1 /*
   2  * Copyright (C) 2012 Grigori Goronzy <greg@kinoho.net>
   3  *
   4  * Permission to use, copy, modify, and/or distribute this software for any
   5  * purpose with or without fee is hereby granted, provided that the above
   6  * copyright notice and this permission notice appear in all copies.
   7  *
   8  * THE SOFTWARE IS PROVIDED "AS IS" AND THE AUTHOR DISCLAIMS ALL WARRANTIES
   9  * WITH REGARD TO THIS SOFTWARE INCLUDING ALL IMPLIED WARRANTIES OF
  10  * MERCHANTABILITY AND FITNESS. IN NO EVENT SHALL THE AUTHOR BE LIABLE FOR
  11  * ANY SPECIAL, DIRECT, INDIRECT, OR CONSEQUENTIAL DAMAGES OR ANY DAMAGES
  12  * WHATSOEVER RESULTING FROM LOSS OF USE, DATA OR PROFITS, WHETHER IN AN
  13  * ACTION OF CONTRACT, NEGLIGENCE OR OTHER TORTIOUS ACTION, ARISING OUT OF
  14  * OR IN CONNECTION WITH THE USE OR PERFORMANCE OF THIS SOFTWARE.
  15  */
  16 
  17 #ifndef UCDN_H
  18 #define UCDN_H
  19 
  20 #if defined(__GNUC__) && (__GNUC__ >= 4) && !defined(__MINGW32__)
  21 # define HB_BEGIN_VISIBILITY _Pragma ("GCC visibility push(hidden)")
  22 # define HB_END_VISIBILITY _Pragma ("GCC visibility pop")
  23 #else
  24 # define HB_BEGIN_VISIBILITY
  25 # define HB_END_VISIBILITY
  26 #endif
  27 #ifdef __cplusplus
  28 # define HB_BEGIN_HEADER  extern "C" { HB_BEGIN_VISIBILITY
  29 # define HB_END_HEADER  HB_END_VISIBILITY }
  30 #else
  31 # define HB_BEGIN_HEADER  HB_BEGIN_VISIBILITY
  32 # define HB_END_HEADER  HB_END_VISIBILITY
  33 #endif
  34 
  35 HB_BEGIN_HEADER
  36 
  37 #if !defined (HB_DONT_DEFINE_STDINT)
  38 
  39 #if defined (_SVR4) || defined (SVR4) || defined (__OpenBSD__) || \
  40     defined (_sgi) || defined (__sun) || defined (sun) || \
  41     defined (__digital__) || defined (__HP_cc)
  42 #  include <inttypes.h>
  43 #elif defined (_AIX)
  44 #  include <sys/inttypes.h>
  45 /* VS 2010 (_MSC_VER 1600) has stdint.h */
  46 #elif defined (_MSC_VER) && _MSC_VER < 1600
  47 typedef __int8 int8_t;
  48 typedef unsigned __int8 uint8_t;
  49 typedef __int16 int16_t;
  50 typedef unsigned __int16 uint16_t;
  51 typedef __int32 int32_t;
  52 typedef unsigned __int32 uint32_t;
  53 typedef __int64 int64_t;
  54 typedef unsigned __int64 uint64_t;
  55 #else
  56 #  include <stdint.h>
  57 #endif
  58 
  59 #endif
  60 
  61 #define UCDN_EAST_ASIAN_F 0
  62 #define UCDN_EAST_ASIAN_H 1
  63 #define UCDN_EAST_ASIAN_W 2
  64 #define UCDN_EAST_ASIAN_NA 3
  65 #define UCDN_EAST_ASIAN_A 4
  66 #define UCDN_EAST_ASIAN_N 5
  67 
  68 #define UCDN_SCRIPT_COMMON 0
  69 #define UCDN_SCRIPT_LATIN 1
  70 #define UCDN_SCRIPT_GREEK 2
  71 #define UCDN_SCRIPT_CYRILLIC 3
  72 #define UCDN_SCRIPT_ARMENIAN 4
  73 #define UCDN_SCRIPT_HEBREW 5
  74 #define UCDN_SCRIPT_ARABIC 6
  75 #define UCDN_SCRIPT_SYRIAC 7
  76 #define UCDN_SCRIPT_THAANA 8
  77 #define UCDN_SCRIPT_DEVANAGARI 9
  78 #define UCDN_SCRIPT_BENGALI 10
  79 #define UCDN_SCRIPT_GURMUKHI 11
  80 #define UCDN_SCRIPT_GUJARATI 12
  81 #define UCDN_SCRIPT_ORIYA 13
  82 #define UCDN_SCRIPT_TAMIL 14
  83 #define UCDN_SCRIPT_TELUGU 15
  84 #define UCDN_SCRIPT_KANNADA 16
  85 #define UCDN_SCRIPT_MALAYALAM 17
  86 #define UCDN_SCRIPT_SINHALA 18
  87 #define UCDN_SCRIPT_THAI 19
  88 #define UCDN_SCRIPT_LAO 20
  89 #define UCDN_SCRIPT_TIBETAN 21
  90 #define UCDN_SCRIPT_MYANMAR 22
  91 #define UCDN_SCRIPT_GEORGIAN 23
  92 #define UCDN_SCRIPT_HANGUL 24
  93 #define UCDN_SCRIPT_ETHIOPIC 25
  94 #define UCDN_SCRIPT_CHEROKEE 26
  95 #define UCDN_SCRIPT_CANADIAN_ABORIGINAL 27
  96 #define UCDN_SCRIPT_OGHAM 28
  97 #define UCDN_SCRIPT_RUNIC 29
  98 #define UCDN_SCRIPT_KHMER 30
  99 #define UCDN_SCRIPT_MONGOLIAN 31
 100 #define UCDN_SCRIPT_HIRAGANA 32
 101 #define UCDN_SCRIPT_KATAKANA 33
 102 #define UCDN_SCRIPT_BOPOMOFO 34
 103 #define UCDN_SCRIPT_HAN 35
 104 #define UCDN_SCRIPT_YI 36
 105 #define UCDN_SCRIPT_OLD_ITALIC 37
 106 #define UCDN_SCRIPT_GOTHIC 38
 107 #define UCDN_SCRIPT_DESERET 39
 108 #define UCDN_SCRIPT_INHERITED 40
 109 #define UCDN_SCRIPT_TAGALOG 41
 110 #define UCDN_SCRIPT_HANUNOO 42
 111 #define UCDN_SCRIPT_BUHID 43
 112 #define UCDN_SCRIPT_TAGBANWA 44
 113 #define UCDN_SCRIPT_LIMBU 45
 114 #define UCDN_SCRIPT_TAI_LE 46
 115 #define UCDN_SCRIPT_LINEAR_B 47
 116 #define UCDN_SCRIPT_UGARITIC 48
 117 #define UCDN_SCRIPT_SHAVIAN 49
 118 #define UCDN_SCRIPT_OSMANYA 50
 119 #define UCDN_SCRIPT_CYPRIOT 51
 120 #define UCDN_SCRIPT_BRAILLE 52
 121 #define UCDN_SCRIPT_BUGINESE 53
 122 #define UCDN_SCRIPT_COPTIC 54
 123 #define UCDN_SCRIPT_NEW_TAI_LUE 55
 124 #define UCDN_SCRIPT_GLAGOLITIC 56
 125 #define UCDN_SCRIPT_TIFINAGH 57
 126 #define UCDN_SCRIPT_SYLOTI_NAGRI 58
 127 #define UCDN_SCRIPT_OLD_PERSIAN 59
 128 #define UCDN_SCRIPT_KHAROSHTHI 60
 129 #define UCDN_SCRIPT_BALINESE 61
 130 #define UCDN_SCRIPT_CUNEIFORM 62
 131 #define UCDN_SCRIPT_PHOENICIAN 63
 132 #define UCDN_SCRIPT_PHAGS_PA 64
 133 #define UCDN_SCRIPT_NKO 65
 134 #define UCDN_SCRIPT_SUNDANESE 66
 135 #define UCDN_SCRIPT_LEPCHA 67
 136 #define UCDN_SCRIPT_OL_CHIKI 68
 137 #define UCDN_SCRIPT_VAI 69
 138 #define UCDN_SCRIPT_SAURASHTRA 70
 139 #define UCDN_SCRIPT_KAYAH_LI 71
 140 #define UCDN_SCRIPT_REJANG 72
 141 #define UCDN_SCRIPT_LYCIAN 73
 142 #define UCDN_SCRIPT_CARIAN 74
 143 #define UCDN_SCRIPT_LYDIAN 75
 144 #define UCDN_SCRIPT_CHAM 76
 145 #define UCDN_SCRIPT_TAI_THAM 77
 146 #define UCDN_SCRIPT_TAI_VIET 78
 147 #define UCDN_SCRIPT_AVESTAN 79
 148 #define UCDN_SCRIPT_EGYPTIAN_HIEROGLYPHS 80
 149 #define UCDN_SCRIPT_SAMARITAN 81
 150 #define UCDN_SCRIPT_LISU 82
 151 #define UCDN_SCRIPT_BAMUM 83
 152 #define UCDN_SCRIPT_JAVANESE 84
 153 #define UCDN_SCRIPT_MEETEI_MAYEK 85
 154 #define UCDN_SCRIPT_IMPERIAL_ARAMAIC 86
 155 #define UCDN_SCRIPT_OLD_SOUTH_ARABIAN 87
 156 #define UCDN_SCRIPT_INSCRIPTIONAL_PARTHIAN 88
 157 #define UCDN_SCRIPT_INSCRIPTIONAL_PAHLAVI 89
 158 #define UCDN_SCRIPT_OLD_TURKIC 90
 159 #define UCDN_SCRIPT_KAITHI 91
 160 #define UCDN_SCRIPT_BATAK 92
 161 #define UCDN_SCRIPT_BRAHMI 93
 162 #define UCDN_SCRIPT_MANDAIC 94
 163 #define UCDN_SCRIPT_CHAKMA 95
 164 #define UCDN_SCRIPT_MEROITIC_CURSIVE 96
 165 #define UCDN_SCRIPT_MEROITIC_HIEROGLYPHS 97
 166 #define UCDN_SCRIPT_MIAO 98
 167 #define UCDN_SCRIPT_SHARADA 99
 168 #define UCDN_SCRIPT_SORA_SOMPENG 100
 169 #define UCDN_SCRIPT_TAKRI 101
 170 #define UCDN_SCRIPT_UNKNOWN 102
 171 #define UCDN_SCRIPT_BASSA_VAH 103
 172 #define UCDN_SCRIPT_CAUCASIAN_ALBANIAN 104
 173 #define UCDN_SCRIPT_DUPLOYAN 105
 174 #define UCDN_SCRIPT_ELBASAN 106
 175 #define UCDN_SCRIPT_GRANTHA 107
 176 #define UCDN_SCRIPT_KHOJKI 108
 177 #define UCDN_SCRIPT_KHUDAWADI 109
 178 #define UCDN_SCRIPT_LINEAR_A 110
 179 #define UCDN_SCRIPT_MAHAJANI 111
 180 #define UCDN_SCRIPT_MANICHAEAN 112
 181 #define UCDN_SCRIPT_MENDE_KIKAKUI 113
 182 #define UCDN_SCRIPT_MODI 114
 183 #define UCDN_SCRIPT_MRO 115
 184 #define UCDN_SCRIPT_NABATAEAN 116
 185 #define UCDN_SCRIPT_OLD_NORTH_ARABIAN 117
 186 #define UCDN_SCRIPT_OLD_PERMIC 118
 187 #define UCDN_SCRIPT_PAHAWH_HMONG 119
 188 #define UCDN_SCRIPT_PALMYRENE 120
 189 #define UCDN_SCRIPT_PAU_CIN_HAU 121
 190 #define UCDN_SCRIPT_PSALTER_PAHLAVI 122
 191 #define UCDN_SCRIPT_SIDDHAM 123
 192 #define UCDN_SCRIPT_TIRHUTA 124
 193 #define UCDN_SCRIPT_WARANG_CITI 125
 194 #define UCDN_SCRIPT_AHOM 126
 195 #define UCDN_SCRIPT_ANATOLIAN_HIEROGLYPHS 127
 196 #define UCDN_SCRIPT_HATRAN 128
 197 #define UCDN_SCRIPT_MULTANI 129
 198 #define UCDN_SCRIPT_OLD_HUNGARIAN 130
 199 #define UCDN_SCRIPT_SIGNWRITING 131
 200 
 201 #define UCDN_GENERAL_CATEGORY_CC 0
 202 #define UCDN_GENERAL_CATEGORY_CF 1
 203 #define UCDN_GENERAL_CATEGORY_CN 2
 204 #define UCDN_GENERAL_CATEGORY_CO 3
 205 #define UCDN_GENERAL_CATEGORY_CS 4
 206 #define UCDN_GENERAL_CATEGORY_LL 5
 207 #define UCDN_GENERAL_CATEGORY_LM 6
 208 #define UCDN_GENERAL_CATEGORY_LO 7
 209 #define UCDN_GENERAL_CATEGORY_LT 8
 210 #define UCDN_GENERAL_CATEGORY_LU 9
 211 #define UCDN_GENERAL_CATEGORY_MC 10
 212 #define UCDN_GENERAL_CATEGORY_ME 11
 213 #define UCDN_GENERAL_CATEGORY_MN 12
 214 #define UCDN_GENERAL_CATEGORY_ND 13
 215 #define UCDN_GENERAL_CATEGORY_NL 14
 216 #define UCDN_GENERAL_CATEGORY_NO 15
 217 #define UCDN_GENERAL_CATEGORY_PC 16
 218 #define UCDN_GENERAL_CATEGORY_PD 17
 219 #define UCDN_GENERAL_CATEGORY_PE 18
 220 #define UCDN_GENERAL_CATEGORY_PF 19
 221 #define UCDN_GENERAL_CATEGORY_PI 20
 222 #define UCDN_GENERAL_CATEGORY_PO 21
 223 #define UCDN_GENERAL_CATEGORY_PS 22
 224 #define UCDN_GENERAL_CATEGORY_SC 23
 225 #define UCDN_GENERAL_CATEGORY_SK 24
 226 #define UCDN_GENERAL_CATEGORY_SM 25
 227 #define UCDN_GENERAL_CATEGORY_SO 26
 228 #define UCDN_GENERAL_CATEGORY_ZL 27
 229 #define UCDN_GENERAL_CATEGORY_ZP 28
 230 #define UCDN_GENERAL_CATEGORY_ZS 29
 231 
 232 #define UCDN_BIDI_CLASS_L 0
 233 #define UCDN_BIDI_CLASS_LRE 1
 234 #define UCDN_BIDI_CLASS_LRO 2
 235 #define UCDN_BIDI_CLASS_R 3
 236 #define UCDN_BIDI_CLASS_AL 4
 237 #define UCDN_BIDI_CLASS_RLE 5
 238 #define UCDN_BIDI_CLASS_RLO 6
 239 #define UCDN_BIDI_CLASS_PDF 7
 240 #define UCDN_BIDI_CLASS_EN 8
 241 #define UCDN_BIDI_CLASS_ES 9
 242 #define UCDN_BIDI_CLASS_ET 10
 243 #define UCDN_BIDI_CLASS_AN 11
 244 #define UCDN_BIDI_CLASS_CS 12
 245 #define UCDN_BIDI_CLASS_NSM 13
 246 #define UCDN_BIDI_CLASS_BN 14
 247 #define UCDN_BIDI_CLASS_B 15
 248 #define UCDN_BIDI_CLASS_S 16
 249 #define UCDN_BIDI_CLASS_WS 17
 250 #define UCDN_BIDI_CLASS_ON 18
 251 #define UCDN_BIDI_CLASS_LRI 19
 252 #define UCDN_BIDI_CLASS_RLI 20
 253 #define UCDN_BIDI_CLASS_FSI 21
 254 #define UCDN_BIDI_CLASS_PDI 22
 255 
 256 /**
 257  * Return version of the Unicode database.
 258  *
 259  * @return Unicode database version
 260  */
 261 const char *ucdn_get_unicode_version(void);
 262 
 263 /**
 264  * Get combining class of a codepoint.
 265  *
 266  * @param code Unicode codepoint
 267  * @return combining class value, as defined in UAX#44
 268  */
 269 int ucdn_get_combining_class(uint32_t code);
 270 
 271 /**
 272  * Get east-asian width of a codepoint.
 273  *
 274  * @param code Unicode codepoint
 275  * @return value according to UCDN_EAST_ASIAN_* and as defined in UAX#11.
 276  */
 277 int ucdn_get_east_asian_width(uint32_t code);
 278 
 279 /**
 280  * Get general category of a codepoint.
 281  *
 282  * @param code Unicode codepoint
 283  * @return value according to UCDN_GENERAL_CATEGORY_* and as defined in
 284  * UAX#44.
 285  */
 286 int ucdn_get_general_category(uint32_t code);
 287 
 288 /**
 289  * Get bidirectional class of a codepoint.
 290  *
 291  * @param code Unicode codepoint
 292  * @return value according to UCDN_BIDI_CLASS_* and as defined in UAX#44.
 293  */
 294 int ucdn_get_bidi_class(uint32_t code);
 295 
 296 /**
 297  * Get script of a codepoint.
 298  *
 299  * @param code Unicode codepoint
 300  * @return value according to UCDN_SCRIPT_* and as defined in UAX#24.
 301  */
 302 int ucdn_get_script(uint32_t code);
 303 
 304 /**
 305  * Check if codepoint can be mirrored.
 306  *
 307  * @param code Unicode codepoint
 308  * @return 1 if mirrored character exists, otherwise 0
 309  */
 310 int ucdn_get_mirrored(uint32_t code);
 311 
 312 /**
 313  * Mirror a codepoint.
 314  *
 315  * @param code Unicode codepoint
 316  * @return mirrored codepoint or the original codepoint if no
 317  * mirrored character exists
 318  */
 319 uint32_t ucdn_mirror(uint32_t code);
 320 
 321 /**
 322  * Pairwise canonical decomposition of a codepoint. This includes
 323  * Hangul Jamo decomposition (see chapter 3.12 of the Unicode core
 324  * specification).
 325  *
 326  * Hangul is decomposed into L and V jamos for LV forms, and an
 327  * LV precomposed syllable and a T jamo for LVT forms.
 328  *
 329  * @param code Unicode codepoint
 330  * @param a filled with first codepoint of decomposition
 331  * @param b filled with second codepoint of decomposition, or 0
 332  * @return success
 333  */
 334 int ucdn_decompose(uint32_t code, uint32_t *a, uint32_t *b);
 335 
 336 /**
 337  * Compatibility decomposition of a codepoint.
 338  *
 339  * @param code Unicode codepoint
 340  * @param decomposed filled with decomposition, must be able to hold 18
 341  * characters
 342  * @return length of decomposition or 0 in case none exists
 343  */
 344 int ucdn_compat_decompose(uint32_t code, uint32_t *decomposed);
 345 
 346 /**
 347  * Pairwise canonical composition of two codepoints. This includes
 348  * Hangul Jamo composition (see chapter 3.12 of the Unicode core
 349  * specification).
 350  *
 351  * Hangul composition expects either L and V jamos, or an LV
 352  * precomposed syllable and a T jamo. This is exactly the inverse
 353  * of pairwise Hangul decomposition.
 354  *
 355  * @param code filled with composition
 356  * @param a first codepoint
 357  * @param b second codepoint
 358  * @return success
 359  */
 360 int ucdn_compose(uint32_t *code, uint32_t a, uint32_t b);
 361 
 362 HB_END_HEADER
 363 
 364 #endif