1 /* 2 * Copyright (c) 2009 Public Software Group e. V., Berlin, Germany 3 * 4 * Permission is hereby granted, free of charge, to any person obtaining a 5 * copy of this software and associated documentation files (the "Software"), 6 * to deal in the Software without restriction, including without limitation 7 * the rights to use, copy, modify, merge, publish, distribute, sublicense, 8 * and/or sell copies of the Software, and to permit persons to whom the 9 * Software is furnished to do so, subject to the following conditions: 10 * 11 * The above copyright notice and this permission notice shall be included in 12 * all copies or substantial portions of the Software. 13 * 14 * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR 15 * IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY, 16 * FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE 17 * AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER 18 * LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING 19 * FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER 20 * DEALINGS IN THE SOFTWARE. 21 */ 22 23 24 /* 25 * File name: utf8proc.h 26 * 27 * Description: 28 * Header files for libutf8proc, which is a mapping tool for UTF-8 strings 29 * with following features: 30 * - decomposing and composing of strings 31 * - replacing compatibility characters with their equivalents 32 * - stripping of "default ignorable characters" 33 * like SOFT-HYPHEN or ZERO-WIDTH-SPACE 34 * - folding of certain characters for string comparison 35 * (e.g. HYPHEN U+2010 and MINUS U+2212 to ASCII "-") 36 * (see "LUMP" option) 37 * - optional rejection of strings containing non-assigned code points 38 * - stripping of control characters 39 * - stripping of character marks (accents, etc.) 40 * - transformation of LF, CRLF, CR and NEL to line-feed (LF) 41 * or to the unicode chararacters for paragraph separation (PS) 42 * or line separation (LS). 43 * - unicode case folding (for case insensitive string comparisons) 44 * - rejection of illegal UTF-8 data 45 * (i.e. UTF-8 encoded UTF-16 surrogates) 46 * - support for korean hangul characters 47 * Unicode Version 5.0.0 is supported. 48 */ 49 50 51 #ifndef UTF8PROC_H 52 #define UTF8PROC_H 53 54 55 #include <stdlib.h> 56 #include <sys/types.h> 57 #ifdef _MSC_VER 58 typedef signed char int8_t; 59 typedef unsigned char uint8_t; 60 typedef short int16_t; 61 typedef unsigned short uint16_t; 62 typedef int int32_t; 63 #ifdef _WIN64 64 #define ssize_t __int64 65 #else 66 #define ssize_t int 67 #endif 68 typedef unsigned char bool; 69 enum {false, true}; 70 #else 71 #include <stdbool.h> 72 #include <inttypes.h> 73 #endif 74 #include <limits.h> 75 76 #ifdef __cplusplus 77 extern "C" { 78 #endif 79 80 #ifndef SSIZE_MAX 81 #define SSIZE_MAX ((size_t)SIZE_MAX/2) 82 #endif 83 84 #define UTF8PROC_NULLTERM (1<<0) 85 #define UTF8PROC_STABLE (1<<1) 86 #define UTF8PROC_COMPAT (1<<2) 87 #define UTF8PROC_COMPOSE (1<<3) 88 #define UTF8PROC_DECOMPOSE (1<<4) 89 #define UTF8PROC_IGNORE (1<<5) 90 #define UTF8PROC_REJECTNA (1<<6) 91 #define UTF8PROC_NLF2LS (1<<7) 92 #define UTF8PROC_NLF2PS (1<<8) 93 #define UTF8PROC_NLF2LF (UTF8PROC_NLF2LS | UTF8PROC_NLF2PS) 94 #define UTF8PROC_STRIPCC (1<<9) 95 #define UTF8PROC_CASEFOLD (1<<10) 96 #define UTF8PROC_CHARBOUND (1<<11) 97 #define UTF8PROC_LUMP (1<<12) 98 #define UTF8PROC_STRIPMARK (1<<13) 99 /* 100 * Flags being regarded by several functions in the library: 101 * NULLTERM: The given UTF-8 input is NULL terminated. 102 * STABLE: Unicode Versioning Stability has to be respected. 103 * COMPAT: Compatiblity decomposition 104 * (i.e. formatting information is lost) 105 * COMPOSE: Return a result with composed characters. 106 * DECOMPOSE: Return a result with decomposed characters. 107 * IGNORE: Strip "default ignorable characters" 108 * REJECTNA: Return an error, if the input contains unassigned 109 * code points. 110 * NLF2LS: Indicating that NLF-sequences (LF, CRLF, CR, NEL) are 111 * representing a line break, and should be converted to the 112 * unicode character for line separation (LS). 113 * NLF2PS: Indicating that NLF-sequences are representing a paragraph 114 * break, and should be converted to the unicode character for 115 * paragraph separation (PS). 116 * NLF2LF: Indicating that the meaning of NLF-sequences is unknown. 117 * STRIPCC: Strips and/or convers control characters. 118 * NLF-sequences are transformed into space, except if one of 119 * the NLF2LS/PS/LF options is given. 120 * HorizontalTab (HT) and FormFeed (FF) are treated as a 121 * NLF-sequence in this case. 122 * All other control characters are simply removed. 123 * CASEFOLD: Performs unicode case folding, to be able to do a 124 * case-insensitive string comparison. 125 * CHARBOUND: Inserts 0xFF bytes at the beginning of each sequence which 126 * is representing a single grapheme cluster (see UAX#29). 127 * LUMP: Lumps certain characters together 128 * (e.g. HYPHEN U+2010 and MINUS U+2212 to ASCII "-"). 129 * (See lump.txt for details.) 130 * If NLF2LF is set, this includes a transformation of 131 * paragraph and line separators to ASCII line-feed (LF). 132 * STRIPMARK: Strips all character markings 133 * (non-spacing, spacing and enclosing) (i.e. accents) 134 * NOTE: this option works only with COMPOSE or DECOMPOSE 135 */ 136 137 #define UTF8PROC_ERROR_NOMEM -1 138 #define UTF8PROC_ERROR_OVERFLOW -2 139 #define UTF8PROC_ERROR_INVALIDUTF8 -3 140 #define UTF8PROC_ERROR_NOTASSIGNED -4 141 #define UTF8PROC_ERROR_INVALIDOPTS -5 142 /* 143 * Error codes being returned by almost all functions: 144 * ERROR_NOMEM: Memory could not be allocated. 145 * ERROR_OVERFLOW: The given string is too long to be processed. 146 * ERROR_INVALIDUTF8: The given string is not a legal UTF-8 string. 147 * ERROR_NOTASSIGNED: The REJECTNA flag was set, 148 * and an unassigned code point was found. 149 * ERROR_INVALIDOPTS: Invalid options have been used. 150 */ 151 152 typedef int16_t utf8proc_propval_t; 153 typedef struct utf8proc_property_struct { 154 utf8proc_propval_t category; 155 utf8proc_propval_t combining_class; 156 utf8proc_propval_t bidi_class; 157 utf8proc_propval_t decomp_type; 158 const int32_t *decomp_mapping; 159 unsigned bidi_mirrored:1; 160 int32_t uppercase_mapping; 161 int32_t lowercase_mapping; 162 int32_t titlecase_mapping; 163 int32_t comb1st_index; 164 int32_t comb2nd_index; 165 unsigned comp_exclusion:1; 166 unsigned ignorable:1; 167 unsigned control_boundary:1; 168 unsigned extend:1; 169 const int32_t *casefold_mapping; 170 } utf8proc_property_t; 171 172 #define UTF8PROC_CATEGORY_LU 1 173 #define UTF8PROC_CATEGORY_LL 2 174 #define UTF8PROC_CATEGORY_LT 3 175 #define UTF8PROC_CATEGORY_LM 4 176 #define UTF8PROC_CATEGORY_LO 5 177 #define UTF8PROC_CATEGORY_MN 6 178 #define UTF8PROC_CATEGORY_MC 7 179 #define UTF8PROC_CATEGORY_ME 8 180 #define UTF8PROC_CATEGORY_ND 9 181 #define UTF8PROC_CATEGORY_NL 10 182 #define UTF8PROC_CATEGORY_NO 11 183 #define UTF8PROC_CATEGORY_PC 12 184 #define UTF8PROC_CATEGORY_PD 13 185 #define UTF8PROC_CATEGORY_PS 14 186 #define UTF8PROC_CATEGORY_PE 15 187 #define UTF8PROC_CATEGORY_PI 16 188 #define UTF8PROC_CATEGORY_PF 17 189 #define UTF8PROC_CATEGORY_PO 18 190 #define UTF8PROC_CATEGORY_SM 19 191 #define UTF8PROC_CATEGORY_SC 20 192 #define UTF8PROC_CATEGORY_SK 21 193 #define UTF8PROC_CATEGORY_SO 22 194 #define UTF8PROC_CATEGORY_ZS 23 195 #define UTF8PROC_CATEGORY_ZL 24 196 #define UTF8PROC_CATEGORY_ZP 25 197 #define UTF8PROC_CATEGORY_CC 26 198 #define UTF8PROC_CATEGORY_CF 27 199 #define UTF8PROC_CATEGORY_CS 28 200 #define UTF8PROC_CATEGORY_CO 29 201 #define UTF8PROC_CATEGORY_CN 30 202 #define UTF8PROC_BIDI_CLASS_L 1 203 #define UTF8PROC_BIDI_CLASS_LRE 2 204 #define UTF8PROC_BIDI_CLASS_LRO 3 205 #define UTF8PROC_BIDI_CLASS_R 4 206 #define UTF8PROC_BIDI_CLASS_AL 5 207 #define UTF8PROC_BIDI_CLASS_RLE 6 208 #define UTF8PROC_BIDI_CLASS_RLO 7 209 #define UTF8PROC_BIDI_CLASS_PDF 8 210 #define UTF8PROC_BIDI_CLASS_EN 9 211 #define UTF8PROC_BIDI_CLASS_ES 10 212 #define UTF8PROC_BIDI_CLASS_ET 11 213 #define UTF8PROC_BIDI_CLASS_AN 12 214 #define UTF8PROC_BIDI_CLASS_CS 13 215 #define UTF8PROC_BIDI_CLASS_NSM 14 216 #define UTF8PROC_BIDI_CLASS_BN 15 217 #define UTF8PROC_BIDI_CLASS_B 16 218 #define UTF8PROC_BIDI_CLASS_S 17 219 #define UTF8PROC_BIDI_CLASS_WS 18 220 #define UTF8PROC_BIDI_CLASS_ON 19 221 #define UTF8PROC_DECOMP_TYPE_FONT 1 222 #define UTF8PROC_DECOMP_TYPE_NOBREAK 2 223 #define UTF8PROC_DECOMP_TYPE_INITIAL 3 224 #define UTF8PROC_DECOMP_TYPE_MEDIAL 4 225 #define UTF8PROC_DECOMP_TYPE_FINAL 5 226 #define UTF8PROC_DECOMP_TYPE_ISOLATED 6 227 #define UTF8PROC_DECOMP_TYPE_CIRCLE 7 228 #define UTF8PROC_DECOMP_TYPE_SUPER 8 229 #define UTF8PROC_DECOMP_TYPE_SUB 9 230 #define UTF8PROC_DECOMP_TYPE_VERTICAL 10 231 #define UTF8PROC_DECOMP_TYPE_WIDE 11 232 #define UTF8PROC_DECOMP_TYPE_NARROW 12 233 #define UTF8PROC_DECOMP_TYPE_SMALL 13 234 #define UTF8PROC_DECOMP_TYPE_SQUARE 14 235 #define UTF8PROC_DECOMP_TYPE_FRACTION 15 236 #define UTF8PROC_DECOMP_TYPE_COMPAT 16 237 238 extern const int8_t utf8proc_utf8class[256]; 239 240 const char *utf8proc_version(void); 241 242 const char *utf8proc_errmsg(ssize_t errcode); 243 /* 244 * Returns a static error string for the given error code. 245 */ 246 247 ssize_t utf8proc_iterate(const uint8_t *str, ssize_t strlen, int32_t *dst); 248 /* 249 * Reads a single char from the UTF-8 sequence being pointed to by 'str'. 250 * The maximum number of bytes read is 'strlen', unless 'strlen' is 251 * negative. 252 * If a valid unicode char could be read, it is stored in the variable 253 * being pointed to by 'dst', otherwise that variable will be set to -1. 254 * In case of success the number of bytes read is returned, otherwise a 255 * negative error code is returned. 256 */ 257 258 bool utf8proc_codepoint_valid(int32_t uc); 259 /* 260 * Returns 1, if the given unicode code-point is valid, otherwise 0. 261 */ 262 263 ssize_t utf8proc_encode_char(int32_t uc, uint8_t *dst); 264 /* 265 * Encodes the unicode char with the code point 'uc' as an UTF-8 string in 266 * the byte array being pointed to by 'dst'. This array has to be at least 267 * 4 bytes long. 268 * In case of success the number of bytes written is returned, 269 * otherwise 0. 270 * This function does not check if 'uc' is a valid unicode code point. 271 */ 272 273 const utf8proc_property_t *utf8proc_get_property(int32_t uc); 274 /* 275 * Returns a pointer to a (constant) struct containing information about 276 * the unicode char with the given code point 'uc'. 277 * If the character is not existent a pointer to a special struct is 278 * returned, where 'category' is a NULL pointer. 279 * WARNING: The parameter 'uc' has to be in the range of 0x0000 to 280 * 0x10FFFF, otherwise the program might crash! 281 */ 282 283 ssize_t utf8proc_decompose_char( 284 int32_t uc, int32_t *dst, ssize_t bufsize, 285 int options, int *last_boundclass 286 ); 287 /* 288 * Writes a decomposition of the unicode char 'uc' into the array being 289 * pointed to by 'dst'. 290 * Following flags in the 'options' field are regarded: 291 * REJECTNA: an unassigned unicode code point leads to an error 292 * IGNORE: "default ignorable" chars are stripped 293 * CASEFOLD: unicode casefolding is applied 294 * COMPAT: replace certain characters with their 295 * compatibility decomposition 296 * CHARBOUND: Inserts 0xFF bytes before each grapheme cluster 297 * LUMP: lumps certain different characters together 298 * STRIPMARK: removes all character marks 299 * The pointer 'last_boundclass' has to point to an integer variable which 300 * is storing the last character boundary class, if the CHARBOUND option 301 * is used. 302 * In case of success the number of chars written is returned, 303 * in case of an error, a negative error code is returned. 304 * If the number of written chars would be bigger than 'bufsize', 305 * the buffer (up to 'bufsize') has inpredictable data, and the needed 306 * buffer size is returned. 307 * WARNING: The parameter 'uc' has to be in the range of 0x0000 to 308 * 0x10FFFF, otherwise the program might crash! 309 */ 310 311 ssize_t utf8proc_decompose( 312 const uint8_t *str, ssize_t strlen, 313 int32_t *buffer, ssize_t bufsize, int options 314 ); 315 /* 316 * Does the same as 'utf8proc_decompose_char', but acts on a whole UTF-8 317 * string, and orders the decomposed sequences correctly. 318 * If the NULLTERM flag in 'options' is set, processing will be stopped, 319 * when a NULL byte is encounted, otherwise 'strlen' bytes are processed. 320 * The result in form of unicode code points is written into the buffer 321 * being pointed to by 'buffer', having the length of 'bufsize' entries. 322 * In case of success the number of chars written is returned, 323 * in case of an error, a negative error code is returned. 324 * If the number of written chars would be bigger than 'bufsize', 325 * the buffer (up to 'bufsize') has inpredictable data, and the needed 326 * buffer size is returned. 327 */ 328 329 ssize_t utf8proc_reencode(int32_t *buffer, ssize_t length, int options); 330 /* 331 * Reencodes the sequence of unicode characters given by the pointer 332 * 'buffer' and 'length' as UTF-8. 333 * The result is stored in the same memory area where the data is read. 334 * Following flags in the 'options' field are regarded: 335 * NLF2LS: converts LF, CRLF, CR and NEL into LS 336 * NLF2PS: converts LF, CRLF, CR and NEL into PS 337 * NLF2LF: converts LF, CRLF, CR and NEL into LF 338 * STRIPCC: strips or converts all non-affected control characters 339 * COMPOSE: tries to combine decomposed characters into composite 340 * characters 341 * STABLE: prohibits combining characters which would violate 342 * the unicode versioning stability 343 * In case of success the length of the resulting UTF-8 string is 344 * returned, otherwise a negative error code is returned. 345 * WARNING: The amount of free space being pointed to by 'buffer', has to 346 * exceed the amount of the input data by one byte, and the 347 * entries of the array pointed to by 'str' have to be in the 348 * range of 0x0000 to 0x10FFFF, otherwise the program might 349 * crash! 350 */ 351 352 ssize_t utf8proc_map( 353 const uint8_t *str, ssize_t strlen, uint8_t **dstptr, int options 354 ); 355 /* 356 * Maps the given UTF-8 string being pointed to by 'str' to a new UTF-8 357 * string, which is allocated dynamically, and afterwards pointed to by 358 * the pointer being pointed to by 'dstptr'. 359 * If the NULLTERM flag in the 'options' field is set, the length is 360 * determined by a NULL terminator, otherwise the parameter 'strlen' is 361 * evaluated to determine the string length, but in any case the result 362 * will be NULL terminated (though it might contain NULL characters 363 * before). Other flags in the 'options' field are passed to the functions 364 * defined above, and regarded as described. 365 * In case of success the length of the new string is returned, 366 * otherwise a negative error code is returned. 367 * NOTICE: The memory of the new UTF-8 string will have been allocated with 368 * 'malloc', and has theirfore to be freed with 'free'. 369 */ 370 371 uint8_t *utf8proc_NFD(const uint8_t *str); 372 uint8_t *utf8proc_NFC(const uint8_t *str); 373 uint8_t *utf8proc_NFKD(const uint8_t *str); 374 uint8_t *utf8proc_NFKC(const uint8_t *str); 375 /* 376 * Returns a pointer to newly allocated memory of a NFD, NFC, NFKD or NFKC 377 * normalized version of the null-terminated string 'str'. 378 */ 379 380 #ifdef __cplusplus 381 } 382 #endif 383 384 #endif 385 386