glib/pcre/ucp.h

   1 /*************************************************
   2 *          Unicode Property Table handler        *
   3 *************************************************/
   4
   5 #ifndef _UCP_H
   6 #define _UCP_H
   7
   8 /* This file contains definitions of the property values that are returned by
   9 the UCD access macros. New values that are added for new releases of Unicode
  10 should always be at the end of each enum, for backwards compatibility. */
  11
  12 /* These are the general character categories. */
  13 #ifdef GLIB_COMPILATION
  14 #include "gunicode.h"
  15 #else
  16 #include <glib.h>
  17 #endif
  18
  19 enum {
  20   ucp_C,     /* Other */
  21   ucp_L,     /* Letter */
  22   ucp_M,     /* Mark */
  23   ucp_N,     /* Number */
  24   ucp_P,     /* Punctuation */
  25   ucp_S,     /* Symbol */
  26   ucp_Z      /* Separator */
  27 };
  28
  29 /* These are the particular character types. */
  30
  31 enum {
  32   ucp_Cc = G_UNICODE_CONTROL,                   /* Control */
  33   ucp_Cf = G_UNICODE_FORMAT,                    /* Format */
  34   ucp_Cn = G_UNICODE_UNASSIGNED,                /* Unassigned */
  35   ucp_Co = G_UNICODE_PRIVATE_USE,               /* Private use */
  36   ucp_Cs = G_UNICODE_SURROGATE,                 /* Surrogate */
  37   ucp_Ll = G_UNICODE_LOWERCASE_LETTER,          /* Lower case letter */
  38   ucp_Lm = G_UNICODE_MODIFIER_LETTER,           /* Modifier letter */
  39   ucp_Lo = G_UNICODE_OTHER_LETTER,              /* Other letter */
  40   ucp_Lt = G_UNICODE_TITLECASE_LETTER,          /* Title case letter */
  41   ucp_Lu = G_UNICODE_UPPERCASE_LETTER,          /* Upper case letter */
  42   ucp_Mc = G_UNICODE_SPACING_MARK,              /* Spacing mark */
  43   ucp_Me = G_UNICODE_ENCLOSING_MARK,            /* Enclosing mark */
  44   ucp_Mn = G_UNICODE_NON_SPACING_MARK,          /* Non-spacing mark */
  45   ucp_Nd = G_UNICODE_DECIMAL_NUMBER,            /* Decimal number */
  46   ucp_Nl = G_UNICODE_LETTER_NUMBER,             /* Letter number */
  47   ucp_No = G_UNICODE_OTHER_NUMBER,              /* Other number */
  48   ucp_Pc = G_UNICODE_CONNECT_PUNCTUATION,       /* Connector punctuation */
  49   ucp_Pd = G_UNICODE_DASH_PUNCTUATION,          /* Dash punctuation */
  50   ucp_Pe = G_UNICODE_CLOSE_PUNCTUATION,         /* Close punctuation */
  51   ucp_Pf = G_UNICODE_FINAL_PUNCTUATION,         /* Final punctuation */
  52   ucp_Pi = G_UNICODE_INITIAL_PUNCTUATION,       /* Initial punctuation */
  53   ucp_Po = G_UNICODE_OTHER_PUNCTUATION,         /* Other punctuation */
  54   ucp_Ps = G_UNICODE_OPEN_PUNCTUATION,          /* Open punctuation */
  55   ucp_Sc = G_UNICODE_CURRENCY_SYMBOL,           /* Currency symbol */
  56   ucp_Sk = G_UNICODE_MODIFIER_SYMBOL,           /* Modifier symbol */
  57   ucp_Sm = G_UNICODE_MATH_SYMBOL,               /* Mathematical symbol */
  58   ucp_So = G_UNICODE_OTHER_SYMBOL,              /* Other symbol */
  59   ucp_Zl = G_UNICODE_LINE_SEPARATOR,            /* Line separator */
  60   ucp_Zp = G_UNICODE_PARAGRAPH_SEPARATOR,       /* Paragraph separator */
  61   ucp_Zs = G_UNICODE_SPACE_SEPARATOR            /* Space separator */
  62 };
  63
  64 /* These are the script identifications. */
  65
  66 enum {
  67   ucp_Common = G_UNICODE_SCRIPT_COMMON,
  68   ucp_Inherited = G_UNICODE_SCRIPT_INHERITED,
  69
  70   ucp_Arabic = G_UNICODE_SCRIPT_ARABIC,
  71   ucp_Armenian = G_UNICODE_SCRIPT_ARMENIAN,
  72   ucp_Bengali = G_UNICODE_SCRIPT_BENGALI,
  73   ucp_Bopomofo = G_UNICODE_SCRIPT_BOPOMOFO,
  74   ucp_Braille = G_UNICODE_SCRIPT_BRAILLE,
  75   ucp_Buginese = G_UNICODE_SCRIPT_BUGINESE,
  76   ucp_Buhid = G_UNICODE_SCRIPT_BUHID,
  77   ucp_Canadian_Aboriginal = G_UNICODE_SCRIPT_CANADIAN_ABORIGINAL,
  78   ucp_Cherokee = G_UNICODE_SCRIPT_CHEROKEE,
  79   ucp_Coptic = G_UNICODE_SCRIPT_COPTIC,
  80   ucp_Cypriot = G_UNICODE_SCRIPT_CYPRIOT,
  81   ucp_Cyrillic = G_UNICODE_SCRIPT_CYRILLIC,
  82   ucp_Deseret = G_UNICODE_SCRIPT_DESERET,
  83   ucp_Devanagari = G_UNICODE_SCRIPT_DEVANAGARI,
  84   ucp_Ethiopic = G_UNICODE_SCRIPT_ETHIOPIC,
  85   ucp_Georgian = G_UNICODE_SCRIPT_GEORGIAN,
  86   ucp_Glagolitic = G_UNICODE_SCRIPT_GLAGOLITIC,
  87   ucp_Gothic = G_UNICODE_SCRIPT_GOTHIC,
  88   ucp_Greek = G_UNICODE_SCRIPT_GREEK,
  89   ucp_Gujarati = G_UNICODE_SCRIPT_GUJARATI,
  90   ucp_Gurmukhi = G_UNICODE_SCRIPT_GURMUKHI,
  91   ucp_Han = G_UNICODE_SCRIPT_HAN,
  92   ucp_Hangul = G_UNICODE_SCRIPT_HANGUL,
  93   ucp_Hanunoo = G_UNICODE_SCRIPT_HANUNOO,
  94   ucp_Hebrew = G_UNICODE_SCRIPT_HEBREW,
  95   ucp_Hiragana = G_UNICODE_SCRIPT_HIRAGANA,
  96   ucp_Kannada = G_UNICODE_SCRIPT_KANNADA,
  97   ucp_Katakana = G_UNICODE_SCRIPT_KATAKANA,
  98   ucp_Kharoshthi = G_UNICODE_SCRIPT_KHAROSHTHI,
  99   ucp_Khmer = G_UNICODE_SCRIPT_KHMER,
 100   ucp_Lao = G_UNICODE_SCRIPT_LAO,
 101   ucp_Latin = G_UNICODE_SCRIPT_LATIN,
 102   ucp_Limbu = G_UNICODE_SCRIPT_LIMBU,
 103   ucp_Linear_B = G_UNICODE_SCRIPT_LINEAR_B,
 104   ucp_Malayalam = G_UNICODE_SCRIPT_MALAYALAM,
 105   ucp_Mongolian = G_UNICODE_SCRIPT_MONGOLIAN,
 106   ucp_Myanmar = G_UNICODE_SCRIPT_MYANMAR,
 107   ucp_New_Tai_Lue = G_UNICODE_SCRIPT_NEW_TAI_LUE,
 108   ucp_Ogham = G_UNICODE_SCRIPT_OGHAM,
 109   ucp_Old_Italic = G_UNICODE_SCRIPT_OLD_ITALIC,
 110   ucp_Old_Persian = G_UNICODE_SCRIPT_OLD_PERSIAN,
 111   ucp_Oriya = G_UNICODE_SCRIPT_ORIYA,
 112   ucp_Osmanya = G_UNICODE_SCRIPT_OSMANYA,
 113   ucp_Runic = G_UNICODE_SCRIPT_RUNIC,
 114   ucp_Shavian = G_UNICODE_SCRIPT_SHAVIAN,
 115   ucp_Sinhala = G_UNICODE_SCRIPT_SINHALA,
 116   ucp_Syloti_Nagri = G_UNICODE_SCRIPT_SYLOTI_NAGRI,
 117   ucp_Syriac = G_UNICODE_SCRIPT_SYRIAC,
 118   ucp_Tagalog = G_UNICODE_SCRIPT_TAGALOG,
 119   ucp_Tagbanwa = G_UNICODE_SCRIPT_TAGBANWA,
 120   ucp_Tai_Le = G_UNICODE_SCRIPT_TAI_LE,
 121   ucp_Tamil = G_UNICODE_SCRIPT_TAMIL,
 122   ucp_Telugu = G_UNICODE_SCRIPT_TELUGU,
 123   ucp_Thaana = G_UNICODE_SCRIPT_THAANA,
 124   ucp_Thai = G_UNICODE_SCRIPT_THAI,
 125   ucp_Tibetan = G_UNICODE_SCRIPT_TIBETAN,
 126   ucp_Tifinagh = G_UNICODE_SCRIPT_TIFINAGH,
 127   ucp_Ugaritic = G_UNICODE_SCRIPT_UGARITIC,
 128   ucp_Yi = G_UNICODE_SCRIPT_YI,
 129   /* New for Unicode 5.0: */
 130   ucp_Balinese = G_UNICODE_SCRIPT_BALINESE,
 131   ucp_Cuneiform = G_UNICODE_SCRIPT_CUNEIFORM,
 132   ucp_Nko = G_UNICODE_SCRIPT_NKO,
 133   ucp_Phags_Pa = G_UNICODE_SCRIPT_PHAGS_PA,
 134   ucp_Phoenician = G_UNICODE_SCRIPT_PHOENICIAN,
 135   /* New for Unicode 5.1: */
 136   ucp_Carian = G_UNICODE_SCRIPT_CARIAN,
 137   ucp_Cham = G_UNICODE_SCRIPT_CHAM,
 138   ucp_Kayah_Li = G_UNICODE_SCRIPT_KAYAH_LI,
 139   ucp_Lepcha = G_UNICODE_SCRIPT_LEPCHA,
 140   ucp_Lycian = G_UNICODE_SCRIPT_LYCIAN,
 141   ucp_Lydian = G_UNICODE_SCRIPT_LYDIAN,
 142   ucp_Ol_Chiki = G_UNICODE_SCRIPT_OL_CHIKI,
 143   ucp_Rejang = G_UNICODE_SCRIPT_REJANG,
 144   ucp_Saurashtra = G_UNICODE_SCRIPT_SAURASHTRA,
 145   ucp_Sundanese = G_UNICODE_SCRIPT_SUNDANESE,
 146   ucp_Vai = G_UNICODE_SCRIPT_VAI,
 147   /* New for Unicode 5.2: */
 148   ucp_Avestan = G_UNICODE_SCRIPT_AVESTAN,
 149   ucp_Bamum = G_UNICODE_SCRIPT_BAMUM,
 150   ucp_Egyptian_Hieroglyphs = G_UNICODE_SCRIPT_EGYPTIAN_HIEROGLYPHS,
 151   ucp_Imperial_Aramaic = G_UNICODE_SCRIPT_IMPERIAL_ARAMAIC,
 152   ucp_Inscriptional_Pahlavi = G_UNICODE_SCRIPT_INSCRIPTIONAL_PAHLAVI,
 153   ucp_Inscriptional_Parthian = G_UNICODE_SCRIPT_INSCRIPTIONAL_PARTHIAN,
 154   ucp_Javanese = G_UNICODE_SCRIPT_JAVANESE,
 155   ucp_Kaithi = G_UNICODE_SCRIPT_KAITHI,
 156   ucp_Lisu = G_UNICODE_SCRIPT_LISU,
 157   ucp_Meetei_Mayek = G_UNICODE_SCRIPT_MEETEI_MAYEK,
 158   ucp_Old_South_Arabian = G_UNICODE_SCRIPT_OLD_SOUTH_ARABIAN,
 159   ucp_Old_Turkic = G_UNICODE_SCRIPT_OLD_TURKIC,
 160   ucp_Samaritan = G_UNICODE_SCRIPT_SAMARITAN,
 161   ucp_Tai_Tham = G_UNICODE_SCRIPT_TAI_THAM,
 162   ucp_Tai_Viet = G_UNICODE_SCRIPT_TAI_VIET,
 163   /* New for Unicode 6.0.0: */
 164   ucp_Batak = G_UNICODE_SCRIPT_BATAK,
 165   ucp_Brahmi = G_UNICODE_SCRIPT_BRAHMI,
 166   ucp_Mandaic = G_UNICODE_SCRIPT_MANDAIC,
 167   /* New for Unicode 6.1.0: */
 168   ucp_Chakma = G_UNICODE_SCRIPT_CHAKMA,
 169   ucp_Meroitic_Cursive = G_UNICODE_SCRIPT_MEROITIC_CURSIVE,
 170   ucp_Meroitic_Hieroglyphs = G_UNICODE_SCRIPT_MEROITIC_HIEROGLYPHS,
 171   ucp_Miao = G_UNICODE_SCRIPT_MIAO,
 172   ucp_Sharada = G_UNICODE_SCRIPT_SHARADA,
 173   ucp_Sora_Sompeng = G_UNICODE_SCRIPT_SORA_SOMPENG,
 174   ucp_Takri = G_UNICODE_SCRIPT_TAKRI,
 175 };
 176
 177 #endif
 178
 179 /* End of ucp.h */