Timerix/utf8proc
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

Fix #26: use doxygen for generating API docs

Browse Source
This commit is contained in:
Jonas Fonseca 2015-03-17 11:58:48 -04:00
parent 321cb997c5
commit 03a4e8854a
4 changed files with 1947 additions and 313 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

1
.gitignore vendored
View File

@ -12,6 +12,7 @@
data/*.txt data/*.txt
data/*.ttf data/*.ttf
data/*.sfd data/*.sfd
/docs/
bench/bench bench/bench
bench/icu bench/icu
bench/unistring bench/unistring

1528
Doxyfile Normal file
View File

File diff suppressed because it is too large Load Diff

10
utf8proc.c
View File

@ -234,7 +234,7 @@ DLLEXPORT int utf8proc_charwidth(int32_t c) {
return utf8proc_get_property(c)->charwidth; return utf8proc_get_property(c)->charwidth;
} }
DLLEXPORT int utf8proc_category(int32_t c) { DLLEXPORT utf8proc_category_t utf8proc_category(int32_t c) {
return utf8proc_get_property(c)->category; return utf8proc_get_property(c)->category;
} }
@ -247,7 +247,7 @@ DLLEXPORT const char *utf8proc_category_string(int32_t c) {
return utf8proc_decompose_char((replacement_uc), dst, bufsize, \ return utf8proc_decompose_char((replacement_uc), dst, bufsize, \
options & ~UTF8PROC_LUMP, last_boundclass) options & ~UTF8PROC_LUMP, last_boundclass)
DLLEXPORT ssize_t utf8proc_decompose_char(int32_t uc, int32_t *dst, ssize_t bufsize, int options, int *last_boundclass) { DLLEXPORT ssize_t utf8proc_decompose_char(int32_t uc, int32_t *dst, ssize_t bufsize, utf8proc_option_t options, int *last_boundclass) {
const utf8proc_property_t *property; const utf8proc_property_t *property;
utf8proc_propval_t category; utf8proc_propval_t category;
int32_t hangul_sindex; int32_t hangul_sindex;
@ -353,7 +353,7 @@ DLLEXPORT ssize_t utf8proc_decompose_char(int32_t uc, int32_t *dst, ssize_t bufs
DLLEXPORT ssize_t utf8proc_decompose( DLLEXPORT ssize_t utf8proc_decompose(
const uint8_t *str, ssize_t strlen, const uint8_t *str, ssize_t strlen,
int32_t *buffer, ssize_t bufsize, int options int32_t *buffer, ssize_t bufsize, utf8proc_option_t options
) { ) {
/* strlen will be ignored, if UTF8PROC_NULLTERM is set in options */ /* strlen will be ignored, if UTF8PROC_NULLTERM is set in options */
ssize_t wpos = 0; ssize_t wpos = 0;
@ -413,7 +413,7 @@ DLLEXPORT ssize_t utf8proc_decompose(
return wpos; return wpos;
} }
DLLEXPORT ssize_t utf8proc_reencode(int32_t *buffer, ssize_t length, int options) { DLLEXPORT ssize_t utf8proc_reencode(int32_t *buffer, ssize_t length, utf8proc_option_t options) {
/* UTF8PROC_NULLTERM option will be ignored, 'length' is never ignored /* UTF8PROC_NULLTERM option will be ignored, 'length' is never ignored
ASSERT: 'buffer' has one spare byte of free space at the end! */ ASSERT: 'buffer' has one spare byte of free space at the end! */
if (options & (UTF8PROC_NLF2LS | UTF8PROC_NLF2PS | UTF8PROC_STRIPCC)) { if (options & (UTF8PROC_NLF2LS | UTF8PROC_NLF2PS | UTF8PROC_STRIPCC)) {
@ -529,7 +529,7 @@ DLLEXPORT ssize_t utf8proc_reencode(int32_t *buffer, ssize_t length, int options
} }
DLLEXPORT ssize_t utf8proc_map( DLLEXPORT ssize_t utf8proc_map(
const uint8_t *str, ssize_t strlen, uint8_t **dstptr, int options const uint8_t *str, ssize_t strlen, uint8_t **dstptr, utf8proc_option_t options
) { ) {
int32_t *buffer; int32_t *buffer;
ssize_t result; ssize_t result;

585
utf8proc.h
View File

@ -21,12 +21,11 @@
*/ */
/* /**
* File name: utf8proc.h * @mainpage
*
* uf8proc is a mapping tool for UTF-8 strings with the following features:
* *
* Description:
* Header files for utf8proc, which is a mapping tool for UTF-8 strings
* with following features:
* - decomposing and composing of strings * - decomposing and composing of strings
* - replacing compatibility characters with their equivalents * - replacing compatibility characters with their equivalents
* - stripping of "default ignorable characters" * - stripping of "default ignorable characters"
@ -44,9 +43,13 @@
* - rejection of illegal UTF-8 data * - rejection of illegal UTF-8 data
* (i.e. UTF-8 encoded UTF-16 surrogates) * (i.e. UTF-8 encoded UTF-16 surrogates)
* - support for korean hangul characters * - support for korean hangul characters
*
* Unicode Version 7.0.0 is supported. * Unicode Version 7.0.0 is supported.
*
* See @ref utf8proc.h for the API.
*/ */
/** @file */
#ifndef UTF8PROC_H #ifndef UTF8PROC_H
#define UTF8PROC_H #define UTF8PROC_H
@ -95,79 +98,111 @@ extern "C" {
#define SSIZE_MAX ((size_t)SIZE_MAX/2) #define SSIZE_MAX ((size_t)SIZE_MAX/2)
#endif #endif
#define UTF8PROC_NULLTERM (1<<0) /**
#define UTF8PROC_STABLE (1<<1) * Option flags used by several functions in the library.
#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: Compatibility 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.md 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
*/ */
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". */
UTF8PROC_IGNORE = (1<<5),
/** Return an error, if the input contains unassigned code points. */
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 #define UTF8PROC_ERROR_NOMEM -1
/** The given string is too long to be processed. */
#define UTF8PROC_ERROR_OVERFLOW -2 #define UTF8PROC_ERROR_OVERFLOW -2
/** The given string is not a legal UTF-8 string. */
#define UTF8PROC_ERROR_INVALIDUTF8 -3 #define UTF8PROC_ERROR_INVALIDUTF8 -3
/** The @ref UTF8PROC_REJECTNA flag was set and an unassigned code point was found. */
#define UTF8PROC_ERROR_NOTASSIGNED -4 #define UTF8PROC_ERROR_NOTASSIGNED -4
/** Invalid options have been used. */
#define UTF8PROC_ERROR_INVALIDOPTS -5 #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 int16_t utf8proc_propval_t; typedef int16_t utf8proc_propval_t;
/** Struct containing information about a codepoint. */
typedef struct utf8proc_property_struct { typedef struct utf8proc_property_struct {
/**
* Unicode category.
* @see utf8proc_category_t.
*/
utf8proc_propval_t category; utf8proc_propval_t category;
utf8proc_propval_t combining_class; utf8proc_propval_t combining_class;
/**
* Bidirectional class.
* @see utf8proc_bidi_class_t.
*/
utf8proc_propval_t bidi_class; utf8proc_propval_t bidi_class;
/**
* @anchor Decomposition type.
* @see utf8proc_decomp_type_t.
*/
utf8proc_propval_t decomp_type; utf8proc_propval_t decomp_type;
const int32_t *decomp_mapping; const int32_t *decomp_mapping;
const int32_t *casefold_mapping; const int32_t *casefold_mapping;
@ -178,256 +213,326 @@ typedef struct utf8proc_property_struct {
int32_t comb2nd_index; int32_t comb2nd_index;
unsigned bidi_mirrored:1; unsigned bidi_mirrored:1;
unsigned comp_exclusion:1; 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 ignorable:1;
unsigned control_boundary:1; unsigned control_boundary:1;
/**
* Boundclass.
* @see utf8proc_boundclass_t.
*/
unsigned boundclass:4; unsigned boundclass:4;
/** The width of the codepoint. */
unsigned charwidth:2; unsigned charwidth:2;
} utf8proc_property_t; } utf8proc_property_t;
#define UTF8PROC_CATEGORY_CN 0 /** Unicode categories. */
#define UTF8PROC_CATEGORY_LU 1 typedef enum {
#define UTF8PROC_CATEGORY_LL 2 UTF8PROC_CATEGORY_CN = 0, /**< Other, not assigned */
#define UTF8PROC_CATEGORY_LT 3 UTF8PROC_CATEGORY_LU = 1, /**< Letter, uppercase */
#define UTF8PROC_CATEGORY_LM 4 UTF8PROC_CATEGORY_LL = 2, /**< Letter, lowercase */
#define UTF8PROC_CATEGORY_LO 5 UTF8PROC_CATEGORY_LT = 3, /**< Letter, titlecase */
#define UTF8PROC_CATEGORY_MN 6 UTF8PROC_CATEGORY_LM = 4, /**< Letter, modifier */
#define UTF8PROC_CATEGORY_MC 7 UTF8PROC_CATEGORY_LO = 5, /**< Letter, other */
#define UTF8PROC_CATEGORY_ME 8 UTF8PROC_CATEGORY_MN = 6, /**< Mark, nonspacing */
#define UTF8PROC_CATEGORY_ND 9 UTF8PROC_CATEGORY_MC = 7, /**< Mark, spacing combining */
#define UTF8PROC_CATEGORY_NL 10 UTF8PROC_CATEGORY_ME = 8, /**< Mark, enclosing */
#define UTF8PROC_CATEGORY_NO 11 UTF8PROC_CATEGORY_ND = 9, /**< Number, decimal digit */
#define UTF8PROC_CATEGORY_PC 12 UTF8PROC_CATEGORY_NL = 10, /**< Number, letter */
#define UTF8PROC_CATEGORY_PD 13 UTF8PROC_CATEGORY_NO = 11, /**< Number, other */
#define UTF8PROC_CATEGORY_PS 14 UTF8PROC_CATEGORY_PC = 12, /**< Punctuation, connector */
#define UTF8PROC_CATEGORY_PE 15 UTF8PROC_CATEGORY_PD = 13, /**< Punctuation, dash */
#define UTF8PROC_CATEGORY_PI 16 UTF8PROC_CATEGORY_PS = 14, /**< Punctuation, open */
#define UTF8PROC_CATEGORY_PF 17 UTF8PROC_CATEGORY_PE = 15, /**< Punctuation, close */
#define UTF8PROC_CATEGORY_PO 18 UTF8PROC_CATEGORY_PI = 16, /**< Punctuation, initial quote */
#define UTF8PROC_CATEGORY_SM 19 UTF8PROC_CATEGORY_PF = 17, /**< Punctuation, final quote */
#define UTF8PROC_CATEGORY_SC 20 UTF8PROC_CATEGORY_PO = 18, /**< Punctuation, other */
#define UTF8PROC_CATEGORY_SK 21 UTF8PROC_CATEGORY_SM = 19, /**< Symbol, math */
#define UTF8PROC_CATEGORY_SO 22 UTF8PROC_CATEGORY_SC = 20, /**< Symbol, currency */
#define UTF8PROC_CATEGORY_ZS 23 UTF8PROC_CATEGORY_SK = 21, /**< Symbol, modifier */
#define UTF8PROC_CATEGORY_ZL 24 UTF8PROC_CATEGORY_SO = 22, /**< Symbol, other */
#define UTF8PROC_CATEGORY_ZP 25 UTF8PROC_CATEGORY_ZS = 23, /**< Separator, space */
#define UTF8PROC_CATEGORY_CC 26 UTF8PROC_CATEGORY_ZL = 24, /**< Separator, line */
#define UTF8PROC_CATEGORY_CF 27 UTF8PROC_CATEGORY_ZP = 25, /**< Separator, paragraph */
#define UTF8PROC_CATEGORY_CS 28 UTF8PROC_CATEGORY_CC = 26, /**< Other, control */
#define UTF8PROC_CATEGORY_CO 29 UTF8PROC_CATEGORY_CF = 27, /**< Other, format */
#define UTF8PROC_BIDI_CLASS_L 1 UTF8PROC_CATEGORY_CS = 28, /**< Other, surrogate */
#define UTF8PROC_BIDI_CLASS_LRE 2 UTF8PROC_CATEGORY_CO = 29, /**< Other, private use */
#define UTF8PROC_BIDI_CLASS_LRO 3 } utf8proc_category_t;
#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_BIDI_CLASS_LRI 20 /* new in Unicode 6.3 */
#define UTF8PROC_BIDI_CLASS_RLI 21 /* new in Unicode 6.3 */
#define UTF8PROC_BIDI_CLASS_FSI 22 /* new in Unicode 6.3 */
#define UTF8PROC_BIDI_CLASS_PDI 23 /* new in Unicode 6.3 */
#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
/* values for boundclass property: */ /** Bidirectional character classes. */
#define UTF8PROC_BOUNDCLASS_START 0 typedef enum {
#define UTF8PROC_BOUNDCLASS_OTHER 1 UTF8PROC_BIDI_CLASS_L = 1, /**< Left-to-Right */
#define UTF8PROC_BOUNDCLASS_CR 2 UTF8PROC_BIDI_CLASS_LRE = 2, /**< Left-to-Right Embedding */
#define UTF8PROC_BOUNDCLASS_LF 3 UTF8PROC_BIDI_CLASS_LRO = 3, /**< Left-to-Right Override */
#define UTF8PROC_BOUNDCLASS_CONTROL 4 UTF8PROC_BIDI_CLASS_R = 4, /**< Right-to-Left */
#define UTF8PROC_BOUNDCLASS_EXTEND 5 UTF8PROC_BIDI_CLASS_AL = 5, /**< Right-to-Left Arabic */
#define UTF8PROC_BOUNDCLASS_L 6 UTF8PROC_BIDI_CLASS_RLE = 6, /**< Right-to-Left Embedding */
#define UTF8PROC_BOUNDCLASS_V 7 UTF8PROC_BIDI_CLASS_RLO = 7, /**< Right-to-Left Override */
#define UTF8PROC_BOUNDCLASS_T 8 UTF8PROC_BIDI_CLASS_PDF = 8, /**< Pop Directional Format */
#define UTF8PROC_BOUNDCLASS_LV 9 UTF8PROC_BIDI_CLASS_EN = 9, /**< European Number */
#define UTF8PROC_BOUNDCLASS_LVT 10 UTF8PROC_BIDI_CLASS_ES = 10, /**< European Separator */
#define UTF8PROC_BOUNDCLASS_REGIONAL_INDICATOR 11 UTF8PROC_BIDI_CLASS_ET = 11, /**< European Number Terminator */
#define UTF8PROC_BOUNDCLASS_SPACINGMARK 12 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. */
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_t;
/**
* Array containing the byte lengths of a UTF-8 encoded codepoint based
* on the first byte.
*/
DLLEXPORT extern const int8_t utf8proc_utf8class[256]; DLLEXPORT extern const int8_t utf8proc_utf8class[256];
/**
* Returns the version as a string.
*/
DLLEXPORT const char *utf8proc_version(void); DLLEXPORT const char *utf8proc_version(void);
DLLEXPORT const char *utf8proc_errmsg(ssize_t errcode); /**
/* * Con
* Returns a static error string for the given error code. * Returns a static error string for the given error code.
*/ */
DLLEXPORT const char *utf8proc_errmsg(ssize_t errcode);
DLLEXPORT ssize_t utf8proc_iterate(const uint8_t *str, ssize_t strlen, int32_t *dst); /**
/* * Reads a single codepoint from the UTF-8 sequence being pointed to by 'str'.
* 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 * The maximum number of bytes read is 'strlen', unless 'strlen' is
* negative. * negative (in which case up to 4 bytes are read).
* 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. * If a valid codepoint could be read, it is stored in the variable
* being 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 * In case of success the number of bytes read is returned, otherwise a
* negative error code is returned. * negative error code is returned.
*/ */
DLLEXPORT ssize_t utf8proc_iterate(const uint8_t *str, ssize_t strlen, int32_t *codepoint_ref);
DLLEXPORT bool utf8proc_codepoint_valid(int32_t uc); /**
/* * Check if a codepoint is valid.
* Returns 1, if the given unicode code-point is valid, otherwise 0. *
* @return 1, if the given codepoint is valid, otherwise 0.
*/ */
DLLEXPORT bool utf8proc_codepoint_valid(int32_t codepoint);
DLLEXPORT ssize_t utf8proc_encode_char(int32_t uc, uint8_t *dst); /**
/* * Encodes the codepoint as an UTF-8 string in
* 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 * the byte array being pointed to by 'dst'. This array has to be at least
* 4 bytes long. * 4 bytes long.
*
* In case of success the number of bytes written is returned, * In case of success the number of bytes written is returned,
* otherwise 0. * otherwise 0.
* This function does not check if 'uc' is a valid unicode code point. *
* This function does not check if the codepoint is a valid unicode code point.
*/ */
DLLEXPORT ssize_t utf8proc_encode_char(int32_t codepoint, uint8_t *dst);
DLLEXPORT const utf8proc_property_t *utf8proc_get_property(int32_t uc); /**
/* * Lookup the properties for a given codepoint.
* Returns a pointer to a (constant) struct containing information about *
* the unicode char with the given code point 'uc'. * @param codepoint The codepoint.
* If the character is not existent a pointer to a special struct is *
* returned, where 'category' is 0 (UTF8PROC_CATEGORY_CN). * @returns
* A pointer to a (constant) struct containing information about
* the codepoint.
* @par
* If the codepoint is not existent a pointer to a special struct is
* returned, where `category` is 0 (@ref UTF8PROC_CATEGORY_CN).
*/ */
DLLEXPORT const utf8proc_property_t *utf8proc_get_property(int32_t codepoint);
DLLEXPORT ssize_t utf8proc_decompose_char( /** Decompose a codepoint into an array of codepoints.
int32_t uc, int32_t *dst, ssize_t bufsize, *
int options, int *last_boundclass * @param codepoint the codepoint.
); * @param dst the destination buffer.
/* * @param bufsize the size of the destination buffer.
* Writes a decomposition of the unicode char 'uc' into the array being * @param options one or more of the following flags:
* pointed to by 'dst'. * - @ref UTF8PROC_REJECTNA - return an error `codepoint` is unassigned
* Following flags in the 'options' field are regarded: * - @ref UTF8PROC_IGNORE - strip "default ignorable" codepoints
* REJECTNA: an unassigned unicode code point leads to an error * - @ref UTF8PROC_CASEFOLD - apply Unicode casefolding
* IGNORE: "default ignorable" chars are stripped * - @ref UTF8PROC_COMPAT - replace certain codepoints with their
* CASEFOLD: unicode casefolding is applied
* COMPAT: replace certain characters with their
* compatibility decomposition * compatibility decomposition
* CHARBOUND: Inserts 0xFF bytes before each grapheme cluster * - @ref UTF8PROC_CHARBOUND - insert 0xFF bytes before each grapheme cluster
* LUMP: lumps certain different characters together * - @ref UTF8PROC_LUMP - lump certain different codepoints together
* STRIPMARK: removes all character marks * - @ref UTF8PROC_STRIPMARK - remove all character marks
* The pointer 'last_boundclass' has to point to an integer variable which * @param last_boundclass
* is storing the last character boundary class, if the CHARBOUND option * This pointer has to point to an integer variable which is storing
* is used. * the last codepoint's boundary class, if the @ref UTF8PROC_CHARBOUND
* In case of success the number of chars written is returned, * option is used.
* in case of an error, a negative error code is returned. *
* If the number of written chars would be bigger than 'bufsize', * @return
* the buffer (up to 'bufsize') has inpredictable data, and the needed * In case of success the number of codepoints written is returned, in case
* of an error, a negative error code is returned.
* @par
* If the number of written codepoints would be bigger than 'bufsize', the
* buffer (up to 'bufsize') has inpredictable data, and the needed
* buffer size is returned. * buffer size is returned.
*/ */
DLLEXPORT ssize_t utf8proc_decompose_char(
DLLEXPORT ssize_t utf8proc_decompose( int32_t codepoint, int32_t *dst, ssize_t bufsize,
const uint8_t *str, ssize_t strlen, utf8proc_option_t options, int *last_boundclass
int32_t *buffer, ssize_t bufsize, int options
); );
/*
/**
* Does the same as 'utf8proc_decompose_char', but acts on a whole UTF-8 * Does the same as 'utf8proc_decompose_char', but acts on a whole UTF-8
* string, and orders the decomposed sequences correctly. * string, and orders the decomposed sequences correctly.
* If the NULLTERM flag in 'options' is set, processing will be stopped, *
* 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. * when a NULL byte is encounted, otherwise 'strlen' bytes are processed.
* The result in form of unicode code points is written into the buffer * The result in form of unicode code points is written into the buffer
* being pointed to by 'buffer', having the length of 'bufsize' entries. * 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 success the number of codepoints written is returned,
* in case of an error, a negative error code is returned. * in case of an error, a negative error code is returned.
* If the number of written chars would be bigger than 'bufsize', *
* If the number of written codepoints would be bigger than 'bufsize',
* the buffer (up to 'bufsize') has inpredictable data, and the needed * the buffer (up to 'bufsize') has inpredictable data, and the needed
* buffer size is returned. * buffer size is returned.
*/ */
DLLEXPORT ssize_t utf8proc_decompose(
const uint8_t *str, ssize_t strlen,
int32_t *buffer, ssize_t bufsize, utf8proc_option_t options
);
DLLEXPORT ssize_t utf8proc_reencode(int32_t *buffer, ssize_t length, int options); /**
/* * Reencodes the sequence of codepoints given by the pointer
* Reencodes the sequence of unicode characters given by the pointer
* 'buffer' and 'length' as UTF-8. * 'buffer' and 'length' as UTF-8.
*
* The result is stored in the same memory area where the data is read. * 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 * @param buffer the (native-endian UTF-32) unicode codepoints to re-encode.
* NLF2PS: converts LF, CRLF, CR and NEL into PS * @param length the length (in codepoints) of the buffer.
* NLF2LF: converts LF, CRLF, CR and NEL into LF * @param options one or more of the following flags:
* STRIPCC: strips or converts all non-affected control characters * - @ref UTF8PROC_NLF2LS - convert LF, CRLF, CR and NEL into LS
* COMPOSE: tries to combine decomposed characters into composite * - @ref UTF8PROC_NLF2PS - convert LF, CRLF, CR and NEL into PS
* characters * - @ref UTF8PROC_NLF2LF - convert LF, CRLF, CR and NEL into LF
* STABLE: prohibits combining characters which would violate * - @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 which would violate
* the unicode versioning stability * the unicode versioning stability
*
* @return
* In case of success the length of the resulting UTF-8 string is * In case of success the length of the resulting UTF-8 string is
* returned, otherwise a negative error code is returned. * returned, otherwise a negative error code is returned.
* WARNING: The amount of free space being pointed to by 'buffer', has to *
* @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 * 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 * entries of the array pointed to by 'str' have to be in the
* range of 0x0000 to 0x10FFFF, otherwise the program might * range of 0x0000 to 0x10FFFF, otherwise the program might
* crash! * crash!
*/ */
DLLEXPORT ssize_t utf8proc_reencode(int32_t *buffer, ssize_t length, utf8proc_option_t options);
DLLEXPORT bool utf8proc_grapheme_break(int32_t c1, int32_t c2); /**
/* * Given a pair of consecutive codepoints, return whether a grapheme break is
* Given a pair of consecutive codepoints (c1,c2), return whether a grapheme break is
* permitted between them (as defined by the extended grapheme clusters in UAX#29). * permitted between them (as defined by the extended grapheme clusters in UAX#29).
*/ */
DLLEXPORT bool utf8proc_grapheme_break(int32_t codepoint1, int32_t codepoint2);
DLLEXPORT int utf8proc_charwidth(int32_t c); /**
/* Given a codepoint c, return a character width analogous to wcwidth(c), * Given a codepoint, return a character width analogous to wcwidth(codepoint),
except that a width of 0 is returned for non-printable characters * except that a width of 0 is returned for non-printable codepoints
instead of -1 as in wcwidth. * 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. */
DLLEXPORT int utf8proc_charwidth(int32_t codepoint);
If you want to check for particular types of non-printable characters, /**
(analogous to isprint or iscntrl), use utf8proc_category(c). */ * Return the Unicode category for the codepoint (one of the
* @ref utf8proc_category_t constants.)
*/
DLLEXPORT utf8proc_category_t utf8proc_category(int32_t codepoint);
DLLEXPORT int utf8proc_category(int32_t c); /**
/* Return the Unicode character category for c (one of the * Return the two-letter (nul-terminated) Unicode category string for
UTF8PROC_CATEGORY_* constants.) */ * the codepoint (e.g. "Lu" or "Co").
*/
DLLEXPORT const char *utf8proc_category_string(int32_t codepoint);
DLLEXPORT const char *utf8proc_category_string(int32_t c); /**
/* Return the two-letter (nul-terminated) Unicode category string for
c (e.g. "Lu" or "Co"). */
DLLEXPORT ssize_t utf8proc_map(
const uint8_t *str, ssize_t strlen, uint8_t **dstptr, int options
);
/*
* Maps the given UTF-8 string being pointed to by 'str' to a new UTF-8 * 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 * string, which is allocated dynamically, and afterwards pointed to by
* the pointer being pointed to by 'dstptr'. * the pointer being pointed to by 'dstptr'.
* If the NULLTERM flag in the 'options' field is set, the length is *
* 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 * determined by a NULL terminator, otherwise the parameter 'strlen' is
* evaluated to determine the string length, but in any case the result * evaluated to determine the string length, but in any case the result
* will be NULL terminated (though it might contain NULL characters * will be NULL terminated (though it might contain NULL characters
* before). Other flags in the 'options' field are passed to the functions * before). Other flags in the 'options' field are passed to the
* defined above, and regarded as described. * functions defined above, and regarded as described.
*
* In case of success the length of the new string is returned, * In case of success the length of the new string is returned,
* otherwise a negative error code 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'. * *NOTICE*: The memory of the new UTF-8 string will have been allocated
* with 'malloc', and has theirfore to be freed with 'free'.
*/ */
DLLEXPORT ssize_t utf8proc_map(
const uint8_t *str, ssize_t strlen, uint8_t **dstptr, utf8proc_option_t options
);
/** @name Normalized versions.
*
* Returns a pointer to newly allocated memory of a NFD, NFC, NFKD or NFKC
* normalized version of the null-terminated string 'str'.
*/
/** @{ */
DLLEXPORT uint8_t *utf8proc_NFD(const uint8_t *str); DLLEXPORT uint8_t *utf8proc_NFD(const uint8_t *str);
DLLEXPORT uint8_t *utf8proc_NFC(const uint8_t *str); DLLEXPORT uint8_t *utf8proc_NFC(const uint8_t *str);
DLLEXPORT uint8_t *utf8proc_NFKD(const uint8_t *str); DLLEXPORT uint8_t *utf8proc_NFKD(const uint8_t *str);
DLLEXPORT uint8_t *utf8proc_NFKC(const uint8_t *str); DLLEXPORT 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'.
*/
#ifdef __cplusplus #ifdef __cplusplus
} }