| 6 |
and semantics are as close as possible to those of the Perl 5 language. |
and semantics are as close as possible to those of the Perl 5 language. |
| 7 |
|
|
| 8 |
Written by Philip Hazel |
Written by Philip Hazel |
| 9 |
Copyright (c) 1997-2008 University of Cambridge |
Copyright (c) 1997-2009 University of Cambridge |
| 10 |
|
|
| 11 |
----------------------------------------------------------------------------- |
----------------------------------------------------------------------------- |
| 12 |
Redistribution and use in source and binary forms, with or without |
Redistribution and use in source and binary forms, with or without |
| 109 |
table itself. Maintenance is more error-prone, but frequent changes to this |
table itself. Maintenance is more error-prone, but frequent changes to this |
| 110 |
data are unlikely. |
data are unlikely. |
| 111 |
|
|
| 112 |
July 2008: There is now a script called maint/GenerateUtt.py which can be used |
July 2008: There is now a script called maint/GenerateUtt.py that can be used |
| 113 |
to generate this data instead of maintaining it entirely by hand. */ |
to generate this data instead of maintaining it entirely by hand. |
| 114 |
|
|
| 115 |
const char _pcre_utt_names[] = |
The script was updated in March 2009 to generate a new EBCDIC-compliant |
| 116 |
"Any\0" |
version. Like all other character and string literals that are compared against |
| 117 |
"Arabic\0" |
the regular expression pattern, we must use STR_ macros instead of literal |
| 118 |
"Armenian\0" |
strings to make sure that UTF-8 support works on EBCDIC platforms. */ |
| 119 |
"Balinese\0" |
|
| 120 |
"Bengali\0" |
#define STRING_Any0 STR_A STR_n STR_y "\0" |
| 121 |
"Bopomofo\0" |
#define STRING_Arabic0 STR_A STR_r STR_a STR_b STR_i STR_c "\0" |
| 122 |
"Braille\0" |
#define STRING_Armenian0 STR_A STR_r STR_m STR_e STR_n STR_i STR_a STR_n "\0" |
| 123 |
"Buginese\0" |
#define STRING_Balinese0 STR_B STR_a STR_l STR_i STR_n STR_e STR_s STR_e "\0" |
| 124 |
"Buhid\0" |
#define STRING_Bengali0 STR_B STR_e STR_n STR_g STR_a STR_l STR_i "\0" |
| 125 |
"C\0" |
#define STRING_Bopomofo0 STR_B STR_o STR_p STR_o STR_m STR_o STR_f STR_o "\0" |
| 126 |
"Canadian_Aboriginal\0" |
#define STRING_Braille0 STR_B STR_r STR_a STR_i STR_l STR_l STR_e "\0" |
| 127 |
"Carian\0" |
#define STRING_Buginese0 STR_B STR_u STR_g STR_i STR_n STR_e STR_s STR_e "\0" |
| 128 |
"Cc\0" |
#define STRING_Buhid0 STR_B STR_u STR_h STR_i STR_d "\0" |
| 129 |
"Cf\0" |
#define STRING_C0 STR_C "\0" |
| 130 |
"Cham\0" |
#define STRING_Canadian_Aboriginal0 STR_C STR_a STR_n STR_a STR_d STR_i STR_a STR_n STR_UNDERSCORE STR_A STR_b STR_o STR_r STR_i STR_g STR_i STR_n STR_a STR_l "\0" |
| 131 |
"Cherokee\0" |
#define STRING_Carian0 STR_C STR_a STR_r STR_i STR_a STR_n "\0" |
| 132 |
"Cn\0" |
#define STRING_Cc0 STR_C STR_c "\0" |
| 133 |
"Co\0" |
#define STRING_Cf0 STR_C STR_f "\0" |
| 134 |
"Common\0" |
#define STRING_Cham0 STR_C STR_h STR_a STR_m "\0" |
| 135 |
"Coptic\0" |
#define STRING_Cherokee0 STR_C STR_h STR_e STR_r STR_o STR_k STR_e STR_e "\0" |
| 136 |
"Cs\0" |
#define STRING_Cn0 STR_C STR_n "\0" |
| 137 |
"Cuneiform\0" |
#define STRING_Co0 STR_C STR_o "\0" |
| 138 |
"Cypriot\0" |
#define STRING_Common0 STR_C STR_o STR_m STR_m STR_o STR_n "\0" |
| 139 |
"Cyrillic\0" |
#define STRING_Coptic0 STR_C STR_o STR_p STR_t STR_i STR_c "\0" |
| 140 |
"Deseret\0" |
#define STRING_Cs0 STR_C STR_s "\0" |
| 141 |
"Devanagari\0" |
#define STRING_Cuneiform0 STR_C STR_u STR_n STR_e STR_i STR_f STR_o STR_r STR_m "\0" |
| 142 |
"Ethiopic\0" |
#define STRING_Cypriot0 STR_C STR_y STR_p STR_r STR_i STR_o STR_t "\0" |
| 143 |
"Georgian\0" |
#define STRING_Cyrillic0 STR_C STR_y STR_r STR_i STR_l STR_l STR_i STR_c "\0" |
| 144 |
"Glagolitic\0" |
#define STRING_Deseret0 STR_D STR_e STR_s STR_e STR_r STR_e STR_t "\0" |
| 145 |
"Gothic\0" |
#define STRING_Devanagari0 STR_D STR_e STR_v STR_a STR_n STR_a STR_g STR_a STR_r STR_i "\0" |
| 146 |
"Greek\0" |
#define STRING_Ethiopic0 STR_E STR_t STR_h STR_i STR_o STR_p STR_i STR_c "\0" |
| 147 |
"Gujarati\0" |
#define STRING_Georgian0 STR_G STR_e STR_o STR_r STR_g STR_i STR_a STR_n "\0" |
| 148 |
"Gurmukhi\0" |
#define STRING_Glagolitic0 STR_G STR_l STR_a STR_g STR_o STR_l STR_i STR_t STR_i STR_c "\0" |
| 149 |
"Han\0" |
#define STRING_Gothic0 STR_G STR_o STR_t STR_h STR_i STR_c "\0" |
| 150 |
"Hangul\0" |
#define STRING_Greek0 STR_G STR_r STR_e STR_e STR_k "\0" |
| 151 |
"Hanunoo\0" |
#define STRING_Gujarati0 STR_G STR_u STR_j STR_a STR_r STR_a STR_t STR_i "\0" |
| 152 |
"Hebrew\0" |
#define STRING_Gurmukhi0 STR_G STR_u STR_r STR_m STR_u STR_k STR_h STR_i "\0" |
| 153 |
"Hiragana\0" |
#define STRING_Han0 STR_H STR_a STR_n "\0" |
| 154 |
"Inherited\0" |
#define STRING_Hangul0 STR_H STR_a STR_n STR_g STR_u STR_l "\0" |
| 155 |
"Kannada\0" |
#define STRING_Hanunoo0 STR_H STR_a STR_n STR_u STR_n STR_o STR_o "\0" |
| 156 |
"Katakana\0" |
#define STRING_Hebrew0 STR_H STR_e STR_b STR_r STR_e STR_w "\0" |
| 157 |
"Kayah_Li\0" |
#define STRING_Hiragana0 STR_H STR_i STR_r STR_a STR_g STR_a STR_n STR_a "\0" |
| 158 |
"Kharoshthi\0" |
#define STRING_Inherited0 STR_I STR_n STR_h STR_e STR_r STR_i STR_t STR_e STR_d "\0" |
| 159 |
"Khmer\0" |
#define STRING_Kannada0 STR_K STR_a STR_n STR_n STR_a STR_d STR_a "\0" |
| 160 |
"L\0" |
#define STRING_Katakana0 STR_K STR_a STR_t STR_a STR_k STR_a STR_n STR_a "\0" |
| 161 |
"L&\0" |
#define STRING_Kayah_Li0 STR_K STR_a STR_y STR_a STR_h STR_UNDERSCORE STR_L STR_i "\0" |
| 162 |
"Lao\0" |
#define STRING_Kharoshthi0 STR_K STR_h STR_a STR_r STR_o STR_s STR_h STR_t STR_h STR_i "\0" |
| 163 |
"Latin\0" |
#define STRING_Khmer0 STR_K STR_h STR_m STR_e STR_r "\0" |
| 164 |
"Lepcha\0" |
#define STRING_L0 STR_L "\0" |
| 165 |
"Limbu\0" |
#define STRING_L_AMPERSAND0 STR_L STR_AMPERSAND "\0" |
| 166 |
"Linear_B\0" |
#define STRING_Lao0 STR_L STR_a STR_o "\0" |
| 167 |
"Ll\0" |
#define STRING_Latin0 STR_L STR_a STR_t STR_i STR_n "\0" |
| 168 |
"Lm\0" |
#define STRING_Lepcha0 STR_L STR_e STR_p STR_c STR_h STR_a "\0" |
| 169 |
"Lo\0" |
#define STRING_Limbu0 STR_L STR_i STR_m STR_b STR_u "\0" |
| 170 |
"Lt\0" |
#define STRING_Linear_B0 STR_L STR_i STR_n STR_e STR_a STR_r STR_UNDERSCORE STR_B "\0" |
| 171 |
"Lu\0" |
#define STRING_Ll0 STR_L STR_l "\0" |
| 172 |
"Lycian\0" |
#define STRING_Lm0 STR_L STR_m "\0" |
| 173 |
"Lydian\0" |
#define STRING_Lo0 STR_L STR_o "\0" |
| 174 |
"M\0" |
#define STRING_Lt0 STR_L STR_t "\0" |
| 175 |
"Malayalam\0" |
#define STRING_Lu0 STR_L STR_u "\0" |
| 176 |
"Mc\0" |
#define STRING_Lycian0 STR_L STR_y STR_c STR_i STR_a STR_n "\0" |
| 177 |
"Me\0" |
#define STRING_Lydian0 STR_L STR_y STR_d STR_i STR_a STR_n "\0" |
| 178 |
"Mn\0" |
#define STRING_M0 STR_M "\0" |
| 179 |
"Mongolian\0" |
#define STRING_Malayalam0 STR_M STR_a STR_l STR_a STR_y STR_a STR_l STR_a STR_m "\0" |
| 180 |
"Myanmar\0" |
#define STRING_Mc0 STR_M STR_c "\0" |
| 181 |
"N\0" |
#define STRING_Me0 STR_M STR_e "\0" |
| 182 |
"Nd\0" |
#define STRING_Mn0 STR_M STR_n "\0" |
| 183 |
"New_Tai_Lue\0" |
#define STRING_Mongolian0 STR_M STR_o STR_n STR_g STR_o STR_l STR_i STR_a STR_n "\0" |
| 184 |
"Nko\0" |
#define STRING_Myanmar0 STR_M STR_y STR_a STR_n STR_m STR_a STR_r "\0" |
| 185 |
"Nl\0" |
#define STRING_N0 STR_N "\0" |
| 186 |
"No\0" |
#define STRING_Nd0 STR_N STR_d "\0" |
| 187 |
"Ogham\0" |
#define STRING_New_Tai_Lue0 STR_N STR_e STR_w STR_UNDERSCORE STR_T STR_a STR_i STR_UNDERSCORE STR_L STR_u STR_e "\0" |
| 188 |
"Ol_Chiki\0" |
#define STRING_Nko0 STR_N STR_k STR_o "\0" |
| 189 |
"Old_Italic\0" |
#define STRING_Nl0 STR_N STR_l "\0" |
| 190 |
"Old_Persian\0" |
#define STRING_No0 STR_N STR_o "\0" |
| 191 |
"Oriya\0" |
#define STRING_Ogham0 STR_O STR_g STR_h STR_a STR_m "\0" |
| 192 |
"Osmanya\0" |
#define STRING_Ol_Chiki0 STR_O STR_l STR_UNDERSCORE STR_C STR_h STR_i STR_k STR_i "\0" |
| 193 |
"P\0" |
#define STRING_Old_Italic0 STR_O STR_l STR_d STR_UNDERSCORE STR_I STR_t STR_a STR_l STR_i STR_c "\0" |
| 194 |
"Pc\0" |
#define STRING_Old_Persian0 STR_O STR_l STR_d STR_UNDERSCORE STR_P STR_e STR_r STR_s STR_i STR_a STR_n "\0" |
| 195 |
"Pd\0" |
#define STRING_Oriya0 STR_O STR_r STR_i STR_y STR_a "\0" |
| 196 |
"Pe\0" |
#define STRING_Osmanya0 STR_O STR_s STR_m STR_a STR_n STR_y STR_a "\0" |
| 197 |
"Pf\0" |
#define STRING_P0 STR_P "\0" |
| 198 |
"Phags_Pa\0" |
#define STRING_Pc0 STR_P STR_c "\0" |
| 199 |
"Phoenician\0" |
#define STRING_Pd0 STR_P STR_d "\0" |
| 200 |
"Pi\0" |
#define STRING_Pe0 STR_P STR_e "\0" |
| 201 |
"Po\0" |
#define STRING_Pf0 STR_P STR_f "\0" |
| 202 |
"Ps\0" |
#define STRING_Phags_Pa0 STR_P STR_h STR_a STR_g STR_s STR_UNDERSCORE STR_P STR_a "\0" |
| 203 |
"Rejang\0" |
#define STRING_Phoenician0 STR_P STR_h STR_o STR_e STR_n STR_i STR_c STR_i STR_a STR_n "\0" |
| 204 |
"Runic\0" |
#define STRING_Pi0 STR_P STR_i "\0" |
| 205 |
"S\0" |
#define STRING_Po0 STR_P STR_o "\0" |
| 206 |
"Saurashtra\0" |
#define STRING_Ps0 STR_P STR_s "\0" |
| 207 |
"Sc\0" |
#define STRING_Rejang0 STR_R STR_e STR_j STR_a STR_n STR_g "\0" |
| 208 |
"Shavian\0" |
#define STRING_Runic0 STR_R STR_u STR_n STR_i STR_c "\0" |
| 209 |
"Sinhala\0" |
#define STRING_S0 STR_S "\0" |
| 210 |
"Sk\0" |
#define STRING_Saurashtra0 STR_S STR_a STR_u STR_r STR_a STR_s STR_h STR_t STR_r STR_a "\0" |
| 211 |
"Sm\0" |
#define STRING_Sc0 STR_S STR_c "\0" |
| 212 |
"So\0" |
#define STRING_Shavian0 STR_S STR_h STR_a STR_v STR_i STR_a STR_n "\0" |
| 213 |
"Sundanese\0" |
#define STRING_Sinhala0 STR_S STR_i STR_n STR_h STR_a STR_l STR_a "\0" |
| 214 |
"Syloti_Nagri\0" |
#define STRING_Sk0 STR_S STR_k "\0" |
| 215 |
"Syriac\0" |
#define STRING_Sm0 STR_S STR_m "\0" |
| 216 |
"Tagalog\0" |
#define STRING_So0 STR_S STR_o "\0" |
| 217 |
"Tagbanwa\0" |
#define STRING_Sundanese0 STR_S STR_u STR_n STR_d STR_a STR_n STR_e STR_s STR_e "\0" |
| 218 |
"Tai_Le\0" |
#define STRING_Syloti_Nagri0 STR_S STR_y STR_l STR_o STR_t STR_i STR_UNDERSCORE STR_N STR_a STR_g STR_r STR_i "\0" |
| 219 |
"Tamil\0" |
#define STRING_Syriac0 STR_S STR_y STR_r STR_i STR_a STR_c "\0" |
| 220 |
"Telugu\0" |
#define STRING_Tagalog0 STR_T STR_a STR_g STR_a STR_l STR_o STR_g "\0" |
| 221 |
"Thaana\0" |
#define STRING_Tagbanwa0 STR_T STR_a STR_g STR_b STR_a STR_n STR_w STR_a "\0" |
| 222 |
"Thai\0" |
#define STRING_Tai_Le0 STR_T STR_a STR_i STR_UNDERSCORE STR_L STR_e "\0" |
| 223 |
"Tibetan\0" |
#define STRING_Tamil0 STR_T STR_a STR_m STR_i STR_l "\0" |
| 224 |
"Tifinagh\0" |
#define STRING_Telugu0 STR_T STR_e STR_l STR_u STR_g STR_u "\0" |
| 225 |
"Ugaritic\0" |
#define STRING_Thaana0 STR_T STR_h STR_a STR_a STR_n STR_a "\0" |
| 226 |
"Vai\0" |
#define STRING_Thai0 STR_T STR_h STR_a STR_i "\0" |
| 227 |
"Yi\0" |
#define STRING_Tibetan0 STR_T STR_i STR_b STR_e STR_t STR_a STR_n "\0" |
| 228 |
"Z\0" |
#define STRING_Tifinagh0 STR_T STR_i STR_f STR_i STR_n STR_a STR_g STR_h "\0" |
| 229 |
"Zl\0" |
#define STRING_Ugaritic0 STR_U STR_g STR_a STR_r STR_i STR_t STR_i STR_c "\0" |
| 230 |
"Zp\0" |
#define STRING_Vai0 STR_V STR_a STR_i "\0" |
| 231 |
"Zs\0"; |
#define STRING_Yi0 STR_Y STR_i "\0" |
| 232 |
|
#define STRING_Z0 STR_Z "\0" |
| 233 |
|
#define STRING_Zl0 STR_Z STR_l "\0" |
| 234 |
|
#define STRING_Zp0 STR_Z STR_p "\0" |
| 235 |
|
#define STRING_Zs0 STR_Z STR_s "\0" |
| 236 |
|
|
| 237 |
|
const char _pcre_utt_names[] = |
| 238 |
|
STRING_Any0 |
| 239 |
|
STRING_Arabic0 |
| 240 |
|
STRING_Armenian0 |
| 241 |
|
STRING_Balinese0 |
| 242 |
|
STRING_Bengali0 |
| 243 |
|
STRING_Bopomofo0 |
| 244 |
|
STRING_Braille0 |
| 245 |
|
STRING_Buginese0 |
| 246 |
|
STRING_Buhid0 |
| 247 |
|
STRING_C0 |
| 248 |
|
STRING_Canadian_Aboriginal0 |
| 249 |
|
STRING_Carian0 |
| 250 |
|
STRING_Cc0 |
| 251 |
|
STRING_Cf0 |
| 252 |
|
STRING_Cham0 |
| 253 |
|
STRING_Cherokee0 |
| 254 |
|
STRING_Cn0 |
| 255 |
|
STRING_Co0 |
| 256 |
|
STRING_Common0 |
| 257 |
|
STRING_Coptic0 |
| 258 |
|
STRING_Cs0 |
| 259 |
|
STRING_Cuneiform0 |
| 260 |
|
STRING_Cypriot0 |
| 261 |
|
STRING_Cyrillic0 |
| 262 |
|
STRING_Deseret0 |
| 263 |
|
STRING_Devanagari0 |
| 264 |
|
STRING_Ethiopic0 |
| 265 |
|
STRING_Georgian0 |
| 266 |
|
STRING_Glagolitic0 |
| 267 |
|
STRING_Gothic0 |
| 268 |
|
STRING_Greek0 |
| 269 |
|
STRING_Gujarati0 |
| 270 |
|
STRING_Gurmukhi0 |
| 271 |
|
STRING_Han0 |
| 272 |
|
STRING_Hangul0 |
| 273 |
|
STRING_Hanunoo0 |
| 274 |
|
STRING_Hebrew0 |
| 275 |
|
STRING_Hiragana0 |
| 276 |
|
STRING_Inherited0 |
| 277 |
|
STRING_Kannada0 |
| 278 |
|
STRING_Katakana0 |
| 279 |
|
STRING_Kayah_Li0 |
| 280 |
|
STRING_Kharoshthi0 |
| 281 |
|
STRING_Khmer0 |
| 282 |
|
STRING_L0 |
| 283 |
|
STRING_L_AMPERSAND0 |
| 284 |
|
STRING_Lao0 |
| 285 |
|
STRING_Latin0 |
| 286 |
|
STRING_Lepcha0 |
| 287 |
|
STRING_Limbu0 |
| 288 |
|
STRING_Linear_B0 |
| 289 |
|
STRING_Ll0 |
| 290 |
|
STRING_Lm0 |
| 291 |
|
STRING_Lo0 |
| 292 |
|
STRING_Lt0 |
| 293 |
|
STRING_Lu0 |
| 294 |
|
STRING_Lycian0 |
| 295 |
|
STRING_Lydian0 |
| 296 |
|
STRING_M0 |
| 297 |
|
STRING_Malayalam0 |
| 298 |
|
STRING_Mc0 |
| 299 |
|
STRING_Me0 |
| 300 |
|
STRING_Mn0 |
| 301 |
|
STRING_Mongolian0 |
| 302 |
|
STRING_Myanmar0 |
| 303 |
|
STRING_N0 |
| 304 |
|
STRING_Nd0 |
| 305 |
|
STRING_New_Tai_Lue0 |
| 306 |
|
STRING_Nko0 |
| 307 |
|
STRING_Nl0 |
| 308 |
|
STRING_No0 |
| 309 |
|
STRING_Ogham0 |
| 310 |
|
STRING_Ol_Chiki0 |
| 311 |
|
STRING_Old_Italic0 |
| 312 |
|
STRING_Old_Persian0 |
| 313 |
|
STRING_Oriya0 |
| 314 |
|
STRING_Osmanya0 |
| 315 |
|
STRING_P0 |
| 316 |
|
STRING_Pc0 |
| 317 |
|
STRING_Pd0 |
| 318 |
|
STRING_Pe0 |
| 319 |
|
STRING_Pf0 |
| 320 |
|
STRING_Phags_Pa0 |
| 321 |
|
STRING_Phoenician0 |
| 322 |
|
STRING_Pi0 |
| 323 |
|
STRING_Po0 |
| 324 |
|
STRING_Ps0 |
| 325 |
|
STRING_Rejang0 |
| 326 |
|
STRING_Runic0 |
| 327 |
|
STRING_S0 |
| 328 |
|
STRING_Saurashtra0 |
| 329 |
|
STRING_Sc0 |
| 330 |
|
STRING_Shavian0 |
| 331 |
|
STRING_Sinhala0 |
| 332 |
|
STRING_Sk0 |
| 333 |
|
STRING_Sm0 |
| 334 |
|
STRING_So0 |
| 335 |
|
STRING_Sundanese0 |
| 336 |
|
STRING_Syloti_Nagri0 |
| 337 |
|
STRING_Syriac0 |
| 338 |
|
STRING_Tagalog0 |
| 339 |
|
STRING_Tagbanwa0 |
| 340 |
|
STRING_Tai_Le0 |
| 341 |
|
STRING_Tamil0 |
| 342 |
|
STRING_Telugu0 |
| 343 |
|
STRING_Thaana0 |
| 344 |
|
STRING_Thai0 |
| 345 |
|
STRING_Tibetan0 |
| 346 |
|
STRING_Tifinagh0 |
| 347 |
|
STRING_Ugaritic0 |
| 348 |
|
STRING_Vai0 |
| 349 |
|
STRING_Yi0 |
| 350 |
|
STRING_Z0 |
| 351 |
|
STRING_Zl0 |
| 352 |
|
STRING_Zp0 |
| 353 |
|
STRING_Zs0; |
| 354 |
|
|
| 355 |
const ucp_type_table _pcre_utt[] = { |
const ucp_type_table _pcre_utt[] = { |
| 356 |
{ 0, PT_ANY, 0 }, |
{ 0, PT_ANY, 0 }, |