forked from uncrustify/uncrustify
-
Notifications
You must be signed in to change notification settings - Fork 0
Expand file tree
/
Copy pathunicode.cpp
More file actions
493 lines (442 loc) · 9.67 KB
/
unicode.cpp
File metadata and controls
493 lines (442 loc) · 9.67 KB
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
294
295
296
297
298
299
300
301
302
303
304
305
306
307
308
309
310
311
312
313
314
315
316
317
318
319
320
321
322
323
324
325
326
327
328
329
330
331
332
333
334
335
336
337
338
339
340
341
342
343
344
345
346
347
348
349
350
351
352
353
354
355
356
357
358
359
360
361
362
363
364
365
366
367
368
369
370
371
372
373
374
375
376
377
378
379
380
381
382
383
384
385
386
387
388
389
390
391
392
393
394
395
396
397
398
399
400
401
402
403
404
405
406
407
408
409
410
411
412
413
414
415
416
417
418
419
420
421
422
423
424
425
426
427
428
429
430
431
432
433
434
435
436
437
438
439
440
441
442
443
444
445
446
447
448
449
450
451
452
453
454
455
456
457
458
459
460
461
462
463
464
465
466
467
468
469
470
471
472
473
474
475
476
477
478
479
480
481
482
483
484
485
486
487
488
489
490
491
492
493
/**
* @file unicode.cpp
* Detects, read and writes characters in the proper format.
*
* @author Ben Gardner
* @license GPL v2+
*/
#include "uncrustify_types.h"
#include "prototypes.h"
#include "unc_ctype.h"
#include <cstring>
#include <cstdlib>
/**
* See if all characters are ASCII (0-127)
*/
bool is_ascii(const vector<UINT8>& data)
{
for (int idx = 0; idx < (int)data.size(); idx++)
{
if (data[idx] & 0x80)
{
return false;
}
}
return true;
}
/**
* Convert the array of bytes into an array of ints
*/
bool decode_bytes(const vector<UINT8>& in_data, deque<int>& out_data)
{
out_data.resize(in_data.size());
for (int idx = 0; idx < (int)in_data.size(); idx++)
{
out_data[idx] = in_data[idx];
}
return true;
}
void encode_utf8(int ch, vector<UINT8>& res)
{
if (ch < 0)
{
/* illegal code - do not store */
}
else if (ch < 0x80)
{
/* 0xxxxxxx */
res.push_back(ch);
}
else if (ch < 0x0800)
{
/* 110xxxxx 10xxxxxx */
res.push_back(0xC0 | (ch >> 6));
res.push_back(0x80 | (ch & 0x3f));
}
else if (ch < 0x10000)
{
/* 1110xxxx 10xxxxxx 10xxxxxx */
res.push_back(0xE0 | (ch >> 12));
res.push_back(0x80 | ((ch >> 6) & 0x3f));
res.push_back(0x80 | (ch & 0x3f));
}
else if (ch < 0x200000)
{
/* 11110xxx 10xxxxxx 10xxxxxx 10xxxxxx */
res.push_back(0xF0 | (ch >> 18));
res.push_back(0x80 | ((ch >> 12) & 0x3f));
res.push_back(0x80 | ((ch >> 6) & 0x3f));
res.push_back(0x80 | (ch & 0x3f));
}
else if (ch < 0x4000000)
{
/* 111110xx 10xxxxxx 10xxxxxx 10xxxxxx 10xxxxxx */
res.push_back(0xF8 | (ch >> 24));
res.push_back(0x80 | ((ch >> 18) & 0x3f));
res.push_back(0x80 | ((ch >> 12) & 0x3f));
res.push_back(0x80 | ((ch >> 6) & 0x3f));
res.push_back(0x80 | (ch & 0x3f));
}
else /* (ch <= 0x7fffffff) */
{
/* 1111110x 10xxxxxx 10xxxxxx 10xxxxxx 10xxxxxx 10xxxxxx */
res.push_back(0xFC | (ch >> 30));
res.push_back(0x80 | ((ch >> 24) & 0x3f));
res.push_back(0x80 | ((ch >> 18) & 0x3f));
res.push_back(0x80 | ((ch >> 12) & 0x3f));
res.push_back(0x80 | ((ch >> 6) & 0x3f));
res.push_back(0x80 | (ch & 0x3f));
}
}
/**
* Decode UTF-8 sequences from in_data and put the chars in out_data.
* If there are any decoding errors, then return false.
*/
bool decode_utf8(const vector<UINT8>& in_data, deque<int>& out_data)
{
int idx = 0;
int ch, tmp, cnt;
out_data.clear();
/* check for UTF-8 BOM silliness and skip */
if (in_data.size() >= 3)
{
if ((in_data[0] == 0xef) &&
(in_data[1] == 0xbb) &&
(in_data[2] == 0xbf))
{
/* skip it */
idx = 3;
}
}
while (idx < (int)in_data.size())
{
ch = in_data[idx++];
if (ch < 0x80) /* 1-byte sequence */
{
out_data.push_back(ch);
continue;
}
else if ((ch & 0xE0) == 0xC0) /* 2-byte sequence */
{
ch &= 0x1F;
cnt = 1;
}
else if ((ch & 0xF0) == 0xE0) /* 3-byte sequence */
{
ch &= 0x0F;
cnt = 2;
}
else if ((ch & 0xF8) == 0xF0) /* 4-byte sequence */
{
ch &= 0x07;
cnt = 3;
}
else if ((ch & 0xFC) == 0xF8) /* 5-byte sequence */
{
ch &= 0x03;
cnt = 4;
}
else if ((ch & 0xFE) == 0xFC) /* 6-byte sequence */
{
ch &= 0x01;
cnt = 5;
}
else
{
/* invalid UTF-8 sequence */
return false;
}
while ((cnt-- > 0) && (idx < (int)in_data.size()))
{
tmp = in_data[idx++];
if ((tmp & 0xC0) != 0x80)
{
/* invalid UTF-8 sequence */
return false;
}
ch = (ch << 6) | (tmp & 0x3f);
}
if (cnt >= 0)
{
/* short UTF-8 sequence */
return false;
}
out_data.push_back(ch);
}
return true;
}
/**
* Extract 2 bytes from the stream and increment idx by 2
*/
static int get_word(const vector<UINT8>& in_data, int& idx, bool be)
{
int ch;
if ((idx + 2) > in_data.size())
{
ch = -1;
}
else if (be)
{
ch = (in_data[idx] << 8) | in_data[idx + 1];
}
else
{
ch = in_data[idx] | (in_data[idx + 1] << 8);
}
idx += 2;
return ch;
}
/**
* Deocde a UTF-16 sequence.
* Sets enc based on the BOM.
* Must have the BOM as the first two bytes.
*/
bool decode_utf16(const vector<UINT8>& in_data, deque<int>& out_data, CharEncoding& enc)
{
out_data.clear();
if (in_data.size() & 1)
{
/* can't have and odd length */
return false;
}
if (in_data.size() < 2)
{
/* we require the BOM */
return false;
}
if ((in_data[0] == 0xfe) && (in_data[1] == 0xff))
{
enc = ENC_UTF16_BE;
}
else if ((in_data[0] == 0xff) && (in_data[1] == 0xfe))
{
enc = ENC_UTF16_LE;
}
else
{
return false;
}
bool be = (enc == ENC_UTF16_BE);
int idx = 2;
while (idx < (int)in_data.size())
{
int ch = get_word(in_data, idx, be);
if ((ch & 0xfc00) == 0xd800)
{
ch &= 0x3ff;
ch <<= 10;
int tmp = get_word(in_data, idx, be);
if ((tmp & 0xfc00) != 0xdc00)
{
return false;
}
ch |= (tmp & 0x3ff);
ch += 0x10000;
out_data.push_back(ch);
}
else if (((ch >= 0) && (ch < 0xD800)) || (ch >= 0xE000))
{
out_data.push_back(ch);
}
else
{
/* invalid character */
return false;
}
}
return true;
}
/**
* Looks for the BOM of UTF-16 BE/LE and UTF-8.
* If found, set enc and return true.
* Sets enc to ENC_ASCII and returns false if not found.
*/
bool decode_bom(const vector<UINT8>& in_data, CharEncoding& enc)
{
enc = ENC_ASCII;
if (in_data.size() >= 2)
{
if ((in_data[0] == 0xfe) && (in_data[1] == 0xff))
{
enc = ENC_UTF16_BE;
return true;
}
else if ((in_data[0] == 0xff) && (in_data[1] == 0xfe))
{
enc = ENC_UTF16_LE;
return true;
}
else if ((in_data.size() >= 3) &&
(in_data[0] == 0xef) &&
(in_data[1] == 0xbb) &&
(in_data[2] == 0xbf))
{
enc = ENC_UTF8;
return true;
}
}
return false;
}
/**
* Figure out the encoding and convert to an int sequence
*/
bool decode_unicode(const vector<UINT8>& in_data, deque<int>& out_data, CharEncoding& enc)
{
/* check for a BOM */
if (decode_bom(in_data, enc))
{
if (enc == ENC_UTF8)
{
return decode_utf8(in_data, out_data);
}
else
{
return decode_utf16(in_data, out_data, enc);
}
}
if (is_ascii(in_data))
{
enc = ENC_ASCII;
return decode_bytes(in_data, out_data);
}
if (decode_utf8(in_data, out_data))
{
enc = ENC_UTF8;
return true;
}
/* it is an unrecognized byte sequence */
enc = ENC_BYTE;
return decode_bytes(in_data, out_data);
}
/**
* Write for ASCII and BYTE encoding
*/
void write_byte(int ch, FILE *pf)
{
if (ch < 0x100)
{
fputc(ch, pf);
}
else
{
/* illegal code - do not store */
}
}
/**
* Writes a single character to a file using UTF-8 encoding
*/
void write_utf8(int ch, FILE *pf)
{
vector<UINT8> dq;
dq.reserve(6);
encode_utf8(ch, dq);
fwrite(&dq[0], dq.size(), 1, pf);
}
void write_utf16(int ch, bool be, FILE *pf)
{
/* U+0000 to U+D7FF and U+E000 to U+FFFF */
if (((ch >= 0) && (ch < 0xD800)) || ((ch >= 0xE000) && (ch < 0x10000)))
{
if (be)
{
fputc((ch >> 8), pf);
fputc((ch & 0xff), pf);
}
else
{
fputc((ch >> 8), pf);
fputc((ch & 0xff), pf);
}
}
else if ((ch >= 0x10000) && (ch < 0x110000))
{
int v1 = ch - 0x10000;
int w1 = 0xD800 + (v1 >> 10);
int w2 = 0xDC00 + (v1 & 0x3ff);
if (be)
{
fputc((w1 >> 8), pf);
fputc((w1 & 0xff), pf);
fputc((w2 >> 8), pf);
fputc((w2 & 0xff), pf);
}
else
{
fputc((w1 & 0xff), pf);
fputc((w1 >> 8), pf);
fputc((w2 & 0xff), pf);
fputc((w2 >> 8), pf);
}
}
else
{
/* illegal code - do not store */
}
}
void write_bom(FILE *pf, CharEncoding enc, bool force)
{
switch (enc)
{
case ENC_ASCII:
case ENC_BYTE:
default:
break;
case ENC_UTF8:
if (force)
{
write_byte(0xef, pf);
write_byte(0xbb, pf);
write_byte(0xbf, pf);
}
break;
case ENC_UTF16_LE:
write_utf16(0xfeff, false, pf);
break;
case ENC_UTF16_BE:
write_utf16(0xfeff, true, pf);
break;
}
}
/**
* @param ch the 31-bit char value
*/
void write_char(FILE *pf, int ch, CharEncoding enc)
{
if (ch >= 0)
{
switch (enc)
{
case ENC_BYTE:
write_byte(ch & 0xff, pf);
break;
case ENC_ASCII:
default:
write_byte(ch, pf);
break;
case ENC_UTF8:
write_utf8(ch, pf);
break;
case ENC_UTF16_LE:
write_utf16(ch, false, pf);
break;
case ENC_UTF16_BE:
write_utf16(ch, true, pf);
break;
}
}
}
void write_string(FILE *pf, const char *ascii_text, CharEncoding enc)
{
while (*ascii_text)
{
write_char(pf, *ascii_text, enc);
ascii_text++;
}
}
void write_string(FILE *pf, const deque<int>& text, CharEncoding enc)
{
for (int idx = 0; idx < (int)text.size(); idx++)
{
write_char(pf, text[idx], enc);
}
}