pcre2_ucp.h 8.0 KB

123456789101112131415161718192021222324252627282930313233343536373839404142434445464748495051525354555657585960616263646566676869707172737475767778798081828384858687888990919293949596979899100101102103104105106107108109110111112113114115116117118119120121122123124125126127128129130131132133134135136137138139140141142143144145146147148149150151152153154155156157158159160161162163164165166167168169170171172173174175176177178179180181182183184185186187188189190191192193194195196197198199200201202203204205206207208209210211212213214215216217218219220221222223224225226227228229230231232233234235236237238239240241242243244245246247248249250251252253254255256257258259260261262263264265266267268269270271272273274275276277278279280281282283284285286287288289290291292293294295296297298299300301302303304305
  1. /*************************************************
  2. * Perl-Compatible Regular Expressions *
  3. *************************************************/
  4. /* PCRE is a library of functions to support regular expressions whose syntax
  5. and semantics are as close as possible to those of the Perl 5 language.
  6. Written by Philip Hazel
  7. Original API code Copyright (c) 1997-2012 University of Cambridge
  8. New API code Copyright (c) 2016-2018 University of Cambridge
  9. -----------------------------------------------------------------------------
  10. Redistribution and use in source and binary forms, with or without
  11. modification, are permitted provided that the following conditions are met:
  12. * Redistributions of source code must retain the above copyright notice,
  13. this list of conditions and the following disclaimer.
  14. * Redistributions in binary form must reproduce the above copyright
  15. notice, this list of conditions and the following disclaimer in the
  16. documentation and/or other materials provided with the distribution.
  17. * Neither the name of the University of Cambridge nor the names of its
  18. contributors may be used to endorse or promote products derived from
  19. this software without specific prior written permission.
  20. THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS "AS IS"
  21. AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE
  22. IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE
  23. ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT OWNER OR CONTRIBUTORS BE
  24. LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR
  25. CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF
  26. SUBSTITUTE GOODS OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS
  27. INTERRUPTION) HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN
  28. CONTRACT, STRICT LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE)
  29. ARISING IN ANY WAY OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE
  30. POSSIBILITY OF SUCH DAMAGE.
  31. -----------------------------------------------------------------------------
  32. */
  33. #ifndef PCRE2_UCP_H_IDEMPOTENT_GUARD
  34. #define PCRE2_UCP_H_IDEMPOTENT_GUARD
  35. /* This file contains definitions of the property values that are returned by
  36. the UCD access macros. New values that are added for new releases of Unicode
  37. should always be at the end of each enum, for backwards compatibility.
  38. IMPORTANT: Note also that the specific numeric values of the enums have to be
  39. the same as the values that are generated by the maint/MultiStage2.py script,
  40. where the equivalent property descriptive names are listed in vectors.
  41. ALSO: The specific values of the first two enums are assumed for the table
  42. called catposstab in pcre2_compile.c. */
  43. /* These are the general character categories. */
  44. enum {
  45. ucp_C, /* Other */
  46. ucp_L, /* Letter */
  47. ucp_M, /* Mark */
  48. ucp_N, /* Number */
  49. ucp_P, /* Punctuation */
  50. ucp_S, /* Symbol */
  51. ucp_Z /* Separator */
  52. };
  53. /* These are the particular character categories. */
  54. enum {
  55. ucp_Cc, /* Control */
  56. ucp_Cf, /* Format */
  57. ucp_Cn, /* Unassigned */
  58. ucp_Co, /* Private use */
  59. ucp_Cs, /* Surrogate */
  60. ucp_Ll, /* Lower case letter */
  61. ucp_Lm, /* Modifier letter */
  62. ucp_Lo, /* Other letter */
  63. ucp_Lt, /* Title case letter */
  64. ucp_Lu, /* Upper case letter */
  65. ucp_Mc, /* Spacing mark */
  66. ucp_Me, /* Enclosing mark */
  67. ucp_Mn, /* Non-spacing mark */
  68. ucp_Nd, /* Decimal number */
  69. ucp_Nl, /* Letter number */
  70. ucp_No, /* Other number */
  71. ucp_Pc, /* Connector punctuation */
  72. ucp_Pd, /* Dash punctuation */
  73. ucp_Pe, /* Close punctuation */
  74. ucp_Pf, /* Final punctuation */
  75. ucp_Pi, /* Initial punctuation */
  76. ucp_Po, /* Other punctuation */
  77. ucp_Ps, /* Open punctuation */
  78. ucp_Sc, /* Currency symbol */
  79. ucp_Sk, /* Modifier symbol */
  80. ucp_Sm, /* Mathematical symbol */
  81. ucp_So, /* Other symbol */
  82. ucp_Zl, /* Line separator */
  83. ucp_Zp, /* Paragraph separator */
  84. ucp_Zs /* Space separator */
  85. };
  86. /* These are grapheme break properties. The Extended Pictographic property
  87. comes from the emoji-data.txt file. */
  88. enum {
  89. ucp_gbCR, /* 0 */
  90. ucp_gbLF, /* 1 */
  91. ucp_gbControl, /* 2 */
  92. ucp_gbExtend, /* 3 */
  93. ucp_gbPrepend, /* 4 */
  94. ucp_gbSpacingMark, /* 5 */
  95. ucp_gbL, /* 6 Hangul syllable type L */
  96. ucp_gbV, /* 7 Hangul syllable type V */
  97. ucp_gbT, /* 8 Hangul syllable type T */
  98. ucp_gbLV, /* 9 Hangul syllable type LV */
  99. ucp_gbLVT, /* 10 Hangul syllable type LVT */
  100. ucp_gbRegionalIndicator, /* 11 */
  101. ucp_gbOther, /* 12 */
  102. ucp_gbZWJ, /* 13 */
  103. ucp_gbExtended_Pictographic /* 14 */
  104. };
  105. /* These are the script identifications. */
  106. enum {
  107. ucp_Unknown,
  108. ucp_Arabic,
  109. ucp_Armenian,
  110. ucp_Bengali,
  111. ucp_Bopomofo,
  112. ucp_Braille,
  113. ucp_Buginese,
  114. ucp_Buhid,
  115. ucp_Canadian_Aboriginal,
  116. ucp_Cherokee,
  117. ucp_Common,
  118. ucp_Coptic,
  119. ucp_Cypriot,
  120. ucp_Cyrillic,
  121. ucp_Deseret,
  122. ucp_Devanagari,
  123. ucp_Ethiopic,
  124. ucp_Georgian,
  125. ucp_Glagolitic,
  126. ucp_Gothic,
  127. ucp_Greek,
  128. ucp_Gujarati,
  129. ucp_Gurmukhi,
  130. ucp_Han,
  131. ucp_Hangul,
  132. ucp_Hanunoo,
  133. ucp_Hebrew,
  134. ucp_Hiragana,
  135. ucp_Inherited,
  136. ucp_Kannada,
  137. ucp_Katakana,
  138. ucp_Kharoshthi,
  139. ucp_Khmer,
  140. ucp_Lao,
  141. ucp_Latin,
  142. ucp_Limbu,
  143. ucp_Linear_B,
  144. ucp_Malayalam,
  145. ucp_Mongolian,
  146. ucp_Myanmar,
  147. ucp_New_Tai_Lue,
  148. ucp_Ogham,
  149. ucp_Old_Italic,
  150. ucp_Old_Persian,
  151. ucp_Oriya,
  152. ucp_Osmanya,
  153. ucp_Runic,
  154. ucp_Shavian,
  155. ucp_Sinhala,
  156. ucp_Syloti_Nagri,
  157. ucp_Syriac,
  158. ucp_Tagalog,
  159. ucp_Tagbanwa,
  160. ucp_Tai_Le,
  161. ucp_Tamil,
  162. ucp_Telugu,
  163. ucp_Thaana,
  164. ucp_Thai,
  165. ucp_Tibetan,
  166. ucp_Tifinagh,
  167. ucp_Ugaritic,
  168. ucp_Yi,
  169. /* New for Unicode 5.0 */
  170. ucp_Balinese,
  171. ucp_Cuneiform,
  172. ucp_Nko,
  173. ucp_Phags_Pa,
  174. ucp_Phoenician,
  175. /* New for Unicode 5.1 */
  176. ucp_Carian,
  177. ucp_Cham,
  178. ucp_Kayah_Li,
  179. ucp_Lepcha,
  180. ucp_Lycian,
  181. ucp_Lydian,
  182. ucp_Ol_Chiki,
  183. ucp_Rejang,
  184. ucp_Saurashtra,
  185. ucp_Sundanese,
  186. ucp_Vai,
  187. /* New for Unicode 5.2 */
  188. ucp_Avestan,
  189. ucp_Bamum,
  190. ucp_Egyptian_Hieroglyphs,
  191. ucp_Imperial_Aramaic,
  192. ucp_Inscriptional_Pahlavi,
  193. ucp_Inscriptional_Parthian,
  194. ucp_Javanese,
  195. ucp_Kaithi,
  196. ucp_Lisu,
  197. ucp_Meetei_Mayek,
  198. ucp_Old_South_Arabian,
  199. ucp_Old_Turkic,
  200. ucp_Samaritan,
  201. ucp_Tai_Tham,
  202. ucp_Tai_Viet,
  203. /* New for Unicode 6.0.0 */
  204. ucp_Batak,
  205. ucp_Brahmi,
  206. ucp_Mandaic,
  207. /* New for Unicode 6.1.0 */
  208. ucp_Chakma,
  209. ucp_Meroitic_Cursive,
  210. ucp_Meroitic_Hieroglyphs,
  211. ucp_Miao,
  212. ucp_Sharada,
  213. ucp_Sora_Sompeng,
  214. ucp_Takri,
  215. /* New for Unicode 7.0.0 */
  216. ucp_Bassa_Vah,
  217. ucp_Caucasian_Albanian,
  218. ucp_Duployan,
  219. ucp_Elbasan,
  220. ucp_Grantha,
  221. ucp_Khojki,
  222. ucp_Khudawadi,
  223. ucp_Linear_A,
  224. ucp_Mahajani,
  225. ucp_Manichaean,
  226. ucp_Mende_Kikakui,
  227. ucp_Modi,
  228. ucp_Mro,
  229. ucp_Nabataean,
  230. ucp_Old_North_Arabian,
  231. ucp_Old_Permic,
  232. ucp_Pahawh_Hmong,
  233. ucp_Palmyrene,
  234. ucp_Psalter_Pahlavi,
  235. ucp_Pau_Cin_Hau,
  236. ucp_Siddham,
  237. ucp_Tirhuta,
  238. ucp_Warang_Citi,
  239. /* New for Unicode 8.0.0 */
  240. ucp_Ahom,
  241. ucp_Anatolian_Hieroglyphs,
  242. ucp_Hatran,
  243. ucp_Multani,
  244. ucp_Old_Hungarian,
  245. ucp_SignWriting,
  246. /* New for Unicode 10.0.0 (no update since 8.0.0) */
  247. ucp_Adlam,
  248. ucp_Bhaiksuki,
  249. ucp_Marchen,
  250. ucp_Newa,
  251. ucp_Osage,
  252. ucp_Tangut,
  253. ucp_Masaram_Gondi,
  254. ucp_Nushu,
  255. ucp_Soyombo,
  256. ucp_Zanabazar_Square,
  257. /* New for Unicode 11.0.0 */
  258. ucp_Dogra,
  259. ucp_Gunjala_Gondi,
  260. ucp_Hanifi_Rohingya,
  261. ucp_Makasar,
  262. ucp_Medefaidrin,
  263. ucp_Old_Sogdian,
  264. ucp_Sogdian,
  265. /* New for Unicode 12.0.0 */
  266. ucp_Elymaic,
  267. ucp_Nandinagari,
  268. ucp_Nyiakeng_Puachue_Hmong,
  269. ucp_Wancho,
  270. /* New for Unicode 13.0.0 */
  271. ucp_Chorasmian,
  272. ucp_Dives_Akuru,
  273. ucp_Khitan_Small_Script,
  274. ucp_Yezidi,
  275. /* New for Unicode 14.0.0 */
  276. ucp_Cypro_Minoan,
  277. ucp_Old_Uyghur,
  278. ucp_Tangsa,
  279. ucp_Toto,
  280. ucp_Vithkuqi
  281. };
  282. #endif /* PCRE2_UCP_H_IDEMPOTENT_GUARD */
  283. /* End of pcre2_ucp.h */