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
494
495
496
497
498
499
500
501
502
503
504
505
506
507
508
509
510
511
512
513
514
515
516
517
518
519
520
521
522
523
524
525
526
527
528
529
530
531
532
533
534
535
|
// © 2016 and later: Unicode, Inc. and others.
// License & terms of use: http://www.unicode.org/copyright.html
/*
*******************************************************************************
*
* Copyright (C) 2001-2012, International Business Machines
* Corporation and others. All Rights Reserved.
*
*******************************************************************************
* file name: ustr_wcs.cpp
* encoding: UTF-8
* tab size: 8 (not used)
* indentation:4
*
* created on: 2004sep07
* created by: Markus W. Scherer
*
* u_strToWCS() and u_strFromWCS() functions
* moved here from ustrtrns.c for better modularization.
*/
#include "unicode/utypes.h"
#include "unicode/ustring.h"
#include "cstring.h"
#include "cwchar.h"
#include "cmemory.h"
#include "ustr_imp.h"
#include "ustr_cnv.h"
#if defined(U_WCHAR_IS_UTF16) || defined(U_WCHAR_IS_UTF32) || !UCONFIG_NO_CONVERSION
#define _STACK_BUFFER_CAPACITY 1000
#define _BUFFER_CAPACITY_MULTIPLIER 2
#if !defined(U_WCHAR_IS_UTF16) && !defined(U_WCHAR_IS_UTF32)
// TODO: We should use CharString for char buffers and UnicodeString for char16_t buffers.
// Then we could change this to work only with wchar_t buffers.
static inline UBool
u_growAnyBufferFromStatic(void *context,
void **pBuffer, int32_t *pCapacity, int32_t reqCapacity,
int32_t length, int32_t size) {
// Use char* not void* to avoid the compiler's strict-aliasing assumptions
// and related warnings.
char *newBuffer=(char *)uprv_malloc(reqCapacity*size);
if(newBuffer!=nullptr) {
if(length>0) {
uprv_memcpy(newBuffer, *pBuffer, (size_t)length*size);
}
*pCapacity=reqCapacity;
} else {
*pCapacity=0;
}
/* release the old pBuffer if it was not statically allocated */
if(*pBuffer!=(char *)context) {
uprv_free(*pBuffer);
}
*pBuffer=newBuffer;
return newBuffer!=nullptr;
}
/* helper function */
static wchar_t*
_strToWCS(wchar_t *dest,
int32_t destCapacity,
int32_t *pDestLength,
const char16_t *src,
int32_t srcLength,
UErrorCode *pErrorCode){
char stackBuffer [_STACK_BUFFER_CAPACITY];
char* tempBuf = stackBuffer;
int32_t tempBufCapacity = _STACK_BUFFER_CAPACITY;
char* tempBufLimit = stackBuffer + tempBufCapacity;
UConverter* conv = nullptr;
char* saveBuf = tempBuf;
wchar_t* intTarget=nullptr;
int32_t intTargetCapacity=0;
int count=0,retVal=0;
const char16_t *pSrcLimit =nullptr;
const char16_t *pSrc = src;
conv = u_getDefaultConverter(pErrorCode);
if(U_FAILURE(*pErrorCode)){
return nullptr;
}
if(srcLength == -1){
srcLength = u_strlen(pSrc);
}
pSrcLimit = pSrc + srcLength;
for(;;) {
/* reset the error state */
*pErrorCode = U_ZERO_ERROR;
/* convert to chars using default converter */
ucnv_fromUnicode(conv,&tempBuf,tempBufLimit,&pSrc,pSrcLimit,nullptr,(UBool)(pSrc==pSrcLimit),pErrorCode);
count =(tempBuf - saveBuf);
/* This should rarely occur */
if(*pErrorCode==U_BUFFER_OVERFLOW_ERROR){
tempBuf = saveBuf;
/* we don't have enough room on the stack grow the buffer */
int32_t newCapacity = 2 * srcLength;
if(newCapacity <= tempBufCapacity) {
newCapacity = _BUFFER_CAPACITY_MULTIPLIER * tempBufCapacity;
}
if(!u_growAnyBufferFromStatic(stackBuffer,(void**) &tempBuf, &tempBufCapacity,
newCapacity, count, 1)) {
goto cleanup;
}
saveBuf = tempBuf;
tempBufLimit = tempBuf + tempBufCapacity;
tempBuf = tempBuf + count;
} else {
break;
}
}
if(U_FAILURE(*pErrorCode)){
goto cleanup;
}
/* done with conversion null terminate the char buffer */
if(count>=tempBufCapacity){
tempBuf = saveBuf;
/* we don't have enough room on the stack grow the buffer */
if(!u_growAnyBufferFromStatic(stackBuffer,(void**) &tempBuf, &tempBufCapacity,
count+1, count, 1)) {
goto cleanup;
}
saveBuf = tempBuf;
}
saveBuf[count]=0;
/* allocate more space than required
* here we assume that every char requires
* no more than 2 wchar_ts
*/
intTargetCapacity = (count * _BUFFER_CAPACITY_MULTIPLIER + 1) /*for null termination */;
intTarget = (wchar_t*)uprv_malloc( intTargetCapacity * sizeof(wchar_t) );
if(intTarget){
int32_t nulLen = 0;
int32_t remaining = intTargetCapacity;
wchar_t* pIntTarget=intTarget;
tempBuf = saveBuf;
/* now convert the mbs to wcs */
for(;;){
/* we can call the system API since we are sure that
* there is atleast 1 null in the input
*/
retVal = uprv_mbstowcs(pIntTarget,(tempBuf+nulLen),remaining);
if(retVal==-1){
*pErrorCode = U_INVALID_CHAR_FOUND;
break;
}else if(retVal== remaining){/* should never occur */
int numWritten = (pIntTarget-intTarget);
u_growAnyBufferFromStatic(nullptr,(void**) &intTarget,
&intTargetCapacity,
intTargetCapacity * _BUFFER_CAPACITY_MULTIPLIER,
numWritten,
sizeof(wchar_t));
pIntTarget = intTarget;
remaining=intTargetCapacity;
if(nulLen!=count){ /*there are embedded nulls*/
pIntTarget+=numWritten;
remaining-=numWritten;
}
}else{
int32_t nulVal;
/*scan for nulls */
/* we donot check for limit since tempBuf is null terminated */
while(tempBuf[nulLen++] != 0){
}
nulVal = (nulLen < srcLength) ? 1 : 0;
pIntTarget = pIntTarget + retVal+nulVal;
remaining -=(retVal+nulVal);
/* check if we have reached the source limit*/
if(nulLen>=(count)){
break;
}
}
}
count = (int32_t)(pIntTarget-intTarget);
if(0 < count && count <= destCapacity){
uprv_memcpy(dest, intTarget, (size_t)count*sizeof(wchar_t));
}
if(pDestLength){
*pDestLength = count;
}
/* free the allocated memory */
uprv_free(intTarget);
}else{
*pErrorCode = U_MEMORY_ALLOCATION_ERROR;
}
cleanup:
/* are we still using stack buffer */
if(stackBuffer != saveBuf){
uprv_free(saveBuf);
}
u_terminateWChars(dest,destCapacity,count,pErrorCode);
u_releaseDefaultConverter(conv);
return dest;
}
#endif
U_CAPI wchar_t* U_EXPORT2
u_strToWCS(wchar_t *dest,
int32_t destCapacity,
int32_t *pDestLength,
const char16_t *src,
int32_t srcLength,
UErrorCode *pErrorCode){
/* args check */
if(pErrorCode==nullptr || U_FAILURE(*pErrorCode)){
return nullptr;
}
if( (src==nullptr && srcLength!=0) || srcLength < -1 ||
(destCapacity<0) || (dest == nullptr && destCapacity > 0)
) {
*pErrorCode = U_ILLEGAL_ARGUMENT_ERROR;
return nullptr;
}
#ifdef U_WCHAR_IS_UTF16
/* wchar_t is UTF-16 just do a memcpy */
if(srcLength == -1){
srcLength = u_strlen(src);
}
if(0 < srcLength && srcLength <= destCapacity){
u_memcpy((char16_t *)dest, src, srcLength);
}
if(pDestLength){
*pDestLength = srcLength;
}
u_terminateUChars((char16_t *)dest,destCapacity,srcLength,pErrorCode);
return dest;
#elif defined U_WCHAR_IS_UTF32
return (wchar_t*)u_strToUTF32((UChar32*)dest, destCapacity, pDestLength,
src, srcLength, pErrorCode);
#else
return _strToWCS(dest,destCapacity,pDestLength,src,srcLength, pErrorCode);
#endif
}
#if !defined(U_WCHAR_IS_UTF16) && !defined(U_WCHAR_IS_UTF32)
/* helper function */
static char16_t*
_strFromWCS( char16_t *dest,
int32_t destCapacity,
int32_t *pDestLength,
const wchar_t *src,
int32_t srcLength,
UErrorCode *pErrorCode)
{
int32_t retVal =0, count =0 ;
UConverter* conv = nullptr;
char16_t* pTarget = nullptr;
char16_t* pTargetLimit = nullptr;
char16_t* target = nullptr;
char16_t uStack [_STACK_BUFFER_CAPACITY];
wchar_t wStack[_STACK_BUFFER_CAPACITY];
wchar_t* pWStack = wStack;
char cStack[_STACK_BUFFER_CAPACITY];
int32_t cStackCap = _STACK_BUFFER_CAPACITY;
char* pCSrc=cStack;
char* pCSave=pCSrc;
char* pCSrcLimit=nullptr;
const wchar_t* pSrc = src;
const wchar_t* pSrcLimit = nullptr;
if(srcLength ==-1){
/* if the wchar_t source is null terminated we can safely
* assume that there are no embedded nulls, this is a fast
* path for null terminated strings.
*/
for(;;){
/* convert wchars to chars */
retVal = uprv_wcstombs(pCSrc,src, cStackCap);
if(retVal == -1){
*pErrorCode = U_ILLEGAL_CHAR_FOUND;
goto cleanup;
}else if(retVal >= (cStackCap-1)){
/* Should rarely occur */
u_growAnyBufferFromStatic(cStack,(void**)&pCSrc,&cStackCap,
cStackCap * _BUFFER_CAPACITY_MULTIPLIER, 0, sizeof(char));
pCSave = pCSrc;
}else{
/* converted every thing */
pCSrc = pCSrc+retVal;
break;
}
}
}else{
/* here the source is not null terminated
* so it may have nulls embedded and we need to
* do some extra processing
*/
int32_t remaining =cStackCap;
pSrcLimit = src + srcLength;
for(;;){
int32_t nulLen = 0;
/* find nulls in the string */
while(nulLen<srcLength && pSrc[nulLen++]!=0){
}
if((pSrc+nulLen) < pSrcLimit){
/* check if we have enough room in pCSrc */
if(remaining < (nulLen * MB_CUR_MAX)){
/* should rarely occur */
int32_t len = (pCSrc-pCSave);
pCSrc = pCSave;
/* we do not have enough room so grow the buffer*/
u_growAnyBufferFromStatic(cStack,(void**)&pCSrc,&cStackCap,
_BUFFER_CAPACITY_MULTIPLIER*cStackCap+(nulLen*MB_CUR_MAX),len,sizeof(char));
pCSave = pCSrc;
pCSrc = pCSave+len;
remaining = cStackCap-(pCSrc - pCSave);
}
/* we have found a null so convert the
* chunk from beginning of non-null char to null
*/
retVal = uprv_wcstombs(pCSrc,pSrc,remaining);
if(retVal==-1){
/* an error occurred bail out */
*pErrorCode = U_ILLEGAL_CHAR_FOUND;
goto cleanup;
}
pCSrc += retVal+1 /* already null terminated */;
pSrc += nulLen; /* skip past the null */
srcLength-=nulLen; /* decrement the srcLength */
remaining -= (pCSrc-pCSave);
}else{
/* the source is not null terminated and we are
* end of source so we copy the source to a temp buffer
* null terminate it and convert wchar_ts to chars
*/
if(nulLen >= _STACK_BUFFER_CAPACITY){
/* Should rarely occur */
/* allocate new buffer buffer */
pWStack =(wchar_t*) uprv_malloc(sizeof(wchar_t) * (nulLen + 1));
if(pWStack==nullptr){
*pErrorCode = U_MEMORY_ALLOCATION_ERROR;
goto cleanup;
}
}
if(nulLen>0){
/* copy the contents to tempStack */
uprv_memcpy(pWStack, pSrc, (size_t)nulLen*sizeof(wchar_t));
}
/* null terminate the tempBuffer */
pWStack[nulLen] =0 ;
if(remaining < (nulLen * MB_CUR_MAX)){
/* Should rarely occur */
int32_t len = (pCSrc-pCSave);
pCSrc = pCSave;
/* we do not have enough room so grow the buffer*/
u_growAnyBufferFromStatic(cStack,(void**)&pCSrc,&cStackCap,
cStackCap+(nulLen*MB_CUR_MAX),len,sizeof(char));
pCSave = pCSrc;
pCSrc = pCSave+len;
remaining = cStackCap-(pCSrc - pCSave);
}
/* convert to chars */
retVal = uprv_wcstombs(pCSrc,pWStack,remaining);
pCSrc += retVal;
pSrc += nulLen;
srcLength-=nulLen; /* decrement the srcLength */
break;
}
}
}
/* OK..now we have converted from wchar_ts to chars now
* convert chars to UChars
*/
pCSrcLimit = pCSrc;
pCSrc = pCSave;
pTarget = target= dest;
pTargetLimit = dest + destCapacity;
conv= u_getDefaultConverter(pErrorCode);
if(U_FAILURE(*pErrorCode)|| conv==nullptr){
goto cleanup;
}
for(;;) {
*pErrorCode = U_ZERO_ERROR;
/* convert to stack buffer*/
ucnv_toUnicode(conv,&pTarget,pTargetLimit,(const char**)&pCSrc,pCSrcLimit,nullptr,(UBool)(pCSrc==pCSrcLimit),pErrorCode);
/* increment count to number written to stack */
count+= pTarget - target;
if(*pErrorCode==U_BUFFER_OVERFLOW_ERROR){
target = uStack;
pTarget = uStack;
pTargetLimit = uStack + _STACK_BUFFER_CAPACITY;
} else {
break;
}
}
if(pDestLength){
*pDestLength =count;
}
u_terminateUChars(dest,destCapacity,count,pErrorCode);
cleanup:
if(cStack != pCSave){
uprv_free(pCSave);
}
if(wStack != pWStack){
uprv_free(pWStack);
}
u_releaseDefaultConverter(conv);
return dest;
}
#endif
U_CAPI char16_t* U_EXPORT2
u_strFromWCS(char16_t *dest,
int32_t destCapacity,
int32_t *pDestLength,
const wchar_t *src,
int32_t srcLength,
UErrorCode *pErrorCode)
{
/* args check */
if(pErrorCode==nullptr || U_FAILURE(*pErrorCode)){
return nullptr;
}
if( (src==nullptr && srcLength!=0) || srcLength < -1 ||
(destCapacity<0) || (dest == nullptr && destCapacity > 0)
) {
*pErrorCode = U_ILLEGAL_ARGUMENT_ERROR;
return nullptr;
}
#ifdef U_WCHAR_IS_UTF16
/* wchar_t is UTF-16 just do a memcpy */
if(srcLength == -1){
srcLength = u_strlen((const char16_t *)src);
}
if(0 < srcLength && srcLength <= destCapacity){
u_memcpy(dest, (const char16_t *)src, srcLength);
}
if(pDestLength){
*pDestLength = srcLength;
}
u_terminateUChars(dest,destCapacity,srcLength,pErrorCode);
return dest;
#elif defined U_WCHAR_IS_UTF32
return u_strFromUTF32(dest, destCapacity, pDestLength,
(UChar32*)src, srcLength, pErrorCode);
#else
return _strFromWCS(dest,destCapacity,pDestLength,src,srcLength,pErrorCode);
#endif
}
#endif /* #if !defined(U_WCHAR_IS_UTF16) && !defined(U_WCHAR_IS_UTF32) && !UCONFIG_NO_CONVERSION */
|