Import a local modified version of utf8proc for Unicode normalisation.

This commit is contained in:
Chris Young 2014-05-30 20:01:47 +01:00 committed by Daniel Silverstone
parent e5d5e68eb5
commit 9fb4fd738a
3 changed files with 14370 additions and 0 deletions

594
utils/utf8proc.c Normal file
View File

@ -0,0 +1,594 @@
/*
* 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.
*/
/*
* This library contains derived data from a modified version of the
* Unicode data files.
*
* The original data files are available at
* http://www.unicode.org/Public/UNIDATA/
*
* Please notice the copyright statement in the file "utf8proc_data.c".
*/
/*
* File name: utf8proc.c
*
* Description:
* Implementation of libutf8proc.
*/
#include "utf8proc.h"
#include "utf8proc_data.c"
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,
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,
0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0,
0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0,
0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0,
0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0,
2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2,
2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2,
3, 3, 3, 3, 3, 3, 3, 3, 3, 3, 3, 3, 3, 3, 3, 3,
4, 4, 4, 4, 4, 4, 4, 4, 0, 0, 0, 0, 0, 0, 0, 0 };
#define UTF8PROC_HANGUL_SBASE 0xAC00
#define UTF8PROC_HANGUL_LBASE 0x1100
#define UTF8PROC_HANGUL_VBASE 0x1161
#define UTF8PROC_HANGUL_TBASE 0x11A7
#define UTF8PROC_HANGUL_LCOUNT 19
#define UTF8PROC_HANGUL_VCOUNT 21
#define UTF8PROC_HANGUL_TCOUNT 28
#define UTF8PROC_HANGUL_NCOUNT 588
#define UTF8PROC_HANGUL_SCOUNT 11172
/* END is exclusive */
#define UTF8PROC_HANGUL_L_START 0x1100
#define UTF8PROC_HANGUL_L_END 0x115A
#define UTF8PROC_HANGUL_L_FILLER 0x115F
#define UTF8PROC_HANGUL_V_START 0x1160
#define UTF8PROC_HANGUL_V_END 0x11A3
#define UTF8PROC_HANGUL_T_START 0x11A8
#define UTF8PROC_HANGUL_T_END 0x11FA
#define UTF8PROC_HANGUL_S_START 0xAC00
#define UTF8PROC_HANGUL_S_END 0xD7A4
#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
const char *utf8proc_version(void) {
return "1.1.6";
}
const char *utf8proc_errmsg(ssize_t errcode) {
switch (errcode) {
case UTF8PROC_ERROR_NOMEM:
return "Memory for processing UTF-8 data could not be allocated.";
case UTF8PROC_ERROR_OVERFLOW:
return "UTF-8 string is too long to be processed.";
case UTF8PROC_ERROR_INVALIDUTF8:
return "Invalid UTF-8 string";
case UTF8PROC_ERROR_NOTASSIGNED:
return "Unassigned Unicode code point found in UTF-8 string.";
case UTF8PROC_ERROR_INVALIDOPTS:
return "Invalid options for UTF-8 processing chosen.";
default:
return "An unknown error occured while processing UTF-8 data.";
}
}
ssize_t utf8proc_iterate(
const uint8_t *str, ssize_t strlen, int32_t *dst
) {
int length;
int i;
int32_t uc = -1;
*dst = -1;
if (!strlen) return 0;
length = utf8proc_utf8class[str[0]];
if (!length) return UTF8PROC_ERROR_INVALIDUTF8;
if (strlen >= 0 && length > strlen) return UTF8PROC_ERROR_INVALIDUTF8;
for (i=1; i<length; i++) {
if ((str[i] & 0xC0) != 0x80) return UTF8PROC_ERROR_INVALIDUTF8;
}
switch (length) {
case 1:
uc = str[0];
break;
case 2:
uc = ((str[0] & 0x1F) << 6) + (str[1] & 0x3F);
if (uc < 0x80) uc = -1;
break;
case 3:
uc = ((str[0] & 0x0F) << 12) + ((str[1] & 0x3F) << 6)
+ (str[2] & 0x3F);
if (uc < 0x800 || (uc >= 0xD800 && uc < 0xE000) ||
(uc >= 0xFDD0 && uc < 0xFDF0)) uc = -1;
break;
case 4:
uc = ((str[0] & 0x07) << 18) + ((str[1] & 0x3F) << 12)
+ ((str[2] & 0x3F) << 6) + (str[3] & 0x3F);
if (uc < 0x10000 || uc >= 0x110000) uc = -1;
break;
}
if (uc < 0 || ((uc & 0xFFFF) >= 0xFFFE))
return UTF8PROC_ERROR_INVALIDUTF8;
*dst = uc;
return length;
}
bool utf8proc_codepoint_valid(int32_t uc) {
if (uc < 0 || uc >= 0x110000 ||
((uc & 0xFFFF) >= 0xFFFE) || (uc >= 0xD800 && uc < 0xE000) ||
(uc >= 0xFDD0 && uc < 0xFDF0)) return false;
else return true;
}
ssize_t utf8proc_encode_char(int32_t uc, uint8_t *dst) {
if (uc < 0x00) {
return 0;
} else if (uc < 0x80) {
dst[0] = uc;
return 1;
} else if (uc < 0x800) {
dst[0] = 0xC0 + (uc >> 6);
dst[1] = 0x80 + (uc & 0x3F);
return 2;
} else if (uc == 0xFFFF) {
dst[0] = 0xFF;
return 1;
} else if (uc == 0xFFFE) {
dst[0] = 0xFE;
return 1;
} else if (uc < 0x10000) {
dst[0] = 0xE0 + (uc >> 12);
dst[1] = 0x80 + ((uc >> 6) & 0x3F);
dst[2] = 0x80 + (uc & 0x3F);
return 3;
} else if (uc < 0x110000) {
dst[0] = 0xF0 + (uc >> 18);
dst[1] = 0x80 + ((uc >> 12) & 0x3F);
dst[2] = 0x80 + ((uc >> 6) & 0x3F);
dst[3] = 0x80 + (uc & 0x3F);
return 4;
} else return 0;
}
const utf8proc_property_t *utf8proc_get_property(int32_t uc) {
/* ASSERT: uc >= 0 && uc < 0x110000 */
return utf8proc_properties + (
utf8proc_stage2table[
utf8proc_stage1table[uc >> 8] + (uc & 0xFF)
]
);
}
#define utf8proc_decompose_lump(replacement_uc) \
return utf8proc_decompose_char((replacement_uc), dst, bufsize, \
options & ~UTF8PROC_LUMP, last_boundclass)
ssize_t utf8proc_decompose_char(int32_t uc, int32_t *dst, ssize_t bufsize,
int options, int *last_boundclass) {
/* ASSERT: uc >= 0 && uc < 0x110000 */
const utf8proc_property_t *property;
utf8proc_propval_t category;
int32_t hangul_sindex;
property = utf8proc_get_property(uc);
category = property->category;
hangul_sindex = uc - UTF8PROC_HANGUL_SBASE;
if (options & (UTF8PROC_COMPOSE|UTF8PROC_DECOMPOSE)) {
if (hangul_sindex >= 0 && hangul_sindex < UTF8PROC_HANGUL_SCOUNT) {
int32_t hangul_tindex;
if (bufsize >= 1) {
dst[0] = UTF8PROC_HANGUL_LBASE +
hangul_sindex / UTF8PROC_HANGUL_NCOUNT;
if (bufsize >= 2) dst[1] = UTF8PROC_HANGUL_VBASE +
(hangul_sindex % UTF8PROC_HANGUL_NCOUNT) / UTF8PROC_HANGUL_TCOUNT;
}
hangul_tindex = hangul_sindex % UTF8PROC_HANGUL_TCOUNT;
if (!hangul_tindex) return 2;
if (bufsize >= 3) dst[2] = UTF8PROC_HANGUL_TBASE + hangul_tindex;
return 3;
}
}
if (options & UTF8PROC_REJECTNA) {
if (!category) return UTF8PROC_ERROR_NOTASSIGNED;
}
if (options & UTF8PROC_IGNORE) {
if (property->ignorable) return 0;
}
if (options & UTF8PROC_LUMP) {
if (category == UTF8PROC_CATEGORY_ZS) utf8proc_decompose_lump(0x0020);
if (uc == 0x2018 || uc == 0x2019 || uc == 0x02BC || uc == 0x02C8)
utf8proc_decompose_lump(0x0027);
if (category == UTF8PROC_CATEGORY_PD || uc == 0x2212)
utf8proc_decompose_lump(0x002D);
if (uc == 0x2044 || uc == 0x2215) utf8proc_decompose_lump(0x002F);
if (uc == 0x2236) utf8proc_decompose_lump(0x003A);
if (uc == 0x2039 || uc == 0x2329 || uc == 0x3008)
utf8proc_decompose_lump(0x003C);
if (uc == 0x203A || uc == 0x232A || uc == 0x3009)
utf8proc_decompose_lump(0x003E);
if (uc == 0x2216) utf8proc_decompose_lump(0x005C);
if (uc == 0x02C4 || uc == 0x02C6 || uc == 0x2038 || uc == 0x2303)
utf8proc_decompose_lump(0x005E);
if (category == UTF8PROC_CATEGORY_PC || uc == 0x02CD)
utf8proc_decompose_lump(0x005F);
if (uc == 0x02CB) utf8proc_decompose_lump(0x0060);
if (uc == 0x2223) utf8proc_decompose_lump(0x007C);
if (uc == 0x223C) utf8proc_decompose_lump(0x007E);
if ((options & UTF8PROC_NLF2LS) && (options & UTF8PROC_NLF2PS)) {
if (category == UTF8PROC_CATEGORY_ZL ||
category == UTF8PROC_CATEGORY_ZP)
utf8proc_decompose_lump(0x000A);
}
}
if (options & UTF8PROC_STRIPMARK) {
if (category == UTF8PROC_CATEGORY_MN ||
category == UTF8PROC_CATEGORY_MC ||
category == UTF8PROC_CATEGORY_ME) return 0;
}
if (options & UTF8PROC_CASEFOLD) {
if (property->casefold_mapping) {
const int32_t *casefold_entry;
ssize_t written = 0;
for (casefold_entry = property->casefold_mapping;
*casefold_entry >= 0; casefold_entry++) {
written += utf8proc_decompose_char(*casefold_entry, dst+written,
(bufsize > written) ? (bufsize - written) : 0, options,
last_boundclass);
if (written < 0) return UTF8PROC_ERROR_OVERFLOW;
}
return written;
}
}
if (options & (UTF8PROC_COMPOSE|UTF8PROC_DECOMPOSE)) {
if (property->decomp_mapping &&
(!property->decomp_type || (options & UTF8PROC_COMPAT))) {
const int32_t *decomp_entry;
ssize_t written = 0;
for (decomp_entry = property->decomp_mapping;
*decomp_entry >= 0; decomp_entry++) {
written += utf8proc_decompose_char(*decomp_entry, dst+written,
(bufsize > written) ? (bufsize - written) : 0, options,
last_boundclass);
if (written < 0) return UTF8PROC_ERROR_OVERFLOW;
}
return written;
}
}
if (options & UTF8PROC_CHARBOUND) {
bool boundary;
int tbc, lbc;
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;
if (boundary) {
if (bufsize >= 1) dst[0] = 0xFFFF;
if (bufsize >= 2) dst[1] = uc;
return 2;
}
}
if (bufsize >= 1) *dst = uc;
return 1;
}
ssize_t utf8proc_decompose(
const uint8_t *str, ssize_t strlen,
int32_t *buffer, ssize_t bufsize, int options
) {
/* strlen will be ignored, if UTF8PROC_NULLTERM is set in options */
ssize_t wpos = 0;
if ((options & UTF8PROC_COMPOSE) && (options & UTF8PROC_DECOMPOSE))
return UTF8PROC_ERROR_INVALIDOPTS;
if ((options & UTF8PROC_STRIPMARK) &&
!(options & UTF8PROC_COMPOSE) && !(options & UTF8PROC_DECOMPOSE))
return UTF8PROC_ERROR_INVALIDOPTS;
{
int32_t uc;
ssize_t rpos = 0;
ssize_t decomp_result;
int boundclass = UTF8PROC_BOUNDCLASS_START;
while (1) {
if (options & UTF8PROC_NULLTERM) {
rpos += utf8proc_iterate(str + rpos, -1, &uc);
/* checking of return value is not neccessary,
as 'uc' is < 0 in case of error */
if (uc < 0) return UTF8PROC_ERROR_INVALIDUTF8;
if (rpos < 0) return UTF8PROC_ERROR_OVERFLOW;
if (uc == 0) break;
} else {
if (rpos >= strlen) break;
rpos += utf8proc_iterate(str + rpos, strlen - rpos, &uc);
if (uc < 0) return UTF8PROC_ERROR_INVALIDUTF8;
}
decomp_result = utf8proc_decompose_char(
uc, buffer + wpos, (bufsize > wpos) ? (bufsize - wpos) : 0, options,
&boundclass
);
if (decomp_result < 0) return decomp_result;
wpos += decomp_result;
/* prohibiting integer overflows due to too long strings: */
if (wpos < 0 || wpos > SSIZE_MAX/sizeof(int32_t)/2)
return UTF8PROC_ERROR_OVERFLOW;
}
}
if ((options & (UTF8PROC_COMPOSE|UTF8PROC_DECOMPOSE)) && bufsize >= wpos) {
ssize_t pos = 0;
while (pos < wpos-1) {
int32_t uc1, uc2;
const utf8proc_property_t *property1, *property2;
uc1 = buffer[pos];
uc2 = buffer[pos+1];
property1 = utf8proc_get_property(uc1);
property2 = utf8proc_get_property(uc2);
if (property1->combining_class > property2->combining_class &&
property2->combining_class > 0) {
buffer[pos] = uc2;
buffer[pos+1] = uc1;
if (pos > 0) pos--; else pos++;
} else {
pos++;
}
}
}
return wpos;
}
ssize_t utf8proc_normalise(int32_t *buffer, ssize_t length, int options) {
/* UTF8PROC_NULLTERM option will be ignored, 'length' is never ignored
ASSERT: 'buffer' has one spare byte of free space at the end! */
if (options & (UTF8PROC_NLF2LS | UTF8PROC_NLF2PS | UTF8PROC_STRIPCC)) {
ssize_t rpos;
ssize_t wpos = 0;
int32_t uc;
for (rpos = 0; rpos < length; rpos++) {
uc = buffer[rpos];
if (uc == 0x000D && rpos < length-1 && buffer[rpos+1] == 0x000A) rpos++;
if (uc == 0x000A || uc == 0x000D || uc == 0x0085 ||
((options & UTF8PROC_STRIPCC) && (uc == 0x000B || uc == 0x000C))) {
if (options & UTF8PROC_NLF2LS) {
if (options & UTF8PROC_NLF2PS) {
buffer[wpos++] = 0x000A;
} else {
buffer[wpos++] = 0x2028;
}
} else {
if (options & UTF8PROC_NLF2PS) {
buffer[wpos++] = 0x2029;
} else {
buffer[wpos++] = 0x0020;
}
}
} else if ((options & UTF8PROC_STRIPCC) &&
(uc < 0x0020 || (uc >= 0x007F && uc < 0x00A0))) {
if (uc == 0x0009) buffer[wpos++] = 0x0020;
} else {
buffer[wpos++] = uc;
}
}
length = wpos;
}
if (options & UTF8PROC_COMPOSE) {
int32_t *starter = NULL;
int32_t current_char;
const utf8proc_property_t *starter_property = NULL, *current_property;
utf8proc_propval_t max_combining_class = -1;
ssize_t rpos;
ssize_t wpos = 0;
int32_t composition;
for (rpos = 0; rpos < length; rpos++) {
current_char = buffer[rpos];
current_property = utf8proc_get_property(current_char);
if (starter && current_property->combining_class > max_combining_class) {
/* combination perhaps possible */
int32_t hangul_lindex;
int32_t hangul_sindex;
hangul_lindex = *starter - UTF8PROC_HANGUL_LBASE;
if (hangul_lindex >= 0 && hangul_lindex < UTF8PROC_HANGUL_LCOUNT) {
int32_t hangul_vindex;
hangul_vindex = current_char - UTF8PROC_HANGUL_VBASE;
if (hangul_vindex >= 0 && hangul_vindex < UTF8PROC_HANGUL_VCOUNT) {
*starter = UTF8PROC_HANGUL_SBASE +
(hangul_lindex * UTF8PROC_HANGUL_VCOUNT + hangul_vindex) *
UTF8PROC_HANGUL_TCOUNT;
starter_property = NULL;
continue;
}
}
hangul_sindex = *starter - UTF8PROC_HANGUL_SBASE;
if (hangul_sindex >= 0 && hangul_sindex < UTF8PROC_HANGUL_SCOUNT &&
(hangul_sindex % UTF8PROC_HANGUL_TCOUNT) == 0) {
int32_t hangul_tindex;
hangul_tindex = current_char - UTF8PROC_HANGUL_TBASE;
if (hangul_tindex >= 0 && hangul_tindex < UTF8PROC_HANGUL_TCOUNT) {
*starter += hangul_tindex;
starter_property = NULL;
continue;
}
}
if (!starter_property) {
starter_property = utf8proc_get_property(*starter);
}
if (starter_property->comb1st_index >= 0 &&
current_property->comb2nd_index >= 0) {
composition = utf8proc_combinations[
starter_property->comb1st_index +
current_property->comb2nd_index
];
if (composition >= 0 && (!(options & UTF8PROC_STABLE) ||
!(utf8proc_get_property(composition)->comp_exclusion))) {
*starter = composition;
starter_property = NULL;
continue;
}
}
}
buffer[wpos] = current_char;
if (current_property->combining_class) {
if (current_property->combining_class > max_combining_class) {
max_combining_class = current_property->combining_class;
}
} else {
starter = buffer + wpos;
starter_property = NULL;
max_combining_class = -1;
}
wpos++;
}
length = wpos;
}
return length;
}
ssize_t utf8proc_reencode(int32_t *buffer, ssize_t length, int options) {
length = utf8proc_normalise(buffer, length, options);
if (length < 0) return length;
{
ssize_t rpos, wpos = 0;
int32_t uc;
for (rpos = 0; rpos < length; rpos++) {
uc = buffer[rpos];
wpos += utf8proc_encode_char(uc, ((uint8_t *)buffer) + wpos);
}
((uint8_t *)buffer)[wpos] = 0;
return wpos;
}
}
ssize_t utf8proc_map(
const uint8_t *str, ssize_t strlen, uint8_t **dstptr, int options
) {
int32_t *buffer;
ssize_t result;
*dstptr = NULL;
result = utf8proc_decompose(str, strlen, NULL, 0, options);
if (result < 0) return result;
buffer = malloc(result * sizeof(int32_t) + 1);
if (!buffer) return UTF8PROC_ERROR_NOMEM;
result = utf8proc_decompose(str, strlen, buffer, result, options);
if (result < 0) {
free(buffer);
return result;
}
result = utf8proc_reencode(buffer, result, options);
if (result < 0) {
free(buffer);
return result;
}
{
int32_t *newptr;
newptr = realloc(buffer, (size_t)result+1);
if (newptr) buffer = newptr;
}
*dstptr = (uint8_t *)buffer;
return result;
}
uint8_t *utf8proc_NFD(const uint8_t *str) {
uint8_t *retval;
utf8proc_map(str, 0, &retval, UTF8PROC_NULLTERM | UTF8PROC_STABLE |
UTF8PROC_DECOMPOSE);
return retval;
}
uint8_t *utf8proc_NFC(const uint8_t *str) {
uint8_t *retval;
utf8proc_map(str, 0, &retval, UTF8PROC_NULLTERM | UTF8PROC_STABLE |
UTF8PROC_COMPOSE);
return retval;
}
uint8_t *utf8proc_NFKD(const uint8_t *str) {
uint8_t *retval;
utf8proc_map(str, 0, &retval, UTF8PROC_NULLTERM | UTF8PROC_STABLE |
UTF8PROC_DECOMPOSE | UTF8PROC_COMPAT);
return retval;
}
uint8_t *utf8proc_NFKC(const uint8_t *str) {
uint8_t *retval;
utf8proc_map(str, 0, &retval, UTF8PROC_NULLTERM | UTF8PROC_STABLE |
UTF8PROC_COMPOSE | UTF8PROC_COMPAT);
return retval;
}

393
utils/utf8proc.h Normal file
View File

@ -0,0 +1,393 @@
/*
* 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.
*/
/*
* File name: utf8proc.h
*
* 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.
*/
#ifndef UTF8PROC_H
#define UTF8PROC_H
#include <stdlib.h>
#include <sys/types.h>
#ifdef _MSC_VER
typedef signed char int8_t;
typedef unsigned char uint8_t;
typedef short int16_t;
typedef unsigned short uint16_t;
typedef int int32_t;
#ifdef _WIN64
#define ssize_t __int64
#else
#define ssize_t int
#endif
typedef unsigned char bool;
enum {false, true};
#else
#include <stdbool.h>
#include <inttypes.h>
#endif
#include <limits.h>
#ifdef __cplusplus
extern "C" {
#endif
#ifndef SSIZE_MAX
#define SSIZE_MAX ((size_t)SIZE_MAX/2)
#endif
#define UTF8PROC_CCC_VIRAMA 9
#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
*/
#define UTF8PROC_ERROR_NOMEM -1
#define UTF8PROC_ERROR_OVERFLOW -2
#define UTF8PROC_ERROR_INVALIDUTF8 -3
#define UTF8PROC_ERROR_NOTASSIGNED -4
#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.
*/
typedef int16_t utf8proc_propval_t;
typedef struct utf8proc_property_struct {
utf8proc_propval_t category;
utf8proc_propval_t combining_class;
utf8proc_propval_t bidi_class;
utf8proc_propval_t decomp_type;
const int32_t *decomp_mapping;
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;
unsigned ignorable:1;
unsigned control_boundary:1;
unsigned extend:1;
const int32_t *casefold_mapping;
} 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
extern const int8_t utf8proc_utf8class[256];
const char *utf8proc_version(void);
const char *utf8proc_errmsg(ssize_t errcode);
/*
* Returns a static error string for the given error code.
*/
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.
*/
bool utf8proc_codepoint_valid(int32_t uc);
/*
* Returns 1, if the given unicode code-point is valid, otherwise 0.
*/
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.
*/
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!
*/
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!
*/
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.
*/
ssize_t utf8proc_normalise(int32_t *buffer, ssize_t length, int options);
/*
* Reencodes the sequence of unicode characters given by the pointer
* 'buffer' and 'length'. See utf8proc_reencode for further details.
*/
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!
*/
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
* 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'.
*/
uint8_t *utf8proc_NFD(const uint8_t *str);
uint8_t *utf8proc_NFC(const uint8_t *str);
uint8_t *utf8proc_NFKD(const uint8_t *str);
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
}
#endif
#endif

13383
utils/utf8proc_data.c Normal file

File diff suppressed because it is too large Load Diff