summaryrefslogtreecommitdiff
path: root/intl/unicharutil/util/nsUnicodeScriptCodes.h
blob: 40bc6039e4bc5cf03941a05b7bb9ede431a620db (plain)
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
199
200
201
202
203
204
205
206
207
208
209
210
211
212
213
214
215
216
217
218
219
220
221
222
223
224
225
226
227
228
229
230
231
232
233
234
235
236
237
238
239
240
241
242
243
244
245
246
247
248
249
250
251
252
253
254
255
256
257
258
259
260
261
262
263
264
265
266
267
268
269
270
271
272
273
274
275
276
277
278
279
280
281
282
283
284
285
286
287
288
289
290
291
292
293

/* -*- Mode: C++; tab-width: 20; indent-tabs-mode: nil; c-basic-offset: 4 -*- */
/* This Source Code Form is subject to the terms of the Mozilla Public
 * License, v. 2.0. If a copy of the MPL was not distributed with this
 * file, You can obtain one at http://mozilla.org/MPL/2.0/. */

/*
 * Derived from the Unicode Character Database by genUnicodePropertyData.pl
 *
 * For Unicode terms of use, see http://www.unicode.org/terms_of_use.html
 */

/*
 * Created on Wed Oct 26 09:12:45 2016 from UCD data files with version info:
 *

# Date: 2015-06-16, 20:24:00 GMT [KW]
#
# Unicode Character Database
# Copyright (c) 1991-2015 Unicode, Inc.
# For terms of use, see http://www.unicode.org/terms_of_use.html
#
# For documentation, see the following:
# NamesList.html
# UAX #38, "Unicode Han Database (Unihan)"
# UAX #44, "Unicode Character Database."
#
# The UAXes can be accessed at http://www.unicode.org/versions/Unicode8.0.0/

This directory contains the final data files
for the Unicode Character Database, for Version 8.0.0 of the Unicode
Standard.


# Scripts-8.0.0.txt
# Date: 2015-03-11, 22:29:42 GMT [MD]

# BidiMirroring-8.0.0.txt
# Date: 2015-01-20, 18:30:00 GMT [KW, LI]

# BidiBrackets-8.0.0.txt
# Date: 2015-01-20, 19:00:00 GMT [AG, LI, KW]

# HangulSyllableType-8.0.0.txt
# Date: 2014-12-16, 23:07:45 GMT [MD]

# LineBreak-8.0.0.txt
# Date: 2015-02-13, 09:15:00 GMT [KW, LI]

# EastAsianWidth-8.0.0.txt
# Date: 2015-02-10, 21:00:00 GMT [KW, LI]

# File: xidmodifications.txt
# Version: 8.0.0
# Generated: 2015-05-17, 03:09:04 GMT

#
# Unihan_Variants.txt
# Date: 2015-04-30 18:38:20 GMT [JHJ]

# VerticalOrientation-13.txt
# Date: 2014-09-03, 17:30:00 GMT [EM, KI, LI]

 *
 * * * * * This file contains MACHINE-GENERATED DATA, do not edit! * * * * *
 */

#ifndef NS_UNICODE_SCRIPT_CODES
#define NS_UNICODE_SCRIPT_CODES

#pragma pack(1)

#if !ENABLE_INTL_API

struct nsCharProps1 {
  unsigned char mMirrorOffsetIndex:5;
  unsigned char mHangulType:3;
  unsigned char mCombiningClass:8;
};

#endif

#if ENABLE_INTL_API

struct nsCharProps2 {
  // Currently only 6 bits are defined here, so 2 more could be added without
  // affecting the storage requirements for this struct.
  unsigned char mVertOrient:2;
  unsigned char mXidmod:4;
};

#endif

#if !ENABLE_INTL_API

struct nsCharProps2 {
  unsigned char mScriptCode:8;
  unsigned char mPairedBracketType:2;
  unsigned char mEastAsianWidthFWH:1;
  unsigned char mCategory:5;
  unsigned char mBidiCategory:5;
  unsigned char mXidmod:4;
  signed char   mNumericValue:5;
  unsigned char mVertOrient:2;
  unsigned char mLineBreak; // only 6 bits actually needed
};

#endif

#pragma pack()

namespace mozilla {
namespace unicode {
enum class Script {
  COMMON = 0,
  INHERITED = 1,
  ARABIC = 2,
  ARMENIAN = 3,
  BENGALI = 4,
  BOPOMOFO = 5,
  CHEROKEE = 6,
  COPTIC = 7,
  CYRILLIC = 8,
  DESERET = 9,
  DEVANAGARI = 10,
  ETHIOPIC = 11,
  GEORGIAN = 12,
  GOTHIC = 13,
  GREEK = 14,
  GUJARATI = 15,
  GURMUKHI = 16,
  HAN = 17,
  HANGUL = 18,
  HEBREW = 19,
  HIRAGANA = 20,
  KANNADA = 21,
  KATAKANA = 22,
  KHMER = 23,
  LAO = 24,
  LATIN = 25,
  MALAYALAM = 26,
  MONGOLIAN = 27,
  MYANMAR = 28,
  OGHAM = 29,
  OLD_ITALIC = 30,
  ORIYA = 31,
  RUNIC = 32,
  SINHALA = 33,
  SYRIAC = 34,
  TAMIL = 35,
  TELUGU = 36,
  THAANA = 37,
  THAI = 38,
  TIBETAN = 39,
  CANADIAN_ABORIGINAL = 40,
  YI = 41,
  TAGALOG = 42,
  HANUNOO = 43,
  BUHID = 44,
  TAGBANWA = 45,
  BRAILLE = 46,
  CYPRIOT = 47,
  LIMBU = 48,
  LINEAR_B = 49,
  OSMANYA = 50,
  SHAVIAN = 51,
  TAI_LE = 52,
  UGARITIC = 53,
  KATAKANA_OR_HIRAGANA = 54,
  BUGINESE = 55,
  GLAGOLITIC = 56,
  KHAROSHTHI = 57,
  SYLOTI_NAGRI = 58,
  NEW_TAI_LUE = 59,
  TIFINAGH = 60,
  OLD_PERSIAN = 61,
  BALINESE = 62,
  BATAK = 63,
  BLISSYMBOLS = 64,
  BRAHMI = 65,
  CHAM = 66,
  CIRTH = 67,
  OLD_CHURCH_SLAVONIC_CYRILLIC = 68,
  DEMOTIC_EGYPTIAN = 69,
  HIERATIC_EGYPTIAN = 70,
  EGYPTIAN_HIEROGLYPHS = 71,
  KHUTSURI = 72,
  SIMPLIFIED_HAN = 73,
  TRADITIONAL_HAN = 74,
  PAHAWH_HMONG = 75,
  OLD_HUNGARIAN = 76,
  HARAPPAN_INDUS = 77,
  JAVANESE = 78,
  KAYAH_LI = 79,
  LATIN_FRAKTUR = 80,
  LATIN_GAELIC = 81,
  LEPCHA = 82,
  LINEAR_A = 83,
  MANDAIC = 84,
  MAYAN_HIEROGLYPHS = 85,
  MEROITIC_HIEROGLYPHS = 86,
  NKO = 87,
  OLD_TURKIC = 88,
  OLD_PERMIC = 89,
  PHAGS_PA = 90,
  PHOENICIAN = 91,
  MIAO = 92,
  RONGORONGO = 93,
  SARATI = 94,
  ESTRANGELO_SYRIAC = 95,
  WESTERN_SYRIAC = 96,
  EASTERN_SYRIAC = 97,
  TENGWAR = 98,
  VAI = 99,
  VISIBLE_SPEECH = 100,
  CUNEIFORM = 101,
  UNWRITTEN_LANGUAGES = 102,
  UNKNOWN = 103,
  CARIAN = 104,
  JAPANESE = 105,
  TAI_THAM = 106,
  LYCIAN = 107,
  LYDIAN = 108,
  OL_CHIKI = 109,
  REJANG = 110,
  SAURASHTRA = 111,
  SIGNWRITING = 112,
  SUNDANESE = 113,
  MOON = 114,
  MEETEI_MAYEK = 115,
  IMPERIAL_ARAMAIC = 116,
  AVESTAN = 117,
  CHAKMA = 118,
  KOREAN = 119,
  KAITHI = 120,
  MANICHAEAN = 121,
  INSCRIPTIONAL_PAHLAVI = 122,
  PSALTER_PAHLAVI = 123,
  BOOK_PAHLAVI = 124,
  INSCRIPTIONAL_PARTHIAN = 125,
  SAMARITAN = 126,
  TAI_VIET = 127,
  MATHEMATICAL_NOTATION = 128,
  SYMBOLS = 129,
  BAMUM = 130,
  LISU = 131,
  NAKHI_GEBA = 132,
  OLD_SOUTH_ARABIAN = 133,
  BASSA_VAH = 134,
  DUPLOYAN = 135,
  ELBASAN = 136,
  GRANTHA = 137,
  KPELLE = 138,
  LOMA = 139,
  MENDE_KIKAKUI = 140,
  MEROITIC_CURSIVE = 141,
  OLD_NORTH_ARABIAN = 142,
  NABATAEAN = 143,
  PALMYRENE = 144,
  KHUDAWADI = 145,
  WARANG_CITI = 146,
  AFAKA = 147,
  JURCHEN = 148,
  MRO = 149,
  NUSHU = 150,
  SHARADA = 151,
  SORA_SOMPENG = 152,
  TAKRI = 153,
  TANGUT = 154,
  WOLEAI = 155,
  ANATOLIAN_HIEROGLYPHS = 156,
  KHOJKI = 157,
  TIRHUTA = 158,
  CAUCASIAN_ALBANIAN = 159,
  MAHAJANI = 160,
  AHOM = 161,
  HATRAN = 162,
  MODI = 163,
  MULTANI = 164,
  PAU_CIN_HAU = 165,
  SIDDHAM = 166,

  NUM_SCRIPT_CODES = 167,

  INVALID = -1
};
} // namespace unicode
} // namespace mozilla

#endif
/*
 * * * * * This file contains MACHINE-GENERATED DATA, do not edit! * * * * *
 */