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
32namespace OT {
33
34struct Range {
35 hb_codepoint_t start;
36 hb_codepoint_t end;
37 unsigned int bit;
38};
39
40/* Note: The contents of this array was generated using src/gen-unicode-ranges.py. */
41static Range os2UnicodeRangesSorted[] =
42{
43 { 0x0, 0x7F, 0}, // Basic Latin
44 { 0x80, 0xFF, 1}, // Latin-1 Supplement
45 { 0x100, 0x17F, 2}, // Latin Extended-A
46 { 0x180, 0x24F, 3}, // Latin Extended-B
47 { 0x250, 0x2AF, 4}, // IPA Extensions
48 { 0x2B0, 0x2FF, 5}, // Spacing Modifier Letters
49 { 0x300, 0x36F, 6}, // Combining Diacritical Marks
50 { 0x370, 0x3FF, 7}, // Greek and Coptic
51 { 0x400, 0x4FF, 9}, // Cyrillic
52 { 0x500, 0x52F, 9}, // Cyrillic Supplement
53 { 0x530, 0x58F, 10}, // Armenian
54 { 0x590, 0x5FF, 11}, // Hebrew
55 { 0x600, 0x6FF, 13}, // Arabic
56 { 0x700, 0x74F, 71}, // Syriac
57 { 0x750, 0x77F, 13}, // Arabic Supplement
58 { 0x780, 0x7BF, 72}, // Thaana
59 { 0x7C0, 0x7FF, 14}, // NKo
60 { 0x900, 0x97F, 15}, // Devanagari
61 { 0x980, 0x9FF, 16}, // Bengali
62 { 0xA00, 0xA7F, 17}, // Gurmukhi
63 { 0xA80, 0xAFF, 18}, // Gujarati
64 { 0xB00, 0xB7F, 19}, // Oriya
65 { 0xB80, 0xBFF, 20}, // Tamil
66 { 0xC00, 0xC7F, 21}, // Telugu
67 { 0xC80, 0xCFF, 22}, // Kannada
68 { 0xD00, 0xD7F, 23}, // Malayalam
69 { 0xD80, 0xDFF, 73}, // Sinhala
70 { 0xE00, 0xE7F, 24}, // Thai
71 { 0xE80, 0xEFF, 25}, // Lao
72 { 0xF00, 0xFFF, 70}, // Tibetan
73 { 0x1000, 0x109F, 74}, // Myanmar
74 { 0x10A0, 0x10FF, 26}, // Georgian
75 { 0x1100, 0x11FF, 28}, // Hangul Jamo
76 { 0x1200, 0x137F, 75}, // Ethiopic
77 { 0x1380, 0x139F, 75}, // Ethiopic Supplement
78 { 0x13A0, 0x13FF, 76}, // Cherokee
79 { 0x1400, 0x167F, 77}, // Unified Canadian Aboriginal Syllabics
80 { 0x1680, 0x169F, 78}, // Ogham
81 { 0x16A0, 0x16FF, 79}, // Runic
82 { 0x1700, 0x171F, 84}, // Tagalog
83 { 0x1720, 0x173F, 84}, // Hanunoo
84 { 0x1740, 0x175F, 84}, // Buhid
85 { 0x1760, 0x177F, 84}, // Tagbanwa
86 { 0x1780, 0x17FF, 80}, // Khmer
87 { 0x1800, 0x18AF, 81}, // Mongolian
88 { 0x1900, 0x194F, 93}, // Limbu
89 { 0x1950, 0x197F, 94}, // Tai Le
90 { 0x1980, 0x19DF, 95}, // New Tai Lue
91 { 0x19E0, 0x19FF, 80}, // Khmer Symbols
92 { 0x1A00, 0x1A1F, 96}, // Buginese
93 { 0x1B00, 0x1B7F, 27}, // Balinese
94 { 0x1B80, 0x1BBF, 112}, // Sundanese
95 { 0x1C00, 0x1C4F, 113}, // Lepcha
96 { 0x1C50, 0x1C7F, 114}, // Ol Chiki
97 { 0x1D00, 0x1D7F, 4}, // Phonetic Extensions
98 { 0x1D80, 0x1DBF, 4}, // Phonetic Extensions Supplement
99 { 0x1DC0, 0x1DFF, 6}, // Combining Diacritical Marks Supplement
100 { 0x1E00, 0x1EFF, 29}, // Latin Extended Additional
101 { 0x1F00, 0x1FFF, 30}, // Greek Extended
102 { 0x2000, 0x206F, 31}, // General Punctuation
103 { 0x2070, 0x209F, 32}, // Superscripts And Subscripts
104 { 0x20A0, 0x20CF, 33}, // Currency Symbols
105 { 0x20D0, 0x20FF, 34}, // Combining Diacritical Marks For Symbols
106 { 0x2100, 0x214F, 35}, // Letterlike Symbols
107 { 0x2150, 0x218F, 36}, // Number Forms
108 { 0x2190, 0x21FF, 37}, // Arrows
109 { 0x2200, 0x22FF, 38}, // Mathematical Operators
110 { 0x2300, 0x23FF, 39}, // Miscellaneous Technical
111 { 0x2400, 0x243F, 40}, // Control Pictures
112 { 0x2440, 0x245F, 41}, // Optical Character Recognition
113 { 0x2460, 0x24FF, 42}, // Enclosed Alphanumerics
114 { 0x2500, 0x257F, 43}, // Box Drawing
115 { 0x2580, 0x259F, 44}, // Block Elements
116 { 0x25A0, 0x25FF, 45}, // Geometric Shapes
117 { 0x2600, 0x26FF, 46}, // Miscellaneous Symbols
118 { 0x2700, 0x27BF, 47}, // Dingbats
119 { 0x27C0, 0x27EF, 38}, // Miscellaneous Mathematical Symbols-A
120 { 0x27F0, 0x27FF, 37}, // Supplemental Arrows-A
121 { 0x2800, 0x28FF, 82}, // Braille Patterns
122 { 0x2900, 0x297F, 37}, // Supplemental Arrows-B
123 { 0x2980, 0x29FF, 38}, // Miscellaneous Mathematical Symbols-B
124 { 0x2A00, 0x2AFF, 38}, // Supplemental Mathematical Operators
125 { 0x2B00, 0x2BFF, 37}, // Miscellaneous Symbols and Arrows
126 { 0x2C00, 0x2C5F, 97}, // Glagolitic
127 { 0x2C60, 0x2C7F, 29}, // Latin Extended-C
128 { 0x2C80, 0x2CFF, 8}, // Coptic
129 { 0x2D00, 0x2D2F, 26}, // Georgian Supplement
130 { 0x2D30, 0x2D7F, 98}, // Tifinagh
131 { 0x2D80, 0x2DDF, 75}, // Ethiopic Extended
132 { 0x2DE0, 0x2DFF, 9}, // Cyrillic Extended-A
133 { 0x2E00, 0x2E7F, 31}, // Supplemental Punctuation
134 { 0x2E80, 0x2EFF, 59}, // CJK Radicals Supplement
135 { 0x2F00, 0x2FDF, 59}, // Kangxi Radicals
136 { 0x2FF0, 0x2FFF, 59}, // Ideographic Description Characters
137 { 0x3000, 0x303F, 48}, // CJK Symbols And Punctuation
138 { 0x3040, 0x309F, 49}, // Hiragana
139 { 0x30A0, 0x30FF, 50}, // Katakana
140 { 0x3100, 0x312F, 51}, // Bopomofo
141 { 0x3130, 0x318F, 52}, // Hangul Compatibility Jamo
142 { 0x3190, 0x319F, 59}, // Kanbun
143 { 0x31A0, 0x31BF, 51}, // Bopomofo Extended
144 { 0x31C0, 0x31EF, 61}, // CJK Strokes
145 { 0x31F0, 0x31FF, 50}, // Katakana Phonetic Extensions
146 { 0x3200, 0x32FF, 54}, // Enclosed CJK Letters And Months
147 { 0x3300, 0x33FF, 55}, // CJK Compatibility
148 { 0x3400, 0x4DBF, 59}, // CJK Unified Ideographs Extension A
149 { 0x4DC0, 0x4DFF, 99}, // Yijing Hexagram Symbols
150 { 0x4E00, 0x9FFF, 59}, // CJK Unified Ideographs
151 { 0xA000, 0xA48F, 83}, // Yi Syllables
152 { 0xA490, 0xA4CF, 83}, // Yi Radicals
153 { 0xA500, 0xA63F, 12}, // Vai
154 { 0xA640, 0xA69F, 9}, // Cyrillic Extended-B
155 { 0xA700, 0xA71F, 5}, // Modifier Tone Letters
156 { 0xA720, 0xA7FF, 29}, // Latin Extended-D
157 { 0xA800, 0xA82F, 100}, // Syloti Nagri
158 { 0xA840, 0xA87F, 53}, // Phags-pa
159 { 0xA880, 0xA8DF, 115}, // Saurashtra
160 { 0xA900, 0xA92F, 116}, // Kayah Li
161 { 0xA930, 0xA95F, 117}, // Rejang
162 { 0xAA00, 0xAA5F, 118}, // Cham
163 { 0xAC00, 0xD7AF, 56}, // Hangul Syllables
164 { 0xD800, 0xDFFF, 57}, // Non-Plane 0 *
165 { 0xE000, 0xF8FF, 60}, // Private Use Area (plane 0)
166 { 0xF900, 0xFAFF, 61}, // CJK Compatibility Ideographs
167 { 0xFB00, 0xFB4F, 62}, // Alphabetic Presentation Forms
168 { 0xFB50, 0xFDFF, 63}, // Arabic Presentation Forms-A
169 { 0xFE00, 0xFE0F, 91}, // Variation Selectors
170 { 0xFE10, 0xFE1F, 65}, // Vertical Forms
171 { 0xFE20, 0xFE2F, 64}, // Combining Half Marks
172 { 0xFE30, 0xFE4F, 65}, // CJK Compatibility Forms
173 { 0xFE50, 0xFE6F, 66}, // Small Form Variants
174 { 0xFE70, 0xFEFF, 67}, // Arabic Presentation Forms-B
175 { 0xFF00, 0xFFEF, 68}, // Halfwidth And Fullwidth Forms
176 { 0xFFF0, 0xFFFF, 69}, // Specials
177 { 0x10000, 0x1007F, 101}, // Linear B Syllabary
178 { 0x10080, 0x100FF, 101}, // Linear B Ideograms
179 { 0x10100, 0x1013F, 101}, // Aegean Numbers
180 { 0x10140, 0x1018F, 102}, // Ancient Greek Numbers
181 { 0x10190, 0x101CF, 119}, // Ancient Symbols
182 { 0x101D0, 0x101FF, 120}, // Phaistos Disc
183 { 0x10280, 0x1029F, 121}, // Lycian
184 { 0x102A0, 0x102DF, 121}, // Carian
185 { 0x10300, 0x1032F, 85}, // Old Italic
186 { 0x10330, 0x1034F, 86}, // Gothic
187 { 0x10380, 0x1039F, 103}, // Ugaritic
188 { 0x103A0, 0x103DF, 104}, // Old Persian
189 { 0x10400, 0x1044F, 87}, // Deseret
190 { 0x10450, 0x1047F, 105}, // Shavian
191 { 0x10480, 0x104AF, 106}, // Osmanya
192 { 0x10800, 0x1083F, 107}, // Cypriot Syllabary
193 { 0x10900, 0x1091F, 58}, // Phoenician
194 { 0x10920, 0x1093F, 121}, // Lydian
195 { 0x10A00, 0x10A5F, 108}, // Kharoshthi
196 { 0x12000, 0x123FF, 110}, // Cuneiform
197 { 0x12400, 0x1247F, 110}, // Cuneiform Numbers and Punctuation
198 { 0x1D000, 0x1D0FF, 88}, // Byzantine Musical Symbols
199 { 0x1D100, 0x1D1FF, 88}, // Musical Symbols
200 { 0x1D200, 0x1D24F, 88}, // Ancient Greek Musical Notation
201 { 0x1D300, 0x1D35F, 109}, // Tai Xuan Jing Symbols
202 { 0x1D360, 0x1D37F, 111}, // Counting Rod Numerals
203 { 0x1D400, 0x1D7FF, 89}, // Mathematical Alphanumeric Symbols
204 { 0x1F000, 0x1F02F, 122}, // Mahjong Tiles
205 { 0x1F030, 0x1F09F, 122}, // Domino Tiles
206 { 0x20000, 0x2A6DF, 59}, // CJK Unified Ideographs Extension B
207 { 0x2F800, 0x2FA1F, 61}, // CJK Compatibility Ideographs Supplement
208 { 0xE0000, 0xE007F, 92}, // Tags
209 { 0xE0100, 0xE01EF, 91}, // Variation Selectors Supplement
210 { 0xF0000, 0xFFFFD, 90}, // Private Use (plane 15)
211 {0x100000, 0x10FFFD, 90}, // Private Use (plane 16)
212};
213
214static int
215_compare_range (const void *_key, const void *_item, void *_arg)
216{
217 hb_codepoint_t cp = *((hb_codepoint_t *) _key);
218 const Range *range = (Range *) _item;
219
220 if (cp < range->start)
221 return -1;
222 else if (cp <= range->end)
223 return 0;
224 else
225 return 1;
226}
227
228/**
229 * hb_get_unicode_range_bit:
230 * Returns the bit to be set in os/2 ulUnicodeRange for a given codepoint.
231 **/
232static unsigned int
233hb_get_unicode_range_bit (hb_codepoint_t cp)
234{
235 Range *range = (Range*) hb_bsearch_r (&cp, os2UnicodeRangesSorted,
236 sizeof (os2UnicodeRangesSorted) / sizeof(Range),
237 sizeof(Range),
238 _compare_range, nullptr);
239 if (range != nullptr)
240 return range->bit;
241 return -1;
242}
243
244} /* namespace OT */
245
246#endif /* HB_OT_OS2_UNICODE_RANGES_HH */
247