1 /*
   2  * Copyright © 2018  Google, 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  * Google Author(s): Garret Rieger
  25  */
  26 
  27 #ifndef HB_OT_OS2_UNICODE_RANGES_HH
  28 #define HB_OT_OS2_UNICODE_RANGES_HH
  29 
  30 #include "hb.hh"
  31 
  32 namespace OT {
  33 
  34 struct OS2Range
  35 {
  36   static int
  37   cmp (const void *_key, const void *_item)
  38   {
  39     hb_codepoint_t cp = *((hb_codepoint_t *) _key);
  40     const OS2Range *range = (OS2Range *) _item;
  41 
  42     if (cp < range->start)
  43       return -1;
  44     else if (cp <= range->end)
  45       return 0;
  46     else
  47       return +1;
  48   }
  49 
  50   hb_codepoint_t start;
  51   hb_codepoint_t end;
  52   unsigned int bit;
  53 };
  54 
  55 /* Note: The contents of this array was generated using gen-os2-unicode-ranges.py. */
  56 static const OS2Range _hb_os2_unicode_ranges[] =
  57 {
  58   {     0x0,     0x7F,   0}, // Basic Latin
  59   {    0x80,     0xFF,   1}, // Latin-1 Supplement
  60   {   0x100,    0x17F,   2}, // Latin Extended-A
  61   {   0x180,    0x24F,   3}, // Latin Extended-B
  62   {   0x250,    0x2AF,   4}, // IPA Extensions
  63   {   0x2B0,    0x2FF,   5}, // Spacing Modifier Letters
  64   {   0x300,    0x36F,   6}, // Combining Diacritical Marks
  65   {   0x370,    0x3FF,   7}, // Greek and Coptic
  66   {   0x400,    0x4FF,   9}, // Cyrillic
  67   {   0x500,    0x52F,   9}, // Cyrillic Supplement
  68   {   0x530,    0x58F,  10}, // Armenian
  69   {   0x590,    0x5FF,  11}, // Hebrew
  70   {   0x600,    0x6FF,  13}, // Arabic
  71   {   0x700,    0x74F,  71}, // Syriac
  72   {   0x750,    0x77F,  13}, // Arabic Supplement
  73   {   0x780,    0x7BF,  72}, // Thaana
  74   {   0x7C0,    0x7FF,  14}, // NKo
  75   {   0x900,    0x97F,  15}, // Devanagari
  76   {   0x980,    0x9FF,  16}, // Bengali
  77   {   0xA00,    0xA7F,  17}, // Gurmukhi
  78   {   0xA80,    0xAFF,  18}, // Gujarati
  79   {   0xB00,    0xB7F,  19}, // Oriya
  80   {   0xB80,    0xBFF,  20}, // Tamil
  81   {   0xC00,    0xC7F,  21}, // Telugu
  82   {   0xC80,    0xCFF,  22}, // Kannada
  83   {   0xD00,    0xD7F,  23}, // Malayalam
  84   {   0xD80,    0xDFF,  73}, // Sinhala
  85   {   0xE00,    0xE7F,  24}, // Thai
  86   {   0xE80,    0xEFF,  25}, // Lao
  87   {   0xF00,    0xFFF,  70}, // Tibetan
  88   {  0x1000,   0x109F,  74}, // Myanmar
  89   {  0x10A0,   0x10FF,  26}, // Georgian
  90   {  0x1100,   0x11FF,  28}, // Hangul Jamo
  91   {  0x1200,   0x137F,  75}, // Ethiopic
  92   {  0x1380,   0x139F,  75}, // Ethiopic Supplement
  93   {  0x13A0,   0x13FF,  76}, // Cherokee
  94   {  0x1400,   0x167F,  77}, // Unified Canadian Aboriginal Syllabics
  95   {  0x1680,   0x169F,  78}, // Ogham
  96   {  0x16A0,   0x16FF,  79}, // Runic
  97   {  0x1700,   0x171F,  84}, // Tagalog
  98   {  0x1720,   0x173F,  84}, // Hanunoo
  99   {  0x1740,   0x175F,  84}, // Buhid
 100   {  0x1760,   0x177F,  84}, // Tagbanwa
 101   {  0x1780,   0x17FF,  80}, // Khmer
 102   {  0x1800,   0x18AF,  81}, // Mongolian
 103   {  0x1900,   0x194F,  93}, // Limbu
 104   {  0x1950,   0x197F,  94}, // Tai Le
 105   {  0x1980,   0x19DF,  95}, // New Tai Lue
 106   {  0x19E0,   0x19FF,  80}, // Khmer Symbols
 107   {  0x1A00,   0x1A1F,  96}, // Buginese
 108   {  0x1B00,   0x1B7F,  27}, // Balinese
 109   {  0x1B80,   0x1BBF, 112}, // Sundanese
 110   {  0x1C00,   0x1C4F, 113}, // Lepcha
 111   {  0x1C50,   0x1C7F, 114}, // Ol Chiki
 112   {  0x1D00,   0x1D7F,   4}, // Phonetic Extensions
 113   {  0x1D80,   0x1DBF,   4}, // Phonetic Extensions Supplement
 114   {  0x1DC0,   0x1DFF,   6}, // Combining Diacritical Marks Supplement
 115   {  0x1E00,   0x1EFF,  29}, // Latin Extended Additional
 116   {  0x1F00,   0x1FFF,  30}, // Greek Extended
 117   {  0x2000,   0x206F,  31}, // General Punctuation
 118   {  0x2070,   0x209F,  32}, // Superscripts And Subscripts
 119   {  0x20A0,   0x20CF,  33}, // Currency Symbols
 120   {  0x20D0,   0x20FF,  34}, // Combining Diacritical Marks For Symbols
 121   {  0x2100,   0x214F,  35}, // Letterlike Symbols
 122   {  0x2150,   0x218F,  36}, // Number Forms
 123   {  0x2190,   0x21FF,  37}, // Arrows
 124   {  0x2200,   0x22FF,  38}, // Mathematical Operators
 125   {  0x2300,   0x23FF,  39}, // Miscellaneous Technical
 126   {  0x2400,   0x243F,  40}, // Control Pictures
 127   {  0x2440,   0x245F,  41}, // Optical Character Recognition
 128   {  0x2460,   0x24FF,  42}, // Enclosed Alphanumerics
 129   {  0x2500,   0x257F,  43}, // Box Drawing
 130   {  0x2580,   0x259F,  44}, // Block Elements
 131   {  0x25A0,   0x25FF,  45}, // Geometric Shapes
 132   {  0x2600,   0x26FF,  46}, // Miscellaneous Symbols
 133   {  0x2700,   0x27BF,  47}, // Dingbats
 134   {  0x27C0,   0x27EF,  38}, // Miscellaneous Mathematical Symbols-A
 135   {  0x27F0,   0x27FF,  37}, // Supplemental Arrows-A
 136   {  0x2800,   0x28FF,  82}, // Braille Patterns
 137   {  0x2900,   0x297F,  37}, // Supplemental Arrows-B
 138   {  0x2980,   0x29FF,  38}, // Miscellaneous Mathematical Symbols-B
 139   {  0x2A00,   0x2AFF,  38}, // Supplemental Mathematical Operators
 140   {  0x2B00,   0x2BFF,  37}, // Miscellaneous Symbols and Arrows
 141   {  0x2C00,   0x2C5F,  97}, // Glagolitic
 142   {  0x2C60,   0x2C7F,  29}, // Latin Extended-C
 143   {  0x2C80,   0x2CFF,   8}, // Coptic
 144   {  0x2D00,   0x2D2F,  26}, // Georgian Supplement
 145   {  0x2D30,   0x2D7F,  98}, // Tifinagh
 146   {  0x2D80,   0x2DDF,  75}, // Ethiopic Extended
 147   {  0x2DE0,   0x2DFF,   9}, // Cyrillic Extended-A
 148   {  0x2E00,   0x2E7F,  31}, // Supplemental Punctuation
 149   {  0x2E80,   0x2EFF,  59}, // CJK Radicals Supplement
 150   {  0x2F00,   0x2FDF,  59}, // Kangxi Radicals
 151   {  0x2FF0,   0x2FFF,  59}, // Ideographic Description Characters
 152   {  0x3000,   0x303F,  48}, // CJK Symbols And Punctuation
 153   {  0x3040,   0x309F,  49}, // Hiragana
 154   {  0x30A0,   0x30FF,  50}, // Katakana
 155   {  0x3100,   0x312F,  51}, // Bopomofo
 156   {  0x3130,   0x318F,  52}, // Hangul Compatibility Jamo
 157   {  0x3190,   0x319F,  59}, // Kanbun
 158   {  0x31A0,   0x31BF,  51}, // Bopomofo Extended
 159   {  0x31C0,   0x31EF,  61}, // CJK Strokes
 160   {  0x31F0,   0x31FF,  50}, // Katakana Phonetic Extensions
 161   {  0x3200,   0x32FF,  54}, // Enclosed CJK Letters And Months
 162   {  0x3300,   0x33FF,  55}, // CJK Compatibility
 163   {  0x3400,   0x4DBF,  59}, // CJK Unified Ideographs Extension A
 164   {  0x4DC0,   0x4DFF,  99}, // Yijing Hexagram Symbols
 165   {  0x4E00,   0x9FFF,  59}, // CJK Unified Ideographs
 166   {  0xA000,   0xA48F,  83}, // Yi Syllables
 167   {  0xA490,   0xA4CF,  83}, // Yi Radicals
 168   {  0xA500,   0xA63F,  12}, // Vai
 169   {  0xA640,   0xA69F,   9}, // Cyrillic Extended-B
 170   {  0xA700,   0xA71F,   5}, // Modifier Tone Letters
 171   {  0xA720,   0xA7FF,  29}, // Latin Extended-D
 172   {  0xA800,   0xA82F, 100}, // Syloti Nagri
 173   {  0xA840,   0xA87F,  53}, // Phags-pa
 174   {  0xA880,   0xA8DF, 115}, // Saurashtra
 175   {  0xA900,   0xA92F, 116}, // Kayah Li
 176   {  0xA930,   0xA95F, 117}, // Rejang
 177   {  0xAA00,   0xAA5F, 118}, // Cham
 178   {  0xAC00,   0xD7AF,  56}, // Hangul Syllables
 179   {  0xD800,   0xDFFF,  57}, // Non-Plane 0 *
 180   {  0xE000,   0xF8FF,  60}, // Private Use Area (plane 0)
 181   {  0xF900,   0xFAFF,  61}, // CJK Compatibility Ideographs
 182   {  0xFB00,   0xFB4F,  62}, // Alphabetic Presentation Forms
 183   {  0xFB50,   0xFDFF,  63}, // Arabic Presentation Forms-A
 184   {  0xFE00,   0xFE0F,  91}, // Variation Selectors
 185   {  0xFE10,   0xFE1F,  65}, // Vertical Forms
 186   {  0xFE20,   0xFE2F,  64}, // Combining Half Marks
 187   {  0xFE30,   0xFE4F,  65}, // CJK Compatibility Forms
 188   {  0xFE50,   0xFE6F,  66}, // Small Form Variants
 189   {  0xFE70,   0xFEFF,  67}, // Arabic Presentation Forms-B
 190   {  0xFF00,   0xFFEF,  68}, // Halfwidth And Fullwidth Forms
 191   {  0xFFF0,   0xFFFF,  69}, // Specials
 192   { 0x10000,  0x1007F, 101}, // Linear B Syllabary
 193   { 0x10080,  0x100FF, 101}, // Linear B Ideograms
 194   { 0x10100,  0x1013F, 101}, // Aegean Numbers
 195   { 0x10140,  0x1018F, 102}, // Ancient Greek Numbers
 196   { 0x10190,  0x101CF, 119}, // Ancient Symbols
 197   { 0x101D0,  0x101FF, 120}, // Phaistos Disc
 198   { 0x10280,  0x1029F, 121}, // Lycian
 199   { 0x102A0,  0x102DF, 121}, // Carian
 200   { 0x10300,  0x1032F,  85}, // Old Italic
 201   { 0x10330,  0x1034F,  86}, // Gothic
 202   { 0x10380,  0x1039F, 103}, // Ugaritic
 203   { 0x103A0,  0x103DF, 104}, // Old Persian
 204   { 0x10400,  0x1044F,  87}, // Deseret
 205   { 0x10450,  0x1047F, 105}, // Shavian
 206   { 0x10480,  0x104AF, 106}, // Osmanya
 207   { 0x10800,  0x1083F, 107}, // Cypriot Syllabary
 208   { 0x10900,  0x1091F,  58}, // Phoenician
 209   { 0x10920,  0x1093F, 121}, // Lydian
 210   { 0x10A00,  0x10A5F, 108}, // Kharoshthi
 211   { 0x12000,  0x123FF, 110}, // Cuneiform
 212   { 0x12400,  0x1247F, 110}, // Cuneiform Numbers and Punctuation
 213   { 0x1D000,  0x1D0FF,  88}, // Byzantine Musical Symbols
 214   { 0x1D100,  0x1D1FF,  88}, // Musical Symbols
 215   { 0x1D200,  0x1D24F,  88}, // Ancient Greek Musical Notation
 216   { 0x1D300,  0x1D35F, 109}, // Tai Xuan Jing Symbols
 217   { 0x1D360,  0x1D37F, 111}, // Counting Rod Numerals
 218   { 0x1D400,  0x1D7FF,  89}, // Mathematical Alphanumeric Symbols
 219   { 0x1F000,  0x1F02F, 122}, // Mahjong Tiles
 220   { 0x1F030,  0x1F09F, 122}, // Domino Tiles
 221   { 0x20000,  0x2A6DF,  59}, // CJK Unified Ideographs Extension B
 222   { 0x2F800,  0x2FA1F,  61}, // CJK Compatibility Ideographs Supplement
 223   { 0xE0000,  0xE007F,  92}, // Tags
 224   { 0xE0100,  0xE01EF,  91}, // Variation Selectors Supplement
 225   { 0xF0000,  0xFFFFD,  90}, // Private Use (plane 15)
 226   {0x100000, 0x10FFFD,  90}, // Private Use (plane 16)
 227 };
 228 
 229 /**
 230  * _hb_ot_os2_get_unicode_range_bit:
 231  * Returns the bit to be set in os/2 ulUnicodeOS2Range for a given codepoint.
 232  **/
 233 static unsigned int
 234 _hb_ot_os2_get_unicode_range_bit (hb_codepoint_t cp)
 235 {
 236   OS2Range *range = (OS2Range*) hb_bsearch (&cp, _hb_os2_unicode_ranges,
 237                                             ARRAY_LENGTH (_hb_os2_unicode_ranges),
 238                                             sizeof (OS2Range),
 239                                             OS2Range::cmp);
 240   if (range != nullptr)
 241     return range->bit;
 242   return -1;
 243 }
 244 
 245 } /* namespace OT */
 246 
 247 #endif /* HB_OT_OS2_UNICODE_RANGES_HH */