Coverage Report

Created: 2025-08-29 06:41

/src/libxml2/parser.c
Line
Count
Source (jump to first uncovered line)
1
/*
2
 * parser.c : an XML 1.0 parser, namespaces and validity support are mostly
3
 *            implemented on top of the SAX interfaces
4
 *
5
 * References:
6
 *   The XML specification:
7
 *     http://www.w3.org/TR/REC-xml
8
 *   Original 1.0 version:
9
 *     http://www.w3.org/TR/1998/REC-xml-19980210
10
 *   XML second edition working draft
11
 *     http://www.w3.org/TR/2000/WD-xml-2e-20000814
12
 *
13
 * Okay this is a big file, the parser core is around 7000 lines, then it
14
 * is followed by the progressive parser top routines, then the various
15
 * high level APIs to call the parser and a few miscellaneous functions.
16
 * A number of helper functions and deprecated ones have been moved to
17
 * parserInternals.c to reduce this file size.
18
 * As much as possible the functions are associated with their relative
19
 * production in the XML specification. A few productions defining the
20
 * different ranges of character are actually implanted either in
21
 * parserInternals.h or parserInternals.c
22
 * The DOM tree build is realized from the default SAX callbacks in
23
 * the module SAX2.c.
24
 * The routines doing the validation checks are in valid.c and called either
25
 * from the SAX callbacks or as standalone functions using a preparsed
26
 * document.
27
 *
28
 * See Copyright for the status of this software.
29
 *
30
 * daniel@veillard.com
31
 */
32
33
/* To avoid EBCDIC trouble when parsing on zOS */
34
#if defined(__MVS__)
35
#pragma convert("ISO8859-1")
36
#endif
37
38
#define IN_LIBXML
39
#include "libxml.h"
40
41
#if defined(_WIN32)
42
#define XML_DIR_SEP '\\'
43
#else
44
#define XML_DIR_SEP '/'
45
#endif
46
47
#include <stdlib.h>
48
#include <limits.h>
49
#include <string.h>
50
#include <stdarg.h>
51
#include <stddef.h>
52
#include <ctype.h>
53
#include <stdlib.h>
54
#include <libxml/parser.h>
55
#include <libxml/xmlmemory.h>
56
#include <libxml/tree.h>
57
#include <libxml/parserInternals.h>
58
#include <libxml/valid.h>
59
#include <libxml/entities.h>
60
#include <libxml/xmlerror.h>
61
#include <libxml/encoding.h>
62
#include <libxml/xmlIO.h>
63
#include <libxml/uri.h>
64
#include <libxml/SAX2.h>
65
#include <libxml/HTMLparser.h>
66
#ifdef LIBXML_CATALOG_ENABLED
67
#include <libxml/catalog.h>
68
#endif
69
70
#include "private/buf.h"
71
#include "private/dict.h"
72
#include "private/entities.h"
73
#include "private/error.h"
74
#include "private/html.h"
75
#include "private/io.h"
76
#include "private/memory.h"
77
#include "private/parser.h"
78
79
43.7k
#define NS_INDEX_EMPTY  INT_MAX
80
27.8k
#define NS_INDEX_XML    (INT_MAX - 1)
81
3.42k
#define URI_HASH_EMPTY  0xD943A04E
82
4.07k
#define URI_HASH_XML    0xF0451F02
83
84
#ifndef STDIN_FILENO
85
0
  #define STDIN_FILENO 0
86
#endif
87
88
#ifndef SIZE_MAX
89
  #define SIZE_MAX ((size_t) -1)
90
#endif
91
92
629
#define XML_MAX_ATTRS 100000000 /* 100 million */
93
94
struct _xmlStartTag {
95
    const xmlChar *prefix;
96
    const xmlChar *URI;
97
    int line;
98
    int nsNr;
99
};
100
101
typedef struct {
102
    void *saxData;
103
    unsigned prefixHashValue;
104
    unsigned uriHashValue;
105
    unsigned elementId;
106
    int oldIndex;
107
} xmlParserNsExtra;
108
109
typedef struct {
110
    unsigned hashValue;
111
    int index;
112
} xmlParserNsBucket;
113
114
struct _xmlParserNsData {
115
    xmlParserNsExtra *extra;
116
117
    unsigned hashSize;
118
    unsigned hashElems;
119
    xmlParserNsBucket *hash;
120
121
    unsigned elementId;
122
    int defaultNsIndex;
123
    int minNsIndex;
124
};
125
126
static int
127
xmlParseElementStart(xmlParserCtxtPtr ctxt);
128
129
static void
130
xmlParseElementEnd(xmlParserCtxtPtr ctxt);
131
132
static xmlEntityPtr
133
xmlLookupGeneralEntity(xmlParserCtxtPtr ctxt, const xmlChar *name, int inAttr);
134
135
static const xmlChar *
136
xmlParseEntityRefInternal(xmlParserCtxtPtr ctxt);
137
138
/************************************************************************
139
 *                  *
140
 *  Arbitrary limits set in the parser. See XML_PARSE_HUGE    *
141
 *                  *
142
 ************************************************************************/
143
144
#define XML_PARSER_BIG_ENTITY 1000
145
#define XML_PARSER_LOT_ENTITY 5000
146
147
/*
148
 * Constants for protection against abusive entity expansion
149
 * ("billion laughs").
150
 */
151
152
/*
153
 * A certain amount of entity expansion which is always allowed.
154
 */
155
20.2k
#define XML_PARSER_ALLOWED_EXPANSION 1000000
156
157
/*
158
 * Fixed cost for each entity reference. This crudely models processing time
159
 * as well to protect, for example, against exponential expansion of empty
160
 * or very short entities.
161
 */
162
33.3k
#define XML_ENT_FIXED_COST 20
163
164
46.8M
#define XML_PARSER_BIG_BUFFER_SIZE 300
165
40.0k
#define XML_PARSER_BUFFER_SIZE 100
166
17.4k
#define SAX_COMPAT_MODE BAD_CAST "SAX compatibility mode document"
167
168
/**
169
 * XML_PARSER_CHUNK_SIZE
170
 *
171
 * When calling GROW that's the minimal amount of data
172
 * the parser expected to have received. It is not a hard
173
 * limit but an optimization when reading strings like Names
174
 * It is not strictly needed as long as inputs available characters
175
 * are followed by 0, which should be provided by the I/O level
176
 */
177
#define XML_PARSER_CHUNK_SIZE 100
178
179
/**
180
 * xmlParserVersion:
181
 *
182
 * Constant string describing the internal version of the library
183
 */
184
const char *const
185
xmlParserVersion = LIBXML_VERSION_STRING LIBXML_VERSION_EXTRA;
186
187
/*
188
 * List of XML prefixed PI allowed by W3C specs
189
 */
190
191
static const char* const xmlW3CPIs[] = {
192
    "xml-stylesheet",
193
    "xml-model",
194
    NULL
195
};
196
197
198
/* DEPR void xmlParserHandleReference(xmlParserCtxtPtr ctxt); */
199
static xmlEntityPtr xmlParseStringPEReference(xmlParserCtxtPtr ctxt,
200
                                              const xmlChar **str);
201
202
static void
203
xmlCtxtParseEntity(xmlParserCtxtPtr ctxt, xmlEntityPtr ent);
204
205
static int
206
xmlLoadEntityContent(xmlParserCtxtPtr ctxt, xmlEntityPtr entity);
207
208
/************************************************************************
209
 *                  *
210
 *    Some factorized error routines        *
211
 *                  *
212
 ************************************************************************/
213
214
static void
215
0
xmlErrMemory(xmlParserCtxtPtr ctxt) {
216
0
    xmlCtxtErrMemory(ctxt);
217
0
}
218
219
/**
220
 * xmlErrAttributeDup:
221
 * @ctxt:  an XML parser context
222
 * @prefix:  the attribute prefix
223
 * @localname:  the attribute localname
224
 *
225
 * Handle a redefinition of attribute error
226
 */
227
static void
228
xmlErrAttributeDup(xmlParserCtxtPtr ctxt, const xmlChar * prefix,
229
                   const xmlChar * localname)
230
6.10k
{
231
6.10k
    if (prefix == NULL)
232
396
        xmlCtxtErr(ctxt, NULL, XML_FROM_PARSER, XML_ERR_ATTRIBUTE_REDEFINED,
233
396
                   XML_ERR_FATAL, localname, NULL, NULL, 0,
234
396
                   "Attribute %s redefined\n", localname);
235
5.70k
    else
236
5.70k
        xmlCtxtErr(ctxt, NULL, XML_FROM_PARSER, XML_ERR_ATTRIBUTE_REDEFINED,
237
5.70k
                   XML_ERR_FATAL, prefix, localname, NULL, 0,
238
5.70k
                   "Attribute %s:%s redefined\n", prefix, localname);
239
6.10k
}
240
241
/**
242
 * xmlFatalErrMsg:
243
 * @ctxt:  an XML parser context
244
 * @error:  the error number
245
 * @msg:  the error message
246
 *
247
 * Handle a fatal parser error, i.e. violating Well-Formedness constraints
248
 */
249
static void LIBXML_ATTR_FORMAT(3,0)
250
xmlFatalErrMsg(xmlParserCtxtPtr ctxt, xmlParserErrors error,
251
               const char *msg)
252
20.7M
{
253
20.7M
    xmlCtxtErr(ctxt, NULL, XML_FROM_PARSER, error, XML_ERR_FATAL,
254
20.7M
               NULL, NULL, NULL, 0, "%s", msg);
255
20.7M
}
256
257
/**
258
 * xmlWarningMsg:
259
 * @ctxt:  an XML parser context
260
 * @error:  the error number
261
 * @msg:  the error message
262
 * @str1:  extra data
263
 * @str2:  extra data
264
 *
265
 * Handle a warning.
266
 */
267
void LIBXML_ATTR_FORMAT(3,0)
268
xmlWarningMsg(xmlParserCtxtPtr ctxt, xmlParserErrors error,
269
              const char *msg, const xmlChar *str1, const xmlChar *str2)
270
1.20k
{
271
1.20k
    xmlCtxtErr(ctxt, NULL, XML_FROM_PARSER, error, XML_ERR_WARNING,
272
1.20k
               str1, str2, NULL, 0, msg, str1, str2);
273
1.20k
}
274
275
/**
276
 * xmlValidityError:
277
 * @ctxt:  an XML parser context
278
 * @error:  the error number
279
 * @msg:  the error message
280
 * @str1:  extra data
281
 *
282
 * Handle a validity error.
283
 */
284
static void LIBXML_ATTR_FORMAT(3,0)
285
xmlValidityError(xmlParserCtxtPtr ctxt, xmlParserErrors error,
286
              const char *msg, const xmlChar *str1, const xmlChar *str2)
287
0
{
288
0
    ctxt->valid = 0;
289
290
0
    xmlCtxtErr(ctxt, NULL, XML_FROM_DTD, error, XML_ERR_ERROR,
291
0
               str1, str2, NULL, 0, msg, str1, str2);
292
0
}
293
294
/**
295
 * xmlFatalErrMsgInt:
296
 * @ctxt:  an XML parser context
297
 * @error:  the error number
298
 * @msg:  the error message
299
 * @val:  an integer value
300
 *
301
 * Handle a fatal parser error, i.e. violating Well-Formedness constraints
302
 */
303
static void LIBXML_ATTR_FORMAT(3,0)
304
xmlFatalErrMsgInt(xmlParserCtxtPtr ctxt, xmlParserErrors error,
305
                  const char *msg, int val)
306
1.58M
{
307
1.58M
    xmlCtxtErr(ctxt, NULL, XML_FROM_PARSER, error, XML_ERR_FATAL,
308
1.58M
               NULL, NULL, NULL, val, msg, val);
309
1.58M
}
310
311
/**
312
 * xmlFatalErrMsgStrIntStr:
313
 * @ctxt:  an XML parser context
314
 * @error:  the error number
315
 * @msg:  the error message
316
 * @str1:  an string info
317
 * @val:  an integer value
318
 * @str2:  an string info
319
 *
320
 * Handle a fatal parser error, i.e. violating Well-Formedness constraints
321
 */
322
static void LIBXML_ATTR_FORMAT(3,0)
323
xmlFatalErrMsgStrIntStr(xmlParserCtxtPtr ctxt, xmlParserErrors error,
324
                  const char *msg, const xmlChar *str1, int val,
325
      const xmlChar *str2)
326
4.03M
{
327
4.03M
    xmlCtxtErr(ctxt, NULL, XML_FROM_PARSER, error, XML_ERR_FATAL,
328
4.03M
               str1, str2, NULL, val, msg, str1, val, str2);
329
4.03M
}
330
331
/**
332
 * xmlFatalErrMsgStr:
333
 * @ctxt:  an XML parser context
334
 * @error:  the error number
335
 * @msg:  the error message
336
 * @val:  a string value
337
 *
338
 * Handle a fatal parser error, i.e. violating Well-Formedness constraints
339
 */
340
static void LIBXML_ATTR_FORMAT(3,0)
341
xmlFatalErrMsgStr(xmlParserCtxtPtr ctxt, xmlParserErrors error,
342
                  const char *msg, const xmlChar * val)
343
91.4k
{
344
91.4k
    xmlCtxtErr(ctxt, NULL, XML_FROM_PARSER, error, XML_ERR_FATAL,
345
91.4k
               val, NULL, NULL, 0, msg, val);
346
91.4k
}
347
348
/**
349
 * xmlErrMsgStr:
350
 * @ctxt:  an XML parser context
351
 * @error:  the error number
352
 * @msg:  the error message
353
 * @val:  a string value
354
 *
355
 * Handle a non fatal parser error
356
 */
357
static void LIBXML_ATTR_FORMAT(3,0)
358
xmlErrMsgStr(xmlParserCtxtPtr ctxt, xmlParserErrors error,
359
                  const char *msg, const xmlChar * val)
360
0
{
361
0
    xmlCtxtErr(ctxt, NULL, XML_FROM_PARSER, error, XML_ERR_ERROR,
362
0
               val, NULL, NULL, 0, msg, val);
363
0
}
364
365
/**
366
 * xmlNsErr:
367
 * @ctxt:  an XML parser context
368
 * @error:  the error number
369
 * @msg:  the message
370
 * @info1:  extra information string
371
 * @info2:  extra information string
372
 *
373
 * Handle a fatal parser error, i.e. violating Well-Formedness constraints
374
 */
375
static void LIBXML_ATTR_FORMAT(3,0)
376
xmlNsErr(xmlParserCtxtPtr ctxt, xmlParserErrors error,
377
         const char *msg,
378
         const xmlChar * info1, const xmlChar * info2,
379
         const xmlChar * info3)
380
55.3k
{
381
55.3k
    ctxt->nsWellFormed = 0;
382
383
55.3k
    xmlCtxtErr(ctxt, NULL, XML_FROM_NAMESPACE, error, XML_ERR_ERROR,
384
55.3k
               info1, info2, info3, 0, msg, info1, info2, info3);
385
55.3k
}
386
387
/**
388
 * xmlNsWarn
389
 * @ctxt:  an XML parser context
390
 * @error:  the error number
391
 * @msg:  the message
392
 * @info1:  extra information string
393
 * @info2:  extra information string
394
 *
395
 * Handle a namespace warning error
396
 */
397
static void LIBXML_ATTR_FORMAT(3,0)
398
xmlNsWarn(xmlParserCtxtPtr ctxt, xmlParserErrors error,
399
         const char *msg,
400
         const xmlChar * info1, const xmlChar * info2,
401
         const xmlChar * info3)
402
3.84k
{
403
3.84k
    xmlCtxtErr(ctxt, NULL, XML_FROM_NAMESPACE, error, XML_ERR_WARNING,
404
3.84k
               info1, info2, info3, 0, msg, info1, info2, info3);
405
3.84k
}
406
407
static void
408
86.9k
xmlSaturatedAdd(unsigned long *dst, unsigned long val) {
409
86.9k
    if (val > ULONG_MAX - *dst)
410
0
        *dst = ULONG_MAX;
411
86.9k
    else
412
86.9k
        *dst += val;
413
86.9k
}
414
415
static void
416
20.2k
xmlSaturatedAddSizeT(unsigned long *dst, unsigned long val) {
417
20.2k
    if (val > ULONG_MAX - *dst)
418
0
        *dst = ULONG_MAX;
419
20.2k
    else
420
20.2k
        *dst += val;
421
20.2k
}
422
423
/**
424
 * xmlParserEntityCheck:
425
 * @ctxt:  parser context
426
 * @extra:  sum of unexpanded entity sizes
427
 *
428
 * Check for non-linear entity expansion behaviour.
429
 *
430
 * In some cases like xmlExpandEntityInAttValue, this function is called
431
 * for each, possibly nested entity and its unexpanded content length.
432
 *
433
 * In other cases like xmlParseReference, it's only called for each
434
 * top-level entity with its unexpanded content length plus the sum of
435
 * the unexpanded content lengths (plus fixed cost) of all nested
436
 * entities.
437
 *
438
 * Summing the unexpanded lengths also adds the length of the reference.
439
 * This is by design. Taking the length of the entity name into account
440
 * discourages attacks that try to waste CPU time with abusively long
441
 * entity names. See test/recurse/lol6.xml for example. Each call also
442
 * adds some fixed cost XML_ENT_FIXED_COST to discourage attacks with
443
 * short entities.
444
 *
445
 * Returns 1 on error, 0 on success.
446
 */
447
static int
448
xmlParserEntityCheck(xmlParserCtxtPtr ctxt, unsigned long extra)
449
20.2k
{
450
20.2k
    unsigned long consumed;
451
20.2k
    unsigned long *expandedSize;
452
20.2k
    xmlParserInputPtr input = ctxt->input;
453
20.2k
    xmlEntityPtr entity = input->entity;
454
455
20.2k
    if ((entity) && (entity->flags & XML_ENT_CHECKED))
456
0
        return(0);
457
458
    /*
459
     * Compute total consumed bytes so far, including input streams of
460
     * external entities.
461
     */
462
20.2k
    consumed = input->consumed;
463
20.2k
    xmlSaturatedAddSizeT(&consumed, input->cur - input->base);
464
20.2k
    xmlSaturatedAdd(&consumed, ctxt->sizeentities);
465
466
20.2k
    if (entity)
467
0
        expandedSize = &entity->expandedSize;
468
20.2k
    else
469
20.2k
        expandedSize = &ctxt->sizeentcopy;
470
471
    /*
472
     * Add extra cost and some fixed cost.
473
     */
474
20.2k
    xmlSaturatedAdd(expandedSize, extra);
475
20.2k
    xmlSaturatedAdd(expandedSize, XML_ENT_FIXED_COST);
476
477
    /*
478
     * It's important to always use saturation arithmetic when tracking
479
     * entity sizes to make the size checks reliable. If "sizeentcopy"
480
     * overflows, we have to abort.
481
     */
482
20.2k
    if ((*expandedSize > XML_PARSER_ALLOWED_EXPANSION) &&
483
20.2k
        ((*expandedSize >= ULONG_MAX) ||
484
2.78k
         (*expandedSize / ctxt->maxAmpl > consumed))) {
485
217
        xmlFatalErrMsg(ctxt, XML_ERR_RESOURCE_LIMIT,
486
217
                       "Maximum entity amplification factor exceeded, see "
487
217
                       "xmlCtxtSetMaxAmplification.\n");
488
217
        xmlHaltParser(ctxt);
489
217
        return(1);
490
217
    }
491
492
19.9k
    return(0);
493
20.2k
}
494
495
/************************************************************************
496
 *                  *
497
 *    Library wide options          *
498
 *                  *
499
 ************************************************************************/
500
501
/**
502
  * xmlHasFeature:
503
  * @feature: the feature to be examined
504
  *
505
  * Examines if the library has been compiled with a given feature.
506
  *
507
  * Returns a non-zero value if the feature exist, otherwise zero.
508
  * Returns zero (0) if the feature does not exist or an unknown
509
  * unknown feature is requested, non-zero otherwise.
510
  */
511
int
512
xmlHasFeature(xmlFeature feature)
513
0
{
514
0
    switch (feature) {
515
0
  case XML_WITH_THREAD:
516
0
#ifdef LIBXML_THREAD_ENABLED
517
0
      return(1);
518
#else
519
      return(0);
520
#endif
521
0
        case XML_WITH_TREE:
522
0
            return(1);
523
0
        case XML_WITH_OUTPUT:
524
0
#ifdef LIBXML_OUTPUT_ENABLED
525
0
            return(1);
526
#else
527
            return(0);
528
#endif
529
0
        case XML_WITH_PUSH:
530
#ifdef LIBXML_PUSH_ENABLED
531
            return(1);
532
#else
533
0
            return(0);
534
0
#endif
535
0
        case XML_WITH_READER:
536
#ifdef LIBXML_READER_ENABLED
537
            return(1);
538
#else
539
0
            return(0);
540
0
#endif
541
0
        case XML_WITH_PATTERN:
542
0
#ifdef LIBXML_PATTERN_ENABLED
543
0
            return(1);
544
#else
545
            return(0);
546
#endif
547
0
        case XML_WITH_WRITER:
548
#ifdef LIBXML_WRITER_ENABLED
549
            return(1);
550
#else
551
0
            return(0);
552
0
#endif
553
0
        case XML_WITH_SAX1:
554
#ifdef LIBXML_SAX1_ENABLED
555
            return(1);
556
#else
557
0
            return(0);
558
0
#endif
559
0
        case XML_WITH_HTTP:
560
#ifdef LIBXML_HTTP_ENABLED
561
            return(1);
562
#else
563
0
            return(0);
564
0
#endif
565
0
        case XML_WITH_VALID:
566
#ifdef LIBXML_VALID_ENABLED
567
            return(1);
568
#else
569
0
            return(0);
570
0
#endif
571
0
        case XML_WITH_HTML:
572
0
#ifdef LIBXML_HTML_ENABLED
573
0
            return(1);
574
#else
575
            return(0);
576
#endif
577
0
        case XML_WITH_LEGACY:
578
0
            return(0);
579
0
        case XML_WITH_C14N:
580
#ifdef LIBXML_C14N_ENABLED
581
            return(1);
582
#else
583
0
            return(0);
584
0
#endif
585
0
        case XML_WITH_CATALOG:
586
0
#ifdef LIBXML_CATALOG_ENABLED
587
0
            return(1);
588
#else
589
            return(0);
590
#endif
591
0
        case XML_WITH_XPATH:
592
0
#ifdef LIBXML_XPATH_ENABLED
593
0
            return(1);
594
#else
595
            return(0);
596
#endif
597
0
        case XML_WITH_XPTR:
598
0
#ifdef LIBXML_XPTR_ENABLED
599
0
            return(1);
600
#else
601
            return(0);
602
#endif
603
0
        case XML_WITH_XINCLUDE:
604
0
#ifdef LIBXML_XINCLUDE_ENABLED
605
0
            return(1);
606
#else
607
            return(0);
608
#endif
609
0
        case XML_WITH_ICONV:
610
0
#ifdef LIBXML_ICONV_ENABLED
611
0
            return(1);
612
#else
613
            return(0);
614
#endif
615
0
        case XML_WITH_ISO8859X:
616
0
#ifdef LIBXML_ISO8859X_ENABLED
617
0
            return(1);
618
#else
619
            return(0);
620
#endif
621
0
        case XML_WITH_UNICODE:
622
0
            return(0);
623
0
        case XML_WITH_REGEXP:
624
#ifdef LIBXML_REGEXP_ENABLED
625
            return(1);
626
#else
627
0
            return(0);
628
0
#endif
629
0
        case XML_WITH_AUTOMATA:
630
#ifdef LIBXML_REGEXP_ENABLED
631
            return(1);
632
#else
633
0
            return(0);
634
0
#endif
635
0
        case XML_WITH_EXPR:
636
#ifdef LIBXML_EXPR_ENABLED
637
            return(1);
638
#else
639
0
            return(0);
640
0
#endif
641
0
        case XML_WITH_RELAXNG:
642
#ifdef LIBXML_RELAXNG_ENABLED
643
            return(1);
644
#else
645
0
            return(0);
646
0
#endif
647
0
        case XML_WITH_SCHEMAS:
648
#ifdef LIBXML_SCHEMAS_ENABLED
649
            return(1);
650
#else
651
0
            return(0);
652
0
#endif
653
0
        case XML_WITH_SCHEMATRON:
654
#ifdef LIBXML_SCHEMATRON_ENABLED
655
            return(1);
656
#else
657
0
            return(0);
658
0
#endif
659
0
        case XML_WITH_MODULES:
660
0
#ifdef LIBXML_MODULES_ENABLED
661
0
            return(1);
662
#else
663
            return(0);
664
#endif
665
0
        case XML_WITH_DEBUG:
666
0
#ifdef LIBXML_DEBUG_ENABLED
667
0
            return(1);
668
#else
669
            return(0);
670
#endif
671
0
        case XML_WITH_DEBUG_MEM:
672
0
            return(0);
673
0
        case XML_WITH_ZLIB:
674
#ifdef LIBXML_ZLIB_ENABLED
675
            return(1);
676
#else
677
0
            return(0);
678
0
#endif
679
0
        case XML_WITH_LZMA:
680
#ifdef LIBXML_LZMA_ENABLED
681
            return(1);
682
#else
683
0
            return(0);
684
0
#endif
685
0
        case XML_WITH_ICU:
686
#ifdef LIBXML_ICU_ENABLED
687
            return(1);
688
#else
689
0
            return(0);
690
0
#endif
691
0
        default:
692
0
      break;
693
0
     }
694
0
     return(0);
695
0
}
696
697
/************************************************************************
698
 *                  *
699
 *      Simple string buffer        *
700
 *                  *
701
 ************************************************************************/
702
703
typedef struct {
704
    xmlChar *mem;
705
    unsigned size;
706
    unsigned cap; /* size < cap */
707
    unsigned max; /* size <= max */
708
    xmlParserErrors code;
709
} xmlSBuf;
710
711
static void
712
88.9k
xmlSBufInit(xmlSBuf *buf, unsigned max) {
713
88.9k
    buf->mem = NULL;
714
88.9k
    buf->size = 0;
715
88.9k
    buf->cap = 0;
716
88.9k
    buf->max = max;
717
88.9k
    buf->code = XML_ERR_OK;
718
88.9k
}
719
720
static int
721
60.1k
xmlSBufGrow(xmlSBuf *buf, unsigned len) {
722
60.1k
    xmlChar *mem;
723
60.1k
    unsigned cap;
724
725
60.1k
    if (len >= UINT_MAX / 2 - buf->size) {
726
0
        if (buf->code == XML_ERR_OK)
727
0
            buf->code = XML_ERR_RESOURCE_LIMIT;
728
0
        return(-1);
729
0
    }
730
731
60.1k
    cap = (buf->size + len) * 2;
732
60.1k
    if (cap < 240)
733
36.2k
        cap = 240;
734
735
60.1k
    mem = xmlRealloc(buf->mem, cap);
736
60.1k
    if (mem == NULL) {
737
0
        buf->code = XML_ERR_NO_MEMORY;
738
0
        return(-1);
739
0
    }
740
741
60.1k
    buf->mem = mem;
742
60.1k
    buf->cap = cap;
743
744
60.1k
    return(0);
745
60.1k
}
746
747
static void
748
45.4M
xmlSBufAddString(xmlSBuf *buf, const xmlChar *str, unsigned len) {
749
45.4M
    if (buf->max - buf->size < len) {
750
3.26k
        if (buf->code == XML_ERR_OK)
751
79
            buf->code = XML_ERR_RESOURCE_LIMIT;
752
3.26k
        return;
753
3.26k
    }
754
755
45.4M
    if (buf->cap - buf->size <= len) {
756
55.9k
        if (xmlSBufGrow(buf, len) < 0)
757
0
            return;
758
55.9k
    }
759
760
45.4M
    if (len > 0)
761
45.4M
        memcpy(buf->mem + buf->size, str, len);
762
45.4M
    buf->size += len;
763
45.4M
}
764
765
static void
766
45.0M
xmlSBufAddCString(xmlSBuf *buf, const char *str, unsigned len) {
767
45.0M
    xmlSBufAddString(buf, (const xmlChar *) str, len);
768
45.0M
}
769
770
static void
771
35.9k
xmlSBufAddChar(xmlSBuf *buf, int c) {
772
35.9k
    xmlChar *end;
773
774
35.9k
    if (buf->max - buf->size < 4) {
775
96
        if (buf->code == XML_ERR_OK)
776
1
            buf->code = XML_ERR_RESOURCE_LIMIT;
777
96
        return;
778
96
    }
779
780
35.8k
    if (buf->cap - buf->size <= 4) {
781
4.22k
        if (xmlSBufGrow(buf, 4) < 0)
782
0
            return;
783
4.22k
    }
784
785
35.8k
    end = buf->mem + buf->size;
786
787
35.8k
    if (c < 0x80) {
788
18.4k
        *end = (xmlChar) c;
789
18.4k
        buf->size += 1;
790
18.4k
    } else {
791
17.3k
        buf->size += xmlCopyCharMultiByte(end, c);
792
17.3k
    }
793
35.8k
}
794
795
static void
796
42.1M
xmlSBufAddReplChar(xmlSBuf *buf) {
797
42.1M
    xmlSBufAddCString(buf, "\xEF\xBF\xBD", 3);
798
42.1M
}
799
800
static void
801
80
xmlSBufReportError(xmlSBuf *buf, xmlParserCtxtPtr ctxt, const char *errMsg) {
802
80
    if (buf->code == XML_ERR_NO_MEMORY)
803
0
        xmlCtxtErrMemory(ctxt);
804
80
    else
805
80
        xmlFatalErr(ctxt, buf->code, errMsg);
806
80
}
807
808
static xmlChar *
809
xmlSBufFinish(xmlSBuf *buf, int *sizeOut, xmlParserCtxtPtr ctxt,
810
46.6k
              const char *errMsg) {
811
46.6k
    if (buf->mem == NULL) {
812
10.4k
        buf->mem = xmlMalloc(1);
813
10.4k
        if (buf->mem == NULL) {
814
0
            buf->code = XML_ERR_NO_MEMORY;
815
10.4k
        } else {
816
10.4k
            buf->mem[0] = 0;
817
10.4k
        }
818
36.1k
    } else {
819
36.1k
        buf->mem[buf->size] = 0;
820
36.1k
    }
821
822
46.6k
    if (buf->code == XML_ERR_OK) {
823
46.6k
        if (sizeOut != NULL)
824
18.5k
            *sizeOut = buf->size;
825
46.6k
        return(buf->mem);
826
46.6k
    }
827
828
8
    xmlSBufReportError(buf, ctxt, errMsg);
829
830
8
    xmlFree(buf->mem);
831
832
8
    if (sizeOut != NULL)
833
8
        *sizeOut = 0;
834
8
    return(NULL);
835
46.6k
}
836
837
static void
838
40.5k
xmlSBufCleanup(xmlSBuf *buf, xmlParserCtxtPtr ctxt, const char *errMsg) {
839
40.5k
    if (buf->code != XML_ERR_OK)
840
72
        xmlSBufReportError(buf, ctxt, errMsg);
841
842
40.5k
    xmlFree(buf->mem);
843
40.5k
}
844
845
static int
846
xmlUTF8MultibyteLen(xmlParserCtxtPtr ctxt, const xmlChar *str,
847
117M
                    const char *errMsg) {
848
117M
    int c = str[0];
849
117M
    int c1 = str[1];
850
851
117M
    if ((c1 & 0xC0) != 0x80)
852
23.1M
        goto encoding_error;
853
854
93.8M
    if (c < 0xE0) {
855
        /* 2-byte sequence */
856
5.16M
        if (c < 0xC2)
857
2.39M
            goto encoding_error;
858
859
2.77M
        return(2);
860
88.7M
    } else {
861
88.7M
        int c2 = str[2];
862
863
88.7M
        if ((c2 & 0xC0) != 0x80)
864
16.7k
            goto encoding_error;
865
866
88.7M
        if (c < 0xF0) {
867
            /* 3-byte sequence */
868
88.6M
            if (c == 0xE0) {
869
                /* overlong */
870
1.23k
                if (c1 < 0xA0)
871
1
                    goto encoding_error;
872
88.6M
            } else if (c == 0xED) {
873
                /* surrogate */
874
56
                if (c1 >= 0xA0)
875
1
                    goto encoding_error;
876
88.6M
            } else if (c == 0xEF) {
877
                /* U+FFFE and U+FFFF are invalid Chars */
878
587
                if ((c1 == 0xBF) && (c2 >= 0xBE))
879
20
                    xmlFatalErrMsg(ctxt, XML_ERR_INVALID_CHAR, errMsg);
880
587
            }
881
882
88.6M
            return(3);
883
88.6M
        } else {
884
            /* 4-byte sequence */
885
33.3k
            if ((str[3] & 0xC0) != 0x80)
886
2.92k
                goto encoding_error;
887
30.4k
            if (c == 0xF0) {
888
                /* overlong */
889
3.29k
                if (c1 < 0x90)
890
26
                    goto encoding_error;
891
27.1k
            } else if (c >= 0xF4) {
892
                /* greater than 0x10FFFF */
893
1.26k
                if ((c > 0xF4) || (c1 >= 0x90))
894
1.13k
                    goto encoding_error;
895
1.26k
            }
896
897
29.3k
            return(4);
898
30.4k
        }
899
88.7M
    }
900
901
25.5M
encoding_error:
902
    /* Only report the first error */
903
25.5M
    if ((ctxt->input->flags & XML_INPUT_ENCODING_ERROR) == 0) {
904
162
        xmlCtxtErrIO(ctxt, XML_ERR_INVALID_ENCODING, NULL);
905
162
        ctxt->input->flags |= XML_INPUT_ENCODING_ERROR;
906
162
    }
907
908
25.5M
    return(0);
909
93.8M
}
910
911
/************************************************************************
912
 *                  *
913
 *    SAX2 defaulted attributes handling      *
914
 *                  *
915
 ************************************************************************/
916
917
/**
918
 * xmlCtxtInitializeLate:
919
 * @ctxt:  an XML parser context
920
 *
921
 * Final initialization of the parser context before starting to parse.
922
 *
923
 * This accounts for users modifying struct members of parser context
924
 * directly.
925
 */
926
static void
927
793
xmlCtxtInitializeLate(xmlParserCtxtPtr ctxt) {
928
793
    xmlSAXHandlerPtr sax;
929
930
    /* Avoid unused variable warning if features are disabled. */
931
793
    (void) sax;
932
933
    /*
934
     * Changing the SAX struct directly is still widespread practice
935
     * in internal and external code.
936
     */
937
793
    if (ctxt == NULL) return;
938
793
    sax = ctxt->sax;
939
#ifdef LIBXML_SAX1_ENABLED
940
    /*
941
     * Only enable SAX2 if there SAX2 element handlers, except when there
942
     * are no element handlers at all.
943
     */
944
    if (((ctxt->options & XML_PARSE_SAX1) == 0) &&
945
        (sax) &&
946
        (sax->initialized == XML_SAX2_MAGIC) &&
947
        ((sax->startElementNs != NULL) ||
948
         (sax->endElementNs != NULL) ||
949
         ((sax->startElement == NULL) && (sax->endElement == NULL))))
950
        ctxt->sax2 = 1;
951
#else
952
793
    ctxt->sax2 = 1;
953
793
#endif /* LIBXML_SAX1_ENABLED */
954
955
    /*
956
     * Some users replace the dictionary directly in the context struct.
957
     * We really need an API function to do that cleanly.
958
     */
959
793
    ctxt->str_xml = xmlDictLookup(ctxt->dict, BAD_CAST "xml", 3);
960
793
    ctxt->str_xmlns = xmlDictLookup(ctxt->dict, BAD_CAST "xmlns", 5);
961
793
    ctxt->str_xml_ns = xmlDictLookup(ctxt->dict, XML_XML_NAMESPACE, 36);
962
793
    if ((ctxt->str_xml==NULL) || (ctxt->str_xmlns==NULL) ||
963
793
    (ctxt->str_xml_ns == NULL)) {
964
0
        xmlErrMemory(ctxt);
965
0
    }
966
967
793
    xmlDictSetLimit(ctxt->dict,
968
793
                    (ctxt->options & XML_PARSE_HUGE) ?
969
0
                        0 :
970
793
                        XML_MAX_DICTIONARY_LIMIT);
971
793
}
972
973
typedef struct {
974
    xmlHashedString prefix;
975
    xmlHashedString name;
976
    xmlHashedString value;
977
    const xmlChar *valueEnd;
978
    int external;
979
    int expandedSize;
980
} xmlDefAttr;
981
982
typedef struct _xmlDefAttrs xmlDefAttrs;
983
typedef xmlDefAttrs *xmlDefAttrsPtr;
984
struct _xmlDefAttrs {
985
    int nbAttrs;  /* number of defaulted attributes on that element */
986
    int maxAttrs;       /* the size of the array */
987
#if __STDC_VERSION__ >= 199901L
988
    /* Using a C99 flexible array member avoids UBSan errors. */
989
    xmlDefAttr attrs[] ATTRIBUTE_COUNTED_BY(maxAttrs);
990
#else
991
    xmlDefAttr attrs[1];
992
#endif
993
};
994
995
/**
996
 * xmlAttrNormalizeSpace:
997
 * @src: the source string
998
 * @dst: the target string
999
 *
1000
 * Normalize the space in non CDATA attribute values:
1001
 * If the attribute type is not CDATA, then the XML processor MUST further
1002
 * process the normalized attribute value by discarding any leading and
1003
 * trailing space (#x20) characters, and by replacing sequences of space
1004
 * (#x20) characters by a single space (#x20) character.
1005
 * Note that the size of dst need to be at least src, and if one doesn't need
1006
 * to preserve dst (and it doesn't come from a dictionary or read-only) then
1007
 * passing src as dst is just fine.
1008
 *
1009
 * Returns a pointer to the normalized value (dst) or NULL if no conversion
1010
 *         is needed.
1011
 */
1012
static xmlChar *
1013
xmlAttrNormalizeSpace(const xmlChar *src, xmlChar *dst)
1014
57
{
1015
57
    if ((src == NULL) || (dst == NULL))
1016
0
        return(NULL);
1017
1018
62
    while (*src == 0x20) src++;
1019
46.7k
    while (*src != 0) {
1020
46.7k
  if (*src == 0x20) {
1021
32
      while (*src == 0x20) src++;
1022
16
      if (*src != 0)
1023
11
    *dst++ = 0x20;
1024
46.7k
  } else {
1025
46.7k
      *dst++ = *src++;
1026
46.7k
  }
1027
46.7k
    }
1028
57
    *dst = 0;
1029
57
    if (dst == src)
1030
52
       return(NULL);
1031
5
    return(dst);
1032
57
}
1033
1034
/**
1035
 * xmlAddDefAttrs:
1036
 * @ctxt:  an XML parser context
1037
 * @fullname:  the element fullname
1038
 * @fullattr:  the attribute fullname
1039
 * @value:  the attribute value
1040
 *
1041
 * Add a defaulted attribute for an element
1042
 */
1043
static void
1044
xmlAddDefAttrs(xmlParserCtxtPtr ctxt,
1045
               const xmlChar *fullname,
1046
               const xmlChar *fullattr,
1047
320
               const xmlChar *value) {
1048
320
    xmlDefAttrsPtr defaults;
1049
320
    xmlDefAttr *attr;
1050
320
    int len, expandedSize;
1051
320
    xmlHashedString name;
1052
320
    xmlHashedString prefix;
1053
320
    xmlHashedString hvalue;
1054
320
    const xmlChar *localname;
1055
1056
    /*
1057
     * Allows to detect attribute redefinitions
1058
     */
1059
320
    if (ctxt->attsSpecial != NULL) {
1060
308
        if (xmlHashLookup2(ctxt->attsSpecial, fullname, fullattr) != NULL)
1061
251
      return;
1062
308
    }
1063
1064
69
    if (ctxt->attsDefault == NULL) {
1065
12
        ctxt->attsDefault = xmlHashCreateDict(10, ctxt->dict);
1066
12
  if (ctxt->attsDefault == NULL)
1067
0
      goto mem_error;
1068
12
    }
1069
1070
    /*
1071
     * split the element name into prefix:localname , the string found
1072
     * are within the DTD and then not associated to namespace names.
1073
     */
1074
69
    localname = xmlSplitQName3(fullname, &len);
1075
69
    if (localname == NULL) {
1076
69
        name = xmlDictLookupHashed(ctxt->dict, fullname, -1);
1077
69
  prefix.name = NULL;
1078
69
    } else {
1079
0
        name = xmlDictLookupHashed(ctxt->dict, localname, -1);
1080
0
  prefix = xmlDictLookupHashed(ctxt->dict, fullname, len);
1081
0
        if (prefix.name == NULL)
1082
0
            goto mem_error;
1083
0
    }
1084
69
    if (name.name == NULL)
1085
0
        goto mem_error;
1086
1087
    /*
1088
     * make sure there is some storage
1089
     */
1090
69
    defaults = xmlHashLookup2(ctxt->attsDefault, name.name, prefix.name);
1091
69
    if ((defaults == NULL) ||
1092
69
        (defaults->nbAttrs >= defaults->maxAttrs)) {
1093
22
        xmlDefAttrsPtr temp;
1094
22
        int newSize;
1095
1096
22
        if (defaults == NULL) {
1097
15
            newSize = 4;
1098
15
        } else {
1099
7
            if ((defaults->maxAttrs >= XML_MAX_ATTRS) ||
1100
7
                ((size_t) defaults->maxAttrs >
1101
7
                     SIZE_MAX / 2 / sizeof(temp[0]) - sizeof(*defaults)))
1102
0
                goto mem_error;
1103
1104
7
            if (defaults->maxAttrs > XML_MAX_ATTRS / 2)
1105
0
                newSize = XML_MAX_ATTRS;
1106
7
            else
1107
7
                newSize = defaults->maxAttrs * 2;
1108
7
        }
1109
22
        temp = xmlRealloc(defaults,
1110
22
                          sizeof(*defaults) + newSize * sizeof(xmlDefAttr));
1111
22
  if (temp == NULL)
1112
0
      goto mem_error;
1113
22
        if (defaults == NULL)
1114
15
            temp->nbAttrs = 0;
1115
22
  temp->maxAttrs = newSize;
1116
22
        defaults = temp;
1117
22
  if (xmlHashUpdateEntry2(ctxt->attsDefault, name.name, prefix.name,
1118
22
                          defaults, NULL) < 0) {
1119
0
      xmlFree(defaults);
1120
0
      goto mem_error;
1121
0
  }
1122
22
    }
1123
1124
    /*
1125
     * Split the attribute name into prefix:localname , the string found
1126
     * are within the DTD and hen not associated to namespace names.
1127
     */
1128
69
    localname = xmlSplitQName3(fullattr, &len);
1129
69
    if (localname == NULL) {
1130
26
        name = xmlDictLookupHashed(ctxt->dict, fullattr, -1);
1131
26
  prefix.name = NULL;
1132
43
    } else {
1133
43
        name = xmlDictLookupHashed(ctxt->dict, localname, -1);
1134
43
  prefix = xmlDictLookupHashed(ctxt->dict, fullattr, len);
1135
43
        if (prefix.name == NULL)
1136
0
            goto mem_error;
1137
43
    }
1138
69
    if (name.name == NULL)
1139
0
        goto mem_error;
1140
1141
    /* intern the string and precompute the end */
1142
69
    len = strlen((const char *) value);
1143
69
    hvalue = xmlDictLookupHashed(ctxt->dict, value, len);
1144
69
    if (hvalue.name == NULL)
1145
0
        goto mem_error;
1146
1147
69
    expandedSize = strlen((const char *) name.name);
1148
69
    if (prefix.name != NULL)
1149
43
        expandedSize += strlen((const char *) prefix.name);
1150
69
    expandedSize += len;
1151
1152
69
    attr = &defaults->attrs[defaults->nbAttrs++];
1153
69
    attr->name = name;
1154
69
    attr->prefix = prefix;
1155
69
    attr->value = hvalue;
1156
69
    attr->valueEnd = hvalue.name + len;
1157
69
    attr->external = PARSER_EXTERNAL(ctxt);
1158
69
    attr->expandedSize = expandedSize;
1159
1160
69
    return;
1161
1162
0
mem_error:
1163
0
    xmlErrMemory(ctxt);
1164
0
}
1165
1166
/**
1167
 * xmlAddSpecialAttr:
1168
 * @ctxt:  an XML parser context
1169
 * @fullname:  the element fullname
1170
 * @fullattr:  the attribute fullname
1171
 * @type:  the attribute type
1172
 *
1173
 * Register this attribute type
1174
 */
1175
static void
1176
xmlAddSpecialAttr(xmlParserCtxtPtr ctxt,
1177
      const xmlChar *fullname,
1178
      const xmlChar *fullattr,
1179
      int type)
1180
790
{
1181
790
    if (ctxt->attsSpecial == NULL) {
1182
274
        ctxt->attsSpecial = xmlHashCreateDict(10, ctxt->dict);
1183
274
  if (ctxt->attsSpecial == NULL)
1184
0
      goto mem_error;
1185
274
    }
1186
1187
790
    if (xmlHashAdd2(ctxt->attsSpecial, fullname, fullattr,
1188
790
                    XML_INT_TO_PTR(type)) < 0)
1189
0
        goto mem_error;
1190
790
    return;
1191
1192
790
mem_error:
1193
0
    xmlErrMemory(ctxt);
1194
0
}
1195
1196
/**
1197
 * xmlCleanSpecialAttrCallback:
1198
 *
1199
 * Removes CDATA attributes from the special attribute table
1200
 */
1201
static void
1202
xmlCleanSpecialAttrCallback(void *payload, void *data,
1203
                            const xmlChar *fullname, const xmlChar *fullattr,
1204
371
                            const xmlChar *unused ATTRIBUTE_UNUSED) {
1205
371
    xmlParserCtxtPtr ctxt = (xmlParserCtxtPtr) data;
1206
1207
371
    if (XML_PTR_TO_INT(payload) == XML_ATTRIBUTE_CDATA) {
1208
81
        xmlHashRemoveEntry2(ctxt->attsSpecial, fullname, fullattr, NULL);
1209
81
    }
1210
371
}
1211
1212
/**
1213
 * xmlCleanSpecialAttr:
1214
 * @ctxt:  an XML parser context
1215
 *
1216
 * Trim the list of attributes defined to remove all those of type
1217
 * CDATA as they are not special. This call should be done when finishing
1218
 * to parse the DTD and before starting to parse the document root.
1219
 */
1220
static void
1221
xmlCleanSpecialAttr(xmlParserCtxtPtr ctxt)
1222
391
{
1223
391
    if (ctxt->attsSpecial == NULL)
1224
117
        return;
1225
1226
274
    xmlHashScanFull(ctxt->attsSpecial, xmlCleanSpecialAttrCallback, ctxt);
1227
1228
274
    if (xmlHashSize(ctxt->attsSpecial) == 0) {
1229
0
        xmlHashFree(ctxt->attsSpecial, NULL);
1230
0
        ctxt->attsSpecial = NULL;
1231
0
    }
1232
274
}
1233
1234
/**
1235
 * xmlCheckLanguageID:
1236
 * @lang:  pointer to the string value
1237
 *
1238
 * DEPRECATED: Internal function, do not use.
1239
 *
1240
 * Checks that the value conforms to the LanguageID production:
1241
 *
1242
 * NOTE: this is somewhat deprecated, those productions were removed from
1243
 *       the XML Second edition.
1244
 *
1245
 * [33] LanguageID ::= Langcode ('-' Subcode)*
1246
 * [34] Langcode ::= ISO639Code |  IanaCode |  UserCode
1247
 * [35] ISO639Code ::= ([a-z] | [A-Z]) ([a-z] | [A-Z])
1248
 * [36] IanaCode ::= ('i' | 'I') '-' ([a-z] | [A-Z])+
1249
 * [37] UserCode ::= ('x' | 'X') '-' ([a-z] | [A-Z])+
1250
 * [38] Subcode ::= ([a-z] | [A-Z])+
1251
 *
1252
 * The current REC reference the successors of RFC 1766, currently 5646
1253
 *
1254
 * http://www.rfc-editor.org/rfc/rfc5646.txt
1255
 * langtag       = language
1256
 *                 ["-" script]
1257
 *                 ["-" region]
1258
 *                 *("-" variant)
1259
 *                 *("-" extension)
1260
 *                 ["-" privateuse]
1261
 * language      = 2*3ALPHA            ; shortest ISO 639 code
1262
 *                 ["-" extlang]       ; sometimes followed by
1263
 *                                     ; extended language subtags
1264
 *               / 4ALPHA              ; or reserved for future use
1265
 *               / 5*8ALPHA            ; or registered language subtag
1266
 *
1267
 * extlang       = 3ALPHA              ; selected ISO 639 codes
1268
 *                 *2("-" 3ALPHA)      ; permanently reserved
1269
 *
1270
 * script        = 4ALPHA              ; ISO 15924 code
1271
 *
1272
 * region        = 2ALPHA              ; ISO 3166-1 code
1273
 *               / 3DIGIT              ; UN M.49 code
1274
 *
1275
 * variant       = 5*8alphanum         ; registered variants
1276
 *               / (DIGIT 3alphanum)
1277
 *
1278
 * extension     = singleton 1*("-" (2*8alphanum))
1279
 *
1280
 *                                     ; Single alphanumerics
1281
 *                                     ; "x" reserved for private use
1282
 * singleton     = DIGIT               ; 0 - 9
1283
 *               / %x41-57             ; A - W
1284
 *               / %x59-5A             ; Y - Z
1285
 *               / %x61-77             ; a - w
1286
 *               / %x79-7A             ; y - z
1287
 *
1288
 * it sounds right to still allow Irregular i-xxx IANA and user codes too
1289
 * The parser below doesn't try to cope with extension or privateuse
1290
 * that could be added but that's not interoperable anyway
1291
 *
1292
 * Returns 1 if correct 0 otherwise
1293
 **/
1294
int
1295
xmlCheckLanguageID(const xmlChar * lang)
1296
0
{
1297
0
    const xmlChar *cur = lang, *nxt;
1298
1299
0
    if (cur == NULL)
1300
0
        return (0);
1301
0
    if (((cur[0] == 'i') && (cur[1] == '-')) ||
1302
0
        ((cur[0] == 'I') && (cur[1] == '-')) ||
1303
0
        ((cur[0] == 'x') && (cur[1] == '-')) ||
1304
0
        ((cur[0] == 'X') && (cur[1] == '-'))) {
1305
        /*
1306
         * Still allow IANA code and user code which were coming
1307
         * from the previous version of the XML-1.0 specification
1308
         * it's deprecated but we should not fail
1309
         */
1310
0
        cur += 2;
1311
0
        while (((cur[0] >= 'A') && (cur[0] <= 'Z')) ||
1312
0
               ((cur[0] >= 'a') && (cur[0] <= 'z')))
1313
0
            cur++;
1314
0
        return(cur[0] == 0);
1315
0
    }
1316
0
    nxt = cur;
1317
0
    while (((nxt[0] >= 'A') && (nxt[0] <= 'Z')) ||
1318
0
           ((nxt[0] >= 'a') && (nxt[0] <= 'z')))
1319
0
           nxt++;
1320
0
    if (nxt - cur >= 4) {
1321
        /*
1322
         * Reserved
1323
         */
1324
0
        if ((nxt - cur > 8) || (nxt[0] != 0))
1325
0
            return(0);
1326
0
        return(1);
1327
0
    }
1328
0
    if (nxt - cur < 2)
1329
0
        return(0);
1330
    /* we got an ISO 639 code */
1331
0
    if (nxt[0] == 0)
1332
0
        return(1);
1333
0
    if (nxt[0] != '-')
1334
0
        return(0);
1335
1336
0
    nxt++;
1337
0
    cur = nxt;
1338
    /* now we can have extlang or script or region or variant */
1339
0
    if ((nxt[0] >= '0') && (nxt[0] <= '9'))
1340
0
        goto region_m49;
1341
1342
0
    while (((nxt[0] >= 'A') && (nxt[0] <= 'Z')) ||
1343
0
           ((nxt[0] >= 'a') && (nxt[0] <= 'z')))
1344
0
           nxt++;
1345
0
    if (nxt - cur == 4)
1346
0
        goto script;
1347
0
    if (nxt - cur == 2)
1348
0
        goto region;
1349
0
    if ((nxt - cur >= 5) && (nxt - cur <= 8))
1350
0
        goto variant;
1351
0
    if (nxt - cur != 3)
1352
0
        return(0);
1353
    /* we parsed an extlang */
1354
0
    if (nxt[0] == 0)
1355
0
        return(1);
1356
0
    if (nxt[0] != '-')
1357
0
        return(0);
1358
1359
0
    nxt++;
1360
0
    cur = nxt;
1361
    /* now we can have script or region or variant */
1362
0
    if ((nxt[0] >= '0') && (nxt[0] <= '9'))
1363
0
        goto region_m49;
1364
1365
0
    while (((nxt[0] >= 'A') && (nxt[0] <= 'Z')) ||
1366
0
           ((nxt[0] >= 'a') && (nxt[0] <= 'z')))
1367
0
           nxt++;
1368
0
    if (nxt - cur == 2)
1369
0
        goto region;
1370
0
    if ((nxt - cur >= 5) && (nxt - cur <= 8))
1371
0
        goto variant;
1372
0
    if (nxt - cur != 4)
1373
0
        return(0);
1374
    /* we parsed a script */
1375
0
script:
1376
0
    if (nxt[0] == 0)
1377
0
        return(1);
1378
0
    if (nxt[0] != '-')
1379
0
        return(0);
1380
1381
0
    nxt++;
1382
0
    cur = nxt;
1383
    /* now we can have region or variant */
1384
0
    if ((nxt[0] >= '0') && (nxt[0] <= '9'))
1385
0
        goto region_m49;
1386
1387
0
    while (((nxt[0] >= 'A') && (nxt[0] <= 'Z')) ||
1388
0
           ((nxt[0] >= 'a') && (nxt[0] <= 'z')))
1389
0
           nxt++;
1390
1391
0
    if ((nxt - cur >= 5) && (nxt - cur <= 8))
1392
0
        goto variant;
1393
0
    if (nxt - cur != 2)
1394
0
        return(0);
1395
    /* we parsed a region */
1396
0
region:
1397
0
    if (nxt[0] == 0)
1398
0
        return(1);
1399
0
    if (nxt[0] != '-')
1400
0
        return(0);
1401
1402
0
    nxt++;
1403
0
    cur = nxt;
1404
    /* now we can just have a variant */
1405
0
    while (((nxt[0] >= 'A') && (nxt[0] <= 'Z')) ||
1406
0
           ((nxt[0] >= 'a') && (nxt[0] <= 'z')))
1407
0
           nxt++;
1408
1409
0
    if ((nxt - cur < 5) || (nxt - cur > 8))
1410
0
        return(0);
1411
1412
    /* we parsed a variant */
1413
0
variant:
1414
0
    if (nxt[0] == 0)
1415
0
        return(1);
1416
0
    if (nxt[0] != '-')
1417
0
        return(0);
1418
    /* extensions and private use subtags not checked */
1419
0
    return (1);
1420
1421
0
region_m49:
1422
0
    if (((nxt[1] >= '0') && (nxt[1] <= '9')) &&
1423
0
        ((nxt[2] >= '0') && (nxt[2] <= '9'))) {
1424
0
        nxt += 3;
1425
0
        goto region;
1426
0
    }
1427
0
    return(0);
1428
0
}
1429
1430
/************************************************************************
1431
 *                  *
1432
 *    Parser stacks related functions and macros    *
1433
 *                  *
1434
 ************************************************************************/
1435
1436
static xmlChar *
1437
xmlParseStringEntityRef(xmlParserCtxtPtr ctxt, const xmlChar **str);
1438
1439
/**
1440
 * xmlParserNsCreate:
1441
 *
1442
 * Create a new namespace database.
1443
 *
1444
 * Returns the new obejct.
1445
 */
1446
xmlParserNsData *
1447
795
xmlParserNsCreate(void) {
1448
795
    xmlParserNsData *nsdb = xmlMalloc(sizeof(*nsdb));
1449
1450
795
    if (nsdb == NULL)
1451
0
        return(NULL);
1452
795
    memset(nsdb, 0, sizeof(*nsdb));
1453
795
    nsdb->defaultNsIndex = INT_MAX;
1454
1455
795
    return(nsdb);
1456
795
}
1457
1458
/**
1459
 * xmlParserNsFree:
1460
 * @nsdb: namespace database
1461
 *
1462
 * Free a namespace database.
1463
 */
1464
void
1465
795
xmlParserNsFree(xmlParserNsData *nsdb) {
1466
795
    if (nsdb == NULL)
1467
0
        return;
1468
1469
795
    xmlFree(nsdb->extra);
1470
795
    xmlFree(nsdb->hash);
1471
795
    xmlFree(nsdb);
1472
795
}
1473
1474
/**
1475
 * xmlParserNsReset:
1476
 * @nsdb: namespace database
1477
 *
1478
 * Reset a namespace database.
1479
 */
1480
static void
1481
0
xmlParserNsReset(xmlParserNsData *nsdb) {
1482
0
    if (nsdb == NULL)
1483
0
        return;
1484
1485
0
    nsdb->hashElems = 0;
1486
0
    nsdb->elementId = 0;
1487
0
    nsdb->defaultNsIndex = INT_MAX;
1488
1489
0
    if (nsdb->hash)
1490
0
        memset(nsdb->hash, 0, nsdb->hashSize * sizeof(nsdb->hash[0]));
1491
0
}
1492
1493
/**
1494
 * xmlParserStartElement:
1495
 * @nsdb: namespace database
1496
 *
1497
 * Signal that a new element has started.
1498
 *
1499
 * Returns 0 on success, -1 if the element counter overflowed.
1500
 */
1501
static int
1502
4.29M
xmlParserNsStartElement(xmlParserNsData *nsdb) {
1503
4.29M
    if (nsdb->elementId == UINT_MAX)
1504
0
        return(-1);
1505
4.29M
    nsdb->elementId++;
1506
1507
4.29M
    return(0);
1508
4.29M
}
1509
1510
/**
1511
 * xmlParserNsLookup:
1512
 * @ctxt: parser context
1513
 * @prefix: namespace prefix
1514
 * @bucketPtr: optional bucket (return value)
1515
 *
1516
 * Lookup namespace with given prefix. If @bucketPtr is non-NULL, it will
1517
 * be set to the matching bucket, or the first empty bucket if no match
1518
 * was found.
1519
 *
1520
 * Returns the namespace index on success, INT_MAX if no namespace was
1521
 * found.
1522
 */
1523
static int
1524
xmlParserNsLookup(xmlParserCtxtPtr ctxt, const xmlHashedString *prefix,
1525
4.50M
                  xmlParserNsBucket **bucketPtr) {
1526
4.50M
    xmlParserNsBucket *bucket, *tombstone;
1527
4.50M
    unsigned index, hashValue;
1528
1529
4.50M
    if (prefix->name == NULL)
1530
4.41M
        return(ctxt->nsdb->defaultNsIndex);
1531
1532
92.5k
    if (ctxt->nsdb->hashSize == 0)
1533
13.7k
        return(INT_MAX);
1534
1535
78.8k
    hashValue = prefix->hashValue;
1536
78.8k
    index = hashValue & (ctxt->nsdb->hashSize - 1);
1537
78.8k
    bucket = &ctxt->nsdb->hash[index];
1538
78.8k
    tombstone = NULL;
1539
1540
125k
    while (bucket->hashValue) {
1541
109k
        if (bucket->index == INT_MAX) {
1542
8.39k
            if (tombstone == NULL)
1543
6.38k
                tombstone = bucket;
1544
100k
        } else if (bucket->hashValue == hashValue) {
1545
62.3k
            if (ctxt->nsTab[bucket->index * 2] == prefix->name) {
1546
62.3k
                if (bucketPtr != NULL)
1547
28.2k
                    *bucketPtr = bucket;
1548
62.3k
                return(bucket->index);
1549
62.3k
            }
1550
62.3k
        }
1551
1552
46.8k
        index++;
1553
46.8k
        bucket++;
1554
46.8k
        if (index == ctxt->nsdb->hashSize) {
1555
4.24k
            index = 0;
1556
4.24k
            bucket = ctxt->nsdb->hash;
1557
4.24k
        }
1558
46.8k
    }
1559
1560
16.4k
    if (bucketPtr != NULL)
1561
3.17k
        *bucketPtr = tombstone ? tombstone : bucket;
1562
16.4k
    return(INT_MAX);
1563
78.8k
}
1564
1565
/**
1566
 * xmlParserNsLookupUri:
1567
 * @ctxt: parser context
1568
 * @prefix: namespace prefix
1569
 *
1570
 * Lookup namespace URI with given prefix.
1571
 *
1572
 * Returns the namespace URI on success, NULL if no namespace was found.
1573
 */
1574
static const xmlChar *
1575
4.08M
xmlParserNsLookupUri(xmlParserCtxtPtr ctxt, const xmlHashedString *prefix) {
1576
4.08M
    const xmlChar *ret;
1577
4.08M
    int nsIndex;
1578
1579
4.08M
    if (prefix->name == ctxt->str_xml)
1580
180
        return(ctxt->str_xml_ns);
1581
1582
    /*
1583
     * minNsIndex is used when building an entity tree. We must
1584
     * ignore namespaces declared outside the entity.
1585
     */
1586
4.08M
    nsIndex = xmlParserNsLookup(ctxt, prefix, NULL);
1587
4.08M
    if ((nsIndex == INT_MAX) || (nsIndex < ctxt->nsdb->minNsIndex))
1588
3.73M
        return(NULL);
1589
1590
353k
    ret = ctxt->nsTab[nsIndex * 2 + 1];
1591
353k
    if (ret[0] == 0)
1592
322
        ret = NULL;
1593
353k
    return(ret);
1594
4.08M
}
1595
1596
/**
1597
 * xmlParserNsLookupSax:
1598
 * @ctxt: parser context
1599
 * @prefix: namespace prefix
1600
 *
1601
 * Lookup extra data for the given prefix. This returns data stored
1602
 * with xmlParserNsUdpateSax.
1603
 *
1604
 * Returns the data on success, NULL if no namespace was found.
1605
 */
1606
void *
1607
360k
xmlParserNsLookupSax(xmlParserCtxtPtr ctxt, const xmlChar *prefix) {
1608
360k
    xmlHashedString hprefix;
1609
360k
    int nsIndex;
1610
1611
360k
    if (prefix == ctxt->str_xml)
1612
10.3k
        return(NULL);
1613
1614
350k
    hprefix.name = prefix;
1615
350k
    if (prefix != NULL)
1616
7.99k
        hprefix.hashValue = xmlDictComputeHash(ctxt->dict, prefix);
1617
342k
    else
1618
342k
        hprefix.hashValue = 0;
1619
350k
    nsIndex = xmlParserNsLookup(ctxt, &hprefix, NULL);
1620
350k
    if ((nsIndex == INT_MAX) || (nsIndex < ctxt->nsdb->minNsIndex))
1621
0
        return(NULL);
1622
1623
350k
    return(ctxt->nsdb->extra[nsIndex].saxData);
1624
350k
}
1625
1626
/**
1627
 * xmlParserNsUpdateSax:
1628
 * @ctxt: parser context
1629
 * @prefix: namespace prefix
1630
 * @saxData: extra data for SAX handler
1631
 *
1632
 * Sets or updates extra data for the given prefix. This value will be
1633
 * returned by xmlParserNsLookupSax as long as the namespace with the
1634
 * given prefix is in scope.
1635
 *
1636
 * Returns the data on success, NULL if no namespace was found.
1637
 */
1638
int
1639
xmlParserNsUpdateSax(xmlParserCtxtPtr ctxt, const xmlChar *prefix,
1640
23.3k
                     void *saxData) {
1641
23.3k
    xmlHashedString hprefix;
1642
23.3k
    int nsIndex;
1643
1644
23.3k
    if (prefix == ctxt->str_xml)
1645
0
        return(-1);
1646
1647
23.3k
    hprefix.name = prefix;
1648
23.3k
    if (prefix != NULL)
1649
15.5k
        hprefix.hashValue = xmlDictComputeHash(ctxt->dict, prefix);
1650
7.81k
    else
1651
7.81k
        hprefix.hashValue = 0;
1652
23.3k
    nsIndex = xmlParserNsLookup(ctxt, &hprefix, NULL);
1653
23.3k
    if ((nsIndex == INT_MAX) || (nsIndex < ctxt->nsdb->minNsIndex))
1654
0
        return(-1);
1655
1656
23.3k
    ctxt->nsdb->extra[nsIndex].saxData = saxData;
1657
23.3k
    return(0);
1658
23.3k
}
1659
1660
/**
1661
 * xmlParserNsGrow:
1662
 * @ctxt: parser context
1663
 *
1664
 * Grows the namespace tables.
1665
 *
1666
 * Returns 0 on success, -1 if a memory allocation failed.
1667
 */
1668
static int
1669
930
xmlParserNsGrow(xmlParserCtxtPtr ctxt) {
1670
930
    const xmlChar **table;
1671
930
    xmlParserNsExtra *extra;
1672
930
    int newSize;
1673
1674
930
    newSize = xmlGrowCapacity(ctxt->nsMax,
1675
930
                              sizeof(table[0]) + sizeof(extra[0]),
1676
930
                              16, XML_MAX_ITEMS);
1677
930
    if (newSize < 0)
1678
0
        goto error;
1679
1680
930
    table = xmlRealloc(ctxt->nsTab, 2 * newSize * sizeof(table[0]));
1681
930
    if (table == NULL)
1682
0
        goto error;
1683
930
    ctxt->nsTab = table;
1684
1685
930
    extra = xmlRealloc(ctxt->nsdb->extra, newSize * sizeof(extra[0]));
1686
930
    if (extra == NULL)
1687
0
        goto error;
1688
930
    ctxt->nsdb->extra = extra;
1689
1690
930
    ctxt->nsMax = newSize;
1691
930
    return(0);
1692
1693
0
error:
1694
0
    xmlErrMemory(ctxt);
1695
0
    return(-1);
1696
930
}
1697
1698
/**
1699
 * xmlParserNsPush:
1700
 * @ctxt: parser context
1701
 * @prefix: prefix with hash value
1702
 * @uri: uri with hash value
1703
 * @saxData: extra data for SAX handler
1704
 * @defAttr: whether the namespace comes from a default attribute
1705
 *
1706
 * Push a new namespace on the table.
1707
 *
1708
 * Returns 1 if the namespace was pushed, 0 if the namespace was ignored,
1709
 * -1 if a memory allocation failed.
1710
 */
1711
static int
1712
xmlParserNsPush(xmlParserCtxtPtr ctxt, const xmlHashedString *prefix,
1713
23.9k
                const xmlHashedString *uri, void *saxData, int defAttr) {
1714
23.9k
    xmlParserNsBucket *bucket = NULL;
1715
23.9k
    xmlParserNsExtra *extra;
1716
23.9k
    const xmlChar **ns;
1717
23.9k
    unsigned hashValue, nsIndex, oldIndex;
1718
1719
23.9k
    if ((prefix != NULL) && (prefix->name == ctxt->str_xml))
1720
0
        return(0);
1721
1722
23.9k
    if ((ctxt->nsNr >= ctxt->nsMax) && (xmlParserNsGrow(ctxt) < 0)) {
1723
0
        xmlErrMemory(ctxt);
1724
0
        return(-1);
1725
0
    }
1726
1727
    /*
1728
     * Default namespace and 'xml' namespace
1729
     */
1730
23.9k
    if ((prefix == NULL) || (prefix->name == NULL)) {
1731
7.96k
        oldIndex = ctxt->nsdb->defaultNsIndex;
1732
1733
7.96k
        if (oldIndex != INT_MAX) {
1734
5.50k
            extra = &ctxt->nsdb->extra[oldIndex];
1735
1736
5.50k
            if (extra->elementId == ctxt->nsdb->elementId) {
1737
150
                if (defAttr == 0)
1738
150
                    xmlErrAttributeDup(ctxt, NULL, BAD_CAST "xmlns");
1739
150
                return(0);
1740
150
            }
1741
1742
5.35k
            if ((ctxt->options & XML_PARSE_NSCLEAN) &&
1743
5.35k
                (uri->name == ctxt->nsTab[oldIndex * 2 + 1]))
1744
0
                return(0);
1745
5.35k
        }
1746
1747
7.81k
        ctxt->nsdb->defaultNsIndex = ctxt->nsNr;
1748
7.81k
        goto populate_entry;
1749
7.96k
    }
1750
1751
    /*
1752
     * Hash table lookup
1753
     */
1754
16.0k
    oldIndex = xmlParserNsLookup(ctxt, prefix, &bucket);
1755
16.0k
    if (oldIndex != INT_MAX) {
1756
12.7k
        extra = &ctxt->nsdb->extra[oldIndex];
1757
1758
        /*
1759
         * Check for duplicate definitions on the same element.
1760
         */
1761
12.7k
        if (extra->elementId == ctxt->nsdb->elementId) {
1762
516
            if (defAttr == 0)
1763
516
                xmlErrAttributeDup(ctxt, BAD_CAST "xmlns", prefix->name);
1764
516
            return(0);
1765
516
        }
1766
1767
12.1k
        if ((ctxt->options & XML_PARSE_NSCLEAN) &&
1768
12.1k
            (uri->name == ctxt->nsTab[bucket->index * 2 + 1]))
1769
0
            return(0);
1770
1771
12.1k
        bucket->index = ctxt->nsNr;
1772
12.1k
        goto populate_entry;
1773
12.1k
    }
1774
1775
    /*
1776
     * Insert new bucket
1777
     */
1778
1779
3.32k
    hashValue = prefix->hashValue;
1780
1781
    /*
1782
     * Grow hash table, 50% fill factor
1783
     */
1784
3.32k
    if (ctxt->nsdb->hashElems + 1 > ctxt->nsdb->hashSize / 2) {
1785
220
        xmlParserNsBucket *newHash;
1786
220
        unsigned newSize, i, index;
1787
1788
220
        if (ctxt->nsdb->hashSize > UINT_MAX / 2) {
1789
0
            xmlErrMemory(ctxt);
1790
0
            return(-1);
1791
0
        }
1792
220
        newSize = ctxt->nsdb->hashSize ? ctxt->nsdb->hashSize * 2 : 16;
1793
220
        newHash = xmlMalloc(newSize * sizeof(newHash[0]));
1794
220
        if (newHash == NULL) {
1795
0
            xmlErrMemory(ctxt);
1796
0
            return(-1);
1797
0
        }
1798
220
        memset(newHash, 0, newSize * sizeof(newHash[0]));
1799
1800
9.66k
        for (i = 0; i < ctxt->nsdb->hashSize; i++) {
1801
9.44k
            unsigned hv = ctxt->nsdb->hash[i].hashValue;
1802
9.44k
            unsigned newIndex;
1803
1804
9.44k
            if ((hv == 0) || (ctxt->nsdb->hash[i].index == INT_MAX))
1805
9.11k
                continue;
1806
322
            newIndex = hv & (newSize - 1);
1807
1808
449
            while (newHash[newIndex].hashValue != 0) {
1809
127
                newIndex++;
1810
127
                if (newIndex == newSize)
1811
0
                    newIndex = 0;
1812
127
            }
1813
1814
322
            newHash[newIndex] = ctxt->nsdb->hash[i];
1815
322
        }
1816
1817
220
        xmlFree(ctxt->nsdb->hash);
1818
220
        ctxt->nsdb->hash = newHash;
1819
220
        ctxt->nsdb->hashSize = newSize;
1820
1821
        /*
1822
         * Relookup
1823
         */
1824
220
        index = hashValue & (newSize - 1);
1825
1826
237
        while (newHash[index].hashValue != 0) {
1827
17
            index++;
1828
17
            if (index == newSize)
1829
0
                index = 0;
1830
17
        }
1831
1832
220
        bucket = &newHash[index];
1833
220
    }
1834
1835
3.32k
    bucket->hashValue = hashValue;
1836
3.32k
    bucket->index = ctxt->nsNr;
1837
3.32k
    ctxt->nsdb->hashElems++;
1838
3.32k
    oldIndex = INT_MAX;
1839
1840
23.3k
populate_entry:
1841
23.3k
    nsIndex = ctxt->nsNr;
1842
1843
23.3k
    ns = &ctxt->nsTab[nsIndex * 2];
1844
23.3k
    ns[0] = prefix ? prefix->name : NULL;
1845
23.3k
    ns[1] = uri->name;
1846
1847
23.3k
    extra = &ctxt->nsdb->extra[nsIndex];
1848
23.3k
    extra->saxData = saxData;
1849
23.3k
    extra->prefixHashValue = prefix ? prefix->hashValue : 0;
1850
23.3k
    extra->uriHashValue = uri->hashValue;
1851
23.3k
    extra->elementId = ctxt->nsdb->elementId;
1852
23.3k
    extra->oldIndex = oldIndex;
1853
1854
23.3k
    ctxt->nsNr++;
1855
1856
23.3k
    return(1);
1857
3.32k
}
1858
1859
/**
1860
 * xmlParserNsPop:
1861
 * @ctxt: an XML parser context
1862
 * @nr:  the number to pop
1863
 *
1864
 * Pops the top @nr namespaces and restores the hash table.
1865
 *
1866
 * Returns the number of namespaces popped.
1867
 */
1868
static int
1869
xmlParserNsPop(xmlParserCtxtPtr ctxt, int nr)
1870
13.6k
{
1871
13.6k
    int i;
1872
1873
    /* assert(nr <= ctxt->nsNr); */
1874
1875
36.9k
    for (i = ctxt->nsNr - 1; i >= ctxt->nsNr - nr; i--) {
1876
23.3k
        const xmlChar *prefix = ctxt->nsTab[i * 2];
1877
23.3k
        xmlParserNsExtra *extra = &ctxt->nsdb->extra[i];
1878
1879
23.3k
        if (prefix == NULL) {
1880
7.80k
            ctxt->nsdb->defaultNsIndex = extra->oldIndex;
1881
15.5k
        } else {
1882
15.5k
            xmlHashedString hprefix;
1883
15.5k
            xmlParserNsBucket *bucket = NULL;
1884
1885
15.5k
            hprefix.name = prefix;
1886
15.5k
            hprefix.hashValue = extra->prefixHashValue;
1887
15.5k
            xmlParserNsLookup(ctxt, &hprefix, &bucket);
1888
            /* assert(bucket && bucket->hashValue); */
1889
15.5k
            bucket->index = extra->oldIndex;
1890
15.5k
        }
1891
23.3k
    }
1892
1893
13.6k
    ctxt->nsNr -= nr;
1894
13.6k
    return(nr);
1895
13.6k
}
1896
1897
static int
1898
603
xmlCtxtGrowAttrs(xmlParserCtxtPtr ctxt) {
1899
603
    const xmlChar **atts;
1900
603
    unsigned *attallocs;
1901
603
    int newSize;
1902
1903
603
    newSize = xmlGrowCapacity(ctxt->maxatts / 5,
1904
603
                              sizeof(atts[0]) * 5 + sizeof(attallocs[0]),
1905
603
                              10, XML_MAX_ATTRS);
1906
603
    if (newSize < 0) {
1907
0
        xmlFatalErr(ctxt, XML_ERR_RESOURCE_LIMIT,
1908
0
                    "Maximum number of attributes exceeded");
1909
0
        return(-1);
1910
0
    }
1911
1912
603
    atts = xmlRealloc(ctxt->atts, newSize * sizeof(atts[0]) * 5);
1913
603
    if (atts == NULL)
1914
0
        goto mem_error;
1915
603
    ctxt->atts = atts;
1916
1917
603
    attallocs = xmlRealloc(ctxt->attallocs,
1918
603
                           newSize * sizeof(attallocs[0]));
1919
603
    if (attallocs == NULL)
1920
0
        goto mem_error;
1921
603
    ctxt->attallocs = attallocs;
1922
1923
603
    ctxt->maxatts = newSize * 5;
1924
1925
603
    return(0);
1926
1927
0
mem_error:
1928
0
    xmlErrMemory(ctxt);
1929
0
    return(-1);
1930
603
}
1931
1932
/**
1933
 * xmlCtxtPushInput:
1934
 * @ctxt:  an XML parser context
1935
 * @value:  the parser input
1936
 *
1937
 * Pushes a new parser input on top of the input stack
1938
 *
1939
 * Returns -1 in case of error, the index in the stack otherwise
1940
 */
1941
int
1942
xmlCtxtPushInput(xmlParserCtxtPtr ctxt, xmlParserInputPtr value)
1943
8.76k
{
1944
8.76k
    char *directory = NULL;
1945
8.76k
    int maxDepth;
1946
1947
8.76k
    if ((ctxt == NULL) || (value == NULL))
1948
0
        return(-1);
1949
1950
8.76k
    maxDepth = (ctxt->options & XML_PARSE_HUGE) ? 40 : 20;
1951
1952
8.76k
    if (ctxt->inputNr >= ctxt->inputMax) {
1953
81
        xmlParserInputPtr *tmp;
1954
81
        int newSize;
1955
1956
81
        newSize = xmlGrowCapacity(ctxt->inputMax, sizeof(tmp[0]),
1957
81
                                  5, maxDepth);
1958
81
        if (newSize < 0) {
1959
0
            xmlFatalErrMsg(ctxt, XML_ERR_RESOURCE_LIMIT,
1960
0
                           "Maximum entity nesting depth exceeded");
1961
0
            xmlHaltParser(ctxt);
1962
0
            return(-1);
1963
0
        }
1964
81
        tmp = xmlRealloc(ctxt->inputTab, newSize * sizeof(tmp[0]));
1965
81
        if (tmp == NULL) {
1966
0
            xmlErrMemory(ctxt);
1967
0
            return(-1);
1968
0
        }
1969
81
        ctxt->inputTab = tmp;
1970
81
        ctxt->inputMax = newSize;
1971
81
    }
1972
1973
8.76k
    if ((ctxt->inputNr == 0) && (value->filename != NULL)) {
1974
0
        directory = xmlParserGetDirectory(value->filename);
1975
0
        if (directory == NULL) {
1976
0
            xmlErrMemory(ctxt);
1977
0
            return(-1);
1978
0
        }
1979
0
    }
1980
1981
8.76k
    if (ctxt->input_id >= INT_MAX) {
1982
0
        xmlFatalErrMsg(ctxt, XML_ERR_RESOURCE_LIMIT, "Input ID overflow\n");
1983
0
        return(-1);
1984
0
    }
1985
1986
8.76k
    ctxt->inputTab[ctxt->inputNr] = value;
1987
8.76k
    ctxt->input = value;
1988
1989
8.76k
    if (ctxt->inputNr == 0) {
1990
793
        xmlFree(ctxt->directory);
1991
793
        ctxt->directory = directory;
1992
793
    }
1993
1994
    /*
1995
     * Internally, the input ID is only used to detect parameter entity
1996
     * boundaries. But there are entity loaders in downstream code that
1997
     * detect the main document by checking for "input_id == 1".
1998
     */
1999
8.76k
    value->id = ctxt->input_id++;
2000
2001
8.76k
    return(ctxt->inputNr++);
2002
8.76k
}
2003
2004
/**
2005
 * xmlCtxtPopInput:
2006
 * @ctxt: an XML parser context
2007
 *
2008
 * Pops the top parser input from the input stack
2009
 *
2010
 * Returns the input just removed
2011
 */
2012
xmlParserInputPtr
2013
xmlCtxtPopInput(xmlParserCtxtPtr ctxt)
2014
10.3k
{
2015
10.3k
    xmlParserInputPtr ret;
2016
2017
10.3k
    if (ctxt == NULL)
2018
0
        return(NULL);
2019
10.3k
    if (ctxt->inputNr <= 0)
2020
1.59k
        return (NULL);
2021
8.76k
    ctxt->inputNr--;
2022
8.76k
    if (ctxt->inputNr > 0)
2023
7.97k
        ctxt->input = ctxt->inputTab[ctxt->inputNr - 1];
2024
793
    else
2025
793
        ctxt->input = NULL;
2026
8.76k
    ret = ctxt->inputTab[ctxt->inputNr];
2027
8.76k
    ctxt->inputTab[ctxt->inputNr] = NULL;
2028
8.76k
    return (ret);
2029
10.3k
}
2030
2031
/**
2032
 * nodePush:
2033
 * @ctxt:  an XML parser context
2034
 * @value:  the element node
2035
 *
2036
 * DEPRECATED: Internal function, do not use.
2037
 *
2038
 * Pushes a new element node on top of the node stack
2039
 *
2040
 * Returns -1 in case of error, the index in the stack otherwise
2041
 */
2042
int
2043
nodePush(xmlParserCtxtPtr ctxt, xmlNodePtr value)
2044
4.08M
{
2045
4.08M
    if (ctxt == NULL)
2046
0
        return(0);
2047
2048
4.08M
    if (ctxt->nodeNr >= ctxt->nodeMax) {
2049
3.91k
        int maxDepth = (ctxt->options & XML_PARSE_HUGE) ? 2048 : 256;
2050
3.91k
        xmlNodePtr *tmp;
2051
3.91k
        int newSize;
2052
2053
3.91k
        newSize = xmlGrowCapacity(ctxt->nodeMax, sizeof(tmp[0]),
2054
3.91k
                                  10, maxDepth);
2055
3.91k
        if (newSize < 0) {
2056
54
            xmlFatalErrMsgInt(ctxt, XML_ERR_RESOURCE_LIMIT,
2057
54
                    "Excessive depth in document: %d,"
2058
54
                    " use XML_PARSE_HUGE option\n",
2059
54
                    ctxt->nodeNr);
2060
54
            xmlHaltParser(ctxt);
2061
54
            return(-1);
2062
54
        }
2063
2064
3.85k
  tmp = xmlRealloc(ctxt->nodeTab, newSize * sizeof(tmp[0]));
2065
3.85k
        if (tmp == NULL) {
2066
0
            xmlErrMemory(ctxt);
2067
0
            return (-1);
2068
0
        }
2069
3.85k
        ctxt->nodeTab = tmp;
2070
3.85k
  ctxt->nodeMax = newSize;
2071
3.85k
    }
2072
2073
4.08M
    ctxt->nodeTab[ctxt->nodeNr] = value;
2074
4.08M
    ctxt->node = value;
2075
4.08M
    return (ctxt->nodeNr++);
2076
4.08M
}
2077
2078
/**
2079
 * nodePop:
2080
 * @ctxt: an XML parser context
2081
 *
2082
 * DEPRECATED: Internal function, do not use.
2083
 *
2084
 * Pops the top element node from the node stack
2085
 *
2086
 * Returns the node just removed
2087
 */
2088
xmlNodePtr
2089
nodePop(xmlParserCtxtPtr ctxt)
2090
4.08M
{
2091
4.08M
    xmlNodePtr ret;
2092
2093
4.08M
    if (ctxt == NULL) return(NULL);
2094
4.08M
    if (ctxt->nodeNr <= 0)
2095
24
        return (NULL);
2096
4.08M
    ctxt->nodeNr--;
2097
4.08M
    if (ctxt->nodeNr > 0)
2098
4.08M
        ctxt->node = ctxt->nodeTab[ctxt->nodeNr - 1];
2099
136
    else
2100
136
        ctxt->node = NULL;
2101
4.08M
    ret = ctxt->nodeTab[ctxt->nodeNr];
2102
4.08M
    ctxt->nodeTab[ctxt->nodeNr] = NULL;
2103
4.08M
    return (ret);
2104
4.08M
}
2105
2106
/**
2107
 * nameNsPush:
2108
 * @ctxt:  an XML parser context
2109
 * @value:  the element name
2110
 * @prefix:  the element prefix
2111
 * @URI:  the element namespace name
2112
 * @line:  the current line number for error messages
2113
 * @nsNr:  the number of namespaces pushed on the namespace table
2114
 *
2115
 * Pushes a new element name/prefix/URL on top of the name stack
2116
 *
2117
 * Returns -1 in case of error, the index in the stack otherwise
2118
 */
2119
static int
2120
nameNsPush(xmlParserCtxtPtr ctxt, const xmlChar * value,
2121
           const xmlChar *prefix, const xmlChar *URI, int line, int nsNr)
2122
4.08M
{
2123
4.08M
    xmlStartTag *tag;
2124
2125
4.08M
    if (ctxt->nameNr >= ctxt->nameMax) {
2126
4.01k
        const xmlChar **tmp;
2127
4.01k
        xmlStartTag *tmp2;
2128
4.01k
        int newSize;
2129
2130
4.01k
        newSize = xmlGrowCapacity(ctxt->nameMax,
2131
4.01k
                                  sizeof(tmp[0]) + sizeof(tmp2[0]),
2132
4.01k
                                  10, XML_MAX_ITEMS);
2133
4.01k
        if (newSize < 0)
2134
0
            goto mem_error;
2135
2136
4.01k
        tmp = xmlRealloc(ctxt->nameTab, newSize * sizeof(tmp[0]));
2137
4.01k
        if (tmp == NULL)
2138
0
      goto mem_error;
2139
4.01k
  ctxt->nameTab = tmp;
2140
2141
4.01k
        tmp2 = xmlRealloc(ctxt->pushTab, newSize * sizeof(tmp2[0]));
2142
4.01k
        if (tmp2 == NULL)
2143
0
      goto mem_error;
2144
4.01k
  ctxt->pushTab = tmp2;
2145
2146
4.01k
        ctxt->nameMax = newSize;
2147
4.08M
    } else if (ctxt->pushTab == NULL) {
2148
721
        ctxt->pushTab = xmlMalloc(ctxt->nameMax * sizeof(ctxt->pushTab[0]));
2149
721
        if (ctxt->pushTab == NULL)
2150
0
            goto mem_error;
2151
721
    }
2152
4.08M
    ctxt->nameTab[ctxt->nameNr] = value;
2153
4.08M
    ctxt->name = value;
2154
4.08M
    tag = &ctxt->pushTab[ctxt->nameNr];
2155
4.08M
    tag->prefix = prefix;
2156
4.08M
    tag->URI = URI;
2157
4.08M
    tag->line = line;
2158
4.08M
    tag->nsNr = nsNr;
2159
4.08M
    return (ctxt->nameNr++);
2160
0
mem_error:
2161
0
    xmlErrMemory(ctxt);
2162
0
    return (-1);
2163
4.08M
}
2164
#ifdef LIBXML_PUSH_ENABLED
2165
/**
2166
 * nameNsPop:
2167
 * @ctxt: an XML parser context
2168
 *
2169
 * Pops the top element/prefix/URI name from the name stack
2170
 *
2171
 * Returns the name just removed
2172
 */
2173
static const xmlChar *
2174
nameNsPop(xmlParserCtxtPtr ctxt)
2175
{
2176
    const xmlChar *ret;
2177
2178
    if (ctxt->nameNr <= 0)
2179
        return (NULL);
2180
    ctxt->nameNr--;
2181
    if (ctxt->nameNr > 0)
2182
        ctxt->name = ctxt->nameTab[ctxt->nameNr - 1];
2183
    else
2184
        ctxt->name = NULL;
2185
    ret = ctxt->nameTab[ctxt->nameNr];
2186
    ctxt->nameTab[ctxt->nameNr] = NULL;
2187
    return (ret);
2188
}
2189
#endif /* LIBXML_PUSH_ENABLED */
2190
2191
/**
2192
 * namePop:
2193
 * @ctxt: an XML parser context
2194
 *
2195
 * DEPRECATED: Internal function, do not use.
2196
 *
2197
 * Pops the top element name from the name stack
2198
 *
2199
 * Returns the name just removed
2200
 */
2201
static const xmlChar *
2202
namePop(xmlParserCtxtPtr ctxt)
2203
4.08M
{
2204
4.08M
    const xmlChar *ret;
2205
2206
4.08M
    if ((ctxt == NULL) || (ctxt->nameNr <= 0))
2207
0
        return (NULL);
2208
4.08M
    ctxt->nameNr--;
2209
4.08M
    if (ctxt->nameNr > 0)
2210
4.08M
        ctxt->name = ctxt->nameTab[ctxt->nameNr - 1];
2211
301
    else
2212
301
        ctxt->name = NULL;
2213
4.08M
    ret = ctxt->nameTab[ctxt->nameNr];
2214
4.08M
    ctxt->nameTab[ctxt->nameNr] = NULL;
2215
4.08M
    return (ret);
2216
4.08M
}
2217
2218
4.29M
static int spacePush(xmlParserCtxtPtr ctxt, int val) {
2219
4.29M
    if (ctxt->spaceNr >= ctxt->spaceMax) {
2220
4.35k
        int *tmp;
2221
4.35k
        int newSize;
2222
2223
4.35k
        newSize = xmlGrowCapacity(ctxt->spaceMax, sizeof(tmp[0]),
2224
4.35k
                                  10, XML_MAX_ITEMS);
2225
4.35k
        if (newSize < 0) {
2226
0
      xmlErrMemory(ctxt);
2227
0
      return(-1);
2228
0
        }
2229
2230
4.35k
        tmp = xmlRealloc(ctxt->spaceTab, newSize * sizeof(tmp[0]));
2231
4.35k
        if (tmp == NULL) {
2232
0
      xmlErrMemory(ctxt);
2233
0
      return(-1);
2234
0
  }
2235
4.35k
  ctxt->spaceTab = tmp;
2236
2237
4.35k
        ctxt->spaceMax = newSize;
2238
4.35k
    }
2239
4.29M
    ctxt->spaceTab[ctxt->spaceNr] = val;
2240
4.29M
    ctxt->space = &ctxt->spaceTab[ctxt->spaceNr];
2241
4.29M
    return(ctxt->spaceNr++);
2242
4.29M
}
2243
2244
4.29M
static int spacePop(xmlParserCtxtPtr ctxt) {
2245
4.29M
    int ret;
2246
4.29M
    if (ctxt->spaceNr <= 0) return(0);
2247
4.29M
    ctxt->spaceNr--;
2248
4.29M
    if (ctxt->spaceNr > 0)
2249
4.29M
  ctxt->space = &ctxt->spaceTab[ctxt->spaceNr - 1];
2250
0
    else
2251
0
        ctxt->space = &ctxt->spaceTab[0];
2252
4.29M
    ret = ctxt->spaceTab[ctxt->spaceNr];
2253
4.29M
    ctxt->spaceTab[ctxt->spaceNr] = -1;
2254
4.29M
    return(ret);
2255
4.29M
}
2256
2257
/*
2258
 * Macros for accessing the content. Those should be used only by the parser,
2259
 * and not exported.
2260
 *
2261
 * Dirty macros, i.e. one often need to make assumption on the context to
2262
 * use them
2263
 *
2264
 *   CUR_PTR return the current pointer to the xmlChar to be parsed.
2265
 *           To be used with extreme caution since operations consuming
2266
 *           characters may move the input buffer to a different location !
2267
 *   CUR     returns the current xmlChar value, i.e. a 8 bit value if compiled
2268
 *           This should be used internally by the parser
2269
 *           only to compare to ASCII values otherwise it would break when
2270
 *           running with UTF-8 encoding.
2271
 *   RAW     same as CUR but in the input buffer, bypass any token
2272
 *           extraction that may have been done
2273
 *   NXT(n)  returns the n'th next xmlChar. Same as CUR is should be used only
2274
 *           to compare on ASCII based substring.
2275
 *   SKIP(n) Skip n xmlChar, and must also be used only to skip ASCII defined
2276
 *           strings without newlines within the parser.
2277
 *   NEXT1(l) Skip 1 xmlChar, and must also be used only to skip 1 non-newline ASCII
2278
 *           defined char within the parser.
2279
 * Clean macros, not dependent of an ASCII context, expect UTF-8 encoding
2280
 *
2281
 *   NEXT    Skip to the next character, this does the proper decoding
2282
 *           in UTF-8 mode. It also pop-up unfinished entities on the fly.
2283
 *   NEXTL(l) Skip the current unicode character of l xmlChars long.
2284
 *   CUR_SCHAR  same but operate on a string instead of the context
2285
 *   COPY_BUF  copy the current unicode char to the target buffer, increment
2286
 *            the index
2287
 *   GROW, SHRINK  handling of input buffers
2288
 */
2289
2290
21.5M
#define RAW (*ctxt->input->cur)
2291
398M
#define CUR (*ctxt->input->cur)
2292
9.23M
#define NXT(val) ctxt->input->cur[(val)]
2293
795M
#define CUR_PTR ctxt->input->cur
2294
12.8M
#define BASE_PTR ctxt->input->base
2295
2296
#define CMP4( s, c1, c2, c3, c4 ) \
2297
13.1M
  ( ((unsigned char *) s)[ 0 ] == c1 && ((unsigned char *) s)[ 1 ] == c2 && \
2298
6.58M
    ((unsigned char *) s)[ 2 ] == c3 && ((unsigned char *) s)[ 3 ] == c4 )
2299
#define CMP5( s, c1, c2, c3, c4, c5 ) \
2300
13.1M
  ( CMP4( s, c1, c2, c3, c4 ) && ((unsigned char *) s)[ 4 ] == c5 )
2301
#define CMP6( s, c1, c2, c3, c4, c5, c6 ) \
2302
13.1M
  ( CMP5( s, c1, c2, c3, c4, c5 ) && ((unsigned char *) s)[ 5 ] == c6 )
2303
#define CMP7( s, c1, c2, c3, c4, c5, c6, c7 ) \
2304
13.0M
  ( CMP6( s, c1, c2, c3, c4, c5, c6 ) && ((unsigned char *) s)[ 6 ] == c7 )
2305
#define CMP8( s, c1, c2, c3, c4, c5, c6, c7, c8 ) \
2306
13.0M
  ( CMP7( s, c1, c2, c3, c4, c5, c6, c7 ) && ((unsigned char *) s)[ 7 ] == c8 )
2307
#define CMP9( s, c1, c2, c3, c4, c5, c6, c7, c8, c9 ) \
2308
6.53M
  ( CMP8( s, c1, c2, c3, c4, c5, c6, c7, c8 ) && \
2309
6.53M
    ((unsigned char *) s)[ 8 ] == c9 )
2310
#define CMP10( s, c1, c2, c3, c4, c5, c6, c7, c8, c9, c10 ) \
2311
73
  ( CMP9( s, c1, c2, c3, c4, c5, c6, c7, c8, c9 ) && \
2312
73
    ((unsigned char *) s)[ 9 ] == c10 )
2313
2314
204k
#define SKIP(val) do {             \
2315
204k
    ctxt->input->cur += (val),ctxt->input->col+=(val);      \
2316
204k
    if (*ctxt->input->cur == 0)           \
2317
204k
        xmlParserGrow(ctxt);           \
2318
204k
  } while (0)
2319
2320
#define SKIPL(val) do {             \
2321
    int skipl;                \
2322
    for(skipl=0; skipl<val; skipl++) {          \
2323
  if (*(ctxt->input->cur) == '\n') {        \
2324
  ctxt->input->line++; ctxt->input->col = 1;      \
2325
  } else ctxt->input->col++;          \
2326
  ctxt->input->cur++;           \
2327
    }                 \
2328
    if (*ctxt->input->cur == 0)           \
2329
        xmlParserGrow(ctxt);            \
2330
  } while (0)
2331
2332
#define SHRINK \
2333
8.75M
    if (!PARSER_PROGRESSIVE(ctxt)) \
2334
8.75M
  xmlParserShrink(ctxt);
2335
2336
#define GROW \
2337
27.6M
    if ((!PARSER_PROGRESSIVE(ctxt)) && \
2338
27.6M
        (ctxt->input->end - ctxt->input->cur < INPUT_CHUNK)) \
2339
97.4k
  xmlParserGrow(ctxt);
2340
2341
4.33M
#define SKIP_BLANKS xmlSkipBlankChars(ctxt)
2342
2343
183k
#define SKIP_BLANKS_PE xmlSkipBlankCharsPE(ctxt)
2344
2345
454k
#define NEXT xmlNextChar(ctxt)
2346
2347
4.39M
#define NEXT1 {               \
2348
4.39M
  ctxt->input->col++;           \
2349
4.39M
  ctxt->input->cur++;           \
2350
4.39M
  if (*ctxt->input->cur == 0)         \
2351
4.39M
      xmlParserGrow(ctxt);           \
2352
4.39M
    }
2353
2354
450M
#define NEXTL(l) do {             \
2355
450M
    if (*(ctxt->input->cur) == '\n') {         \
2356
7.64M
  ctxt->input->line++; ctxt->input->col = 1;      \
2357
443M
    } else ctxt->input->col++;           \
2358
450M
    ctxt->input->cur += l;        \
2359
450M
  } while (0)
2360
2361
3.34M
#define CUR_SCHAR(s, l) xmlStringCurrentChar(ctxt, s, &l)
2362
2363
#define COPY_BUF(b, i, v)           \
2364
64.1M
    if (v < 0x80) b[i++] = v;           \
2365
64.1M
    else i += xmlCopyCharMultiByte(&b[i],v)
2366
2367
static int
2368
61.2M
xmlCurrentCharRecover(xmlParserCtxtPtr ctxt, int *len) {
2369
61.2M
    int c = xmlCurrentChar(ctxt, len);
2370
2371
61.2M
    if (c == XML_INVALID_CHAR)
2372
22.0M
        c = 0xFFFD; /* replacement character */
2373
2374
61.2M
    return(c);
2375
61.2M
}
2376
2377
/**
2378
 * xmlSkipBlankChars:
2379
 * @ctxt:  the XML parser context
2380
 *
2381
 * DEPRECATED: Internal function, do not use.
2382
 *
2383
 * Skip whitespace in the input stream.
2384
 *
2385
 * Returns the number of space chars skipped
2386
 */
2387
int
2388
4.47M
xmlSkipBlankChars(xmlParserCtxtPtr ctxt) {
2389
4.47M
    const xmlChar *cur;
2390
4.47M
    int res = 0;
2391
2392
4.47M
    cur = ctxt->input->cur;
2393
4.47M
    while (IS_BLANK_CH(*cur)) {
2394
263k
        if (*cur == '\n') {
2395
71.0k
            ctxt->input->line++; ctxt->input->col = 1;
2396
192k
        } else {
2397
192k
            ctxt->input->col++;
2398
192k
        }
2399
263k
        cur++;
2400
263k
        if (res < INT_MAX)
2401
263k
            res++;
2402
263k
        if (*cur == 0) {
2403
896
            ctxt->input->cur = cur;
2404
896
            xmlParserGrow(ctxt);
2405
896
            cur = ctxt->input->cur;
2406
896
        }
2407
263k
    }
2408
4.47M
    ctxt->input->cur = cur;
2409
2410
4.47M
    if (res > 4)
2411
12.8k
        GROW;
2412
2413
4.47M
    return(res);
2414
4.47M
}
2415
2416
static void
2417
7.92k
xmlPopPE(xmlParserCtxtPtr ctxt) {
2418
7.92k
    unsigned long consumed;
2419
7.92k
    xmlEntityPtr ent;
2420
2421
7.92k
    ent = ctxt->input->entity;
2422
2423
7.92k
    ent->flags &= ~XML_ENT_EXPANDING;
2424
2425
7.92k
    if ((ent->flags & XML_ENT_CHECKED) == 0) {
2426
34
        int result;
2427
2428
        /*
2429
         * Read the rest of the stream in case of errors. We want
2430
         * to account for the whole entity size.
2431
         */
2432
34
        do {
2433
34
            ctxt->input->cur = ctxt->input->end;
2434
34
            xmlParserShrink(ctxt);
2435
34
            result = xmlParserGrow(ctxt);
2436
34
        } while (result > 0);
2437
2438
34
        consumed = ctxt->input->consumed;
2439
34
        xmlSaturatedAddSizeT(&consumed,
2440
34
                             ctxt->input->end - ctxt->input->base);
2441
2442
34
        xmlSaturatedAdd(&ent->expandedSize, consumed);
2443
2444
        /*
2445
         * Add to sizeentities when parsing an external entity
2446
         * for the first time.
2447
         */
2448
34
        if (ent->etype == XML_EXTERNAL_PARAMETER_ENTITY) {
2449
0
            xmlSaturatedAdd(&ctxt->sizeentities, consumed);
2450
0
        }
2451
2452
34
        ent->flags |= XML_ENT_CHECKED;
2453
34
    }
2454
2455
7.92k
    xmlFreeInputStream(xmlCtxtPopInput(ctxt));
2456
2457
7.92k
    xmlParserEntityCheck(ctxt, ent->expandedSize);
2458
2459
7.92k
    GROW;
2460
7.92k
}
2461
2462
/**
2463
 * xmlSkipBlankCharsPE:
2464
 * @ctxt:  the XML parser context
2465
 *
2466
 * Skip whitespace in the input stream, also handling parameter
2467
 * entities.
2468
 *
2469
 * Returns the number of space chars skipped
2470
 */
2471
static int
2472
183k
xmlSkipBlankCharsPE(xmlParserCtxtPtr ctxt) {
2473
183k
    int res = 0;
2474
183k
    int inParam;
2475
183k
    int expandParam;
2476
2477
183k
    inParam = PARSER_IN_PE(ctxt);
2478
183k
    expandParam = PARSER_EXTERNAL(ctxt);
2479
2480
183k
    if (!inParam && !expandParam)
2481
135k
        return(xmlSkipBlankChars(ctxt));
2482
2483
    /*
2484
     * It's Okay to use CUR/NEXT here since all the blanks are on
2485
     * the ASCII range.
2486
     */
2487
88.8k
    while (PARSER_STOPPED(ctxt) == 0) {
2488
88.7k
        if (IS_BLANK_CH(CUR)) { /* CHECKED tstblanks.xml */
2489
33.2k
            NEXT;
2490
55.5k
        } else if (CUR == '%') {
2491
6.58k
            if ((expandParam == 0) ||
2492
6.58k
                (IS_BLANK_CH(NXT(1))) || (NXT(1) == 0))
2493
6.58k
                break;
2494
2495
            /*
2496
             * Expand parameter entity. We continue to consume
2497
             * whitespace at the start of the entity and possible
2498
             * even consume the whole entity and pop it. We might
2499
             * even pop multiple PEs in this loop.
2500
             */
2501
0
            xmlParsePEReference(ctxt);
2502
2503
0
            inParam = PARSER_IN_PE(ctxt);
2504
0
            expandParam = PARSER_EXTERNAL(ctxt);
2505
48.9k
        } else if (CUR == 0) {
2506
7.91k
            if (inParam == 0)
2507
0
                break;
2508
2509
7.91k
            xmlPopPE(ctxt);
2510
2511
7.91k
            inParam = PARSER_IN_PE(ctxt);
2512
7.91k
            expandParam = PARSER_EXTERNAL(ctxt);
2513
41.0k
        } else {
2514
41.0k
            break;
2515
41.0k
        }
2516
2517
        /*
2518
         * Also increase the counter when entering or exiting a PERef.
2519
         * The spec says: "When a parameter-entity reference is recognized
2520
         * in the DTD and included, its replacement text MUST be enlarged
2521
         * by the attachment of one leading and one following space (#x20)
2522
         * character."
2523
         */
2524
41.1k
        if (res < INT_MAX)
2525
41.1k
            res++;
2526
41.1k
    }
2527
2528
47.6k
    return(res);
2529
183k
}
2530
2531
/************************************************************************
2532
 *                  *
2533
 *    Commodity functions to handle entities      *
2534
 *                  *
2535
 ************************************************************************/
2536
2537
/**
2538
 * xmlPopInput:
2539
 * @ctxt:  an XML parser context
2540
 *
2541
 * DEPRECATED: Internal function, don't use.
2542
 *
2543
 * Returns the current xmlChar in the parser context
2544
 */
2545
xmlChar
2546
0
xmlPopInput(xmlParserCtxtPtr ctxt) {
2547
0
    xmlParserInputPtr input;
2548
2549
0
    if ((ctxt == NULL) || (ctxt->inputNr <= 1)) return(0);
2550
0
    input = xmlCtxtPopInput(ctxt);
2551
0
    xmlFreeInputStream(input);
2552
0
    if (*ctxt->input->cur == 0)
2553
0
        xmlParserGrow(ctxt);
2554
0
    return(CUR);
2555
0
}
2556
2557
/**
2558
 * xmlPushInput:
2559
 * @ctxt:  an XML parser context
2560
 * @input:  an XML parser input fragment (entity, XML fragment ...).
2561
 *
2562
 * DEPRECATED: Internal function, don't use.
2563
 *
2564
 * Push an input stream onto the stack.
2565
 *
2566
 * Returns -1 in case of error or the index in the input stack
2567
 */
2568
int
2569
0
xmlPushInput(xmlParserCtxtPtr ctxt, xmlParserInputPtr input) {
2570
0
    int ret;
2571
2572
0
    if ((ctxt == NULL) || (input == NULL))
2573
0
        return(-1);
2574
2575
0
    ret = xmlCtxtPushInput(ctxt, input);
2576
0
    if (ret >= 0)
2577
0
        GROW;
2578
0
    return(ret);
2579
0
}
2580
2581
/**
2582
 * xmlParseCharRef:
2583
 * @ctxt:  an XML parser context
2584
 *
2585
 * DEPRECATED: Internal function, don't use.
2586
 *
2587
 * Parse a numeric character reference. Always consumes '&'.
2588
 *
2589
 * [66] CharRef ::= '&#' [0-9]+ ';' |
2590
 *                  '&#x' [0-9a-fA-F]+ ';'
2591
 *
2592
 * [ WFC: Legal Character ]
2593
 * Characters referred to using character references must match the
2594
 * production for Char.
2595
 *
2596
 * Returns the value parsed (as an int), 0 in case of error
2597
 */
2598
int
2599
10.9k
xmlParseCharRef(xmlParserCtxtPtr ctxt) {
2600
10.9k
    int val = 0;
2601
10.9k
    int count = 0;
2602
2603
    /*
2604
     * Using RAW/CUR/NEXT is okay since we are working on ASCII range here
2605
     */
2606
10.9k
    if ((RAW == '&') && (NXT(1) == '#') &&
2607
10.9k
        (NXT(2) == 'x')) {
2608
3.12k
  SKIP(3);
2609
3.12k
  GROW;
2610
19.6k
  while ((RAW != ';') && (PARSER_STOPPED(ctxt) == 0)) {
2611
18.4k
      if (count++ > 20) {
2612
342
    count = 0;
2613
342
    GROW;
2614
342
      }
2615
18.4k
      if ((RAW >= '0') && (RAW <= '9'))
2616
9.19k
          val = val * 16 + (CUR - '0');
2617
9.26k
      else if ((RAW >= 'a') && (RAW <= 'f') && (count < 20))
2618
6.92k
          val = val * 16 + (CUR - 'a') + 10;
2619
2.34k
      else if ((RAW >= 'A') && (RAW <= 'F') && (count < 20))
2620
400
          val = val * 16 + (CUR - 'A') + 10;
2621
1.94k
      else {
2622
1.94k
    xmlFatalErr(ctxt, XML_ERR_INVALID_HEX_CHARREF, NULL);
2623
1.94k
    val = 0;
2624
1.94k
    break;
2625
1.94k
      }
2626
16.5k
      if (val > 0x110000)
2627
7.21k
          val = 0x110000;
2628
2629
16.5k
      NEXT;
2630
16.5k
      count++;
2631
16.5k
  }
2632
3.12k
  if (RAW == ';') {
2633
      /* on purpose to avoid reentrancy problems with NEXT and SKIP */
2634
1.17k
      ctxt->input->col++;
2635
1.17k
      ctxt->input->cur++;
2636
1.17k
  }
2637
7.87k
    } else if  ((RAW == '&') && (NXT(1) == '#')) {
2638
7.87k
  SKIP(2);
2639
7.87k
  GROW;
2640
23.3k
  while (RAW != ';') { /* loop blocked by count */
2641
16.3k
      if (count++ > 20) {
2642
0
    count = 0;
2643
0
    GROW;
2644
0
      }
2645
16.3k
      if ((RAW >= '0') && (RAW <= '9'))
2646
15.4k
          val = val * 10 + (CUR - '0');
2647
874
      else {
2648
874
    xmlFatalErr(ctxt, XML_ERR_INVALID_DEC_CHARREF, NULL);
2649
874
    val = 0;
2650
874
    break;
2651
874
      }
2652
15.4k
      if (val > 0x110000)
2653
0
          val = 0x110000;
2654
2655
15.4k
      NEXT;
2656
15.4k
      count++;
2657
15.4k
  }
2658
7.87k
  if (RAW == ';') {
2659
      /* on purpose to avoid reentrancy problems with NEXT and SKIP */
2660
7.00k
      ctxt->input->col++;
2661
7.00k
      ctxt->input->cur++;
2662
7.00k
  }
2663
7.87k
    } else {
2664
0
        if (RAW == '&')
2665
0
            SKIP(1);
2666
0
        xmlFatalErr(ctxt, XML_ERR_INVALID_CHARREF, NULL);
2667
0
    }
2668
2669
    /*
2670
     * [ WFC: Legal Character ]
2671
     * Characters referred to using character references must match the
2672
     * production for Char.
2673
     */
2674
10.9k
    if (val >= 0x110000) {
2675
0
        xmlFatalErrMsgInt(ctxt, XML_ERR_INVALID_CHAR,
2676
0
                "xmlParseCharRef: character reference out of bounds\n",
2677
0
          val);
2678
10.9k
    } else if (IS_CHAR(val)) {
2679
8.09k
        return(val);
2680
8.09k
    } else {
2681
2.90k
        xmlFatalErrMsgInt(ctxt, XML_ERR_INVALID_CHAR,
2682
2.90k
                          "xmlParseCharRef: invalid xmlChar value %d\n",
2683
2.90k
                    val);
2684
2.90k
    }
2685
2.90k
    return(0);
2686
10.9k
}
2687
2688
/**
2689
 * xmlParseStringCharRef:
2690
 * @ctxt:  an XML parser context
2691
 * @str:  a pointer to an index in the string
2692
 *
2693
 * parse Reference declarations, variant parsing from a string rather
2694
 * than an an input flow.
2695
 *
2696
 * [66] CharRef ::= '&#' [0-9]+ ';' |
2697
 *                  '&#x' [0-9a-fA-F]+ ';'
2698
 *
2699
 * [ WFC: Legal Character ]
2700
 * Characters referred to using character references must match the
2701
 * production for Char.
2702
 *
2703
 * Returns the value parsed (as an int), 0 in case of error, str will be
2704
 *         updated to the current value of the index
2705
 */
2706
static int
2707
40.7k
xmlParseStringCharRef(xmlParserCtxtPtr ctxt, const xmlChar **str) {
2708
40.7k
    const xmlChar *ptr;
2709
40.7k
    xmlChar cur;
2710
40.7k
    int val = 0;
2711
2712
40.7k
    if ((str == NULL) || (*str == NULL)) return(0);
2713
40.7k
    ptr = *str;
2714
40.7k
    cur = *ptr;
2715
40.7k
    if ((cur == '&') && (ptr[1] == '#') && (ptr[2] == 'x')) {
2716
7.40k
  ptr += 3;
2717
7.40k
  cur = *ptr;
2718
71.4k
  while (cur != ';') { /* Non input consuming loop */
2719
66.1k
      if ((cur >= '0') && (cur <= '9'))
2720
177
          val = val * 16 + (cur - '0');
2721
65.9k
      else if ((cur >= 'a') && (cur <= 'f'))
2722
16.1k
          val = val * 16 + (cur - 'a') + 10;
2723
49.8k
      else if ((cur >= 'A') && (cur <= 'F'))
2724
47.6k
          val = val * 16 + (cur - 'A') + 10;
2725
2.14k
      else {
2726
2.14k
    xmlFatalErr(ctxt, XML_ERR_INVALID_HEX_CHARREF, NULL);
2727
2.14k
    val = 0;
2728
2.14k
    break;
2729
2.14k
      }
2730
64.0k
      if (val > 0x110000)
2731
44.4k
          val = 0x110000;
2732
2733
64.0k
      ptr++;
2734
64.0k
      cur = *ptr;
2735
64.0k
  }
2736
7.40k
  if (cur == ';')
2737
5.25k
      ptr++;
2738
33.3k
    } else if  ((cur == '&') && (ptr[1] == '#')){
2739
33.3k
  ptr += 2;
2740
33.3k
  cur = *ptr;
2741
139k
  while (cur != ';') { /* Non input consuming loops */
2742
109k
      if ((cur >= '0') && (cur <= '9'))
2743
105k
          val = val * 10 + (cur - '0');
2744
4.20k
      else {
2745
4.20k
    xmlFatalErr(ctxt, XML_ERR_INVALID_DEC_CHARREF, NULL);
2746
4.20k
    val = 0;
2747
4.20k
    break;
2748
4.20k
      }
2749
105k
      if (val > 0x110000)
2750
54
          val = 0x110000;
2751
2752
105k
      ptr++;
2753
105k
      cur = *ptr;
2754
105k
  }
2755
33.3k
  if (cur == ';')
2756
29.1k
      ptr++;
2757
33.3k
    } else {
2758
0
  xmlFatalErr(ctxt, XML_ERR_INVALID_CHARREF, NULL);
2759
0
  return(0);
2760
0
    }
2761
40.7k
    *str = ptr;
2762
2763
    /*
2764
     * [ WFC: Legal Character ]
2765
     * Characters referred to using character references must match the
2766
     * production for Char.
2767
     */
2768
40.7k
    if (val >= 0x110000) {
2769
329
        xmlFatalErrMsgInt(ctxt, XML_ERR_INVALID_CHAR,
2770
329
                "xmlParseStringCharRef: character reference out of bounds\n",
2771
329
                val);
2772
40.4k
    } else if (IS_CHAR(val)) {
2773
33.1k
        return(val);
2774
33.1k
    } else {
2775
7.34k
        xmlFatalErrMsgInt(ctxt, XML_ERR_INVALID_CHAR,
2776
7.34k
        "xmlParseStringCharRef: invalid xmlChar value %d\n",
2777
7.34k
        val);
2778
7.34k
    }
2779
7.67k
    return(0);
2780
40.7k
}
2781
2782
/**
2783
 * xmlParserHandlePEReference:
2784
 * @ctxt:  the parser context
2785
 *
2786
 * DEPRECATED: Internal function, do not use.
2787
 *
2788
 * [69] PEReference ::= '%' Name ';'
2789
 *
2790
 * [ WFC: No Recursion ]
2791
 * A parsed entity must not contain a recursive
2792
 * reference to itself, either directly or indirectly.
2793
 *
2794
 * [ WFC: Entity Declared ]
2795
 * In a document without any DTD, a document with only an internal DTD
2796
 * subset which contains no parameter entity references, or a document
2797
 * with "standalone='yes'", ...  ... The declaration of a parameter
2798
 * entity must precede any reference to it...
2799
 *
2800
 * [ VC: Entity Declared ]
2801
 * In a document with an external subset or external parameter entities
2802
 * with "standalone='no'", ...  ... The declaration of a parameter entity
2803
 * must precede any reference to it...
2804
 *
2805
 * [ WFC: In DTD ]
2806
 * Parameter-entity references may only appear in the DTD.
2807
 * NOTE: misleading but this is handled.
2808
 *
2809
 * A PEReference may have been detected in the current input stream
2810
 * the handling is done accordingly to
2811
 *      http://www.w3.org/TR/REC-xml#entproc
2812
 * i.e.
2813
 *   - Included in literal in entity values
2814
 *   - Included as Parameter Entity reference within DTDs
2815
 */
2816
void
2817
0
xmlParserHandlePEReference(xmlParserCtxtPtr ctxt) {
2818
0
    xmlParsePEReference(ctxt);
2819
0
}
2820
2821
/**
2822
 * xmlStringLenDecodeEntities:
2823
 * @ctxt:  the parser context
2824
 * @str:  the input string
2825
 * @len: the string length
2826
 * @what:  combination of XML_SUBSTITUTE_REF and XML_SUBSTITUTE_PEREF
2827
 * @end:  an end marker xmlChar, 0 if none
2828
 * @end2:  an end marker xmlChar, 0 if none
2829
 * @end3:  an end marker xmlChar, 0 if none
2830
 *
2831
 * DEPRECATED: Internal function, don't use.
2832
 *
2833
 * Returns A newly allocated string with the substitution done. The caller
2834
 *      must deallocate it !
2835
 */
2836
xmlChar *
2837
xmlStringLenDecodeEntities(xmlParserCtxtPtr ctxt, const xmlChar *str, int len,
2838
                           int what ATTRIBUTE_UNUSED,
2839
0
                           xmlChar end, xmlChar end2, xmlChar end3) {
2840
0
    if ((ctxt == NULL) || (str == NULL) || (len < 0))
2841
0
        return(NULL);
2842
2843
0
    if ((str[len] != 0) ||
2844
0
        (end != 0) || (end2 != 0) || (end3 != 0))
2845
0
        return(NULL);
2846
2847
0
    return(xmlExpandEntitiesInAttValue(ctxt, str, 0));
2848
0
}
2849
2850
/**
2851
 * xmlStringDecodeEntities:
2852
 * @ctxt:  the parser context
2853
 * @str:  the input string
2854
 * @what:  combination of XML_SUBSTITUTE_REF and XML_SUBSTITUTE_PEREF
2855
 * @end:  an end marker xmlChar, 0 if none
2856
 * @end2:  an end marker xmlChar, 0 if none
2857
 * @end3:  an end marker xmlChar, 0 if none
2858
 *
2859
 * DEPRECATED: Internal function, don't use.
2860
 *
2861
 * Returns A newly allocated string with the substitution done. The caller
2862
 *      must deallocate it !
2863
 */
2864
xmlChar *
2865
xmlStringDecodeEntities(xmlParserCtxtPtr ctxt, const xmlChar *str,
2866
                        int what ATTRIBUTE_UNUSED,
2867
0
            xmlChar end, xmlChar  end2, xmlChar end3) {
2868
0
    if ((ctxt == NULL) || (str == NULL))
2869
0
        return(NULL);
2870
2871
0
    if ((end != 0) || (end2 != 0) || (end3 != 0))
2872
0
        return(NULL);
2873
2874
0
    return(xmlExpandEntitiesInAttValue(ctxt, str, 0));
2875
0
}
2876
2877
/************************************************************************
2878
 *                  *
2879
 *    Commodity functions, cleanup needed ?     *
2880
 *                  *
2881
 ************************************************************************/
2882
2883
/**
2884
 * areBlanks:
2885
 * @ctxt:  an XML parser context
2886
 * @str:  a xmlChar *
2887
 * @len:  the size of @str
2888
 * @blank_chars: we know the chars are blanks
2889
 *
2890
 * Is this a sequence of blank chars that one can ignore ?
2891
 *
2892
 * Returns 1 if ignorable 0 otherwise.
2893
 */
2894
2895
static int areBlanks(xmlParserCtxtPtr ctxt, const xmlChar *str, int len,
2896
0
                     int blank_chars) {
2897
0
    int i;
2898
0
    xmlNodePtr lastChild;
2899
2900
    /*
2901
     * Check for xml:space value.
2902
     */
2903
0
    if ((ctxt->space == NULL) || (*(ctxt->space) == 1) ||
2904
0
        (*(ctxt->space) == -2))
2905
0
  return(0);
2906
2907
    /*
2908
     * Check that the string is made of blanks
2909
     */
2910
0
    if (blank_chars == 0) {
2911
0
  for (i = 0;i < len;i++)
2912
0
      if (!(IS_BLANK_CH(str[i]))) return(0);
2913
0
    }
2914
2915
    /*
2916
     * Look if the element is mixed content in the DTD if available
2917
     */
2918
0
    if (ctxt->node == NULL) return(0);
2919
0
    if (ctxt->myDoc != NULL) {
2920
0
        xmlElementPtr elemDecl = NULL;
2921
0
        xmlDocPtr doc = ctxt->myDoc;
2922
0
        const xmlChar *prefix = NULL;
2923
2924
0
        if (ctxt->node->ns)
2925
0
            prefix = ctxt->node->ns->prefix;
2926
0
        if (doc->intSubset != NULL)
2927
0
            elemDecl = xmlHashLookup2(doc->intSubset->elements, ctxt->node->name,
2928
0
                                      prefix);
2929
0
        if ((elemDecl == NULL) && (doc->extSubset != NULL))
2930
0
            elemDecl = xmlHashLookup2(doc->extSubset->elements, ctxt->node->name,
2931
0
                                      prefix);
2932
0
        if (elemDecl != NULL) {
2933
0
            if (elemDecl->etype == XML_ELEMENT_TYPE_ELEMENT)
2934
0
                return(1);
2935
0
            if ((elemDecl->etype == XML_ELEMENT_TYPE_ANY) ||
2936
0
                (elemDecl->etype == XML_ELEMENT_TYPE_MIXED))
2937
0
                return(0);
2938
0
        }
2939
0
    }
2940
2941
    /*
2942
     * Otherwise, heuristic :-\
2943
     *
2944
     * When push parsing, we could be at the end of a chunk.
2945
     * This makes the look-ahead and consequently the NOBLANKS
2946
     * option unreliable.
2947
     */
2948
0
    if ((RAW != '<') && (RAW != 0xD)) return(0);
2949
0
    if ((ctxt->node->children == NULL) &&
2950
0
  (RAW == '<') && (NXT(1) == '/')) return(0);
2951
2952
0
    lastChild = xmlGetLastChild(ctxt->node);
2953
0
    if (lastChild == NULL) {
2954
0
        if ((ctxt->node->type != XML_ELEMENT_NODE) &&
2955
0
            (ctxt->node->content != NULL)) return(0);
2956
0
    } else if (xmlNodeIsText(lastChild))
2957
0
        return(0);
2958
0
    else if ((ctxt->node->children != NULL) &&
2959
0
             (xmlNodeIsText(ctxt->node->children)))
2960
0
        return(0);
2961
0
    return(1);
2962
0
}
2963
2964
/************************************************************************
2965
 *                  *
2966
 *    Extra stuff for namespace support     *
2967
 *  Relates to http://www.w3.org/TR/WD-xml-names      *
2968
 *                  *
2969
 ************************************************************************/
2970
2971
/**
2972
 * xmlSplitQName:
2973
 * @ctxt:  an XML parser context
2974
 * @name:  an XML parser context
2975
 * @prefixOut:  a xmlChar **
2976
 *
2977
 * DEPRECATED: Don't use.
2978
 *
2979
 * parse an UTF8 encoded XML qualified name string
2980
 *
2981
 * [NS 5] QName ::= (Prefix ':')? LocalPart
2982
 *
2983
 * [NS 6] Prefix ::= NCName
2984
 *
2985
 * [NS 7] LocalPart ::= NCName
2986
 *
2987
 * Returns the local part, and prefix is updated
2988
 *   to get the Prefix if any.
2989
 */
2990
2991
xmlChar *
2992
0
xmlSplitQName(xmlParserCtxtPtr ctxt, const xmlChar *name, xmlChar **prefixOut) {
2993
0
    xmlChar buf[XML_MAX_NAMELEN + 5];
2994
0
    xmlChar *buffer = NULL;
2995
0
    int len = 0;
2996
0
    int max = XML_MAX_NAMELEN;
2997
0
    xmlChar *ret = NULL;
2998
0
    xmlChar *prefix;
2999
0
    const xmlChar *cur = name;
3000
0
    int c;
3001
3002
0
    if (prefixOut == NULL) return(NULL);
3003
0
    *prefixOut = NULL;
3004
3005
0
    if (cur == NULL) return(NULL);
3006
3007
    /* nasty but well=formed */
3008
0
    if (cur[0] == ':')
3009
0
  return(xmlStrdup(name));
3010
3011
0
    c = *cur++;
3012
0
    while ((c != 0) && (c != ':') && (len < max)) { /* tested bigname.xml */
3013
0
  buf[len++] = c;
3014
0
  c = *cur++;
3015
0
    }
3016
0
    if (len >= max) {
3017
  /*
3018
   * Okay someone managed to make a huge name, so he's ready to pay
3019
   * for the processing speed.
3020
   */
3021
0
  max = len * 2;
3022
3023
0
  buffer = xmlMalloc(max);
3024
0
  if (buffer == NULL) {
3025
0
      xmlErrMemory(ctxt);
3026
0
      return(NULL);
3027
0
  }
3028
0
  memcpy(buffer, buf, len);
3029
0
  while ((c != 0) && (c != ':')) { /* tested bigname.xml */
3030
0
      if (len + 10 > max) {
3031
0
          xmlChar *tmp;
3032
0
                int newSize;
3033
3034
0
                newSize = xmlGrowCapacity(max, 1, 1, XML_MAX_ITEMS);
3035
0
                if (newSize < 0) {
3036
0
        xmlErrMemory(ctxt);
3037
0
        xmlFree(buffer);
3038
0
        return(NULL);
3039
0
                }
3040
0
    tmp = xmlRealloc(buffer, newSize);
3041
0
    if (tmp == NULL) {
3042
0
        xmlErrMemory(ctxt);
3043
0
        xmlFree(buffer);
3044
0
        return(NULL);
3045
0
    }
3046
0
    buffer = tmp;
3047
0
    max = newSize;
3048
0
      }
3049
0
      buffer[len++] = c;
3050
0
      c = *cur++;
3051
0
  }
3052
0
  buffer[len] = 0;
3053
0
    }
3054
3055
0
    if ((c == ':') && (*cur == 0)) {
3056
0
        if (buffer != NULL)
3057
0
      xmlFree(buffer);
3058
0
  return(xmlStrdup(name));
3059
0
    }
3060
3061
0
    if (buffer == NULL) {
3062
0
  ret = xmlStrndup(buf, len);
3063
0
        if (ret == NULL) {
3064
0
      xmlErrMemory(ctxt);
3065
0
      return(NULL);
3066
0
        }
3067
0
    } else {
3068
0
  ret = buffer;
3069
0
  buffer = NULL;
3070
0
  max = XML_MAX_NAMELEN;
3071
0
    }
3072
3073
3074
0
    if (c == ':') {
3075
0
  c = *cur;
3076
0
        prefix = ret;
3077
0
  if (c == 0) {
3078
0
      ret = xmlStrndup(BAD_CAST "", 0);
3079
0
            if (ret == NULL) {
3080
0
                xmlFree(prefix);
3081
0
                return(NULL);
3082
0
            }
3083
0
            *prefixOut = prefix;
3084
0
            return(ret);
3085
0
  }
3086
0
  len = 0;
3087
3088
  /*
3089
   * Check that the first character is proper to start
3090
   * a new name
3091
   */
3092
0
  if (!(((c >= 0x61) && (c <= 0x7A)) ||
3093
0
        ((c >= 0x41) && (c <= 0x5A)) ||
3094
0
        (c == '_') || (c == ':'))) {
3095
0
      int l;
3096
0
      int first = CUR_SCHAR(cur, l);
3097
3098
0
      if (!IS_LETTER(first) && (first != '_')) {
3099
0
    xmlFatalErrMsgStr(ctxt, XML_NS_ERR_QNAME,
3100
0
          "Name %s is not XML Namespace compliant\n",
3101
0
          name);
3102
0
      }
3103
0
  }
3104
0
  cur++;
3105
3106
0
  while ((c != 0) && (len < max)) { /* tested bigname2.xml */
3107
0
      buf[len++] = c;
3108
0
      c = *cur++;
3109
0
  }
3110
0
  if (len >= max) {
3111
      /*
3112
       * Okay someone managed to make a huge name, so he's ready to pay
3113
       * for the processing speed.
3114
       */
3115
0
      max = len * 2;
3116
3117
0
      buffer = xmlMalloc(max);
3118
0
      if (buffer == NULL) {
3119
0
          xmlErrMemory(ctxt);
3120
0
                xmlFree(prefix);
3121
0
    return(NULL);
3122
0
      }
3123
0
      memcpy(buffer, buf, len);
3124
0
      while (c != 0) { /* tested bigname2.xml */
3125
0
    if (len + 10 > max) {
3126
0
        xmlChar *tmp;
3127
0
                    int newSize;
3128
3129
0
                    newSize = xmlGrowCapacity(max, 1, 1, XML_MAX_ITEMS);
3130
0
                    if (newSize < 0) {
3131
0
                        xmlErrMemory(ctxt);
3132
0
                        xmlFree(buffer);
3133
0
                        return(NULL);
3134
0
                    }
3135
0
        tmp = xmlRealloc(buffer, newSize);
3136
0
        if (tmp == NULL) {
3137
0
      xmlErrMemory(ctxt);
3138
0
                        xmlFree(prefix);
3139
0
      xmlFree(buffer);
3140
0
      return(NULL);
3141
0
        }
3142
0
        buffer = tmp;
3143
0
                    max = newSize;
3144
0
    }
3145
0
    buffer[len++] = c;
3146
0
    c = *cur++;
3147
0
      }
3148
0
      buffer[len] = 0;
3149
0
  }
3150
3151
0
  if (buffer == NULL) {
3152
0
      ret = xmlStrndup(buf, len);
3153
0
            if (ret == NULL) {
3154
0
                xmlFree(prefix);
3155
0
                return(NULL);
3156
0
            }
3157
0
  } else {
3158
0
      ret = buffer;
3159
0
  }
3160
3161
0
        *prefixOut = prefix;
3162
0
    }
3163
3164
0
    return(ret);
3165
0
}
3166
3167
/************************************************************************
3168
 *                  *
3169
 *      The parser itself       *
3170
 *  Relates to http://www.w3.org/TR/REC-xml       *
3171
 *                  *
3172
 ************************************************************************/
3173
3174
/************************************************************************
3175
 *                  *
3176
 *  Routines to parse Name, NCName and NmToken      *
3177
 *                  *
3178
 ************************************************************************/
3179
3180
/*
3181
 * The two following functions are related to the change of accepted
3182
 * characters for Name and NmToken in the Revision 5 of XML-1.0
3183
 * They correspond to the modified production [4] and the new production [4a]
3184
 * changes in that revision. Also note that the macros used for the
3185
 * productions Letter, Digit, CombiningChar and Extender are not needed
3186
 * anymore.
3187
 * We still keep compatibility to pre-revision5 parsing semantic if the
3188
 * new XML_PARSE_OLD10 option is given to the parser.
3189
 */
3190
static int
3191
4.36M
xmlIsNameStartChar(xmlParserCtxtPtr ctxt, int c) {
3192
4.36M
    if ((ctxt->options & XML_PARSE_OLD10) == 0) {
3193
        /*
3194
   * Use the new checks of production [4] [4a] amd [5] of the
3195
   * Update 5 of XML-1.0
3196
   */
3197
4.36M
  if ((c != ' ') && (c != '>') && (c != '/') && /* accelerators */
3198
4.36M
      (((c >= 'a') && (c <= 'z')) ||
3199
4.36M
       ((c >= 'A') && (c <= 'Z')) ||
3200
4.36M
       (c == '_') || (c == ':') ||
3201
4.36M
       ((c >= 0xC0) && (c <= 0xD6)) ||
3202
4.36M
       ((c >= 0xD8) && (c <= 0xF6)) ||
3203
4.36M
       ((c >= 0xF8) && (c <= 0x2FF)) ||
3204
4.36M
       ((c >= 0x370) && (c <= 0x37D)) ||
3205
4.36M
       ((c >= 0x37F) && (c <= 0x1FFF)) ||
3206
4.36M
       ((c >= 0x200C) && (c <= 0x200D)) ||
3207
4.36M
       ((c >= 0x2070) && (c <= 0x218F)) ||
3208
4.36M
       ((c >= 0x2C00) && (c <= 0x2FEF)) ||
3209
4.36M
       ((c >= 0x3001) && (c <= 0xD7FF)) ||
3210
4.36M
       ((c >= 0xF900) && (c <= 0xFDCF)) ||
3211
4.36M
       ((c >= 0xFDF0) && (c <= 0xFFFD)) ||
3212
4.36M
       ((c >= 0x10000) && (c <= 0xEFFFF))))
3213
184k
      return(1);
3214
4.36M
    } else {
3215
0
        if (IS_LETTER(c) || (c == '_') || (c == ':'))
3216
0
      return(1);
3217
0
    }
3218
4.17M
    return(0);
3219
4.36M
}
3220
3221
static int
3222
7.91M
xmlIsNameChar(xmlParserCtxtPtr ctxt, int c) {
3223
7.91M
    if ((ctxt->options & XML_PARSE_OLD10) == 0) {
3224
        /*
3225
   * Use the new checks of production [4] [4a] amd [5] of the
3226
   * Update 5 of XML-1.0
3227
   */
3228
7.91M
  if ((c != ' ') && (c != '>') && (c != '/') && /* accelerators */
3229
7.91M
      (((c >= 'a') && (c <= 'z')) ||
3230
7.91M
       ((c >= 'A') && (c <= 'Z')) ||
3231
7.91M
       ((c >= '0') && (c <= '9')) || /* !start */
3232
7.91M
       (c == '_') || (c == ':') ||
3233
7.91M
       (c == '-') || (c == '.') || (c == 0xB7) || /* !start */
3234
7.91M
       ((c >= 0xC0) && (c <= 0xD6)) ||
3235
7.91M
       ((c >= 0xD8) && (c <= 0xF6)) ||
3236
7.91M
       ((c >= 0xF8) && (c <= 0x2FF)) ||
3237
7.91M
       ((c >= 0x300) && (c <= 0x36F)) || /* !start */
3238
7.91M
       ((c >= 0x370) && (c <= 0x37D)) ||
3239
7.91M
       ((c >= 0x37F) && (c <= 0x1FFF)) ||
3240
7.91M
       ((c >= 0x200C) && (c <= 0x200D)) ||
3241
7.91M
       ((c >= 0x203F) && (c <= 0x2040)) || /* !start */
3242
7.91M
       ((c >= 0x2070) && (c <= 0x218F)) ||
3243
7.91M
       ((c >= 0x2C00) && (c <= 0x2FEF)) ||
3244
7.91M
       ((c >= 0x3001) && (c <= 0xD7FF)) ||
3245
7.91M
       ((c >= 0xF900) && (c <= 0xFDCF)) ||
3246
7.91M
       ((c >= 0xFDF0) && (c <= 0xFFFD)) ||
3247
7.91M
       ((c >= 0x10000) && (c <= 0xEFFFF))))
3248
7.73M
       return(1);
3249
7.91M
    } else {
3250
0
        if ((IS_LETTER(c)) || (IS_DIGIT(c)) ||
3251
0
            (c == '.') || (c == '-') ||
3252
0
      (c == '_') || (c == ':') ||
3253
0
      (IS_COMBINING(c)) ||
3254
0
      (IS_EXTENDER(c)))
3255
0
      return(1);
3256
0
    }
3257
179k
    return(0);
3258
7.91M
}
3259
3260
static const xmlChar *
3261
47.4k
xmlParseNameComplex(xmlParserCtxtPtr ctxt) {
3262
47.4k
    const xmlChar *ret;
3263
47.4k
    int len = 0, l;
3264
47.4k
    int c;
3265
47.4k
    int maxLength = (ctxt->options & XML_PARSE_HUGE) ?
3266
0
                    XML_MAX_TEXT_LENGTH :
3267
47.4k
                    XML_MAX_NAME_LENGTH;
3268
3269
    /*
3270
     * Handler for more complex cases
3271
     */
3272
47.4k
    c = xmlCurrentChar(ctxt, &l);
3273
47.4k
    if ((ctxt->options & XML_PARSE_OLD10) == 0) {
3274
        /*
3275
   * Use the new checks of production [4] [4a] amd [5] of the
3276
   * Update 5 of XML-1.0
3277
   */
3278
47.4k
  if ((c == ' ') || (c == '>') || (c == '/') || /* accelerators */
3279
47.4k
      (!(((c >= 'a') && (c <= 'z')) ||
3280
17.5k
         ((c >= 'A') && (c <= 'Z')) ||
3281
17.5k
         (c == '_') || (c == ':') ||
3282
17.5k
         ((c >= 0xC0) && (c <= 0xD6)) ||
3283
17.5k
         ((c >= 0xD8) && (c <= 0xF6)) ||
3284
17.5k
         ((c >= 0xF8) && (c <= 0x2FF)) ||
3285
17.5k
         ((c >= 0x370) && (c <= 0x37D)) ||
3286
17.5k
         ((c >= 0x37F) && (c <= 0x1FFF)) ||
3287
17.5k
         ((c >= 0x200C) && (c <= 0x200D)) ||
3288
17.5k
         ((c >= 0x2070) && (c <= 0x218F)) ||
3289
17.5k
         ((c >= 0x2C00) && (c <= 0x2FEF)) ||
3290
17.5k
         ((c >= 0x3001) && (c <= 0xD7FF)) ||
3291
17.5k
         ((c >= 0xF900) && (c <= 0xFDCF)) ||
3292
17.5k
         ((c >= 0xFDF0) && (c <= 0xFFFD)) ||
3293
41.1k
         ((c >= 0x10000) && (c <= 0xEFFFF))))) {
3294
41.1k
      return(NULL);
3295
41.1k
  }
3296
6.30k
  len += l;
3297
6.30k
  NEXTL(l);
3298
6.30k
  c = xmlCurrentChar(ctxt, &l);
3299
509k
  while ((c != ' ') && (c != '>') && (c != '/') && /* accelerators */
3300
509k
         (((c >= 'a') && (c <= 'z')) ||
3301
509k
          ((c >= 'A') && (c <= 'Z')) ||
3302
509k
          ((c >= '0') && (c <= '9')) || /* !start */
3303
509k
          (c == '_') || (c == ':') ||
3304
509k
          (c == '-') || (c == '.') || (c == 0xB7) || /* !start */
3305
509k
          ((c >= 0xC0) && (c <= 0xD6)) ||
3306
509k
          ((c >= 0xD8) && (c <= 0xF6)) ||
3307
509k
          ((c >= 0xF8) && (c <= 0x2FF)) ||
3308
509k
          ((c >= 0x300) && (c <= 0x36F)) || /* !start */
3309
509k
          ((c >= 0x370) && (c <= 0x37D)) ||
3310
509k
          ((c >= 0x37F) && (c <= 0x1FFF)) ||
3311
509k
          ((c >= 0x200C) && (c <= 0x200D)) ||
3312
509k
          ((c >= 0x203F) && (c <= 0x2040)) || /* !start */
3313
509k
          ((c >= 0x2070) && (c <= 0x218F)) ||
3314
509k
          ((c >= 0x2C00) && (c <= 0x2FEF)) ||
3315
509k
          ((c >= 0x3001) && (c <= 0xD7FF)) ||
3316
509k
          ((c >= 0xF900) && (c <= 0xFDCF)) ||
3317
509k
          ((c >= 0xFDF0) && (c <= 0xFFFD)) ||
3318
509k
          ((c >= 0x10000) && (c <= 0xEFFFF))
3319
509k
    )) {
3320
503k
            if (len <= INT_MAX - l)
3321
503k
          len += l;
3322
503k
      NEXTL(l);
3323
503k
      c = xmlCurrentChar(ctxt, &l);
3324
503k
  }
3325
6.30k
    } else {
3326
0
  if ((c == ' ') || (c == '>') || (c == '/') || /* accelerators */
3327
0
      (!IS_LETTER(c) && (c != '_') &&
3328
0
       (c != ':'))) {
3329
0
      return(NULL);
3330
0
  }
3331
0
  len += l;
3332
0
  NEXTL(l);
3333
0
  c = xmlCurrentChar(ctxt, &l);
3334
3335
0
  while ((c != ' ') && (c != '>') && (c != '/') && /* test bigname.xml */
3336
0
         ((IS_LETTER(c)) || (IS_DIGIT(c)) ||
3337
0
    (c == '.') || (c == '-') ||
3338
0
    (c == '_') || (c == ':') ||
3339
0
    (IS_COMBINING(c)) ||
3340
0
    (IS_EXTENDER(c)))) {
3341
0
            if (len <= INT_MAX - l)
3342
0
          len += l;
3343
0
      NEXTL(l);
3344
0
      c = xmlCurrentChar(ctxt, &l);
3345
0
  }
3346
0
    }
3347
6.30k
    if (len > maxLength) {
3348
4
        xmlFatalErr(ctxt, XML_ERR_NAME_TOO_LONG, "Name");
3349
4
        return(NULL);
3350
4
    }
3351
6.30k
    if (ctxt->input->cur - ctxt->input->base < len) {
3352
        /*
3353
         * There were a couple of bugs where PERefs lead to to a change
3354
         * of the buffer. Check the buffer size to avoid passing an invalid
3355
         * pointer to xmlDictLookup.
3356
         */
3357
0
        xmlFatalErr(ctxt, XML_ERR_INTERNAL_ERROR,
3358
0
                    "unexpected change of input buffer");
3359
0
        return (NULL);
3360
0
    }
3361
6.30k
    if ((*ctxt->input->cur == '\n') && (ctxt->input->cur[-1] == '\r'))
3362
0
        ret = xmlDictLookup(ctxt->dict, ctxt->input->cur - (len + 1), len);
3363
6.30k
    else
3364
6.30k
        ret = xmlDictLookup(ctxt->dict, ctxt->input->cur - len, len);
3365
6.30k
    if (ret == NULL)
3366
0
        xmlErrMemory(ctxt);
3367
6.30k
    return(ret);
3368
6.30k
}
3369
3370
/**
3371
 * xmlParseName:
3372
 * @ctxt:  an XML parser context
3373
 *
3374
 * DEPRECATED: Internal function, don't use.
3375
 *
3376
 * parse an XML name.
3377
 *
3378
 * [4] NameChar ::= Letter | Digit | '.' | '-' | '_' | ':' |
3379
 *                  CombiningChar | Extender
3380
 *
3381
 * [5] Name ::= (Letter | '_' | ':') (NameChar)*
3382
 *
3383
 * [6] Names ::= Name (#x20 Name)*
3384
 *
3385
 * Returns the Name parsed or NULL
3386
 */
3387
3388
const xmlChar *
3389
155k
xmlParseName(xmlParserCtxtPtr ctxt) {
3390
155k
    const xmlChar *in;
3391
155k
    const xmlChar *ret;
3392
155k
    size_t count = 0;
3393
155k
    size_t maxLength = (ctxt->options & XML_PARSE_HUGE) ?
3394
0
                       XML_MAX_TEXT_LENGTH :
3395
155k
                       XML_MAX_NAME_LENGTH;
3396
3397
155k
    GROW;
3398
3399
    /*
3400
     * Accelerator for simple ASCII names
3401
     */
3402
155k
    in = ctxt->input->cur;
3403
155k
    if (((*in >= 0x61) && (*in <= 0x7A)) ||
3404
155k
  ((*in >= 0x41) && (*in <= 0x5A)) ||
3405
155k
  (*in == '_') || (*in == ':')) {
3406
112k
  in++;
3407
197k
  while (((*in >= 0x61) && (*in <= 0x7A)) ||
3408
197k
         ((*in >= 0x41) && (*in <= 0x5A)) ||
3409
197k
         ((*in >= 0x30) && (*in <= 0x39)) ||
3410
197k
         (*in == '_') || (*in == '-') ||
3411
197k
         (*in == ':') || (*in == '.'))
3412
84.3k
      in++;
3413
112k
  if ((*in > 0) && (*in < 0x80)) {
3414
107k
      count = in - ctxt->input->cur;
3415
107k
            if (count > maxLength) {
3416
0
                xmlFatalErr(ctxt, XML_ERR_NAME_TOO_LONG, "Name");
3417
0
                return(NULL);
3418
0
            }
3419
107k
      ret = xmlDictLookup(ctxt->dict, ctxt->input->cur, count);
3420
107k
      ctxt->input->cur = in;
3421
107k
      ctxt->input->col += count;
3422
107k
      if (ret == NULL)
3423
0
          xmlErrMemory(ctxt);
3424
107k
      return(ret);
3425
107k
  }
3426
112k
    }
3427
    /* accelerator for special cases */
3428
47.4k
    return(xmlParseNameComplex(ctxt));
3429
155k
}
3430
3431
static xmlHashedString
3432
4.29M
xmlParseNCNameComplex(xmlParserCtxtPtr ctxt) {
3433
4.29M
    xmlHashedString ret;
3434
4.29M
    int len = 0, l;
3435
4.29M
    int c;
3436
4.29M
    int maxLength = (ctxt->options & XML_PARSE_HUGE) ?
3437
0
                    XML_MAX_TEXT_LENGTH :
3438
4.29M
                    XML_MAX_NAME_LENGTH;
3439
4.29M
    size_t startPosition = 0;
3440
3441
4.29M
    ret.name = NULL;
3442
4.29M
    ret.hashValue = 0;
3443
3444
    /*
3445
     * Handler for more complex cases
3446
     */
3447
4.29M
    startPosition = CUR_PTR - BASE_PTR;
3448
4.29M
    c = xmlCurrentChar(ctxt, &l);
3449
4.29M
    if ((c == ' ') || (c == '>') || (c == '/') || /* accelerators */
3450
4.29M
  (!xmlIsNameStartChar(ctxt, c) || (c == ':'))) {
3451
4.18M
  return(ret);
3452
4.18M
    }
3453
3454
3.15M
    while ((c != ' ') && (c != '>') && (c != '/') && /* test bigname.xml */
3455
3.15M
     (xmlIsNameChar(ctxt, c) && (c != ':'))) {
3456
3.04M
        if (len <= INT_MAX - l)
3457
3.04M
      len += l;
3458
3.04M
  NEXTL(l);
3459
3.04M
  c = xmlCurrentChar(ctxt, &l);
3460
3.04M
    }
3461
109k
    if (len > maxLength) {
3462
66
        xmlFatalErr(ctxt, XML_ERR_NAME_TOO_LONG, "NCName");
3463
66
        return(ret);
3464
66
    }
3465
109k
    ret = xmlDictLookupHashed(ctxt->dict, (BASE_PTR + startPosition), len);
3466
109k
    if (ret.name == NULL)
3467
0
        xmlErrMemory(ctxt);
3468
109k
    return(ret);
3469
109k
}
3470
3471
/**
3472
 * xmlParseNCName:
3473
 * @ctxt:  an XML parser context
3474
 * @len:  length of the string parsed
3475
 *
3476
 * parse an XML name.
3477
 *
3478
 * [4NS] NCNameChar ::= Letter | Digit | '.' | '-' | '_' |
3479
 *                      CombiningChar | Extender
3480
 *
3481
 * [5NS] NCName ::= (Letter | '_') (NCNameChar)*
3482
 *
3483
 * Returns the Name parsed or NULL
3484
 */
3485
3486
static xmlHashedString
3487
8.41M
xmlParseNCName(xmlParserCtxtPtr ctxt) {
3488
8.41M
    const xmlChar *in, *e;
3489
8.41M
    xmlHashedString ret;
3490
8.41M
    size_t count = 0;
3491
8.41M
    size_t maxLength = (ctxt->options & XML_PARSE_HUGE) ?
3492
0
                       XML_MAX_TEXT_LENGTH :
3493
8.41M
                       XML_MAX_NAME_LENGTH;
3494
3495
8.41M
    ret.name = NULL;
3496
3497
    /*
3498
     * Accelerator for simple ASCII names
3499
     */
3500
8.41M
    in = ctxt->input->cur;
3501
8.41M
    e = ctxt->input->end;
3502
8.41M
    if ((((*in >= 0x61) && (*in <= 0x7A)) ||
3503
8.41M
   ((*in >= 0x41) && (*in <= 0x5A)) ||
3504
8.41M
   (*in == '_')) && (in < e)) {
3505
4.21M
  in++;
3506
5.10M
  while ((((*in >= 0x61) && (*in <= 0x7A)) ||
3507
5.10M
          ((*in >= 0x41) && (*in <= 0x5A)) ||
3508
5.10M
          ((*in >= 0x30) && (*in <= 0x39)) ||
3509
5.10M
          (*in == '_') || (*in == '-') ||
3510
5.10M
          (*in == '.')) && (in < e))
3511
889k
      in++;
3512
4.21M
  if (in >= e)
3513
19
      goto complex;
3514
4.21M
  if ((*in > 0) && (*in < 0x80)) {
3515
4.12M
      count = in - ctxt->input->cur;
3516
4.12M
            if (count > maxLength) {
3517
0
                xmlFatalErr(ctxt, XML_ERR_NAME_TOO_LONG, "NCName");
3518
0
                return(ret);
3519
0
            }
3520
4.12M
      ret = xmlDictLookupHashed(ctxt->dict, ctxt->input->cur, count);
3521
4.12M
      ctxt->input->cur = in;
3522
4.12M
      ctxt->input->col += count;
3523
4.12M
      if (ret.name == NULL) {
3524
0
          xmlErrMemory(ctxt);
3525
0
      }
3526
4.12M
      return(ret);
3527
4.12M
  }
3528
4.21M
    }
3529
4.29M
complex:
3530
4.29M
    return(xmlParseNCNameComplex(ctxt));
3531
8.41M
}
3532
3533
/**
3534
 * xmlParseNameAndCompare:
3535
 * @ctxt:  an XML parser context
3536
 *
3537
 * parse an XML name and compares for match
3538
 * (specialized for endtag parsing)
3539
 *
3540
 * Returns NULL for an illegal name, (xmlChar*) 1 for success
3541
 * and the name for mismatch
3542
 */
3543
3544
static const xmlChar *
3545
43.5k
xmlParseNameAndCompare(xmlParserCtxtPtr ctxt, xmlChar const *other) {
3546
43.5k
    register const xmlChar *cmp = other;
3547
43.5k
    register const xmlChar *in;
3548
43.5k
    const xmlChar *ret;
3549
3550
43.5k
    GROW;
3551
3552
43.5k
    in = ctxt->input->cur;
3553
52.9k
    while (*in != 0 && *in == *cmp) {
3554
9.40k
  ++in;
3555
9.40k
  ++cmp;
3556
9.40k
    }
3557
43.5k
    if (*cmp == 0 && (*in == '>' || IS_BLANK_CH (*in))) {
3558
  /* success */
3559
7.15k
  ctxt->input->col += in - ctxt->input->cur;
3560
7.15k
  ctxt->input->cur = in;
3561
7.15k
  return (const xmlChar*) 1;
3562
7.15k
    }
3563
    /* failure (or end of input buffer), check with full function */
3564
36.3k
    ret = xmlParseName (ctxt);
3565
    /* strings coming from the dictionary direct compare possible */
3566
36.3k
    if (ret == other) {
3567
154
  return (const xmlChar*) 1;
3568
154
    }
3569
36.2k
    return ret;
3570
36.3k
}
3571
3572
/**
3573
 * xmlParseStringName:
3574
 * @ctxt:  an XML parser context
3575
 * @str:  a pointer to the string pointer (IN/OUT)
3576
 *
3577
 * parse an XML name.
3578
 *
3579
 * [4] NameChar ::= Letter | Digit | '.' | '-' | '_' | ':' |
3580
 *                  CombiningChar | Extender
3581
 *
3582
 * [5] Name ::= (Letter | '_' | ':') (NameChar)*
3583
 *
3584
 * [6] Names ::= Name (#x20 Name)*
3585
 *
3586
 * Returns the Name parsed or NULL. The @str pointer
3587
 * is updated to the current location in the string.
3588
 */
3589
3590
static xmlChar *
3591
72.5k
xmlParseStringName(xmlParserCtxtPtr ctxt, const xmlChar** str) {
3592
72.5k
    xmlChar buf[XML_MAX_NAMELEN + 5];
3593
72.5k
    xmlChar *ret;
3594
72.5k
    const xmlChar *cur = *str;
3595
72.5k
    int len = 0, l;
3596
72.5k
    int c;
3597
72.5k
    int maxLength = (ctxt->options & XML_PARSE_HUGE) ?
3598
0
                    XML_MAX_TEXT_LENGTH :
3599
72.5k
                    XML_MAX_NAME_LENGTH;
3600
3601
72.5k
    c = CUR_SCHAR(cur, l);
3602
72.5k
    if (!xmlIsNameStartChar(ctxt, c)) {
3603
5.75k
  return(NULL);
3604
5.75k
    }
3605
3606
66.7k
    COPY_BUF(buf, len, c);
3607
66.7k
    cur += l;
3608
66.7k
    c = CUR_SCHAR(cur, l);
3609
164k
    while (xmlIsNameChar(ctxt, c)) {
3610
99.2k
  COPY_BUF(buf, len, c);
3611
99.2k
  cur += l;
3612
99.2k
  c = CUR_SCHAR(cur, l);
3613
99.2k
  if (len >= XML_MAX_NAMELEN) { /* test bigentname.xml */
3614
      /*
3615
       * Okay someone managed to make a huge name, so he's ready to pay
3616
       * for the processing speed.
3617
       */
3618
1.05k
      xmlChar *buffer;
3619
1.05k
      int max = len * 2;
3620
3621
1.05k
      buffer = xmlMalloc(max);
3622
1.05k
      if (buffer == NULL) {
3623
0
          xmlErrMemory(ctxt);
3624
0
    return(NULL);
3625
0
      }
3626
1.05k
      memcpy(buffer, buf, len);
3627
3.10M
      while (xmlIsNameChar(ctxt, c)) {
3628
3.10M
    if (len + 10 > max) {
3629
10.1k
        xmlChar *tmp;
3630
10.1k
                    int newSize;
3631
3632
10.1k
                    newSize = xmlGrowCapacity(max, 1, 1, maxLength);
3633
10.1k
                    if (newSize < 0) {
3634
1
                        xmlFatalErr(ctxt, XML_ERR_NAME_TOO_LONG, "NCName");
3635
1
                        xmlFree(buffer);
3636
1
                        return(NULL);
3637
1
                    }
3638
10.1k
        tmp = xmlRealloc(buffer, newSize);
3639
10.1k
        if (tmp == NULL) {
3640
0
      xmlErrMemory(ctxt);
3641
0
      xmlFree(buffer);
3642
0
      return(NULL);
3643
0
        }
3644
10.1k
        buffer = tmp;
3645
10.1k
                    max = newSize;
3646
10.1k
    }
3647
3.10M
    COPY_BUF(buffer, len, c);
3648
3.10M
    cur += l;
3649
3.10M
    c = CUR_SCHAR(cur, l);
3650
3.10M
      }
3651
1.05k
      buffer[len] = 0;
3652
1.05k
      *str = cur;
3653
1.05k
      return(buffer);
3654
1.05k
  }
3655
99.2k
    }
3656
65.7k
    if (len > maxLength) {
3657
0
        xmlFatalErr(ctxt, XML_ERR_NAME_TOO_LONG, "NCName");
3658
0
        return(NULL);
3659
0
    }
3660
65.7k
    *str = cur;
3661
65.7k
    ret = xmlStrndup(buf, len);
3662
65.7k
    if (ret == NULL)
3663
0
        xmlErrMemory(ctxt);
3664
65.7k
    return(ret);
3665
65.7k
}
3666
3667
/**
3668
 * xmlParseNmtoken:
3669
 * @ctxt:  an XML parser context
3670
 *
3671
 * DEPRECATED: Internal function, don't use.
3672
 *
3673
 * parse an XML Nmtoken.
3674
 *
3675
 * [7] Nmtoken ::= (NameChar)+
3676
 *
3677
 * [8] Nmtokens ::= Nmtoken (#x20 Nmtoken)*
3678
 *
3679
 * Returns the Nmtoken parsed or NULL
3680
 */
3681
3682
xmlChar *
3683
15.8k
xmlParseNmtoken(xmlParserCtxtPtr ctxt) {
3684
15.8k
    xmlChar buf[XML_MAX_NAMELEN + 5];
3685
15.8k
    xmlChar *ret;
3686
15.8k
    int len = 0, l;
3687
15.8k
    int c;
3688
15.8k
    int maxLength = (ctxt->options & XML_PARSE_HUGE) ?
3689
0
                    XML_MAX_TEXT_LENGTH :
3690
15.8k
                    XML_MAX_NAME_LENGTH;
3691
3692
15.8k
    c = xmlCurrentChar(ctxt, &l);
3693
3694
127k
    while (xmlIsNameChar(ctxt, c)) {
3695
112k
  COPY_BUF(buf, len, c);
3696
112k
  NEXTL(l);
3697
112k
  c = xmlCurrentChar(ctxt, &l);
3698
112k
  if (len >= XML_MAX_NAMELEN) {
3699
      /*
3700
       * Okay someone managed to make a huge token, so he's ready to pay
3701
       * for the processing speed.
3702
       */
3703
792
      xmlChar *buffer;
3704
792
      int max = len * 2;
3705
3706
792
      buffer = xmlMalloc(max);
3707
792
      if (buffer == NULL) {
3708
0
          xmlErrMemory(ctxt);
3709
0
    return(NULL);
3710
0
      }
3711
792
      memcpy(buffer, buf, len);
3712
1.36M
      while (xmlIsNameChar(ctxt, c)) {
3713
1.36M
    if (len + 10 > max) {
3714
1.43k
        xmlChar *tmp;
3715
1.43k
                    int newSize;
3716
3717
1.43k
                    newSize = xmlGrowCapacity(max, 1, 1, maxLength);
3718
1.43k
                    if (newSize < 0) {
3719
60
                        xmlFatalErr(ctxt, XML_ERR_NAME_TOO_LONG, "NmToken");
3720
60
                        xmlFree(buffer);
3721
60
                        return(NULL);
3722
60
                    }
3723
1.37k
        tmp = xmlRealloc(buffer, newSize);
3724
1.37k
        if (tmp == NULL) {
3725
0
      xmlErrMemory(ctxt);
3726
0
      xmlFree(buffer);
3727
0
      return(NULL);
3728
0
        }
3729
1.37k
        buffer = tmp;
3730
1.37k
                    max = newSize;
3731
1.37k
    }
3732
1.36M
    COPY_BUF(buffer, len, c);
3733
1.36M
    NEXTL(l);
3734
1.36M
    c = xmlCurrentChar(ctxt, &l);
3735
1.36M
      }
3736
732
      buffer[len] = 0;
3737
732
      return(buffer);
3738
792
  }
3739
112k
    }
3740
15.0k
    if (len == 0)
3741
4.93k
        return(NULL);
3742
10.1k
    if (len > maxLength) {
3743
0
        xmlFatalErr(ctxt, XML_ERR_NAME_TOO_LONG, "NmToken");
3744
0
        return(NULL);
3745
0
    }
3746
10.1k
    ret = xmlStrndup(buf, len);
3747
10.1k
    if (ret == NULL)
3748
0
        xmlErrMemory(ctxt);
3749
10.1k
    return(ret);
3750
10.1k
}
3751
3752
/**
3753
 * xmlExpandPEsInEntityValue:
3754
 * @ctxt:  parser context
3755
 * @buf:  string buffer
3756
 * @str:  entity value
3757
 * @length:  size of entity value
3758
 * @depth:  nesting depth
3759
 *
3760
 * Validate an entity value and expand parameter entities.
3761
 */
3762
static void
3763
xmlExpandPEsInEntityValue(xmlParserCtxtPtr ctxt, xmlSBuf *buf,
3764
27.7k
                          const xmlChar *str, int length, int depth) {
3765
27.7k
    int maxDepth = (ctxt->options & XML_PARSE_HUGE) ? 40 : 20;
3766
27.7k
    const xmlChar *end, *chunk;
3767
27.7k
    int c, l;
3768
3769
27.7k
    if (str == NULL)
3770
0
        return;
3771
3772
27.7k
    depth += 1;
3773
27.7k
    if (depth > maxDepth) {
3774
0
  xmlFatalErrMsg(ctxt, XML_ERR_RESOURCE_LIMIT,
3775
0
                       "Maximum entity nesting depth exceeded");
3776
0
  return;
3777
0
    }
3778
3779
27.7k
    end = str + length;
3780
27.7k
    chunk = str;
3781
3782
107M
    while ((str < end) && (!PARSER_STOPPED(ctxt))) {
3783
107M
        c = *str;
3784
3785
107M
        if (c >= 0x80) {
3786
103M
            l = xmlUTF8MultibyteLen(ctxt, str,
3787
103M
                    "invalid character in entity value\n");
3788
103M
            if (l == 0) {
3789
13.6M
                if (chunk < str)
3790
118k
                    xmlSBufAddString(buf, chunk, str - chunk);
3791
13.6M
                xmlSBufAddReplChar(buf);
3792
13.6M
                str += 1;
3793
13.6M
                chunk = str;
3794
90.2M
            } else {
3795
90.2M
                str += l;
3796
90.2M
            }
3797
103M
        } else if (c == '&') {
3798
55.1k
            if (str[1] == '#') {
3799
32.0k
                if (chunk < str)
3800
28.0k
                    xmlSBufAddString(buf, chunk, str - chunk);
3801
3802
32.0k
                c = xmlParseStringCharRef(ctxt, &str);
3803
32.0k
                if (c == 0)
3804
7.67k
                    return;
3805
3806
24.4k
                xmlSBufAddChar(buf, c);
3807
3808
24.4k
                chunk = str;
3809
24.4k
            } else {
3810
23.0k
                xmlChar *name;
3811
3812
                /*
3813
                 * General entity references are checked for
3814
                 * syntactic validity.
3815
                 */
3816
23.0k
                str++;
3817
23.0k
                name = xmlParseStringName(ctxt, &str);
3818
3819
23.0k
                if ((name == NULL) || (*str++ != ';')) {
3820
1.54k
                    xmlFatalErrMsg(ctxt, XML_ERR_ENTITY_CHAR_ERROR,
3821
1.54k
                            "EntityValue: '&' forbidden except for entities "
3822
1.54k
                            "references\n");
3823
1.54k
                    xmlFree(name);
3824
1.54k
                    return;
3825
1.54k
                }
3826
3827
21.4k
                xmlFree(name);
3828
21.4k
            }
3829
3.18M
        } else if (c == '%') {
3830
6.23k
            xmlEntityPtr ent;
3831
3832
6.23k
            if (chunk < str)
3833
5.69k
                xmlSBufAddString(buf, chunk, str - chunk);
3834
3835
6.23k
            ent = xmlParseStringPEReference(ctxt, &str);
3836
6.23k
            if (ent == NULL)
3837
6.21k
                return;
3838
3839
18
            if (!PARSER_EXTERNAL(ctxt)) {
3840
18
                xmlFatalErr(ctxt, XML_ERR_ENTITY_PE_INTERNAL, NULL);
3841
18
                return;
3842
18
            }
3843
3844
0
            if (ent->content == NULL) {
3845
                /*
3846
                 * Note: external parsed entities will not be loaded,
3847
                 * it is not required for a non-validating parser to
3848
                 * complete external PEReferences coming from the
3849
                 * internal subset
3850
                 */
3851
0
                if (((ctxt->options & XML_PARSE_NO_XXE) == 0) &&
3852
0
                    ((ctxt->replaceEntities) ||
3853
0
                     (ctxt->validate))) {
3854
0
                    xmlLoadEntityContent(ctxt, ent);
3855
0
                } else {
3856
0
                    xmlWarningMsg(ctxt, XML_ERR_ENTITY_PROCESSING,
3857
0
                                  "not validating will not read content for "
3858
0
                                  "PE entity %s\n", ent->name, NULL);
3859
0
                }
3860
0
            }
3861
3862
            /*
3863
             * TODO: Skip if ent->content is still NULL.
3864
             */
3865
3866
0
            if (xmlParserEntityCheck(ctxt, ent->length))
3867
0
                return;
3868
3869
0
            if (ent->flags & XML_ENT_EXPANDING) {
3870
0
                xmlFatalErr(ctxt, XML_ERR_ENTITY_LOOP, NULL);
3871
0
                xmlHaltParser(ctxt);
3872
0
                return;
3873
0
            }
3874
3875
0
            ent->flags |= XML_ENT_EXPANDING;
3876
0
            xmlExpandPEsInEntityValue(ctxt, buf, ent->content, ent->length,
3877
0
                                      depth);
3878
0
            ent->flags &= ~XML_ENT_EXPANDING;
3879
3880
0
            chunk = str;
3881
3.18M
        } else {
3882
            /* Normal ASCII char */
3883
3.18M
            if (!IS_BYTE_CHAR(c)) {
3884
883k
                xmlFatalErrMsg(ctxt, XML_ERR_INVALID_CHAR,
3885
883k
                        "invalid character in entity value\n");
3886
883k
                if (chunk < str)
3887
18.0k
                    xmlSBufAddString(buf, chunk, str - chunk);
3888
883k
                xmlSBufAddReplChar(buf);
3889
883k
                str += 1;
3890
883k
                chunk = str;
3891
2.29M
            } else {
3892
2.29M
                str += 1;
3893
2.29M
            }
3894
3.18M
        }
3895
107M
    }
3896
3897
12.2k
    if (chunk < str)
3898
1.63k
        xmlSBufAddString(buf, chunk, str - chunk);
3899
12.2k
}
3900
3901
/**
3902
 * xmlParseEntityValue:
3903
 * @ctxt:  an XML parser context
3904
 * @orig:  if non-NULL store a copy of the original entity value
3905
 *
3906
 * DEPRECATED: Internal function, don't use.
3907
 *
3908
 * parse a value for ENTITY declarations
3909
 *
3910
 * [9] EntityValue ::= '"' ([^%&"] | PEReference | Reference)* '"' |
3911
 *                 "'" ([^%&'] | PEReference | Reference)* "'"
3912
 *
3913
 * Returns the EntityValue parsed with reference substituted or NULL
3914
 */
3915
xmlChar *
3916
27.7k
xmlParseEntityValue(xmlParserCtxtPtr ctxt, xmlChar **orig) {
3917
27.7k
    unsigned maxLength = (ctxt->options & XML_PARSE_HUGE) ?
3918
0
                         XML_MAX_HUGE_LENGTH :
3919
27.7k
                         XML_MAX_TEXT_LENGTH;
3920
27.7k
    xmlSBuf buf;
3921
27.7k
    const xmlChar *start;
3922
27.7k
    int quote, length;
3923
3924
27.7k
    xmlSBufInit(&buf, maxLength);
3925
3926
27.7k
    GROW;
3927
3928
27.7k
    quote = CUR;
3929
27.7k
    if ((quote != '"') && (quote != '\'')) {
3930
0
  xmlFatalErr(ctxt, XML_ERR_ATTRIBUTE_NOT_STARTED, NULL);
3931
0
  return(NULL);
3932
0
    }
3933
27.7k
    CUR_PTR++;
3934
3935
27.7k
    length = 0;
3936
3937
    /*
3938
     * Copy raw content of the entity into a buffer
3939
     */
3940
350M
    while (1) {
3941
350M
        int c;
3942
3943
350M
        if (PARSER_STOPPED(ctxt))
3944
0
            goto error;
3945
3946
350M
        if (CUR_PTR >= ctxt->input->end) {
3947
13
            xmlFatalErrMsg(ctxt, XML_ERR_ENTITY_NOT_FINISHED, NULL);
3948
13
            goto error;
3949
13
        }
3950
3951
350M
        c = CUR;
3952
3953
350M
        if (c == 0) {
3954
5
            xmlFatalErrMsg(ctxt, XML_ERR_INVALID_CHAR,
3955
5
                    "invalid character in entity value\n");
3956
5
            goto error;
3957
5
        }
3958
350M
        if (c == quote)
3959
27.7k
            break;
3960
350M
        NEXTL(1);
3961
350M
        length += 1;
3962
3963
        /*
3964
         * TODO: Check growth threshold
3965
         */
3966
350M
        if (ctxt->input->end - CUR_PTR < 10)
3967
32.0k
            GROW;
3968
350M
    }
3969
3970
27.7k
    start = CUR_PTR - length;
3971
3972
27.7k
    if (orig != NULL) {
3973
27.7k
        *orig = xmlStrndup(start, length);
3974
27.7k
        if (*orig == NULL)
3975
0
            xmlErrMemory(ctxt);
3976
27.7k
    }
3977
3978
27.7k
    xmlExpandPEsInEntityValue(ctxt, &buf, start, length, ctxt->inputNr);
3979
3980
27.7k
    NEXTL(1);
3981
3982
27.7k
    return(xmlSBufFinish(&buf, NULL, ctxt, "entity length too long"));
3983
3984
18
error:
3985
18
    xmlSBufCleanup(&buf, ctxt, "entity length too long");
3986
18
    return(NULL);
3987
27.7k
}
3988
3989
/**
3990
 * xmlCheckEntityInAttValue:
3991
 * @ctxt:  parser context
3992
 * @pent:  entity
3993
 * @depth:  nesting depth
3994
 *
3995
 * Check an entity reference in an attribute value for validity
3996
 * without expanding it.
3997
 */
3998
static void
3999
129
xmlCheckEntityInAttValue(xmlParserCtxtPtr ctxt, xmlEntityPtr pent, int depth) {
4000
129
    int maxDepth = (ctxt->options & XML_PARSE_HUGE) ? 40 : 20;
4001
129
    const xmlChar *str;
4002
129
    unsigned long expandedSize = pent->length;
4003
129
    int c, flags;
4004
4005
129
    depth += 1;
4006
129
    if (depth > maxDepth) {
4007
0
  xmlFatalErrMsg(ctxt, XML_ERR_RESOURCE_LIMIT,
4008
0
                       "Maximum entity nesting depth exceeded");
4009
0
  return;
4010
0
    }
4011
4012
129
    if (pent->flags & XML_ENT_EXPANDING) {
4013
1
        xmlFatalErr(ctxt, XML_ERR_ENTITY_LOOP, NULL);
4014
1
        xmlHaltParser(ctxt);
4015
1
        return;
4016
1
    }
4017
4018
    /*
4019
     * If we're parsing a default attribute value in DTD content,
4020
     * the entity might reference other entities which weren't
4021
     * defined yet, so the check isn't reliable.
4022
     */
4023
128
    if (ctxt->inSubset == 0)
4024
128
        flags = XML_ENT_CHECKED | XML_ENT_VALIDATED;
4025
0
    else
4026
0
        flags = XML_ENT_VALIDATED;
4027
4028
128
    str = pent->content;
4029
128
    if (str == NULL)
4030
0
        goto done;
4031
4032
    /*
4033
     * Note that entity values are already validated. We only check
4034
     * for illegal less-than signs and compute the expanded size
4035
     * of the entity. No special handling for multi-byte characters
4036
     * is needed.
4037
     */
4038
13.8M
    while (!PARSER_STOPPED(ctxt)) {
4039
13.8M
        c = *str;
4040
4041
13.8M
  if (c != '&') {
4042
13.7M
            if (c == 0)
4043
126
                break;
4044
4045
13.7M
            if (c == '<')
4046
36.8k
                xmlFatalErrMsgStr(ctxt, XML_ERR_LT_IN_ATTRIBUTE,
4047
36.8k
                        "'<' in entity '%s' is not allowed in attributes "
4048
36.8k
                        "values\n", pent->name);
4049
4050
13.7M
            str += 1;
4051
13.7M
        } else if (str[1] == '#') {
4052
8
            int val;
4053
4054
8
      val = xmlParseStringCharRef(ctxt, &str);
4055
8
      if (val == 0) {
4056
1
                pent->content[0] = 0;
4057
1
                break;
4058
1
            }
4059
20.2k
  } else {
4060
20.2k
            xmlChar *name;
4061
20.2k
            xmlEntityPtr ent;
4062
4063
20.2k
      name = xmlParseStringEntityRef(ctxt, &str);
4064
20.2k
      if (name == NULL) {
4065
0
                pent->content[0] = 0;
4066
0
                break;
4067
0
            }
4068
4069
20.2k
            ent = xmlLookupGeneralEntity(ctxt, name, /* inAttr */ 1);
4070
20.2k
            xmlFree(name);
4071
4072
20.2k
            if ((ent != NULL) &&
4073
20.2k
                (ent->etype != XML_INTERNAL_PREDEFINED_ENTITY)) {
4074
13.1k
                if ((ent->flags & flags) != flags) {
4075
75
                    pent->flags |= XML_ENT_EXPANDING;
4076
75
                    xmlCheckEntityInAttValue(ctxt, ent, depth);
4077
75
                    pent->flags &= ~XML_ENT_EXPANDING;
4078
75
                }
4079
4080
13.1k
                xmlSaturatedAdd(&expandedSize, ent->expandedSize);
4081
13.1k
                xmlSaturatedAdd(&expandedSize, XML_ENT_FIXED_COST);
4082
13.1k
            }
4083
20.2k
        }
4084
13.8M
    }
4085
4086
128
done:
4087
128
    if (ctxt->inSubset == 0)
4088
128
        pent->expandedSize = expandedSize;
4089
4090
128
    pent->flags |= flags;
4091
128
}
4092
4093
/**
4094
 * xmlExpandEntityInAttValue:
4095
 * @ctxt:  parser context
4096
 * @buf:  string buffer
4097
 * @str:  entity or attribute value
4098
 * @pent:  entity for entity value, NULL for attribute values
4099
 * @normalize:  whether to collapse whitespace
4100
 * @inSpace:  whitespace state
4101
 * @depth:  nesting depth
4102
 * @check:  whether to check for amplification
4103
 *
4104
 * Expand general entity references in an entity or attribute value.
4105
 * Perform attribute value normalization.
4106
 */
4107
static void
4108
xmlExpandEntityInAttValue(xmlParserCtxtPtr ctxt, xmlSBuf *buf,
4109
                          const xmlChar *str, xmlEntityPtr pent, int normalize,
4110
6.52k
                          int *inSpace, int depth, int check) {
4111
6.52k
    int maxDepth = (ctxt->options & XML_PARSE_HUGE) ? 40 : 20;
4112
6.52k
    int c, chunkSize;
4113
4114
6.52k
    if (str == NULL)
4115
0
        return;
4116
4117
6.52k
    depth += 1;
4118
6.52k
    if (depth > maxDepth) {
4119
0
  xmlFatalErrMsg(ctxt, XML_ERR_RESOURCE_LIMIT,
4120
0
                       "Maximum entity nesting depth exceeded");
4121
0
  return;
4122
0
    }
4123
4124
6.52k
    if (pent != NULL) {
4125
6.52k
        if (pent->flags & XML_ENT_EXPANDING) {
4126
0
            xmlFatalErr(ctxt, XML_ERR_ENTITY_LOOP, NULL);
4127
0
            xmlHaltParser(ctxt);
4128
0
            return;
4129
0
        }
4130
4131
6.52k
        if (check) {
4132
6.52k
            if (xmlParserEntityCheck(ctxt, pent->length))
4133
168
                return;
4134
6.52k
        }
4135
6.52k
    }
4136
4137
6.35k
    chunkSize = 0;
4138
4139
    /*
4140
     * Note that entity values are already validated. No special
4141
     * handling for multi-byte characters is needed.
4142
     */
4143
1.26G
    while (!PARSER_STOPPED(ctxt)) {
4144
1.26G
        c = *str;
4145
4146
1.26G
  if (c != '&') {
4147
1.26G
            if (c == 0)
4148
5.92k
                break;
4149
4150
            /*
4151
             * If this function is called without an entity, it is used to
4152
             * expand entities in an attribute content where less-than was
4153
             * already unscaped and is allowed.
4154
             */
4155
1.26G
            if ((pent != NULL) && (c == '<')) {
4156
429
                xmlFatalErrMsgStr(ctxt, XML_ERR_LT_IN_ATTRIBUTE,
4157
429
                        "'<' in entity '%s' is not allowed in attributes "
4158
429
                        "values\n", pent->name);
4159
429
                break;
4160
429
            }
4161
4162
1.26G
            if (c <= 0x20) {
4163
86.0k
                if ((normalize) && (*inSpace)) {
4164
                    /* Skip char */
4165
0
                    if (chunkSize > 0) {
4166
0
                        xmlSBufAddString(buf, str - chunkSize, chunkSize);
4167
0
                        chunkSize = 0;
4168
0
                    }
4169
86.0k
                } else if (c < 0x20) {
4170
43.4k
                    if (chunkSize > 0) {
4171
43.2k
                        xmlSBufAddString(buf, str - chunkSize, chunkSize);
4172
43.2k
                        chunkSize = 0;
4173
43.2k
                    }
4174
4175
43.4k
                    xmlSBufAddCString(buf, " ", 1);
4176
43.4k
                } else {
4177
42.5k
                    chunkSize += 1;
4178
42.5k
                }
4179
4180
86.0k
                *inSpace = 1;
4181
1.26G
            } else {
4182
1.26G
                chunkSize += 1;
4183
1.26G
                *inSpace = 0;
4184
1.26G
            }
4185
4186
1.26G
            str += 1;
4187
1.26G
        } else if (str[1] == '#') {
4188
8.68k
            int val;
4189
4190
8.68k
            if (chunkSize > 0) {
4191
7.44k
                xmlSBufAddString(buf, str - chunkSize, chunkSize);
4192
7.44k
                chunkSize = 0;
4193
7.44k
            }
4194
4195
8.68k
      val = xmlParseStringCharRef(ctxt, &str);
4196
8.68k
      if (val == 0) {
4197
1
                if (pent != NULL)
4198
1
                    pent->content[0] = 0;
4199
1
                break;
4200
1
            }
4201
4202
8.68k
            if (val == ' ') {
4203
0
                if ((!normalize) || (!*inSpace))
4204
0
                    xmlSBufAddCString(buf, " ", 1);
4205
0
                *inSpace = 1;
4206
8.68k
            } else {
4207
8.68k
                xmlSBufAddChar(buf, val);
4208
8.68k
                *inSpace = 0;
4209
8.68k
            }
4210
23.0k
  } else {
4211
23.0k
            xmlChar *name;
4212
23.0k
            xmlEntityPtr ent;
4213
4214
23.0k
            if (chunkSize > 0) {
4215
20.1k
                xmlSBufAddString(buf, str - chunkSize, chunkSize);
4216
20.1k
                chunkSize = 0;
4217
20.1k
            }
4218
4219
23.0k
      name = xmlParseStringEntityRef(ctxt, &str);
4220
23.0k
            if (name == NULL) {
4221
2
                if (pent != NULL)
4222
2
                    pent->content[0] = 0;
4223
2
                break;
4224
2
            }
4225
4226
23.0k
            ent = xmlLookupGeneralEntity(ctxt, name, /* inAttr */ 1);
4227
23.0k
            xmlFree(name);
4228
4229
23.0k
      if ((ent != NULL) &&
4230
23.0k
    (ent->etype == XML_INTERNAL_PREDEFINED_ENTITY)) {
4231
11.9k
    if (ent->content == NULL) {
4232
0
        xmlFatalErrMsg(ctxt, XML_ERR_INTERNAL_ERROR,
4233
0
          "predefined entity has no content\n");
4234
0
                    break;
4235
0
                }
4236
4237
11.9k
                xmlSBufAddString(buf, ent->content, ent->length);
4238
4239
11.9k
                *inSpace = 0;
4240
11.9k
      } else if ((ent != NULL) && (ent->content != NULL)) {
4241
2.79k
                if (pent != NULL)
4242
2.79k
                    pent->flags |= XML_ENT_EXPANDING;
4243
2.79k
    xmlExpandEntityInAttValue(ctxt, buf, ent->content, ent,
4244
2.79k
                                          normalize, inSpace, depth, check);
4245
2.79k
                if (pent != NULL)
4246
2.79k
                    pent->flags &= ~XML_ENT_EXPANDING;
4247
2.79k
      }
4248
23.0k
        }
4249
1.26G
    }
4250
4251
6.35k
    if (chunkSize > 0)
4252
5.01k
        xmlSBufAddString(buf, str - chunkSize, chunkSize);
4253
6.35k
}
4254
4255
/**
4256
 * xmlExpandEntitiesInAttValue:
4257
 * @ctxt:  parser context
4258
 * @str:  entity or attribute value
4259
 * @normalize:  whether to collapse whitespace
4260
 *
4261
 * Expand general entity references in an entity or attribute value.
4262
 * Perform attribute value normalization.
4263
 *
4264
 * Returns the expanded attribtue value.
4265
 */
4266
xmlChar *
4267
xmlExpandEntitiesInAttValue(xmlParserCtxtPtr ctxt, const xmlChar *str,
4268
0
                            int normalize) {
4269
0
    unsigned maxLength = (ctxt->options & XML_PARSE_HUGE) ?
4270
0
                         XML_MAX_HUGE_LENGTH :
4271
0
                         XML_MAX_TEXT_LENGTH;
4272
0
    xmlSBuf buf;
4273
0
    int inSpace = 1;
4274
4275
0
    xmlSBufInit(&buf, maxLength);
4276
4277
0
    xmlExpandEntityInAttValue(ctxt, &buf, str, NULL, normalize, &inSpace,
4278
0
                              ctxt->inputNr, /* check */ 0);
4279
4280
0
    if ((normalize) && (inSpace) && (buf.size > 0))
4281
0
        buf.size--;
4282
4283
0
    return(xmlSBufFinish(&buf, NULL, ctxt, "AttValue length too long"));
4284
0
}
4285
4286
/**
4287
 * xmlParseAttValueInternal:
4288
 * @ctxt:  an XML parser context
4289
 * @len:  attribute len result
4290
 * @alloc:  whether the attribute was reallocated as a new string
4291
 * @normalize:  if 1 then further non-CDATA normalization must be done
4292
 *
4293
 * parse a value for an attribute.
4294
 * NOTE: if no normalization is needed, the routine will return pointers
4295
 *       directly from the data buffer.
4296
 *
4297
 * 3.3.3 Attribute-Value Normalization:
4298
 * Before the value of an attribute is passed to the application or
4299
 * checked for validity, the XML processor must normalize it as follows:
4300
 * - a character reference is processed by appending the referenced
4301
 *   character to the attribute value
4302
 * - an entity reference is processed by recursively processing the
4303
 *   replacement text of the entity
4304
 * - a whitespace character (#x20, #xD, #xA, #x9) is processed by
4305
 *   appending #x20 to the normalized value, except that only a single
4306
 *   #x20 is appended for a "#xD#xA" sequence that is part of an external
4307
 *   parsed entity or the literal entity value of an internal parsed entity
4308
 * - other characters are processed by appending them to the normalized value
4309
 * If the declared value is not CDATA, then the XML processor must further
4310
 * process the normalized attribute value by discarding any leading and
4311
 * trailing space (#x20) characters, and by replacing sequences of space
4312
 * (#x20) characters by a single space (#x20) character.
4313
 * All attributes for which no declaration has been read should be treated
4314
 * by a non-validating parser as if declared CDATA.
4315
 *
4316
 * Returns the AttValue parsed or NULL. The value has to be freed by the
4317
 *     caller if it was copied, this can be detected by val[*len] == 0.
4318
 */
4319
static xmlChar *
4320
xmlParseAttValueInternal(xmlParserCtxtPtr ctxt, int *attlen, int *alloc,
4321
61.2k
                         int normalize, int isNamespace) {
4322
61.2k
    unsigned maxLength = (ctxt->options & XML_PARSE_HUGE) ?
4323
0
                         XML_MAX_HUGE_LENGTH :
4324
61.2k
                         XML_MAX_TEXT_LENGTH;
4325
61.2k
    xmlSBuf buf;
4326
61.2k
    xmlChar *ret;
4327
61.2k
    int c, l, quote, flags, chunkSize;
4328
61.2k
    int inSpace = 1;
4329
61.2k
    int replaceEntities;
4330
4331
    /* Always expand namespace URIs */
4332
61.2k
    replaceEntities = (ctxt->replaceEntities) || (isNamespace);
4333
4334
61.2k
    xmlSBufInit(&buf, maxLength);
4335
4336
61.2k
    GROW;
4337
4338
61.2k
    quote = CUR;
4339
61.2k
    if ((quote != '"') && (quote != '\'')) {
4340
1.80k
  xmlFatalErr(ctxt, XML_ERR_ATTRIBUTE_NOT_STARTED, NULL);
4341
1.80k
  return(NULL);
4342
1.80k
    }
4343
59.4k
    NEXTL(1);
4344
4345
59.4k
    if (ctxt->inSubset == 0)
4346
59.1k
        flags = XML_ENT_CHECKED | XML_ENT_VALIDATED;
4347
325
    else
4348
325
        flags = XML_ENT_VALIDATED;
4349
4350
59.4k
    inSpace = 1;
4351
59.4k
    chunkSize = 0;
4352
4353
33.7M
    while (1) {
4354
33.7M
        if (PARSER_STOPPED(ctxt))
4355
169
            goto error;
4356
4357
33.7M
        if (CUR_PTR >= ctxt->input->end) {
4358
81
            xmlFatalErrMsg(ctxt, XML_ERR_ATTRIBUTE_NOT_FINISHED,
4359
81
                           "AttValue: ' expected\n");
4360
81
            goto error;
4361
81
        }
4362
4363
        /*
4364
         * TODO: Check growth threshold
4365
         */
4366
33.7M
        if (ctxt->input->end - CUR_PTR < 10)
4367
8.46k
            GROW;
4368
4369
33.7M
        c = CUR;
4370
4371
33.7M
        if (c >= 0x80) {
4372
13.1M
            l = xmlUTF8MultibyteLen(ctxt, CUR_PTR,
4373
13.1M
                    "invalid character in attribute value\n");
4374
13.1M
            if (l == 0) {
4375
11.9M
                if (chunkSize > 0) {
4376
44.4k
                    xmlSBufAddString(&buf, CUR_PTR - chunkSize, chunkSize);
4377
44.4k
                    chunkSize = 0;
4378
44.4k
                }
4379
11.9M
                xmlSBufAddReplChar(&buf);
4380
11.9M
                NEXTL(1);
4381
11.9M
            } else {
4382
1.27M
                chunkSize += l;
4383
1.27M
                NEXTL(l);
4384
1.27M
            }
4385
4386
13.1M
            inSpace = 0;
4387
20.5M
        } else if (c != '&') {
4388
20.5M
            if (c > 0x20) {
4389
1.93M
                if (c == quote)
4390
58.8k
                    break;
4391
4392
1.87M
                if (c == '<')
4393
37.5k
                    xmlFatalErr(ctxt, XML_ERR_LT_IN_ATTRIBUTE, NULL);
4394
4395
1.87M
                chunkSize += 1;
4396
1.87M
                inSpace = 0;
4397
18.6M
            } else if (!IS_BYTE_CHAR(c)) {
4398
15.6M
                xmlFatalErrMsg(ctxt, XML_ERR_INVALID_CHAR,
4399
15.6M
                        "invalid character in attribute value\n");
4400
15.6M
                if (chunkSize > 0) {
4401
25.1k
                    xmlSBufAddString(&buf, CUR_PTR - chunkSize, chunkSize);
4402
25.1k
                    chunkSize = 0;
4403
25.1k
                }
4404
15.6M
                xmlSBufAddReplChar(&buf);
4405
15.6M
                inSpace = 0;
4406
15.6M
            } else {
4407
                /* Whitespace */
4408
2.95M
                if ((normalize) && (inSpace)) {
4409
                    /* Skip char */
4410
1.57k
                    if (chunkSize > 0) {
4411
298
                        xmlSBufAddString(&buf, CUR_PTR - chunkSize, chunkSize);
4412
298
                        chunkSize = 0;
4413
298
                    }
4414
2.95M
                } else if (c < 0x20) {
4415
                    /* Convert to space */
4416
2.89M
                    if (chunkSize > 0) {
4417
23.9k
                        xmlSBufAddString(&buf, CUR_PTR - chunkSize, chunkSize);
4418
23.9k
                        chunkSize = 0;
4419
23.9k
                    }
4420
4421
2.89M
                    xmlSBufAddCString(&buf, " ", 1);
4422
2.89M
                } else {
4423
55.5k
                    chunkSize += 1;
4424
55.5k
                }
4425
4426
2.95M
                inSpace = 1;
4427
4428
2.95M
                if ((c == 0xD) && (NXT(1) == 0xA))
4429
14
                    CUR_PTR++;
4430
2.95M
            }
4431
4432
20.5M
            NEXTL(1);
4433
20.5M
        } else if (NXT(1) == '#') {
4434
5.04k
            int val;
4435
4436
5.04k
            if (chunkSize > 0) {
4437
1.89k
                xmlSBufAddString(&buf, CUR_PTR - chunkSize, chunkSize);
4438
1.89k
                chunkSize = 0;
4439
1.89k
            }
4440
4441
5.04k
            val = xmlParseCharRef(ctxt);
4442
5.04k
            if (val == 0)
4443
282
                goto error;
4444
4445
4.75k
            if ((val == '&') && (!replaceEntities)) {
4446
                /*
4447
                 * The reparsing will be done in xmlNodeParseContent()
4448
                 * called from SAX2.c
4449
                 */
4450
264
                xmlSBufAddCString(&buf, "&#38;", 5);
4451
264
                inSpace = 0;
4452
4.49k
            } else if (val == ' ') {
4453
1.69k
                if ((!normalize) || (!inSpace))
4454
1.42k
                    xmlSBufAddCString(&buf, " ", 1);
4455
1.69k
                inSpace = 1;
4456
2.79k
            } else {
4457
2.79k
                xmlSBufAddChar(&buf, val);
4458
2.79k
                inSpace = 0;
4459
2.79k
            }
4460
31.3k
        } else {
4461
31.3k
            const xmlChar *name;
4462
31.3k
            xmlEntityPtr ent;
4463
4464
31.3k
            if (chunkSize > 0) {
4465
12.4k
                xmlSBufAddString(&buf, CUR_PTR - chunkSize, chunkSize);
4466
12.4k
                chunkSize = 0;
4467
12.4k
            }
4468
4469
31.3k
            name = xmlParseEntityRefInternal(ctxt);
4470
31.3k
            if (name == NULL) {
4471
                /*
4472
                 * Probably a literal '&' which wasn't escaped.
4473
                 * TODO: Handle gracefully in recovery mode.
4474
                 */
4475
8.63k
                continue;
4476
8.63k
            }
4477
4478
22.7k
            ent = xmlLookupGeneralEntity(ctxt, name, /* isAttr */ 1);
4479
22.7k
            if (ent == NULL)
4480
10.2k
                continue;
4481
4482
12.5k
            if (ent->etype == XML_INTERNAL_PREDEFINED_ENTITY) {
4483
3.06k
                if ((ent->content[0] == '&') && (!replaceEntities))
4484
376
                    xmlSBufAddCString(&buf, "&#38;", 5);
4485
2.68k
                else
4486
2.68k
                    xmlSBufAddString(&buf, ent->content, ent->length);
4487
3.06k
                inSpace = 0;
4488
9.43k
            } else if (replaceEntities) {
4489
3.73k
                xmlExpandEntityInAttValue(ctxt, &buf, ent->content, ent,
4490
3.73k
                                          normalize, &inSpace, ctxt->inputNr,
4491
3.73k
                                          /* check */ 1);
4492
5.70k
            } else {
4493
5.70k
                if ((ent->flags & flags) != flags)
4494
54
                    xmlCheckEntityInAttValue(ctxt, ent, ctxt->inputNr);
4495
4496
5.70k
                if (xmlParserEntityCheck(ctxt, ent->expandedSize)) {
4497
33
                    ent->content[0] = 0;
4498
33
                    goto error;
4499
33
                }
4500
4501
                /*
4502
                 * Just output the reference
4503
                 */
4504
5.66k
                xmlSBufAddCString(&buf, "&", 1);
4505
5.66k
                xmlSBufAddString(&buf, ent->name, xmlStrlen(ent->name));
4506
5.66k
                xmlSBufAddCString(&buf, ";", 1);
4507
4508
5.66k
                inSpace = 0;
4509
5.66k
            }
4510
12.5k
  }
4511
33.7M
    }
4512
4513
58.8k
    if ((buf.mem == NULL) && (alloc != NULL)) {
4514
39.9k
        ret = (xmlChar *) CUR_PTR - chunkSize;
4515
4516
39.9k
        if (attlen != NULL)
4517
39.9k
            *attlen = chunkSize;
4518
39.9k
        if ((normalize) && (inSpace) && (chunkSize > 0))
4519
0
            *attlen -= 1;
4520
39.9k
        *alloc = 0;
4521
4522
        /* Report potential error */
4523
39.9k
        xmlSBufCleanup(&buf, ctxt, "AttValue length too long");
4524
39.9k
    } else {
4525
18.9k
        if (chunkSize > 0)
4526
13.8k
            xmlSBufAddString(&buf, CUR_PTR - chunkSize, chunkSize);
4527
4528
18.9k
        if ((normalize) && (inSpace) && (buf.size > 0))
4529
51
            buf.size--;
4530
4531
18.9k
        ret = xmlSBufFinish(&buf, attlen, ctxt, "AttValue length too long");
4532
4533
18.9k
        if (ret != NULL) {
4534
18.9k
            if (attlen != NULL)
4535
18.5k
                *attlen = buf.size;
4536
18.9k
            if (alloc != NULL)
4537
18.5k
                *alloc = 1;
4538
18.9k
        }
4539
18.9k
    }
4540
4541
58.8k
    NEXTL(1);
4542
4543
58.8k
    return(ret);
4544
4545
565
error:
4546
565
    xmlSBufCleanup(&buf, ctxt, "AttValue length too long");
4547
565
    return(NULL);
4548
59.4k
}
4549
4550
/**
4551
 * xmlParseAttValue:
4552
 * @ctxt:  an XML parser context
4553
 *
4554
 * DEPRECATED: Internal function, don't use.
4555
 *
4556
 * parse a value for an attribute
4557
 * Note: the parser won't do substitution of entities here, this
4558
 * will be handled later in xmlStringGetNodeList
4559
 *
4560
 * [10] AttValue ::= '"' ([^<&"] | Reference)* '"' |
4561
 *                   "'" ([^<&'] | Reference)* "'"
4562
 *
4563
 * 3.3.3 Attribute-Value Normalization:
4564
 * Before the value of an attribute is passed to the application or
4565
 * checked for validity, the XML processor must normalize it as follows:
4566
 * - a character reference is processed by appending the referenced
4567
 *   character to the attribute value
4568
 * - an entity reference is processed by recursively processing the
4569
 *   replacement text of the entity
4570
 * - a whitespace character (#x20, #xD, #xA, #x9) is processed by
4571
 *   appending #x20 to the normalized value, except that only a single
4572
 *   #x20 is appended for a "#xD#xA" sequence that is part of an external
4573
 *   parsed entity or the literal entity value of an internal parsed entity
4574
 * - other characters are processed by appending them to the normalized value
4575
 * If the declared value is not CDATA, then the XML processor must further
4576
 * process the normalized attribute value by discarding any leading and
4577
 * trailing space (#x20) characters, and by replacing sequences of space
4578
 * (#x20) characters by a single space (#x20) character.
4579
 * All attributes for which no declaration has been read should be treated
4580
 * by a non-validating parser as if declared CDATA.
4581
 *
4582
 * Returns the AttValue parsed or NULL. The value has to be freed by the caller.
4583
 */
4584
4585
4586
xmlChar *
4587
326
xmlParseAttValue(xmlParserCtxtPtr ctxt) {
4588
326
    if ((ctxt == NULL) || (ctxt->input == NULL)) return(NULL);
4589
326
    return(xmlParseAttValueInternal(ctxt, NULL, NULL, 0, 0));
4590
326
}
4591
4592
/**
4593
 * xmlParseSystemLiteral:
4594
 * @ctxt:  an XML parser context
4595
 *
4596
 * DEPRECATED: Internal function, don't use.
4597
 *
4598
 * parse an XML Literal
4599
 *
4600
 * [11] SystemLiteral ::= ('"' [^"]* '"') | ("'" [^']* "'")
4601
 *
4602
 * Returns the SystemLiteral parsed or NULL
4603
 */
4604
4605
xmlChar *
4606
733
xmlParseSystemLiteral(xmlParserCtxtPtr ctxt) {
4607
733
    xmlChar *buf = NULL;
4608
733
    int len = 0;
4609
733
    int size = XML_PARSER_BUFFER_SIZE;
4610
733
    int cur, l;
4611
733
    int maxLength = (ctxt->options & XML_PARSE_HUGE) ?
4612
0
                    XML_MAX_TEXT_LENGTH :
4613
733
                    XML_MAX_NAME_LENGTH;
4614
733
    xmlChar stop;
4615
4616
733
    if (RAW == '"') {
4617
1
        NEXT;
4618
1
  stop = '"';
4619
732
    } else if (RAW == '\'') {
4620
732
        NEXT;
4621
732
  stop = '\'';
4622
732
    } else {
4623
0
  xmlFatalErr(ctxt, XML_ERR_LITERAL_NOT_STARTED, NULL);
4624
0
  return(NULL);
4625
0
    }
4626
4627
733
    buf = xmlMalloc(size);
4628
733
    if (buf == NULL) {
4629
0
        xmlErrMemory(ctxt);
4630
0
  return(NULL);
4631
0
    }
4632
733
    cur = xmlCurrentCharRecover(ctxt, &l);
4633
18.4k
    while ((IS_CHAR(cur)) && (cur != stop)) { /* checked */
4634
17.6k
  if (len + 5 >= size) {
4635
17
      xmlChar *tmp;
4636
17
            int newSize;
4637
4638
17
            newSize = xmlGrowCapacity(size, 1, 1, maxLength);
4639
17
            if (newSize < 0) {
4640
1
                xmlFatalErr(ctxt, XML_ERR_NAME_TOO_LONG, "SystemLiteral");
4641
1
                xmlFree(buf);
4642
1
                return(NULL);
4643
1
            }
4644
16
      tmp = xmlRealloc(buf, newSize);
4645
16
      if (tmp == NULL) {
4646
0
          xmlFree(buf);
4647
0
    xmlErrMemory(ctxt);
4648
0
    return(NULL);
4649
0
      }
4650
16
      buf = tmp;
4651
16
            size = newSize;
4652
16
  }
4653
17.6k
  COPY_BUF(buf, len, cur);
4654
17.6k
  NEXTL(l);
4655
17.6k
  cur = xmlCurrentCharRecover(ctxt, &l);
4656
17.6k
    }
4657
732
    buf[len] = 0;
4658
732
    if (!IS_CHAR(cur)) {
4659
0
  xmlFatalErr(ctxt, XML_ERR_LITERAL_NOT_FINISHED, NULL);
4660
732
    } else {
4661
732
  NEXT;
4662
732
    }
4663
732
    return(buf);
4664
733
}
4665
4666
/**
4667
 * xmlParsePubidLiteral:
4668
 * @ctxt:  an XML parser context
4669
 *
4670
 * DEPRECATED: Internal function, don't use.
4671
 *
4672
 * parse an XML public literal
4673
 *
4674
 * [12] PubidLiteral ::= '"' PubidChar* '"' | "'" (PubidChar - "'")* "'"
4675
 *
4676
 * Returns the PubidLiteral parsed or NULL.
4677
 */
4678
4679
xmlChar *
4680
520
xmlParsePubidLiteral(xmlParserCtxtPtr ctxt) {
4681
520
    xmlChar *buf = NULL;
4682
520
    int len = 0;
4683
520
    int size = XML_PARSER_BUFFER_SIZE;
4684
520
    int maxLength = (ctxt->options & XML_PARSE_HUGE) ?
4685
0
                    XML_MAX_TEXT_LENGTH :
4686
520
                    XML_MAX_NAME_LENGTH;
4687
520
    xmlChar cur;
4688
520
    xmlChar stop;
4689
4690
520
    if (RAW == '"') {
4691
1
        NEXT;
4692
1
  stop = '"';
4693
519
    } else if (RAW == '\'') {
4694
409
        NEXT;
4695
409
  stop = '\'';
4696
409
    } else {
4697
110
  xmlFatalErr(ctxt, XML_ERR_LITERAL_NOT_STARTED, NULL);
4698
110
  return(NULL);
4699
110
    }
4700
410
    buf = xmlMalloc(size);
4701
410
    if (buf == NULL) {
4702
0
  xmlErrMemory(ctxt);
4703
0
  return(NULL);
4704
0
    }
4705
410
    cur = CUR;
4706
822
    while ((IS_PUBIDCHAR_CH(cur)) && (cur != stop) &&
4707
822
           (PARSER_STOPPED(ctxt) == 0)) { /* checked */
4708
412
  if (len + 1 >= size) {
4709
0
      xmlChar *tmp;
4710
0
            int newSize;
4711
4712
0
      newSize = xmlGrowCapacity(size, 1, 1, maxLength);
4713
0
            if (newSize < 0) {
4714
0
                xmlFatalErr(ctxt, XML_ERR_NAME_TOO_LONG, "Public ID");
4715
0
                xmlFree(buf);
4716
0
                return(NULL);
4717
0
            }
4718
0
      tmp = xmlRealloc(buf, newSize);
4719
0
      if (tmp == NULL) {
4720
0
    xmlErrMemory(ctxt);
4721
0
    xmlFree(buf);
4722
0
    return(NULL);
4723
0
      }
4724
0
      buf = tmp;
4725
0
            size = newSize;
4726
0
  }
4727
412
  buf[len++] = cur;
4728
412
  NEXT;
4729
412
  cur = CUR;
4730
412
    }
4731
410
    buf[len] = 0;
4732
410
    if (cur != stop) {
4733
0
  xmlFatalErr(ctxt, XML_ERR_LITERAL_NOT_FINISHED, NULL);
4734
410
    } else {
4735
410
  NEXTL(1);
4736
410
    }
4737
410
    return(buf);
4738
410
}
4739
4740
static void xmlParseCharDataComplex(xmlParserCtxtPtr ctxt, int partial);
4741
4742
/*
4743
 * used for the test in the inner loop of the char data testing
4744
 */
4745
static const unsigned char test_char_data[256] = {
4746
    0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00,
4747
    0x00, 0x09, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x9, CR/LF separated */
4748
    0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00,
4749
    0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00,
4750
    0x20, 0x21, 0x22, 0x23, 0x24, 0x25, 0x00, 0x27, /* & */
4751
    0x28, 0x29, 0x2A, 0x2B, 0x2C, 0x2D, 0x2E, 0x2F,
4752
    0x30, 0x31, 0x32, 0x33, 0x34, 0x35, 0x36, 0x37,
4753
    0x38, 0x39, 0x3A, 0x3B, 0x00, 0x3D, 0x3E, 0x3F, /* < */
4754
    0x40, 0x41, 0x42, 0x43, 0x44, 0x45, 0x46, 0x47,
4755
    0x48, 0x49, 0x4A, 0x4B, 0x4C, 0x4D, 0x4E, 0x4F,
4756
    0x50, 0x51, 0x52, 0x53, 0x54, 0x55, 0x56, 0x57,
4757
    0x58, 0x59, 0x5A, 0x5B, 0x5C, 0x00, 0x5E, 0x5F, /* ] */
4758
    0x60, 0x61, 0x62, 0x63, 0x64, 0x65, 0x66, 0x67,
4759
    0x68, 0x69, 0x6A, 0x6B, 0x6C, 0x6D, 0x6E, 0x6F,
4760
    0x70, 0x71, 0x72, 0x73, 0x74, 0x75, 0x76, 0x77,
4761
    0x78, 0x79, 0x7A, 0x7B, 0x7C, 0x7D, 0x7E, 0x7F,
4762
    0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* non-ascii */
4763
    0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00,
4764
    0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00,
4765
    0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00,
4766
    0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00,
4767
    0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00,
4768
    0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00,
4769
    0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00,
4770
    0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00,
4771
    0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00,
4772
    0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00,
4773
    0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00,
4774
    0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00,
4775
    0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00,
4776
    0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00,
4777
    0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00
4778
};
4779
4780
static void
4781
xmlCharacters(xmlParserCtxtPtr ctxt, const xmlChar *buf, int size,
4782
1.20M
              int isBlank) {
4783
1.20M
    int checkBlanks;
4784
4785
1.20M
    if ((ctxt->sax == NULL) || (ctxt->disableSAX))
4786
0
        return;
4787
4788
1.20M
    checkBlanks = (!ctxt->keepBlanks) ||
4789
1.20M
                  (ctxt->sax->ignorableWhitespace != ctxt->sax->characters);
4790
4791
    /*
4792
     * Calling areBlanks with only parts of a text node
4793
     * is fundamentally broken, making the NOBLANKS option
4794
     * essentially unusable.
4795
     */
4796
1.20M
    if ((checkBlanks) &&
4797
1.20M
        (areBlanks(ctxt, buf, size, isBlank))) {
4798
0
        if ((ctxt->sax->ignorableWhitespace != NULL) &&
4799
0
            (ctxt->keepBlanks))
4800
0
            ctxt->sax->ignorableWhitespace(ctxt->userData, buf, size);
4801
1.20M
    } else {
4802
1.20M
        if (ctxt->sax->characters != NULL)
4803
1.20M
            ctxt->sax->characters(ctxt->userData, buf, size);
4804
4805
        /*
4806
         * The old code used to update this value for "complex" data
4807
         * even if checkBlanks was false. This was probably a bug.
4808
         */
4809
1.20M
        if ((checkBlanks) && (*ctxt->space == -1))
4810
0
            *ctxt->space = -2;
4811
1.20M
    }
4812
1.20M
}
4813
4814
/**
4815
 * xmlParseCharDataInternal:
4816
 * @ctxt:  an XML parser context
4817
 * @partial:  buffer may contain partial UTF-8 sequences
4818
 *
4819
 * Parse character data. Always makes progress if the first char isn't
4820
 * '<' or '&'.
4821
 *
4822
 * The right angle bracket (>) may be represented using the string "&gt;",
4823
 * and must, for compatibility, be escaped using "&gt;" or a character
4824
 * reference when it appears in the string "]]>" in content, when that
4825
 * string is not marking the end of a CDATA section.
4826
 *
4827
 * [14] CharData ::= [^<&]* - ([^<&]* ']]>' [^<&]*)
4828
 */
4829
static void
4830
2.13M
xmlParseCharDataInternal(xmlParserCtxtPtr ctxt, int partial) {
4831
2.13M
    const xmlChar *in;
4832
2.13M
    int nbchar = 0;
4833
2.13M
    int line = ctxt->input->line;
4834
2.13M
    int col = ctxt->input->col;
4835
2.13M
    int ccol;
4836
4837
2.13M
    GROW;
4838
    /*
4839
     * Accelerated common case where input don't need to be
4840
     * modified before passing it to the handler.
4841
     */
4842
2.13M
    in = ctxt->input->cur;
4843
2.14M
    do {
4844
2.19M
get_more_space:
4845
2.25M
        while (*in == 0x20) { in++; ctxt->input->col++; }
4846
2.19M
        if (*in == 0xA) {
4847
3.44M
            do {
4848
3.44M
                ctxt->input->line++; ctxt->input->col = 1;
4849
3.44M
                in++;
4850
3.44M
            } while (*in == 0xA);
4851
50.1k
            goto get_more_space;
4852
50.1k
        }
4853
2.14M
        if (*in == '<') {
4854
12.3k
            nbchar = in - ctxt->input->cur;
4855
12.3k
            if (nbchar > 0) {
4856
12.3k
                const xmlChar *tmp = ctxt->input->cur;
4857
12.3k
                ctxt->input->cur = in;
4858
4859
12.3k
                xmlCharacters(ctxt, tmp, nbchar, 1);
4860
12.3k
            }
4861
12.3k
            return;
4862
12.3k
        }
4863
4864
2.18M
get_more:
4865
2.18M
        ccol = ctxt->input->col;
4866
7.62M
        while (test_char_data[*in]) {
4867
5.44M
            in++;
4868
5.44M
            ccol++;
4869
5.44M
        }
4870
2.18M
        ctxt->input->col = ccol;
4871
2.18M
        if (*in == 0xA) {
4872
2.74M
            do {
4873
2.74M
                ctxt->input->line++; ctxt->input->col = 1;
4874
2.74M
                in++;
4875
2.74M
            } while (*in == 0xA);
4876
41.4k
            goto get_more;
4877
41.4k
        }
4878
2.13M
        if (*in == ']') {
4879
12.4k
            if ((in[1] == ']') && (in[2] == '>')) {
4880
1.25k
                xmlFatalErr(ctxt, XML_ERR_MISPLACED_CDATA_END, NULL);
4881
1.25k
                ctxt->input->cur = in + 1;
4882
1.25k
                return;
4883
1.25k
            }
4884
11.1k
            if ((!partial) || (ctxt->input->end - in >= 2)) {
4885
11.1k
                in++;
4886
11.1k
                ctxt->input->col++;
4887
11.1k
                goto get_more;
4888
11.1k
            }
4889
11.1k
        }
4890
2.12M
        nbchar = in - ctxt->input->cur;
4891
2.12M
        if (nbchar > 0) {
4892
540k
            const xmlChar *tmp = ctxt->input->cur;
4893
540k
            ctxt->input->cur = in;
4894
4895
540k
            xmlCharacters(ctxt, tmp, nbchar, 0);
4896
4897
540k
            line = ctxt->input->line;
4898
540k
            col = ctxt->input->col;
4899
540k
        }
4900
2.12M
        ctxt->input->cur = in;
4901
2.12M
        if (*in == 0xD) {
4902
5.23k
            in++;
4903
5.23k
            if (*in == 0xA) {
4904
1.08k
                ctxt->input->cur = in;
4905
1.08k
                in++;
4906
1.08k
                ctxt->input->line++; ctxt->input->col = 1;
4907
1.08k
                continue; /* while */
4908
1.08k
            }
4909
4.15k
            in--;
4910
4.15k
        }
4911
2.12M
        if (*in == '<') {
4912
371k
            return;
4913
371k
        }
4914
1.75M
        if (*in == '&') {
4915
6.21k
            return;
4916
6.21k
        }
4917
1.74M
        if ((partial) && (*in == ']') && (ctxt->input->end - in < 2)) {
4918
0
            return;
4919
0
        }
4920
1.74M
        SHRINK;
4921
1.74M
        GROW;
4922
1.74M
        in = ctxt->input->cur;
4923
1.74M
    } while (((*in >= 0x20) && (*in <= 0x7F)) ||
4924
1.74M
             (*in == 0x09) || (*in == 0x0a));
4925
1.74M
    ctxt->input->line = line;
4926
1.74M
    ctxt->input->col = col;
4927
1.74M
    xmlParseCharDataComplex(ctxt, partial);
4928
1.74M
}
4929
4930
/**
4931
 * xmlParseCharDataComplex:
4932
 * @ctxt:  an XML parser context
4933
 * @cdata:  int indicating whether we are within a CDATA section
4934
 *
4935
 * Always makes progress if the first char isn't '<' or '&'.
4936
 *
4937
 * parse a CharData section.this is the fallback function
4938
 * of xmlParseCharData() when the parsing requires handling
4939
 * of non-ASCII characters.
4940
 */
4941
static void
4942
1.74M
xmlParseCharDataComplex(xmlParserCtxtPtr ctxt, int partial) {
4943
1.74M
    xmlChar buf[XML_PARSER_BIG_BUFFER_SIZE + 5];
4944
1.74M
    int nbchar = 0;
4945
1.74M
    int cur, l;
4946
4947
1.74M
    cur = xmlCurrentCharRecover(ctxt, &l);
4948
48.5M
    while ((cur != '<') && /* checked */
4949
48.5M
           (cur != '&') &&
4950
48.5M
           ((!partial) || (cur != ']') ||
4951
48.4M
            (ctxt->input->end - ctxt->input->cur >= 2)) &&
4952
48.5M
     (IS_CHAR(cur))) {
4953
46.8M
  if ((cur == ']') && (NXT(1) == ']') && (NXT(2) == '>')) {
4954
12.3k
      xmlFatalErr(ctxt, XML_ERR_MISPLACED_CDATA_END, NULL);
4955
12.3k
  }
4956
46.8M
  COPY_BUF(buf, nbchar, cur);
4957
  /* move current position before possible calling of ctxt->sax->characters */
4958
46.8M
  NEXTL(l);
4959
46.8M
  if (nbchar >= XML_PARSER_BIG_BUFFER_SIZE) {
4960
377k
      buf[nbchar] = 0;
4961
4962
377k
            xmlCharacters(ctxt, buf, nbchar, 0);
4963
377k
      nbchar = 0;
4964
377k
            SHRINK;
4965
377k
  }
4966
46.8M
  cur = xmlCurrentCharRecover(ctxt, &l);
4967
46.8M
    }
4968
1.74M
    if (nbchar != 0) {
4969
270k
        buf[nbchar] = 0;
4970
4971
270k
        xmlCharacters(ctxt, buf, nbchar, 0);
4972
270k
    }
4973
    /*
4974
     * cur == 0 can mean
4975
     *
4976
     * - End of buffer.
4977
     * - An actual 0 character.
4978
     * - An incomplete UTF-8 sequence. This is allowed if partial is set.
4979
     */
4980
1.74M
    if (ctxt->input->cur < ctxt->input->end) {
4981
1.74M
        if ((cur == 0) && (CUR != 0)) {
4982
39
            if (partial == 0) {
4983
39
                xmlFatalErrMsgInt(ctxt, XML_ERR_INVALID_CHAR,
4984
39
                        "Incomplete UTF-8 sequence starting with %02X\n", CUR);
4985
39
                NEXTL(1);
4986
39
            }
4987
1.74M
        } else if ((cur != '<') && (cur != '&') && (cur != ']')) {
4988
            /* Generate the error and skip the offending character */
4989
1.57M
            xmlFatalErrMsgInt(ctxt, XML_ERR_INVALID_CHAR,
4990
1.57M
                              "PCDATA invalid Char value %d\n", cur);
4991
1.57M
            NEXTL(l);
4992
1.57M
        }
4993
1.74M
    }
4994
1.74M
}
4995
4996
/**
4997
 * xmlParseCharData:
4998
 * @ctxt:  an XML parser context
4999
 * @cdata:  unused
5000
 *
5001
 * DEPRECATED: Internal function, don't use.
5002
 */
5003
void
5004
0
xmlParseCharData(xmlParserCtxtPtr ctxt, ATTRIBUTE_UNUSED int cdata) {
5005
0
    xmlParseCharDataInternal(ctxt, 0);
5006
0
}
5007
5008
/**
5009
 * xmlParseExternalID:
5010
 * @ctxt:  an XML parser context
5011
 * @publicID:  a xmlChar** receiving PubidLiteral
5012
 * @strict: indicate whether we should restrict parsing to only
5013
 *          production [75], see NOTE below
5014
 *
5015
 * DEPRECATED: Internal function, don't use.
5016
 *
5017
 * Parse an External ID or a Public ID
5018
 *
5019
 * NOTE: Productions [75] and [83] interact badly since [75] can generate
5020
 *       'PUBLIC' S PubidLiteral S SystemLiteral
5021
 *
5022
 * [75] ExternalID ::= 'SYSTEM' S SystemLiteral
5023
 *                   | 'PUBLIC' S PubidLiteral S SystemLiteral
5024
 *
5025
 * [83] PublicID ::= 'PUBLIC' S PubidLiteral
5026
 *
5027
 * Returns the function returns SystemLiteral and in the second
5028
 *                case publicID receives PubidLiteral, is strict is off
5029
 *                it is possible to return NULL and have publicID set.
5030
 */
5031
5032
xmlChar *
5033
1.60k
xmlParseExternalID(xmlParserCtxtPtr ctxt, xmlChar **publicID, int strict) {
5034
1.60k
    xmlChar *URI = NULL;
5035
5036
1.60k
    *publicID = NULL;
5037
1.60k
    if (CMP6(CUR_PTR, 'S', 'Y', 'S', 'T', 'E', 'M')) {
5038
673
        SKIP(6);
5039
673
  if (SKIP_BLANKS == 0) {
5040
0
      xmlFatalErrMsg(ctxt, XML_ERR_SPACE_REQUIRED,
5041
0
                     "Space required after 'SYSTEM'\n");
5042
0
  }
5043
673
  URI = xmlParseSystemLiteral(ctxt);
5044
673
  if (URI == NULL) {
5045
0
      xmlFatalErr(ctxt, XML_ERR_URI_REQUIRED, NULL);
5046
0
        }
5047
930
    } else if (CMP6(CUR_PTR, 'P', 'U', 'B', 'L', 'I', 'C')) {
5048
520
        SKIP(6);
5049
520
  if (SKIP_BLANKS == 0) {
5050
0
      xmlFatalErrMsg(ctxt, XML_ERR_SPACE_REQUIRED,
5051
0
        "Space required after 'PUBLIC'\n");
5052
0
  }
5053
520
  *publicID = xmlParsePubidLiteral(ctxt);
5054
520
  if (*publicID == NULL) {
5055
110
      xmlFatalErr(ctxt, XML_ERR_PUBID_REQUIRED, NULL);
5056
110
  }
5057
520
  if (strict) {
5058
      /*
5059
       * We don't handle [83] so "S SystemLiteral" is required.
5060
       */
5061
0
      if (SKIP_BLANKS == 0) {
5062
0
    xmlFatalErrMsg(ctxt, XML_ERR_SPACE_REQUIRED,
5063
0
      "Space required after the Public Identifier\n");
5064
0
      }
5065
520
  } else {
5066
      /*
5067
       * We handle [83] so we return immediately, if
5068
       * "S SystemLiteral" is not detected. We skip blanks if no
5069
             * system literal was found, but this is harmless since we must
5070
             * be at the end of a NotationDecl.
5071
       */
5072
520
      if (SKIP_BLANKS == 0) return(NULL);
5073
60
      if ((CUR != '\'') && (CUR != '"')) return(NULL);
5074
60
  }
5075
60
  URI = xmlParseSystemLiteral(ctxt);
5076
60
  if (URI == NULL) {
5077
1
      xmlFatalErr(ctxt, XML_ERR_URI_REQUIRED, NULL);
5078
1
        }
5079
60
    }
5080
1.14k
    return(URI);
5081
1.60k
}
5082
5083
/**
5084
 * xmlParseCommentComplex:
5085
 * @ctxt:  an XML parser context
5086
 * @buf:  the already parsed part of the buffer
5087
 * @len:  number of bytes in the buffer
5088
 * @size:  allocated size of the buffer
5089
 *
5090
 * Skip an XML (SGML) comment <!-- .... -->
5091
 *  The spec says that "For compatibility, the string "--" (double-hyphen)
5092
 *  must not occur within comments. "
5093
 * This is the slow routine in case the accelerator for ascii didn't work
5094
 *
5095
 * [15] Comment ::= '<!--' ((Char - '-') | ('-' (Char - '-')))* '-->'
5096
 */
5097
static void
5098
xmlParseCommentComplex(xmlParserCtxtPtr ctxt, xmlChar *buf,
5099
11.1k
                       size_t len, size_t size) {
5100
11.1k
    int q, ql;
5101
11.1k
    int r, rl;
5102
11.1k
    int cur, l;
5103
11.1k
    int maxLength = (ctxt->options & XML_PARSE_HUGE) ?
5104
0
                    XML_MAX_HUGE_LENGTH :
5105
11.1k
                    XML_MAX_TEXT_LENGTH;
5106
5107
11.1k
    if (buf == NULL) {
5108
1.64k
        len = 0;
5109
1.64k
  size = XML_PARSER_BUFFER_SIZE;
5110
1.64k
  buf = xmlMalloc(size);
5111
1.64k
  if (buf == NULL) {
5112
0
      xmlErrMemory(ctxt);
5113
0
      return;
5114
0
  }
5115
1.64k
    }
5116
11.1k
    q = xmlCurrentCharRecover(ctxt, &ql);
5117
11.1k
    if (q == 0)
5118
484
        goto not_terminated;
5119
10.6k
    if (!IS_CHAR(q)) {
5120
44
        xmlFatalErrMsgInt(ctxt, XML_ERR_INVALID_CHAR,
5121
44
                          "xmlParseComment: invalid xmlChar value %d\n",
5122
44
                    q);
5123
44
  xmlFree (buf);
5124
44
  return;
5125
44
    }
5126
10.6k
    NEXTL(ql);
5127
10.6k
    r = xmlCurrentCharRecover(ctxt, &rl);
5128
10.6k
    if (r == 0)
5129
3
        goto not_terminated;
5130
10.6k
    if (!IS_CHAR(r)) {
5131
17
        xmlFatalErrMsgInt(ctxt, XML_ERR_INVALID_CHAR,
5132
17
                          "xmlParseComment: invalid xmlChar value %d\n",
5133
17
                    r);
5134
17
  xmlFree (buf);
5135
17
  return;
5136
17
    }
5137
10.6k
    NEXTL(rl);
5138
10.6k
    cur = xmlCurrentCharRecover(ctxt, &l);
5139
10.6k
    if (cur == 0)
5140
347
        goto not_terminated;
5141
851k
    while (IS_CHAR(cur) && /* checked */
5142
851k
           ((cur != '>') ||
5143
841k
      (r != '-') || (q != '-'))) {
5144
840k
  if ((r == '-') && (q == '-')) {
5145
8.02k
      xmlFatalErr(ctxt, XML_ERR_HYPHEN_IN_COMMENT, NULL);
5146
8.02k
  }
5147
840k
  if (len + 5 >= size) {
5148
23.7k
      xmlChar *tmp;
5149
23.7k
            int newSize;
5150
5151
23.7k
      newSize = xmlGrowCapacity(size, 1, 1, maxLength);
5152
23.7k
            if (newSize < 0) {
5153
0
                xmlFatalErrMsgStr(ctxt, XML_ERR_COMMENT_NOT_FINISHED,
5154
0
                             "Comment too big found", NULL);
5155
0
                xmlFree (buf);
5156
0
                return;
5157
0
            }
5158
23.7k
      tmp = xmlRealloc(buf, newSize);
5159
23.7k
      if (tmp == NULL) {
5160
0
    xmlErrMemory(ctxt);
5161
0
    xmlFree(buf);
5162
0
    return;
5163
0
      }
5164
23.7k
      buf = tmp;
5165
23.7k
            size = newSize;
5166
23.7k
  }
5167
840k
  COPY_BUF(buf, len, q);
5168
5169
840k
  q = r;
5170
840k
  ql = rl;
5171
840k
  r = cur;
5172
840k
  rl = l;
5173
5174
840k
  NEXTL(l);
5175
840k
  cur = xmlCurrentCharRecover(ctxt, &l);
5176
5177
840k
    }
5178
10.2k
    buf[len] = 0;
5179
10.2k
    if (cur == 0) {
5180
9.21k
  xmlFatalErrMsgStr(ctxt, XML_ERR_COMMENT_NOT_FINISHED,
5181
9.21k
                       "Comment not terminated \n<!--%.50s\n", buf);
5182
9.21k
    } else if (!IS_CHAR(cur)) {
5183
952
        xmlFatalErrMsgInt(ctxt, XML_ERR_INVALID_CHAR,
5184
952
                          "xmlParseComment: invalid xmlChar value %d\n",
5185
952
                    cur);
5186
952
    } else {
5187
113
        NEXT;
5188
113
  if ((ctxt->sax != NULL) && (ctxt->sax->comment != NULL) &&
5189
113
      (!ctxt->disableSAX))
5190
113
      ctxt->sax->comment(ctxt->userData, buf);
5191
113
    }
5192
10.2k
    xmlFree(buf);
5193
10.2k
    return;
5194
834
not_terminated:
5195
834
    xmlFatalErrMsgStr(ctxt, XML_ERR_COMMENT_NOT_FINISHED,
5196
834
       "Comment not terminated\n", NULL);
5197
834
    xmlFree(buf);
5198
834
}
5199
5200
/**
5201
 * xmlParseComment:
5202
 * @ctxt:  an XML parser context
5203
 *
5204
 * DEPRECATED: Internal function, don't use.
5205
 *
5206
 * Parse an XML (SGML) comment. Always consumes '<!'.
5207
 *
5208
 *  The spec says that "For compatibility, the string "--" (double-hyphen)
5209
 *  must not occur within comments. "
5210
 *
5211
 * [15] Comment ::= '<!--' ((Char - '-') | ('-' (Char - '-')))* '-->'
5212
 */
5213
void
5214
13.0k
xmlParseComment(xmlParserCtxtPtr ctxt) {
5215
13.0k
    xmlChar *buf = NULL;
5216
13.0k
    size_t size = XML_PARSER_BUFFER_SIZE;
5217
13.0k
    size_t len = 0;
5218
13.0k
    size_t maxLength = (ctxt->options & XML_PARSE_HUGE) ?
5219
0
                       XML_MAX_HUGE_LENGTH :
5220
13.0k
                       XML_MAX_TEXT_LENGTH;
5221
13.0k
    const xmlChar *in;
5222
13.0k
    size_t nbchar = 0;
5223
13.0k
    int ccol;
5224
5225
    /*
5226
     * Check that there is a comment right here.
5227
     */
5228
13.0k
    if ((RAW != '<') || (NXT(1) != '!'))
5229
0
        return;
5230
13.0k
    SKIP(2);
5231
13.0k
    if ((RAW != '-') || (NXT(1) != '-'))
5232
0
        return;
5233
13.0k
    SKIP(2);
5234
13.0k
    GROW;
5235
5236
    /*
5237
     * Accelerated common case where input don't need to be
5238
     * modified before passing it to the handler.
5239
     */
5240
13.0k
    in = ctxt->input->cur;
5241
13.0k
    do {
5242
13.0k
  if (*in == 0xA) {
5243
61
      do {
5244
61
    ctxt->input->line++; ctxt->input->col = 1;
5245
61
    in++;
5246
61
      } while (*in == 0xA);
5247
61
  }
5248
24.0k
get_more:
5249
24.0k
        ccol = ctxt->input->col;
5250
425k
  while (((*in > '-') && (*in <= 0x7F)) ||
5251
425k
         ((*in >= 0x20) && (*in < '-')) ||
5252
425k
         (*in == 0x09)) {
5253
401k
        in++;
5254
401k
        ccol++;
5255
401k
  }
5256
24.0k
  ctxt->input->col = ccol;
5257
24.0k
  if (*in == 0xA) {
5258
2.64k
      do {
5259
2.64k
    ctxt->input->line++; ctxt->input->col = 1;
5260
2.64k
    in++;
5261
2.64k
      } while (*in == 0xA);
5262
569
      goto get_more;
5263
569
  }
5264
23.4k
  nbchar = in - ctxt->input->cur;
5265
  /*
5266
   * save current set of data
5267
   */
5268
23.4k
  if (nbchar > 0) {
5269
20.3k
            if (nbchar > maxLength - len) {
5270
0
                xmlFatalErrMsgStr(ctxt, XML_ERR_COMMENT_NOT_FINISHED,
5271
0
                                  "Comment too big found", NULL);
5272
0
                xmlFree(buf);
5273
0
                return;
5274
0
            }
5275
20.3k
            if (buf == NULL) {
5276
11.2k
                if ((*in == '-') && (in[1] == '-'))
5277
2.60k
                    size = nbchar + 1;
5278
8.69k
                else
5279
8.69k
                    size = XML_PARSER_BUFFER_SIZE + nbchar;
5280
11.2k
                buf = xmlMalloc(size);
5281
11.2k
                if (buf == NULL) {
5282
0
                    xmlErrMemory(ctxt);
5283
0
                    return;
5284
0
                }
5285
11.2k
                len = 0;
5286
11.2k
            } else if (len + nbchar + 1 >= size) {
5287
842
                xmlChar *new_buf;
5288
842
                size += len + nbchar + XML_PARSER_BUFFER_SIZE;
5289
842
                new_buf = xmlRealloc(buf, size);
5290
842
                if (new_buf == NULL) {
5291
0
                    xmlErrMemory(ctxt);
5292
0
                    xmlFree(buf);
5293
0
                    return;
5294
0
                }
5295
842
                buf = new_buf;
5296
842
            }
5297
20.3k
            memcpy(&buf[len], ctxt->input->cur, nbchar);
5298
20.3k
            len += nbchar;
5299
20.3k
            buf[len] = 0;
5300
20.3k
  }
5301
23.4k
  ctxt->input->cur = in;
5302
23.4k
  if (*in == 0xA) {
5303
0
      in++;
5304
0
      ctxt->input->line++; ctxt->input->col = 1;
5305
0
  }
5306
23.4k
  if (*in == 0xD) {
5307
0
      in++;
5308
0
      if (*in == 0xA) {
5309
0
    ctxt->input->cur = in;
5310
0
    in++;
5311
0
    ctxt->input->line++; ctxt->input->col = 1;
5312
0
    goto get_more;
5313
0
      }
5314
0
      in--;
5315
0
  }
5316
23.4k
  SHRINK;
5317
23.4k
  GROW;
5318
23.4k
  in = ctxt->input->cur;
5319
23.4k
  if (*in == '-') {
5320
12.2k
      if (in[1] == '-') {
5321
3.47k
          if (in[2] == '>') {
5322
1.85k
        SKIP(3);
5323
1.85k
        if ((ctxt->sax != NULL) && (ctxt->sax->comment != NULL) &&
5324
1.85k
            (!ctxt->disableSAX)) {
5325
1.85k
      if (buf != NULL)
5326
1.77k
          ctxt->sax->comment(ctxt->userData, buf);
5327
86
      else
5328
86
          ctxt->sax->comment(ctxt->userData, BAD_CAST "");
5329
1.85k
        }
5330
1.85k
        if (buf != NULL)
5331
1.77k
            xmlFree(buf);
5332
1.85k
        return;
5333
1.85k
    }
5334
1.61k
    if (buf != NULL) {
5335
833
        xmlFatalErrMsgStr(ctxt, XML_ERR_HYPHEN_IN_COMMENT,
5336
833
                          "Double hyphen within comment: "
5337
833
                                      "<!--%.50s\n",
5338
833
              buf);
5339
833
    } else
5340
779
        xmlFatalErrMsgStr(ctxt, XML_ERR_HYPHEN_IN_COMMENT,
5341
779
                          "Double hyphen within comment\n", NULL);
5342
1.61k
    in++;
5343
1.61k
    ctxt->input->col++;
5344
1.61k
      }
5345
10.3k
      in++;
5346
10.3k
      ctxt->input->col++;
5347
10.3k
      goto get_more;
5348
12.2k
  }
5349
23.4k
    } while (((*in >= 0x20) && (*in <= 0x7F)) || (*in == 0x09) || (*in == 0x0a));
5350
11.1k
    xmlParseCommentComplex(ctxt, buf, len, size);
5351
11.1k
}
5352
5353
5354
/**
5355
 * xmlParsePITarget:
5356
 * @ctxt:  an XML parser context
5357
 *
5358
 * DEPRECATED: Internal function, don't use.
5359
 *
5360
 * parse the name of a PI
5361
 *
5362
 * [17] PITarget ::= Name - (('X' | 'x') ('M' | 'm') ('L' | 'l'))
5363
 *
5364
 * Returns the PITarget name or NULL
5365
 */
5366
5367
const xmlChar *
5368
6.60k
xmlParsePITarget(xmlParserCtxtPtr ctxt) {
5369
6.60k
    const xmlChar *name;
5370
5371
6.60k
    name = xmlParseName(ctxt);
5372
6.60k
    if ((name != NULL) &&
5373
6.60k
        ((name[0] == 'x') || (name[0] == 'X')) &&
5374
6.60k
        ((name[1] == 'm') || (name[1] == 'M')) &&
5375
6.60k
        ((name[2] == 'l') || (name[2] == 'L'))) {
5376
149
  int i;
5377
149
  if ((name[0] == 'x') && (name[1] == 'm') &&
5378
149
      (name[2] == 'l') && (name[3] == 0)) {
5379
100
      xmlFatalErrMsg(ctxt, XML_ERR_RESERVED_XML_NAME,
5380
100
     "XML declaration allowed only at the start of the document\n");
5381
100
      return(name);
5382
100
  } else if (name[3] == 0) {
5383
17
      xmlFatalErr(ctxt, XML_ERR_RESERVED_XML_NAME, NULL);
5384
17
      return(name);
5385
17
  }
5386
96
  for (i = 0;;i++) {
5387
96
      if (xmlW3CPIs[i] == NULL) break;
5388
64
      if (xmlStrEqual(name, (const xmlChar *)xmlW3CPIs[i]))
5389
0
          return(name);
5390
64
  }
5391
32
  xmlWarningMsg(ctxt, XML_ERR_RESERVED_XML_NAME,
5392
32
          "xmlParsePITarget: invalid name prefix 'xml'\n",
5393
32
          NULL, NULL);
5394
32
    }
5395
6.48k
    if ((name != NULL) && (xmlStrchr(name, ':') != NULL)) {
5396
81
  xmlNsErr(ctxt, XML_NS_ERR_COLON,
5397
81
     "colons are forbidden from PI names '%s'\n", name, NULL, NULL);
5398
81
    }
5399
6.48k
    return(name);
5400
6.60k
}
5401
5402
#ifdef LIBXML_CATALOG_ENABLED
5403
/**
5404
 * xmlParseCatalogPI:
5405
 * @ctxt:  an XML parser context
5406
 * @catalog:  the PI value string
5407
 *
5408
 * parse an XML Catalog Processing Instruction.
5409
 *
5410
 * <?oasis-xml-catalog catalog="http://example.com/catalog.xml"?>
5411
 *
5412
 * Occurs only if allowed by the user and if happening in the Misc
5413
 * part of the document before any doctype information
5414
 * This will add the given catalog to the parsing context in order
5415
 * to be used if there is a resolution need further down in the document
5416
 */
5417
5418
static void
5419
0
xmlParseCatalogPI(xmlParserCtxtPtr ctxt, const xmlChar *catalog) {
5420
0
    xmlChar *URL = NULL;
5421
0
    const xmlChar *tmp, *base;
5422
0
    xmlChar marker;
5423
5424
0
    tmp = catalog;
5425
0
    while (IS_BLANK_CH(*tmp)) tmp++;
5426
0
    if (xmlStrncmp(tmp, BAD_CAST"catalog", 7))
5427
0
  goto error;
5428
0
    tmp += 7;
5429
0
    while (IS_BLANK_CH(*tmp)) tmp++;
5430
0
    if (*tmp != '=') {
5431
0
  return;
5432
0
    }
5433
0
    tmp++;
5434
0
    while (IS_BLANK_CH(*tmp)) tmp++;
5435
0
    marker = *tmp;
5436
0
    if ((marker != '\'') && (marker != '"'))
5437
0
  goto error;
5438
0
    tmp++;
5439
0
    base = tmp;
5440
0
    while ((*tmp != 0) && (*tmp != marker)) tmp++;
5441
0
    if (*tmp == 0)
5442
0
  goto error;
5443
0
    URL = xmlStrndup(base, tmp - base);
5444
0
    tmp++;
5445
0
    while (IS_BLANK_CH(*tmp)) tmp++;
5446
0
    if (*tmp != 0)
5447
0
  goto error;
5448
5449
0
    if (URL != NULL) {
5450
        /*
5451
         * Unfortunately, the catalog API doesn't report OOM errors.
5452
         * xmlGetLastError isn't very helpful since we don't know
5453
         * where the last error came from. We'd have to reset it
5454
         * before this call and restore it afterwards.
5455
         */
5456
0
  ctxt->catalogs = xmlCatalogAddLocal(ctxt->catalogs, URL);
5457
0
  xmlFree(URL);
5458
0
    }
5459
0
    return;
5460
5461
0
error:
5462
0
    xmlWarningMsg(ctxt, XML_WAR_CATALOG_PI,
5463
0
            "Catalog PI syntax error: %s\n",
5464
0
      catalog, NULL);
5465
0
    if (URL != NULL)
5466
0
  xmlFree(URL);
5467
0
}
5468
#endif
5469
5470
/**
5471
 * xmlParsePI:
5472
 * @ctxt:  an XML parser context
5473
 *
5474
 * DEPRECATED: Internal function, don't use.
5475
 *
5476
 * parse an XML Processing Instruction.
5477
 *
5478
 * [16] PI ::= '<?' PITarget (S (Char* - (Char* '?>' Char*)))? '?>'
5479
 *
5480
 * The processing is transferred to SAX once parsed.
5481
 */
5482
5483
void
5484
6.60k
xmlParsePI(xmlParserCtxtPtr ctxt) {
5485
6.60k
    xmlChar *buf = NULL;
5486
6.60k
    size_t len = 0;
5487
6.60k
    size_t size = XML_PARSER_BUFFER_SIZE;
5488
6.60k
    size_t maxLength = (ctxt->options & XML_PARSE_HUGE) ?
5489
0
                       XML_MAX_HUGE_LENGTH :
5490
6.60k
                       XML_MAX_TEXT_LENGTH;
5491
6.60k
    int cur, l;
5492
6.60k
    const xmlChar *target;
5493
5494
6.60k
    if ((RAW == '<') && (NXT(1) == '?')) {
5495
  /*
5496
   * this is a Processing Instruction.
5497
   */
5498
6.60k
  SKIP(2);
5499
5500
  /*
5501
   * Parse the target name and check for special support like
5502
   * namespace.
5503
   */
5504
6.60k
        target = xmlParsePITarget(ctxt);
5505
6.60k
  if (target != NULL) {
5506
5.67k
      if ((RAW == '?') && (NXT(1) == '>')) {
5507
4.24k
    SKIP(2);
5508
5509
    /*
5510
     * SAX: PI detected.
5511
     */
5512
4.24k
    if ((ctxt->sax) && (!ctxt->disableSAX) &&
5513
4.24k
        (ctxt->sax->processingInstruction != NULL))
5514
4.24k
        ctxt->sax->processingInstruction(ctxt->userData,
5515
4.24k
                                         target, NULL);
5516
4.24k
    return;
5517
4.24k
      }
5518
1.42k
      buf = xmlMalloc(size);
5519
1.42k
      if (buf == NULL) {
5520
0
    xmlErrMemory(ctxt);
5521
0
    return;
5522
0
      }
5523
1.42k
      if (SKIP_BLANKS == 0) {
5524
595
    xmlFatalErrMsgStr(ctxt, XML_ERR_SPACE_REQUIRED,
5525
595
        "ParsePI: PI %s space expected\n", target);
5526
595
      }
5527
1.42k
      cur = xmlCurrentCharRecover(ctxt, &l);
5528
11.5M
      while (IS_CHAR(cur) && /* checked */
5529
11.5M
       ((cur != '?') || (NXT(1) != '>'))) {
5530
11.5M
    if (len + 5 >= size) {
5531
1.00k
        xmlChar *tmp;
5532
1.00k
                    int newSize;
5533
5534
1.00k
                    newSize = xmlGrowCapacity(size, 1, 1, maxLength);
5535
1.00k
                    if (newSize < 0) {
5536
0
                        xmlFatalErrMsgStr(ctxt, XML_ERR_PI_NOT_FINISHED,
5537
0
                                          "PI %s too big found", target);
5538
0
                        xmlFree(buf);
5539
0
                        return;
5540
0
                    }
5541
1.00k
        tmp = xmlRealloc(buf, newSize);
5542
1.00k
        if (tmp == NULL) {
5543
0
      xmlErrMemory(ctxt);
5544
0
      xmlFree(buf);
5545
0
      return;
5546
0
        }
5547
1.00k
        buf = tmp;
5548
1.00k
                    size = newSize;
5549
1.00k
    }
5550
11.5M
    COPY_BUF(buf, len, cur);
5551
11.5M
    NEXTL(l);
5552
11.5M
    cur = xmlCurrentCharRecover(ctxt, &l);
5553
11.5M
      }
5554
1.42k
      buf[len] = 0;
5555
1.42k
      if (cur != '?') {
5556
503
    xmlFatalErrMsgStr(ctxt, XML_ERR_PI_NOT_FINISHED,
5557
503
          "ParsePI: PI %s never end ...\n", target);
5558
922
      } else {
5559
922
    SKIP(2);
5560
5561
922
#ifdef LIBXML_CATALOG_ENABLED
5562
922
    if ((ctxt->inSubset == 0) &&
5563
922
        (xmlStrEqual(target, XML_CATALOG_PI))) {
5564
0
        xmlCatalogAllow allow = xmlCatalogGetDefaults();
5565
5566
0
        if ((ctxt->options & XML_PARSE_CATALOG_PI) &&
5567
0
                        ((allow == XML_CATA_ALLOW_DOCUMENT) ||
5568
0
       (allow == XML_CATA_ALLOW_ALL)))
5569
0
      xmlParseCatalogPI(ctxt, buf);
5570
0
    }
5571
922
#endif
5572
5573
    /*
5574
     * SAX: PI detected.
5575
     */
5576
922
    if ((ctxt->sax) && (!ctxt->disableSAX) &&
5577
922
        (ctxt->sax->processingInstruction != NULL))
5578
922
        ctxt->sax->processingInstruction(ctxt->userData,
5579
922
                                         target, buf);
5580
922
      }
5581
1.42k
      xmlFree(buf);
5582
1.42k
  } else {
5583
931
      xmlFatalErr(ctxt, XML_ERR_PI_NOT_STARTED, NULL);
5584
931
  }
5585
6.60k
    }
5586
6.60k
}
5587
5588
/**
5589
 * xmlParseNotationDecl:
5590
 * @ctxt:  an XML parser context
5591
 *
5592
 * DEPRECATED: Internal function, don't use.
5593
 *
5594
 * Parse a notation declaration. Always consumes '<!'.
5595
 *
5596
 * [82] NotationDecl ::= '<!NOTATION' S Name S (ExternalID |  PublicID) S? '>'
5597
 *
5598
 * Hence there is actually 3 choices:
5599
 *     'PUBLIC' S PubidLiteral
5600
 *     'PUBLIC' S PubidLiteral S SystemLiteral
5601
 * and 'SYSTEM' S SystemLiteral
5602
 *
5603
 * See the NOTE on xmlParseExternalID().
5604
 */
5605
5606
void
5607
1.21k
xmlParseNotationDecl(xmlParserCtxtPtr ctxt) {
5608
1.21k
    const xmlChar *name;
5609
1.21k
    xmlChar *Pubid;
5610
1.21k
    xmlChar *Systemid;
5611
5612
1.21k
    if ((CUR != '<') || (NXT(1) != '!'))
5613
0
        return;
5614
1.21k
    SKIP(2);
5615
5616
1.21k
    if (CMP8(CUR_PTR, 'N', 'O', 'T', 'A', 'T', 'I', 'O', 'N')) {
5617
1.21k
  int inputid = ctxt->input->id;
5618
1.21k
  SKIP(8);
5619
1.21k
  if (SKIP_BLANKS_PE == 0) {
5620
0
      xmlFatalErrMsg(ctxt, XML_ERR_SPACE_REQUIRED,
5621
0
         "Space required after '<!NOTATION'\n");
5622
0
      return;
5623
0
  }
5624
5625
1.21k
        name = xmlParseName(ctxt);
5626
1.21k
  if (name == NULL) {
5627
0
      xmlFatalErr(ctxt, XML_ERR_NOTATION_NOT_STARTED, NULL);
5628
0
      return;
5629
0
  }
5630
1.21k
  if (xmlStrchr(name, ':') != NULL) {
5631
0
      xmlNsErr(ctxt, XML_NS_ERR_COLON,
5632
0
         "colons are forbidden from notation names '%s'\n",
5633
0
         name, NULL, NULL);
5634
0
  }
5635
1.21k
  if (SKIP_BLANKS_PE == 0) {
5636
2
      xmlFatalErrMsg(ctxt, XML_ERR_SPACE_REQUIRED,
5637
2
         "Space required after the NOTATION name'\n");
5638
2
      return;
5639
2
  }
5640
5641
  /*
5642
   * Parse the IDs.
5643
   */
5644
1.21k
  Systemid = xmlParseExternalID(ctxt, &Pubid, 0);
5645
1.21k
  SKIP_BLANKS_PE;
5646
5647
1.21k
  if (RAW == '>') {
5648
1.21k
      if (inputid != ctxt->input->id) {
5649
0
    xmlFatalErrMsg(ctxt, XML_ERR_ENTITY_BOUNDARY,
5650
0
                         "Notation declaration doesn't start and stop"
5651
0
                               " in the same entity\n");
5652
0
      }
5653
1.21k
      NEXT;
5654
1.21k
      if ((ctxt->sax != NULL) && (!ctxt->disableSAX) &&
5655
1.21k
    (ctxt->sax->notationDecl != NULL))
5656
1.21k
    ctxt->sax->notationDecl(ctxt->userData, name, Pubid, Systemid);
5657
1.21k
  } else {
5658
2
      xmlFatalErr(ctxt, XML_ERR_NOTATION_NOT_FINISHED, NULL);
5659
2
  }
5660
1.21k
  if (Systemid != NULL) xmlFree(Systemid);
5661
1.21k
  if (Pubid != NULL) xmlFree(Pubid);
5662
1.21k
    }
5663
1.21k
}
5664
5665
/**
5666
 * xmlParseEntityDecl:
5667
 * @ctxt:  an XML parser context
5668
 *
5669
 * DEPRECATED: Internal function, don't use.
5670
 *
5671
 * Parse an entity declaration. Always consumes '<!'.
5672
 *
5673
 * [70] EntityDecl ::= GEDecl | PEDecl
5674
 *
5675
 * [71] GEDecl ::= '<!ENTITY' S Name S EntityDef S? '>'
5676
 *
5677
 * [72] PEDecl ::= '<!ENTITY' S '%' S Name S PEDef S? '>'
5678
 *
5679
 * [73] EntityDef ::= EntityValue | (ExternalID NDataDecl?)
5680
 *
5681
 * [74] PEDef ::= EntityValue | ExternalID
5682
 *
5683
 * [76] NDataDecl ::= S 'NDATA' S Name
5684
 *
5685
 * [ VC: Notation Declared ]
5686
 * The Name must match the declared name of a notation.
5687
 */
5688
5689
void
5690
27.9k
xmlParseEntityDecl(xmlParserCtxtPtr ctxt) {
5691
27.9k
    const xmlChar *name = NULL;
5692
27.9k
    xmlChar *value = NULL;
5693
27.9k
    xmlChar *URI = NULL, *literal = NULL;
5694
27.9k
    const xmlChar *ndata = NULL;
5695
27.9k
    int isParameter = 0;
5696
27.9k
    xmlChar *orig = NULL;
5697
5698
27.9k
    if ((CUR != '<') || (NXT(1) != '!'))
5699
0
        return;
5700
27.9k
    SKIP(2);
5701
5702
    /* GROW; done in the caller */
5703
27.9k
    if (CMP6(CUR_PTR, 'E', 'N', 'T', 'I', 'T', 'Y')) {
5704
27.9k
  int inputid = ctxt->input->id;
5705
27.9k
  SKIP(6);
5706
27.9k
  if (SKIP_BLANKS_PE == 0) {
5707
9.71k
      xmlFatalErrMsg(ctxt, XML_ERR_SPACE_REQUIRED,
5708
9.71k
         "Space required after '<!ENTITY'\n");
5709
9.71k
  }
5710
5711
27.9k
  if (RAW == '%') {
5712
11.0k
      NEXT;
5713
11.0k
      if (SKIP_BLANKS_PE == 0) {
5714
9.71k
    xmlFatalErrMsg(ctxt, XML_ERR_SPACE_REQUIRED,
5715
9.71k
             "Space required after '%%'\n");
5716
9.71k
      }
5717
11.0k
      isParameter = 1;
5718
11.0k
  }
5719
5720
27.9k
        name = xmlParseName(ctxt);
5721
27.9k
  if (name == NULL) {
5722
216
      xmlFatalErrMsg(ctxt, XML_ERR_NAME_REQUIRED,
5723
216
                     "xmlParseEntityDecl: no name\n");
5724
216
            return;
5725
216
  }
5726
27.7k
  if (xmlStrchr(name, ':') != NULL) {
5727
0
      xmlNsErr(ctxt, XML_NS_ERR_COLON,
5728
0
         "colons are forbidden from entities names '%s'\n",
5729
0
         name, NULL, NULL);
5730
0
  }
5731
27.7k
  if (SKIP_BLANKS_PE == 0) {
5732
4.60k
      xmlFatalErrMsg(ctxt, XML_ERR_SPACE_REQUIRED,
5733
4.60k
         "Space required after the entity name\n");
5734
4.60k
  }
5735
5736
  /*
5737
   * handle the various case of definitions...
5738
   */
5739
27.7k
  if (isParameter) {
5740
11.0k
      if ((RAW == '"') || (RAW == '\'')) {
5741
11.0k
          value = xmlParseEntityValue(ctxt, &orig);
5742
11.0k
    if (value) {
5743
11.0k
        if ((ctxt->sax != NULL) &&
5744
11.0k
      (!ctxt->disableSAX) && (ctxt->sax->entityDecl != NULL))
5745
11.0k
      ctxt->sax->entityDecl(ctxt->userData, name,
5746
11.0k
                        XML_INTERNAL_PARAMETER_ENTITY,
5747
11.0k
            NULL, NULL, value);
5748
11.0k
    }
5749
11.0k
      } else {
5750
0
          URI = xmlParseExternalID(ctxt, &literal, 1);
5751
0
    if ((URI == NULL) && (literal == NULL)) {
5752
0
        xmlFatalErr(ctxt, XML_ERR_VALUE_REQUIRED, NULL);
5753
0
    }
5754
0
    if (URI) {
5755
0
                    if (xmlStrchr(URI, '#')) {
5756
0
                        xmlFatalErr(ctxt, XML_ERR_URI_FRAGMENT, NULL);
5757
0
                    } else {
5758
0
                        if ((ctxt->sax != NULL) &&
5759
0
                            (!ctxt->disableSAX) &&
5760
0
                            (ctxt->sax->entityDecl != NULL))
5761
0
                            ctxt->sax->entityDecl(ctxt->userData, name,
5762
0
                                        XML_EXTERNAL_PARAMETER_ENTITY,
5763
0
                                        literal, URI, NULL);
5764
0
                    }
5765
0
    }
5766
0
      }
5767
16.7k
  } else {
5768
16.7k
      if ((RAW == '"') || (RAW == '\'')) {
5769
16.7k
          value = xmlParseEntityValue(ctxt, &orig);
5770
16.7k
    if ((ctxt->sax != NULL) &&
5771
16.7k
        (!ctxt->disableSAX) && (ctxt->sax->entityDecl != NULL))
5772
16.7k
        ctxt->sax->entityDecl(ctxt->userData, name,
5773
16.7k
        XML_INTERNAL_GENERAL_ENTITY,
5774
16.7k
        NULL, NULL, value);
5775
    /*
5776
     * For expat compatibility in SAX mode.
5777
     */
5778
16.7k
    if ((ctxt->myDoc == NULL) ||
5779
16.7k
        (xmlStrEqual(ctxt->myDoc->version, SAX_COMPAT_MODE))) {
5780
0
        if (ctxt->myDoc == NULL) {
5781
0
      ctxt->myDoc = xmlNewDoc(SAX_COMPAT_MODE);
5782
0
      if (ctxt->myDoc == NULL) {
5783
0
          xmlErrMemory(ctxt);
5784
0
          goto done;
5785
0
      }
5786
0
      ctxt->myDoc->properties = XML_DOC_INTERNAL;
5787
0
        }
5788
0
        if (ctxt->myDoc->intSubset == NULL) {
5789
0
      ctxt->myDoc->intSubset = xmlNewDtd(ctxt->myDoc,
5790
0
              BAD_CAST "fake", NULL, NULL);
5791
0
                        if (ctxt->myDoc->intSubset == NULL) {
5792
0
                            xmlErrMemory(ctxt);
5793
0
                            goto done;
5794
0
                        }
5795
0
                    }
5796
5797
0
        xmlSAX2EntityDecl(ctxt, name, XML_INTERNAL_GENERAL_ENTITY,
5798
0
                    NULL, NULL, value);
5799
0
    }
5800
16.7k
      } else {
5801
0
          URI = xmlParseExternalID(ctxt, &literal, 1);
5802
0
    if ((URI == NULL) && (literal == NULL)) {
5803
0
        xmlFatalErr(ctxt, XML_ERR_VALUE_REQUIRED, NULL);
5804
0
    }
5805
0
    if (URI) {
5806
0
                    if (xmlStrchr(URI, '#')) {
5807
0
                        xmlFatalErr(ctxt, XML_ERR_URI_FRAGMENT, NULL);
5808
0
                    }
5809
0
    }
5810
0
    if ((RAW != '>') && (SKIP_BLANKS_PE == 0)) {
5811
0
        xmlFatalErrMsg(ctxt, XML_ERR_SPACE_REQUIRED,
5812
0
           "Space required before 'NDATA'\n");
5813
0
    }
5814
0
    if (CMP5(CUR_PTR, 'N', 'D', 'A', 'T', 'A')) {
5815
0
        SKIP(5);
5816
0
        if (SKIP_BLANKS_PE == 0) {
5817
0
      xmlFatalErrMsg(ctxt, XML_ERR_SPACE_REQUIRED,
5818
0
               "Space required after 'NDATA'\n");
5819
0
        }
5820
0
        ndata = xmlParseName(ctxt);
5821
0
        if ((ctxt->sax != NULL) && (!ctxt->disableSAX) &&
5822
0
            (ctxt->sax->unparsedEntityDecl != NULL))
5823
0
      ctxt->sax->unparsedEntityDecl(ctxt->userData, name,
5824
0
            literal, URI, ndata);
5825
0
    } else {
5826
0
        if ((ctxt->sax != NULL) &&
5827
0
            (!ctxt->disableSAX) && (ctxt->sax->entityDecl != NULL))
5828
0
      ctxt->sax->entityDecl(ctxt->userData, name,
5829
0
            XML_EXTERNAL_GENERAL_PARSED_ENTITY,
5830
0
            literal, URI, NULL);
5831
        /*
5832
         * For expat compatibility in SAX mode.
5833
         * assuming the entity replacement was asked for
5834
         */
5835
0
        if ((ctxt->replaceEntities != 0) &&
5836
0
      ((ctxt->myDoc == NULL) ||
5837
0
      (xmlStrEqual(ctxt->myDoc->version, SAX_COMPAT_MODE)))) {
5838
0
      if (ctxt->myDoc == NULL) {
5839
0
          ctxt->myDoc = xmlNewDoc(SAX_COMPAT_MODE);
5840
0
          if (ctxt->myDoc == NULL) {
5841
0
              xmlErrMemory(ctxt);
5842
0
        goto done;
5843
0
          }
5844
0
          ctxt->myDoc->properties = XML_DOC_INTERNAL;
5845
0
      }
5846
5847
0
      if (ctxt->myDoc->intSubset == NULL) {
5848
0
          ctxt->myDoc->intSubset = xmlNewDtd(ctxt->myDoc,
5849
0
            BAD_CAST "fake", NULL, NULL);
5850
0
                            if (ctxt->myDoc->intSubset == NULL) {
5851
0
                                xmlErrMemory(ctxt);
5852
0
                                goto done;
5853
0
                            }
5854
0
                        }
5855
0
      xmlSAX2EntityDecl(ctxt, name,
5856
0
                  XML_EXTERNAL_GENERAL_PARSED_ENTITY,
5857
0
                  literal, URI, NULL);
5858
0
        }
5859
0
    }
5860
0
      }
5861
16.7k
  }
5862
27.7k
  SKIP_BLANKS_PE;
5863
27.7k
  if (RAW != '>') {
5864
23
      xmlFatalErrMsgStr(ctxt, XML_ERR_ENTITY_NOT_FINISHED,
5865
23
              "xmlParseEntityDecl: entity %s not terminated\n", name);
5866
23
      xmlHaltParser(ctxt);
5867
27.7k
  } else {
5868
27.7k
      if (inputid != ctxt->input->id) {
5869
0
    xmlFatalErrMsg(ctxt, XML_ERR_ENTITY_BOUNDARY,
5870
0
                         "Entity declaration doesn't start and stop in"
5871
0
                               " the same entity\n");
5872
0
      }
5873
27.7k
      NEXT;
5874
27.7k
  }
5875
27.7k
  if (orig != NULL) {
5876
      /*
5877
       * Ugly mechanism to save the raw entity value.
5878
       */
5879
27.7k
      xmlEntityPtr cur = NULL;
5880
5881
27.7k
      if (isParameter) {
5882
11.0k
          if ((ctxt->sax != NULL) &&
5883
11.0k
        (ctxt->sax->getParameterEntity != NULL))
5884
11.0k
        cur = ctxt->sax->getParameterEntity(ctxt->userData, name);
5885
16.6k
      } else {
5886
16.6k
          if ((ctxt->sax != NULL) &&
5887
16.6k
        (ctxt->sax->getEntity != NULL))
5888
16.6k
        cur = ctxt->sax->getEntity(ctxt->userData, name);
5889
16.6k
    if ((cur == NULL) && (ctxt->userData==ctxt)) {
5890
0
        cur = xmlSAX2GetEntity(ctxt, name);
5891
0
    }
5892
16.6k
      }
5893
27.7k
            if ((cur != NULL) && (cur->orig == NULL)) {
5894
604
    cur->orig = orig;
5895
604
                orig = NULL;
5896
604
      }
5897
27.7k
  }
5898
5899
27.7k
done:
5900
27.7k
  if (value != NULL) xmlFree(value);
5901
27.7k
  if (URI != NULL) xmlFree(URI);
5902
27.7k
  if (literal != NULL) xmlFree(literal);
5903
27.7k
        if (orig != NULL) xmlFree(orig);
5904
27.7k
    }
5905
27.9k
}
5906
5907
/**
5908
 * xmlParseDefaultDecl:
5909
 * @ctxt:  an XML parser context
5910
 * @value:  Receive a possible fixed default value for the attribute
5911
 *
5912
 * DEPRECATED: Internal function, don't use.
5913
 *
5914
 * Parse an attribute default declaration
5915
 *
5916
 * [60] DefaultDecl ::= '#REQUIRED' | '#IMPLIED' | (('#FIXED' S)? AttValue)
5917
 *
5918
 * [ VC: Required Attribute ]
5919
 * if the default declaration is the keyword #REQUIRED, then the
5920
 * attribute must be specified for all elements of the type in the
5921
 * attribute-list declaration.
5922
 *
5923
 * [ VC: Attribute Default Legal ]
5924
 * The declared default value must meet the lexical constraints of
5925
 * the declared attribute type c.f. xmlValidateAttributeDecl()
5926
 *
5927
 * [ VC: Fixed Attribute Default ]
5928
 * if an attribute has a default value declared with the #FIXED
5929
 * keyword, instances of that attribute must match the default value.
5930
 *
5931
 * [ WFC: No < in Attribute Values ]
5932
 * handled in xmlParseAttValue()
5933
 *
5934
 * returns: XML_ATTRIBUTE_NONE, XML_ATTRIBUTE_REQUIRED, XML_ATTRIBUTE_IMPLIED
5935
 *          or XML_ATTRIBUTE_FIXED.
5936
 */
5937
5938
int
5939
796
xmlParseDefaultDecl(xmlParserCtxtPtr ctxt, xmlChar **value) {
5940
796
    int val;
5941
796
    xmlChar *ret;
5942
5943
796
    *value = NULL;
5944
796
    if (CMP9(CUR_PTR, '#', 'R', 'E', 'Q', 'U', 'I', 'R', 'E', 'D')) {
5945
173
  SKIP(9);
5946
173
  return(XML_ATTRIBUTE_REQUIRED);
5947
173
    }
5948
623
    if (CMP8(CUR_PTR, '#', 'I', 'M', 'P', 'L', 'I', 'E', 'D')) {
5949
297
  SKIP(8);
5950
297
  return(XML_ATTRIBUTE_IMPLIED);
5951
297
    }
5952
326
    val = XML_ATTRIBUTE_NONE;
5953
326
    if (CMP6(CUR_PTR, '#', 'F', 'I', 'X', 'E', 'D')) {
5954
268
  SKIP(6);
5955
268
  val = XML_ATTRIBUTE_FIXED;
5956
268
  if (SKIP_BLANKS_PE == 0) {
5957
0
      xmlFatalErrMsg(ctxt, XML_ERR_SPACE_REQUIRED,
5958
0
         "Space required after '#FIXED'\n");
5959
0
  }
5960
268
    }
5961
326
    ret = xmlParseAttValue(ctxt);
5962
326
    if (ret == NULL) {
5963
1
  xmlFatalErrMsg(ctxt, (xmlParserErrors)ctxt->errNo,
5964
1
           "Attribute default value declaration error\n");
5965
1
    } else
5966
325
        *value = ret;
5967
326
    return(val);
5968
623
}
5969
5970
/**
5971
 * xmlParseNotationType:
5972
 * @ctxt:  an XML parser context
5973
 *
5974
 * DEPRECATED: Internal function, don't use.
5975
 *
5976
 * parse an Notation attribute type.
5977
 *
5978
 * Note: the leading 'NOTATION' S part has already being parsed...
5979
 *
5980
 * [58] NotationType ::= 'NOTATION' S '(' S? Name (S? '|' S? Name)* S? ')'
5981
 *
5982
 * [ VC: Notation Attributes ]
5983
 * Values of this type must match one of the notation names included
5984
 * in the declaration; all notation names in the declaration must be declared.
5985
 *
5986
 * Returns: the notation attribute tree built while parsing
5987
 */
5988
5989
xmlEnumerationPtr
5990
0
xmlParseNotationType(xmlParserCtxtPtr ctxt) {
5991
0
    const xmlChar *name;
5992
0
    xmlEnumerationPtr ret = NULL, last = NULL, cur, tmp;
5993
5994
0
    if (RAW != '(') {
5995
0
  xmlFatalErr(ctxt, XML_ERR_NOTATION_NOT_STARTED, NULL);
5996
0
  return(NULL);
5997
0
    }
5998
0
    do {
5999
0
        NEXT;
6000
0
  SKIP_BLANKS_PE;
6001
0
        name = xmlParseName(ctxt);
6002
0
  if (name == NULL) {
6003
0
      xmlFatalErrMsg(ctxt, XML_ERR_NAME_REQUIRED,
6004
0
         "Name expected in NOTATION declaration\n");
6005
0
            xmlFreeEnumeration(ret);
6006
0
      return(NULL);
6007
0
  }
6008
0
        tmp = NULL;
6009
#ifdef LIBXML_VALID_ENABLED
6010
        if (ctxt->validate) {
6011
            tmp = ret;
6012
            while (tmp != NULL) {
6013
                if (xmlStrEqual(name, tmp->name)) {
6014
                    xmlValidityError(ctxt, XML_DTD_DUP_TOKEN,
6015
              "standalone: attribute notation value token %s duplicated\n",
6016
                                     name, NULL);
6017
                    if (!xmlDictOwns(ctxt->dict, name))
6018
                        xmlFree((xmlChar *) name);
6019
                    break;
6020
                }
6021
                tmp = tmp->next;
6022
            }
6023
        }
6024
#endif /* LIBXML_VALID_ENABLED */
6025
0
  if (tmp == NULL) {
6026
0
      cur = xmlCreateEnumeration(name);
6027
0
      if (cur == NULL) {
6028
0
                xmlErrMemory(ctxt);
6029
0
                xmlFreeEnumeration(ret);
6030
0
                return(NULL);
6031
0
            }
6032
0
      if (last == NULL) ret = last = cur;
6033
0
      else {
6034
0
    last->next = cur;
6035
0
    last = cur;
6036
0
      }
6037
0
  }
6038
0
  SKIP_BLANKS_PE;
6039
0
    } while (RAW == '|');
6040
0
    if (RAW != ')') {
6041
0
  xmlFatalErr(ctxt, XML_ERR_NOTATION_NOT_FINISHED, NULL);
6042
0
        xmlFreeEnumeration(ret);
6043
0
  return(NULL);
6044
0
    }
6045
0
    NEXT;
6046
0
    return(ret);
6047
0
}
6048
6049
/**
6050
 * xmlParseEnumerationType:
6051
 * @ctxt:  an XML parser context
6052
 *
6053
 * DEPRECATED: Internal function, don't use.
6054
 *
6055
 * parse an Enumeration attribute type.
6056
 *
6057
 * [59] Enumeration ::= '(' S? Nmtoken (S? '|' S? Nmtoken)* S? ')'
6058
 *
6059
 * [ VC: Enumeration ]
6060
 * Values of this type must match one of the Nmtoken tokens in
6061
 * the declaration
6062
 *
6063
 * Returns: the enumeration attribute tree built while parsing
6064
 */
6065
6066
xmlEnumerationPtr
6067
0
xmlParseEnumerationType(xmlParserCtxtPtr ctxt) {
6068
0
    xmlChar *name;
6069
0
    xmlEnumerationPtr ret = NULL, last = NULL, cur, tmp;
6070
6071
0
    if (RAW != '(') {
6072
0
  xmlFatalErr(ctxt, XML_ERR_ATTLIST_NOT_STARTED, NULL);
6073
0
  return(NULL);
6074
0
    }
6075
0
    do {
6076
0
        NEXT;
6077
0
  SKIP_BLANKS_PE;
6078
0
        name = xmlParseNmtoken(ctxt);
6079
0
  if (name == NULL) {
6080
0
      xmlFatalErr(ctxt, XML_ERR_NMTOKEN_REQUIRED, NULL);
6081
0
      return(ret);
6082
0
  }
6083
0
        tmp = NULL;
6084
#ifdef LIBXML_VALID_ENABLED
6085
        if (ctxt->validate) {
6086
            tmp = ret;
6087
            while (tmp != NULL) {
6088
                if (xmlStrEqual(name, tmp->name)) {
6089
                    xmlValidityError(ctxt, XML_DTD_DUP_TOKEN,
6090
              "standalone: attribute enumeration value token %s duplicated\n",
6091
                                     name, NULL);
6092
                    if (!xmlDictOwns(ctxt->dict, name))
6093
                        xmlFree(name);
6094
                    break;
6095
                }
6096
                tmp = tmp->next;
6097
            }
6098
        }
6099
#endif /* LIBXML_VALID_ENABLED */
6100
0
  if (tmp == NULL) {
6101
0
      cur = xmlCreateEnumeration(name);
6102
0
      if (!xmlDictOwns(ctxt->dict, name))
6103
0
    xmlFree(name);
6104
0
      if (cur == NULL) {
6105
0
                xmlErrMemory(ctxt);
6106
0
                xmlFreeEnumeration(ret);
6107
0
                return(NULL);
6108
0
            }
6109
0
      if (last == NULL) ret = last = cur;
6110
0
      else {
6111
0
    last->next = cur;
6112
0
    last = cur;
6113
0
      }
6114
0
  }
6115
0
  SKIP_BLANKS_PE;
6116
0
    } while (RAW == '|');
6117
0
    if (RAW != ')') {
6118
0
  xmlFatalErr(ctxt, XML_ERR_ATTLIST_NOT_FINISHED, NULL);
6119
0
  return(ret);
6120
0
    }
6121
0
    NEXT;
6122
0
    return(ret);
6123
0
}
6124
6125
/**
6126
 * xmlParseEnumeratedType:
6127
 * @ctxt:  an XML parser context
6128
 * @tree:  the enumeration tree built while parsing
6129
 *
6130
 * DEPRECATED: Internal function, don't use.
6131
 *
6132
 * parse an Enumerated attribute type.
6133
 *
6134
 * [57] EnumeratedType ::= NotationType | Enumeration
6135
 *
6136
 * [58] NotationType ::= 'NOTATION' S '(' S? Name (S? '|' S? Name)* S? ')'
6137
 *
6138
 *
6139
 * Returns: XML_ATTRIBUTE_ENUMERATION or XML_ATTRIBUTE_NOTATION
6140
 */
6141
6142
int
6143
0
xmlParseEnumeratedType(xmlParserCtxtPtr ctxt, xmlEnumerationPtr *tree) {
6144
0
    if (CMP8(CUR_PTR, 'N', 'O', 'T', 'A', 'T', 'I', 'O', 'N')) {
6145
0
  SKIP(8);
6146
0
  if (SKIP_BLANKS_PE == 0) {
6147
0
      xmlFatalErrMsg(ctxt, XML_ERR_SPACE_REQUIRED,
6148
0
         "Space required after 'NOTATION'\n");
6149
0
      return(0);
6150
0
  }
6151
0
  *tree = xmlParseNotationType(ctxt);
6152
0
  if (*tree == NULL) return(0);
6153
0
  return(XML_ATTRIBUTE_NOTATION);
6154
0
    }
6155
0
    *tree = xmlParseEnumerationType(ctxt);
6156
0
    if (*tree == NULL) return(0);
6157
0
    return(XML_ATTRIBUTE_ENUMERATION);
6158
0
}
6159
6160
/**
6161
 * xmlParseAttributeType:
6162
 * @ctxt:  an XML parser context
6163
 * @tree:  the enumeration tree built while parsing
6164
 *
6165
 * DEPRECATED: Internal function, don't use.
6166
 *
6167
 * parse the Attribute list def for an element
6168
 *
6169
 * [54] AttType ::= StringType | TokenizedType | EnumeratedType
6170
 *
6171
 * [55] StringType ::= 'CDATA'
6172
 *
6173
 * [56] TokenizedType ::= 'ID' | 'IDREF' | 'IDREFS' | 'ENTITY' |
6174
 *                        'ENTITIES' | 'NMTOKEN' | 'NMTOKENS'
6175
 *
6176
 * Validity constraints for attribute values syntax are checked in
6177
 * xmlValidateAttributeValue()
6178
 *
6179
 * [ VC: ID ]
6180
 * Values of type ID must match the Name production. A name must not
6181
 * appear more than once in an XML document as a value of this type;
6182
 * i.e., ID values must uniquely identify the elements which bear them.
6183
 *
6184
 * [ VC: One ID per Element Type ]
6185
 * No element type may have more than one ID attribute specified.
6186
 *
6187
 * [ VC: ID Attribute Default ]
6188
 * An ID attribute must have a declared default of #IMPLIED or #REQUIRED.
6189
 *
6190
 * [ VC: IDREF ]
6191
 * Values of type IDREF must match the Name production, and values
6192
 * of type IDREFS must match Names; each IDREF Name must match the value
6193
 * of an ID attribute on some element in the XML document; i.e. IDREF
6194
 * values must match the value of some ID attribute.
6195
 *
6196
 * [ VC: Entity Name ]
6197
 * Values of type ENTITY must match the Name production, values
6198
 * of type ENTITIES must match Names; each Entity Name must match the
6199
 * name of an unparsed entity declared in the DTD.
6200
 *
6201
 * [ VC: Name Token ]
6202
 * Values of type NMTOKEN must match the Nmtoken production; values
6203
 * of type NMTOKENS must match Nmtokens.
6204
 *
6205
 * Returns the attribute type
6206
 */
6207
int
6208
796
xmlParseAttributeType(xmlParserCtxtPtr ctxt, xmlEnumerationPtr *tree) {
6209
796
    if (CMP5(CUR_PTR, 'C', 'D', 'A', 'T', 'A')) {
6210
442
  SKIP(5);
6211
442
  return(XML_ATTRIBUTE_CDATA);
6212
442
     } else if (CMP6(CUR_PTR, 'I', 'D', 'R', 'E', 'F', 'S')) {
6213
0
  SKIP(6);
6214
0
  return(XML_ATTRIBUTE_IDREFS);
6215
354
     } else if (CMP5(CUR_PTR, 'I', 'D', 'R', 'E', 'F')) {
6216
1
  SKIP(5);
6217
1
  return(XML_ATTRIBUTE_IDREF);
6218
353
     } else if ((RAW == 'I') && (NXT(1) == 'D')) {
6219
59
        SKIP(2);
6220
59
  return(XML_ATTRIBUTE_ID);
6221
294
     } else if (CMP6(CUR_PTR, 'E', 'N', 'T', 'I', 'T', 'Y')) {
6222
0
  SKIP(6);
6223
0
  return(XML_ATTRIBUTE_ENTITY);
6224
294
     } else if (CMP8(CUR_PTR, 'E', 'N', 'T', 'I', 'T', 'I', 'E', 'S')) {
6225
294
  SKIP(8);
6226
294
  return(XML_ATTRIBUTE_ENTITIES);
6227
294
     } else if (CMP8(CUR_PTR, 'N', 'M', 'T', 'O', 'K', 'E', 'N', 'S')) {
6228
0
  SKIP(8);
6229
0
  return(XML_ATTRIBUTE_NMTOKENS);
6230
0
     } else if (CMP7(CUR_PTR, 'N', 'M', 'T', 'O', 'K', 'E', 'N')) {
6231
0
  SKIP(7);
6232
0
  return(XML_ATTRIBUTE_NMTOKEN);
6233
0
     }
6234
0
     return(xmlParseEnumeratedType(ctxt, tree));
6235
796
}
6236
6237
/**
6238
 * xmlParseAttributeListDecl:
6239
 * @ctxt:  an XML parser context
6240
 *
6241
 * DEPRECATED: Internal function, don't use.
6242
 *
6243
 * Parse an attribute list declaration for an element. Always consumes '<!'.
6244
 *
6245
 * [52] AttlistDecl ::= '<!ATTLIST' S Name AttDef* S? '>'
6246
 *
6247
 * [53] AttDef ::= S Name S AttType S DefaultDecl
6248
 *
6249
 */
6250
void
6251
8.19k
xmlParseAttributeListDecl(xmlParserCtxtPtr ctxt) {
6252
8.19k
    const xmlChar *elemName;
6253
8.19k
    const xmlChar *attrName;
6254
8.19k
    xmlEnumerationPtr tree;
6255
6256
8.19k
    if ((CUR != '<') || (NXT(1) != '!'))
6257
0
        return;
6258
8.19k
    SKIP(2);
6259
6260
8.19k
    if (CMP7(CUR_PTR, 'A', 'T', 'T', 'L', 'I', 'S', 'T')) {
6261
8.19k
  int inputid = ctxt->input->id;
6262
6263
8.19k
  SKIP(7);
6264
8.19k
  if (SKIP_BLANKS_PE == 0) {
6265
0
      xmlFatalErrMsg(ctxt, XML_ERR_SPACE_REQUIRED,
6266
0
                     "Space required after '<!ATTLIST'\n");
6267
0
  }
6268
8.19k
        elemName = xmlParseName(ctxt);
6269
8.19k
  if (elemName == NULL) {
6270
0
      xmlFatalErrMsg(ctxt, XML_ERR_NAME_REQUIRED,
6271
0
         "ATTLIST: no name for Element\n");
6272
0
      return;
6273
0
  }
6274
8.19k
  SKIP_BLANKS_PE;
6275
8.19k
  GROW;
6276
8.98k
  while ((RAW != '>') && (PARSER_STOPPED(ctxt) == 0)) {
6277
805
      int type;
6278
805
      int def;
6279
805
      xmlChar *defaultValue = NULL;
6280
6281
805
      GROW;
6282
805
            tree = NULL;
6283
805
      attrName = xmlParseName(ctxt);
6284
805
      if (attrName == NULL) {
6285
5
    xmlFatalErrMsg(ctxt, XML_ERR_NAME_REQUIRED,
6286
5
             "ATTLIST: no name for Attribute\n");
6287
5
    break;
6288
5
      }
6289
800
      GROW;
6290
800
      if (SKIP_BLANKS_PE == 0) {
6291
4
    xmlFatalErrMsg(ctxt, XML_ERR_SPACE_REQUIRED,
6292
4
            "Space required after the attribute name\n");
6293
4
    break;
6294
4
      }
6295
6296
796
      type = xmlParseAttributeType(ctxt, &tree);
6297
796
      if (type <= 0) {
6298
0
          break;
6299
0
      }
6300
6301
796
      GROW;
6302
796
      if (SKIP_BLANKS_PE == 0) {
6303
0
    xmlFatalErrMsg(ctxt, XML_ERR_SPACE_REQUIRED,
6304
0
             "Space required after the attribute type\n");
6305
0
          if (tree != NULL)
6306
0
        xmlFreeEnumeration(tree);
6307
0
    break;
6308
0
      }
6309
6310
796
      def = xmlParseDefaultDecl(ctxt, &defaultValue);
6311
796
      if (def <= 0) {
6312
0
                if (defaultValue != NULL)
6313
0
        xmlFree(defaultValue);
6314
0
          if (tree != NULL)
6315
0
        xmlFreeEnumeration(tree);
6316
0
          break;
6317
0
      }
6318
796
      if ((type != XML_ATTRIBUTE_CDATA) && (defaultValue != NULL))
6319
57
          xmlAttrNormalizeSpace(defaultValue, defaultValue);
6320
6321
796
      GROW;
6322
796
            if (RAW != '>') {
6323
498
    if (SKIP_BLANKS_PE == 0) {
6324
6
        xmlFatalErrMsg(ctxt, XML_ERR_SPACE_REQUIRED,
6325
6
      "Space required after the attribute default value\n");
6326
6
        if (defaultValue != NULL)
6327
5
      xmlFree(defaultValue);
6328
6
        if (tree != NULL)
6329
0
      xmlFreeEnumeration(tree);
6330
6
        break;
6331
6
    }
6332
498
      }
6333
790
      if ((ctxt->sax != NULL) && (!ctxt->disableSAX) &&
6334
790
    (ctxt->sax->attributeDecl != NULL))
6335
790
    ctxt->sax->attributeDecl(ctxt->userData, elemName, attrName,
6336
790
                          type, def, defaultValue, tree);
6337
0
      else if (tree != NULL)
6338
0
    xmlFreeEnumeration(tree);
6339
6340
790
      if ((ctxt->sax2) && (defaultValue != NULL) &&
6341
790
          (def != XML_ATTRIBUTE_IMPLIED) &&
6342
790
    (def != XML_ATTRIBUTE_REQUIRED)) {
6343
320
    xmlAddDefAttrs(ctxt, elemName, attrName, defaultValue);
6344
320
      }
6345
790
      if (ctxt->sax2) {
6346
790
    xmlAddSpecialAttr(ctxt, elemName, attrName, type);
6347
790
      }
6348
790
      if (defaultValue != NULL)
6349
320
          xmlFree(defaultValue);
6350
790
      GROW;
6351
790
  }
6352
8.19k
  if (RAW == '>') {
6353
8.17k
      if (inputid != ctxt->input->id) {
6354
0
    xmlFatalErrMsg(ctxt, XML_ERR_ENTITY_BOUNDARY,
6355
0
                               "Attribute list declaration doesn't start and"
6356
0
                               " stop in the same entity\n");
6357
0
      }
6358
8.17k
      NEXT;
6359
8.17k
  }
6360
8.19k
    }
6361
8.19k
}
6362
6363
/**
6364
 * xmlParseElementMixedContentDecl:
6365
 * @ctxt:  an XML parser context
6366
 * @inputchk:  the input used for the current entity, needed for boundary checks
6367
 *
6368
 * DEPRECATED: Internal function, don't use.
6369
 *
6370
 * parse the declaration for a Mixed Element content
6371
 * The leading '(' and spaces have been skipped in xmlParseElementContentDecl
6372
 *
6373
 * [51] Mixed ::= '(' S? '#PCDATA' (S? '|' S? Name)* S? ')*' |
6374
 *                '(' S? '#PCDATA' S? ')'
6375
 *
6376
 * [ VC: Proper Group/PE Nesting ] applies to [51] too (see [49])
6377
 *
6378
 * [ VC: No Duplicate Types ]
6379
 * The same name must not appear more than once in a single
6380
 * mixed-content declaration.
6381
 *
6382
 * returns: the list of the xmlElementContentPtr describing the element choices
6383
 */
6384
xmlElementContentPtr
6385
0
xmlParseElementMixedContentDecl(xmlParserCtxtPtr ctxt, int inputchk) {
6386
0
    xmlElementContentPtr ret = NULL, cur = NULL, n;
6387
0
    const xmlChar *elem = NULL;
6388
6389
0
    GROW;
6390
0
    if (CMP7(CUR_PTR, '#', 'P', 'C', 'D', 'A', 'T', 'A')) {
6391
0
  SKIP(7);
6392
0
  SKIP_BLANKS_PE;
6393
0
  if (RAW == ')') {
6394
0
      if (ctxt->input->id != inputchk) {
6395
0
    xmlFatalErrMsg(ctxt, XML_ERR_ENTITY_BOUNDARY,
6396
0
                               "Element content declaration doesn't start and"
6397
0
                               " stop in the same entity\n");
6398
0
      }
6399
0
      NEXT;
6400
0
      ret = xmlNewDocElementContent(ctxt->myDoc, NULL, XML_ELEMENT_CONTENT_PCDATA);
6401
0
      if (ret == NULL)
6402
0
                goto mem_error;
6403
0
      if (RAW == '*') {
6404
0
    ret->ocur = XML_ELEMENT_CONTENT_MULT;
6405
0
    NEXT;
6406
0
      }
6407
0
      return(ret);
6408
0
  }
6409
0
  if ((RAW == '(') || (RAW == '|')) {
6410
0
      ret = cur = xmlNewDocElementContent(ctxt->myDoc, NULL, XML_ELEMENT_CONTENT_PCDATA);
6411
0
      if (ret == NULL)
6412
0
                goto mem_error;
6413
0
  }
6414
0
  while ((RAW == '|') && (PARSER_STOPPED(ctxt) == 0)) {
6415
0
      NEXT;
6416
0
            n = xmlNewDocElementContent(ctxt->myDoc, NULL, XML_ELEMENT_CONTENT_OR);
6417
0
            if (n == NULL)
6418
0
                goto mem_error;
6419
0
      if (elem == NULL) {
6420
0
    n->c1 = cur;
6421
0
    if (cur != NULL)
6422
0
        cur->parent = n;
6423
0
    ret = cur = n;
6424
0
      } else {
6425
0
          cur->c2 = n;
6426
0
    n->parent = cur;
6427
0
    n->c1 = xmlNewDocElementContent(ctxt->myDoc, elem, XML_ELEMENT_CONTENT_ELEMENT);
6428
0
                if (n->c1 == NULL)
6429
0
                    goto mem_error;
6430
0
    n->c1->parent = n;
6431
0
    cur = n;
6432
0
      }
6433
0
      SKIP_BLANKS_PE;
6434
0
      elem = xmlParseName(ctxt);
6435
0
      if (elem == NULL) {
6436
0
    xmlFatalErrMsg(ctxt, XML_ERR_NAME_REQUIRED,
6437
0
      "xmlParseElementMixedContentDecl : Name expected\n");
6438
0
    xmlFreeDocElementContent(ctxt->myDoc, ret);
6439
0
    return(NULL);
6440
0
      }
6441
0
      SKIP_BLANKS_PE;
6442
0
      GROW;
6443
0
  }
6444
0
  if ((RAW == ')') && (NXT(1) == '*')) {
6445
0
      if (elem != NULL) {
6446
0
    cur->c2 = xmlNewDocElementContent(ctxt->myDoc, elem,
6447
0
                                   XML_ELEMENT_CONTENT_ELEMENT);
6448
0
    if (cur->c2 == NULL)
6449
0
                    goto mem_error;
6450
0
    cur->c2->parent = cur;
6451
0
            }
6452
0
            if (ret != NULL)
6453
0
                ret->ocur = XML_ELEMENT_CONTENT_MULT;
6454
0
      if (ctxt->input->id != inputchk) {
6455
0
    xmlFatalErrMsg(ctxt, XML_ERR_ENTITY_BOUNDARY,
6456
0
                               "Element content declaration doesn't start and"
6457
0
                               " stop in the same entity\n");
6458
0
      }
6459
0
      SKIP(2);
6460
0
  } else {
6461
0
      xmlFreeDocElementContent(ctxt->myDoc, ret);
6462
0
      xmlFatalErr(ctxt, XML_ERR_MIXED_NOT_STARTED, NULL);
6463
0
      return(NULL);
6464
0
  }
6465
6466
0
    } else {
6467
0
  xmlFatalErr(ctxt, XML_ERR_PCDATA_REQUIRED, NULL);
6468
0
    }
6469
0
    return(ret);
6470
6471
0
mem_error:
6472
0
    xmlErrMemory(ctxt);
6473
0
    xmlFreeDocElementContent(ctxt->myDoc, ret);
6474
0
    return(NULL);
6475
0
}
6476
6477
/**
6478
 * xmlParseElementChildrenContentDeclPriv:
6479
 * @ctxt:  an XML parser context
6480
 * @inputchk:  the input used for the current entity, needed for boundary checks
6481
 * @depth: the level of recursion
6482
 *
6483
 * parse the declaration for a Mixed Element content
6484
 * The leading '(' and spaces have been skipped in xmlParseElementContentDecl
6485
 *
6486
 *
6487
 * [47] children ::= (choice | seq) ('?' | '*' | '+')?
6488
 *
6489
 * [48] cp ::= (Name | choice | seq) ('?' | '*' | '+')?
6490
 *
6491
 * [49] choice ::= '(' S? cp ( S? '|' S? cp )* S? ')'
6492
 *
6493
 * [50] seq ::= '(' S? cp ( S? ',' S? cp )* S? ')'
6494
 *
6495
 * [ VC: Proper Group/PE Nesting ] applies to [49] and [50]
6496
 * TODO Parameter-entity replacement text must be properly nested
6497
 *  with parenthesized groups. That is to say, if either of the
6498
 *  opening or closing parentheses in a choice, seq, or Mixed
6499
 *  construct is contained in the replacement text for a parameter
6500
 *  entity, both must be contained in the same replacement text. For
6501
 *  interoperability, if a parameter-entity reference appears in a
6502
 *  choice, seq, or Mixed construct, its replacement text should not
6503
 *  be empty, and neither the first nor last non-blank character of
6504
 *  the replacement text should be a connector (| or ,).
6505
 *
6506
 * Returns the tree of xmlElementContentPtr describing the element
6507
 *          hierarchy.
6508
 */
6509
static xmlElementContentPtr
6510
xmlParseElementChildrenContentDeclPriv(xmlParserCtxtPtr ctxt, int inputchk,
6511
6
                                       int depth) {
6512
6
    int maxDepth = (ctxt->options & XML_PARSE_HUGE) ? 2048 : 256;
6513
6
    xmlElementContentPtr ret = NULL, cur = NULL, last = NULL, op = NULL;
6514
6
    const xmlChar *elem;
6515
6
    xmlChar type = 0;
6516
6517
6
    if (depth > maxDepth) {
6518
0
        xmlFatalErrMsgInt(ctxt, XML_ERR_RESOURCE_LIMIT,
6519
0
                "xmlParseElementChildrenContentDecl : depth %d too deep, "
6520
0
                "use XML_PARSE_HUGE\n", depth);
6521
0
  return(NULL);
6522
0
    }
6523
6
    SKIP_BLANKS_PE;
6524
6
    GROW;
6525
6
    if (RAW == '(') {
6526
1
  int inputid = ctxt->input->id;
6527
6528
        /* Recurse on first child */
6529
1
  NEXT;
6530
1
  SKIP_BLANKS_PE;
6531
1
        cur = ret = xmlParseElementChildrenContentDeclPriv(ctxt, inputid,
6532
1
                                                           depth + 1);
6533
1
        if (cur == NULL)
6534
1
            return(NULL);
6535
0
  SKIP_BLANKS_PE;
6536
0
  GROW;
6537
5
    } else {
6538
5
  elem = xmlParseName(ctxt);
6539
5
  if (elem == NULL) {
6540
0
      xmlFatalErr(ctxt, XML_ERR_ELEMCONTENT_NOT_STARTED, NULL);
6541
0
      return(NULL);
6542
0
  }
6543
5
        cur = ret = xmlNewDocElementContent(ctxt->myDoc, elem, XML_ELEMENT_CONTENT_ELEMENT);
6544
5
  if (cur == NULL) {
6545
0
      xmlErrMemory(ctxt);
6546
0
      return(NULL);
6547
0
  }
6548
5
  GROW;
6549
5
  if (RAW == '?') {
6550
1
      cur->ocur = XML_ELEMENT_CONTENT_OPT;
6551
1
      NEXT;
6552
4
  } else if (RAW == '*') {
6553
0
      cur->ocur = XML_ELEMENT_CONTENT_MULT;
6554
0
      NEXT;
6555
4
  } else if (RAW == '+') {
6556
0
      cur->ocur = XML_ELEMENT_CONTENT_PLUS;
6557
0
      NEXT;
6558
4
  } else {
6559
4
      cur->ocur = XML_ELEMENT_CONTENT_ONCE;
6560
4
  }
6561
5
  GROW;
6562
5
    }
6563
5
    SKIP_BLANKS_PE;
6564
10
    while ((RAW != ')') && (PARSER_STOPPED(ctxt) == 0)) {
6565
        /*
6566
   * Each loop we parse one separator and one element.
6567
   */
6568
7
        if (RAW == ',') {
6569
5
      if (type == 0) type = CUR;
6570
6571
      /*
6572
       * Detect "Name | Name , Name" error
6573
       */
6574
3
      else if (type != CUR) {
6575
0
    xmlFatalErrMsgInt(ctxt, XML_ERR_SEPARATOR_REQUIRED,
6576
0
        "xmlParseElementChildrenContentDecl : '%c' expected\n",
6577
0
                      type);
6578
0
    if ((last != NULL) && (last != ret))
6579
0
        xmlFreeDocElementContent(ctxt->myDoc, last);
6580
0
    if (ret != NULL)
6581
0
        xmlFreeDocElementContent(ctxt->myDoc, ret);
6582
0
    return(NULL);
6583
0
      }
6584
5
      NEXT;
6585
6586
5
      op = xmlNewDocElementContent(ctxt->myDoc, NULL, XML_ELEMENT_CONTENT_SEQ);
6587
5
      if (op == NULL) {
6588
0
                xmlErrMemory(ctxt);
6589
0
    if ((last != NULL) && (last != ret))
6590
0
        xmlFreeDocElementContent(ctxt->myDoc, last);
6591
0
          xmlFreeDocElementContent(ctxt->myDoc, ret);
6592
0
    return(NULL);
6593
0
      }
6594
5
      if (last == NULL) {
6595
2
    op->c1 = ret;
6596
2
    if (ret != NULL)
6597
2
        ret->parent = op;
6598
2
    ret = cur = op;
6599
3
      } else {
6600
3
          cur->c2 = op;
6601
3
    if (op != NULL)
6602
3
        op->parent = cur;
6603
3
    op->c1 = last;
6604
3
    if (last != NULL)
6605
3
        last->parent = op;
6606
3
    cur =op;
6607
3
    last = NULL;
6608
3
      }
6609
5
  } else if (RAW == '|') {
6610
1
      if (type == 0) type = CUR;
6611
6612
      /*
6613
       * Detect "Name , Name | Name" error
6614
       */
6615
0
      else if (type != CUR) {
6616
0
    xmlFatalErrMsgInt(ctxt, XML_ERR_SEPARATOR_REQUIRED,
6617
0
        "xmlParseElementChildrenContentDecl : '%c' expected\n",
6618
0
          type);
6619
0
    if ((last != NULL) && (last != ret))
6620
0
        xmlFreeDocElementContent(ctxt->myDoc, last);
6621
0
    if (ret != NULL)
6622
0
        xmlFreeDocElementContent(ctxt->myDoc, ret);
6623
0
    return(NULL);
6624
0
      }
6625
1
      NEXT;
6626
6627
1
      op = xmlNewDocElementContent(ctxt->myDoc, NULL, XML_ELEMENT_CONTENT_OR);
6628
1
      if (op == NULL) {
6629
0
                xmlErrMemory(ctxt);
6630
0
    if ((last != NULL) && (last != ret))
6631
0
        xmlFreeDocElementContent(ctxt->myDoc, last);
6632
0
    if (ret != NULL)
6633
0
        xmlFreeDocElementContent(ctxt->myDoc, ret);
6634
0
    return(NULL);
6635
0
      }
6636
1
      if (last == NULL) {
6637
1
    op->c1 = ret;
6638
1
    if (ret != NULL)
6639
1
        ret->parent = op;
6640
1
    ret = cur = op;
6641
1
      } else {
6642
0
          cur->c2 = op;
6643
0
    if (op != NULL)
6644
0
        op->parent = cur;
6645
0
    op->c1 = last;
6646
0
    if (last != NULL)
6647
0
        last->parent = op;
6648
0
    cur =op;
6649
0
    last = NULL;
6650
0
      }
6651
1
  } else {
6652
1
      xmlFatalErr(ctxt, XML_ERR_ELEMCONTENT_NOT_FINISHED, NULL);
6653
1
      if ((last != NULL) && (last != ret))
6654
0
          xmlFreeDocElementContent(ctxt->myDoc, last);
6655
1
      if (ret != NULL)
6656
1
    xmlFreeDocElementContent(ctxt->myDoc, ret);
6657
1
      return(NULL);
6658
1
  }
6659
6
  GROW;
6660
6
  SKIP_BLANKS_PE;
6661
6
  GROW;
6662
6
  if (RAW == '(') {
6663
4
      int inputid = ctxt->input->id;
6664
      /* Recurse on second child */
6665
4
      NEXT;
6666
4
      SKIP_BLANKS_PE;
6667
4
      last = xmlParseElementChildrenContentDeclPriv(ctxt, inputid,
6668
4
                                                          depth + 1);
6669
4
            if (last == NULL) {
6670
1
    if (ret != NULL)
6671
1
        xmlFreeDocElementContent(ctxt->myDoc, ret);
6672
1
    return(NULL);
6673
1
            }
6674
3
      SKIP_BLANKS_PE;
6675
3
  } else {
6676
2
      elem = xmlParseName(ctxt);
6677
2
      if (elem == NULL) {
6678
0
    xmlFatalErr(ctxt, XML_ERR_ELEMCONTENT_NOT_STARTED, NULL);
6679
0
    if (ret != NULL)
6680
0
        xmlFreeDocElementContent(ctxt->myDoc, ret);
6681
0
    return(NULL);
6682
0
      }
6683
2
      last = xmlNewDocElementContent(ctxt->myDoc, elem, XML_ELEMENT_CONTENT_ELEMENT);
6684
2
      if (last == NULL) {
6685
0
                xmlErrMemory(ctxt);
6686
0
    if (ret != NULL)
6687
0
        xmlFreeDocElementContent(ctxt->myDoc, ret);
6688
0
    return(NULL);
6689
0
      }
6690
2
      if (RAW == '?') {
6691
1
    last->ocur = XML_ELEMENT_CONTENT_OPT;
6692
1
    NEXT;
6693
1
      } else if (RAW == '*') {
6694
0
    last->ocur = XML_ELEMENT_CONTENT_MULT;
6695
0
    NEXT;
6696
1
      } else if (RAW == '+') {
6697
0
    last->ocur = XML_ELEMENT_CONTENT_PLUS;
6698
0
    NEXT;
6699
1
      } else {
6700
1
    last->ocur = XML_ELEMENT_CONTENT_ONCE;
6701
1
      }
6702
2
  }
6703
5
  SKIP_BLANKS_PE;
6704
5
  GROW;
6705
5
    }
6706
3
    if ((cur != NULL) && (last != NULL)) {
6707
2
        cur->c2 = last;
6708
2
  if (last != NULL)
6709
2
      last->parent = cur;
6710
2
    }
6711
3
    if (ctxt->input->id != inputchk) {
6712
0
  xmlFatalErrMsg(ctxt, XML_ERR_ENTITY_BOUNDARY,
6713
0
                       "Element content declaration doesn't start and stop in"
6714
0
                       " the same entity\n");
6715
0
    }
6716
3
    NEXT;
6717
3
    if (RAW == '?') {
6718
0
  if (ret != NULL) {
6719
0
      if ((ret->ocur == XML_ELEMENT_CONTENT_PLUS) ||
6720
0
          (ret->ocur == XML_ELEMENT_CONTENT_MULT))
6721
0
          ret->ocur = XML_ELEMENT_CONTENT_MULT;
6722
0
      else
6723
0
          ret->ocur = XML_ELEMENT_CONTENT_OPT;
6724
0
  }
6725
0
  NEXT;
6726
3
    } else if (RAW == '*') {
6727
0
  if (ret != NULL) {
6728
0
      ret->ocur = XML_ELEMENT_CONTENT_MULT;
6729
0
      cur = ret;
6730
      /*
6731
       * Some normalization:
6732
       * (a | b* | c?)* == (a | b | c)*
6733
       */
6734
0
      while ((cur != NULL) && (cur->type == XML_ELEMENT_CONTENT_OR)) {
6735
0
    if ((cur->c1 != NULL) &&
6736
0
              ((cur->c1->ocur == XML_ELEMENT_CONTENT_OPT) ||
6737
0
         (cur->c1->ocur == XML_ELEMENT_CONTENT_MULT)))
6738
0
        cur->c1->ocur = XML_ELEMENT_CONTENT_ONCE;
6739
0
    if ((cur->c2 != NULL) &&
6740
0
              ((cur->c2->ocur == XML_ELEMENT_CONTENT_OPT) ||
6741
0
         (cur->c2->ocur == XML_ELEMENT_CONTENT_MULT)))
6742
0
        cur->c2->ocur = XML_ELEMENT_CONTENT_ONCE;
6743
0
    cur = cur->c2;
6744
0
      }
6745
0
  }
6746
0
  NEXT;
6747
3
    } else if (RAW == '+') {
6748
3
  if (ret != NULL) {
6749
3
      int found = 0;
6750
6751
3
      if ((ret->ocur == XML_ELEMENT_CONTENT_OPT) ||
6752
3
          (ret->ocur == XML_ELEMENT_CONTENT_MULT))
6753
0
          ret->ocur = XML_ELEMENT_CONTENT_MULT;
6754
3
      else
6755
3
          ret->ocur = XML_ELEMENT_CONTENT_PLUS;
6756
      /*
6757
       * Some normalization:
6758
       * (a | b*)+ == (a | b)*
6759
       * (a | b?)+ == (a | b)*
6760
       */
6761
4
      while ((cur != NULL) && (cur->type == XML_ELEMENT_CONTENT_OR)) {
6762
1
    if ((cur->c1 != NULL) &&
6763
1
              ((cur->c1->ocur == XML_ELEMENT_CONTENT_OPT) ||
6764
1
         (cur->c1->ocur == XML_ELEMENT_CONTENT_MULT))) {
6765
0
        cur->c1->ocur = XML_ELEMENT_CONTENT_ONCE;
6766
0
        found = 1;
6767
0
    }
6768
1
    if ((cur->c2 != NULL) &&
6769
1
              ((cur->c2->ocur == XML_ELEMENT_CONTENT_OPT) ||
6770
1
         (cur->c2->ocur == XML_ELEMENT_CONTENT_MULT))) {
6771
1
        cur->c2->ocur = XML_ELEMENT_CONTENT_ONCE;
6772
1
        found = 1;
6773
1
    }
6774
1
    cur = cur->c2;
6775
1
      }
6776
3
      if (found)
6777
1
    ret->ocur = XML_ELEMENT_CONTENT_MULT;
6778
3
  }
6779
3
  NEXT;
6780
3
    }
6781
3
    return(ret);
6782
5
}
6783
6784
/**
6785
 * xmlParseElementChildrenContentDecl:
6786
 * @ctxt:  an XML parser context
6787
 * @inputchk:  the input used for the current entity, needed for boundary checks
6788
 *
6789
 * DEPRECATED: Internal function, don't use.
6790
 *
6791
 * parse the declaration for a Mixed Element content
6792
 * The leading '(' and spaces have been skipped in xmlParseElementContentDecl
6793
 *
6794
 * [47] children ::= (choice | seq) ('?' | '*' | '+')?
6795
 *
6796
 * [48] cp ::= (Name | choice | seq) ('?' | '*' | '+')?
6797
 *
6798
 * [49] choice ::= '(' S? cp ( S? '|' S? cp )* S? ')'
6799
 *
6800
 * [50] seq ::= '(' S? cp ( S? ',' S? cp )* S? ')'
6801
 *
6802
 * [ VC: Proper Group/PE Nesting ] applies to [49] and [50]
6803
 * TODO Parameter-entity replacement text must be properly nested
6804
 *  with parenthesized groups. That is to say, if either of the
6805
 *  opening or closing parentheses in a choice, seq, or Mixed
6806
 *  construct is contained in the replacement text for a parameter
6807
 *  entity, both must be contained in the same replacement text. For
6808
 *  interoperability, if a parameter-entity reference appears in a
6809
 *  choice, seq, or Mixed construct, its replacement text should not
6810
 *  be empty, and neither the first nor last non-blank character of
6811
 *  the replacement text should be a connector (| or ,).
6812
 *
6813
 * Returns the tree of xmlElementContentPtr describing the element
6814
 *          hierarchy.
6815
 */
6816
xmlElementContentPtr
6817
0
xmlParseElementChildrenContentDecl(xmlParserCtxtPtr ctxt, int inputchk) {
6818
    /* stub left for API/ABI compat */
6819
0
    return(xmlParseElementChildrenContentDeclPriv(ctxt, inputchk, 1));
6820
0
}
6821
6822
/**
6823
 * xmlParseElementContentDecl:
6824
 * @ctxt:  an XML parser context
6825
 * @name:  the name of the element being defined.
6826
 * @result:  the Element Content pointer will be stored here if any
6827
 *
6828
 * DEPRECATED: Internal function, don't use.
6829
 *
6830
 * parse the declaration for an Element content either Mixed or Children,
6831
 * the cases EMPTY and ANY are handled directly in xmlParseElementDecl
6832
 *
6833
 * [46] contentspec ::= 'EMPTY' | 'ANY' | Mixed | children
6834
 *
6835
 * returns: the type of element content XML_ELEMENT_TYPE_xxx
6836
 */
6837
6838
int
6839
xmlParseElementContentDecl(xmlParserCtxtPtr ctxt, const xmlChar *name,
6840
1
                           xmlElementContentPtr *result) {
6841
6842
1
    xmlElementContentPtr tree = NULL;
6843
1
    int inputid = ctxt->input->id;
6844
1
    int res;
6845
6846
1
    *result = NULL;
6847
6848
1
    if (RAW != '(') {
6849
0
  xmlFatalErrMsgStr(ctxt, XML_ERR_ELEMCONTENT_NOT_STARTED,
6850
0
    "xmlParseElementContentDecl : %s '(' expected\n", name);
6851
0
  return(-1);
6852
0
    }
6853
1
    NEXT;
6854
1
    GROW;
6855
1
    SKIP_BLANKS_PE;
6856
1
    if (CMP7(CUR_PTR, '#', 'P', 'C', 'D', 'A', 'T', 'A')) {
6857
0
        tree = xmlParseElementMixedContentDecl(ctxt, inputid);
6858
0
  res = XML_ELEMENT_TYPE_MIXED;
6859
1
    } else {
6860
1
        tree = xmlParseElementChildrenContentDeclPriv(ctxt, inputid, 1);
6861
1
  res = XML_ELEMENT_TYPE_ELEMENT;
6862
1
    }
6863
1
    SKIP_BLANKS_PE;
6864
1
    *result = tree;
6865
1
    return(res);
6866
1
}
6867
6868
/**
6869
 * xmlParseElementDecl:
6870
 * @ctxt:  an XML parser context
6871
 *
6872
 * DEPRECATED: Internal function, don't use.
6873
 *
6874
 * Parse an element declaration. Always consumes '<!'.
6875
 *
6876
 * [45] elementdecl ::= '<!ELEMENT' S Name S contentspec S? '>'
6877
 *
6878
 * [ VC: Unique Element Type Declaration ]
6879
 * No element type may be declared more than once
6880
 *
6881
 * Returns the type of the element, or -1 in case of error
6882
 */
6883
int
6884
341
xmlParseElementDecl(xmlParserCtxtPtr ctxt) {
6885
341
    const xmlChar *name;
6886
341
    int ret = -1;
6887
341
    xmlElementContentPtr content  = NULL;
6888
6889
341
    if ((CUR != '<') || (NXT(1) != '!'))
6890
0
        return(ret);
6891
341
    SKIP(2);
6892
6893
    /* GROW; done in the caller */
6894
341
    if (CMP7(CUR_PTR, 'E', 'L', 'E', 'M', 'E', 'N', 'T')) {
6895
341
  int inputid = ctxt->input->id;
6896
6897
341
  SKIP(7);
6898
341
  if (SKIP_BLANKS_PE == 0) {
6899
0
      xmlFatalErrMsg(ctxt, XML_ERR_SPACE_REQUIRED,
6900
0
               "Space required after 'ELEMENT'\n");
6901
0
      return(-1);
6902
0
  }
6903
341
        name = xmlParseName(ctxt);
6904
341
  if (name == NULL) {
6905
0
      xmlFatalErrMsg(ctxt, XML_ERR_NAME_REQUIRED,
6906
0
         "xmlParseElementDecl: no name for Element\n");
6907
0
      return(-1);
6908
0
  }
6909
341
  if (SKIP_BLANKS_PE == 0) {
6910
0
      xmlFatalErrMsg(ctxt, XML_ERR_SPACE_REQUIRED,
6911
0
         "Space required after the element name\n");
6912
0
  }
6913
341
  if (CMP5(CUR_PTR, 'E', 'M', 'P', 'T', 'Y')) {
6914
2
      SKIP(5);
6915
      /*
6916
       * Element must always be empty.
6917
       */
6918
2
      ret = XML_ELEMENT_TYPE_EMPTY;
6919
339
  } else if ((RAW == 'A') && (NXT(1) == 'N') &&
6920
339
             (NXT(2) == 'Y')) {
6921
338
      SKIP(3);
6922
      /*
6923
       * Element is a generic container.
6924
       */
6925
338
      ret = XML_ELEMENT_TYPE_ANY;
6926
338
  } else if (RAW == '(') {
6927
1
      ret = xmlParseElementContentDecl(ctxt, name, &content);
6928
1
  } else {
6929
      /*
6930
       * [ WFC: PEs in Internal Subset ] error handling.
6931
       */
6932
0
            xmlFatalErrMsg(ctxt, XML_ERR_ELEMCONTENT_NOT_STARTED,
6933
0
                  "xmlParseElementDecl: 'EMPTY', 'ANY' or '(' expected\n");
6934
0
      return(-1);
6935
0
  }
6936
6937
341
  SKIP_BLANKS_PE;
6938
6939
341
  if (RAW != '>') {
6940
1
      xmlFatalErr(ctxt, XML_ERR_GT_REQUIRED, NULL);
6941
1
      if (content != NULL) {
6942
0
    xmlFreeDocElementContent(ctxt->myDoc, content);
6943
0
      }
6944
340
  } else {
6945
340
      if (inputid != ctxt->input->id) {
6946
0
    xmlFatalErrMsg(ctxt, XML_ERR_ENTITY_BOUNDARY,
6947
0
                               "Element declaration doesn't start and stop in"
6948
0
                               " the same entity\n");
6949
0
      }
6950
6951
340
      NEXT;
6952
340
      if ((ctxt->sax != NULL) && (!ctxt->disableSAX) &&
6953
340
    (ctxt->sax->elementDecl != NULL)) {
6954
340
    if (content != NULL)
6955
0
        content->parent = NULL;
6956
340
          ctxt->sax->elementDecl(ctxt->userData, name, ret,
6957
340
                           content);
6958
340
    if ((content != NULL) && (content->parent == NULL)) {
6959
        /*
6960
         * this is a trick: if xmlAddElementDecl is called,
6961
         * instead of copying the full tree it is plugged directly
6962
         * if called from the parser. Avoid duplicating the
6963
         * interfaces or change the API/ABI
6964
         */
6965
0
        xmlFreeDocElementContent(ctxt->myDoc, content);
6966
0
    }
6967
340
      } else if (content != NULL) {
6968
0
    xmlFreeDocElementContent(ctxt->myDoc, content);
6969
0
      }
6970
340
  }
6971
341
    }
6972
341
    return(ret);
6973
341
}
6974
6975
/**
6976
 * xmlParseConditionalSections
6977
 * @ctxt:  an XML parser context
6978
 *
6979
 * Parse a conditional section. Always consumes '<!['.
6980
 *
6981
 * [61] conditionalSect ::= includeSect | ignoreSect
6982
 * [62] includeSect ::= '<![' S? 'INCLUDE' S? '[' extSubsetDecl ']]>'
6983
 * [63] ignoreSect ::= '<![' S? 'IGNORE' S? '[' ignoreSectContents* ']]>'
6984
 * [64] ignoreSectContents ::= Ignore ('<![' ignoreSectContents ']]>' Ignore)*
6985
 * [65] Ignore ::= Char* - (Char* ('<![' | ']]>') Char*)
6986
 */
6987
6988
static void
6989
0
xmlParseConditionalSections(xmlParserCtxtPtr ctxt) {
6990
0
    int *inputIds = NULL;
6991
0
    size_t inputIdsSize = 0;
6992
0
    size_t depth = 0;
6993
6994
0
    while (PARSER_STOPPED(ctxt) == 0) {
6995
0
        if ((RAW == '<') && (NXT(1) == '!') && (NXT(2) == '[')) {
6996
0
            int id = ctxt->input->id;
6997
6998
0
            SKIP(3);
6999
0
            SKIP_BLANKS_PE;
7000
7001
0
            if (CMP7(CUR_PTR, 'I', 'N', 'C', 'L', 'U', 'D', 'E')) {
7002
0
                SKIP(7);
7003
0
                SKIP_BLANKS_PE;
7004
0
                if (RAW != '[') {
7005
0
                    xmlFatalErr(ctxt, XML_ERR_CONDSEC_INVALID, NULL);
7006
0
                    xmlHaltParser(ctxt);
7007
0
                    goto error;
7008
0
                }
7009
0
                if (ctxt->input->id != id) {
7010
0
                    xmlFatalErrMsg(ctxt, XML_ERR_ENTITY_BOUNDARY,
7011
0
                                   "All markup of the conditional section is"
7012
0
                                   " not in the same entity\n");
7013
0
                }
7014
0
                NEXT;
7015
7016
0
                if (inputIdsSize <= depth) {
7017
0
                    int *tmp;
7018
0
                    int newSize;
7019
7020
0
                    newSize = xmlGrowCapacity(inputIdsSize, sizeof(tmp[0]),
7021
0
                                              4, 1000);
7022
0
                    if (newSize < 0) {
7023
0
                        xmlFatalErrMsg(ctxt, XML_ERR_RESOURCE_LIMIT,
7024
0
                                       "Maximum conditional section nesting"
7025
0
                                       " depth exceeded\n");
7026
0
                        goto error;
7027
0
                    }
7028
0
                    tmp = xmlRealloc(inputIds, newSize * sizeof(tmp[0]));
7029
0
                    if (tmp == NULL) {
7030
0
                        xmlErrMemory(ctxt);
7031
0
                        goto error;
7032
0
                    }
7033
0
                    inputIds = tmp;
7034
0
                    inputIdsSize = newSize;
7035
0
                }
7036
0
                inputIds[depth] = id;
7037
0
                depth++;
7038
0
            } else if (CMP6(CUR_PTR, 'I', 'G', 'N', 'O', 'R', 'E')) {
7039
0
                size_t ignoreDepth = 0;
7040
7041
0
                SKIP(6);
7042
0
                SKIP_BLANKS_PE;
7043
0
                if (RAW != '[') {
7044
0
                    xmlFatalErr(ctxt, XML_ERR_CONDSEC_INVALID, NULL);
7045
0
                    xmlHaltParser(ctxt);
7046
0
                    goto error;
7047
0
                }
7048
0
                if (ctxt->input->id != id) {
7049
0
                    xmlFatalErrMsg(ctxt, XML_ERR_ENTITY_BOUNDARY,
7050
0
                                   "All markup of the conditional section is"
7051
0
                                   " not in the same entity\n");
7052
0
                }
7053
0
                NEXT;
7054
7055
0
                while (PARSER_STOPPED(ctxt) == 0) {
7056
0
                    if (RAW == 0) {
7057
0
                        xmlFatalErr(ctxt, XML_ERR_CONDSEC_NOT_FINISHED, NULL);
7058
0
                        goto error;
7059
0
                    }
7060
0
                    if ((RAW == '<') && (NXT(1) == '!') && (NXT(2) == '[')) {
7061
0
                        SKIP(3);
7062
0
                        ignoreDepth++;
7063
                        /* Check for integer overflow */
7064
0
                        if (ignoreDepth == 0) {
7065
0
                            xmlErrMemory(ctxt);
7066
0
                            goto error;
7067
0
                        }
7068
0
                    } else if ((RAW == ']') && (NXT(1) == ']') &&
7069
0
                               (NXT(2) == '>')) {
7070
0
                        SKIP(3);
7071
0
                        if (ignoreDepth == 0)
7072
0
                            break;
7073
0
                        ignoreDepth--;
7074
0
                    } else {
7075
0
                        NEXT;
7076
0
                    }
7077
0
                }
7078
7079
0
                if (ctxt->input->id != id) {
7080
0
                    xmlFatalErrMsg(ctxt, XML_ERR_ENTITY_BOUNDARY,
7081
0
                                   "All markup of the conditional section is"
7082
0
                                   " not in the same entity\n");
7083
0
                }
7084
0
            } else {
7085
0
                xmlFatalErr(ctxt, XML_ERR_CONDSEC_INVALID_KEYWORD, NULL);
7086
0
                xmlHaltParser(ctxt);
7087
0
                goto error;
7088
0
            }
7089
0
        } else if ((depth > 0) &&
7090
0
                   (RAW == ']') && (NXT(1) == ']') && (NXT(2) == '>')) {
7091
0
            depth--;
7092
0
            if (ctxt->input->id != inputIds[depth]) {
7093
0
                xmlFatalErrMsg(ctxt, XML_ERR_ENTITY_BOUNDARY,
7094
0
                               "All markup of the conditional section is not"
7095
0
                               " in the same entity\n");
7096
0
            }
7097
0
            SKIP(3);
7098
0
        } else if ((RAW == '<') && ((NXT(1) == '!') || (NXT(1) == '?'))) {
7099
0
            xmlParseMarkupDecl(ctxt);
7100
0
        } else {
7101
0
            xmlFatalErr(ctxt, XML_ERR_EXT_SUBSET_NOT_FINISHED, NULL);
7102
0
            xmlHaltParser(ctxt);
7103
0
            goto error;
7104
0
        }
7105
7106
0
        if (depth == 0)
7107
0
            break;
7108
7109
0
        SKIP_BLANKS_PE;
7110
0
        SHRINK;
7111
0
        GROW;
7112
0
    }
7113
7114
0
error:
7115
0
    xmlFree(inputIds);
7116
0
}
7117
7118
/**
7119
 * xmlParseMarkupDecl:
7120
 * @ctxt:  an XML parser context
7121
 *
7122
 * DEPRECATED: Internal function, don't use.
7123
 *
7124
 * Parse markup declarations. Always consumes '<!' or '<?'.
7125
 *
7126
 * [29] markupdecl ::= elementdecl | AttlistDecl | EntityDecl |
7127
 *                     NotationDecl | PI | Comment
7128
 *
7129
 * [ VC: Proper Declaration/PE Nesting ]
7130
 * Parameter-entity replacement text must be properly nested with
7131
 * markup declarations. That is to say, if either the first character
7132
 * or the last character of a markup declaration (markupdecl above) is
7133
 * contained in the replacement text for a parameter-entity reference,
7134
 * both must be contained in the same replacement text.
7135
 *
7136
 * [ WFC: PEs in Internal Subset ]
7137
 * In the internal DTD subset, parameter-entity references can occur
7138
 * only where markup declarations can occur, not within markup declarations.
7139
 * (This does not apply to references that occur in external parameter
7140
 * entities or to the external subset.)
7141
 */
7142
void
7143
53.5k
xmlParseMarkupDecl(xmlParserCtxtPtr ctxt) {
7144
53.5k
    GROW;
7145
53.5k
    if (CUR == '<') {
7146
53.5k
        if (NXT(1) == '!') {
7147
53.4k
      switch (NXT(2)) {
7148
28.3k
          case 'E':
7149
28.3k
        if (NXT(3) == 'L')
7150
341
      xmlParseElementDecl(ctxt);
7151
27.9k
        else if (NXT(3) == 'N')
7152
27.9k
      xmlParseEntityDecl(ctxt);
7153
2
                    else
7154
2
                        SKIP(2);
7155
28.3k
        break;
7156
8.19k
          case 'A':
7157
8.19k
        xmlParseAttributeListDecl(ctxt);
7158
8.19k
        break;
7159
1.21k
          case 'N':
7160
1.21k
        xmlParseNotationDecl(ctxt);
7161
1.21k
        break;
7162
7.87k
          case '-':
7163
7.87k
        xmlParseComment(ctxt);
7164
7.87k
        break;
7165
7.89k
    default:
7166
7.89k
                    xmlFatalErr(ctxt,
7167
7.89k
                                ctxt->inSubset == 2 ?
7168
0
                                    XML_ERR_EXT_SUBSET_NOT_FINISHED :
7169
7.89k
                                    XML_ERR_INT_SUBSET_NOT_FINISHED,
7170
7.89k
                                NULL);
7171
7.89k
                    SKIP(2);
7172
7.89k
        break;
7173
53.4k
      }
7174
53.4k
  } else if (NXT(1) == '?') {
7175
96
      xmlParsePI(ctxt);
7176
96
  }
7177
53.5k
    }
7178
53.5k
}
7179
7180
/**
7181
 * xmlParseTextDecl:
7182
 * @ctxt:  an XML parser context
7183
 *
7184
 * DEPRECATED: Internal function, don't use.
7185
 *
7186
 * parse an XML declaration header for external entities
7187
 *
7188
 * [77] TextDecl ::= '<?xml' VersionInfo? EncodingDecl S? '?>'
7189
 */
7190
7191
void
7192
0
xmlParseTextDecl(xmlParserCtxtPtr ctxt) {
7193
0
    xmlChar *version;
7194
7195
    /*
7196
     * We know that '<?xml' is here.
7197
     */
7198
0
    if ((CMP5(CUR_PTR, '<', '?', 'x', 'm', 'l')) && (IS_BLANK_CH(NXT(5)))) {
7199
0
  SKIP(5);
7200
0
    } else {
7201
0
  xmlFatalErr(ctxt, XML_ERR_XMLDECL_NOT_STARTED, NULL);
7202
0
  return;
7203
0
    }
7204
7205
0
    if (SKIP_BLANKS == 0) {
7206
0
  xmlFatalErrMsg(ctxt, XML_ERR_SPACE_REQUIRED,
7207
0
           "Space needed after '<?xml'\n");
7208
0
    }
7209
7210
    /*
7211
     * We may have the VersionInfo here.
7212
     */
7213
0
    version = xmlParseVersionInfo(ctxt);
7214
0
    if (version == NULL) {
7215
0
  version = xmlCharStrdup(XML_DEFAULT_VERSION);
7216
0
        if (version == NULL) {
7217
0
            xmlErrMemory(ctxt);
7218
0
            return;
7219
0
        }
7220
0
    } else {
7221
0
  if (SKIP_BLANKS == 0) {
7222
0
      xmlFatalErrMsg(ctxt, XML_ERR_SPACE_REQUIRED,
7223
0
               "Space needed here\n");
7224
0
  }
7225
0
    }
7226
0
    ctxt->input->version = version;
7227
7228
    /*
7229
     * We must have the encoding declaration
7230
     */
7231
0
    xmlParseEncodingDecl(ctxt);
7232
7233
0
    SKIP_BLANKS;
7234
0
    if ((RAW == '?') && (NXT(1) == '>')) {
7235
0
        SKIP(2);
7236
0
    } else if (RAW == '>') {
7237
        /* Deprecated old WD ... */
7238
0
  xmlFatalErr(ctxt, XML_ERR_XMLDECL_NOT_FINISHED, NULL);
7239
0
  NEXT;
7240
0
    } else {
7241
0
        int c;
7242
7243
0
  xmlFatalErr(ctxt, XML_ERR_XMLDECL_NOT_FINISHED, NULL);
7244
0
        while ((PARSER_STOPPED(ctxt) == 0) && ((c = CUR) != 0)) {
7245
0
            NEXT;
7246
0
            if (c == '>')
7247
0
                break;
7248
0
        }
7249
0
    }
7250
0
}
7251
7252
/**
7253
 * xmlParseExternalSubset:
7254
 * @ctxt:  an XML parser context
7255
 * @ExternalID: the external identifier
7256
 * @SystemID: the system identifier (or URL)
7257
 *
7258
 * DEPRECATED: Internal function, don't use.
7259
 *
7260
 * parse Markup declarations from an external subset
7261
 *
7262
 * [30] extSubset ::= textDecl? extSubsetDecl
7263
 *
7264
 * [31] extSubsetDecl ::= (markupdecl | conditionalSect | PEReference | S) *
7265
 */
7266
void
7267
xmlParseExternalSubset(xmlParserCtxtPtr ctxt, const xmlChar *ExternalID,
7268
0
                       const xmlChar *SystemID) {
7269
0
    int oldInputNr;
7270
7271
0
    xmlCtxtInitializeLate(ctxt);
7272
7273
0
    xmlDetectEncoding(ctxt);
7274
7275
0
    if (CMP5(CUR_PTR, '<', '?', 'x', 'm', 'l')) {
7276
0
  xmlParseTextDecl(ctxt);
7277
0
    }
7278
0
    if (ctxt->myDoc == NULL) {
7279
0
        ctxt->myDoc = xmlNewDoc(BAD_CAST "1.0");
7280
0
  if (ctxt->myDoc == NULL) {
7281
0
      xmlErrMemory(ctxt);
7282
0
      return;
7283
0
  }
7284
0
  ctxt->myDoc->properties = XML_DOC_INTERNAL;
7285
0
    }
7286
0
    if ((ctxt->myDoc != NULL) && (ctxt->myDoc->intSubset == NULL) &&
7287
0
        (xmlCreateIntSubset(ctxt->myDoc, NULL, ExternalID, SystemID) == NULL)) {
7288
0
        xmlErrMemory(ctxt);
7289
0
    }
7290
7291
0
    ctxt->inSubset = 2;
7292
0
    oldInputNr = ctxt->inputNr;
7293
7294
0
    SKIP_BLANKS_PE;
7295
0
    while (((RAW != 0) || (ctxt->inputNr > oldInputNr)) &&
7296
0
           (!PARSER_STOPPED(ctxt))) {
7297
0
  GROW;
7298
0
        if ((RAW == '<') && (NXT(1) == '!') && (NXT(2) == '[')) {
7299
0
            xmlParseConditionalSections(ctxt);
7300
0
        } else if ((RAW == '<') && ((NXT(1) == '!') || (NXT(1) == '?'))) {
7301
0
            xmlParseMarkupDecl(ctxt);
7302
0
        } else {
7303
0
            xmlFatalErr(ctxt, XML_ERR_EXT_SUBSET_NOT_FINISHED, NULL);
7304
0
            xmlHaltParser(ctxt);
7305
0
            return;
7306
0
        }
7307
0
        SKIP_BLANKS_PE;
7308
0
        SHRINK;
7309
0
    }
7310
7311
0
    while (ctxt->inputNr > oldInputNr)
7312
0
        xmlPopPE(ctxt);
7313
7314
0
    xmlParserCheckEOF(ctxt, XML_ERR_EXT_SUBSET_NOT_FINISHED);
7315
0
}
7316
7317
/**
7318
 * xmlParseReference:
7319
 * @ctxt:  an XML parser context
7320
 *
7321
 * DEPRECATED: Internal function, don't use.
7322
 *
7323
 * parse and handle entity references in content, depending on the SAX
7324
 * interface, this may end-up in a call to character() if this is a
7325
 * CharRef, a predefined entity, if there is no reference() callback.
7326
 * or if the parser was asked to switch to that mode.
7327
 *
7328
 * Always consumes '&'.
7329
 *
7330
 * [67] Reference ::= EntityRef | CharRef
7331
 */
7332
void
7333
36.0k
xmlParseReference(xmlParserCtxtPtr ctxt) {
7334
36.0k
    xmlEntityPtr ent = NULL;
7335
36.0k
    const xmlChar *name;
7336
36.0k
    xmlChar *val;
7337
7338
36.0k
    if (RAW != '&')
7339
0
        return;
7340
7341
    /*
7342
     * Simple case of a CharRef
7343
     */
7344
36.0k
    if (NXT(1) == '#') {
7345
5.95k
  int i = 0;
7346
5.95k
  xmlChar out[16];
7347
5.95k
  int value = xmlParseCharRef(ctxt);
7348
7349
5.95k
  if (value == 0)
7350
2.62k
      return;
7351
7352
        /*
7353
         * Just encode the value in UTF-8
7354
         */
7355
3.33k
        COPY_BUF(out, i, value);
7356
3.33k
        out[i] = 0;
7357
3.33k
        if ((ctxt->sax != NULL) && (ctxt->sax->characters != NULL) &&
7358
3.33k
            (!ctxt->disableSAX))
7359
3.33k
            ctxt->sax->characters(ctxt->userData, out, i);
7360
3.33k
  return;
7361
5.95k
    }
7362
7363
    /*
7364
     * We are seeing an entity reference
7365
     */
7366
30.0k
    name = xmlParseEntityRefInternal(ctxt);
7367
30.0k
    if (name == NULL)
7368
19.3k
        return;
7369
10.7k
    ent = xmlLookupGeneralEntity(ctxt, name, /* isAttr */ 0);
7370
10.7k
    if (ent == NULL) {
7371
        /*
7372
         * Create a reference for undeclared entities.
7373
         */
7374
8.64k
        if ((ctxt->replaceEntities == 0) &&
7375
8.64k
            (ctxt->sax != NULL) &&
7376
8.64k
            (ctxt->disableSAX == 0) &&
7377
8.64k
            (ctxt->sax->reference != NULL)) {
7378
8.64k
            ctxt->sax->reference(ctxt->userData, name);
7379
8.64k
        }
7380
8.64k
        return;
7381
8.64k
    }
7382
2.07k
    if (!ctxt->wellFormed)
7383
2.03k
  return;
7384
7385
    /* special case of predefined entities */
7386
47
    if ((ent->name == NULL) ||
7387
47
        (ent->etype == XML_INTERNAL_PREDEFINED_ENTITY)) {
7388
0
  val = ent->content;
7389
0
  if (val == NULL) return;
7390
  /*
7391
   * inline the entity.
7392
   */
7393
0
  if ((ctxt->sax != NULL) && (ctxt->sax->characters != NULL) &&
7394
0
      (!ctxt->disableSAX))
7395
0
      ctxt->sax->characters(ctxt->userData, val, xmlStrlen(val));
7396
0
  return;
7397
0
    }
7398
7399
    /*
7400
     * Some users try to parse entities on their own and used to set
7401
     * the renamed "checked" member. Fix the flags to cover this
7402
     * case.
7403
     */
7404
47
    if (((ent->flags & XML_ENT_PARSED) == 0) && (ent->children != NULL))
7405
0
        ent->flags |= XML_ENT_PARSED;
7406
7407
    /*
7408
     * The first reference to the entity trigger a parsing phase
7409
     * where the ent->children is filled with the result from
7410
     * the parsing.
7411
     * Note: external parsed entities will not be loaded, it is not
7412
     * required for a non-validating parser, unless the parsing option
7413
     * of validating, or substituting entities were given. Doing so is
7414
     * far more secure as the parser will only process data coming from
7415
     * the document entity by default.
7416
     *
7417
     * FIXME: This doesn't work correctly since entities can be
7418
     * expanded with different namespace declarations in scope.
7419
     * For example:
7420
     *
7421
     * <!DOCTYPE doc [
7422
     *   <!ENTITY ent "<ns:elem/>">
7423
     * ]>
7424
     * <doc>
7425
     *   <decl1 xmlns:ns="urn:ns1">
7426
     *     &ent;
7427
     *   </decl1>
7428
     *   <decl2 xmlns:ns="urn:ns2">
7429
     *     &ent;
7430
     *   </decl2>
7431
     * </doc>
7432
     *
7433
     * Proposed fix:
7434
     *
7435
     * - Ignore current namespace declarations when parsing the
7436
     *   entity. If a prefix can't be resolved, don't report an error
7437
     *   but mark it as unresolved.
7438
     * - Try to resolve these prefixes when expanding the entity.
7439
     *   This will require a specialized version of xmlStaticCopyNode
7440
     *   which can also make use of the namespace hash table to avoid
7441
     *   quadratic behavior.
7442
     *
7443
     * Alternatively, we could simply reparse the entity on each
7444
     * expansion like we already do with custom SAX callbacks.
7445
     * External entity content should be cached in this case.
7446
     */
7447
47
    if ((ent->etype == XML_INTERNAL_GENERAL_ENTITY) ||
7448
47
        (((ctxt->options & XML_PARSE_NO_XXE) == 0) &&
7449
0
         ((ctxt->replaceEntities) ||
7450
47
          (ctxt->validate)))) {
7451
47
        if ((ent->flags & XML_ENT_PARSED) == 0) {
7452
47
            xmlCtxtParseEntity(ctxt, ent);
7453
47
        } else if (ent->children == NULL) {
7454
            /*
7455
             * Probably running in SAX mode and the callbacks don't
7456
             * build the entity content. Parse the entity again.
7457
             *
7458
             * This will also be triggered in normal tree builder mode
7459
             * if an entity happens to be empty, causing unnecessary
7460
             * reloads. It's hard to come up with a reliable check in
7461
             * which mode we're running.
7462
             */
7463
0
            xmlCtxtParseEntity(ctxt, ent);
7464
0
        }
7465
47
    }
7466
7467
    /*
7468
     * We also check for amplification if entities aren't substituted.
7469
     * They might be expanded later.
7470
     */
7471
47
    if (xmlParserEntityCheck(ctxt, ent->expandedSize))
7472
0
        return;
7473
7474
47
    if ((ctxt->sax == NULL) || (ctxt->disableSAX))
7475
40
        return;
7476
7477
7
    if (ctxt->replaceEntities == 0) {
7478
  /*
7479
   * Create a reference
7480
   */
7481
7
        if (ctxt->sax->reference != NULL)
7482
7
      ctxt->sax->reference(ctxt->userData, ent->name);
7483
7
    } else if ((ent->children != NULL) && (ctxt->node != NULL)) {
7484
0
        xmlNodePtr copy, cur;
7485
7486
        /*
7487
         * Seems we are generating the DOM content, copy the tree
7488
   */
7489
0
        cur = ent->children;
7490
7491
        /*
7492
         * Handle first text node with SAX to coalesce text efficiently
7493
         */
7494
0
        if ((cur->type == XML_TEXT_NODE) ||
7495
0
            (cur->type == XML_CDATA_SECTION_NODE)) {
7496
0
            int len = xmlStrlen(cur->content);
7497
7498
0
            if ((cur->type == XML_TEXT_NODE) ||
7499
0
                (ctxt->options & XML_PARSE_NOCDATA)) {
7500
0
                if (ctxt->sax->characters != NULL)
7501
0
                    ctxt->sax->characters(ctxt, cur->content, len);
7502
0
            } else {
7503
0
                if (ctxt->sax->cdataBlock != NULL)
7504
0
                    ctxt->sax->cdataBlock(ctxt, cur->content, len);
7505
0
            }
7506
7507
0
            cur = cur->next;
7508
0
        }
7509
7510
0
        while (cur != NULL) {
7511
0
            xmlNodePtr last;
7512
7513
            /*
7514
             * Handle last text node with SAX to coalesce text efficiently
7515
             */
7516
0
            if ((cur->next == NULL) &&
7517
0
                ((cur->type == XML_TEXT_NODE) ||
7518
0
                 (cur->type == XML_CDATA_SECTION_NODE))) {
7519
0
                int len = xmlStrlen(cur->content);
7520
7521
0
                if ((cur->type == XML_TEXT_NODE) ||
7522
0
                    (ctxt->options & XML_PARSE_NOCDATA)) {
7523
0
                    if (ctxt->sax->characters != NULL)
7524
0
                        ctxt->sax->characters(ctxt, cur->content, len);
7525
0
                } else {
7526
0
                    if (ctxt->sax->cdataBlock != NULL)
7527
0
                        ctxt->sax->cdataBlock(ctxt, cur->content, len);
7528
0
                }
7529
7530
0
                break;
7531
0
            }
7532
7533
            /*
7534
             * Reset coalesce buffer stats only for non-text nodes.
7535
             */
7536
0
            ctxt->nodemem = 0;
7537
0
            ctxt->nodelen = 0;
7538
7539
0
            copy = xmlDocCopyNode(cur, ctxt->myDoc, 1);
7540
7541
0
            if (copy == NULL) {
7542
0
                xmlErrMemory(ctxt);
7543
0
                break;
7544
0
            }
7545
7546
0
            if (ctxt->parseMode == XML_PARSE_READER) {
7547
                /* Needed for reader */
7548
0
                copy->extra = cur->extra;
7549
                /* Maybe needed for reader */
7550
0
                copy->_private = cur->_private;
7551
0
            }
7552
7553
0
            copy->parent = ctxt->node;
7554
0
            last = ctxt->node->last;
7555
0
            if (last == NULL) {
7556
0
                ctxt->node->children = copy;
7557
0
            } else {
7558
0
                last->next = copy;
7559
0
                copy->prev = last;
7560
0
            }
7561
0
            ctxt->node->last = copy;
7562
7563
0
            cur = cur->next;
7564
0
        }
7565
0
    }
7566
7
}
7567
7568
static void
7569
28.3k
xmlHandleUndeclaredEntity(xmlParserCtxtPtr ctxt, const xmlChar *name) {
7570
    /*
7571
     * [ WFC: Entity Declared ]
7572
     * In a document without any DTD, a document with only an
7573
     * internal DTD subset which contains no parameter entity
7574
     * references, or a document with "standalone='yes'", the
7575
     * Name given in the entity reference must match that in an
7576
     * entity declaration, except that well-formed documents
7577
     * need not declare any of the following entities: amp, lt,
7578
     * gt, apos, quot.
7579
     * The declaration of a parameter entity must precede any
7580
     * reference to it.
7581
     * Similarly, the declaration of a general entity must
7582
     * precede any reference to it which appears in a default
7583
     * value in an attribute-list declaration. Note that if
7584
     * entities are declared in the external subset or in
7585
     * external parameter entities, a non-validating processor
7586
     * is not obligated to read and process their declarations;
7587
     * for such documents, the rule that an entity must be
7588
     * declared is a well-formedness constraint only if
7589
     * standalone='yes'.
7590
     */
7591
28.3k
    if ((ctxt->standalone == 1) ||
7592
28.3k
        ((ctxt->hasExternalSubset == 0) &&
7593
28.3k
         (ctxt->hasPErefs == 0))) {
7594
27.1k
        xmlFatalErrMsgStr(ctxt, XML_ERR_UNDECLARED_ENTITY,
7595
27.1k
                          "Entity '%s' not defined\n", name);
7596
27.1k
    } else if (ctxt->validate) {
7597
        /*
7598
         * [ VC: Entity Declared ]
7599
         * In a document with an external subset or external
7600
         * parameter entities with "standalone='no'", ...
7601
         * ... The declaration of a parameter entity must
7602
         * precede any reference to it...
7603
         */
7604
0
        xmlValidityError(ctxt, XML_ERR_UNDECLARED_ENTITY,
7605
0
                         "Entity '%s' not defined\n", name, NULL);
7606
1.16k
    } else if ((ctxt->loadsubset & ~XML_SKIP_IDS) ||
7607
1.16k
               ((ctxt->replaceEntities) &&
7608
1.16k
                ((ctxt->options & XML_PARSE_NO_XXE) == 0))) {
7609
        /*
7610
         * Also raise a non-fatal error
7611
         *
7612
         * - if the external subset is loaded and all entity declarations
7613
         *   should be available, or
7614
         * - entity substition was requested without restricting
7615
         *   external entity access.
7616
         */
7617
0
        xmlErrMsgStr(ctxt, XML_WAR_UNDECLARED_ENTITY,
7618
0
                     "Entity '%s' not defined\n", name);
7619
1.16k
    } else {
7620
1.16k
        xmlWarningMsg(ctxt, XML_WAR_UNDECLARED_ENTITY,
7621
1.16k
                      "Entity '%s' not defined\n", name, NULL);
7622
1.16k
    }
7623
7624
28.3k
    ctxt->valid = 0;
7625
28.3k
}
7626
7627
static xmlEntityPtr
7628
76.7k
xmlLookupGeneralEntity(xmlParserCtxtPtr ctxt, const xmlChar *name, int inAttr) {
7629
76.7k
    xmlEntityPtr ent = NULL;
7630
7631
    /*
7632
     * Predefined entities override any extra definition
7633
     */
7634
76.7k
    if ((ctxt->options & XML_PARSE_OLDSAX) == 0) {
7635
76.7k
        ent = xmlGetPredefinedEntity(name);
7636
76.7k
        if (ent != NULL)
7637
23.0k
            return(ent);
7638
76.7k
    }
7639
7640
    /*
7641
     * Ask first SAX for entity resolution, otherwise try the
7642
     * entities which may have stored in the parser context.
7643
     */
7644
53.6k
    if (ctxt->sax != NULL) {
7645
53.6k
  if (ctxt->sax->getEntity != NULL)
7646
53.6k
      ent = ctxt->sax->getEntity(ctxt->userData, name);
7647
53.6k
  if ((ctxt->wellFormed == 1 ) && (ent == NULL) &&
7648
53.6k
      (ctxt->options & XML_PARSE_OLDSAX))
7649
0
      ent = xmlGetPredefinedEntity(name);
7650
53.6k
  if ((ctxt->wellFormed == 1 ) && (ent == NULL) &&
7651
53.6k
      (ctxt->userData==ctxt)) {
7652
12
      ent = xmlSAX2GetEntity(ctxt, name);
7653
12
  }
7654
53.6k
    }
7655
7656
53.6k
    if (ent == NULL) {
7657
27.2k
        xmlHandleUndeclaredEntity(ctxt, name);
7658
27.2k
    }
7659
7660
    /*
7661
     * [ WFC: Parsed Entity ]
7662
     * An entity reference must not contain the name of an
7663
     * unparsed entity
7664
     */
7665
26.4k
    else if (ent->etype == XML_EXTERNAL_GENERAL_UNPARSED_ENTITY) {
7666
0
  xmlFatalErrMsgStr(ctxt, XML_ERR_UNPARSED_ENTITY,
7667
0
     "Entity reference to unparsed entity %s\n", name);
7668
0
        ent = NULL;
7669
0
    }
7670
7671
    /*
7672
     * [ WFC: No External Entity References ]
7673
     * Attribute values cannot contain direct or indirect
7674
     * entity references to external entities.
7675
     */
7676
26.4k
    else if (ent->etype == XML_EXTERNAL_GENERAL_PARSED_ENTITY) {
7677
0
        if (inAttr) {
7678
0
            xmlFatalErrMsgStr(ctxt, XML_ERR_ENTITY_IS_EXTERNAL,
7679
0
                 "Attribute references external entity '%s'\n", name);
7680
0
            ent = NULL;
7681
0
        }
7682
0
    }
7683
7684
53.6k
    return(ent);
7685
76.7k
}
7686
7687
/**
7688
 * xmlParseEntityRefInternal:
7689
 * @ctxt:  an XML parser context
7690
 * @inAttr:  whether we are in an attribute value
7691
 *
7692
 * Parse an entity reference. Always consumes '&'.
7693
 *
7694
 * [68] EntityRef ::= '&' Name ';'
7695
 *
7696
 * Returns the name, or NULL in case of error.
7697
 */
7698
static const xmlChar *
7699
61.4k
xmlParseEntityRefInternal(xmlParserCtxtPtr ctxt) {
7700
61.4k
    const xmlChar *name;
7701
7702
61.4k
    GROW;
7703
7704
61.4k
    if (RAW != '&')
7705
0
        return(NULL);
7706
61.4k
    NEXT;
7707
61.4k
    name = xmlParseName(ctxt);
7708
61.4k
    if (name == NULL) {
7709
10.1k
  xmlFatalErrMsg(ctxt, XML_ERR_NAME_REQUIRED,
7710
10.1k
           "xmlParseEntityRef: no name\n");
7711
10.1k
        return(NULL);
7712
10.1k
    }
7713
51.2k
    if (RAW != ';') {
7714
17.8k
  xmlFatalErr(ctxt, XML_ERR_ENTITYREF_SEMICOL_MISSING, NULL);
7715
17.8k
  return(NULL);
7716
17.8k
    }
7717
33.4k
    NEXT;
7718
7719
33.4k
    return(name);
7720
51.2k
}
7721
7722
/**
7723
 * xmlParseEntityRef:
7724
 * @ctxt:  an XML parser context
7725
 *
7726
 * DEPRECATED: Internal function, don't use.
7727
 *
7728
 * Returns the xmlEntityPtr if found, or NULL otherwise.
7729
 */
7730
xmlEntityPtr
7731
0
xmlParseEntityRef(xmlParserCtxtPtr ctxt) {
7732
0
    const xmlChar *name;
7733
7734
0
    if (ctxt == NULL)
7735
0
        return(NULL);
7736
7737
0
    name = xmlParseEntityRefInternal(ctxt);
7738
0
    if (name == NULL)
7739
0
        return(NULL);
7740
7741
0
    return(xmlLookupGeneralEntity(ctxt, name, /* inAttr */ 0));
7742
0
}
7743
7744
/**
7745
 * xmlParseStringEntityRef:
7746
 * @ctxt:  an XML parser context
7747
 * @str:  a pointer to an index in the string
7748
 *
7749
 * parse ENTITY references declarations, but this version parses it from
7750
 * a string value.
7751
 *
7752
 * [68] EntityRef ::= '&' Name ';'
7753
 *
7754
 * [ WFC: Entity Declared ]
7755
 * In a document without any DTD, a document with only an internal DTD
7756
 * subset which contains no parameter entity references, or a document
7757
 * with "standalone='yes'", the Name given in the entity reference
7758
 * must match that in an entity declaration, except that well-formed
7759
 * documents need not declare any of the following entities: amp, lt,
7760
 * gt, apos, quot.  The declaration of a parameter entity must precede
7761
 * any reference to it.  Similarly, the declaration of a general entity
7762
 * must precede any reference to it which appears in a default value in an
7763
 * attribute-list declaration. Note that if entities are declared in the
7764
 * external subset or in external parameter entities, a non-validating
7765
 * processor is not obligated to read and process their declarations;
7766
 * for such documents, the rule that an entity must be declared is a
7767
 * well-formedness constraint only if standalone='yes'.
7768
 *
7769
 * [ WFC: Parsed Entity ]
7770
 * An entity reference must not contain the name of an unparsed entity
7771
 *
7772
 * Returns the xmlEntityPtr if found, or NULL otherwise. The str pointer
7773
 * is updated to the current location in the string.
7774
 */
7775
static xmlChar *
7776
43.2k
xmlParseStringEntityRef(xmlParserCtxtPtr ctxt, const xmlChar ** str) {
7777
43.2k
    xmlChar *name;
7778
43.2k
    const xmlChar *ptr;
7779
43.2k
    xmlChar cur;
7780
7781
43.2k
    if ((str == NULL) || (*str == NULL))
7782
0
        return(NULL);
7783
43.2k
    ptr = *str;
7784
43.2k
    cur = *ptr;
7785
43.2k
    if (cur != '&')
7786
0
  return(NULL);
7787
7788
43.2k
    ptr++;
7789
43.2k
    name = xmlParseStringName(ctxt, &ptr);
7790
43.2k
    if (name == NULL) {
7791
2
  xmlFatalErrMsg(ctxt, XML_ERR_NAME_REQUIRED,
7792
2
           "xmlParseStringEntityRef: no name\n");
7793
2
  *str = ptr;
7794
2
  return(NULL);
7795
2
    }
7796
43.2k
    if (*ptr != ';') {
7797
0
  xmlFatalErr(ctxt, XML_ERR_ENTITYREF_SEMICOL_MISSING, NULL);
7798
0
        xmlFree(name);
7799
0
  *str = ptr;
7800
0
  return(NULL);
7801
0
    }
7802
43.2k
    ptr++;
7803
7804
43.2k
    *str = ptr;
7805
43.2k
    return(name);
7806
43.2k
}
7807
7808
/**
7809
 * xmlParsePEReference:
7810
 * @ctxt:  an XML parser context
7811
 *
7812
 * DEPRECATED: Internal function, don't use.
7813
 *
7814
 * Parse a parameter entity reference. Always consumes '%'.
7815
 *
7816
 * The entity content is handled directly by pushing it's content as
7817
 * a new input stream.
7818
 *
7819
 * [69] PEReference ::= '%' Name ';'
7820
 *
7821
 * [ WFC: No Recursion ]
7822
 * A parsed entity must not contain a recursive
7823
 * reference to itself, either directly or indirectly.
7824
 *
7825
 * [ WFC: Entity Declared ]
7826
 * In a document without any DTD, a document with only an internal DTD
7827
 * subset which contains no parameter entity references, or a document
7828
 * with "standalone='yes'", ...  ... The declaration of a parameter
7829
 * entity must precede any reference to it...
7830
 *
7831
 * [ VC: Entity Declared ]
7832
 * In a document with an external subset or external parameter entities
7833
 * with "standalone='no'", ...  ... The declaration of a parameter entity
7834
 * must precede any reference to it...
7835
 *
7836
 * [ WFC: In DTD ]
7837
 * Parameter-entity references may only appear in the DTD.
7838
 * NOTE: misleading but this is handled.
7839
 */
7840
void
7841
xmlParsePEReference(xmlParserCtxtPtr ctxt)
7842
11.9k
{
7843
11.9k
    const xmlChar *name;
7844
11.9k
    xmlEntityPtr entity = NULL;
7845
11.9k
    xmlParserInputPtr input;
7846
7847
11.9k
    if (RAW != '%')
7848
0
        return;
7849
11.9k
    NEXT;
7850
11.9k
    name = xmlParseName(ctxt);
7851
11.9k
    if (name == NULL) {
7852
46
  xmlFatalErrMsg(ctxt, XML_ERR_PEREF_NO_NAME, "PEReference: no name\n");
7853
46
  return;
7854
46
    }
7855
11.8k
    if (RAW != ';') {
7856
3.94k
  xmlFatalErr(ctxt, XML_ERR_PEREF_SEMICOL_MISSING, NULL);
7857
3.94k
        return;
7858
3.94k
    }
7859
7860
7.94k
    NEXT;
7861
7862
    /* Must be set before xmlHandleUndeclaredEntity */
7863
7.94k
    ctxt->hasPErefs = 1;
7864
7865
    /*
7866
     * Request the entity from SAX
7867
     */
7868
7.94k
    if ((ctxt->sax != NULL) &&
7869
7.94k
  (ctxt->sax->getParameterEntity != NULL))
7870
7.94k
  entity = ctxt->sax->getParameterEntity(ctxt->userData, name);
7871
7872
7.94k
    if (entity == NULL) {
7873
18
        xmlHandleUndeclaredEntity(ctxt, name);
7874
7.92k
    } else {
7875
  /*
7876
   * Internal checking in case the entity quest barfed
7877
   */
7878
7.92k
  if ((entity->etype != XML_INTERNAL_PARAMETER_ENTITY) &&
7879
7.92k
      (entity->etype != XML_EXTERNAL_PARAMETER_ENTITY)) {
7880
0
      xmlWarningMsg(ctxt, XML_WAR_UNDECLARED_ENTITY,
7881
0
      "Internal: %%%s; is not a parameter entity\n",
7882
0
        name, NULL);
7883
7.92k
  } else {
7884
7.92k
      if ((entity->etype == XML_EXTERNAL_PARAMETER_ENTITY) &&
7885
7.92k
                ((ctxt->options & XML_PARSE_NO_XXE) ||
7886
0
     ((ctxt->loadsubset == 0) &&
7887
0
      (ctxt->replaceEntities == 0) &&
7888
0
      (ctxt->validate == 0))))
7889
0
    return;
7890
7891
7.92k
            if (entity->flags & XML_ENT_EXPANDING) {
7892
0
                xmlFatalErr(ctxt, XML_ERR_ENTITY_LOOP, NULL);
7893
0
                xmlHaltParser(ctxt);
7894
0
                return;
7895
0
            }
7896
7897
7.92k
      input = xmlNewEntityInputStream(ctxt, entity);
7898
7.92k
      if (xmlCtxtPushInput(ctxt, input) < 0) {
7899
0
                xmlFreeInputStream(input);
7900
0
    return;
7901
0
            }
7902
7903
7.92k
            entity->flags |= XML_ENT_EXPANDING;
7904
7905
7.92k
            GROW;
7906
7907
7.92k
      if (entity->etype == XML_EXTERNAL_PARAMETER_ENTITY) {
7908
0
                xmlDetectEncoding(ctxt);
7909
7910
0
                if ((CMP5(CUR_PTR, '<', '?', 'x', 'm', 'l')) &&
7911
0
                    (IS_BLANK_CH(NXT(5)))) {
7912
0
                    xmlParseTextDecl(ctxt);
7913
0
                }
7914
0
            }
7915
7.92k
  }
7916
7.92k
    }
7917
7.94k
}
7918
7919
/**
7920
 * xmlLoadEntityContent:
7921
 * @ctxt:  an XML parser context
7922
 * @entity: an unloaded system entity
7923
 *
7924
 * Load the content of an entity.
7925
 *
7926
 * Returns 0 in case of success and -1 in case of failure
7927
 */
7928
static int
7929
0
xmlLoadEntityContent(xmlParserCtxtPtr ctxt, xmlEntityPtr entity) {
7930
0
    xmlParserInputPtr oldinput, input = NULL;
7931
0
    xmlParserInputPtr *oldinputTab;
7932
0
    const xmlChar *oldencoding;
7933
0
    xmlChar *content = NULL;
7934
0
    xmlResourceType rtype;
7935
0
    size_t length, i;
7936
0
    int oldinputNr, oldinputMax;
7937
0
    int ret = -1;
7938
0
    int res;
7939
7940
0
    if ((ctxt == NULL) || (entity == NULL) ||
7941
0
        ((entity->etype != XML_EXTERNAL_PARAMETER_ENTITY) &&
7942
0
   (entity->etype != XML_EXTERNAL_GENERAL_PARSED_ENTITY)) ||
7943
0
  (entity->content != NULL)) {
7944
0
  xmlFatalErr(ctxt, XML_ERR_ARGUMENT,
7945
0
              "xmlLoadEntityContent parameter error");
7946
0
        return(-1);
7947
0
    }
7948
7949
0
    if (entity->etype == XML_EXTERNAL_PARAMETER_ENTITY)
7950
0
        rtype = XML_RESOURCE_PARAMETER_ENTITY;
7951
0
    else
7952
0
        rtype = XML_RESOURCE_GENERAL_ENTITY;
7953
7954
0
    input = xmlLoadResource(ctxt, (char *) entity->URI,
7955
0
                            (char *) entity->ExternalID, rtype);
7956
0
    if (input == NULL)
7957
0
        return(-1);
7958
7959
0
    oldinput = ctxt->input;
7960
0
    oldinputNr = ctxt->inputNr;
7961
0
    oldinputMax = ctxt->inputMax;
7962
0
    oldinputTab = ctxt->inputTab;
7963
0
    oldencoding = ctxt->encoding;
7964
7965
0
    ctxt->input = NULL;
7966
0
    ctxt->inputNr = 0;
7967
0
    ctxt->inputMax = 1;
7968
0
    ctxt->encoding = NULL;
7969
0
    ctxt->inputTab = xmlMalloc(sizeof(xmlParserInputPtr));
7970
0
    if (ctxt->inputTab == NULL) {
7971
0
        xmlErrMemory(ctxt);
7972
0
        xmlFreeInputStream(input);
7973
0
        goto error;
7974
0
    }
7975
7976
0
    xmlBufResetInput(input->buf->buffer, input);
7977
7978
0
    if (xmlCtxtPushInput(ctxt, input) < 0) {
7979
0
        xmlFreeInputStream(input);
7980
0
        goto error;
7981
0
    }
7982
7983
0
    xmlDetectEncoding(ctxt);
7984
7985
    /*
7986
     * Parse a possible text declaration first
7987
     */
7988
0
    if ((CMP5(CUR_PTR, '<', '?', 'x', 'm', 'l')) && (IS_BLANK_CH(NXT(5)))) {
7989
0
  xmlParseTextDecl(ctxt);
7990
        /*
7991
         * An XML-1.0 document can't reference an entity not XML-1.0
7992
         */
7993
0
        if ((xmlStrEqual(ctxt->version, BAD_CAST "1.0")) &&
7994
0
            (!xmlStrEqual(ctxt->input->version, BAD_CAST "1.0"))) {
7995
0
            xmlFatalErrMsg(ctxt, XML_ERR_VERSION_MISMATCH,
7996
0
                           "Version mismatch between document and entity\n");
7997
0
        }
7998
0
    }
7999
8000
0
    length = input->cur - input->base;
8001
0
    xmlBufShrink(input->buf->buffer, length);
8002
0
    xmlSaturatedAdd(&ctxt->sizeentities, length);
8003
8004
0
    while ((res = xmlParserInputBufferGrow(input->buf, 4096)) > 0)
8005
0
        ;
8006
8007
0
    xmlBufResetInput(input->buf->buffer, input);
8008
8009
0
    if (res < 0) {
8010
0
        xmlCtxtErrIO(ctxt, input->buf->error, NULL);
8011
0
        goto error;
8012
0
    }
8013
8014
0
    length = xmlBufUse(input->buf->buffer);
8015
0
    if (length > INT_MAX) {
8016
0
        xmlErrMemory(ctxt);
8017
0
        goto error;
8018
0
    }
8019
8020
0
    content = xmlStrndup(xmlBufContent(input->buf->buffer), length);
8021
0
    if (content == NULL) {
8022
0
        xmlErrMemory(ctxt);
8023
0
        goto error;
8024
0
    }
8025
8026
0
    for (i = 0; i < length; ) {
8027
0
        int clen = length - i;
8028
0
        int c = xmlGetUTF8Char(content + i, &clen);
8029
8030
0
        if ((c < 0) || (!IS_CHAR(c))) {
8031
0
            xmlFatalErrMsgInt(ctxt, XML_ERR_INVALID_CHAR,
8032
0
                              "xmlLoadEntityContent: invalid char value %d\n",
8033
0
                              content[i]);
8034
0
            goto error;
8035
0
        }
8036
0
        i += clen;
8037
0
    }
8038
8039
0
    xmlSaturatedAdd(&ctxt->sizeentities, length);
8040
0
    entity->content = content;
8041
0
    entity->length = length;
8042
0
    content = NULL;
8043
0
    ret = 0;
8044
8045
0
error:
8046
0
    while (ctxt->inputNr > 0)
8047
0
        xmlFreeInputStream(xmlCtxtPopInput(ctxt));
8048
0
    xmlFree(ctxt->inputTab);
8049
0
    xmlFree((xmlChar *) ctxt->encoding);
8050
8051
0
    ctxt->input = oldinput;
8052
0
    ctxt->inputNr = oldinputNr;
8053
0
    ctxt->inputMax = oldinputMax;
8054
0
    ctxt->inputTab = oldinputTab;
8055
0
    ctxt->encoding = oldencoding;
8056
8057
0
    xmlFree(content);
8058
8059
0
    return(ret);
8060
0
}
8061
8062
/**
8063
 * xmlParseStringPEReference:
8064
 * @ctxt:  an XML parser context
8065
 * @str:  a pointer to an index in the string
8066
 *
8067
 * parse PEReference declarations
8068
 *
8069
 * [69] PEReference ::= '%' Name ';'
8070
 *
8071
 * [ WFC: No Recursion ]
8072
 * A parsed entity must not contain a recursive
8073
 * reference to itself, either directly or indirectly.
8074
 *
8075
 * [ WFC: Entity Declared ]
8076
 * In a document without any DTD, a document with only an internal DTD
8077
 * subset which contains no parameter entity references, or a document
8078
 * with "standalone='yes'", ...  ... The declaration of a parameter
8079
 * entity must precede any reference to it...
8080
 *
8081
 * [ VC: Entity Declared ]
8082
 * In a document with an external subset or external parameter entities
8083
 * with "standalone='no'", ...  ... The declaration of a parameter entity
8084
 * must precede any reference to it...
8085
 *
8086
 * [ WFC: In DTD ]
8087
 * Parameter-entity references may only appear in the DTD.
8088
 * NOTE: misleading but this is handled.
8089
 *
8090
 * Returns the string of the entity content.
8091
 *         str is updated to the current value of the index
8092
 */
8093
static xmlEntityPtr
8094
6.23k
xmlParseStringPEReference(xmlParserCtxtPtr ctxt, const xmlChar **str) {
8095
6.23k
    const xmlChar *ptr;
8096
6.23k
    xmlChar cur;
8097
6.23k
    xmlChar *name;
8098
6.23k
    xmlEntityPtr entity = NULL;
8099
8100
6.23k
    if ((str == NULL) || (*str == NULL)) return(NULL);
8101
6.23k
    ptr = *str;
8102
6.23k
    cur = *ptr;
8103
6.23k
    if (cur != '%')
8104
0
        return(NULL);
8105
6.23k
    ptr++;
8106
6.23k
    name = xmlParseStringName(ctxt, &ptr);
8107
6.23k
    if (name == NULL) {
8108
4.63k
  xmlFatalErrMsg(ctxt, XML_ERR_NAME_REQUIRED,
8109
4.63k
           "xmlParseStringPEReference: no name\n");
8110
4.63k
  *str = ptr;
8111
4.63k
  return(NULL);
8112
4.63k
    }
8113
1.60k
    cur = *ptr;
8114
1.60k
    if (cur != ';') {
8115
535
  xmlFatalErr(ctxt, XML_ERR_ENTITYREF_SEMICOL_MISSING, NULL);
8116
535
  xmlFree(name);
8117
535
  *str = ptr;
8118
535
  return(NULL);
8119
535
    }
8120
1.06k
    ptr++;
8121
8122
    /* Must be set before xmlHandleUndeclaredEntity */
8123
1.06k
    ctxt->hasPErefs = 1;
8124
8125
    /*
8126
     * Request the entity from SAX
8127
     */
8128
1.06k
    if ((ctxt->sax != NULL) &&
8129
1.06k
  (ctxt->sax->getParameterEntity != NULL))
8130
1.06k
  entity = ctxt->sax->getParameterEntity(ctxt->userData, name);
8131
8132
1.06k
    if (entity == NULL) {
8133
1.04k
        xmlHandleUndeclaredEntity(ctxt, name);
8134
1.04k
    } else {
8135
  /*
8136
   * Internal checking in case the entity quest barfed
8137
   */
8138
18
  if ((entity->etype != XML_INTERNAL_PARAMETER_ENTITY) &&
8139
18
      (entity->etype != XML_EXTERNAL_PARAMETER_ENTITY)) {
8140
0
      xmlWarningMsg(ctxt, XML_WAR_UNDECLARED_ENTITY,
8141
0
        "%%%s; is not a parameter entity\n",
8142
0
        name, NULL);
8143
0
  }
8144
18
    }
8145
8146
1.06k
    xmlFree(name);
8147
1.06k
    *str = ptr;
8148
1.06k
    return(entity);
8149
1.60k
}
8150
8151
/**
8152
 * xmlParseDocTypeDecl:
8153
 * @ctxt:  an XML parser context
8154
 *
8155
 * DEPRECATED: Internal function, don't use.
8156
 *
8157
 * parse a DOCTYPE declaration
8158
 *
8159
 * [28] doctypedecl ::= '<!DOCTYPE' S Name (S ExternalID)? S?
8160
 *                      ('[' (markupdecl | PEReference | S)* ']' S?)? '>'
8161
 *
8162
 * [ VC: Root Element Type ]
8163
 * The Name in the document type declaration must match the element
8164
 * type of the root element.
8165
 */
8166
8167
void
8168
391
xmlParseDocTypeDecl(xmlParserCtxtPtr ctxt) {
8169
391
    const xmlChar *name = NULL;
8170
391
    xmlChar *ExternalID = NULL;
8171
391
    xmlChar *URI = NULL;
8172
8173
    /*
8174
     * We know that '<!DOCTYPE' has been detected.
8175
     */
8176
391
    SKIP(9);
8177
8178
391
    if (SKIP_BLANKS == 0) {
8179
27
        xmlFatalErrMsg(ctxt, XML_ERR_SPACE_REQUIRED,
8180
27
                       "Space required after 'DOCTYPE'\n");
8181
27
    }
8182
8183
    /*
8184
     * Parse the DOCTYPE name.
8185
     */
8186
391
    name = xmlParseName(ctxt);
8187
391
    if (name == NULL) {
8188
0
  xmlFatalErrMsg(ctxt, XML_ERR_NAME_REQUIRED,
8189
0
           "xmlParseDocTypeDecl : no DOCTYPE name !\n");
8190
0
    }
8191
391
    ctxt->intSubName = name;
8192
8193
391
    SKIP_BLANKS;
8194
8195
    /*
8196
     * Check for SystemID and ExternalID
8197
     */
8198
391
    URI = xmlParseExternalID(ctxt, &ExternalID, 1);
8199
8200
391
    if ((URI != NULL) || (ExternalID != NULL)) {
8201
0
        ctxt->hasExternalSubset = 1;
8202
0
    }
8203
391
    ctxt->extSubURI = URI;
8204
391
    ctxt->extSubSystem = ExternalID;
8205
8206
391
    SKIP_BLANKS;
8207
8208
    /*
8209
     * Create and update the internal subset.
8210
     */
8211
391
    if ((ctxt->sax != NULL) && (ctxt->sax->internalSubset != NULL) &&
8212
391
  (!ctxt->disableSAX))
8213
391
  ctxt->sax->internalSubset(ctxt->userData, name, ExternalID, URI);
8214
8215
391
    if ((RAW != '[') && (RAW != '>')) {
8216
0
  xmlFatalErr(ctxt, XML_ERR_DOCTYPE_NOT_FINISHED, NULL);
8217
0
    }
8218
391
}
8219
8220
/**
8221
 * xmlParseInternalSubset:
8222
 * @ctxt:  an XML parser context
8223
 *
8224
 * parse the internal subset declaration
8225
 *
8226
 * [28 end] ('[' (markupdecl | PEReference | S)* ']' S?)? '>'
8227
 */
8228
8229
static void
8230
391
xmlParseInternalSubset(xmlParserCtxtPtr ctxt) {
8231
    /*
8232
     * Is there any DTD definition ?
8233
     */
8234
391
    if (RAW == '[') {
8235
391
        int oldInputNr = ctxt->inputNr;
8236
8237
391
        NEXT;
8238
  /*
8239
   * Parse the succession of Markup declarations and
8240
   * PEReferences.
8241
   * Subsequence (markupdecl | PEReference | S)*
8242
   */
8243
391
  SKIP_BLANKS;
8244
65.8k
  while (((RAW != ']') || (ctxt->inputNr > oldInputNr)) &&
8245
65.8k
               (PARSER_STOPPED(ctxt) == 0)) {
8246
8247
            /*
8248
             * Conditional sections are allowed from external entities included
8249
             * by PE References in the internal subset.
8250
             */
8251
65.5k
            if ((PARSER_EXTERNAL(ctxt)) &&
8252
65.5k
                (RAW == '<') && (NXT(1) == '!') && (NXT(2) == '[')) {
8253
0
                xmlParseConditionalSections(ctxt);
8254
65.5k
            } else if ((RAW == '<') && ((NXT(1) == '!') || (NXT(1) == '?'))) {
8255
53.5k
          xmlParseMarkupDecl(ctxt);
8256
53.5k
            } else if (RAW == '%') {
8257
11.9k
          xmlParsePEReference(ctxt);
8258
11.9k
            } else {
8259
26
    xmlFatalErr(ctxt, XML_ERR_INT_SUBSET_NOT_FINISHED, NULL);
8260
26
                break;
8261
26
            }
8262
65.5k
      SKIP_BLANKS_PE;
8263
65.5k
            SHRINK;
8264
65.5k
            GROW;
8265
65.5k
  }
8266
8267
406
        while (ctxt->inputNr > oldInputNr)
8268
15
            xmlPopPE(ctxt);
8269
8270
391
  if (RAW == ']') {
8271
326
      NEXT;
8272
326
      SKIP_BLANKS;
8273
326
  }
8274
391
    }
8275
8276
    /*
8277
     * We should be at the end of the DOCTYPE declaration.
8278
     */
8279
391
    if ((ctxt->wellFormed) && (RAW != '>')) {
8280
0
  xmlFatalErr(ctxt, XML_ERR_DOCTYPE_NOT_FINISHED, NULL);
8281
0
  return;
8282
0
    }
8283
391
    NEXT;
8284
391
}
8285
8286
#ifdef LIBXML_SAX1_ENABLED
8287
/**
8288
 * xmlParseAttribute:
8289
 * @ctxt:  an XML parser context
8290
 * @value:  a xmlChar ** used to store the value of the attribute
8291
 *
8292
 * DEPRECATED: Internal function, don't use.
8293
 *
8294
 * parse an attribute
8295
 *
8296
 * [41] Attribute ::= Name Eq AttValue
8297
 *
8298
 * [ WFC: No External Entity References ]
8299
 * Attribute values cannot contain direct or indirect entity references
8300
 * to external entities.
8301
 *
8302
 * [ WFC: No < in Attribute Values ]
8303
 * The replacement text of any entity referred to directly or indirectly in
8304
 * an attribute value (other than "&lt;") must not contain a <.
8305
 *
8306
 * [ VC: Attribute Value Type ]
8307
 * The attribute must have been declared; the value must be of the type
8308
 * declared for it.
8309
 *
8310
 * [25] Eq ::= S? '=' S?
8311
 *
8312
 * With namespace:
8313
 *
8314
 * [NS 11] Attribute ::= QName Eq AttValue
8315
 *
8316
 * Also the case QName == xmlns:??? is handled independently as a namespace
8317
 * definition.
8318
 *
8319
 * Returns the attribute name, and the value in *value.
8320
 */
8321
8322
const xmlChar *
8323
xmlParseAttribute(xmlParserCtxtPtr ctxt, xmlChar **value) {
8324
    const xmlChar *name;
8325
    xmlChar *val;
8326
8327
    *value = NULL;
8328
    GROW;
8329
    name = xmlParseName(ctxt);
8330
    if (name == NULL) {
8331
  xmlFatalErrMsg(ctxt, XML_ERR_NAME_REQUIRED,
8332
                 "error parsing attribute name\n");
8333
        return(NULL);
8334
    }
8335
8336
    /*
8337
     * read the value
8338
     */
8339
    SKIP_BLANKS;
8340
    if (RAW == '=') {
8341
        NEXT;
8342
  SKIP_BLANKS;
8343
  val = xmlParseAttValue(ctxt);
8344
    } else {
8345
  xmlFatalErrMsgStr(ctxt, XML_ERR_ATTRIBUTE_WITHOUT_VALUE,
8346
         "Specification mandates value for attribute %s\n", name);
8347
  return(name);
8348
    }
8349
8350
    /*
8351
     * Check that xml:lang conforms to the specification
8352
     * No more registered as an error, just generate a warning now
8353
     * since this was deprecated in XML second edition
8354
     */
8355
    if ((ctxt->pedantic) && (xmlStrEqual(name, BAD_CAST "xml:lang"))) {
8356
  if (!xmlCheckLanguageID(val)) {
8357
      xmlWarningMsg(ctxt, XML_WAR_LANG_VALUE,
8358
              "Malformed value for xml:lang : %s\n",
8359
        val, NULL);
8360
  }
8361
    }
8362
8363
    /*
8364
     * Check that xml:space conforms to the specification
8365
     */
8366
    if (xmlStrEqual(name, BAD_CAST "xml:space")) {
8367
  if (xmlStrEqual(val, BAD_CAST "default"))
8368
      *(ctxt->space) = 0;
8369
  else if (xmlStrEqual(val, BAD_CAST "preserve"))
8370
      *(ctxt->space) = 1;
8371
  else {
8372
    xmlWarningMsg(ctxt, XML_WAR_SPACE_VALUE,
8373
"Invalid value \"%s\" for xml:space : \"default\" or \"preserve\" expected\n",
8374
                                 val, NULL);
8375
  }
8376
    }
8377
8378
    *value = val;
8379
    return(name);
8380
}
8381
8382
/**
8383
 * xmlParseStartTag:
8384
 * @ctxt:  an XML parser context
8385
 *
8386
 * DEPRECATED: Internal function, don't use.
8387
 *
8388
 * Parse a start tag. Always consumes '<'.
8389
 *
8390
 * [40] STag ::= '<' Name (S Attribute)* S? '>'
8391
 *
8392
 * [ WFC: Unique Att Spec ]
8393
 * No attribute name may appear more than once in the same start-tag or
8394
 * empty-element tag.
8395
 *
8396
 * [44] EmptyElemTag ::= '<' Name (S Attribute)* S? '/>'
8397
 *
8398
 * [ WFC: Unique Att Spec ]
8399
 * No attribute name may appear more than once in the same start-tag or
8400
 * empty-element tag.
8401
 *
8402
 * With namespace:
8403
 *
8404
 * [NS 8] STag ::= '<' QName (S Attribute)* S? '>'
8405
 *
8406
 * [NS 10] EmptyElement ::= '<' QName (S Attribute)* S? '/>'
8407
 *
8408
 * Returns the element name parsed
8409
 */
8410
8411
const xmlChar *
8412
xmlParseStartTag(xmlParserCtxtPtr ctxt) {
8413
    const xmlChar *name;
8414
    const xmlChar *attname;
8415
    xmlChar *attvalue;
8416
    const xmlChar **atts = ctxt->atts;
8417
    int nbatts = 0;
8418
    int maxatts = ctxt->maxatts;
8419
    int i;
8420
8421
    if (RAW != '<') return(NULL);
8422
    NEXT1;
8423
8424
    name = xmlParseName(ctxt);
8425
    if (name == NULL) {
8426
  xmlFatalErrMsg(ctxt, XML_ERR_NAME_REQUIRED,
8427
       "xmlParseStartTag: invalid element name\n");
8428
        return(NULL);
8429
    }
8430
8431
    /*
8432
     * Now parse the attributes, it ends up with the ending
8433
     *
8434
     * (S Attribute)* S?
8435
     */
8436
    SKIP_BLANKS;
8437
    GROW;
8438
8439
    while (((RAW != '>') &&
8440
     ((RAW != '/') || (NXT(1) != '>')) &&
8441
     (IS_BYTE_CHAR(RAW))) && (PARSER_STOPPED(ctxt) == 0)) {
8442
  attname = xmlParseAttribute(ctxt, &attvalue);
8443
        if (attname == NULL)
8444
      break;
8445
        if (attvalue != NULL) {
8446
      /*
8447
       * [ WFC: Unique Att Spec ]
8448
       * No attribute name may appear more than once in the same
8449
       * start-tag or empty-element tag.
8450
       */
8451
      for (i = 0; i < nbatts;i += 2) {
8452
          if (xmlStrEqual(atts[i], attname)) {
8453
        xmlErrAttributeDup(ctxt, NULL, attname);
8454
        goto failed;
8455
    }
8456
      }
8457
      /*
8458
       * Add the pair to atts
8459
       */
8460
      if (nbatts + 4 > maxatts) {
8461
          const xmlChar **n;
8462
                int newSize;
8463
8464
                newSize = xmlGrowCapacity(maxatts, sizeof(n[0]) * 2,
8465
                                          11, XML_MAX_ATTRS);
8466
                if (newSize < 0) {
8467
        xmlErrMemory(ctxt);
8468
        goto failed;
8469
    }
8470
#ifdef FUZZING_BUILD_MODE_UNSAFE_FOR_PRODUCTION
8471
                if (newSize < 2)
8472
                    newSize = 2;
8473
#endif
8474
          n = xmlRealloc(atts, newSize * sizeof(n[0]) * 2);
8475
    if (n == NULL) {
8476
        xmlErrMemory(ctxt);
8477
        goto failed;
8478
    }
8479
    atts = n;
8480
                maxatts = newSize * 2;
8481
    ctxt->atts = atts;
8482
    ctxt->maxatts = maxatts;
8483
      }
8484
8485
      atts[nbatts++] = attname;
8486
      atts[nbatts++] = attvalue;
8487
      atts[nbatts] = NULL;
8488
      atts[nbatts + 1] = NULL;
8489
8490
            attvalue = NULL;
8491
  }
8492
8493
failed:
8494
8495
        if (attvalue != NULL)
8496
            xmlFree(attvalue);
8497
8498
  GROW
8499
  if ((RAW == '>') || (((RAW == '/') && (NXT(1) == '>'))))
8500
      break;
8501
  if (SKIP_BLANKS == 0) {
8502
      xmlFatalErrMsg(ctxt, XML_ERR_SPACE_REQUIRED,
8503
         "attributes construct error\n");
8504
  }
8505
  SHRINK;
8506
        GROW;
8507
    }
8508
8509
    /*
8510
     * SAX: Start of Element !
8511
     */
8512
    if ((ctxt->sax != NULL) && (ctxt->sax->startElement != NULL) &&
8513
  (!ctxt->disableSAX)) {
8514
  if (nbatts > 0)
8515
      ctxt->sax->startElement(ctxt->userData, name, atts);
8516
  else
8517
      ctxt->sax->startElement(ctxt->userData, name, NULL);
8518
    }
8519
8520
    if (atts != NULL) {
8521
        /* Free only the content strings */
8522
        for (i = 1;i < nbatts;i+=2)
8523
      if (atts[i] != NULL)
8524
         xmlFree((xmlChar *) atts[i]);
8525
    }
8526
    return(name);
8527
}
8528
8529
/**
8530
 * xmlParseEndTag1:
8531
 * @ctxt:  an XML parser context
8532
 * @line:  line of the start tag
8533
 * @nsNr:  number of namespaces on the start tag
8534
 *
8535
 * Parse an end tag. Always consumes '</'.
8536
 *
8537
 * [42] ETag ::= '</' Name S? '>'
8538
 *
8539
 * With namespace
8540
 *
8541
 * [NS 9] ETag ::= '</' QName S? '>'
8542
 */
8543
8544
static void
8545
xmlParseEndTag1(xmlParserCtxtPtr ctxt, int line) {
8546
    const xmlChar *name;
8547
8548
    GROW;
8549
    if ((RAW != '<') || (NXT(1) != '/')) {
8550
  xmlFatalErrMsg(ctxt, XML_ERR_LTSLASH_REQUIRED,
8551
           "xmlParseEndTag: '</' not found\n");
8552
  return;
8553
    }
8554
    SKIP(2);
8555
8556
    name = xmlParseNameAndCompare(ctxt,ctxt->name);
8557
8558
    /*
8559
     * We should definitely be at the ending "S? '>'" part
8560
     */
8561
    GROW;
8562
    SKIP_BLANKS;
8563
    if ((!IS_BYTE_CHAR(RAW)) || (RAW != '>')) {
8564
  xmlFatalErr(ctxt, XML_ERR_GT_REQUIRED, NULL);
8565
    } else
8566
  NEXT1;
8567
8568
    /*
8569
     * [ WFC: Element Type Match ]
8570
     * The Name in an element's end-tag must match the element type in the
8571
     * start-tag.
8572
     *
8573
     */
8574
    if (name != (xmlChar*)1) {
8575
        if (name == NULL) name = BAD_CAST "unparsable";
8576
        xmlFatalErrMsgStrIntStr(ctxt, XML_ERR_TAG_NAME_MISMATCH,
8577
         "Opening and ending tag mismatch: %s line %d and %s\n",
8578
                    ctxt->name, line, name);
8579
    }
8580
8581
    /*
8582
     * SAX: End of Tag
8583
     */
8584
    if ((ctxt->sax != NULL) && (ctxt->sax->endElement != NULL) &&
8585
  (!ctxt->disableSAX))
8586
        ctxt->sax->endElement(ctxt->userData, ctxt->name);
8587
8588
    namePop(ctxt);
8589
    spacePop(ctxt);
8590
}
8591
8592
/**
8593
 * xmlParseEndTag:
8594
 * @ctxt:  an XML parser context
8595
 *
8596
 * DEPRECATED: Internal function, don't use.
8597
 *
8598
 * parse an end of tag
8599
 *
8600
 * [42] ETag ::= '</' Name S? '>'
8601
 *
8602
 * With namespace
8603
 *
8604
 * [NS 9] ETag ::= '</' QName S? '>'
8605
 */
8606
8607
void
8608
xmlParseEndTag(xmlParserCtxtPtr ctxt) {
8609
    xmlParseEndTag1(ctxt, 0);
8610
}
8611
#endif /* LIBXML_SAX1_ENABLED */
8612
8613
/************************************************************************
8614
 *                  *
8615
 *          SAX 2 specific operations       *
8616
 *                  *
8617
 ************************************************************************/
8618
8619
/**
8620
 * xmlParseQNameHashed:
8621
 * @ctxt:  an XML parser context
8622
 * @prefix:  pointer to store the prefix part
8623
 *
8624
 * parse an XML Namespace QName
8625
 *
8626
 * [6]  QName  ::= (Prefix ':')? LocalPart
8627
 * [7]  Prefix  ::= NCName
8628
 * [8]  LocalPart  ::= NCName
8629
 *
8630
 * Returns the Name parsed or NULL
8631
 */
8632
8633
static xmlHashedString
8634
8.33M
xmlParseQNameHashed(xmlParserCtxtPtr ctxt, xmlHashedString *prefix) {
8635
8.33M
    xmlHashedString l, p;
8636
8.33M
    int start, isNCName = 0;
8637
8638
8.33M
    l.name = NULL;
8639
8.33M
    p.name = NULL;
8640
8641
8.33M
    GROW;
8642
8.33M
    start = CUR_PTR - BASE_PTR;
8643
8644
8.33M
    l = xmlParseNCName(ctxt);
8645
8.33M
    if (l.name != NULL) {
8646
4.15M
        isNCName = 1;
8647
4.15M
        if (CUR == ':') {
8648
82.3k
            NEXT;
8649
82.3k
            p = l;
8650
82.3k
            l = xmlParseNCName(ctxt);
8651
82.3k
        }
8652
4.15M
    }
8653
8.33M
    if ((l.name == NULL) || (CUR == ':')) {
8654
4.19M
        xmlChar *tmp;
8655
8656
4.19M
        l.name = NULL;
8657
4.19M
        p.name = NULL;
8658
4.19M
        if ((isNCName == 0) && (CUR != ':'))
8659
4.17M
            return(l);
8660
15.8k
        tmp = xmlParseNmtoken(ctxt);
8661
15.8k
        if (tmp != NULL)
8662
10.8k
            xmlFree(tmp);
8663
15.8k
        l = xmlDictLookupHashed(ctxt->dict, BASE_PTR + start,
8664
15.8k
                                CUR_PTR - (BASE_PTR + start));
8665
15.8k
        if (l.name == NULL) {
8666
0
            xmlErrMemory(ctxt);
8667
0
            return(l);
8668
0
        }
8669
15.8k
        xmlNsErr(ctxt, XML_NS_ERR_QNAME,
8670
15.8k
                 "Failed to parse QName '%s'\n", l.name, NULL, NULL);
8671
15.8k
    }
8672
8673
4.16M
    *prefix = p;
8674
4.16M
    return(l);
8675
8.33M
}
8676
8677
/**
8678
 * xmlParseQName:
8679
 * @ctxt:  an XML parser context
8680
 * @prefix:  pointer to store the prefix part
8681
 *
8682
 * parse an XML Namespace QName
8683
 *
8684
 * [6]  QName  ::= (Prefix ':')? LocalPart
8685
 * [7]  Prefix  ::= NCName
8686
 * [8]  LocalPart  ::= NCName
8687
 *
8688
 * Returns the Name parsed or NULL
8689
 */
8690
8691
static const xmlChar *
8692
1.45k
xmlParseQName(xmlParserCtxtPtr ctxt, const xmlChar **prefix) {
8693
1.45k
    xmlHashedString n, p;
8694
8695
1.45k
    n = xmlParseQNameHashed(ctxt, &p);
8696
1.45k
    if (n.name == NULL)
8697
127
        return(NULL);
8698
1.32k
    *prefix = p.name;
8699
1.32k
    return(n.name);
8700
1.45k
}
8701
8702
/**
8703
 * xmlParseQNameAndCompare:
8704
 * @ctxt:  an XML parser context
8705
 * @name:  the localname
8706
 * @prefix:  the prefix, if any.
8707
 *
8708
 * parse an XML name and compares for match
8709
 * (specialized for endtag parsing)
8710
 *
8711
 * Returns NULL for an illegal name, (xmlChar*) 1 for success
8712
 * and the name for mismatch
8713
 */
8714
8715
static const xmlChar *
8716
xmlParseQNameAndCompare(xmlParserCtxtPtr ctxt, xmlChar const *name,
8717
4.35k
                        xmlChar const *prefix) {
8718
4.35k
    const xmlChar *cmp;
8719
4.35k
    const xmlChar *in;
8720
4.35k
    const xmlChar *ret;
8721
4.35k
    const xmlChar *prefix2;
8722
8723
4.35k
    if (prefix == NULL) return(xmlParseNameAndCompare(ctxt, name));
8724
8725
4.35k
    GROW;
8726
4.35k
    in = ctxt->input->cur;
8727
8728
4.35k
    cmp = prefix;
8729
7.72k
    while (*in != 0 && *in == *cmp) {
8730
3.37k
  ++in;
8731
3.37k
  ++cmp;
8732
3.37k
    }
8733
4.35k
    if ((*cmp == 0) && (*in == ':')) {
8734
3.03k
        in++;
8735
3.03k
  cmp = name;
8736
5.97k
  while (*in != 0 && *in == *cmp) {
8737
2.94k
      ++in;
8738
2.94k
      ++cmp;
8739
2.94k
  }
8740
3.03k
  if (*cmp == 0 && (*in == '>' || IS_BLANK_CH (*in))) {
8741
      /* success */
8742
2.90k
            ctxt->input->col += in - ctxt->input->cur;
8743
2.90k
      ctxt->input->cur = in;
8744
2.90k
      return((const xmlChar*) 1);
8745
2.90k
  }
8746
3.03k
    }
8747
    /*
8748
     * all strings coms from the dictionary, equality can be done directly
8749
     */
8750
1.45k
    ret = xmlParseQName (ctxt, &prefix2);
8751
1.45k
    if (ret == NULL)
8752
127
        return(NULL);
8753
1.32k
    if ((ret == name) && (prefix == prefix2))
8754
37
  return((const xmlChar*) 1);
8755
1.28k
    return ret;
8756
1.32k
}
8757
8758
/**
8759
 * xmlParseAttribute2:
8760
 * @ctxt:  an XML parser context
8761
 * @pref:  the element prefix
8762
 * @elem:  the element name
8763
 * @prefix:  a xmlChar ** used to store the value of the attribute prefix
8764
 * @value:  a xmlChar ** used to store the value of the attribute
8765
 * @len:  an int * to save the length of the attribute
8766
 * @alloc:  an int * to indicate if the attribute was allocated
8767
 *
8768
 * parse an attribute in the new SAX2 framework.
8769
 *
8770
 * Returns the attribute name, and the value in *value, .
8771
 */
8772
8773
static xmlHashedString
8774
xmlParseAttribute2(xmlParserCtxtPtr ctxt,
8775
                   const xmlChar * pref, const xmlChar * elem,
8776
                   xmlHashedString * hprefix, xmlChar ** value,
8777
                   int *len, int *alloc)
8778
4.03M
{
8779
4.03M
    xmlHashedString hname;
8780
4.03M
    const xmlChar *prefix, *name;
8781
4.03M
    xmlChar *val = NULL, *internal_val = NULL;
8782
4.03M
    int normalize = 0;
8783
4.03M
    int isNamespace;
8784
8785
4.03M
    *value = NULL;
8786
4.03M
    GROW;
8787
4.03M
    hname = xmlParseQNameHashed(ctxt, hprefix);
8788
4.03M
    if (hname.name == NULL) {
8789
3.96M
        xmlFatalErrMsg(ctxt, XML_ERR_NAME_REQUIRED,
8790
3.96M
                       "error parsing attribute name\n");
8791
3.96M
        return(hname);
8792
3.96M
    }
8793
74.9k
    name = hname.name;
8794
74.9k
    prefix = hprefix->name;
8795
8796
    /*
8797
     * get the type if needed
8798
     */
8799
74.9k
    if (ctxt->attsSpecial != NULL) {
8800
2.27k
        int type;
8801
8802
2.27k
        type = XML_PTR_TO_INT(xmlHashQLookup2(ctxt->attsSpecial, pref, elem,
8803
2.27k
                                              prefix, name));
8804
2.27k
        if (type != 0)
8805
198
            normalize = 1;
8806
2.27k
    }
8807
8808
    /*
8809
     * read the value
8810
     */
8811
74.9k
    SKIP_BLANKS;
8812
74.9k
    if (RAW == '=') {
8813
60.9k
        NEXT;
8814
60.9k
        SKIP_BLANKS;
8815
60.9k
        isNamespace = (((prefix == NULL) && (name == ctxt->str_xmlns)) ||
8816
60.9k
                       (prefix == ctxt->str_xmlns));
8817
60.9k
        val = xmlParseAttValueInternal(ctxt, len, alloc, normalize,
8818
60.9k
                                       isNamespace);
8819
60.9k
        if (val == NULL)
8820
2.38k
            goto error;
8821
60.9k
    } else {
8822
14.0k
        xmlFatalErrMsgStr(ctxt, XML_ERR_ATTRIBUTE_WITHOUT_VALUE,
8823
14.0k
                          "Specification mandates value for attribute %s\n",
8824
14.0k
                          name);
8825
14.0k
        goto error;
8826
14.0k
    }
8827
8828
58.5k
    if (prefix == ctxt->str_xml) {
8829
        /*
8830
         * Check that xml:lang conforms to the specification
8831
         * No more registered as an error, just generate a warning now
8832
         * since this was deprecated in XML second edition
8833
         */
8834
10.1k
        if ((ctxt->pedantic) && (xmlStrEqual(name, BAD_CAST "lang"))) {
8835
0
            internal_val = xmlStrndup(val, *len);
8836
0
            if (internal_val == NULL)
8837
0
                goto mem_error;
8838
0
            if (!xmlCheckLanguageID(internal_val)) {
8839
0
                xmlWarningMsg(ctxt, XML_WAR_LANG_VALUE,
8840
0
                              "Malformed value for xml:lang : %s\n",
8841
0
                              internal_val, NULL);
8842
0
            }
8843
0
        }
8844
8845
        /*
8846
         * Check that xml:space conforms to the specification
8847
         */
8848
10.1k
        if (xmlStrEqual(name, BAD_CAST "space")) {
8849
5
            internal_val = xmlStrndup(val, *len);
8850
5
            if (internal_val == NULL)
8851
0
                goto mem_error;
8852
5
            if (xmlStrEqual(internal_val, BAD_CAST "default"))
8853
1
                *(ctxt->space) = 0;
8854
4
            else if (xmlStrEqual(internal_val, BAD_CAST "preserve"))
8855
0
                *(ctxt->space) = 1;
8856
4
            else {
8857
4
                xmlWarningMsg(ctxt, XML_WAR_SPACE_VALUE,
8858
4
                              "Invalid value \"%s\" for xml:space : \"default\" or \"preserve\" expected\n",
8859
4
                              internal_val, NULL);
8860
4
            }
8861
5
        }
8862
10.1k
        if (internal_val) {
8863
5
            xmlFree(internal_val);
8864
5
        }
8865
10.1k
    }
8866
8867
58.5k
    *value = val;
8868
58.5k
    return (hname);
8869
8870
0
mem_error:
8871
0
    xmlErrMemory(ctxt);
8872
16.4k
error:
8873
16.4k
    if ((val != NULL) && (*alloc != 0))
8874
0
        xmlFree(val);
8875
16.4k
    return(hname);
8876
0
}
8877
8878
/**
8879
 * xmlAttrHashInsert:
8880
 * @ctxt: parser context
8881
 * @size: size of the hash table
8882
 * @name: attribute name
8883
 * @uri: namespace uri
8884
 * @hashValue: combined hash value of name and uri
8885
 * @aindex: attribute index (this is a multiple of 5)
8886
 *
8887
 * Inserts a new attribute into the hash table.
8888
 *
8889
 * Returns INT_MAX if no existing attribute was found, the attribute
8890
 * index if an attribute was found, -1 if a memory allocation failed.
8891
 */
8892
static int
8893
xmlAttrHashInsert(xmlParserCtxtPtr ctxt, unsigned size, const xmlChar *name,
8894
14.0k
                  const xmlChar *uri, unsigned hashValue, int aindex) {
8895
14.0k
    xmlAttrHashBucket *table = ctxt->attrHash;
8896
14.0k
    xmlAttrHashBucket *bucket;
8897
14.0k
    unsigned hindex;
8898
8899
14.0k
    hindex = hashValue & (size - 1);
8900
14.0k
    bucket = &table[hindex];
8901
8902
14.6k
    while (bucket->index >= 0) {
8903
7.75k
        const xmlChar **atts = &ctxt->atts[bucket->index];
8904
8905
7.75k
        if (name == atts[0]) {
8906
7.58k
            int nsIndex = XML_PTR_TO_INT(atts[2]);
8907
8908
7.58k
            if ((nsIndex == NS_INDEX_EMPTY) ? (uri == NULL) :
8909
7.58k
                (nsIndex == NS_INDEX_XML) ? (uri == ctxt->str_xml_ns) :
8910
7.13k
                (uri == ctxt->nsTab[nsIndex * 2 + 1]))
8911
7.12k
                return(bucket->index);
8912
7.58k
        }
8913
8914
630
        hindex++;
8915
630
        bucket++;
8916
630
        if (hindex >= size) {
8917
201
            hindex = 0;
8918
201
            bucket = table;
8919
201
        }
8920
630
    }
8921
8922
6.91k
    bucket->index = aindex;
8923
8924
6.91k
    return(INT_MAX);
8925
14.0k
}
8926
8927
static int
8928
xmlAttrHashInsertQName(xmlParserCtxtPtr ctxt, unsigned size,
8929
                       const xmlChar *name, const xmlChar *prefix,
8930
6.61k
                       unsigned hashValue, int aindex) {
8931
6.61k
    xmlAttrHashBucket *table = ctxt->attrHash;
8932
6.61k
    xmlAttrHashBucket *bucket;
8933
6.61k
    unsigned hindex;
8934
8935
6.61k
    hindex = hashValue & (size - 1);
8936
6.61k
    bucket = &table[hindex];
8937
8938
12.7k
    while (bucket->index >= 0) {
8939
7.77k
        const xmlChar **atts = &ctxt->atts[bucket->index];
8940
8941
7.77k
        if ((name == atts[0]) && (prefix == atts[1]))
8942
1.64k
            return(bucket->index);
8943
8944
6.13k
        hindex++;
8945
6.13k
        bucket++;
8946
6.13k
        if (hindex >= size) {
8947
3.76k
            hindex = 0;
8948
3.76k
            bucket = table;
8949
3.76k
        }
8950
6.13k
    }
8951
8952
4.97k
    bucket->index = aindex;
8953
8954
4.97k
    return(INT_MAX);
8955
6.61k
}
8956
/**
8957
 * xmlParseStartTag2:
8958
 * @ctxt:  an XML parser context
8959
 *
8960
 * Parse a start tag. Always consumes '<'.
8961
 *
8962
 * This routine is called when running SAX2 parsing
8963
 *
8964
 * [40] STag ::= '<' Name (S Attribute)* S? '>'
8965
 *
8966
 * [ WFC: Unique Att Spec ]
8967
 * No attribute name may appear more than once in the same start-tag or
8968
 * empty-element tag.
8969
 *
8970
 * [44] EmptyElemTag ::= '<' Name (S Attribute)* S? '/>'
8971
 *
8972
 * [ WFC: Unique Att Spec ]
8973
 * No attribute name may appear more than once in the same start-tag or
8974
 * empty-element tag.
8975
 *
8976
 * With namespace:
8977
 *
8978
 * [NS 8] STag ::= '<' QName (S Attribute)* S? '>'
8979
 *
8980
 * [NS 10] EmptyElement ::= '<' QName (S Attribute)* S? '/>'
8981
 *
8982
 * Returns the element name parsed
8983
 */
8984
8985
static const xmlChar *
8986
xmlParseStartTag2(xmlParserCtxtPtr ctxt, const xmlChar **pref,
8987
4.29M
                  const xmlChar **URI, int *nbNsPtr) {
8988
4.29M
    xmlHashedString hlocalname;
8989
4.29M
    xmlHashedString hprefix;
8990
4.29M
    xmlHashedString hattname;
8991
4.29M
    xmlHashedString haprefix;
8992
4.29M
    const xmlChar *localname;
8993
4.29M
    const xmlChar *prefix;
8994
4.29M
    const xmlChar *attname;
8995
4.29M
    const xmlChar *aprefix;
8996
4.29M
    const xmlChar *uri;
8997
4.29M
    xmlChar *attvalue = NULL;
8998
4.29M
    const xmlChar **atts = ctxt->atts;
8999
4.29M
    unsigned attrHashSize = 0;
9000
4.29M
    int maxatts = ctxt->maxatts;
9001
4.29M
    int nratts, nbatts, nbdef;
9002
4.29M
    int i, j, nbNs, nbTotalDef, attval, nsIndex, maxAtts;
9003
4.29M
    int alloc = 0;
9004
4.29M
    int numNsErr = 0;
9005
4.29M
    int numDupErr = 0;
9006
9007
4.29M
    if (RAW != '<') return(NULL);
9008
4.29M
    NEXT1;
9009
9010
4.29M
    nbatts = 0;
9011
4.29M
    nratts = 0;
9012
4.29M
    nbdef = 0;
9013
4.29M
    nbNs = 0;
9014
4.29M
    nbTotalDef = 0;
9015
4.29M
    attval = 0;
9016
9017
4.29M
    if (xmlParserNsStartElement(ctxt->nsdb) < 0) {
9018
0
        xmlErrMemory(ctxt);
9019
0
        return(NULL);
9020
0
    }
9021
9022
4.29M
    hlocalname = xmlParseQNameHashed(ctxt, &hprefix);
9023
4.29M
    if (hlocalname.name == NULL) {
9024
212k
  xmlFatalErrMsg(ctxt, XML_ERR_NAME_REQUIRED,
9025
212k
           "StartTag: invalid element name\n");
9026
212k
        return(NULL);
9027
212k
    }
9028
4.08M
    localname = hlocalname.name;
9029
4.08M
    prefix = hprefix.name;
9030
9031
    /*
9032
     * Now parse the attributes, it ends up with the ending
9033
     *
9034
     * (S Attribute)* S?
9035
     */
9036
4.08M
    SKIP_BLANKS;
9037
4.08M
    GROW;
9038
9039
    /*
9040
     * The ctxt->atts array will be ultimately passed to the SAX callback
9041
     * containing five xmlChar pointers for each attribute:
9042
     *
9043
     * [0] attribute name
9044
     * [1] attribute prefix
9045
     * [2] namespace URI
9046
     * [3] attribute value
9047
     * [4] end of attribute value
9048
     *
9049
     * To save memory, we reuse this array temporarily and store integers
9050
     * in these pointer variables.
9051
     *
9052
     * [0] attribute name
9053
     * [1] attribute prefix
9054
     * [2] hash value of attribute prefix, and later namespace index
9055
     * [3] for non-allocated values: ptrdiff_t offset into input buffer
9056
     * [4] for non-allocated values: ptrdiff_t offset into input buffer
9057
     *
9058
     * The ctxt->attallocs array contains an additional unsigned int for
9059
     * each attribute, containing the hash value of the attribute name
9060
     * and the alloc flag in bit 31.
9061
     */
9062
9063
4.11M
    while (((RAW != '>') &&
9064
4.11M
     ((RAW != '/') || (NXT(1) != '>')) &&
9065
4.11M
     (IS_BYTE_CHAR(RAW))) && (PARSER_STOPPED(ctxt) == 0)) {
9066
4.03M
  int len = -1;
9067
9068
4.03M
  hattname = xmlParseAttribute2(ctxt, prefix, localname,
9069
4.03M
                                          &haprefix, &attvalue, &len,
9070
4.03M
                                          &alloc);
9071
4.03M
        if (hattname.name == NULL)
9072
3.96M
      break;
9073
74.9k
        if (attvalue == NULL)
9074
16.4k
            goto next_attr;
9075
58.5k
        attname = hattname.name;
9076
58.5k
        aprefix = haprefix.name;
9077
58.5k
  if (len < 0) len = xmlStrlen(attvalue);
9078
9079
58.5k
        if ((attname == ctxt->str_xmlns) && (aprefix == NULL)) {
9080
7.96k
            xmlHashedString huri;
9081
7.96k
            xmlURIPtr parsedUri;
9082
9083
7.96k
            huri = xmlDictLookupHashed(ctxt->dict, attvalue, len);
9084
7.96k
            uri = huri.name;
9085
7.96k
            if (uri == NULL) {
9086
0
                xmlErrMemory(ctxt);
9087
0
                goto next_attr;
9088
0
            }
9089
7.96k
            if (*uri != 0) {
9090
7.85k
                if (xmlParseURISafe((const char *) uri, &parsedUri) < 0) {
9091
0
                    xmlErrMemory(ctxt);
9092
0
                    goto next_attr;
9093
0
                }
9094
7.85k
                if (parsedUri == NULL) {
9095
3.65k
                    xmlNsErr(ctxt, XML_WAR_NS_URI,
9096
3.65k
                             "xmlns: '%s' is not a valid URI\n",
9097
3.65k
                                       uri, NULL, NULL);
9098
4.20k
                } else {
9099
4.20k
                    if (parsedUri->scheme == NULL) {
9100
3.84k
                        xmlNsWarn(ctxt, XML_WAR_NS_URI_RELATIVE,
9101
3.84k
                                  "xmlns: URI %s is not absolute\n",
9102
3.84k
                                  uri, NULL, NULL);
9103
3.84k
                    }
9104
4.20k
                    xmlFreeURI(parsedUri);
9105
4.20k
                }
9106
7.85k
                if (uri == ctxt->str_xml_ns) {
9107
0
                    if (attname != ctxt->str_xml) {
9108
0
                        xmlNsErr(ctxt, XML_NS_ERR_XML_NAMESPACE,
9109
0
                     "xml namespace URI cannot be the default namespace\n",
9110
0
                                 NULL, NULL, NULL);
9111
0
                    }
9112
0
                    goto next_attr;
9113
0
                }
9114
7.85k
                if ((len == 29) &&
9115
7.85k
                    (xmlStrEqual(uri,
9116
0
                             BAD_CAST "http://www.w3.org/2000/xmlns/"))) {
9117
0
                    xmlNsErr(ctxt, XML_NS_ERR_XML_NAMESPACE,
9118
0
                         "reuse of the xmlns namespace name is forbidden\n",
9119
0
                             NULL, NULL, NULL);
9120
0
                    goto next_attr;
9121
0
                }
9122
7.85k
            }
9123
9124
7.96k
            if (xmlParserNsPush(ctxt, NULL, &huri, NULL, 0) > 0)
9125
7.81k
                nbNs++;
9126
50.5k
        } else if (aprefix == ctxt->str_xmlns) {
9127
16.6k
            xmlHashedString huri;
9128
16.6k
            xmlURIPtr parsedUri;
9129
9130
16.6k
            huri = xmlDictLookupHashed(ctxt->dict, attvalue, len);
9131
16.6k
            uri = huri.name;
9132
16.6k
            if (uri == NULL) {
9133
0
                xmlErrMemory(ctxt);
9134
0
                goto next_attr;
9135
0
            }
9136
9137
16.6k
            if (attname == ctxt->str_xml) {
9138
0
                if (uri != ctxt->str_xml_ns) {
9139
0
                    xmlNsErr(ctxt, XML_NS_ERR_XML_NAMESPACE,
9140
0
                             "xml namespace prefix mapped to wrong URI\n",
9141
0
                             NULL, NULL, NULL);
9142
0
                }
9143
                /*
9144
                 * Do not keep a namespace definition node
9145
                 */
9146
0
                goto next_attr;
9147
0
            }
9148
16.6k
            if (uri == ctxt->str_xml_ns) {
9149
0
                if (attname != ctxt->str_xml) {
9150
0
                    xmlNsErr(ctxt, XML_NS_ERR_XML_NAMESPACE,
9151
0
                             "xml namespace URI mapped to wrong prefix\n",
9152
0
                             NULL, NULL, NULL);
9153
0
                }
9154
0
                goto next_attr;
9155
0
            }
9156
16.6k
            if (attname == ctxt->str_xmlns) {
9157
1
                xmlNsErr(ctxt, XML_NS_ERR_XML_NAMESPACE,
9158
1
                         "redefinition of the xmlns prefix is forbidden\n",
9159
1
                         NULL, NULL, NULL);
9160
1
                goto next_attr;
9161
1
            }
9162
16.6k
            if ((len == 29) &&
9163
16.6k
                (xmlStrEqual(uri,
9164
231
                             BAD_CAST "http://www.w3.org/2000/xmlns/"))) {
9165
193
                xmlNsErr(ctxt, XML_NS_ERR_XML_NAMESPACE,
9166
193
                         "reuse of the xmlns namespace name is forbidden\n",
9167
193
                         NULL, NULL, NULL);
9168
193
                goto next_attr;
9169
193
            }
9170
16.4k
            if ((uri == NULL) || (uri[0] == 0)) {
9171
445
                xmlNsErr(ctxt, XML_NS_ERR_XML_NAMESPACE,
9172
445
                         "xmlns:%s: Empty XML namespace is not allowed\n",
9173
445
                              attname, NULL, NULL);
9174
445
                goto next_attr;
9175
16.0k
            } else {
9176
16.0k
                if (xmlParseURISafe((const char *) uri, &parsedUri) < 0) {
9177
0
                    xmlErrMemory(ctxt);
9178
0
                    goto next_attr;
9179
0
                }
9180
16.0k
                if (parsedUri == NULL) {
9181
4.96k
                    xmlNsErr(ctxt, XML_WAR_NS_URI,
9182
4.96k
                         "xmlns:%s: '%s' is not a valid URI\n",
9183
4.96k
                                       attname, uri, NULL);
9184
11.0k
                } else {
9185
11.0k
                    if ((ctxt->pedantic) && (parsedUri->scheme == NULL)) {
9186
0
                        xmlNsWarn(ctxt, XML_WAR_NS_URI_RELATIVE,
9187
0
                                  "xmlns:%s: URI %s is not absolute\n",
9188
0
                                  attname, uri, NULL);
9189
0
                    }
9190
11.0k
                    xmlFreeURI(parsedUri);
9191
11.0k
                }
9192
16.0k
            }
9193
9194
16.0k
            if (xmlParserNsPush(ctxt, &hattname, &huri, NULL, 0) > 0)
9195
15.5k
                nbNs++;
9196
33.9k
        } else {
9197
            /*
9198
             * Populate attributes array, see above for repurposing
9199
             * of xmlChar pointers.
9200
             */
9201
33.9k
            if ((atts == NULL) || (nbatts + 5 > maxatts)) {
9202
601
                int res = xmlCtxtGrowAttrs(ctxt);
9203
9204
601
                maxatts = ctxt->maxatts;
9205
601
                atts = ctxt->atts;
9206
9207
601
                if (res < 0)
9208
0
                    goto next_attr;
9209
601
            }
9210
33.9k
            ctxt->attallocs[nratts++] = (hattname.hashValue & 0x7FFFFFFF) |
9211
33.9k
                                        ((unsigned) alloc << 31);
9212
33.9k
            atts[nbatts++] = attname;
9213
33.9k
            atts[nbatts++] = aprefix;
9214
33.9k
            atts[nbatts++] = (const xmlChar *) (size_t) haprefix.hashValue;
9215
33.9k
            if (alloc) {
9216
10.7k
                atts[nbatts++] = attvalue;
9217
10.7k
                attvalue += len;
9218
10.7k
                atts[nbatts++] = attvalue;
9219
23.1k
            } else {
9220
                /*
9221
                 * attvalue points into the input buffer which can be
9222
                 * reallocated. Store differences to input->base instead.
9223
                 * The pointers will be reconstructed later.
9224
                 */
9225
23.1k
                atts[nbatts++] = (void *) (attvalue - BASE_PTR);
9226
23.1k
                attvalue += len;
9227
23.1k
                atts[nbatts++] = (void *) (attvalue - BASE_PTR);
9228
23.1k
            }
9229
            /*
9230
             * tag if some deallocation is needed
9231
             */
9232
33.9k
            if (alloc != 0) attval = 1;
9233
33.9k
            attvalue = NULL; /* moved into atts */
9234
33.9k
        }
9235
9236
74.9k
next_attr:
9237
74.9k
        if ((attvalue != NULL) && (alloc != 0)) {
9238
7.82k
            xmlFree(attvalue);
9239
7.82k
            attvalue = NULL;
9240
7.82k
        }
9241
9242
74.9k
  GROW
9243
74.9k
  if ((RAW == '>') || (((RAW == '/') && (NXT(1) == '>'))))
9244
14.0k
      break;
9245
60.9k
  if (SKIP_BLANKS == 0) {
9246
28.3k
      xmlFatalErrMsg(ctxt, XML_ERR_SPACE_REQUIRED,
9247
28.3k
         "attributes construct error\n");
9248
28.3k
      break;
9249
28.3k
  }
9250
32.5k
        GROW;
9251
32.5k
    }
9252
9253
    /*
9254
     * Namespaces from default attributes
9255
     */
9256
4.08M
    if (ctxt->attsDefault != NULL) {
9257
25
        xmlDefAttrsPtr defaults;
9258
9259
25
  defaults = xmlHashLookup2(ctxt->attsDefault, localname, prefix);
9260
25
  if (defaults != NULL) {
9261
24
      for (i = 0; i < defaults->nbAttrs; i++) {
9262
12
                xmlDefAttr *attr = &defaults->attrs[i];
9263
9264
12
          attname = attr->name.name;
9265
12
    aprefix = attr->prefix.name;
9266
9267
12
    if ((attname == ctxt->str_xmlns) && (aprefix == NULL)) {
9268
0
                    xmlParserEntityCheck(ctxt, attr->expandedSize);
9269
9270
0
                    if (xmlParserNsPush(ctxt, NULL, &attr->value, NULL, 1) > 0)
9271
0
                        nbNs++;
9272
12
    } else if (aprefix == ctxt->str_xmlns) {
9273
0
                    xmlParserEntityCheck(ctxt, attr->expandedSize);
9274
9275
0
                    if (xmlParserNsPush(ctxt, &attr->name, &attr->value,
9276
0
                                      NULL, 1) > 0)
9277
0
                        nbNs++;
9278
12
    } else {
9279
12
                    if (nratts + nbTotalDef >= XML_MAX_ATTRS) {
9280
0
                        xmlFatalErr(ctxt, XML_ERR_RESOURCE_LIMIT,
9281
0
                                    "Maximum number of attributes exceeded");
9282
0
                        break;
9283
0
                    }
9284
12
                    nbTotalDef += 1;
9285
12
                }
9286
12
      }
9287
12
  }
9288
25
    }
9289
9290
    /*
9291
     * Resolve attribute namespaces
9292
     */
9293
4.11M
    for (i = 0; i < nbatts; i += 5) {
9294
33.9k
        attname = atts[i];
9295
33.9k
        aprefix = atts[i+1];
9296
9297
        /*
9298
  * The default namespace does not apply to attribute names.
9299
  */
9300
33.9k
  if (aprefix == NULL) {
9301
10.6k
            nsIndex = NS_INDEX_EMPTY;
9302
23.2k
        } else if (aprefix == ctxt->str_xml) {
9303
10.1k
            nsIndex = NS_INDEX_XML;
9304
13.1k
        } else {
9305
13.1k
            haprefix.name = aprefix;
9306
13.1k
            haprefix.hashValue = (size_t) atts[i+2];
9307
13.1k
            nsIndex = xmlParserNsLookup(ctxt, &haprefix, NULL);
9308
9309
13.1k
      if ((nsIndex == INT_MAX) || (nsIndex < ctxt->nsdb->minNsIndex)) {
9310
6.58k
                xmlNsErr(ctxt, XML_NS_ERR_UNDEFINED_NAMESPACE,
9311
6.58k
        "Namespace prefix %s for %s on %s is not defined\n",
9312
6.58k
        aprefix, attname, localname);
9313
6.58k
                nsIndex = NS_INDEX_EMPTY;
9314
6.58k
            }
9315
13.1k
        }
9316
9317
33.9k
        atts[i+2] = XML_INT_TO_PTR(nsIndex);
9318
33.9k
    }
9319
9320
    /*
9321
     * Maximum number of attributes including default attributes.
9322
     */
9323
4.08M
    maxAtts = nratts + nbTotalDef;
9324
9325
    /*
9326
     * Verify that attribute names are unique.
9327
     */
9328
4.08M
    if (maxAtts > 1) {
9329
4.21k
        attrHashSize = 4;
9330
8.18k
        while (attrHashSize / 2 < (unsigned) maxAtts)
9331
3.97k
            attrHashSize *= 2;
9332
9333
4.21k
        if (attrHashSize > ctxt->attrHashMax) {
9334
81
            xmlAttrHashBucket *tmp;
9335
9336
81
            tmp = xmlRealloc(ctxt->attrHash, attrHashSize * sizeof(tmp[0]));
9337
81
            if (tmp == NULL) {
9338
0
                xmlErrMemory(ctxt);
9339
0
                goto done;
9340
0
            }
9341
9342
81
            ctxt->attrHash = tmp;
9343
81
            ctxt->attrHashMax = attrHashSize;
9344
81
        }
9345
9346
4.21k
        memset(ctxt->attrHash, -1, attrHashSize * sizeof(ctxt->attrHash[0]));
9347
9348
23.1k
        for (i = 0, j = 0; j < nratts; i += 5, j++) {
9349
18.9k
            const xmlChar *nsuri;
9350
18.9k
            unsigned hashValue, nameHashValue, uriHashValue;
9351
18.9k
            int res;
9352
9353
18.9k
            attname = atts[i];
9354
18.9k
            aprefix = atts[i+1];
9355
18.9k
            nsIndex = XML_PTR_TO_INT(atts[i+2]);
9356
            /* Hash values always have bit 31 set, see dict.c */
9357
18.9k
            nameHashValue = ctxt->attallocs[j] | 0x80000000;
9358
9359
18.9k
            if (nsIndex == NS_INDEX_EMPTY) {
9360
                /*
9361
                 * Prefix with empty namespace means an undeclared
9362
                 * prefix which was already reported above.
9363
                 */
9364
8.33k
                if (aprefix != NULL)
9365
4.91k
                    continue;
9366
3.41k
                nsuri = NULL;
9367
3.41k
                uriHashValue = URI_HASH_EMPTY;
9368
10.6k
            } else if (nsIndex == NS_INDEX_XML) {
9369
4.07k
                nsuri = ctxt->str_xml_ns;
9370
4.07k
                uriHashValue = URI_HASH_XML;
9371
6.55k
            } else {
9372
6.55k
                nsuri = ctxt->nsTab[nsIndex * 2 + 1];
9373
6.55k
                uriHashValue = ctxt->nsdb->extra[nsIndex].uriHashValue;
9374
6.55k
            }
9375
9376
14.0k
            hashValue = xmlDictCombineHash(nameHashValue, uriHashValue);
9377
14.0k
            res = xmlAttrHashInsert(ctxt, attrHashSize, attname, nsuri,
9378
14.0k
                                    hashValue, i);
9379
14.0k
            if (res < 0)
9380
0
                continue;
9381
9382
            /*
9383
             * [ WFC: Unique Att Spec ]
9384
             * No attribute name may appear more than once in the same
9385
             * start-tag or empty-element tag.
9386
             * As extended by the Namespace in XML REC.
9387
             */
9388
14.0k
            if (res < INT_MAX) {
9389
7.12k
                if (aprefix == atts[res+1]) {
9390
3.79k
                    xmlErrAttributeDup(ctxt, aprefix, attname);
9391
3.79k
                    numDupErr += 1;
9392
3.79k
                } else {
9393
3.33k
                    xmlNsErr(ctxt, XML_NS_ERR_ATTRIBUTE_REDEFINED,
9394
3.33k
                             "Namespaced Attribute %s in '%s' redefined\n",
9395
3.33k
                             attname, nsuri, NULL);
9396
3.33k
                    numNsErr += 1;
9397
3.33k
                }
9398
7.12k
            }
9399
14.0k
        }
9400
4.21k
    }
9401
9402
    /*
9403
     * Default attributes
9404
     */
9405
4.08M
    if (ctxt->attsDefault != NULL) {
9406
25
        xmlDefAttrsPtr defaults;
9407
9408
25
  defaults = xmlHashLookup2(ctxt->attsDefault, localname, prefix);
9409
25
  if (defaults != NULL) {
9410
24
      for (i = 0; i < defaults->nbAttrs; i++) {
9411
12
                xmlDefAttr *attr = &defaults->attrs[i];
9412
12
                const xmlChar *nsuri = NULL;
9413
12
                unsigned hashValue, uriHashValue = 0;
9414
12
                int res;
9415
9416
12
          attname = attr->name.name;
9417
12
    aprefix = attr->prefix.name;
9418
9419
12
    if ((attname == ctxt->str_xmlns) && (aprefix == NULL))
9420
0
                    continue;
9421
12
    if (aprefix == ctxt->str_xmlns)
9422
0
                    continue;
9423
9424
12
                if (aprefix == NULL) {
9425
0
                    nsIndex = NS_INDEX_EMPTY;
9426
0
                    nsuri = NULL;
9427
0
                    uriHashValue = URI_HASH_EMPTY;
9428
12
                } else if (aprefix == ctxt->str_xml) {
9429
0
                    nsIndex = NS_INDEX_XML;
9430
0
                    nsuri = ctxt->str_xml_ns;
9431
0
                    uriHashValue = URI_HASH_XML;
9432
12
                } else {
9433
12
                    nsIndex = xmlParserNsLookup(ctxt, &attr->prefix, NULL);
9434
12
                    if ((nsIndex == INT_MAX) ||
9435
12
                        (nsIndex < ctxt->nsdb->minNsIndex)) {
9436
12
                        xmlNsErr(ctxt, XML_NS_ERR_UNDEFINED_NAMESPACE,
9437
12
                                 "Namespace prefix %s for %s on %s is not "
9438
12
                                 "defined\n",
9439
12
                                 aprefix, attname, localname);
9440
12
                        nsIndex = NS_INDEX_EMPTY;
9441
12
                        nsuri = NULL;
9442
12
                        uriHashValue = URI_HASH_EMPTY;
9443
12
                    } else {
9444
0
                        nsuri = ctxt->nsTab[nsIndex * 2 + 1];
9445
0
                        uriHashValue = ctxt->nsdb->extra[nsIndex].uriHashValue;
9446
0
                    }
9447
12
                }
9448
9449
                /*
9450
                 * Check whether the attribute exists
9451
                 */
9452
12
                if (maxAtts > 1) {
9453
3
                    hashValue = xmlDictCombineHash(attr->name.hashValue,
9454
3
                                                   uriHashValue);
9455
3
                    res = xmlAttrHashInsert(ctxt, attrHashSize, attname, nsuri,
9456
3
                                            hashValue, nbatts);
9457
3
                    if (res < 0)
9458
0
                        continue;
9459
3
                    if (res < INT_MAX) {
9460
2
                        if (aprefix == atts[res+1])
9461
0
                            continue;
9462
2
                        xmlNsErr(ctxt, XML_NS_ERR_ATTRIBUTE_REDEFINED,
9463
2
                                 "Namespaced Attribute %s in '%s' redefined\n",
9464
2
                                 attname, nsuri, NULL);
9465
2
                    }
9466
3
                }
9467
9468
12
                xmlParserEntityCheck(ctxt, attr->expandedSize);
9469
9470
12
                if ((atts == NULL) || (nbatts + 5 > maxatts)) {
9471
2
                    res = xmlCtxtGrowAttrs(ctxt);
9472
9473
2
                    maxatts = ctxt->maxatts;
9474
2
                    atts = ctxt->atts;
9475
9476
2
                    if (res < 0) {
9477
0
                        localname = NULL;
9478
0
                        goto done;
9479
0
                    }
9480
2
                }
9481
9482
12
                atts[nbatts++] = attname;
9483
12
                atts[nbatts++] = aprefix;
9484
12
                atts[nbatts++] = XML_INT_TO_PTR(nsIndex);
9485
12
                atts[nbatts++] = attr->value.name;
9486
12
                atts[nbatts++] = attr->valueEnd;
9487
12
                if ((ctxt->standalone == 1) && (attr->external != 0)) {
9488
0
                    xmlValidityError(ctxt, XML_DTD_STANDALONE_DEFAULTED,
9489
0
                            "standalone: attribute %s on %s defaulted "
9490
0
                            "from external subset\n",
9491
0
                            attname, localname);
9492
0
                }
9493
12
                nbdef++;
9494
12
      }
9495
12
  }
9496
25
    }
9497
9498
    /*
9499
     * Using a single hash table for nsUri/localName pairs cannot
9500
     * detect duplicate QNames reliably. The following example will
9501
     * only result in two namespace errors.
9502
     *
9503
     * <doc xmlns:a="a" xmlns:b="a">
9504
     *   <elem a:a="" b:a="" b:a=""/>
9505
     * </doc>
9506
     *
9507
     * If we saw more than one namespace error but no duplicate QNames
9508
     * were found, we have to scan for duplicate QNames.
9509
     */
9510
4.08M
    if ((numDupErr == 0) && (numNsErr > 1)) {
9511
1.64k
        memset(ctxt->attrHash, -1,
9512
1.64k
               attrHashSize * sizeof(ctxt->attrHash[0]));
9513
9514
8.71k
        for (i = 0, j = 0; j < nratts; i += 5, j++) {
9515
7.06k
            unsigned hashValue, nameHashValue, prefixHashValue;
9516
7.06k
            int res;
9517
9518
7.06k
            aprefix = atts[i+1];
9519
7.06k
            if (aprefix == NULL)
9520
458
                continue;
9521
9522
6.61k
            attname = atts[i];
9523
            /* Hash values always have bit 31 set, see dict.c */
9524
6.61k
            nameHashValue = ctxt->attallocs[j] | 0x80000000;
9525
6.61k
            prefixHashValue = xmlDictComputeHash(ctxt->dict, aprefix);
9526
9527
6.61k
            hashValue = xmlDictCombineHash(nameHashValue, prefixHashValue);
9528
6.61k
            res = xmlAttrHashInsertQName(ctxt, attrHashSize, attname,
9529
6.61k
                                         aprefix, hashValue, i);
9530
6.61k
            if (res < INT_MAX)
9531
1.64k
                xmlErrAttributeDup(ctxt, aprefix, attname);
9532
6.61k
        }
9533
1.64k
    }
9534
9535
    /*
9536
     * Reconstruct attribute pointers
9537
     */
9538
4.11M
    for (i = 0, j = 0; i < nbatts; i += 5, j++) {
9539
        /* namespace URI */
9540
33.9k
        nsIndex = XML_PTR_TO_INT(atts[i+2]);
9541
33.9k
        if (nsIndex == INT_MAX)
9542
17.2k
            atts[i+2] = NULL;
9543
16.6k
        else if (nsIndex == INT_MAX - 1)
9544
10.1k
            atts[i+2] = ctxt->str_xml_ns;
9545
6.55k
        else
9546
6.55k
            atts[i+2] = ctxt->nsTab[nsIndex * 2 + 1];
9547
9548
33.9k
        if ((j < nratts) && (ctxt->attallocs[j] & 0x80000000) == 0) {
9549
23.1k
            atts[i+3] = BASE_PTR + XML_PTR_TO_INT(atts[i+3]);  /* value */
9550
23.1k
            atts[i+4] = BASE_PTR + XML_PTR_TO_INT(atts[i+4]);  /* valuend */
9551
23.1k
        }
9552
33.9k
    }
9553
9554
4.08M
    uri = xmlParserNsLookupUri(ctxt, &hprefix);
9555
4.08M
    if ((prefix != NULL) && (uri == NULL)) {
9556
20.2k
  xmlNsErr(ctxt, XML_NS_ERR_UNDEFINED_NAMESPACE,
9557
20.2k
           "Namespace prefix %s on %s is not defined\n",
9558
20.2k
     prefix, localname, NULL);
9559
20.2k
    }
9560
4.08M
    *pref = prefix;
9561
4.08M
    *URI = uri;
9562
9563
    /*
9564
     * SAX callback
9565
     */
9566
4.08M
    if ((ctxt->sax != NULL) && (ctxt->sax->startElementNs != NULL) &&
9567
4.08M
  (!ctxt->disableSAX)) {
9568
4.08M
  if (nbNs > 0)
9569
13.6k
      ctxt->sax->startElementNs(ctxt->userData, localname, prefix, uri,
9570
13.6k
                          nbNs, ctxt->nsTab + 2 * (ctxt->nsNr - nbNs),
9571
13.6k
        nbatts / 5, nbdef, atts);
9572
4.07M
  else
9573
4.07M
      ctxt->sax->startElementNs(ctxt->userData, localname, prefix, uri,
9574
4.07M
                          0, NULL, nbatts / 5, nbdef, atts);
9575
4.08M
    }
9576
9577
4.08M
done:
9578
    /*
9579
     * Free allocated attribute values
9580
     */
9581
4.08M
    if (attval != 0) {
9582
22.5k
  for (i = 0, j = 0; j < nratts; i += 5, j++)
9583
16.2k
      if (ctxt->attallocs[j] & 0x80000000)
9584
10.7k
          xmlFree((xmlChar *) atts[i+3]);
9585
6.31k
    }
9586
9587
4.08M
    *nbNsPtr = nbNs;
9588
4.08M
    return(localname);
9589
4.08M
}
9590
9591
/**
9592
 * xmlParseEndTag2:
9593
 * @ctxt:  an XML parser context
9594
 * @line:  line of the start tag
9595
 * @nsNr:  number of namespaces on the start tag
9596
 *
9597
 * Parse an end tag. Always consumes '</'.
9598
 *
9599
 * [42] ETag ::= '</' Name S? '>'
9600
 *
9601
 * With namespace
9602
 *
9603
 * [NS 9] ETag ::= '</' QName S? '>'
9604
 */
9605
9606
static void
9607
48.1k
xmlParseEndTag2(xmlParserCtxtPtr ctxt, const xmlStartTag *tag) {
9608
48.1k
    const xmlChar *name;
9609
9610
48.1k
    GROW;
9611
48.1k
    if ((RAW != '<') || (NXT(1) != '/')) {
9612
232
  xmlFatalErr(ctxt, XML_ERR_LTSLASH_REQUIRED, NULL);
9613
232
  return;
9614
232
    }
9615
47.8k
    SKIP(2);
9616
9617
47.8k
    if (tag->prefix == NULL)
9618
43.5k
        name = xmlParseNameAndCompare(ctxt, ctxt->name);
9619
4.35k
    else
9620
4.35k
        name = xmlParseQNameAndCompare(ctxt, ctxt->name, tag->prefix);
9621
9622
    /*
9623
     * We should definitely be at the ending "S? '>'" part
9624
     */
9625
47.8k
    GROW;
9626
47.8k
    SKIP_BLANKS;
9627
47.8k
    if ((!IS_BYTE_CHAR(RAW)) || (RAW != '>')) {
9628
32.1k
  xmlFatalErr(ctxt, XML_ERR_GT_REQUIRED, NULL);
9629
32.1k
    } else
9630
15.7k
  NEXT1;
9631
9632
    /*
9633
     * [ WFC: Element Type Match ]
9634
     * The Name in an element's end-tag must match the element type in the
9635
     * start-tag.
9636
     *
9637
     */
9638
47.8k
    if (name != (xmlChar*)1) {
9639
37.6k
        if (name == NULL) name = BAD_CAST "unparsable";
9640
37.6k
        xmlFatalErrMsgStrIntStr(ctxt, XML_ERR_TAG_NAME_MISMATCH,
9641
37.6k
         "Opening and ending tag mismatch: %s line %d and %s\n",
9642
37.6k
                    ctxt->name, tag->line, name);
9643
37.6k
    }
9644
9645
    /*
9646
     * SAX: End of Tag
9647
     */
9648
47.8k
    if ((ctxt->sax != NULL) && (ctxt->sax->endElementNs != NULL) &&
9649
47.8k
  (!ctxt->disableSAX))
9650
47.8k
  ctxt->sax->endElementNs(ctxt->userData, ctxt->name, tag->prefix,
9651
47.8k
                                tag->URI);
9652
9653
47.8k
    spacePop(ctxt);
9654
47.8k
    if (tag->nsNr != 0)
9655
2.90k
  xmlParserNsPop(ctxt, tag->nsNr);
9656
47.8k
}
9657
9658
/**
9659
 * xmlParseCDSect:
9660
 * @ctxt:  an XML parser context
9661
 *
9662
 * DEPRECATED: Internal function, don't use.
9663
 *
9664
 * Parse escaped pure raw content. Always consumes '<!['.
9665
 *
9666
 * [18] CDSect ::= CDStart CData CDEnd
9667
 *
9668
 * [19] CDStart ::= '<![CDATA['
9669
 *
9670
 * [20] Data ::= (Char* - (Char* ']]>' Char*))
9671
 *
9672
 * [21] CDEnd ::= ']]>'
9673
 */
9674
void
9675
7.96k
xmlParseCDSect(xmlParserCtxtPtr ctxt) {
9676
7.96k
    xmlChar *buf = NULL;
9677
7.96k
    int len = 0;
9678
7.96k
    int size = XML_PARSER_BUFFER_SIZE;
9679
7.96k
    int r, rl;
9680
7.96k
    int s, sl;
9681
7.96k
    int cur, l;
9682
7.96k
    int maxLength = (ctxt->options & XML_PARSE_HUGE) ?
9683
0
                    XML_MAX_HUGE_LENGTH :
9684
7.96k
                    XML_MAX_TEXT_LENGTH;
9685
9686
7.96k
    if ((CUR != '<') || (NXT(1) != '!') || (NXT(2) != '['))
9687
0
        return;
9688
7.96k
    SKIP(3);
9689
9690
7.96k
    if (!CMP6(CUR_PTR, 'C', 'D', 'A', 'T', 'A', '['))
9691
0
        return;
9692
7.96k
    SKIP(6);
9693
9694
7.96k
    r = xmlCurrentCharRecover(ctxt, &rl);
9695
7.96k
    if (!IS_CHAR(r)) {
9696
71
  xmlFatalErr(ctxt, XML_ERR_CDATA_NOT_FINISHED, NULL);
9697
71
        goto out;
9698
71
    }
9699
7.89k
    NEXTL(rl);
9700
7.89k
    s = xmlCurrentCharRecover(ctxt, &sl);
9701
7.89k
    if (!IS_CHAR(s)) {
9702
18
  xmlFatalErr(ctxt, XML_ERR_CDATA_NOT_FINISHED, NULL);
9703
18
        goto out;
9704
18
    }
9705
7.87k
    NEXTL(sl);
9706
7.87k
    cur = xmlCurrentCharRecover(ctxt, &l);
9707
7.87k
    buf = xmlMalloc(size);
9708
7.87k
    if (buf == NULL) {
9709
0
  xmlErrMemory(ctxt);
9710
0
        goto out;
9711
0
    }
9712
202k
    while (IS_CHAR(cur) &&
9713
202k
           ((r != ']') || (s != ']') || (cur != '>'))) {
9714
194k
  if (len + 5 >= size) {
9715
789
      xmlChar *tmp;
9716
789
            int newSize;
9717
9718
789
            newSize = xmlGrowCapacity(size, 1, 1, maxLength);
9719
789
            if (newSize < 0) {
9720
0
                xmlFatalErrMsg(ctxt, XML_ERR_CDATA_NOT_FINISHED,
9721
0
                               "CData section too big found\n");
9722
0
                goto out;
9723
0
            }
9724
789
      tmp = xmlRealloc(buf, newSize);
9725
789
      if (tmp == NULL) {
9726
0
    xmlErrMemory(ctxt);
9727
0
                goto out;
9728
0
      }
9729
789
      buf = tmp;
9730
789
      size = newSize;
9731
789
  }
9732
194k
  COPY_BUF(buf, len, r);
9733
194k
  r = s;
9734
194k
  rl = sl;
9735
194k
  s = cur;
9736
194k
  sl = l;
9737
194k
  NEXTL(l);
9738
194k
  cur = xmlCurrentCharRecover(ctxt, &l);
9739
194k
    }
9740
7.87k
    buf[len] = 0;
9741
7.87k
    if (cur != '>') {
9742
187
  xmlFatalErrMsgStr(ctxt, XML_ERR_CDATA_NOT_FINISHED,
9743
187
                       "CData section not finished\n%.50s\n", buf);
9744
187
        goto out;
9745
187
    }
9746
7.68k
    NEXTL(l);
9747
9748
    /*
9749
     * OK the buffer is to be consumed as cdata.
9750
     */
9751
7.68k
    if ((ctxt->sax != NULL) && (!ctxt->disableSAX)) {
9752
7.68k
        if ((ctxt->sax->cdataBlock != NULL) &&
9753
7.68k
            ((ctxt->options & XML_PARSE_NOCDATA) == 0)) {
9754
7.68k
            ctxt->sax->cdataBlock(ctxt->userData, buf, len);
9755
7.68k
        } else if (ctxt->sax->characters != NULL) {
9756
0
            ctxt->sax->characters(ctxt->userData, buf, len);
9757
0
        }
9758
7.68k
    }
9759
9760
7.96k
out:
9761
7.96k
    xmlFree(buf);
9762
7.96k
}
9763
9764
/**
9765
 * xmlParseContentInternal:
9766
 * @ctxt:  an XML parser context
9767
 *
9768
 * Parse a content sequence. Stops at EOF or '</'. Leaves checking of
9769
 * unexpected EOF to the caller.
9770
 */
9771
9772
static void
9773
702
xmlParseContentInternal(xmlParserCtxtPtr ctxt) {
9774
702
    int oldNameNr = ctxt->nameNr;
9775
702
    int oldSpaceNr = ctxt->spaceNr;
9776
702
    int oldNodeNr = ctxt->nodeNr;
9777
9778
702
    GROW;
9779
6.53M
    while ((ctxt->input->cur < ctxt->input->end) &&
9780
6.53M
     (PARSER_STOPPED(ctxt) == 0)) {
9781
6.53M
  const xmlChar *cur = ctxt->input->cur;
9782
9783
  /*
9784
   * First case : a Processing Instruction.
9785
   */
9786
6.53M
  if ((*cur == '<') && (cur[1] == '?')) {
9787
6.47k
      xmlParsePI(ctxt);
9788
6.47k
  }
9789
9790
  /*
9791
   * Second case : a CDSection
9792
   */
9793
  /* 2.6.0 test was *cur not RAW */
9794
6.53M
  else if (CMP9(CUR_PTR, '<', '!', '[', 'C', 'D', 'A', 'T', 'A', '[')) {
9795
7.96k
      xmlParseCDSect(ctxt);
9796
7.96k
  }
9797
9798
  /*
9799
   * Third case :  a comment
9800
   */
9801
6.52M
  else if ((*cur == '<') && (NXT(1) == '!') &&
9802
6.52M
     (NXT(2) == '-') && (NXT(3) == '-')) {
9803
5.14k
      xmlParseComment(ctxt);
9804
5.14k
  }
9805
9806
  /*
9807
   * Fourth case :  a sub-element.
9808
   */
9809
6.51M
  else if (*cur == '<') {
9810
4.34M
            if (NXT(1) == '/') {
9811
47.8k
                if (ctxt->nameNr <= oldNameNr)
9812
3
                    break;
9813
47.8k
          xmlParseElementEnd(ctxt);
9814
4.29M
            } else {
9815
4.29M
          xmlParseElementStart(ctxt);
9816
4.29M
            }
9817
4.34M
  }
9818
9819
  /*
9820
   * Fifth case : a reference. If if has not been resolved,
9821
   *    parsing returns it's Name, create the node
9822
   */
9823
9824
2.17M
  else if (*cur == '&') {
9825
36.0k
      xmlParseReference(ctxt);
9826
36.0k
  }
9827
9828
  /*
9829
   * Last case, text. Note that References are handled directly.
9830
   */
9831
2.13M
  else {
9832
2.13M
      xmlParseCharDataInternal(ctxt, 0);
9833
2.13M
  }
9834
9835
6.53M
  SHRINK;
9836
6.53M
  GROW;
9837
6.53M
    }
9838
9839
702
    if ((ctxt->nameNr > oldNameNr) &&
9840
702
        (ctxt->input->cur >= ctxt->input->end) &&
9841
702
        (ctxt->wellFormed)) {
9842
0
        const xmlChar *name = ctxt->nameTab[ctxt->nameNr - 1];
9843
0
        int line = ctxt->pushTab[ctxt->nameNr - 1].line;
9844
0
        xmlFatalErrMsgStrIntStr(ctxt, XML_ERR_TAG_NOT_FINISHED,
9845
0
                "Premature end of data in tag %s line %d\n",
9846
0
                name, line, NULL);
9847
0
    }
9848
9849
    /*
9850
     * Clean up in error case
9851
     */
9852
9853
34.5k
    while (ctxt->nodeNr > oldNodeNr)
9854
33.8k
        nodePop(ctxt);
9855
9856
34.7k
    while (ctxt->nameNr > oldNameNr) {
9857
34.0k
        xmlStartTag *tag = &ctxt->pushTab[ctxt->nameNr - 1];
9858
9859
34.0k
        if (tag->nsNr != 0)
9860
3.36k
            xmlParserNsPop(ctxt, tag->nsNr);
9861
9862
34.0k
        namePop(ctxt);
9863
34.0k
    }
9864
9865
34.7k
    while (ctxt->spaceNr > oldSpaceNr)
9866
34.0k
        spacePop(ctxt);
9867
702
}
9868
9869
/**
9870
 * xmlParseContent:
9871
 * @ctxt:  an XML parser context
9872
 *
9873
 * Parse XML element content. This is useful if you're only interested
9874
 * in custom SAX callbacks. If you want a node list, use
9875
 * xmlCtxtParseContent.
9876
 */
9877
void
9878
0
xmlParseContent(xmlParserCtxtPtr ctxt) {
9879
0
    if ((ctxt == NULL) || (ctxt->input == NULL))
9880
0
        return;
9881
9882
0
    xmlCtxtInitializeLate(ctxt);
9883
9884
0
    xmlParseContentInternal(ctxt);
9885
9886
0
    xmlParserCheckEOF(ctxt, XML_ERR_NOT_WELL_BALANCED);
9887
0
}
9888
9889
/**
9890
 * xmlParseElement:
9891
 * @ctxt:  an XML parser context
9892
 *
9893
 * DEPRECATED: Internal function, don't use.
9894
 *
9895
 * parse an XML element
9896
 *
9897
 * [39] element ::= EmptyElemTag | STag content ETag
9898
 *
9899
 * [ WFC: Element Type Match ]
9900
 * The Name in an element's end-tag must match the element type in the
9901
 * start-tag.
9902
 *
9903
 */
9904
9905
void
9906
723
xmlParseElement(xmlParserCtxtPtr ctxt) {
9907
723
    if (xmlParseElementStart(ctxt) != 0)
9908
68
        return;
9909
9910
655
    xmlParseContentInternal(ctxt);
9911
9912
655
    if (ctxt->input->cur >= ctxt->input->end) {
9913
420
        if (ctxt->wellFormed) {
9914
0
            const xmlChar *name = ctxt->nameTab[ctxt->nameNr - 1];
9915
0
            int line = ctxt->pushTab[ctxt->nameNr - 1].line;
9916
0
            xmlFatalErrMsgStrIntStr(ctxt, XML_ERR_TAG_NOT_FINISHED,
9917
0
                    "Premature end of data in tag %s line %d\n",
9918
0
                    name, line, NULL);
9919
0
        }
9920
420
        return;
9921
420
    }
9922
9923
235
    xmlParseElementEnd(ctxt);
9924
235
}
9925
9926
/**
9927
 * xmlParseElementStart:
9928
 * @ctxt:  an XML parser context
9929
 *
9930
 * Parse the start of an XML element. Returns -1 in case of error, 0 if an
9931
 * opening tag was parsed, 1 if an empty element was parsed.
9932
 *
9933
 * Always consumes '<'.
9934
 */
9935
static int
9936
4.29M
xmlParseElementStart(xmlParserCtxtPtr ctxt) {
9937
4.29M
    int maxDepth = (ctxt->options & XML_PARSE_HUGE) ? 2048 : 256;
9938
4.29M
    const xmlChar *name;
9939
4.29M
    const xmlChar *prefix = NULL;
9940
4.29M
    const xmlChar *URI = NULL;
9941
4.29M
    xmlParserNodeInfo node_info;
9942
4.29M
    int line;
9943
4.29M
    xmlNodePtr cur;
9944
4.29M
    int nbNs = 0;
9945
9946
4.29M
    if (ctxt->nameNr > maxDepth) {
9947
0
        xmlFatalErrMsgInt(ctxt, XML_ERR_RESOURCE_LIMIT,
9948
0
                "Excessive depth in document: %d use XML_PARSE_HUGE option\n",
9949
0
                ctxt->nameNr);
9950
0
  xmlHaltParser(ctxt);
9951
0
  return(-1);
9952
0
    }
9953
9954
    /* Capture start position */
9955
4.29M
    if (ctxt->record_info) {
9956
0
        node_info.begin_pos = ctxt->input->consumed +
9957
0
                          (CUR_PTR - ctxt->input->base);
9958
0
  node_info.begin_line = ctxt->input->line;
9959
0
    }
9960
9961
4.29M
    if (ctxt->spaceNr == 0)
9962
0
  spacePush(ctxt, -1);
9963
4.29M
    else if (*ctxt->space == -2)
9964
0
  spacePush(ctxt, -1);
9965
4.29M
    else
9966
4.29M
  spacePush(ctxt, *ctxt->space);
9967
9968
4.29M
    line = ctxt->input->line;
9969
#ifdef LIBXML_SAX1_ENABLED
9970
    if (ctxt->sax2)
9971
#endif /* LIBXML_SAX1_ENABLED */
9972
4.29M
        name = xmlParseStartTag2(ctxt, &prefix, &URI, &nbNs);
9973
#ifdef LIBXML_SAX1_ENABLED
9974
    else
9975
  name = xmlParseStartTag(ctxt);
9976
#endif /* LIBXML_SAX1_ENABLED */
9977
4.29M
    if (name == NULL) {
9978
212k
  spacePop(ctxt);
9979
212k
        return(-1);
9980
212k
    }
9981
4.08M
    nameNsPush(ctxt, name, prefix, URI, line, nbNs);
9982
4.08M
    cur = ctxt->node;
9983
9984
#ifdef LIBXML_VALID_ENABLED
9985
    /*
9986
     * [ VC: Root Element Type ]
9987
     * The Name in the document type declaration must match the element
9988
     * type of the root element.
9989
     */
9990
    if (ctxt->validate && ctxt->wellFormed && ctxt->myDoc &&
9991
        ctxt->node && (ctxt->node == ctxt->myDoc->children))
9992
        ctxt->valid &= xmlValidateRoot(&ctxt->vctxt, ctxt->myDoc);
9993
#endif /* LIBXML_VALID_ENABLED */
9994
9995
    /*
9996
     * Check for an Empty Element.
9997
     */
9998
4.08M
    if ((RAW == '/') && (NXT(1) == '>')) {
9999
1.87k
        SKIP(2);
10000
1.87k
  if (ctxt->sax2) {
10001
1.87k
      if ((ctxt->sax != NULL) && (ctxt->sax->endElementNs != NULL) &&
10002
1.87k
    (!ctxt->disableSAX))
10003
1.87k
    ctxt->sax->endElementNs(ctxt->userData, name, prefix, URI);
10004
#ifdef LIBXML_SAX1_ENABLED
10005
  } else {
10006
      if ((ctxt->sax != NULL) && (ctxt->sax->endElement != NULL) &&
10007
    (!ctxt->disableSAX))
10008
    ctxt->sax->endElement(ctxt->userData, name);
10009
#endif /* LIBXML_SAX1_ENABLED */
10010
1.87k
  }
10011
1.87k
  namePop(ctxt);
10012
1.87k
  spacePop(ctxt);
10013
1.87k
  if (nbNs > 0)
10014
424
      xmlParserNsPop(ctxt, nbNs);
10015
1.87k
  if (cur != NULL && ctxt->record_info) {
10016
0
            node_info.node = cur;
10017
0
            node_info.end_pos = ctxt->input->consumed +
10018
0
                                (CUR_PTR - ctxt->input->base);
10019
0
            node_info.end_line = ctxt->input->line;
10020
0
            xmlParserAddNodeInfo(ctxt, &node_info);
10021
0
  }
10022
1.87k
  return(1);
10023
1.87k
    }
10024
4.08M
    if (RAW == '>') {
10025
82.5k
        NEXT1;
10026
82.5k
        if (cur != NULL && ctxt->record_info) {
10027
0
            node_info.node = cur;
10028
0
            node_info.end_pos = 0;
10029
0
            node_info.end_line = 0;
10030
0
            xmlParserAddNodeInfo(ctxt, &node_info);
10031
0
        }
10032
4.00M
    } else {
10033
4.00M
        xmlFatalErrMsgStrIntStr(ctxt, XML_ERR_GT_REQUIRED,
10034
4.00M
         "Couldn't find end of Start Tag %s line %d\n",
10035
4.00M
                    name, line, NULL);
10036
10037
  /*
10038
   * end of parsing of this node.
10039
   */
10040
4.00M
  nodePop(ctxt);
10041
4.00M
  namePop(ctxt);
10042
4.00M
  spacePop(ctxt);
10043
4.00M
  if (nbNs > 0)
10044
6.91k
      xmlParserNsPop(ctxt, nbNs);
10045
4.00M
  return(-1);
10046
4.00M
    }
10047
10048
82.5k
    return(0);
10049
4.08M
}
10050
10051
/**
10052
 * xmlParseElementEnd:
10053
 * @ctxt:  an XML parser context
10054
 *
10055
 * Parse the end of an XML element. Always consumes '</'.
10056
 */
10057
static void
10058
48.1k
xmlParseElementEnd(xmlParserCtxtPtr ctxt) {
10059
48.1k
    xmlNodePtr cur = ctxt->node;
10060
10061
48.1k
    if (ctxt->nameNr <= 0) {
10062
0
        if ((RAW == '<') && (NXT(1) == '/'))
10063
0
            SKIP(2);
10064
0
        return;
10065
0
    }
10066
10067
    /*
10068
     * parse the end of tag: '</' should be here.
10069
     */
10070
48.1k
    if (ctxt->sax2) {
10071
48.1k
  xmlParseEndTag2(ctxt, &ctxt->pushTab[ctxt->nameNr - 1]);
10072
48.1k
  namePop(ctxt);
10073
48.1k
    }
10074
#ifdef LIBXML_SAX1_ENABLED
10075
    else
10076
  xmlParseEndTag1(ctxt, 0);
10077
#endif /* LIBXML_SAX1_ENABLED */
10078
10079
    /*
10080
     * Capture end position
10081
     */
10082
48.1k
    if (cur != NULL && ctxt->record_info) {
10083
0
        xmlParserNodeInfoPtr node_info;
10084
10085
0
        node_info = (xmlParserNodeInfoPtr) xmlParserFindNodeInfo(ctxt, cur);
10086
0
        if (node_info != NULL) {
10087
0
            node_info->end_pos = ctxt->input->consumed +
10088
0
                                 (CUR_PTR - ctxt->input->base);
10089
0
            node_info->end_line = ctxt->input->line;
10090
0
        }
10091
0
    }
10092
48.1k
}
10093
10094
/**
10095
 * xmlParseVersionNum:
10096
 * @ctxt:  an XML parser context
10097
 *
10098
 * DEPRECATED: Internal function, don't use.
10099
 *
10100
 * parse the XML version value.
10101
 *
10102
 * [26] VersionNum ::= '1.' [0-9]+
10103
 *
10104
 * In practice allow [0-9].[0-9]+ at that level
10105
 *
10106
 * Returns the string giving the XML version number, or NULL
10107
 */
10108
xmlChar *
10109
289
xmlParseVersionNum(xmlParserCtxtPtr ctxt) {
10110
289
    xmlChar *buf = NULL;
10111
289
    int len = 0;
10112
289
    int size = 10;
10113
289
    int maxLength = (ctxt->options & XML_PARSE_HUGE) ?
10114
0
                    XML_MAX_TEXT_LENGTH :
10115
289
                    XML_MAX_NAME_LENGTH;
10116
289
    xmlChar cur;
10117
10118
289
    buf = xmlMalloc(size);
10119
289
    if (buf == NULL) {
10120
0
  xmlErrMemory(ctxt);
10121
0
  return(NULL);
10122
0
    }
10123
289
    cur = CUR;
10124
289
    if (!((cur >= '0') && (cur <= '9'))) {
10125
1
  xmlFree(buf);
10126
1
  return(NULL);
10127
1
    }
10128
288
    buf[len++] = cur;
10129
288
    NEXT;
10130
288
    cur=CUR;
10131
288
    if (cur != '.') {
10132
5
  xmlFree(buf);
10133
5
  return(NULL);
10134
5
    }
10135
283
    buf[len++] = cur;
10136
283
    NEXT;
10137
283
    cur=CUR;
10138
50.5k
    while ((cur >= '0') && (cur <= '9')) {
10139
50.2k
  if (len + 1 >= size) {
10140
22
      xmlChar *tmp;
10141
22
            int newSize;
10142
10143
22
            newSize = xmlGrowCapacity(size, 1, 1, maxLength);
10144
22
            if (newSize < 0) {
10145
1
                xmlFatalErr(ctxt, XML_ERR_NAME_TOO_LONG, "VersionNum");
10146
1
                xmlFree(buf);
10147
1
                return(NULL);
10148
1
            }
10149
21
      tmp = xmlRealloc(buf, newSize);
10150
21
      if (tmp == NULL) {
10151
0
    xmlErrMemory(ctxt);
10152
0
          xmlFree(buf);
10153
0
    return(NULL);
10154
0
      }
10155
21
      buf = tmp;
10156
21
            size = newSize;
10157
21
  }
10158
50.2k
  buf[len++] = cur;
10159
50.2k
  NEXT;
10160
50.2k
  cur=CUR;
10161
50.2k
    }
10162
282
    buf[len] = 0;
10163
282
    return(buf);
10164
283
}
10165
10166
/**
10167
 * xmlParseVersionInfo:
10168
 * @ctxt:  an XML parser context
10169
 *
10170
 * DEPRECATED: Internal function, don't use.
10171
 *
10172
 * parse the XML version.
10173
 *
10174
 * [24] VersionInfo ::= S 'version' Eq (' VersionNum ' | " VersionNum ")
10175
 *
10176
 * [25] Eq ::= S? '=' S?
10177
 *
10178
 * Returns the version string, e.g. "1.0"
10179
 */
10180
10181
xmlChar *
10182
333
xmlParseVersionInfo(xmlParserCtxtPtr ctxt) {
10183
333
    xmlChar *version = NULL;
10184
10185
333
    if (CMP7(CUR_PTR, 'v', 'e', 'r', 's', 'i', 'o', 'n')) {
10186
289
  SKIP(7);
10187
289
  SKIP_BLANKS;
10188
289
  if (RAW != '=') {
10189
0
      xmlFatalErr(ctxt, XML_ERR_EQUAL_REQUIRED, NULL);
10190
0
      return(NULL);
10191
0
        }
10192
289
  NEXT;
10193
289
  SKIP_BLANKS;
10194
289
  if (RAW == '"') {
10195
288
      NEXT;
10196
288
      version = xmlParseVersionNum(ctxt);
10197
288
      if (RAW != '"') {
10198
6
    xmlFatalErr(ctxt, XML_ERR_STRING_NOT_CLOSED, NULL);
10199
6
      } else
10200
282
          NEXT;
10201
288
  } else if (RAW == '\''){
10202
1
      NEXT;
10203
1
      version = xmlParseVersionNum(ctxt);
10204
1
      if (RAW != '\'') {
10205
1
    xmlFatalErr(ctxt, XML_ERR_STRING_NOT_CLOSED, NULL);
10206
1
      } else
10207
0
          NEXT;
10208
1
  } else {
10209
0
      xmlFatalErr(ctxt, XML_ERR_STRING_NOT_STARTED, NULL);
10210
0
  }
10211
289
    }
10212
333
    return(version);
10213
333
}
10214
10215
/**
10216
 * xmlParseEncName:
10217
 * @ctxt:  an XML parser context
10218
 *
10219
 * DEPRECATED: Internal function, don't use.
10220
 *
10221
 * parse the XML encoding name
10222
 *
10223
 * [81] EncName ::= [A-Za-z] ([A-Za-z0-9._] | '-')*
10224
 *
10225
 * Returns the encoding name value or NULL
10226
 */
10227
xmlChar *
10228
321
xmlParseEncName(xmlParserCtxtPtr ctxt) {
10229
321
    xmlChar *buf = NULL;
10230
321
    int len = 0;
10231
321
    int size = 10;
10232
321
    int maxLength = (ctxt->options & XML_PARSE_HUGE) ?
10233
0
                    XML_MAX_TEXT_LENGTH :
10234
321
                    XML_MAX_NAME_LENGTH;
10235
321
    xmlChar cur;
10236
10237
321
    cur = CUR;
10238
321
    if (((cur >= 'a') && (cur <= 'z')) ||
10239
321
        ((cur >= 'A') && (cur <= 'Z'))) {
10240
321
  buf = xmlMalloc(size);
10241
321
  if (buf == NULL) {
10242
0
      xmlErrMemory(ctxt);
10243
0
      return(NULL);
10244
0
  }
10245
10246
321
  buf[len++] = cur;
10247
321
  NEXT;
10248
321
  cur = CUR;
10249
3.15k
  while (((cur >= 'a') && (cur <= 'z')) ||
10250
3.15k
         ((cur >= 'A') && (cur <= 'Z')) ||
10251
3.15k
         ((cur >= '0') && (cur <= '9')) ||
10252
3.15k
         (cur == '.') || (cur == '_') ||
10253
3.15k
         (cur == '-')) {
10254
2.83k
      if (len + 1 >= size) {
10255
310
          xmlChar *tmp;
10256
310
                int newSize;
10257
10258
310
                newSize = xmlGrowCapacity(size, 1, 1, maxLength);
10259
310
                if (newSize < 0) {
10260
0
                    xmlFatalErr(ctxt, XML_ERR_NAME_TOO_LONG, "EncName");
10261
0
                    xmlFree(buf);
10262
0
                    return(NULL);
10263
0
                }
10264
310
    tmp = xmlRealloc(buf, newSize);
10265
310
    if (tmp == NULL) {
10266
0
        xmlErrMemory(ctxt);
10267
0
        xmlFree(buf);
10268
0
        return(NULL);
10269
0
    }
10270
310
    buf = tmp;
10271
310
                size = newSize;
10272
310
      }
10273
2.83k
      buf[len++] = cur;
10274
2.83k
      NEXT;
10275
2.83k
      cur = CUR;
10276
2.83k
        }
10277
321
  buf[len] = 0;
10278
321
    } else {
10279
0
  xmlFatalErr(ctxt, XML_ERR_ENCODING_NAME, NULL);
10280
0
    }
10281
321
    return(buf);
10282
321
}
10283
10284
/**
10285
 * xmlParseEncodingDecl:
10286
 * @ctxt:  an XML parser context
10287
 *
10288
 * DEPRECATED: Internal function, don't use.
10289
 *
10290
 * parse the XML encoding declaration
10291
 *
10292
 * [80] EncodingDecl ::= S 'encoding' Eq ('"' EncName '"' |  "'" EncName "'")
10293
 *
10294
 * this setups the conversion filters.
10295
 *
10296
 * Returns the encoding value or NULL
10297
 */
10298
10299
const xmlChar *
10300
333
xmlParseEncodingDecl(xmlParserCtxtPtr ctxt) {
10301
333
    xmlChar *encoding = NULL;
10302
10303
333
    SKIP_BLANKS;
10304
333
    if (CMP8(CUR_PTR, 'e', 'n', 'c', 'o', 'd', 'i', 'n', 'g') == 0)
10305
12
        return(NULL);
10306
10307
321
    SKIP(8);
10308
321
    SKIP_BLANKS;
10309
321
    if (RAW != '=') {
10310
0
        xmlFatalErr(ctxt, XML_ERR_EQUAL_REQUIRED, NULL);
10311
0
        return(NULL);
10312
0
    }
10313
321
    NEXT;
10314
321
    SKIP_BLANKS;
10315
321
    if (RAW == '"') {
10316
282
        NEXT;
10317
282
        encoding = xmlParseEncName(ctxt);
10318
282
        if (RAW != '"') {
10319
0
            xmlFatalErr(ctxt, XML_ERR_STRING_NOT_CLOSED, NULL);
10320
0
            xmlFree((xmlChar *) encoding);
10321
0
            return(NULL);
10322
0
        } else
10323
282
            NEXT;
10324
282
    } else if (RAW == '\''){
10325
39
        NEXT;
10326
39
        encoding = xmlParseEncName(ctxt);
10327
39
        if (RAW != '\'') {
10328
0
            xmlFatalErr(ctxt, XML_ERR_STRING_NOT_CLOSED, NULL);
10329
0
            xmlFree((xmlChar *) encoding);
10330
0
            return(NULL);
10331
0
        } else
10332
39
            NEXT;
10333
39
    } else {
10334
0
        xmlFatalErr(ctxt, XML_ERR_STRING_NOT_STARTED, NULL);
10335
0
    }
10336
10337
321
    if (encoding == NULL)
10338
0
        return(NULL);
10339
10340
321
    xmlSetDeclaredEncoding(ctxt, encoding);
10341
10342
321
    return(ctxt->encoding);
10343
321
}
10344
10345
/**
10346
 * xmlParseSDDecl:
10347
 * @ctxt:  an XML parser context
10348
 *
10349
 * DEPRECATED: Internal function, don't use.
10350
 *
10351
 * parse the XML standalone declaration
10352
 *
10353
 * [32] SDDecl ::= S 'standalone' Eq
10354
 *                 (("'" ('yes' | 'no') "'") | ('"' ('yes' | 'no')'"'))
10355
 *
10356
 * [ VC: Standalone Document Declaration ]
10357
 * TODO The standalone document declaration must have the value "no"
10358
 * if any external markup declarations contain declarations of:
10359
 *  - attributes with default values, if elements to which these
10360
 *    attributes apply appear in the document without specifications
10361
 *    of values for these attributes, or
10362
 *  - entities (other than amp, lt, gt, apos, quot), if references
10363
 *    to those entities appear in the document, or
10364
 *  - attributes with values subject to normalization, where the
10365
 *    attribute appears in the document with a value which will change
10366
 *    as a result of normalization, or
10367
 *  - element types with element content, if white space occurs directly
10368
 *    within any instance of those types.
10369
 *
10370
 * Returns:
10371
 *   1 if standalone="yes"
10372
 *   0 if standalone="no"
10373
 *  -2 if standalone attribute is missing or invalid
10374
 *    (A standalone value of -2 means that the XML declaration was found,
10375
 *     but no value was specified for the standalone attribute).
10376
 */
10377
10378
int
10379
73
xmlParseSDDecl(xmlParserCtxtPtr ctxt) {
10380
73
    int standalone = -2;
10381
10382
73
    SKIP_BLANKS;
10383
73
    if (CMP10(CUR_PTR, 's', 't', 'a', 'n', 'd', 'a', 'l', 'o', 'n', 'e')) {
10384
0
  SKIP(10);
10385
0
        SKIP_BLANKS;
10386
0
  if (RAW != '=') {
10387
0
      xmlFatalErr(ctxt, XML_ERR_EQUAL_REQUIRED, NULL);
10388
0
      return(standalone);
10389
0
        }
10390
0
  NEXT;
10391
0
  SKIP_BLANKS;
10392
0
        if (RAW == '\''){
10393
0
      NEXT;
10394
0
      if ((RAW == 'n') && (NXT(1) == 'o')) {
10395
0
          standalone = 0;
10396
0
                SKIP(2);
10397
0
      } else if ((RAW == 'y') && (NXT(1) == 'e') &&
10398
0
                 (NXT(2) == 's')) {
10399
0
          standalone = 1;
10400
0
    SKIP(3);
10401
0
            } else {
10402
0
    xmlFatalErr(ctxt, XML_ERR_STANDALONE_VALUE, NULL);
10403
0
      }
10404
0
      if (RAW != '\'') {
10405
0
    xmlFatalErr(ctxt, XML_ERR_STRING_NOT_CLOSED, NULL);
10406
0
      } else
10407
0
          NEXT;
10408
0
  } else if (RAW == '"'){
10409
0
      NEXT;
10410
0
      if ((RAW == 'n') && (NXT(1) == 'o')) {
10411
0
          standalone = 0;
10412
0
    SKIP(2);
10413
0
      } else if ((RAW == 'y') && (NXT(1) == 'e') &&
10414
0
                 (NXT(2) == 's')) {
10415
0
          standalone = 1;
10416
0
                SKIP(3);
10417
0
            } else {
10418
0
    xmlFatalErr(ctxt, XML_ERR_STANDALONE_VALUE, NULL);
10419
0
      }
10420
0
      if (RAW != '"') {
10421
0
    xmlFatalErr(ctxt, XML_ERR_STRING_NOT_CLOSED, NULL);
10422
0
      } else
10423
0
          NEXT;
10424
0
  } else {
10425
0
      xmlFatalErr(ctxt, XML_ERR_STRING_NOT_STARTED, NULL);
10426
0
        }
10427
0
    }
10428
73
    return(standalone);
10429
73
}
10430
10431
/**
10432
 * xmlParseXMLDecl:
10433
 * @ctxt:  an XML parser context
10434
 *
10435
 * DEPRECATED: Internal function, don't use.
10436
 *
10437
 * parse an XML declaration header
10438
 *
10439
 * [23] XMLDecl ::= '<?xml' VersionInfo EncodingDecl? SDDecl? S? '?>'
10440
 */
10441
10442
void
10443
333
xmlParseXMLDecl(xmlParserCtxtPtr ctxt) {
10444
333
    xmlChar *version;
10445
10446
    /*
10447
     * This value for standalone indicates that the document has an
10448
     * XML declaration but it does not have a standalone attribute.
10449
     * It will be overwritten later if a standalone attribute is found.
10450
     */
10451
10452
333
    ctxt->standalone = -2;
10453
10454
    /*
10455
     * We know that '<?xml' is here.
10456
     */
10457
333
    SKIP(5);
10458
10459
333
    if (!IS_BLANK_CH(RAW)) {
10460
0
  xmlFatalErrMsg(ctxt, XML_ERR_SPACE_REQUIRED,
10461
0
                 "Blank needed after '<?xml'\n");
10462
0
    }
10463
333
    SKIP_BLANKS;
10464
10465
    /*
10466
     * We must have the VersionInfo here.
10467
     */
10468
333
    version = xmlParseVersionInfo(ctxt);
10469
333
    if (version == NULL) {
10470
51
  xmlFatalErr(ctxt, XML_ERR_VERSION_MISSING, NULL);
10471
282
    } else {
10472
282
  if (!xmlStrEqual(version, (const xmlChar *) XML_DEFAULT_VERSION)) {
10473
      /*
10474
       * Changed here for XML-1.0 5th edition
10475
       */
10476
76
      if (ctxt->options & XML_PARSE_OLD10) {
10477
0
    xmlFatalErrMsgStr(ctxt, XML_ERR_UNKNOWN_VERSION,
10478
0
                "Unsupported version '%s'\n",
10479
0
                version);
10480
76
      } else {
10481
76
          if ((version[0] == '1') && ((version[1] == '.'))) {
10482
0
        xmlWarningMsg(ctxt, XML_WAR_UNKNOWN_VERSION,
10483
0
                      "Unsupported version '%s'\n",
10484
0
          version, NULL);
10485
76
    } else {
10486
76
        xmlFatalErrMsgStr(ctxt, XML_ERR_UNKNOWN_VERSION,
10487
76
              "Unsupported version '%s'\n",
10488
76
              version);
10489
76
    }
10490
76
      }
10491
76
  }
10492
282
  if (ctxt->version != NULL)
10493
0
      xmlFree((void *) ctxt->version);
10494
282
  ctxt->version = version;
10495
282
    }
10496
10497
    /*
10498
     * We may have the encoding declaration
10499
     */
10500
333
    if (!IS_BLANK_CH(RAW)) {
10501
51
        if ((RAW == '?') && (NXT(1) == '>')) {
10502
0
      SKIP(2);
10503
0
      return;
10504
0
  }
10505
51
  xmlFatalErrMsg(ctxt, XML_ERR_SPACE_REQUIRED, "Blank needed here\n");
10506
51
    }
10507
333
    xmlParseEncodingDecl(ctxt);
10508
10509
    /*
10510
     * We may have the standalone status.
10511
     */
10512
333
    if ((ctxt->encoding != NULL) && (!IS_BLANK_CH(RAW))) {
10513
310
        if ((RAW == '?') && (NXT(1) == '>')) {
10514
260
      SKIP(2);
10515
260
      return;
10516
260
  }
10517
50
  xmlFatalErrMsg(ctxt, XML_ERR_SPACE_REQUIRED, "Blank needed here\n");
10518
50
    }
10519
10520
    /*
10521
     * We can grow the input buffer freely at that point
10522
     */
10523
73
    GROW;
10524
10525
73
    SKIP_BLANKS;
10526
73
    ctxt->standalone = xmlParseSDDecl(ctxt);
10527
10528
73
    SKIP_BLANKS;
10529
73
    if ((RAW == '?') && (NXT(1) == '>')) {
10530
0
        SKIP(2);
10531
73
    } else if (RAW == '>') {
10532
        /* Deprecated old WD ... */
10533
0
  xmlFatalErr(ctxt, XML_ERR_XMLDECL_NOT_FINISHED, NULL);
10534
0
  NEXT;
10535
73
    } else {
10536
73
        int c;
10537
10538
73
  xmlFatalErr(ctxt, XML_ERR_XMLDECL_NOT_FINISHED, NULL);
10539
23.6k
        while ((PARSER_STOPPED(ctxt) == 0) &&
10540
23.6k
               ((c = CUR) != 0)) {
10541
23.6k
            NEXT;
10542
23.6k
            if (c == '>')
10543
72
                break;
10544
23.6k
        }
10545
73
    }
10546
73
}
10547
10548
/**
10549
 * xmlCtxtGetVersion:
10550
 * @ctxt:  parser context
10551
 *
10552
 * Available since 2.14.0.
10553
 *
10554
 * Returns the version from the XML declaration.
10555
 */
10556
const xmlChar *
10557
0
xmlCtxtGetVersion(xmlParserCtxtPtr ctxt) {
10558
0
    if (ctxt == NULL)
10559
0
        return(NULL);
10560
10561
0
    return(ctxt->version);
10562
0
}
10563
10564
/**
10565
 * xmlCtxtGetStandalone:
10566
 * @ctxt:  parser context
10567
 *
10568
 * Available since 2.14.0.
10569
 *
10570
 * Returns the value from the standalone document declaration.
10571
 */
10572
int
10573
0
xmlCtxtGetStandalone(xmlParserCtxtPtr ctxt) {
10574
0
    if (ctxt == NULL)
10575
0
        return(0);
10576
10577
0
    return(ctxt->standalone);
10578
0
}
10579
10580
/**
10581
 * xmlParseMisc:
10582
 * @ctxt:  an XML parser context
10583
 *
10584
 * DEPRECATED: Internal function, don't use.
10585
 *
10586
 * parse an XML Misc* optional field.
10587
 *
10588
 * [27] Misc ::= Comment | PI |  S
10589
 */
10590
10591
void
10592
1.90k
xmlParseMisc(xmlParserCtxtPtr ctxt) {
10593
1.94k
    while (PARSER_STOPPED(ctxt) == 0) {
10594
1.64k
        SKIP_BLANKS;
10595
1.64k
        GROW;
10596
1.64k
        if ((RAW == '<') && (NXT(1) == '?')) {
10597
31
      xmlParsePI(ctxt);
10598
1.61k
        } else if (CMP4(CUR_PTR, '<', '!', '-', '-')) {
10599
7
      xmlParseComment(ctxt);
10600
1.61k
        } else {
10601
1.61k
            break;
10602
1.61k
        }
10603
1.64k
    }
10604
1.90k
}
10605
10606
static void
10607
792
xmlFinishDocument(xmlParserCtxtPtr ctxt) {
10608
792
    xmlDocPtr doc;
10609
10610
    /*
10611
     * SAX: end of the document processing.
10612
     */
10613
792
    if ((ctxt->sax) && (ctxt->sax->endDocument != NULL))
10614
792
        ctxt->sax->endDocument(ctxt->userData);
10615
10616
792
    doc = ctxt->myDoc;
10617
792
    if (doc != NULL) {
10618
792
        if (ctxt->wellFormed) {
10619
0
            doc->properties |= XML_DOC_WELLFORMED;
10620
0
            if (ctxt->valid)
10621
0
                doc->properties |= XML_DOC_DTDVALID;
10622
0
            if (ctxt->nsWellFormed)
10623
0
                doc->properties |= XML_DOC_NSVALID;
10624
0
        }
10625
10626
792
        if (ctxt->options & XML_PARSE_OLD10)
10627
0
            doc->properties |= XML_DOC_OLD10;
10628
10629
        /*
10630
         * Remove locally kept entity definitions if the tree was not built
10631
         */
10632
792
  if (xmlStrEqual(doc->version, SAX_COMPAT_MODE)) {
10633
0
            xmlFreeDoc(doc);
10634
0
            ctxt->myDoc = NULL;
10635
0
        }
10636
792
    }
10637
792
}
10638
10639
/**
10640
 * xmlParseDocument:
10641
 * @ctxt:  an XML parser context
10642
 *
10643
 * Parse an XML document and invoke the SAX handlers. This is useful
10644
 * if you're only interested in custom SAX callbacks. If you want a
10645
 * document tree, use xmlCtxtParseDocument.
10646
 *
10647
 * Returns 0, -1 in case of error.
10648
 */
10649
10650
int
10651
793
xmlParseDocument(xmlParserCtxtPtr ctxt) {
10652
793
    if ((ctxt == NULL) || (ctxt->input == NULL))
10653
0
        return(-1);
10654
10655
793
    GROW;
10656
10657
    /*
10658
     * SAX: detecting the level.
10659
     */
10660
793
    xmlCtxtInitializeLate(ctxt);
10661
10662
793
    if ((ctxt->sax) && (ctxt->sax->setDocumentLocator)) {
10663
793
        ctxt->sax->setDocumentLocator(ctxt->userData,
10664
793
                (xmlSAXLocator *) &xmlDefaultSAXLocator);
10665
793
    }
10666
10667
793
    xmlDetectEncoding(ctxt);
10668
10669
793
    if (CUR == 0) {
10670
1
  xmlFatalErr(ctxt, XML_ERR_DOCUMENT_EMPTY, NULL);
10671
1
  return(-1);
10672
1
    }
10673
10674
792
    GROW;
10675
792
    if ((CMP5(CUR_PTR, '<', '?', 'x', 'm', 'l')) && (IS_BLANK_CH(NXT(5)))) {
10676
10677
  /*
10678
   * Note that we will switch encoding on the fly.
10679
   */
10680
333
  xmlParseXMLDecl(ctxt);
10681
333
  SKIP_BLANKS;
10682
459
    } else {
10683
459
  ctxt->version = xmlCharStrdup(XML_DEFAULT_VERSION);
10684
459
        if (ctxt->version == NULL) {
10685
0
            xmlErrMemory(ctxt);
10686
0
            return(-1);
10687
0
        }
10688
459
    }
10689
792
    if ((ctxt->sax) && (ctxt->sax->startDocument) && (!ctxt->disableSAX))
10690
792
        ctxt->sax->startDocument(ctxt->userData);
10691
792
    if ((ctxt->myDoc != NULL) && (ctxt->input != NULL) &&
10692
792
        (ctxt->input->buf != NULL) && (ctxt->input->buf->compressed >= 0)) {
10693
0
  ctxt->myDoc->compression = ctxt->input->buf->compressed;
10694
0
    }
10695
10696
    /*
10697
     * The Misc part of the Prolog
10698
     */
10699
792
    xmlParseMisc(ctxt);
10700
10701
    /*
10702
     * Then possibly doc type declaration(s) and more Misc
10703
     * (doctypedecl Misc*)?
10704
     */
10705
792
    GROW;
10706
792
    if (CMP9(CUR_PTR, '<', '!', 'D', 'O', 'C', 'T', 'Y', 'P', 'E')) {
10707
10708
391
  ctxt->inSubset = 1;
10709
391
  xmlParseDocTypeDecl(ctxt);
10710
391
  if (RAW == '[') {
10711
391
      xmlParseInternalSubset(ctxt);
10712
391
  } else if (RAW == '>') {
10713
0
            NEXT;
10714
0
        }
10715
10716
  /*
10717
   * Create and update the external subset.
10718
   */
10719
391
  ctxt->inSubset = 2;
10720
391
  if ((ctxt->sax != NULL) && (ctxt->sax->externalSubset != NULL) &&
10721
391
      (!ctxt->disableSAX))
10722
352
      ctxt->sax->externalSubset(ctxt->userData, ctxt->intSubName,
10723
352
                                ctxt->extSubSystem, ctxt->extSubURI);
10724
391
  ctxt->inSubset = 0;
10725
10726
391
        xmlCleanSpecialAttr(ctxt);
10727
10728
391
  xmlParseMisc(ctxt);
10729
391
    }
10730
10731
    /*
10732
     * Time to start parsing the tree itself
10733
     */
10734
792
    GROW;
10735
792
    if (RAW != '<') {
10736
69
        if (ctxt->wellFormed)
10737
0
            xmlFatalErrMsg(ctxt, XML_ERR_DOCUMENT_EMPTY,
10738
0
                           "Start tag expected, '<' not found\n");
10739
723
    } else {
10740
723
  xmlParseElement(ctxt);
10741
10742
  /*
10743
   * The Misc part at the end
10744
   */
10745
723
  xmlParseMisc(ctxt);
10746
10747
723
        xmlParserCheckEOF(ctxt, XML_ERR_DOCUMENT_END);
10748
723
    }
10749
10750
792
    ctxt->instate = XML_PARSER_EOF;
10751
792
    xmlFinishDocument(ctxt);
10752
10753
792
    if (! ctxt->wellFormed) {
10754
792
  ctxt->valid = 0;
10755
792
  return(-1);
10756
792
    }
10757
10758
0
    return(0);
10759
792
}
10760
10761
/**
10762
 * xmlParseExtParsedEnt:
10763
 * @ctxt:  an XML parser context
10764
 *
10765
 * DEPRECATED: Internal function, don't use.
10766
 *
10767
 * parse a general parsed entity
10768
 * An external general parsed entity is well-formed if it matches the
10769
 * production labeled extParsedEnt.
10770
 *
10771
 * [78] extParsedEnt ::= TextDecl? content
10772
 *
10773
 * Returns 0, -1 in case of error. the parser context is augmented
10774
 *                as a result of the parsing.
10775
 */
10776
10777
int
10778
0
xmlParseExtParsedEnt(xmlParserCtxtPtr ctxt) {
10779
0
    if ((ctxt == NULL) || (ctxt->input == NULL))
10780
0
        return(-1);
10781
10782
0
    xmlCtxtInitializeLate(ctxt);
10783
10784
0
    if ((ctxt->sax) && (ctxt->sax->setDocumentLocator)) {
10785
0
        ctxt->sax->setDocumentLocator(ctxt->userData,
10786
0
                (xmlSAXLocator *) &xmlDefaultSAXLocator);
10787
0
    }
10788
10789
0
    xmlDetectEncoding(ctxt);
10790
10791
0
    if (CUR == 0) {
10792
0
  xmlFatalErr(ctxt, XML_ERR_DOCUMENT_EMPTY, NULL);
10793
0
    }
10794
10795
    /*
10796
     * Check for the XMLDecl in the Prolog.
10797
     */
10798
0
    GROW;
10799
0
    if ((CMP5(CUR_PTR, '<', '?', 'x', 'm', 'l')) && (IS_BLANK_CH(NXT(5)))) {
10800
10801
  /*
10802
   * Note that we will switch encoding on the fly.
10803
   */
10804
0
  xmlParseXMLDecl(ctxt);
10805
0
  SKIP_BLANKS;
10806
0
    } else {
10807
0
  ctxt->version = xmlCharStrdup(XML_DEFAULT_VERSION);
10808
0
    }
10809
0
    if ((ctxt->sax) && (ctxt->sax->startDocument) && (!ctxt->disableSAX))
10810
0
        ctxt->sax->startDocument(ctxt->userData);
10811
10812
    /*
10813
     * Doing validity checking on chunk doesn't make sense
10814
     */
10815
0
    ctxt->options &= ~XML_PARSE_DTDVALID;
10816
0
    ctxt->validate = 0;
10817
0
    ctxt->depth = 0;
10818
10819
0
    xmlParseContentInternal(ctxt);
10820
10821
0
    if (ctxt->input->cur < ctxt->input->end)
10822
0
  xmlFatalErr(ctxt, XML_ERR_NOT_WELL_BALANCED, NULL);
10823
10824
    /*
10825
     * SAX: end of the document processing.
10826
     */
10827
0
    if ((ctxt->sax) && (ctxt->sax->endDocument != NULL))
10828
0
        ctxt->sax->endDocument(ctxt->userData);
10829
10830
0
    if (! ctxt->wellFormed) return(-1);
10831
0
    return(0);
10832
0
}
10833
10834
#ifdef LIBXML_PUSH_ENABLED
10835
/************************************************************************
10836
 *                  *
10837
 *    Progressive parsing interfaces        *
10838
 *                  *
10839
 ************************************************************************/
10840
10841
/**
10842
 * xmlParseLookupChar:
10843
 * @ctxt:  an XML parser context
10844
 * @c:  character
10845
 *
10846
 * Check whether the input buffer contains a character.
10847
 */
10848
static int
10849
xmlParseLookupChar(xmlParserCtxtPtr ctxt, int c) {
10850
    const xmlChar *cur;
10851
10852
    if (ctxt->checkIndex == 0) {
10853
        cur = ctxt->input->cur + 1;
10854
    } else {
10855
        cur = ctxt->input->cur + ctxt->checkIndex;
10856
    }
10857
10858
    if (memchr(cur, c, ctxt->input->end - cur) == NULL) {
10859
        size_t index = ctxt->input->end - ctxt->input->cur;
10860
10861
        if (index > LONG_MAX) {
10862
            ctxt->checkIndex = 0;
10863
            return(1);
10864
        }
10865
        ctxt->checkIndex = index;
10866
        return(0);
10867
    } else {
10868
        ctxt->checkIndex = 0;
10869
        return(1);
10870
    }
10871
}
10872
10873
/**
10874
 * xmlParseLookupString:
10875
 * @ctxt:  an XML parser context
10876
 * @startDelta: delta to apply at the start
10877
 * @str:  string
10878
 * @strLen:  length of string
10879
 *
10880
 * Check whether the input buffer contains a string.
10881
 */
10882
static const xmlChar *
10883
xmlParseLookupString(xmlParserCtxtPtr ctxt, size_t startDelta,
10884
                     const char *str, size_t strLen) {
10885
    const xmlChar *cur, *term;
10886
10887
    if (ctxt->checkIndex == 0) {
10888
        cur = ctxt->input->cur + startDelta;
10889
    } else {
10890
        cur = ctxt->input->cur + ctxt->checkIndex;
10891
    }
10892
10893
    term = BAD_CAST strstr((const char *) cur, str);
10894
    if (term == NULL) {
10895
        const xmlChar *end = ctxt->input->end;
10896
        size_t index;
10897
10898
        /* Rescan (strLen - 1) characters. */
10899
        if ((size_t) (end - cur) < strLen)
10900
            end = cur;
10901
        else
10902
            end -= strLen - 1;
10903
        index = end - ctxt->input->cur;
10904
        if (index > LONG_MAX) {
10905
            ctxt->checkIndex = 0;
10906
            return(ctxt->input->end - strLen);
10907
        }
10908
        ctxt->checkIndex = index;
10909
    } else {
10910
        ctxt->checkIndex = 0;
10911
    }
10912
10913
    return(term);
10914
}
10915
10916
/**
10917
 * xmlParseLookupCharData:
10918
 * @ctxt:  an XML parser context
10919
 *
10920
 * Check whether the input buffer contains terminated char data.
10921
 */
10922
static int
10923
xmlParseLookupCharData(xmlParserCtxtPtr ctxt) {
10924
    const xmlChar *cur = ctxt->input->cur + ctxt->checkIndex;
10925
    const xmlChar *end = ctxt->input->end;
10926
    size_t index;
10927
10928
    while (cur < end) {
10929
        if ((*cur == '<') || (*cur == '&')) {
10930
            ctxt->checkIndex = 0;
10931
            return(1);
10932
        }
10933
        cur++;
10934
    }
10935
10936
    index = cur - ctxt->input->cur;
10937
    if (index > LONG_MAX) {
10938
        ctxt->checkIndex = 0;
10939
        return(1);
10940
    }
10941
    ctxt->checkIndex = index;
10942
    return(0);
10943
}
10944
10945
/**
10946
 * xmlParseLookupGt:
10947
 * @ctxt:  an XML parser context
10948
 *
10949
 * Check whether there's enough data in the input buffer to finish parsing
10950
 * a start tag. This has to take quotes into account.
10951
 */
10952
static int
10953
xmlParseLookupGt(xmlParserCtxtPtr ctxt) {
10954
    const xmlChar *cur;
10955
    const xmlChar *end = ctxt->input->end;
10956
    int state = ctxt->endCheckState;
10957
    size_t index;
10958
10959
    if (ctxt->checkIndex == 0)
10960
        cur = ctxt->input->cur + 1;
10961
    else
10962
        cur = ctxt->input->cur + ctxt->checkIndex;
10963
10964
    while (cur < end) {
10965
        if (state) {
10966
            if (*cur == state)
10967
                state = 0;
10968
        } else if (*cur == '\'' || *cur == '"') {
10969
            state = *cur;
10970
        } else if (*cur == '>') {
10971
            ctxt->checkIndex = 0;
10972
            ctxt->endCheckState = 0;
10973
            return(1);
10974
        }
10975
        cur++;
10976
    }
10977
10978
    index = cur - ctxt->input->cur;
10979
    if (index > LONG_MAX) {
10980
        ctxt->checkIndex = 0;
10981
        ctxt->endCheckState = 0;
10982
        return(1);
10983
    }
10984
    ctxt->checkIndex = index;
10985
    ctxt->endCheckState = state;
10986
    return(0);
10987
}
10988
10989
/**
10990
 * xmlParseLookupInternalSubset:
10991
 * @ctxt:  an XML parser context
10992
 *
10993
 * Check whether there's enough data in the input buffer to finish parsing
10994
 * the internal subset.
10995
 */
10996
static int
10997
xmlParseLookupInternalSubset(xmlParserCtxtPtr ctxt) {
10998
    /*
10999
     * Sorry, but progressive parsing of the internal subset is not
11000
     * supported. We first check that the full content of the internal
11001
     * subset is available and parsing is launched only at that point.
11002
     * Internal subset ends with "']' S? '>'" in an unescaped section and
11003
     * not in a ']]>' sequence which are conditional sections.
11004
     */
11005
    const xmlChar *cur, *start;
11006
    const xmlChar *end = ctxt->input->end;
11007
    int state = ctxt->endCheckState;
11008
    size_t index;
11009
11010
    if (ctxt->checkIndex == 0) {
11011
        cur = ctxt->input->cur + 1;
11012
    } else {
11013
        cur = ctxt->input->cur + ctxt->checkIndex;
11014
    }
11015
    start = cur;
11016
11017
    while (cur < end) {
11018
        if (state == '-') {
11019
            if ((*cur == '-') &&
11020
                (cur[1] == '-') &&
11021
                (cur[2] == '>')) {
11022
                state = 0;
11023
                cur += 3;
11024
                start = cur;
11025
                continue;
11026
            }
11027
        }
11028
        else if (state == ']') {
11029
            if (*cur == '>') {
11030
                ctxt->checkIndex = 0;
11031
                ctxt->endCheckState = 0;
11032
                return(1);
11033
            }
11034
            if (IS_BLANK_CH(*cur)) {
11035
                state = ' ';
11036
            } else if (*cur != ']') {
11037
                state = 0;
11038
                start = cur;
11039
                continue;
11040
            }
11041
        }
11042
        else if (state == ' ') {
11043
            if (*cur == '>') {
11044
                ctxt->checkIndex = 0;
11045
                ctxt->endCheckState = 0;
11046
                return(1);
11047
            }
11048
            if (!IS_BLANK_CH(*cur)) {
11049
                state = 0;
11050
                start = cur;
11051
                continue;
11052
            }
11053
        }
11054
        else if (state != 0) {
11055
            if (*cur == state) {
11056
                state = 0;
11057
                start = cur + 1;
11058
            }
11059
        }
11060
        else if (*cur == '<') {
11061
            if ((cur[1] == '!') &&
11062
                (cur[2] == '-') &&
11063
                (cur[3] == '-')) {
11064
                state = '-';
11065
                cur += 4;
11066
                /* Don't treat <!--> as comment */
11067
                start = cur;
11068
                continue;
11069
            }
11070
        }
11071
        else if ((*cur == '"') || (*cur == '\'') || (*cur == ']')) {
11072
            state = *cur;
11073
        }
11074
11075
        cur++;
11076
    }
11077
11078
    /*
11079
     * Rescan the three last characters to detect "<!--" and "-->"
11080
     * split across chunks.
11081
     */
11082
    if ((state == 0) || (state == '-')) {
11083
        if (cur - start < 3)
11084
            cur = start;
11085
        else
11086
            cur -= 3;
11087
    }
11088
    index = cur - ctxt->input->cur;
11089
    if (index > LONG_MAX) {
11090
        ctxt->checkIndex = 0;
11091
        ctxt->endCheckState = 0;
11092
        return(1);
11093
    }
11094
    ctxt->checkIndex = index;
11095
    ctxt->endCheckState = state;
11096
    return(0);
11097
}
11098
11099
/**
11100
 * xmlParseTryOrFinish:
11101
 * @ctxt:  an XML parser context
11102
 * @terminate:  last chunk indicator
11103
 *
11104
 * Try to progress on parsing
11105
 *
11106
 * Returns zero if no parsing was possible
11107
 */
11108
static int
11109
xmlParseTryOrFinish(xmlParserCtxtPtr ctxt, int terminate) {
11110
    int ret = 0;
11111
    size_t avail;
11112
    xmlChar cur, next;
11113
11114
    if (ctxt->input == NULL)
11115
        return(0);
11116
11117
    if ((ctxt->input != NULL) &&
11118
        (ctxt->input->cur - ctxt->input->base > 4096)) {
11119
        xmlParserShrink(ctxt);
11120
    }
11121
11122
    while (ctxt->disableSAX == 0) {
11123
        avail = ctxt->input->end - ctxt->input->cur;
11124
        if (avail < 1)
11125
      goto done;
11126
        switch (ctxt->instate) {
11127
            case XML_PARSER_EOF:
11128
          /*
11129
     * Document parsing is done !
11130
     */
11131
          goto done;
11132
            case XML_PARSER_START:
11133
                /*
11134
                 * Very first chars read from the document flow.
11135
                 */
11136
                if ((!terminate) && (avail < 4))
11137
                    goto done;
11138
11139
                /*
11140
                 * We need more bytes to detect EBCDIC code pages.
11141
                 * See xmlDetectEBCDIC.
11142
                 */
11143
                if ((CMP4(CUR_PTR, 0x4C, 0x6F, 0xA7, 0x94)) &&
11144
                    (!terminate) && (avail < 200))
11145
                    goto done;
11146
11147
                xmlDetectEncoding(ctxt);
11148
                ctxt->instate = XML_PARSER_XML_DECL;
11149
    break;
11150
11151
            case XML_PARSER_XML_DECL:
11152
    if ((!terminate) && (avail < 2))
11153
        goto done;
11154
    cur = ctxt->input->cur[0];
11155
    next = ctxt->input->cur[1];
11156
          if ((cur == '<') && (next == '?')) {
11157
        /* PI or XML decl */
11158
        if ((!terminate) &&
11159
                        (!xmlParseLookupString(ctxt, 2, "?>", 2)))
11160
      goto done;
11161
        if ((ctxt->input->cur[2] == 'x') &&
11162
      (ctxt->input->cur[3] == 'm') &&
11163
      (ctxt->input->cur[4] == 'l') &&
11164
      (IS_BLANK_CH(ctxt->input->cur[5]))) {
11165
      ret += 5;
11166
      xmlParseXMLDecl(ctxt);
11167
        } else {
11168
      ctxt->version = xmlCharStrdup(XML_DEFAULT_VERSION);
11169
                        if (ctxt->version == NULL) {
11170
                            xmlErrMemory(ctxt);
11171
                            break;
11172
                        }
11173
        }
11174
    } else {
11175
        ctxt->version = xmlCharStrdup(XML_DEFAULT_VERSION);
11176
        if (ctxt->version == NULL) {
11177
            xmlErrMemory(ctxt);
11178
      break;
11179
        }
11180
    }
11181
                if ((ctxt->sax) && (ctxt->sax->setDocumentLocator)) {
11182
                    ctxt->sax->setDocumentLocator(ctxt->userData,
11183
                            (xmlSAXLocator *) &xmlDefaultSAXLocator);
11184
                }
11185
                if ((ctxt->sax) && (ctxt->sax->startDocument) &&
11186
                    (!ctxt->disableSAX))
11187
                    ctxt->sax->startDocument(ctxt->userData);
11188
                ctxt->instate = XML_PARSER_MISC;
11189
    break;
11190
            case XML_PARSER_START_TAG: {
11191
          const xmlChar *name;
11192
    const xmlChar *prefix = NULL;
11193
    const xmlChar *URI = NULL;
11194
                int line = ctxt->input->line;
11195
    int nbNs = 0;
11196
11197
    if ((!terminate) && (avail < 2))
11198
        goto done;
11199
    cur = ctxt->input->cur[0];
11200
          if (cur != '<') {
11201
        xmlFatalErrMsg(ctxt, XML_ERR_DOCUMENT_EMPTY,
11202
                                   "Start tag expected, '<' not found");
11203
                    ctxt->instate = XML_PARSER_EOF;
11204
                    xmlFinishDocument(ctxt);
11205
        goto done;
11206
    }
11207
    if ((!terminate) && (!xmlParseLookupGt(ctxt)))
11208
                    goto done;
11209
    if (ctxt->spaceNr == 0)
11210
        spacePush(ctxt, -1);
11211
    else if (*ctxt->space == -2)
11212
        spacePush(ctxt, -1);
11213
    else
11214
        spacePush(ctxt, *ctxt->space);
11215
#ifdef LIBXML_SAX1_ENABLED
11216
    if (ctxt->sax2)
11217
#endif /* LIBXML_SAX1_ENABLED */
11218
        name = xmlParseStartTag2(ctxt, &prefix, &URI, &nbNs);
11219
#ifdef LIBXML_SAX1_ENABLED
11220
    else
11221
        name = xmlParseStartTag(ctxt);
11222
#endif /* LIBXML_SAX1_ENABLED */
11223
    if (name == NULL) {
11224
        spacePop(ctxt);
11225
                    ctxt->instate = XML_PARSER_EOF;
11226
                    xmlFinishDocument(ctxt);
11227
        goto done;
11228
    }
11229
#ifdef LIBXML_VALID_ENABLED
11230
    /*
11231
     * [ VC: Root Element Type ]
11232
     * The Name in the document type declaration must match
11233
     * the element type of the root element.
11234
     */
11235
    if (ctxt->validate && ctxt->wellFormed && ctxt->myDoc &&
11236
        ctxt->node && (ctxt->node == ctxt->myDoc->children))
11237
        ctxt->valid &= xmlValidateRoot(&ctxt->vctxt, ctxt->myDoc);
11238
#endif /* LIBXML_VALID_ENABLED */
11239
11240
    /*
11241
     * Check for an Empty Element.
11242
     */
11243
    if ((RAW == '/') && (NXT(1) == '>')) {
11244
        SKIP(2);
11245
11246
        if (ctxt->sax2) {
11247
      if ((ctxt->sax != NULL) &&
11248
          (ctxt->sax->endElementNs != NULL) &&
11249
          (!ctxt->disableSAX))
11250
          ctxt->sax->endElementNs(ctxt->userData, name,
11251
                                  prefix, URI);
11252
      if (nbNs > 0)
11253
          xmlParserNsPop(ctxt, nbNs);
11254
#ifdef LIBXML_SAX1_ENABLED
11255
        } else {
11256
      if ((ctxt->sax != NULL) &&
11257
          (ctxt->sax->endElement != NULL) &&
11258
          (!ctxt->disableSAX))
11259
          ctxt->sax->endElement(ctxt->userData, name);
11260
#endif /* LIBXML_SAX1_ENABLED */
11261
        }
11262
        spacePop(ctxt);
11263
    } else if (RAW == '>') {
11264
        NEXT;
11265
                    nameNsPush(ctxt, name, prefix, URI, line, nbNs);
11266
    } else {
11267
        xmlFatalErrMsgStr(ctxt, XML_ERR_GT_REQUIRED,
11268
           "Couldn't find end of Start Tag %s\n",
11269
           name);
11270
        nodePop(ctxt);
11271
        spacePop(ctxt);
11272
                    if (nbNs > 0)
11273
                        xmlParserNsPop(ctxt, nbNs);
11274
    }
11275
11276
                if (ctxt->nameNr == 0)
11277
                    ctxt->instate = XML_PARSER_EPILOG;
11278
                else
11279
                    ctxt->instate = XML_PARSER_CONTENT;
11280
                break;
11281
      }
11282
            case XML_PARSER_CONTENT: {
11283
    cur = ctxt->input->cur[0];
11284
11285
    if (cur == '<') {
11286
                    if ((!terminate) && (avail < 2))
11287
                        goto done;
11288
        next = ctxt->input->cur[1];
11289
11290
                    if (next == '/') {
11291
                        ctxt->instate = XML_PARSER_END_TAG;
11292
                        break;
11293
                    } else if (next == '?') {
11294
                        if ((!terminate) &&
11295
                            (!xmlParseLookupString(ctxt, 2, "?>", 2)))
11296
                            goto done;
11297
                        xmlParsePI(ctxt);
11298
                        ctxt->instate = XML_PARSER_CONTENT;
11299
                        break;
11300
                    } else if (next == '!') {
11301
                        if ((!terminate) && (avail < 3))
11302
                            goto done;
11303
                        next = ctxt->input->cur[2];
11304
11305
                        if (next == '-') {
11306
                            if ((!terminate) && (avail < 4))
11307
                                goto done;
11308
                            if (ctxt->input->cur[3] == '-') {
11309
                                if ((!terminate) &&
11310
                                    (!xmlParseLookupString(ctxt, 4, "-->", 3)))
11311
                                    goto done;
11312
                                xmlParseComment(ctxt);
11313
                                ctxt->instate = XML_PARSER_CONTENT;
11314
                                break;
11315
                            }
11316
                        } else if (next == '[') {
11317
                            if ((!terminate) && (avail < 9))
11318
                                goto done;
11319
                            if ((ctxt->input->cur[2] == '[') &&
11320
                                (ctxt->input->cur[3] == 'C') &&
11321
                                (ctxt->input->cur[4] == 'D') &&
11322
                                (ctxt->input->cur[5] == 'A') &&
11323
                                (ctxt->input->cur[6] == 'T') &&
11324
                                (ctxt->input->cur[7] == 'A') &&
11325
                                (ctxt->input->cur[8] == '[')) {
11326
                                if ((!terminate) &&
11327
                                    (!xmlParseLookupString(ctxt, 9, "]]>", 3)))
11328
                                    goto done;
11329
                                ctxt->instate = XML_PARSER_CDATA_SECTION;
11330
                                xmlParseCDSect(ctxt);
11331
                                ctxt->instate = XML_PARSER_CONTENT;
11332
                                break;
11333
                            }
11334
                        }
11335
                    }
11336
    } else if (cur == '&') {
11337
        if ((!terminate) && (!xmlParseLookupChar(ctxt, ';')))
11338
      goto done;
11339
        xmlParseReference(ctxt);
11340
                    break;
11341
    } else {
11342
        /* TODO Avoid the extra copy, handle directly !!! */
11343
        /*
11344
         * Goal of the following test is:
11345
         *  - minimize calls to the SAX 'character' callback
11346
         *    when they are mergeable
11347
         *  - handle an problem for isBlank when we only parse
11348
         *    a sequence of blank chars and the next one is
11349
         *    not available to check against '<' presence.
11350
         *  - tries to homogenize the differences in SAX
11351
         *    callbacks between the push and pull versions
11352
         *    of the parser.
11353
         */
11354
        if (avail < XML_PARSER_BIG_BUFFER_SIZE) {
11355
      if ((!terminate) && (!xmlParseLookupCharData(ctxt)))
11356
          goto done;
11357
                    }
11358
                    ctxt->checkIndex = 0;
11359
        xmlParseCharDataInternal(ctxt, !terminate);
11360
                    break;
11361
    }
11362
11363
                ctxt->instate = XML_PARSER_START_TAG;
11364
    break;
11365
      }
11366
            case XML_PARSER_END_TAG:
11367
    if ((!terminate) && (!xmlParseLookupChar(ctxt, '>')))
11368
        goto done;
11369
    if (ctxt->sax2) {
11370
              xmlParseEndTag2(ctxt, &ctxt->pushTab[ctxt->nameNr - 1]);
11371
        nameNsPop(ctxt);
11372
    }
11373
#ifdef LIBXML_SAX1_ENABLED
11374
      else
11375
        xmlParseEndTag1(ctxt, 0);
11376
#endif /* LIBXML_SAX1_ENABLED */
11377
    if (ctxt->nameNr == 0) {
11378
        ctxt->instate = XML_PARSER_EPILOG;
11379
    } else {
11380
        ctxt->instate = XML_PARSER_CONTENT;
11381
    }
11382
    break;
11383
            case XML_PARSER_MISC:
11384
            case XML_PARSER_PROLOG:
11385
            case XML_PARSER_EPILOG:
11386
    SKIP_BLANKS;
11387
                avail = ctxt->input->end - ctxt->input->cur;
11388
    if (avail < 1)
11389
        goto done;
11390
    if (ctxt->input->cur[0] == '<') {
11391
                    if ((!terminate) && (avail < 2))
11392
                        goto done;
11393
                    next = ctxt->input->cur[1];
11394
                    if (next == '?') {
11395
                        if ((!terminate) &&
11396
                            (!xmlParseLookupString(ctxt, 2, "?>", 2)))
11397
                            goto done;
11398
                        xmlParsePI(ctxt);
11399
                        break;
11400
                    } else if (next == '!') {
11401
                        if ((!terminate) && (avail < 3))
11402
                            goto done;
11403
11404
                        if (ctxt->input->cur[2] == '-') {
11405
                            if ((!terminate) && (avail < 4))
11406
                                goto done;
11407
                            if (ctxt->input->cur[3] == '-') {
11408
                                if ((!terminate) &&
11409
                                    (!xmlParseLookupString(ctxt, 4, "-->", 3)))
11410
                                    goto done;
11411
                                xmlParseComment(ctxt);
11412
                                break;
11413
                            }
11414
                        } else if (ctxt->instate == XML_PARSER_MISC) {
11415
                            if ((!terminate) && (avail < 9))
11416
                                goto done;
11417
                            if ((ctxt->input->cur[2] == 'D') &&
11418
                                (ctxt->input->cur[3] == 'O') &&
11419
                                (ctxt->input->cur[4] == 'C') &&
11420
                                (ctxt->input->cur[5] == 'T') &&
11421
                                (ctxt->input->cur[6] == 'Y') &&
11422
                                (ctxt->input->cur[7] == 'P') &&
11423
                                (ctxt->input->cur[8] == 'E')) {
11424
                                if ((!terminate) && (!xmlParseLookupGt(ctxt)))
11425
                                    goto done;
11426
                                ctxt->inSubset = 1;
11427
                                xmlParseDocTypeDecl(ctxt);
11428
                                if (RAW == '[') {
11429
                                    ctxt->instate = XML_PARSER_DTD;
11430
                                } else {
11431
                                    if (RAW == '>')
11432
                                        NEXT;
11433
                                    /*
11434
                                     * Create and update the external subset.
11435
                                     */
11436
                                    ctxt->inSubset = 2;
11437
                                    if ((ctxt->sax != NULL) &&
11438
                                        (!ctxt->disableSAX) &&
11439
                                        (ctxt->sax->externalSubset != NULL))
11440
                                        ctxt->sax->externalSubset(
11441
                                                ctxt->userData,
11442
                                                ctxt->intSubName,
11443
                                                ctxt->extSubSystem,
11444
                                                ctxt->extSubURI);
11445
                                    ctxt->inSubset = 0;
11446
                                    xmlCleanSpecialAttr(ctxt);
11447
                                    ctxt->instate = XML_PARSER_PROLOG;
11448
                                }
11449
                                break;
11450
                            }
11451
                        }
11452
                    }
11453
                }
11454
11455
                if (ctxt->instate == XML_PARSER_EPILOG) {
11456
                    if (ctxt->errNo == XML_ERR_OK)
11457
                        xmlFatalErr(ctxt, XML_ERR_DOCUMENT_END, NULL);
11458
        ctxt->instate = XML_PARSER_EOF;
11459
                    xmlFinishDocument(ctxt);
11460
                } else {
11461
        ctxt->instate = XML_PARSER_START_TAG;
11462
    }
11463
    break;
11464
            case XML_PARSER_DTD: {
11465
                if ((!terminate) && (!xmlParseLookupInternalSubset(ctxt)))
11466
                    goto done;
11467
    xmlParseInternalSubset(ctxt);
11468
    ctxt->inSubset = 2;
11469
    if ((ctxt->sax != NULL) && (!ctxt->disableSAX) &&
11470
        (ctxt->sax->externalSubset != NULL))
11471
        ctxt->sax->externalSubset(ctxt->userData, ctxt->intSubName,
11472
          ctxt->extSubSystem, ctxt->extSubURI);
11473
    ctxt->inSubset = 0;
11474
    xmlCleanSpecialAttr(ctxt);
11475
    ctxt->instate = XML_PARSER_PROLOG;
11476
                break;
11477
      }
11478
            default:
11479
                xmlFatalErrMsg(ctxt, XML_ERR_INTERNAL_ERROR,
11480
      "PP: internal error\n");
11481
    ctxt->instate = XML_PARSER_EOF;
11482
    break;
11483
  }
11484
    }
11485
done:
11486
    return(ret);
11487
}
11488
11489
/**
11490
 * xmlParseChunk:
11491
 * @ctxt:  an XML parser context
11492
 * @chunk:  chunk of memory
11493
 * @size:  size of chunk in bytes
11494
 * @terminate:  last chunk indicator
11495
 *
11496
 * Parse a chunk of memory in push parser mode.
11497
 *
11498
 * Assumes that the parser context was initialized with
11499
 * xmlCreatePushParserCtxt.
11500
 *
11501
 * The last chunk, which will often be empty, must be marked with
11502
 * the @terminate flag. With the default SAX callbacks, the resulting
11503
 * document will be available in ctxt->myDoc. This pointer will not
11504
 * be freed when calling xmlFreeParserCtxt and must be freed by the
11505
 * caller. If the document isn't well-formed, it will still be returned
11506
 * in ctxt->myDoc.
11507
 *
11508
 * As an exception, xmlCtxtResetPush will free the document in
11509
 * ctxt->myDoc. So ctxt->myDoc should be set to NULL after extracting
11510
 * the document.
11511
 *
11512
 * Returns an xmlParserErrors code (0 on success).
11513
 */
11514
int
11515
xmlParseChunk(xmlParserCtxtPtr ctxt, const char *chunk, int size,
11516
              int terminate) {
11517
    size_t curBase;
11518
    size_t maxLength;
11519
    size_t pos;
11520
    int end_in_lf = 0;
11521
    int res;
11522
11523
    if ((ctxt == NULL) || (size < 0))
11524
        return(XML_ERR_ARGUMENT);
11525
    if ((chunk == NULL) && (size > 0))
11526
        return(XML_ERR_ARGUMENT);
11527
    if ((ctxt->input == NULL) || (ctxt->input->buf == NULL))
11528
        return(XML_ERR_ARGUMENT);
11529
    if (ctxt->disableSAX != 0)
11530
        return(ctxt->errNo);
11531
11532
    ctxt->input->flags |= XML_INPUT_PROGRESSIVE;
11533
    if (ctxt->instate == XML_PARSER_START)
11534
        xmlCtxtInitializeLate(ctxt);
11535
    if ((size > 0) && (chunk != NULL) && (!terminate) &&
11536
        (chunk[size - 1] == '\r')) {
11537
  end_in_lf = 1;
11538
  size--;
11539
    }
11540
11541
    /*
11542
     * Also push an empty chunk to make sure that the raw buffer
11543
     * will be flushed if there is an encoder.
11544
     */
11545
    pos = ctxt->input->cur - ctxt->input->base;
11546
    res = xmlParserInputBufferPush(ctxt->input->buf, size, chunk);
11547
    xmlBufUpdateInput(ctxt->input->buf->buffer, ctxt->input, pos);
11548
    if (res < 0) {
11549
        xmlCtxtErrIO(ctxt, ctxt->input->buf->error, NULL);
11550
        xmlHaltParser(ctxt);
11551
        return(ctxt->errNo);
11552
    }
11553
11554
    xmlParseTryOrFinish(ctxt, terminate);
11555
11556
    curBase = ctxt->input->cur - ctxt->input->base;
11557
    maxLength = (ctxt->options & XML_PARSE_HUGE) ?
11558
                XML_MAX_HUGE_LENGTH :
11559
                XML_MAX_LOOKUP_LIMIT;
11560
    if (curBase > maxLength) {
11561
        xmlFatalErr(ctxt, XML_ERR_RESOURCE_LIMIT,
11562
                    "Buffer size limit exceeded, try XML_PARSE_HUGE\n");
11563
        xmlHaltParser(ctxt);
11564
    }
11565
11566
    if ((ctxt->errNo != XML_ERR_OK) && (ctxt->disableSAX != 0))
11567
        return(ctxt->errNo);
11568
11569
    if (end_in_lf == 1) {
11570
  pos = ctxt->input->cur - ctxt->input->base;
11571
  res = xmlParserInputBufferPush(ctxt->input->buf, 1, "\r");
11572
  xmlBufUpdateInput(ctxt->input->buf->buffer, ctxt->input, pos);
11573
        if (res < 0) {
11574
            xmlCtxtErrIO(ctxt, ctxt->input->buf->error, NULL);
11575
            xmlHaltParser(ctxt);
11576
            return(ctxt->errNo);
11577
        }
11578
    }
11579
    if (terminate) {
11580
  /*
11581
   * Check for termination
11582
   */
11583
        if ((ctxt->instate != XML_PARSER_EOF) &&
11584
            (ctxt->instate != XML_PARSER_EPILOG)) {
11585
            if (ctxt->nameNr > 0) {
11586
                const xmlChar *name = ctxt->nameTab[ctxt->nameNr - 1];
11587
                int line = ctxt->pushTab[ctxt->nameNr - 1].line;
11588
                xmlFatalErrMsgStrIntStr(ctxt, XML_ERR_TAG_NOT_FINISHED,
11589
                        "Premature end of data in tag %s line %d\n",
11590
                        name, line, NULL);
11591
            } else if (ctxt->instate == XML_PARSER_START) {
11592
                xmlFatalErr(ctxt, XML_ERR_DOCUMENT_EMPTY, NULL);
11593
            } else {
11594
                xmlFatalErrMsg(ctxt, XML_ERR_DOCUMENT_EMPTY,
11595
                               "Start tag expected, '<' not found\n");
11596
            }
11597
        } else {
11598
            xmlParserCheckEOF(ctxt, XML_ERR_DOCUMENT_END);
11599
        }
11600
  if (ctxt->instate != XML_PARSER_EOF) {
11601
            ctxt->instate = XML_PARSER_EOF;
11602
            xmlFinishDocument(ctxt);
11603
  }
11604
    }
11605
    if (ctxt->wellFormed == 0)
11606
  return((xmlParserErrors) ctxt->errNo);
11607
    else
11608
        return(0);
11609
}
11610
11611
/************************************************************************
11612
 *                  *
11613
 *    I/O front end functions to the parser     *
11614
 *                  *
11615
 ************************************************************************/
11616
11617
/**
11618
 * xmlCreatePushParserCtxt:
11619
 * @sax:  a SAX handler (optional)
11620
 * @user_data:  user data for SAX callbacks (optional)
11621
 * @chunk:  initial chunk (optional, deprecated)
11622
 * @size:  size of initial chunk in bytes
11623
 * @filename:  file name or URI (optional)
11624
 *
11625
 * Create a parser context for using the XML parser in push mode.
11626
 * See xmlParseChunk.
11627
 *
11628
 * Passing an initial chunk is useless and deprecated.
11629
 *
11630
 * The push parser doesn't support recovery mode or the
11631
 * XML_PARSE_NOBLANKS option.
11632
 *
11633
 * @filename is used as base URI to fetch external entities and for
11634
 * error reports.
11635
 *
11636
 * Returns the new parser context or NULL if a memory allocation
11637
 * failed.
11638
 */
11639
11640
xmlParserCtxtPtr
11641
xmlCreatePushParserCtxt(xmlSAXHandlerPtr sax, void *user_data,
11642
                        const char *chunk, int size, const char *filename) {
11643
    xmlParserCtxtPtr ctxt;
11644
    xmlParserInputPtr input;
11645
11646
    ctxt = xmlNewSAXParserCtxt(sax, user_data);
11647
    if (ctxt == NULL)
11648
  return(NULL);
11649
11650
    ctxt->options &= ~XML_PARSE_NODICT;
11651
    ctxt->dictNames = 1;
11652
11653
    input = xmlNewPushInput(filename, chunk, size);
11654
    if (input == NULL) {
11655
  xmlFreeParserCtxt(ctxt);
11656
  return(NULL);
11657
    }
11658
    if (xmlCtxtPushInput(ctxt, input) < 0) {
11659
        xmlFreeInputStream(input);
11660
        xmlFreeParserCtxt(ctxt);
11661
        return(NULL);
11662
    }
11663
11664
    return(ctxt);
11665
}
11666
#endif /* LIBXML_PUSH_ENABLED */
11667
11668
/**
11669
 * xmlStopParser:
11670
 * @ctxt:  an XML parser context
11671
 *
11672
 * Blocks further parser processing
11673
 */
11674
void
11675
477k
xmlStopParser(xmlParserCtxtPtr ctxt) {
11676
477k
    if (ctxt == NULL)
11677
477k
        return;
11678
0
    xmlHaltParser(ctxt);
11679
0
    if (ctxt->errNo != XML_ERR_NO_MEMORY)
11680
0
        ctxt->errNo = XML_ERR_USER_STOP;
11681
0
}
11682
11683
/**
11684
 * xmlCreateIOParserCtxt:
11685
 * @sax:  a SAX handler (optional)
11686
 * @user_data:  user data for SAX callbacks (optional)
11687
 * @ioread:  an I/O read function
11688
 * @ioclose:  an I/O close function (optional)
11689
 * @ioctx:  an I/O handler
11690
 * @enc:  the charset encoding if known (deprecated)
11691
 *
11692
 * Create a parser context for using the XML parser with an existing
11693
 * I/O stream
11694
 *
11695
 * Returns the new parser context or NULL
11696
 */
11697
xmlParserCtxtPtr
11698
xmlCreateIOParserCtxt(xmlSAXHandlerPtr sax, void *user_data,
11699
                      xmlInputReadCallback ioread,
11700
                      xmlInputCloseCallback ioclose,
11701
0
                      void *ioctx, xmlCharEncoding enc) {
11702
0
    xmlParserCtxtPtr ctxt;
11703
0
    xmlParserInputPtr input;
11704
0
    const char *encoding;
11705
11706
0
    ctxt = xmlNewSAXParserCtxt(sax, user_data);
11707
0
    if (ctxt == NULL)
11708
0
  return(NULL);
11709
11710
0
    encoding = xmlGetCharEncodingName(enc);
11711
0
    input = xmlCtxtNewInputFromIO(ctxt, NULL, ioread, ioclose, ioctx,
11712
0
                                  encoding, 0);
11713
0
    if (input == NULL) {
11714
0
  xmlFreeParserCtxt(ctxt);
11715
0
        return (NULL);
11716
0
    }
11717
0
    if (xmlCtxtPushInput(ctxt, input) < 0) {
11718
0
        xmlFreeInputStream(input);
11719
0
        xmlFreeParserCtxt(ctxt);
11720
0
        return(NULL);
11721
0
    }
11722
11723
0
    return(ctxt);
11724
0
}
11725
11726
#ifdef LIBXML_VALID_ENABLED
11727
/************************************************************************
11728
 *                  *
11729
 *    Front ends when parsing a DTD       *
11730
 *                  *
11731
 ************************************************************************/
11732
11733
/**
11734
 * xmlCtxtParseDtd:
11735
 * @ctxt:  a parser context
11736
 * @input:  a parser input
11737
 * @publicId:  public ID of the DTD (optional)
11738
 * @systemId:  system ID of the DTD (optional)
11739
 *
11740
 * Parse a DTD.
11741
 *
11742
 * Option XML_PARSE_DTDLOAD should be enabled in the parser context
11743
 * to make external entities work.
11744
 *
11745
 * Availabe since 2.14.0.
11746
 *
11747
 * Returns the resulting xmlDtdPtr or NULL in case of error.
11748
 * @input will be freed by the function in any case.
11749
 */
11750
xmlDtdPtr
11751
xmlCtxtParseDtd(xmlParserCtxtPtr ctxt, xmlParserInputPtr input,
11752
                const xmlChar *publicId, const xmlChar *systemId) {
11753
    xmlDtdPtr ret = NULL;
11754
11755
    if ((ctxt == NULL) || (input == NULL)) {
11756
        xmlFatalErr(ctxt, XML_ERR_ARGUMENT, NULL);
11757
        xmlFreeInputStream(input);
11758
        return(NULL);
11759
    }
11760
11761
    if (xmlCtxtPushInput(ctxt, input) < 0) {
11762
        xmlFreeInputStream(input);
11763
        return(NULL);
11764
    }
11765
11766
    if (publicId == NULL)
11767
        publicId = BAD_CAST "none";
11768
    if (systemId == NULL)
11769
        systemId = BAD_CAST "none";
11770
11771
    ctxt->myDoc = xmlNewDoc(BAD_CAST "1.0");
11772
    if (ctxt->myDoc == NULL) {
11773
        xmlErrMemory(ctxt);
11774
        goto error;
11775
    }
11776
    ctxt->myDoc->properties = XML_DOC_INTERNAL;
11777
    ctxt->myDoc->extSubset = xmlNewDtd(ctxt->myDoc, BAD_CAST "none",
11778
                                       publicId, systemId);
11779
    if (ctxt->myDoc->extSubset == NULL) {
11780
        xmlErrMemory(ctxt);
11781
        xmlFreeDoc(ctxt->myDoc);
11782
        goto error;
11783
    }
11784
11785
    xmlParseExternalSubset(ctxt, publicId, systemId);
11786
11787
    if (ctxt->wellFormed) {
11788
        ret = ctxt->myDoc->extSubset;
11789
        ctxt->myDoc->extSubset = NULL;
11790
        if (ret != NULL) {
11791
            xmlNodePtr tmp;
11792
11793
            ret->doc = NULL;
11794
            tmp = ret->children;
11795
            while (tmp != NULL) {
11796
                tmp->doc = NULL;
11797
                tmp = tmp->next;
11798
            }
11799
        }
11800
    } else {
11801
        ret = NULL;
11802
    }
11803
    xmlFreeDoc(ctxt->myDoc);
11804
    ctxt->myDoc = NULL;
11805
11806
error:
11807
    xmlFreeInputStream(xmlCtxtPopInput(ctxt));
11808
11809
    return(ret);
11810
}
11811
11812
/**
11813
 * xmlIOParseDTD:
11814
 * @sax:  the SAX handler block or NULL
11815
 * @input:  an Input Buffer
11816
 * @enc:  the charset encoding if known
11817
 *
11818
 * DEPRECATED: Use xmlCtxtParseDtd.
11819
 *
11820
 * Load and parse a DTD
11821
 *
11822
 * Returns the resulting xmlDtdPtr or NULL in case of error.
11823
 * @input will be freed by the function in any case.
11824
 */
11825
11826
xmlDtdPtr
11827
xmlIOParseDTD(xmlSAXHandlerPtr sax, xmlParserInputBufferPtr input,
11828
        xmlCharEncoding enc) {
11829
    xmlDtdPtr ret = NULL;
11830
    xmlParserCtxtPtr ctxt;
11831
    xmlParserInputPtr pinput = NULL;
11832
11833
    if (input == NULL)
11834
  return(NULL);
11835
11836
    ctxt = xmlNewSAXParserCtxt(sax, NULL);
11837
    if (ctxt == NULL) {
11838
        xmlFreeParserInputBuffer(input);
11839
  return(NULL);
11840
    }
11841
    xmlCtxtSetOptions(ctxt, XML_PARSE_DTDLOAD);
11842
11843
    /*
11844
     * generate a parser input from the I/O handler
11845
     */
11846
11847
    pinput = xmlNewIOInputStream(ctxt, input, XML_CHAR_ENCODING_NONE);
11848
    if (pinput == NULL) {
11849
        xmlFreeParserInputBuffer(input);
11850
  xmlFreeParserCtxt(ctxt);
11851
  return(NULL);
11852
    }
11853
11854
    if (enc != XML_CHAR_ENCODING_NONE) {
11855
        xmlSwitchEncoding(ctxt, enc);
11856
    }
11857
11858
    ret = xmlCtxtParseDtd(ctxt, pinput, NULL, NULL);
11859
11860
    xmlFreeParserCtxt(ctxt);
11861
    return(ret);
11862
}
11863
11864
/**
11865
 * xmlSAXParseDTD:
11866
 * @sax:  the SAX handler block
11867
 * @ExternalID:  a NAME* containing the External ID of the DTD
11868
 * @SystemID:  a NAME* containing the URL to the DTD
11869
 *
11870
 * DEPRECATED: Use xmlCtxtParseDtd.
11871
 *
11872
 * Load and parse an external subset.
11873
 *
11874
 * Returns the resulting xmlDtdPtr or NULL in case of error.
11875
 */
11876
11877
xmlDtdPtr
11878
xmlSAXParseDTD(xmlSAXHandlerPtr sax, const xmlChar *ExternalID,
11879
                          const xmlChar *SystemID) {
11880
    xmlDtdPtr ret = NULL;
11881
    xmlParserCtxtPtr ctxt;
11882
    xmlParserInputPtr input = NULL;
11883
    xmlChar* systemIdCanonic;
11884
11885
    if ((ExternalID == NULL) && (SystemID == NULL)) return(NULL);
11886
11887
    ctxt = xmlNewSAXParserCtxt(sax, NULL);
11888
    if (ctxt == NULL) {
11889
  return(NULL);
11890
    }
11891
    xmlCtxtSetOptions(ctxt, XML_PARSE_DTDLOAD);
11892
11893
    /*
11894
     * Canonicalise the system ID
11895
     */
11896
    systemIdCanonic = xmlCanonicPath(SystemID);
11897
    if ((SystemID != NULL) && (systemIdCanonic == NULL)) {
11898
  xmlFreeParserCtxt(ctxt);
11899
  return(NULL);
11900
    }
11901
11902
    /*
11903
     * Ask the Entity resolver to load the damn thing
11904
     */
11905
11906
    if ((ctxt->sax != NULL) && (ctxt->sax->resolveEntity != NULL))
11907
  input = ctxt->sax->resolveEntity(ctxt->userData, ExternalID,
11908
                                   systemIdCanonic);
11909
    if (input == NULL) {
11910
  xmlFreeParserCtxt(ctxt);
11911
  if (systemIdCanonic != NULL)
11912
      xmlFree(systemIdCanonic);
11913
  return(NULL);
11914
    }
11915
11916
    if (input->filename == NULL)
11917
  input->filename = (char *) systemIdCanonic;
11918
    else
11919
  xmlFree(systemIdCanonic);
11920
11921
    ret = xmlCtxtParseDtd(ctxt, input, ExternalID, SystemID);
11922
11923
    xmlFreeParserCtxt(ctxt);
11924
    return(ret);
11925
}
11926
11927
11928
/**
11929
 * xmlParseDTD:
11930
 * @ExternalID:  a NAME* containing the External ID of the DTD
11931
 * @SystemID:  a NAME* containing the URL to the DTD
11932
 *
11933
 * Load and parse an external subset.
11934
 *
11935
 * Returns the resulting xmlDtdPtr or NULL in case of error.
11936
 */
11937
11938
xmlDtdPtr
11939
xmlParseDTD(const xmlChar *ExternalID, const xmlChar *SystemID) {
11940
    return(xmlSAXParseDTD(NULL, ExternalID, SystemID));
11941
}
11942
#endif /* LIBXML_VALID_ENABLED */
11943
11944
/************************************************************************
11945
 *                  *
11946
 *    Front ends when parsing an Entity     *
11947
 *                  *
11948
 ************************************************************************/
11949
11950
static xmlNodePtr
11951
xmlCtxtParseContentInternal(xmlParserCtxtPtr ctxt, xmlParserInputPtr input,
11952
47
                            int hasTextDecl, int buildTree) {
11953
47
    xmlNodePtr root = NULL;
11954
47
    xmlNodePtr list = NULL;
11955
47
    xmlChar *rootName = BAD_CAST "#root";
11956
47
    int result;
11957
11958
47
    if (buildTree) {
11959
47
        root = xmlNewDocNode(ctxt->myDoc, NULL, rootName, NULL);
11960
47
        if (root == NULL) {
11961
0
            xmlErrMemory(ctxt);
11962
0
            goto error;
11963
0
        }
11964
47
    }
11965
11966
47
    if (xmlCtxtPushInput(ctxt, input) < 0)
11967
0
        goto error;
11968
11969
47
    nameNsPush(ctxt, rootName, NULL, NULL, 0, 0);
11970
47
    spacePush(ctxt, -1);
11971
11972
47
    if (buildTree)
11973
47
        nodePush(ctxt, root);
11974
11975
47
    if (hasTextDecl) {
11976
0
        xmlDetectEncoding(ctxt);
11977
11978
        /*
11979
         * Parse a possible text declaration first
11980
         */
11981
0
        if ((CMP5(CUR_PTR, '<', '?', 'x', 'm', 'l')) &&
11982
0
            (IS_BLANK_CH(NXT(5)))) {
11983
0
            xmlParseTextDecl(ctxt);
11984
            /*
11985
             * An XML-1.0 document can't reference an entity not XML-1.0
11986
             */
11987
0
            if ((xmlStrEqual(ctxt->version, BAD_CAST "1.0")) &&
11988
0
                (!xmlStrEqual(ctxt->input->version, BAD_CAST "1.0"))) {
11989
0
                xmlFatalErrMsg(ctxt, XML_ERR_VERSION_MISMATCH,
11990
0
                               "Version mismatch between document and "
11991
0
                               "entity\n");
11992
0
            }
11993
0
        }
11994
0
    }
11995
11996
47
    xmlParseContentInternal(ctxt);
11997
11998
47
    if (ctxt->input->cur < ctxt->input->end)
11999
40
  xmlFatalErr(ctxt, XML_ERR_NOT_WELL_BALANCED, NULL);
12000
12001
47
    if ((ctxt->wellFormed) ||
12002
47
        ((ctxt->recovery) && (!xmlCtxtIsCatastrophicError(ctxt)))) {
12003
47
        if (root != NULL) {
12004
47
            xmlNodePtr cur;
12005
12006
            /*
12007
             * Unlink newly created node list.
12008
             */
12009
47
            list = root->children;
12010
47
            root->children = NULL;
12011
47
            root->last = NULL;
12012
282
            for (cur = list; cur != NULL; cur = cur->next)
12013
235
                cur->parent = NULL;
12014
47
        }
12015
47
    }
12016
12017
    /*
12018
     * Read the rest of the stream in case of errors. We want
12019
     * to account for the whole entity size.
12020
     */
12021
47
    do {
12022
47
        ctxt->input->cur = ctxt->input->end;
12023
47
        xmlParserShrink(ctxt);
12024
47
        result = xmlParserGrow(ctxt);
12025
47
    } while (result > 0);
12026
12027
47
    if (buildTree)
12028
47
        nodePop(ctxt);
12029
12030
47
    namePop(ctxt);
12031
47
    spacePop(ctxt);
12032
12033
47
    xmlCtxtPopInput(ctxt);
12034
12035
47
error:
12036
47
    xmlFreeNode(root);
12037
12038
47
    return(list);
12039
47
}
12040
12041
static void
12042
47
xmlCtxtParseEntity(xmlParserCtxtPtr ctxt, xmlEntityPtr ent) {
12043
47
    xmlParserInputPtr input;
12044
47
    xmlNodePtr list;
12045
47
    unsigned long consumed;
12046
47
    int isExternal;
12047
47
    int buildTree;
12048
47
    int oldMinNsIndex;
12049
47
    int oldNodelen, oldNodemem;
12050
12051
47
    isExternal = (ent->etype == XML_EXTERNAL_GENERAL_PARSED_ENTITY);
12052
47
    buildTree = (ctxt->node != NULL);
12053
12054
    /*
12055
     * Recursion check
12056
     */
12057
47
    if (ent->flags & XML_ENT_EXPANDING) {
12058
0
        xmlFatalErr(ctxt, XML_ERR_ENTITY_LOOP, NULL);
12059
0
        xmlHaltParser(ctxt);
12060
0
        goto error;
12061
0
    }
12062
12063
    /*
12064
     * Load entity
12065
     */
12066
47
    input = xmlNewEntityInputStream(ctxt, ent);
12067
47
    if (input == NULL)
12068
0
        goto error;
12069
12070
    /*
12071
     * When building a tree, we need to limit the scope of namespace
12072
     * declarations, so that entities don't reference xmlNs structs
12073
     * from the parent of a reference.
12074
     */
12075
47
    oldMinNsIndex = ctxt->nsdb->minNsIndex;
12076
47
    if (buildTree)
12077
47
        ctxt->nsdb->minNsIndex = ctxt->nsNr;
12078
12079
47
    oldNodelen = ctxt->nodelen;
12080
47
    oldNodemem = ctxt->nodemem;
12081
47
    ctxt->nodelen = 0;
12082
47
    ctxt->nodemem = 0;
12083
12084
    /*
12085
     * Parse content
12086
     *
12087
     * This initiates a recursive call chain:
12088
     *
12089
     * - xmlCtxtParseContentInternal
12090
     * - xmlParseContentInternal
12091
     * - xmlParseReference
12092
     * - xmlCtxtParseEntity
12093
     *
12094
     * The nesting depth is limited by the maximum number of inputs,
12095
     * see xmlCtxtPushInput.
12096
     *
12097
     * It's possible to make this non-recursive (minNsIndex must be
12098
     * stored in the input struct) at the expense of code readability.
12099
     */
12100
12101
47
    ent->flags |= XML_ENT_EXPANDING;
12102
12103
47
    list = xmlCtxtParseContentInternal(ctxt, input, isExternal, buildTree);
12104
12105
47
    ent->flags &= ~XML_ENT_EXPANDING;
12106
12107
47
    ctxt->nsdb->minNsIndex = oldMinNsIndex;
12108
47
    ctxt->nodelen = oldNodelen;
12109
47
    ctxt->nodemem = oldNodemem;
12110
12111
    /*
12112
     * Entity size accounting
12113
     */
12114
47
    consumed = input->consumed;
12115
47
    xmlSaturatedAddSizeT(&consumed, input->end - input->base);
12116
12117
47
    if ((ent->flags & XML_ENT_CHECKED) == 0)
12118
47
        xmlSaturatedAdd(&ent->expandedSize, consumed);
12119
12120
47
    if ((ent->flags & XML_ENT_PARSED) == 0) {
12121
47
        if (isExternal)
12122
0
            xmlSaturatedAdd(&ctxt->sizeentities, consumed);
12123
12124
47
        ent->children = list;
12125
12126
282
        while (list != NULL) {
12127
235
            list->parent = (xmlNodePtr) ent;
12128
12129
            /*
12130
             * Downstream code like the nginx xslt module can set
12131
             * ctxt->myDoc->extSubset to a separate DTD, so the entity
12132
             * might have a different or a NULL document.
12133
             */
12134
235
            if (list->doc != ent->doc)
12135
0
                xmlSetTreeDoc(list, ent->doc);
12136
12137
235
            if (list->next == NULL)
12138
47
                ent->last = list;
12139
235
            list = list->next;
12140
235
        }
12141
47
    } else {
12142
0
        xmlFreeNodeList(list);
12143
0
    }
12144
12145
47
    xmlFreeInputStream(input);
12146
12147
47
error:
12148
47
    ent->flags |= XML_ENT_PARSED | XML_ENT_CHECKED;
12149
47
}
12150
12151
/**
12152
 * xmlParseCtxtExternalEntity:
12153
 * @ctxt:  the existing parsing context
12154
 * @URL:  the URL for the entity to load
12155
 * @ID:  the System ID for the entity to load
12156
 * @listOut:  the return value for the set of parsed nodes
12157
 *
12158
 * Parse an external general entity within an existing parsing context
12159
 * An external general parsed entity is well-formed if it matches the
12160
 * production labeled extParsedEnt.
12161
 *
12162
 * [78] extParsedEnt ::= TextDecl? content
12163
 *
12164
 * Returns 0 if the entity is well formed, -1 in case of args problem and
12165
 *    the parser error code otherwise
12166
 */
12167
12168
int
12169
xmlParseCtxtExternalEntity(xmlParserCtxtPtr ctxt, const xmlChar *URL,
12170
0
                           const xmlChar *ID, xmlNodePtr *listOut) {
12171
0
    xmlParserInputPtr input;
12172
0
    xmlNodePtr list;
12173
12174
0
    if (listOut != NULL)
12175
0
        *listOut = NULL;
12176
12177
0
    if (ctxt == NULL)
12178
0
        return(XML_ERR_ARGUMENT);
12179
12180
0
    input = xmlLoadResource(ctxt, (char *) URL, (char *) ID,
12181
0
                            XML_RESOURCE_GENERAL_ENTITY);
12182
0
    if (input == NULL)
12183
0
        return(ctxt->errNo);
12184
12185
0
    xmlCtxtInitializeLate(ctxt);
12186
12187
0
    list = xmlCtxtParseContentInternal(ctxt, input, /* hasTextDecl */ 1, 1);
12188
0
    if (listOut != NULL)
12189
0
        *listOut = list;
12190
0
    else
12191
0
        xmlFreeNodeList(list);
12192
12193
0
    xmlFreeInputStream(input);
12194
0
    return(ctxt->errNo);
12195
0
}
12196
12197
#ifdef LIBXML_SAX1_ENABLED
12198
/**
12199
 * xmlParseExternalEntity:
12200
 * @doc:  the document the chunk pertains to
12201
 * @sax:  the SAX handler block (possibly NULL)
12202
 * @user_data:  The user data returned on SAX callbacks (possibly NULL)
12203
 * @depth:  Used for loop detection, use 0
12204
 * @URL:  the URL for the entity to load
12205
 * @ID:  the System ID for the entity to load
12206
 * @list:  the return value for the set of parsed nodes
12207
 *
12208
 * DEPRECATED: Use xmlParseCtxtExternalEntity.
12209
 *
12210
 * Parse an external general entity
12211
 * An external general parsed entity is well-formed if it matches the
12212
 * production labeled extParsedEnt.
12213
 *
12214
 * [78] extParsedEnt ::= TextDecl? content
12215
 *
12216
 * Returns 0 if the entity is well formed, -1 in case of args problem and
12217
 *    the parser error code otherwise
12218
 */
12219
12220
int
12221
xmlParseExternalEntity(xmlDocPtr doc, xmlSAXHandlerPtr sax, void *user_data,
12222
    int depth, const xmlChar *URL, const xmlChar *ID, xmlNodePtr *list) {
12223
    xmlParserCtxtPtr ctxt;
12224
    int ret;
12225
12226
    if (list != NULL)
12227
        *list = NULL;
12228
12229
    if (doc == NULL)
12230
        return(XML_ERR_ARGUMENT);
12231
12232
    ctxt = xmlNewSAXParserCtxt(sax, user_data);
12233
    if (ctxt == NULL)
12234
        return(XML_ERR_NO_MEMORY);
12235
12236
    ctxt->depth = depth;
12237
    ctxt->myDoc = doc;
12238
    ret = xmlParseCtxtExternalEntity(ctxt, URL, ID, list);
12239
12240
    xmlFreeParserCtxt(ctxt);
12241
    return(ret);
12242
}
12243
12244
/**
12245
 * xmlParseBalancedChunkMemory:
12246
 * @doc:  the document the chunk pertains to (must not be NULL)
12247
 * @sax:  the SAX handler block (possibly NULL)
12248
 * @user_data:  The user data returned on SAX callbacks (possibly NULL)
12249
 * @depth:  Used for loop detection, use 0
12250
 * @string:  the input string in UTF8 or ISO-Latin (zero terminated)
12251
 * @lst:  the return value for the set of parsed nodes
12252
 *
12253
 * Parse a well-balanced chunk of an XML document
12254
 * called by the parser
12255
 * The allowed sequence for the Well Balanced Chunk is the one defined by
12256
 * the content production in the XML grammar:
12257
 *
12258
 * [43] content ::= (element | CharData | Reference | CDSect | PI | Comment)*
12259
 *
12260
 * Returns 0 if the chunk is well balanced, -1 in case of args problem and
12261
 *    the parser error code otherwise
12262
 */
12263
12264
int
12265
xmlParseBalancedChunkMemory(xmlDocPtr doc, xmlSAXHandlerPtr sax,
12266
     void *user_data, int depth, const xmlChar *string, xmlNodePtr *lst) {
12267
    return xmlParseBalancedChunkMemoryRecover( doc, sax, user_data,
12268
                                                depth, string, lst, 0 );
12269
}
12270
#endif /* LIBXML_SAX1_ENABLED */
12271
12272
/**
12273
 * xmlCtxtParseContent:
12274
 * @ctxt:  parser context
12275
 * @input:  parser input
12276
 * @node:  target node or document
12277
 * @hasTextDecl:  whether to parse text declaration
12278
 *
12279
 * Parse a well-balanced chunk of XML matching the 'content' production.
12280
 *
12281
 * Namespaces in scope of @node and entities of @node's document are
12282
 * recognized. When validating, the DTD of @node's document is used.
12283
 *
12284
 * Always consumes @input even in error case.
12285
 *
12286
 * Available since 2.14.0.
12287
 *
12288
 * Returns a node list or NULL in case of error.
12289
 */
12290
xmlNodePtr
12291
xmlCtxtParseContent(xmlParserCtxtPtr ctxt, xmlParserInputPtr input,
12292
0
                    xmlNodePtr node, int hasTextDecl) {
12293
0
    xmlDocPtr doc;
12294
0
    xmlNodePtr cur, list = NULL;
12295
0
    int nsnr = 0;
12296
0
    xmlDictPtr oldDict;
12297
0
    int oldOptions, oldDictNames, oldLoadSubset;
12298
12299
0
    if ((ctxt == NULL) || (input == NULL) || (node == NULL)) {
12300
0
        xmlFatalErr(ctxt, XML_ERR_ARGUMENT, NULL);
12301
0
        goto exit;
12302
0
    }
12303
12304
0
    doc = node->doc;
12305
0
    if (doc == NULL) {
12306
0
        xmlFatalErr(ctxt, XML_ERR_ARGUMENT, NULL);
12307
0
        goto exit;
12308
0
    }
12309
12310
0
    switch (node->type) {
12311
0
        case XML_ELEMENT_NODE:
12312
0
        case XML_DOCUMENT_NODE:
12313
0
        case XML_HTML_DOCUMENT_NODE:
12314
0
            break;
12315
12316
0
        case XML_ATTRIBUTE_NODE:
12317
0
        case XML_TEXT_NODE:
12318
0
        case XML_CDATA_SECTION_NODE:
12319
0
        case XML_ENTITY_REF_NODE:
12320
0
        case XML_PI_NODE:
12321
0
        case XML_COMMENT_NODE:
12322
0
            for (cur = node->parent; cur != NULL; cur = node->parent) {
12323
0
                if ((cur->type == XML_ELEMENT_NODE) ||
12324
0
                    (cur->type == XML_DOCUMENT_NODE) ||
12325
0
                    (cur->type == XML_HTML_DOCUMENT_NODE)) {
12326
0
                    node = cur;
12327
0
                    break;
12328
0
                }
12329
0
            }
12330
0
            break;
12331
12332
0
        default:
12333
0
            xmlFatalErr(ctxt, XML_ERR_ARGUMENT, NULL);
12334
0
            goto exit;
12335
0
    }
12336
12337
0
#ifdef LIBXML_HTML_ENABLED
12338
0
    if (ctxt->html)
12339
0
        htmlCtxtReset(ctxt);
12340
0
    else
12341
0
#endif
12342
0
        xmlCtxtReset(ctxt);
12343
12344
0
    oldDict = ctxt->dict;
12345
0
    oldOptions = ctxt->options;
12346
0
    oldDictNames = ctxt->dictNames;
12347
0
    oldLoadSubset = ctxt->loadsubset;
12348
12349
    /*
12350
     * Use input doc's dict if present, else assure XML_PARSE_NODICT is set.
12351
     */
12352
0
    if (doc->dict != NULL) {
12353
0
        ctxt->dict = doc->dict;
12354
0
    } else {
12355
0
        ctxt->options |= XML_PARSE_NODICT;
12356
0
        ctxt->dictNames = 0;
12357
0
    }
12358
12359
    /*
12360
     * Disable IDs
12361
     */
12362
0
    ctxt->loadsubset |= XML_SKIP_IDS;
12363
12364
0
    ctxt->myDoc = doc;
12365
12366
0
#ifdef LIBXML_HTML_ENABLED
12367
0
    if (ctxt->html) {
12368
        /*
12369
         * When parsing in context, it makes no sense to add implied
12370
         * elements like html/body/etc...
12371
         */
12372
0
        ctxt->options |= HTML_PARSE_NOIMPLIED;
12373
12374
0
        list = htmlCtxtParseContentInternal(ctxt, input);
12375
0
    } else
12376
0
#endif
12377
0
    {
12378
0
        xmlCtxtInitializeLate(ctxt);
12379
12380
        /*
12381
         * initialize the SAX2 namespaces stack
12382
         */
12383
0
        cur = node;
12384
0
        while ((cur != NULL) && (cur->type == XML_ELEMENT_NODE)) {
12385
0
            xmlNsPtr ns = cur->nsDef;
12386
0
            xmlHashedString hprefix, huri;
12387
12388
0
            while (ns != NULL) {
12389
0
                hprefix = xmlDictLookupHashed(ctxt->dict, ns->prefix, -1);
12390
0
                huri = xmlDictLookupHashed(ctxt->dict, ns->href, -1);
12391
0
                if (xmlParserNsPush(ctxt, &hprefix, &huri, ns, 1) > 0)
12392
0
                    nsnr++;
12393
0
                ns = ns->next;
12394
0
            }
12395
0
            cur = cur->parent;
12396
0
        }
12397
12398
0
        list = xmlCtxtParseContentInternal(ctxt, input, hasTextDecl, 1);
12399
12400
0
        if (nsnr > 0)
12401
0
            xmlParserNsPop(ctxt, nsnr);
12402
0
    }
12403
12404
0
    ctxt->dict = oldDict;
12405
0
    ctxt->options = oldOptions;
12406
0
    ctxt->dictNames = oldDictNames;
12407
0
    ctxt->loadsubset = oldLoadSubset;
12408
0
    ctxt->myDoc = NULL;
12409
0
    ctxt->node = NULL;
12410
12411
0
exit:
12412
0
    xmlFreeInputStream(input);
12413
0
    return(list);
12414
0
}
12415
12416
/**
12417
 * xmlParseInNodeContext:
12418
 * @node:  the context node
12419
 * @data:  the input string
12420
 * @datalen:  the input string length in bytes
12421
 * @options:  a combination of xmlParserOption
12422
 * @listOut:  the return value for the set of parsed nodes
12423
 *
12424
 * Parse a well-balanced chunk of an XML document
12425
 * within the context (DTD, namespaces, etc ...) of the given node.
12426
 *
12427
 * The allowed sequence for the data is a Well Balanced Chunk defined by
12428
 * the content production in the XML grammar:
12429
 *
12430
 * [43] content ::= (element | CharData | Reference | CDSect | PI | Comment)*
12431
 *
12432
 * This function assumes the encoding of @node's document which is
12433
 * typically not what you want. A better alternative is
12434
 * xmlCtxtParseContent.
12435
 *
12436
 * Returns XML_ERR_OK if the chunk is well balanced, and the parser
12437
 * error code otherwise
12438
 */
12439
xmlParserErrors
12440
xmlParseInNodeContext(xmlNodePtr node, const char *data, int datalen,
12441
0
                      int options, xmlNodePtr *listOut) {
12442
0
    xmlParserCtxtPtr ctxt;
12443
0
    xmlParserInputPtr input;
12444
0
    xmlDocPtr doc;
12445
0
    xmlNodePtr list;
12446
0
    xmlParserErrors ret;
12447
12448
0
    if (listOut == NULL)
12449
0
        return(XML_ERR_INTERNAL_ERROR);
12450
0
    *listOut = NULL;
12451
12452
0
    if ((node == NULL) || (data == NULL) || (datalen < 0))
12453
0
        return(XML_ERR_INTERNAL_ERROR);
12454
12455
0
    doc = node->doc;
12456
0
    if (doc == NULL)
12457
0
        return(XML_ERR_INTERNAL_ERROR);
12458
12459
0
#ifdef LIBXML_HTML_ENABLED
12460
0
    if (doc->type == XML_HTML_DOCUMENT_NODE) {
12461
0
        ctxt = htmlNewParserCtxt();
12462
0
    }
12463
0
    else
12464
0
#endif
12465
0
        ctxt = xmlNewParserCtxt();
12466
12467
0
    if (ctxt == NULL)
12468
0
        return(XML_ERR_NO_MEMORY);
12469
12470
0
    input = xmlCtxtNewInputFromMemory(ctxt, NULL, data, datalen,
12471
0
                                      (const char *) doc->encoding,
12472
0
                                      XML_INPUT_BUF_STATIC);
12473
0
    if (input == NULL) {
12474
0
        xmlFreeParserCtxt(ctxt);
12475
0
        return(XML_ERR_NO_MEMORY);
12476
0
    }
12477
12478
0
    xmlCtxtUseOptions(ctxt, options);
12479
12480
0
    list = xmlCtxtParseContent(ctxt, input, node, /* hasTextDecl */ 0);
12481
12482
0
    if (list == NULL) {
12483
0
        ret = ctxt->errNo;
12484
0
        if (ret == XML_ERR_ARGUMENT)
12485
0
            ret = XML_ERR_INTERNAL_ERROR;
12486
0
    } else {
12487
0
        ret = XML_ERR_OK;
12488
0
        *listOut = list;
12489
0
    }
12490
12491
0
    xmlFreeParserCtxt(ctxt);
12492
12493
0
    return(ret);
12494
0
}
12495
12496
#ifdef LIBXML_SAX1_ENABLED
12497
/**
12498
 * xmlParseBalancedChunkMemoryRecover:
12499
 * @doc:  the document the chunk pertains to (must not be NULL)
12500
 * @sax:  the SAX handler block (possibly NULL)
12501
 * @user_data:  The user data returned on SAX callbacks (possibly NULL)
12502
 * @depth:  Used for loop detection, use 0
12503
 * @string:  the input string in UTF8 or ISO-Latin (zero terminated)
12504
 * @listOut:  the return value for the set of parsed nodes
12505
 * @recover: return nodes even if the data is broken (use 0)
12506
 *
12507
 * Parse a well-balanced chunk of an XML document
12508
 *
12509
 * The allowed sequence for the Well Balanced Chunk is the one defined by
12510
 * the content production in the XML grammar:
12511
 *
12512
 * [43] content ::= (element | CharData | Reference | CDSect | PI | Comment)*
12513
 *
12514
 * Returns 0 if the chunk is well balanced, or thehe parser error code
12515
 * otherwise.
12516
 *
12517
 * In case recover is set to 1, the nodelist will not be empty even if
12518
 * the parsed chunk is not well balanced, assuming the parsing succeeded to
12519
 * some extent.
12520
 */
12521
int
12522
xmlParseBalancedChunkMemoryRecover(xmlDocPtr doc, xmlSAXHandlerPtr sax,
12523
     void *user_data, int depth, const xmlChar *string, xmlNodePtr *listOut,
12524
     int recover) {
12525
    xmlParserCtxtPtr ctxt;
12526
    xmlParserInputPtr input;
12527
    xmlNodePtr list;
12528
    int ret;
12529
12530
    if (listOut != NULL)
12531
        *listOut = NULL;
12532
12533
    if (string == NULL)
12534
        return(XML_ERR_ARGUMENT);
12535
12536
    ctxt = xmlNewSAXParserCtxt(sax, user_data);
12537
    if (ctxt == NULL)
12538
        return(XML_ERR_NO_MEMORY);
12539
12540
    xmlCtxtInitializeLate(ctxt);
12541
12542
    ctxt->depth = depth;
12543
    ctxt->myDoc = doc;
12544
    if (recover) {
12545
        ctxt->options |= XML_PARSE_RECOVER;
12546
        ctxt->recovery = 1;
12547
    }
12548
12549
    input = xmlNewStringInputStream(ctxt, string);
12550
    if (input == NULL) {
12551
        ret = ctxt->errNo;
12552
        goto error;
12553
    }
12554
12555
    list = xmlCtxtParseContentInternal(ctxt, input, /* hasTextDecl */ 0, 1);
12556
    if (listOut != NULL)
12557
        *listOut = list;
12558
    else
12559
        xmlFreeNodeList(list);
12560
12561
    if (!ctxt->wellFormed)
12562
        ret = ctxt->errNo;
12563
    else
12564
        ret = XML_ERR_OK;
12565
12566
error:
12567
    xmlFreeInputStream(input);
12568
    xmlFreeParserCtxt(ctxt);
12569
    return(ret);
12570
}
12571
12572
/**
12573
 * xmlSAXParseEntity:
12574
 * @sax:  the SAX handler block
12575
 * @filename:  the filename
12576
 *
12577
 * DEPRECATED: Don't use.
12578
 *
12579
 * parse an XML external entity out of context and build a tree.
12580
 * It use the given SAX function block to handle the parsing callback.
12581
 * If sax is NULL, fallback to the default DOM tree building routines.
12582
 *
12583
 * [78] extParsedEnt ::= TextDecl? content
12584
 *
12585
 * This correspond to a "Well Balanced" chunk
12586
 *
12587
 * Returns the resulting document tree
12588
 */
12589
12590
xmlDocPtr
12591
xmlSAXParseEntity(xmlSAXHandlerPtr sax, const char *filename) {
12592
    xmlDocPtr ret;
12593
    xmlParserCtxtPtr ctxt;
12594
12595
    ctxt = xmlCreateFileParserCtxt(filename);
12596
    if (ctxt == NULL) {
12597
  return(NULL);
12598
    }
12599
    if (sax != NULL) {
12600
        if (sax->initialized == XML_SAX2_MAGIC) {
12601
            *ctxt->sax = *sax;
12602
        } else {
12603
            memset(ctxt->sax, 0, sizeof(*ctxt->sax));
12604
            memcpy(ctxt->sax, sax, sizeof(xmlSAXHandlerV1));
12605
        }
12606
        ctxt->userData = NULL;
12607
    }
12608
12609
    xmlParseExtParsedEnt(ctxt);
12610
12611
    if (ctxt->wellFormed) {
12612
  ret = ctxt->myDoc;
12613
    } else {
12614
        ret = NULL;
12615
        xmlFreeDoc(ctxt->myDoc);
12616
    }
12617
12618
    xmlFreeParserCtxt(ctxt);
12619
12620
    return(ret);
12621
}
12622
12623
/**
12624
 * xmlParseEntity:
12625
 * @filename:  the filename
12626
 *
12627
 * parse an XML external entity out of context and build a tree.
12628
 *
12629
 * [78] extParsedEnt ::= TextDecl? content
12630
 *
12631
 * This correspond to a "Well Balanced" chunk
12632
 *
12633
 * Returns the resulting document tree
12634
 */
12635
12636
xmlDocPtr
12637
xmlParseEntity(const char *filename) {
12638
    return(xmlSAXParseEntity(NULL, filename));
12639
}
12640
#endif /* LIBXML_SAX1_ENABLED */
12641
12642
/**
12643
 * xmlCreateEntityParserCtxt:
12644
 * @URL:  the entity URL
12645
 * @ID:  the entity PUBLIC ID
12646
 * @base:  a possible base for the target URI
12647
 *
12648
 * DEPRECATED: Don't use.
12649
 *
12650
 * Create a parser context for an external entity
12651
 * Automatic support for ZLIB/Compress compressed document is provided
12652
 * by default if found at compile-time.
12653
 *
12654
 * Returns the new parser context or NULL
12655
 */
12656
xmlParserCtxtPtr
12657
xmlCreateEntityParserCtxt(const xmlChar *URL, const xmlChar *ID,
12658
0
                    const xmlChar *base) {
12659
0
    xmlParserCtxtPtr ctxt;
12660
0
    xmlParserInputPtr input;
12661
0
    xmlChar *uri = NULL;
12662
12663
0
    ctxt = xmlNewParserCtxt();
12664
0
    if (ctxt == NULL)
12665
0
  return(NULL);
12666
12667
0
    if (base != NULL) {
12668
0
        if (xmlBuildURISafe(URL, base, &uri) < 0)
12669
0
            goto error;
12670
0
        if (uri != NULL)
12671
0
            URL = uri;
12672
0
    }
12673
12674
0
    input = xmlLoadResource(ctxt, (char *) URL, (char *) ID,
12675
0
                            XML_RESOURCE_UNKNOWN);
12676
0
    if (input == NULL)
12677
0
        goto error;
12678
12679
0
    if (xmlCtxtPushInput(ctxt, input) < 0) {
12680
0
        xmlFreeInputStream(input);
12681
0
        goto error;
12682
0
    }
12683
12684
0
    xmlFree(uri);
12685
0
    return(ctxt);
12686
12687
0
error:
12688
0
    xmlFree(uri);
12689
0
    xmlFreeParserCtxt(ctxt);
12690
0
    return(NULL);
12691
0
}
12692
12693
/************************************************************************
12694
 *                  *
12695
 *    Front ends when parsing from a file     *
12696
 *                  *
12697
 ************************************************************************/
12698
12699
/**
12700
 * xmlCreateURLParserCtxt:
12701
 * @filename:  the filename or URL
12702
 * @options:  a combination of xmlParserOption
12703
 *
12704
 * DEPRECATED: Use xmlNewParserCtxt and xmlCtxtReadFile.
12705
 *
12706
 * Create a parser context for a file or URL content.
12707
 * Automatic support for ZLIB/Compress compressed document is provided
12708
 * by default if found at compile-time and for file accesses
12709
 *
12710
 * Returns the new parser context or NULL
12711
 */
12712
xmlParserCtxtPtr
12713
xmlCreateURLParserCtxt(const char *filename, int options)
12714
0
{
12715
0
    xmlParserCtxtPtr ctxt;
12716
0
    xmlParserInputPtr input;
12717
12718
0
    ctxt = xmlNewParserCtxt();
12719
0
    if (ctxt == NULL)
12720
0
  return(NULL);
12721
12722
0
    options |= XML_PARSE_UNZIP;
12723
12724
0
    xmlCtxtUseOptions(ctxt, options);
12725
0
    ctxt->linenumbers = 1;
12726
12727
0
    input = xmlLoadResource(ctxt, filename, NULL, XML_RESOURCE_MAIN_DOCUMENT);
12728
0
    if (input == NULL) {
12729
0
  xmlFreeParserCtxt(ctxt);
12730
0
  return(NULL);
12731
0
    }
12732
0
    if (xmlCtxtPushInput(ctxt, input) < 0) {
12733
0
        xmlFreeInputStream(input);
12734
0
        xmlFreeParserCtxt(ctxt);
12735
0
        return(NULL);
12736
0
    }
12737
12738
0
    return(ctxt);
12739
0
}
12740
12741
/**
12742
 * xmlCreateFileParserCtxt:
12743
 * @filename:  the filename
12744
 *
12745
 * DEPRECATED: Use xmlNewParserCtxt and xmlCtxtReadFile.
12746
 *
12747
 * Create a parser context for a file content.
12748
 * Automatic support for ZLIB/Compress compressed document is provided
12749
 * by default if found at compile-time.
12750
 *
12751
 * Returns the new parser context or NULL
12752
 */
12753
xmlParserCtxtPtr
12754
xmlCreateFileParserCtxt(const char *filename)
12755
0
{
12756
0
    return(xmlCreateURLParserCtxt(filename, 0));
12757
0
}
12758
12759
#ifdef LIBXML_SAX1_ENABLED
12760
/**
12761
 * xmlSAXParseFileWithData:
12762
 * @sax:  the SAX handler block
12763
 * @filename:  the filename
12764
 * @recovery:  work in recovery mode, i.e. tries to read no Well Formed
12765
 *             documents
12766
 * @data:  the userdata
12767
 *
12768
 * DEPRECATED: Use xmlNewSAXParserCtxt and xmlCtxtReadFile.
12769
 *
12770
 * parse an XML file and build a tree. Automatic support for ZLIB/Compress
12771
 * compressed document is provided by default if found at compile-time.
12772
 * It use the given SAX function block to handle the parsing callback.
12773
 * If sax is NULL, fallback to the default DOM tree building routines.
12774
 *
12775
 * User data (void *) is stored within the parser context in the
12776
 * context's _private member, so it is available nearly everywhere in libxml
12777
 *
12778
 * Returns the resulting document tree
12779
 */
12780
12781
xmlDocPtr
12782
xmlSAXParseFileWithData(xmlSAXHandlerPtr sax, const char *filename,
12783
                        int recovery, void *data) {
12784
    xmlDocPtr ret = NULL;
12785
    xmlParserCtxtPtr ctxt;
12786
    xmlParserInputPtr input;
12787
12788
    ctxt = xmlNewSAXParserCtxt(sax, NULL);
12789
    if (ctxt == NULL)
12790
  return(NULL);
12791
12792
    if (data != NULL)
12793
  ctxt->_private = data;
12794
12795
    if (recovery) {
12796
        ctxt->options |= XML_PARSE_RECOVER;
12797
        ctxt->recovery = 1;
12798
    }
12799
12800
    if ((filename != NULL) && (filename[0] == '-') && (filename[1] == 0))
12801
        input = xmlCtxtNewInputFromFd(ctxt, filename, STDIN_FILENO, NULL, 0);
12802
    else
12803
        input = xmlCtxtNewInputFromUrl(ctxt, filename, NULL, NULL, 0);
12804
12805
    if (input != NULL)
12806
        ret = xmlCtxtParseDocument(ctxt, input);
12807
12808
    xmlFreeParserCtxt(ctxt);
12809
    return(ret);
12810
}
12811
12812
/**
12813
 * xmlSAXParseFile:
12814
 * @sax:  the SAX handler block
12815
 * @filename:  the filename
12816
 * @recovery:  work in recovery mode, i.e. tries to read no Well Formed
12817
 *             documents
12818
 *
12819
 * DEPRECATED: Use xmlNewSAXParserCtxt and xmlCtxtReadFile.
12820
 *
12821
 * parse an XML file and build a tree. Automatic support for ZLIB/Compress
12822
 * compressed document is provided by default if found at compile-time.
12823
 * It use the given SAX function block to handle the parsing callback.
12824
 * If sax is NULL, fallback to the default DOM tree building routines.
12825
 *
12826
 * Returns the resulting document tree
12827
 */
12828
12829
xmlDocPtr
12830
xmlSAXParseFile(xmlSAXHandlerPtr sax, const char *filename,
12831
                          int recovery) {
12832
    return(xmlSAXParseFileWithData(sax,filename,recovery,NULL));
12833
}
12834
12835
/**
12836
 * xmlRecoverDoc:
12837
 * @cur:  a pointer to an array of xmlChar
12838
 *
12839
 * DEPRECATED: Use xmlReadDoc with XML_PARSE_RECOVER.
12840
 *
12841
 * parse an XML in-memory document and build a tree.
12842
 * In the case the document is not Well Formed, a attempt to build a
12843
 * tree is tried anyway
12844
 *
12845
 * Returns the resulting document tree or NULL in case of failure
12846
 */
12847
12848
xmlDocPtr
12849
xmlRecoverDoc(const xmlChar *cur) {
12850
    return(xmlSAXParseDoc(NULL, cur, 1));
12851
}
12852
12853
/**
12854
 * xmlParseFile:
12855
 * @filename:  the filename
12856
 *
12857
 * DEPRECATED: Use xmlReadFile.
12858
 *
12859
 * parse an XML file and build a tree. Automatic support for ZLIB/Compress
12860
 * compressed document is provided by default if found at compile-time.
12861
 *
12862
 * Returns the resulting document tree if the file was wellformed,
12863
 * NULL otherwise.
12864
 */
12865
12866
xmlDocPtr
12867
xmlParseFile(const char *filename) {
12868
    return(xmlSAXParseFile(NULL, filename, 0));
12869
}
12870
12871
/**
12872
 * xmlRecoverFile:
12873
 * @filename:  the filename
12874
 *
12875
 * DEPRECATED: Use xmlReadFile with XML_PARSE_RECOVER.
12876
 *
12877
 * parse an XML file and build a tree. Automatic support for ZLIB/Compress
12878
 * compressed document is provided by default if found at compile-time.
12879
 * In the case the document is not Well Formed, it attempts to build
12880
 * a tree anyway
12881
 *
12882
 * Returns the resulting document tree or NULL in case of failure
12883
 */
12884
12885
xmlDocPtr
12886
xmlRecoverFile(const char *filename) {
12887
    return(xmlSAXParseFile(NULL, filename, 1));
12888
}
12889
12890
12891
/**
12892
 * xmlSetupParserForBuffer:
12893
 * @ctxt:  an XML parser context
12894
 * @buffer:  a xmlChar * buffer
12895
 * @filename:  a file name
12896
 *
12897
 * DEPRECATED: Don't use.
12898
 *
12899
 * Setup the parser context to parse a new buffer; Clears any prior
12900
 * contents from the parser context. The buffer parameter must not be
12901
 * NULL, but the filename parameter can be
12902
 */
12903
void
12904
xmlSetupParserForBuffer(xmlParserCtxtPtr ctxt, const xmlChar* buffer,
12905
                             const char* filename)
12906
{
12907
    xmlParserInputPtr input;
12908
12909
    if ((ctxt == NULL) || (buffer == NULL))
12910
        return;
12911
12912
    xmlClearParserCtxt(ctxt);
12913
12914
    input = xmlCtxtNewInputFromString(ctxt, filename, (const char *) buffer,
12915
                                      NULL, 0);
12916
    if (input == NULL)
12917
        return;
12918
    if (xmlCtxtPushInput(ctxt, input) < 0)
12919
        xmlFreeInputStream(input);
12920
}
12921
12922
/**
12923
 * xmlSAXUserParseFile:
12924
 * @sax:  a SAX handler
12925
 * @user_data:  The user data returned on SAX callbacks
12926
 * @filename:  a file name
12927
 *
12928
 * DEPRECATED: Use xmlNewSAXParserCtxt and xmlCtxtReadFile.
12929
 *
12930
 * parse an XML file and call the given SAX handler routines.
12931
 * Automatic support for ZLIB/Compress compressed document is provided
12932
 *
12933
 * Returns 0 in case of success or a error number otherwise
12934
 */
12935
int
12936
xmlSAXUserParseFile(xmlSAXHandlerPtr sax, void *user_data,
12937
                    const char *filename) {
12938
    int ret = 0;
12939
    xmlParserCtxtPtr ctxt;
12940
12941
    ctxt = xmlCreateFileParserCtxt(filename);
12942
    if (ctxt == NULL) return -1;
12943
    if (sax != NULL) {
12944
        if (sax->initialized == XML_SAX2_MAGIC) {
12945
            *ctxt->sax = *sax;
12946
        } else {
12947
            memset(ctxt->sax, 0, sizeof(*ctxt->sax));
12948
            memcpy(ctxt->sax, sax, sizeof(xmlSAXHandlerV1));
12949
        }
12950
  ctxt->userData = user_data;
12951
    }
12952
12953
    xmlParseDocument(ctxt);
12954
12955
    if (ctxt->wellFormed)
12956
  ret = 0;
12957
    else {
12958
        if (ctxt->errNo != 0)
12959
      ret = ctxt->errNo;
12960
  else
12961
      ret = -1;
12962
    }
12963
    if (ctxt->myDoc != NULL) {
12964
        xmlFreeDoc(ctxt->myDoc);
12965
  ctxt->myDoc = NULL;
12966
    }
12967
    xmlFreeParserCtxt(ctxt);
12968
12969
    return ret;
12970
}
12971
#endif /* LIBXML_SAX1_ENABLED */
12972
12973
/************************************************************************
12974
 *                  *
12975
 *    Front ends when parsing from memory     *
12976
 *                  *
12977
 ************************************************************************/
12978
12979
/**
12980
 * xmlCreateMemoryParserCtxt:
12981
 * @buffer:  a pointer to a char array
12982
 * @size:  the size of the array
12983
 *
12984
 * Create a parser context for an XML in-memory document. The input buffer
12985
 * must not contain a terminating null byte.
12986
 *
12987
 * Returns the new parser context or NULL
12988
 */
12989
xmlParserCtxtPtr
12990
0
xmlCreateMemoryParserCtxt(const char *buffer, int size) {
12991
0
    xmlParserCtxtPtr ctxt;
12992
0
    xmlParserInputPtr input;
12993
12994
0
    if (size < 0)
12995
0
  return(NULL);
12996
12997
0
    ctxt = xmlNewParserCtxt();
12998
0
    if (ctxt == NULL)
12999
0
  return(NULL);
13000
13001
0
    input = xmlCtxtNewInputFromMemory(ctxt, NULL, buffer, size, NULL, 0);
13002
0
    if (input == NULL) {
13003
0
  xmlFreeParserCtxt(ctxt);
13004
0
  return(NULL);
13005
0
    }
13006
0
    if (xmlCtxtPushInput(ctxt, input) < 0) {
13007
0
        xmlFreeInputStream(input);
13008
0
        xmlFreeParserCtxt(ctxt);
13009
0
        return(NULL);
13010
0
    }
13011
13012
0
    return(ctxt);
13013
0
}
13014
13015
#ifdef LIBXML_SAX1_ENABLED
13016
/**
13017
 * xmlSAXParseMemoryWithData:
13018
 * @sax:  the SAX handler block
13019
 * @buffer:  an pointer to a char array
13020
 * @size:  the size of the array
13021
 * @recovery:  work in recovery mode, i.e. tries to read no Well Formed
13022
 *             documents
13023
 * @data:  the userdata
13024
 *
13025
 * DEPRECATED: Use xmlNewSAXParserCtxt and xmlCtxtReadMemory.
13026
 *
13027
 * parse an XML in-memory block and use the given SAX function block
13028
 * to handle the parsing callback. If sax is NULL, fallback to the default
13029
 * DOM tree building routines.
13030
 *
13031
 * User data (void *) is stored within the parser context in the
13032
 * context's _private member, so it is available nearly everywhere in libxml
13033
 *
13034
 * Returns the resulting document tree
13035
 */
13036
13037
xmlDocPtr
13038
xmlSAXParseMemoryWithData(xmlSAXHandlerPtr sax, const char *buffer,
13039
                          int size, int recovery, void *data) {
13040
    xmlDocPtr ret = NULL;
13041
    xmlParserCtxtPtr ctxt;
13042
    xmlParserInputPtr input;
13043
13044
    if (size < 0)
13045
        return(NULL);
13046
13047
    ctxt = xmlNewSAXParserCtxt(sax, NULL);
13048
    if (ctxt == NULL)
13049
        return(NULL);
13050
13051
    if (data != NULL)
13052
  ctxt->_private=data;
13053
13054
    if (recovery) {
13055
        ctxt->options |= XML_PARSE_RECOVER;
13056
        ctxt->recovery = 1;
13057
    }
13058
13059
    input = xmlCtxtNewInputFromMemory(ctxt, NULL, buffer, size, NULL,
13060
                                      XML_INPUT_BUF_STATIC);
13061
13062
    if (input != NULL)
13063
        ret = xmlCtxtParseDocument(ctxt, input);
13064
13065
    xmlFreeParserCtxt(ctxt);
13066
    return(ret);
13067
}
13068
13069
/**
13070
 * xmlSAXParseMemory:
13071
 * @sax:  the SAX handler block
13072
 * @buffer:  an pointer to a char array
13073
 * @size:  the size of the array
13074
 * @recovery:  work in recovery mode, i.e. tries to read not Well Formed
13075
 *             documents
13076
 *
13077
 * DEPRECATED: Use xmlNewSAXParserCtxt and xmlCtxtReadMemory.
13078
 *
13079
 * parse an XML in-memory block and use the given SAX function block
13080
 * to handle the parsing callback. If sax is NULL, fallback to the default
13081
 * DOM tree building routines.
13082
 *
13083
 * Returns the resulting document tree
13084
 */
13085
xmlDocPtr
13086
xmlSAXParseMemory(xmlSAXHandlerPtr sax, const char *buffer,
13087
            int size, int recovery) {
13088
    return xmlSAXParseMemoryWithData(sax, buffer, size, recovery, NULL);
13089
}
13090
13091
/**
13092
 * xmlParseMemory:
13093
 * @buffer:  an pointer to a char array
13094
 * @size:  the size of the array
13095
 *
13096
 * DEPRECATED: Use xmlReadMemory.
13097
 *
13098
 * parse an XML in-memory block and build a tree.
13099
 *
13100
 * Returns the resulting document tree
13101
 */
13102
13103
xmlDocPtr xmlParseMemory(const char *buffer, int size) {
13104
   return(xmlSAXParseMemory(NULL, buffer, size, 0));
13105
}
13106
13107
/**
13108
 * xmlRecoverMemory:
13109
 * @buffer:  an pointer to a char array
13110
 * @size:  the size of the array
13111
 *
13112
 * DEPRECATED: Use xmlReadMemory with XML_PARSE_RECOVER.
13113
 *
13114
 * parse an XML in-memory block and build a tree.
13115
 * In the case the document is not Well Formed, an attempt to
13116
 * build a tree is tried anyway
13117
 *
13118
 * Returns the resulting document tree or NULL in case of error
13119
 */
13120
13121
xmlDocPtr xmlRecoverMemory(const char *buffer, int size) {
13122
   return(xmlSAXParseMemory(NULL, buffer, size, 1));
13123
}
13124
13125
/**
13126
 * xmlSAXUserParseMemory:
13127
 * @sax:  a SAX handler
13128
 * @user_data:  The user data returned on SAX callbacks
13129
 * @buffer:  an in-memory XML document input
13130
 * @size:  the length of the XML document in bytes
13131
 *
13132
 * DEPRECATED: Use xmlNewSAXParserCtxt and xmlCtxtReadMemory.
13133
 *
13134
 * parse an XML in-memory buffer and call the given SAX handler routines.
13135
 *
13136
 * Returns 0 in case of success or a error number otherwise
13137
 */
13138
int xmlSAXUserParseMemory(xmlSAXHandlerPtr sax, void *user_data,
13139
        const char *buffer, int size) {
13140
    int ret = 0;
13141
    xmlParserCtxtPtr ctxt;
13142
13143
    ctxt = xmlCreateMemoryParserCtxt(buffer, size);
13144
    if (ctxt == NULL) return -1;
13145
    if (sax != NULL) {
13146
        if (sax->initialized == XML_SAX2_MAGIC) {
13147
            *ctxt->sax = *sax;
13148
        } else {
13149
            memset(ctxt->sax, 0, sizeof(*ctxt->sax));
13150
            memcpy(ctxt->sax, sax, sizeof(xmlSAXHandlerV1));
13151
        }
13152
  ctxt->userData = user_data;
13153
    }
13154
13155
    xmlParseDocument(ctxt);
13156
13157
    if (ctxt->wellFormed)
13158
  ret = 0;
13159
    else {
13160
        if (ctxt->errNo != 0)
13161
      ret = ctxt->errNo;
13162
  else
13163
      ret = -1;
13164
    }
13165
    if (ctxt->myDoc != NULL) {
13166
        xmlFreeDoc(ctxt->myDoc);
13167
  ctxt->myDoc = NULL;
13168
    }
13169
    xmlFreeParserCtxt(ctxt);
13170
13171
    return ret;
13172
}
13173
#endif /* LIBXML_SAX1_ENABLED */
13174
13175
/**
13176
 * xmlCreateDocParserCtxt:
13177
 * @str:  a pointer to an array of xmlChar
13178
 *
13179
 * Creates a parser context for an XML in-memory document.
13180
 *
13181
 * Returns the new parser context or NULL
13182
 */
13183
xmlParserCtxtPtr
13184
0
xmlCreateDocParserCtxt(const xmlChar *str) {
13185
0
    xmlParserCtxtPtr ctxt;
13186
0
    xmlParserInputPtr input;
13187
13188
0
    ctxt = xmlNewParserCtxt();
13189
0
    if (ctxt == NULL)
13190
0
  return(NULL);
13191
13192
0
    input = xmlCtxtNewInputFromString(ctxt, NULL, (const char *) str, NULL, 0);
13193
0
    if (input == NULL) {
13194
0
  xmlFreeParserCtxt(ctxt);
13195
0
  return(NULL);
13196
0
    }
13197
0
    if (xmlCtxtPushInput(ctxt, input) < 0) {
13198
0
        xmlFreeInputStream(input);
13199
0
        xmlFreeParserCtxt(ctxt);
13200
0
        return(NULL);
13201
0
    }
13202
13203
0
    return(ctxt);
13204
0
}
13205
13206
#ifdef LIBXML_SAX1_ENABLED
13207
/**
13208
 * xmlSAXParseDoc:
13209
 * @sax:  the SAX handler block
13210
 * @cur:  a pointer to an array of xmlChar
13211
 * @recovery:  work in recovery mode, i.e. tries to read no Well Formed
13212
 *             documents
13213
 *
13214
 * DEPRECATED: Use xmlNewSAXParserCtxt and xmlCtxtReadDoc.
13215
 *
13216
 * parse an XML in-memory document and build a tree.
13217
 * It use the given SAX function block to handle the parsing callback.
13218
 * If sax is NULL, fallback to the default DOM tree building routines.
13219
 *
13220
 * Returns the resulting document tree
13221
 */
13222
13223
xmlDocPtr
13224
xmlSAXParseDoc(xmlSAXHandlerPtr sax, const xmlChar *cur, int recovery) {
13225
    xmlDocPtr ret;
13226
    xmlParserCtxtPtr ctxt;
13227
    xmlSAXHandlerPtr oldsax = NULL;
13228
13229
    if (cur == NULL) return(NULL);
13230
13231
13232
    ctxt = xmlCreateDocParserCtxt(cur);
13233
    if (ctxt == NULL) return(NULL);
13234
    if (sax != NULL) {
13235
        oldsax = ctxt->sax;
13236
        ctxt->sax = sax;
13237
        ctxt->userData = NULL;
13238
    }
13239
13240
    xmlParseDocument(ctxt);
13241
    if ((ctxt->wellFormed) || recovery) ret = ctxt->myDoc;
13242
    else {
13243
       ret = NULL;
13244
       xmlFreeDoc(ctxt->myDoc);
13245
       ctxt->myDoc = NULL;
13246
    }
13247
    if (sax != NULL)
13248
  ctxt->sax = oldsax;
13249
    xmlFreeParserCtxt(ctxt);
13250
13251
    return(ret);
13252
}
13253
13254
/**
13255
 * xmlParseDoc:
13256
 * @cur:  a pointer to an array of xmlChar
13257
 *
13258
 * DEPRECATED: Use xmlReadDoc.
13259
 *
13260
 * parse an XML in-memory document and build a tree.
13261
 *
13262
 * Returns the resulting document tree
13263
 */
13264
13265
xmlDocPtr
13266
xmlParseDoc(const xmlChar *cur) {
13267
    return(xmlSAXParseDoc(NULL, cur, 0));
13268
}
13269
#endif /* LIBXML_SAX1_ENABLED */
13270
13271
/************************************************************************
13272
 *                  *
13273
 *  New set (2.6.0) of simpler and more flexible APIs   *
13274
 *                  *
13275
 ************************************************************************/
13276
13277
/**
13278
 * DICT_FREE:
13279
 * @str:  a string
13280
 *
13281
 * Free a string if it is not owned by the "dict" dictionary in the
13282
 * current scope
13283
 */
13284
#define DICT_FREE(str)            \
13285
0
  if ((str) && ((!dict) ||       \
13286
0
      (xmlDictOwns(dict, (const xmlChar *)(str)) == 0)))  \
13287
0
      xmlFree((char *)(str));
13288
13289
/**
13290
 * xmlCtxtReset:
13291
 * @ctxt: an XML parser context
13292
 *
13293
 * Reset a parser context
13294
 */
13295
void
13296
xmlCtxtReset(xmlParserCtxtPtr ctxt)
13297
0
{
13298
0
    xmlParserInputPtr input;
13299
0
    xmlDictPtr dict;
13300
13301
0
    if (ctxt == NULL)
13302
0
        return;
13303
13304
0
    dict = ctxt->dict;
13305
13306
0
    while ((input = xmlCtxtPopInput(ctxt)) != NULL) { /* Non consuming */
13307
0
        xmlFreeInputStream(input);
13308
0
    }
13309
0
    ctxt->inputNr = 0;
13310
0
    ctxt->input = NULL;
13311
13312
0
    ctxt->spaceNr = 0;
13313
0
    if (ctxt->spaceTab != NULL) {
13314
0
  ctxt->spaceTab[0] = -1;
13315
0
  ctxt->space = &ctxt->spaceTab[0];
13316
0
    } else {
13317
0
        ctxt->space = NULL;
13318
0
    }
13319
13320
13321
0
    ctxt->nodeNr = 0;
13322
0
    ctxt->node = NULL;
13323
13324
0
    ctxt->nameNr = 0;
13325
0
    ctxt->name = NULL;
13326
13327
0
    ctxt->nsNr = 0;
13328
0
    xmlParserNsReset(ctxt->nsdb);
13329
13330
0
    DICT_FREE(ctxt->version);
13331
0
    ctxt->version = NULL;
13332
0
    DICT_FREE(ctxt->encoding);
13333
0
    ctxt->encoding = NULL;
13334
0
    DICT_FREE(ctxt->extSubURI);
13335
0
    ctxt->extSubURI = NULL;
13336
0
    DICT_FREE(ctxt->extSubSystem);
13337
0
    ctxt->extSubSystem = NULL;
13338
13339
0
    if (ctxt->directory != NULL) {
13340
0
        xmlFree(ctxt->directory);
13341
0
        ctxt->directory = NULL;
13342
0
    }
13343
13344
0
    if (ctxt->myDoc != NULL)
13345
0
        xmlFreeDoc(ctxt->myDoc);
13346
0
    ctxt->myDoc = NULL;
13347
13348
0
    ctxt->standalone = -1;
13349
0
    ctxt->hasExternalSubset = 0;
13350
0
    ctxt->hasPErefs = 0;
13351
0
    ctxt->html = 0;
13352
0
    ctxt->instate = XML_PARSER_START;
13353
13354
0
    ctxt->wellFormed = 1;
13355
0
    ctxt->nsWellFormed = 1;
13356
0
    ctxt->disableSAX = 0;
13357
0
    ctxt->valid = 1;
13358
0
    ctxt->record_info = 0;
13359
0
    ctxt->checkIndex = 0;
13360
0
    ctxt->endCheckState = 0;
13361
0
    ctxt->inSubset = 0;
13362
0
    ctxt->errNo = XML_ERR_OK;
13363
0
    ctxt->depth = 0;
13364
0
    ctxt->catalogs = NULL;
13365
0
    ctxt->sizeentities = 0;
13366
0
    ctxt->sizeentcopy = 0;
13367
0
    xmlInitNodeInfoSeq(&ctxt->node_seq);
13368
13369
0
    if (ctxt->attsDefault != NULL) {
13370
0
        xmlHashFree(ctxt->attsDefault, xmlHashDefaultDeallocator);
13371
0
        ctxt->attsDefault = NULL;
13372
0
    }
13373
0
    if (ctxt->attsSpecial != NULL) {
13374
0
        xmlHashFree(ctxt->attsSpecial, NULL);
13375
0
        ctxt->attsSpecial = NULL;
13376
0
    }
13377
13378
0
#ifdef LIBXML_CATALOG_ENABLED
13379
0
    if (ctxt->catalogs != NULL)
13380
0
  xmlCatalogFreeLocal(ctxt->catalogs);
13381
0
#endif
13382
0
    ctxt->nbErrors = 0;
13383
0
    ctxt->nbWarnings = 0;
13384
0
    if (ctxt->lastError.code != XML_ERR_OK)
13385
0
        xmlResetError(&ctxt->lastError);
13386
0
}
13387
13388
/**
13389
 * xmlCtxtResetPush:
13390
 * @ctxt: an XML parser context
13391
 * @chunk:  a pointer to an array of chars
13392
 * @size:  number of chars in the array
13393
 * @filename:  an optional file name or URI
13394
 * @encoding:  the document encoding, or NULL
13395
 *
13396
 * Reset a push parser context
13397
 *
13398
 * Returns 0 in case of success and 1 in case of error
13399
 */
13400
int
13401
xmlCtxtResetPush(xmlParserCtxtPtr ctxt, const char *chunk,
13402
                 int size, const char *filename, const char *encoding)
13403
0
{
13404
0
    xmlParserInputPtr input;
13405
13406
0
    if (ctxt == NULL)
13407
0
        return(1);
13408
13409
0
    xmlCtxtReset(ctxt);
13410
13411
0
    input = xmlNewPushInput(filename, chunk, size);
13412
0
    if (input == NULL)
13413
0
        return(1);
13414
13415
0
    if (xmlCtxtPushInput(ctxt, input) < 0) {
13416
0
        xmlFreeInputStream(input);
13417
0
        return(1);
13418
0
    }
13419
13420
0
    if (encoding != NULL)
13421
0
        xmlSwitchEncodingName(ctxt, encoding);
13422
13423
0
    return(0);
13424
0
}
13425
13426
static int
13427
xmlCtxtSetOptionsInternal(xmlParserCtxtPtr ctxt, int options, int keepMask)
13428
795
{
13429
795
    int allMask;
13430
13431
795
    if (ctxt == NULL)
13432
0
        return(-1);
13433
13434
    /*
13435
     * XInclude options aren't handled by the parser.
13436
     *
13437
     * XML_PARSE_XINCLUDE
13438
     * XML_PARSE_NOXINCNODE
13439
     * XML_PARSE_NOBASEFIX
13440
     */
13441
795
    allMask = XML_PARSE_RECOVER |
13442
795
              XML_PARSE_NOENT |
13443
795
              XML_PARSE_DTDLOAD |
13444
795
              XML_PARSE_DTDATTR |
13445
795
              XML_PARSE_DTDVALID |
13446
795
              XML_PARSE_NOERROR |
13447
795
              XML_PARSE_NOWARNING |
13448
795
              XML_PARSE_PEDANTIC |
13449
795
              XML_PARSE_NOBLANKS |
13450
#ifdef LIBXML_SAX1_ENABLED
13451
              XML_PARSE_SAX1 |
13452
#endif
13453
795
              XML_PARSE_NONET |
13454
795
              XML_PARSE_NODICT |
13455
795
              XML_PARSE_NSCLEAN |
13456
795
              XML_PARSE_NOCDATA |
13457
795
              XML_PARSE_COMPACT |
13458
795
              XML_PARSE_OLD10 |
13459
795
              XML_PARSE_HUGE |
13460
795
              XML_PARSE_OLDSAX |
13461
795
              XML_PARSE_IGNORE_ENC |
13462
795
              XML_PARSE_BIG_LINES |
13463
795
              XML_PARSE_NO_XXE |
13464
795
              XML_PARSE_UNZIP |
13465
795
              XML_PARSE_NO_SYS_CATALOG |
13466
795
              XML_PARSE_CATALOG_PI;
13467
13468
795
    ctxt->options = (ctxt->options & keepMask) | (options & allMask);
13469
13470
    /*
13471
     * For some options, struct members are historically the source
13472
     * of truth. The values are initalized from global variables and
13473
     * old code could also modify them directly. Several older API
13474
     * functions that don't take an options argument rely on these
13475
     * deprecated mechanisms.
13476
     *
13477
     * Once public access to struct members and the globals are
13478
     * disabled, we can use the options bitmask as source of
13479
     * truth, making all these struct members obsolete.
13480
     *
13481
     * The XML_DETECT_IDS flags is misnamed. It simply enables
13482
     * loading of the external subset.
13483
     */
13484
795
    ctxt->recovery = (options & XML_PARSE_RECOVER) ? 1 : 0;
13485
795
    ctxt->replaceEntities = (options & XML_PARSE_NOENT) ? 1 : 0;
13486
795
    ctxt->loadsubset = (options & XML_PARSE_DTDLOAD) ? XML_DETECT_IDS : 0;
13487
795
    ctxt->loadsubset |= (options & XML_PARSE_DTDATTR) ? XML_COMPLETE_ATTRS : 0;
13488
795
    ctxt->validate = (options & XML_PARSE_DTDVALID) ? 1 : 0;
13489
795
    ctxt->pedantic = (options & XML_PARSE_PEDANTIC) ? 1 : 0;
13490
795
    ctxt->keepBlanks = (options & XML_PARSE_NOBLANKS) ? 0 : 1;
13491
795
    ctxt->dictNames = (options & XML_PARSE_NODICT) ? 0 : 1;
13492
13493
795
    if (options & XML_PARSE_HUGE) {
13494
0
        if (ctxt->dict != NULL)
13495
0
            xmlDictSetLimit(ctxt->dict, 0);
13496
0
    }
13497
13498
795
    ctxt->linenumbers = 1;
13499
13500
795
    return(options & ~allMask);
13501
795
}
13502
13503
/**
13504
 * xmlCtxtSetOptions:
13505
 * @ctxt: an XML parser context
13506
 * @options:  a bitmask of xmlParserOption values
13507
 *
13508
 * Applies the options to the parser context. Unset options are
13509
 * cleared.
13510
 *
13511
 * Available since 2.13.0. With older versions, you can use
13512
 * xmlCtxtUseOptions.
13513
 *
13514
 * XML_PARSE_RECOVER
13515
 *
13516
 * Enable "recovery" mode which allows non-wellformed documents.
13517
 * How this mode behaves exactly is unspecified and may change
13518
 * without further notice. Use of this feature is DISCOURAGED.
13519
 *
13520
 * Not supported by the push parser.
13521
 *
13522
 * XML_PARSE_NOENT
13523
 *
13524
 * Despite the confusing name, this option enables substitution
13525
 * of entities. The resulting tree won't contain any entity
13526
 * reference nodes.
13527
 *
13528
 * This option also enables loading of external entities (both
13529
 * general and parameter entities) which is dangerous. If you
13530
 * process untrusted data, it's recommended to set the
13531
 * XML_PARSE_NO_XXE option to disable loading of external
13532
 * entities.
13533
 *
13534
 * XML_PARSE_DTDLOAD
13535
 *
13536
 * Enables loading of an external DTD and the loading and
13537
 * substitution of external parameter entities. Has no effect
13538
 * if XML_PARSE_NO_XXE is set.
13539
 *
13540
 * XML_PARSE_DTDATTR
13541
 *
13542
 * Adds default attributes from the DTD to the result document.
13543
 *
13544
 * Implies XML_PARSE_DTDLOAD, but loading of external content
13545
 * can be disabled with XML_PARSE_NO_XXE.
13546
 *
13547
 * XML_PARSE_DTDVALID
13548
 *
13549
 * This option enables DTD validation which requires to load
13550
 * external DTDs and external entities (both general and
13551
 * parameter entities) unless XML_PARSE_NO_XXE was set.
13552
 *
13553
 * XML_PARSE_NO_XXE
13554
 *
13555
 * Disables loading of external DTDs or entities.
13556
 *
13557
 * Available since 2.13.0.
13558
 *
13559
 * XML_PARSE_NOERROR
13560
 *
13561
 * Disable error and warning reports to the error handlers.
13562
 * Errors are still accessible with xmlCtxtGetLastError.
13563
 *
13564
 * XML_PARSE_NOWARNING
13565
 *
13566
 * Disable warning reports.
13567
 *
13568
 * XML_PARSE_PEDANTIC
13569
 *
13570
 * Enable some pedantic warnings.
13571
 *
13572
 * XML_PARSE_NOBLANKS
13573
 *
13574
 * Remove some whitespace from the result document. Where to
13575
 * remove whitespace depends on DTD element declarations or a
13576
 * broken heuristic with unfixable bugs. Use of this option is
13577
 * DISCOURAGED.
13578
 *
13579
 * Not supported by the push parser.
13580
 *
13581
 * XML_PARSE_SAX1
13582
 *
13583
 * Always invoke the deprecated SAX1 startElement and endElement
13584
 * handlers. This option is DEPRECATED.
13585
 *
13586
 * XML_PARSE_NONET
13587
 *
13588
 * Disable network access with the builtin HTTP client.
13589
 *
13590
 * XML_PARSE_NODICT
13591
 *
13592
 * Create a document without interned strings, making all
13593
 * strings separate memory allocations.
13594
 *
13595
 * XML_PARSE_NSCLEAN
13596
 *
13597
 * Remove redundant namespace declarations from the result
13598
 * document.
13599
 *
13600
 * XML_PARSE_NOCDATA
13601
 *
13602
 * Output normal text nodes instead of CDATA nodes.
13603
 *
13604
 * XML_PARSE_COMPACT
13605
 *
13606
 * Store small strings directly in the node struct to save
13607
 * memory.
13608
 *
13609
 * XML_PARSE_OLD10
13610
 *
13611
 * Use old Name productions from before XML 1.0 Fifth Edition.
13612
 * This options is DEPRECATED.
13613
 *
13614
 * XML_PARSE_HUGE
13615
 *
13616
 * Relax some internal limits.
13617
 *
13618
 * Maximum size of text nodes, tags, comments, processing instructions,
13619
 * CDATA sections, entity values
13620
 *
13621
 * normal: 10M
13622
 * huge:    1B
13623
 *
13624
 * Maximum size of names, system literals, pubid literals
13625
 *
13626
 * normal: 50K
13627
 * huge:   10M
13628
 *
13629
 * Maximum nesting depth of elements
13630
 *
13631
 * normal:  256
13632
 * huge:   2048
13633
 *
13634
 * Maximum nesting depth of entities
13635
 *
13636
 * normal: 20
13637
 * huge:   40
13638
 *
13639
 * XML_PARSE_OLDSAX
13640
 *
13641
 * Enable an unspecified legacy mode for SAX parsers. This
13642
 * option is DEPRECATED.
13643
 *
13644
 * XML_PARSE_IGNORE_ENC
13645
 *
13646
 * Ignore the encoding in the XML declaration. This option is
13647
 * mostly unneeded these days. The only effect is to enforce
13648
 * UTF-8 decoding of ASCII-like data.
13649
 *
13650
 * XML_PARSE_BIG_LINES
13651
 *
13652
 * Enable reporting of line numbers larger than 65535.
13653
 *
13654
 * XML_PARSE_UNZIP
13655
 *
13656
 * Enable input decompression. Setting this option is discouraged
13657
 * to avoid zip bombs.
13658
 *
13659
 * Available since 2.14.0.
13660
 *
13661
 * XML_PARSE_NO_SYS_CATALOG
13662
 *
13663
 * Disables the global system XML catalog.
13664
 *
13665
 * Available since 2.14.0.
13666
 *
13667
 * XML_PARSE_CATALOG_PI
13668
 *
13669
 * Enable XML catalog processing instructions.
13670
 *
13671
 * Available since 2.14.0.
13672
 *
13673
 * Returns 0 in case of success, the set of unknown or unimplemented options
13674
 *         in case of error.
13675
 */
13676
int
13677
xmlCtxtSetOptions(xmlParserCtxtPtr ctxt, int options)
13678
0
{
13679
0
#ifdef LIBXML_HTML_ENABLED
13680
0
    if ((ctxt != NULL) && (ctxt->html))
13681
0
        return(htmlCtxtSetOptions(ctxt, options));
13682
0
#endif
13683
13684
0
    return(xmlCtxtSetOptionsInternal(ctxt, options, 0));
13685
0
}
13686
13687
/**
13688
 * xmlCtxtGetOptions:
13689
 * @ctxt: an XML parser context
13690
 *
13691
 * Get the current options of the parser context.
13692
 *
13693
 * Available since 2.14.0.
13694
 *
13695
 * Returns the current options set in the parser context, or -1 if ctxt is NULL.
13696
 */
13697
int
13698
xmlCtxtGetOptions(xmlParserCtxtPtr ctxt)
13699
0
{
13700
0
    if (ctxt == NULL)
13701
0
        return(-1);
13702
13703
0
    return(ctxt->options);
13704
0
}
13705
13706
/**
13707
 * xmlCtxtUseOptions:
13708
 * @ctxt: an XML parser context
13709
 * @options:  a combination of xmlParserOption
13710
 *
13711
 * DEPRECATED: Use xmlCtxtSetOptions.
13712
 *
13713
 * Applies the options to the parser context. The following options
13714
 * are never cleared and can only be enabled:
13715
 *
13716
 * XML_PARSE_NOERROR
13717
 * XML_PARSE_NOWARNING
13718
 * XML_PARSE_NONET
13719
 * XML_PARSE_NSCLEAN
13720
 * XML_PARSE_NOCDATA
13721
 * XML_PARSE_COMPACT
13722
 * XML_PARSE_OLD10
13723
 * XML_PARSE_HUGE
13724
 * XML_PARSE_OLDSAX
13725
 * XML_PARSE_IGNORE_ENC
13726
 * XML_PARSE_BIG_LINES
13727
 *
13728
 * Returns 0 in case of success, the set of unknown or unimplemented options
13729
 *         in case of error.
13730
 */
13731
int
13732
xmlCtxtUseOptions(xmlParserCtxtPtr ctxt, int options)
13733
795
{
13734
795
    int keepMask;
13735
13736
795
#ifdef LIBXML_HTML_ENABLED
13737
795
    if ((ctxt != NULL) && (ctxt->html))
13738
0
        return(htmlCtxtUseOptions(ctxt, options));
13739
795
#endif
13740
13741
    /*
13742
     * For historic reasons, some options can only be enabled.
13743
     */
13744
795
    keepMask = XML_PARSE_NOERROR |
13745
795
               XML_PARSE_NOWARNING |
13746
795
               XML_PARSE_NONET |
13747
795
               XML_PARSE_NSCLEAN |
13748
795
               XML_PARSE_NOCDATA |
13749
795
               XML_PARSE_COMPACT |
13750
795
               XML_PARSE_OLD10 |
13751
795
               XML_PARSE_HUGE |
13752
795
               XML_PARSE_OLDSAX |
13753
795
               XML_PARSE_IGNORE_ENC |
13754
795
               XML_PARSE_BIG_LINES;
13755
13756
795
    return(xmlCtxtSetOptionsInternal(ctxt, options, keepMask));
13757
795
}
13758
13759
/**
13760
 * xmlCtxtSetMaxAmplification:
13761
 * @ctxt: an XML parser context
13762
 * @maxAmpl:  maximum amplification factor
13763
 *
13764
 * To protect against exponential entity expansion ("billion laughs"), the
13765
 * size of serialized output is (roughly) limited to the input size
13766
 * multiplied by this factor. The default value is 5.
13767
 *
13768
 * When working with documents making heavy use of entity expansion, it can
13769
 * be necessary to increase the value. For security reasons, this should only
13770
 * be considered when processing trusted input.
13771
 */
13772
void
13773
xmlCtxtSetMaxAmplification(xmlParserCtxtPtr ctxt, unsigned maxAmpl)
13774
0
{
13775
0
    ctxt->maxAmpl = maxAmpl;
13776
0
}
13777
13778
/**
13779
 * xmlCtxtParseDocument:
13780
 * @ctxt:  an XML parser context
13781
 * @input:  parser input
13782
 *
13783
 * Parse an XML document and return the resulting document tree.
13784
 * Takes ownership of the input object.
13785
 *
13786
 * Available since 2.13.0.
13787
 *
13788
 * Returns the resulting document tree or NULL
13789
 */
13790
xmlDocPtr
13791
xmlCtxtParseDocument(xmlParserCtxtPtr ctxt, xmlParserInputPtr input)
13792
793
{
13793
793
    xmlDocPtr ret = NULL;
13794
13795
793
    if ((ctxt == NULL) || (input == NULL)) {
13796
0
        xmlFatalErr(ctxt, XML_ERR_ARGUMENT, NULL);
13797
0
        xmlFreeInputStream(input);
13798
0
        return(NULL);
13799
0
    }
13800
13801
    /* assert(ctxt->inputNr == 0); */
13802
793
    while (ctxt->inputNr > 0)
13803
0
        xmlFreeInputStream(xmlCtxtPopInput(ctxt));
13804
13805
793
    if (xmlCtxtPushInput(ctxt, input) < 0) {
13806
0
        xmlFreeInputStream(input);
13807
0
        return(NULL);
13808
0
    }
13809
13810
793
    xmlParseDocument(ctxt);
13811
13812
793
    ret = xmlCtxtGetDocument(ctxt);
13813
13814
    /* assert(ctxt->inputNr == 1); */
13815
1.58k
    while (ctxt->inputNr > 0)
13816
793
        xmlFreeInputStream(xmlCtxtPopInput(ctxt));
13817
13818
793
    return(ret);
13819
793
}
13820
13821
/**
13822
 * xmlReadDoc:
13823
 * @cur:  a pointer to a zero terminated string
13824
 * @URL:  base URL (optional)
13825
 * @encoding:  the document encoding (optional)
13826
 * @options:  a combination of xmlParserOption
13827
 *
13828
 * Convenience function to parse an XML document from a
13829
 * zero-terminated string.
13830
 *
13831
 * See xmlCtxtReadDoc for details.
13832
 *
13833
 * Returns the resulting document tree
13834
 */
13835
xmlDocPtr
13836
xmlReadDoc(const xmlChar *cur, const char *URL, const char *encoding,
13837
           int options)
13838
0
{
13839
0
    xmlParserCtxtPtr ctxt;
13840
0
    xmlParserInputPtr input;
13841
0
    xmlDocPtr doc = NULL;
13842
13843
0
    ctxt = xmlNewParserCtxt();
13844
0
    if (ctxt == NULL)
13845
0
        return(NULL);
13846
13847
0
    xmlCtxtUseOptions(ctxt, options);
13848
13849
0
    input = xmlCtxtNewInputFromString(ctxt, URL, (const char *) cur, encoding,
13850
0
                                      XML_INPUT_BUF_STATIC);
13851
13852
0
    if (input != NULL)
13853
0
        doc = xmlCtxtParseDocument(ctxt, input);
13854
13855
0
    xmlFreeParserCtxt(ctxt);
13856
0
    return(doc);
13857
0
}
13858
13859
/**
13860
 * xmlReadFile:
13861
 * @filename:  a file or URL
13862
 * @encoding:  the document encoding (optional)
13863
 * @options:  a combination of xmlParserOption
13864
 *
13865
 * Convenience function to parse an XML file from the filesystem,
13866
 * the network or a global user-define resource loader.
13867
 *
13868
 * This function always enables the XML_PARSE_UNZIP option for
13869
 * backward compatibility. If a "-" filename is passed, it will
13870
 * read from stdin. Both of these features are potentially
13871
 * insecure and might be removed from later versions.
13872
 *
13873
 * See xmlCtxtReadFile for details.
13874
 *
13875
 * Returns the resulting document tree
13876
 */
13877
xmlDocPtr
13878
xmlReadFile(const char *filename, const char *encoding, int options)
13879
0
{
13880
0
    xmlParserCtxtPtr ctxt;
13881
0
    xmlParserInputPtr input;
13882
0
    xmlDocPtr doc = NULL;
13883
13884
0
    ctxt = xmlNewParserCtxt();
13885
0
    if (ctxt == NULL)
13886
0
        return(NULL);
13887
13888
0
    options |= XML_PARSE_UNZIP;
13889
13890
0
    xmlCtxtUseOptions(ctxt, options);
13891
13892
    /*
13893
     * Backward compatibility for users of command line utilities like
13894
     * xmlstarlet expecting "-" to mean stdin. This is dangerous and
13895
     * should be removed at some point.
13896
     */
13897
0
    if ((filename != NULL) && (filename[0] == '-') && (filename[1] == 0))
13898
0
        input = xmlCtxtNewInputFromFd(ctxt, filename, STDIN_FILENO,
13899
0
                                      encoding, 0);
13900
0
    else
13901
0
        input = xmlCtxtNewInputFromUrl(ctxt, filename, NULL, encoding, 0);
13902
13903
0
    if (input != NULL)
13904
0
        doc = xmlCtxtParseDocument(ctxt, input);
13905
13906
0
    xmlFreeParserCtxt(ctxt);
13907
0
    return(doc);
13908
0
}
13909
13910
/**
13911
 * xmlReadMemory:
13912
 * @buffer:  a pointer to a char array
13913
 * @size:  the size of the array
13914
 * @url:  base URL (optional)
13915
 * @encoding:  the document encoding (optional)
13916
 * @options:  a combination of xmlParserOption
13917
 *
13918
 * Parse an XML in-memory document and build a tree. The input buffer must
13919
 * not contain a terminating null byte.
13920
 *
13921
 * See xmlCtxtReadMemory for details.
13922
 *
13923
 * Returns the resulting document tree
13924
 */
13925
xmlDocPtr
13926
xmlReadMemory(const char *buffer, int size, const char *url,
13927
              const char *encoding, int options)
13928
795
{
13929
795
    xmlParserCtxtPtr ctxt;
13930
795
    xmlParserInputPtr input;
13931
795
    xmlDocPtr doc = NULL;
13932
13933
795
    if (size < 0)
13934
0
  return(NULL);
13935
13936
795
    ctxt = xmlNewParserCtxt();
13937
795
    if (ctxt == NULL)
13938
0
        return(NULL);
13939
13940
795
    xmlCtxtUseOptions(ctxt, options);
13941
13942
795
    input = xmlCtxtNewInputFromMemory(ctxt, url, buffer, size, encoding,
13943
795
                                      XML_INPUT_BUF_STATIC);
13944
13945
795
    if (input != NULL)
13946
793
        doc = xmlCtxtParseDocument(ctxt, input);
13947
13948
795
    xmlFreeParserCtxt(ctxt);
13949
795
    return(doc);
13950
795
}
13951
13952
/**
13953
 * xmlReadFd:
13954
 * @fd:  an open file descriptor
13955
 * @URL:  base URL (optional)
13956
 * @encoding:  the document encoding (optional)
13957
 * @options:  a combination of xmlParserOption
13958
 *
13959
 * Parse an XML from a file descriptor and build a tree.
13960
 *
13961
 * See xmlCtxtReadFd for details.
13962
 *
13963
 * NOTE that the file descriptor will not be closed when the
13964
 * context is freed or reset.
13965
 *
13966
 * Returns the resulting document tree
13967
 */
13968
xmlDocPtr
13969
xmlReadFd(int fd, const char *URL, const char *encoding, int options)
13970
0
{
13971
0
    xmlParserCtxtPtr ctxt;
13972
0
    xmlParserInputPtr input;
13973
0
    xmlDocPtr doc = NULL;
13974
13975
0
    ctxt = xmlNewParserCtxt();
13976
0
    if (ctxt == NULL)
13977
0
        return(NULL);
13978
13979
0
    xmlCtxtUseOptions(ctxt, options);
13980
13981
0
    input = xmlCtxtNewInputFromFd(ctxt, URL, fd, encoding, 0);
13982
13983
0
    if (input != NULL)
13984
0
        doc = xmlCtxtParseDocument(ctxt, input);
13985
13986
0
    xmlFreeParserCtxt(ctxt);
13987
0
    return(doc);
13988
0
}
13989
13990
/**
13991
 * xmlReadIO:
13992
 * @ioread:  an I/O read function
13993
 * @ioclose:  an I/O close function (optional)
13994
 * @ioctx:  an I/O handler
13995
 * @URL:  base URL (optional)
13996
 * @encoding:  the document encoding (optional)
13997
 * @options:  a combination of xmlParserOption
13998
 *
13999
 * Parse an XML document from I/O functions and context and build a tree.
14000
 *
14001
 * See xmlCtxtReadIO for details.
14002
 *
14003
 * Returns the resulting document tree
14004
 */
14005
xmlDocPtr
14006
xmlReadIO(xmlInputReadCallback ioread, xmlInputCloseCallback ioclose,
14007
          void *ioctx, const char *URL, const char *encoding, int options)
14008
0
{
14009
0
    xmlParserCtxtPtr ctxt;
14010
0
    xmlParserInputPtr input;
14011
0
    xmlDocPtr doc = NULL;
14012
14013
0
    ctxt = xmlNewParserCtxt();
14014
0
    if (ctxt == NULL)
14015
0
        return(NULL);
14016
14017
0
    xmlCtxtUseOptions(ctxt, options);
14018
14019
0
    input = xmlCtxtNewInputFromIO(ctxt, URL, ioread, ioclose, ioctx,
14020
0
                                  encoding, 0);
14021
14022
0
    if (input != NULL)
14023
0
        doc = xmlCtxtParseDocument(ctxt, input);
14024
14025
0
    xmlFreeParserCtxt(ctxt);
14026
0
    return(doc);
14027
0
}
14028
14029
/**
14030
 * xmlCtxtReadDoc:
14031
 * @ctxt:  an XML parser context
14032
 * @str:  a pointer to a zero terminated string
14033
 * @URL:  base URL (optional)
14034
 * @encoding:  the document encoding (optional)
14035
 * @options:  a combination of xmlParserOption
14036
 *
14037
 * Parse an XML in-memory document and build a tree.
14038
 *
14039
 * @URL is used as base to resolve external entities and for error
14040
 * reporting.
14041
 *
14042
 * See xmlCtxtUseOptions for details.
14043
 *
14044
 * Returns the resulting document tree
14045
 */
14046
xmlDocPtr
14047
xmlCtxtReadDoc(xmlParserCtxtPtr ctxt, const xmlChar *str,
14048
               const char *URL, const char *encoding, int options)
14049
0
{
14050
0
    xmlParserInputPtr input;
14051
14052
0
    if (ctxt == NULL)
14053
0
        return(NULL);
14054
14055
0
    xmlCtxtReset(ctxt);
14056
0
    xmlCtxtUseOptions(ctxt, options);
14057
14058
0
    input = xmlCtxtNewInputFromString(ctxt, URL, (const char *) str, encoding,
14059
0
                                      XML_INPUT_BUF_STATIC);
14060
0
    if (input == NULL)
14061
0
        return(NULL);
14062
14063
0
    return(xmlCtxtParseDocument(ctxt, input));
14064
0
}
14065
14066
/**
14067
 * xmlCtxtReadFile:
14068
 * @ctxt:  an XML parser context
14069
 * @filename:  a file or URL
14070
 * @encoding:  the document encoding (optional)
14071
 * @options:  a combination of xmlParserOption
14072
 *
14073
 * Parse an XML file from the filesystem, the network or a user-defined
14074
 * resource loader.
14075
 *
14076
 * This function always enables the XML_PARSE_UNZIP option for
14077
 * backward compatibility. This feature is potentially insecure
14078
 * and might be removed from later versions.
14079
 *
14080
 * Returns the resulting document tree
14081
 */
14082
xmlDocPtr
14083
xmlCtxtReadFile(xmlParserCtxtPtr ctxt, const char *filename,
14084
                const char *encoding, int options)
14085
0
{
14086
0
    xmlParserInputPtr input;
14087
14088
0
    if (ctxt == NULL)
14089
0
        return(NULL);
14090
14091
0
    options |= XML_PARSE_UNZIP;
14092
14093
0
    xmlCtxtReset(ctxt);
14094
0
    xmlCtxtUseOptions(ctxt, options);
14095
14096
0
    input = xmlCtxtNewInputFromUrl(ctxt, filename, NULL, encoding, 0);
14097
0
    if (input == NULL)
14098
0
        return(NULL);
14099
14100
0
    return(xmlCtxtParseDocument(ctxt, input));
14101
0
}
14102
14103
/**
14104
 * xmlCtxtReadMemory:
14105
 * @ctxt:  an XML parser context
14106
 * @buffer:  a pointer to a char array
14107
 * @size:  the size of the array
14108
 * @URL:  base URL (optional)
14109
 * @encoding:  the document encoding (optional)
14110
 * @options:  a combination of xmlParserOption
14111
 *
14112
 * Parse an XML in-memory document and build a tree. The input buffer must
14113
 * not contain a terminating null byte.
14114
 *
14115
 * @URL is used as base to resolve external entities and for error
14116
 * reporting.
14117
 *
14118
 * See xmlCtxtUseOptions for details.
14119
 *
14120
 * Returns the resulting document tree
14121
 */
14122
xmlDocPtr
14123
xmlCtxtReadMemory(xmlParserCtxtPtr ctxt, const char *buffer, int size,
14124
                  const char *URL, const char *encoding, int options)
14125
0
{
14126
0
    xmlParserInputPtr input;
14127
14128
0
    if ((ctxt == NULL) || (size < 0))
14129
0
        return(NULL);
14130
14131
0
    xmlCtxtReset(ctxt);
14132
0
    xmlCtxtUseOptions(ctxt, options);
14133
14134
0
    input = xmlCtxtNewInputFromMemory(ctxt, URL, buffer, size, encoding,
14135
0
                                      XML_INPUT_BUF_STATIC);
14136
0
    if (input == NULL)
14137
0
        return(NULL);
14138
14139
0
    return(xmlCtxtParseDocument(ctxt, input));
14140
0
}
14141
14142
/**
14143
 * xmlCtxtReadFd:
14144
 * @ctxt:  an XML parser context
14145
 * @fd:  an open file descriptor
14146
 * @URL:  base URL (optional)
14147
 * @encoding:  the document encoding (optional)
14148
 * @options:  a combination of xmlParserOption
14149
 *
14150
 * Parse an XML document from a file descriptor and build a tree.
14151
 *
14152
 * NOTE that the file descriptor will not be closed when the
14153
 * context is freed or reset.
14154
 *
14155
 * @URL is used as base to resolve external entities and for error
14156
 * reporting.
14157
 *
14158
 * See xmlCtxtUseOptions for details.
14159
 *
14160
 * Returns the resulting document tree
14161
 */
14162
xmlDocPtr
14163
xmlCtxtReadFd(xmlParserCtxtPtr ctxt, int fd,
14164
              const char *URL, const char *encoding, int options)
14165
0
{
14166
0
    xmlParserInputPtr input;
14167
14168
0
    if (ctxt == NULL)
14169
0
        return(NULL);
14170
14171
0
    xmlCtxtReset(ctxt);
14172
0
    xmlCtxtUseOptions(ctxt, options);
14173
14174
0
    input = xmlCtxtNewInputFromFd(ctxt, URL, fd, encoding, 0);
14175
0
    if (input == NULL)
14176
0
        return(NULL);
14177
14178
0
    return(xmlCtxtParseDocument(ctxt, input));
14179
0
}
14180
14181
/**
14182
 * xmlCtxtReadIO:
14183
 * @ctxt:  an XML parser context
14184
 * @ioread:  an I/O read function
14185
 * @ioclose:  an I/O close function
14186
 * @ioctx:  an I/O handler
14187
 * @URL:  the base URL to use for the document
14188
 * @encoding:  the document encoding, or NULL
14189
 * @options:  a combination of xmlParserOption
14190
 *
14191
 * parse an XML document from I/O functions and source and build a tree.
14192
 * This reuses the existing @ctxt parser context
14193
 *
14194
 * @URL is used as base to resolve external entities and for error
14195
 * reporting.
14196
 *
14197
 * See xmlCtxtUseOptions for details.
14198
 *
14199
 * Returns the resulting document tree
14200
 */
14201
xmlDocPtr
14202
xmlCtxtReadIO(xmlParserCtxtPtr ctxt, xmlInputReadCallback ioread,
14203
              xmlInputCloseCallback ioclose, void *ioctx,
14204
        const char *URL,
14205
              const char *encoding, int options)
14206
0
{
14207
0
    xmlParserInputPtr input;
14208
14209
0
    if (ctxt == NULL)
14210
0
        return(NULL);
14211
14212
0
    xmlCtxtReset(ctxt);
14213
0
    xmlCtxtUseOptions(ctxt, options);
14214
14215
0
    input = xmlCtxtNewInputFromIO(ctxt, URL, ioread, ioclose, ioctx,
14216
0
                                  encoding, 0);
14217
0
    if (input == NULL)
14218
0
        return(NULL);
14219
14220
0
    return(xmlCtxtParseDocument(ctxt, input));
14221
0
}
14222