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
536
537
538
539
540
541
542
543
544
545
546
547
548
549
550
551
552
553
554
555
556
557
558
559
560
561
562
563
564
565
566
567
568
569
570
571
572
573
574
575
576
577
578
579
580
581
582
583
584
585
586
587
588
589
590
591
592
593
594
595
596
597
598
599
600
601
602
603
604
605
606
607
608
609
610
611
612
613
614
615
616
617
618
619
620
621
622
623
624
625
626
627
628
629
630
631
632
633
634
635
636
637
638
639
640
641
642
643
644
645
646
647
648
649
650
651
652
653
654
655
656
657
658
659
660
661
662
663
664
665
666
667
668
669
670
671
672
673
674
675
676
677
678
679
680
681
682
683
684
685
686
687
688
689
690
691
692
693
694
695
696
697
698
699
700
701
702
703
704
705
706
707
708
709
710
711
712
713
714
715
716
717
718
719
720
721
722
723
724
725
726
727
728
729
730
731
732
733
734
735
736
737
738
739
740
741
742
743
744
745
746
747
748
749
750
751
752
753
754
755
756
757
758
759
760
761
762
763
764
765
766
767
768
769
770
771
772
773
774
775
776
777
778
779
780
781
782
783
784
785
786
787
788
|
// Copyright (C) 2016 and later: Unicode, Inc. and others.
// License & terms of use: http://www.unicode.org/copyright.html
/*
*******************************************************************************
*
* Copyright (C) 1998-2016, International Business Machines
* Corporation and others. All Rights Reserved.
*
*******************************************************************************
*
* File ucbuf.cpp
*
* Modification History:
*
* Date Name Description
* 05/10/01 Ram Creation.
*******************************************************************************
*/
#include "unicode/utypes.h"
#include "unicode/putil.h"
#include "unicode/uchar.h"
#include "unicode/ucnv.h"
#include "unicode/ucnv_err.h"
#include "unicode/ustring.h"
#include "unicode/utf16.h"
#include "filestrm.h"
#include "cstring.h"
#include "cmemory.h"
#include "ustrfmt.h"
#include "ucbuf.h"
#include <stdio.h>
#if !UCONFIG_NO_CONVERSION
#define MAX_IN_BUF 1000
#define MAX_U_BUF 1500
#define CONTEXT_LEN 20
struct UCHARBUF {
UChar* buffer;
UChar* currentPos;
UChar* bufLimit;
int32_t bufCapacity;
int32_t remaining;
int32_t signatureLength;
FileStream* in;
UConverter* conv;
UBool showWarning; /* makes this API not produce any errors */
UBool isBuffered;
};
U_CAPI UBool U_EXPORT2
ucbuf_autodetect_fs(FileStream* in, const char** cp, UConverter** conv, int32_t* signatureLength, UErrorCode* error){
char start[8];
int32_t numRead;
UChar target[1]={ 0 };
UChar* pTarget;
const char* pStart;
/* read a few bytes */
numRead=T_FileStream_read(in, start, sizeof(start));
*cp = ucnv_detectUnicodeSignature(start, numRead, signatureLength, error);
/* unread the bytes beyond what was consumed for U+FEFF */
T_FileStream_rewind(in);
if (*signatureLength > 0) {
T_FileStream_read(in, start, *signatureLength);
}
if(*cp==NULL){
*conv =NULL;
return FALSE;
}
/* open the converter for the detected Unicode charset */
*conv = ucnv_open(*cp,error);
/* convert and ignore initial U+FEFF, and the buffer overflow */
pTarget = target;
pStart = start;
ucnv_toUnicode(*conv, &pTarget, target+1, &pStart, start+*signatureLength, NULL, FALSE, error);
*signatureLength = (int32_t)(pStart - start);
if(*error==U_BUFFER_OVERFLOW_ERROR) {
*error=U_ZERO_ERROR;
}
/* verify that we successfully read exactly U+FEFF */
if(U_SUCCESS(*error) && (pTarget!=(target+1) || target[0]!=0xfeff)) {
*error=U_INTERNAL_PROGRAM_ERROR;
}
return TRUE;
}
static UBool ucbuf_isCPKnown(const char* cp){
if(ucnv_compareNames("UTF-8",cp)==0){
return TRUE;
}
if(ucnv_compareNames("UTF-16BE",cp)==0){
return TRUE;
}
if(ucnv_compareNames("UTF-16LE",cp)==0){
return TRUE;
}
if(ucnv_compareNames("UTF-16",cp)==0){
return TRUE;
}
if(ucnv_compareNames("UTF-32",cp)==0){
return TRUE;
}
if(ucnv_compareNames("UTF-32BE",cp)==0){
return TRUE;
}
if(ucnv_compareNames("UTF-32LE",cp)==0){
return TRUE;
}
if(ucnv_compareNames("SCSU",cp)==0){
return TRUE;
}
if(ucnv_compareNames("BOCU-1",cp)==0){
return TRUE;
}
if(ucnv_compareNames("UTF-7",cp)==0){
return TRUE;
}
return FALSE;
}
U_CAPI FileStream * U_EXPORT2
ucbuf_autodetect(const char* fileName, const char** cp,UConverter** conv, int32_t* signatureLength,UErrorCode* error){
FileStream* in=NULL;
if(error==NULL || U_FAILURE(*error)){
return NULL;
}
if(conv==NULL || cp==NULL || fileName==NULL){
*error = U_ILLEGAL_ARGUMENT_ERROR;
return NULL;
}
/* open the file */
in= T_FileStream_open(fileName,"rb");
if(in == NULL){
*error=U_FILE_ACCESS_ERROR;
return NULL;
}
if(ucbuf_autodetect_fs(in,cp,conv,signatureLength,error)) {
return in;
} else {
ucnv_close(*conv);
*conv=NULL;
T_FileStream_close(in);
return NULL;
}
}
/* fill the uchar buffer */
static UCHARBUF*
ucbuf_fillucbuf( UCHARBUF* buf,UErrorCode* error){
UChar* pTarget=NULL;
UChar* target=NULL;
const char* source=NULL;
char carr[MAX_IN_BUF] = {'\0'};
char* cbuf = carr;
int32_t inputRead=0;
int32_t outputWritten=0;
int32_t offset=0;
const char* sourceLimit =NULL;
int32_t cbufSize=0;
pTarget = buf->buffer;
/* check if we arrived here without exhausting the buffer*/
if(buf->currentPos<buf->bufLimit){
offset = (int32_t)(buf->bufLimit-buf->currentPos);
memmove(buf->buffer,buf->currentPos,offset* sizeof(UChar));
}
#if UCBUF_DEBUG
memset(pTarget+offset,0xff,sizeof(UChar)*(MAX_IN_BUF-offset));
#endif
if(buf->isBuffered){
cbufSize = MAX_IN_BUF;
/* read the file */
inputRead=T_FileStream_read(buf->in,cbuf,cbufSize-offset);
buf->remaining-=inputRead;
}else{
cbufSize = T_FileStream_size(buf->in);
cbuf = (char*)uprv_malloc(cbufSize);
if (cbuf == NULL) {
*error = U_MEMORY_ALLOCATION_ERROR;
return NULL;
}
inputRead= T_FileStream_read(buf->in,cbuf,cbufSize);
buf->remaining-=inputRead;
}
/* just to be sure...*/
if ( 0 == inputRead )
buf->remaining = 0;
target=pTarget;
/* convert the bytes */
if(buf->conv){
/* set the callback to stop */
UConverterToUCallback toUOldAction ;
void* toUOldContext;
void* toUNewContext=NULL;
ucnv_setToUCallBack(buf->conv,
UCNV_TO_U_CALLBACK_STOP,
toUNewContext,
&toUOldAction,
(const void**)&toUOldContext,
error);
/* since state is saved in the converter we add offset to source*/
target = pTarget+offset;
source = cbuf;
sourceLimit = source + inputRead;
ucnv_toUnicode(buf->conv,&target,target+(buf->bufCapacity-offset),
&source,sourceLimit,NULL,
(UBool)(buf->remaining==0),error);
if(U_FAILURE(*error)){
char context[CONTEXT_LEN+1];
char preContext[CONTEXT_LEN+1];
char postContext[CONTEXT_LEN+1];
int8_t len = CONTEXT_LEN;
int32_t start=0;
int32_t stop =0;
int32_t pos =0;
/* use erro1 to preserve the error code */
UErrorCode error1 =U_ZERO_ERROR;
if( buf->showWarning==TRUE){
fprintf(stderr,"\n###WARNING: Encountered abnormal bytes while"
" converting input stream to target encoding: %s\n",
u_errorName(*error));
}
/* now get the context chars */
ucnv_getInvalidChars(buf->conv,context,&len,&error1);
context[len]= 0 ; /* null terminate the buffer */
pos = (int32_t)(source - cbuf - len);
/* for pre-context */
start = (pos <=CONTEXT_LEN)? 0 : (pos - (CONTEXT_LEN-1));
stop = pos-len;
memcpy(preContext,cbuf+start,stop-start);
/* null terminate the buffer */
preContext[stop-start] = 0;
/* for post-context */
start = pos+len;
stop = (int32_t)(((pos+CONTEXT_LEN)<= (sourceLimit-cbuf) )? (pos+(CONTEXT_LEN-1)) : (sourceLimit-cbuf));
memcpy(postContext,source,stop-start);
/* null terminate the buffer */
postContext[stop-start] = 0;
if(buf->showWarning ==TRUE){
/* print out the context */
fprintf(stderr,"\tPre-context: %s\n",preContext);
fprintf(stderr,"\tContext: %s\n",context);
fprintf(stderr,"\tPost-context: %s\n", postContext);
}
/* reset the converter */
ucnv_reset(buf->conv);
/* set the call back to substitute
* and restart conversion
*/
ucnv_setToUCallBack(buf->conv,
UCNV_TO_U_CALLBACK_SUBSTITUTE,
toUNewContext,
&toUOldAction,
(const void**)&toUOldContext,
&error1);
/* reset source and target start positions */
target = pTarget+offset;
source = cbuf;
/* re convert */
ucnv_toUnicode(buf->conv,&target,target+(buf->bufCapacity-offset),
&source,sourceLimit,NULL,
(UBool)(buf->remaining==0),&error1);
}
outputWritten = (int32_t)(target - pTarget);
#if UCBUF_DEBUG
{
int i;
target = pTarget;
for(i=0;i<numRead;i++){
/* printf("%c", (char)(*target++));*/
}
}
#endif
}else{
u_charsToUChars(cbuf,target+offset,inputRead);
outputWritten=((buf->remaining>cbufSize)? cbufSize:inputRead+offset);
}
buf->currentPos = pTarget;
buf->bufLimit=pTarget+outputWritten;
*buf->bufLimit=0; /*NUL terminate*/
if(cbuf!=carr){
uprv_free(cbuf);
}
return buf;
}
/* get a UChar from the stream*/
U_CAPI int32_t U_EXPORT2
ucbuf_getc(UCHARBUF* buf,UErrorCode* error){
if(error==NULL || U_FAILURE(*error)){
return FALSE;
}
if(buf->currentPos>=buf->bufLimit){
if(buf->remaining==0){
return U_EOF;
}
buf=ucbuf_fillucbuf(buf,error);
if(U_FAILURE(*error)){
return U_EOF;
}
}
return *(buf->currentPos++);
}
/* get a UChar32 from the stream*/
U_CAPI int32_t U_EXPORT2
ucbuf_getc32(UCHARBUF* buf,UErrorCode* error){
int32_t retVal = (int32_t)U_EOF;
if(error==NULL || U_FAILURE(*error)){
return FALSE;
}
if(buf->currentPos+1>=buf->bufLimit){
if(buf->remaining==0){
return U_EOF;
}
buf=ucbuf_fillucbuf(buf,error);
if(U_FAILURE(*error)){
return U_EOF;
}
}
if(U16_IS_LEAD(*(buf->currentPos))){
retVal=U16_GET_SUPPLEMENTARY(buf->currentPos[0],buf->currentPos[1]);
buf->currentPos+=2;
}else{
retVal = *(buf->currentPos++);
}
return retVal;
}
/* u_unescapeAt() callback to return a UChar*/
static UChar U_CALLCONV
_charAt(int32_t offset, void *context) {
return ((UCHARBUF*) context)->currentPos[offset];
}
/* getc and escape it */
U_CAPI int32_t U_EXPORT2
ucbuf_getcx32(UCHARBUF* buf,UErrorCode* error) {
int32_t length;
int32_t offset;
UChar32 c32,c1,c2;
if(error==NULL || U_FAILURE(*error)){
return FALSE;
}
/* Fill the buffer if it is empty */
if (buf->currentPos >=buf->bufLimit-2) {
ucbuf_fillucbuf(buf,error);
}
/* Get the next character in the buffer */
if (buf->currentPos < buf->bufLimit) {
c1 = *(buf->currentPos)++;
} else {
c1 = U_EOF;
}
c2 = *(buf->currentPos);
/* If it isn't a backslash, return it */
if (c1 != 0x005C) {
return c1;
}
/* Determine the amount of data in the buffer */
length = (int32_t)(buf->bufLimit - buf->currentPos);
/* The longest escape sequence is \Uhhhhhhhh; make sure
we have at least that many characters */
if (length < 10) {
/* fill the buffer */
ucbuf_fillucbuf(buf,error);
length = (int32_t)(buf->bufLimit - buf->buffer);
}
/* Process the escape */
offset = 0;
c32 = u_unescapeAt(_charAt, &offset, length, (void*)buf);
/* check if u_unescapeAt unescaped and converted
* to c32 or not
*/
if(c32==(UChar32)0xFFFFFFFF){
if(buf->showWarning) {
char context[CONTEXT_LEN+1];
int32_t len = CONTEXT_LEN;
if(length < len) {
len = length;
}
context[len]= 0 ; /* null terminate the buffer */
u_UCharsToChars( buf->currentPos, context, len);
fprintf(stderr,"Bad escape: [%c%s]...\n", (int)c1, context);
}
*error= U_ILLEGAL_ESCAPE_SEQUENCE;
return c1;
}else if(c32!=c2 || (c32==0x0075 && c2==0x0075 && c1==0x005C) /* for \u0075 c2=0x0075 and c32==0x0075*/){
/* Update the current buffer position */
buf->currentPos += offset;
}else{
/* unescaping failed so we just return
* c1 and not consume the buffer
* this is useful for rules with escapes
* in resouce bundles
* eg: \' \\ \"
*/
return c1;
}
return c32;
}
U_CAPI UCHARBUF* U_EXPORT2
ucbuf_open(const char* fileName,const char** cp,UBool showWarning, UBool buffered, UErrorCode* error){
FileStream* in = NULL;
int32_t fileSize=0;
const char* knownCp;
if(error==NULL || U_FAILURE(*error)){
return NULL;
}
if(cp==NULL || fileName==NULL){
*error = U_ILLEGAL_ARGUMENT_ERROR;
return FALSE;
}
if (!uprv_strcmp(fileName, "-")) {
in = T_FileStream_stdin();
}else{
in = T_FileStream_open(fileName, "rb");
}
if(in!=NULL){
UCHARBUF* buf =(UCHARBUF*) uprv_malloc(sizeof(UCHARBUF));
fileSize = T_FileStream_size(in);
if(buf == NULL){
*error = U_MEMORY_ALLOCATION_ERROR;
T_FileStream_close(in);
return NULL;
}
buf->in=in;
buf->conv=NULL;
buf->showWarning = showWarning;
buf->isBuffered = buffered;
buf->signatureLength=0;
if(*cp==NULL || **cp=='\0'){
/* don't have code page name... try to autodetect */
ucbuf_autodetect_fs(in,cp,&buf->conv,&buf->signatureLength,error);
}else if(ucbuf_isCPKnown(*cp)){
/* discard BOM */
ucbuf_autodetect_fs(in,&knownCp,&buf->conv,&buf->signatureLength,error);
}
if(U_SUCCESS(*error) && buf->conv==NULL) {
buf->conv=ucnv_open(*cp,error);
}
if(U_FAILURE(*error)){
ucnv_close(buf->conv);
uprv_free(buf);
T_FileStream_close(in);
return NULL;
}
if((buf->conv==NULL) && (buf->showWarning==TRUE)){
fprintf(stderr,"###WARNING: No converter defined. Using codepage of system.\n");
}
buf->remaining=fileSize-buf->signatureLength;
if(buf->isBuffered){
buf->bufCapacity=MAX_U_BUF;
}else{
buf->bufCapacity=buf->remaining+buf->signatureLength+1/*for terminating nul*/;
}
buf->buffer=(UChar*) uprv_malloc(U_SIZEOF_UCHAR * buf->bufCapacity );
if (buf->buffer == NULL) {
*error = U_MEMORY_ALLOCATION_ERROR;
ucbuf_close(buf);
return NULL;
}
buf->currentPos=buf->buffer;
buf->bufLimit=buf->buffer;
if(U_FAILURE(*error)){
fprintf(stderr, "Could not open codepage [%s]: %s\n", *cp, u_errorName(*error));
ucbuf_close(buf);
return NULL;
}
ucbuf_fillucbuf(buf,error);
if(U_FAILURE(*error)){
ucbuf_close(buf);
return NULL;
}
return buf;
}
*error =U_FILE_ACCESS_ERROR;
return NULL;
}
/* TODO: this method will fail if at the
* begining of buffer and the uchar to unget
* is from the previous buffer. Need to implement
* system to take care of that situation.
*/
U_CAPI void U_EXPORT2
ucbuf_ungetc(int32_t c,UCHARBUF* buf){
/* decrement currentPos pointer
* if not at the begining of buffer
*/
if(buf->currentPos!=buf->buffer){
if(*(buf->currentPos-1)==c){
buf->currentPos--;
} else {
/* ungetc failed - did not match. */
}
} else {
/* ungetc failed - beginning of buffer. */
}
}
/* frees the resources of UChar* buffer */
static void
ucbuf_closebuf(UCHARBUF* buf){
uprv_free(buf->buffer);
buf->buffer = NULL;
}
/* close the buf and release resources*/
U_CAPI void U_EXPORT2
ucbuf_close(UCHARBUF* buf){
if(buf!=NULL){
if(buf->conv){
ucnv_close(buf->conv);
}
T_FileStream_close(buf->in);
ucbuf_closebuf(buf);
uprv_free(buf);
}
}
/* rewind the buf and file stream */
U_CAPI void U_EXPORT2
ucbuf_rewind(UCHARBUF* buf,UErrorCode* error){
if(error==NULL || U_FAILURE(*error)){
return;
}
if(buf){
buf->currentPos=buf->buffer;
buf->bufLimit=buf->buffer;
T_FileStream_rewind(buf->in);
buf->remaining=T_FileStream_size(buf->in)-buf->signatureLength;
ucnv_resetToUnicode(buf->conv);
if(buf->signatureLength>0) {
UChar target[1]={ 0 };
UChar* pTarget;
char start[8];
const char* pStart;
int32_t numRead;
/* read the signature bytes */
numRead=T_FileStream_read(buf->in, start, buf->signatureLength);
/* convert and ignore initial U+FEFF, and the buffer overflow */
pTarget = target;
pStart = start;
ucnv_toUnicode(buf->conv, &pTarget, target+1, &pStart, start+numRead, NULL, FALSE, error);
if(*error==U_BUFFER_OVERFLOW_ERROR) {
*error=U_ZERO_ERROR;
}
/* verify that we successfully read exactly U+FEFF */
if(U_SUCCESS(*error) && (numRead!=buf->signatureLength || pTarget!=(target+1) || target[0]!=0xfeff)) {
*error=U_INTERNAL_PROGRAM_ERROR;
}
}
}
}
U_CAPI int32_t U_EXPORT2
ucbuf_size(UCHARBUF* buf){
if(buf){
if(buf->isBuffered){
return (T_FileStream_size(buf->in)-buf->signatureLength)/ucnv_getMinCharSize(buf->conv);
}else{
return (int32_t)(buf->bufLimit - buf->buffer);
}
}
return 0;
}
U_CAPI const UChar* U_EXPORT2
ucbuf_getBuffer(UCHARBUF* buf,int32_t* len,UErrorCode* error){
if(error==NULL || U_FAILURE(*error)){
return NULL;
}
if(buf==NULL || len==NULL){
*error = U_ILLEGAL_ARGUMENT_ERROR;
return NULL;
}
*len = (int32_t)(buf->bufLimit - buf->buffer);
return buf->buffer;
}
U_CAPI const char* U_EXPORT2
ucbuf_resolveFileName(const char* inputDir, const char* fileName, char* target, int32_t* len, UErrorCode* status){
int32_t requiredLen = 0;
int32_t dirlen = 0;
int32_t filelen = 0;
if(status==NULL || U_FAILURE(*status)){
return NULL;
}
if(inputDir == NULL || fileName == NULL || len==NULL || (target==NULL && *len>0)){
*status = U_ILLEGAL_ARGUMENT_ERROR;
return NULL;
}
dirlen = (int32_t)uprv_strlen(inputDir);
filelen = (int32_t)uprv_strlen(fileName);
if(inputDir[dirlen-1] != U_FILE_SEP_CHAR) {
requiredLen = dirlen + filelen + 2;
if((*len < requiredLen) || target==NULL){
*len = requiredLen;
*status = U_BUFFER_OVERFLOW_ERROR;
return NULL;
}
target[0] = '\0';
/*
* append the input dir to openFileName if the first char in
* filename is not file seperation char and the last char input directory is not '.'.
* This is to support :
* genrb -s. /home/icu/data
* genrb -s. icu/data
* The user cannot mix notations like
* genrb -s. /icu/data --- the absolute path specified. -s redundant
* user should use
* genrb -s. icu/data --- start from CWD and look in icu/data dir
*/
if( (fileName[0] != U_FILE_SEP_CHAR) && (inputDir[dirlen-1] !='.')){
uprv_strcpy(target, inputDir);
target[dirlen] = U_FILE_SEP_CHAR;
}
target[dirlen + 1] = '\0';
} else {
requiredLen = dirlen + filelen + 1;
if((*len < requiredLen) || target==NULL){
*len = requiredLen;
*status = U_BUFFER_OVERFLOW_ERROR;
return NULL;
}
uprv_strcpy(target, inputDir);
}
uprv_strcat(target, fileName);
return target;
}
/*
* Unicode TR 13 says any of the below chars is
* a new line char in a readline function in addition
* to CR+LF combination which needs to be
* handled seperately
*/
static UBool ucbuf_isCharNewLine(UChar c){
switch(c){
case 0x000A: /* LF */
case 0x000D: /* CR */
case 0x000C: /* FF */
case 0x0085: /* NEL */
case 0x2028: /* LS */
case 0x2029: /* PS */
return TRUE;
default:
return FALSE;
}
}
U_CAPI const UChar* U_EXPORT2
ucbuf_readline(UCHARBUF* buf,int32_t* len,UErrorCode* err){
UChar* temp = buf->currentPos;
UChar* savePos =NULL;
UChar c=0x0000;
if(buf->isBuffered){
/* The input is buffered we have to do more
* for returning a pointer U_TRUNCATED_CHAR_FOUND
*/
for(;;){
c = *temp++;
if(buf->remaining==0){
return NULL; /* end of file is reached return NULL */
}
if(temp>=buf->bufLimit && buf->currentPos == buf->buffer){
*err= U_TRUNCATED_CHAR_FOUND;
return NULL;
}else{
ucbuf_fillucbuf(buf,err);
if(U_FAILURE(*err)){
return NULL;
}
}
/*
* Accoding to TR 13 readLine functions must interpret
* CR, CR+LF, LF, NEL, PS, LS or FF as line seperators
*/
/* Windows CR LF */
if(c ==0x0d && temp <= buf->bufLimit && *temp == 0x0a ){
*len = (int32_t)(temp++ - buf->currentPos);
savePos = buf->currentPos;
buf->currentPos = temp;
return savePos;
}
/* else */
if (temp>=buf->bufLimit|| ucbuf_isCharNewLine(c)){ /* Unipad inserts 2028 line separators! */
*len = (int32_t)(temp - buf->currentPos);
savePos = buf->currentPos;
buf->currentPos = temp;
return savePos;
}
}
}else{
/* we know that all input is read into the internal
* buffer so we can safely return pointers
*/
for(;;){
c = *temp++;
if(buf->currentPos==buf->bufLimit){
return NULL; /* end of file is reached return NULL */
}
/* Windows CR LF */
if(c ==0x0d && temp <= buf->bufLimit && *temp == 0x0a ){
*len = (int32_t)(temp++ - buf->currentPos);
savePos = buf->currentPos;
buf->currentPos = temp;
return savePos;
}
/* else */
if (temp>=buf->bufLimit|| ucbuf_isCharNewLine(c)) { /* Unipad inserts 2028 line separators! */
*len = (int32_t)(temp - buf->currentPos);
savePos = buf->currentPos;
buf->currentPos = temp;
return savePos;
}
}
}
/* not reached */
/* A compiler warning will appear if all paths don't contain a return statement. */
/* return NULL;*/
}
#endif
|