1 //===--- UnicodeCharSets.h - Contains important sets of characters --------===//
2 //
3 // The LLVM Compiler Infrastructure
4 //
5 // This file is distributed under the University of Illinois Open Source
6 // License. See LICENSE.TXT for details.
7 //
8 //===----------------------------------------------------------------------===//
9 #ifndef CLANG_LEX_UNICODECHARSETS_H
10 #define CLANG_LEX_UNICODECHARSETS_H
11
12 #include "llvm/ADT/ArrayRef.h"
13 #include "llvm/ADT/SmallPtrSet.h"
14 #include "llvm/Support/Compiler.h"
15 #include "llvm/Support/Debug.h"
16 #include "llvm/Support/Mutex.h"
17 #include "llvm/Support/MutexGuard.h"
18 #include "llvm/Support/raw_ostream.h"
19
20 namespace {
21 struct UnicodeCharRange {
22 uint32_t Lower;
23 uint32_t Upper;
24 };
25 typedef llvm::ArrayRef<UnicodeCharRange> UnicodeCharSet;
26
27 typedef llvm::SmallPtrSet<const UnicodeCharRange *, 16> ValidatedCharSetsTy;
28 }
29
getValidatedCharSets()30 static inline ValidatedCharSetsTy &getValidatedCharSets() {
31 static ValidatedCharSetsTy Validated;
32 return Validated;
33 }
34
35 /// Returns true if each of the ranges in \p CharSet is a proper closed range
36 /// [min, max], and if the ranges themselves are ordered and non-overlapping.
isValidCharSet(UnicodeCharSet CharSet)37 static inline bool isValidCharSet(UnicodeCharSet CharSet) {
38 #ifndef NDEBUG
39 static llvm::sys::Mutex ValidationMutex;
40
41 // Check the validation cache.
42 {
43 llvm::MutexGuard Guard(ValidationMutex);
44 if (getValidatedCharSets().count(CharSet.data()))
45 return true;
46 }
47
48 // Walk through the ranges.
49 uint32_t Prev = 0;
50 for (UnicodeCharSet::iterator I = CharSet.begin(), E = CharSet.end();
51 I != E; ++I) {
52 if (Prev >= I->Lower) {
53 DEBUG(llvm::dbgs() << "Upper bound 0x");
54 DEBUG(llvm::dbgs().write_hex(Prev));
55 DEBUG(llvm::dbgs() << " should be less than succeeding lower bound 0x");
56 DEBUG(llvm::dbgs().write_hex(I->Lower) << "\n");
57 return false;
58 }
59 if (I->Upper < I->Lower) {
60 DEBUG(llvm::dbgs() << "Upper bound 0x");
61 DEBUG(llvm::dbgs().write_hex(I->Lower));
62 DEBUG(llvm::dbgs() << " should not be less than lower bound 0x");
63 DEBUG(llvm::dbgs().write_hex(I->Upper) << "\n");
64 return false;
65 }
66 Prev = I->Upper;
67 }
68
69 // Update the validation cache.
70 {
71 llvm::MutexGuard Guard(ValidationMutex);
72 getValidatedCharSets().insert(CharSet.data());
73 }
74 #endif
75 return true;
76 }
77
78 /// Returns true if the Unicode code point \p C is within the set of
79 /// characters specified by \p CharSet.
isCharInSet(uint32_t C,UnicodeCharSet CharSet)80 LLVM_READONLY static inline bool isCharInSet(uint32_t C,
81 UnicodeCharSet CharSet) {
82 assert(isValidCharSet(CharSet));
83
84 size_t LowPoint = 0;
85 size_t HighPoint = CharSet.size();
86
87 // Binary search the set of char ranges.
88 while (HighPoint != LowPoint) {
89 size_t MidPoint = (HighPoint + LowPoint) / 2;
90 if (C < CharSet[MidPoint].Lower)
91 HighPoint = MidPoint;
92 else if (C > CharSet[MidPoint].Upper)
93 LowPoint = MidPoint + 1;
94 else
95 return true;
96 }
97
98 return false;
99 }
100
101
102 // C11 D.1, C++11 [charname.allowed]
103 static const UnicodeCharRange C11AllowedIDChars[] = {
104 // 1
105 { 0x00A8, 0x00A8 }, { 0x00AA, 0x00AA }, { 0x00AD, 0x00AD },
106 { 0x00AF, 0x00AF }, { 0x00B2, 0x00B5 }, { 0x00B7, 0x00BA },
107 { 0x00BC, 0x00BE }, { 0x00C0, 0x00D6 }, { 0x00D8, 0x00F6 },
108 { 0x00F8, 0x00FF },
109 // 2
110 { 0x0100, 0x167F }, { 0x1681, 0x180D }, { 0x180F, 0x1FFF },
111 // 3
112 { 0x200B, 0x200D }, { 0x202A, 0x202E }, { 0x203F, 0x2040 },
113 { 0x2054, 0x2054 }, { 0x2060, 0x206F },
114 // 4
115 { 0x2070, 0x218F }, { 0x2460, 0x24FF }, { 0x2776, 0x2793 },
116 { 0x2C00, 0x2DFF }, { 0x2E80, 0x2FFF },
117 // 5
118 { 0x3004, 0x3007 }, { 0x3021, 0x302F }, { 0x3031, 0x303F },
119 // 6
120 { 0x3040, 0xD7FF },
121 // 7
122 { 0xF900, 0xFD3D }, { 0xFD40, 0xFDCF }, { 0xFDF0, 0xFE44 },
123 { 0xFE47, 0xFFFD },
124 // 8
125 { 0x10000, 0x1FFFD }, { 0x20000, 0x2FFFD }, { 0x30000, 0x3FFFD },
126 { 0x40000, 0x4FFFD }, { 0x50000, 0x5FFFD }, { 0x60000, 0x6FFFD },
127 { 0x70000, 0x7FFFD }, { 0x80000, 0x8FFFD }, { 0x90000, 0x9FFFD },
128 { 0xA0000, 0xAFFFD }, { 0xB0000, 0xBFFFD }, { 0xC0000, 0xCFFFD },
129 { 0xD0000, 0xDFFFD }, { 0xE0000, 0xEFFFD }
130 };
131
132 // C++03 [extendid]
133 // Note that this is not the same as C++98, but we don't distinguish C++98
134 // and C++03 in Clang.
135 static const UnicodeCharRange CXX03AllowedIDChars[] = {
136 // Latin
137 { 0x00C0, 0x00D6 }, { 0x00D8, 0x00F6 }, { 0x00F8, 0x01F5 },
138 { 0x01FA, 0x0217 }, { 0x0250, 0x02A8 },
139
140 // Greek
141 { 0x0384, 0x0384 }, { 0x0388, 0x038A }, { 0x038C, 0x038C },
142 { 0x038E, 0x03A1 }, { 0x03A3, 0x03CE }, { 0x03D0, 0x03D6 },
143 { 0x03DA, 0x03DA }, { 0x03DC, 0x03DC }, { 0x03DE, 0x03DE },
144 { 0x03E0, 0x03E0 }, { 0x03E2, 0x03F3 },
145
146 // Cyrillic
147 { 0x0401, 0x040D }, { 0x040F, 0x044F }, { 0x0451, 0x045C },
148 { 0x045E, 0x0481 }, { 0x0490, 0x04C4 }, { 0x04C7, 0x04C8 },
149 { 0x04CB, 0x04CC }, { 0x04D0, 0x04EB }, { 0x04EE, 0x04F5 },
150 { 0x04F8, 0x04F9 },
151
152 // Armenian
153 { 0x0531, 0x0556 }, { 0x0561, 0x0587 },
154
155 // Hebrew
156 { 0x05D0, 0x05EA }, { 0x05F0, 0x05F4 },
157
158 // Arabic
159 { 0x0621, 0x063A }, { 0x0640, 0x0652 }, { 0x0670, 0x06B7 },
160 { 0x06BA, 0x06BE }, { 0x06C0, 0x06CE }, { 0x06E5, 0x06E7 },
161
162 // Devanagari
163 { 0x0905, 0x0939 }, { 0x0958, 0x0962 },
164
165 // Bengali
166 { 0x0985, 0x098C }, { 0x098F, 0x0990 }, { 0x0993, 0x09A8 },
167 { 0x09AA, 0x09B0 }, { 0x09B2, 0x09B2 }, { 0x09B6, 0x09B9 },
168 { 0x09DC, 0x09DD }, { 0x09DF, 0x09E1 }, { 0x09F0, 0x09F1 },
169
170 // Gurmukhi
171 { 0x0A05, 0x0A0A }, { 0x0A0F, 0x0A10 }, { 0x0A13, 0x0A28 },
172 { 0x0A2A, 0x0A30 }, { 0x0A32, 0x0A33 }, { 0x0A35, 0x0A36 },
173 { 0x0A38, 0x0A39 }, { 0x0A59, 0x0A5C }, { 0x0A5E, 0x0A5E },
174
175 // Gujarti
176 { 0x0A85, 0x0A8B }, { 0x0A8D, 0x0A8D }, { 0x0A8F, 0x0A91 },
177 { 0x0A93, 0x0AA8 }, { 0x0AAA, 0x0AB0 }, { 0x0AB2, 0x0AB3 },
178 { 0x0AB5, 0x0AB9 }, { 0x0AE0, 0x0AE0 },
179
180 // Oriya
181 { 0x0B05, 0x0B0C }, { 0x0B0F, 0x0B10 }, { 0x0B13, 0x0B28 },
182 { 0x0B2A, 0x0B30 }, { 0x0B32, 0x0B33 }, { 0x0B36, 0x0B39 },
183 { 0x0B5C, 0x0B5D }, { 0x0B5F, 0x0B61 },
184
185 // Tamil
186 { 0x0B85, 0x0B8A }, { 0x0B8E, 0x0B90 }, { 0x0B92, 0x0B95 },
187 { 0x0B99, 0x0B9A }, { 0x0B9C, 0x0B9C }, { 0x0B9E, 0x0B9F },
188 { 0x0BA3, 0x0BA4 }, { 0x0BA8, 0x0BAA }, { 0x0BAE, 0x0BB5 },
189 { 0x0BB7, 0x0BB9 },
190
191 // Telugu
192 { 0x0C05, 0x0C0C }, { 0x0C0E, 0x0C10 }, { 0x0C12, 0x0C28 },
193 { 0x0C2A, 0x0C33 }, { 0x0C35, 0x0C39 }, { 0x0C60, 0x0C61 },
194
195 // Kannada
196 { 0x0C85, 0x0C8C }, { 0x0C8E, 0x0C90 }, { 0x0C92, 0x0CA8 },
197 { 0x0CAA, 0x0CB3 }, { 0x0CB5, 0x0CB9 }, { 0x0CE0, 0x0CE1 },
198
199 // Malayam
200 { 0x0D05, 0x0D0C }, { 0x0D0E, 0x0D10 }, { 0x0D12, 0x0D28 },
201 { 0x0D2A, 0x0D39 }, { 0x0D60, 0x0D61 },
202
203 // Thai
204 { 0x0E01, 0x0E30 }, { 0x0E32, 0x0E33 }, { 0x0E40, 0x0E46 },
205 { 0x0E4F, 0x0E5B },
206
207 // Lao
208 { 0x0E81, 0x0E82 }, { 0x0E84, 0x0E84 }, { 0x0E87, 0x0E87 },
209 { 0x0E88, 0x0E88 }, { 0x0E8A, 0x0E8A }, { 0x0E8D, 0x0E8D },
210 { 0x0E94, 0x0E97 }, { 0x0E99, 0x0E9F }, { 0x0EA1, 0x0EA3 },
211 { 0x0EA5, 0x0EA5 }, { 0x0EA7, 0x0EA7 }, { 0x0EAA, 0x0EAA },
212 { 0x0EAB, 0x0EAB }, { 0x0EAD, 0x0EB0 }, { 0x0EB2, 0x0EB2 },
213 { 0x0EB3, 0x0EB3 }, { 0x0EBD, 0x0EBD }, { 0x0EC0, 0x0EC4 },
214 { 0x0EC6, 0x0EC6 },
215
216 // Georgian
217 { 0x10A0, 0x10C5 }, { 0x10D0, 0x10F6 },
218
219 // Hangul
220 { 0x1100, 0x1159 }, { 0x1161, 0x11A2 }, { 0x11A8, 0x11F9 },
221
222 // Latin (2)
223 { 0x1E00, 0x1E9A }, { 0x1EA0, 0x1EF9 },
224
225 // Greek (2)
226 { 0x1F00, 0x1F15 }, { 0x1F18, 0x1F1D }, { 0x1F20, 0x1F45 },
227 { 0x1F48, 0x1F4D }, { 0x1F50, 0x1F57 }, { 0x1F59, 0x1F59 },
228 { 0x1F5B, 0x1F5B }, { 0x1F5D, 0x1F5D }, { 0x1F5F, 0x1F7D },
229 { 0x1F80, 0x1FB4 }, { 0x1FB6, 0x1FBC }, { 0x1FC2, 0x1FC4 },
230 { 0x1FC6, 0x1FCC }, { 0x1FD0, 0x1FD3 }, { 0x1FD6, 0x1FDB },
231 { 0x1FE0, 0x1FEC }, { 0x1FF2, 0x1FF4 }, { 0x1FF6, 0x1FFC },
232
233 // Hiragana
234 { 0x3041, 0x3094 }, { 0x309B, 0x309E },
235
236 // Katakana
237 { 0x30A1, 0x30FE },
238
239 // Bopmofo [sic]
240 { 0x3105, 0x312C },
241
242 // CJK Unified Ideographs
243 { 0x4E00, 0x9FA5 }, { 0xF900, 0xFA2D }, { 0xFB1F, 0xFB36 },
244 { 0xFB38, 0xFB3C }, { 0xFB3E, 0xFB3E }, { 0xFB40, 0xFB41 },
245 { 0xFB42, 0xFB44 }, { 0xFB46, 0xFBB1 }, { 0xFBD3, 0xFD3F },
246 { 0xFD50, 0xFD8F }, { 0xFD92, 0xFDC7 }, { 0xFDF0, 0xFDFB },
247 { 0xFE70, 0xFE72 }, { 0xFE74, 0xFE74 }, { 0xFE76, 0xFEFC },
248 { 0xFF21, 0xFF3A }, { 0xFF41, 0xFF5A }, { 0xFF66, 0xFFBE },
249 { 0xFFC2, 0xFFC7 }, { 0xFFCA, 0xFFCF }, { 0xFFD2, 0xFFD7 },
250 { 0xFFDA, 0xFFDC }
251 };
252
253 // C99 Annex D
254 static const UnicodeCharRange C99AllowedIDChars[] = {
255 // Latin (1)
256 { 0x00AA, 0x00AA },
257
258 // Special characters (1)
259 { 0x00B5, 0x00B5 }, { 0x00B7, 0x00B7 },
260
261 // Latin (2)
262 { 0x00BA, 0x00BA }, { 0x00C0, 0x00D6 }, { 0x00D8, 0x00F6 },
263 { 0x00F8, 0x01F5 }, { 0x01FA, 0x0217 }, { 0x0250, 0x02A8 },
264
265 // Special characters (2)
266 { 0x02B0, 0x02B8 }, { 0x02BB, 0x02BB }, { 0x02BD, 0x02C1 },
267 { 0x02D0, 0x02D1 }, { 0x02E0, 0x02E4 }, { 0x037A, 0x037A },
268
269 // Greek (1)
270 { 0x0386, 0x0386 }, { 0x0388, 0x038A }, { 0x038C, 0x038C },
271 { 0x038E, 0x03A1 }, { 0x03A3, 0x03CE }, { 0x03D0, 0x03D6 },
272 { 0x03DA, 0x03DA }, { 0x03DC, 0x03DC }, { 0x03DE, 0x03DE },
273 { 0x03E0, 0x03E0 }, { 0x03E2, 0x03F3 },
274
275 // Cyrillic
276 { 0x0401, 0x040C }, { 0x040E, 0x044F }, { 0x0451, 0x045C },
277 { 0x045E, 0x0481 }, { 0x0490, 0x04C4 }, { 0x04C7, 0x04C8 },
278 { 0x04CB, 0x04CC }, { 0x04D0, 0x04EB }, { 0x04EE, 0x04F5 },
279 { 0x04F8, 0x04F9 },
280
281 // Armenian (1)
282 { 0x0531, 0x0556 },
283
284 // Special characters (3)
285 { 0x0559, 0x0559 },
286
287 // Armenian (2)
288 { 0x0561, 0x0587 },
289
290 // Hebrew
291 { 0x05B0, 0x05B9 }, { 0x05BB, 0x05BD }, { 0x05BF, 0x05BF },
292 { 0x05C1, 0x05C2 }, { 0x05D0, 0x05EA }, { 0x05F0, 0x05F2 },
293
294 // Arabic (1)
295 { 0x0621, 0x063A }, { 0x0640, 0x0652 },
296
297 // Digits (1)
298 { 0x0660, 0x0669 },
299
300 // Arabic (2)
301 { 0x0670, 0x06B7 }, { 0x06BA, 0x06BE }, { 0x06C0, 0x06CE },
302 { 0x06D0, 0x06DC }, { 0x06E5, 0x06E8 }, { 0x06EA, 0x06ED },
303
304 // Digits (2)
305 { 0x06F0, 0x06F9 },
306
307 // Devanagari and Special characeter 0x093D.
308 { 0x0901, 0x0903 }, { 0x0905, 0x0939 }, { 0x093D, 0x094D },
309 { 0x0950, 0x0952 }, { 0x0958, 0x0963 },
310
311 // Digits (3)
312 { 0x0966, 0x096F },
313
314 // Bengali (1)
315 { 0x0981, 0x0983 }, { 0x0985, 0x098C }, { 0x098F, 0x0990 },
316 { 0x0993, 0x09A8 }, { 0x09AA, 0x09B0 }, { 0x09B2, 0x09B2 },
317 { 0x09B6, 0x09B9 }, { 0x09BE, 0x09C4 }, { 0x09C7, 0x09C8 },
318 { 0x09CB, 0x09CD }, { 0x09DC, 0x09DD }, { 0x09DF, 0x09E3 },
319
320 // Digits (4)
321 { 0x09E6, 0x09EF },
322
323 // Bengali (2)
324 { 0x09F0, 0x09F1 },
325
326 // Gurmukhi (1)
327 { 0x0A02, 0x0A02 }, { 0x0A05, 0x0A0A }, { 0x0A0F, 0x0A10 },
328 { 0x0A13, 0x0A28 }, { 0x0A2A, 0x0A30 }, { 0x0A32, 0x0A33 },
329 { 0x0A35, 0x0A36 }, { 0x0A38, 0x0A39 }, { 0x0A3E, 0x0A42 },
330 { 0x0A47, 0x0A48 }, { 0x0A4B, 0x0A4D }, { 0x0A59, 0x0A5C },
331 { 0x0A5E, 0x0A5E },
332
333 // Digits (5)
334 { 0x0A66, 0x0A6F },
335
336 // Gurmukhi (2)
337 { 0x0A74, 0x0A74 },
338
339 // Gujarti
340 { 0x0A81, 0x0A83 }, { 0x0A85, 0x0A8B }, { 0x0A8D, 0x0A8D },
341 { 0x0A8F, 0x0A91 }, { 0x0A93, 0x0AA8 }, { 0x0AAA, 0x0AB0 },
342 { 0x0AB2, 0x0AB3 }, { 0x0AB5, 0x0AB9 }, { 0x0ABD, 0x0AC5 },
343 { 0x0AC7, 0x0AC9 }, { 0x0ACB, 0x0ACD }, { 0x0AD0, 0x0AD0 },
344 { 0x0AE0, 0x0AE0 },
345
346 // Digits (6)
347 { 0x0AE6, 0x0AEF },
348
349 // Oriya and Special character 0x0B3D
350 { 0x0B01, 0x0B03 }, { 0x0B05, 0x0B0C }, { 0x0B0F, 0x0B10 },
351 { 0x0B13, 0x0B28 }, { 0x0B2A, 0x0B30 }, { 0x0B32, 0x0B33 },
352 { 0x0B36, 0x0B39 }, { 0x0B3D, 0x0B43 }, { 0x0B47, 0x0B48 },
353 { 0x0B4B, 0x0B4D }, { 0x0B5C, 0x0B5D }, { 0x0B5F, 0x0B61 },
354
355 // Digits (7)
356 { 0x0B66, 0x0B6F },
357
358 // Tamil
359 { 0x0B82, 0x0B83 }, { 0x0B85, 0x0B8A }, { 0x0B8E, 0x0B90 },
360 { 0x0B92, 0x0B95 }, { 0x0B99, 0x0B9A }, { 0x0B9C, 0x0B9C },
361 { 0x0B9E, 0x0B9F }, { 0x0BA3, 0x0BA4 }, { 0x0BA8, 0x0BAA },
362 { 0x0BAE, 0x0BB5 }, { 0x0BB7, 0x0BB9 }, { 0x0BBE, 0x0BC2 },
363 { 0x0BC6, 0x0BC8 }, { 0x0BCA, 0x0BCD },
364
365 // Digits (8)
366 { 0x0BE7, 0x0BEF },
367
368 // Telugu
369 { 0x0C01, 0x0C03 }, { 0x0C05, 0x0C0C }, { 0x0C0E, 0x0C10 },
370 { 0x0C12, 0x0C28 }, { 0x0C2A, 0x0C33 }, { 0x0C35, 0x0C39 },
371 { 0x0C3E, 0x0C44 }, { 0x0C46, 0x0C48 }, { 0x0C4A, 0x0C4D },
372 { 0x0C60, 0x0C61 },
373
374 // Digits (9)
375 { 0x0C66, 0x0C6F },
376
377 // Kannada
378 { 0x0C82, 0x0C83 }, { 0x0C85, 0x0C8C }, { 0x0C8E, 0x0C90 },
379 { 0x0C92, 0x0CA8 }, { 0x0CAA, 0x0CB3 }, { 0x0CB5, 0x0CB9 },
380 { 0x0CBE, 0x0CC4 }, { 0x0CC6, 0x0CC8 }, { 0x0CCA, 0x0CCD },
381 { 0x0CDE, 0x0CDE }, { 0x0CE0, 0x0CE1 },
382
383 // Digits (10)
384 { 0x0CE6, 0x0CEF },
385
386 // Malayam
387 { 0x0D02, 0x0D03 }, { 0x0D05, 0x0D0C }, { 0x0D0E, 0x0D10 },
388 { 0x0D12, 0x0D28 }, { 0x0D2A, 0x0D39 }, { 0x0D3E, 0x0D43 },
389 { 0x0D46, 0x0D48 }, { 0x0D4A, 0x0D4D }, { 0x0D60, 0x0D60 },
390
391 // Digits (11)
392 { 0x0D66, 0x0D6F },
393
394 // Thai...including Digits { 0x0E50, 0x0E59 }
395 { 0x0E01, 0x0E3A }, { 0x0E40, 0x0E5B },
396
397 // Lao (1)
398 { 0x0E81, 0x0E82 }, { 0x0E84, 0x0E84 }, { 0x0E87, 0x0E88 },
399 { 0x0E8A, 0x0E8A }, { 0x0E8D, 0x0E8D }, { 0x0E94, 0x0E97 },
400 { 0x0E99, 0x0E9F }, { 0x0EA1, 0x0EA3 }, { 0x0EA5, 0x0EA5 },
401 { 0x0EA7, 0x0EA7 }, { 0x0EAA, 0x0EAB }, { 0x0EAD, 0x0EAE },
402 { 0x0EB0, 0x0EB9 }, { 0x0EBB, 0x0EBD }, { 0x0EC0, 0x0EC4 },
403 { 0x0EC6, 0x0EC6 }, { 0x0EC8, 0x0ECD },
404
405 // Digits (12)
406 { 0x0ED0, 0x0ED9 },
407
408 // Lao (2)
409 { 0x0EDC, 0x0EDD },
410
411 // Tibetan (1)
412 { 0x0F00, 0x0F00 }, { 0x0F18, 0x0F19 },
413
414 // Digits (13)
415 { 0x0F20, 0x0F33 },
416
417 // Tibetan (2)
418 { 0x0F35, 0x0F35 }, { 0x0F37, 0x0F37 }, { 0x0F39, 0x0F39 },
419 { 0x0F3E, 0x0F47 }, { 0x0F49, 0x0F69 }, { 0x0F71, 0x0F84 },
420 { 0x0F86, 0x0F8B }, { 0x0F90, 0x0F95 }, { 0x0F97, 0x0F97 },
421 { 0x0F99, 0x0FAD }, { 0x0FB1, 0x0FB7 }, { 0x0FB9, 0x0FB9 },
422
423 // Georgian
424 { 0x10A0, 0x10C5 }, { 0x10D0, 0x10F6 },
425
426 // Latin (3)
427 { 0x1E00, 0x1E9B }, { 0x1EA0, 0x1EF9 },
428
429 // Greek (2)
430 { 0x1F00, 0x1F15 }, { 0x1F18, 0x1F1D }, { 0x1F20, 0x1F45 },
431 { 0x1F48, 0x1F4D }, { 0x1F50, 0x1F57 }, { 0x1F59, 0x1F59 },
432 { 0x1F5B, 0x1F5B }, { 0x1F5D, 0x1F5D }, { 0x1F5F, 0x1F7D },
433 { 0x1F80, 0x1FB4 }, { 0x1FB6, 0x1FBC },
434
435 // Special characters (4)
436 { 0x1FBE, 0x1FBE },
437
438 // Greek (3)
439 { 0x1FC2, 0x1FC4 }, { 0x1FC6, 0x1FCC }, { 0x1FD0, 0x1FD3 },
440 { 0x1FD6, 0x1FDB }, { 0x1FE0, 0x1FEC }, { 0x1FF2, 0x1FF4 },
441 { 0x1FF6, 0x1FFC },
442
443 // Special characters (5)
444 { 0x203F, 0x2040 },
445
446 // Latin (4)
447 { 0x207F, 0x207F },
448
449 // Special characters (6)
450 { 0x2102, 0x2102 }, { 0x2107, 0x2107 }, { 0x210A, 0x2113 },
451 { 0x2115, 0x2115 }, { 0x2118, 0x211D }, { 0x2124, 0x2124 },
452 { 0x2126, 0x2126 }, { 0x2128, 0x2128 }, { 0x212A, 0x2131 },
453 { 0x2133, 0x2138 }, { 0x2160, 0x2182 }, { 0x3005, 0x3007 },
454 { 0x3021, 0x3029 },
455
456 // Hiragana
457 { 0x3041, 0x3093 }, { 0x309B, 0x309C },
458
459 // Katakana
460 { 0x30A1, 0x30F6 }, { 0x30FB, 0x30FC },
461
462 // Bopmofo [sic]
463 { 0x3105, 0x312C },
464
465 // CJK Unified Ideographs
466 { 0x4E00, 0x9FA5 },
467
468 // Hangul,
469 { 0xAC00, 0xD7A3 }
470 };
471
472 // C11 D.2, C++11 [charname.disallowed]
473 static const UnicodeCharRange C11DisallowedInitialIDChars[] = {
474 { 0x0300, 0x036F }, { 0x1DC0, 0x1DFF }, { 0x20D0, 0x20FF },
475 { 0xFE20, 0xFE2F }
476 };
477
478 // C99 6.4.2.1p3: The initial character [of an identifier] shall not be a
479 // universal character name designating a digit.
480 // C99 Annex D defines these characters as "Digits".
481 static const UnicodeCharRange C99DisallowedInitialIDChars[] = {
482 { 0x0660, 0x0669 }, { 0x06F0, 0x06F9 }, { 0x0966, 0x096F },
483 { 0x09E6, 0x09EF }, { 0x0A66, 0x0A6F }, { 0x0AE6, 0x0AEF },
484 { 0x0B66, 0x0B6F }, { 0x0BE7, 0x0BEF }, { 0x0C66, 0x0C6F },
485 { 0x0CE6, 0x0CEF }, { 0x0D66, 0x0D6F }, { 0x0E50, 0x0E59 },
486 { 0x0ED0, 0x0ED9 }, { 0x0F20, 0x0F33 }
487 };
488
489 // Unicode v6.2, chapter 6.2, table 6-2.
490 static const UnicodeCharRange UnicodeWhitespaceChars[] = {
491 { 0x0085, 0x0085 }, { 0x00A0, 0x00A0 }, { 0x1680, 0x1680 },
492 { 0x180E, 0x180E }, { 0x2000, 0x200A }, { 0x2028, 0x2029 },
493 { 0x202F, 0x202F }, { 0x205F, 0x205F }, { 0x3000, 0x3000 }
494 };
495
496 #endif
497