]>
Commit | Line | Data |
---|---|---|
50668cf6 | 1 | ; Table of UCNs which are valid in identifiers. |
83ffe9cd | 2 | ; Copyright (C) 2003-2023 Free Software Foundation, Inc. |
50668cf6 GK |
3 | ; |
4 | ; This program is free software; you can redistribute it and/or modify it | |
5 | ; under the terms of the GNU General Public License as published by the | |
748086b7 | 6 | ; Free Software Foundation; either version 3, or (at your option) any |
50668cf6 GK |
7 | ; later version. |
8 | ; | |
9 | ; This program is distributed in the hope that it will be useful, | |
10 | ; but WITHOUT ANY WARRANTY; without even the implied warranty of | |
11 | ; MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the | |
12 | ; GNU General Public License for more details. | |
13 | ; | |
14 | ; You should have received a copy of the GNU General Public License | |
748086b7 JJ |
15 | ; along with this program; see the file COPYING3. If not see |
16 | ; <http://www.gnu.org/licenses/>. | |
50668cf6 GK |
17 | ; |
18 | ; This file reproduces the table in ISO/IEC 9899:1999 (C99) Annex | |
19 | ; D, which is itself a reproduction from ISO/IEC TR 10176:1998, and | |
20 | ; the similar table from ISO/IEC 14882:1988 (C++98) Annex E, which is | |
21 | ; a reproduction of ISO/IEC PDTR 10176. Unfortunately these tables | |
d3f4ff8b JM |
22 | ; are not identical. It also reproduces the somewhat different tables |
23 | ; in C11 and C++11, which are identical to each other. | |
e6cc3a24 ZW |
24 | |
25 | [C99] | |
26 | ||
27 | ; Latin | |
28 | 00aa 00ba 00c0-00d6 00d8-00f6 00f8-01f5 01fa-0217 0250-02a8 1e00-1e9b | |
29 | 1ea0-1ef9 207f | |
30 | ||
31 | ; Greek | |
32 | 0386 0388-038a 038c 038e-03a1 03a3-03ce 03d0-03d6 03da 03dc 03de 03e0 | |
33 | 03e2-03f3 1f00-1f15 1f18-1f1d 1f20-1f45 1f48-1f4d 1f50-1f57 1f59 1f5b | |
34 | 1f5d 1f5f-1f7d 1f80-1fb4 1fb6-1fbc 1fc2-1fc4 1fc6-1fcc 1fd0-1fd3 | |
35 | 1fd6-1fdb 1fe0-1fec 1ff2-1ff4 1ff6-1ffc | |
36 | ||
37 | ; Cyrillic | |
38 | 0401-040c 040e-044f 0451-045c 045e-0481 0490-04c4 04c7-04c8 04cb-04cc | |
39 | 04d0-04eb 04ee-04f5 04f8-04f9 | |
40 | ||
41 | ; Armenian | |
42 | 0531-0556 0561-0587 | |
43 | ||
44 | ; Hebrew | |
45 | 05b0-05b9 05bb-05bd 05bf 05c1-05c2 05d0-05ea 05f0-05f2 | |
46 | ||
47 | ; Arabic | |
48 | 0621-063a 0640-0652 0670-06b7 06ba-06be 06c0-06ce 06d0-06dc 06e5-06e8 | |
49 | 06ea-06ed | |
50 | ||
51 | ; Devanagari | |
52 | 0901-0903 0905-0939 093e-094d 0950-0952 0958-0963 | |
53 | ||
54 | ; Bengali | |
55 | 0981-0983 0985-098c 098f-0990 0993-09a8 09aa-09b0 09b2 09b6-09b9 | |
56 | 09be-09c4 09c7-09c8 09cb-09cd 09dc-09dd 09df-09e3 09f0-09f1 | |
57 | ||
58 | ; Gurmukhi | |
59 | 0a02 0a05-0a0a 0a0f-0a10 0a13-0a28 0a2a-0a30 0a32-0a33 0a35-0a36 | |
60 | 0a38-0a39 0a3e-0a42 0a47-0a48 0a4b-0a4d 0a59-0a5c 0a5e 0a74 | |
61 | ||
62 | ; Gujarati | |
63 | 0a81-0a83 0a85-0a8b 0a8d 0a8f-0a91 0a93-0aa8 0aaa-0ab0 0ab2-0ab3 | |
64 | 0ab5-0ab9 0abd-0ac5 0ac7-0ac9 0acb-0acd 0ad0 0ae0 | |
65 | ||
66 | ; Oriya | |
67 | 0b01-0b03 0b05-0b0c 0b0f-0b10 0b13-0b28 0b2a-0b30 0b32-0b33 0b36-0b39 | |
68 | 0b3e-0b43 0b47-0b48 0b4b-0b4d 0b5c-0b5d 0b5f-0b61 | |
69 | ||
70 | ; Tamil | |
71 | 0b82-0b83 0b85-0b8a 0b8e-0b90 0b92-0b95 0b99-0b9a 0b9c 0b9e-0b9f | |
72 | 0ba3-0ba4 0ba8-0baa 0bae-0bb5 0bb7-0bb9 0bbe-0bc2 0bc6-0bc8 0bca-0bcd | |
73 | ||
74 | ; Telugu | |
75 | 0c01-0c03 0c05-0c0c 0c0e-0c10 0c12-0c28 0c2a-0c33 0c35-0c39 0c3e-0c44 | |
76 | 0c46-0c48 0c4a-0c4d 0c60-0c61 | |
77 | ||
78 | ; Kannada | |
79 | 0c82-0c83 0c85-0c8c 0c8e-0c90 0c92-0ca8 0caa-0cb3 0cb5-0cb9 0cbe-0cc4 | |
80 | 0cc6-0cc8 0cca-0ccd 0cde 0ce0-0ce1 | |
81 | ||
82 | ; Malayalam | |
83 | 0d02-0d03 0d05-0d0c 0d0e-0d10 0d12-0d28 0d2a-0d39 0d3e-0d43 0d46-0d48 | |
84 | 0d4a-0d4d 0d60-0d61 | |
85 | ||
86 | # CORRECTION: exclude 0e50-0e59 from the Thai range as it also appears | |
87 | # in the Digits range below. | |
88 | ; Thai | |
89 | 0e01-0e3a 0e40-0e49 0e5a-0e5b | |
90 | ||
91 | ; Lao | |
92 | 0e81-0e82 0e84 0e87-0e88 0e8a 0e8d 0e94-0e97 0e99-0e9f 0ea1-0ea3 0ea5 | |
93 | 0ea7 0eaa-0eab 0ead-0eae 0eb0-0eb9 0ebb-0ebd 0ec0-0ec4 0ec6 0ec8-0ecd | |
94 | 0edc-0edd | |
95 | ||
96 | ; Tibetan | |
97 | 0f00 0f18-0f19 0f35 0f37 0f39 0f3e-0f47 0f49-0f69 0f71-0f84 0f86-0f8b | |
98 | 0f90-0f95 0f97 0f99-0fad 0fb1-0fb7 0fb9 | |
99 | ||
100 | ; Georgian | |
101 | 10a0-10c5 10d0-10f6 | |
102 | ||
103 | ; Hiragana | |
104 | 3041-3093 309b-309c | |
105 | ||
106 | ; Katakana | |
107 | 30a1-30f6 30fb-30fc | |
108 | ||
109 | ; Bopomofo | |
110 | 3105-312c | |
111 | ||
112 | ; CJK Unified Ideographs | |
113 | 4e00-9fa5 | |
114 | ||
115 | ; Hangul | |
116 | ac00-d7a3 | |
117 | ||
118 | ; Special characters | |
119 | 00b5 00b7 02b0-02b8 02bb 02bd-02c1 02d0-02d1 02e0-02e4 037a 0559 093d | |
120 | 0b3d 1fbe 203f-2040 2102 2107 210a-2113 2115 2118-211d 2124 2126 2128 | |
121 | 212a-2131 2133-2138 2160-2182 3005-3007 3021-3029 | |
122 | ||
54848ff8 | 123 | [C99DIG] |
e6cc3a24 ZW |
124 | 0660-0669 06f0-06f9 0966-096f 09e6-09ef 0a66-0a6f 0ae6-0aef 0b66-0b6f |
125 | 0be7-0bef 0c66-0c6f 0ce6-0cef 0d66-0d6f 0e50-0e59 0ed0-0ed9 0f20-0f33 | |
126 | ||
127 | [CXX] | |
128 | ||
129 | ; Latin | |
130 | 00c0-00d6 00d8-00f6 00f8-01f5 01fa-0217 0250-02a8 1e00-1e9a 1ea0-1ef9 | |
131 | ||
132 | ; Greek | |
133 | 0384 0388-038a 038c 038e-03a1 03a3-03ce 03d0-03d6 03da 03dc 03de 03e0 | |
134 | 03e2-03f3 1f00-1f15 1f18-1f1d 1f20-1f45 1f48-1f4d 1f50-1f57 1f59 1f5b | |
135 | 1f5d 1f5f-1f7d 1f80-1fb4 1fb6-1fbc 1fc2-1fc4 1fc6-1fcc 1fd0-1fd3 | |
136 | 1fd6-1fdb 1fe0-1fec 1ff2-1ff4 1ff6-1ffc | |
137 | ||
138 | ; Cyrillic | |
139 | 0401-040d 040f-044f 0451-045c 045e-0481 0490-04c4 04c7-04c8 04cb-04cc | |
140 | 04d0-04eb 04ee-04f5 04f8-04f9 | |
141 | ||
142 | ; Armenian | |
143 | 0531-0556 0561-0587 | |
144 | ||
145 | ; Hebrew | |
146 | 05d0-05ea 05f0-05f4 | |
147 | ||
148 | ; Arabic | |
149 | 0621-063a 0640-0652 0670-06b7 06ba-06be 06c0-06ce 06e5-06e7 | |
150 | ||
151 | ; Devanagari | |
152 | 0905-0939 0958-0962 | |
153 | ||
154 | ; Bengali | |
155 | 0985-098c 098f-0990 0993-09a8 09aa-09b0 09b2 09b6-09b9 09dc-09dd | |
156 | 09df-09e1 09f0-09f1 | |
157 | ||
158 | ; Gurmukhi | |
159 | 0a05-0a0a 0a0f-0a10 0a13-0a28 0a2a-0a30 0a32-0a33 0a35-0a36 0a38-0a39 | |
160 | 0a59-0a5c 0a5e | |
161 | ||
162 | ; Gujarati | |
163 | 0a85-0a8b 0a8d 0a8f-0a91 0a93-0aa8 0aaa-0ab0 0ab2-0ab3 0ab5-0ab9 0ae0 | |
164 | ||
165 | ; Oriya | |
166 | 0b05-0b0c 0b0f-0b10 0b13-0b28 0b2a-0b30 0b32-0b33 0b36-0b39 0b5c-0b5d | |
167 | 0b5f-0b61 | |
168 | ||
169 | ; Tamil | |
170 | 0b85-0b8a 0b8e-0b90 0b92-0b95 0b99-0b9a 0b9c 0b9e-0b9f 0ba3-0ba4 | |
171 | 0ba8-0baa 0bae-0bb5 0bb7-0bb9 | |
172 | ||
173 | ; Telugu | |
174 | 0c05-0c0c 0c0e-0c10 0c12-0c28 0c2a-0c33 0c35-0c39 0c60-0c61 | |
175 | ||
176 | ; Kannada | |
177 | 0c85-0c8c 0c8e-0c90 0c92-0ca8 0caa-0cb3 0cb5-0cb9 0ce0-0ce1 | |
178 | ||
179 | ; Malayalam | |
180 | 0d05-0d0c 0d0e-0d10 0d12-0d28 0d2a-0d39 0d60-0d61 | |
181 | ||
e6cc3a24 | 182 | ; Thai |
50668cf6 | 183 | 0e01-0e30 0e32-0e33 0e40-0e46 0e4f-0e5b |
e6cc3a24 ZW |
184 | |
185 | ; Digits | |
186 | 0e50-0e59 | |
187 | ||
e6cc3a24 ZW |
188 | ; Lao |
189 | 0e81-0e82 0e84 0e87-0e88 0e8a 0e8d 0e94-0e97 0e99-0e9f 0ea1-0ea3 0ea5 | |
190 | 0ea7 0eaa-0eab 0ead-0eb0 0eb2 0eb3 0ebd 0ec0-0ec4 0ec6 | |
191 | ||
192 | ; Georgian | |
193 | 10a0-10c5 10d0-10f6 | |
194 | ||
195 | ; Hiragana | |
196 | 3041-3094 309b-309e | |
197 | ||
198 | ; Katakana | |
199 | 30a1-30fe | |
200 | ||
e6cc3a24 ZW |
201 | ; Bopomofo |
202 | 3105-312c | |
203 | ||
204 | ; Hangul | |
205 | 1100-1159 1161-11a2 11a8-11f9 | |
206 | ||
207 | ; CJK Unified Ideographs | |
208 | f900-fa2d fb1f-fb36 fb38-fb3c fb3e fb40-fb41 fb42-fb44 fb46-fbb1 | |
209 | fbd3-fd3f fd50-fd8f fd92-fdc7 fdf0-fdfb fe70-fe72 fe74 fe76-fefc | |
210 | ff21-ff3a ff41-ff5a ff66-ffbe ffc2-ffc7 ffca-ffcf ffd2-ffd7 | |
211 | ffda-ffdc 4e00-9fa5 | |
212 | ||
d3f4ff8b JM |
213 | [C11] |
214 | ; Group 1 | |
215 | 00a8 00aa 00ad 00af 00b2-00b5 00b7-00ba 00bc-00be 00c0-00d6 00d8-00f6 | |
216 | 00f8-00ff | |
217 | ||
218 | ; Group 2, minus characters under C11NOSTART | |
219 | 0100-02ff 0370-167f 1681-180d 180f-1dbf 1e00-1fff | |
220 | ||
221 | ; Group 3 | |
222 | 200b-200d 202a-202e 203f-2040 2054 2060-206f | |
223 | ||
224 | ; Group 4, minus characters under C11NOSTART | |
225 | 2070-20cf 2100-218f 2460-24ff 2776-2793 2c00-2dff 2e80-2fff | |
226 | ||
227 | ; Group 5 | |
228 | 3004-3007 3021-302f 3031-303f | |
229 | ||
230 | ; Group 6 | |
231 | 3040-d7ff | |
232 | ||
233 | ; Group 7, minus characters under C11NOSTART | |
234 | f900-fd3d fd40-fdcf fdf0-fe1f fe30-fe44 fe47-fffd | |
235 | ||
236 | ; Group 8 | |
237 | 10000-1fffd 20000-2fffd 30000-3fffd 40000-4fffd 50000-5fffd | |
238 | 60000-6fffd 70000-7fffd 80000-8fffd 90000-9fffd a0000-afffd | |
239 | b0000-bfffd c0000-cfffd d0000-dfffd e0000-efffd | |
240 | ||
241 | [C11NOSTART] | |
242 | ; Group 1 | |
243 | 0300-036f 1dc0-1dff 20d0-20ff fe20-fe2f |