src/hb-glib.cc

   1 /*
   2  * Copyright (C) 2009  Red Hat, Inc.
   3  *
   4  *  This is part of HarfBuzz, a text shaping library.
   5  *
   6  * Permission is hereby granted, without written agreement and without
   7  * license or royalty fees, to use, copy, modify, and distribute this
   8  * software and its documentation for any purpose, provided that the
   9  * above copyright notice and the following two paragraphs appear in
  10  * all copies of this software.
  11  *
  12  * IN NO EVENT SHALL THE COPYRIGHT HOLDER BE LIABLE TO ANY PARTY FOR
  13  * DIRECT, INDIRECT, SPECIAL, INCIDENTAL, OR CONSEQUENTIAL DAMAGES
  14  * ARISING OUT OF THE USE OF THIS SOFTWARE AND ITS DOCUMENTATION, EVEN
  15  * IF THE COPYRIGHT HOLDER HAS BEEN ADVISED OF THE POSSIBILITY OF SUCH
  16  * DAMAGE.
  17  *
  18  * THE COPYRIGHT HOLDER SPECIFICALLY DISCLAIMS ANY WARRANTIES, INCLUDING,
  19  * BUT NOT LIMITED TO, THE IMPLIED WARRANTIES OF MERCHANTABILITY AND
  20  * FITNESS FOR A PARTICULAR PURPOSE.  THE SOFTWARE PROVIDED HEREUNDER IS
  21  * ON AN "AS IS" BASIS, AND THE COPYRIGHT HOLDER HAS NO OBLIGATION TO
  22  * PROVIDE MAINTENANCE, SUPPORT, UPDATES, ENHANCEMENTS, OR MODIFICATIONS.
  23  *
  24  * Red Hat Author(s): Behdad Esfahbod
  25  */
  26
  27 #include "hb-private.h"
  28
  29 #include "hb-glib.h"
  30
  31 #include "hb-unicode-private.hh"
  32
  33 #include <glib.h>
  34
  35 HB_BEGIN_DECLS
  36
  37
  38 static unsigned int
  39 hb_glib_get_combining_class (hb_unicode_funcs_t *ufuncs,
  40                              hb_codepoint_t      unicode,
  41                              void               *user_data)
  42
  43 {
  44   return g_unichar_combining_class (unicode);
  45 }
  46
  47 static unsigned int
  48 hb_glib_get_eastasian_width (hb_unicode_funcs_t *ufuncs,
  49                              hb_codepoint_t      unicode,
  50                              void               *user_data)
  51 {
  52   return g_unichar_iswide (unicode) ? 2 : 1;
  53 }
  54
  55 static hb_unicode_general_category_t
  56 hb_glib_get_general_category (hb_unicode_funcs_t *ufuncs,
  57                               hb_codepoint_t      unicode,
  58                               void               *user_data)
  59
  60 {
  61   /* hb_unicode_general_category_t and GUnicodeType are identical */
  62   return (hb_unicode_general_category_t) g_unichar_type (unicode);
  63 }
  64
  65 static hb_codepoint_t
  66 hb_glib_get_mirroring (hb_unicode_funcs_t *ufuncs,
  67                        hb_codepoint_t      unicode,
  68                        void               *user_data)
  69 {
  70   g_unichar_get_mirror_char (unicode, &unicode);
  71   return unicode;
  72 }
  73
  74 static hb_script_t
  75 hb_glib_get_script (hb_unicode_funcs_t *ufuncs,
  76                     hb_codepoint_t      unicode,
  77                     void               *user_data)
  78 {
  79   GUnicodeScript script = g_unichar_get_script (unicode);
  80   switch (script)
  81   {
  82 #define MATCH_SCRIPT(C) case G_UNICODE_SCRIPT_##C: return HB_SCRIPT_##C
  83 #define MATCH_SCRIPT2(C1, C2) case G_UNICODE_SCRIPT_##C1: return HB_SCRIPT_##C2
  84
  85   MATCH_SCRIPT2(INVALID_CODE, INVALID);
  86
  87   MATCH_SCRIPT (COMMON);             /* Zyyy */
  88   MATCH_SCRIPT (INHERITED);          /* Qaai */
  89   MATCH_SCRIPT (ARABIC);             /* Arab */
  90   MATCH_SCRIPT (ARMENIAN);           /* Armn */
  91   MATCH_SCRIPT (BENGALI);            /* Beng */
  92   MATCH_SCRIPT (BOPOMOFO);           /* Bopo */
  93   MATCH_SCRIPT (CHEROKEE);           /* Cher */
  94   MATCH_SCRIPT (COPTIC);             /* Qaac */
  95   MATCH_SCRIPT (CYRILLIC);           /* Cyrl (Cyrs) */
  96   MATCH_SCRIPT (DESERET);            /* Dsrt */
  97   MATCH_SCRIPT (DEVANAGARI);         /* Deva */
  98   MATCH_SCRIPT (ETHIOPIC);           /* Ethi */
  99   MATCH_SCRIPT (GEORGIAN);           /* Geor (Geon); Geoa) */
 100   MATCH_SCRIPT (GOTHIC);             /* Goth */
 101   MATCH_SCRIPT (GREEK);              /* Grek */
 102   MATCH_SCRIPT (GUJARATI);           /* Gujr */
 103   MATCH_SCRIPT (GURMUKHI);           /* Guru */
 104   MATCH_SCRIPT (HAN);                /* Hani */
 105   MATCH_SCRIPT (HANGUL);             /* Hang */
 106   MATCH_SCRIPT (HEBREW);             /* Hebr */
 107   MATCH_SCRIPT (HIRAGANA);           /* Hira */
 108   MATCH_SCRIPT (KANNADA);            /* Knda */
 109   MATCH_SCRIPT (KATAKANA);           /* Kana */
 110   MATCH_SCRIPT (KHMER);              /* Khmr */
 111   MATCH_SCRIPT (LAO);                /* Laoo */
 112   MATCH_SCRIPT (LATIN);              /* Latn (Latf); Latg) */
 113   MATCH_SCRIPT (MALAYALAM);          /* Mlym */
 114   MATCH_SCRIPT (MONGOLIAN);          /* Mong */
 115   MATCH_SCRIPT (MYANMAR);            /* Mymr */
 116   MATCH_SCRIPT (OGHAM);              /* Ogam */
 117   MATCH_SCRIPT (OLD_ITALIC);         /* Ital */
 118   MATCH_SCRIPT (ORIYA);              /* Orya */
 119   MATCH_SCRIPT (RUNIC);              /* Runr */
 120   MATCH_SCRIPT (SINHALA);            /* Sinh */
 121   MATCH_SCRIPT (SYRIAC);             /* Syrc (Syrj, Syrn); Syre) */
 122   MATCH_SCRIPT (TAMIL);              /* Taml */
 123   MATCH_SCRIPT (TELUGU);             /* Telu */
 124   MATCH_SCRIPT (THAANA);             /* Thaa */
 125   MATCH_SCRIPT (THAI);               /* Thai */
 126   MATCH_SCRIPT (TIBETAN);            /* Tibt */
 127   MATCH_SCRIPT (CANADIAN_ABORIGINAL);/* Cans */
 128   MATCH_SCRIPT (YI);                 /* Yiii */
 129   MATCH_SCRIPT (TAGALOG);            /* Tglg */
 130   MATCH_SCRIPT (HANUNOO);            /* Hano */
 131   MATCH_SCRIPT (BUHID);              /* Buhd */
 132   MATCH_SCRIPT (TAGBANWA);           /* Tagb */
 133
 134   /* Unicode-4.0 additions */
 135   MATCH_SCRIPT (BRAILLE);            /* Brai */
 136   MATCH_SCRIPT (CYPRIOT);            /* Cprt */
 137   MATCH_SCRIPT (LIMBU);              /* Limb */
 138   MATCH_SCRIPT (OSMANYA);            /* Osma */
 139   MATCH_SCRIPT (SHAVIAN);            /* Shaw */
 140   MATCH_SCRIPT (LINEAR_B);           /* Linb */
 141   MATCH_SCRIPT (TAI_LE);             /* Tale */
 142   MATCH_SCRIPT (UGARITIC);           /* Ugar */
 143
 144   /* Unicode-4.1 additions */
 145   MATCH_SCRIPT (NEW_TAI_LUE);        /* Talu */
 146   MATCH_SCRIPT (BUGINESE);           /* Bugi */
 147   MATCH_SCRIPT (GLAGOLITIC);         /* Glag */
 148   MATCH_SCRIPT (TIFINAGH);           /* Tfng */
 149   MATCH_SCRIPT (SYLOTI_NAGRI);       /* Sylo */
 150   MATCH_SCRIPT (OLD_PERSIAN);        /* Xpeo */
 151   MATCH_SCRIPT (KHAROSHTHI);         /* Khar */
 152
 153   /* Unicode-5.0 additions */
 154   MATCH_SCRIPT (UNKNOWN);            /* Zzzz */
 155   MATCH_SCRIPT (BALINESE);           /* Bali */
 156   MATCH_SCRIPT (CUNEIFORM);          /* Xsux */
 157   MATCH_SCRIPT (PHOENICIAN);         /* Phnx */
 158   MATCH_SCRIPT (PHAGS_PA);           /* Phag */
 159   MATCH_SCRIPT (NKO);                /* Nkoo */
 160
 161   /* Unicode-5.1 additions */
 162   MATCH_SCRIPT (KAYAH_LI);           /* Kali */
 163   MATCH_SCRIPT (LEPCHA);             /* Lepc */
 164   MATCH_SCRIPT (REJANG);             /* Rjng */
 165   MATCH_SCRIPT (SUNDANESE);          /* Sund */
 166   MATCH_SCRIPT (SAURASHTRA);         /* Saur */
 167   MATCH_SCRIPT (CHAM);               /* Cham */
 168   MATCH_SCRIPT (OL_CHIKI);           /* Olck */
 169   MATCH_SCRIPT (VAI);                /* Vaii */
 170   MATCH_SCRIPT (CARIAN);             /* Cari */
 171   MATCH_SCRIPT (LYCIAN);             /* Lyci */
 172   MATCH_SCRIPT (LYDIAN);             /* Lydi */
 173
 174   /* Unicode-5.2 additions */
 175 #if GLIB_CHECK_VERSION(2,26,0)
 176   MATCH_SCRIPT (AVESTAN);                /* Avst */
 177   MATCH_SCRIPT (BAMUM);                  /* Bamu */
 178   MATCH_SCRIPT (EGYPTIAN_HIEROGLYPHS);   /* Egyp */
 179   MATCH_SCRIPT (IMPERIAL_ARAMAIC);       /* Armi */
 180   MATCH_SCRIPT (INSCRIPTIONAL_PAHLAVI);  /* Phli */
 181   MATCH_SCRIPT (INSCRIPTIONAL_PARTHIAN); /* Prti */
 182   MATCH_SCRIPT (JAVANESE);               /* Java */
 183   MATCH_SCRIPT (KAITHI);                 /* Kthi */
 184   MATCH_SCRIPT (TAI_THAM);               /* Lana */
 185   MATCH_SCRIPT (LISU);                   /* Lisu */
 186   MATCH_SCRIPT (MEETEI_MAYEK);           /* Mtei */
 187   MATCH_SCRIPT (OLD_SOUTH_ARABIAN);      /* Sarb */
 188 #if GLIB_CHECK_VERSION(2,27,92)
 189   MATCH_SCRIPT (OLD_TURKIC);             /* Orkh */
 190 #else
 191   MATCH_SCRIPT2(OLD_TURKISH, OLD_TURKIC);/* Orkh */
 192 #endif
 193   MATCH_SCRIPT (SAMARITAN);              /* Samr */
 194   MATCH_SCRIPT (TAI_VIET);               /* Tavt */
 195 #endif
 196
 197   /* Unicode-6.0 additions */
 198 #if GLIB_CHECK_VERSION(2,28,0)
 199   MATCH_SCRIPT (BATAK);                  /* Batk */
 200   MATCH_SCRIPT (BRAHMI);                 /* Brah */
 201   MATCH_SCRIPT (MANDAIC);                /* Mand */
 202 #endif
 203
 204 #undef MATCH_SCRIPT
 205 #undef MATCH_SCRIPT2
 206   }
 207
 208   return HB_SCRIPT_UNKNOWN;
 209 }
 210
 211 static hb_unicode_funcs_t glib_ufuncs = {
 212   HB_REFERENCE_COUNT_INVALID, /* ref_count */
 213   NULL, /* parent */
 214   TRUE, /* immutable */
 215   {
 216     hb_glib_get_combining_class,
 217     hb_glib_get_eastasian_width,
 218     hb_glib_get_general_category,
 219     hb_glib_get_mirroring,
 220     hb_glib_get_script
 221   }
 222 };
 223
 224 hb_unicode_funcs_t *
 225 hb_glib_get_unicode_funcs (void)
 226 {
 227   return &glib_ufuncs;
 228 }
 229
 230
 231 HB_END_DECLS