = 18, /**< E_BASE + GLUE_AFTER_ZJW */
+} utf8proc_boundclass_t;
+
+/**
+ * Function pointer type passed to @ref utf8proc_map_custom and
+ * @ref utf8proc_decompose_custom, which is used to specify a user-defined
+ * mapping of codepoints to be applied in conjunction with other mappings.
+ */
+typedef utf8proc_int32_t (*utf8proc_custom_func)(utf8proc_int32_t codepoint, void *data);
+
+#if defined(DOXYGEN) || defined(UTF8PROC_DATA_EXPORT)
+/**
+ * Array containing the byte lengths of a UTF-8 encoded codepoint based
+ * on the first byte.
+ */
+UTF8PROC_DLLEXPORT extern const utf8proc_int8_t utf8proc_utf8class[256];
#endif
-UTF8PROC_API
-const char *utf8proc_version(void);
+/**
+ * Returns the utf8proc API version as a string MAJOR.MINOR.PATCH
+ * (http://semver.org format), possibly with a "-dev" suffix for
+ * development versions.
+ */
+UTF8PROC_DLLEXPORT const char *utf8proc_version(void);
+
+/**
+ * Returns an informative error string for the given utf8proc error code
+ * (e.g. the error codes returned by @ref utf8proc_map).
+ */
+UTF8PROC_DLLEXPORT const char *utf8proc_errmsg(utf8proc_ssize_t errcode);
+
+/**
+ * Reads a single codepoint from the UTF-8 sequence being pointed to by `str`.
+ * The maximum number of bytes read is `strlen`, unless `strlen` is
+ * negative (in which case up to 4 bytes are read).
+ *
+ * If a valid codepoint could be read, it is stored in the variable
+ * pointed to by `codepoint_ref`, otherwise that variable will be set to -1.
+ * In case of success, the number of bytes read is returned; otherwise, a
+ * negative error code is returned.
+ */
+UTF8PROC_DLLEXPORT utf8proc_ssize_t utf8proc_iterate(const utf8proc_uint8_t *str, utf8proc_ssize_t strlen, utf8proc_int32_t *codepoint_ref);
+
+/**
+ * Check if a codepoint is valid (regardless of whether it has been
+ * assigned a value by the current Unicode standard).
+ *
+ * @return 1 if the given `codepoint` is valid and otherwise return 0.
+ */
+UTF8PROC_DLLEXPORT utf8proc_bool utf8proc_codepoint_valid(utf8proc_int32_t codepoint);
-UTF8PROC_API
-const char *utf8proc_errmsg(ssize_t errcode);
-/*
- * Returns a static error string for the given error code.
+/**
+ * Encodes the codepoint as an UTF-8 string in the byte array pointed
+ * to by `dst`. This array must be at least 4 bytes long.
+ *
+ * In case of success the number of bytes written is returned, and
+ * otherwise 0 is returned.
+ *
+ * This function does not check whether `codepoint` is valid Unicode.
*/
+UTF8PROC_DLLEXPORT utf8proc_ssize_t utf8proc_encode_char(utf8proc_int32_t codepoint, utf8proc_uint8_t *dst);
-UTF8PROC_API
-ssize_t utf8proc_iterate(const uint8_t *str, ssize_t strlen, int32_t *dst);
-/*
- * Reads a single char from the UTF-8 sequence being pointed to by 'str'.
- * The maximum number of bytes read is 'strlen', unless 'strlen' is
- * negative.
- * If a valid unicode char could be read, it is stored in the variable
- * being pointed to by 'dst', otherwise that variable will be set to -1.
- * In case of success the number of bytes read is returned, otherwise a
- * negative error code is returned.
+/**
+ * Look up the properties for a given codepoint.
+ *
+ * @param codepoint The Unicode codepoint.
+ *
+ * @returns
+ * A pointer to a (constant) struct containing information about
+ * the codepoint.
+ * @par
+ * If the codepoint is unassigned or invalid, a pointer to a special struct is
+ * returned in which `category` is 0 (@ref UTF8PROC_CATEGORY_CN).
*/
+UTF8PROC_DLLEXPORT const utf8proc_property_t *utf8proc_get_property(utf8proc_int32_t codepoint);
-UTF8PROC_API
-bool utf8proc_codepoint_valid(int32_t uc);
-/*
- * Returns 1, if the given unicode code-point is valid, otherwise 0.
+/** Decompose a codepoint into an array of codepoints.
+ *
+ * @param codepoint the codepoint.
+ * @param dst the destination buffer.
+ * @param bufsize the size of the destination buffer.
+ * @param options one or more of the following flags:
+ * - @ref UTF8PROC_REJECTNA - return an error `codepoint` is unassigned
+ * - @ref UTF8PROC_IGNORE - strip "default ignorable" codepoints
+ * - @ref UTF8PROC_CASEFOLD - apply Unicode casefolding
+ * - @ref UTF8PROC_COMPAT - replace certain codepoints with their
+ * compatibility decomposition
+ * - @ref UTF8PROC_CHARBOUND - insert 0xFF bytes before each grapheme cluster
+ * - @ref UTF8PROC_LUMP - lump certain different codepoints together
+ * - @ref UTF8PROC_STRIPMARK - remove all character marks
+ * @param last_boundclass
+ * Pointer to an integer variable containing
+ * the previous codepoint's boundary class if the @ref UTF8PROC_CHARBOUND
+ * option is used. Otherwise, this parameter is ignored.
+ *
+ * @return
+ * In case of success, the number of codepoints written is returned; in case
+ * of an error, a negative error code is returned (@ref utf8proc_errmsg).
+ * @par
+ * If the number of written codepoints would be bigger than `bufsize`, the
+ * required buffer size is returned, while the buffer will be overwritten with
+ * undefined data.
+ */
+UTF8PROC_DLLEXPORT utf8proc_ssize_t utf8proc_decompose_char(
+ utf8proc_int32_t codepoint, utf8proc_int32_t *dst, utf8proc_ssize_t bufsize,
+ utf8proc_option_t options, int *last_boundclass
+);
+
+/**
+ * The same as @ref utf8proc_decompose_char, but acts on a whole UTF-8
+ * string and orders the decomposed sequences correctly.
+ *
+ * If the @ref UTF8PROC_NULLTERM flag in `options` is set, processing
+ * will be stopped, when a NULL byte is encounted, otherwise `strlen`
+ * bytes are processed. The result (in the form of 32-bit unicode
+ * codepoints) is written into the buffer being pointed to by
+ * `buffer` (which must contain at least `bufsize` entries). In case of
+ * success, the number of codepoints written is returned; in case of an
+ * error, a negative error code is returned (@ref utf8proc_errmsg).
+ * See @ref utf8proc_decompose_custom to supply additional transformations.
+ *
+ * If the number of written codepoints would be bigger than `bufsize`, the
+ * required buffer size is returned, while the buffer will be overwritten with
+ * undefined data.
+ */
+UTF8PROC_DLLEXPORT utf8proc_ssize_t utf8proc_decompose(
+ const utf8proc_uint8_t *str, utf8proc_ssize_t strlen,
+ utf8proc_int32_t *buffer, utf8proc_ssize_t bufsize, utf8proc_option_t options
+);
+
+/**
+ * The same as @ref utf8proc_decompose, but also takes a `custom_func` mapping function
+ * that is called on each codepoint in `str` before any other transformations
+ * (along with a `custom_data` pointer that is passed through to `custom_func`).
+ * The `custom_func` argument is ignored if it is `NULL`. See also @ref utf8proc_map_custom.
+ */
+UTF8PROC_DLLEXPORT utf8proc_ssize_t utf8proc_decompose_custom(
+ const utf8proc_uint8_t *str, utf8proc_ssize_t strlen,
+ utf8proc_int32_t *buffer, utf8proc_ssize_t bufsize, utf8proc_option_t options,
+ utf8proc_custom_func custom_func, void *custom_data
+);
+
+/**
+ * Normalizes the sequence of `length` codepoints pointed to by `buffer`
+ * in-place (i.e., the result is also stored in `buffer`).
+ *
+ * @param buffer the (native-endian UTF-32) unicode codepoints to re-encode.
+ * @param length the length (in codepoints) of the buffer.
+ * @param options a bitwise or (`|`) of one or more of the following flags:
+ * - @ref UTF8PROC_NLF2LS - convert LF, CRLF, CR and NEL into LS
+ * - @ref UTF8PROC_NLF2PS - convert LF, CRLF, CR and NEL into PS
+ * - @ref UTF8PROC_NLF2LF - convert LF, CRLF, CR and NEL into LF
+ * - @ref UTF8PROC_STRIPCC - strip or convert all non-affected control characters
+ * - @ref UTF8PROC_COMPOSE - try to combine decomposed codepoints into composite
+ * codepoints
+ * - @ref UTF8PROC_STABLE - prohibit combining characters that would violate
+ * the unicode versioning stability
+ *
+ * @return
+ * In case of success, the length (in codepoints) of the normalized UTF-32 string is
+ * returned; otherwise, a negative error code is returned (@ref utf8proc_errmsg).
+ *
+ * @warning The entries of the array pointed to by `str` have to be in the
+ * range `0x0000` to `0x10FFFF`. Otherwise, the program might crash!
*/
+UTF8PROC_DLLEXPORT utf8proc_ssize_t utf8proc_normalize_utf32(utf8proc_int32_t *buffer, utf8proc_ssize_t length, utf8proc_option_t options);
-UTF8PROC_API
-ssize_t utf8proc_encode_char(int32_t uc, uint8_t *dst);
-/*
- * Encodes the unicode char with the code point 'uc' as an UTF-8 string in
- * the byte array being pointed to by 'dst'. This array has to be at least
- * 4 bytes long.
- * In case of success the number of bytes written is returned,
- * otherwise 0.
- * This function does not check if 'uc' is a valid unicode code point.
+/**
+ * Reencodes the sequence of `length` codepoints pointed to by `buffer`
+ * UTF-8 data in-place (i.e., the result is also stored in `buffer`).
+ * Can optionally normalize the UTF-32 sequence prior to UTF-8 conversion.
+ *
+ * @param buffer the (native-endian UTF-32) unicode codepoints to re-encode.
+ * @param length the length (in codepoints) of the buffer.
+ * @param options a bitwise or (`|`) of one or more of the following flags:
+ * - @ref UTF8PROC_NLF2LS - convert LF, CRLF, CR and NEL into LS
+ * - @ref UTF8PROC_NLF2PS - convert LF, CRLF, CR and NEL into PS
+ * - @ref UTF8PROC_NLF2LF - convert LF, CRLF, CR and NEL into LF
+ * - @ref UTF8PROC_STRIPCC - strip or convert all non-affected control characters
+ * - @ref UTF8PROC_COMPOSE - try to combine decomposed codepoints into composite
+ * codepoints
+ * - @ref UTF8PROC_STABLE - prohibit combining characters that would violate
+ * the unicode versioning stability
+ * - @ref UTF8PROC_CHARBOUND - insert 0xFF bytes before each grapheme cluster
+ *
+ * @return
+ * In case of success, the length (in bytes) of the resulting nul-terminated
+ * UTF-8 string is returned; otherwise, a negative error code is returned
+ * (@ref utf8proc_errmsg).
+ *
+ * @warning The amount of free space pointed to by `buffer` must
+ * exceed the amount of the input data by one byte, and the
+ * entries of the array pointed to by `str` have to be in the
+ * range `0x0000` to `0x10FFFF`. Otherwise, the program might crash!
+ */
+UTF8PROC_DLLEXPORT utf8proc_ssize_t utf8proc_reencode(utf8proc_int32_t *buffer, utf8proc_ssize_t length, utf8proc_option_t options);
+
+/**
+ * Given a pair of consecutive codepoints, return whether a grapheme break is
+ * permitted between them (as defined by the extended grapheme clusters in UAX#29).
+ *
+ * @param state Beginning with Version 29 (Unicode 9.0.0), this algorithm requires
+ * state to break graphemes. This state can be passed in as a pointer
+ * in the `state` argument and should initially be set to 0. If the
+ * state is not passed in (i.e. a null pointer is passed), UAX#29 rules
+ * GB10/12/13 which require this state will not be applied, essentially
+ * matching the rules in Unicode 8.0.0.
+ *
+ * @warning If the state parameter is used, `utf8proc_grapheme_break_stateful` must
+ * be called IN ORDER on ALL potential breaks in a string.
*/
+UTF8PROC_DLLEXPORT utf8proc_bool utf8proc_grapheme_break_stateful(
+ utf8proc_int32_t codepoint1, utf8proc_int32_t codepoint2, utf8proc_int32_t *state);
-UTF8PROC_API
-const utf8proc_property_t *utf8proc_get_property(int32_t uc);
-/*
- * Returns a pointer to a (constant) struct containing information about
- * the unicode char with the given code point 'uc'.
- * If the character is not existent a pointer to a special struct is
- * returned, where 'category' is a NULL pointer.
- * WARNING: The parameter 'uc' has to be in the range of 0x0000 to
- * 0x10FFFF, otherwise the program might crash!
+/**
+ * Same as @ref utf8proc_grapheme_break_stateful, except without support for the
+ * Unicode 9 additions to the algorithm. Supported for legacy reasons.
*/
+UTF8PROC_DLLEXPORT utf8proc_bool utf8proc_grapheme_break(
+ utf8proc_int32_t codepoint1, utf8proc_int32_t codepoint2);
-UTF8PROC_API
-ssize_t utf8proc_decompose_char(
- int32_t uc, int32_t *dst, ssize_t bufsize,
- int options, int *last_boundclass
-);
-/*
- * Writes a decomposition of the unicode char 'uc' into the array being
- * pointed to by 'dst'.
- * Following flags in the 'options' field are regarded:
- * REJECTNA: an unassigned unicode code point leads to an error
- * IGNORE: "default ignorable" chars are stripped
- * CASEFOLD: unicode casefolding is applied
- * COMPAT: replace certain characters with their
- * compatibility decomposition
- * CHARBOUND: Inserts 0xFF bytes before each grapheme cluster
- * LUMP: lumps certain different characters together
- * STRIPMARK: removes all character marks
- * The pointer 'last_boundclass' has to point to an integer variable which
- * is storing the last character boundary class, if the CHARBOUND option
- * is used.
- * In case of success the number of chars written is returned,
- * in case of an error, a negative error code is returned.
- * If the number of written chars would be bigger than 'bufsize',
- * the buffer (up to 'bufsize') has inpredictable data, and the needed
- * buffer size is returned.
- * WARNING: The parameter 'uc' has to be in the range of 0x0000 to
- * 0x10FFFF, otherwise the program might crash!
- */
-
-UTF8PROC_API
-ssize_t utf8proc_decompose(
- const uint8_t *str, ssize_t strlen,
- int32_t *buffer, ssize_t bufsize, int options
-);
-/*
- * Does the same as 'utf8proc_decompose_char', but acts on a whole UTF-8
- * string, and orders the decomposed sequences correctly.
- * If the NULLTERM flag in 'options' is set, processing will be stopped,
- * when a NULL byte is encounted, otherwise 'strlen' bytes are processed.
- * The result in form of unicode code points is written into the buffer
- * being pointed to by 'buffer', having the length of 'bufsize' entries.
- * In case of success the number of chars written is returned,
- * in case of an error, a negative error code is returned.
- * If the number of written chars would be bigger than 'bufsize',
- * the buffer (up to 'bufsize') has inpredictable data, and the needed
- * buffer size is returned.
+
+/**
+ * Given a codepoint `c`, return the codepoint of the corresponding
+ * lower-case character, if any; otherwise (if there is no lower-case
+ * variant, or if `c` is not a valid codepoint) return `c`.
*/
+UTF8PROC_DLLEXPORT utf8proc_int32_t utf8proc_tolower(utf8proc_int32_t c);
-UTF8PROC_API
-ssize_t utf8proc_reencode(int32_t *buffer, ssize_t length, int options);
-/*
- * Reencodes the sequence of unicode characters given by the pointer
- * 'buffer' and 'length' as UTF-8.
- * The result is stored in the same memory area where the data is read.
- * Following flags in the 'options' field are regarded:
- * NLF2LS: converts LF, CRLF, CR and NEL into LS
- * NLF2PS: converts LF, CRLF, CR and NEL into PS
- * NLF2LF: converts LF, CRLF, CR and NEL into LF
- * STRIPCC: strips or converts all non-affected control characters
- * COMPOSE: tries to combine decomposed characters into composite
- * characters
- * STABLE: prohibits combining characters which would violate
- * the unicode versioning stability
- * In case of success the length of the resulting UTF-8 string is
- * returned, otherwise a negative error code is returned.
- * WARNING: The amount of free space being pointed to by 'buffer', has to
- * exceed the amount of the input data by one byte, and the
- * entries of the array pointed to by 'str' have to be in the
- * range of 0x0000 to 0x10FFFF, otherwise the program might
- * crash!
- */
-
-UTF8PROC_API
-ssize_t utf8proc_map(
- const uint8_t *str, ssize_t strlen, uint8_t **dstptr, int options
+/**
+ * Given a codepoint `c`, return the codepoint of the corresponding
+ * upper-case character, if any; otherwise (if there is no upper-case
+ * variant, or if `c` is not a valid codepoint) return `c`.
+ */
+UTF8PROC_DLLEXPORT utf8proc_int32_t utf8proc_toupper(utf8proc_int32_t c);
+
+/**
+ * Given a codepoint `c`, return the codepoint of the corresponding
+ * title-case character, if any; otherwise (if there is no title-case
+ * variant, or if `c` is not a valid codepoint) return `c`.
+ */
+UTF8PROC_DLLEXPORT utf8proc_int32_t utf8proc_totitle(utf8proc_int32_t c);
+
+/**
+ * Given a codepoint, return a character width analogous to `wcwidth(codepoint)`,
+ * except that a width of 0 is returned for non-printable codepoints
+ * instead of -1 as in `wcwidth`.
+ *
+ * @note
+ * If you want to check for particular types of non-printable characters,
+ * (analogous to `isprint` or `iscntrl`), use @ref utf8proc_category. */
+UTF8PROC_DLLEXPORT int utf8proc_charwidth(utf8proc_int32_t codepoint);
+
+/**
+ * Return the Unicode category for the codepoint (one of the
+ * @ref utf8proc_category_t constants.)
+ */
+UTF8PROC_DLLEXPORT utf8proc_category_t utf8proc_category(utf8proc_int32_t codepoint);
+
+/**
+ * Return the two-letter (nul-terminated) Unicode category string for
+ * the codepoint (e.g. `"Lu"` or `"Co"`).
+ */
+UTF8PROC_DLLEXPORT const char *utf8proc_category_string(utf8proc_int32_t codepoint);
+
+/**
+ * Maps the given UTF-8 string pointed to by `str` to a new UTF-8
+ * string, allocated dynamically by `malloc` and returned via `dstptr`.
+ *
+ * If the @ref UTF8PROC_NULLTERM flag in the `options` field is set,
+ * the length is determined by a NULL terminator, otherwise the
+ * parameter `strlen` is evaluated to determine the string length, but
+ * in any case the result will be NULL terminated (though it might
+ * contain NULL characters with the string if `str` contained NULL
+ * characters). Other flags in the `options` field are passed to the
+ * functions defined above, and regarded as described. See also
+ * @ref utfproc_map_custom to supply a custom codepoint transformation.
+ *
+ * In case of success the length of the new string is returned,
+ * otherwise a negative error code is returned.
+ *
+ * @note The memory of the new UTF-8 string will have been allocated
+ * with `malloc`, and should therefore be deallocated with `free`.
+ */
+UTF8PROC_DLLEXPORT utf8proc_ssize_t utf8proc_map(
+ const utf8proc_uint8_t *str, utf8proc_ssize_t strlen, utf8proc_uint8_t **dstptr, utf8proc_option_t options
);
-/*
- * Maps the given UTF-8 string being pointed to by 'str' to a new UTF-8
- * string, which is allocated dynamically, and afterwards pointed to by
- * the pointer being pointed to by 'dstptr'.
- * If the NULLTERM flag in the 'options' field is set, the length is
- * determined by a NULL terminator, otherwise the parameter 'strlen' is
- * evaluated to determine the string length, but in any case the result
- * will be NULL terminated (though it might contain NULL characters
- * before). Other flags in the 'options' field are passed to the functions
- * defined above, and regarded as described.
- * In case of success the length of the new string is returned,
- * otherwise a negative error code is returned.
- * NOTICE: The memory of the new UTF-8 string will have been allocated with
- * 'malloc', and has theirfore to be freed with 'free'.
- */
-
-UTF8PROC_API
-uint8_t *utf8proc_NFD(const uint8_t *str);
-UTF8PROC_API
-uint8_t *utf8proc_NFC(const uint8_t *str);
-UTF8PROC_API
-uint8_t *utf8proc_NFKD(const uint8_t *str);
-UTF8PROC_API
-uint8_t *utf8proc_NFKC(const uint8_t *str);
-/*
- * Returns a pointer to newly allocated memory of a NFD, NFC, NFKD or NFKC
- * normalized version of the null-terminated string 'str'.
+
+/**
+ * Like @ref utf8proc_map, but also takes a `custom_func` mapping function
+ * that is called on each codepoint in `str` before any other transformations
+ * (along with a `custom_data` pointer that is passed through to `custom_func`).
+ * The `custom_func` argument is ignored if it is `NULL`.
+ */
+UTF8PROC_DLLEXPORT utf8proc_ssize_t utf8proc_map_custom(
+ const utf8proc_uint8_t *str, utf8proc_ssize_t strlen, utf8proc_uint8_t **dstptr, utf8proc_option_t options,
+ utf8proc_custom_func custom_func, void *custom_data
+);
+
+/** @name Unicode normalization
+ *
+ * Returns a pointer to newly allocated memory of a NFD, NFC, NFKD or NFKC
+ * normalized version of the null-terminated string `str`. These
+ * are shortcuts to calling @ref utf8proc_map with @ref UTF8PROC_NULLTERM
+ * combined with @ref UTF8PROC_STABLE and flags indicating the normalization.
*/
+/** @{ */
+/** NFD normalization (@ref UTF8PROC_DECOMPOSE). */
+UTF8PROC_DLLEXPORT utf8proc_uint8_t *utf8proc_NFD(const utf8proc_uint8_t *str);
+/** NFC normalization (@ref UTF8PROC_COMPOSE). */
+UTF8PROC_DLLEXPORT utf8proc_uint8_t *utf8proc_NFC(const utf8proc_uint8_t *str);
+/** NFKD normalization (@ref UTF8PROC_DECOMPOSE and @ref UTF8PROC_COMPAT). */
+UTF8PROC_DLLEXPORT utf8proc_uint8_t *utf8proc_NFKD(const utf8proc_uint8_t *str);
+/** NFKC normalization (@ref UTF8PROC_COMPOSE and @ref UTF8PROC_COMPAT). */
+UTF8PROC_DLLEXPORT utf8proc_uint8_t *utf8proc_NFKC(const utf8proc_uint8_t *str);
+/** @} */
#ifdef __cplusplus
}
#endif
#endif
-#endif /* SVN_INTERNAL_UTF8PROC */
Modified: subversion/branches/better-pristines/subversion/tests/cmdline/davautocheck.sh
URL: http://svn.apache.org/viewvc/subversion/branches/better-pristines/subversion/tests/cmdline/davautocheck.sh?rev=1809147&r1=1809146&r2=1809147&view=diff
==============================================================================
--- subversion/branches/better-pristines/subversion/tests/cmdline/davautocheck.sh (original)
+++ subversion/branches/better-pristines/subversion/tests/cmdline/davautocheck.sh Thu Sep 21 10:49:13 2017
@@ -778,14 +778,22 @@ else
|| fail "Subversion client couldn't find and/or load ra_dav library '$HTTP_LIBRARY'"
fi
+# Our configure script extracts the HTTPD version from
+# headers. However, that may not be the same as the runtime version;
+# an example of this discrepancy occurs on OSX 1.9.5, where the
+# headers report 2.2.26 but the server reports 2.2.29. Since our tests
+# use the version to interpret test case results, use the actual
+# runtime version here to avoid spurious test failures.
+HTTPD_VERSION="$($APXS -q HTTPD_VERSION)"
+
if [ $# = 0 ]; then
- TIME_CMD "$MAKE" check "BASE_URL=$BASE_URL" $SSL_MAKE_VAR
+ TIME_CMD "$MAKE" check "BASE_URL=$BASE_URL" "HTTPD_VERSION=$HTTPD_VERSION" $SSL_MAKE_VAR
r=$?
else
(cd "$ABS_BUILDDIR/subversion/tests/cmdline/"
TEST="$1"
shift
- TIME_CMD "$ABS_SRCDIR/subversion/tests/cmdline/${TEST}_tests.py" "--url=$BASE_URL" $SSL_TEST_ARG "$@")
+ TIME_CMD "$ABS_SRCDIR/subversion/tests/cmdline/${TEST}_tests.py" "--url=$BASE_URL" "--httpd-version=$HTTPD_VERSION" $SSL_TEST_ARG "$@")
r=$?
fi
Modified: subversion/branches/better-pristines/subversion/tests/libsvn_client/conflicts-test.c
URL: http://svn.apache.org/viewvc/subversion/branches/better-pristines/subversion/tests/libsvn_client/conflicts-test.c?rev=1809147&r1=1809146&r2=1809147&view=diff
==============================================================================
--- subversion/branches/better-pristines/subversion/tests/libsvn_client/conflicts-test.c (original)
+++ subversion/branches/better-pristines/subversion/tests/libsvn_client/conflicts-test.c Thu Sep 21 10:49:13 2017
@@ -4906,6 +4906,7 @@ test_cherry_pick_post_move_edit(const sv
svn_client_ctx_t *ctx;
svn_client_conflict_t *conflict;
svn_boolean_t tree_conflicted;
+ svn_stringbuf_t *buf;
SVN_ERR(svn_test__sandbox_create(b,
"test_cherry_pick_post_move_edit",
@@ -4918,20 +4919,24 @@ test_cherry_pick_post_move_edit(const sv
/* On "trunk", move the file mu. */
SVN_ERR(sbox_wc_move(b, "A/mu", "A/mu-moved"));
SVN_ERR(sbox_wc_commit(b, "")); /* r3 */
- /* On "trunk", edit mu-moved. This will be r4, which we'll cherry-pick. */
- SVN_ERR(sbox_file_write(b, "A/mu-moved", "Modified content.\n"));
+ /* On "trunk", edit mu-moved. This will be r4. */
+ SVN_ERR(sbox_file_write(b, "A/mu-moved", "Modified content." APR_EOL_STR));
SVN_ERR(sbox_wc_commit(b, "")); /* r4 */
+ /* On "trunk", edit mu-moved. This will be r5, which we'll cherry-pick. */
+ SVN_ERR(sbox_file_write(b, "A/mu-moved",
+ "More modified content." APR_EOL_STR));
+ SVN_ERR(sbox_wc_commit(b, "")); /* r5 */
SVN_ERR(sbox_wc_update(b, "", SVN_INVALID_REVNUM));
- /* Perform a cherry-pick merge of r4 from A to A1. */
+ /* Perform a cherry-pick merge of r5 from A to A1. */
SVN_ERR(svn_test__create_client_ctx(&ctx, b, b->pool));
trunk_url = apr_pstrcat(b->pool, b->repos_url, "/A", SVN_VA_NULL);
peg_rev.kind = svn_opt_revision_number;
- peg_rev.value.number = 4;
+ peg_rev.value.number = 5;
merge_range.start.kind = svn_opt_revision_number;
- merge_range.start.value.number = 3;
+ merge_range.start.value.number = 4;
merge_range.end.kind = svn_opt_revision_number;
- merge_range.end.value.number = 4;
+ merge_range.end.value.number = 5;
ranges_to_merge = apr_array_make(b->pool, 1,
sizeof(svn_opt_revision_range_t *));
APR_ARRAY_PUSH(ranges_to_merge, svn_opt_revision_range_t *) = &merge_range;
@@ -4974,6 +4979,16 @@ test_cherry_pick_post_move_edit(const sv
svn_client_conflict_option_local_move_file_text_merge,
ctx, b->pool));
+ /* The node "A1/mu-moved" should no longer exist. */
+ SVN_TEST_ASSERT_ERROR(svn_client_conflict_get(&conflict,
+ sbox_wc_path(b, "A1/mu-moved"),
+ ctx, pool, pool),
+ SVN_ERR_WC_PATH_NOT_FOUND);
+
+ /* And "A1/mu" should have expected contents. */
+ SVN_ERR(svn_stringbuf_from_file2(&buf, sbox_wc_path(b, "A1/mu"), pool));
+ SVN_TEST_STRING_ASSERT(buf->data, "More modified content." APR_EOL_STR);
+
return SVN_NO_ERROR;
}