Coverage Report

Created: 2025-07-18 06:31

/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
31.9k
#define NS_INDEX_EMPTY  INT_MAX
80
32.0k
#define NS_INDEX_XML    (INT_MAX - 1)
81
1.39k
#define URI_HASH_EMPTY  0xD943A04E
82
10.3k
#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
485
#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
66.9k
#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
73.0k
#define XML_ENT_FIXED_COST 20
163
164
34.9M
#define XML_PARSER_BIG_BUFFER_SIZE 300
165
24.7k
#define XML_PARSER_BUFFER_SIZE 100
166
17.2k
#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
11.1k
{
231
11.1k
    if (prefix == NULL)
232
794
        xmlCtxtErr(ctxt, NULL, XML_FROM_PARSER, XML_ERR_ATTRIBUTE_REDEFINED,
233
794
                   XML_ERR_FATAL, localname, NULL, NULL, 0,
234
794
                   "Attribute %s redefined\n", localname);
235
10.3k
    else
236
10.3k
        xmlCtxtErr(ctxt, NULL, XML_FROM_PARSER, XML_ERR_ATTRIBUTE_REDEFINED,
237
10.3k
                   XML_ERR_FATAL, prefix, localname, NULL, 0,
238
10.3k
                   "Attribute %s:%s redefined\n", prefix, localname);
239
11.1k
}
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
14.2M
{
253
14.2M
    xmlCtxtErr(ctxt, NULL, XML_FROM_PARSER, error, XML_ERR_FATAL,
254
14.2M
               NULL, NULL, NULL, 0, "%s", msg);
255
14.2M
}
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
183
{
271
183
    xmlCtxtErr(ctxt, NULL, XML_FROM_PARSER, error, XML_ERR_WARNING,
272
183
               str1, str2, NULL, 0, msg, str1, str2);
273
183
}
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
2.04M
{
307
2.04M
    xmlCtxtErr(ctxt, NULL, XML_FROM_PARSER, error, XML_ERR_FATAL,
308
2.04M
               NULL, NULL, NULL, val, msg, val);
309
2.04M
}
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
3.74M
{
327
3.74M
    xmlCtxtErr(ctxt, NULL, XML_FROM_PARSER, error, XML_ERR_FATAL,
328
3.74M
               str1, str2, NULL, val, msg, str1, val, str2);
329
3.74M
}
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
44.0k
{
344
44.0k
    xmlCtxtErr(ctxt, NULL, XML_FROM_PARSER, error, XML_ERR_FATAL,
345
44.0k
               val, NULL, NULL, 0, msg, val);
346
44.0k
}
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
28.0k
{
381
28.0k
    ctxt->nsWellFormed = 0;
382
383
28.0k
    xmlCtxtErr(ctxt, NULL, XML_FROM_NAMESPACE, error, XML_ERR_ERROR,
384
28.0k
               info1, info2, info3, 0, msg, info1, info2, info3);
385
28.0k
}
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
3.64k
{
403
3.64k
    xmlCtxtErr(ctxt, NULL, XML_FROM_NAMESPACE, error, XML_ERR_WARNING,
404
3.64k
               info1, info2, info3, 0, msg, info1, info2, info3);
405
3.64k
}
406
407
static void
408
213k
xmlSaturatedAdd(unsigned long *dst, unsigned long val) {
409
213k
    if (val > ULONG_MAX - *dst)
410
0
        *dst = ULONG_MAX;
411
213k
    else
412
213k
        *dst += val;
413
213k
}
414
415
static void
416
67.0k
xmlSaturatedAddSizeT(unsigned long *dst, unsigned long val) {
417
67.0k
    if (val > ULONG_MAX - *dst)
418
0
        *dst = ULONG_MAX;
419
67.0k
    else
420
67.0k
        *dst += val;
421
67.0k
}
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
66.9k
{
450
66.9k
    unsigned long consumed;
451
66.9k
    unsigned long *expandedSize;
452
66.9k
    xmlParserInputPtr input = ctxt->input;
453
66.9k
    xmlEntityPtr entity = input->entity;
454
455
66.9k
    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
66.9k
    consumed = input->consumed;
463
66.9k
    xmlSaturatedAddSizeT(&consumed, input->cur - input->base);
464
66.9k
    xmlSaturatedAdd(&consumed, ctxt->sizeentities);
465
466
66.9k
    if (entity)
467
0
        expandedSize = &entity->expandedSize;
468
66.9k
    else
469
66.9k
        expandedSize = &ctxt->sizeentcopy;
470
471
    /*
472
     * Add extra cost and some fixed cost.
473
     */
474
66.9k
    xmlSaturatedAdd(expandedSize, extra);
475
66.9k
    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
66.9k
    if ((*expandedSize > XML_PARSER_ALLOWED_EXPANSION) &&
483
66.9k
        ((*expandedSize >= ULONG_MAX) ||
484
2.77k
         (*expandedSize / ctxt->maxAmpl > consumed))) {
485
176
        xmlFatalErrMsg(ctxt, XML_ERR_RESOURCE_LIMIT,
486
176
                       "Maximum entity amplification factor exceeded, see "
487
176
                       "xmlCtxtSetMaxAmplification.\n");
488
176
        xmlHaltParser(ctxt);
489
176
        return(1);
490
176
    }
491
492
66.8k
    return(0);
493
66.9k
}
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
55.2k
xmlSBufInit(xmlSBuf *buf, unsigned max) {
713
55.2k
    buf->mem = NULL;
714
55.2k
    buf->size = 0;
715
55.2k
    buf->cap = 0;
716
55.2k
    buf->max = max;
717
55.2k
    buf->code = XML_ERR_OK;
718
55.2k
}
719
720
static int
721
51.1k
xmlSBufGrow(xmlSBuf *buf, unsigned len) {
722
51.1k
    xmlChar *mem;
723
51.1k
    unsigned cap;
724
725
51.1k
    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
51.1k
    cap = (buf->size + len) * 2;
732
51.1k
    if (cap < 240)
733
30.8k
        cap = 240;
734
735
51.1k
    mem = xmlRealloc(buf->mem, cap);
736
51.1k
    if (mem == NULL) {
737
0
        buf->code = XML_ERR_NO_MEMORY;
738
0
        return(-1);
739
0
    }
740
741
51.1k
    buf->mem = mem;
742
51.1k
    buf->cap = cap;
743
744
51.1k
    return(0);
745
51.1k
}
746
747
static void
748
31.6M
xmlSBufAddString(xmlSBuf *buf, const xmlChar *str, unsigned len) {
749
31.6M
    if (buf->max - buf->size < len) {
750
3.26k
        if (buf->code == XML_ERR_OK)
751
78
            buf->code = XML_ERR_RESOURCE_LIMIT;
752
3.26k
        return;
753
3.26k
    }
754
755
31.6M
    if (buf->cap - buf->size <= len) {
756
45.2k
        if (xmlSBufGrow(buf, len) < 0)
757
0
            return;
758
45.2k
    }
759
760
31.6M
    if (len > 0)
761
31.6M
        memcpy(buf->mem + buf->size, str, len);
762
31.6M
    buf->size += len;
763
31.6M
}
764
765
static void
766
31.2M
xmlSBufAddCString(xmlSBuf *buf, const char *str, unsigned len) {
767
31.2M
    xmlSBufAddString(buf, (const xmlChar *) str, len);
768
31.2M
}
769
770
static void
771
29.9k
xmlSBufAddChar(xmlSBuf *buf, int c) {
772
29.9k
    xmlChar *end;
773
774
29.9k
    if (buf->max - buf->size < 4) {
775
110
        if (buf->code == XML_ERR_OK)
776
0
            buf->code = XML_ERR_RESOURCE_LIMIT;
777
110
        return;
778
110
    }
779
780
29.8k
    if (buf->cap - buf->size <= 4) {
781
5.83k
        if (xmlSBufGrow(buf, 4) < 0)
782
0
            return;
783
5.83k
    }
784
785
29.8k
    end = buf->mem + buf->size;
786
787
29.8k
    if (c < 0x80) {
788
23.7k
        *end = (xmlChar) c;
789
23.7k
        buf->size += 1;
790
23.7k
    } else {
791
6.06k
        buf->size += xmlCopyCharMultiByte(end, c);
792
6.06k
    }
793
29.8k
}
794
795
static void
796
27.9M
xmlSBufAddReplChar(xmlSBuf *buf) {
797
27.9M
    xmlSBufAddCString(buf, "\xEF\xBF\xBD", 3);
798
27.9M
}
799
800
static void
801
78
xmlSBufReportError(xmlSBuf *buf, xmlParserCtxtPtr ctxt, const char *errMsg) {
802
78
    if (buf->code == XML_ERR_NO_MEMORY)
803
0
        xmlCtxtErrMemory(ctxt);
804
78
    else
805
78
        xmlFatalErr(ctxt, buf->code, errMsg);
806
78
}
807
808
static xmlChar *
809
xmlSBufFinish(xmlSBuf *buf, int *sizeOut, xmlParserCtxtPtr ctxt,
810
38.6k
              const char *errMsg) {
811
38.6k
    if (buf->mem == NULL) {
812
7.20k
        buf->mem = xmlMalloc(1);
813
7.20k
        if (buf->mem == NULL) {
814
0
            buf->code = XML_ERR_NO_MEMORY;
815
7.20k
        } else {
816
7.20k
            buf->mem[0] = 0;
817
7.20k
        }
818
31.4k
    } else {
819
31.4k
        buf->mem[buf->size] = 0;
820
31.4k
    }
821
822
38.6k
    if (buf->code == XML_ERR_OK) {
823
38.6k
        if (sizeOut != NULL)
824
17.0k
            *sizeOut = buf->size;
825
38.6k
        return(buf->mem);
826
38.6k
    }
827
828
16
    xmlSBufReportError(buf, ctxt, errMsg);
829
830
16
    xmlFree(buf->mem);
831
832
16
    if (sizeOut != NULL)
833
16
        *sizeOut = 0;
834
16
    return(NULL);
835
38.6k
}
836
837
static void
838
15.8k
xmlSBufCleanup(xmlSBuf *buf, xmlParserCtxtPtr ctxt, const char *errMsg) {
839
15.8k
    if (buf->code != XML_ERR_OK)
840
62
        xmlSBufReportError(buf, ctxt, errMsg);
841
842
15.8k
    xmlFree(buf->mem);
843
15.8k
}
844
845
static int
846
xmlUTF8MultibyteLen(xmlParserCtxtPtr ctxt, const xmlChar *str,
847
112M
                    const char *errMsg) {
848
112M
    int c = str[0];
849
112M
    int c1 = str[1];
850
851
112M
    if ((c1 & 0xC0) != 0x80)
852
15.9M
        goto encoding_error;
853
854
96.0M
    if (c < 0xE0) {
855
        /* 2-byte sequence */
856
3.18M
        if (c < 0xC2)
857
1.68M
            goto encoding_error;
858
859
1.50M
        return(2);
860
92.8M
    } else {
861
92.8M
        int c2 = str[2];
862
863
92.8M
        if ((c2 & 0xC0) != 0x80)
864
6.89k
            goto encoding_error;
865
866
92.8M
        if (c < 0xF0) {
867
            /* 3-byte sequence */
868
92.8M
            if (c == 0xE0) {
869
                /* overlong */
870
357
                if (c1 < 0xA0)
871
0
                    goto encoding_error;
872
92.8M
            } else if (c == 0xED) {
873
                /* surrogate */
874
22
                if (c1 >= 0xA0)
875
0
                    goto encoding_error;
876
92.8M
            } else if (c == 0xEF) {
877
                /* U+FFFE and U+FFFF are invalid Chars */
878
19.9k
                if ((c1 == 0xBF) && (c2 >= 0xBE))
879
1.22k
                    xmlFatalErrMsg(ctxt, XML_ERR_INVALID_CHAR, errMsg);
880
19.9k
            }
881
882
92.8M
            return(3);
883
92.8M
        } else {
884
            /* 4-byte sequence */
885
14.0k
            if ((str[3] & 0xC0) != 0x80)
886
2.81k
                goto encoding_error;
887
11.2k
            if (c == 0xF0) {
888
                /* overlong */
889
1.28k
                if (c1 < 0x90)
890
11
                    goto encoding_error;
891
9.99k
            } else if (c >= 0xF4) {
892
                /* greater than 0x10FFFF */
893
963
                if ((c > 0xF4) || (c1 >= 0x90))
894
963
                    goto encoding_error;
895
963
            }
896
897
10.3k
            return(4);
898
11.2k
        }
899
92.8M
    }
900
901
17.6M
encoding_error:
902
    /* Only report the first error */
903
17.6M
    if ((ctxt->input->flags & XML_INPUT_ENCODING_ERROR) == 0) {
904
93
        xmlCtxtErrIO(ctxt, XML_ERR_INVALID_ENCODING, NULL);
905
93
        ctxt->input->flags |= XML_INPUT_ENCODING_ERROR;
906
93
    }
907
908
17.6M
    return(0);
909
96.0M
}
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
542
xmlCtxtInitializeLate(xmlParserCtxtPtr ctxt) {
928
542
    xmlSAXHandlerPtr sax;
929
930
    /* Avoid unused variable warning if features are disabled. */
931
542
    (void) sax;
932
933
    /*
934
     * Changing the SAX struct directly is still widespread practice
935
     * in internal and external code.
936
     */
937
542
    if (ctxt == NULL) return;
938
542
    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
542
    ctxt->sax2 = 1;
953
542
#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
542
    ctxt->str_xml = xmlDictLookup(ctxt->dict, BAD_CAST "xml", 3);
960
542
    ctxt->str_xmlns = xmlDictLookup(ctxt->dict, BAD_CAST "xmlns", 5);
961
542
    ctxt->str_xml_ns = xmlDictLookup(ctxt->dict, XML_XML_NAMESPACE, 36);
962
542
    if ((ctxt->str_xml==NULL) || (ctxt->str_xmlns==NULL) ||
963
542
    (ctxt->str_xml_ns == NULL)) {
964
0
        xmlErrMemory(ctxt);
965
0
    }
966
967
542
    xmlDictSetLimit(ctxt->dict,
968
542
                    (ctxt->options & XML_PARSE_HUGE) ?
969
0
                        0 :
970
542
                        XML_MAX_DICTIONARY_LIMIT);
971
542
}
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
28
{
1015
28
    if ((src == NULL) || (dst == NULL))
1016
0
        return(NULL);
1017
1018
28
    while (*src == 0x20) src++;
1019
13.9k
    while (*src != 0) {
1020
13.8k
  if (*src == 0x20) {
1021
34
      while (*src == 0x20) src++;
1022
17
      if (*src != 0)
1023
17
    *dst++ = 0x20;
1024
13.8k
  } else {
1025
13.8k
      *dst++ = *src++;
1026
13.8k
  }
1027
13.8k
    }
1028
28
    *dst = 0;
1029
28
    if (dst == src)
1030
28
       return(NULL);
1031
0
    return(dst);
1032
28
}
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
28
               const xmlChar *value) {
1048
28
    xmlDefAttrsPtr defaults;
1049
28
    xmlDefAttr *attr;
1050
28
    int len, expandedSize;
1051
28
    xmlHashedString name;
1052
28
    xmlHashedString prefix;
1053
28
    xmlHashedString hvalue;
1054
28
    const xmlChar *localname;
1055
1056
    /*
1057
     * Allows to detect attribute redefinitions
1058
     */
1059
28
    if (ctxt->attsSpecial != NULL) {
1060
24
        if (xmlHashLookup2(ctxt->attsSpecial, fullname, fullattr) != NULL)
1061
8
      return;
1062
24
    }
1063
1064
20
    if (ctxt->attsDefault == NULL) {
1065
4
        ctxt->attsDefault = xmlHashCreateDict(10, ctxt->dict);
1066
4
  if (ctxt->attsDefault == NULL)
1067
0
      goto mem_error;
1068
4
    }
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
20
    localname = xmlSplitQName3(fullname, &len);
1075
20
    if (localname == NULL) {
1076
20
        name = xmlDictLookupHashed(ctxt->dict, fullname, -1);
1077
20
  prefix.name = NULL;
1078
20
    } 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
20
    if (name.name == NULL)
1085
0
        goto mem_error;
1086
1087
    /*
1088
     * make sure there is some storage
1089
     */
1090
20
    defaults = xmlHashLookup2(ctxt->attsDefault, name.name, prefix.name);
1091
20
    if ((defaults == NULL) ||
1092
20
        (defaults->nbAttrs >= defaults->maxAttrs)) {
1093
8
        xmlDefAttrsPtr temp;
1094
8
        int newSize;
1095
1096
8
        if (defaults == NULL) {
1097
4
            newSize = 4;
1098
4
        } else {
1099
4
            if ((defaults->maxAttrs >= XML_MAX_ATTRS) ||
1100
4
                ((size_t) defaults->maxAttrs >
1101
4
                     SIZE_MAX / 2 / sizeof(temp[0]) - sizeof(*defaults)))
1102
0
                goto mem_error;
1103
1104
4
            if (defaults->maxAttrs > XML_MAX_ATTRS / 2)
1105
0
                newSize = XML_MAX_ATTRS;
1106
4
            else
1107
4
                newSize = defaults->maxAttrs * 2;
1108
4
        }
1109
8
        temp = xmlRealloc(defaults,
1110
8
                          sizeof(*defaults) + newSize * sizeof(xmlDefAttr));
1111
8
  if (temp == NULL)
1112
0
      goto mem_error;
1113
8
        if (defaults == NULL)
1114
4
            temp->nbAttrs = 0;
1115
8
  temp->maxAttrs = newSize;
1116
8
        defaults = temp;
1117
8
  if (xmlHashUpdateEntry2(ctxt->attsDefault, name.name, prefix.name,
1118
8
                          defaults, NULL) < 0) {
1119
0
      xmlFree(defaults);
1120
0
      goto mem_error;
1121
0
  }
1122
8
    }
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
20
    localname = xmlSplitQName3(fullattr, &len);
1129
20
    if (localname == NULL) {
1130
15
        name = xmlDictLookupHashed(ctxt->dict, fullattr, -1);
1131
15
  prefix.name = NULL;
1132
15
    } else {
1133
5
        name = xmlDictLookupHashed(ctxt->dict, localname, -1);
1134
5
  prefix = xmlDictLookupHashed(ctxt->dict, fullattr, len);
1135
5
        if (prefix.name == NULL)
1136
0
            goto mem_error;
1137
5
    }
1138
20
    if (name.name == NULL)
1139
0
        goto mem_error;
1140
1141
    /* intern the string and precompute the end */
1142
20
    len = strlen((const char *) value);
1143
20
    hvalue = xmlDictLookupHashed(ctxt->dict, value, len);
1144
20
    if (hvalue.name == NULL)
1145
0
        goto mem_error;
1146
1147
20
    expandedSize = strlen((const char *) name.name);
1148
20
    if (prefix.name != NULL)
1149
5
        expandedSize += strlen((const char *) prefix.name);
1150
20
    expandedSize += len;
1151
1152
20
    attr = &defaults->attrs[defaults->nbAttrs++];
1153
20
    attr->name = name;
1154
20
    attr->prefix = prefix;
1155
20
    attr->value = hvalue;
1156
20
    attr->valueEnd = hvalue.name + len;
1157
20
    attr->external = PARSER_EXTERNAL(ctxt);
1158
20
    attr->expandedSize = expandedSize;
1159
1160
20
    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
1.29k
{
1181
1.29k
    if (ctxt->attsSpecial == NULL) {
1182
224
        ctxt->attsSpecial = xmlHashCreateDict(10, ctxt->dict);
1183
224
  if (ctxt->attsSpecial == NULL)
1184
0
      goto mem_error;
1185
224
    }
1186
1187
1.29k
    if (xmlHashAdd2(ctxt->attsSpecial, fullname, fullattr,
1188
1.29k
                    XML_INT_TO_PTR(type)) < 0)
1189
0
        goto mem_error;
1190
1.29k
    return;
1191
1192
1.29k
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
240
                            const xmlChar *unused ATTRIBUTE_UNUSED) {
1205
240
    xmlParserCtxtPtr ctxt = (xmlParserCtxtPtr) data;
1206
1207
240
    if (XML_PTR_TO_INT(payload) == XML_ATTRIBUTE_CDATA) {
1208
0
        xmlHashRemoveEntry2(ctxt->attsSpecial, fullname, fullattr, NULL);
1209
0
    }
1210
240
}
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
297
{
1223
297
    if (ctxt->attsSpecial == NULL)
1224
73
        return;
1225
1226
224
    xmlHashScanFull(ctxt->attsSpecial, xmlCleanSpecialAttrCallback, ctxt);
1227
1228
224
    if (xmlHashSize(ctxt->attsSpecial) == 0) {
1229
0
        xmlHashFree(ctxt->attsSpecial, NULL);
1230
0
        ctxt->attsSpecial = NULL;
1231
0
    }
1232
224
}
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
543
xmlParserNsCreate(void) {
1448
543
    xmlParserNsData *nsdb = xmlMalloc(sizeof(*nsdb));
1449
1450
543
    if (nsdb == NULL)
1451
0
        return(NULL);
1452
543
    memset(nsdb, 0, sizeof(*nsdb));
1453
543
    nsdb->defaultNsIndex = INT_MAX;
1454
1455
543
    return(nsdb);
1456
543
}
1457
1458
/**
1459
 * xmlParserNsFree:
1460
 * @nsdb: namespace database
1461
 *
1462
 * Free a namespace database.
1463
 */
1464
void
1465
543
xmlParserNsFree(xmlParserNsData *nsdb) {
1466
543
    if (nsdb == NULL)
1467
0
        return;
1468
1469
543
    xmlFree(nsdb->extra);
1470
543
    xmlFree(nsdb->hash);
1471
543
    xmlFree(nsdb);
1472
543
}
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
4.04M
xmlParserNsStartElement(xmlParserNsData *nsdb) {
1503
4.04M
    if (nsdb->elementId == UINT_MAX)
1504
0
        return(-1);
1505
4.04M
    nsdb->elementId++;
1506
1507
4.04M
    return(0);
1508
4.04M
}
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
3.90M
                  xmlParserNsBucket **bucketPtr) {
1526
3.90M
    xmlParserNsBucket *bucket, *tombstone;
1527
3.90M
    unsigned index, hashValue;
1528
1529
3.90M
    if (prefix->name == NULL)
1530
3.86M
        return(ctxt->nsdb->defaultNsIndex);
1531
1532
39.9k
    if (ctxt->nsdb->hashSize == 0)
1533
11.7k
        return(INT_MAX);
1534
1535
28.2k
    hashValue = prefix->hashValue;
1536
28.2k
    index = hashValue & (ctxt->nsdb->hashSize - 1);
1537
28.2k
    bucket = &ctxt->nsdb->hash[index];
1538
28.2k
    tombstone = NULL;
1539
1540
46.7k
    while (bucket->hashValue) {
1541
41.2k
        if (bucket->index == INT_MAX) {
1542
3.16k
            if (tombstone == NULL)
1543
2.64k
                tombstone = bucket;
1544
38.0k
        } else if (bucket->hashValue == hashValue) {
1545
22.7k
            if (ctxt->nsTab[bucket->index * 2] == prefix->name) {
1546
22.7k
                if (bucketPtr != NULL)
1547
12.5k
                    *bucketPtr = bucket;
1548
22.7k
                return(bucket->index);
1549
22.7k
            }
1550
22.7k
        }
1551
1552
18.5k
        index++;
1553
18.5k
        bucket++;
1554
18.5k
        if (index == ctxt->nsdb->hashSize) {
1555
1.60k
            index = 0;
1556
1.60k
            bucket = ctxt->nsdb->hash;
1557
1.60k
        }
1558
18.5k
    }
1559
1560
5.48k
    if (bucketPtr != NULL)
1561
919
        *bucketPtr = tombstone ? tombstone : bucket;
1562
5.48k
    return(INT_MAX);
1563
28.2k
}
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
3.78M
xmlParserNsLookupUri(xmlParserCtxtPtr ctxt, const xmlHashedString *prefix) {
1576
3.78M
    const xmlChar *ret;
1577
3.78M
    int nsIndex;
1578
1579
3.78M
    if (prefix->name == ctxt->str_xml)
1580
3
        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
3.78M
    nsIndex = xmlParserNsLookup(ctxt, prefix, NULL);
1587
3.78M
    if ((nsIndex == INT_MAX) || (nsIndex < ctxt->nsdb->minNsIndex))
1588
3.68M
        return(NULL);
1589
1590
98.0k
    ret = ctxt->nsTab[nsIndex * 2 + 1];
1591
98.0k
    if (ret[0] == 0)
1592
330
        ret = NULL;
1593
98.0k
    return(ret);
1594
3.78M
}
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
104k
xmlParserNsLookupSax(xmlParserCtxtPtr ctxt, const xmlChar *prefix) {
1608
104k
    xmlHashedString hprefix;
1609
104k
    int nsIndex;
1610
1611
104k
    if (prefix == ctxt->str_xml)
1612
11.3k
        return(NULL);
1613
1614
92.9k
    hprefix.name = prefix;
1615
92.9k
    if (prefix != NULL)
1616
1.23k
        hprefix.hashValue = xmlDictComputeHash(ctxt->dict, prefix);
1617
91.7k
    else
1618
91.7k
        hprefix.hashValue = 0;
1619
92.9k
    nsIndex = xmlParserNsLookup(ctxt, &hprefix, NULL);
1620
92.9k
    if ((nsIndex == INT_MAX) || (nsIndex < ctxt->nsdb->minNsIndex))
1621
0
        return(NULL);
1622
1623
92.9k
    return(ctxt->nsdb->extra[nsIndex].saxData);
1624
92.9k
}
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
11.1k
                     void *saxData) {
1641
11.1k
    xmlHashedString hprefix;
1642
11.1k
    int nsIndex;
1643
1644
11.1k
    if (prefix == ctxt->str_xml)
1645
0
        return(-1);
1646
1647
11.1k
    hprefix.name = prefix;
1648
11.1k
    if (prefix != NULL)
1649
6.65k
        hprefix.hashValue = xmlDictComputeHash(ctxt->dict, prefix);
1650
4.49k
    else
1651
4.49k
        hprefix.hashValue = 0;
1652
11.1k
    nsIndex = xmlParserNsLookup(ctxt, &hprefix, NULL);
1653
11.1k
    if ((nsIndex == INT_MAX) || (nsIndex < ctxt->nsdb->minNsIndex))
1654
0
        return(-1);
1655
1656
11.1k
    ctxt->nsdb->extra[nsIndex].saxData = saxData;
1657
11.1k
    return(0);
1658
11.1k
}
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
518
xmlParserNsGrow(xmlParserCtxtPtr ctxt) {
1670
518
    const xmlChar **table;
1671
518
    xmlParserNsExtra *extra;
1672
518
    int newSize;
1673
1674
518
    newSize = xmlGrowCapacity(ctxt->nsMax,
1675
518
                              sizeof(table[0]) + sizeof(extra[0]),
1676
518
                              16, XML_MAX_ITEMS);
1677
518
    if (newSize < 0)
1678
0
        goto error;
1679
1680
518
    table = xmlRealloc(ctxt->nsTab, 2 * newSize * sizeof(table[0]));
1681
518
    if (table == NULL)
1682
0
        goto error;
1683
518
    ctxt->nsTab = table;
1684
1685
518
    extra = xmlRealloc(ctxt->nsdb->extra, newSize * sizeof(extra[0]));
1686
518
    if (extra == NULL)
1687
0
        goto error;
1688
518
    ctxt->nsdb->extra = extra;
1689
1690
518
    ctxt->nsMax = newSize;
1691
518
    return(0);
1692
1693
0
error:
1694
0
    xmlErrMemory(ctxt);
1695
0
    return(-1);
1696
518
}
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
11.4k
                const xmlHashedString *uri, void *saxData, int defAttr) {
1714
11.4k
    xmlParserNsBucket *bucket = NULL;
1715
11.4k
    xmlParserNsExtra *extra;
1716
11.4k
    const xmlChar **ns;
1717
11.4k
    unsigned hashValue, nsIndex, oldIndex;
1718
1719
11.4k
    if ((prefix != NULL) && (prefix->name == ctxt->str_xml))
1720
0
        return(0);
1721
1722
11.4k
    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
11.4k
    if ((prefix == NULL) || (prefix->name == NULL)) {
1731
4.59k
        oldIndex = ctxt->nsdb->defaultNsIndex;
1732
1733
4.59k
        if (oldIndex != INT_MAX) {
1734
4.03k
            extra = &ctxt->nsdb->extra[oldIndex];
1735
1736
4.03k
            if (extra->elementId == ctxt->nsdb->elementId) {
1737
97
                if (defAttr == 0)
1738
97
                    xmlErrAttributeDup(ctxt, NULL, BAD_CAST "xmlns");
1739
97
                return(0);
1740
97
            }
1741
1742
3.93k
            if ((ctxt->options & XML_PARSE_NSCLEAN) &&
1743
3.93k
                (uri->name == ctxt->nsTab[oldIndex * 2 + 1]))
1744
0
                return(0);
1745
3.93k
        }
1746
1747
4.49k
        ctxt->nsdb->defaultNsIndex = ctxt->nsNr;
1748
4.49k
        goto populate_entry;
1749
4.59k
    }
1750
1751
    /*
1752
     * Hash table lookup
1753
     */
1754
6.86k
    oldIndex = xmlParserNsLookup(ctxt, prefix, &bucket);
1755
6.86k
    if (oldIndex != INT_MAX) {
1756
5.90k
        extra = &ctxt->nsdb->extra[oldIndex];
1757
1758
        /*
1759
         * Check for duplicate definitions on the same element.
1760
         */
1761
5.90k
        if (extra->elementId == ctxt->nsdb->elementId) {
1762
209
            if (defAttr == 0)
1763
209
                xmlErrAttributeDup(ctxt, BAD_CAST "xmlns", prefix->name);
1764
209
            return(0);
1765
209
        }
1766
1767
5.70k
        if ((ctxt->options & XML_PARSE_NSCLEAN) &&
1768
5.70k
            (uri->name == ctxt->nsTab[bucket->index * 2 + 1]))
1769
0
            return(0);
1770
1771
5.70k
        bucket->index = ctxt->nsNr;
1772
5.70k
        goto populate_entry;
1773
5.70k
    }
1774
1775
    /*
1776
     * Insert new bucket
1777
     */
1778
1779
957
    hashValue = prefix->hashValue;
1780
1781
    /*
1782
     * Grow hash table, 50% fill factor
1783
     */
1784
957
    if (ctxt->nsdb->hashElems + 1 > ctxt->nsdb->hashSize / 2) {
1785
75
        xmlParserNsBucket *newHash;
1786
75
        unsigned newSize, i, index;
1787
1788
75
        if (ctxt->nsdb->hashSize > UINT_MAX / 2) {
1789
0
            xmlErrMemory(ctxt);
1790
0
            return(-1);
1791
0
        }
1792
75
        newSize = ctxt->nsdb->hashSize ? ctxt->nsdb->hashSize * 2 : 16;
1793
75
        newHash = xmlMalloc(newSize * sizeof(newHash[0]));
1794
75
        if (newHash == NULL) {
1795
0
            xmlErrMemory(ctxt);
1796
0
            return(-1);
1797
0
        }
1798
75
        memset(newHash, 0, newSize * sizeof(newHash[0]));
1799
1800
2.47k
        for (i = 0; i < ctxt->nsdb->hashSize; i++) {
1801
2.40k
            unsigned hv = ctxt->nsdb->hash[i].hashValue;
1802
2.40k
            unsigned newIndex;
1803
1804
2.40k
            if ((hv == 0) || (ctxt->nsdb->hash[i].index == INT_MAX))
1805
2.27k
                continue;
1806
121
            newIndex = hv & (newSize - 1);
1807
1808
156
            while (newHash[newIndex].hashValue != 0) {
1809
35
                newIndex++;
1810
35
                if (newIndex == newSize)
1811
0
                    newIndex = 0;
1812
35
            }
1813
1814
121
            newHash[newIndex] = ctxt->nsdb->hash[i];
1815
121
        }
1816
1817
75
        xmlFree(ctxt->nsdb->hash);
1818
75
        ctxt->nsdb->hash = newHash;
1819
75
        ctxt->nsdb->hashSize = newSize;
1820
1821
        /*
1822
         * Relookup
1823
         */
1824
75
        index = hashValue & (newSize - 1);
1825
1826
98
        while (newHash[index].hashValue != 0) {
1827
23
            index++;
1828
23
            if (index == newSize)
1829
0
                index = 0;
1830
23
        }
1831
1832
75
        bucket = &newHash[index];
1833
75
    }
1834
1835
957
    bucket->hashValue = hashValue;
1836
957
    bucket->index = ctxt->nsNr;
1837
957
    ctxt->nsdb->hashElems++;
1838
957
    oldIndex = INT_MAX;
1839
1840
11.1k
populate_entry:
1841
11.1k
    nsIndex = ctxt->nsNr;
1842
1843
11.1k
    ns = &ctxt->nsTab[nsIndex * 2];
1844
11.1k
    ns[0] = prefix ? prefix->name : NULL;
1845
11.1k
    ns[1] = uri->name;
1846
1847
11.1k
    extra = &ctxt->nsdb->extra[nsIndex];
1848
11.1k
    extra->saxData = saxData;
1849
11.1k
    extra->prefixHashValue = prefix ? prefix->hashValue : 0;
1850
11.1k
    extra->uriHashValue = uri->hashValue;
1851
11.1k
    extra->elementId = ctxt->nsdb->elementId;
1852
11.1k
    extra->oldIndex = oldIndex;
1853
1854
11.1k
    ctxt->nsNr++;
1855
1856
11.1k
    return(1);
1857
957
}
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
7.39k
{
1871
7.39k
    int i;
1872
1873
    /* assert(nr <= ctxt->nsNr); */
1874
1875
18.5k
    for (i = ctxt->nsNr - 1; i >= ctxt->nsNr - nr; i--) {
1876
11.1k
        const xmlChar *prefix = ctxt->nsTab[i * 2];
1877
11.1k
        xmlParserNsExtra *extra = &ctxt->nsdb->extra[i];
1878
1879
11.1k
        if (prefix == NULL) {
1880
4.49k
            ctxt->nsdb->defaultNsIndex = extra->oldIndex;
1881
6.65k
        } else {
1882
6.65k
            xmlHashedString hprefix;
1883
6.65k
            xmlParserNsBucket *bucket = NULL;
1884
1885
6.65k
            hprefix.name = prefix;
1886
6.65k
            hprefix.hashValue = extra->prefixHashValue;
1887
6.65k
            xmlParserNsLookup(ctxt, &hprefix, &bucket);
1888
            /* assert(bucket && bucket->hashValue); */
1889
6.65k
            bucket->index = extra->oldIndex;
1890
6.65k
        }
1891
11.1k
    }
1892
1893
7.39k
    ctxt->nsNr -= nr;
1894
7.39k
    return(nr);
1895
7.39k
}
1896
1897
static int
1898
477
xmlCtxtGrowAttrs(xmlParserCtxtPtr ctxt) {
1899
477
    const xmlChar **atts;
1900
477
    unsigned *attallocs;
1901
477
    int newSize;
1902
1903
477
    newSize = xmlGrowCapacity(ctxt->maxatts / 5,
1904
477
                              sizeof(atts[0]) * 5 + sizeof(attallocs[0]),
1905
477
                              10, XML_MAX_ATTRS);
1906
477
    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
477
    atts = xmlRealloc(ctxt->atts, newSize * sizeof(atts[0]) * 5);
1913
477
    if (atts == NULL)
1914
0
        goto mem_error;
1915
477
    ctxt->atts = atts;
1916
1917
477
    attallocs = xmlRealloc(ctxt->attallocs,
1918
477
                           newSize * sizeof(attallocs[0]));
1919
477
    if (attallocs == NULL)
1920
0
        goto mem_error;
1921
477
    ctxt->attallocs = attallocs;
1922
1923
477
    ctxt->maxatts = newSize * 5;
1924
1925
477
    return(0);
1926
1927
0
mem_error:
1928
0
    xmlErrMemory(ctxt);
1929
0
    return(-1);
1930
477
}
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
608
{
1944
608
    char *directory = NULL;
1945
608
    int maxDepth;
1946
1947
608
    if ((ctxt == NULL) || (value == NULL))
1948
0
        return(-1);
1949
1950
608
    maxDepth = (ctxt->options & XML_PARSE_HUGE) ? 40 : 20;
1951
1952
608
    if (ctxt->inputNr >= ctxt->inputMax) {
1953
55
        xmlParserInputPtr *tmp;
1954
55
        int newSize;
1955
1956
55
        newSize = xmlGrowCapacity(ctxt->inputMax, sizeof(tmp[0]),
1957
55
                                  5, maxDepth);
1958
55
        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
55
        tmp = xmlRealloc(ctxt->inputTab, newSize * sizeof(tmp[0]));
1965
55
        if (tmp == NULL) {
1966
0
            xmlErrMemory(ctxt);
1967
0
            return(-1);
1968
0
        }
1969
55
        ctxt->inputTab = tmp;
1970
55
        ctxt->inputMax = newSize;
1971
55
    }
1972
1973
608
    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
608
    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
608
    ctxt->inputTab[ctxt->inputNr] = value;
1987
608
    ctxt->input = value;
1988
1989
608
    if (ctxt->inputNr == 0) {
1990
542
        xmlFree(ctxt->directory);
1991
542
        ctxt->directory = directory;
1992
542
    }
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
608
    value->id = ctxt->input_id++;
2000
2001
608
    return(ctxt->inputNr++);
2002
608
}
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
1.69k
{
2015
1.69k
    xmlParserInputPtr ret;
2016
2017
1.69k
    if (ctxt == NULL)
2018
0
        return(NULL);
2019
1.69k
    if (ctxt->inputNr <= 0)
2020
1.08k
        return (NULL);
2021
608
    ctxt->inputNr--;
2022
608
    if (ctxt->inputNr > 0)
2023
66
        ctxt->input = ctxt->inputTab[ctxt->inputNr - 1];
2024
542
    else
2025
542
        ctxt->input = NULL;
2026
608
    ret = ctxt->inputTab[ctxt->inputNr];
2027
608
    ctxt->inputTab[ctxt->inputNr] = NULL;
2028
608
    return (ret);
2029
1.69k
}
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
3.78M
{
2045
3.78M
    if (ctxt == NULL)
2046
0
        return(0);
2047
2048
3.78M
    if (ctxt->nodeNr >= ctxt->nodeMax) {
2049
2.53k
        int maxDepth = (ctxt->options & XML_PARSE_HUGE) ? 2048 : 256;
2050
2.53k
        xmlNodePtr *tmp;
2051
2.53k
        int newSize;
2052
2053
2.53k
        newSize = xmlGrowCapacity(ctxt->nodeMax, sizeof(tmp[0]),
2054
2.53k
                                  10, maxDepth);
2055
2.53k
        if (newSize < 0) {
2056
45
            xmlFatalErrMsgInt(ctxt, XML_ERR_RESOURCE_LIMIT,
2057
45
                    "Excessive depth in document: %d,"
2058
45
                    " use XML_PARSE_HUGE option\n",
2059
45
                    ctxt->nodeNr);
2060
45
            xmlHaltParser(ctxt);
2061
45
            return(-1);
2062
45
        }
2063
2064
2.48k
  tmp = xmlRealloc(ctxt->nodeTab, newSize * sizeof(tmp[0]));
2065
2.48k
        if (tmp == NULL) {
2066
0
            xmlErrMemory(ctxt);
2067
0
            return (-1);
2068
0
        }
2069
2.48k
        ctxt->nodeTab = tmp;
2070
2.48k
  ctxt->nodeMax = newSize;
2071
2.48k
    }
2072
2073
3.78M
    ctxt->nodeTab[ctxt->nodeNr] = value;
2074
3.78M
    ctxt->node = value;
2075
3.78M
    return (ctxt->nodeNr++);
2076
3.78M
}
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
3.78M
{
2091
3.78M
    xmlNodePtr ret;
2092
2093
3.78M
    if (ctxt == NULL) return(NULL);
2094
3.78M
    if (ctxt->nodeNr <= 0)
2095
11
        return (NULL);
2096
3.78M
    ctxt->nodeNr--;
2097
3.78M
    if (ctxt->nodeNr > 0)
2098
3.78M
        ctxt->node = ctxt->nodeTab[ctxt->nodeNr - 1];
2099
118
    else
2100
118
        ctxt->node = NULL;
2101
3.78M
    ret = ctxt->nodeTab[ctxt->nodeNr];
2102
3.78M
    ctxt->nodeTab[ctxt->nodeNr] = NULL;
2103
3.78M
    return (ret);
2104
3.78M
}
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
3.78M
{
2123
3.78M
    xmlStartTag *tag;
2124
2125
3.78M
    if (ctxt->nameNr >= ctxt->nameMax) {
2126
2.62k
        const xmlChar **tmp;
2127
2.62k
        xmlStartTag *tmp2;
2128
2.62k
        int newSize;
2129
2130
2.62k
        newSize = xmlGrowCapacity(ctxt->nameMax,
2131
2.62k
                                  sizeof(tmp[0]) + sizeof(tmp2[0]),
2132
2.62k
                                  10, XML_MAX_ITEMS);
2133
2.62k
        if (newSize < 0)
2134
0
            goto mem_error;
2135
2136
2.62k
        tmp = xmlRealloc(ctxt->nameTab, newSize * sizeof(tmp[0]));
2137
2.62k
        if (tmp == NULL)
2138
0
      goto mem_error;
2139
2.62k
  ctxt->nameTab = tmp;
2140
2141
2.62k
        tmp2 = xmlRealloc(ctxt->pushTab, newSize * sizeof(tmp2[0]));
2142
2.62k
        if (tmp2 == NULL)
2143
0
      goto mem_error;
2144
2.62k
  ctxt->pushTab = tmp2;
2145
2146
2.62k
        ctxt->nameMax = newSize;
2147
3.78M
    } else if (ctxt->pushTab == NULL) {
2148
487
        ctxt->pushTab = xmlMalloc(ctxt->nameMax * sizeof(ctxt->pushTab[0]));
2149
487
        if (ctxt->pushTab == NULL)
2150
0
            goto mem_error;
2151
487
    }
2152
3.78M
    ctxt->nameTab[ctxt->nameNr] = value;
2153
3.78M
    ctxt->name = value;
2154
3.78M
    tag = &ctxt->pushTab[ctxt->nameNr];
2155
3.78M
    tag->prefix = prefix;
2156
3.78M
    tag->URI = URI;
2157
3.78M
    tag->line = line;
2158
3.78M
    tag->nsNr = nsNr;
2159
3.78M
    return (ctxt->nameNr++);
2160
0
mem_error:
2161
0
    xmlErrMemory(ctxt);
2162
0
    return (-1);
2163
3.78M
}
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
3.78M
{
2204
3.78M
    const xmlChar *ret;
2205
2206
3.78M
    if ((ctxt == NULL) || (ctxt->nameNr <= 0))
2207
0
        return (NULL);
2208
3.78M
    ctxt->nameNr--;
2209
3.78M
    if (ctxt->nameNr > 0)
2210
3.78M
        ctxt->name = ctxt->nameTab[ctxt->nameNr - 1];
2211
240
    else
2212
240
        ctxt->name = NULL;
2213
3.78M
    ret = ctxt->nameTab[ctxt->nameNr];
2214
3.78M
    ctxt->nameTab[ctxt->nameNr] = NULL;
2215
3.78M
    return (ret);
2216
3.78M
}
2217
2218
4.04M
static int spacePush(xmlParserCtxtPtr ctxt, int val) {
2219
4.04M
    if (ctxt->spaceNr >= ctxt->spaceMax) {
2220
2.86k
        int *tmp;
2221
2.86k
        int newSize;
2222
2223
2.86k
        newSize = xmlGrowCapacity(ctxt->spaceMax, sizeof(tmp[0]),
2224
2.86k
                                  10, XML_MAX_ITEMS);
2225
2.86k
        if (newSize < 0) {
2226
0
      xmlErrMemory(ctxt);
2227
0
      return(-1);
2228
0
        }
2229
2230
2.86k
        tmp = xmlRealloc(ctxt->spaceTab, newSize * sizeof(tmp[0]));
2231
2.86k
        if (tmp == NULL) {
2232
0
      xmlErrMemory(ctxt);
2233
0
      return(-1);
2234
0
  }
2235
2.86k
  ctxt->spaceTab = tmp;
2236
2237
2.86k
        ctxt->spaceMax = newSize;
2238
2.86k
    }
2239
4.04M
    ctxt->spaceTab[ctxt->spaceNr] = val;
2240
4.04M
    ctxt->space = &ctxt->spaceTab[ctxt->spaceNr];
2241
4.04M
    return(ctxt->spaceNr++);
2242
4.04M
}
2243
2244
4.04M
static int spacePop(xmlParserCtxtPtr ctxt) {
2245
4.04M
    int ret;
2246
4.04M
    if (ctxt->spaceNr <= 0) return(0);
2247
4.04M
    ctxt->spaceNr--;
2248
4.04M
    if (ctxt->spaceNr > 0)
2249
4.04M
  ctxt->space = &ctxt->spaceTab[ctxt->spaceNr - 1];
2250
0
    else
2251
0
        ctxt->space = &ctxt->spaceTab[0];
2252
4.04M
    ret = ctxt->spaceTab[ctxt->spaceNr];
2253
4.04M
    ctxt->spaceTab[ctxt->spaceNr] = -1;
2254
4.04M
    return(ret);
2255
4.04M
}
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
19.9M
#define RAW (*ctxt->input->cur)
2291
384M
#define CUR (*ctxt->input->cur)
2292
9.16M
#define NXT(val) ctxt->input->cur[(val)]
2293
764M
#define CUR_PTR ctxt->input->cur
2294
11.9M
#define BASE_PTR ctxt->input->base
2295
2296
#define CMP4( s, c1, c2, c3, c4 ) \
2297
13.4M
  ( ((unsigned char *) s)[ 0 ] == c1 && ((unsigned char *) s)[ 1 ] == c2 && \
2298
6.73M
    ((unsigned char *) s)[ 2 ] == c3 && ((unsigned char *) s)[ 3 ] == c4 )
2299
#define CMP5( s, c1, c2, c3, c4, c5 ) \
2300
13.4M
  ( CMP4( s, c1, c2, c3, c4 ) && ((unsigned char *) s)[ 4 ] == c5 )
2301
#define CMP6( s, c1, c2, c3, c4, c5, c6 ) \
2302
13.4M
  ( CMP5( s, c1, c2, c3, c4, c5 ) && ((unsigned char *) s)[ 5 ] == c6 )
2303
#define CMP7( s, c1, c2, c3, c4, c5, c6, c7 ) \
2304
13.3M
  ( 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
13.3M
  ( 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
6.68M
  ( CMP8( s, c1, c2, c3, c4, c5, c6, c7, c8 ) && \
2309
6.68M
    ((unsigned char *) s)[ 8 ] == c9 )
2310
#define CMP10( s, c1, c2, c3, c4, c5, c6, c7, c8, c9, c10 ) \
2311
75
  ( CMP9( s, c1, c2, c3, c4, c5, c6, c7, c8, c9 ) && \
2312
75
    ((unsigned char *) s)[ 9 ] == c10 )
2313
2314
177k
#define SKIP(val) do {             \
2315
177k
    ctxt->input->cur += (val),ctxt->input->col+=(val);      \
2316
177k
    if (*ctxt->input->cur == 0)           \
2317
177k
        xmlParserGrow(ctxt);           \
2318
177k
  } 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
9.21M
    if (!PARSER_PROGRESSIVE(ctxt)) \
2334
9.21M
  xmlParserShrink(ctxt);
2335
2336
#define GROW \
2337
27.4M
    if ((!PARSER_PROGRESSIVE(ctxt)) && \
2338
27.4M
        (ctxt->input->end - ctxt->input->cur < INPUT_CHUNK)) \
2339
77.7k
  xmlParserGrow(ctxt);
2340
2341
3.95M
#define SKIP_BLANKS xmlSkipBlankChars(ctxt)
2342
2343
104k
#define SKIP_BLANKS_PE xmlSkipBlankCharsPE(ctxt)
2344
2345
381k
#define NEXT xmlNextChar(ctxt)
2346
2347
4.14M
#define NEXT1 {               \
2348
4.14M
  ctxt->input->col++;           \
2349
4.14M
  ctxt->input->cur++;           \
2350
4.14M
  if (*ctxt->input->cur == 0)         \
2351
4.14M
      xmlParserGrow(ctxt);           \
2352
4.14M
    }
2353
2354
424M
#define NEXTL(l) do {             \
2355
424M
    if (*(ctxt->input->cur) == '\n') {         \
2356
4.26M
  ctxt->input->line++; ctxt->input->col = 1;      \
2357
420M
    } else ctxt->input->col++;           \
2358
424M
    ctxt->input->cur += l;        \
2359
424M
  } while (0)
2360
2361
4.32M
#define CUR_SCHAR(s, l) xmlStringCurrentChar(ctxt, s, &l)
2362
2363
#define COPY_BUF(b, i, v)           \
2364
50.8M
    if (v < 0x80) b[i++] = v;           \
2365
50.8M
    else i += xmlCopyCharMultiByte(&b[i],v)
2366
2367
static int
2368
47.3M
xmlCurrentCharRecover(xmlParserCtxtPtr ctxt, int *len) {
2369
47.3M
    int c = xmlCurrentChar(ctxt, len);
2370
2371
47.3M
    if (c == XML_INVALID_CHAR)
2372
13.3M
        c = 0xFFFD; /* replacement character */
2373
2374
47.3M
    return(c);
2375
47.3M
}
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
4.06M
xmlSkipBlankChars(xmlParserCtxtPtr ctxt) {
2389
4.06M
    const xmlChar *cur;
2390
4.06M
    int res = 0;
2391
2392
4.06M
    cur = ctxt->input->cur;
2393
4.06M
    while (IS_BLANK_CH(*cur)) {
2394
192k
        if (*cur == '\n') {
2395
45.9k
            ctxt->input->line++; ctxt->input->col = 1;
2396
146k
        } else {
2397
146k
            ctxt->input->col++;
2398
146k
        }
2399
192k
        cur++;
2400
192k
        if (res < INT_MAX)
2401
192k
            res++;
2402
192k
        if (*cur == 0) {
2403
187
            ctxt->input->cur = cur;
2404
187
            xmlParserGrow(ctxt);
2405
187
            cur = ctxt->input->cur;
2406
187
        }
2407
192k
    }
2408
4.06M
    ctxt->input->cur = cur;
2409
2410
4.06M
    if (res > 4)
2411
8.66k
        GROW;
2412
2413
4.06M
    return(res);
2414
4.06M
}
2415
2416
static void
2417
25
xmlPopPE(xmlParserCtxtPtr ctxt) {
2418
25
    unsigned long consumed;
2419
25
    xmlEntityPtr ent;
2420
2421
25
    ent = ctxt->input->entity;
2422
2423
25
    ent->flags &= ~XML_ENT_EXPANDING;
2424
2425
25
    if ((ent->flags & XML_ENT_CHECKED) == 0) {
2426
14
        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
14
        do {
2433
14
            ctxt->input->cur = ctxt->input->end;
2434
14
            xmlParserShrink(ctxt);
2435
14
            result = xmlParserGrow(ctxt);
2436
14
        } while (result > 0);
2437
2438
14
        consumed = ctxt->input->consumed;
2439
14
        xmlSaturatedAddSizeT(&consumed,
2440
14
                             ctxt->input->end - ctxt->input->base);
2441
2442
14
        xmlSaturatedAdd(&ent->expandedSize, consumed);
2443
2444
        /*
2445
         * Add to sizeentities when parsing an external entity
2446
         * for the first time.
2447
         */
2448
14
        if (ent->etype == XML_EXTERNAL_PARAMETER_ENTITY) {
2449
0
            xmlSaturatedAdd(&ctxt->sizeentities, consumed);
2450
0
        }
2451
2452
14
        ent->flags |= XML_ENT_CHECKED;
2453
14
    }
2454
2455
25
    xmlFreeInputStream(xmlCtxtPopInput(ctxt));
2456
2457
25
    xmlParserEntityCheck(ctxt, ent->expandedSize);
2458
2459
25
    GROW;
2460
25
}
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
104k
xmlSkipBlankCharsPE(xmlParserCtxtPtr ctxt) {
2473
104k
    int res = 0;
2474
104k
    int inParam;
2475
104k
    int expandParam;
2476
2477
104k
    inParam = PARSER_IN_PE(ctxt);
2478
104k
    expandParam = PARSER_EXTERNAL(ctxt);
2479
2480
104k
    if (!inParam && !expandParam)
2481
104k
        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
201
    while (PARSER_STOPPED(ctxt) == 0) {
2488
190
        if (IS_BLANK_CH(CUR)) { /* CHECKED tstblanks.xml */
2489
88
            NEXT;
2490
102
        } else if (CUR == '%') {
2491
11
            if ((expandParam == 0) ||
2492
11
                (IS_BLANK_CH(NXT(1))) || (NXT(1) == 0))
2493
11
                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
91
        } else if (CUR == 0) {
2506
22
            if (inParam == 0)
2507
0
                break;
2508
2509
22
            xmlPopPE(ctxt);
2510
2511
22
            inParam = PARSER_IN_PE(ctxt);
2512
22
            expandParam = PARSER_EXTERNAL(ctxt);
2513
69
        } else {
2514
69
            break;
2515
69
        }
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
110
        if (res < INT_MAX)
2525
110
            res++;
2526
110
    }
2527
2528
91
    return(res);
2529
104k
}
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
11.8k
xmlParseCharRef(xmlParserCtxtPtr ctxt) {
2600
11.8k
    int val = 0;
2601
11.8k
    int count = 0;
2602
2603
    /*
2604
     * Using RAW/CUR/NEXT is okay since we are working on ASCII range here
2605
     */
2606
11.8k
    if ((RAW == '&') && (NXT(1) == '#') &&
2607
11.8k
        (NXT(2) == 'x')) {
2608
1.48k
  SKIP(3);
2609
1.48k
  GROW;
2610
5.71k
  while ((RAW != ';') && (PARSER_STOPPED(ctxt) == 0)) {
2611
5.41k
      if (count++ > 20) {
2612
6
    count = 0;
2613
6
    GROW;
2614
6
      }
2615
5.41k
      if ((RAW >= '0') && (RAW <= '9'))
2616
3.09k
          val = val * 16 + (CUR - '0');
2617
2.31k
      else if ((RAW >= 'a') && (RAW <= 'f') && (count < 20))
2618
1.03k
          val = val * 16 + (CUR - 'a') + 10;
2619
1.28k
      else if ((RAW >= 'A') && (RAW <= 'F') && (count < 20))
2620
92
          val = val * 16 + (CUR - 'A') + 10;
2621
1.19k
      else {
2622
1.19k
    xmlFatalErr(ctxt, XML_ERR_INVALID_HEX_CHARREF, NULL);
2623
1.19k
    val = 0;
2624
1.19k
    break;
2625
1.19k
      }
2626
4.22k
      if (val > 0x110000)
2627
158
          val = 0x110000;
2628
2629
4.22k
      NEXT;
2630
4.22k
      count++;
2631
4.22k
  }
2632
1.48k
  if (RAW == ';') {
2633
      /* on purpose to avoid reentrancy problems with NEXT and SKIP */
2634
296
      ctxt->input->col++;
2635
296
      ctxt->input->cur++;
2636
296
  }
2637
10.3k
    } else if  ((RAW == '&') && (NXT(1) == '#')) {
2638
10.3k
  SKIP(2);
2639
10.3k
  GROW;
2640
31.9k
  while (RAW != ';') { /* loop blocked by count */
2641
22.0k
      if (count++ > 20) {
2642
113
    count = 0;
2643
113
    GROW;
2644
113
      }
2645
22.0k
      if ((RAW >= '0') && (RAW <= '9'))
2646
21.6k
          val = val * 10 + (CUR - '0');
2647
365
      else {
2648
365
    xmlFatalErr(ctxt, XML_ERR_INVALID_DEC_CHARREF, NULL);
2649
365
    val = 0;
2650
365
    break;
2651
365
      }
2652
21.6k
      if (val > 0x110000)
2653
634
          val = 0x110000;
2654
2655
21.6k
      NEXT;
2656
21.6k
      count++;
2657
21.6k
  }
2658
10.3k
  if (RAW == ';') {
2659
      /* on purpose to avoid reentrancy problems with NEXT and SKIP */
2660
9.95k
      ctxt->input->col++;
2661
9.95k
      ctxt->input->cur++;
2662
9.95k
  }
2663
10.3k
    } 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
11.8k
    if (val >= 0x110000) {
2675
21
        xmlFatalErrMsgInt(ctxt, XML_ERR_INVALID_CHAR,
2676
21
                "xmlParseCharRef: character reference out of bounds\n",
2677
21
          val);
2678
11.7k
    } else if (IS_CHAR(val)) {
2679
10.0k
        return(val);
2680
10.0k
    } else {
2681
1.75k
        xmlFatalErrMsgInt(ctxt, XML_ERR_INVALID_CHAR,
2682
1.75k
                          "xmlParseCharRef: invalid xmlChar value %d\n",
2683
1.75k
                    val);
2684
1.75k
    }
2685
1.77k
    return(0);
2686
11.8k
}
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
32.2k
xmlParseStringCharRef(xmlParserCtxtPtr ctxt, const xmlChar **str) {
2708
32.2k
    const xmlChar *ptr;
2709
32.2k
    xmlChar cur;
2710
32.2k
    int val = 0;
2711
2712
32.2k
    if ((str == NULL) || (*str == NULL)) return(0);
2713
32.2k
    ptr = *str;
2714
32.2k
    cur = *ptr;
2715
32.2k
    if ((cur == '&') && (ptr[1] == '#') && (ptr[2] == 'x')) {
2716
12.7k
  ptr += 3;
2717
12.7k
  cur = *ptr;
2718
79.6k
  while (cur != ';') { /* Non input consuming loop */
2719
70.8k
      if ((cur >= '0') && (cur <= '9'))
2720
13.5k
          val = val * 16 + (cur - '0');
2721
57.3k
      else if ((cur >= 'a') && (cur <= 'f'))
2722
14.8k
          val = val * 16 + (cur - 'a') + 10;
2723
42.4k
      else if ((cur >= 'A') && (cur <= 'F'))
2724
38.5k
          val = val * 16 + (cur - 'A') + 10;
2725
3.91k
      else {
2726
3.91k
    xmlFatalErr(ctxt, XML_ERR_INVALID_HEX_CHARREF, NULL);
2727
3.91k
    val = 0;
2728
3.91k
    break;
2729
3.91k
      }
2730
66.9k
      if (val > 0x110000)
2731
35.8k
          val = 0x110000;
2732
2733
66.9k
      ptr++;
2734
66.9k
      cur = *ptr;
2735
66.9k
  }
2736
12.7k
  if (cur == ';')
2737
8.78k
      ptr++;
2738
19.5k
    } else if  ((cur == '&') && (ptr[1] == '#')){
2739
19.5k
  ptr += 2;
2740
19.5k
  cur = *ptr;
2741
70.6k
  while (cur != ';') { /* Non input consuming loops */
2742
52.8k
      if ((cur >= '0') && (cur <= '9'))
2743
51.1k
          val = val * 10 + (cur - '0');
2744
1.72k
      else {
2745
1.72k
    xmlFatalErr(ctxt, XML_ERR_INVALID_DEC_CHARREF, NULL);
2746
1.72k
    val = 0;
2747
1.72k
    break;
2748
1.72k
      }
2749
51.1k
      if (val > 0x110000)
2750
0
          val = 0x110000;
2751
2752
51.1k
      ptr++;
2753
51.1k
      cur = *ptr;
2754
51.1k
  }
2755
19.5k
  if (cur == ';')
2756
17.8k
      ptr++;
2757
19.5k
    } else {
2758
0
  xmlFatalErr(ctxt, XML_ERR_INVALID_CHARREF, NULL);
2759
0
  return(0);
2760
0
    }
2761
32.2k
    *str = ptr;
2762
2763
    /*
2764
     * [ WFC: Legal Character ]
2765
     * Characters referred to using character references must match the
2766
     * production for Char.
2767
     */
2768
32.2k
    if (val >= 0x110000) {
2769
258
        xmlFatalErrMsgInt(ctxt, XML_ERR_INVALID_CHAR,
2770
258
                "xmlParseStringCharRef: character reference out of bounds\n",
2771
258
                val);
2772
31.9k
    } else if (IS_CHAR(val)) {
2773
25.7k
        return(val);
2774
25.7k
    } else {
2775
6.24k
        xmlFatalErrMsgInt(ctxt, XML_ERR_INVALID_CHAR,
2776
6.24k
        "xmlParseStringCharRef: invalid xmlChar value %d\n",
2777
6.24k
        val);
2778
6.24k
    }
2779
6.49k
    return(0);
2780
32.2k
}
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
4.05M
xmlIsNameStartChar(xmlParserCtxtPtr ctxt, int c) {
3192
4.05M
    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
4.05M
  if ((c != ' ') && (c != '>') && (c != '/') && /* accelerators */
3198
4.05M
      (((c >= 'a') && (c <= 'z')) ||
3199
4.05M
       ((c >= 'A') && (c <= 'Z')) ||
3200
4.05M
       (c == '_') || (c == ':') ||
3201
4.05M
       ((c >= 0xC0) && (c <= 0xD6)) ||
3202
4.05M
       ((c >= 0xD8) && (c <= 0xF6)) ||
3203
4.05M
       ((c >= 0xF8) && (c <= 0x2FF)) ||
3204
4.05M
       ((c >= 0x370) && (c <= 0x37D)) ||
3205
4.05M
       ((c >= 0x37F) && (c <= 0x1FFF)) ||
3206
4.05M
       ((c >= 0x200C) && (c <= 0x200D)) ||
3207
4.05M
       ((c >= 0x2070) && (c <= 0x218F)) ||
3208
4.05M
       ((c >= 0x2C00) && (c <= 0x2FEF)) ||
3209
4.05M
       ((c >= 0x3001) && (c <= 0xD7FF)) ||
3210
4.05M
       ((c >= 0xF900) && (c <= 0xFDCF)) ||
3211
4.05M
       ((c >= 0xFDF0) && (c <= 0xFFFD)) ||
3212
4.05M
       ((c >= 0x10000) && (c <= 0xEFFFF))))
3213
119k
      return(1);
3214
4.05M
    } else {
3215
0
        if (IS_LETTER(c) || (c == '_') || (c == ':'))
3216
0
      return(1);
3217
0
    }
3218
3.93M
    return(0);
3219
4.05M
}
3220
3221
static int
3222
9.04M
xmlIsNameChar(xmlParserCtxtPtr ctxt, int c) {
3223
9.04M
    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
9.04M
  if ((c != ' ') && (c != '>') && (c != '/') && /* accelerators */
3229
9.04M
      (((c >= 'a') && (c <= 'z')) ||
3230
9.04M
       ((c >= 'A') && (c <= 'Z')) ||
3231
9.04M
       ((c >= '0') && (c <= '9')) || /* !start */
3232
9.04M
       (c == '_') || (c == ':') ||
3233
9.04M
       (c == '-') || (c == '.') || (c == 0xB7) || /* !start */
3234
9.04M
       ((c >= 0xC0) && (c <= 0xD6)) ||
3235
9.04M
       ((c >= 0xD8) && (c <= 0xF6)) ||
3236
9.04M
       ((c >= 0xF8) && (c <= 0x2FF)) ||
3237
9.04M
       ((c >= 0x300) && (c <= 0x36F)) || /* !start */
3238
9.04M
       ((c >= 0x370) && (c <= 0x37D)) ||
3239
9.04M
       ((c >= 0x37F) && (c <= 0x1FFF)) ||
3240
9.04M
       ((c >= 0x200C) && (c <= 0x200D)) ||
3241
9.04M
       ((c >= 0x203F) && (c <= 0x2040)) || /* !start */
3242
9.04M
       ((c >= 0x2070) && (c <= 0x218F)) ||
3243
9.04M
       ((c >= 0x2C00) && (c <= 0x2FEF)) ||
3244
9.04M
       ((c >= 0x3001) && (c <= 0xD7FF)) ||
3245
9.04M
       ((c >= 0xF900) && (c <= 0xFDCF)) ||
3246
9.04M
       ((c >= 0xFDF0) && (c <= 0xFFFD)) ||
3247
9.04M
       ((c >= 0x10000) && (c <= 0xEFFFF))))
3248
8.92M
       return(1);
3249
9.04M
    } 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
117k
    return(0);
3258
9.04M
}
3259
3260
static const xmlChar *
3261
74.0k
xmlParseNameComplex(xmlParserCtxtPtr ctxt) {
3262
74.0k
    const xmlChar *ret;
3263
74.0k
    int len = 0, l;
3264
74.0k
    int c;
3265
74.0k
    int maxLength = (ctxt->options & XML_PARSE_HUGE) ?
3266
0
                    XML_MAX_TEXT_LENGTH :
3267
74.0k
                    XML_MAX_NAME_LENGTH;
3268
3269
    /*
3270
     * Handler for more complex cases
3271
     */
3272
74.0k
    c = xmlCurrentChar(ctxt, &l);
3273
74.0k
    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
74.0k
  if ((c == ' ') || (c == '>') || (c == '/') || /* accelerators */
3279
74.0k
      (!(((c >= 'a') && (c <= 'z')) ||
3280
27.5k
         ((c >= 'A') && (c <= 'Z')) ||
3281
27.5k
         (c == '_') || (c == ':') ||
3282
27.5k
         ((c >= 0xC0) && (c <= 0xD6)) ||
3283
27.5k
         ((c >= 0xD8) && (c <= 0xF6)) ||
3284
27.5k
         ((c >= 0xF8) && (c <= 0x2FF)) ||
3285
27.5k
         ((c >= 0x370) && (c <= 0x37D)) ||
3286
27.5k
         ((c >= 0x37F) && (c <= 0x1FFF)) ||
3287
27.5k
         ((c >= 0x200C) && (c <= 0x200D)) ||
3288
27.5k
         ((c >= 0x2070) && (c <= 0x218F)) ||
3289
27.5k
         ((c >= 0x2C00) && (c <= 0x2FEF)) ||
3290
27.5k
         ((c >= 0x3001) && (c <= 0xD7FF)) ||
3291
27.5k
         ((c >= 0xF900) && (c <= 0xFDCF)) ||
3292
27.5k
         ((c >= 0xFDF0) && (c <= 0xFFFD)) ||
3293
62.5k
         ((c >= 0x10000) && (c <= 0xEFFFF))))) {
3294
62.5k
      return(NULL);
3295
62.5k
  }
3296
11.5k
  len += l;
3297
11.5k
  NEXTL(l);
3298
11.5k
  c = xmlCurrentChar(ctxt, &l);
3299
1.87M
  while ((c != ' ') && (c != '>') && (c != '/') && /* accelerators */
3300
1.87M
         (((c >= 'a') && (c <= 'z')) ||
3301
1.87M
          ((c >= 'A') && (c <= 'Z')) ||
3302
1.87M
          ((c >= '0') && (c <= '9')) || /* !start */
3303
1.87M
          (c == '_') || (c == ':') ||
3304
1.87M
          (c == '-') || (c == '.') || (c == 0xB7) || /* !start */
3305
1.87M
          ((c >= 0xC0) && (c <= 0xD6)) ||
3306
1.87M
          ((c >= 0xD8) && (c <= 0xF6)) ||
3307
1.87M
          ((c >= 0xF8) && (c <= 0x2FF)) ||
3308
1.87M
          ((c >= 0x300) && (c <= 0x36F)) || /* !start */
3309
1.87M
          ((c >= 0x370) && (c <= 0x37D)) ||
3310
1.87M
          ((c >= 0x37F) && (c <= 0x1FFF)) ||
3311
1.87M
          ((c >= 0x200C) && (c <= 0x200D)) ||
3312
1.87M
          ((c >= 0x203F) && (c <= 0x2040)) || /* !start */
3313
1.87M
          ((c >= 0x2070) && (c <= 0x218F)) ||
3314
1.87M
          ((c >= 0x2C00) && (c <= 0x2FEF)) ||
3315
1.87M
          ((c >= 0x3001) && (c <= 0xD7FF)) ||
3316
1.87M
          ((c >= 0xF900) && (c <= 0xFDCF)) ||
3317
1.87M
          ((c >= 0xFDF0) && (c <= 0xFFFD)) ||
3318
1.87M
          ((c >= 0x10000) && (c <= 0xEFFFF))
3319
1.87M
    )) {
3320
1.86M
            if (len <= INT_MAX - l)
3321
1.86M
          len += l;
3322
1.86M
      NEXTL(l);
3323
1.86M
      c = xmlCurrentChar(ctxt, &l);
3324
1.86M
  }
3325
11.5k
    } 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
11.5k
    if (len > maxLength) {
3348
26
        xmlFatalErr(ctxt, XML_ERR_NAME_TOO_LONG, "Name");
3349
26
        return(NULL);
3350
26
    }
3351
11.4k
    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
11.4k
    if ((*ctxt->input->cur == '\n') && (ctxt->input->cur[-1] == '\r'))
3362
0
        ret = xmlDictLookup(ctxt->dict, ctxt->input->cur - (len + 1), len);
3363
11.4k
    else
3364
11.4k
        ret = xmlDictLookup(ctxt->dict, ctxt->input->cur - len, len);
3365
11.4k
    if (ret == NULL)
3366
0
        xmlErrMemory(ctxt);
3367
11.4k
    return(ret);
3368
11.4k
}
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
221k
xmlParseName(xmlParserCtxtPtr ctxt) {
3390
221k
    const xmlChar *in;
3391
221k
    const xmlChar *ret;
3392
221k
    size_t count = 0;
3393
221k
    size_t maxLength = (ctxt->options & XML_PARSE_HUGE) ?
3394
0
                       XML_MAX_TEXT_LENGTH :
3395
221k
                       XML_MAX_NAME_LENGTH;
3396
3397
221k
    GROW;
3398
3399
    /*
3400
     * Accelerator for simple ASCII names
3401
     */
3402
221k
    in = ctxt->input->cur;
3403
221k
    if (((*in >= 0x61) && (*in <= 0x7A)) ||
3404
221k
  ((*in >= 0x41) && (*in <= 0x5A)) ||
3405
221k
  (*in == '_') || (*in == ':')) {
3406
157k
  in++;
3407
265k
  while (((*in >= 0x61) && (*in <= 0x7A)) ||
3408
265k
         ((*in >= 0x41) && (*in <= 0x5A)) ||
3409
265k
         ((*in >= 0x30) && (*in <= 0x39)) ||
3410
265k
         (*in == '_') || (*in == '-') ||
3411
265k
         (*in == ':') || (*in == '.'))
3412
107k
      in++;
3413
157k
  if ((*in > 0) && (*in < 0x80)) {
3414
147k
      count = in - ctxt->input->cur;
3415
147k
            if (count > maxLength) {
3416
0
                xmlFatalErr(ctxt, XML_ERR_NAME_TOO_LONG, "Name");
3417
0
                return(NULL);
3418
0
            }
3419
147k
      ret = xmlDictLookup(ctxt->dict, ctxt->input->cur, count);
3420
147k
      ctxt->input->cur = in;
3421
147k
      ctxt->input->col += count;
3422
147k
      if (ret == NULL)
3423
0
          xmlErrMemory(ctxt);
3424
147k
      return(ret);
3425
147k
  }
3426
157k
    }
3427
    /* accelerator for special cases */
3428
74.0k
    return(xmlParseNameComplex(ctxt));
3429
221k
}
3430
3431
static xmlHashedString
3432
4.03M
xmlParseNCNameComplex(xmlParserCtxtPtr ctxt) {
3433
4.03M
    xmlHashedString ret;
3434
4.03M
    int len = 0, l;
3435
4.03M
    int c;
3436
4.03M
    int maxLength = (ctxt->options & XML_PARSE_HUGE) ?
3437
0
                    XML_MAX_TEXT_LENGTH :
3438
4.03M
                    XML_MAX_NAME_LENGTH;
3439
4.03M
    size_t startPosition = 0;
3440
3441
4.03M
    ret.name = NULL;
3442
4.03M
    ret.hashValue = 0;
3443
3444
    /*
3445
     * Handler for more complex cases
3446
     */
3447
4.03M
    startPosition = CUR_PTR - BASE_PTR;
3448
4.03M
    c = xmlCurrentChar(ctxt, &l);
3449
4.03M
    if ((c == ' ') || (c == '>') || (c == '/') || /* accelerators */
3450
4.03M
  (!xmlIsNameStartChar(ctxt, c) || (c == ':'))) {
3451
3.94M
  return(ret);
3452
3.94M
    }
3453
3454
3.33M
    while ((c != ' ') && (c != '>') && (c != '/') && /* test bigname.xml */
3455
3.33M
     (xmlIsNameChar(ctxt, c) && (c != ':'))) {
3456
3.24M
        if (len <= INT_MAX - l)
3457
3.24M
      len += l;
3458
3.24M
  NEXTL(l);
3459
3.24M
  c = xmlCurrentChar(ctxt, &l);
3460
3.24M
    }
3461
88.5k
    if (len > maxLength) {
3462
49
        xmlFatalErr(ctxt, XML_ERR_NAME_TOO_LONG, "NCName");
3463
49
        return(ret);
3464
49
    }
3465
88.5k
    ret = xmlDictLookupHashed(ctxt->dict, (BASE_PTR + startPosition), len);
3466
88.5k
    if (ret.name == NULL)
3467
0
        xmlErrMemory(ctxt);
3468
88.5k
    return(ret);
3469
88.5k
}
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
7.80M
xmlParseNCName(xmlParserCtxtPtr ctxt) {
3488
7.80M
    const xmlChar *in, *e;
3489
7.80M
    xmlHashedString ret;
3490
7.80M
    size_t count = 0;
3491
7.80M
    size_t maxLength = (ctxt->options & XML_PARSE_HUGE) ?
3492
0
                       XML_MAX_TEXT_LENGTH :
3493
7.80M
                       XML_MAX_NAME_LENGTH;
3494
3495
7.80M
    ret.name = NULL;
3496
3497
    /*
3498
     * Accelerator for simple ASCII names
3499
     */
3500
7.80M
    in = ctxt->input->cur;
3501
7.80M
    e = ctxt->input->end;
3502
7.80M
    if ((((*in >= 0x61) && (*in <= 0x7A)) ||
3503
7.80M
   ((*in >= 0x41) && (*in <= 0x5A)) ||
3504
7.80M
   (*in == '_')) && (in < e)) {
3505
3.85M
  in++;
3506
4.79M
  while ((((*in >= 0x61) && (*in <= 0x7A)) ||
3507
4.79M
          ((*in >= 0x41) && (*in <= 0x5A)) ||
3508
4.79M
          ((*in >= 0x30) && (*in <= 0x39)) ||
3509
4.79M
          (*in == '_') || (*in == '-') ||
3510
4.79M
          (*in == '.')) && (in < e))
3511
939k
      in++;
3512
3.85M
  if (in >= e)
3513
88
      goto complex;
3514
3.85M
  if ((*in > 0) && (*in < 0x80)) {
3515
3.77M
      count = in - ctxt->input->cur;
3516
3.77M
            if (count > maxLength) {
3517
0
                xmlFatalErr(ctxt, XML_ERR_NAME_TOO_LONG, "NCName");
3518
0
                return(ret);
3519
0
            }
3520
3.77M
      ret = xmlDictLookupHashed(ctxt->dict, ctxt->input->cur, count);
3521
3.77M
      ctxt->input->cur = in;
3522
3.77M
      ctxt->input->col += count;
3523
3.77M
      if (ret.name == NULL) {
3524
0
          xmlErrMemory(ctxt);
3525
0
      }
3526
3.77M
      return(ret);
3527
3.77M
  }
3528
3.85M
    }
3529
4.03M
complex:
3530
4.03M
    return(xmlParseNCNameComplex(ctxt));
3531
7.80M
}
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
61.7k
xmlParseNameAndCompare(xmlParserCtxtPtr ctxt, xmlChar const *other) {
3546
61.7k
    register const xmlChar *cmp = other;
3547
61.7k
    register const xmlChar *in;
3548
61.7k
    const xmlChar *ret;
3549
3550
61.7k
    GROW;
3551
3552
61.7k
    in = ctxt->input->cur;
3553
71.1k
    while (*in != 0 && *in == *cmp) {
3554
9.41k
  ++in;
3555
9.41k
  ++cmp;
3556
9.41k
    }
3557
61.7k
    if (*cmp == 0 && (*in == '>' || IS_BLANK_CH (*in))) {
3558
  /* success */
3559
7.14k
  ctxt->input->col += in - ctxt->input->cur;
3560
7.14k
  ctxt->input->cur = in;
3561
7.14k
  return (const xmlChar*) 1;
3562
7.14k
    }
3563
    /* failure (or end of input buffer), check with full function */
3564
54.6k
    ret = xmlParseName (ctxt);
3565
    /* strings coming from the dictionary direct compare possible */
3566
54.6k
    if (ret == other) {
3567
36
  return (const xmlChar*) 1;
3568
36
    }
3569
54.5k
    return ret;
3570
54.6k
}
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
27.9k
xmlParseStringName(xmlParserCtxtPtr ctxt, const xmlChar** str) {
3592
27.9k
    xmlChar buf[XML_MAX_NAMELEN + 5];
3593
27.9k
    xmlChar *ret;
3594
27.9k
    const xmlChar *cur = *str;
3595
27.9k
    int len = 0, l;
3596
27.9k
    int c;
3597
27.9k
    int maxLength = (ctxt->options & XML_PARSE_HUGE) ?
3598
0
                    XML_MAX_TEXT_LENGTH :
3599
27.9k
                    XML_MAX_NAME_LENGTH;
3600
3601
27.9k
    c = CUR_SCHAR(cur, l);
3602
27.9k
    if (!xmlIsNameStartChar(ctxt, c)) {
3603
3.11k
  return(NULL);
3604
3.11k
    }
3605
3606
24.8k
    COPY_BUF(buf, len, c);
3607
24.8k
    cur += l;
3608
24.8k
    c = CUR_SCHAR(cur, l);
3609
82.6k
    while (xmlIsNameChar(ctxt, c)) {
3610
59.0k
  COPY_BUF(buf, len, c);
3611
59.0k
  cur += l;
3612
59.0k
  c = CUR_SCHAR(cur, l);
3613
59.0k
  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
1.18k
      xmlChar *buffer;
3619
1.18k
      int max = len * 2;
3620
3621
1.18k
      buffer = xmlMalloc(max);
3622
1.18k
      if (buffer == NULL) {
3623
0
          xmlErrMemory(ctxt);
3624
0
    return(NULL);
3625
0
      }
3626
1.18k
      memcpy(buffer, buf, len);
3627
4.21M
      while (xmlIsNameChar(ctxt, c)) {
3628
4.20M
    if (len + 10 > max) {
3629
11.8k
        xmlChar *tmp;
3630
11.8k
                    int newSize;
3631
3632
11.8k
                    newSize = xmlGrowCapacity(max, 1, 1, maxLength);
3633
11.8k
                    if (newSize < 0) {
3634
32
                        xmlFatalErr(ctxt, XML_ERR_NAME_TOO_LONG, "NCName");
3635
32
                        xmlFree(buffer);
3636
32
                        return(NULL);
3637
32
                    }
3638
11.8k
        tmp = xmlRealloc(buffer, newSize);
3639
11.8k
        if (tmp == NULL) {
3640
0
      xmlErrMemory(ctxt);
3641
0
      xmlFree(buffer);
3642
0
      return(NULL);
3643
0
        }
3644
11.8k
        buffer = tmp;
3645
11.8k
                    max = newSize;
3646
11.8k
    }
3647
4.20M
    COPY_BUF(buffer, len, c);
3648
4.20M
    cur += l;
3649
4.20M
    c = CUR_SCHAR(cur, l);
3650
4.20M
      }
3651
1.15k
      buffer[len] = 0;
3652
1.15k
      *str = cur;
3653
1.15k
      return(buffer);
3654
1.18k
  }
3655
59.0k
    }
3656
23.6k
    if (len > maxLength) {
3657
0
        xmlFatalErr(ctxt, XML_ERR_NAME_TOO_LONG, "NCName");
3658
0
        return(NULL);
3659
0
    }
3660
23.6k
    *str = cur;
3661
23.6k
    ret = xmlStrndup(buf, len);
3662
23.6k
    if (ret == NULL)
3663
0
        xmlErrMemory(ctxt);
3664
23.6k
    return(ret);
3665
23.6k
}
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
8.11k
xmlParseNmtoken(xmlParserCtxtPtr ctxt) {
3684
8.11k
    xmlChar buf[XML_MAX_NAMELEN + 5];
3685
8.11k
    xmlChar *ret;
3686
8.11k
    int len = 0, l;
3687
8.11k
    int c;
3688
8.11k
    int maxLength = (ctxt->options & XML_PARSE_HUGE) ?
3689
0
                    XML_MAX_TEXT_LENGTH :
3690
8.11k
                    XML_MAX_NAME_LENGTH;
3691
3692
8.11k
    c = xmlCurrentChar(ctxt, &l);
3693
3694
52.3k
    while (xmlIsNameChar(ctxt, c)) {
3695
44.6k
  COPY_BUF(buf, len, c);
3696
44.6k
  NEXTL(l);
3697
44.6k
  c = xmlCurrentChar(ctxt, &l);
3698
44.6k
  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
363
      xmlChar *buffer;
3704
363
      int max = len * 2;
3705
3706
363
      buffer = xmlMalloc(max);
3707
363
      if (buffer == NULL) {
3708
0
          xmlErrMemory(ctxt);
3709
0
    return(NULL);
3710
0
      }
3711
363
      memcpy(buffer, buf, len);
3712
1.36M
      while (xmlIsNameChar(ctxt, c)) {
3713
1.36M
    if (len + 10 > max) {
3714
1.74k
        xmlChar *tmp;
3715
1.74k
                    int newSize;
3716
3717
1.74k
                    newSize = xmlGrowCapacity(max, 1, 1, maxLength);
3718
1.74k
                    if (newSize < 0) {
3719
55
                        xmlFatalErr(ctxt, XML_ERR_NAME_TOO_LONG, "NmToken");
3720
55
                        xmlFree(buffer);
3721
55
                        return(NULL);
3722
55
                    }
3723
1.68k
        tmp = xmlRealloc(buffer, newSize);
3724
1.68k
        if (tmp == NULL) {
3725
0
      xmlErrMemory(ctxt);
3726
0
      xmlFree(buffer);
3727
0
      return(NULL);
3728
0
        }
3729
1.68k
        buffer = tmp;
3730
1.68k
                    max = newSize;
3731
1.68k
    }
3732
1.36M
    COPY_BUF(buffer, len, c);
3733
1.36M
    NEXTL(l);
3734
1.36M
    c = xmlCurrentChar(ctxt, &l);
3735
1.36M
      }
3736
308
      buffer[len] = 0;
3737
308
      return(buffer);
3738
363
  }
3739
44.6k
    }
3740
7.75k
    if (len == 0)
3741
1.73k
        return(NULL);
3742
6.02k
    if (len > maxLength) {
3743
0
        xmlFatalErr(ctxt, XML_ERR_NAME_TOO_LONG, "NmToken");
3744
0
        return(NULL);
3745
0
    }
3746
6.02k
    ret = xmlStrndup(buf, len);
3747
6.02k
    if (ret == NULL)
3748
0
        xmlErrMemory(ctxt);
3749
6.02k
    return(ret);
3750
6.02k
}
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
21.5k
                          const xmlChar *str, int length, int depth) {
3765
21.5k
    int maxDepth = (ctxt->options & XML_PARSE_HUGE) ? 40 : 20;
3766
21.5k
    const xmlChar *end, *chunk;
3767
21.5k
    int c, l;
3768
3769
21.5k
    if (str == NULL)
3770
0
        return;
3771
3772
21.5k
    depth += 1;
3773
21.5k
    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
21.5k
    end = str + length;
3780
21.5k
    chunk = str;
3781
3782
103M
    while ((str < end) && (!PARSER_STOPPED(ctxt))) {
3783
103M
        c = *str;
3784
3785
103M
        if (c >= 0x80) {
3786
101M
            l = xmlUTF8MultibyteLen(ctxt, str,
3787
101M
                    "invalid character in entity value\n");
3788
101M
            if (l == 0) {
3789
8.18M
                if (chunk < str)
3790
30.8k
                    xmlSBufAddString(buf, chunk, str - chunk);
3791
8.18M
                xmlSBufAddReplChar(buf);
3792
8.18M
                str += 1;
3793
8.18M
                chunk = str;
3794
92.8M
            } else {
3795
92.8M
                str += l;
3796
92.8M
            }
3797
101M
        } else if (c == '&') {
3798
37.2k
            if (str[1] == '#') {
3799
26.5k
                if (chunk < str)
3800
18.5k
                    xmlSBufAddString(buf, chunk, str - chunk);
3801
3802
26.5k
                c = xmlParseStringCharRef(ctxt, &str);
3803
26.5k
                if (c == 0)
3804
6.49k
                    return;
3805
3806
20.0k
                xmlSBufAddChar(buf, c);
3807
3808
20.0k
                chunk = str;
3809
20.0k
            } else {
3810
10.6k
                xmlChar *name;
3811
3812
                /*
3813
                 * General entity references are checked for
3814
                 * syntactic validity.
3815
                 */
3816
10.6k
                str++;
3817
10.6k
                name = xmlParseStringName(ctxt, &str);
3818
3819
10.6k
                if ((name == NULL) || (*str++ != ';')) {
3820
438
                    xmlFatalErrMsg(ctxt, XML_ERR_ENTITY_CHAR_ERROR,
3821
438
                            "EntityValue: '&' forbidden except for entities "
3822
438
                            "references\n");
3823
438
                    xmlFree(name);
3824
438
                    return;
3825
438
                }
3826
3827
10.2k
                xmlFree(name);
3828
10.2k
            }
3829
2.39M
        } else if (c == '%') {
3830
3.43k
            xmlEntityPtr ent;
3831
3832
3.43k
            if (chunk < str)
3833
2.88k
                xmlSBufAddString(buf, chunk, str - chunk);
3834
3835
3.43k
            ent = xmlParseStringPEReference(ctxt, &str);
3836
3.43k
            if (ent == NULL)
3837
3.43k
                return;
3838
3839
0
            if (!PARSER_EXTERNAL(ctxt)) {
3840
0
                xmlFatalErr(ctxt, XML_ERR_ENTITY_PE_INTERNAL, NULL);
3841
0
                return;
3842
0
            }
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
2.39M
        } else {
3882
            /* Normal ASCII char */
3883
2.39M
            if (!IS_BYTE_CHAR(c)) {
3884
678k
                xmlFatalErrMsg(ctxt, XML_ERR_INVALID_CHAR,
3885
678k
                        "invalid character in entity value\n");
3886
678k
                if (chunk < str)
3887
10.9k
                    xmlSBufAddString(buf, chunk, str - chunk);
3888
678k
                xmlSBufAddReplChar(buf);
3889
678k
                str += 1;
3890
678k
                chunk = str;
3891
1.71M
            } else {
3892
1.71M
                str += 1;
3893
1.71M
            }
3894
2.39M
        }
3895
103M
    }
3896
3897
11.1k
    if (chunk < str)
3898
6.31k
        xmlSBufAddString(buf, chunk, str - chunk);
3899
11.1k
}
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
21.5k
xmlParseEntityValue(xmlParserCtxtPtr ctxt, xmlChar **orig) {
3917
21.5k
    unsigned maxLength = (ctxt->options & XML_PARSE_HUGE) ?
3918
0
                         XML_MAX_HUGE_LENGTH :
3919
21.5k
                         XML_MAX_TEXT_LENGTH;
3920
21.5k
    xmlSBuf buf;
3921
21.5k
    const xmlChar *start;
3922
21.5k
    int quote, length;
3923
3924
21.5k
    xmlSBufInit(&buf, maxLength);
3925
3926
21.5k
    GROW;
3927
3928
21.5k
    quote = CUR;
3929
21.5k
    if ((quote != '"') && (quote != '\'')) {
3930
0
  xmlFatalErr(ctxt, XML_ERR_ATTRIBUTE_NOT_STARTED, NULL);
3931
0
  return(NULL);
3932
0
    }
3933
21.5k
    CUR_PTR++;
3934
3935
21.5k
    length = 0;
3936
3937
    /*
3938
     * Copy raw content of the entity into a buffer
3939
     */
3940
345M
    while (1) {
3941
345M
        int c;
3942
3943
345M
        if (PARSER_STOPPED(ctxt))
3944
0
            goto error;
3945
3946
345M
        if (CUR_PTR >= ctxt->input->end) {
3947
14
            xmlFatalErrMsg(ctxt, XML_ERR_ENTITY_NOT_FINISHED, NULL);
3948
14
            goto error;
3949
14
        }
3950
3951
345M
        c = CUR;
3952
3953
345M
        if (c == 0) {
3954
4
            xmlFatalErrMsg(ctxt, XML_ERR_INVALID_CHAR,
3955
4
                    "invalid character in entity value\n");
3956
4
            goto error;
3957
4
        }
3958
345M
        if (c == quote)
3959
21.5k
            break;
3960
345M
        NEXTL(1);
3961
345M
        length += 1;
3962
3963
        /*
3964
         * TODO: Check growth threshold
3965
         */
3966
345M
        if (ctxt->input->end - CUR_PTR < 10)
3967
30.5k
            GROW;
3968
345M
    }
3969
3970
21.5k
    start = CUR_PTR - length;
3971
3972
21.5k
    if (orig != NULL) {
3973
21.5k
        *orig = xmlStrndup(start, length);
3974
21.5k
        if (*orig == NULL)
3975
0
            xmlErrMemory(ctxt);
3976
21.5k
    }
3977
3978
21.5k
    xmlExpandPEsInEntityValue(ctxt, &buf, start, length, ctxt->inputNr);
3979
3980
21.5k
    NEXTL(1);
3981
3982
21.5k
    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
21.5k
}
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
79
xmlCheckEntityInAttValue(xmlParserCtxtPtr ctxt, xmlEntityPtr pent, int depth) {
4000
79
    int maxDepth = (ctxt->options & XML_PARSE_HUGE) ? 40 : 20;
4001
79
    const xmlChar *str;
4002
79
    unsigned long expandedSize = pent->length;
4003
79
    int c, flags;
4004
4005
79
    depth += 1;
4006
79
    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
79
    if (pent->flags & XML_ENT_EXPANDING) {
4013
0
        xmlFatalErr(ctxt, XML_ERR_ENTITY_LOOP, NULL);
4014
0
        xmlHaltParser(ctxt);
4015
0
        return;
4016
0
    }
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
79
    if (ctxt->inSubset == 0)
4024
79
        flags = XML_ENT_CHECKED | XML_ENT_VALIDATED;
4025
0
    else
4026
0
        flags = XML_ENT_VALIDATED;
4027
4028
79
    str = pent->content;
4029
79
    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
5.97M
    while (!PARSER_STOPPED(ctxt)) {
4039
5.97M
        c = *str;
4040
4041
5.97M
  if (c != '&') {
4042
5.96M
            if (c == 0)
4043
75
                break;
4044
4045
5.96M
            if (c == '<')
4046
16.9k
                xmlFatalErrMsgStr(ctxt, XML_ERR_LT_IN_ATTRIBUTE,
4047
16.9k
                        "'<' in entity '%s' is not allowed in attributes "
4048
16.9k
                        "values\n", pent->name);
4049
4050
5.96M
            str += 1;
4051
5.96M
        } else if (str[1] == '#') {
4052
4
            int val;
4053
4054
4
      val = xmlParseStringCharRef(ctxt, &str);
4055
4
      if (val == 0) {
4056
4
                pent->content[0] = 0;
4057
4
                break;
4058
4
            }
4059
9.34k
  } else {
4060
9.34k
            xmlChar *name;
4061
9.34k
            xmlEntityPtr ent;
4062
4063
9.34k
      name = xmlParseStringEntityRef(ctxt, &str);
4064
9.34k
      if (name == NULL) {
4065
0
                pent->content[0] = 0;
4066
0
                break;
4067
0
            }
4068
4069
9.34k
            ent = xmlLookupGeneralEntity(ctxt, name, /* inAttr */ 1);
4070
9.34k
            xmlFree(name);
4071
4072
9.34k
            if ((ent != NULL) &&
4073
9.34k
                (ent->etype != XML_INTERNAL_PREDEFINED_ENTITY)) {
4074
6.06k
                if ((ent->flags & flags) != flags) {
4075
50
                    pent->flags |= XML_ENT_EXPANDING;
4076
50
                    xmlCheckEntityInAttValue(ctxt, ent, depth);
4077
50
                    pent->flags &= ~XML_ENT_EXPANDING;
4078
50
                }
4079
4080
6.06k
                xmlSaturatedAdd(&expandedSize, ent->expandedSize);
4081
6.06k
                xmlSaturatedAdd(&expandedSize, XML_ENT_FIXED_COST);
4082
6.06k
            }
4083
9.34k
        }
4084
5.97M
    }
4085
4086
79
done:
4087
79
    if (ctxt->inSubset == 0)
4088
79
        pent->expandedSize = expandedSize;
4089
4090
79
    pent->flags |= flags;
4091
79
}
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
4.80k
                          int *inSpace, int depth, int check) {
4111
4.80k
    int maxDepth = (ctxt->options & XML_PARSE_HUGE) ? 40 : 20;
4112
4.80k
    int c, chunkSize;
4113
4114
4.80k
    if (str == NULL)
4115
0
        return;
4116
4117
4.80k
    depth += 1;
4118
4.80k
    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
4.80k
    if (pent != NULL) {
4125
4.80k
        if (pent->flags & XML_ENT_EXPANDING) {
4126
1
            xmlFatalErr(ctxt, XML_ERR_ENTITY_LOOP, NULL);
4127
1
            xmlHaltParser(ctxt);
4128
1
            return;
4129
1
        }
4130
4131
4.80k
        if (check) {
4132
4.80k
            if (xmlParserEntityCheck(ctxt, pent->length))
4133
141
                return;
4134
4.80k
        }
4135
4.80k
    }
4136
4137
4.66k
    chunkSize = 0;
4138
4139
    /*
4140
     * Note that entity values are already validated. No special
4141
     * handling for multi-byte characters is needed.
4142
     */
4143
1.23G
    while (!PARSER_STOPPED(ctxt)) {
4144
1.23G
        c = *str;
4145
4146
1.23G
  if (c != '&') {
4147
1.23G
            if (c == 0)
4148
4.50k
                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
1.23G
            if ((pent != NULL) && (c == '<')) {
4156
162
                xmlFatalErrMsgStr(ctxt, XML_ERR_LT_IN_ATTRIBUTE,
4157
162
                        "'<' in entity '%s' is not allowed in attributes "
4158
162
                        "values\n", pent->name);
4159
162
                break;
4160
162
            }
4161
4162
1.23G
            if (c <= 0x20) {
4163
77.9k
                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
77.9k
                } else if (c < 0x20) {
4170
39.8k
                    if (chunkSize > 0) {
4171
39.8k
                        xmlSBufAddString(buf, str - chunkSize, chunkSize);
4172
39.8k
                        chunkSize = 0;
4173
39.8k
                    }
4174
4175
39.8k
                    xmlSBufAddCString(buf, " ", 1);
4176
39.8k
                } else {
4177
38.0k
                    chunkSize += 1;
4178
38.0k
                }
4179
4180
77.9k
                *inSpace = 1;
4181
1.23G
            } else {
4182
1.23G
                chunkSize += 1;
4183
1.23G
                *inSpace = 0;
4184
1.23G
            }
4185
4186
1.23G
            str += 1;
4187
1.23G
        } else if (str[1] == '#') {
4188
5.67k
            int val;
4189
4190
5.67k
            if (chunkSize > 0) {
4191
5.67k
                xmlSBufAddString(buf, str - chunkSize, chunkSize);
4192
5.67k
                chunkSize = 0;
4193
5.67k
            }
4194
4195
5.67k
      val = xmlParseStringCharRef(ctxt, &str);
4196
5.67k
      if (val == 0) {
4197
0
                if (pent != NULL)
4198
0
                    pent->content[0] = 0;
4199
0
                break;
4200
0
            }
4201
4202
5.67k
            if (val == ' ') {
4203
0
                if ((!normalize) || (!*inSpace))
4204
0
                    xmlSBufAddCString(buf, " ", 1);
4205
0
                *inSpace = 1;
4206
5.67k
            } else {
4207
5.67k
                xmlSBufAddChar(buf, val);
4208
5.67k
                *inSpace = 0;
4209
5.67k
            }
4210
5.67k
  } else {
4211
4.48k
            xmlChar *name;
4212
4.48k
            xmlEntityPtr ent;
4213
4214
4.48k
            if (chunkSize > 0) {
4215
2.50k
                xmlSBufAddString(buf, str - chunkSize, chunkSize);
4216
2.50k
                chunkSize = 0;
4217
2.50k
            }
4218
4219
4.48k
      name = xmlParseStringEntityRef(ctxt, &str);
4220
4.48k
            if (name == NULL) {
4221
0
                if (pent != NULL)
4222
0
                    pent->content[0] = 0;
4223
0
                break;
4224
0
            }
4225
4226
4.48k
            ent = xmlLookupGeneralEntity(ctxt, name, /* inAttr */ 1);
4227
4.48k
            xmlFree(name);
4228
4229
4.48k
      if ((ent != NULL) &&
4230
4.48k
    (ent->etype == XML_INTERNAL_PREDEFINED_ENTITY)) {
4231
1.62k
    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
1.62k
                xmlSBufAddString(buf, ent->content, ent->length);
4238
4239
1.62k
                *inSpace = 0;
4240
2.85k
      } else if ((ent != NULL) && (ent->content != NULL)) {
4241
1.96k
                if (pent != NULL)
4242
1.96k
                    pent->flags |= XML_ENT_EXPANDING;
4243
1.96k
    xmlExpandEntityInAttValue(ctxt, buf, ent->content, ent,
4244
1.96k
                                          normalize, inSpace, depth, check);
4245
1.96k
                if (pent != NULL)
4246
1.96k
                    pent->flags &= ~XML_ENT_EXPANDING;
4247
1.96k
      }
4248
4.48k
        }
4249
1.23G
    }
4250
4251
4.66k
    if (chunkSize > 0)
4252
3.68k
        xmlSBufAddString(buf, str - chunkSize, chunkSize);
4253
4.66k
}
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
33.6k
                         int normalize, int isNamespace) {
4322
33.6k
    unsigned maxLength = (ctxt->options & XML_PARSE_HUGE) ?
4323
0
                         XML_MAX_HUGE_LENGTH :
4324
33.6k
                         XML_MAX_TEXT_LENGTH;
4325
33.6k
    xmlSBuf buf;
4326
33.6k
    xmlChar *ret;
4327
33.6k
    int c, l, quote, flags, chunkSize;
4328
33.6k
    int inSpace = 1;
4329
33.6k
    int replaceEntities;
4330
4331
    /* Always expand namespace URIs */
4332
33.6k
    replaceEntities = (ctxt->replaceEntities) || (isNamespace);
4333
4334
33.6k
    xmlSBufInit(&buf, maxLength);
4335
4336
33.6k
    GROW;
4337
4338
33.6k
    quote = CUR;
4339
33.6k
    if ((quote != '"') && (quote != '\'')) {
4340
753
  xmlFatalErr(ctxt, XML_ERR_ATTRIBUTE_NOT_STARTED, NULL);
4341
753
  return(NULL);
4342
753
    }
4343
32.9k
    NEXTL(1);
4344
4345
32.9k
    if (ctxt->inSubset == 0)
4346
32.8k
        flags = XML_ENT_CHECKED | XML_ENT_VALIDATED;
4347
28
    else
4348
28
        flags = XML_ENT_VALIDATED;
4349
4350
32.9k
    inSpace = 1;
4351
32.9k
    chunkSize = 0;
4352
4353
25.7M
    while (1) {
4354
25.7M
        if (PARSER_STOPPED(ctxt))
4355
142
            goto error;
4356
4357
25.7M
        if (CUR_PTR >= ctxt->input->end) {
4358
51
            xmlFatalErrMsg(ctxt, XML_ERR_ATTRIBUTE_NOT_FINISHED,
4359
51
                           "AttValue: ' expected\n");
4360
51
            goto error;
4361
51
        }
4362
4363
        /*
4364
         * TODO: Check growth threshold
4365
         */
4366
25.7M
        if (ctxt->input->end - CUR_PTR < 10)
4367
5.95k
            GROW;
4368
4369
25.7M
        c = CUR;
4370
4371
25.7M
        if (c >= 0x80) {
4372
10.9M
            l = xmlUTF8MultibyteLen(ctxt, CUR_PTR,
4373
10.9M
                    "invalid character in attribute value\n");
4374
10.9M
            if (l == 0) {
4375
9.44M
                if (chunkSize > 0) {
4376
69.0k
                    xmlSBufAddString(&buf, CUR_PTR - chunkSize, chunkSize);
4377
69.0k
                    chunkSize = 0;
4378
69.0k
                }
4379
9.44M
                xmlSBufAddReplChar(&buf);
4380
9.44M
                NEXTL(1);
4381
9.44M
            } else {
4382
1.50M
                chunkSize += l;
4383
1.50M
                NEXTL(l);
4384
1.50M
            }
4385
4386
10.9M
            inSpace = 0;
4387
14.7M
        } else if (c != '&') {
4388
14.6M
            if (c > 0x20) {
4389
1.71M
                if (c == quote)
4390
31.9k
                    break;
4391
4392
1.68M
                if (c == '<')
4393
72.3k
                    xmlFatalErr(ctxt, XML_ERR_LT_IN_ATTRIBUTE, NULL);
4394
4395
1.68M
                chunkSize += 1;
4396
1.68M
                inSpace = 0;
4397
12.9M
            } else if (!IS_BYTE_CHAR(c)) {
4398
9.63M
                xmlFatalErrMsg(ctxt, XML_ERR_INVALID_CHAR,
4399
9.63M
                        "invalid character in attribute value\n");
4400
9.63M
                if (chunkSize > 0) {
4401
27.3k
                    xmlSBufAddString(&buf, CUR_PTR - chunkSize, chunkSize);
4402
27.3k
                    chunkSize = 0;
4403
27.3k
                }
4404
9.63M
                xmlSBufAddReplChar(&buf);
4405
9.63M
                inSpace = 0;
4406
9.63M
            } else {
4407
                /* Whitespace */
4408
3.27M
                if ((normalize) && (inSpace)) {
4409
                    /* Skip char */
4410
0
                    if (chunkSize > 0) {
4411
0
                        xmlSBufAddString(&buf, CUR_PTR - chunkSize, chunkSize);
4412
0
                        chunkSize = 0;
4413
0
                    }
4414
3.27M
                } else if (c < 0x20) {
4415
                    /* Convert to space */
4416
3.17M
                    if (chunkSize > 0) {
4417
42.2k
                        xmlSBufAddString(&buf, CUR_PTR - chunkSize, chunkSize);
4418
42.2k
                        chunkSize = 0;
4419
42.2k
                    }
4420
4421
3.17M
                    xmlSBufAddCString(&buf, " ", 1);
4422
3.17M
                } else {
4423
103k
                    chunkSize += 1;
4424
103k
                }
4425
4426
3.27M
                inSpace = 1;
4427
4428
3.27M
                if ((c == 0xD) && (NXT(1) == 0xA))
4429
35
                    CUR_PTR++;
4430
3.27M
            }
4431
4432
14.5M
            NEXTL(1);
4433
14.5M
        } else if (NXT(1) == '#') {
4434
8.87k
            int val;
4435
4436
8.87k
            if (chunkSize > 0) {
4437
1.99k
                xmlSBufAddString(&buf, CUR_PTR - chunkSize, chunkSize);
4438
1.99k
                chunkSize = 0;
4439
1.99k
            }
4440
4441
8.87k
            val = xmlParseCharRef(ctxt);
4442
8.87k
            if (val == 0)
4443
757
                goto error;
4444
4445
8.11k
            if ((val == '&') && (!replaceEntities)) {
4446
                /*
4447
                 * The reparsing will be done in xmlNodeParseContent()
4448
                 * called from SAX2.c
4449
                 */
4450
1.03k
                xmlSBufAddCString(&buf, "&#38;", 5);
4451
1.03k
                inSpace = 0;
4452
7.08k
            } else if (val == ' ') {
4453
2.89k
                if ((!normalize) || (!inSpace))
4454
2.89k
                    xmlSBufAddCString(&buf, " ", 1);
4455
2.89k
                inSpace = 1;
4456
4.18k
            } else {
4457
4.18k
                xmlSBufAddChar(&buf, val);
4458
4.18k
                inSpace = 0;
4459
4.18k
            }
4460
114k
        } else {
4461
114k
            const xmlChar *name;
4462
114k
            xmlEntityPtr ent;
4463
4464
114k
            if (chunkSize > 0) {
4465
42.4k
                xmlSBufAddString(&buf, CUR_PTR - chunkSize, chunkSize);
4466
42.4k
                chunkSize = 0;
4467
42.4k
            }
4468
4469
114k
            name = xmlParseEntityRefInternal(ctxt);
4470
114k
            if (name == NULL) {
4471
                /*
4472
                 * Probably a literal '&' which wasn't escaped.
4473
                 * TODO: Handle gracefully in recovery mode.
4474
                 */
4475
33.8k
                continue;
4476
33.8k
            }
4477
4478
80.8k
            ent = xmlLookupGeneralEntity(ctxt, name, /* isAttr */ 1);
4479
80.8k
            if (ent == NULL)
4480
10.8k
                continue;
4481
4482
70.0k
            if (ent->etype == XML_INTERNAL_PREDEFINED_ENTITY) {
4483
5.13k
                if ((ent->content[0] == '&') && (!replaceEntities))
4484
2.34k
                    xmlSBufAddCString(&buf, "&#38;", 5);
4485
2.78k
                else
4486
2.78k
                    xmlSBufAddString(&buf, ent->content, ent->length);
4487
5.13k
                inSpace = 0;
4488
64.9k
            } else if (replaceEntities) {
4489
2.84k
                xmlExpandEntityInAttValue(ctxt, &buf, ent->content, ent,
4490
2.84k
                                          normalize, &inSpace, ctxt->inputNr,
4491
2.84k
                                          /* check */ 1);
4492
62.1k
            } else {
4493
62.1k
                if ((ent->flags & flags) != flags)
4494
29
                    xmlCheckEntityInAttValue(ctxt, ent, ctxt->inputNr);
4495
4496
62.1k
                if (xmlParserEntityCheck(ctxt, ent->expandedSize)) {
4497
24
                    ent->content[0] = 0;
4498
24
                    goto error;
4499
24
                }
4500
4501
                /*
4502
                 * Just output the reference
4503
                 */
4504
62.0k
                xmlSBufAddCString(&buf, "&", 1);
4505
62.0k
                xmlSBufAddString(&buf, ent->name, xmlStrlen(ent->name));
4506
62.0k
                xmlSBufAddCString(&buf, ";", 1);
4507
4508
62.0k
                inSpace = 0;
4509
62.0k
            }
4510
70.0k
  }
4511
25.7M
    }
4512
4513
31.9k
    if ((buf.mem == NULL) && (alloc != NULL)) {
4514
14.8k
        ret = (xmlChar *) CUR_PTR - chunkSize;
4515
4516
14.8k
        if (attlen != NULL)
4517
14.8k
            *attlen = chunkSize;
4518
14.8k
        if ((normalize) && (inSpace) && (chunkSize > 0))
4519
0
            *attlen -= 1;
4520
14.8k
        *alloc = 0;
4521
4522
        /* Report potential error */
4523
14.8k
        xmlSBufCleanup(&buf, ctxt, "AttValue length too long");
4524
17.1k
    } else {
4525
17.1k
        if (chunkSize > 0)
4526
16.0k
            xmlSBufAddString(&buf, CUR_PTR - chunkSize, chunkSize);
4527
4528
17.1k
        if ((normalize) && (inSpace) && (buf.size > 0))
4529
0
            buf.size--;
4530
4531
17.1k
        ret = xmlSBufFinish(&buf, attlen, ctxt, "AttValue length too long");
4532
4533
17.1k
        if (ret != NULL) {
4534
17.0k
            if (attlen != NULL)
4535
17.0k
                *attlen = buf.size;
4536
17.0k
            if (alloc != NULL)
4537
17.0k
                *alloc = 1;
4538
17.0k
        }
4539
17.1k
    }
4540
4541
31.9k
    NEXTL(1);
4542
4543
31.9k
    return(ret);
4544
4545
974
error:
4546
974
    xmlSBufCleanup(&buf, ctxt, "AttValue length too long");
4547
974
    return(NULL);
4548
32.9k
}
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
28
xmlParseAttValue(xmlParserCtxtPtr ctxt) {
4588
28
    if ((ctxt == NULL) || (ctxt->input == NULL)) return(NULL);
4589
28
    return(xmlParseAttValueInternal(ctxt, NULL, NULL, 0, 0));
4590
28
}
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
397
xmlParseSystemLiteral(xmlParserCtxtPtr ctxt) {
4607
397
    xmlChar *buf = NULL;
4608
397
    int len = 0;
4609
397
    int size = XML_PARSER_BUFFER_SIZE;
4610
397
    int cur, l;
4611
397
    int maxLength = (ctxt->options & XML_PARSE_HUGE) ?
4612
0
                    XML_MAX_TEXT_LENGTH :
4613
397
                    XML_MAX_NAME_LENGTH;
4614
397
    xmlChar stop;
4615
4616
397
    if (RAW == '"') {
4617
397
        NEXT;
4618
397
  stop = '"';
4619
397
    } else if (RAW == '\'') {
4620
0
        NEXT;
4621
0
  stop = '\'';
4622
0
    } else {
4623
0
  xmlFatalErr(ctxt, XML_ERR_LITERAL_NOT_STARTED, NULL);
4624
0
  return(NULL);
4625
0
    }
4626
4627
397
    buf = xmlMalloc(size);
4628
397
    if (buf == NULL) {
4629
0
        xmlErrMemory(ctxt);
4630
0
  return(NULL);
4631
0
    }
4632
397
    cur = xmlCurrentCharRecover(ctxt, &l);
4633
1.49M
    while ((IS_CHAR(cur)) && (cur != stop)) { /* checked */
4634
1.49M
  if (len + 5 >= size) {
4635
4.10k
      xmlChar *tmp;
4636
4.10k
            int newSize;
4637
4638
4.10k
            newSize = xmlGrowCapacity(size, 1, 1, maxLength);
4639
4.10k
            if (newSize < 0) {
4640
0
                xmlFatalErr(ctxt, XML_ERR_NAME_TOO_LONG, "SystemLiteral");
4641
0
                xmlFree(buf);
4642
0
                return(NULL);
4643
0
            }
4644
4.10k
      tmp = xmlRealloc(buf, newSize);
4645
4.10k
      if (tmp == NULL) {
4646
0
          xmlFree(buf);
4647
0
    xmlErrMemory(ctxt);
4648
0
    return(NULL);
4649
0
      }
4650
4.10k
      buf = tmp;
4651
4.10k
            size = newSize;
4652
4.10k
  }
4653
1.49M
  COPY_BUF(buf, len, cur);
4654
1.49M
  NEXTL(l);
4655
1.49M
  cur = xmlCurrentCharRecover(ctxt, &l);
4656
1.49M
    }
4657
397
    buf[len] = 0;
4658
397
    if (!IS_CHAR(cur)) {
4659
5
  xmlFatalErr(ctxt, XML_ERR_LITERAL_NOT_FINISHED, NULL);
4660
392
    } else {
4661
392
  NEXT;
4662
392
    }
4663
397
    return(buf);
4664
397
}
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
397
xmlParsePubidLiteral(xmlParserCtxtPtr ctxt) {
4681
397
    xmlChar *buf = NULL;
4682
397
    int len = 0;
4683
397
    int size = XML_PARSER_BUFFER_SIZE;
4684
397
    int maxLength = (ctxt->options & XML_PARSE_HUGE) ?
4685
0
                    XML_MAX_TEXT_LENGTH :
4686
397
                    XML_MAX_NAME_LENGTH;
4687
397
    xmlChar cur;
4688
397
    xmlChar stop;
4689
4690
397
    if (RAW == '"') {
4691
397
        NEXT;
4692
397
  stop = '"';
4693
397
    } else if (RAW == '\'') {
4694
0
        NEXT;
4695
0
  stop = '\'';
4696
0
    } else {
4697
0
  xmlFatalErr(ctxt, XML_ERR_LITERAL_NOT_STARTED, NULL);
4698
0
  return(NULL);
4699
0
    }
4700
397
    buf = xmlMalloc(size);
4701
397
    if (buf == NULL) {
4702
0
  xmlErrMemory(ctxt);
4703
0
  return(NULL);
4704
0
    }
4705
397
    cur = CUR;
4706
1.58k
    while ((IS_PUBIDCHAR_CH(cur)) && (cur != stop) &&
4707
1.58k
           (PARSER_STOPPED(ctxt) == 0)) { /* checked */
4708
1.19k
  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
1.19k
  buf[len++] = cur;
4728
1.19k
  NEXT;
4729
1.19k
  cur = CUR;
4730
1.19k
    }
4731
397
    buf[len] = 0;
4732
397
    if (cur != stop) {
4733
0
  xmlFatalErr(ctxt, XML_ERR_LITERAL_NOT_FINISHED, NULL);
4734
397
    } else {
4735
397
  NEXTL(1);
4736
397
    }
4737
397
    return(buf);
4738
397
}
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
937k
              int isBlank) {
4783
937k
    int checkBlanks;
4784
4785
937k
    if ((ctxt->sax == NULL) || (ctxt->disableSAX))
4786
0
        return;
4787
4788
937k
    checkBlanks = (!ctxt->keepBlanks) ||
4789
937k
                  (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
937k
    if ((checkBlanks) &&
4797
937k
        (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
937k
    } else {
4802
937k
        if (ctxt->sax->characters != NULL)
4803
937k
            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
937k
        if ((checkBlanks) && (*ctxt->space == -1))
4810
0
            *ctxt->space = -2;
4811
937k
    }
4812
937k
}
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
2.54M
xmlParseCharDataInternal(xmlParserCtxtPtr ctxt, int partial) {
4831
2.54M
    const xmlChar *in;
4832
2.54M
    int nbchar = 0;
4833
2.54M
    int line = ctxt->input->line;
4834
2.54M
    int col = ctxt->input->col;
4835
2.54M
    int ccol;
4836
4837
2.54M
    GROW;
4838
    /*
4839
     * Accelerated common case where input don't need to be
4840
     * modified before passing it to the handler.
4841
     */
4842
2.54M
    in = ctxt->input->cur;
4843
2.54M
    do {
4844
2.57M
get_more_space:
4845
2.62M
        while (*in == 0x20) { in++; ctxt->input->col++; }
4846
2.57M
        if (*in == 0xA) {
4847
1.18M
            do {
4848
1.18M
                ctxt->input->line++; ctxt->input->col = 1;
4849
1.18M
                in++;
4850
1.18M
            } while (*in == 0xA);
4851
27.0k
            goto get_more_space;
4852
27.0k
        }
4853
2.54M
        if (*in == '<') {
4854
8.31k
            nbchar = in - ctxt->input->cur;
4855
8.31k
            if (nbchar > 0) {
4856
8.31k
                const xmlChar *tmp = ctxt->input->cur;
4857
8.31k
                ctxt->input->cur = in;
4858
4859
8.31k
                xmlCharacters(ctxt, tmp, nbchar, 1);
4860
8.31k
            }
4861
8.31k
            return;
4862
8.31k
        }
4863
4864
2.56M
get_more:
4865
2.56M
        ccol = ctxt->input->col;
4866
7.61M
        while (test_char_data[*in]) {
4867
5.04M
            in++;
4868
5.04M
            ccol++;
4869
5.04M
        }
4870
2.56M
        ctxt->input->col = ccol;
4871
2.56M
        if (*in == 0xA) {
4872
1.38M
            do {
4873
1.38M
                ctxt->input->line++; ctxt->input->col = 1;
4874
1.38M
                in++;
4875
1.38M
            } while (*in == 0xA);
4876
25.2k
            goto get_more;
4877
25.2k
        }
4878
2.54M
        if (*in == ']') {
4879
5.94k
            if ((in[1] == ']') && (in[2] == '>')) {
4880
1.29k
                xmlFatalErr(ctxt, XML_ERR_MISPLACED_CDATA_END, NULL);
4881
1.29k
                ctxt->input->cur = in + 1;
4882
1.29k
                return;
4883
1.29k
            }
4884
4.64k
            if ((!partial) || (ctxt->input->end - in >= 2)) {
4885
4.64k
                in++;
4886
4.64k
                ctxt->input->col++;
4887
4.64k
                goto get_more;
4888
4.64k
            }
4889
4.64k
        }
4890
2.53M
        nbchar = in - ctxt->input->cur;
4891
2.53M
        if (nbchar > 0) {
4892
454k
            const xmlChar *tmp = ctxt->input->cur;
4893
454k
            ctxt->input->cur = in;
4894
4895
454k
            xmlCharacters(ctxt, tmp, nbchar, 0);
4896
4897
454k
            line = ctxt->input->line;
4898
454k
            col = ctxt->input->col;
4899
454k
        }
4900
2.53M
        ctxt->input->cur = in;
4901
2.53M
        if (*in == 0xD) {
4902
3.12k
            in++;
4903
3.12k
            if (*in == 0xA) {
4904
249
                ctxt->input->cur = in;
4905
249
                in++;
4906
249
                ctxt->input->line++; ctxt->input->col = 1;
4907
249
                continue; /* while */
4908
249
            }
4909
2.88k
            in--;
4910
2.88k
        }
4911
2.53M
        if (*in == '<') {
4912
357k
            return;
4913
357k
        }
4914
2.17M
        if (*in == '&') {
4915
2.30k
            return;
4916
2.30k
        }
4917
2.17M
        if ((partial) && (*in == ']') && (ctxt->input->end - in < 2)) {
4918
0
            return;
4919
0
        }
4920
2.17M
        SHRINK;
4921
2.17M
        GROW;
4922
2.17M
        in = ctxt->input->cur;
4923
2.17M
    } while (((*in >= 0x20) && (*in <= 0x7F)) ||
4924
2.17M
             (*in == 0x09) || (*in == 0x0a));
4925
2.17M
    ctxt->input->line = line;
4926
2.17M
    ctxt->input->col = col;
4927
2.17M
    xmlParseCharDataComplex(ctxt, partial);
4928
2.17M
}
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
2.17M
xmlParseCharDataComplex(xmlParserCtxtPtr ctxt, int partial) {
4943
2.17M
    xmlChar buf[XML_PARSER_BIG_BUFFER_SIZE + 5];
4944
2.17M
    int nbchar = 0;
4945
2.17M
    int cur, l;
4946
4947
2.17M
    cur = xmlCurrentCharRecover(ctxt, &l);
4948
37.0M
    while ((cur != '<') && /* checked */
4949
37.0M
           (cur != '&') &&
4950
37.0M
           ((!partial) || (cur != ']') ||
4951
36.9M
            (ctxt->input->end - ctxt->input->cur >= 2)) &&
4952
37.0M
     (IS_CHAR(cur))) {
4953
34.9M
  if ((cur == ']') && (NXT(1) == ']') && (NXT(2) == '>')) {
4954
8.59k
      xmlFatalErr(ctxt, XML_ERR_MISPLACED_CDATA_END, NULL);
4955
8.59k
  }
4956
34.9M
  COPY_BUF(buf, nbchar, cur);
4957
  /* move current position before possible calling of ctxt->sax->characters */
4958
34.9M
  NEXTL(l);
4959
34.9M
  if (nbchar >= XML_PARSER_BIG_BUFFER_SIZE) {
4960
304k
      buf[nbchar] = 0;
4961
4962
304k
            xmlCharacters(ctxt, buf, nbchar, 0);
4963
304k
      nbchar = 0;
4964
304k
            SHRINK;
4965
304k
  }
4966
34.9M
  cur = xmlCurrentCharRecover(ctxt, &l);
4967
34.9M
    }
4968
2.17M
    if (nbchar != 0) {
4969
170k
        buf[nbchar] = 0;
4970
4971
170k
        xmlCharacters(ctxt, buf, nbchar, 0);
4972
170k
    }
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
2.17M
    if (ctxt->input->cur < ctxt->input->end) {
4981
2.17M
        if ((cur == 0) && (CUR != 0)) {
4982
5
            if (partial == 0) {
4983
5
                xmlFatalErrMsgInt(ctxt, XML_ERR_INVALID_CHAR,
4984
5
                        "Incomplete UTF-8 sequence starting with %02X\n", CUR);
4985
5
                NEXTL(1);
4986
5
            }
4987
2.17M
        } else if ((cur != '<') && (cur != '&') && (cur != ']')) {
4988
            /* Generate the error and skip the offending character */
4989
2.03M
            xmlFatalErrMsgInt(ctxt, XML_ERR_INVALID_CHAR,
4990
2.03M
                              "PCDATA invalid Char value %d\n", cur);
4991
2.03M
            NEXTL(l);
4992
2.03M
        }
4993
2.17M
    }
4994
2.17M
}
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
1.46k
xmlParseExternalID(xmlParserCtxtPtr ctxt, xmlChar **publicID, int strict) {
5034
1.46k
    xmlChar *URI = NULL;
5035
5036
1.46k
    *publicID = NULL;
5037
1.46k
    if (CMP6(CUR_PTR, 'S', 'Y', 'S', 'T', 'E', 'M')) {
5038
0
        SKIP(6);
5039
0
  if (SKIP_BLANKS == 0) {
5040
0
      xmlFatalErrMsg(ctxt, XML_ERR_SPACE_REQUIRED,
5041
0
                     "Space required after 'SYSTEM'\n");
5042
0
  }
5043
0
  URI = xmlParseSystemLiteral(ctxt);
5044
0
  if (URI == NULL) {
5045
0
      xmlFatalErr(ctxt, XML_ERR_URI_REQUIRED, NULL);
5046
0
        }
5047
1.46k
    } else if (CMP6(CUR_PTR, 'P', 'U', 'B', 'L', 'I', 'C')) {
5048
397
        SKIP(6);
5049
397
  if (SKIP_BLANKS == 0) {
5050
0
      xmlFatalErrMsg(ctxt, XML_ERR_SPACE_REQUIRED,
5051
0
        "Space required after 'PUBLIC'\n");
5052
0
  }
5053
397
  *publicID = xmlParsePubidLiteral(ctxt);
5054
397
  if (*publicID == NULL) {
5055
0
      xmlFatalErr(ctxt, XML_ERR_PUBID_REQUIRED, NULL);
5056
0
  }
5057
397
  if (strict) {
5058
      /*
5059
       * We don't handle [83] so "S SystemLiteral" is required.
5060
       */
5061
397
      if (SKIP_BLANKS == 0) {
5062
0
    xmlFatalErrMsg(ctxt, XML_ERR_SPACE_REQUIRED,
5063
0
      "Space required after the Public Identifier\n");
5064
0
      }
5065
397
  } 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
0
      if (SKIP_BLANKS == 0) return(NULL);
5073
0
      if ((CUR != '\'') && (CUR != '"')) return(NULL);
5074
0
  }
5075
397
  URI = xmlParseSystemLiteral(ctxt);
5076
397
  if (URI == NULL) {
5077
0
      xmlFatalErr(ctxt, XML_ERR_URI_REQUIRED, NULL);
5078
0
        }
5079
397
    }
5080
1.46k
    return(URI);
5081
1.46k
}
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
2.84k
                       size_t len, size_t size) {
5100
2.84k
    int q, ql;
5101
2.84k
    int r, rl;
5102
2.84k
    int cur, l;
5103
2.84k
    int maxLength = (ctxt->options & XML_PARSE_HUGE) ?
5104
0
                    XML_MAX_HUGE_LENGTH :
5105
2.84k
                    XML_MAX_TEXT_LENGTH;
5106
5107
2.84k
    if (buf == NULL) {
5108
49
        len = 0;
5109
49
  size = XML_PARSER_BUFFER_SIZE;
5110
49
  buf = xmlMalloc(size);
5111
49
  if (buf == NULL) {
5112
0
      xmlErrMemory(ctxt);
5113
0
      return;
5114
0
  }
5115
49
    }
5116
2.84k
    q = xmlCurrentCharRecover(ctxt, &ql);
5117
2.84k
    if (q == 0)
5118
1.10k
        goto not_terminated;
5119
1.74k
    if (!IS_CHAR(q)) {
5120
198
        xmlFatalErrMsgInt(ctxt, XML_ERR_INVALID_CHAR,
5121
198
                          "xmlParseComment: invalid xmlChar value %d\n",
5122
198
                    q);
5123
198
  xmlFree (buf);
5124
198
  return;
5125
198
    }
5126
1.54k
    NEXTL(ql);
5127
1.54k
    r = xmlCurrentCharRecover(ctxt, &rl);
5128
1.54k
    if (r == 0)
5129
0
        goto not_terminated;
5130
1.54k
    if (!IS_CHAR(r)) {
5131
89
        xmlFatalErrMsgInt(ctxt, XML_ERR_INVALID_CHAR,
5132
89
                          "xmlParseComment: invalid xmlChar value %d\n",
5133
89
                    r);
5134
89
  xmlFree (buf);
5135
89
  return;
5136
89
    }
5137
1.45k
    NEXTL(rl);
5138
1.45k
    cur = xmlCurrentCharRecover(ctxt, &l);
5139
1.45k
    if (cur == 0)
5140
731
        goto not_terminated;
5141
30.7k
    while (IS_CHAR(cur) && /* checked */
5142
30.7k
           ((cur != '>') ||
5143
30.4k
      (r != '-') || (q != '-'))) {
5144
30.0k
  if ((r == '-') && (q == '-')) {
5145
595
      xmlFatalErr(ctxt, XML_ERR_HYPHEN_IN_COMMENT, NULL);
5146
595
  }
5147
30.0k
  if (len + 5 >= size) {
5148
52
      xmlChar *tmp;
5149
52
            int newSize;
5150
5151
52
      newSize = xmlGrowCapacity(size, 1, 1, maxLength);
5152
52
            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
52
      tmp = xmlRealloc(buf, newSize);
5159
52
      if (tmp == NULL) {
5160
0
    xmlErrMemory(ctxt);
5161
0
    xmlFree(buf);
5162
0
    return;
5163
0
      }
5164
52
      buf = tmp;
5165
52
            size = newSize;
5166
52
  }
5167
30.0k
  COPY_BUF(buf, len, q);
5168
5169
30.0k
  q = r;
5170
30.0k
  ql = rl;
5171
30.0k
  r = cur;
5172
30.0k
  rl = l;
5173
5174
30.0k
  NEXTL(l);
5175
30.0k
  cur = xmlCurrentCharRecover(ctxt, &l);
5176
5177
30.0k
    }
5178
728
    buf[len] = 0;
5179
728
    if (cur == 0) {
5180
44
  xmlFatalErrMsgStr(ctxt, XML_ERR_COMMENT_NOT_FINISHED,
5181
44
                       "Comment not terminated \n<!--%.50s\n", buf);
5182
684
    } else if (!IS_CHAR(cur)) {
5183
242
        xmlFatalErrMsgInt(ctxt, XML_ERR_INVALID_CHAR,
5184
242
                          "xmlParseComment: invalid xmlChar value %d\n",
5185
242
                    cur);
5186
442
    } else {
5187
442
        NEXT;
5188
442
  if ((ctxt->sax != NULL) && (ctxt->sax->comment != NULL) &&
5189
442
      (!ctxt->disableSAX))
5190
442
      ctxt->sax->comment(ctxt->userData, buf);
5191
442
    }
5192
728
    xmlFree(buf);
5193
728
    return;
5194
1.83k
not_terminated:
5195
1.83k
    xmlFatalErrMsgStr(ctxt, XML_ERR_COMMENT_NOT_FINISHED,
5196
1.83k
       "Comment not terminated\n", NULL);
5197
1.83k
    xmlFree(buf);
5198
1.83k
}
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
7.01k
xmlParseComment(xmlParserCtxtPtr ctxt) {
5215
7.01k
    xmlChar *buf = NULL;
5216
7.01k
    size_t size = XML_PARSER_BUFFER_SIZE;
5217
7.01k
    size_t len = 0;
5218
7.01k
    size_t maxLength = (ctxt->options & XML_PARSE_HUGE) ?
5219
0
                       XML_MAX_HUGE_LENGTH :
5220
7.01k
                       XML_MAX_TEXT_LENGTH;
5221
7.01k
    const xmlChar *in;
5222
7.01k
    size_t nbchar = 0;
5223
7.01k
    int ccol;
5224
5225
    /*
5226
     * Check that there is a comment right here.
5227
     */
5228
7.01k
    if ((RAW != '<') || (NXT(1) != '!'))
5229
0
        return;
5230
7.01k
    SKIP(2);
5231
7.01k
    if ((RAW != '-') || (NXT(1) != '-'))
5232
0
        return;
5233
7.01k
    SKIP(2);
5234
7.01k
    GROW;
5235
5236
    /*
5237
     * Accelerated common case where input don't need to be
5238
     * modified before passing it to the handler.
5239
     */
5240
7.01k
    in = ctxt->input->cur;
5241
7.03k
    do {
5242
7.03k
  if (*in == 0xA) {
5243
80
      do {
5244
80
    ctxt->input->line++; ctxt->input->col = 1;
5245
80
    in++;
5246
80
      } while (*in == 0xA);
5247
80
  }
5248
11.0k
get_more:
5249
11.0k
        ccol = ctxt->input->col;
5250
107k
  while (((*in > '-') && (*in <= 0x7F)) ||
5251
107k
         ((*in >= 0x20) && (*in < '-')) ||
5252
107k
         (*in == 0x09)) {
5253
96.2k
        in++;
5254
96.2k
        ccol++;
5255
96.2k
  }
5256
11.0k
  ctxt->input->col = ccol;
5257
11.0k
  if (*in == 0xA) {
5258
743
      do {
5259
743
    ctxt->input->line++; ctxt->input->col = 1;
5260
743
    in++;
5261
743
      } while (*in == 0xA);
5262
723
      goto get_more;
5263
723
  }
5264
10.3k
  nbchar = in - ctxt->input->cur;
5265
  /*
5266
   * save current set of data
5267
   */
5268
10.3k
  if (nbchar > 0) {
5269
7.44k
            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
7.44k
            if (buf == NULL) {
5276
5.78k
                if ((*in == '-') && (in[1] == '-'))
5277
3.72k
                    size = nbchar + 1;
5278
2.05k
                else
5279
2.05k
                    size = XML_PARSER_BUFFER_SIZE + nbchar;
5280
5.78k
                buf = xmlMalloc(size);
5281
5.78k
                if (buf == NULL) {
5282
0
                    xmlErrMemory(ctxt);
5283
0
                    return;
5284
0
                }
5285
5.78k
                len = 0;
5286
5.78k
            } else if (len + nbchar + 1 >= size) {
5287
759
                xmlChar *new_buf;
5288
759
                size += len + nbchar + XML_PARSER_BUFFER_SIZE;
5289
759
                new_buf = xmlRealloc(buf, size);
5290
759
                if (new_buf == NULL) {
5291
0
                    xmlErrMemory(ctxt);
5292
0
                    xmlFree(buf);
5293
0
                    return;
5294
0
                }
5295
759
                buf = new_buf;
5296
759
            }
5297
7.44k
            memcpy(&buf[len], ctxt->input->cur, nbchar);
5298
7.44k
            len += nbchar;
5299
7.44k
            buf[len] = 0;
5300
7.44k
  }
5301
10.3k
  ctxt->input->cur = in;
5302
10.3k
  if (*in == 0xA) {
5303
0
      in++;
5304
0
      ctxt->input->line++; ctxt->input->col = 1;
5305
0
  }
5306
10.3k
  if (*in == 0xD) {
5307
555
      in++;
5308
555
      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
555
      in--;
5315
555
  }
5316
10.3k
  SHRINK;
5317
10.3k
  GROW;
5318
10.3k
  in = ctxt->input->cur;
5319
10.3k
  if (*in == '-') {
5320
7.49k
      if (in[1] == '-') {
5321
5.25k
          if (in[2] == '>') {
5322
4.16k
        SKIP(3);
5323
4.16k
        if ((ctxt->sax != NULL) && (ctxt->sax->comment != NULL) &&
5324
4.16k
            (!ctxt->disableSAX)) {
5325
4.16k
      if (buf != NULL)
5326
2.98k
          ctxt->sax->comment(ctxt->userData, buf);
5327
1.18k
      else
5328
1.18k
          ctxt->sax->comment(ctxt->userData, BAD_CAST "");
5329
4.16k
        }
5330
4.16k
        if (buf != NULL)
5331
2.98k
            xmlFree(buf);
5332
4.16k
        return;
5333
4.16k
    }
5334
1.09k
    if (buf != NULL) {
5335
743
        xmlFatalErrMsgStr(ctxt, XML_ERR_HYPHEN_IN_COMMENT,
5336
743
                          "Double hyphen within comment: "
5337
743
                                      "<!--%.50s\n",
5338
743
              buf);
5339
743
    } else
5340
348
        xmlFatalErrMsgStr(ctxt, XML_ERR_HYPHEN_IN_COMMENT,
5341
348
                          "Double hyphen within comment\n", NULL);
5342
1.09k
    in++;
5343
1.09k
    ctxt->input->col++;
5344
1.09k
      }
5345
3.32k
      in++;
5346
3.32k
      ctxt->input->col++;
5347
3.32k
      goto get_more;
5348
7.49k
  }
5349
10.3k
    } while (((*in >= 0x20) && (*in <= 0x7F)) || (*in == 0x09) || (*in == 0x0a));
5350
2.84k
    xmlParseCommentComplex(ctxt, buf, len, size);
5351
2.84k
}
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
7.75k
xmlParsePITarget(xmlParserCtxtPtr ctxt) {
5369
7.75k
    const xmlChar *name;
5370
5371
7.75k
    name = xmlParseName(ctxt);
5372
7.75k
    if ((name != NULL) &&
5373
7.75k
        ((name[0] == 'x') || (name[0] == 'X')) &&
5374
7.75k
        ((name[1] == 'm') || (name[1] == 'M')) &&
5375
7.75k
        ((name[2] == 'l') || (name[2] == 'L'))) {
5376
34
  int i;
5377
34
  if ((name[0] == 'x') && (name[1] == 'm') &&
5378
34
      (name[2] == 'l') && (name[3] == 0)) {
5379
0
      xmlFatalErrMsg(ctxt, XML_ERR_RESERVED_XML_NAME,
5380
0
     "XML declaration allowed only at the start of the document\n");
5381
0
      return(name);
5382
34
  } else if (name[3] == 0) {
5383
12
      xmlFatalErr(ctxt, XML_ERR_RESERVED_XML_NAME, NULL);
5384
12
      return(name);
5385
12
  }
5386
66
  for (i = 0;;i++) {
5387
66
      if (xmlW3CPIs[i] == NULL) break;
5388
44
      if (xmlStrEqual(name, (const xmlChar *)xmlW3CPIs[i]))
5389
0
          return(name);
5390
44
  }
5391
22
  xmlWarningMsg(ctxt, XML_ERR_RESERVED_XML_NAME,
5392
22
          "xmlParsePITarget: invalid name prefix 'xml'\n",
5393
22
          NULL, NULL);
5394
22
    }
5395
7.73k
    if ((name != NULL) && (xmlStrchr(name, ':') != NULL)) {
5396
21
  xmlNsErr(ctxt, XML_NS_ERR_COLON,
5397
21
     "colons are forbidden from PI names '%s'\n", name, NULL, NULL);
5398
21
    }
5399
7.73k
    return(name);
5400
7.75k
}
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
7.75k
xmlParsePI(xmlParserCtxtPtr ctxt) {
5485
7.75k
    xmlChar *buf = NULL;
5486
7.75k
    size_t len = 0;
5487
7.75k
    size_t size = XML_PARSER_BUFFER_SIZE;
5488
7.75k
    size_t maxLength = (ctxt->options & XML_PARSE_HUGE) ?
5489
0
                       XML_MAX_HUGE_LENGTH :
5490
7.75k
                       XML_MAX_TEXT_LENGTH;
5491
7.75k
    int cur, l;
5492
7.75k
    const xmlChar *target;
5493
5494
7.75k
    if ((RAW == '<') && (NXT(1) == '?')) {
5495
  /*
5496
   * this is a Processing Instruction.
5497
   */
5498
7.75k
  SKIP(2);
5499
5500
  /*
5501
   * Parse the target name and check for special support like
5502
   * namespace.
5503
   */
5504
7.75k
        target = xmlParsePITarget(ctxt);
5505
7.75k
  if (target != NULL) {
5506
6.67k
      if ((RAW == '?') && (NXT(1) == '>')) {
5507
4.79k
    SKIP(2);
5508
5509
    /*
5510
     * SAX: PI detected.
5511
     */
5512
4.79k
    if ((ctxt->sax) && (!ctxt->disableSAX) &&
5513
4.79k
        (ctxt->sax->processingInstruction != NULL))
5514
4.79k
        ctxt->sax->processingInstruction(ctxt->userData,
5515
4.79k
                                         target, NULL);
5516
4.79k
    return;
5517
4.79k
      }
5518
1.88k
      buf = xmlMalloc(size);
5519
1.88k
      if (buf == NULL) {
5520
0
    xmlErrMemory(ctxt);
5521
0
    return;
5522
0
      }
5523
1.88k
      if (SKIP_BLANKS == 0) {
5524
1.19k
    xmlFatalErrMsgStr(ctxt, XML_ERR_SPACE_REQUIRED,
5525
1.19k
        "ParsePI: PI %s space expected\n", target);
5526
1.19k
      }
5527
1.88k
      cur = xmlCurrentCharRecover(ctxt, &l);
5528
8.62M
      while (IS_CHAR(cur) && /* checked */
5529
8.62M
       ((cur != '?') || (NXT(1) != '>'))) {
5530
8.61M
    if (len + 5 >= size) {
5531
1.01k
        xmlChar *tmp;
5532
1.01k
                    int newSize;
5533
5534
1.01k
                    newSize = xmlGrowCapacity(size, 1, 1, maxLength);
5535
1.01k
                    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
1.01k
        tmp = xmlRealloc(buf, newSize);
5542
1.01k
        if (tmp == NULL) {
5543
0
      xmlErrMemory(ctxt);
5544
0
      xmlFree(buf);
5545
0
      return;
5546
0
        }
5547
1.01k
        buf = tmp;
5548
1.01k
                    size = newSize;
5549
1.01k
    }
5550
8.61M
    COPY_BUF(buf, len, cur);
5551
8.61M
    NEXTL(l);
5552
8.61M
    cur = xmlCurrentCharRecover(ctxt, &l);
5553
8.61M
      }
5554
1.88k
      buf[len] = 0;
5555
1.88k
      if (cur != '?') {
5556
745
    xmlFatalErrMsgStr(ctxt, XML_ERR_PI_NOT_FINISHED,
5557
745
          "ParsePI: PI %s never end ...\n", target);
5558
1.14k
      } else {
5559
1.14k
    SKIP(2);
5560
5561
1.14k
#ifdef LIBXML_CATALOG_ENABLED
5562
1.14k
    if ((ctxt->inSubset == 0) &&
5563
1.14k
        (xmlStrEqual(target, XML_CATALOG_PI))) {
5564
47
        xmlCatalogAllow allow = xmlCatalogGetDefaults();
5565
5566
47
        if ((ctxt->options & XML_PARSE_CATALOG_PI) &&
5567
47
                        ((allow == XML_CATA_ALLOW_DOCUMENT) ||
5568
0
       (allow == XML_CATA_ALLOW_ALL)))
5569
0
      xmlParseCatalogPI(ctxt, buf);
5570
47
    }
5571
1.14k
#endif
5572
5573
    /*
5574
     * SAX: PI detected.
5575
     */
5576
1.14k
    if ((ctxt->sax) && (!ctxt->disableSAX) &&
5577
1.14k
        (ctxt->sax->processingInstruction != NULL))
5578
1.14k
        ctxt->sax->processingInstruction(ctxt->userData,
5579
1.14k
                                         target, buf);
5580
1.14k
      }
5581
1.88k
      xmlFree(buf);
5582
1.88k
  } else {
5583
1.07k
      xmlFatalErr(ctxt, XML_ERR_PI_NOT_STARTED, NULL);
5584
1.07k
  }
5585
7.75k
    }
5586
7.75k
}
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
0
xmlParseNotationDecl(xmlParserCtxtPtr ctxt) {
5608
0
    const xmlChar *name;
5609
0
    xmlChar *Pubid;
5610
0
    xmlChar *Systemid;
5611
5612
0
    if ((CUR != '<') || (NXT(1) != '!'))
5613
0
        return;
5614
0
    SKIP(2);
5615
5616
0
    if (CMP8(CUR_PTR, 'N', 'O', 'T', 'A', 'T', 'I', 'O', 'N')) {
5617
0
  int inputid = ctxt->input->id;
5618
0
  SKIP(8);
5619
0
  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
0
        name = xmlParseName(ctxt);
5626
0
  if (name == NULL) {
5627
0
      xmlFatalErr(ctxt, XML_ERR_NOTATION_NOT_STARTED, NULL);
5628
0
      return;
5629
0
  }
5630
0
  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
0
  if (SKIP_BLANKS_PE == 0) {
5636
0
      xmlFatalErrMsg(ctxt, XML_ERR_SPACE_REQUIRED,
5637
0
         "Space required after the NOTATION name'\n");
5638
0
      return;
5639
0
  }
5640
5641
  /*
5642
   * Parse the IDs.
5643
   */
5644
0
  Systemid = xmlParseExternalID(ctxt, &Pubid, 0);
5645
0
  SKIP_BLANKS_PE;
5646
5647
0
  if (RAW == '>') {
5648
0
      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
0
      NEXT;
5654
0
      if ((ctxt->sax != NULL) && (!ctxt->disableSAX) &&
5655
0
    (ctxt->sax->notationDecl != NULL))
5656
0
    ctxt->sax->notationDecl(ctxt->userData, name, Pubid, Systemid);
5657
0
  } else {
5658
0
      xmlFatalErr(ctxt, XML_ERR_NOTATION_NOT_FINISHED, NULL);
5659
0
  }
5660
0
  if (Systemid != NULL) xmlFree(Systemid);
5661
0
  if (Pubid != NULL) xmlFree(Pubid);
5662
0
    }
5663
0
}
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
22.7k
xmlParseEntityDecl(xmlParserCtxtPtr ctxt) {
5691
22.7k
    const xmlChar *name = NULL;
5692
22.7k
    xmlChar *value = NULL;
5693
22.7k
    xmlChar *URI = NULL, *literal = NULL;
5694
22.7k
    const xmlChar *ndata = NULL;
5695
22.7k
    int isParameter = 0;
5696
22.7k
    xmlChar *orig = NULL;
5697
5698
22.7k
    if ((CUR != '<') || (NXT(1) != '!'))
5699
0
        return;
5700
22.7k
    SKIP(2);
5701
5702
    /* GROW; done in the caller */
5703
22.7k
    if (CMP6(CUR_PTR, 'E', 'N', 'T', 'I', 'T', 'Y')) {
5704
22.7k
  int inputid = ctxt->input->id;
5705
22.7k
  SKIP(6);
5706
22.7k
  if (SKIP_BLANKS_PE == 0) {
5707
4.87k
      xmlFatalErrMsg(ctxt, XML_ERR_SPACE_REQUIRED,
5708
4.87k
         "Space required after '<!ENTITY'\n");
5709
4.87k
  }
5710
5711
22.7k
  if (RAW == '%') {
5712
4.87k
      NEXT;
5713
4.87k
      if (SKIP_BLANKS_PE == 0) {
5714
4.87k
    xmlFatalErrMsg(ctxt, XML_ERR_SPACE_REQUIRED,
5715
4.87k
             "Space required after '%%'\n");
5716
4.87k
      }
5717
4.87k
      isParameter = 1;
5718
4.87k
  }
5719
5720
22.7k
        name = xmlParseName(ctxt);
5721
22.7k
  if (name == NULL) {
5722
3
      xmlFatalErrMsg(ctxt, XML_ERR_NAME_REQUIRED,
5723
3
                     "xmlParseEntityDecl: no name\n");
5724
3
            return;
5725
3
  }
5726
22.7k
  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
22.7k
  if (SKIP_BLANKS_PE == 0) {
5732
3.01k
      xmlFatalErrMsg(ctxt, XML_ERR_SPACE_REQUIRED,
5733
3.01k
         "Space required after the entity name\n");
5734
3.01k
  }
5735
5736
  /*
5737
   * handle the various case of definitions...
5738
   */
5739
22.7k
  if (isParameter) {
5740
4.87k
      if ((RAW == '"') || (RAW == '\'')) {
5741
4.87k
          value = xmlParseEntityValue(ctxt, &orig);
5742
4.87k
    if (value) {
5743
4.86k
        if ((ctxt->sax != NULL) &&
5744
4.86k
      (!ctxt->disableSAX) && (ctxt->sax->entityDecl != NULL))
5745
4.86k
      ctxt->sax->entityDecl(ctxt->userData, name,
5746
4.86k
                        XML_INTERNAL_PARAMETER_ENTITY,
5747
4.86k
            NULL, NULL, value);
5748
4.86k
    }
5749
4.87k
      } 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
17.8k
  } else {
5768
17.8k
      if ((RAW == '"') || (RAW == '\'')) {
5769
16.6k
          value = xmlParseEntityValue(ctxt, &orig);
5770
16.6k
    if ((ctxt->sax != NULL) &&
5771
16.6k
        (!ctxt->disableSAX) && (ctxt->sax->entityDecl != NULL))
5772
16.6k
        ctxt->sax->entityDecl(ctxt->userData, name,
5773
16.6k
        XML_INTERNAL_GENERAL_ENTITY,
5774
16.6k
        NULL, NULL, value);
5775
    /*
5776
     * For expat compatibility in SAX mode.
5777
     */
5778
16.6k
    if ((ctxt->myDoc == NULL) ||
5779
16.6k
        (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
16.6k
      } else {
5801
1.16k
          URI = xmlParseExternalID(ctxt, &literal, 1);
5802
1.16k
    if ((URI == NULL) && (literal == NULL)) {
5803
766
        xmlFatalErr(ctxt, XML_ERR_VALUE_REQUIRED, NULL);
5804
766
    }
5805
1.16k
    if (URI) {
5806
397
                    if (xmlStrchr(URI, '#')) {
5807
294
                        xmlFatalErr(ctxt, XML_ERR_URI_FRAGMENT, NULL);
5808
294
                    }
5809
397
    }
5810
1.16k
    if ((RAW != '>') && (SKIP_BLANKS_PE == 0)) {
5811
5
        xmlFatalErrMsg(ctxt, XML_ERR_SPACE_REQUIRED,
5812
5
           "Space required before 'NDATA'\n");
5813
5
    }
5814
1.16k
    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
1.16k
    } else {
5826
1.16k
        if ((ctxt->sax != NULL) &&
5827
1.16k
            (!ctxt->disableSAX) && (ctxt->sax->entityDecl != NULL))
5828
1.16k
      ctxt->sax->entityDecl(ctxt->userData, name,
5829
1.16k
            XML_EXTERNAL_GENERAL_PARSED_ENTITY,
5830
1.16k
            literal, URI, NULL);
5831
        /*
5832
         * For expat compatibility in SAX mode.
5833
         * assuming the entity replacement was asked for
5834
         */
5835
1.16k
        if ((ctxt->replaceEntities != 0) &&
5836
1.16k
      ((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
1.16k
    }
5860
1.16k
      }
5861
17.8k
  }
5862
22.7k
  SKIP_BLANKS_PE;
5863
22.7k
  if (RAW != '>') {
5864
28
      xmlFatalErrMsgStr(ctxt, XML_ERR_ENTITY_NOT_FINISHED,
5865
28
              "xmlParseEntityDecl: entity %s not terminated\n", name);
5866
28
      xmlHaltParser(ctxt);
5867
22.6k
  } else {
5868
22.6k
      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
22.6k
      NEXT;
5874
22.6k
  }
5875
22.7k
  if (orig != NULL) {
5876
      /*
5877
       * Ugly mechanism to save the raw entity value.
5878
       */
5879
21.5k
      xmlEntityPtr cur = NULL;
5880
5881
21.5k
      if (isParameter) {
5882
4.86k
          if ((ctxt->sax != NULL) &&
5883
4.86k
        (ctxt->sax->getParameterEntity != NULL))
5884
4.86k
        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
21.5k
            if ((cur != NULL) && (cur->orig == NULL)) {
5894
419
    cur->orig = orig;
5895
419
                orig = NULL;
5896
419
      }
5897
21.5k
  }
5898
5899
22.7k
done:
5900
22.7k
  if (value != NULL) xmlFree(value);
5901
22.7k
  if (URI != NULL) xmlFree(URI);
5902
22.7k
  if (literal != NULL) xmlFree(literal);
5903
22.7k
        if (orig != NULL) xmlFree(orig);
5904
22.7k
    }
5905
22.7k
}
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
1.29k
xmlParseDefaultDecl(xmlParserCtxtPtr ctxt, xmlChar **value) {
5940
1.29k
    int val;
5941
1.29k
    xmlChar *ret;
5942
5943
1.29k
    *value = NULL;
5944
1.29k
    if (CMP9(CUR_PTR, '#', 'R', 'E', 'Q', 'U', 'I', 'R', 'E', 'D')) {
5945
0
  SKIP(9);
5946
0
  return(XML_ATTRIBUTE_REQUIRED);
5947
0
    }
5948
1.29k
    if (CMP8(CUR_PTR, '#', 'I', 'M', 'P', 'L', 'I', 'E', 'D')) {
5949
1.27k
  SKIP(8);
5950
1.27k
  return(XML_ATTRIBUTE_IMPLIED);
5951
1.27k
    }
5952
28
    val = XML_ATTRIBUTE_NONE;
5953
28
    if (CMP6(CUR_PTR, '#', 'F', 'I', 'X', 'E', 'D')) {
5954
0
  SKIP(6);
5955
0
  val = XML_ATTRIBUTE_FIXED;
5956
0
  if (SKIP_BLANKS_PE == 0) {
5957
0
      xmlFatalErrMsg(ctxt, XML_ERR_SPACE_REQUIRED,
5958
0
         "Space required after '#FIXED'\n");
5959
0
  }
5960
0
    }
5961
28
    ret = xmlParseAttValue(ctxt);
5962
28
    if (ret == NULL) {
5963
0
  xmlFatalErrMsg(ctxt, (xmlParserErrors)ctxt->errNo,
5964
0
           "Attribute default value declaration error\n");
5965
0
    } else
5966
28
        *value = ret;
5967
28
    return(val);
5968
1.29k
}
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
1
xmlParseEnumerationType(xmlParserCtxtPtr ctxt) {
6068
1
    xmlChar *name;
6069
1
    xmlEnumerationPtr ret = NULL, last = NULL, cur, tmp;
6070
6071
1
    if (RAW != '(') {
6072
1
  xmlFatalErr(ctxt, XML_ERR_ATTLIST_NOT_STARTED, NULL);
6073
1
  return(NULL);
6074
1
    }
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
1
xmlParseEnumeratedType(xmlParserCtxtPtr ctxt, xmlEnumerationPtr *tree) {
6144
1
    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
1
    *tree = xmlParseEnumerationType(ctxt);
6156
1
    if (*tree == NULL) return(0);
6157
0
    return(XML_ATTRIBUTE_ENUMERATION);
6158
1
}
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
1.29k
xmlParseAttributeType(xmlParserCtxtPtr ctxt, xmlEnumerationPtr *tree) {
6209
1.29k
    if (CMP5(CUR_PTR, 'C', 'D', 'A', 'T', 'A')) {
6210
0
  SKIP(5);
6211
0
  return(XML_ATTRIBUTE_CDATA);
6212
1.29k
     } else if (CMP6(CUR_PTR, 'I', 'D', 'R', 'E', 'F', 'S')) {
6213
0
  SKIP(6);
6214
0
  return(XML_ATTRIBUTE_IDREFS);
6215
1.29k
     } else if (CMP5(CUR_PTR, 'I', 'D', 'R', 'E', 'F')) {
6216
0
  SKIP(5);
6217
0
  return(XML_ATTRIBUTE_IDREF);
6218
1.29k
     } else if ((RAW == 'I') && (NXT(1) == 'D')) {
6219
28
        SKIP(2);
6220
28
  return(XML_ATTRIBUTE_ID);
6221
1.27k
     } else if (CMP6(CUR_PTR, 'E', 'N', 'T', 'I', 'T', 'Y')) {
6222
0
  SKIP(6);
6223
0
  return(XML_ATTRIBUTE_ENTITY);
6224
1.27k
     } else if (CMP8(CUR_PTR, 'E', 'N', 'T', 'I', 'T', 'I', 'E', 'S')) {
6225
1.27k
  SKIP(8);
6226
1.27k
  return(XML_ATTRIBUTE_ENTITIES);
6227
1.27k
     } else if (CMP8(CUR_PTR, 'N', 'M', 'T', 'O', 'K', 'E', 'N', 'S')) {
6228
0
  SKIP(8);
6229
0
  return(XML_ATTRIBUTE_NMTOKENS);
6230
1
     } 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
1
     return(xmlParseEnumeratedType(ctxt, tree));
6235
1.29k
}
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
1.27k
xmlParseAttributeListDecl(xmlParserCtxtPtr ctxt) {
6252
1.27k
    const xmlChar *elemName;
6253
1.27k
    const xmlChar *attrName;
6254
1.27k
    xmlEnumerationPtr tree;
6255
6256
1.27k
    if ((CUR != '<') || (NXT(1) != '!'))
6257
0
        return;
6258
1.27k
    SKIP(2);
6259
6260
1.27k
    if (CMP7(CUR_PTR, 'A', 'T', 'T', 'L', 'I', 'S', 'T')) {
6261
1.27k
  int inputid = ctxt->input->id;
6262
6263
1.27k
  SKIP(7);
6264
1.27k
  if (SKIP_BLANKS_PE == 0) {
6265
0
      xmlFatalErrMsg(ctxt, XML_ERR_SPACE_REQUIRED,
6266
0
                     "Space required after '<!ATTLIST'\n");
6267
0
  }
6268
1.27k
        elemName = xmlParseName(ctxt);
6269
1.27k
  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
1.27k
  SKIP_BLANKS_PE;
6275
1.27k
  GROW;
6276
2.57k
  while ((RAW != '>') && (PARSER_STOPPED(ctxt) == 0)) {
6277
1.30k
      int type;
6278
1.30k
      int def;
6279
1.30k
      xmlChar *defaultValue = NULL;
6280
6281
1.30k
      GROW;
6282
1.30k
            tree = NULL;
6283
1.30k
      attrName = xmlParseName(ctxt);
6284
1.30k
      if (attrName == NULL) {
6285
0
    xmlFatalErrMsg(ctxt, XML_ERR_NAME_REQUIRED,
6286
0
             "ATTLIST: no name for Attribute\n");
6287
0
    break;
6288
0
      }
6289
1.30k
      GROW;
6290
1.30k
      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
1.29k
      type = xmlParseAttributeType(ctxt, &tree);
6297
1.29k
      if (type <= 0) {
6298
1
          break;
6299
1
      }
6300
6301
1.29k
      GROW;
6302
1.29k
      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
1.29k
      def = xmlParseDefaultDecl(ctxt, &defaultValue);
6311
1.29k
      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
1.29k
      if ((type != XML_ATTRIBUTE_CDATA) && (defaultValue != NULL))
6319
28
          xmlAttrNormalizeSpace(defaultValue, defaultValue);
6320
6321
1.29k
      GROW;
6322
1.29k
            if (RAW != '>') {
6323
28
    if (SKIP_BLANKS_PE == 0) {
6324
0
        xmlFatalErrMsg(ctxt, XML_ERR_SPACE_REQUIRED,
6325
0
      "Space required after the attribute default value\n");
6326
0
        if (defaultValue != NULL)
6327
0
      xmlFree(defaultValue);
6328
0
        if (tree != NULL)
6329
0
      xmlFreeEnumeration(tree);
6330
0
        break;
6331
0
    }
6332
28
      }
6333
1.29k
      if ((ctxt->sax != NULL) && (!ctxt->disableSAX) &&
6334
1.29k
    (ctxt->sax->attributeDecl != NULL))
6335
1.29k
    ctxt->sax->attributeDecl(ctxt->userData, elemName, attrName,
6336
1.29k
                          type, def, defaultValue, tree);
6337
0
      else if (tree != NULL)
6338
0
    xmlFreeEnumeration(tree);
6339
6340
1.29k
      if ((ctxt->sax2) && (defaultValue != NULL) &&
6341
1.29k
          (def != XML_ATTRIBUTE_IMPLIED) &&
6342
1.29k
    (def != XML_ATTRIBUTE_REQUIRED)) {
6343
28
    xmlAddDefAttrs(ctxt, elemName, attrName, defaultValue);
6344
28
      }
6345
1.29k
      if (ctxt->sax2) {
6346
1.29k
    xmlAddSpecialAttr(ctxt, elemName, attrName, type);
6347
1.29k
      }
6348
1.29k
      if (defaultValue != NULL)
6349
28
          xmlFree(defaultValue);
6350
1.29k
      GROW;
6351
1.29k
  }
6352
1.27k
  if (RAW == '>') {
6353
1.27k
      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
1.27k
      NEXT;
6359
1.27k
  }
6360
1.27k
    }
6361
1.27k
}
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
0
                                       int depth) {
6512
0
    int maxDepth = (ctxt->options & XML_PARSE_HUGE) ? 2048 : 256;
6513
0
    xmlElementContentPtr ret = NULL, cur = NULL, last = NULL, op = NULL;
6514
0
    const xmlChar *elem;
6515
0
    xmlChar type = 0;
6516
6517
0
    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
0
    SKIP_BLANKS_PE;
6524
0
    GROW;
6525
0
    if (RAW == '(') {
6526
0
  int inputid = ctxt->input->id;
6527
6528
        /* Recurse on first child */
6529
0
  NEXT;
6530
0
  SKIP_BLANKS_PE;
6531
0
        cur = ret = xmlParseElementChildrenContentDeclPriv(ctxt, inputid,
6532
0
                                                           depth + 1);
6533
0
        if (cur == NULL)
6534
0
            return(NULL);
6535
0
  SKIP_BLANKS_PE;
6536
0
  GROW;
6537
0
    } else {
6538
0
  elem = xmlParseName(ctxt);
6539
0
  if (elem == NULL) {
6540
0
      xmlFatalErr(ctxt, XML_ERR_ELEMCONTENT_NOT_STARTED, NULL);
6541
0
      return(NULL);
6542
0
  }
6543
0
        cur = ret = xmlNewDocElementContent(ctxt->myDoc, elem, XML_ELEMENT_CONTENT_ELEMENT);
6544
0
  if (cur == NULL) {
6545
0
      xmlErrMemory(ctxt);
6546
0
      return(NULL);
6547
0
  }
6548
0
  GROW;
6549
0
  if (RAW == '?') {
6550
0
      cur->ocur = XML_ELEMENT_CONTENT_OPT;
6551
0
      NEXT;
6552
0
  } else if (RAW == '*') {
6553
0
      cur->ocur = XML_ELEMENT_CONTENT_MULT;
6554
0
      NEXT;
6555
0
  } else if (RAW == '+') {
6556
0
      cur->ocur = XML_ELEMENT_CONTENT_PLUS;
6557
0
      NEXT;
6558
0
  } else {
6559
0
      cur->ocur = XML_ELEMENT_CONTENT_ONCE;
6560
0
  }
6561
0
  GROW;
6562
0
    }
6563
0
    SKIP_BLANKS_PE;
6564
0
    while ((RAW != ')') && (PARSER_STOPPED(ctxt) == 0)) {
6565
        /*
6566
   * Each loop we parse one separator and one element.
6567
   */
6568
0
        if (RAW == ',') {
6569
0
      if (type == 0) type = CUR;
6570
6571
      /*
6572
       * Detect "Name | Name , Name" error
6573
       */
6574
0
      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
0
      NEXT;
6585
6586
0
      op = xmlNewDocElementContent(ctxt->myDoc, NULL, XML_ELEMENT_CONTENT_SEQ);
6587
0
      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
0
      if (last == NULL) {
6595
0
    op->c1 = ret;
6596
0
    if (ret != NULL)
6597
0
        ret->parent = op;
6598
0
    ret = cur = op;
6599
0
      } else {
6600
0
          cur->c2 = op;
6601
0
    if (op != NULL)
6602
0
        op->parent = cur;
6603
0
    op->c1 = last;
6604
0
    if (last != NULL)
6605
0
        last->parent = op;
6606
0
    cur =op;
6607
0
    last = NULL;
6608
0
      }
6609
0
  } else if (RAW == '|') {
6610
0
      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
0
      NEXT;
6626
6627
0
      op = xmlNewDocElementContent(ctxt->myDoc, NULL, XML_ELEMENT_CONTENT_OR);
6628
0
      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
0
      if (last == NULL) {
6637
0
    op->c1 = ret;
6638
0
    if (ret != NULL)
6639
0
        ret->parent = op;
6640
0
    ret = cur = op;
6641
0
      } 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
0
  } else {
6652
0
      xmlFatalErr(ctxt, XML_ERR_ELEMCONTENT_NOT_FINISHED, NULL);
6653
0
      if ((last != NULL) && (last != ret))
6654
0
          xmlFreeDocElementContent(ctxt->myDoc, last);
6655
0
      if (ret != NULL)
6656
0
    xmlFreeDocElementContent(ctxt->myDoc, ret);
6657
0
      return(NULL);
6658
0
  }
6659
0
  GROW;
6660
0
  SKIP_BLANKS_PE;
6661
0
  GROW;
6662
0
  if (RAW == '(') {
6663
0
      int inputid = ctxt->input->id;
6664
      /* Recurse on second child */
6665
0
      NEXT;
6666
0
      SKIP_BLANKS_PE;
6667
0
      last = xmlParseElementChildrenContentDeclPriv(ctxt, inputid,
6668
0
                                                          depth + 1);
6669
0
            if (last == NULL) {
6670
0
    if (ret != NULL)
6671
0
        xmlFreeDocElementContent(ctxt->myDoc, ret);
6672
0
    return(NULL);
6673
0
            }
6674
0
      SKIP_BLANKS_PE;
6675
0
  } else {
6676
0
      elem = xmlParseName(ctxt);
6677
0
      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
0
      last = xmlNewDocElementContent(ctxt->myDoc, elem, XML_ELEMENT_CONTENT_ELEMENT);
6684
0
      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
0
      if (RAW == '?') {
6691
0
    last->ocur = XML_ELEMENT_CONTENT_OPT;
6692
0
    NEXT;
6693
0
      } else if (RAW == '*') {
6694
0
    last->ocur = XML_ELEMENT_CONTENT_MULT;
6695
0
    NEXT;
6696
0
      } else if (RAW == '+') {
6697
0
    last->ocur = XML_ELEMENT_CONTENT_PLUS;
6698
0
    NEXT;
6699
0
      } else {
6700
0
    last->ocur = XML_ELEMENT_CONTENT_ONCE;
6701
0
      }
6702
0
  }
6703
0
  SKIP_BLANKS_PE;
6704
0
  GROW;
6705
0
    }
6706
0
    if ((cur != NULL) && (last != NULL)) {
6707
0
        cur->c2 = last;
6708
0
  if (last != NULL)
6709
0
      last->parent = cur;
6710
0
    }
6711
0
    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
0
    NEXT;
6717
0
    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
0
    } 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
0
    } else if (RAW == '+') {
6748
0
  if (ret != NULL) {
6749
0
      int found = 0;
6750
6751
0
      if ((ret->ocur == XML_ELEMENT_CONTENT_OPT) ||
6752
0
          (ret->ocur == XML_ELEMENT_CONTENT_MULT))
6753
0
          ret->ocur = XML_ELEMENT_CONTENT_MULT;
6754
0
      else
6755
0
          ret->ocur = XML_ELEMENT_CONTENT_PLUS;
6756
      /*
6757
       * Some normalization:
6758
       * (a | b*)+ == (a | b)*
6759
       * (a | b?)+ == (a | b)*
6760
       */
6761
0
      while ((cur != NULL) && (cur->type == XML_ELEMENT_CONTENT_OR)) {
6762
0
    if ((cur->c1 != NULL) &&
6763
0
              ((cur->c1->ocur == XML_ELEMENT_CONTENT_OPT) ||
6764
0
         (cur->c1->ocur == XML_ELEMENT_CONTENT_MULT))) {
6765
0
        cur->c1->ocur = XML_ELEMENT_CONTENT_ONCE;
6766
0
        found = 1;
6767
0
    }
6768
0
    if ((cur->c2 != NULL) &&
6769
0
              ((cur->c2->ocur == XML_ELEMENT_CONTENT_OPT) ||
6770
0
         (cur->c2->ocur == XML_ELEMENT_CONTENT_MULT))) {
6771
0
        cur->c2->ocur = XML_ELEMENT_CONTENT_ONCE;
6772
0
        found = 1;
6773
0
    }
6774
0
    cur = cur->c2;
6775
0
      }
6776
0
      if (found)
6777
0
    ret->ocur = XML_ELEMENT_CONTENT_MULT;
6778
0
  }
6779
0
  NEXT;
6780
0
    }
6781
0
    return(ret);
6782
0
}
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
0
                           xmlElementContentPtr *result) {
6841
6842
0
    xmlElementContentPtr tree = NULL;
6843
0
    int inputid = ctxt->input->id;
6844
0
    int res;
6845
6846
0
    *result = NULL;
6847
6848
0
    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
0
    NEXT;
6854
0
    GROW;
6855
0
    SKIP_BLANKS_PE;
6856
0
    if (CMP7(CUR_PTR, '#', 'P', 'C', 'D', 'A', 'T', 'A')) {
6857
0
        tree = xmlParseElementMixedContentDecl(ctxt, inputid);
6858
0
  res = XML_ELEMENT_TYPE_MIXED;
6859
0
    } else {
6860
0
        tree = xmlParseElementChildrenContentDeclPriv(ctxt, inputid, 1);
6861
0
  res = XML_ELEMENT_TYPE_ELEMENT;
6862
0
    }
6863
0
    SKIP_BLANKS_PE;
6864
0
    *result = tree;
6865
0
    return(res);
6866
0
}
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
0
xmlParseElementDecl(xmlParserCtxtPtr ctxt) {
6885
0
    const xmlChar *name;
6886
0
    int ret = -1;
6887
0
    xmlElementContentPtr content  = NULL;
6888
6889
0
    if ((CUR != '<') || (NXT(1) != '!'))
6890
0
        return(ret);
6891
0
    SKIP(2);
6892
6893
    /* GROW; done in the caller */
6894
0
    if (CMP7(CUR_PTR, 'E', 'L', 'E', 'M', 'E', 'N', 'T')) {
6895
0
  int inputid = ctxt->input->id;
6896
6897
0
  SKIP(7);
6898
0
  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
0
        name = xmlParseName(ctxt);
6904
0
  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
0
  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
0
  if (CMP5(CUR_PTR, 'E', 'M', 'P', 'T', 'Y')) {
6914
0
      SKIP(5);
6915
      /*
6916
       * Element must always be empty.
6917
       */
6918
0
      ret = XML_ELEMENT_TYPE_EMPTY;
6919
0
  } else if ((RAW == 'A') && (NXT(1) == 'N') &&
6920
0
             (NXT(2) == 'Y')) {
6921
0
      SKIP(3);
6922
      /*
6923
       * Element is a generic container.
6924
       */
6925
0
      ret = XML_ELEMENT_TYPE_ANY;
6926
0
  } else if (RAW == '(') {
6927
0
      ret = xmlParseElementContentDecl(ctxt, name, &content);
6928
0
  } 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
0
  SKIP_BLANKS_PE;
6938
6939
0
  if (RAW != '>') {
6940
0
      xmlFatalErr(ctxt, XML_ERR_GT_REQUIRED, NULL);
6941
0
      if (content != NULL) {
6942
0
    xmlFreeDocElementContent(ctxt->myDoc, content);
6943
0
      }
6944
0
  } else {
6945
0
      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
0
      NEXT;
6952
0
      if ((ctxt->sax != NULL) && (!ctxt->disableSAX) &&
6953
0
    (ctxt->sax->elementDecl != NULL)) {
6954
0
    if (content != NULL)
6955
0
        content->parent = NULL;
6956
0
          ctxt->sax->elementDecl(ctxt->userData, name, ret,
6957
0
                           content);
6958
0
    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
0
      } else if (content != NULL) {
6968
0
    xmlFreeDocElementContent(ctxt->myDoc, content);
6969
0
      }
6970
0
  }
6971
0
    }
6972
0
    return(ret);
6973
0
}
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
25.7k
xmlParseMarkupDecl(xmlParserCtxtPtr ctxt) {
7144
25.7k
    GROW;
7145
25.7k
    if (CUR == '<') {
7146
25.7k
        if (NXT(1) == '!') {
7147
25.7k
      switch (NXT(2)) {
7148
22.7k
          case 'E':
7149
22.7k
        if (NXT(3) == 'L')
7150
0
      xmlParseElementDecl(ctxt);
7151
22.7k
        else if (NXT(3) == 'N')
7152
22.7k
      xmlParseEntityDecl(ctxt);
7153
1
                    else
7154
1
                        SKIP(2);
7155
22.7k
        break;
7156
1.27k
          case 'A':
7157
1.27k
        xmlParseAttributeListDecl(ctxt);
7158
1.27k
        break;
7159
0
          case 'N':
7160
0
        xmlParseNotationDecl(ctxt);
7161
0
        break;
7162
0
          case '-':
7163
0
        xmlParseComment(ctxt);
7164
0
        break;
7165
1.70k
    default:
7166
1.70k
                    xmlFatalErr(ctxt,
7167
1.70k
                                ctxt->inSubset == 2 ?
7168
0
                                    XML_ERR_EXT_SUBSET_NOT_FINISHED :
7169
1.70k
                                    XML_ERR_INT_SUBSET_NOT_FINISHED,
7170
1.70k
                                NULL);
7171
1.70k
                    SKIP(2);
7172
1.70k
        break;
7173
25.7k
      }
7174
25.7k
  } else if (NXT(1) == '?') {
7175
66
      xmlParsePI(ctxt);
7176
66
  }
7177
25.7k
    }
7178
25.7k
}
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
21.6k
xmlParseReference(xmlParserCtxtPtr ctxt) {
7334
21.6k
    xmlEntityPtr ent = NULL;
7335
21.6k
    const xmlChar *name;
7336
21.6k
    xmlChar *val;
7337
7338
21.6k
    if (RAW != '&')
7339
0
        return;
7340
7341
    /*
7342
     * Simple case of a CharRef
7343
     */
7344
21.6k
    if (NXT(1) == '#') {
7345
2.92k
  int i = 0;
7346
2.92k
  xmlChar out[16];
7347
2.92k
  int value = xmlParseCharRef(ctxt);
7348
7349
2.92k
  if (value == 0)
7350
1.02k
      return;
7351
7352
        /*
7353
         * Just encode the value in UTF-8
7354
         */
7355
1.90k
        COPY_BUF(out, i, value);
7356
1.90k
        out[i] = 0;
7357
1.90k
        if ((ctxt->sax != NULL) && (ctxt->sax->characters != NULL) &&
7358
1.90k
            (!ctxt->disableSAX))
7359
1.90k
            ctxt->sax->characters(ctxt->userData, out, i);
7360
1.90k
  return;
7361
2.92k
    }
7362
7363
    /*
7364
     * We are seeing an entity reference
7365
     */
7366
18.7k
    name = xmlParseEntityRefInternal(ctxt);
7367
18.7k
    if (name == NULL)
7368
13.2k
        return;
7369
5.48k
    ent = xmlLookupGeneralEntity(ctxt, name, /* isAttr */ 0);
7370
5.48k
    if (ent == NULL) {
7371
        /*
7372
         * Create a reference for undeclared entities.
7373
         */
7374
4.90k
        if ((ctxt->replaceEntities == 0) &&
7375
4.90k
            (ctxt->sax != NULL) &&
7376
4.90k
            (ctxt->disableSAX == 0) &&
7377
4.90k
            (ctxt->sax->reference != NULL)) {
7378
4.90k
            ctxt->sax->reference(ctxt->userData, name);
7379
4.90k
        }
7380
4.90k
        return;
7381
4.90k
    }
7382
585
    if (!ctxt->wellFormed)
7383
544
  return;
7384
7385
    /* special case of predefined entities */
7386
41
    if ((ent->name == NULL) ||
7387
41
        (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
41
    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
41
    if ((ent->etype == XML_INTERNAL_GENERAL_ENTITY) ||
7448
41
        (((ctxt->options & XML_PARSE_NO_XXE) == 0) &&
7449
0
         ((ctxt->replaceEntities) ||
7450
41
          (ctxt->validate)))) {
7451
41
        if ((ent->flags & XML_ENT_PARSED) == 0) {
7452
41
            xmlCtxtParseEntity(ctxt, ent);
7453
41
        } 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
41
    }
7466
7467
    /*
7468
     * We also check for amplification if entities aren't substituted.
7469
     * They might be expanded later.
7470
     */
7471
41
    if (xmlParserEntityCheck(ctxt, ent->expandedSize))
7472
0
        return;
7473
7474
41
    if ((ctxt->sax == NULL) || (ctxt->disableSAX))
7475
39
        return;
7476
7477
2
    if (ctxt->replaceEntities == 0) {
7478
  /*
7479
   * Create a reference
7480
   */
7481
2
        if (ctxt->sax->reference != NULL)
7482
2
      ctxt->sax->reference(ctxt->userData, ent->name);
7483
2
    } 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
2
}
7567
7568
static void
7569
16.7k
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
16.7k
    if ((ctxt->standalone == 1) ||
7592
16.7k
        ((ctxt->hasExternalSubset == 0) &&
7593
16.7k
         (ctxt->hasPErefs == 0))) {
7594
16.6k
        xmlFatalErrMsgStr(ctxt, XML_ERR_UNDECLARED_ENTITY,
7595
16.6k
                          "Entity '%s' not defined\n", name);
7596
16.6k
    } 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
156
    } else if ((ctxt->loadsubset & ~XML_SKIP_IDS) ||
7607
156
               ((ctxt->replaceEntities) &&
7608
156
                ((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
156
    } else {
7620
156
        xmlWarningMsg(ctxt, XML_WAR_UNDECLARED_ENTITY,
7621
156
                      "Entity '%s' not defined\n", name, NULL);
7622
156
    }
7623
7624
16.7k
    ctxt->valid = 0;
7625
16.7k
}
7626
7627
static xmlEntityPtr
7628
100k
xmlLookupGeneralEntity(xmlParserCtxtPtr ctxt, const xmlChar *name, int inAttr) {
7629
100k
    xmlEntityPtr ent = NULL;
7630
7631
    /*
7632
     * Predefined entities override any extra definition
7633
     */
7634
100k
    if ((ctxt->options & XML_PARSE_OLDSAX) == 0) {
7635
100k
        ent = xmlGetPredefinedEntity(name);
7636
100k
        if (ent != NULL)
7637
10.1k
            return(ent);
7638
100k
    }
7639
7640
    /*
7641
     * Ask first SAX for entity resolution, otherwise try the
7642
     * entities which may have stored in the parser context.
7643
     */
7644
90.0k
    if (ctxt->sax != NULL) {
7645
90.0k
  if (ctxt->sax->getEntity != NULL)
7646
90.0k
      ent = ctxt->sax->getEntity(ctxt->userData, name);
7647
90.0k
  if ((ctxt->wellFormed == 1 ) && (ent == NULL) &&
7648
90.0k
      (ctxt->options & XML_PARSE_OLDSAX))
7649
0
      ent = xmlGetPredefinedEntity(name);
7650
90.0k
  if ((ctxt->wellFormed == 1 ) && (ent == NULL) &&
7651
90.0k
      (ctxt->userData==ctxt)) {
7652
1
      ent = xmlSAX2GetEntity(ctxt, name);
7653
1
  }
7654
90.0k
    }
7655
7656
90.0k
    if (ent == NULL) {
7657
16.6k
        xmlHandleUndeclaredEntity(ctxt, name);
7658
16.6k
    }
7659
7660
    /*
7661
     * [ WFC: Parsed Entity ]
7662
     * An entity reference must not contain the name of an
7663
     * unparsed entity
7664
     */
7665
73.4k
    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
73.4k
    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
90.0k
    return(ent);
7685
100k
}
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
133k
xmlParseEntityRefInternal(xmlParserCtxtPtr ctxt) {
7700
133k
    const xmlChar *name;
7701
7702
133k
    GROW;
7703
7704
133k
    if (RAW != '&')
7705
0
        return(NULL);
7706
133k
    NEXT;
7707
133k
    name = xmlParseName(ctxt);
7708
133k
    if (name == NULL) {
7709
16.0k
  xmlFatalErrMsg(ctxt, XML_ERR_NAME_REQUIRED,
7710
16.0k
           "xmlParseEntityRef: no name\n");
7711
16.0k
        return(NULL);
7712
16.0k
    }
7713
117k
    if (RAW != ';') {
7714
31.0k
  xmlFatalErr(ctxt, XML_ERR_ENTITYREF_SEMICOL_MISSING, NULL);
7715
31.0k
  return(NULL);
7716
31.0k
    }
7717
86.3k
    NEXT;
7718
7719
86.3k
    return(name);
7720
117k
}
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
13.8k
xmlParseStringEntityRef(xmlParserCtxtPtr ctxt, const xmlChar ** str) {
7777
13.8k
    xmlChar *name;
7778
13.8k
    const xmlChar *ptr;
7779
13.8k
    xmlChar cur;
7780
7781
13.8k
    if ((str == NULL) || (*str == NULL))
7782
0
        return(NULL);
7783
13.8k
    ptr = *str;
7784
13.8k
    cur = *ptr;
7785
13.8k
    if (cur != '&')
7786
0
  return(NULL);
7787
7788
13.8k
    ptr++;
7789
13.8k
    name = xmlParseStringName(ctxt, &ptr);
7790
13.8k
    if (name == NULL) {
7791
0
  xmlFatalErrMsg(ctxt, XML_ERR_NAME_REQUIRED,
7792
0
           "xmlParseStringEntityRef: no name\n");
7793
0
  *str = ptr;
7794
0
  return(NULL);
7795
0
    }
7796
13.8k
    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
13.8k
    ptr++;
7803
7804
13.8k
    *str = ptr;
7805
13.8k
    return(name);
7806
13.8k
}
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
58
{
7843
58
    const xmlChar *name;
7844
58
    xmlEntityPtr entity = NULL;
7845
58
    xmlParserInputPtr input;
7846
7847
58
    if (RAW != '%')
7848
0
        return;
7849
58
    NEXT;
7850
58
    name = xmlParseName(ctxt);
7851
58
    if (name == NULL) {
7852
33
  xmlFatalErrMsg(ctxt, XML_ERR_PEREF_NO_NAME, "PEReference: no name\n");
7853
33
  return;
7854
33
    }
7855
25
    if (RAW != ';') {
7856
0
  xmlFatalErr(ctxt, XML_ERR_PEREF_SEMICOL_MISSING, NULL);
7857
0
        return;
7858
0
    }
7859
7860
25
    NEXT;
7861
7862
    /* Must be set before xmlHandleUndeclaredEntity */
7863
25
    ctxt->hasPErefs = 1;
7864
7865
    /*
7866
     * Request the entity from SAX
7867
     */
7868
25
    if ((ctxt->sax != NULL) &&
7869
25
  (ctxt->sax->getParameterEntity != NULL))
7870
25
  entity = ctxt->sax->getParameterEntity(ctxt->userData, name);
7871
7872
25
    if (entity == NULL) {
7873
0
        xmlHandleUndeclaredEntity(ctxt, name);
7874
25
    } else {
7875
  /*
7876
   * Internal checking in case the entity quest barfed
7877
   */
7878
25
  if ((entity->etype != XML_INTERNAL_PARAMETER_ENTITY) &&
7879
25
      (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
25
  } else {
7884
25
      if ((entity->etype == XML_EXTERNAL_PARAMETER_ENTITY) &&
7885
25
                ((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
25
            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
25
      input = xmlNewEntityInputStream(ctxt, entity);
7898
25
      if (xmlCtxtPushInput(ctxt, input) < 0) {
7899
0
                xmlFreeInputStream(input);
7900
0
    return;
7901
0
            }
7902
7903
25
            entity->flags |= XML_ENT_EXPANDING;
7904
7905
25
            GROW;
7906
7907
25
      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
25
  }
7916
25
    }
7917
25
}
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
3.43k
xmlParseStringPEReference(xmlParserCtxtPtr ctxt, const xmlChar **str) {
8095
3.43k
    const xmlChar *ptr;
8096
3.43k
    xmlChar cur;
8097
3.43k
    xmlChar *name;
8098
3.43k
    xmlEntityPtr entity = NULL;
8099
8100
3.43k
    if ((str == NULL) || (*str == NULL)) return(NULL);
8101
3.43k
    ptr = *str;
8102
3.43k
    cur = *ptr;
8103
3.43k
    if (cur != '%')
8104
0
        return(NULL);
8105
3.43k
    ptr++;
8106
3.43k
    name = xmlParseStringName(ctxt, &ptr);
8107
3.43k
    if (name == NULL) {
8108
2.81k
  xmlFatalErrMsg(ctxt, XML_ERR_NAME_REQUIRED,
8109
2.81k
           "xmlParseStringPEReference: no name\n");
8110
2.81k
  *str = ptr;
8111
2.81k
  return(NULL);
8112
2.81k
    }
8113
621
    cur = *ptr;
8114
621
    if (cur != ';') {
8115
477
  xmlFatalErr(ctxt, XML_ERR_ENTITYREF_SEMICOL_MISSING, NULL);
8116
477
  xmlFree(name);
8117
477
  *str = ptr;
8118
477
  return(NULL);
8119
477
    }
8120
144
    ptr++;
8121
8122
    /* Must be set before xmlHandleUndeclaredEntity */
8123
144
    ctxt->hasPErefs = 1;
8124
8125
    /*
8126
     * Request the entity from SAX
8127
     */
8128
144
    if ((ctxt->sax != NULL) &&
8129
144
  (ctxt->sax->getParameterEntity != NULL))
8130
144
  entity = ctxt->sax->getParameterEntity(ctxt->userData, name);
8131
8132
144
    if (entity == NULL) {
8133
144
        xmlHandleUndeclaredEntity(ctxt, name);
8134
144
    } else {
8135
  /*
8136
   * Internal checking in case the entity quest barfed
8137
   */
8138
0
  if ((entity->etype != XML_INTERNAL_PARAMETER_ENTITY) &&
8139
0
      (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
0
    }
8145
8146
144
    xmlFree(name);
8147
144
    *str = ptr;
8148
144
    return(entity);
8149
621
}
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
297
xmlParseDocTypeDecl(xmlParserCtxtPtr ctxt) {
8169
297
    const xmlChar *name = NULL;
8170
297
    xmlChar *ExternalID = NULL;
8171
297
    xmlChar *URI = NULL;
8172
8173
    /*
8174
     * We know that '<!DOCTYPE' has been detected.
8175
     */
8176
297
    SKIP(9);
8177
8178
297
    if (SKIP_BLANKS == 0) {
8179
20
        xmlFatalErrMsg(ctxt, XML_ERR_SPACE_REQUIRED,
8180
20
                       "Space required after 'DOCTYPE'\n");
8181
20
    }
8182
8183
    /*
8184
     * Parse the DOCTYPE name.
8185
     */
8186
297
    name = xmlParseName(ctxt);
8187
297
    if (name == NULL) {
8188
0
  xmlFatalErrMsg(ctxt, XML_ERR_NAME_REQUIRED,
8189
0
           "xmlParseDocTypeDecl : no DOCTYPE name !\n");
8190
0
    }
8191
297
    ctxt->intSubName = name;
8192
8193
297
    SKIP_BLANKS;
8194
8195
    /*
8196
     * Check for SystemID and ExternalID
8197
     */
8198
297
    URI = xmlParseExternalID(ctxt, &ExternalID, 1);
8199
8200
297
    if ((URI != NULL) || (ExternalID != NULL)) {
8201
0
        ctxt->hasExternalSubset = 1;
8202
0
    }
8203
297
    ctxt->extSubURI = URI;
8204
297
    ctxt->extSubSystem = ExternalID;
8205
8206
297
    SKIP_BLANKS;
8207
8208
    /*
8209
     * Create and update the internal subset.
8210
     */
8211
297
    if ((ctxt->sax != NULL) && (ctxt->sax->internalSubset != NULL) &&
8212
297
  (!ctxt->disableSAX))
8213
297
  ctxt->sax->internalSubset(ctxt->userData, name, ExternalID, URI);
8214
8215
297
    if ((RAW != '[') && (RAW != '>')) {
8216
0
  xmlFatalErr(ctxt, XML_ERR_DOCTYPE_NOT_FINISHED, NULL);
8217
0
    }
8218
297
}
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
297
xmlParseInternalSubset(xmlParserCtxtPtr ctxt) {
8231
    /*
8232
     * Is there any DTD definition ?
8233
     */
8234
297
    if (RAW == '[') {
8235
297
        int oldInputNr = ctxt->inputNr;
8236
8237
297
        NEXT;
8238
  /*
8239
   * Parse the succession of Markup declarations and
8240
   * PEReferences.
8241
   * Subsequence (markupdecl | PEReference | S)*
8242
   */
8243
297
  SKIP_BLANKS;
8244
26.1k
  while (((RAW != ']') || (ctxt->inputNr > oldInputNr)) &&
8245
26.1k
               (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
25.8k
            if ((PARSER_EXTERNAL(ctxt)) &&
8252
25.8k
                (RAW == '<') && (NXT(1) == '!') && (NXT(2) == '[')) {
8253
0
                xmlParseConditionalSections(ctxt);
8254
25.8k
            } else if ((RAW == '<') && ((NXT(1) == '!') || (NXT(1) == '?'))) {
8255
25.7k
          xmlParseMarkupDecl(ctxt);
8256
25.7k
            } else if (RAW == '%') {
8257
58
          xmlParsePEReference(ctxt);
8258
58
            } else {
8259
13
    xmlFatalErr(ctxt, XML_ERR_INT_SUBSET_NOT_FINISHED, NULL);
8260
13
                break;
8261
13
            }
8262
25.8k
      SKIP_BLANKS_PE;
8263
25.8k
            SHRINK;
8264
25.8k
            GROW;
8265
25.8k
  }
8266
8267
300
        while (ctxt->inputNr > oldInputNr)
8268
3
            xmlPopPE(ctxt);
8269
8270
297
  if (RAW == ']') {
8271
245
      NEXT;
8272
245
      SKIP_BLANKS;
8273
245
  }
8274
297
    }
8275
8276
    /*
8277
     * We should be at the end of the DOCTYPE declaration.
8278
     */
8279
297
    if ((ctxt->wellFormed) && (RAW != '>')) {
8280
0
  xmlFatalErr(ctxt, XML_ERR_DOCTYPE_NOT_FINISHED, NULL);
8281
0
  return;
8282
0
    }
8283
297
    NEXT;
8284
297
}
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
7.75M
xmlParseQNameHashed(xmlParserCtxtPtr ctxt, xmlHashedString *prefix) {
8635
7.75M
    xmlHashedString l, p;
8636
7.75M
    int start, isNCName = 0;
8637
8638
7.75M
    l.name = NULL;
8639
7.75M
    p.name = NULL;
8640
8641
7.75M
    GROW;
8642
7.75M
    start = CUR_PTR - BASE_PTR;
8643
8644
7.75M
    l = xmlParseNCName(ctxt);
8645
7.75M
    if (l.name != NULL) {
8646
3.82M
        isNCName = 1;
8647
3.82M
        if (CUR == ':') {
8648
46.8k
            NEXT;
8649
46.8k
            p = l;
8650
46.8k
            l = xmlParseNCName(ctxt);
8651
46.8k
        }
8652
3.82M
    }
8653
7.75M
    if ((l.name == NULL) || (CUR == ':')) {
8654
3.94M
        xmlChar *tmp;
8655
8656
3.94M
        l.name = NULL;
8657
3.94M
        p.name = NULL;
8658
3.94M
        if ((isNCName == 0) && (CUR != ':'))
8659
3.93M
            return(l);
8660
8.11k
        tmp = xmlParseNmtoken(ctxt);
8661
8.11k
        if (tmp != NULL)
8662
6.32k
            xmlFree(tmp);
8663
8.11k
        l = xmlDictLookupHashed(ctxt->dict, BASE_PTR + start,
8664
8.11k
                                CUR_PTR - (BASE_PTR + start));
8665
8.11k
        if (l.name == NULL) {
8666
0
            xmlErrMemory(ctxt);
8667
0
            return(l);
8668
0
        }
8669
8.11k
        xmlNsErr(ctxt, XML_NS_ERR_QNAME,
8670
8.11k
                 "Failed to parse QName '%s'\n", l.name, NULL, NULL);
8671
8.11k
    }
8672
8673
3.82M
    *prefix = p;
8674
3.82M
    return(l);
8675
7.75M
}
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
1.90k
xmlParseQName(xmlParserCtxtPtr ctxt, const xmlChar **prefix) {
8693
1.90k
    xmlHashedString n, p;
8694
8695
1.90k
    n = xmlParseQNameHashed(ctxt, &p);
8696
1.90k
    if (n.name == NULL)
8697
31
        return(NULL);
8698
1.87k
    *prefix = p.name;
8699
1.87k
    return(n.name);
8700
1.90k
}
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
3.76k
                        xmlChar const *prefix) {
8718
3.76k
    const xmlChar *cmp;
8719
3.76k
    const xmlChar *in;
8720
3.76k
    const xmlChar *ret;
8721
3.76k
    const xmlChar *prefix2;
8722
8723
3.76k
    if (prefix == NULL) return(xmlParseNameAndCompare(ctxt, name));
8724
8725
3.76k
    GROW;
8726
3.76k
    in = ctxt->input->cur;
8727
8728
3.76k
    cmp = prefix;
8729
6.09k
    while (*in != 0 && *in == *cmp) {
8730
2.32k
  ++in;
8731
2.32k
  ++cmp;
8732
2.32k
    }
8733
3.76k
    if ((*cmp == 0) && (*in == ':')) {
8734
2.22k
        in++;
8735
2.22k
  cmp = name;
8736
4.28k
  while (*in != 0 && *in == *cmp) {
8737
2.05k
      ++in;
8738
2.05k
      ++cmp;
8739
2.05k
  }
8740
2.22k
  if (*cmp == 0 && (*in == '>' || IS_BLANK_CH (*in))) {
8741
      /* success */
8742
1.86k
            ctxt->input->col += in - ctxt->input->cur;
8743
1.86k
      ctxt->input->cur = in;
8744
1.86k
      return((const xmlChar*) 1);
8745
1.86k
  }
8746
2.22k
    }
8747
    /*
8748
     * all strings coms from the dictionary, equality can be done directly
8749
     */
8750
1.90k
    ret = xmlParseQName (ctxt, &prefix2);
8751
1.90k
    if (ret == NULL)
8752
31
        return(NULL);
8753
1.87k
    if ((ret == name) && (prefix == prefix2))
8754
97
  return((const xmlChar*) 1);
8755
1.77k
    return ret;
8756
1.87k
}
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
3.71M
{
8779
3.71M
    xmlHashedString hname;
8780
3.71M
    const xmlChar *prefix, *name;
8781
3.71M
    xmlChar *val = NULL, *internal_val = NULL;
8782
3.71M
    int normalize = 0;
8783
3.71M
    int isNamespace;
8784
8785
3.71M
    *value = NULL;
8786
3.71M
    GROW;
8787
3.71M
    hname = xmlParseQNameHashed(ctxt, hprefix);
8788
3.71M
    if (hname.name == NULL) {
8789
3.67M
        xmlFatalErrMsg(ctxt, XML_ERR_NAME_REQUIRED,
8790
3.67M
                       "error parsing attribute name\n");
8791
3.67M
        return(hname);
8792
3.67M
    }
8793
38.9k
    name = hname.name;
8794
38.9k
    prefix = hprefix->name;
8795
8796
    /*
8797
     * get the type if needed
8798
     */
8799
38.9k
    if (ctxt->attsSpecial != NULL) {
8800
656
        int type;
8801
8802
656
        type = XML_PTR_TO_INT(xmlHashQLookup2(ctxt->attsSpecial, pref, elem,
8803
656
                                              prefix, name));
8804
656
        if (type != 0)
8805
0
            normalize = 1;
8806
656
    }
8807
8808
    /*
8809
     * read the value
8810
     */
8811
38.9k
    SKIP_BLANKS;
8812
38.9k
    if (RAW == '=') {
8813
33.6k
        NEXT;
8814
33.6k
        SKIP_BLANKS;
8815
33.6k
        isNamespace = (((prefix == NULL) && (name == ctxt->str_xmlns)) ||
8816
33.6k
                       (prefix == ctxt->str_xmlns));
8817
33.6k
        val = xmlParseAttValueInternal(ctxt, len, alloc, normalize,
8818
33.6k
                                       isNamespace);
8819
33.6k
        if (val == NULL)
8820
1.74k
            goto error;
8821
33.6k
    } else {
8822
5.24k
        xmlFatalErrMsgStr(ctxt, XML_ERR_ATTRIBUTE_WITHOUT_VALUE,
8823
5.24k
                          "Specification mandates value for attribute %s\n",
8824
5.24k
                          name);
8825
5.24k
        goto error;
8826
5.24k
    }
8827
8828
31.9k
    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
11.3k
        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
11.3k
        if (xmlStrEqual(name, BAD_CAST "space")) {
8849
7
            internal_val = xmlStrndup(val, *len);
8850
7
            if (internal_val == NULL)
8851
0
                goto mem_error;
8852
7
            if (xmlStrEqual(internal_val, BAD_CAST "default"))
8853
0
                *(ctxt->space) = 0;
8854
7
            else if (xmlStrEqual(internal_val, BAD_CAST "preserve"))
8855
3
                *(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
7
        }
8862
11.3k
        if (internal_val) {
8863
7
            xmlFree(internal_val);
8864
7
        }
8865
11.3k
    }
8866
8867
31.9k
    *value = val;
8868
31.9k
    return (hname);
8869
8870
0
mem_error:
8871
0
    xmlErrMemory(ctxt);
8872
6.99k
error:
8873
6.99k
    if ((val != NULL) && (*alloc != 0))
8874
0
        xmlFree(val);
8875
6.99k
    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
11.8k
                  const xmlChar *uri, unsigned hashValue, int aindex) {
8895
11.8k
    xmlAttrHashBucket *table = ctxt->attrHash;
8896
11.8k
    xmlAttrHashBucket *bucket;
8897
11.8k
    unsigned hindex;
8898
8899
11.8k
    hindex = hashValue & (size - 1);
8900
11.8k
    bucket = &table[hindex];
8901
8902
11.9k
    while (bucket->index >= 0) {
8903
10.8k
        const xmlChar **atts = &ctxt->atts[bucket->index];
8904
8905
10.8k
        if (name == atts[0]) {
8906
10.8k
            int nsIndex = XML_PTR_TO_INT(atts[2]);
8907
8908
10.8k
            if ((nsIndex == NS_INDEX_EMPTY) ? (uri == NULL) :
8909
10.8k
                (nsIndex == NS_INDEX_XML) ? (uri == ctxt->str_xml_ns) :
8910
10.1k
                (uri == ctxt->nsTab[nsIndex * 2 + 1]))
8911
10.8k
                return(bucket->index);
8912
10.8k
        }
8913
8914
50
        hindex++;
8915
50
        bucket++;
8916
50
        if (hindex >= size) {
8917
5
            hindex = 0;
8918
5
            bucket = table;
8919
5
        }
8920
50
    }
8921
8922
1.01k
    bucket->index = aindex;
8923
8924
1.01k
    return(INT_MAX);
8925
11.8k
}
8926
8927
static int
8928
xmlAttrHashInsertQName(xmlParserCtxtPtr ctxt, unsigned size,
8929
                       const xmlChar *name, const xmlChar *prefix,
8930
0
                       unsigned hashValue, int aindex) {
8931
0
    xmlAttrHashBucket *table = ctxt->attrHash;
8932
0
    xmlAttrHashBucket *bucket;
8933
0
    unsigned hindex;
8934
8935
0
    hindex = hashValue & (size - 1);
8936
0
    bucket = &table[hindex];
8937
8938
0
    while (bucket->index >= 0) {
8939
0
        const xmlChar **atts = &ctxt->atts[bucket->index];
8940
8941
0
        if ((name == atts[0]) && (prefix == atts[1]))
8942
0
            return(bucket->index);
8943
8944
0
        hindex++;
8945
0
        bucket++;
8946
0
        if (hindex >= size) {
8947
0
            hindex = 0;
8948
0
            bucket = table;
8949
0
        }
8950
0
    }
8951
8952
0
    bucket->index = aindex;
8953
8954
0
    return(INT_MAX);
8955
0
}
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
4.04M
                  const xmlChar **URI, int *nbNsPtr) {
8988
4.04M
    xmlHashedString hlocalname;
8989
4.04M
    xmlHashedString hprefix;
8990
4.04M
    xmlHashedString hattname;
8991
4.04M
    xmlHashedString haprefix;
8992
4.04M
    const xmlChar *localname;
8993
4.04M
    const xmlChar *prefix;
8994
4.04M
    const xmlChar *attname;
8995
4.04M
    const xmlChar *aprefix;
8996
4.04M
    const xmlChar *uri;
8997
4.04M
    xmlChar *attvalue = NULL;
8998
4.04M
    const xmlChar **atts = ctxt->atts;
8999
4.04M
    unsigned attrHashSize = 0;
9000
4.04M
    int maxatts = ctxt->maxatts;
9001
4.04M
    int nratts, nbatts, nbdef;
9002
4.04M
    int i, j, nbNs, nbTotalDef, attval, nsIndex, maxAtts;
9003
4.04M
    int alloc = 0;
9004
4.04M
    int numNsErr = 0;
9005
4.04M
    int numDupErr = 0;
9006
9007
4.04M
    if (RAW != '<') return(NULL);
9008
4.04M
    NEXT1;
9009
9010
4.04M
    nbatts = 0;
9011
4.04M
    nratts = 0;
9012
4.04M
    nbdef = 0;
9013
4.04M
    nbNs = 0;
9014
4.04M
    nbTotalDef = 0;
9015
4.04M
    attval = 0;
9016
9017
4.04M
    if (xmlParserNsStartElement(ctxt->nsdb) < 0) {
9018
0
        xmlErrMemory(ctxt);
9019
0
        return(NULL);
9020
0
    }
9021
9022
4.04M
    hlocalname = xmlParseQNameHashed(ctxt, &hprefix);
9023
4.04M
    if (hlocalname.name == NULL) {
9024
258k
  xmlFatalErrMsg(ctxt, XML_ERR_NAME_REQUIRED,
9025
258k
           "StartTag: invalid element name\n");
9026
258k
        return(NULL);
9027
258k
    }
9028
3.78M
    localname = hlocalname.name;
9029
3.78M
    prefix = hprefix.name;
9030
9031
    /*
9032
     * Now parse the attributes, it ends up with the ending
9033
     *
9034
     * (S Attribute)* S?
9035
     */
9036
3.78M
    SKIP_BLANKS;
9037
3.78M
    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
3.80M
    while (((RAW != '>') &&
9064
3.80M
     ((RAW != '/') || (NXT(1) != '>')) &&
9065
3.80M
     (IS_BYTE_CHAR(RAW))) && (PARSER_STOPPED(ctxt) == 0)) {
9066
3.71M
  int len = -1;
9067
9068
3.71M
  hattname = xmlParseAttribute2(ctxt, prefix, localname,
9069
3.71M
                                          &haprefix, &attvalue, &len,
9070
3.71M
                                          &alloc);
9071
3.71M
        if (hattname.name == NULL)
9072
3.67M
      break;
9073
38.9k
        if (attvalue == NULL)
9074
6.99k
            goto next_attr;
9075
31.9k
        attname = hattname.name;
9076
31.9k
        aprefix = haprefix.name;
9077
31.9k
  if (len < 0) len = xmlStrlen(attvalue);
9078
9079
31.9k
        if ((attname == ctxt->str_xmlns) && (aprefix == NULL)) {
9080
4.59k
            xmlHashedString huri;
9081
4.59k
            xmlURIPtr parsedUri;
9082
9083
4.59k
            huri = xmlDictLookupHashed(ctxt->dict, attvalue, len);
9084
4.59k
            uri = huri.name;
9085
4.59k
            if (uri == NULL) {
9086
0
                xmlErrMemory(ctxt);
9087
0
                goto next_attr;
9088
0
            }
9089
4.59k
            if (*uri != 0) {
9090
4.48k
                if (xmlParseURISafe((const char *) uri, &parsedUri) < 0) {
9091
0
                    xmlErrMemory(ctxt);
9092
0
                    goto next_attr;
9093
0
                }
9094
4.48k
                if (parsedUri == NULL) {
9095
707
                    xmlNsErr(ctxt, XML_WAR_NS_URI,
9096
707
                             "xmlns: '%s' is not a valid URI\n",
9097
707
                                       uri, NULL, NULL);
9098
3.77k
                } else {
9099
3.77k
                    if (parsedUri->scheme == NULL) {
9100
3.64k
                        xmlNsWarn(ctxt, XML_WAR_NS_URI_RELATIVE,
9101
3.64k
                                  "xmlns: URI %s is not absolute\n",
9102
3.64k
                                  uri, NULL, NULL);
9103
3.64k
                    }
9104
3.77k
                    xmlFreeURI(parsedUri);
9105
3.77k
                }
9106
4.48k
                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
4.48k
                if ((len == 29) &&
9115
4.48k
                    (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
4.48k
            }
9123
9124
4.59k
            if (xmlParserNsPush(ctxt, NULL, &huri, NULL, 0) > 0)
9125
4.49k
                nbNs++;
9126
27.3k
        } else if (aprefix == ctxt->str_xmlns) {
9127
7.48k
            xmlHashedString huri;
9128
7.48k
            xmlURIPtr parsedUri;
9129
9130
7.48k
            huri = xmlDictLookupHashed(ctxt->dict, attvalue, len);
9131
7.48k
            uri = huri.name;
9132
7.48k
            if (uri == NULL) {
9133
0
                xmlErrMemory(ctxt);
9134
0
                goto next_attr;
9135
0
            }
9136
9137
7.48k
            if (attname == ctxt->str_xml) {
9138
550
                if (uri != ctxt->str_xml_ns) {
9139
550
                    xmlNsErr(ctxt, XML_NS_ERR_XML_NAMESPACE,
9140
550
                             "xml namespace prefix mapped to wrong URI\n",
9141
550
                             NULL, NULL, NULL);
9142
550
                }
9143
                /*
9144
                 * Do not keep a namespace definition node
9145
                 */
9146
550
                goto next_attr;
9147
550
            }
9148
6.93k
            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
6.93k
            if (attname == ctxt->str_xmlns) {
9157
0
                xmlNsErr(ctxt, XML_NS_ERR_XML_NAMESPACE,
9158
0
                         "redefinition of the xmlns prefix is forbidden\n",
9159
0
                         NULL, NULL, NULL);
9160
0
                goto next_attr;
9161
0
            }
9162
6.93k
            if ((len == 29) &&
9163
6.93k
                (xmlStrEqual(uri,
9164
90
                             BAD_CAST "http://www.w3.org/2000/xmlns/"))) {
9165
69
                xmlNsErr(ctxt, XML_NS_ERR_XML_NAMESPACE,
9166
69
                         "reuse of the xmlns namespace name is forbidden\n",
9167
69
                         NULL, NULL, NULL);
9168
69
                goto next_attr;
9169
69
            }
9170
6.87k
            if ((uri == NULL) || (uri[0] == 0)) {
9171
4
                xmlNsErr(ctxt, XML_NS_ERR_XML_NAMESPACE,
9172
4
                         "xmlns:%s: Empty XML namespace is not allowed\n",
9173
4
                              attname, NULL, NULL);
9174
4
                goto next_attr;
9175
6.86k
            } else {
9176
6.86k
                if (xmlParseURISafe((const char *) uri, &parsedUri) < 0) {
9177
0
                    xmlErrMemory(ctxt);
9178
0
                    goto next_attr;
9179
0
                }
9180
6.86k
                if (parsedUri == NULL) {
9181
2.23k
                    xmlNsErr(ctxt, XML_WAR_NS_URI,
9182
2.23k
                         "xmlns:%s: '%s' is not a valid URI\n",
9183
2.23k
                                       attname, uri, NULL);
9184
4.63k
                } else {
9185
4.63k
                    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
4.63k
                    xmlFreeURI(parsedUri);
9191
4.63k
                }
9192
6.86k
            }
9193
9194
6.86k
            if (xmlParserNsPush(ctxt, &hattname, &huri, NULL, 0) > 0)
9195
6.65k
                nbNs++;
9196
19.8k
        } else {
9197
            /*
9198
             * Populate attributes array, see above for repurposing
9199
             * of xmlChar pointers.
9200
             */
9201
19.8k
            if ((atts == NULL) || (nbatts + 5 > maxatts)) {
9202
477
                int res = xmlCtxtGrowAttrs(ctxt);
9203
9204
477
                maxatts = ctxt->maxatts;
9205
477
                atts = ctxt->atts;
9206
9207
477
                if (res < 0)
9208
0
                    goto next_attr;
9209
477
            }
9210
19.8k
            ctxt->attallocs[nratts++] = (hattname.hashValue & 0x7FFFFFFF) |
9211
19.8k
                                        ((unsigned) alloc << 31);
9212
19.8k
            atts[nbatts++] = attname;
9213
19.8k
            atts[nbatts++] = aprefix;
9214
19.8k
            atts[nbatts++] = (const xmlChar *) (size_t) haprefix.hashValue;
9215
19.8k
            if (alloc) {
9216
13.9k
                atts[nbatts++] = attvalue;
9217
13.9k
                attvalue += len;
9218
13.9k
                atts[nbatts++] = attvalue;
9219
13.9k
            } 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
5.84k
                atts[nbatts++] = (void *) (attvalue - BASE_PTR);
9226
5.84k
                attvalue += len;
9227
5.84k
                atts[nbatts++] = (void *) (attvalue - BASE_PTR);
9228
5.84k
            }
9229
            /*
9230
             * tag if some deallocation is needed
9231
             */
9232
19.8k
            if (alloc != 0) attval = 1;
9233
19.8k
            attvalue = NULL; /* moved into atts */
9234
19.8k
        }
9235
9236
38.9k
next_attr:
9237
38.9k
        if ((attvalue != NULL) && (alloc != 0)) {
9238
3.07k
            xmlFree(attvalue);
9239
3.07k
            attvalue = NULL;
9240
3.07k
        }
9241
9242
38.9k
  GROW
9243
38.9k
  if ((RAW == '>') || (((RAW == '/') && (NXT(1) == '>'))))
9244
10.1k
      break;
9245
28.7k
  if (SKIP_BLANKS == 0) {
9246
8.67k
      xmlFatalErrMsg(ctxt, XML_ERR_SPACE_REQUIRED,
9247
8.67k
         "attributes construct error\n");
9248
8.67k
      break;
9249
8.67k
  }
9250
20.0k
        GROW;
9251
20.0k
    }
9252
9253
    /*
9254
     * Namespaces from default attributes
9255
     */
9256
3.78M
    if (ctxt->attsDefault != NULL) {
9257
0
        xmlDefAttrsPtr defaults;
9258
9259
0
  defaults = xmlHashLookup2(ctxt->attsDefault, localname, prefix);
9260
0
  if (defaults != NULL) {
9261
0
      for (i = 0; i < defaults->nbAttrs; i++) {
9262
0
                xmlDefAttr *attr = &defaults->attrs[i];
9263
9264
0
          attname = attr->name.name;
9265
0
    aprefix = attr->prefix.name;
9266
9267
0
    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
0
    } 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
0
    } else {
9279
0
                    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
0
                    nbTotalDef += 1;
9285
0
                }
9286
0
      }
9287
0
  }
9288
0
    }
9289
9290
    /*
9291
     * Resolve attribute namespaces
9292
     */
9293
3.80M
    for (i = 0; i < nbatts; i += 5) {
9294
19.8k
        attname = atts[i];
9295
19.8k
        aprefix = atts[i+1];
9296
9297
        /*
9298
  * The default namespace does not apply to attribute names.
9299
  */
9300
19.8k
  if (aprefix == NULL) {
9301
6.82k
            nsIndex = NS_INDEX_EMPTY;
9302
13.0k
        } else if (aprefix == ctxt->str_xml) {
9303
11.3k
            nsIndex = NS_INDEX_XML;
9304
11.3k
        } else {
9305
1.61k
            haprefix.name = aprefix;
9306
1.61k
            haprefix.hashValue = (size_t) atts[i+2];
9307
1.61k
            nsIndex = xmlParserNsLookup(ctxt, &haprefix, NULL);
9308
9309
1.61k
      if ((nsIndex == INT_MAX) || (nsIndex < ctxt->nsdb->minNsIndex)) {
9310
1.46k
                xmlNsErr(ctxt, XML_NS_ERR_UNDEFINED_NAMESPACE,
9311
1.46k
        "Namespace prefix %s for %s on %s is not defined\n",
9312
1.46k
        aprefix, attname, localname);
9313
1.46k
                nsIndex = NS_INDEX_EMPTY;
9314
1.46k
            }
9315
1.61k
        }
9316
9317
19.8k
        atts[i+2] = XML_INT_TO_PTR(nsIndex);
9318
19.8k
    }
9319
9320
    /*
9321
     * Maximum number of attributes including default attributes.
9322
     */
9323
3.78M
    maxAtts = nratts + nbTotalDef;
9324
9325
    /*
9326
     * Verify that attribute names are unique.
9327
     */
9328
3.78M
    if (maxAtts > 1) {
9329
470
        attrHashSize = 4;
9330
863
        while (attrHashSize / 2 < (unsigned) maxAtts)
9331
393
            attrHashSize *= 2;
9332
9333
470
        if (attrHashSize > ctxt->attrHashMax) {
9334
60
            xmlAttrHashBucket *tmp;
9335
9336
60
            tmp = xmlRealloc(ctxt->attrHash, attrHashSize * sizeof(tmp[0]));
9337
60
            if (tmp == NULL) {
9338
0
                xmlErrMemory(ctxt);
9339
0
                goto done;
9340
0
            }
9341
9342
60
            ctxt->attrHash = tmp;
9343
60
            ctxt->attrHashMax = attrHashSize;
9344
60
        }
9345
9346
470
        memset(ctxt->attrHash, -1, attrHashSize * sizeof(ctxt->attrHash[0]));
9347
9348
13.2k
        for (i = 0, j = 0; j < nratts; i += 5, j++) {
9349
12.7k
            const xmlChar *nsuri;
9350
12.7k
            unsigned hashValue, nameHashValue, uriHashValue;
9351
12.7k
            int res;
9352
9353
12.7k
            attname = atts[i];
9354
12.7k
            aprefix = atts[i+1];
9355
12.7k
            nsIndex = XML_PTR_TO_INT(atts[i+2]);
9356
            /* Hash values always have bit 31 set, see dict.c */
9357
12.7k
            nameHashValue = ctxt->attallocs[j] | 0x80000000;
9358
9359
12.7k
            if (nsIndex == NS_INDEX_EMPTY) {
9360
                /*
9361
                 * Prefix with empty namespace means an undeclared
9362
                 * prefix which was already reported above.
9363
                 */
9364
2.30k
                if (aprefix != NULL)
9365
912
                    continue;
9366
1.39k
                nsuri = NULL;
9367
1.39k
                uriHashValue = URI_HASH_EMPTY;
9368
10.4k
            } else if (nsIndex == NS_INDEX_XML) {
9369
10.3k
                nsuri = ctxt->str_xml_ns;
9370
10.3k
                uriHashValue = URI_HASH_XML;
9371
10.3k
            } else {
9372
158
                nsuri = ctxt->nsTab[nsIndex * 2 + 1];
9373
158
                uriHashValue = ctxt->nsdb->extra[nsIndex].uriHashValue;
9374
158
            }
9375
9376
11.8k
            hashValue = xmlDictCombineHash(nameHashValue, uriHashValue);
9377
11.8k
            res = xmlAttrHashInsert(ctxt, attrHashSize, attname, nsuri,
9378
11.8k
                                    hashValue, i);
9379
11.8k
            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
11.8k
            if (res < INT_MAX) {
9389
10.8k
                if (aprefix == atts[res+1]) {
9390
10.8k
                    xmlErrAttributeDup(ctxt, aprefix, attname);
9391
10.8k
                    numDupErr += 1;
9392
10.8k
                } else {
9393
39
                    xmlNsErr(ctxt, XML_NS_ERR_ATTRIBUTE_REDEFINED,
9394
39
                             "Namespaced Attribute %s in '%s' redefined\n",
9395
39
                             attname, nsuri, NULL);
9396
39
                    numNsErr += 1;
9397
39
                }
9398
10.8k
            }
9399
11.8k
        }
9400
470
    }
9401
9402
    /*
9403
     * Default attributes
9404
     */
9405
3.78M
    if (ctxt->attsDefault != NULL) {
9406
0
        xmlDefAttrsPtr defaults;
9407
9408
0
  defaults = xmlHashLookup2(ctxt->attsDefault, localname, prefix);
9409
0
  if (defaults != NULL) {
9410
0
      for (i = 0; i < defaults->nbAttrs; i++) {
9411
0
                xmlDefAttr *attr = &defaults->attrs[i];
9412
0
                const xmlChar *nsuri = NULL;
9413
0
                unsigned hashValue, uriHashValue = 0;
9414
0
                int res;
9415
9416
0
          attname = attr->name.name;
9417
0
    aprefix = attr->prefix.name;
9418
9419
0
    if ((attname == ctxt->str_xmlns) && (aprefix == NULL))
9420
0
                    continue;
9421
0
    if (aprefix == ctxt->str_xmlns)
9422
0
                    continue;
9423
9424
0
                if (aprefix == NULL) {
9425
0
                    nsIndex = NS_INDEX_EMPTY;
9426
0
                    nsuri = NULL;
9427
0
                    uriHashValue = URI_HASH_EMPTY;
9428
0
                } 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
0
                } else {
9433
0
                    nsIndex = xmlParserNsLookup(ctxt, &attr->prefix, NULL);
9434
0
                    if ((nsIndex == INT_MAX) ||
9435
0
                        (nsIndex < ctxt->nsdb->minNsIndex)) {
9436
0
                        xmlNsErr(ctxt, XML_NS_ERR_UNDEFINED_NAMESPACE,
9437
0
                                 "Namespace prefix %s for %s on %s is not "
9438
0
                                 "defined\n",
9439
0
                                 aprefix, attname, localname);
9440
0
                        nsIndex = NS_INDEX_EMPTY;
9441
0
                        nsuri = NULL;
9442
0
                        uriHashValue = URI_HASH_EMPTY;
9443
0
                    } else {
9444
0
                        nsuri = ctxt->nsTab[nsIndex * 2 + 1];
9445
0
                        uriHashValue = ctxt->nsdb->extra[nsIndex].uriHashValue;
9446
0
                    }
9447
0
                }
9448
9449
                /*
9450
                 * Check whether the attribute exists
9451
                 */
9452
0
                if (maxAtts > 1) {
9453
0
                    hashValue = xmlDictCombineHash(attr->name.hashValue,
9454
0
                                                   uriHashValue);
9455
0
                    res = xmlAttrHashInsert(ctxt, attrHashSize, attname, nsuri,
9456
0
                                            hashValue, nbatts);
9457
0
                    if (res < 0)
9458
0
                        continue;
9459
0
                    if (res < INT_MAX) {
9460
0
                        if (aprefix == atts[res+1])
9461
0
                            continue;
9462
0
                        xmlNsErr(ctxt, XML_NS_ERR_ATTRIBUTE_REDEFINED,
9463
0
                                 "Namespaced Attribute %s in '%s' redefined\n",
9464
0
                                 attname, nsuri, NULL);
9465
0
                    }
9466
0
                }
9467
9468
0
                xmlParserEntityCheck(ctxt, attr->expandedSize);
9469
9470
0
                if ((atts == NULL) || (nbatts + 5 > maxatts)) {
9471
0
                    res = xmlCtxtGrowAttrs(ctxt);
9472
9473
0
                    maxatts = ctxt->maxatts;
9474
0
                    atts = ctxt->atts;
9475
9476
0
                    if (res < 0) {
9477
0
                        localname = NULL;
9478
0
                        goto done;
9479
0
                    }
9480
0
                }
9481
9482
0
                atts[nbatts++] = attname;
9483
0
                atts[nbatts++] = aprefix;
9484
0
                atts[nbatts++] = XML_INT_TO_PTR(nsIndex);
9485
0
                atts[nbatts++] = attr->value.name;
9486
0
                atts[nbatts++] = attr->valueEnd;
9487
0
                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
0
                nbdef++;
9494
0
      }
9495
0
  }
9496
0
    }
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
3.78M
    if ((numDupErr == 0) && (numNsErr > 1)) {
9511
0
        memset(ctxt->attrHash, -1,
9512
0
               attrHashSize * sizeof(ctxt->attrHash[0]));
9513
9514
0
        for (i = 0, j = 0; j < nratts; i += 5, j++) {
9515
0
            unsigned hashValue, nameHashValue, prefixHashValue;
9516
0
            int res;
9517
9518
0
            aprefix = atts[i+1];
9519
0
            if (aprefix == NULL)
9520
0
                continue;
9521
9522
0
            attname = atts[i];
9523
            /* Hash values always have bit 31 set, see dict.c */
9524
0
            nameHashValue = ctxt->attallocs[j] | 0x80000000;
9525
0
            prefixHashValue = xmlDictComputeHash(ctxt->dict, aprefix);
9526
9527
0
            hashValue = xmlDictCombineHash(nameHashValue, prefixHashValue);
9528
0
            res = xmlAttrHashInsertQName(ctxt, attrHashSize, attname,
9529
0
                                         aprefix, hashValue, i);
9530
0
            if (res < INT_MAX)
9531
0
                xmlErrAttributeDup(ctxt, aprefix, attname);
9532
0
        }
9533
0
    }
9534
9535
    /*
9536
     * Reconstruct attribute pointers
9537
     */
9538
3.80M
    for (i = 0, j = 0; i < nbatts; i += 5, j++) {
9539
        /* namespace URI */
9540
19.8k
        nsIndex = XML_PTR_TO_INT(atts[i+2]);
9541
19.8k
        if (nsIndex == INT_MAX)
9542
8.28k
            atts[i+2] = NULL;
9543
11.5k
        else if (nsIndex == INT_MAX - 1)
9544
11.3k
            atts[i+2] = ctxt->str_xml_ns;
9545
159
        else
9546
159
            atts[i+2] = ctxt->nsTab[nsIndex * 2 + 1];
9547
9548
19.8k
        if ((j < nratts) && (ctxt->attallocs[j] & 0x80000000) == 0) {
9549
5.84k
            atts[i+3] = BASE_PTR + XML_PTR_TO_INT(atts[i+3]);  /* value */
9550
5.84k
            atts[i+4] = BASE_PTR + XML_PTR_TO_INT(atts[i+4]);  /* valuend */
9551
5.84k
        }
9552
19.8k
    }
9553
9554
3.78M
    uri = xmlParserNsLookupUri(ctxt, &hprefix);
9555
3.78M
    if ((prefix != NULL) && (uri == NULL)) {
9556
14.8k
  xmlNsErr(ctxt, XML_NS_ERR_UNDEFINED_NAMESPACE,
9557
14.8k
           "Namespace prefix %s on %s is not defined\n",
9558
14.8k
     prefix, localname, NULL);
9559
14.8k
    }
9560
3.78M
    *pref = prefix;
9561
3.78M
    *URI = uri;
9562
9563
    /*
9564
     * SAX callback
9565
     */
9566
3.78M
    if ((ctxt->sax != NULL) && (ctxt->sax->startElementNs != NULL) &&
9567
3.78M
  (!ctxt->disableSAX)) {
9568
3.78M
  if (nbNs > 0)
9569
7.40k
      ctxt->sax->startElementNs(ctxt->userData, localname, prefix, uri,
9570
7.40k
                          nbNs, ctxt->nsTab + 2 * (ctxt->nsNr - nbNs),
9571
7.40k
        nbatts / 5, nbdef, atts);
9572
3.77M
  else
9573
3.77M
      ctxt->sax->startElementNs(ctxt->userData, localname, prefix, uri,
9574
3.77M
                          0, NULL, nbatts / 5, nbdef, atts);
9575
3.78M
    }
9576
9577
3.78M
done:
9578
    /*
9579
     * Free allocated attribute values
9580
     */
9581
3.78M
    if (attval != 0) {
9582
17.7k
  for (i = 0, j = 0; j < nratts; i += 5, j++)
9583
14.8k
      if (ctxt->attallocs[j] & 0x80000000)
9584
13.9k
          xmlFree((xmlChar *) atts[i+3]);
9585
2.97k
    }
9586
9587
3.78M
    *nbNsPtr = nbNs;
9588
3.78M
    return(localname);
9589
3.78M
}
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
65.7k
xmlParseEndTag2(xmlParserCtxtPtr ctxt, const xmlStartTag *tag) {
9608
65.7k
    const xmlChar *name;
9609
9610
65.7k
    GROW;
9611
65.7k
    if ((RAW != '<') || (NXT(1) != '/')) {
9612
200
  xmlFatalErr(ctxt, XML_ERR_LTSLASH_REQUIRED, NULL);
9613
200
  return;
9614
200
    }
9615
65.5k
    SKIP(2);
9616
9617
65.5k
    if (tag->prefix == NULL)
9618
61.7k
        name = xmlParseNameAndCompare(ctxt, ctxt->name);
9619
3.76k
    else
9620
3.76k
        name = xmlParseQNameAndCompare(ctxt, ctxt->name, tag->prefix);
9621
9622
    /*
9623
     * We should definitely be at the ending "S? '>'" part
9624
     */
9625
65.5k
    GROW;
9626
65.5k
    SKIP_BLANKS;
9627
65.5k
    if ((!IS_BYTE_CHAR(RAW)) || (RAW != '>')) {
9628
47.9k
  xmlFatalErr(ctxt, XML_ERR_GT_REQUIRED, NULL);
9629
47.9k
    } else
9630
17.5k
  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
65.5k
    if (name != (xmlChar*)1) {
9639
56.3k
        if (name == NULL) name = BAD_CAST "unparsable";
9640
56.3k
        xmlFatalErrMsgStrIntStr(ctxt, XML_ERR_TAG_NAME_MISMATCH,
9641
56.3k
         "Opening and ending tag mismatch: %s line %d and %s\n",
9642
56.3k
                    ctxt->name, tag->line, name);
9643
56.3k
    }
9644
9645
    /*
9646
     * SAX: End of Tag
9647
     */
9648
65.5k
    if ((ctxt->sax != NULL) && (ctxt->sax->endElementNs != NULL) &&
9649
65.5k
  (!ctxt->disableSAX))
9650
65.5k
  ctxt->sax->endElementNs(ctxt->userData, ctxt->name, tag->prefix,
9651
65.5k
                                tag->URI);
9652
9653
65.5k
    spacePop(ctxt);
9654
65.5k
    if (tag->nsNr != 0)
9655
3.81k
  xmlParserNsPop(ctxt, tag->nsNr);
9656
65.5k
}
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
6.28k
xmlParseCDSect(xmlParserCtxtPtr ctxt) {
9676
6.28k
    xmlChar *buf = NULL;
9677
6.28k
    int len = 0;
9678
6.28k
    int size = XML_PARSER_BUFFER_SIZE;
9679
6.28k
    int r, rl;
9680
6.28k
    int s, sl;
9681
6.28k
    int cur, l;
9682
6.28k
    int maxLength = (ctxt->options & XML_PARSE_HUGE) ?
9683
0
                    XML_MAX_HUGE_LENGTH :
9684
6.28k
                    XML_MAX_TEXT_LENGTH;
9685
9686
6.28k
    if ((CUR != '<') || (NXT(1) != '!') || (NXT(2) != '['))
9687
0
        return;
9688
6.28k
    SKIP(3);
9689
9690
6.28k
    if (!CMP6(CUR_PTR, 'C', 'D', 'A', 'T', 'A', '['))
9691
0
        return;
9692
6.28k
    SKIP(6);
9693
9694
6.28k
    r = xmlCurrentCharRecover(ctxt, &rl);
9695
6.28k
    if (!IS_CHAR(r)) {
9696
1
  xmlFatalErr(ctxt, XML_ERR_CDATA_NOT_FINISHED, NULL);
9697
1
        goto out;
9698
1
    }
9699
6.28k
    NEXTL(rl);
9700
6.28k
    s = xmlCurrentCharRecover(ctxt, &sl);
9701
6.28k
    if (!IS_CHAR(s)) {
9702
27
  xmlFatalErr(ctxt, XML_ERR_CDATA_NOT_FINISHED, NULL);
9703
27
        goto out;
9704
27
    }
9705
6.26k
    NEXTL(sl);
9706
6.26k
    cur = xmlCurrentCharRecover(ctxt, &l);
9707
6.26k
    buf = xmlMalloc(size);
9708
6.26k
    if (buf == NULL) {
9709
0
  xmlErrMemory(ctxt);
9710
0
        goto out;
9711
0
    }
9712
53.0k
    while (IS_CHAR(cur) &&
9713
53.0k
           ((r != ']') || (s != ']') || (cur != '>'))) {
9714
46.8k
  if (len + 5 >= size) {
9715
409
      xmlChar *tmp;
9716
409
            int newSize;
9717
9718
409
            newSize = xmlGrowCapacity(size, 1, 1, maxLength);
9719
409
            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
409
      tmp = xmlRealloc(buf, newSize);
9725
409
      if (tmp == NULL) {
9726
0
    xmlErrMemory(ctxt);
9727
0
                goto out;
9728
0
      }
9729
409
      buf = tmp;
9730
409
      size = newSize;
9731
409
  }
9732
46.8k
  COPY_BUF(buf, len, r);
9733
46.8k
  r = s;
9734
46.8k
  rl = sl;
9735
46.8k
  s = cur;
9736
46.8k
  sl = l;
9737
46.8k
  NEXTL(l);
9738
46.8k
  cur = xmlCurrentCharRecover(ctxt, &l);
9739
46.8k
    }
9740
6.26k
    buf[len] = 0;
9741
6.26k
    if (cur != '>') {
9742
82
  xmlFatalErrMsgStr(ctxt, XML_ERR_CDATA_NOT_FINISHED,
9743
82
                       "CData section not finished\n%.50s\n", buf);
9744
82
        goto out;
9745
82
    }
9746
6.17k
    NEXTL(l);
9747
9748
    /*
9749
     * OK the buffer is to be consumed as cdata.
9750
     */
9751
6.17k
    if ((ctxt->sax != NULL) && (!ctxt->disableSAX)) {
9752
6.17k
        if ((ctxt->sax->cdataBlock != NULL) &&
9753
6.17k
            ((ctxt->options & XML_PARSE_NOCDATA) == 0)) {
9754
6.17k
            ctxt->sax->cdataBlock(ctxt->userData, buf, len);
9755
6.17k
        } else if (ctxt->sax->characters != NULL) {
9756
0
            ctxt->sax->characters(ctxt->userData, buf, len);
9757
0
        }
9758
6.17k
    }
9759
9760
6.28k
out:
9761
6.28k
    xmlFree(buf);
9762
6.28k
}
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
488
xmlParseContentInternal(xmlParserCtxtPtr ctxt) {
9774
488
    int oldNameNr = ctxt->nameNr;
9775
488
    int oldSpaceNr = ctxt->spaceNr;
9776
488
    int oldNodeNr = ctxt->nodeNr;
9777
9778
488
    GROW;
9779
6.69M
    while ((ctxt->input->cur < ctxt->input->end) &&
9780
6.69M
     (PARSER_STOPPED(ctxt) == 0)) {
9781
6.69M
  const xmlChar *cur = ctxt->input->cur;
9782
9783
  /*
9784
   * First case : a Processing Instruction.
9785
   */
9786
6.69M
  if ((*cur == '<') && (cur[1] == '?')) {
9787
7.66k
      xmlParsePI(ctxt);
9788
7.66k
  }
9789
9790
  /*
9791
   * Second case : a CDSection
9792
   */
9793
  /* 2.6.0 test was *cur not RAW */
9794
6.68M
  else if (CMP9(CUR_PTR, '<', '!', '[', 'C', 'D', 'A', 'T', 'A', '[')) {
9795
6.28k
      xmlParseCDSect(ctxt);
9796
6.28k
  }
9797
9798
  /*
9799
   * Third case :  a comment
9800
   */
9801
6.67M
  else if ((*cur == '<') && (NXT(1) == '!') &&
9802
6.67M
     (NXT(2) == '-') && (NXT(3) == '-')) {
9803
7.01k
      xmlParseComment(ctxt);
9804
7.01k
  }
9805
9806
  /*
9807
   * Fourth case :  a sub-element.
9808
   */
9809
6.67M
  else if (*cur == '<') {
9810
4.10M
            if (NXT(1) == '/') {
9811
65.5k
                if (ctxt->nameNr <= oldNameNr)
9812
0
                    break;
9813
65.5k
          xmlParseElementEnd(ctxt);
9814
4.04M
            } else {
9815
4.04M
          xmlParseElementStart(ctxt);
9816
4.04M
            }
9817
4.10M
  }
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
2.56M
  else if (*cur == '&') {
9825
21.6k
      xmlParseReference(ctxt);
9826
21.6k
  }
9827
9828
  /*
9829
   * Last case, text. Note that References are handled directly.
9830
   */
9831
2.54M
  else {
9832
2.54M
      xmlParseCharDataInternal(ctxt, 0);
9833
2.54M
  }
9834
9835
6.69M
  SHRINK;
9836
6.69M
  GROW;
9837
6.69M
    }
9838
9839
488
    if ((ctxt->nameNr > oldNameNr) &&
9840
488
        (ctxt->input->cur >= ctxt->input->end) &&
9841
488
        (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
23.5k
    while (ctxt->nodeNr > oldNodeNr)
9854
23.0k
        nodePop(ctxt);
9855
9856
23.6k
    while (ctxt->nameNr > oldNameNr) {
9857
23.1k
        xmlStartTag *tag = &ctxt->pushTab[ctxt->nameNr - 1];
9858
9859
23.1k
        if (tag->nsNr != 0)
9860
1.31k
            xmlParserNsPop(ctxt, tag->nsNr);
9861
9862
23.1k
        namePop(ctxt);
9863
23.1k
    }
9864
9865
23.6k
    while (ctxt->spaceNr > oldSpaceNr)
9866
23.1k
        spacePop(ctxt);
9867
488
}
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
488
xmlParseElement(xmlParserCtxtPtr ctxt) {
9907
488
    if (xmlParseElementStart(ctxt) != 0)
9908
41
        return;
9909
9910
447
    xmlParseContentInternal(ctxt);
9911
9912
447
    if (ctxt->input->cur >= ctxt->input->end) {
9913
247
        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
247
        return;
9921
247
    }
9922
9923
200
    xmlParseElementEnd(ctxt);
9924
200
}
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
4.04M
xmlParseElementStart(xmlParserCtxtPtr ctxt) {
9937
4.04M
    int maxDepth = (ctxt->options & XML_PARSE_HUGE) ? 2048 : 256;
9938
4.04M
    const xmlChar *name;
9939
4.04M
    const xmlChar *prefix = NULL;
9940
4.04M
    const xmlChar *URI = NULL;
9941
4.04M
    xmlParserNodeInfo node_info;
9942
4.04M
    int line;
9943
4.04M
    xmlNodePtr cur;
9944
4.04M
    int nbNs = 0;
9945
9946
4.04M
    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
4.04M
    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
4.04M
    if (ctxt->spaceNr == 0)
9962
0
  spacePush(ctxt, -1);
9963
4.04M
    else if (*ctxt->space == -2)
9964
0
  spacePush(ctxt, -1);
9965
4.04M
    else
9966
4.04M
  spacePush(ctxt, *ctxt->space);
9967
9968
4.04M
    line = ctxt->input->line;
9969
#ifdef LIBXML_SAX1_ENABLED
9970
    if (ctxt->sax2)
9971
#endif /* LIBXML_SAX1_ENABLED */
9972
4.04M
        name = xmlParseStartTag2(ctxt, &prefix, &URI, &nbNs);
9973
#ifdef LIBXML_SAX1_ENABLED
9974
    else
9975
  name = xmlParseStartTag(ctxt);
9976
#endif /* LIBXML_SAX1_ENABLED */
9977
4.04M
    if (name == NULL) {
9978
258k
  spacePop(ctxt);
9979
258k
        return(-1);
9980
258k
    }
9981
3.78M
    nameNsPush(ctxt, name, prefix, URI, line, nbNs);
9982
3.78M
    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
3.78M
    if ((RAW == '/') && (NXT(1) == '>')) {
9999
1.46k
        SKIP(2);
10000
1.46k
  if (ctxt->sax2) {
10001
1.46k
      if ((ctxt->sax != NULL) && (ctxt->sax->endElementNs != NULL) &&
10002
1.46k
    (!ctxt->disableSAX))
10003
1.46k
    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
1.46k
  }
10011
1.46k
  namePop(ctxt);
10012
1.46k
  spacePop(ctxt);
10013
1.46k
  if (nbNs > 0)
10014
170
      xmlParserNsPop(ctxt, nbNs);
10015
1.46k
  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
1.46k
  return(1);
10023
1.46k
    }
10024
3.78M
    if (RAW == '>') {
10025
89.1k
        NEXT1;
10026
89.1k
        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
3.69M
    } else {
10033
3.69M
        xmlFatalErrMsgStrIntStr(ctxt, XML_ERR_GT_REQUIRED,
10034
3.69M
         "Couldn't find end of Start Tag %s line %d\n",
10035
3.69M
                    name, line, NULL);
10036
10037
  /*
10038
   * end of parsing of this node.
10039
   */
10040
3.69M
  nodePop(ctxt);
10041
3.69M
  namePop(ctxt);
10042
3.69M
  spacePop(ctxt);
10043
3.69M
  if (nbNs > 0)
10044
2.09k
      xmlParserNsPop(ctxt, nbNs);
10045
3.69M
  return(-1);
10046
3.69M
    }
10047
10048
89.1k
    return(0);
10049
3.78M
}
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
65.7k
xmlParseElementEnd(xmlParserCtxtPtr ctxt) {
10059
65.7k
    xmlNodePtr cur = ctxt->node;
10060
10061
65.7k
    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
65.7k
    if (ctxt->sax2) {
10071
65.7k
  xmlParseEndTag2(ctxt, &ctxt->pushTab[ctxt->nameNr - 1]);
10072
65.7k
  namePop(ctxt);
10073
65.7k
    }
10074
#ifdef LIBXML_SAX1_ENABLED
10075
    else
10076
  xmlParseEndTag1(ctxt, 0);
10077
#endif /* LIBXML_SAX1_ENABLED */
10078
10079
    /*
10080
     * Capture end position
10081
     */
10082
65.7k
    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
65.7k
}
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
279
xmlParseVersionNum(xmlParserCtxtPtr ctxt) {
10110
279
    xmlChar *buf = NULL;
10111
279
    int len = 0;
10112
279
    int size = 10;
10113
279
    int maxLength = (ctxt->options & XML_PARSE_HUGE) ?
10114
0
                    XML_MAX_TEXT_LENGTH :
10115
279
                    XML_MAX_NAME_LENGTH;
10116
279
    xmlChar cur;
10117
10118
279
    buf = xmlMalloc(size);
10119
279
    if (buf == NULL) {
10120
0
  xmlErrMemory(ctxt);
10121
0
  return(NULL);
10122
0
    }
10123
279
    cur = CUR;
10124
279
    if (!((cur >= '0') && (cur <= '9'))) {
10125
0
  xmlFree(buf);
10126
0
  return(NULL);
10127
0
    }
10128
279
    buf[len++] = cur;
10129
279
    NEXT;
10130
279
    cur=CUR;
10131
279
    if (cur != '.') {
10132
4
  xmlFree(buf);
10133
4
  return(NULL);
10134
4
    }
10135
275
    buf[len++] = cur;
10136
275
    NEXT;
10137
275
    cur=CUR;
10138
568
    while ((cur >= '0') && (cur <= '9')) {
10139
293
  if (len + 1 >= size) {
10140
2
      xmlChar *tmp;
10141
2
            int newSize;
10142
10143
2
            newSize = xmlGrowCapacity(size, 1, 1, maxLength);
10144
2
            if (newSize < 0) {
10145
0
                xmlFatalErr(ctxt, XML_ERR_NAME_TOO_LONG, "VersionNum");
10146
0
                xmlFree(buf);
10147
0
                return(NULL);
10148
0
            }
10149
2
      tmp = xmlRealloc(buf, newSize);
10150
2
      if (tmp == NULL) {
10151
0
    xmlErrMemory(ctxt);
10152
0
          xmlFree(buf);
10153
0
    return(NULL);
10154
0
      }
10155
2
      buf = tmp;
10156
2
            size = newSize;
10157
2
  }
10158
293
  buf[len++] = cur;
10159
293
  NEXT;
10160
293
  cur=CUR;
10161
293
    }
10162
275
    buf[len] = 0;
10163
275
    return(buf);
10164
275
}
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
294
xmlParseVersionInfo(xmlParserCtxtPtr ctxt) {
10183
294
    xmlChar *version = NULL;
10184
10185
294
    if (CMP7(CUR_PTR, 'v', 'e', 'r', 's', 'i', 'o', 'n')) {
10186
279
  SKIP(7);
10187
279
  SKIP_BLANKS;
10188
279
  if (RAW != '=') {
10189
0
      xmlFatalErr(ctxt, XML_ERR_EQUAL_REQUIRED, NULL);
10190
0
      return(NULL);
10191
0
        }
10192
279
  NEXT;
10193
279
  SKIP_BLANKS;
10194
279
  if (RAW == '"') {
10195
279
      NEXT;
10196
279
      version = xmlParseVersionNum(ctxt);
10197
279
      if (RAW != '"') {
10198
4
    xmlFatalErr(ctxt, XML_ERR_STRING_NOT_CLOSED, NULL);
10199
4
      } else
10200
275
          NEXT;
10201
279
  } else if (RAW == '\''){
10202
0
      NEXT;
10203
0
      version = xmlParseVersionNum(ctxt);
10204
0
      if (RAW != '\'') {
10205
0
    xmlFatalErr(ctxt, XML_ERR_STRING_NOT_CLOSED, NULL);
10206
0
      } else
10207
0
          NEXT;
10208
0
  } else {
10209
0
      xmlFatalErr(ctxt, XML_ERR_STRING_NOT_STARTED, NULL);
10210
0
  }
10211
279
    }
10212
294
    return(version);
10213
294
}
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
289
xmlParseEncName(xmlParserCtxtPtr ctxt) {
10229
289
    xmlChar *buf = NULL;
10230
289
    int len = 0;
10231
289
    int size = 10;
10232
289
    int maxLength = (ctxt->options & XML_PARSE_HUGE) ?
10233
0
                    XML_MAX_TEXT_LENGTH :
10234
289
                    XML_MAX_NAME_LENGTH;
10235
289
    xmlChar cur;
10236
10237
289
    cur = CUR;
10238
289
    if (((cur >= 'a') && (cur <= 'z')) ||
10239
289
        ((cur >= 'A') && (cur <= 'Z'))) {
10240
289
  buf = xmlMalloc(size);
10241
289
  if (buf == NULL) {
10242
0
      xmlErrMemory(ctxt);
10243
0
      return(NULL);
10244
0
  }
10245
10246
289
  buf[len++] = cur;
10247
289
  NEXT;
10248
289
  cur = CUR;
10249
2.83k
  while (((cur >= 'a') && (cur <= 'z')) ||
10250
2.83k
         ((cur >= 'A') && (cur <= 'Z')) ||
10251
2.83k
         ((cur >= '0') && (cur <= '9')) ||
10252
2.83k
         (cur == '.') || (cur == '_') ||
10253
2.83k
         (cur == '-')) {
10254
2.54k
      if (len + 1 >= size) {
10255
276
          xmlChar *tmp;
10256
276
                int newSize;
10257
10258
276
                newSize = xmlGrowCapacity(size, 1, 1, maxLength);
10259
276
                if (newSize < 0) {
10260
0
                    xmlFatalErr(ctxt, XML_ERR_NAME_TOO_LONG, "EncName");
10261
0
                    xmlFree(buf);
10262
0
                    return(NULL);
10263
0
                }
10264
276
    tmp = xmlRealloc(buf, newSize);
10265
276
    if (tmp == NULL) {
10266
0
        xmlErrMemory(ctxt);
10267
0
        xmlFree(buf);
10268
0
        return(NULL);
10269
0
    }
10270
276
    buf = tmp;
10271
276
                size = newSize;
10272
276
      }
10273
2.54k
      buf[len++] = cur;
10274
2.54k
      NEXT;
10275
2.54k
      cur = CUR;
10276
2.54k
        }
10277
289
  buf[len] = 0;
10278
289
    } else {
10279
0
  xmlFatalErr(ctxt, XML_ERR_ENCODING_NAME, NULL);
10280
0
    }
10281
289
    return(buf);
10282
289
}
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
294
xmlParseEncodingDecl(xmlParserCtxtPtr ctxt) {
10301
294
    xmlChar *encoding = NULL;
10302
10303
294
    SKIP_BLANKS;
10304
294
    if (CMP8(CUR_PTR, 'e', 'n', 'c', 'o', 'd', 'i', 'n', 'g') == 0)
10305
5
        return(NULL);
10306
10307
289
    SKIP(8);
10308
289
    SKIP_BLANKS;
10309
289
    if (RAW != '=') {
10310
0
        xmlFatalErr(ctxt, XML_ERR_EQUAL_REQUIRED, NULL);
10311
0
        return(NULL);
10312
0
    }
10313
289
    NEXT;
10314
289
    SKIP_BLANKS;
10315
289
    if (RAW == '"') {
10316
274
        NEXT;
10317
274
        encoding = xmlParseEncName(ctxt);
10318
274
        if (RAW != '"') {
10319
4
            xmlFatalErr(ctxt, XML_ERR_STRING_NOT_CLOSED, NULL);
10320
4
            xmlFree((xmlChar *) encoding);
10321
4
            return(NULL);
10322
4
        } else
10323
270
            NEXT;
10324
274
    } else if (RAW == '\''){
10325
15
        NEXT;
10326
15
        encoding = xmlParseEncName(ctxt);
10327
15
        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
15
            NEXT;
10333
15
    } else {
10334
0
        xmlFatalErr(ctxt, XML_ERR_STRING_NOT_STARTED, NULL);
10335
0
    }
10336
10337
285
    if (encoding == NULL)
10338
0
        return(NULL);
10339
10340
285
    xmlSetDeclaredEncoding(ctxt, encoding);
10341
10342
285
    return(ctxt->encoding);
10343
285
}
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
75
xmlParseSDDecl(xmlParserCtxtPtr ctxt) {
10380
75
    int standalone = -2;
10381
10382
75
    SKIP_BLANKS;
10383
75
    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
75
    return(standalone);
10429
75
}
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
294
xmlParseXMLDecl(xmlParserCtxtPtr ctxt) {
10444
294
    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
294
    ctxt->standalone = -2;
10453
10454
    /*
10455
     * We know that '<?xml' is here.
10456
     */
10457
294
    SKIP(5);
10458
10459
294
    if (!IS_BLANK_CH(RAW)) {
10460
0
  xmlFatalErrMsg(ctxt, XML_ERR_SPACE_REQUIRED,
10461
0
                 "Blank needed after '<?xml'\n");
10462
0
    }
10463
294
    SKIP_BLANKS;
10464
10465
    /*
10466
     * We must have the VersionInfo here.
10467
     */
10468
294
    version = xmlParseVersionInfo(ctxt);
10469
294
    if (version == NULL) {
10470
19
  xmlFatalErr(ctxt, XML_ERR_VERSION_MISSING, NULL);
10471
275
    } else {
10472
275
  if (!xmlStrEqual(version, (const xmlChar *) XML_DEFAULT_VERSION)) {
10473
      /*
10474
       * Changed here for XML-1.0 5th edition
10475
       */
10476
90
      if (ctxt->options & XML_PARSE_OLD10) {
10477
0
    xmlFatalErrMsgStr(ctxt, XML_ERR_UNKNOWN_VERSION,
10478
0
                "Unsupported version '%s'\n",
10479
0
                version);
10480
90
      } else {
10481
90
          if ((version[0] == '1') && ((version[1] == '.'))) {
10482
1
        xmlWarningMsg(ctxt, XML_WAR_UNKNOWN_VERSION,
10483
1
                      "Unsupported version '%s'\n",
10484
1
          version, NULL);
10485
89
    } else {
10486
89
        xmlFatalErrMsgStr(ctxt, XML_ERR_UNKNOWN_VERSION,
10487
89
              "Unsupported version '%s'\n",
10488
89
              version);
10489
89
    }
10490
90
      }
10491
90
  }
10492
275
  if (ctxt->version != NULL)
10493
0
      xmlFree((void *) ctxt->version);
10494
275
  ctxt->version = version;
10495
275
    }
10496
10497
    /*
10498
     * We may have the encoding declaration
10499
     */
10500
294
    if (!IS_BLANK_CH(RAW)) {
10501
19
        if ((RAW == '?') && (NXT(1) == '>')) {
10502
0
      SKIP(2);
10503
0
      return;
10504
0
  }
10505
19
  xmlFatalErrMsg(ctxt, XML_ERR_SPACE_REQUIRED, "Blank needed here\n");
10506
19
    }
10507
294
    xmlParseEncodingDecl(ctxt);
10508
10509
    /*
10510
     * We may have the standalone status.
10511
     */
10512
294
    if ((ctxt->encoding != NULL) && (!IS_BLANK_CH(RAW))) {
10513
281
        if ((RAW == '?') && (NXT(1) == '>')) {
10514
219
      SKIP(2);
10515
219
      return;
10516
219
  }
10517
62
  xmlFatalErrMsg(ctxt, XML_ERR_SPACE_REQUIRED, "Blank needed here\n");
10518
62
    }
10519
10520
    /*
10521
     * We can grow the input buffer freely at that point
10522
     */
10523
75
    GROW;
10524
10525
75
    SKIP_BLANKS;
10526
75
    ctxt->standalone = xmlParseSDDecl(ctxt);
10527
10528
75
    SKIP_BLANKS;
10529
75
    if ((RAW == '?') && (NXT(1) == '>')) {
10530
1
        SKIP(2);
10531
74
    } else if (RAW == '>') {
10532
        /* Deprecated old WD ... */
10533
0
  xmlFatalErr(ctxt, XML_ERR_XMLDECL_NOT_FINISHED, NULL);
10534
0
  NEXT;
10535
74
    } else {
10536
74
        int c;
10537
10538
74
  xmlFatalErr(ctxt, XML_ERR_XMLDECL_NOT_FINISHED, NULL);
10539
16.8k
        while ((PARSER_STOPPED(ctxt) == 0) &&
10540
16.8k
               ((c = CUR) != 0)) {
10541
16.8k
            NEXT;
10542
16.8k
            if (c == '>')
10543
74
                break;
10544
16.8k
        }
10545
74
    }
10546
75
}
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
1.32k
xmlParseMisc(xmlParserCtxtPtr ctxt) {
10593
1.34k
    while (PARSER_STOPPED(ctxt) == 0) {
10594
1.09k
        SKIP_BLANKS;
10595
1.09k
        GROW;
10596
1.09k
        if ((RAW == '<') && (NXT(1) == '?')) {
10597
22
      xmlParsePI(ctxt);
10598
1.07k
        } else if (CMP4(CUR_PTR, '<', '!', '-', '-')) {
10599
1
      xmlParseComment(ctxt);
10600
1.07k
        } else {
10601
1.07k
            break;
10602
1.07k
        }
10603
1.09k
    }
10604
1.32k
}
10605
10606
static void
10607
541
xmlFinishDocument(xmlParserCtxtPtr ctxt) {
10608
541
    xmlDocPtr doc;
10609
10610
    /*
10611
     * SAX: end of the document processing.
10612
     */
10613
541
    if ((ctxt->sax) && (ctxt->sax->endDocument != NULL))
10614
541
        ctxt->sax->endDocument(ctxt->userData);
10615
10616
541
    doc = ctxt->myDoc;
10617
541
    if (doc != NULL) {
10618
541
        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
541
        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
541
  if (xmlStrEqual(doc->version, SAX_COMPAT_MODE)) {
10633
0
            xmlFreeDoc(doc);
10634
0
            ctxt->myDoc = NULL;
10635
0
        }
10636
541
    }
10637
541
}
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
542
xmlParseDocument(xmlParserCtxtPtr ctxt) {
10652
542
    if ((ctxt == NULL) || (ctxt->input == NULL))
10653
0
        return(-1);
10654
10655
542
    GROW;
10656
10657
    /*
10658
     * SAX: detecting the level.
10659
     */
10660
542
    xmlCtxtInitializeLate(ctxt);
10661
10662
542
    if ((ctxt->sax) && (ctxt->sax->setDocumentLocator)) {
10663
542
        ctxt->sax->setDocumentLocator(ctxt->userData,
10664
542
                (xmlSAXLocator *) &xmlDefaultSAXLocator);
10665
542
    }
10666
10667
542
    xmlDetectEncoding(ctxt);
10668
10669
542
    if (CUR == 0) {
10670
1
  xmlFatalErr(ctxt, XML_ERR_DOCUMENT_EMPTY, NULL);
10671
1
  return(-1);
10672
1
    }
10673
10674
541
    GROW;
10675
541
    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
294
  xmlParseXMLDecl(ctxt);
10681
294
  SKIP_BLANKS;
10682
294
    } else {
10683
247
  ctxt->version = xmlCharStrdup(XML_DEFAULT_VERSION);
10684
247
        if (ctxt->version == NULL) {
10685
0
            xmlErrMemory(ctxt);
10686
0
            return(-1);
10687
0
        }
10688
247
    }
10689
541
    if ((ctxt->sax) && (ctxt->sax->startDocument) && (!ctxt->disableSAX))
10690
541
        ctxt->sax->startDocument(ctxt->userData);
10691
541
    if ((ctxt->myDoc != NULL) && (ctxt->input != NULL) &&
10692
541
        (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
541
    xmlParseMisc(ctxt);
10700
10701
    /*
10702
     * Then possibly doc type declaration(s) and more Misc
10703
     * (doctypedecl Misc*)?
10704
     */
10705
541
    GROW;
10706
541
    if (CMP9(CUR_PTR, '<', '!', 'D', 'O', 'C', 'T', 'Y', 'P', 'E')) {
10707
10708
297
  ctxt->inSubset = 1;
10709
297
  xmlParseDocTypeDecl(ctxt);
10710
297
  if (RAW == '[') {
10711
297
      xmlParseInternalSubset(ctxt);
10712
297
  } else if (RAW == '>') {
10713
0
            NEXT;
10714
0
        }
10715
10716
  /*
10717
   * Create and update the external subset.
10718
   */
10719
297
  ctxt->inSubset = 2;
10720
297
  if ((ctxt->sax != NULL) && (ctxt->sax->externalSubset != NULL) &&
10721
297
      (!ctxt->disableSAX))
10722
258
      ctxt->sax->externalSubset(ctxt->userData, ctxt->intSubName,
10723
258
                                ctxt->extSubSystem, ctxt->extSubURI);
10724
297
  ctxt->inSubset = 0;
10725
10726
297
        xmlCleanSpecialAttr(ctxt);
10727
10728
297
  xmlParseMisc(ctxt);
10729
297
    }
10730
10731
    /*
10732
     * Time to start parsing the tree itself
10733
     */
10734
541
    GROW;
10735
541
    if (RAW != '<') {
10736
53
        if (ctxt->wellFormed)
10737
1
            xmlFatalErrMsg(ctxt, XML_ERR_DOCUMENT_EMPTY,
10738
1
                           "Start tag expected, '<' not found\n");
10739
488
    } else {
10740
488
  xmlParseElement(ctxt);
10741
10742
  /*
10743
   * The Misc part at the end
10744
   */
10745
488
  xmlParseMisc(ctxt);
10746
10747
488
        xmlParserCheckEOF(ctxt, XML_ERR_DOCUMENT_END);
10748
488
    }
10749
10750
541
    ctxt->instate = XML_PARSER_EOF;
10751
541
    xmlFinishDocument(ctxt);
10752
10753
541
    if (! ctxt->wellFormed) {
10754
541
  ctxt->valid = 0;
10755
541
  return(-1);
10756
541
    }
10757
10758
0
    return(0);
10759
541
}
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
326k
xmlStopParser(xmlParserCtxtPtr ctxt) {
11676
326k
    if (ctxt == NULL)
11677
326k
        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
41
                            int hasTextDecl, int buildTree) {
11953
41
    xmlNodePtr root = NULL;
11954
41
    xmlNodePtr list = NULL;
11955
41
    xmlChar *rootName = BAD_CAST "#root";
11956
41
    int result;
11957
11958
41
    if (buildTree) {
11959
41
        root = xmlNewDocNode(ctxt->myDoc, NULL, rootName, NULL);
11960
41
        if (root == NULL) {
11961
0
            xmlErrMemory(ctxt);
11962
0
            goto error;
11963
0
        }
11964
41
    }
11965
11966
41
    if (xmlCtxtPushInput(ctxt, input) < 0)
11967
0
        goto error;
11968
11969
41
    nameNsPush(ctxt, rootName, NULL, NULL, 0, 0);
11970
41
    spacePush(ctxt, -1);
11971
11972
41
    if (buildTree)
11973
41
        nodePush(ctxt, root);
11974
11975
41
    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
41
    xmlParseContentInternal(ctxt);
11997
11998
41
    if (ctxt->input->cur < ctxt->input->end)
11999
39
  xmlFatalErr(ctxt, XML_ERR_NOT_WELL_BALANCED, NULL);
12000
12001
41
    if ((ctxt->wellFormed) ||
12002
41
        ((ctxt->recovery) && (!xmlCtxtIsCatastrophicError(ctxt)))) {
12003
41
        if (root != NULL) {
12004
41
            xmlNodePtr cur;
12005
12006
            /*
12007
             * Unlink newly created node list.
12008
             */
12009
41
            list = root->children;
12010
41
            root->children = NULL;
12011
41
            root->last = NULL;
12012
246
            for (cur = list; cur != NULL; cur = cur->next)
12013
205
                cur->parent = NULL;
12014
41
        }
12015
41
    }
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
41
    do {
12022
41
        ctxt->input->cur = ctxt->input->end;
12023
41
        xmlParserShrink(ctxt);
12024
41
        result = xmlParserGrow(ctxt);
12025
41
    } while (result > 0);
12026
12027
41
    if (buildTree)
12028
41
        nodePop(ctxt);
12029
12030
41
    namePop(ctxt);
12031
41
    spacePop(ctxt);
12032
12033
41
    xmlCtxtPopInput(ctxt);
12034
12035
41
error:
12036
41
    xmlFreeNode(root);
12037
12038
41
    return(list);
12039
41
}
12040
12041
static void
12042
41
xmlCtxtParseEntity(xmlParserCtxtPtr ctxt, xmlEntityPtr ent) {
12043
41
    xmlParserInputPtr input;
12044
41
    xmlNodePtr list;
12045
41
    unsigned long consumed;
12046
41
    int isExternal;
12047
41
    int buildTree;
12048
41
    int oldMinNsIndex;
12049
41
    int oldNodelen, oldNodemem;
12050
12051
41
    isExternal = (ent->etype == XML_EXTERNAL_GENERAL_PARSED_ENTITY);
12052
41
    buildTree = (ctxt->node != NULL);
12053
12054
    /*
12055
     * Recursion check
12056
     */
12057
41
    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
41
    input = xmlNewEntityInputStream(ctxt, ent);
12067
41
    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
41
    oldMinNsIndex = ctxt->nsdb->minNsIndex;
12076
41
    if (buildTree)
12077
41
        ctxt->nsdb->minNsIndex = ctxt->nsNr;
12078
12079
41
    oldNodelen = ctxt->nodelen;
12080
41
    oldNodemem = ctxt->nodemem;
12081
41
    ctxt->nodelen = 0;
12082
41
    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
41
    ent->flags |= XML_ENT_EXPANDING;
12102
12103
41
    list = xmlCtxtParseContentInternal(ctxt, input, isExternal, buildTree);
12104
12105
41
    ent->flags &= ~XML_ENT_EXPANDING;
12106
12107
41
    ctxt->nsdb->minNsIndex = oldMinNsIndex;
12108
41
    ctxt->nodelen = oldNodelen;
12109
41
    ctxt->nodemem = oldNodemem;
12110
12111
    /*
12112
     * Entity size accounting
12113
     */
12114
41
    consumed = input->consumed;
12115
41
    xmlSaturatedAddSizeT(&consumed, input->end - input->base);
12116
12117
41
    if ((ent->flags & XML_ENT_CHECKED) == 0)
12118
41
        xmlSaturatedAdd(&ent->expandedSize, consumed);
12119
12120
41
    if ((ent->flags & XML_ENT_PARSED) == 0) {
12121
41
        if (isExternal)
12122
0
            xmlSaturatedAdd(&ctxt->sizeentities, consumed);
12123
12124
41
        ent->children = list;
12125
12126
246
        while (list != NULL) {
12127
205
            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
205
            if (list->doc != ent->doc)
12135
0
                xmlSetTreeDoc(list, ent->doc);
12136
12137
205
            if (list->next == NULL)
12138
41
                ent->last = list;
12139
205
            list = list->next;
12140
205
        }
12141
41
    } else {
12142
0
        xmlFreeNodeList(list);
12143
0
    }
12144
12145
41
    xmlFreeInputStream(input);
12146
12147
41
error:
12148
41
    ent->flags |= XML_ENT_PARSED | XML_ENT_CHECKED;
12149
41
}
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
543
{
13429
543
    int allMask;
13430
13431
543
    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
543
    allMask = XML_PARSE_RECOVER |
13442
543
              XML_PARSE_NOENT |
13443
543
              XML_PARSE_DTDLOAD |
13444
543
              XML_PARSE_DTDATTR |
13445
543
              XML_PARSE_DTDVALID |
13446
543
              XML_PARSE_NOERROR |
13447
543
              XML_PARSE_NOWARNING |
13448
543
              XML_PARSE_PEDANTIC |
13449
543
              XML_PARSE_NOBLANKS |
13450
#ifdef LIBXML_SAX1_ENABLED
13451
              XML_PARSE_SAX1 |
13452
#endif
13453
543
              XML_PARSE_NONET |
13454
543
              XML_PARSE_NODICT |
13455
543
              XML_PARSE_NSCLEAN |
13456
543
              XML_PARSE_NOCDATA |
13457
543
              XML_PARSE_COMPACT |
13458
543
              XML_PARSE_OLD10 |
13459
543
              XML_PARSE_HUGE |
13460
543
              XML_PARSE_OLDSAX |
13461
543
              XML_PARSE_IGNORE_ENC |
13462
543
              XML_PARSE_BIG_LINES |
13463
543
              XML_PARSE_NO_XXE |
13464
543
              XML_PARSE_UNZIP |
13465
543
              XML_PARSE_NO_SYS_CATALOG |
13466
543
              XML_PARSE_CATALOG_PI;
13467
13468
543
    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
543
    ctxt->recovery = (options & XML_PARSE_RECOVER) ? 1 : 0;
13485
543
    ctxt->replaceEntities = (options & XML_PARSE_NOENT) ? 1 : 0;
13486
543
    ctxt->loadsubset = (options & XML_PARSE_DTDLOAD) ? XML_DETECT_IDS : 0;
13487
543
    ctxt->loadsubset |= (options & XML_PARSE_DTDATTR) ? XML_COMPLETE_ATTRS : 0;
13488
543
    ctxt->validate = (options & XML_PARSE_DTDVALID) ? 1 : 0;
13489
543
    ctxt->pedantic = (options & XML_PARSE_PEDANTIC) ? 1 : 0;
13490
543
    ctxt->keepBlanks = (options & XML_PARSE_NOBLANKS) ? 0 : 1;
13491
543
    ctxt->dictNames = (options & XML_PARSE_NODICT) ? 0 : 1;
13492
13493
543
    if (options & XML_PARSE_HUGE) {
13494
0
        if (ctxt->dict != NULL)
13495
0
            xmlDictSetLimit(ctxt->dict, 0);
13496
0
    }
13497
13498
543
    ctxt->linenumbers = 1;
13499
13500
543
    return(options & ~allMask);
13501
543
}
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
543
{
13734
543
    int keepMask;
13735
13736
543
#ifdef LIBXML_HTML_ENABLED
13737
543
    if ((ctxt != NULL) && (ctxt->html))
13738
0
        return(htmlCtxtUseOptions(ctxt, options));
13739
543
#endif
13740
13741
    /*
13742
     * For historic reasons, some options can only be enabled.
13743
     */
13744
543
    keepMask = XML_PARSE_NOERROR |
13745
543
               XML_PARSE_NOWARNING |
13746
543
               XML_PARSE_NONET |
13747
543
               XML_PARSE_NSCLEAN |
13748
543
               XML_PARSE_NOCDATA |
13749
543
               XML_PARSE_COMPACT |
13750
543
               XML_PARSE_OLD10 |
13751
543
               XML_PARSE_HUGE |
13752
543
               XML_PARSE_OLDSAX |
13753
543
               XML_PARSE_IGNORE_ENC |
13754
543
               XML_PARSE_BIG_LINES;
13755
13756
543
    return(xmlCtxtSetOptionsInternal(ctxt, options, keepMask));
13757
543
}
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
542
{
13793
542
    xmlDocPtr ret = NULL;
13794
13795
542
    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
542
    while (ctxt->inputNr > 0)
13803
0
        xmlFreeInputStream(xmlCtxtPopInput(ctxt));
13804
13805
542
    if (xmlCtxtPushInput(ctxt, input) < 0) {
13806
0
        xmlFreeInputStream(input);
13807
0
        return(NULL);
13808
0
    }
13809
13810
542
    xmlParseDocument(ctxt);
13811
13812
542
    ret = xmlCtxtGetDocument(ctxt);
13813
13814
    /* assert(ctxt->inputNr == 1); */
13815
1.08k
    while (ctxt->inputNr > 0)
13816
542
        xmlFreeInputStream(xmlCtxtPopInput(ctxt));
13817
13818
542
    return(ret);
13819
542
}
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
543
{
13929
543
    xmlParserCtxtPtr ctxt;
13930
543
    xmlParserInputPtr input;
13931
543
    xmlDocPtr doc = NULL;
13932
13933
543
    if (size < 0)
13934
0
  return(NULL);
13935
13936
543
    ctxt = xmlNewParserCtxt();
13937
543
    if (ctxt == NULL)
13938
0
        return(NULL);
13939
13940
543
    xmlCtxtUseOptions(ctxt, options);
13941
13942
543
    input = xmlCtxtNewInputFromMemory(ctxt, url, buffer, size, encoding,
13943
543
                                      XML_INPUT_BUF_STATIC);
13944
13945
543
    if (input != NULL)
13946
542
        doc = xmlCtxtParseDocument(ctxt, input);
13947
13948
543
    xmlFreeParserCtxt(ctxt);
13949
543
    return(doc);
13950
543
}
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