tommy/libpostal
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

[unicode] Upgrading to JuliaLang's utf8proc (Unicode 7, maintained)

Browse Source
This commit is contained in:
Al
2015-03-17 12:20:08 -04:00
parent 621b25c964
commit f787851754
3 changed files with 13170 additions and 10233 deletions
Download Patch File Download Diff File Expand all files Collapse all files

169
src/utf8proc/utf8proc.c
View File

@@ -43,7 +43,7 @@
#include "utf8proc_data.c" #include "utf8proc_data.c"
const int8_t utf8proc_utf8class[256] = { DLLEXPORT const int8_t utf8proc_utf8class[256] = {
1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1,
1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1,
1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1,
@@ -81,25 +81,14 @@ const int8_t utf8proc_utf8class[256] = {
#define UTF8PROC_HANGUL_S_START 0xAC00 #define UTF8PROC_HANGUL_S_START 0xAC00
#define UTF8PROC_HANGUL_S_END 0xD7A4 #define UTF8PROC_HANGUL_S_END 0xD7A4
/* Should follow semantic-versioning rules (semver.org) based on API
#define UTF8PROC_BOUNDCLASS_START 0 compatibility. (Note that the shared-library version number will
#define UTF8PROC_BOUNDCLASS_OTHER 1 be different, being based on ABI compatibility.): */
#define UTF8PROC_BOUNDCLASS_CR 2 DLLEXPORT const char *utf8proc_version(void) {
#define UTF8PROC_BOUNDCLASS_LF 3 return "1.2-dev";
#define UTF8PROC_BOUNDCLASS_CONTROL 4
#define UTF8PROC_BOUNDCLASS_EXTEND 5
#define UTF8PROC_BOUNDCLASS_L 6
#define UTF8PROC_BOUNDCLASS_V 7
#define UTF8PROC_BOUNDCLASS_T 8
#define UTF8PROC_BOUNDCLASS_LV 9
#define UTF8PROC_BOUNDCLASS_LVT 10
const char *utf8proc_version(void) {
return "1.1.6";
} }
const char *utf8proc_errmsg(ssize_t errcode) { DLLEXPORT const char *utf8proc_errmsg(ssize_t errcode) {
switch (errcode) { switch (errcode) {
case UTF8PROC_ERROR_NOMEM: case UTF8PROC_ERROR_NOMEM:
return "Memory for processing UTF-8 data could not be allocated."; return "Memory for processing UTF-8 data could not be allocated.";
@@ -112,11 +101,11 @@ const char *utf8proc_errmsg(ssize_t errcode) {
case UTF8PROC_ERROR_INVALIDOPTS: case UTF8PROC_ERROR_INVALIDOPTS:
return "Invalid options for UTF-8 processing chosen."; return "Invalid options for UTF-8 processing chosen.";
default: default:
return "An unknown error occured while processing UTF-8 data."; return "An unknown error occurred while processing UTF-8 data.";
} }
} }
ssize_t utf8proc_iterate( DLLEXPORT ssize_t utf8proc_iterate(
const uint8_t *str, ssize_t strlen, int32_t *dst const uint8_t *str, ssize_t strlen, int32_t *dst
) { ) {
int length; int length;
@@ -156,14 +145,14 @@ ssize_t utf8proc_iterate(
return length; return length;
} }
bool utf8proc_codepoint_valid(int32_t uc) { DLLEXPORT bool utf8proc_codepoint_valid(int32_t uc) {
if (uc < 0 || uc >= 0x110000 || if (uc < 0 || uc >= 0x110000 ||
((uc & 0xFFFF) >= 0xFFFE) || (uc >= 0xD800 && uc < 0xE000) || ((uc & 0xFFFF) >= 0xFFFE) || (uc >= 0xD800 && uc < 0xE000) ||
(uc >= 0xFDD0 && uc < 0xFDF0)) return false; (uc >= 0xFDD0 && uc < 0xFDF0)) return false;
else return true; else return true;
} }
ssize_t utf8proc_encode_char(int32_t uc, uint8_t *dst) { DLLEXPORT ssize_t utf8proc_encode_char(int32_t uc, uint8_t *dst) {
if (uc < 0x00) { if (uc < 0x00) {
return 0; return 0;
} else if (uc < 0x80) { } else if (uc < 0x80) {
@@ -193,7 +182,8 @@ ssize_t utf8proc_encode_char(int32_t uc, uint8_t *dst) {
} else return 0; } else return 0;
} }
const utf8proc_property_t *utf8proc_get_property(int32_t uc) { /* internal "unsafe" version that does not check whether uc is in range */
static const utf8proc_property_t *get_property(int32_t uc) {
/* ASSERT: uc >= 0 && uc < 0x110000 */ /* ASSERT: uc >= 0 && uc < 0x110000 */
return utf8proc_properties + ( return utf8proc_properties + (
utf8proc_stage2table[ utf8proc_stage2table[
@@ -202,17 +192,67 @@ const utf8proc_property_t *utf8proc_get_property(int32_t uc) {
); );
} }
DLLEXPORT const utf8proc_property_t *utf8proc_get_property(int32_t uc) {
return uc < 0 || uc >= 0x110000 ? utf8proc_properties : get_property(uc);
}
/* return whether there is a grapheme break between boundclasses lbc and tbc */
static bool grapheme_break(int lbc, int tbc) {
return
(lbc == UTF8PROC_BOUNDCLASS_START) ? true :
(lbc == UTF8PROC_BOUNDCLASS_CR &&
tbc == UTF8PROC_BOUNDCLASS_LF) ? false :
(lbc >= UTF8PROC_BOUNDCLASS_CR && lbc <= UTF8PROC_BOUNDCLASS_CONTROL) ? true :
(tbc >= UTF8PROC_BOUNDCLASS_CR && tbc <= UTF8PROC_BOUNDCLASS_CONTROL) ? true :
(tbc == UTF8PROC_BOUNDCLASS_EXTEND) ? false :
(lbc == UTF8PROC_BOUNDCLASS_L &&
(tbc == UTF8PROC_BOUNDCLASS_L ||
tbc == UTF8PROC_BOUNDCLASS_V ||
tbc == UTF8PROC_BOUNDCLASS_LV ||
tbc == UTF8PROC_BOUNDCLASS_LVT)) ? false :
((lbc == UTF8PROC_BOUNDCLASS_LV ||
lbc == UTF8PROC_BOUNDCLASS_V) &&
(tbc == UTF8PROC_BOUNDCLASS_V ||
tbc == UTF8PROC_BOUNDCLASS_T)) ? false :
((lbc == UTF8PROC_BOUNDCLASS_LVT ||
lbc == UTF8PROC_BOUNDCLASS_T) &&
tbc == UTF8PROC_BOUNDCLASS_T) ? false :
(lbc == UTF8PROC_BOUNDCLASS_REGIONAL_INDICATOR &&
tbc == UTF8PROC_BOUNDCLASS_REGIONAL_INDICATOR) ? false :
(tbc != UTF8PROC_BOUNDCLASS_SPACINGMARK);
}
/* return whether there is a grapheme break between codepoints c1 and c2 */
DLLEXPORT bool utf8proc_grapheme_break(int32_t c1, int32_t c2) {
return grapheme_break(utf8proc_get_property(c1)->boundclass,
utf8proc_get_property(c2)->boundclass);
}
/* return a character width analogous to wcwidth (except portable and
hopefully less buggy than most system wcwidth functions). */
DLLEXPORT int utf8proc_charwidth(int32_t c) {
return utf8proc_get_property(c)->charwidth;
}
DLLEXPORT int utf8proc_category(int32_t c) {
return utf8proc_get_property(c)->category;
}
DLLEXPORT const char *utf8proc_category_string(int32_t c) {
static const char s[][3] = {"Cn","Lu","Ll","Lt","Lm","Lo","Mn","Mc","Me","Nd","Nl","No","Pc","Pd","Ps","Pe","Pi","Pf","Po","Sm","Sc","Sk","So","Zs","Zl","Zp","Cc","Cf","Cs","Co"};
return s[utf8proc_category(c)];
}
#define utf8proc_decompose_lump(replacement_uc) \ #define utf8proc_decompose_lump(replacement_uc) \
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)
ssize_t utf8proc_decompose_char(int32_t uc, int32_t *dst, ssize_t bufsize, DLLEXPORT ssize_t utf8proc_decompose_char(int32_t uc, int32_t *dst, ssize_t bufsize, int options, int *last_boundclass) {
int options, int *last_boundclass) {
/* ASSERT: uc >= 0 && uc < 0x110000 */
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;
property = utf8proc_get_property(uc); if (uc < 0 || uc >= 0x110000) return UTF8PROC_ERROR_NOTASSIGNED;
property = get_property(uc);
category = property->category; category = property->category;
hangul_sindex = uc - UTF8PROC_HANGUL_SBASE; hangul_sindex = uc - UTF8PROC_HANGUL_SBASE;
if (options & (UTF8PROC_COMPOSE|UTF8PROC_DECOMPOSE)) { if (options & (UTF8PROC_COMPOSE|UTF8PROC_DECOMPOSE)) {
@@ -298,48 +338,8 @@ ssize_t utf8proc_decompose_char(int32_t uc, int32_t *dst, ssize_t bufsize,
} }
if (options & UTF8PROC_CHARBOUND) { if (options & UTF8PROC_CHARBOUND) {
bool boundary; bool boundary;
int tbc, lbc; int tbc = property->boundclass;
tbc = boundary = grapheme_break(*last_boundclass, tbc);
(uc == 0x000D) ? UTF8PROC_BOUNDCLASS_CR :
(uc == 0x000A) ? UTF8PROC_BOUNDCLASS_LF :
((category == UTF8PROC_CATEGORY_ZL ||
category == UTF8PROC_CATEGORY_ZP ||
category == UTF8PROC_CATEGORY_CC ||
category == UTF8PROC_CATEGORY_CF) &&
!(uc == 0x200C || uc == 0x200D)) ? UTF8PROC_BOUNDCLASS_CONTROL :
property->extend ? UTF8PROC_BOUNDCLASS_EXTEND :
((uc >= UTF8PROC_HANGUL_L_START && uc < UTF8PROC_HANGUL_L_END) ||
uc == UTF8PROC_HANGUL_L_FILLER) ? UTF8PROC_BOUNDCLASS_L :
(uc >= UTF8PROC_HANGUL_V_START && uc < UTF8PROC_HANGUL_V_END) ?
UTF8PROC_BOUNDCLASS_V :
(uc >= UTF8PROC_HANGUL_T_START && uc < UTF8PROC_HANGUL_T_END) ?
UTF8PROC_BOUNDCLASS_T :
(uc >= UTF8PROC_HANGUL_S_START && uc < UTF8PROC_HANGUL_S_END) ? (
((uc-UTF8PROC_HANGUL_SBASE) % UTF8PROC_HANGUL_TCOUNT == 0) ?
UTF8PROC_BOUNDCLASS_LV : UTF8PROC_BOUNDCLASS_LVT
) :
UTF8PROC_BOUNDCLASS_OTHER;
lbc = *last_boundclass;
boundary =
(tbc == UTF8PROC_BOUNDCLASS_EXTEND) ? false :
(lbc == UTF8PROC_BOUNDCLASS_START) ? true :
(lbc == UTF8PROC_BOUNDCLASS_CR &&
tbc == UTF8PROC_BOUNDCLASS_LF) ? false :
(lbc == UTF8PROC_BOUNDCLASS_CONTROL) ? true :
(tbc == UTF8PROC_BOUNDCLASS_CONTROL) ? true :
(lbc == UTF8PROC_BOUNDCLASS_L &&
(tbc == UTF8PROC_BOUNDCLASS_L ||
tbc == UTF8PROC_BOUNDCLASS_V ||
tbc == UTF8PROC_BOUNDCLASS_LV ||
tbc == UTF8PROC_BOUNDCLASS_LVT)) ? false :
((lbc == UTF8PROC_BOUNDCLASS_LV ||
lbc == UTF8PROC_BOUNDCLASS_V) &&
(tbc == UTF8PROC_BOUNDCLASS_V ||
tbc == UTF8PROC_BOUNDCLASS_T)) ? false :
((lbc == UTF8PROC_BOUNDCLASS_LVT ||
lbc == UTF8PROC_BOUNDCLASS_T) &&
tbc == UTF8PROC_BOUNDCLASS_T) ? false :
true;
*last_boundclass = tbc; *last_boundclass = tbc;
if (boundary) { if (boundary) {
if (bufsize >= 1) dst[0] = 0xFFFF; if (bufsize >= 1) dst[0] = 0xFFFF;
@@ -351,7 +351,7 @@ ssize_t utf8proc_decompose_char(int32_t uc, int32_t *dst, ssize_t bufsize,
return 1; return 1;
} }
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, int options
) { ) {
@@ -370,7 +370,7 @@ ssize_t utf8proc_decompose(
while (1) { while (1) {
if (options & UTF8PROC_NULLTERM) { if (options & UTF8PROC_NULLTERM) {
rpos += utf8proc_iterate(str + rpos, -1, &uc); rpos += utf8proc_iterate(str + rpos, -1, &uc);
/* checking of return value is not neccessary, /* checking of return value is not necessary,
as 'uc' is < 0 in case of error */ as 'uc' is < 0 in case of error */
if (uc < 0) return UTF8PROC_ERROR_INVALIDUTF8; if (uc < 0) return UTF8PROC_ERROR_INVALIDUTF8;
if (rpos < 0) return UTF8PROC_ERROR_OVERFLOW; if (rpos < 0) return UTF8PROC_ERROR_OVERFLOW;
@@ -398,8 +398,8 @@ ssize_t utf8proc_decompose(
const utf8proc_property_t *property1, *property2; const utf8proc_property_t *property1, *property2;
uc1 = buffer[pos]; uc1 = buffer[pos];
uc2 = buffer[pos+1]; uc2 = buffer[pos+1];
property1 = utf8proc_get_property(uc1); property1 = get_property(uc1);
property2 = utf8proc_get_property(uc2); property2 = get_property(uc2);
if (property1->combining_class > property2->combining_class && if (property1->combining_class > property2->combining_class &&
property2->combining_class > 0) { property2->combining_class > 0) {
buffer[pos] = uc2; buffer[pos] = uc2;
@@ -413,7 +413,7 @@ ssize_t utf8proc_decompose(
return wpos; return wpos;
} }
ssize_t utf8proc_reencode(int32_t *buffer, ssize_t length, int options) { DLLEXPORT ssize_t utf8proc_reencode(int32_t *buffer, ssize_t length, int 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)) {
@@ -457,7 +457,7 @@ ssize_t utf8proc_reencode(int32_t *buffer, ssize_t length, int options) {
int32_t composition; int32_t composition;
for (rpos = 0; rpos < length; rpos++) { for (rpos = 0; rpos < length; rpos++) {
current_char = buffer[rpos]; current_char = buffer[rpos];
current_property = utf8proc_get_property(current_char); current_property = get_property(current_char);
if (starter && current_property->combining_class > max_combining_class) { if (starter && current_property->combining_class > max_combining_class) {
/* combination perhaps possible */ /* combination perhaps possible */
int32_t hangul_lindex; int32_t hangul_lindex;
@@ -486,7 +486,7 @@ ssize_t utf8proc_reencode(int32_t *buffer, ssize_t length, int options) {
} }
} }
if (!starter_property) { if (!starter_property) {
starter_property = utf8proc_get_property(*starter); starter_property = get_property(*starter);
} }
if (starter_property->comb1st_index >= 0 && if (starter_property->comb1st_index >= 0 &&
current_property->comb2nd_index >= 0) { current_property->comb2nd_index >= 0) {
@@ -495,7 +495,7 @@ ssize_t utf8proc_reencode(int32_t *buffer, ssize_t length, int options) {
current_property->comb2nd_index current_property->comb2nd_index
]; ];
if (composition >= 0 && (!(options & UTF8PROC_STABLE) || if (composition >= 0 && (!(options & UTF8PROC_STABLE) ||
!(utf8proc_get_property(composition)->comp_exclusion))) { !(get_property(composition)->comp_exclusion))) {
*starter = composition; *starter = composition;
starter_property = NULL; starter_property = NULL;
continue; continue;
@@ -528,7 +528,7 @@ ssize_t utf8proc_reencode(int32_t *buffer, ssize_t length, int options) {
} }
} }
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, int options
) { ) {
int32_t *buffer; int32_t *buffer;
@@ -536,7 +536,7 @@ ssize_t utf8proc_map(
*dstptr = NULL; *dstptr = NULL;
result = utf8proc_decompose(str, strlen, NULL, 0, options); result = utf8proc_decompose(str, strlen, NULL, 0, options);
if (result < 0) return result; if (result < 0) return result;
buffer = malloc(result * sizeof(int32_t) + 1); buffer = (int32_t *) malloc(result * sizeof(int32_t) + 1);
if (!buffer) return UTF8PROC_ERROR_NOMEM; if (!buffer) return UTF8PROC_ERROR_NOMEM;
result = utf8proc_decompose(str, strlen, buffer, result, options); result = utf8proc_decompose(str, strlen, buffer, result, options);
if (result < 0) { if (result < 0) {
@@ -550,38 +550,37 @@ ssize_t utf8proc_map(
} }
{ {
int32_t *newptr; int32_t *newptr;
newptr = realloc(buffer, (size_t)result+1); newptr = (int32_t *) realloc(buffer, (size_t)result+1);
if (newptr) buffer = newptr; if (newptr) buffer = newptr;
} }
*dstptr = (uint8_t *)buffer; *dstptr = (uint8_t *)buffer;
return result; return result;
} }
uint8_t *utf8proc_NFD(const uint8_t *str) { DLLEXPORT uint8_t *utf8proc_NFD(const uint8_t *str) {
uint8_t *retval; uint8_t *retval;
utf8proc_map(str, 0, &retval, UTF8PROC_NULLTERM | UTF8PROC_STABLE | utf8proc_map(str, 0, &retval, UTF8PROC_NULLTERM | UTF8PROC_STABLE |
UTF8PROC_DECOMPOSE); UTF8PROC_DECOMPOSE);
return retval; return retval;
} }
uint8_t *utf8proc_NFC(const uint8_t *str) { DLLEXPORT uint8_t *utf8proc_NFC(const uint8_t *str) {
uint8_t *retval; uint8_t *retval;
utf8proc_map(str, 0, &retval, UTF8PROC_NULLTERM | UTF8PROC_STABLE | utf8proc_map(str, 0, &retval, UTF8PROC_NULLTERM | UTF8PROC_STABLE |
UTF8PROC_COMPOSE); UTF8PROC_COMPOSE);
return retval; return retval;
} }
uint8_t *utf8proc_NFKD(const uint8_t *str) { DLLEXPORT uint8_t *utf8proc_NFKD(const uint8_t *str) {
uint8_t *retval; uint8_t *retval;
utf8proc_map(str, 0, &retval, UTF8PROC_NULLTERM | UTF8PROC_STABLE | utf8proc_map(str, 0, &retval, UTF8PROC_NULLTERM | UTF8PROC_STABLE |
UTF8PROC_DECOMPOSE | UTF8PROC_COMPAT); UTF8PROC_DECOMPOSE | UTF8PROC_COMPAT);
return retval; return retval;
} }
uint8_t *utf8proc_NFKC(const uint8_t *str) { DLLEXPORT uint8_t *utf8proc_NFKC(const uint8_t *str) {
uint8_t *retval; uint8_t *retval;
utf8proc_map(str, 0, &retval, UTF8PROC_NULLTERM | UTF8PROC_STABLE | utf8proc_map(str, 0, &retval, UTF8PROC_NULLTERM | UTF8PROC_STABLE |
UTF8PROC_COMPOSE | UTF8PROC_COMPAT); UTF8PROC_COMPOSE | UTF8PROC_COMPAT);
return retval; return retval;
} }

124
src/utf8proc/utf8proc.h
View File

@@ -25,7 +25,7 @@
* File name: utf8proc.h * File name: utf8proc.h
* *
* Description: * Description:
* Header files for libutf8proc, which is a mapping tool for UTF-8 strings * Header files for utf8proc, which is a mapping tool for UTF-8 strings
* with following features: * 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
@@ -44,7 +44,7 @@
* - 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 5.0.0 is supported. * Unicode Version 7.0.0 is supported.
*/ */
@@ -60,19 +60,33 @@ typedef unsigned char uint8_t;
typedef short int16_t; typedef short int16_t;
typedef unsigned short uint16_t; typedef unsigned short uint16_t;
typedef int int32_t; typedef int int32_t;
#ifdef _WIN64 # ifdef _WIN64
#define ssize_t __int64 # define ssize_t __int64
#else # else
#define ssize_t int # define ssize_t int
#endif # endif
# ifndef __cplusplus
typedef unsigned char bool; typedef unsigned char bool;
enum {false, true}; enum {false, true};
# endif
#else #else
#include <stdbool.h> # include <stdbool.h>
#include <inttypes.h> # include <inttypes.h>
#endif #endif
#include <limits.h> #include <limits.h>
#ifdef _WIN32
# ifdef UTF8PROC_EXPORTS
# define DLLEXPORT __declspec(dllexport)
# else
# define DLLEXPORT __declspec(dllimport)
# endif
#elif __GNUC__ >= 4
# define DLLEXPORT __attribute__ ((visibility("default")))
#else
# define DLLEXPORT
#endif
#ifdef __cplusplus #ifdef __cplusplus
extern "C" { extern "C" {
#endif #endif
@@ -100,7 +114,7 @@ extern "C" {
* Flags being regarded by several functions in the library: * Flags being regarded by several functions in the library:
* NULLTERM: The given UTF-8 input is NULL terminated. * NULLTERM: The given UTF-8 input is NULL terminated.
* STABLE: Unicode Versioning Stability has to be respected. * STABLE: Unicode Versioning Stability has to be respected.
* COMPAT: Compatiblity decomposition * COMPAT: Compatibility decomposition
* (i.e. formatting information is lost) * (i.e. formatting information is lost)
* COMPOSE: Return a result with composed characters. * COMPOSE: Return a result with composed characters.
* DECOMPOSE: Return a result with decomposed characters. * DECOMPOSE: Return a result with decomposed characters.
@@ -126,7 +140,7 @@ extern "C" {
* is representing a single grapheme cluster (see UAX#29). * is representing a single grapheme cluster (see UAX#29).
* LUMP: Lumps certain characters together * LUMP: Lumps certain characters together
* (e.g. HYPHEN U+2010 and MINUS U+2212 to ASCII "-"). * (e.g. HYPHEN U+2010 and MINUS U+2212 to ASCII "-").
* (See lump.txt for details.) * (See lump.md for details.)
* If NLF2LF is set, this includes a transformation of * If NLF2LF is set, this includes a transformation of
* paragraph and line separators to ASCII line-feed (LF). * paragraph and line separators to ASCII line-feed (LF).
* STRIPMARK: Strips all character markings * STRIPMARK: Strips all character markings
@@ -156,19 +170,21 @@ typedef struct utf8proc_property_struct {
utf8proc_propval_t bidi_class; utf8proc_propval_t bidi_class;
utf8proc_propval_t decomp_type; utf8proc_propval_t decomp_type;
const int32_t *decomp_mapping; const int32_t *decomp_mapping;
unsigned bidi_mirrored:1; const int32_t *casefold_mapping;
int32_t uppercase_mapping; int32_t uppercase_mapping;
int32_t lowercase_mapping; int32_t lowercase_mapping;
int32_t titlecase_mapping; int32_t titlecase_mapping;
int32_t comb1st_index; int32_t comb1st_index;
int32_t comb2nd_index; int32_t comb2nd_index;
unsigned bidi_mirrored:1;
unsigned comp_exclusion:1; unsigned comp_exclusion:1;
unsigned ignorable:1; unsigned ignorable:1;
unsigned control_boundary:1; unsigned control_boundary:1;
unsigned extend:1; unsigned boundclass:4;
const int32_t *casefold_mapping; unsigned charwidth:2;
} utf8proc_property_t; } utf8proc_property_t;
#define UTF8PROC_CATEGORY_CN 0
#define UTF8PROC_CATEGORY_LU 1 #define UTF8PROC_CATEGORY_LU 1
#define UTF8PROC_CATEGORY_LL 2 #define UTF8PROC_CATEGORY_LL 2
#define UTF8PROC_CATEGORY_LT 3 #define UTF8PROC_CATEGORY_LT 3
@@ -198,7 +214,6 @@ typedef struct utf8proc_property_struct {
#define UTF8PROC_CATEGORY_CF 27 #define UTF8PROC_CATEGORY_CF 27
#define UTF8PROC_CATEGORY_CS 28 #define UTF8PROC_CATEGORY_CS 28
#define UTF8PROC_CATEGORY_CO 29 #define UTF8PROC_CATEGORY_CO 29
#define UTF8PROC_CATEGORY_CN 30
#define UTF8PROC_BIDI_CLASS_L 1 #define UTF8PROC_BIDI_CLASS_L 1
#define UTF8PROC_BIDI_CLASS_LRE 2 #define UTF8PROC_BIDI_CLASS_LRE 2
#define UTF8PROC_BIDI_CLASS_LRO 3 #define UTF8PROC_BIDI_CLASS_LRO 3
@@ -218,6 +233,10 @@ typedef struct utf8proc_property_struct {
#define UTF8PROC_BIDI_CLASS_S 17 #define UTF8PROC_BIDI_CLASS_S 17
#define UTF8PROC_BIDI_CLASS_WS 18 #define UTF8PROC_BIDI_CLASS_WS 18
#define UTF8PROC_BIDI_CLASS_ON 19 #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_FONT 1
#define UTF8PROC_DECOMP_TYPE_NOBREAK 2 #define UTF8PROC_DECOMP_TYPE_NOBREAK 2
#define UTF8PROC_DECOMP_TYPE_INITIAL 3 #define UTF8PROC_DECOMP_TYPE_INITIAL 3
@@ -235,16 +254,31 @@ typedef struct utf8proc_property_struct {
#define UTF8PROC_DECOMP_TYPE_FRACTION 15 #define UTF8PROC_DECOMP_TYPE_FRACTION 15
#define UTF8PROC_DECOMP_TYPE_COMPAT 16 #define UTF8PROC_DECOMP_TYPE_COMPAT 16
extern const int8_t utf8proc_utf8class[256]; /* values for boundclass property: */
#define UTF8PROC_BOUNDCLASS_START 0
#define UTF8PROC_BOUNDCLASS_OTHER 1
#define UTF8PROC_BOUNDCLASS_CR 2
#define UTF8PROC_BOUNDCLASS_LF 3
#define UTF8PROC_BOUNDCLASS_CONTROL 4
#define UTF8PROC_BOUNDCLASS_EXTEND 5
#define UTF8PROC_BOUNDCLASS_L 6
#define UTF8PROC_BOUNDCLASS_V 7
#define UTF8PROC_BOUNDCLASS_T 8
#define UTF8PROC_BOUNDCLASS_LV 9
#define UTF8PROC_BOUNDCLASS_LVT 10
#define UTF8PROC_BOUNDCLASS_REGIONAL_INDICATOR 11
#define UTF8PROC_BOUNDCLASS_SPACINGMARK 12
const char *utf8proc_version(void); DLLEXPORT extern const int8_t utf8proc_utf8class[256];
const char *utf8proc_errmsg(ssize_t errcode); DLLEXPORT const char *utf8proc_version(void);
DLLEXPORT const char *utf8proc_errmsg(ssize_t errcode);
/* /*
* Returns a static error string for the given error code. * Returns a static error string for the given error code.
*/ */
ssize_t utf8proc_iterate(const uint8_t *str, ssize_t strlen, int32_t *dst); DLLEXPORT 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'. * 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
@@ -255,12 +289,12 @@ ssize_t utf8proc_iterate(const uint8_t *str, ssize_t strlen, int32_t *dst);
* negative error code is returned. * negative error code is returned.
*/ */
bool utf8proc_codepoint_valid(int32_t uc); DLLEXPORT bool utf8proc_codepoint_valid(int32_t uc);
/* /*
* Returns 1, if the given unicode code-point is valid, otherwise 0. * Returns 1, if the given unicode code-point is valid, otherwise 0.
*/ */
ssize_t utf8proc_encode_char(int32_t uc, uint8_t *dst); DLLEXPORT 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 * 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
@@ -270,17 +304,15 @@ ssize_t utf8proc_encode_char(int32_t uc, uint8_t *dst);
* This function does not check if 'uc' is a valid unicode code point. * This function does not check if 'uc' is a valid unicode code point.
*/ */
const utf8proc_property_t *utf8proc_get_property(int32_t uc); DLLEXPORT const utf8proc_property_t *utf8proc_get_property(int32_t uc);
/* /*
* Returns a pointer to a (constant) struct containing information about * Returns a pointer to a (constant) struct containing information about
* the unicode char with the given code point 'uc'. * the unicode char with the given code point 'uc'.
* If the character is not existent a pointer to a special struct is * If the character is not existent a pointer to a special struct is
* returned, where 'category' is a NULL pointer. * returned, where 'category' is 0 (UTF8PROC_CATEGORY_CN).
* WARNING: The parameter 'uc' has to be in the range of 0x0000 to
* 0x10FFFF, otherwise the program might crash!
*/ */
ssize_t utf8proc_decompose_char( DLLEXPORT ssize_t utf8proc_decompose_char(
int32_t uc, int32_t *dst, ssize_t bufsize, int32_t uc, int32_t *dst, ssize_t bufsize,
int options, int *last_boundclass int options, int *last_boundclass
); );
@@ -304,11 +336,9 @@ ssize_t utf8proc_decompose_char(
* If the number of written chars would be bigger than 'bufsize', * If the number of written chars 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.
* WARNING: The parameter 'uc' has to be in the range of 0x0000 to
* 0x10FFFF, otherwise the program might crash!
*/ */
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, int options
); );
@@ -326,7 +356,7 @@ ssize_t utf8proc_decompose(
* buffer size is returned. * buffer size is returned.
*/ */
ssize_t utf8proc_reencode(int32_t *buffer, ssize_t length, int options); DLLEXPORT ssize_t utf8proc_reencode(int32_t *buffer, ssize_t length, int options);
/* /*
* Reencodes the sequence of unicode characters 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.
@@ -349,7 +379,28 @@ ssize_t utf8proc_reencode(int32_t *buffer, ssize_t length, int options);
* crash! * crash!
*/ */
ssize_t utf8proc_map( DLLEXPORT bool utf8proc_grapheme_break(int32_t c1, int32_t c2);
/*
* 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).
*/
DLLEXPORT int utf8proc_charwidth(int32_t c);
/* Given a codepoint c, return a character width analogous to wcwidth(c),
except that a width of 0 is returned for non-printable characters
instead of -1 as in wcwidth.
If you want to check for particular types of non-printable characters,
(analogous to isprint or iscntrl), use utf8proc_category(c). */
DLLEXPORT int utf8proc_category(int32_t c);
/* Return the Unicode character category for c (one of the
UTF8PROC_CATEGORY_* constants.) */
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 const uint8_t *str, ssize_t strlen, uint8_t **dstptr, int options
); );
/* /*
@@ -368,10 +419,10 @@ ssize_t utf8proc_map(
* 'malloc', and has theirfore to be freed with 'free'. * 'malloc', and has theirfore to be freed with 'free'.
*/ */
uint8_t *utf8proc_NFD(const uint8_t *str); DLLEXPORT uint8_t *utf8proc_NFD(const uint8_t *str);
uint8_t *utf8proc_NFC(const uint8_t *str); DLLEXPORT uint8_t *utf8proc_NFC(const uint8_t *str);
uint8_t *utf8proc_NFKD(const uint8_t *str); DLLEXPORT uint8_t *utf8proc_NFKD(const uint8_t *str);
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 * Returns a pointer to newly allocated memory of a NFD, NFC, NFKD or NFKC
* normalized version of the null-terminated string 'str'. * normalized version of the null-terminated string 'str'.
@@ -381,5 +432,4 @@ uint8_t *utf8proc_NFKC(const uint8_t *str);
} }
#endif #endif
#endif #endif

23110
src/utf8proc/utf8proc_data.c
View File

File diff suppressed because it is too large Load Diff