third_party/cld/encodings/compact_lang_det/letterscript_enum.cc

   1 // Copyright (c) 2006-2009 The Chromium Authors. All rights reserved.
   2 // Use of this source code is governed by a BSD-style license that can be
   3 // found in the LICENSE file.
   4
   5 #include "encodings/compact_lang_det/letterscript_enum.h"
   6
   7 #include "encodings/compact_lang_det/win/cld_logging.h"
   8
   9 static const char* kUnicodeLScriptNames[ULScript_NUM_SCRIPTS] = {
  10   "Common",
  11   "Latin",
  12   "Greek",
  13   "Cyrillic",
  14   "Armenian",
  15   "Hebrew",
  16   "Arabic",
  17   "Syriac",
  18   "Thaana",
  19   "Devanagari",
  20   "Bengali",
  21   "Gurmukhi",
  22   "Gujarati",
  23   "Oriya",
  24   "Tamil",
  25   "Telugu",
  26   "Kannada",
  27   "Malayalam",
  28   "Sinhala",
  29   "Thai",
  30   "Lao",
  31   "Tibetan",
  32   "Myanmar",
  33   "Georgian",
  34   "HanCJK",
  35   "Ethiopic",
  36   "Cherokee",
  37   "Canadian_Aboriginal",
  38   "Ogham",
  39   "Runic",
  40   "Khmer",
  41   "Mongolian",
  42   "Yi",
  43   "Old_Italic",
  44   "Gothic",
  45   "Deseret",
  46   "Inherited",
  47   "Tagalog",
  48   "Hanunoo",
  49   "Buhid",
  50   "Tagbanwa",
  51   "Limbu",
  52   "Tai_Le",
  53   "Linear_B",
  54   "Ugaritic",
  55   "Shavian",
  56   "Osmanya",
  57   "Cypriot",
  58   "Buginese",
  59   "Coptic",
  60   "New_Tai_Lue",
  61   "Glagolitic",
  62   "Tifinagh",
  63   "Syloti_Nagri",
  64   "Old_Persian",
  65   "Kharoshthi",
  66   "Balinese",
  67   "Cuneiform",
  68   "Phoenician",
  69   "Phags_Pa",
  70   "Nko",
  71
  72   // Unicode 5.1 beta
  73   "Sundanese",
  74   "Lepcha",
  75   "Ol_Chiki",
  76   "Vai",
  77   "Saurashtra",
  78   "Kayah_Li",
  79   "Rejang",
  80   "Lycian",
  81   "Carian",
  82   "Lydian",
  83   "Cham",
  84 };
  85
  86
  87 // Unicode 5.1 beta script names from
  88 // http://www.unicode.org/Public/5.1.0/diffs/5.0.0-5.1.0.all.2.diffs
  89 // NOTE: 'Vai ' => "Vaii" to make four letters, not three
  90 // see http://unicode.org/iso15924/iso15924-codes.html
  91 const char* const kLScriptName4[ULScript_NUM_SCRIPTS] = {
  92   "Zyyy", "Latn", "Grek", "Cyrl",   "Armn", "Hebr", "Arab", "Syrc",
  93   "Thaa", "Deva", "Beng", "Guru",   "Gujr", "Orya", "Taml", "Telu",
  94   "Knda", "Mlym", "Sinh", "Thai",   "Laoo", "Tibt", "Mymr", "Geor",
  95   "Hani", "Ethi", "Cher", "Cans",   "Ogam", "Runr", "Khmr", "Mong",
  96
  97   "Yiii", "Ital", "Goth", "Dsrt",   "Zzzz", "Tglg", "Hano", "Buhd",
  98   "Tagb", "Limb", "Tale", "Linb",   "Ugar", "Shaw", "Osma", "Cprt",
  99   "Bugi", "Copt", "Talu", "Glag",   "Tfng", "Sylo", "Xpeo", "Khar",
 100   "Bali", "Xsux", "Phnx", "Phag",   "Nkoo",
 101
 102   // Unicode 5.1 beta
 103   "Sund", "Lepc", "Olck", "Vaii", "Saur", "Kali", "Rjng", "Lyci",
 104   "Cari", "Lydi", "Cham",
 105 };
 106
 107
 108 const char* UnicodeLScriptName(const UnicodeLScript ls) {
 109   CHECK(ls >= 0 && ls < ULScript_NUM_SCRIPTS);
 110   return kUnicodeLScriptNames[ls];
 111 }
 112
 113
 114 const char* UnicodeLScriptCode(const UnicodeLScript ls) {
 115   CHECK(ls >= 0 && ls < ULScript_NUM_SCRIPTS);
 116   return kLScriptName4[ls];
 117 }