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 | 4.86M | #define NS_INDEX_EMPTY INT_MAX |
80 | 214k | #define NS_INDEX_XML (INT_MAX - 1) |
81 | 906k | #define URI_HASH_EMPTY 0xD943A04E |
82 | 106k | #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 | 1.07M | #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 | 1.30M | #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 | 1.30M | #define XML_ENT_FIXED_COST 20 |
163 | | |
164 | 156M | #define XML_PARSER_BIG_BUFFER_SIZE 300 |
165 | 596k | #define XML_PARSER_BUFFER_SIZE 100 |
166 | 890k | #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 | 2.08k | xmlErrMemory(xmlParserCtxtPtr ctxt) { |
216 | 2.08k | xmlCtxtErrMemory(ctxt); |
217 | 2.08k | } |
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 | 9.63k | { |
231 | 9.63k | if (prefix == NULL) |
232 | 3.24k | xmlCtxtErr(ctxt, NULL, XML_FROM_PARSER, XML_ERR_ATTRIBUTE_REDEFINED, |
233 | 3.24k | XML_ERR_FATAL, localname, NULL, NULL, 0, |
234 | 3.24k | "Attribute %s redefined\n", localname); |
235 | 6.39k | else |
236 | 6.39k | xmlCtxtErr(ctxt, NULL, XML_FROM_PARSER, XML_ERR_ATTRIBUTE_REDEFINED, |
237 | 6.39k | XML_ERR_FATAL, prefix, localname, NULL, 0, |
238 | 6.39k | "Attribute %s:%s redefined\n", prefix, localname); |
239 | 9.63k | } |
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 | 47.6M | { |
253 | 47.6M | xmlCtxtErr(ctxt, NULL, XML_FROM_PARSER, error, XML_ERR_FATAL, |
254 | 47.6M | NULL, NULL, NULL, 0, "%s", msg); |
255 | 47.6M | } |
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 | 59.8k | { |
271 | 59.8k | xmlCtxtErr(ctxt, NULL, XML_FROM_PARSER, error, XML_ERR_WARNING, |
272 | 59.8k | str1, str2, NULL, 0, msg, str1, str2); |
273 | 59.8k | } |
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 | 5.01M | { |
307 | 5.01M | xmlCtxtErr(ctxt, NULL, XML_FROM_PARSER, error, XML_ERR_FATAL, |
308 | 5.01M | NULL, NULL, NULL, val, msg, val); |
309 | 5.01M | } |
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 | 314k | { |
327 | 314k | xmlCtxtErr(ctxt, NULL, XML_FROM_PARSER, error, XML_ERR_FATAL, |
328 | 314k | str1, str2, NULL, val, msg, str1, val, str2); |
329 | 314k | } |
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 | 598k | { |
344 | 598k | xmlCtxtErr(ctxt, NULL, XML_FROM_PARSER, error, XML_ERR_FATAL, |
345 | 598k | val, NULL, NULL, 0, msg, val); |
346 | 598k | } |
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 | 20.9k | { |
361 | 20.9k | xmlCtxtErr(ctxt, NULL, XML_FROM_PARSER, error, XML_ERR_ERROR, |
362 | 20.9k | val, NULL, NULL, 0, msg, val); |
363 | 20.9k | } |
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 | 578k | { |
381 | 578k | ctxt->nsWellFormed = 0; |
382 | | |
383 | 578k | xmlCtxtErr(ctxt, NULL, XML_FROM_NAMESPACE, error, XML_ERR_ERROR, |
384 | 578k | info1, info2, info3, 0, msg, info1, info2, info3); |
385 | 578k | } |
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 | 17.5k | { |
403 | 17.5k | xmlCtxtErr(ctxt, NULL, XML_FROM_NAMESPACE, error, XML_ERR_WARNING, |
404 | 17.5k | info1, info2, info3, 0, msg, info1, info2, info3); |
405 | 17.5k | } |
406 | | |
407 | | static void |
408 | 3.99M | xmlSaturatedAdd(unsigned long *dst, unsigned long val) { |
409 | 3.99M | if (val > ULONG_MAX - *dst) |
410 | 0 | *dst = ULONG_MAX; |
411 | 3.99M | else |
412 | 3.99M | *dst += val; |
413 | 3.99M | } |
414 | | |
415 | | static void |
416 | 1.34M | xmlSaturatedAddSizeT(unsigned long *dst, unsigned long val) { |
417 | 1.34M | if (val > ULONG_MAX - *dst) |
418 | 0 | *dst = ULONG_MAX; |
419 | 1.34M | else |
420 | 1.34M | *dst += val; |
421 | 1.34M | } |
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 | 1.31M | { |
450 | 1.31M | unsigned long consumed; |
451 | 1.31M | unsigned long *expandedSize; |
452 | 1.31M | xmlParserInputPtr input = ctxt->input; |
453 | 1.31M | xmlEntityPtr entity = input->entity; |
454 | | |
455 | 1.31M | if ((entity) && (entity->flags & XML_ENT_CHECKED)) |
456 | 3.95k | return(0); |
457 | | |
458 | | /* |
459 | | * Compute total consumed bytes so far, including input streams of |
460 | | * external entities. |
461 | | */ |
462 | 1.30M | consumed = input->consumed; |
463 | 1.30M | xmlSaturatedAddSizeT(&consumed, input->cur - input->base); |
464 | 1.30M | xmlSaturatedAdd(&consumed, ctxt->sizeentities); |
465 | | |
466 | 1.30M | if (entity) |
467 | 34.0k | expandedSize = &entity->expandedSize; |
468 | 1.27M | else |
469 | 1.27M | expandedSize = &ctxt->sizeentcopy; |
470 | | |
471 | | /* |
472 | | * Add extra cost and some fixed cost. |
473 | | */ |
474 | 1.30M | xmlSaturatedAdd(expandedSize, extra); |
475 | 1.30M | 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 | 1.30M | if ((*expandedSize > XML_PARSER_ALLOWED_EXPANSION) && |
483 | 1.30M | ((*expandedSize >= ULONG_MAX) || |
484 | 23.6k | (*expandedSize / ctxt->maxAmpl > consumed))) { |
485 | 1.84k | xmlFatalErrMsg(ctxt, XML_ERR_RESOURCE_LIMIT, |
486 | 1.84k | "Maximum entity amplification factor exceeded, see " |
487 | 1.84k | "xmlCtxtSetMaxAmplification.\n"); |
488 | 1.84k | xmlHaltParser(ctxt); |
489 | 1.84k | return(1); |
490 | 1.84k | } |
491 | | |
492 | 1.30M | return(0); |
493 | 1.30M | } |
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 | 4.91M | xmlSBufInit(xmlSBuf *buf, unsigned max) { |
713 | 4.91M | buf->mem = NULL; |
714 | 4.91M | buf->size = 0; |
715 | 4.91M | buf->cap = 0; |
716 | 4.91M | buf->max = max; |
717 | 4.91M | buf->code = XML_ERR_OK; |
718 | 4.91M | } |
719 | | |
720 | | static int |
721 | 487k | xmlSBufGrow(xmlSBuf *buf, unsigned len) { |
722 | 487k | xmlChar *mem; |
723 | 487k | unsigned cap; |
724 | | |
725 | 487k | 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 | 487k | cap = (buf->size + len) * 2; |
732 | 487k | if (cap < 240) |
733 | 347k | cap = 240; |
734 | | |
735 | 487k | mem = xmlRealloc(buf->mem, cap); |
736 | 487k | if (mem == NULL) { |
737 | 41.9k | buf->code = XML_ERR_NO_MEMORY; |
738 | 41.9k | return(-1); |
739 | 41.9k | } |
740 | | |
741 | 445k | buf->mem = mem; |
742 | 445k | buf->cap = cap; |
743 | | |
744 | 445k | return(0); |
745 | 487k | } |
746 | | |
747 | | static void |
748 | 98.2M | xmlSBufAddString(xmlSBuf *buf, const xmlChar *str, unsigned len) { |
749 | 98.2M | if (buf->max - buf->size < len) { |
750 | 0 | if (buf->code == XML_ERR_OK) |
751 | 0 | buf->code = XML_ERR_RESOURCE_LIMIT; |
752 | 0 | return; |
753 | 0 | } |
754 | | |
755 | 98.2M | if (buf->cap - buf->size <= len) { |
756 | 470k | if (xmlSBufGrow(buf, len) < 0) |
757 | 41.6k | return; |
758 | 470k | } |
759 | | |
760 | 98.2M | if (len > 0) |
761 | 98.2M | memcpy(buf->mem + buf->size, str, len); |
762 | 98.2M | buf->size += len; |
763 | 98.2M | } |
764 | | |
765 | | static void |
766 | 94.5M | xmlSBufAddCString(xmlSBuf *buf, const char *str, unsigned len) { |
767 | 94.5M | xmlSBufAddString(buf, (const xmlChar *) str, len); |
768 | 94.5M | } |
769 | | |
770 | | static void |
771 | 313k | xmlSBufAddChar(xmlSBuf *buf, int c) { |
772 | 313k | xmlChar *end; |
773 | | |
774 | 313k | if (buf->max - buf->size < 4) { |
775 | 0 | if (buf->code == XML_ERR_OK) |
776 | 0 | buf->code = XML_ERR_RESOURCE_LIMIT; |
777 | 0 | return; |
778 | 0 | } |
779 | | |
780 | 313k | if (buf->cap - buf->size <= 4) { |
781 | 16.1k | if (xmlSBufGrow(buf, 4) < 0) |
782 | 276 | return; |
783 | 16.1k | } |
784 | | |
785 | 312k | end = buf->mem + buf->size; |
786 | | |
787 | 312k | if (c < 0x80) { |
788 | 151k | *end = (xmlChar) c; |
789 | 151k | buf->size += 1; |
790 | 161k | } else { |
791 | 161k | buf->size += xmlCopyCharMultiByte(end, c); |
792 | 161k | } |
793 | 312k | } |
794 | | |
795 | | static void |
796 | 82.3M | xmlSBufAddReplChar(xmlSBuf *buf) { |
797 | 82.3M | xmlSBufAddCString(buf, "\xEF\xBF\xBD", 3); |
798 | 82.3M | } |
799 | | |
800 | | static void |
801 | 172 | xmlSBufReportError(xmlSBuf *buf, xmlParserCtxtPtr ctxt, const char *errMsg) { |
802 | 172 | if (buf->code == XML_ERR_NO_MEMORY) |
803 | 172 | xmlCtxtErrMemory(ctxt); |
804 | 0 | else |
805 | 0 | xmlFatalErr(ctxt, buf->code, errMsg); |
806 | 172 | } |
807 | | |
808 | | static xmlChar * |
809 | | xmlSBufFinish(xmlSBuf *buf, int *sizeOut, xmlParserCtxtPtr ctxt, |
810 | 378k | const char *errMsg) { |
811 | 378k | if (buf->mem == NULL) { |
812 | 39.6k | buf->mem = xmlMalloc(1); |
813 | 39.6k | if (buf->mem == NULL) { |
814 | 27 | buf->code = XML_ERR_NO_MEMORY; |
815 | 39.6k | } else { |
816 | 39.6k | buf->mem[0] = 0; |
817 | 39.6k | } |
818 | 338k | } else { |
819 | 338k | buf->mem[buf->size] = 0; |
820 | 338k | } |
821 | | |
822 | 378k | if (buf->code == XML_ERR_OK) { |
823 | 378k | if (sizeOut != NULL) |
824 | 211k | *sizeOut = buf->size; |
825 | 378k | return(buf->mem); |
826 | 378k | } |
827 | | |
828 | 75 | xmlSBufReportError(buf, ctxt, errMsg); |
829 | | |
830 | 75 | xmlFree(buf->mem); |
831 | | |
832 | 75 | if (sizeOut != NULL) |
833 | 28 | *sizeOut = 0; |
834 | 75 | return(NULL); |
835 | 378k | } |
836 | | |
837 | | static void |
838 | 4.52M | xmlSBufCleanup(xmlSBuf *buf, xmlParserCtxtPtr ctxt, const char *errMsg) { |
839 | 4.52M | if (buf->code != XML_ERR_OK) |
840 | 97 | xmlSBufReportError(buf, ctxt, errMsg); |
841 | | |
842 | 4.52M | xmlFree(buf->mem); |
843 | 4.52M | } |
844 | | |
845 | | static int |
846 | | xmlUTF8MultibyteLen(xmlParserCtxtPtr ctxt, const xmlChar *str, |
847 | 171M | const char *errMsg) { |
848 | 171M | int c = str[0]; |
849 | 171M | int c1 = str[1]; |
850 | | |
851 | 171M | if ((c1 & 0xC0) != 0x80) |
852 | 6.27M | goto encoding_error; |
853 | | |
854 | 165M | if (c < 0xE0) { |
855 | | /* 2-byte sequence */ |
856 | 84.7M | if (c < 0xC2) |
857 | 29.3M | goto encoding_error; |
858 | | |
859 | 55.4M | return(2); |
860 | 84.7M | } else { |
861 | 80.3M | int c2 = str[2]; |
862 | | |
863 | 80.3M | if ((c2 & 0xC0) != 0x80) |
864 | 12.7k | goto encoding_error; |
865 | | |
866 | 80.3M | if (c < 0xF0) { |
867 | | /* 3-byte sequence */ |
868 | 80.3M | if (c == 0xE0) { |
869 | | /* overlong */ |
870 | 2.24M | if (c1 < 0xA0) |
871 | 524 | goto encoding_error; |
872 | 78.0M | } else if (c == 0xED) { |
873 | | /* surrogate */ |
874 | 5.00k | if (c1 >= 0xA0) |
875 | 464 | goto encoding_error; |
876 | 78.0M | } else if (c == 0xEF) { |
877 | | /* U+FFFE and U+FFFF are invalid Chars */ |
878 | 157k | if ((c1 == 0xBF) && (c2 >= 0xBE)) |
879 | 6.77k | xmlFatalErrMsg(ctxt, XML_ERR_INVALID_CHAR, errMsg); |
880 | 157k | } |
881 | | |
882 | 80.3M | return(3); |
883 | 80.3M | } else { |
884 | | /* 4-byte sequence */ |
885 | 48.0k | if ((str[3] & 0xC0) != 0x80) |
886 | 3.42k | goto encoding_error; |
887 | 44.6k | if (c == 0xF0) { |
888 | | /* overlong */ |
889 | 19.4k | if (c1 < 0x90) |
890 | 3.32k | goto encoding_error; |
891 | 25.2k | } else if (c >= 0xF4) { |
892 | | /* greater than 0x10FFFF */ |
893 | 23.5k | if ((c > 0xF4) || (c1 >= 0x90)) |
894 | 23.2k | goto encoding_error; |
895 | 23.5k | } |
896 | | |
897 | 18.0k | return(4); |
898 | 44.6k | } |
899 | 80.3M | } |
900 | | |
901 | 35.6M | encoding_error: |
902 | | /* Only report the first error */ |
903 | 35.6M | if ((ctxt->input->flags & XML_INPUT_ENCODING_ERROR) == 0) { |
904 | 25.4k | xmlCtxtErrIO(ctxt, XML_ERR_INVALID_ENCODING, NULL); |
905 | 25.4k | ctxt->input->flags |= XML_INPUT_ENCODING_ERROR; |
906 | 25.4k | } |
907 | | |
908 | 35.6M | return(0); |
909 | 165M | } |
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 | 872k | xmlCtxtInitializeLate(xmlParserCtxtPtr ctxt) { |
928 | 872k | xmlSAXHandlerPtr sax; |
929 | | |
930 | | /* Avoid unused variable warning if features are disabled. */ |
931 | 872k | (void) sax; |
932 | | |
933 | | /* |
934 | | * Changing the SAX struct directly is still widespread practice |
935 | | * in internal and external code. |
936 | | */ |
937 | 872k | if (ctxt == NULL) return; |
938 | 872k | 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 | 872k | ctxt->sax2 = 1; |
953 | 872k | #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 | 872k | ctxt->str_xml = xmlDictLookup(ctxt->dict, BAD_CAST "xml", 3); |
960 | 872k | ctxt->str_xmlns = xmlDictLookup(ctxt->dict, BAD_CAST "xmlns", 5); |
961 | 872k | ctxt->str_xml_ns = xmlDictLookup(ctxt->dict, XML_XML_NAMESPACE, 36); |
962 | 872k | if ((ctxt->str_xml==NULL) || (ctxt->str_xmlns==NULL) || |
963 | 872k | (ctxt->str_xml_ns == NULL)) { |
964 | 0 | xmlErrMemory(ctxt); |
965 | 0 | } |
966 | | |
967 | 872k | xmlDictSetLimit(ctxt->dict, |
968 | 872k | (ctxt->options & XML_PARSE_HUGE) ? |
969 | 0 | 0 : |
970 | 872k | XML_MAX_DICTIONARY_LIMIT); |
971 | 872k | } |
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 | 48.9k | { |
1015 | 48.9k | if ((src == NULL) || (dst == NULL)) |
1016 | 0 | return(NULL); |
1017 | | |
1018 | 49.3k | while (*src == 0x20) src++; |
1019 | 4.89M | while (*src != 0) { |
1020 | 4.84M | if (*src == 0x20) { |
1021 | 16.5k | while (*src == 0x20) src++; |
1022 | 3.28k | if (*src != 0) |
1023 | 2.63k | *dst++ = 0x20; |
1024 | 4.84M | } else { |
1025 | 4.84M | *dst++ = *src++; |
1026 | 4.84M | } |
1027 | 4.84M | } |
1028 | 48.9k | *dst = 0; |
1029 | 48.9k | if (dst == src) |
1030 | 47.9k | return(NULL); |
1031 | 962 | return(dst); |
1032 | 48.9k | } |
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 | 59.7k | const xmlChar *value) { |
1048 | 59.7k | xmlDefAttrsPtr defaults; |
1049 | 59.7k | xmlDefAttr *attr; |
1050 | 59.7k | int len, expandedSize; |
1051 | 59.7k | xmlHashedString name; |
1052 | 59.7k | xmlHashedString prefix; |
1053 | 59.7k | xmlHashedString hvalue; |
1054 | 59.7k | const xmlChar *localname; |
1055 | | |
1056 | | /* |
1057 | | * Allows to detect attribute redefinitions |
1058 | | */ |
1059 | 59.7k | if (ctxt->attsSpecial != NULL) { |
1060 | 46.1k | if (xmlHashLookup2(ctxt->attsSpecial, fullname, fullattr) != NULL) |
1061 | 2.73k | return; |
1062 | 46.1k | } |
1063 | | |
1064 | 56.9k | if (ctxt->attsDefault == NULL) { |
1065 | 16.2k | ctxt->attsDefault = xmlHashCreateDict(10, ctxt->dict); |
1066 | 16.2k | if (ctxt->attsDefault == NULL) |
1067 | 24 | goto mem_error; |
1068 | 16.2k | } |
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 | 56.9k | localname = xmlSplitQName3(fullname, &len); |
1075 | 56.9k | if (localname == NULL) { |
1076 | 56.3k | name = xmlDictLookupHashed(ctxt->dict, fullname, -1); |
1077 | 56.3k | prefix.name = NULL; |
1078 | 56.3k | } else { |
1079 | 620 | name = xmlDictLookupHashed(ctxt->dict, localname, -1); |
1080 | 620 | prefix = xmlDictLookupHashed(ctxt->dict, fullname, len); |
1081 | 620 | if (prefix.name == NULL) |
1082 | 0 | goto mem_error; |
1083 | 620 | } |
1084 | 56.9k | if (name.name == NULL) |
1085 | 0 | goto mem_error; |
1086 | | |
1087 | | /* |
1088 | | * make sure there is some storage |
1089 | | */ |
1090 | 56.9k | defaults = xmlHashLookup2(ctxt->attsDefault, name.name, prefix.name); |
1091 | 56.9k | if ((defaults == NULL) || |
1092 | 56.9k | (defaults->nbAttrs >= defaults->maxAttrs)) { |
1093 | 23.4k | xmlDefAttrsPtr temp; |
1094 | 23.4k | int newSize; |
1095 | | |
1096 | 23.4k | if (defaults == NULL) { |
1097 | 17.6k | newSize = 4; |
1098 | 17.6k | } else { |
1099 | 5.76k | if ((defaults->maxAttrs >= XML_MAX_ATTRS) || |
1100 | 5.76k | ((size_t) defaults->maxAttrs > |
1101 | 5.76k | SIZE_MAX / 2 / sizeof(temp[0]) - sizeof(*defaults))) |
1102 | 0 | goto mem_error; |
1103 | | |
1104 | 5.76k | if (defaults->maxAttrs > XML_MAX_ATTRS / 2) |
1105 | 0 | newSize = XML_MAX_ATTRS; |
1106 | 5.76k | else |
1107 | 5.76k | newSize = defaults->maxAttrs * 2; |
1108 | 5.76k | } |
1109 | 23.4k | temp = xmlRealloc(defaults, |
1110 | 23.4k | sizeof(*defaults) + newSize * sizeof(xmlDefAttr)); |
1111 | 23.4k | if (temp == NULL) |
1112 | 0 | goto mem_error; |
1113 | 23.4k | if (defaults == NULL) |
1114 | 17.6k | temp->nbAttrs = 0; |
1115 | 23.4k | temp->maxAttrs = newSize; |
1116 | 23.4k | defaults = temp; |
1117 | 23.4k | if (xmlHashUpdateEntry2(ctxt->attsDefault, name.name, prefix.name, |
1118 | 23.4k | defaults, NULL) < 0) { |
1119 | 0 | xmlFree(defaults); |
1120 | 0 | goto mem_error; |
1121 | 0 | } |
1122 | 23.4k | } |
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 | 56.9k | localname = xmlSplitQName3(fullattr, &len); |
1129 | 56.9k | if (localname == NULL) { |
1130 | 22.7k | name = xmlDictLookupHashed(ctxt->dict, fullattr, -1); |
1131 | 22.7k | prefix.name = NULL; |
1132 | 34.2k | } else { |
1133 | 34.2k | name = xmlDictLookupHashed(ctxt->dict, localname, -1); |
1134 | 34.2k | prefix = xmlDictLookupHashed(ctxt->dict, fullattr, len); |
1135 | 34.2k | if (prefix.name == NULL) |
1136 | 0 | goto mem_error; |
1137 | 34.2k | } |
1138 | 56.9k | if (name.name == NULL) |
1139 | 0 | goto mem_error; |
1140 | | |
1141 | | /* intern the string and precompute the end */ |
1142 | 56.9k | len = strlen((const char *) value); |
1143 | 56.9k | hvalue = xmlDictLookupHashed(ctxt->dict, value, len); |
1144 | 56.9k | if (hvalue.name == NULL) |
1145 | 0 | goto mem_error; |
1146 | | |
1147 | 56.9k | expandedSize = strlen((const char *) name.name); |
1148 | 56.9k | if (prefix.name != NULL) |
1149 | 34.2k | expandedSize += strlen((const char *) prefix.name); |
1150 | 56.9k | expandedSize += len; |
1151 | | |
1152 | 56.9k | attr = &defaults->attrs[defaults->nbAttrs++]; |
1153 | 56.9k | attr->name = name; |
1154 | 56.9k | attr->prefix = prefix; |
1155 | 56.9k | attr->value = hvalue; |
1156 | 56.9k | attr->valueEnd = hvalue.name + len; |
1157 | 56.9k | attr->external = PARSER_EXTERNAL(ctxt); |
1158 | 56.9k | attr->expandedSize = expandedSize; |
1159 | | |
1160 | 56.9k | return; |
1161 | | |
1162 | 24 | mem_error: |
1163 | 24 | xmlErrMemory(ctxt); |
1164 | 24 | } |
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 | 96.2k | { |
1181 | 96.2k | if (ctxt->attsSpecial == NULL) { |
1182 | 21.7k | ctxt->attsSpecial = xmlHashCreateDict(10, ctxt->dict); |
1183 | 21.7k | if (ctxt->attsSpecial == NULL) |
1184 | 28 | goto mem_error; |
1185 | 21.7k | } |
1186 | | |
1187 | 96.2k | if (xmlHashAdd2(ctxt->attsSpecial, fullname, fullattr, |
1188 | 96.2k | XML_INT_TO_PTR(type)) < 0) |
1189 | 1 | goto mem_error; |
1190 | 96.2k | return; |
1191 | | |
1192 | 96.2k | mem_error: |
1193 | 29 | xmlErrMemory(ctxt); |
1194 | 29 | } |
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 | 92.2k | const xmlChar *unused ATTRIBUTE_UNUSED) { |
1205 | 92.2k | xmlParserCtxtPtr ctxt = (xmlParserCtxtPtr) data; |
1206 | | |
1207 | 92.2k | if (XML_PTR_TO_INT(payload) == XML_ATTRIBUTE_CDATA) { |
1208 | 26.8k | xmlHashRemoveEntry2(ctxt->attsSpecial, fullname, fullattr, NULL); |
1209 | 26.8k | } |
1210 | 92.2k | } |
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 | 154k | { |
1223 | 154k | if (ctxt->attsSpecial == NULL) |
1224 | 133k | return; |
1225 | | |
1226 | 21.6k | xmlHashScanFull(ctxt->attsSpecial, xmlCleanSpecialAttrCallback, ctxt); |
1227 | | |
1228 | 21.6k | if (xmlHashSize(ctxt->attsSpecial) == 0) { |
1229 | 2.85k | xmlHashFree(ctxt->attsSpecial, NULL); |
1230 | 2.85k | ctxt->attsSpecial = NULL; |
1231 | 2.85k | } |
1232 | 21.6k | } |
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 | 1.02M | xmlParserNsCreate(void) { |
1448 | 1.02M | xmlParserNsData *nsdb = xmlMalloc(sizeof(*nsdb)); |
1449 | | |
1450 | 1.02M | if (nsdb == NULL) |
1451 | 50 | return(NULL); |
1452 | 1.02M | memset(nsdb, 0, sizeof(*nsdb)); |
1453 | 1.02M | nsdb->defaultNsIndex = INT_MAX; |
1454 | | |
1455 | 1.02M | return(nsdb); |
1456 | 1.02M | } |
1457 | | |
1458 | | /** |
1459 | | * xmlParserNsFree: |
1460 | | * @nsdb: namespace database |
1461 | | * |
1462 | | * Free a namespace database. |
1463 | | */ |
1464 | | void |
1465 | 1.02M | xmlParserNsFree(xmlParserNsData *nsdb) { |
1466 | 1.02M | if (nsdb == NULL) |
1467 | 0 | return; |
1468 | | |
1469 | 1.02M | xmlFree(nsdb->extra); |
1470 | 1.02M | xmlFree(nsdb->hash); |
1471 | 1.02M | xmlFree(nsdb); |
1472 | 1.02M | } |
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 | 5.05M | xmlParserNsStartElement(xmlParserNsData *nsdb) { |
1503 | 5.05M | if (nsdb->elementId == UINT_MAX) |
1504 | 0 | return(-1); |
1505 | 5.05M | nsdb->elementId++; |
1506 | | |
1507 | 5.05M | return(0); |
1508 | 5.05M | } |
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 | 9.74M | xmlParserNsBucket **bucketPtr) { |
1526 | 9.74M | xmlParserNsBucket *bucket, *tombstone; |
1527 | 9.74M | unsigned index, hashValue; |
1528 | | |
1529 | 9.74M | if (prefix->name == NULL) |
1530 | 1.22M | return(ctxt->nsdb->defaultNsIndex); |
1531 | | |
1532 | 8.52M | if (ctxt->nsdb->hashSize == 0) |
1533 | 697k | return(INT_MAX); |
1534 | | |
1535 | 7.82M | hashValue = prefix->hashValue; |
1536 | 7.82M | index = hashValue & (ctxt->nsdb->hashSize - 1); |
1537 | 7.82M | bucket = &ctxt->nsdb->hash[index]; |
1538 | 7.82M | tombstone = NULL; |
1539 | | |
1540 | 8.35M | while (bucket->hashValue) { |
1541 | 7.95M | if (bucket->index == INT_MAX) { |
1542 | 70.8k | if (tombstone == NULL) |
1543 | 56.6k | tombstone = bucket; |
1544 | 7.88M | } else if (bucket->hashValue == hashValue) { |
1545 | 7.41M | if (ctxt->nsTab[bucket->index * 2] == prefix->name) { |
1546 | 7.41M | if (bucketPtr != NULL) |
1547 | 1.02M | *bucketPtr = bucket; |
1548 | 7.41M | return(bucket->index); |
1549 | 7.41M | } |
1550 | 7.41M | } |
1551 | | |
1552 | 534k | index++; |
1553 | 534k | bucket++; |
1554 | 534k | if (index == ctxt->nsdb->hashSize) { |
1555 | 23.4k | index = 0; |
1556 | 23.4k | bucket = ctxt->nsdb->hash; |
1557 | 23.4k | } |
1558 | 534k | } |
1559 | | |
1560 | 407k | if (bucketPtr != NULL) |
1561 | 111k | *bucketPtr = tombstone ? tombstone : bucket; |
1562 | 407k | return(INT_MAX); |
1563 | 7.82M | } |
1564 | | |
1565 | | /** |
1566 | | * xmlParserNsLookupUri: |
1567 | | * @ctxt: parser context |
1568 | | * @prefix: namespace prefix |
1569 | | * |
1570 | | * Lookup namespace URI with given prefix. |
1571 | | * |
1572 | | * Returns the namespace URI on success, NULL if no namespace was found. |
1573 | | */ |
1574 | | static const xmlChar * |
1575 | 4.63M | xmlParserNsLookupUri(xmlParserCtxtPtr ctxt, const xmlHashedString *prefix) { |
1576 | 4.63M | const xmlChar *ret; |
1577 | 4.63M | int nsIndex; |
1578 | | |
1579 | 4.63M | if (prefix->name == ctxt->str_xml) |
1580 | 10.6k | return(ctxt->str_xml_ns); |
1581 | | |
1582 | | /* |
1583 | | * minNsIndex is used when building an entity tree. We must |
1584 | | * ignore namespaces declared outside the entity. |
1585 | | */ |
1586 | 4.62M | nsIndex = xmlParserNsLookup(ctxt, prefix, NULL); |
1587 | 4.62M | if ((nsIndex == INT_MAX) || (nsIndex < ctxt->nsdb->minNsIndex)) |
1588 | 1.15M | return(NULL); |
1589 | | |
1590 | 3.47M | ret = ctxt->nsTab[nsIndex * 2 + 1]; |
1591 | 3.47M | if (ret[0] == 0) |
1592 | 21.8k | ret = NULL; |
1593 | 3.47M | return(ret); |
1594 | 4.62M | } |
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 | 2.61M | xmlParserNsLookupSax(xmlParserCtxtPtr ctxt, const xmlChar *prefix) { |
1608 | 2.61M | xmlHashedString hprefix; |
1609 | 2.61M | int nsIndex; |
1610 | | |
1611 | 2.61M | if (prefix == ctxt->str_xml) |
1612 | 111k | return(NULL); |
1613 | | |
1614 | 2.50M | hprefix.name = prefix; |
1615 | 2.50M | if (prefix != NULL) |
1616 | 2.48M | hprefix.hashValue = xmlDictComputeHash(ctxt->dict, prefix); |
1617 | 24.2k | else |
1618 | 24.2k | hprefix.hashValue = 0; |
1619 | 2.50M | nsIndex = xmlParserNsLookup(ctxt, &hprefix, NULL); |
1620 | 2.50M | if ((nsIndex == INT_MAX) || (nsIndex < ctxt->nsdb->minNsIndex)) |
1621 | 0 | return(NULL); |
1622 | | |
1623 | 2.50M | return(ctxt->nsdb->extra[nsIndex].saxData); |
1624 | 2.50M | } |
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 | 725k | void *saxData) { |
1641 | 725k | xmlHashedString hprefix; |
1642 | 725k | int nsIndex; |
1643 | | |
1644 | 725k | if (prefix == ctxt->str_xml) |
1645 | 0 | return(-1); |
1646 | | |
1647 | 725k | hprefix.name = prefix; |
1648 | 725k | if (prefix != NULL) |
1649 | 708k | hprefix.hashValue = xmlDictComputeHash(ctxt->dict, prefix); |
1650 | 17.0k | else |
1651 | 17.0k | hprefix.hashValue = 0; |
1652 | 725k | nsIndex = xmlParserNsLookup(ctxt, &hprefix, NULL); |
1653 | 725k | if ((nsIndex == INT_MAX) || (nsIndex < ctxt->nsdb->minNsIndex)) |
1654 | 0 | return(-1); |
1655 | | |
1656 | 725k | ctxt->nsdb->extra[nsIndex].saxData = saxData; |
1657 | 725k | return(0); |
1658 | 725k | } |
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 | 760k | xmlParserNsGrow(xmlParserCtxtPtr ctxt) { |
1670 | 760k | const xmlChar **table; |
1671 | 760k | xmlParserNsExtra *extra; |
1672 | 760k | int newSize; |
1673 | | |
1674 | 760k | newSize = xmlGrowCapacity(ctxt->nsMax, |
1675 | 760k | sizeof(table[0]) + sizeof(extra[0]), |
1676 | 760k | 16, XML_MAX_ITEMS); |
1677 | 760k | if (newSize < 0) |
1678 | 0 | goto error; |
1679 | | |
1680 | 760k | table = xmlRealloc(ctxt->nsTab, 2 * newSize * sizeof(table[0])); |
1681 | 760k | if (table == NULL) |
1682 | 75 | goto error; |
1683 | 760k | ctxt->nsTab = table; |
1684 | | |
1685 | 760k | extra = xmlRealloc(ctxt->nsdb->extra, newSize * sizeof(extra[0])); |
1686 | 760k | if (extra == NULL) |
1687 | 39 | goto error; |
1688 | 760k | ctxt->nsdb->extra = extra; |
1689 | | |
1690 | 760k | ctxt->nsMax = newSize; |
1691 | 760k | return(0); |
1692 | | |
1693 | 114 | error: |
1694 | 114 | xmlErrMemory(ctxt); |
1695 | 114 | return(-1); |
1696 | 760k | } |
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 | 966k | const xmlHashedString *uri, void *saxData, int defAttr) { |
1714 | 966k | xmlParserNsBucket *bucket = NULL; |
1715 | 966k | xmlParserNsExtra *extra; |
1716 | 966k | const xmlChar **ns; |
1717 | 966k | unsigned hashValue, nsIndex, oldIndex; |
1718 | | |
1719 | 966k | if ((prefix != NULL) && (prefix->name == ctxt->str_xml)) |
1720 | 1.13k | return(0); |
1721 | | |
1722 | 965k | if ((ctxt->nsNr >= ctxt->nsMax) && (xmlParserNsGrow(ctxt) < 0)) { |
1723 | 114 | xmlErrMemory(ctxt); |
1724 | 114 | return(-1); |
1725 | 114 | } |
1726 | | |
1727 | | /* |
1728 | | * Default namespace and 'xml' namespace |
1729 | | */ |
1730 | 965k | if ((prefix == NULL) || (prefix->name == NULL)) { |
1731 | 73.6k | oldIndex = ctxt->nsdb->defaultNsIndex; |
1732 | | |
1733 | 73.6k | if (oldIndex != INT_MAX) { |
1734 | 47.4k | extra = &ctxt->nsdb->extra[oldIndex]; |
1735 | | |
1736 | 47.4k | if (extra->elementId == ctxt->nsdb->elementId) { |
1737 | 2.42k | if (defAttr == 0) |
1738 | 593 | xmlErrAttributeDup(ctxt, NULL, BAD_CAST "xmlns"); |
1739 | 2.42k | return(0); |
1740 | 2.42k | } |
1741 | | |
1742 | 44.9k | if ((ctxt->options & XML_PARSE_NSCLEAN) && |
1743 | 44.9k | (uri->name == ctxt->nsTab[oldIndex * 2 + 1])) |
1744 | 0 | return(0); |
1745 | 44.9k | } |
1746 | | |
1747 | 71.2k | ctxt->nsdb->defaultNsIndex = ctxt->nsNr; |
1748 | 71.2k | goto populate_entry; |
1749 | 73.6k | } |
1750 | | |
1751 | | /* |
1752 | | * Hash table lookup |
1753 | | */ |
1754 | 891k | oldIndex = xmlParserNsLookup(ctxt, prefix, &bucket); |
1755 | 891k | if (oldIndex != INT_MAX) { |
1756 | 156k | extra = &ctxt->nsdb->extra[oldIndex]; |
1757 | | |
1758 | | /* |
1759 | | * Check for duplicate definitions on the same element. |
1760 | | */ |
1761 | 156k | if (extra->elementId == ctxt->nsdb->elementId) { |
1762 | 4.70k | if (defAttr == 0) |
1763 | 4.46k | xmlErrAttributeDup(ctxt, BAD_CAST "xmlns", prefix->name); |
1764 | 4.70k | return(0); |
1765 | 4.70k | } |
1766 | | |
1767 | 151k | if ((ctxt->options & XML_PARSE_NSCLEAN) && |
1768 | 151k | (uri->name == ctxt->nsTab[bucket->index * 2 + 1])) |
1769 | 0 | return(0); |
1770 | | |
1771 | 151k | bucket->index = ctxt->nsNr; |
1772 | 151k | goto populate_entry; |
1773 | 151k | } |
1774 | | |
1775 | | /* |
1776 | | * Insert new bucket |
1777 | | */ |
1778 | | |
1779 | 735k | hashValue = prefix->hashValue; |
1780 | | |
1781 | | /* |
1782 | | * Grow hash table, 50% fill factor |
1783 | | */ |
1784 | 735k | if (ctxt->nsdb->hashElems + 1 > ctxt->nsdb->hashSize / 2) { |
1785 | 626k | xmlParserNsBucket *newHash; |
1786 | 626k | unsigned newSize, i, index; |
1787 | | |
1788 | 626k | if (ctxt->nsdb->hashSize > UINT_MAX / 2) { |
1789 | 0 | xmlErrMemory(ctxt); |
1790 | 0 | return(-1); |
1791 | 0 | } |
1792 | 626k | newSize = ctxt->nsdb->hashSize ? ctxt->nsdb->hashSize * 2 : 16; |
1793 | 626k | newHash = xmlMalloc(newSize * sizeof(newHash[0])); |
1794 | 626k | if (newHash == NULL) { |
1795 | 50 | xmlErrMemory(ctxt); |
1796 | 50 | return(-1); |
1797 | 50 | } |
1798 | 626k | memset(newHash, 0, newSize * sizeof(newHash[0])); |
1799 | | |
1800 | 679k | for (i = 0; i < ctxt->nsdb->hashSize; i++) { |
1801 | 53.5k | unsigned hv = ctxt->nsdb->hash[i].hashValue; |
1802 | 53.5k | unsigned newIndex; |
1803 | | |
1804 | 53.5k | if ((hv == 0) || (ctxt->nsdb->hash[i].index == INT_MAX)) |
1805 | 40.8k | continue; |
1806 | 12.7k | newIndex = hv & (newSize - 1); |
1807 | | |
1808 | 21.6k | while (newHash[newIndex].hashValue != 0) { |
1809 | 8.97k | newIndex++; |
1810 | 8.97k | if (newIndex == newSize) |
1811 | 2.56k | newIndex = 0; |
1812 | 8.97k | } |
1813 | | |
1814 | 12.7k | newHash[newIndex] = ctxt->nsdb->hash[i]; |
1815 | 12.7k | } |
1816 | | |
1817 | 626k | xmlFree(ctxt->nsdb->hash); |
1818 | 626k | ctxt->nsdb->hash = newHash; |
1819 | 626k | ctxt->nsdb->hashSize = newSize; |
1820 | | |
1821 | | /* |
1822 | | * Relookup |
1823 | | */ |
1824 | 626k | index = hashValue & (newSize - 1); |
1825 | | |
1826 | 629k | while (newHash[index].hashValue != 0) { |
1827 | 3.52k | index++; |
1828 | 3.52k | if (index == newSize) |
1829 | 507 | index = 0; |
1830 | 3.52k | } |
1831 | | |
1832 | 626k | bucket = &newHash[index]; |
1833 | 626k | } |
1834 | | |
1835 | 735k | bucket->hashValue = hashValue; |
1836 | 735k | bucket->index = ctxt->nsNr; |
1837 | 735k | ctxt->nsdb->hashElems++; |
1838 | 735k | oldIndex = INT_MAX; |
1839 | | |
1840 | 958k | populate_entry: |
1841 | 958k | nsIndex = ctxt->nsNr; |
1842 | | |
1843 | 958k | ns = &ctxt->nsTab[nsIndex * 2]; |
1844 | 958k | ns[0] = prefix ? prefix->name : NULL; |
1845 | 958k | ns[1] = uri->name; |
1846 | | |
1847 | 958k | extra = &ctxt->nsdb->extra[nsIndex]; |
1848 | 958k | extra->saxData = saxData; |
1849 | 958k | extra->prefixHashValue = prefix ? prefix->hashValue : 0; |
1850 | 958k | extra->uriHashValue = uri->hashValue; |
1851 | 958k | extra->elementId = ctxt->nsdb->elementId; |
1852 | 958k | extra->oldIndex = oldIndex; |
1853 | | |
1854 | 958k | ctxt->nsNr++; |
1855 | | |
1856 | 958k | return(1); |
1857 | 735k | } |
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 | 695k | { |
1871 | 695k | int i; |
1872 | | |
1873 | | /* assert(nr <= ctxt->nsNr); */ |
1874 | | |
1875 | 1.63M | for (i = ctxt->nsNr - 1; i >= ctxt->nsNr - nr; i--) { |
1876 | 935k | const xmlChar *prefix = ctxt->nsTab[i * 2]; |
1877 | 935k | xmlParserNsExtra *extra = &ctxt->nsdb->extra[i]; |
1878 | | |
1879 | 935k | if (prefix == NULL) { |
1880 | 67.1k | ctxt->nsdb->defaultNsIndex = extra->oldIndex; |
1881 | 868k | } else { |
1882 | 868k | xmlHashedString hprefix; |
1883 | 868k | xmlParserNsBucket *bucket = NULL; |
1884 | | |
1885 | 868k | hprefix.name = prefix; |
1886 | 868k | hprefix.hashValue = extra->prefixHashValue; |
1887 | 868k | xmlParserNsLookup(ctxt, &hprefix, &bucket); |
1888 | | /* assert(bucket && bucket->hashValue); */ |
1889 | 868k | bucket->index = extra->oldIndex; |
1890 | 868k | } |
1891 | 935k | } |
1892 | | |
1893 | 695k | ctxt->nsNr -= nr; |
1894 | 695k | return(nr); |
1895 | 695k | } |
1896 | | |
1897 | | static int |
1898 | 870k | xmlCtxtGrowAttrs(xmlParserCtxtPtr ctxt) { |
1899 | 870k | const xmlChar **atts; |
1900 | 870k | unsigned *attallocs; |
1901 | 870k | int newSize; |
1902 | | |
1903 | 870k | newSize = xmlGrowCapacity(ctxt->maxatts / 5, |
1904 | 870k | sizeof(atts[0]) * 5 + sizeof(attallocs[0]), |
1905 | 870k | 10, XML_MAX_ATTRS); |
1906 | 870k | 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 | 870k | atts = xmlRealloc(ctxt->atts, newSize * sizeof(atts[0]) * 5); |
1913 | 870k | if (atts == NULL) |
1914 | 51 | goto mem_error; |
1915 | 870k | ctxt->atts = atts; |
1916 | | |
1917 | 870k | attallocs = xmlRealloc(ctxt->attallocs, |
1918 | 870k | newSize * sizeof(attallocs[0])); |
1919 | 870k | if (attallocs == NULL) |
1920 | 42 | goto mem_error; |
1921 | 870k | ctxt->attallocs = attallocs; |
1922 | | |
1923 | 870k | ctxt->maxatts = newSize * 5; |
1924 | | |
1925 | 870k | return(0); |
1926 | | |
1927 | 93 | mem_error: |
1928 | 93 | xmlErrMemory(ctxt); |
1929 | 93 | return(-1); |
1930 | 870k | } |
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 | 933k | { |
1944 | 933k | char *directory = NULL; |
1945 | 933k | int maxDepth; |
1946 | | |
1947 | 933k | if ((ctxt == NULL) || (value == NULL)) |
1948 | 9.05k | return(-1); |
1949 | | |
1950 | 924k | maxDepth = (ctxt->options & XML_PARSE_HUGE) ? 40 : 20; |
1951 | | |
1952 | 924k | if (ctxt->inputNr >= ctxt->inputMax) { |
1953 | 33.7k | xmlParserInputPtr *tmp; |
1954 | 33.7k | int newSize; |
1955 | | |
1956 | 33.7k | newSize = xmlGrowCapacity(ctxt->inputMax, sizeof(tmp[0]), |
1957 | 33.7k | 5, maxDepth); |
1958 | 33.7k | 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 | 33.7k | tmp = xmlRealloc(ctxt->inputTab, newSize * sizeof(tmp[0])); |
1965 | 33.7k | if (tmp == NULL) { |
1966 | 1 | xmlErrMemory(ctxt); |
1967 | 1 | return(-1); |
1968 | 1 | } |
1969 | 33.6k | ctxt->inputTab = tmp; |
1970 | 33.6k | ctxt->inputMax = newSize; |
1971 | 33.6k | } |
1972 | | |
1973 | 924k | if ((ctxt->inputNr == 0) && (value->filename != NULL)) { |
1974 | 65.4k | directory = xmlParserGetDirectory(value->filename); |
1975 | 65.4k | if (directory == NULL) { |
1976 | 0 | xmlErrMemory(ctxt); |
1977 | 0 | return(-1); |
1978 | 0 | } |
1979 | 65.4k | } |
1980 | | |
1981 | 924k | 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 | 924k | ctxt->inputTab[ctxt->inputNr] = value; |
1987 | 924k | ctxt->input = value; |
1988 | | |
1989 | 924k | if (ctxt->inputNr == 0) { |
1990 | 880k | xmlFree(ctxt->directory); |
1991 | 880k | ctxt->directory = directory; |
1992 | 880k | } |
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 | 924k | value->id = ctxt->input_id++; |
2000 | | |
2001 | 924k | return(ctxt->inputNr++); |
2002 | 924k | } |
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 | 2.96M | { |
2015 | 2.96M | xmlParserInputPtr ret; |
2016 | | |
2017 | 2.96M | if (ctxt == NULL) |
2018 | 0 | return(NULL); |
2019 | 2.96M | if (ctxt->inputNr <= 0) |
2020 | 2.05M | return (NULL); |
2021 | 911k | ctxt->inputNr--; |
2022 | 911k | if (ctxt->inputNr > 0) |
2023 | 44.0k | ctxt->input = ctxt->inputTab[ctxt->inputNr - 1]; |
2024 | 867k | else |
2025 | 867k | ctxt->input = NULL; |
2026 | 911k | ret = ctxt->inputTab[ctxt->inputNr]; |
2027 | 911k | ctxt->inputTab[ctxt->inputNr] = NULL; |
2028 | 911k | return (ret); |
2029 | 2.96M | } |
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 | 3.94M | { |
2045 | 3.94M | if (ctxt == NULL) |
2046 | 0 | return(0); |
2047 | | |
2048 | 3.94M | if (ctxt->nodeNr >= ctxt->nodeMax) { |
2049 | 821k | int maxDepth = (ctxt->options & XML_PARSE_HUGE) ? 2048 : 256; |
2050 | 821k | xmlNodePtr *tmp; |
2051 | 821k | int newSize; |
2052 | | |
2053 | 821k | newSize = xmlGrowCapacity(ctxt->nodeMax, sizeof(tmp[0]), |
2054 | 821k | 10, maxDepth); |
2055 | 821k | if (newSize < 0) { |
2056 | 297 | xmlFatalErrMsgInt(ctxt, XML_ERR_RESOURCE_LIMIT, |
2057 | 297 | "Excessive depth in document: %d," |
2058 | 297 | " use XML_PARSE_HUGE option\n", |
2059 | 297 | ctxt->nodeNr); |
2060 | 297 | xmlHaltParser(ctxt); |
2061 | 297 | return(-1); |
2062 | 297 | } |
2063 | | |
2064 | 820k | tmp = xmlRealloc(ctxt->nodeTab, newSize * sizeof(tmp[0])); |
2065 | 820k | if (tmp == NULL) { |
2066 | 46 | xmlErrMemory(ctxt); |
2067 | 46 | return (-1); |
2068 | 46 | } |
2069 | 820k | ctxt->nodeTab = tmp; |
2070 | 820k | ctxt->nodeMax = newSize; |
2071 | 820k | } |
2072 | | |
2073 | 3.94M | ctxt->nodeTab[ctxt->nodeNr] = value; |
2074 | 3.94M | ctxt->node = value; |
2075 | 3.94M | return (ctxt->nodeNr++); |
2076 | 3.94M | } |
2077 | | |
2078 | | /** |
2079 | | * nodePop: |
2080 | | * @ctxt: an XML parser context |
2081 | | * |
2082 | | * DEPRECATED: Internal function, do not use. |
2083 | | * |
2084 | | * Pops the top element node from the node stack |
2085 | | * |
2086 | | * Returns the node just removed |
2087 | | */ |
2088 | | xmlNodePtr |
2089 | | nodePop(xmlParserCtxtPtr ctxt) |
2090 | 4.09M | { |
2091 | 4.09M | xmlNodePtr ret; |
2092 | | |
2093 | 4.09M | if (ctxt == NULL) return(NULL); |
2094 | 4.09M | if (ctxt->nodeNr <= 0) |
2095 | 166k | return (NULL); |
2096 | 3.93M | ctxt->nodeNr--; |
2097 | 3.93M | if (ctxt->nodeNr > 0) |
2098 | 3.28M | ctxt->node = ctxt->nodeTab[ctxt->nodeNr - 1]; |
2099 | 643k | else |
2100 | 643k | ctxt->node = NULL; |
2101 | 3.93M | ret = ctxt->nodeTab[ctxt->nodeNr]; |
2102 | 3.93M | ctxt->nodeTab[ctxt->nodeNr] = NULL; |
2103 | 3.93M | return (ret); |
2104 | 4.09M | } |
2105 | | |
2106 | | /** |
2107 | | * nameNsPush: |
2108 | | * @ctxt: an XML parser context |
2109 | | * @value: the element name |
2110 | | * @prefix: the element prefix |
2111 | | * @URI: the element namespace name |
2112 | | * @line: the current line number for error messages |
2113 | | * @nsNr: the number of namespaces pushed on the namespace table |
2114 | | * |
2115 | | * Pushes a new element name/prefix/URL on top of the name stack |
2116 | | * |
2117 | | * Returns -1 in case of error, the index in the stack otherwise |
2118 | | */ |
2119 | | static int |
2120 | | nameNsPush(xmlParserCtxtPtr ctxt, const xmlChar * value, |
2121 | | const xmlChar *prefix, const xmlChar *URI, int line, int nsNr) |
2122 | 4.64M | { |
2123 | 4.64M | xmlStartTag *tag; |
2124 | | |
2125 | 4.64M | if (ctxt->nameNr >= ctxt->nameMax) { |
2126 | 914k | const xmlChar **tmp; |
2127 | 914k | xmlStartTag *tmp2; |
2128 | 914k | int newSize; |
2129 | | |
2130 | 914k | newSize = xmlGrowCapacity(ctxt->nameMax, |
2131 | 914k | sizeof(tmp[0]) + sizeof(tmp2[0]), |
2132 | 914k | 10, XML_MAX_ITEMS); |
2133 | 914k | if (newSize < 0) |
2134 | 0 | goto mem_error; |
2135 | | |
2136 | 914k | tmp = xmlRealloc(ctxt->nameTab, newSize * sizeof(tmp[0])); |
2137 | 914k | if (tmp == NULL) |
2138 | 269 | goto mem_error; |
2139 | 914k | ctxt->nameTab = tmp; |
2140 | | |
2141 | 914k | tmp2 = xmlRealloc(ctxt->pushTab, newSize * sizeof(tmp2[0])); |
2142 | 914k | if (tmp2 == NULL) |
2143 | 39 | goto mem_error; |
2144 | 914k | ctxt->pushTab = tmp2; |
2145 | | |
2146 | 914k | ctxt->nameMax = newSize; |
2147 | 3.73M | } else if (ctxt->pushTab == NULL) { |
2148 | 695k | ctxt->pushTab = xmlMalloc(ctxt->nameMax * sizeof(ctxt->pushTab[0])); |
2149 | 695k | if (ctxt->pushTab == NULL) |
2150 | 725 | goto mem_error; |
2151 | 695k | } |
2152 | 4.64M | ctxt->nameTab[ctxt->nameNr] = value; |
2153 | 4.64M | ctxt->name = value; |
2154 | 4.64M | tag = &ctxt->pushTab[ctxt->nameNr]; |
2155 | 4.64M | tag->prefix = prefix; |
2156 | 4.64M | tag->URI = URI; |
2157 | 4.64M | tag->line = line; |
2158 | 4.64M | tag->nsNr = nsNr; |
2159 | 4.64M | return (ctxt->nameNr++); |
2160 | 1.03k | mem_error: |
2161 | 1.03k | xmlErrMemory(ctxt); |
2162 | 1.03k | return (-1); |
2163 | 4.64M | } |
2164 | | #ifdef LIBXML_PUSH_ENABLED |
2165 | | /** |
2166 | | * nameNsPop: |
2167 | | * @ctxt: an XML parser context |
2168 | | * |
2169 | | * Pops the top element/prefix/URI name from the name stack |
2170 | | * |
2171 | | * Returns the name just removed |
2172 | | */ |
2173 | | static const xmlChar * |
2174 | | nameNsPop(xmlParserCtxtPtr ctxt) |
2175 | | { |
2176 | | const xmlChar *ret; |
2177 | | |
2178 | | if (ctxt->nameNr <= 0) |
2179 | | return (NULL); |
2180 | | ctxt->nameNr--; |
2181 | | if (ctxt->nameNr > 0) |
2182 | | ctxt->name = ctxt->nameTab[ctxt->nameNr - 1]; |
2183 | | else |
2184 | | ctxt->name = NULL; |
2185 | | ret = ctxt->nameTab[ctxt->nameNr]; |
2186 | | ctxt->nameTab[ctxt->nameNr] = NULL; |
2187 | | return (ret); |
2188 | | } |
2189 | | #endif /* LIBXML_PUSH_ENABLED */ |
2190 | | |
2191 | | /** |
2192 | | * namePop: |
2193 | | * @ctxt: an XML parser context |
2194 | | * |
2195 | | * DEPRECATED: Internal function, do not use. |
2196 | | * |
2197 | | * Pops the top element name from the name stack |
2198 | | * |
2199 | | * Returns the name just removed |
2200 | | */ |
2201 | | static const xmlChar * |
2202 | | namePop(xmlParserCtxtPtr ctxt) |
2203 | 4.60M | { |
2204 | 4.60M | const xmlChar *ret; |
2205 | | |
2206 | 4.60M | if ((ctxt == NULL) || (ctxt->nameNr <= 0)) |
2207 | 277 | return (NULL); |
2208 | 4.60M | ctxt->nameNr--; |
2209 | 4.60M | if (ctxt->nameNr > 0) |
2210 | 3.95M | ctxt->name = ctxt->nameTab[ctxt->nameNr - 1]; |
2211 | 649k | else |
2212 | 649k | ctxt->name = NULL; |
2213 | 4.60M | ret = ctxt->nameTab[ctxt->nameNr]; |
2214 | 4.60M | ctxt->nameTab[ctxt->nameNr] = NULL; |
2215 | 4.60M | return (ret); |
2216 | 4.60M | } |
2217 | | |
2218 | 5.06M | static int spacePush(xmlParserCtxtPtr ctxt, int val) { |
2219 | 5.06M | if (ctxt->spaceNr >= ctxt->spaceMax) { |
2220 | 1.57M | int *tmp; |
2221 | 1.57M | int newSize; |
2222 | | |
2223 | 1.57M | newSize = xmlGrowCapacity(ctxt->spaceMax, sizeof(tmp[0]), |
2224 | 1.57M | 10, XML_MAX_ITEMS); |
2225 | 1.57M | if (newSize < 0) { |
2226 | 0 | xmlErrMemory(ctxt); |
2227 | 0 | return(-1); |
2228 | 0 | } |
2229 | | |
2230 | 1.57M | tmp = xmlRealloc(ctxt->spaceTab, newSize * sizeof(tmp[0])); |
2231 | 1.57M | if (tmp == NULL) { |
2232 | 172 | xmlErrMemory(ctxt); |
2233 | 172 | return(-1); |
2234 | 172 | } |
2235 | 1.57M | ctxt->spaceTab = tmp; |
2236 | | |
2237 | 1.57M | ctxt->spaceMax = newSize; |
2238 | 1.57M | } |
2239 | 5.06M | ctxt->spaceTab[ctxt->spaceNr] = val; |
2240 | 5.06M | ctxt->space = &ctxt->spaceTab[ctxt->spaceNr]; |
2241 | 5.06M | return(ctxt->spaceNr++); |
2242 | 5.06M | } |
2243 | | |
2244 | 5.01M | static int spacePop(xmlParserCtxtPtr ctxt) { |
2245 | 5.01M | int ret; |
2246 | 5.01M | if (ctxt->spaceNr <= 0) return(0); |
2247 | 5.01M | ctxt->spaceNr--; |
2248 | 5.01M | if (ctxt->spaceNr > 0) |
2249 | 5.01M | ctxt->space = &ctxt->spaceTab[ctxt->spaceNr - 1]; |
2250 | 122 | else |
2251 | 122 | ctxt->space = &ctxt->spaceTab[0]; |
2252 | 5.01M | ret = ctxt->spaceTab[ctxt->spaceNr]; |
2253 | 5.01M | ctxt->spaceTab[ctxt->spaceNr] = -1; |
2254 | 5.01M | return(ret); |
2255 | 5.01M | } |
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 | 52.6M | #define RAW (*ctxt->input->cur) |
2291 | 405M | #define CUR (*ctxt->input->cur) |
2292 | 24.5M | #define NXT(val) ctxt->input->cur[(val)] |
2293 | 866M | #define CUR_PTR ctxt->input->cur |
2294 | 25.9M | #define BASE_PTR ctxt->input->base |
2295 | | |
2296 | | #define CMP4( s, c1, c2, c3, c4 ) \ |
2297 | 41.3M | ( ((unsigned char *) s)[ 0 ] == c1 && ((unsigned char *) s)[ 1 ] == c2 && \ |
2298 | 21.5M | ((unsigned char *) s)[ 2 ] == c3 && ((unsigned char *) s)[ 3 ] == c4 ) |
2299 | | #define CMP5( s, c1, c2, c3, c4, c5 ) \ |
2300 | 38.4M | ( CMP4( s, c1, c2, c3, c4 ) && ((unsigned char *) s)[ 4 ] == c5 ) |
2301 | | #define CMP6( s, c1, c2, c3, c4, c5, c6 ) \ |
2302 | 36.3M | ( CMP5( s, c1, c2, c3, c4, c5 ) && ((unsigned char *) s)[ 5 ] == c6 ) |
2303 | | #define CMP7( s, c1, c2, c3, c4, c5, c6, c7 ) \ |
2304 | 35.0M | ( CMP6( s, c1, c2, c3, c4, c5, c6 ) && ((unsigned char *) s)[ 6 ] == c7 ) |
2305 | | #define CMP8( s, c1, c2, c3, c4, c5, c6, c7, c8 ) \ |
2306 | 34.2M | ( 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 | 17.0M | ( CMP8( s, c1, c2, c3, c4, c5, c6, c7, c8 ) && \ |
2309 | 17.0M | ((unsigned char *) s)[ 8 ] == c9 ) |
2310 | | #define CMP10( s, c1, c2, c3, c4, c5, c6, c7, c8, c9, c10 ) \ |
2311 | 80.8k | ( CMP9( s, c1, c2, c3, c4, c5, c6, c7, c8, c9 ) && \ |
2312 | 80.8k | ((unsigned char *) s)[ 9 ] == c10 ) |
2313 | | |
2314 | 6.74M | #define SKIP(val) do { \ |
2315 | 6.74M | ctxt->input->cur += (val),ctxt->input->col+=(val); \ |
2316 | 6.74M | if (*ctxt->input->cur == 0) \ |
2317 | 6.74M | xmlParserGrow(ctxt); \ |
2318 | 6.74M | } 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 | 22.4M | if (!PARSER_PROGRESSIVE(ctxt)) \ |
2334 | 22.4M | xmlParserShrink(ctxt); |
2335 | | |
2336 | | #define GROW \ |
2337 | 77.4M | if ((!PARSER_PROGRESSIVE(ctxt)) && \ |
2338 | 77.4M | (ctxt->input->end - ctxt->input->cur < INPUT_CHUNK)) \ |
2339 | 36.7M | xmlParserGrow(ctxt); |
2340 | | |
2341 | 21.6M | #define SKIP_BLANKS xmlSkipBlankChars(ctxt) |
2342 | | |
2343 | 2.38M | #define SKIP_BLANKS_PE xmlSkipBlankCharsPE(ctxt) |
2344 | | |
2345 | 33.4M | #define NEXT xmlNextChar(ctxt) |
2346 | | |
2347 | 8.28M | #define NEXT1 { \ |
2348 | 8.28M | ctxt->input->col++; \ |
2349 | 8.28M | ctxt->input->cur++; \ |
2350 | 8.28M | if (*ctxt->input->cur == 0) \ |
2351 | 8.28M | xmlParserGrow(ctxt); \ |
2352 | 8.28M | } |
2353 | | |
2354 | 685M | #define NEXTL(l) do { \ |
2355 | 685M | if (*(ctxt->input->cur) == '\n') { \ |
2356 | 68.7M | ctxt->input->line++; ctxt->input->col = 1; \ |
2357 | 616M | } else ctxt->input->col++; \ |
2358 | 685M | ctxt->input->cur += l; \ |
2359 | 685M | } while (0) |
2360 | | |
2361 | 6.83M | #define CUR_SCHAR(s, l) xmlStringCurrentChar(ctxt, s, &l) |
2362 | | |
2363 | | #define COPY_BUF(b, i, v) \ |
2364 | 220M | if (v < 0x80) b[i++] = v; \ |
2365 | 220M | else i += xmlCopyCharMultiByte(&b[i],v) |
2366 | | |
2367 | | static int |
2368 | 204M | xmlCurrentCharRecover(xmlParserCtxtPtr ctxt, int *len) { |
2369 | 204M | int c = xmlCurrentChar(ctxt, len); |
2370 | | |
2371 | 204M | if (c == XML_INVALID_CHAR) |
2372 | 42.8M | c = 0xFFFD; /* replacement character */ |
2373 | | |
2374 | 204M | return(c); |
2375 | 204M | } |
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 | 23.1M | xmlSkipBlankChars(xmlParserCtxtPtr ctxt) { |
2389 | 23.1M | const xmlChar *cur; |
2390 | 23.1M | int res = 0; |
2391 | | |
2392 | 23.1M | cur = ctxt->input->cur; |
2393 | 23.1M | while (IS_BLANK_CH(*cur)) { |
2394 | 13.0M | if (*cur == '\n') { |
2395 | 2.64M | ctxt->input->line++; ctxt->input->col = 1; |
2396 | 10.4M | } else { |
2397 | 10.4M | ctxt->input->col++; |
2398 | 10.4M | } |
2399 | 13.0M | cur++; |
2400 | 13.0M | if (res < INT_MAX) |
2401 | 13.0M | res++; |
2402 | 13.0M | if (*cur == 0) { |
2403 | 575k | ctxt->input->cur = cur; |
2404 | 575k | xmlParserGrow(ctxt); |
2405 | 575k | cur = ctxt->input->cur; |
2406 | 575k | } |
2407 | 13.0M | } |
2408 | 23.1M | ctxt->input->cur = cur; |
2409 | | |
2410 | 23.1M | if (res > 4) |
2411 | 300k | GROW; |
2412 | | |
2413 | 23.1M | return(res); |
2414 | 23.1M | } |
2415 | | |
2416 | | static void |
2417 | 34.0k | xmlPopPE(xmlParserCtxtPtr ctxt) { |
2418 | 34.0k | unsigned long consumed; |
2419 | 34.0k | xmlEntityPtr ent; |
2420 | | |
2421 | 34.0k | ent = ctxt->input->entity; |
2422 | | |
2423 | 34.0k | ent->flags &= ~XML_ENT_EXPANDING; |
2424 | | |
2425 | 34.0k | if ((ent->flags & XML_ENT_CHECKED) == 0) { |
2426 | 24.3k | 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 | 29.7k | do { |
2433 | 29.7k | ctxt->input->cur = ctxt->input->end; |
2434 | 29.7k | xmlParserShrink(ctxt); |
2435 | 29.7k | result = xmlParserGrow(ctxt); |
2436 | 29.7k | } while (result > 0); |
2437 | | |
2438 | 24.3k | consumed = ctxt->input->consumed; |
2439 | 24.3k | xmlSaturatedAddSizeT(&consumed, |
2440 | 24.3k | ctxt->input->end - ctxt->input->base); |
2441 | | |
2442 | 24.3k | xmlSaturatedAdd(&ent->expandedSize, consumed); |
2443 | | |
2444 | | /* |
2445 | | * Add to sizeentities when parsing an external entity |
2446 | | * for the first time. |
2447 | | */ |
2448 | 24.3k | if (ent->etype == XML_EXTERNAL_PARAMETER_ENTITY) { |
2449 | 21.4k | xmlSaturatedAdd(&ctxt->sizeentities, consumed); |
2450 | 21.4k | } |
2451 | | |
2452 | 24.3k | ent->flags |= XML_ENT_CHECKED; |
2453 | 24.3k | } |
2454 | | |
2455 | 34.0k | xmlFreeInputStream(xmlCtxtPopInput(ctxt)); |
2456 | | |
2457 | 34.0k | xmlParserEntityCheck(ctxt, ent->expandedSize); |
2458 | | |
2459 | 34.0k | GROW; |
2460 | 34.0k | } |
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 | 2.38M | xmlSkipBlankCharsPE(xmlParserCtxtPtr ctxt) { |
2473 | 2.38M | int res = 0; |
2474 | 2.38M | int inParam; |
2475 | 2.38M | int expandParam; |
2476 | | |
2477 | 2.38M | inParam = PARSER_IN_PE(ctxt); |
2478 | 2.38M | expandParam = PARSER_EXTERNAL(ctxt); |
2479 | | |
2480 | 2.38M | if (!inParam && !expandParam) |
2481 | 1.56M | 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 | 2.44M | while (PARSER_STOPPED(ctxt) == 0) { |
2488 | 2.42M | if (IS_BLANK_CH(CUR)) { /* CHECKED tstblanks.xml */ |
2489 | 1.57M | NEXT; |
2490 | 1.57M | } else if (CUR == '%') { |
2491 | 90.8k | if ((expandParam == 0) || |
2492 | 90.8k | (IS_BLANK_CH(NXT(1))) || (NXT(1) == 0)) |
2493 | 55.9k | 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 | 34.9k | xmlParsePEReference(ctxt); |
2502 | | |
2503 | 34.9k | inParam = PARSER_IN_PE(ctxt); |
2504 | 34.9k | expandParam = PARSER_EXTERNAL(ctxt); |
2505 | 762k | } else if (CUR == 0) { |
2506 | 20.5k | if (inParam == 0) |
2507 | 4.45k | break; |
2508 | | |
2509 | 16.1k | xmlPopPE(ctxt); |
2510 | | |
2511 | 16.1k | inParam = PARSER_IN_PE(ctxt); |
2512 | 16.1k | expandParam = PARSER_EXTERNAL(ctxt); |
2513 | 742k | } else { |
2514 | 742k | break; |
2515 | 742k | } |
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 | 1.62M | if (res < INT_MAX) |
2525 | 1.62M | res++; |
2526 | 1.62M | } |
2527 | | |
2528 | 823k | return(res); |
2529 | 2.38M | } |
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 | 159k | xmlParseCharRef(xmlParserCtxtPtr ctxt) { |
2600 | 159k | int val = 0; |
2601 | 159k | int count = 0; |
2602 | | |
2603 | | /* |
2604 | | * Using RAW/CUR/NEXT is okay since we are working on ASCII range here |
2605 | | */ |
2606 | 159k | if ((RAW == '&') && (NXT(1) == '#') && |
2607 | 159k | (NXT(2) == 'x')) { |
2608 | 30.6k | SKIP(3); |
2609 | 30.6k | GROW; |
2610 | 114k | while ((RAW != ';') && (PARSER_STOPPED(ctxt) == 0)) { |
2611 | 92.0k | if (count++ > 20) { |
2612 | 1.98k | count = 0; |
2613 | 1.98k | GROW; |
2614 | 1.98k | } |
2615 | 92.0k | if ((RAW >= '0') && (RAW <= '9')) |
2616 | 45.0k | val = val * 16 + (CUR - '0'); |
2617 | 46.9k | else if ((RAW >= 'a') && (RAW <= 'f') && (count < 20)) |
2618 | 5.99k | val = val * 16 + (CUR - 'a') + 10; |
2619 | 40.9k | else if ((RAW >= 'A') && (RAW <= 'F') && (count < 20)) |
2620 | 32.4k | val = val * 16 + (CUR - 'A') + 10; |
2621 | 8.49k | else { |
2622 | 8.49k | xmlFatalErr(ctxt, XML_ERR_INVALID_HEX_CHARREF, NULL); |
2623 | 8.49k | val = 0; |
2624 | 8.49k | break; |
2625 | 8.49k | } |
2626 | 83.5k | if (val > 0x110000) |
2627 | 20.7k | val = 0x110000; |
2628 | | |
2629 | 83.5k | NEXT; |
2630 | 83.5k | count++; |
2631 | 83.5k | } |
2632 | 30.6k | if (RAW == ';') { |
2633 | | /* on purpose to avoid reentrancy problems with NEXT and SKIP */ |
2634 | 22.1k | ctxt->input->col++; |
2635 | 22.1k | ctxt->input->cur++; |
2636 | 22.1k | } |
2637 | 129k | } else if ((RAW == '&') && (NXT(1) == '#')) { |
2638 | 129k | SKIP(2); |
2639 | 129k | GROW; |
2640 | 367k | while (RAW != ';') { /* loop blocked by count */ |
2641 | 242k | if (count++ > 20) { |
2642 | 1.48k | count = 0; |
2643 | 1.48k | GROW; |
2644 | 1.48k | } |
2645 | 242k | if ((RAW >= '0') && (RAW <= '9')) |
2646 | 238k | val = val * 10 + (CUR - '0'); |
2647 | 4.36k | else { |
2648 | 4.36k | xmlFatalErr(ctxt, XML_ERR_INVALID_DEC_CHARREF, NULL); |
2649 | 4.36k | val = 0; |
2650 | 4.36k | break; |
2651 | 4.36k | } |
2652 | 238k | if (val > 0x110000) |
2653 | 17.5k | val = 0x110000; |
2654 | | |
2655 | 238k | NEXT; |
2656 | 238k | count++; |
2657 | 238k | } |
2658 | 129k | if (RAW == ';') { |
2659 | | /* on purpose to avoid reentrancy problems with NEXT and SKIP */ |
2660 | 124k | ctxt->input->col++; |
2661 | 124k | ctxt->input->cur++; |
2662 | 124k | } |
2663 | 129k | } 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 | 159k | if (val >= 0x110000) { |
2675 | 330 | xmlFatalErrMsgInt(ctxt, XML_ERR_INVALID_CHAR, |
2676 | 330 | "xmlParseCharRef: character reference out of bounds\n", |
2677 | 330 | val); |
2678 | 159k | } else if (IS_CHAR(val)) { |
2679 | 145k | return(val); |
2680 | 145k | } else { |
2681 | 13.7k | xmlFatalErrMsgInt(ctxt, XML_ERR_INVALID_CHAR, |
2682 | 13.7k | "xmlParseCharRef: invalid xmlChar value %d\n", |
2683 | 13.7k | val); |
2684 | 13.7k | } |
2685 | 14.0k | return(0); |
2686 | 159k | } |
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 | 205k | xmlParseStringCharRef(xmlParserCtxtPtr ctxt, const xmlChar **str) { |
2708 | 205k | const xmlChar *ptr; |
2709 | 205k | xmlChar cur; |
2710 | 205k | int val = 0; |
2711 | | |
2712 | 205k | if ((str == NULL) || (*str == NULL)) return(0); |
2713 | 205k | ptr = *str; |
2714 | 205k | cur = *ptr; |
2715 | 205k | if ((cur == '&') && (ptr[1] == '#') && (ptr[2] == 'x')) { |
2716 | 170k | ptr += 3; |
2717 | 170k | cur = *ptr; |
2718 | 806k | while (cur != ';') { /* Non input consuming loop */ |
2719 | 638k | if ((cur >= '0') && (cur <= '9')) |
2720 | 491k | val = val * 16 + (cur - '0'); |
2721 | 146k | else if ((cur >= 'a') && (cur <= 'f')) |
2722 | 7.59k | val = val * 16 + (cur - 'a') + 10; |
2723 | 138k | else if ((cur >= 'A') && (cur <= 'F')) |
2724 | 136k | val = val * 16 + (cur - 'A') + 10; |
2725 | 2.50k | else { |
2726 | 2.50k | xmlFatalErr(ctxt, XML_ERR_INVALID_HEX_CHARREF, NULL); |
2727 | 2.50k | val = 0; |
2728 | 2.50k | break; |
2729 | 2.50k | } |
2730 | 635k | if (val > 0x110000) |
2731 | 432 | val = 0x110000; |
2732 | | |
2733 | 635k | ptr++; |
2734 | 635k | cur = *ptr; |
2735 | 635k | } |
2736 | 170k | if (cur == ';') |
2737 | 168k | ptr++; |
2738 | 170k | } else if ((cur == '&') && (ptr[1] == '#')){ |
2739 | 35.1k | ptr += 2; |
2740 | 35.1k | cur = *ptr; |
2741 | 111k | while (cur != ';') { /* Non input consuming loops */ |
2742 | 78.4k | if ((cur >= '0') && (cur <= '9')) |
2743 | 76.5k | val = val * 10 + (cur - '0'); |
2744 | 1.92k | else { |
2745 | 1.92k | xmlFatalErr(ctxt, XML_ERR_INVALID_DEC_CHARREF, NULL); |
2746 | 1.92k | val = 0; |
2747 | 1.92k | break; |
2748 | 1.92k | } |
2749 | 76.5k | if (val > 0x110000) |
2750 | 4.20k | val = 0x110000; |
2751 | | |
2752 | 76.5k | ptr++; |
2753 | 76.5k | cur = *ptr; |
2754 | 76.5k | } |
2755 | 35.1k | if (cur == ';') |
2756 | 33.2k | ptr++; |
2757 | 35.1k | } else { |
2758 | 0 | xmlFatalErr(ctxt, XML_ERR_INVALID_CHARREF, NULL); |
2759 | 0 | return(0); |
2760 | 0 | } |
2761 | 205k | *str = ptr; |
2762 | | |
2763 | | /* |
2764 | | * [ WFC: Legal Character ] |
2765 | | * Characters referred to using character references must match the |
2766 | | * production for Char. |
2767 | | */ |
2768 | 205k | if (val >= 0x110000) { |
2769 | 244 | xmlFatalErrMsgInt(ctxt, XML_ERR_INVALID_CHAR, |
2770 | 244 | "xmlParseStringCharRef: character reference out of bounds\n", |
2771 | 244 | val); |
2772 | 205k | } else if (IS_CHAR(val)) { |
2773 | 200k | return(val); |
2774 | 200k | } else { |
2775 | 5.49k | xmlFatalErrMsgInt(ctxt, XML_ERR_INVALID_CHAR, |
2776 | 5.49k | "xmlParseStringCharRef: invalid xmlChar value %d\n", |
2777 | 5.49k | val); |
2778 | 5.49k | } |
2779 | 5.73k | return(0); |
2780 | 205k | } |
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 | 1.73M | xmlIsNameStartChar(xmlParserCtxtPtr ctxt, int c) { |
3192 | 1.73M | 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 | 1.73M | if ((c != ' ') && (c != '>') && (c != '/') && /* accelerators */ |
3198 | 1.73M | (((c >= 'a') && (c <= 'z')) || |
3199 | 1.73M | ((c >= 'A') && (c <= 'Z')) || |
3200 | 1.73M | (c == '_') || (c == ':') || |
3201 | 1.73M | ((c >= 0xC0) && (c <= 0xD6)) || |
3202 | 1.73M | ((c >= 0xD8) && (c <= 0xF6)) || |
3203 | 1.73M | ((c >= 0xF8) && (c <= 0x2FF)) || |
3204 | 1.73M | ((c >= 0x370) && (c <= 0x37D)) || |
3205 | 1.73M | ((c >= 0x37F) && (c <= 0x1FFF)) || |
3206 | 1.73M | ((c >= 0x200C) && (c <= 0x200D)) || |
3207 | 1.73M | ((c >= 0x2070) && (c <= 0x218F)) || |
3208 | 1.73M | ((c >= 0x2C00) && (c <= 0x2FEF)) || |
3209 | 1.73M | ((c >= 0x3001) && (c <= 0xD7FF)) || |
3210 | 1.73M | ((c >= 0xF900) && (c <= 0xFDCF)) || |
3211 | 1.73M | ((c >= 0xFDF0) && (c <= 0xFFFD)) || |
3212 | 1.73M | ((c >= 0x10000) && (c <= 0xEFFFF)))) |
3213 | 1.19M | return(1); |
3214 | 1.73M | } else { |
3215 | 0 | if (IS_LETTER(c) || (c == '_') || (c == ':')) |
3216 | 0 | return(1); |
3217 | 0 | } |
3218 | 543k | return(0); |
3219 | 1.73M | } |
3220 | | |
3221 | | static int |
3222 | 41.1M | xmlIsNameChar(xmlParserCtxtPtr ctxt, int c) { |
3223 | 41.1M | 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 | 41.1M | if ((c != ' ') && (c != '>') && (c != '/') && /* accelerators */ |
3229 | 41.1M | (((c >= 'a') && (c <= 'z')) || |
3230 | 41.0M | ((c >= 'A') && (c <= 'Z')) || |
3231 | 41.0M | ((c >= '0') && (c <= '9')) || /* !start */ |
3232 | 41.0M | (c == '_') || (c == ':') || |
3233 | 41.0M | (c == '-') || (c == '.') || (c == 0xB7) || /* !start */ |
3234 | 41.0M | ((c >= 0xC0) && (c <= 0xD6)) || |
3235 | 41.0M | ((c >= 0xD8) && (c <= 0xF6)) || |
3236 | 41.0M | ((c >= 0xF8) && (c <= 0x2FF)) || |
3237 | 41.0M | ((c >= 0x300) && (c <= 0x36F)) || /* !start */ |
3238 | 41.0M | ((c >= 0x370) && (c <= 0x37D)) || |
3239 | 41.0M | ((c >= 0x37F) && (c <= 0x1FFF)) || |
3240 | 41.0M | ((c >= 0x200C) && (c <= 0x200D)) || |
3241 | 41.0M | ((c >= 0x203F) && (c <= 0x2040)) || /* !start */ |
3242 | 41.0M | ((c >= 0x2070) && (c <= 0x218F)) || |
3243 | 41.0M | ((c >= 0x2C00) && (c <= 0x2FEF)) || |
3244 | 41.0M | ((c >= 0x3001) && (c <= 0xD7FF)) || |
3245 | 41.0M | ((c >= 0xF900) && (c <= 0xFDCF)) || |
3246 | 41.0M | ((c >= 0xFDF0) && (c <= 0xFFFD)) || |
3247 | 41.0M | ((c >= 0x10000) && (c <= 0xEFFFF)))) |
3248 | 39.8M | return(1); |
3249 | 41.1M | } 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 | 1.25M | return(0); |
3258 | 41.1M | } |
3259 | | |
3260 | | static const xmlChar * |
3261 | 289k | xmlParseNameComplex(xmlParserCtxtPtr ctxt) { |
3262 | 289k | const xmlChar *ret; |
3263 | 289k | int len = 0, l; |
3264 | 289k | int c; |
3265 | 289k | int maxLength = (ctxt->options & XML_PARSE_HUGE) ? |
3266 | 0 | XML_MAX_TEXT_LENGTH : |
3267 | 289k | XML_MAX_NAME_LENGTH; |
3268 | | |
3269 | | /* |
3270 | | * Handler for more complex cases |
3271 | | */ |
3272 | 289k | c = xmlCurrentChar(ctxt, &l); |
3273 | 289k | 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 | 289k | if ((c == ' ') || (c == '>') || (c == '/') || /* accelerators */ |
3279 | 289k | (!(((c >= 'a') && (c <= 'z')) || |
3280 | 278k | ((c >= 'A') && (c <= 'Z')) || |
3281 | 278k | (c == '_') || (c == ':') || |
3282 | 278k | ((c >= 0xC0) && (c <= 0xD6)) || |
3283 | 278k | ((c >= 0xD8) && (c <= 0xF6)) || |
3284 | 278k | ((c >= 0xF8) && (c <= 0x2FF)) || |
3285 | 278k | ((c >= 0x370) && (c <= 0x37D)) || |
3286 | 278k | ((c >= 0x37F) && (c <= 0x1FFF)) || |
3287 | 278k | ((c >= 0x200C) && (c <= 0x200D)) || |
3288 | 278k | ((c >= 0x2070) && (c <= 0x218F)) || |
3289 | 278k | ((c >= 0x2C00) && (c <= 0x2FEF)) || |
3290 | 278k | ((c >= 0x3001) && (c <= 0xD7FF)) || |
3291 | 278k | ((c >= 0xF900) && (c <= 0xFDCF)) || |
3292 | 278k | ((c >= 0xFDF0) && (c <= 0xFFFD)) || |
3293 | 278k | ((c >= 0x10000) && (c <= 0xEFFFF))))) { |
3294 | 207k | return(NULL); |
3295 | 207k | } |
3296 | 82.0k | len += l; |
3297 | 82.0k | NEXTL(l); |
3298 | 82.0k | c = xmlCurrentChar(ctxt, &l); |
3299 | 88.5M | while ((c != ' ') && (c != '>') && (c != '/') && /* accelerators */ |
3300 | 88.5M | (((c >= 'a') && (c <= 'z')) || |
3301 | 88.5M | ((c >= 'A') && (c <= 'Z')) || |
3302 | 88.5M | ((c >= '0') && (c <= '9')) || /* !start */ |
3303 | 88.5M | (c == '_') || (c == ':') || |
3304 | 88.5M | (c == '-') || (c == '.') || (c == 0xB7) || /* !start */ |
3305 | 88.5M | ((c >= 0xC0) && (c <= 0xD6)) || |
3306 | 88.5M | ((c >= 0xD8) && (c <= 0xF6)) || |
3307 | 88.5M | ((c >= 0xF8) && (c <= 0x2FF)) || |
3308 | 88.5M | ((c >= 0x300) && (c <= 0x36F)) || /* !start */ |
3309 | 88.5M | ((c >= 0x370) && (c <= 0x37D)) || |
3310 | 88.5M | ((c >= 0x37F) && (c <= 0x1FFF)) || |
3311 | 88.5M | ((c >= 0x200C) && (c <= 0x200D)) || |
3312 | 88.5M | ((c >= 0x203F) && (c <= 0x2040)) || /* !start */ |
3313 | 88.5M | ((c >= 0x2070) && (c <= 0x218F)) || |
3314 | 88.5M | ((c >= 0x2C00) && (c <= 0x2FEF)) || |
3315 | 88.5M | ((c >= 0x3001) && (c <= 0xD7FF)) || |
3316 | 88.5M | ((c >= 0xF900) && (c <= 0xFDCF)) || |
3317 | 88.5M | ((c >= 0xFDF0) && (c <= 0xFFFD)) || |
3318 | 88.5M | ((c >= 0x10000) && (c <= 0xEFFFF)) |
3319 | 88.5M | )) { |
3320 | 88.4M | if (len <= INT_MAX - l) |
3321 | 88.4M | len += l; |
3322 | 88.4M | NEXTL(l); |
3323 | 88.4M | c = xmlCurrentChar(ctxt, &l); |
3324 | 88.4M | } |
3325 | 82.0k | } 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 | 82.0k | if (len > maxLength) { |
3348 | 703 | xmlFatalErr(ctxt, XML_ERR_NAME_TOO_LONG, "Name"); |
3349 | 703 | return(NULL); |
3350 | 703 | } |
3351 | 81.3k | 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 | 81.3k | if ((*ctxt->input->cur == '\n') && (ctxt->input->cur[-1] == '\r')) |
3362 | 423 | ret = xmlDictLookup(ctxt->dict, ctxt->input->cur - (len + 1), len); |
3363 | 80.9k | else |
3364 | 80.9k | ret = xmlDictLookup(ctxt->dict, ctxt->input->cur - len, len); |
3365 | 81.3k | if (ret == NULL) |
3366 | 1 | xmlErrMemory(ctxt); |
3367 | 81.3k | return(ret); |
3368 | 81.3k | } |
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 | 1.76M | xmlParseName(xmlParserCtxtPtr ctxt) { |
3390 | 1.76M | const xmlChar *in; |
3391 | 1.76M | const xmlChar *ret; |
3392 | 1.76M | size_t count = 0; |
3393 | 1.76M | size_t maxLength = (ctxt->options & XML_PARSE_HUGE) ? |
3394 | 0 | XML_MAX_TEXT_LENGTH : |
3395 | 1.76M | XML_MAX_NAME_LENGTH; |
3396 | | |
3397 | 1.76M | GROW; |
3398 | | |
3399 | | /* |
3400 | | * Accelerator for simple ASCII names |
3401 | | */ |
3402 | 1.76M | in = ctxt->input->cur; |
3403 | 1.76M | if (((*in >= 0x61) && (*in <= 0x7A)) || |
3404 | 1.76M | ((*in >= 0x41) && (*in <= 0x5A)) || |
3405 | 1.76M | (*in == '_') || (*in == ':')) { |
3406 | 1.55M | in++; |
3407 | 266M | while (((*in >= 0x61) && (*in <= 0x7A)) || |
3408 | 266M | ((*in >= 0x41) && (*in <= 0x5A)) || |
3409 | 266M | ((*in >= 0x30) && (*in <= 0x39)) || |
3410 | 266M | (*in == '_') || (*in == '-') || |
3411 | 266M | (*in == ':') || (*in == '.')) |
3412 | 264M | in++; |
3413 | 1.55M | if ((*in > 0) && (*in < 0x80)) { |
3414 | 1.47M | count = in - ctxt->input->cur; |
3415 | 1.47M | if (count > maxLength) { |
3416 | 1.05k | xmlFatalErr(ctxt, XML_ERR_NAME_TOO_LONG, "Name"); |
3417 | 1.05k | return(NULL); |
3418 | 1.05k | } |
3419 | 1.47M | ret = xmlDictLookup(ctxt->dict, ctxt->input->cur, count); |
3420 | 1.47M | ctxt->input->cur = in; |
3421 | 1.47M | ctxt->input->col += count; |
3422 | 1.47M | if (ret == NULL) |
3423 | 1 | xmlErrMemory(ctxt); |
3424 | 1.47M | return(ret); |
3425 | 1.47M | } |
3426 | 1.55M | } |
3427 | | /* accelerator for special cases */ |
3428 | 289k | return(xmlParseNameComplex(ctxt)); |
3429 | 1.76M | } |
3430 | | |
3431 | | static xmlHashedString |
3432 | 698k | xmlParseNCNameComplex(xmlParserCtxtPtr ctxt) { |
3433 | 698k | xmlHashedString ret; |
3434 | 698k | int len = 0, l; |
3435 | 698k | int c; |
3436 | 698k | int maxLength = (ctxt->options & XML_PARSE_HUGE) ? |
3437 | 0 | XML_MAX_TEXT_LENGTH : |
3438 | 698k | XML_MAX_NAME_LENGTH; |
3439 | 698k | size_t startPosition = 0; |
3440 | | |
3441 | 698k | ret.name = NULL; |
3442 | 698k | ret.hashValue = 0; |
3443 | | |
3444 | | /* |
3445 | | * Handler for more complex cases |
3446 | | */ |
3447 | 698k | startPosition = CUR_PTR - BASE_PTR; |
3448 | 698k | c = xmlCurrentChar(ctxt, &l); |
3449 | 698k | if ((c == ' ') || (c == '>') || (c == '/') || /* accelerators */ |
3450 | 698k | (!xmlIsNameStartChar(ctxt, c) || (c == ':'))) { |
3451 | 589k | return(ret); |
3452 | 589k | } |
3453 | | |
3454 | 19.4M | while ((c != ' ') && (c != '>') && (c != '/') && /* test bigname.xml */ |
3455 | 19.4M | (xmlIsNameChar(ctxt, c) && (c != ':'))) { |
3456 | 19.3M | if (len <= INT_MAX - l) |
3457 | 19.3M | len += l; |
3458 | 19.3M | NEXTL(l); |
3459 | 19.3M | c = xmlCurrentChar(ctxt, &l); |
3460 | 19.3M | } |
3461 | 108k | if (len > maxLength) { |
3462 | 611 | xmlFatalErr(ctxt, XML_ERR_NAME_TOO_LONG, "NCName"); |
3463 | 611 | return(ret); |
3464 | 611 | } |
3465 | 108k | ret = xmlDictLookupHashed(ctxt->dict, (BASE_PTR + startPosition), len); |
3466 | 108k | if (ret.name == NULL) |
3467 | 1 | xmlErrMemory(ctxt); |
3468 | 108k | return(ret); |
3469 | 108k | } |
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 | 14.4M | xmlParseNCName(xmlParserCtxtPtr ctxt) { |
3488 | 14.4M | const xmlChar *in, *e; |
3489 | 14.4M | xmlHashedString ret; |
3490 | 14.4M | size_t count = 0; |
3491 | 14.4M | size_t maxLength = (ctxt->options & XML_PARSE_HUGE) ? |
3492 | 0 | XML_MAX_TEXT_LENGTH : |
3493 | 14.4M | XML_MAX_NAME_LENGTH; |
3494 | | |
3495 | 14.4M | ret.name = NULL; |
3496 | | |
3497 | | /* |
3498 | | * Accelerator for simple ASCII names |
3499 | | */ |
3500 | 14.4M | in = ctxt->input->cur; |
3501 | 14.4M | e = ctxt->input->end; |
3502 | 14.4M | if ((((*in >= 0x61) && (*in <= 0x7A)) || |
3503 | 14.4M | ((*in >= 0x41) && (*in <= 0x5A)) || |
3504 | 14.4M | (*in == '_')) && (in < e)) { |
3505 | 13.8M | in++; |
3506 | 83.6M | while ((((*in >= 0x61) && (*in <= 0x7A)) || |
3507 | 83.6M | ((*in >= 0x41) && (*in <= 0x5A)) || |
3508 | 83.6M | ((*in >= 0x30) && (*in <= 0x39)) || |
3509 | 83.6M | (*in == '_') || (*in == '-') || |
3510 | 83.6M | (*in == '.')) && (in < e)) |
3511 | 69.8M | in++; |
3512 | 13.8M | if (in >= e) |
3513 | 4.34k | goto complex; |
3514 | 13.8M | if ((*in > 0) && (*in < 0x80)) { |
3515 | 13.7M | count = in - ctxt->input->cur; |
3516 | 13.7M | if (count > maxLength) { |
3517 | 283 | xmlFatalErr(ctxt, XML_ERR_NAME_TOO_LONG, "NCName"); |
3518 | 283 | return(ret); |
3519 | 283 | } |
3520 | 13.7M | ret = xmlDictLookupHashed(ctxt->dict, ctxt->input->cur, count); |
3521 | 13.7M | ctxt->input->cur = in; |
3522 | 13.7M | ctxt->input->col += count; |
3523 | 13.7M | if (ret.name == NULL) { |
3524 | 5 | xmlErrMemory(ctxt); |
3525 | 5 | } |
3526 | 13.7M | return(ret); |
3527 | 13.7M | } |
3528 | 13.8M | } |
3529 | 698k | complex: |
3530 | 698k | return(xmlParseNCNameComplex(ctxt)); |
3531 | 14.4M | } |
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 | 356k | xmlParseNameAndCompare(xmlParserCtxtPtr ctxt, xmlChar const *other) { |
3546 | 356k | register const xmlChar *cmp = other; |
3547 | 356k | register const xmlChar *in; |
3548 | 356k | const xmlChar *ret; |
3549 | | |
3550 | 356k | GROW; |
3551 | | |
3552 | 356k | in = ctxt->input->cur; |
3553 | 1.25M | while (*in != 0 && *in == *cmp) { |
3554 | 900k | ++in; |
3555 | 900k | ++cmp; |
3556 | 900k | } |
3557 | 356k | if (*cmp == 0 && (*in == '>' || IS_BLANK_CH (*in))) { |
3558 | | /* success */ |
3559 | 278k | ctxt->input->col += in - ctxt->input->cur; |
3560 | 278k | ctxt->input->cur = in; |
3561 | 278k | return (const xmlChar*) 1; |
3562 | 278k | } |
3563 | | /* failure (or end of input buffer), check with full function */ |
3564 | 78.2k | ret = xmlParseName (ctxt); |
3565 | | /* strings coming from the dictionary direct compare possible */ |
3566 | 78.2k | if (ret == other) { |
3567 | 433 | return (const xmlChar*) 1; |
3568 | 433 | } |
3569 | 77.8k | return ret; |
3570 | 78.2k | } |
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 | 1.06M | xmlParseStringName(xmlParserCtxtPtr ctxt, const xmlChar** str) { |
3592 | 1.06M | xmlChar buf[XML_MAX_NAMELEN + 5]; |
3593 | 1.06M | xmlChar *ret; |
3594 | 1.06M | const xmlChar *cur = *str; |
3595 | 1.06M | int len = 0, l; |
3596 | 1.06M | int c; |
3597 | 1.06M | int maxLength = (ctxt->options & XML_PARSE_HUGE) ? |
3598 | 0 | XML_MAX_TEXT_LENGTH : |
3599 | 1.06M | XML_MAX_NAME_LENGTH; |
3600 | | |
3601 | 1.06M | c = CUR_SCHAR(cur, l); |
3602 | 1.06M | if (!xmlIsNameStartChar(ctxt, c)) { |
3603 | 5.84k | return(NULL); |
3604 | 5.84k | } |
3605 | | |
3606 | 1.05M | COPY_BUF(buf, len, c); |
3607 | 1.05M | cur += l; |
3608 | 1.05M | c = CUR_SCHAR(cur, l); |
3609 | 1.66M | while (xmlIsNameChar(ctxt, c)) { |
3610 | 605k | COPY_BUF(buf, len, c); |
3611 | 605k | cur += l; |
3612 | 605k | c = CUR_SCHAR(cur, l); |
3613 | 605k | 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 | 550 | xmlChar *buffer; |
3619 | 550 | int max = len * 2; |
3620 | | |
3621 | 550 | buffer = xmlMalloc(max); |
3622 | 550 | if (buffer == NULL) { |
3623 | 0 | xmlErrMemory(ctxt); |
3624 | 0 | return(NULL); |
3625 | 0 | } |
3626 | 550 | memcpy(buffer, buf, len); |
3627 | 4.10M | while (xmlIsNameChar(ctxt, c)) { |
3628 | 4.10M | if (len + 10 > max) { |
3629 | 5.04k | xmlChar *tmp; |
3630 | 5.04k | int newSize; |
3631 | | |
3632 | 5.04k | newSize = xmlGrowCapacity(max, 1, 1, maxLength); |
3633 | 5.04k | if (newSize < 0) { |
3634 | 106 | xmlFatalErr(ctxt, XML_ERR_NAME_TOO_LONG, "NCName"); |
3635 | 106 | xmlFree(buffer); |
3636 | 106 | return(NULL); |
3637 | 106 | } |
3638 | 4.93k | tmp = xmlRealloc(buffer, newSize); |
3639 | 4.93k | if (tmp == NULL) { |
3640 | 1 | xmlErrMemory(ctxt); |
3641 | 1 | xmlFree(buffer); |
3642 | 1 | return(NULL); |
3643 | 1 | } |
3644 | 4.93k | buffer = tmp; |
3645 | 4.93k | max = newSize; |
3646 | 4.93k | } |
3647 | 4.10M | COPY_BUF(buffer, len, c); |
3648 | 4.10M | cur += l; |
3649 | 4.10M | c = CUR_SCHAR(cur, l); |
3650 | 4.10M | } |
3651 | 443 | buffer[len] = 0; |
3652 | 443 | *str = cur; |
3653 | 443 | return(buffer); |
3654 | 550 | } |
3655 | 605k | } |
3656 | 1.05M | if (len > maxLength) { |
3657 | 0 | xmlFatalErr(ctxt, XML_ERR_NAME_TOO_LONG, "NCName"); |
3658 | 0 | return(NULL); |
3659 | 0 | } |
3660 | 1.05M | *str = cur; |
3661 | 1.05M | ret = xmlStrndup(buf, len); |
3662 | 1.05M | if (ret == NULL) |
3663 | 11 | xmlErrMemory(ctxt); |
3664 | 1.05M | return(ret); |
3665 | 1.05M | } |
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 | 112k | xmlParseNmtoken(xmlParserCtxtPtr ctxt) { |
3684 | 112k | xmlChar buf[XML_MAX_NAMELEN + 5]; |
3685 | 112k | xmlChar *ret; |
3686 | 112k | int len = 0, l; |
3687 | 112k | int c; |
3688 | 112k | int maxLength = (ctxt->options & XML_PARSE_HUGE) ? |
3689 | 0 | XML_MAX_TEXT_LENGTH : |
3690 | 112k | XML_MAX_NAME_LENGTH; |
3691 | | |
3692 | 112k | c = xmlCurrentChar(ctxt, &l); |
3693 | | |
3694 | 556k | while (xmlIsNameChar(ctxt, c)) { |
3695 | 446k | COPY_BUF(buf, len, c); |
3696 | 446k | NEXTL(l); |
3697 | 446k | c = xmlCurrentChar(ctxt, &l); |
3698 | 446k | 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 | 1.44k | xmlChar *buffer; |
3704 | 1.44k | int max = len * 2; |
3705 | | |
3706 | 1.44k | buffer = xmlMalloc(max); |
3707 | 1.44k | if (buffer == NULL) { |
3708 | 1 | xmlErrMemory(ctxt); |
3709 | 1 | return(NULL); |
3710 | 1 | } |
3711 | 1.44k | memcpy(buffer, buf, len); |
3712 | 15.4M | while (xmlIsNameChar(ctxt, c)) { |
3713 | 15.4M | if (len + 10 > max) { |
3714 | 6.48k | xmlChar *tmp; |
3715 | 6.48k | int newSize; |
3716 | | |
3717 | 6.48k | newSize = xmlGrowCapacity(max, 1, 1, maxLength); |
3718 | 6.48k | if (newSize < 0) { |
3719 | 319 | xmlFatalErr(ctxt, XML_ERR_NAME_TOO_LONG, "NmToken"); |
3720 | 319 | xmlFree(buffer); |
3721 | 319 | return(NULL); |
3722 | 319 | } |
3723 | 6.17k | tmp = xmlRealloc(buffer, newSize); |
3724 | 6.17k | if (tmp == NULL) { |
3725 | 2 | xmlErrMemory(ctxt); |
3726 | 2 | xmlFree(buffer); |
3727 | 2 | return(NULL); |
3728 | 2 | } |
3729 | 6.16k | buffer = tmp; |
3730 | 6.16k | max = newSize; |
3731 | 6.16k | } |
3732 | 15.4M | COPY_BUF(buffer, len, c); |
3733 | 15.4M | NEXTL(l); |
3734 | 15.4M | c = xmlCurrentChar(ctxt, &l); |
3735 | 15.4M | } |
3736 | 1.12k | buffer[len] = 0; |
3737 | 1.12k | return(buffer); |
3738 | 1.44k | } |
3739 | 446k | } |
3740 | 110k | if (len == 0) |
3741 | 45.5k | return(NULL); |
3742 | 65.0k | if (len > maxLength) { |
3743 | 0 | xmlFatalErr(ctxt, XML_ERR_NAME_TOO_LONG, "NmToken"); |
3744 | 0 | return(NULL); |
3745 | 0 | } |
3746 | 65.0k | ret = xmlStrndup(buf, len); |
3747 | 65.0k | if (ret == NULL) |
3748 | 4 | xmlErrMemory(ctxt); |
3749 | 65.0k | return(ret); |
3750 | 65.0k | } |
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 | 120k | const xmlChar *str, int length, int depth) { |
3765 | 120k | int maxDepth = (ctxt->options & XML_PARSE_HUGE) ? 40 : 20; |
3766 | 120k | const xmlChar *end, *chunk; |
3767 | 120k | int c, l; |
3768 | | |
3769 | 120k | if (str == NULL) |
3770 | 4.47k | return; |
3771 | | |
3772 | 115k | depth += 1; |
3773 | 115k | 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 | 115k | end = str + length; |
3780 | 115k | chunk = str; |
3781 | | |
3782 | 40.8M | while ((str < end) && (!PARSER_STOPPED(ctxt))) { |
3783 | 40.7M | c = *str; |
3784 | | |
3785 | 40.7M | if (c >= 0x80) { |
3786 | 29.4M | l = xmlUTF8MultibyteLen(ctxt, str, |
3787 | 29.4M | "invalid character in entity value\n"); |
3788 | 29.4M | if (l == 0) { |
3789 | 11.0M | if (chunk < str) |
3790 | 226k | xmlSBufAddString(buf, chunk, str - chunk); |
3791 | 11.0M | xmlSBufAddReplChar(buf); |
3792 | 11.0M | str += 1; |
3793 | 11.0M | chunk = str; |
3794 | 18.3M | } else { |
3795 | 18.3M | str += l; |
3796 | 18.3M | } |
3797 | 29.4M | } else if (c == '&') { |
3798 | 117k | if (str[1] == '#') { |
3799 | 61.3k | if (chunk < str) |
3800 | 35.1k | xmlSBufAddString(buf, chunk, str - chunk); |
3801 | | |
3802 | 61.3k | c = xmlParseStringCharRef(ctxt, &str); |
3803 | 61.3k | if (c == 0) |
3804 | 4.10k | return; |
3805 | | |
3806 | 57.2k | xmlSBufAddChar(buf, c); |
3807 | | |
3808 | 57.2k | chunk = str; |
3809 | 57.2k | } else { |
3810 | 55.9k | xmlChar *name; |
3811 | | |
3812 | | /* |
3813 | | * General entity references are checked for |
3814 | | * syntactic validity. |
3815 | | */ |
3816 | 55.9k | str++; |
3817 | 55.9k | name = xmlParseStringName(ctxt, &str); |
3818 | | |
3819 | 55.9k | if ((name == NULL) || (*str++ != ';')) { |
3820 | 3.25k | xmlFatalErrMsg(ctxt, XML_ERR_ENTITY_CHAR_ERROR, |
3821 | 3.25k | "EntityValue: '&' forbidden except for entities " |
3822 | 3.25k | "references\n"); |
3823 | 3.25k | xmlFree(name); |
3824 | 3.25k | return; |
3825 | 3.25k | } |
3826 | | |
3827 | 52.7k | xmlFree(name); |
3828 | 52.7k | } |
3829 | 11.2M | } else if (c == '%') { |
3830 | 24.9k | xmlEntityPtr ent; |
3831 | | |
3832 | 24.9k | if (chunk < str) |
3833 | 11.4k | xmlSBufAddString(buf, chunk, str - chunk); |
3834 | | |
3835 | 24.9k | ent = xmlParseStringPEReference(ctxt, &str); |
3836 | 24.9k | if (ent == NULL) |
3837 | 6.45k | return; |
3838 | | |
3839 | 18.4k | if (!PARSER_EXTERNAL(ctxt)) { |
3840 | 313 | xmlFatalErr(ctxt, XML_ERR_ENTITY_PE_INTERNAL, NULL); |
3841 | 313 | return; |
3842 | 313 | } |
3843 | | |
3844 | 18.1k | 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 | 9.36k | if (((ctxt->options & XML_PARSE_NO_XXE) == 0) && |
3852 | 9.36k | ((ctxt->replaceEntities) || |
3853 | 9.36k | (ctxt->validate))) { |
3854 | 9.36k | xmlLoadEntityContent(ctxt, ent); |
3855 | 9.36k | } 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 | 9.36k | } |
3861 | | |
3862 | | /* |
3863 | | * TODO: Skip if ent->content is still NULL. |
3864 | | */ |
3865 | | |
3866 | 18.1k | if (xmlParserEntityCheck(ctxt, ent->length)) |
3867 | 19 | return; |
3868 | | |
3869 | 18.1k | if (ent->flags & XML_ENT_EXPANDING) { |
3870 | 4.60k | xmlFatalErr(ctxt, XML_ERR_ENTITY_LOOP, NULL); |
3871 | 4.60k | xmlHaltParser(ctxt); |
3872 | 4.60k | return; |
3873 | 4.60k | } |
3874 | | |
3875 | 13.5k | ent->flags |= XML_ENT_EXPANDING; |
3876 | 13.5k | xmlExpandPEsInEntityValue(ctxt, buf, ent->content, ent->length, |
3877 | 13.5k | depth); |
3878 | 13.5k | ent->flags &= ~XML_ENT_EXPANDING; |
3879 | | |
3880 | 13.5k | chunk = str; |
3881 | 11.1M | } else { |
3882 | | /* Normal ASCII char */ |
3883 | 11.1M | if (!IS_BYTE_CHAR(c)) { |
3884 | 2.74M | xmlFatalErrMsg(ctxt, XML_ERR_INVALID_CHAR, |
3885 | 2.74M | "invalid character in entity value\n"); |
3886 | 2.74M | if (chunk < str) |
3887 | 46.3k | xmlSBufAddString(buf, chunk, str - chunk); |
3888 | 2.74M | xmlSBufAddReplChar(buf); |
3889 | 2.74M | str += 1; |
3890 | 2.74M | chunk = str; |
3891 | 8.43M | } else { |
3892 | 8.43M | str += 1; |
3893 | 8.43M | } |
3894 | 11.1M | } |
3895 | 40.7M | } |
3896 | | |
3897 | 97.1k | if (chunk < str) |
3898 | 85.6k | xmlSBufAddString(buf, chunk, str - chunk); |
3899 | 97.1k | } |
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 | 109k | xmlParseEntityValue(xmlParserCtxtPtr ctxt, xmlChar **orig) { |
3917 | 109k | unsigned maxLength = (ctxt->options & XML_PARSE_HUGE) ? |
3918 | 0 | XML_MAX_HUGE_LENGTH : |
3919 | 109k | XML_MAX_TEXT_LENGTH; |
3920 | 109k | xmlSBuf buf; |
3921 | 109k | const xmlChar *start; |
3922 | 109k | int quote, length; |
3923 | | |
3924 | 109k | xmlSBufInit(&buf, maxLength); |
3925 | | |
3926 | 109k | GROW; |
3927 | | |
3928 | 109k | quote = CUR; |
3929 | 109k | if ((quote != '"') && (quote != '\'')) { |
3930 | 0 | xmlFatalErr(ctxt, XML_ERR_ATTRIBUTE_NOT_STARTED, NULL); |
3931 | 0 | return(NULL); |
3932 | 0 | } |
3933 | 109k | CUR_PTR++; |
3934 | | |
3935 | 109k | length = 0; |
3936 | | |
3937 | | /* |
3938 | | * Copy raw content of the entity into a buffer |
3939 | | */ |
3940 | 35.9M | while (1) { |
3941 | 35.9M | int c; |
3942 | | |
3943 | 35.9M | if (PARSER_STOPPED(ctxt)) |
3944 | 79 | goto error; |
3945 | | |
3946 | 35.9M | if (CUR_PTR >= ctxt->input->end) { |
3947 | 1.36k | xmlFatalErrMsg(ctxt, XML_ERR_ENTITY_NOT_FINISHED, NULL); |
3948 | 1.36k | goto error; |
3949 | 1.36k | } |
3950 | | |
3951 | 35.9M | c = CUR; |
3952 | | |
3953 | 35.9M | if (c == 0) { |
3954 | 1.30k | xmlFatalErrMsg(ctxt, XML_ERR_INVALID_CHAR, |
3955 | 1.30k | "invalid character in entity value\n"); |
3956 | 1.30k | goto error; |
3957 | 1.30k | } |
3958 | 35.9M | if (c == quote) |
3959 | 106k | break; |
3960 | 35.8M | NEXTL(1); |
3961 | 35.8M | length += 1; |
3962 | | |
3963 | | /* |
3964 | | * TODO: Check growth threshold |
3965 | | */ |
3966 | 35.8M | if (ctxt->input->end - CUR_PTR < 10) |
3967 | 23.0k | GROW; |
3968 | 35.8M | } |
3969 | | |
3970 | 106k | start = CUR_PTR - length; |
3971 | | |
3972 | 106k | if (orig != NULL) { |
3973 | 106k | *orig = xmlStrndup(start, length); |
3974 | 106k | if (*orig == NULL) |
3975 | 3 | xmlErrMemory(ctxt); |
3976 | 106k | } |
3977 | | |
3978 | 106k | xmlExpandPEsInEntityValue(ctxt, &buf, start, length, ctxt->inputNr); |
3979 | | |
3980 | 106k | NEXTL(1); |
3981 | | |
3982 | 106k | return(xmlSBufFinish(&buf, NULL, ctxt, "entity length too long")); |
3983 | | |
3984 | 2.74k | error: |
3985 | 2.74k | xmlSBufCleanup(&buf, ctxt, "entity length too long"); |
3986 | 2.74k | return(NULL); |
3987 | 109k | } |
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 | 0 | xmlCheckEntityInAttValue(xmlParserCtxtPtr ctxt, xmlEntityPtr pent, int depth) { |
4000 | 0 | int maxDepth = (ctxt->options & XML_PARSE_HUGE) ? 40 : 20; |
4001 | 0 | const xmlChar *str; |
4002 | 0 | unsigned long expandedSize = pent->length; |
4003 | 0 | int c, flags; |
4004 | |
|
4005 | 0 | depth += 1; |
4006 | 0 | 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 | 0 | 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 | 0 | if (ctxt->inSubset == 0) |
4024 | 0 | flags = XML_ENT_CHECKED | XML_ENT_VALIDATED; |
4025 | 0 | else |
4026 | 0 | flags = XML_ENT_VALIDATED; |
4027 | |
|
4028 | 0 | str = pent->content; |
4029 | 0 | 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 | 0 | while (!PARSER_STOPPED(ctxt)) { |
4039 | 0 | c = *str; |
4040 | |
|
4041 | 0 | if (c != '&') { |
4042 | 0 | if (c == 0) |
4043 | 0 | break; |
4044 | | |
4045 | 0 | if (c == '<') |
4046 | 0 | xmlFatalErrMsgStr(ctxt, XML_ERR_LT_IN_ATTRIBUTE, |
4047 | 0 | "'<' in entity '%s' is not allowed in attributes " |
4048 | 0 | "values\n", pent->name); |
4049 | |
|
4050 | 0 | str += 1; |
4051 | 0 | } else if (str[1] == '#') { |
4052 | 0 | int val; |
4053 | |
|
4054 | 0 | val = xmlParseStringCharRef(ctxt, &str); |
4055 | 0 | if (val == 0) { |
4056 | 0 | pent->content[0] = 0; |
4057 | 0 | break; |
4058 | 0 | } |
4059 | 0 | } else { |
4060 | 0 | xmlChar *name; |
4061 | 0 | xmlEntityPtr ent; |
4062 | |
|
4063 | 0 | name = xmlParseStringEntityRef(ctxt, &str); |
4064 | 0 | if (name == NULL) { |
4065 | 0 | pent->content[0] = 0; |
4066 | 0 | break; |
4067 | 0 | } |
4068 | | |
4069 | 0 | ent = xmlLookupGeneralEntity(ctxt, name, /* inAttr */ 1); |
4070 | 0 | xmlFree(name); |
4071 | |
|
4072 | 0 | if ((ent != NULL) && |
4073 | 0 | (ent->etype != XML_INTERNAL_PREDEFINED_ENTITY)) { |
4074 | 0 | if ((ent->flags & flags) != flags) { |
4075 | 0 | pent->flags |= XML_ENT_EXPANDING; |
4076 | 0 | xmlCheckEntityInAttValue(ctxt, ent, depth); |
4077 | 0 | pent->flags &= ~XML_ENT_EXPANDING; |
4078 | 0 | } |
4079 | |
|
4080 | 0 | xmlSaturatedAdd(&expandedSize, ent->expandedSize); |
4081 | 0 | xmlSaturatedAdd(&expandedSize, XML_ENT_FIXED_COST); |
4082 | 0 | } |
4083 | 0 | } |
4084 | 0 | } |
4085 | |
|
4086 | 0 | done: |
4087 | 0 | if (ctxt->inSubset == 0) |
4088 | 0 | pent->expandedSize = expandedSize; |
4089 | |
|
4090 | 0 | pent->flags |= flags; |
4091 | 0 | } |
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 | 905k | int *inSpace, int depth, int check) { |
4111 | 905k | int maxDepth = (ctxt->options & XML_PARSE_HUGE) ? 40 : 20; |
4112 | 905k | int c, chunkSize; |
4113 | | |
4114 | 905k | if (str == NULL) |
4115 | 0 | return; |
4116 | | |
4117 | 905k | depth += 1; |
4118 | 905k | 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 | 905k | if (pent != NULL) { |
4125 | 905k | if (pent->flags & XML_ENT_EXPANDING) { |
4126 | 321 | xmlFatalErr(ctxt, XML_ERR_ENTITY_LOOP, NULL); |
4127 | 321 | xmlHaltParser(ctxt); |
4128 | 321 | return; |
4129 | 321 | } |
4130 | | |
4131 | 904k | if (check) { |
4132 | 904k | if (xmlParserEntityCheck(ctxt, pent->length)) |
4133 | 929 | return; |
4134 | 904k | } |
4135 | 904k | } |
4136 | | |
4137 | 903k | chunkSize = 0; |
4138 | | |
4139 | | /* |
4140 | | * Note that entity values are already validated. No special |
4141 | | * handling for multi-byte characters is needed. |
4142 | | */ |
4143 | 422M | while (!PARSER_STOPPED(ctxt)) { |
4144 | 422M | c = *str; |
4145 | | |
4146 | 422M | if (c != '&') { |
4147 | 421M | if (c == 0) |
4148 | 873k | 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 | 420M | if ((pent != NULL) && (c == '<')) { |
4156 | 26.2k | xmlFatalErrMsgStr(ctxt, XML_ERR_LT_IN_ATTRIBUTE, |
4157 | 26.2k | "'<' in entity '%s' is not allowed in attributes " |
4158 | 26.2k | "values\n", pent->name); |
4159 | 26.2k | break; |
4160 | 26.2k | } |
4161 | | |
4162 | 420M | if (c <= 0x20) { |
4163 | 3.22M | if ((normalize) && (*inSpace)) { |
4164 | | /* Skip char */ |
4165 | 334k | if (chunkSize > 0) { |
4166 | 72.6k | xmlSBufAddString(buf, str - chunkSize, chunkSize); |
4167 | 72.6k | chunkSize = 0; |
4168 | 72.6k | } |
4169 | 2.88M | } else if (c < 0x20) { |
4170 | 2.46M | if (chunkSize > 0) { |
4171 | 322k | xmlSBufAddString(buf, str - chunkSize, chunkSize); |
4172 | 322k | chunkSize = 0; |
4173 | 322k | } |
4174 | | |
4175 | 2.46M | xmlSBufAddCString(buf, " ", 1); |
4176 | 2.46M | } else { |
4177 | 426k | chunkSize += 1; |
4178 | 426k | } |
4179 | | |
4180 | 3.22M | *inSpace = 1; |
4181 | 417M | } else { |
4182 | 417M | chunkSize += 1; |
4183 | 417M | *inSpace = 0; |
4184 | 417M | } |
4185 | | |
4186 | 420M | str += 1; |
4187 | 420M | } else if (str[1] == '#') { |
4188 | 144k | int val; |
4189 | | |
4190 | 144k | if (chunkSize > 0) { |
4191 | 140k | xmlSBufAddString(buf, str - chunkSize, chunkSize); |
4192 | 140k | chunkSize = 0; |
4193 | 140k | } |
4194 | | |
4195 | 144k | val = xmlParseStringCharRef(ctxt, &str); |
4196 | 144k | if (val == 0) { |
4197 | 1.63k | if (pent != NULL) |
4198 | 1.63k | pent->content[0] = 0; |
4199 | 1.63k | break; |
4200 | 1.63k | } |
4201 | | |
4202 | 142k | if (val == ' ') { |
4203 | 5.13k | if ((!normalize) || (!*inSpace)) |
4204 | 5.13k | xmlSBufAddCString(buf, " ", 1); |
4205 | 5.13k | *inSpace = 1; |
4206 | 137k | } else { |
4207 | 137k | xmlSBufAddChar(buf, val); |
4208 | 137k | *inSpace = 0; |
4209 | 137k | } |
4210 | 984k | } else { |
4211 | 984k | xmlChar *name; |
4212 | 984k | xmlEntityPtr ent; |
4213 | | |
4214 | 984k | if (chunkSize > 0) { |
4215 | 631k | xmlSBufAddString(buf, str - chunkSize, chunkSize); |
4216 | 631k | chunkSize = 0; |
4217 | 631k | } |
4218 | | |
4219 | 984k | name = xmlParseStringEntityRef(ctxt, &str); |
4220 | 984k | if (name == NULL) { |
4221 | 863 | if (pent != NULL) |
4222 | 863 | pent->content[0] = 0; |
4223 | 863 | break; |
4224 | 863 | } |
4225 | | |
4226 | 983k | ent = xmlLookupGeneralEntity(ctxt, name, /* inAttr */ 1); |
4227 | 983k | xmlFree(name); |
4228 | | |
4229 | 983k | if ((ent != NULL) && |
4230 | 983k | (ent->etype == XML_INTERNAL_PREDEFINED_ENTITY)) { |
4231 | 83.2k | 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 | 83.2k | xmlSBufAddString(buf, ent->content, ent->length); |
4238 | | |
4239 | 83.2k | *inSpace = 0; |
4240 | 900k | } else if ((ent != NULL) && (ent->content != NULL)) { |
4241 | 702k | if (pent != NULL) |
4242 | 702k | pent->flags |= XML_ENT_EXPANDING; |
4243 | 702k | xmlExpandEntityInAttValue(ctxt, buf, ent->content, ent, |
4244 | 702k | normalize, inSpace, depth, check); |
4245 | 702k | if (pent != NULL) |
4246 | 702k | pent->flags &= ~XML_ENT_EXPANDING; |
4247 | 702k | } |
4248 | 983k | } |
4249 | 422M | } |
4250 | | |
4251 | 903k | if (chunkSize > 0) |
4252 | 388k | xmlSBufAddString(buf, str - chunkSize, chunkSize); |
4253 | 903k | } |
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 | 4.80M | int normalize, int isNamespace) { |
4322 | 4.80M | unsigned maxLength = (ctxt->options & XML_PARSE_HUGE) ? |
4323 | 0 | XML_MAX_HUGE_LENGTH : |
4324 | 4.80M | XML_MAX_TEXT_LENGTH; |
4325 | 4.80M | xmlSBuf buf; |
4326 | 4.80M | xmlChar *ret; |
4327 | 4.80M | int c, l, quote, flags, chunkSize; |
4328 | 4.80M | int inSpace = 1; |
4329 | 4.80M | int replaceEntities; |
4330 | | |
4331 | | /* Always expand namespace URIs */ |
4332 | 4.80M | replaceEntities = (ctxt->replaceEntities) || (isNamespace); |
4333 | | |
4334 | 4.80M | xmlSBufInit(&buf, maxLength); |
4335 | | |
4336 | 4.80M | GROW; |
4337 | | |
4338 | 4.80M | quote = CUR; |
4339 | 4.80M | if ((quote != '"') && (quote != '\'')) { |
4340 | 15.9k | xmlFatalErr(ctxt, XML_ERR_ATTRIBUTE_NOT_STARTED, NULL); |
4341 | 15.9k | return(NULL); |
4342 | 15.9k | } |
4343 | 4.79M | NEXTL(1); |
4344 | | |
4345 | 4.79M | if (ctxt->inSubset == 0) |
4346 | 4.73M | flags = XML_ENT_CHECKED | XML_ENT_VALIDATED; |
4347 | 60.4k | else |
4348 | 60.4k | flags = XML_ENT_VALIDATED; |
4349 | | |
4350 | 4.79M | inSpace = 1; |
4351 | 4.79M | chunkSize = 0; |
4352 | | |
4353 | 317M | while (1) { |
4354 | 317M | if (PARSER_STOPPED(ctxt)) |
4355 | 1.31k | goto error; |
4356 | | |
4357 | 317M | if (CUR_PTR >= ctxt->input->end) { |
4358 | 9.99k | xmlFatalErrMsg(ctxt, XML_ERR_ATTRIBUTE_NOT_FINISHED, |
4359 | 9.99k | "AttValue: ' expected\n"); |
4360 | 9.99k | goto error; |
4361 | 9.99k | } |
4362 | | |
4363 | | /* |
4364 | | * TODO: Check growth threshold |
4365 | | */ |
4366 | 317M | if (ctxt->input->end - CUR_PTR < 10) |
4367 | 166k | GROW; |
4368 | | |
4369 | 317M | c = CUR; |
4370 | | |
4371 | 317M | if (c >= 0x80) { |
4372 | 141M | l = xmlUTF8MultibyteLen(ctxt, CUR_PTR, |
4373 | 141M | "invalid character in attribute value\n"); |
4374 | 141M | if (l == 0) { |
4375 | 24.5M | if (chunkSize > 0) { |
4376 | 265k | xmlSBufAddString(&buf, CUR_PTR - chunkSize, chunkSize); |
4377 | 265k | chunkSize = 0; |
4378 | 265k | } |
4379 | 24.5M | xmlSBufAddReplChar(&buf); |
4380 | 24.5M | NEXTL(1); |
4381 | 117M | } else { |
4382 | 117M | chunkSize += l; |
4383 | 117M | NEXTL(l); |
4384 | 117M | } |
4385 | | |
4386 | 141M | inSpace = 0; |
4387 | 175M | } else if (c != '&') { |
4388 | 175M | if (c > 0x20) { |
4389 | 119M | if (c == quote) |
4390 | 4.77M | break; |
4391 | | |
4392 | 114M | if (c == '<') |
4393 | 1.18M | xmlFatalErr(ctxt, XML_ERR_LT_IN_ATTRIBUTE, NULL); |
4394 | | |
4395 | 114M | chunkSize += 1; |
4396 | 114M | inSpace = 0; |
4397 | 114M | } else if (!IS_BYTE_CHAR(c)) { |
4398 | 43.9M | xmlFatalErrMsg(ctxt, XML_ERR_INVALID_CHAR, |
4399 | 43.9M | "invalid character in attribute value\n"); |
4400 | 43.9M | if (chunkSize > 0) { |
4401 | 107k | xmlSBufAddString(&buf, CUR_PTR - chunkSize, chunkSize); |
4402 | 107k | chunkSize = 0; |
4403 | 107k | } |
4404 | 43.9M | xmlSBufAddReplChar(&buf); |
4405 | 43.9M | inSpace = 0; |
4406 | 43.9M | } else { |
4407 | | /* Whitespace */ |
4408 | 11.7M | if ((normalize) && (inSpace)) { |
4409 | | /* Skip char */ |
4410 | 191k | if (chunkSize > 0) { |
4411 | 43.2k | xmlSBufAddString(&buf, CUR_PTR - chunkSize, chunkSize); |
4412 | 43.2k | chunkSize = 0; |
4413 | 43.2k | } |
4414 | 11.5M | } else if (c < 0x20) { |
4415 | | /* Convert to space */ |
4416 | 9.77M | if (chunkSize > 0) { |
4417 | 622k | xmlSBufAddString(&buf, CUR_PTR - chunkSize, chunkSize); |
4418 | 622k | chunkSize = 0; |
4419 | 622k | } |
4420 | | |
4421 | 9.77M | xmlSBufAddCString(&buf, " ", 1); |
4422 | 9.77M | } else { |
4423 | 1.73M | chunkSize += 1; |
4424 | 1.73M | } |
4425 | | |
4426 | 11.7M | inSpace = 1; |
4427 | | |
4428 | 11.7M | if ((c == 0xD) && (NXT(1) == 0xA)) |
4429 | 24.5k | CUR_PTR++; |
4430 | 11.7M | } |
4431 | | |
4432 | 170M | NEXTL(1); |
4433 | 170M | } else if (NXT(1) == '#') { |
4434 | 134k | int val; |
4435 | | |
4436 | 134k | if (chunkSize > 0) { |
4437 | 69.3k | xmlSBufAddString(&buf, CUR_PTR - chunkSize, chunkSize); |
4438 | 69.3k | chunkSize = 0; |
4439 | 69.3k | } |
4440 | | |
4441 | 134k | val = xmlParseCharRef(ctxt); |
4442 | 134k | if (val == 0) |
4443 | 2.32k | goto error; |
4444 | | |
4445 | 131k | if ((val == '&') && (!replaceEntities)) { |
4446 | | /* |
4447 | | * The reparsing will be done in xmlNodeParseContent() |
4448 | | * called from SAX2.c |
4449 | | */ |
4450 | 0 | xmlSBufAddCString(&buf, "&", 5); |
4451 | 0 | inSpace = 0; |
4452 | 131k | } else if (val == ' ') { |
4453 | 13.4k | if ((!normalize) || (!inSpace)) |
4454 | 12.6k | xmlSBufAddCString(&buf, " ", 1); |
4455 | 13.4k | inSpace = 1; |
4456 | 118k | } else { |
4457 | 118k | xmlSBufAddChar(&buf, val); |
4458 | 118k | inSpace = 0; |
4459 | 118k | } |
4460 | 535k | } else { |
4461 | 535k | const xmlChar *name; |
4462 | 535k | xmlEntityPtr ent; |
4463 | | |
4464 | 535k | if (chunkSize > 0) { |
4465 | 339k | xmlSBufAddString(&buf, CUR_PTR - chunkSize, chunkSize); |
4466 | 339k | chunkSize = 0; |
4467 | 339k | } |
4468 | | |
4469 | 535k | name = xmlParseEntityRefInternal(ctxt); |
4470 | 535k | if (name == NULL) { |
4471 | | /* |
4472 | | * Probably a literal '&' which wasn't escaped. |
4473 | | * TODO: Handle gracefully in recovery mode. |
4474 | | */ |
4475 | 190k | continue; |
4476 | 190k | } |
4477 | | |
4478 | 344k | ent = xmlLookupGeneralEntity(ctxt, name, /* isAttr */ 1); |
4479 | 344k | if (ent == NULL) |
4480 | 116k | continue; |
4481 | | |
4482 | 227k | if (ent->etype == XML_INTERNAL_PREDEFINED_ENTITY) { |
4483 | 25.3k | if ((ent->content[0] == '&') && (!replaceEntities)) |
4484 | 0 | xmlSBufAddCString(&buf, "&", 5); |
4485 | 25.3k | else |
4486 | 25.3k | xmlSBufAddString(&buf, ent->content, ent->length); |
4487 | 25.3k | inSpace = 0; |
4488 | 202k | } else if (replaceEntities) { |
4489 | 202k | xmlExpandEntityInAttValue(ctxt, &buf, ent->content, ent, |
4490 | 202k | normalize, &inSpace, ctxt->inputNr, |
4491 | 202k | /* check */ 1); |
4492 | 202k | } else { |
4493 | 0 | if ((ent->flags & flags) != flags) |
4494 | 0 | xmlCheckEntityInAttValue(ctxt, ent, ctxt->inputNr); |
4495 | |
|
4496 | 0 | if (xmlParserEntityCheck(ctxt, ent->expandedSize)) { |
4497 | 0 | ent->content[0] = 0; |
4498 | 0 | goto error; |
4499 | 0 | } |
4500 | | |
4501 | | /* |
4502 | | * Just output the reference |
4503 | | */ |
4504 | 0 | xmlSBufAddCString(&buf, "&", 1); |
4505 | 0 | xmlSBufAddString(&buf, ent->name, xmlStrlen(ent->name)); |
4506 | 0 | xmlSBufAddCString(&buf, ";", 1); |
4507 | |
|
4508 | 0 | inSpace = 0; |
4509 | 0 | } |
4510 | 227k | } |
4511 | 317M | } |
4512 | | |
4513 | 4.77M | if ((buf.mem == NULL) && (alloc != NULL)) { |
4514 | 4.50M | ret = (xmlChar *) CUR_PTR - chunkSize; |
4515 | | |
4516 | 4.50M | if (attlen != NULL) |
4517 | 4.50M | *attlen = chunkSize; |
4518 | 4.50M | if ((normalize) && (inSpace) && (chunkSize > 0)) |
4519 | 273 | *attlen -= 1; |
4520 | 4.50M | *alloc = 0; |
4521 | | |
4522 | | /* Report potential error */ |
4523 | 4.50M | xmlSBufCleanup(&buf, ctxt, "AttValue length too long"); |
4524 | 4.50M | } else { |
4525 | 271k | if (chunkSize > 0) |
4526 | 160k | xmlSBufAddString(&buf, CUR_PTR - chunkSize, chunkSize); |
4527 | | |
4528 | 271k | if ((normalize) && (inSpace) && (buf.size > 0)) |
4529 | 783 | buf.size--; |
4530 | | |
4531 | 271k | ret = xmlSBufFinish(&buf, attlen, ctxt, "AttValue length too long"); |
4532 | | |
4533 | 271k | if (ret != NULL) { |
4534 | 271k | if (attlen != NULL) |
4535 | 211k | *attlen = buf.size; |
4536 | 271k | if (alloc != NULL) |
4537 | 211k | *alloc = 1; |
4538 | 271k | } |
4539 | 271k | } |
4540 | | |
4541 | 4.77M | NEXTL(1); |
4542 | | |
4543 | 4.77M | return(ret); |
4544 | | |
4545 | 13.6k | error: |
4546 | 13.6k | xmlSBufCleanup(&buf, ctxt, "AttValue length too long"); |
4547 | 13.6k | return(NULL); |
4548 | 4.79M | } |
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 | 69.0k | xmlParseAttValue(xmlParserCtxtPtr ctxt) { |
4588 | 69.0k | if ((ctxt == NULL) || (ctxt->input == NULL)) return(NULL); |
4589 | 69.0k | return(xmlParseAttValueInternal(ctxt, NULL, NULL, 0, 0)); |
4590 | 69.0k | } |
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 | 108k | xmlParseSystemLiteral(xmlParserCtxtPtr ctxt) { |
4607 | 108k | xmlChar *buf = NULL; |
4608 | 108k | int len = 0; |
4609 | 108k | int size = XML_PARSER_BUFFER_SIZE; |
4610 | 108k | int cur, l; |
4611 | 108k | int maxLength = (ctxt->options & XML_PARSE_HUGE) ? |
4612 | 0 | XML_MAX_TEXT_LENGTH : |
4613 | 108k | XML_MAX_NAME_LENGTH; |
4614 | 108k | xmlChar stop; |
4615 | | |
4616 | 108k | if (RAW == '"') { |
4617 | 90.1k | NEXT; |
4618 | 90.1k | stop = '"'; |
4619 | 90.1k | } else if (RAW == '\'') { |
4620 | 15.7k | NEXT; |
4621 | 15.7k | stop = '\''; |
4622 | 15.7k | } else { |
4623 | 2.74k | xmlFatalErr(ctxt, XML_ERR_LITERAL_NOT_STARTED, NULL); |
4624 | 2.74k | return(NULL); |
4625 | 2.74k | } |
4626 | | |
4627 | 105k | buf = xmlMalloc(size); |
4628 | 105k | if (buf == NULL) { |
4629 | 16 | xmlErrMemory(ctxt); |
4630 | 16 | return(NULL); |
4631 | 16 | } |
4632 | 105k | cur = xmlCurrentCharRecover(ctxt, &l); |
4633 | 10.8M | while ((IS_CHAR(cur)) && (cur != stop)) { /* checked */ |
4634 | 10.7M | if (len + 5 >= size) { |
4635 | 14.5k | xmlChar *tmp; |
4636 | 14.5k | int newSize; |
4637 | | |
4638 | 14.5k | newSize = xmlGrowCapacity(size, 1, 1, maxLength); |
4639 | 14.5k | if (newSize < 0) { |
4640 | 239 | xmlFatalErr(ctxt, XML_ERR_NAME_TOO_LONG, "SystemLiteral"); |
4641 | 239 | xmlFree(buf); |
4642 | 239 | return(NULL); |
4643 | 239 | } |
4644 | 14.3k | tmp = xmlRealloc(buf, newSize); |
4645 | 14.3k | if (tmp == NULL) { |
4646 | 5 | xmlFree(buf); |
4647 | 5 | xmlErrMemory(ctxt); |
4648 | 5 | return(NULL); |
4649 | 5 | } |
4650 | 14.2k | buf = tmp; |
4651 | 14.2k | size = newSize; |
4652 | 14.2k | } |
4653 | 10.7M | COPY_BUF(buf, len, cur); |
4654 | 10.7M | NEXTL(l); |
4655 | 10.7M | cur = xmlCurrentCharRecover(ctxt, &l); |
4656 | 10.7M | } |
4657 | 105k | buf[len] = 0; |
4658 | 105k | if (!IS_CHAR(cur)) { |
4659 | 1.50k | xmlFatalErr(ctxt, XML_ERR_LITERAL_NOT_FINISHED, NULL); |
4660 | 104k | } else { |
4661 | 104k | NEXT; |
4662 | 104k | } |
4663 | 105k | return(buf); |
4664 | 105k | } |
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 | 29.2k | xmlParsePubidLiteral(xmlParserCtxtPtr ctxt) { |
4681 | 29.2k | xmlChar *buf = NULL; |
4682 | 29.2k | int len = 0; |
4683 | 29.2k | int size = XML_PARSER_BUFFER_SIZE; |
4684 | 29.2k | int maxLength = (ctxt->options & XML_PARSE_HUGE) ? |
4685 | 0 | XML_MAX_TEXT_LENGTH : |
4686 | 29.2k | XML_MAX_NAME_LENGTH; |
4687 | 29.2k | xmlChar cur; |
4688 | 29.2k | xmlChar stop; |
4689 | | |
4690 | 29.2k | if (RAW == '"') { |
4691 | 10.3k | NEXT; |
4692 | 10.3k | stop = '"'; |
4693 | 18.9k | } else if (RAW == '\'') { |
4694 | 16.3k | NEXT; |
4695 | 16.3k | stop = '\''; |
4696 | 16.3k | } else { |
4697 | 2.60k | xmlFatalErr(ctxt, XML_ERR_LITERAL_NOT_STARTED, NULL); |
4698 | 2.60k | return(NULL); |
4699 | 2.60k | } |
4700 | 26.6k | buf = xmlMalloc(size); |
4701 | 26.6k | if (buf == NULL) { |
4702 | 3 | xmlErrMemory(ctxt); |
4703 | 3 | return(NULL); |
4704 | 3 | } |
4705 | 26.6k | cur = CUR; |
4706 | 97.1k | while ((IS_PUBIDCHAR_CH(cur)) && (cur != stop) && |
4707 | 97.1k | (PARSER_STOPPED(ctxt) == 0)) { /* checked */ |
4708 | 70.4k | if (len + 1 >= size) { |
4709 | 251 | xmlChar *tmp; |
4710 | 251 | int newSize; |
4711 | | |
4712 | 251 | newSize = xmlGrowCapacity(size, 1, 1, maxLength); |
4713 | 251 | 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 | 251 | tmp = xmlRealloc(buf, newSize); |
4719 | 251 | if (tmp == NULL) { |
4720 | 1 | xmlErrMemory(ctxt); |
4721 | 1 | xmlFree(buf); |
4722 | 1 | return(NULL); |
4723 | 1 | } |
4724 | 250 | buf = tmp; |
4725 | 250 | size = newSize; |
4726 | 250 | } |
4727 | 70.4k | buf[len++] = cur; |
4728 | 70.4k | NEXT; |
4729 | 70.4k | cur = CUR; |
4730 | 70.4k | } |
4731 | 26.6k | buf[len] = 0; |
4732 | 26.6k | if (cur != stop) { |
4733 | 1.51k | xmlFatalErr(ctxt, XML_ERR_LITERAL_NOT_FINISHED, NULL); |
4734 | 25.1k | } else { |
4735 | 25.1k | NEXTL(1); |
4736 | 25.1k | } |
4737 | 26.6k | return(buf); |
4738 | 26.6k | } |
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 | 6.39M | int isBlank) { |
4783 | 6.39M | int checkBlanks; |
4784 | | |
4785 | 6.39M | if ((ctxt->sax == NULL) || (ctxt->disableSAX)) |
4786 | 1.89M | return; |
4787 | | |
4788 | 4.49M | checkBlanks = (!ctxt->keepBlanks) || |
4789 | 4.49M | (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 | 4.49M | if ((checkBlanks) && |
4797 | 4.49M | (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 | 4.49M | } else { |
4802 | 4.49M | if (ctxt->sax->characters != NULL) |
4803 | 4.49M | 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 | 4.49M | if ((checkBlanks) && (*ctxt->space == -1)) |
4810 | 0 | *ctxt->space = -2; |
4811 | 4.49M | } |
4812 | 4.49M | } |
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 ">", |
4823 | | * and must, for compatibility, be escaped using ">" 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 | 9.67M | xmlParseCharDataInternal(xmlParserCtxtPtr ctxt, int partial) { |
4831 | 9.67M | const xmlChar *in; |
4832 | 9.67M | int nbchar = 0; |
4833 | 9.67M | int line = ctxt->input->line; |
4834 | 9.67M | int col = ctxt->input->col; |
4835 | 9.67M | int ccol; |
4836 | | |
4837 | 9.67M | GROW; |
4838 | | /* |
4839 | | * Accelerated common case where input don't need to be |
4840 | | * modified before passing it to the handler. |
4841 | | */ |
4842 | 9.67M | in = ctxt->input->cur; |
4843 | 9.81M | do { |
4844 | 11.9M | get_more_space: |
4845 | 17.1M | while (*in == 0x20) { in++; ctxt->input->col++; } |
4846 | 11.9M | if (*in == 0xA) { |
4847 | 19.0M | do { |
4848 | 19.0M | ctxt->input->line++; ctxt->input->col = 1; |
4849 | 19.0M | in++; |
4850 | 19.0M | } while (*in == 0xA); |
4851 | 2.08M | goto get_more_space; |
4852 | 2.08M | } |
4853 | 9.81M | if (*in == '<') { |
4854 | 2.82M | nbchar = in - ctxt->input->cur; |
4855 | 2.82M | if (nbchar > 0) { |
4856 | 2.82M | const xmlChar *tmp = ctxt->input->cur; |
4857 | 2.82M | ctxt->input->cur = in; |
4858 | | |
4859 | 2.82M | xmlCharacters(ctxt, tmp, nbchar, 1); |
4860 | 2.82M | } |
4861 | 2.82M | return; |
4862 | 2.82M | } |
4863 | | |
4864 | 7.60M | get_more: |
4865 | 7.60M | ccol = ctxt->input->col; |
4866 | 289M | while (test_char_data[*in]) { |
4867 | 282M | in++; |
4868 | 282M | ccol++; |
4869 | 282M | } |
4870 | 7.60M | ctxt->input->col = ccol; |
4871 | 7.60M | if (*in == 0xA) { |
4872 | 6.75M | do { |
4873 | 6.75M | ctxt->input->line++; ctxt->input->col = 1; |
4874 | 6.75M | in++; |
4875 | 6.75M | } while (*in == 0xA); |
4876 | 503k | goto get_more; |
4877 | 503k | } |
4878 | 7.09M | if (*in == ']') { |
4879 | 105k | if ((in[1] == ']') && (in[2] == '>')) { |
4880 | 415 | xmlFatalErr(ctxt, XML_ERR_MISPLACED_CDATA_END, NULL); |
4881 | 415 | ctxt->input->cur = in + 1; |
4882 | 415 | return; |
4883 | 415 | } |
4884 | 105k | if ((!partial) || (ctxt->input->end - in >= 2)) { |
4885 | 105k | in++; |
4886 | 105k | ctxt->input->col++; |
4887 | 105k | goto get_more; |
4888 | 105k | } |
4889 | 105k | } |
4890 | 6.99M | nbchar = in - ctxt->input->cur; |
4891 | 6.99M | if (nbchar > 0) { |
4892 | 1.97M | const xmlChar *tmp = ctxt->input->cur; |
4893 | 1.97M | ctxt->input->cur = in; |
4894 | | |
4895 | 1.97M | xmlCharacters(ctxt, tmp, nbchar, 0); |
4896 | | |
4897 | 1.97M | line = ctxt->input->line; |
4898 | 1.97M | col = ctxt->input->col; |
4899 | 1.97M | } |
4900 | 6.99M | ctxt->input->cur = in; |
4901 | 6.99M | if (*in == 0xD) { |
4902 | 170k | in++; |
4903 | 170k | if (*in == 0xA) { |
4904 | 149k | ctxt->input->cur = in; |
4905 | 149k | in++; |
4906 | 149k | ctxt->input->line++; ctxt->input->col = 1; |
4907 | 149k | continue; /* while */ |
4908 | 149k | } |
4909 | 20.9k | in--; |
4910 | 20.9k | } |
4911 | 6.84M | if (*in == '<') { |
4912 | 1.23M | return; |
4913 | 1.23M | } |
4914 | 5.61M | if (*in == '&') { |
4915 | 126k | return; |
4916 | 126k | } |
4917 | 5.48M | if ((partial) && (*in == ']') && (ctxt->input->end - in < 2)) { |
4918 | 0 | return; |
4919 | 0 | } |
4920 | 5.48M | SHRINK; |
4921 | 5.48M | GROW; |
4922 | 5.48M | in = ctxt->input->cur; |
4923 | 5.63M | } while (((*in >= 0x20) && (*in <= 0x7F)) || |
4924 | 5.63M | (*in == 0x09) || (*in == 0x0a)); |
4925 | 5.49M | ctxt->input->line = line; |
4926 | 5.49M | ctxt->input->col = col; |
4927 | 5.49M | xmlParseCharDataComplex(ctxt, partial); |
4928 | 5.49M | } |
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 | 5.49M | xmlParseCharDataComplex(xmlParserCtxtPtr ctxt, int partial) { |
4943 | 5.49M | xmlChar buf[XML_PARSER_BIG_BUFFER_SIZE + 5]; |
4944 | 5.49M | int nbchar = 0; |
4945 | 5.49M | int cur, l; |
4946 | | |
4947 | 5.49M | cur = xmlCurrentCharRecover(ctxt, &l); |
4948 | 161M | while ((cur != '<') && /* checked */ |
4949 | 161M | (cur != '&') && |
4950 | 161M | ((!partial) || (cur != ']') || |
4951 | 161M | (ctxt->input->end - ctxt->input->cur >= 2)) && |
4952 | 161M | (IS_CHAR(cur))) { |
4953 | 156M | if ((cur == ']') && (NXT(1) == ']') && (NXT(2) == '>')) { |
4954 | 619 | xmlFatalErr(ctxt, XML_ERR_MISPLACED_CDATA_END, NULL); |
4955 | 619 | } |
4956 | 156M | COPY_BUF(buf, nbchar, cur); |
4957 | | /* move current position before possible calling of ctxt->sax->characters */ |
4958 | 156M | NEXTL(l); |
4959 | 156M | if (nbchar >= XML_PARSER_BIG_BUFFER_SIZE) { |
4960 | 814k | buf[nbchar] = 0; |
4961 | | |
4962 | 814k | xmlCharacters(ctxt, buf, nbchar, 0); |
4963 | 814k | nbchar = 0; |
4964 | 814k | SHRINK; |
4965 | 814k | } |
4966 | 156M | cur = xmlCurrentCharRecover(ctxt, &l); |
4967 | 156M | } |
4968 | 5.49M | if (nbchar != 0) { |
4969 | 771k | buf[nbchar] = 0; |
4970 | | |
4971 | 771k | xmlCharacters(ctxt, buf, nbchar, 0); |
4972 | 771k | } |
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 | 5.49M | if (ctxt->input->cur < ctxt->input->end) { |
4981 | 5.46M | if ((cur == 0) && (CUR != 0)) { |
4982 | 8.01k | if (partial == 0) { |
4983 | 8.01k | xmlFatalErrMsgInt(ctxt, XML_ERR_INVALID_CHAR, |
4984 | 8.01k | "Incomplete UTF-8 sequence starting with %02X\n", CUR); |
4985 | 8.01k | NEXTL(1); |
4986 | 8.01k | } |
4987 | 5.46M | } else if ((cur != '<') && (cur != '&') && (cur != ']')) { |
4988 | | /* Generate the error and skip the offending character */ |
4989 | 4.96M | xmlFatalErrMsgInt(ctxt, XML_ERR_INVALID_CHAR, |
4990 | 4.96M | "PCDATA invalid Char value %d\n", cur); |
4991 | 4.96M | NEXTL(l); |
4992 | 4.96M | } |
4993 | 5.46M | } |
4994 | 5.49M | } |
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 | 241k | xmlParseExternalID(xmlParserCtxtPtr ctxt, xmlChar **publicID, int strict) { |
5034 | 241k | xmlChar *URI = NULL; |
5035 | | |
5036 | 241k | *publicID = NULL; |
5037 | 241k | if (CMP6(CUR_PTR, 'S', 'Y', 'S', 'T', 'E', 'M')) { |
5038 | 84.8k | SKIP(6); |
5039 | 84.8k | if (SKIP_BLANKS == 0) { |
5040 | 797 | xmlFatalErrMsg(ctxt, XML_ERR_SPACE_REQUIRED, |
5041 | 797 | "Space required after 'SYSTEM'\n"); |
5042 | 797 | } |
5043 | 84.8k | URI = xmlParseSystemLiteral(ctxt); |
5044 | 84.8k | if (URI == NULL) { |
5045 | 970 | xmlFatalErr(ctxt, XML_ERR_URI_REQUIRED, NULL); |
5046 | 970 | } |
5047 | 156k | } else if (CMP6(CUR_PTR, 'P', 'U', 'B', 'L', 'I', 'C')) { |
5048 | 29.2k | SKIP(6); |
5049 | 29.2k | if (SKIP_BLANKS == 0) { |
5050 | 678 | xmlFatalErrMsg(ctxt, XML_ERR_SPACE_REQUIRED, |
5051 | 678 | "Space required after 'PUBLIC'\n"); |
5052 | 678 | } |
5053 | 29.2k | *publicID = xmlParsePubidLiteral(ctxt); |
5054 | 29.2k | if (*publicID == NULL) { |
5055 | 2.61k | xmlFatalErr(ctxt, XML_ERR_PUBID_REQUIRED, NULL); |
5056 | 2.61k | } |
5057 | 29.2k | if (strict) { |
5058 | | /* |
5059 | | * We don't handle [83] so "S SystemLiteral" is required. |
5060 | | */ |
5061 | 21.3k | if (SKIP_BLANKS == 0) { |
5062 | 2.34k | xmlFatalErrMsg(ctxt, XML_ERR_SPACE_REQUIRED, |
5063 | 2.34k | "Space required after the Public Identifier\n"); |
5064 | 2.34k | } |
5065 | 21.3k | } 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 | 7.93k | if (SKIP_BLANKS == 0) return(NULL); |
5073 | 2.73k | if ((CUR != '\'') && (CUR != '"')) return(NULL); |
5074 | 2.73k | } |
5075 | 23.8k | URI = xmlParseSystemLiteral(ctxt); |
5076 | 23.8k | if (URI == NULL) { |
5077 | 2.03k | xmlFatalErr(ctxt, XML_ERR_URI_REQUIRED, NULL); |
5078 | 2.03k | } |
5079 | 23.8k | } |
5080 | 236k | return(URI); |
5081 | 241k | } |
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 | 55.6k | size_t len, size_t size) { |
5100 | 55.6k | int q, ql; |
5101 | 55.6k | int r, rl; |
5102 | 55.6k | int cur, l; |
5103 | 55.6k | int maxLength = (ctxt->options & XML_PARSE_HUGE) ? |
5104 | 0 | XML_MAX_HUGE_LENGTH : |
5105 | 55.6k | XML_MAX_TEXT_LENGTH; |
5106 | | |
5107 | 55.6k | if (buf == NULL) { |
5108 | 7.73k | len = 0; |
5109 | 7.73k | size = XML_PARSER_BUFFER_SIZE; |
5110 | 7.73k | buf = xmlMalloc(size); |
5111 | 7.73k | if (buf == NULL) { |
5112 | 2 | xmlErrMemory(ctxt); |
5113 | 2 | return; |
5114 | 2 | } |
5115 | 7.73k | } |
5116 | 55.6k | q = xmlCurrentCharRecover(ctxt, &ql); |
5117 | 55.6k | if (q == 0) |
5118 | 2.92k | goto not_terminated; |
5119 | 52.7k | if (!IS_CHAR(q)) { |
5120 | 3.99k | xmlFatalErrMsgInt(ctxt, XML_ERR_INVALID_CHAR, |
5121 | 3.99k | "xmlParseComment: invalid xmlChar value %d\n", |
5122 | 3.99k | q); |
5123 | 3.99k | xmlFree (buf); |
5124 | 3.99k | return; |
5125 | 3.99k | } |
5126 | 48.7k | NEXTL(ql); |
5127 | 48.7k | r = xmlCurrentCharRecover(ctxt, &rl); |
5128 | 48.7k | if (r == 0) |
5129 | 1.25k | goto not_terminated; |
5130 | 47.5k | if (!IS_CHAR(r)) { |
5131 | 3.94k | xmlFatalErrMsgInt(ctxt, XML_ERR_INVALID_CHAR, |
5132 | 3.94k | "xmlParseComment: invalid xmlChar value %d\n", |
5133 | 3.94k | r); |
5134 | 3.94k | xmlFree (buf); |
5135 | 3.94k | return; |
5136 | 3.94k | } |
5137 | 43.5k | NEXTL(rl); |
5138 | 43.5k | cur = xmlCurrentCharRecover(ctxt, &l); |
5139 | 43.5k | if (cur == 0) |
5140 | 622 | goto not_terminated; |
5141 | 5.93M | while (IS_CHAR(cur) && /* checked */ |
5142 | 5.93M | ((cur != '>') || |
5143 | 5.92M | (r != '-') || (q != '-'))) { |
5144 | 5.89M | if ((r == '-') && (q == '-')) { |
5145 | 8.71k | xmlFatalErr(ctxt, XML_ERR_HYPHEN_IN_COMMENT, NULL); |
5146 | 8.71k | } |
5147 | 5.89M | if (len + 5 >= size) { |
5148 | 19.1k | xmlChar *tmp; |
5149 | 19.1k | int newSize; |
5150 | | |
5151 | 19.1k | newSize = xmlGrowCapacity(size, 1, 1, maxLength); |
5152 | 19.1k | 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 | 19.1k | tmp = xmlRealloc(buf, newSize); |
5159 | 19.1k | if (tmp == NULL) { |
5160 | 7 | xmlErrMemory(ctxt); |
5161 | 7 | xmlFree(buf); |
5162 | 7 | return; |
5163 | 7 | } |
5164 | 19.1k | buf = tmp; |
5165 | 19.1k | size = newSize; |
5166 | 19.1k | } |
5167 | 5.89M | COPY_BUF(buf, len, q); |
5168 | | |
5169 | 5.89M | q = r; |
5170 | 5.89M | ql = rl; |
5171 | 5.89M | r = cur; |
5172 | 5.89M | rl = l; |
5173 | | |
5174 | 5.89M | NEXTL(l); |
5175 | 5.89M | cur = xmlCurrentCharRecover(ctxt, &l); |
5176 | | |
5177 | 5.89M | } |
5178 | 42.9k | buf[len] = 0; |
5179 | 42.9k | if (cur == 0) { |
5180 | 6.71k | xmlFatalErrMsgStr(ctxt, XML_ERR_COMMENT_NOT_FINISHED, |
5181 | 6.71k | "Comment not terminated \n<!--%.50s\n", buf); |
5182 | 36.2k | } else if (!IS_CHAR(cur)) { |
5183 | 3.78k | xmlFatalErrMsgInt(ctxt, XML_ERR_INVALID_CHAR, |
5184 | 3.78k | "xmlParseComment: invalid xmlChar value %d\n", |
5185 | 3.78k | cur); |
5186 | 32.4k | } else { |
5187 | 32.4k | NEXT; |
5188 | 32.4k | if ((ctxt->sax != NULL) && (ctxt->sax->comment != NULL) && |
5189 | 32.4k | (!ctxt->disableSAX)) |
5190 | 23.1k | ctxt->sax->comment(ctxt->userData, buf); |
5191 | 32.4k | } |
5192 | 42.9k | xmlFree(buf); |
5193 | 42.9k | return; |
5194 | 4.80k | not_terminated: |
5195 | 4.80k | xmlFatalErrMsgStr(ctxt, XML_ERR_COMMENT_NOT_FINISHED, |
5196 | 4.80k | "Comment not terminated\n", NULL); |
5197 | 4.80k | xmlFree(buf); |
5198 | 4.80k | } |
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 | 167k | xmlParseComment(xmlParserCtxtPtr ctxt) { |
5215 | 167k | xmlChar *buf = NULL; |
5216 | 167k | size_t size = XML_PARSER_BUFFER_SIZE; |
5217 | 167k | size_t len = 0; |
5218 | 167k | size_t maxLength = (ctxt->options & XML_PARSE_HUGE) ? |
5219 | 0 | XML_MAX_HUGE_LENGTH : |
5220 | 167k | XML_MAX_TEXT_LENGTH; |
5221 | 167k | const xmlChar *in; |
5222 | 167k | size_t nbchar = 0; |
5223 | 167k | int ccol; |
5224 | | |
5225 | | /* |
5226 | | * Check that there is a comment right here. |
5227 | | */ |
5228 | 167k | if ((RAW != '<') || (NXT(1) != '!')) |
5229 | 0 | return; |
5230 | 167k | SKIP(2); |
5231 | 167k | if ((RAW != '-') || (NXT(1) != '-')) |
5232 | 1.36k | return; |
5233 | 165k | SKIP(2); |
5234 | 165k | GROW; |
5235 | | |
5236 | | /* |
5237 | | * Accelerated common case where input don't need to be |
5238 | | * modified before passing it to the handler. |
5239 | | */ |
5240 | 165k | in = ctxt->input->cur; |
5241 | 166k | do { |
5242 | 166k | if (*in == 0xA) { |
5243 | 45.1k | do { |
5244 | 45.1k | ctxt->input->line++; ctxt->input->col = 1; |
5245 | 45.1k | in++; |
5246 | 45.1k | } while (*in == 0xA); |
5247 | 20.1k | } |
5248 | 489k | get_more: |
5249 | 489k | ccol = ctxt->input->col; |
5250 | 9.03M | while (((*in > '-') && (*in <= 0x7F)) || |
5251 | 9.03M | ((*in >= 0x20) && (*in < '-')) || |
5252 | 9.03M | (*in == 0x09)) { |
5253 | 8.54M | in++; |
5254 | 8.54M | ccol++; |
5255 | 8.54M | } |
5256 | 489k | ctxt->input->col = ccol; |
5257 | 489k | if (*in == 0xA) { |
5258 | 5.85M | do { |
5259 | 5.85M | ctxt->input->line++; ctxt->input->col = 1; |
5260 | 5.85M | in++; |
5261 | 5.85M | } while (*in == 0xA); |
5262 | 51.0k | goto get_more; |
5263 | 51.0k | } |
5264 | 438k | nbchar = in - ctxt->input->cur; |
5265 | | /* |
5266 | | * save current set of data |
5267 | | */ |
5268 | 438k | if (nbchar > 0) { |
5269 | 417k | 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 | 417k | if (buf == NULL) { |
5276 | 157k | if ((*in == '-') && (in[1] == '-')) |
5277 | 74.1k | size = nbchar + 1; |
5278 | 83.1k | else |
5279 | 83.1k | size = XML_PARSER_BUFFER_SIZE + nbchar; |
5280 | 157k | buf = xmlMalloc(size); |
5281 | 157k | if (buf == NULL) { |
5282 | 8 | xmlErrMemory(ctxt); |
5283 | 8 | return; |
5284 | 8 | } |
5285 | 157k | len = 0; |
5286 | 260k | } else if (len + nbchar + 1 >= size) { |
5287 | 24.5k | xmlChar *new_buf; |
5288 | 24.5k | size += len + nbchar + XML_PARSER_BUFFER_SIZE; |
5289 | 24.5k | new_buf = xmlRealloc(buf, size); |
5290 | 24.5k | if (new_buf == NULL) { |
5291 | 2 | xmlErrMemory(ctxt); |
5292 | 2 | xmlFree(buf); |
5293 | 2 | return; |
5294 | 2 | } |
5295 | 24.5k | buf = new_buf; |
5296 | 24.5k | } |
5297 | 417k | memcpy(&buf[len], ctxt->input->cur, nbchar); |
5298 | 417k | len += nbchar; |
5299 | 417k | buf[len] = 0; |
5300 | 417k | } |
5301 | 438k | ctxt->input->cur = in; |
5302 | 438k | if (*in == 0xA) { |
5303 | 0 | in++; |
5304 | 0 | ctxt->input->line++; ctxt->input->col = 1; |
5305 | 0 | } |
5306 | 438k | if (*in == 0xD) { |
5307 | 128k | in++; |
5308 | 128k | if (*in == 0xA) { |
5309 | 120k | ctxt->input->cur = in; |
5310 | 120k | in++; |
5311 | 120k | ctxt->input->line++; ctxt->input->col = 1; |
5312 | 120k | goto get_more; |
5313 | 120k | } |
5314 | 8.60k | in--; |
5315 | 8.60k | } |
5316 | 318k | SHRINK; |
5317 | 318k | GROW; |
5318 | 318k | in = ctxt->input->cur; |
5319 | 318k | if (*in == '-') { |
5320 | 261k | if (in[1] == '-') { |
5321 | 187k | if (in[2] == '>') { |
5322 | 110k | SKIP(3); |
5323 | 110k | if ((ctxt->sax != NULL) && (ctxt->sax->comment != NULL) && |
5324 | 110k | (!ctxt->disableSAX)) { |
5325 | 62.9k | if (buf != NULL) |
5326 | 62.6k | ctxt->sax->comment(ctxt->userData, buf); |
5327 | 358 | else |
5328 | 358 | ctxt->sax->comment(ctxt->userData, BAD_CAST ""); |
5329 | 62.9k | } |
5330 | 110k | if (buf != NULL) |
5331 | 109k | xmlFree(buf); |
5332 | 110k | return; |
5333 | 110k | } |
5334 | 77.8k | if (buf != NULL) { |
5335 | 76.2k | xmlFatalErrMsgStr(ctxt, XML_ERR_HYPHEN_IN_COMMENT, |
5336 | 76.2k | "Double hyphen within comment: " |
5337 | 76.2k | "<!--%.50s\n", |
5338 | 76.2k | buf); |
5339 | 76.2k | } else |
5340 | 1.61k | xmlFatalErrMsgStr(ctxt, XML_ERR_HYPHEN_IN_COMMENT, |
5341 | 1.61k | "Double hyphen within comment\n", NULL); |
5342 | 77.8k | in++; |
5343 | 77.8k | ctxt->input->col++; |
5344 | 77.8k | } |
5345 | 151k | in++; |
5346 | 151k | ctxt->input->col++; |
5347 | 151k | goto get_more; |
5348 | 261k | } |
5349 | 318k | } while (((*in >= 0x20) && (*in <= 0x7F)) || (*in == 0x09) || (*in == 0x0a)); |
5350 | 55.6k | xmlParseCommentComplex(ctxt, buf, len, size); |
5351 | 55.6k | } |
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 | 114k | xmlParsePITarget(xmlParserCtxtPtr ctxt) { |
5369 | 114k | const xmlChar *name; |
5370 | | |
5371 | 114k | name = xmlParseName(ctxt); |
5372 | 114k | if ((name != NULL) && |
5373 | 114k | ((name[0] == 'x') || (name[0] == 'X')) && |
5374 | 114k | ((name[1] == 'm') || (name[1] == 'M')) && |
5375 | 114k | ((name[2] == 'l') || (name[2] == 'L'))) { |
5376 | 8.74k | int i; |
5377 | 8.74k | if ((name[0] == 'x') && (name[1] == 'm') && |
5378 | 8.74k | (name[2] == 'l') && (name[3] == 0)) { |
5379 | 5.48k | xmlFatalErrMsg(ctxt, XML_ERR_RESERVED_XML_NAME, |
5380 | 5.48k | "XML declaration allowed only at the start of the document\n"); |
5381 | 5.48k | return(name); |
5382 | 5.48k | } else if (name[3] == 0) { |
5383 | 764 | xmlFatalErr(ctxt, XML_ERR_RESERVED_XML_NAME, NULL); |
5384 | 764 | return(name); |
5385 | 764 | } |
5386 | 6.90k | for (i = 0;;i++) { |
5387 | 6.90k | if (xmlW3CPIs[i] == NULL) break; |
5388 | 4.79k | if (xmlStrEqual(name, (const xmlChar *)xmlW3CPIs[i])) |
5389 | 389 | return(name); |
5390 | 4.79k | } |
5391 | 2.11k | xmlWarningMsg(ctxt, XML_ERR_RESERVED_XML_NAME, |
5392 | 2.11k | "xmlParsePITarget: invalid name prefix 'xml'\n", |
5393 | 2.11k | NULL, NULL); |
5394 | 2.11k | } |
5395 | 108k | if ((name != NULL) && (xmlStrchr(name, ':') != NULL)) { |
5396 | 777 | xmlNsErr(ctxt, XML_NS_ERR_COLON, |
5397 | 777 | "colons are forbidden from PI names '%s'\n", name, NULL, NULL); |
5398 | 777 | } |
5399 | 108k | return(name); |
5400 | 114k | } |
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 | 114k | xmlParsePI(xmlParserCtxtPtr ctxt) { |
5485 | 114k | xmlChar *buf = NULL; |
5486 | 114k | size_t len = 0; |
5487 | 114k | size_t size = XML_PARSER_BUFFER_SIZE; |
5488 | 114k | size_t maxLength = (ctxt->options & XML_PARSE_HUGE) ? |
5489 | 0 | XML_MAX_HUGE_LENGTH : |
5490 | 114k | XML_MAX_TEXT_LENGTH; |
5491 | 114k | int cur, l; |
5492 | 114k | const xmlChar *target; |
5493 | | |
5494 | 114k | if ((RAW == '<') && (NXT(1) == '?')) { |
5495 | | /* |
5496 | | * this is a Processing Instruction. |
5497 | | */ |
5498 | 114k | SKIP(2); |
5499 | | |
5500 | | /* |
5501 | | * Parse the target name and check for special support like |
5502 | | * namespace. |
5503 | | */ |
5504 | 114k | target = xmlParsePITarget(ctxt); |
5505 | 114k | if (target != NULL) { |
5506 | 112k | if ((RAW == '?') && (NXT(1) == '>')) { |
5507 | 36.6k | SKIP(2); |
5508 | | |
5509 | | /* |
5510 | | * SAX: PI detected. |
5511 | | */ |
5512 | 36.6k | if ((ctxt->sax) && (!ctxt->disableSAX) && |
5513 | 36.6k | (ctxt->sax->processingInstruction != NULL)) |
5514 | 32.8k | ctxt->sax->processingInstruction(ctxt->userData, |
5515 | 32.8k | target, NULL); |
5516 | 36.6k | return; |
5517 | 36.6k | } |
5518 | 75.8k | buf = xmlMalloc(size); |
5519 | 75.8k | if (buf == NULL) { |
5520 | 7 | xmlErrMemory(ctxt); |
5521 | 7 | return; |
5522 | 7 | } |
5523 | 75.8k | if (SKIP_BLANKS == 0) { |
5524 | 16.4k | xmlFatalErrMsgStr(ctxt, XML_ERR_SPACE_REQUIRED, |
5525 | 16.4k | "ParsePI: PI %s space expected\n", target); |
5526 | 16.4k | } |
5527 | 75.8k | cur = xmlCurrentCharRecover(ctxt, &l); |
5528 | 5.38M | while (IS_CHAR(cur) && /* checked */ |
5529 | 5.38M | ((cur != '?') || (NXT(1) != '>'))) { |
5530 | 5.30M | if (len + 5 >= size) { |
5531 | 14.5k | xmlChar *tmp; |
5532 | 14.5k | int newSize; |
5533 | | |
5534 | 14.5k | newSize = xmlGrowCapacity(size, 1, 1, maxLength); |
5535 | 14.5k | 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 | 14.5k | tmp = xmlRealloc(buf, newSize); |
5542 | 14.5k | if (tmp == NULL) { |
5543 | 2 | xmlErrMemory(ctxt); |
5544 | 2 | xmlFree(buf); |
5545 | 2 | return; |
5546 | 2 | } |
5547 | 14.5k | buf = tmp; |
5548 | 14.5k | size = newSize; |
5549 | 14.5k | } |
5550 | 5.30M | COPY_BUF(buf, len, cur); |
5551 | 5.30M | NEXTL(l); |
5552 | 5.30M | cur = xmlCurrentCharRecover(ctxt, &l); |
5553 | 5.30M | } |
5554 | 75.8k | buf[len] = 0; |
5555 | 75.8k | if (cur != '?') { |
5556 | 14.3k | xmlFatalErrMsgStr(ctxt, XML_ERR_PI_NOT_FINISHED, |
5557 | 14.3k | "ParsePI: PI %s never end ...\n", target); |
5558 | 61.5k | } else { |
5559 | 61.5k | SKIP(2); |
5560 | | |
5561 | 61.5k | #ifdef LIBXML_CATALOG_ENABLED |
5562 | 61.5k | if ((ctxt->inSubset == 0) && |
5563 | 61.5k | (xmlStrEqual(target, XML_CATALOG_PI))) { |
5564 | 263 | xmlCatalogAllow allow = xmlCatalogGetDefaults(); |
5565 | | |
5566 | 263 | if ((ctxt->options & XML_PARSE_CATALOG_PI) && |
5567 | 263 | ((allow == XML_CATA_ALLOW_DOCUMENT) || |
5568 | 0 | (allow == XML_CATA_ALLOW_ALL))) |
5569 | 0 | xmlParseCatalogPI(ctxt, buf); |
5570 | 263 | } |
5571 | 61.5k | #endif |
5572 | | |
5573 | | /* |
5574 | | * SAX: PI detected. |
5575 | | */ |
5576 | 61.5k | if ((ctxt->sax) && (!ctxt->disableSAX) && |
5577 | 61.5k | (ctxt->sax->processingInstruction != NULL)) |
5578 | 52.7k | ctxt->sax->processingInstruction(ctxt->userData, |
5579 | 52.7k | target, buf); |
5580 | 61.5k | } |
5581 | 75.8k | xmlFree(buf); |
5582 | 75.8k | } else { |
5583 | 2.49k | xmlFatalErr(ctxt, XML_ERR_PI_NOT_STARTED, NULL); |
5584 | 2.49k | } |
5585 | 114k | } |
5586 | 114k | } |
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 | 17.7k | xmlParseNotationDecl(xmlParserCtxtPtr ctxt) { |
5608 | 17.7k | const xmlChar *name; |
5609 | 17.7k | xmlChar *Pubid; |
5610 | 17.7k | xmlChar *Systemid; |
5611 | | |
5612 | 17.7k | if ((CUR != '<') || (NXT(1) != '!')) |
5613 | 0 | return; |
5614 | 17.7k | SKIP(2); |
5615 | | |
5616 | 17.7k | if (CMP8(CUR_PTR, 'N', 'O', 'T', 'A', 'T', 'I', 'O', 'N')) { |
5617 | 15.1k | int inputid = ctxt->input->id; |
5618 | 15.1k | SKIP(8); |
5619 | 15.1k | if (SKIP_BLANKS_PE == 0) { |
5620 | 2.63k | xmlFatalErrMsg(ctxt, XML_ERR_SPACE_REQUIRED, |
5621 | 2.63k | "Space required after '<!NOTATION'\n"); |
5622 | 2.63k | return; |
5623 | 2.63k | } |
5624 | | |
5625 | 12.5k | name = xmlParseName(ctxt); |
5626 | 12.5k | if (name == NULL) { |
5627 | 728 | xmlFatalErr(ctxt, XML_ERR_NOTATION_NOT_STARTED, NULL); |
5628 | 728 | return; |
5629 | 728 | } |
5630 | 11.8k | if (xmlStrchr(name, ':') != NULL) { |
5631 | 581 | xmlNsErr(ctxt, XML_NS_ERR_COLON, |
5632 | 581 | "colons are forbidden from notation names '%s'\n", |
5633 | 581 | name, NULL, NULL); |
5634 | 581 | } |
5635 | 11.8k | if (SKIP_BLANKS_PE == 0) { |
5636 | 730 | xmlFatalErrMsg(ctxt, XML_ERR_SPACE_REQUIRED, |
5637 | 730 | "Space required after the NOTATION name'\n"); |
5638 | 730 | return; |
5639 | 730 | } |
5640 | | |
5641 | | /* |
5642 | | * Parse the IDs. |
5643 | | */ |
5644 | 11.0k | Systemid = xmlParseExternalID(ctxt, &Pubid, 0); |
5645 | 11.0k | SKIP_BLANKS_PE; |
5646 | | |
5647 | 11.0k | if (RAW == '>') { |
5648 | 8.21k | if (inputid != ctxt->input->id) { |
5649 | 0 | xmlFatalErrMsg(ctxt, XML_ERR_ENTITY_BOUNDARY, |
5650 | 0 | "Notation declaration doesn't start and stop" |
5651 | 0 | " in the same entity\n"); |
5652 | 0 | } |
5653 | 8.21k | NEXT; |
5654 | 8.21k | if ((ctxt->sax != NULL) && (!ctxt->disableSAX) && |
5655 | 8.21k | (ctxt->sax->notationDecl != NULL)) |
5656 | 7.87k | ctxt->sax->notationDecl(ctxt->userData, name, Pubid, Systemid); |
5657 | 8.21k | } else { |
5658 | 2.86k | xmlFatalErr(ctxt, XML_ERR_NOTATION_NOT_FINISHED, NULL); |
5659 | 2.86k | } |
5660 | 11.0k | if (Systemid != NULL) xmlFree(Systemid); |
5661 | 11.0k | if (Pubid != NULL) xmlFree(Pubid); |
5662 | 11.0k | } |
5663 | 17.7k | } |
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 | 197k | xmlParseEntityDecl(xmlParserCtxtPtr ctxt) { |
5691 | 197k | const xmlChar *name = NULL; |
5692 | 197k | xmlChar *value = NULL; |
5693 | 197k | xmlChar *URI = NULL, *literal = NULL; |
5694 | 197k | const xmlChar *ndata = NULL; |
5695 | 197k | int isParameter = 0; |
5696 | 197k | xmlChar *orig = NULL; |
5697 | | |
5698 | 197k | if ((CUR != '<') || (NXT(1) != '!')) |
5699 | 0 | return; |
5700 | 197k | SKIP(2); |
5701 | | |
5702 | | /* GROW; done in the caller */ |
5703 | 197k | if (CMP6(CUR_PTR, 'E', 'N', 'T', 'I', 'T', 'Y')) { |
5704 | 195k | int inputid = ctxt->input->id; |
5705 | 195k | SKIP(6); |
5706 | 195k | if (SKIP_BLANKS_PE == 0) { |
5707 | 2.30k | xmlFatalErrMsg(ctxt, XML_ERR_SPACE_REQUIRED, |
5708 | 2.30k | "Space required after '<!ENTITY'\n"); |
5709 | 2.30k | } |
5710 | | |
5711 | 195k | if (RAW == '%') { |
5712 | 116k | NEXT; |
5713 | 116k | if (SKIP_BLANKS_PE == 0) { |
5714 | 15.4k | xmlFatalErrMsg(ctxt, XML_ERR_SPACE_REQUIRED, |
5715 | 15.4k | "Space required after '%%'\n"); |
5716 | 15.4k | } |
5717 | 116k | isParameter = 1; |
5718 | 116k | } |
5719 | | |
5720 | 195k | name = xmlParseName(ctxt); |
5721 | 195k | if (name == NULL) { |
5722 | 10.5k | xmlFatalErrMsg(ctxt, XML_ERR_NAME_REQUIRED, |
5723 | 10.5k | "xmlParseEntityDecl: no name\n"); |
5724 | 10.5k | return; |
5725 | 10.5k | } |
5726 | 185k | if (xmlStrchr(name, ':') != NULL) { |
5727 | 770 | xmlNsErr(ctxt, XML_NS_ERR_COLON, |
5728 | 770 | "colons are forbidden from entities names '%s'\n", |
5729 | 770 | name, NULL, NULL); |
5730 | 770 | } |
5731 | 185k | if (SKIP_BLANKS_PE == 0) { |
5732 | 2.98k | xmlFatalErrMsg(ctxt, XML_ERR_SPACE_REQUIRED, |
5733 | 2.98k | "Space required after the entity name\n"); |
5734 | 2.98k | } |
5735 | | |
5736 | | /* |
5737 | | * handle the various case of definitions... |
5738 | | */ |
5739 | 185k | if (isParameter) { |
5740 | 107k | if ((RAW == '"') || (RAW == '\'')) { |
5741 | 53.7k | value = xmlParseEntityValue(ctxt, &orig); |
5742 | 53.7k | if (value) { |
5743 | 52.7k | if ((ctxt->sax != NULL) && |
5744 | 52.7k | (!ctxt->disableSAX) && (ctxt->sax->entityDecl != NULL)) |
5745 | 31.8k | ctxt->sax->entityDecl(ctxt->userData, name, |
5746 | 31.8k | XML_INTERNAL_PARAMETER_ENTITY, |
5747 | 31.8k | NULL, NULL, value); |
5748 | 52.7k | } |
5749 | 53.7k | } else { |
5750 | 53.5k | URI = xmlParseExternalID(ctxt, &literal, 1); |
5751 | 53.5k | if ((URI == NULL) && (literal == NULL)) { |
5752 | 1.79k | xmlFatalErr(ctxt, XML_ERR_VALUE_REQUIRED, NULL); |
5753 | 1.79k | } |
5754 | 53.5k | if (URI) { |
5755 | 51.5k | if (xmlStrchr(URI, '#')) { |
5756 | 227 | xmlFatalErr(ctxt, XML_ERR_URI_FRAGMENT, NULL); |
5757 | 51.3k | } else { |
5758 | 51.3k | if ((ctxt->sax != NULL) && |
5759 | 51.3k | (!ctxt->disableSAX) && |
5760 | 51.3k | (ctxt->sax->entityDecl != NULL)) |
5761 | 42.8k | ctxt->sax->entityDecl(ctxt->userData, name, |
5762 | 42.8k | XML_EXTERNAL_PARAMETER_ENTITY, |
5763 | 42.8k | literal, URI, NULL); |
5764 | 51.3k | } |
5765 | 51.5k | } |
5766 | 53.5k | } |
5767 | 107k | } else { |
5768 | 77.8k | if ((RAW == '"') || (RAW == '\'')) { |
5769 | 55.8k | value = xmlParseEntityValue(ctxt, &orig); |
5770 | 55.8k | if ((ctxt->sax != NULL) && |
5771 | 55.8k | (!ctxt->disableSAX) && (ctxt->sax->entityDecl != NULL)) |
5772 | 23.6k | ctxt->sax->entityDecl(ctxt->userData, name, |
5773 | 23.6k | XML_INTERNAL_GENERAL_ENTITY, |
5774 | 23.6k | NULL, NULL, value); |
5775 | | /* |
5776 | | * For expat compatibility in SAX mode. |
5777 | | */ |
5778 | 55.8k | if ((ctxt->myDoc == NULL) || |
5779 | 55.8k | (xmlStrEqual(ctxt->myDoc->version, SAX_COMPAT_MODE))) { |
5780 | 20.7k | if (ctxt->myDoc == NULL) { |
5781 | 14.4k | ctxt->myDoc = xmlNewDoc(SAX_COMPAT_MODE); |
5782 | 14.4k | if (ctxt->myDoc == NULL) { |
5783 | 14 | xmlErrMemory(ctxt); |
5784 | 14 | goto done; |
5785 | 14 | } |
5786 | 14.4k | ctxt->myDoc->properties = XML_DOC_INTERNAL; |
5787 | 14.4k | } |
5788 | 20.7k | if (ctxt->myDoc->intSubset == NULL) { |
5789 | 14.4k | ctxt->myDoc->intSubset = xmlNewDtd(ctxt->myDoc, |
5790 | 14.4k | BAD_CAST "fake", NULL, NULL); |
5791 | 14.4k | if (ctxt->myDoc->intSubset == NULL) { |
5792 | 2 | xmlErrMemory(ctxt); |
5793 | 2 | goto done; |
5794 | 2 | } |
5795 | 14.4k | } |
5796 | | |
5797 | 20.7k | xmlSAX2EntityDecl(ctxt, name, XML_INTERNAL_GENERAL_ENTITY, |
5798 | 20.7k | NULL, NULL, value); |
5799 | 20.7k | } |
5800 | 55.8k | } else { |
5801 | 22.0k | URI = xmlParseExternalID(ctxt, &literal, 1); |
5802 | 22.0k | if ((URI == NULL) && (literal == NULL)) { |
5803 | 4.52k | xmlFatalErr(ctxt, XML_ERR_VALUE_REQUIRED, NULL); |
5804 | 4.52k | } |
5805 | 22.0k | if (URI) { |
5806 | 16.7k | if (xmlStrchr(URI, '#')) { |
5807 | 378 | xmlFatalErr(ctxt, XML_ERR_URI_FRAGMENT, NULL); |
5808 | 378 | } |
5809 | 16.7k | } |
5810 | 22.0k | if ((RAW != '>') && (SKIP_BLANKS_PE == 0)) { |
5811 | 6.11k | xmlFatalErrMsg(ctxt, XML_ERR_SPACE_REQUIRED, |
5812 | 6.11k | "Space required before 'NDATA'\n"); |
5813 | 6.11k | } |
5814 | 22.0k | if (CMP5(CUR_PTR, 'N', 'D', 'A', 'T', 'A')) { |
5815 | 1.24k | SKIP(5); |
5816 | 1.24k | if (SKIP_BLANKS_PE == 0) { |
5817 | 764 | xmlFatalErrMsg(ctxt, XML_ERR_SPACE_REQUIRED, |
5818 | 764 | "Space required after 'NDATA'\n"); |
5819 | 764 | } |
5820 | 1.24k | ndata = xmlParseName(ctxt); |
5821 | 1.24k | if ((ctxt->sax != NULL) && (!ctxt->disableSAX) && |
5822 | 1.24k | (ctxt->sax->unparsedEntityDecl != NULL)) |
5823 | 306 | ctxt->sax->unparsedEntityDecl(ctxt->userData, name, |
5824 | 306 | literal, URI, ndata); |
5825 | 20.8k | } else { |
5826 | 20.8k | if ((ctxt->sax != NULL) && |
5827 | 20.8k | (!ctxt->disableSAX) && (ctxt->sax->entityDecl != NULL)) |
5828 | 13.1k | ctxt->sax->entityDecl(ctxt->userData, name, |
5829 | 13.1k | XML_EXTERNAL_GENERAL_PARSED_ENTITY, |
5830 | 13.1k | literal, URI, NULL); |
5831 | | /* |
5832 | | * For expat compatibility in SAX mode. |
5833 | | * assuming the entity replacement was asked for |
5834 | | */ |
5835 | 20.8k | if ((ctxt->replaceEntities != 0) && |
5836 | 20.8k | ((ctxt->myDoc == NULL) || |
5837 | 20.8k | (xmlStrEqual(ctxt->myDoc->version, SAX_COMPAT_MODE)))) { |
5838 | 2.04k | if (ctxt->myDoc == NULL) { |
5839 | 922 | ctxt->myDoc = xmlNewDoc(SAX_COMPAT_MODE); |
5840 | 922 | if (ctxt->myDoc == NULL) { |
5841 | 3 | xmlErrMemory(ctxt); |
5842 | 3 | goto done; |
5843 | 3 | } |
5844 | 919 | ctxt->myDoc->properties = XML_DOC_INTERNAL; |
5845 | 919 | } |
5846 | | |
5847 | 2.04k | if (ctxt->myDoc->intSubset == NULL) { |
5848 | 919 | ctxt->myDoc->intSubset = xmlNewDtd(ctxt->myDoc, |
5849 | 919 | BAD_CAST "fake", NULL, NULL); |
5850 | 919 | if (ctxt->myDoc->intSubset == NULL) { |
5851 | 1 | xmlErrMemory(ctxt); |
5852 | 1 | goto done; |
5853 | 1 | } |
5854 | 919 | } |
5855 | 2.04k | xmlSAX2EntityDecl(ctxt, name, |
5856 | 2.04k | XML_EXTERNAL_GENERAL_PARSED_ENTITY, |
5857 | 2.04k | literal, URI, NULL); |
5858 | 2.04k | } |
5859 | 20.8k | } |
5860 | 22.0k | } |
5861 | 77.8k | } |
5862 | 185k | SKIP_BLANKS_PE; |
5863 | 185k | if (RAW != '>') { |
5864 | 29.3k | xmlFatalErrMsgStr(ctxt, XML_ERR_ENTITY_NOT_FINISHED, |
5865 | 29.3k | "xmlParseEntityDecl: entity %s not terminated\n", name); |
5866 | 29.3k | xmlHaltParser(ctxt); |
5867 | 155k | } else { |
5868 | 155k | if (inputid != ctxt->input->id) { |
5869 | 1 | xmlFatalErrMsg(ctxt, XML_ERR_ENTITY_BOUNDARY, |
5870 | 1 | "Entity declaration doesn't start and stop in" |
5871 | 1 | " the same entity\n"); |
5872 | 1 | } |
5873 | 155k | NEXT; |
5874 | 155k | } |
5875 | 185k | if (orig != NULL) { |
5876 | | /* |
5877 | | * Ugly mechanism to save the raw entity value. |
5878 | | */ |
5879 | 106k | xmlEntityPtr cur = NULL; |
5880 | | |
5881 | 106k | if (isParameter) { |
5882 | 52.7k | if ((ctxt->sax != NULL) && |
5883 | 52.7k | (ctxt->sax->getParameterEntity != NULL)) |
5884 | 52.7k | cur = ctxt->sax->getParameterEntity(ctxt->userData, name); |
5885 | 54.0k | } else { |
5886 | 54.0k | if ((ctxt->sax != NULL) && |
5887 | 54.0k | (ctxt->sax->getEntity != NULL)) |
5888 | 54.0k | cur = ctxt->sax->getEntity(ctxt->userData, name); |
5889 | 54.0k | if ((cur == NULL) && (ctxt->userData==ctxt)) { |
5890 | 10.3k | cur = xmlSAX2GetEntity(ctxt, name); |
5891 | 10.3k | } |
5892 | 54.0k | } |
5893 | 106k | if ((cur != NULL) && (cur->orig == NULL)) { |
5894 | 66.6k | cur->orig = orig; |
5895 | 66.6k | orig = NULL; |
5896 | 66.6k | } |
5897 | 106k | } |
5898 | | |
5899 | 185k | done: |
5900 | 185k | if (value != NULL) xmlFree(value); |
5901 | 185k | if (URI != NULL) xmlFree(URI); |
5902 | 185k | if (literal != NULL) xmlFree(literal); |
5903 | 185k | if (orig != NULL) xmlFree(orig); |
5904 | 185k | } |
5905 | 197k | } |
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 | 105k | xmlParseDefaultDecl(xmlParserCtxtPtr ctxt, xmlChar **value) { |
5940 | 105k | int val; |
5941 | 105k | xmlChar *ret; |
5942 | | |
5943 | 105k | *value = NULL; |
5944 | 105k | if (CMP9(CUR_PTR, '#', 'R', 'E', 'Q', 'U', 'I', 'R', 'E', 'D')) { |
5945 | 1.48k | SKIP(9); |
5946 | 1.48k | return(XML_ATTRIBUTE_REQUIRED); |
5947 | 1.48k | } |
5948 | 103k | if (CMP8(CUR_PTR, '#', 'I', 'M', 'P', 'L', 'I', 'E', 'D')) { |
5949 | 34.9k | SKIP(8); |
5950 | 34.9k | return(XML_ATTRIBUTE_IMPLIED); |
5951 | 34.9k | } |
5952 | 69.0k | val = XML_ATTRIBUTE_NONE; |
5953 | 69.0k | if (CMP6(CUR_PTR, '#', 'F', 'I', 'X', 'E', 'D')) { |
5954 | 8.63k | SKIP(6); |
5955 | 8.63k | val = XML_ATTRIBUTE_FIXED; |
5956 | 8.63k | if (SKIP_BLANKS_PE == 0) { |
5957 | 463 | xmlFatalErrMsg(ctxt, XML_ERR_SPACE_REQUIRED, |
5958 | 463 | "Space required after '#FIXED'\n"); |
5959 | 463 | } |
5960 | 8.63k | } |
5961 | 69.0k | ret = xmlParseAttValue(ctxt); |
5962 | 69.0k | if (ret == NULL) { |
5963 | 8.77k | xmlFatalErrMsg(ctxt, (xmlParserErrors)ctxt->errNo, |
5964 | 8.77k | "Attribute default value declaration error\n"); |
5965 | 8.77k | } else |
5966 | 60.2k | *value = ret; |
5967 | 69.0k | return(val); |
5968 | 103k | } |
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 | 1.01k | xmlParseNotationType(xmlParserCtxtPtr ctxt) { |
5991 | 1.01k | const xmlChar *name; |
5992 | 1.01k | xmlEnumerationPtr ret = NULL, last = NULL, cur, tmp; |
5993 | | |
5994 | 1.01k | if (RAW != '(') { |
5995 | 264 | xmlFatalErr(ctxt, XML_ERR_NOTATION_NOT_STARTED, NULL); |
5996 | 264 | return(NULL); |
5997 | 264 | } |
5998 | 2.85k | do { |
5999 | 2.85k | NEXT; |
6000 | 2.85k | SKIP_BLANKS_PE; |
6001 | 2.85k | name = xmlParseName(ctxt); |
6002 | 2.85k | if (name == NULL) { |
6003 | 224 | xmlFatalErrMsg(ctxt, XML_ERR_NAME_REQUIRED, |
6004 | 224 | "Name expected in NOTATION declaration\n"); |
6005 | 224 | xmlFreeEnumeration(ret); |
6006 | 224 | return(NULL); |
6007 | 224 | } |
6008 | 2.62k | 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 | 2.62k | if (tmp == NULL) { |
6026 | 2.62k | cur = xmlCreateEnumeration(name); |
6027 | 2.62k | if (cur == NULL) { |
6028 | 1 | xmlErrMemory(ctxt); |
6029 | 1 | xmlFreeEnumeration(ret); |
6030 | 1 | return(NULL); |
6031 | 1 | } |
6032 | 2.62k | if (last == NULL) ret = last = cur; |
6033 | 2.09k | else { |
6034 | 2.09k | last->next = cur; |
6035 | 2.09k | last = cur; |
6036 | 2.09k | } |
6037 | 2.62k | } |
6038 | 2.62k | SKIP_BLANKS_PE; |
6039 | 2.62k | } while (RAW == '|'); |
6040 | 524 | if (RAW != ')') { |
6041 | 300 | xmlFatalErr(ctxt, XML_ERR_NOTATION_NOT_FINISHED, NULL); |
6042 | 300 | xmlFreeEnumeration(ret); |
6043 | 300 | return(NULL); |
6044 | 300 | } |
6045 | 224 | NEXT; |
6046 | 224 | return(ret); |
6047 | 524 | } |
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 | 16.4k | xmlParseEnumerationType(xmlParserCtxtPtr ctxt) { |
6068 | 16.4k | xmlChar *name; |
6069 | 16.4k | xmlEnumerationPtr ret = NULL, last = NULL, cur, tmp; |
6070 | | |
6071 | 16.4k | if (RAW != '(') { |
6072 | 9.80k | xmlFatalErr(ctxt, XML_ERR_ATTLIST_NOT_STARTED, NULL); |
6073 | 9.80k | return(NULL); |
6074 | 9.80k | } |
6075 | 22.9k | do { |
6076 | 22.9k | NEXT; |
6077 | 22.9k | SKIP_BLANKS_PE; |
6078 | 22.9k | name = xmlParseNmtoken(ctxt); |
6079 | 22.9k | if (name == NULL) { |
6080 | 269 | xmlFatalErr(ctxt, XML_ERR_NMTOKEN_REQUIRED, NULL); |
6081 | 269 | return(ret); |
6082 | 269 | } |
6083 | 22.7k | 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 | 22.7k | if (tmp == NULL) { |
6101 | 22.7k | cur = xmlCreateEnumeration(name); |
6102 | 22.7k | if (!xmlDictOwns(ctxt->dict, name)) |
6103 | 22.7k | xmlFree(name); |
6104 | 22.7k | if (cur == NULL) { |
6105 | 3 | xmlErrMemory(ctxt); |
6106 | 3 | xmlFreeEnumeration(ret); |
6107 | 3 | return(NULL); |
6108 | 3 | } |
6109 | 22.6k | if (last == NULL) ret = last = cur; |
6110 | 16.3k | else { |
6111 | 16.3k | last->next = cur; |
6112 | 16.3k | last = cur; |
6113 | 16.3k | } |
6114 | 22.6k | } |
6115 | 22.6k | SKIP_BLANKS_PE; |
6116 | 22.6k | } while (RAW == '|'); |
6117 | 6.36k | if (RAW != ')') { |
6118 | 936 | xmlFatalErr(ctxt, XML_ERR_ATTLIST_NOT_FINISHED, NULL); |
6119 | 936 | return(ret); |
6120 | 936 | } |
6121 | 5.42k | NEXT; |
6122 | 5.42k | return(ret); |
6123 | 6.36k | } |
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 | 17.7k | xmlParseEnumeratedType(xmlParserCtxtPtr ctxt, xmlEnumerationPtr *tree) { |
6144 | 17.7k | if (CMP8(CUR_PTR, 'N', 'O', 'T', 'A', 'T', 'I', 'O', 'N')) { |
6145 | 1.36k | SKIP(8); |
6146 | 1.36k | if (SKIP_BLANKS_PE == 0) { |
6147 | 348 | xmlFatalErrMsg(ctxt, XML_ERR_SPACE_REQUIRED, |
6148 | 348 | "Space required after 'NOTATION'\n"); |
6149 | 348 | return(0); |
6150 | 348 | } |
6151 | 1.01k | *tree = xmlParseNotationType(ctxt); |
6152 | 1.01k | if (*tree == NULL) return(0); |
6153 | 224 | return(XML_ATTRIBUTE_NOTATION); |
6154 | 1.01k | } |
6155 | 16.4k | *tree = xmlParseEnumerationType(ctxt); |
6156 | 16.4k | if (*tree == NULL) return(0); |
6157 | 6.37k | return(XML_ATTRIBUTE_ENUMERATION); |
6158 | 16.4k | } |
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 | 123k | xmlParseAttributeType(xmlParserCtxtPtr ctxt, xmlEnumerationPtr *tree) { |
6209 | 123k | if (CMP5(CUR_PTR, 'C', 'D', 'A', 'T', 'A')) { |
6210 | 30.1k | SKIP(5); |
6211 | 30.1k | return(XML_ATTRIBUTE_CDATA); |
6212 | 93.1k | } else if (CMP6(CUR_PTR, 'I', 'D', 'R', 'E', 'F', 'S')) { |
6213 | 308 | SKIP(6); |
6214 | 308 | return(XML_ATTRIBUTE_IDREFS); |
6215 | 92.8k | } else if (CMP5(CUR_PTR, 'I', 'D', 'R', 'E', 'F')) { |
6216 | 2.20k | SKIP(5); |
6217 | 2.20k | return(XML_ATTRIBUTE_IDREF); |
6218 | 90.6k | } else if ((RAW == 'I') && (NXT(1) == 'D')) { |
6219 | 58.2k | SKIP(2); |
6220 | 58.2k | return(XML_ATTRIBUTE_ID); |
6221 | 58.2k | } else if (CMP6(CUR_PTR, 'E', 'N', 'T', 'I', 'T', 'Y')) { |
6222 | 299 | SKIP(6); |
6223 | 299 | return(XML_ATTRIBUTE_ENTITY); |
6224 | 32.1k | } else if (CMP8(CUR_PTR, 'E', 'N', 'T', 'I', 'T', 'I', 'E', 'S')) { |
6225 | 962 | SKIP(8); |
6226 | 962 | return(XML_ATTRIBUTE_ENTITIES); |
6227 | 31.1k | } else if (CMP8(CUR_PTR, 'N', 'M', 'T', 'O', 'K', 'E', 'N', 'S')) { |
6228 | 9.68k | SKIP(8); |
6229 | 9.68k | return(XML_ATTRIBUTE_NMTOKENS); |
6230 | 21.4k | } else if (CMP7(CUR_PTR, 'N', 'M', 'T', 'O', 'K', 'E', 'N')) { |
6231 | 3.68k | SKIP(7); |
6232 | 3.68k | return(XML_ATTRIBUTE_NMTOKEN); |
6233 | 3.68k | } |
6234 | 17.7k | return(xmlParseEnumeratedType(ctxt, tree)); |
6235 | 123k | } |
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 | 65.5k | xmlParseAttributeListDecl(xmlParserCtxtPtr ctxt) { |
6252 | 65.5k | const xmlChar *elemName; |
6253 | 65.5k | const xmlChar *attrName; |
6254 | 65.5k | xmlEnumerationPtr tree; |
6255 | | |
6256 | 65.5k | if ((CUR != '<') || (NXT(1) != '!')) |
6257 | 0 | return; |
6258 | 65.5k | SKIP(2); |
6259 | | |
6260 | 65.5k | if (CMP7(CUR_PTR, 'A', 'T', 'T', 'L', 'I', 'S', 'T')) { |
6261 | 63.1k | int inputid = ctxt->input->id; |
6262 | | |
6263 | 63.1k | SKIP(7); |
6264 | 63.1k | if (SKIP_BLANKS_PE == 0) { |
6265 | 1.32k | xmlFatalErrMsg(ctxt, XML_ERR_SPACE_REQUIRED, |
6266 | 1.32k | "Space required after '<!ATTLIST'\n"); |
6267 | 1.32k | } |
6268 | 63.1k | elemName = xmlParseName(ctxt); |
6269 | 63.1k | if (elemName == NULL) { |
6270 | 614 | xmlFatalErrMsg(ctxt, XML_ERR_NAME_REQUIRED, |
6271 | 614 | "ATTLIST: no name for Element\n"); |
6272 | 614 | return; |
6273 | 614 | } |
6274 | 62.5k | SKIP_BLANKS_PE; |
6275 | 62.5k | GROW; |
6276 | 158k | while ((RAW != '>') && (PARSER_STOPPED(ctxt) == 0)) { |
6277 | 127k | int type; |
6278 | 127k | int def; |
6279 | 127k | xmlChar *defaultValue = NULL; |
6280 | | |
6281 | 127k | GROW; |
6282 | 127k | tree = NULL; |
6283 | 127k | attrName = xmlParseName(ctxt); |
6284 | 127k | if (attrName == NULL) { |
6285 | 1.85k | xmlFatalErrMsg(ctxt, XML_ERR_NAME_REQUIRED, |
6286 | 1.85k | "ATTLIST: no name for Attribute\n"); |
6287 | 1.85k | break; |
6288 | 1.85k | } |
6289 | 125k | GROW; |
6290 | 125k | if (SKIP_BLANKS_PE == 0) { |
6291 | 2.40k | xmlFatalErrMsg(ctxt, XML_ERR_SPACE_REQUIRED, |
6292 | 2.40k | "Space required after the attribute name\n"); |
6293 | 2.40k | break; |
6294 | 2.40k | } |
6295 | | |
6296 | 123k | type = xmlParseAttributeType(ctxt, &tree); |
6297 | 123k | if (type <= 0) { |
6298 | 11.2k | break; |
6299 | 11.2k | } |
6300 | | |
6301 | 112k | GROW; |
6302 | 112k | if (SKIP_BLANKS_PE == 0) { |
6303 | 6.60k | xmlFatalErrMsg(ctxt, XML_ERR_SPACE_REQUIRED, |
6304 | 6.60k | "Space required after the attribute type\n"); |
6305 | 6.60k | if (tree != NULL) |
6306 | 1.05k | xmlFreeEnumeration(tree); |
6307 | 6.60k | break; |
6308 | 6.60k | } |
6309 | | |
6310 | 105k | def = xmlParseDefaultDecl(ctxt, &defaultValue); |
6311 | 105k | 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 | 105k | if ((type != XML_ATTRIBUTE_CDATA) && (defaultValue != NULL)) |
6319 | 48.9k | xmlAttrNormalizeSpace(defaultValue, defaultValue); |
6320 | | |
6321 | 105k | GROW; |
6322 | 105k | if (RAW != '>') { |
6323 | 92.5k | if (SKIP_BLANKS_PE == 0) { |
6324 | 9.20k | xmlFatalErrMsg(ctxt, XML_ERR_SPACE_REQUIRED, |
6325 | 9.20k | "Space required after the attribute default value\n"); |
6326 | 9.20k | if (defaultValue != NULL) |
6327 | 526 | xmlFree(defaultValue); |
6328 | 9.20k | if (tree != NULL) |
6329 | 272 | xmlFreeEnumeration(tree); |
6330 | 9.20k | break; |
6331 | 9.20k | } |
6332 | 92.5k | } |
6333 | 96.2k | if ((ctxt->sax != NULL) && (!ctxt->disableSAX) && |
6334 | 96.2k | (ctxt->sax->attributeDecl != NULL)) |
6335 | 50.1k | ctxt->sax->attributeDecl(ctxt->userData, elemName, attrName, |
6336 | 50.1k | type, def, defaultValue, tree); |
6337 | 46.0k | else if (tree != NULL) |
6338 | 1.83k | xmlFreeEnumeration(tree); |
6339 | | |
6340 | 96.2k | if ((ctxt->sax2) && (defaultValue != NULL) && |
6341 | 96.2k | (def != XML_ATTRIBUTE_IMPLIED) && |
6342 | 96.2k | (def != XML_ATTRIBUTE_REQUIRED)) { |
6343 | 59.7k | xmlAddDefAttrs(ctxt, elemName, attrName, defaultValue); |
6344 | 59.7k | } |
6345 | 96.2k | if (ctxt->sax2) { |
6346 | 96.2k | xmlAddSpecialAttr(ctxt, elemName, attrName, type); |
6347 | 96.2k | } |
6348 | 96.2k | if (defaultValue != NULL) |
6349 | 59.7k | xmlFree(defaultValue); |
6350 | 96.2k | GROW; |
6351 | 96.2k | } |
6352 | 62.5k | if (RAW == '>') { |
6353 | 32.3k | if (inputid != ctxt->input->id) { |
6354 | 261 | xmlFatalErrMsg(ctxt, XML_ERR_ENTITY_BOUNDARY, |
6355 | 261 | "Attribute list declaration doesn't start and" |
6356 | 261 | " stop in the same entity\n"); |
6357 | 261 | } |
6358 | 32.3k | NEXT; |
6359 | 32.3k | } |
6360 | 62.5k | } |
6361 | 65.5k | } |
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 | 11.4k | xmlParseElementMixedContentDecl(xmlParserCtxtPtr ctxt, int inputchk) { |
6386 | 11.4k | xmlElementContentPtr ret = NULL, cur = NULL, n; |
6387 | 11.4k | const xmlChar *elem = NULL; |
6388 | | |
6389 | 11.4k | GROW; |
6390 | 11.4k | if (CMP7(CUR_PTR, '#', 'P', 'C', 'D', 'A', 'T', 'A')) { |
6391 | 11.4k | SKIP(7); |
6392 | 11.4k | SKIP_BLANKS_PE; |
6393 | 11.4k | if (RAW == ')') { |
6394 | 8.15k | if (ctxt->input->id != inputchk) { |
6395 | 2 | xmlFatalErrMsg(ctxt, XML_ERR_ENTITY_BOUNDARY, |
6396 | 2 | "Element content declaration doesn't start and" |
6397 | 2 | " stop in the same entity\n"); |
6398 | 2 | } |
6399 | 8.15k | NEXT; |
6400 | 8.15k | ret = xmlNewDocElementContent(ctxt->myDoc, NULL, XML_ELEMENT_CONTENT_PCDATA); |
6401 | 8.15k | if (ret == NULL) |
6402 | 1 | goto mem_error; |
6403 | 8.15k | if (RAW == '*') { |
6404 | 433 | ret->ocur = XML_ELEMENT_CONTENT_MULT; |
6405 | 433 | NEXT; |
6406 | 433 | } |
6407 | 8.15k | return(ret); |
6408 | 8.15k | } |
6409 | 3.28k | if ((RAW == '(') || (RAW == '|')) { |
6410 | 2.73k | ret = cur = xmlNewDocElementContent(ctxt->myDoc, NULL, XML_ELEMENT_CONTENT_PCDATA); |
6411 | 2.73k | if (ret == NULL) |
6412 | 1 | goto mem_error; |
6413 | 2.73k | } |
6414 | 7.24k | while ((RAW == '|') && (PARSER_STOPPED(ctxt) == 0)) { |
6415 | 4.34k | NEXT; |
6416 | 4.34k | n = xmlNewDocElementContent(ctxt->myDoc, NULL, XML_ELEMENT_CONTENT_OR); |
6417 | 4.34k | if (n == NULL) |
6418 | 1 | goto mem_error; |
6419 | 4.33k | if (elem == NULL) { |
6420 | 2.47k | n->c1 = cur; |
6421 | 2.47k | if (cur != NULL) |
6422 | 2.47k | cur->parent = n; |
6423 | 2.47k | ret = cur = n; |
6424 | 2.47k | } else { |
6425 | 1.86k | cur->c2 = n; |
6426 | 1.86k | n->parent = cur; |
6427 | 1.86k | n->c1 = xmlNewDocElementContent(ctxt->myDoc, elem, XML_ELEMENT_CONTENT_ELEMENT); |
6428 | 1.86k | if (n->c1 == NULL) |
6429 | 0 | goto mem_error; |
6430 | 1.86k | n->c1->parent = n; |
6431 | 1.86k | cur = n; |
6432 | 1.86k | } |
6433 | 4.33k | SKIP_BLANKS_PE; |
6434 | 4.33k | elem = xmlParseName(ctxt); |
6435 | 4.33k | if (elem == NULL) { |
6436 | 380 | xmlFatalErrMsg(ctxt, XML_ERR_NAME_REQUIRED, |
6437 | 380 | "xmlParseElementMixedContentDecl : Name expected\n"); |
6438 | 380 | xmlFreeDocElementContent(ctxt->myDoc, ret); |
6439 | 380 | return(NULL); |
6440 | 380 | } |
6441 | 3.95k | SKIP_BLANKS_PE; |
6442 | 3.95k | GROW; |
6443 | 3.95k | } |
6444 | 2.90k | if ((RAW == ')') && (NXT(1) == '*')) { |
6445 | 1.26k | if (elem != NULL) { |
6446 | 1.26k | cur->c2 = xmlNewDocElementContent(ctxt->myDoc, elem, |
6447 | 1.26k | XML_ELEMENT_CONTENT_ELEMENT); |
6448 | 1.26k | if (cur->c2 == NULL) |
6449 | 2 | goto mem_error; |
6450 | 1.26k | cur->c2->parent = cur; |
6451 | 1.26k | } |
6452 | 1.26k | if (ret != NULL) |
6453 | 1.26k | ret->ocur = XML_ELEMENT_CONTENT_MULT; |
6454 | 1.26k | 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 | 1.26k | SKIP(2); |
6460 | 1.64k | } else { |
6461 | 1.64k | xmlFreeDocElementContent(ctxt->myDoc, ret); |
6462 | 1.64k | xmlFatalErr(ctxt, XML_ERR_MIXED_NOT_STARTED, NULL); |
6463 | 1.64k | return(NULL); |
6464 | 1.64k | } |
6465 | | |
6466 | 2.90k | } else { |
6467 | 0 | xmlFatalErr(ctxt, XML_ERR_PCDATA_REQUIRED, NULL); |
6468 | 0 | } |
6469 | 1.26k | return(ret); |
6470 | | |
6471 | 5 | mem_error: |
6472 | 5 | xmlErrMemory(ctxt); |
6473 | 5 | xmlFreeDocElementContent(ctxt->myDoc, ret); |
6474 | 5 | return(NULL); |
6475 | 11.4k | } |
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 | 122k | int depth) { |
6512 | 122k | int maxDepth = (ctxt->options & XML_PARSE_HUGE) ? 2048 : 256; |
6513 | 122k | xmlElementContentPtr ret = NULL, cur = NULL, last = NULL, op = NULL; |
6514 | 122k | const xmlChar *elem; |
6515 | 122k | xmlChar type = 0; |
6516 | | |
6517 | 122k | if (depth > maxDepth) { |
6518 | 216 | xmlFatalErrMsgInt(ctxt, XML_ERR_RESOURCE_LIMIT, |
6519 | 216 | "xmlParseElementChildrenContentDecl : depth %d too deep, " |
6520 | 216 | "use XML_PARSE_HUGE\n", depth); |
6521 | 216 | return(NULL); |
6522 | 216 | } |
6523 | 122k | SKIP_BLANKS_PE; |
6524 | 122k | GROW; |
6525 | 122k | if (RAW == '(') { |
6526 | 78.8k | int inputid = ctxt->input->id; |
6527 | | |
6528 | | /* Recurse on first child */ |
6529 | 78.8k | NEXT; |
6530 | 78.8k | SKIP_BLANKS_PE; |
6531 | 78.8k | cur = ret = xmlParseElementChildrenContentDeclPriv(ctxt, inputid, |
6532 | 78.8k | depth + 1); |
6533 | 78.8k | if (cur == NULL) |
6534 | 71.8k | return(NULL); |
6535 | 7.01k | SKIP_BLANKS_PE; |
6536 | 7.01k | GROW; |
6537 | 43.2k | } else { |
6538 | 43.2k | elem = xmlParseName(ctxt); |
6539 | 43.2k | if (elem == NULL) { |
6540 | 2.35k | xmlFatalErr(ctxt, XML_ERR_ELEMCONTENT_NOT_STARTED, NULL); |
6541 | 2.35k | return(NULL); |
6542 | 2.35k | } |
6543 | 40.9k | cur = ret = xmlNewDocElementContent(ctxt->myDoc, elem, XML_ELEMENT_CONTENT_ELEMENT); |
6544 | 40.9k | if (cur == NULL) { |
6545 | 5 | xmlErrMemory(ctxt); |
6546 | 5 | return(NULL); |
6547 | 5 | } |
6548 | 40.9k | GROW; |
6549 | 40.9k | if (RAW == '?') { |
6550 | 4.16k | cur->ocur = XML_ELEMENT_CONTENT_OPT; |
6551 | 4.16k | NEXT; |
6552 | 36.7k | } else if (RAW == '*') { |
6553 | 3.26k | cur->ocur = XML_ELEMENT_CONTENT_MULT; |
6554 | 3.26k | NEXT; |
6555 | 33.4k | } else if (RAW == '+') { |
6556 | 606 | cur->ocur = XML_ELEMENT_CONTENT_PLUS; |
6557 | 606 | NEXT; |
6558 | 32.8k | } else { |
6559 | 32.8k | cur->ocur = XML_ELEMENT_CONTENT_ONCE; |
6560 | 32.8k | } |
6561 | 40.9k | GROW; |
6562 | 40.9k | } |
6563 | 47.9k | SKIP_BLANKS_PE; |
6564 | 95.4k | while ((RAW != ')') && (PARSER_STOPPED(ctxt) == 0)) { |
6565 | | /* |
6566 | | * Each loop we parse one separator and one element. |
6567 | | */ |
6568 | 54.6k | if (RAW == ',') { |
6569 | 35.0k | if (type == 0) type = CUR; |
6570 | | |
6571 | | /* |
6572 | | * Detect "Name | Name , Name" error |
6573 | | */ |
6574 | 23.0k | else if (type != CUR) { |
6575 | 227 | xmlFatalErrMsgInt(ctxt, XML_ERR_SEPARATOR_REQUIRED, |
6576 | 227 | "xmlParseElementChildrenContentDecl : '%c' expected\n", |
6577 | 227 | type); |
6578 | 227 | if ((last != NULL) && (last != ret)) |
6579 | 227 | xmlFreeDocElementContent(ctxt->myDoc, last); |
6580 | 227 | if (ret != NULL) |
6581 | 227 | xmlFreeDocElementContent(ctxt->myDoc, ret); |
6582 | 227 | return(NULL); |
6583 | 227 | } |
6584 | 34.8k | NEXT; |
6585 | | |
6586 | 34.8k | op = xmlNewDocElementContent(ctxt->myDoc, NULL, XML_ELEMENT_CONTENT_SEQ); |
6587 | 34.8k | if (op == NULL) { |
6588 | 1 | xmlErrMemory(ctxt); |
6589 | 1 | if ((last != NULL) && (last != ret)) |
6590 | 1 | xmlFreeDocElementContent(ctxt->myDoc, last); |
6591 | 1 | xmlFreeDocElementContent(ctxt->myDoc, ret); |
6592 | 1 | return(NULL); |
6593 | 1 | } |
6594 | 34.8k | if (last == NULL) { |
6595 | 12.0k | op->c1 = ret; |
6596 | 12.0k | if (ret != NULL) |
6597 | 12.0k | ret->parent = op; |
6598 | 12.0k | ret = cur = op; |
6599 | 22.8k | } else { |
6600 | 22.8k | cur->c2 = op; |
6601 | 22.8k | if (op != NULL) |
6602 | 22.8k | op->parent = cur; |
6603 | 22.8k | op->c1 = last; |
6604 | 22.8k | if (last != NULL) |
6605 | 22.8k | last->parent = op; |
6606 | 22.8k | cur =op; |
6607 | 22.8k | last = NULL; |
6608 | 22.8k | } |
6609 | 34.8k | } else if (RAW == '|') { |
6610 | 16.9k | if (type == 0) type = CUR; |
6611 | | |
6612 | | /* |
6613 | | * Detect "Name , Name | Name" error |
6614 | | */ |
6615 | 5.14k | else if (type != CUR) { |
6616 | 302 | xmlFatalErrMsgInt(ctxt, XML_ERR_SEPARATOR_REQUIRED, |
6617 | 302 | "xmlParseElementChildrenContentDecl : '%c' expected\n", |
6618 | 302 | type); |
6619 | 302 | if ((last != NULL) && (last != ret)) |
6620 | 302 | xmlFreeDocElementContent(ctxt->myDoc, last); |
6621 | 302 | if (ret != NULL) |
6622 | 302 | xmlFreeDocElementContent(ctxt->myDoc, ret); |
6623 | 302 | return(NULL); |
6624 | 302 | } |
6625 | 16.6k | NEXT; |
6626 | | |
6627 | 16.6k | op = xmlNewDocElementContent(ctxt->myDoc, NULL, XML_ELEMENT_CONTENT_OR); |
6628 | 16.6k | if (op == NULL) { |
6629 | 1 | xmlErrMemory(ctxt); |
6630 | 1 | if ((last != NULL) && (last != ret)) |
6631 | 0 | xmlFreeDocElementContent(ctxt->myDoc, last); |
6632 | 1 | if (ret != NULL) |
6633 | 1 | xmlFreeDocElementContent(ctxt->myDoc, ret); |
6634 | 1 | return(NULL); |
6635 | 1 | } |
6636 | 16.6k | if (last == NULL) { |
6637 | 11.8k | op->c1 = ret; |
6638 | 11.8k | if (ret != NULL) |
6639 | 11.8k | ret->parent = op; |
6640 | 11.8k | ret = cur = op; |
6641 | 11.8k | } else { |
6642 | 4.84k | cur->c2 = op; |
6643 | 4.84k | if (op != NULL) |
6644 | 4.84k | op->parent = cur; |
6645 | 4.84k | op->c1 = last; |
6646 | 4.84k | if (last != NULL) |
6647 | 4.84k | last->parent = op; |
6648 | 4.84k | cur =op; |
6649 | 4.84k | last = NULL; |
6650 | 4.84k | } |
6651 | 16.6k | } else { |
6652 | 2.65k | xmlFatalErr(ctxt, XML_ERR_ELEMCONTENT_NOT_FINISHED, NULL); |
6653 | 2.65k | if ((last != NULL) && (last != ret)) |
6654 | 1.03k | xmlFreeDocElementContent(ctxt->myDoc, last); |
6655 | 2.65k | if (ret != NULL) |
6656 | 2.65k | xmlFreeDocElementContent(ctxt->myDoc, ret); |
6657 | 2.65k | return(NULL); |
6658 | 2.65k | } |
6659 | 51.4k | GROW; |
6660 | 51.4k | SKIP_BLANKS_PE; |
6661 | 51.4k | GROW; |
6662 | 51.4k | if (RAW == '(') { |
6663 | 8.74k | int inputid = ctxt->input->id; |
6664 | | /* Recurse on second child */ |
6665 | 8.74k | NEXT; |
6666 | 8.74k | SKIP_BLANKS_PE; |
6667 | 8.74k | last = xmlParseElementChildrenContentDeclPriv(ctxt, inputid, |
6668 | 8.74k | depth + 1); |
6669 | 8.74k | if (last == NULL) { |
6670 | 3.44k | if (ret != NULL) |
6671 | 3.44k | xmlFreeDocElementContent(ctxt->myDoc, ret); |
6672 | 3.44k | return(NULL); |
6673 | 3.44k | } |
6674 | 5.30k | SKIP_BLANKS_PE; |
6675 | 42.7k | } else { |
6676 | 42.7k | elem = xmlParseName(ctxt); |
6677 | 42.7k | if (elem == NULL) { |
6678 | 494 | xmlFatalErr(ctxt, XML_ERR_ELEMCONTENT_NOT_STARTED, NULL); |
6679 | 494 | if (ret != NULL) |
6680 | 494 | xmlFreeDocElementContent(ctxt->myDoc, ret); |
6681 | 494 | return(NULL); |
6682 | 494 | } |
6683 | 42.2k | last = xmlNewDocElementContent(ctxt->myDoc, elem, XML_ELEMENT_CONTENT_ELEMENT); |
6684 | 42.2k | if (last == NULL) { |
6685 | 4 | xmlErrMemory(ctxt); |
6686 | 4 | if (ret != NULL) |
6687 | 4 | xmlFreeDocElementContent(ctxt->myDoc, ret); |
6688 | 4 | return(NULL); |
6689 | 4 | } |
6690 | 42.2k | if (RAW == '?') { |
6691 | 15.9k | last->ocur = XML_ELEMENT_CONTENT_OPT; |
6692 | 15.9k | NEXT; |
6693 | 26.3k | } else if (RAW == '*') { |
6694 | 9.86k | last->ocur = XML_ELEMENT_CONTENT_MULT; |
6695 | 9.86k | NEXT; |
6696 | 16.4k | } else if (RAW == '+') { |
6697 | 290 | last->ocur = XML_ELEMENT_CONTENT_PLUS; |
6698 | 290 | NEXT; |
6699 | 16.1k | } else { |
6700 | 16.1k | last->ocur = XML_ELEMENT_CONTENT_ONCE; |
6701 | 16.1k | } |
6702 | 42.2k | } |
6703 | 47.5k | SKIP_BLANKS_PE; |
6704 | 47.5k | GROW; |
6705 | 47.5k | } |
6706 | 40.8k | if ((cur != NULL) && (last != NULL)) { |
6707 | 18.3k | cur->c2 = last; |
6708 | 18.3k | if (last != NULL) |
6709 | 18.3k | last->parent = cur; |
6710 | 18.3k | } |
6711 | 40.8k | if (ctxt->input->id != inputchk) { |
6712 | 1 | xmlFatalErrMsg(ctxt, XML_ERR_ENTITY_BOUNDARY, |
6713 | 1 | "Element content declaration doesn't start and stop in" |
6714 | 1 | " the same entity\n"); |
6715 | 1 | } |
6716 | 40.8k | NEXT; |
6717 | 40.8k | if (RAW == '?') { |
6718 | 1.41k | if (ret != NULL) { |
6719 | 1.41k | if ((ret->ocur == XML_ELEMENT_CONTENT_PLUS) || |
6720 | 1.41k | (ret->ocur == XML_ELEMENT_CONTENT_MULT)) |
6721 | 442 | ret->ocur = XML_ELEMENT_CONTENT_MULT; |
6722 | 974 | else |
6723 | 974 | ret->ocur = XML_ELEMENT_CONTENT_OPT; |
6724 | 1.41k | } |
6725 | 1.41k | NEXT; |
6726 | 39.3k | } else if (RAW == '*') { |
6727 | 5.96k | if (ret != NULL) { |
6728 | 5.96k | ret->ocur = XML_ELEMENT_CONTENT_MULT; |
6729 | 5.96k | cur = ret; |
6730 | | /* |
6731 | | * Some normalization: |
6732 | | * (a | b* | c?)* == (a | b | c)* |
6733 | | */ |
6734 | 14.0k | while ((cur != NULL) && (cur->type == XML_ELEMENT_CONTENT_OR)) { |
6735 | 8.09k | if ((cur->c1 != NULL) && |
6736 | 8.09k | ((cur->c1->ocur == XML_ELEMENT_CONTENT_OPT) || |
6737 | 8.09k | (cur->c1->ocur == XML_ELEMENT_CONTENT_MULT))) |
6738 | 460 | cur->c1->ocur = XML_ELEMENT_CONTENT_ONCE; |
6739 | 8.09k | if ((cur->c2 != NULL) && |
6740 | 8.09k | ((cur->c2->ocur == XML_ELEMENT_CONTENT_OPT) || |
6741 | 8.09k | (cur->c2->ocur == XML_ELEMENT_CONTENT_MULT))) |
6742 | 1.25k | cur->c2->ocur = XML_ELEMENT_CONTENT_ONCE; |
6743 | 8.09k | cur = cur->c2; |
6744 | 8.09k | } |
6745 | 5.96k | } |
6746 | 5.96k | NEXT; |
6747 | 33.4k | } else if (RAW == '+') { |
6748 | 2.73k | if (ret != NULL) { |
6749 | 2.73k | int found = 0; |
6750 | | |
6751 | 2.73k | if ((ret->ocur == XML_ELEMENT_CONTENT_OPT) || |
6752 | 2.73k | (ret->ocur == XML_ELEMENT_CONTENT_MULT)) |
6753 | 315 | ret->ocur = XML_ELEMENT_CONTENT_MULT; |
6754 | 2.41k | else |
6755 | 2.41k | ret->ocur = XML_ELEMENT_CONTENT_PLUS; |
6756 | | /* |
6757 | | * Some normalization: |
6758 | | * (a | b*)+ == (a | b)* |
6759 | | * (a | b?)+ == (a | b)* |
6760 | | */ |
6761 | 7.78k | while ((cur != NULL) && (cur->type == XML_ELEMENT_CONTENT_OR)) { |
6762 | 5.05k | if ((cur->c1 != NULL) && |
6763 | 5.05k | ((cur->c1->ocur == XML_ELEMENT_CONTENT_OPT) || |
6764 | 5.05k | (cur->c1->ocur == XML_ELEMENT_CONTENT_MULT))) { |
6765 | 1.25k | cur->c1->ocur = XML_ELEMENT_CONTENT_ONCE; |
6766 | 1.25k | found = 1; |
6767 | 1.25k | } |
6768 | 5.05k | if ((cur->c2 != NULL) && |
6769 | 5.05k | ((cur->c2->ocur == XML_ELEMENT_CONTENT_OPT) || |
6770 | 5.05k | (cur->c2->ocur == XML_ELEMENT_CONTENT_MULT))) { |
6771 | 937 | cur->c2->ocur = XML_ELEMENT_CONTENT_ONCE; |
6772 | 937 | found = 1; |
6773 | 937 | } |
6774 | 5.05k | cur = cur->c2; |
6775 | 5.05k | } |
6776 | 2.73k | if (found) |
6777 | 1.59k | ret->ocur = XML_ELEMENT_CONTENT_MULT; |
6778 | 2.73k | } |
6779 | 2.73k | NEXT; |
6780 | 2.73k | } |
6781 | 40.8k | return(ret); |
6782 | 47.9k | } |
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 | 46.1k | xmlElementContentPtr *result) { |
6841 | | |
6842 | 46.1k | xmlElementContentPtr tree = NULL; |
6843 | 46.1k | int inputid = ctxt->input->id; |
6844 | 46.1k | int res; |
6845 | | |
6846 | 46.1k | *result = NULL; |
6847 | | |
6848 | 46.1k | 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 | 46.1k | NEXT; |
6854 | 46.1k | GROW; |
6855 | 46.1k | SKIP_BLANKS_PE; |
6856 | 46.1k | if (CMP7(CUR_PTR, '#', 'P', 'C', 'D', 'A', 'T', 'A')) { |
6857 | 11.4k | tree = xmlParseElementMixedContentDecl(ctxt, inputid); |
6858 | 11.4k | res = XML_ELEMENT_TYPE_MIXED; |
6859 | 34.7k | } else { |
6860 | 34.7k | tree = xmlParseElementChildrenContentDeclPriv(ctxt, inputid, 1); |
6861 | 34.7k | res = XML_ELEMENT_TYPE_ELEMENT; |
6862 | 34.7k | } |
6863 | 46.1k | SKIP_BLANKS_PE; |
6864 | 46.1k | *result = tree; |
6865 | 46.1k | return(res); |
6866 | 46.1k | } |
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 | 64.6k | xmlParseElementDecl(xmlParserCtxtPtr ctxt) { |
6885 | 64.6k | const xmlChar *name; |
6886 | 64.6k | int ret = -1; |
6887 | 64.6k | xmlElementContentPtr content = NULL; |
6888 | | |
6889 | 64.6k | if ((CUR != '<') || (NXT(1) != '!')) |
6890 | 0 | return(ret); |
6891 | 64.6k | SKIP(2); |
6892 | | |
6893 | | /* GROW; done in the caller */ |
6894 | 64.6k | if (CMP7(CUR_PTR, 'E', 'L', 'E', 'M', 'E', 'N', 'T')) { |
6895 | 62.9k | int inputid = ctxt->input->id; |
6896 | | |
6897 | 62.9k | SKIP(7); |
6898 | 62.9k | if (SKIP_BLANKS_PE == 0) { |
6899 | 865 | xmlFatalErrMsg(ctxt, XML_ERR_SPACE_REQUIRED, |
6900 | 865 | "Space required after 'ELEMENT'\n"); |
6901 | 865 | return(-1); |
6902 | 865 | } |
6903 | 62.1k | name = xmlParseName(ctxt); |
6904 | 62.1k | if (name == NULL) { |
6905 | 881 | xmlFatalErrMsg(ctxt, XML_ERR_NAME_REQUIRED, |
6906 | 881 | "xmlParseElementDecl: no name for Element\n"); |
6907 | 881 | return(-1); |
6908 | 881 | } |
6909 | 61.2k | if (SKIP_BLANKS_PE == 0) { |
6910 | 3.27k | xmlFatalErrMsg(ctxt, XML_ERR_SPACE_REQUIRED, |
6911 | 3.27k | "Space required after the element name\n"); |
6912 | 3.27k | } |
6913 | 61.2k | if (CMP5(CUR_PTR, 'E', 'M', 'P', 'T', 'Y')) { |
6914 | 11.3k | SKIP(5); |
6915 | | /* |
6916 | | * Element must always be empty. |
6917 | | */ |
6918 | 11.3k | ret = XML_ELEMENT_TYPE_EMPTY; |
6919 | 49.8k | } else if ((RAW == 'A') && (NXT(1) == 'N') && |
6920 | 49.8k | (NXT(2) == 'Y')) { |
6921 | 412 | SKIP(3); |
6922 | | /* |
6923 | | * Element is a generic container. |
6924 | | */ |
6925 | 412 | ret = XML_ELEMENT_TYPE_ANY; |
6926 | 49.4k | } else if (RAW == '(') { |
6927 | 46.1k | ret = xmlParseElementContentDecl(ctxt, name, &content); |
6928 | 46.1k | } else { |
6929 | | /* |
6930 | | * [ WFC: PEs in Internal Subset ] error handling. |
6931 | | */ |
6932 | 3.28k | xmlFatalErrMsg(ctxt, XML_ERR_ELEMCONTENT_NOT_STARTED, |
6933 | 3.28k | "xmlParseElementDecl: 'EMPTY', 'ANY' or '(' expected\n"); |
6934 | 3.28k | return(-1); |
6935 | 3.28k | } |
6936 | | |
6937 | 57.9k | SKIP_BLANKS_PE; |
6938 | | |
6939 | 57.9k | if (RAW != '>') { |
6940 | 10.6k | xmlFatalErr(ctxt, XML_ERR_GT_REQUIRED, NULL); |
6941 | 10.6k | if (content != NULL) { |
6942 | 1.24k | xmlFreeDocElementContent(ctxt->myDoc, content); |
6943 | 1.24k | } |
6944 | 47.3k | } else { |
6945 | 47.3k | if (inputid != ctxt->input->id) { |
6946 | 48 | xmlFatalErrMsg(ctxt, XML_ERR_ENTITY_BOUNDARY, |
6947 | 48 | "Element declaration doesn't start and stop in" |
6948 | 48 | " the same entity\n"); |
6949 | 48 | } |
6950 | | |
6951 | 47.3k | NEXT; |
6952 | 47.3k | if ((ctxt->sax != NULL) && (!ctxt->disableSAX) && |
6953 | 47.3k | (ctxt->sax->elementDecl != NULL)) { |
6954 | 37.1k | if (content != NULL) |
6955 | 29.4k | content->parent = NULL; |
6956 | 37.1k | ctxt->sax->elementDecl(ctxt->userData, name, ret, |
6957 | 37.1k | content); |
6958 | 37.1k | 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 | 643 | xmlFreeDocElementContent(ctxt->myDoc, content); |
6966 | 643 | } |
6967 | 37.1k | } else if (content != NULL) { |
6968 | 7.19k | xmlFreeDocElementContent(ctxt->myDoc, content); |
6969 | 7.19k | } |
6970 | 47.3k | } |
6971 | 57.9k | } |
6972 | 59.5k | return(ret); |
6973 | 64.6k | } |
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 | 7.07k | xmlParseConditionalSections(xmlParserCtxtPtr ctxt) { |
6990 | 7.07k | int *inputIds = NULL; |
6991 | 7.07k | size_t inputIdsSize = 0; |
6992 | 7.07k | size_t depth = 0; |
6993 | | |
6994 | 13.1k | while (PARSER_STOPPED(ctxt) == 0) { |
6995 | 12.8k | if ((RAW == '<') && (NXT(1) == '!') && (NXT(2) == '[')) { |
6996 | 7.87k | int id = ctxt->input->id; |
6997 | | |
6998 | 7.87k | SKIP(3); |
6999 | 7.87k | SKIP_BLANKS_PE; |
7000 | | |
7001 | 7.87k | if (CMP7(CUR_PTR, 'I', 'N', 'C', 'L', 'U', 'D', 'E')) { |
7002 | 3.68k | SKIP(7); |
7003 | 3.68k | SKIP_BLANKS_PE; |
7004 | 3.68k | if (RAW != '[') { |
7005 | 403 | xmlFatalErr(ctxt, XML_ERR_CONDSEC_INVALID, NULL); |
7006 | 403 | xmlHaltParser(ctxt); |
7007 | 403 | goto error; |
7008 | 403 | } |
7009 | 3.28k | 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 | 3.28k | NEXT; |
7015 | | |
7016 | 3.28k | if (inputIdsSize <= depth) { |
7017 | 3.28k | int *tmp; |
7018 | 3.28k | int newSize; |
7019 | | |
7020 | 3.28k | newSize = xmlGrowCapacity(inputIdsSize, sizeof(tmp[0]), |
7021 | 3.28k | 4, 1000); |
7022 | 3.28k | 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 | 3.28k | tmp = xmlRealloc(inputIds, newSize * sizeof(tmp[0])); |
7029 | 3.28k | if (tmp == NULL) { |
7030 | 0 | xmlErrMemory(ctxt); |
7031 | 0 | goto error; |
7032 | 0 | } |
7033 | 3.28k | inputIds = tmp; |
7034 | 3.28k | inputIdsSize = newSize; |
7035 | 3.28k | } |
7036 | 3.28k | inputIds[depth] = id; |
7037 | 3.28k | depth++; |
7038 | 4.19k | } else if (CMP6(CUR_PTR, 'I', 'G', 'N', 'O', 'R', 'E')) { |
7039 | 1.45k | size_t ignoreDepth = 0; |
7040 | | |
7041 | 1.45k | SKIP(6); |
7042 | 1.45k | SKIP_BLANKS_PE; |
7043 | 1.45k | if (RAW != '[') { |
7044 | 458 | xmlFatalErr(ctxt, XML_ERR_CONDSEC_INVALID, NULL); |
7045 | 458 | xmlHaltParser(ctxt); |
7046 | 458 | goto error; |
7047 | 458 | } |
7048 | 997 | 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 | 997 | NEXT; |
7054 | | |
7055 | 85.3k | while (PARSER_STOPPED(ctxt) == 0) { |
7056 | 85.3k | if (RAW == 0) { |
7057 | 599 | xmlFatalErr(ctxt, XML_ERR_CONDSEC_NOT_FINISHED, NULL); |
7058 | 599 | goto error; |
7059 | 599 | } |
7060 | 84.7k | if ((RAW == '<') && (NXT(1) == '!') && (NXT(2) == '[')) { |
7061 | 1.01k | SKIP(3); |
7062 | 1.01k | ignoreDepth++; |
7063 | | /* Check for integer overflow */ |
7064 | 1.01k | if (ignoreDepth == 0) { |
7065 | 0 | xmlErrMemory(ctxt); |
7066 | 0 | goto error; |
7067 | 0 | } |
7068 | 83.7k | } else if ((RAW == ']') && (NXT(1) == ']') && |
7069 | 83.7k | (NXT(2) == '>')) { |
7070 | 913 | SKIP(3); |
7071 | 913 | if (ignoreDepth == 0) |
7072 | 396 | break; |
7073 | 517 | ignoreDepth--; |
7074 | 82.8k | } else { |
7075 | 82.8k | NEXT; |
7076 | 82.8k | } |
7077 | 84.7k | } |
7078 | | |
7079 | 398 | 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 | 2.74k | } else { |
7085 | 2.74k | xmlFatalErr(ctxt, XML_ERR_CONDSEC_INVALID_KEYWORD, NULL); |
7086 | 2.74k | xmlHaltParser(ctxt); |
7087 | 2.74k | goto error; |
7088 | 2.74k | } |
7089 | 7.87k | } else if ((depth > 0) && |
7090 | 4.99k | (RAW == ']') && (NXT(1) == ']') && (NXT(2) == '>')) { |
7091 | 649 | depth--; |
7092 | 649 | if (ctxt->input->id != inputIds[depth]) { |
7093 | 225 | xmlFatalErrMsg(ctxt, XML_ERR_ENTITY_BOUNDARY, |
7094 | 225 | "All markup of the conditional section is not" |
7095 | 225 | " in the same entity\n"); |
7096 | 225 | } |
7097 | 649 | SKIP(3); |
7098 | 4.34k | } else if ((RAW == '<') && ((NXT(1) == '!') || (NXT(1) == '?'))) { |
7099 | 2.48k | xmlParseMarkupDecl(ctxt); |
7100 | 2.48k | } else { |
7101 | 1.85k | xmlFatalErr(ctxt, XML_ERR_EXT_SUBSET_NOT_FINISHED, NULL); |
7102 | 1.85k | xmlHaltParser(ctxt); |
7103 | 1.85k | goto error; |
7104 | 1.85k | } |
7105 | | |
7106 | 6.81k | if (depth == 0) |
7107 | 700 | break; |
7108 | | |
7109 | 6.11k | SKIP_BLANKS_PE; |
7110 | 6.11k | SHRINK; |
7111 | 6.11k | GROW; |
7112 | 6.11k | } |
7113 | | |
7114 | 7.07k | error: |
7115 | 7.07k | xmlFree(inputIds); |
7116 | 7.07k | } |
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 | 400k | xmlParseMarkupDecl(xmlParserCtxtPtr ctxt) { |
7144 | 400k | GROW; |
7145 | 400k | if (CUR == '<') { |
7146 | 400k | if (NXT(1) == '!') { |
7147 | 390k | switch (NXT(2)) { |
7148 | 263k | case 'E': |
7149 | 263k | if (NXT(3) == 'L') |
7150 | 64.6k | xmlParseElementDecl(ctxt); |
7151 | 198k | else if (NXT(3) == 'N') |
7152 | 197k | xmlParseEntityDecl(ctxt); |
7153 | 1.11k | else |
7154 | 1.11k | SKIP(2); |
7155 | 263k | break; |
7156 | 65.5k | case 'A': |
7157 | 65.5k | xmlParseAttributeListDecl(ctxt); |
7158 | 65.5k | break; |
7159 | 17.7k | case 'N': |
7160 | 17.7k | xmlParseNotationDecl(ctxt); |
7161 | 17.7k | break; |
7162 | 41.8k | case '-': |
7163 | 41.8k | xmlParseComment(ctxt); |
7164 | 41.8k | break; |
7165 | 2.17k | default: |
7166 | 2.17k | xmlFatalErr(ctxt, |
7167 | 2.17k | ctxt->inSubset == 2 ? |
7168 | 601 | XML_ERR_EXT_SUBSET_NOT_FINISHED : |
7169 | 2.17k | XML_ERR_INT_SUBSET_NOT_FINISHED, |
7170 | 2.17k | NULL); |
7171 | 2.17k | SKIP(2); |
7172 | 2.17k | break; |
7173 | 390k | } |
7174 | 390k | } else if (NXT(1) == '?') { |
7175 | 9.91k | xmlParsePI(ctxt); |
7176 | 9.91k | } |
7177 | 400k | } |
7178 | 400k | } |
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 | 20.7k | xmlParseTextDecl(xmlParserCtxtPtr ctxt) { |
7193 | 20.7k | xmlChar *version; |
7194 | | |
7195 | | /* |
7196 | | * We know that '<?xml' is here. |
7197 | | */ |
7198 | 20.7k | if ((CMP5(CUR_PTR, '<', '?', 'x', 'm', 'l')) && (IS_BLANK_CH(NXT(5)))) { |
7199 | 20.2k | SKIP(5); |
7200 | 20.2k | } else { |
7201 | 434 | xmlFatalErr(ctxt, XML_ERR_XMLDECL_NOT_STARTED, NULL); |
7202 | 434 | return; |
7203 | 434 | } |
7204 | | |
7205 | 20.2k | 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 | 20.2k | version = xmlParseVersionInfo(ctxt); |
7214 | 20.2k | if (version == NULL) { |
7215 | 8.59k | version = xmlCharStrdup(XML_DEFAULT_VERSION); |
7216 | 8.59k | if (version == NULL) { |
7217 | 3 | xmlErrMemory(ctxt); |
7218 | 3 | return; |
7219 | 3 | } |
7220 | 11.6k | } else { |
7221 | 11.6k | if (SKIP_BLANKS == 0) { |
7222 | 3.97k | xmlFatalErrMsg(ctxt, XML_ERR_SPACE_REQUIRED, |
7223 | 3.97k | "Space needed here\n"); |
7224 | 3.97k | } |
7225 | 11.6k | } |
7226 | 20.2k | ctxt->input->version = version; |
7227 | | |
7228 | | /* |
7229 | | * We must have the encoding declaration |
7230 | | */ |
7231 | 20.2k | xmlParseEncodingDecl(ctxt); |
7232 | | |
7233 | 20.2k | SKIP_BLANKS; |
7234 | 20.2k | if ((RAW == '?') && (NXT(1) == '>')) { |
7235 | 5.17k | SKIP(2); |
7236 | 15.1k | } else if (RAW == '>') { |
7237 | | /* Deprecated old WD ... */ |
7238 | 322 | xmlFatalErr(ctxt, XML_ERR_XMLDECL_NOT_FINISHED, NULL); |
7239 | 322 | NEXT; |
7240 | 14.7k | } else { |
7241 | 14.7k | int c; |
7242 | | |
7243 | 14.7k | xmlFatalErr(ctxt, XML_ERR_XMLDECL_NOT_FINISHED, NULL); |
7244 | 394k | while ((PARSER_STOPPED(ctxt) == 0) && ((c = CUR) != 0)) { |
7245 | 393k | NEXT; |
7246 | 393k | if (c == '>') |
7247 | 13.6k | break; |
7248 | 393k | } |
7249 | 14.7k | } |
7250 | 20.2k | } |
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 | 13.5k | const xmlChar *SystemID) { |
7269 | 13.5k | int oldInputNr; |
7270 | | |
7271 | 13.5k | xmlCtxtInitializeLate(ctxt); |
7272 | | |
7273 | 13.5k | xmlDetectEncoding(ctxt); |
7274 | | |
7275 | 13.5k | if (CMP5(CUR_PTR, '<', '?', 'x', 'm', 'l')) { |
7276 | 9.12k | xmlParseTextDecl(ctxt); |
7277 | 9.12k | } |
7278 | 13.5k | 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 | 13.5k | if ((ctxt->myDoc != NULL) && (ctxt->myDoc->intSubset == NULL) && |
7287 | 13.5k | (xmlCreateIntSubset(ctxt->myDoc, NULL, ExternalID, SystemID) == NULL)) { |
7288 | 0 | xmlErrMemory(ctxt); |
7289 | 0 | } |
7290 | | |
7291 | 13.5k | ctxt->inSubset = 2; |
7292 | 13.5k | oldInputNr = ctxt->inputNr; |
7293 | | |
7294 | 13.5k | SKIP_BLANKS_PE; |
7295 | 52.1k | while (((RAW != 0) || (ctxt->inputNr > oldInputNr)) && |
7296 | 52.1k | (!PARSER_STOPPED(ctxt))) { |
7297 | 44.0k | GROW; |
7298 | 44.0k | if ((RAW == '<') && (NXT(1) == '!') && (NXT(2) == '[')) { |
7299 | 3.54k | xmlParseConditionalSections(ctxt); |
7300 | 40.4k | } else if ((RAW == '<') && ((NXT(1) == '!') || (NXT(1) == '?'))) { |
7301 | 35.0k | xmlParseMarkupDecl(ctxt); |
7302 | 35.0k | } else { |
7303 | 5.42k | xmlFatalErr(ctxt, XML_ERR_EXT_SUBSET_NOT_FINISHED, NULL); |
7304 | 5.42k | xmlHaltParser(ctxt); |
7305 | 5.42k | return; |
7306 | 5.42k | } |
7307 | 38.5k | SKIP_BLANKS_PE; |
7308 | 38.5k | SHRINK; |
7309 | 38.5k | } |
7310 | | |
7311 | 8.68k | while (ctxt->inputNr > oldInputNr) |
7312 | 592 | xmlPopPE(ctxt); |
7313 | | |
7314 | 8.08k | xmlParserCheckEOF(ctxt, XML_ERR_EXT_SUBSET_NOT_FINISHED); |
7315 | 8.08k | } |
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 | 284k | xmlParseReference(xmlParserCtxtPtr ctxt) { |
7334 | 284k | xmlEntityPtr ent = NULL; |
7335 | 284k | const xmlChar *name; |
7336 | 284k | xmlChar *val; |
7337 | | |
7338 | 284k | if (RAW != '&') |
7339 | 0 | return; |
7340 | | |
7341 | | /* |
7342 | | * Simple case of a CharRef |
7343 | | */ |
7344 | 284k | if (NXT(1) == '#') { |
7345 | 25.6k | int i = 0; |
7346 | 25.6k | xmlChar out[16]; |
7347 | 25.6k | int value = xmlParseCharRef(ctxt); |
7348 | | |
7349 | 25.6k | if (value == 0) |
7350 | 11.7k | return; |
7351 | | |
7352 | | /* |
7353 | | * Just encode the value in UTF-8 |
7354 | | */ |
7355 | 13.9k | COPY_BUF(out, i, value); |
7356 | 13.9k | out[i] = 0; |
7357 | 13.9k | if ((ctxt->sax != NULL) && (ctxt->sax->characters != NULL) && |
7358 | 13.9k | (!ctxt->disableSAX)) |
7359 | 5.34k | ctxt->sax->characters(ctxt->userData, out, i); |
7360 | 13.9k | return; |
7361 | 25.6k | } |
7362 | | |
7363 | | /* |
7364 | | * We are seeing an entity reference |
7365 | | */ |
7366 | 258k | name = xmlParseEntityRefInternal(ctxt); |
7367 | 258k | if (name == NULL) |
7368 | 126k | return; |
7369 | 132k | ent = xmlLookupGeneralEntity(ctxt, name, /* isAttr */ 0); |
7370 | 132k | if (ent == NULL) { |
7371 | | /* |
7372 | | * Create a reference for undeclared entities. |
7373 | | */ |
7374 | 53.7k | if ((ctxt->replaceEntities == 0) && |
7375 | 53.7k | (ctxt->sax != NULL) && |
7376 | 53.7k | (ctxt->disableSAX == 0) && |
7377 | 53.7k | (ctxt->sax->reference != NULL)) { |
7378 | 0 | ctxt->sax->reference(ctxt->userData, name); |
7379 | 0 | } |
7380 | 53.7k | return; |
7381 | 53.7k | } |
7382 | 78.9k | if (!ctxt->wellFormed) |
7383 | 47.0k | return; |
7384 | | |
7385 | | /* special case of predefined entities */ |
7386 | 31.9k | if ((ent->name == NULL) || |
7387 | 31.9k | (ent->etype == XML_INTERNAL_PREDEFINED_ENTITY)) { |
7388 | 19.8k | val = ent->content; |
7389 | 19.8k | if (val == NULL) return; |
7390 | | /* |
7391 | | * inline the entity. |
7392 | | */ |
7393 | 19.8k | if ((ctxt->sax != NULL) && (ctxt->sax->characters != NULL) && |
7394 | 19.8k | (!ctxt->disableSAX)) |
7395 | 19.8k | ctxt->sax->characters(ctxt->userData, val, xmlStrlen(val)); |
7396 | 19.8k | return; |
7397 | 19.8k | } |
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 | 12.0k | 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 | 12.0k | if ((ent->etype == XML_INTERNAL_GENERAL_ENTITY) || |
7448 | 12.0k | (((ctxt->options & XML_PARSE_NO_XXE) == 0) && |
7449 | 10.0k | ((ctxt->replaceEntities) || |
7450 | 12.0k | (ctxt->validate)))) { |
7451 | 12.0k | if ((ent->flags & XML_ENT_PARSED) == 0) { |
7452 | 10.7k | xmlCtxtParseEntity(ctxt, ent); |
7453 | 10.7k | } 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 | 325 | xmlCtxtParseEntity(ctxt, ent); |
7464 | 325 | } |
7465 | 12.0k | } |
7466 | | |
7467 | | /* |
7468 | | * We also check for amplification if entities aren't substituted. |
7469 | | * They might be expanded later. |
7470 | | */ |
7471 | 12.0k | if (xmlParserEntityCheck(ctxt, ent->expandedSize)) |
7472 | 0 | return; |
7473 | | |
7474 | 12.0k | if ((ctxt->sax == NULL) || (ctxt->disableSAX)) |
7475 | 6.56k | return; |
7476 | | |
7477 | 5.46k | if (ctxt->replaceEntities == 0) { |
7478 | | /* |
7479 | | * Create a reference |
7480 | | */ |
7481 | 0 | if (ctxt->sax->reference != NULL) |
7482 | 0 | ctxt->sax->reference(ctxt->userData, ent->name); |
7483 | 5.46k | } else if ((ent->children != NULL) && (ctxt->node != NULL)) { |
7484 | 3.33k | xmlNodePtr copy, cur; |
7485 | | |
7486 | | /* |
7487 | | * Seems we are generating the DOM content, copy the tree |
7488 | | */ |
7489 | 3.33k | cur = ent->children; |
7490 | | |
7491 | | /* |
7492 | | * Handle first text node with SAX to coalesce text efficiently |
7493 | | */ |
7494 | 3.33k | if ((cur->type == XML_TEXT_NODE) || |
7495 | 3.33k | (cur->type == XML_CDATA_SECTION_NODE)) { |
7496 | 1.69k | int len = xmlStrlen(cur->content); |
7497 | | |
7498 | 1.69k | if ((cur->type == XML_TEXT_NODE) || |
7499 | 1.69k | (ctxt->options & XML_PARSE_NOCDATA)) { |
7500 | 1.69k | if (ctxt->sax->characters != NULL) |
7501 | 1.69k | ctxt->sax->characters(ctxt, cur->content, len); |
7502 | 1.69k | } else { |
7503 | 0 | if (ctxt->sax->cdataBlock != NULL) |
7504 | 0 | ctxt->sax->cdataBlock(ctxt, cur->content, len); |
7505 | 0 | } |
7506 | | |
7507 | 1.69k | cur = cur->next; |
7508 | 1.69k | } |
7509 | | |
7510 | 7.43k | while (cur != NULL) { |
7511 | 5.93k | xmlNodePtr last; |
7512 | | |
7513 | | /* |
7514 | | * Handle last text node with SAX to coalesce text efficiently |
7515 | | */ |
7516 | 5.93k | if ((cur->next == NULL) && |
7517 | 5.93k | ((cur->type == XML_TEXT_NODE) || |
7518 | 2.18k | (cur->type == XML_CDATA_SECTION_NODE))) { |
7519 | 1.81k | int len = xmlStrlen(cur->content); |
7520 | | |
7521 | 1.81k | if ((cur->type == XML_TEXT_NODE) || |
7522 | 1.81k | (ctxt->options & XML_PARSE_NOCDATA)) { |
7523 | 1.81k | if (ctxt->sax->characters != NULL) |
7524 | 1.81k | ctxt->sax->characters(ctxt, cur->content, len); |
7525 | 1.81k | } else { |
7526 | 0 | if (ctxt->sax->cdataBlock != NULL) |
7527 | 0 | ctxt->sax->cdataBlock(ctxt, cur->content, len); |
7528 | 0 | } |
7529 | | |
7530 | 1.81k | break; |
7531 | 1.81k | } |
7532 | | |
7533 | | /* |
7534 | | * Reset coalesce buffer stats only for non-text nodes. |
7535 | | */ |
7536 | 4.12k | ctxt->nodemem = 0; |
7537 | 4.12k | ctxt->nodelen = 0; |
7538 | | |
7539 | 4.12k | copy = xmlDocCopyNode(cur, ctxt->myDoc, 1); |
7540 | | |
7541 | 4.12k | if (copy == NULL) { |
7542 | 25 | xmlErrMemory(ctxt); |
7543 | 25 | break; |
7544 | 25 | } |
7545 | | |
7546 | 4.09k | 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 | 4.09k | copy->parent = ctxt->node; |
7554 | 4.09k | last = ctxt->node->last; |
7555 | 4.09k | if (last == NULL) { |
7556 | 225 | ctxt->node->children = copy; |
7557 | 3.87k | } else { |
7558 | 3.87k | last->next = copy; |
7559 | 3.87k | copy->prev = last; |
7560 | 3.87k | } |
7561 | 4.09k | ctxt->node->last = copy; |
7562 | | |
7563 | 4.09k | cur = cur->next; |
7564 | 4.09k | } |
7565 | 3.33k | } |
7566 | 5.46k | } |
7567 | | |
7568 | | static void |
7569 | 386k | 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 | 386k | if ((ctxt->standalone == 1) || |
7592 | 386k | ((ctxt->hasExternalSubset == 0) && |
7593 | 386k | (ctxt->hasPErefs == 0))) { |
7594 | 365k | xmlFatalErrMsgStr(ctxt, XML_ERR_UNDECLARED_ENTITY, |
7595 | 365k | "Entity '%s' not defined\n", name); |
7596 | 365k | } 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 | 20.9k | } else if ((ctxt->loadsubset & ~XML_SKIP_IDS) || |
7607 | 20.9k | ((ctxt->replaceEntities) && |
7608 | 20.9k | ((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 | 20.9k | xmlErrMsgStr(ctxt, XML_WAR_UNDECLARED_ENTITY, |
7618 | 20.9k | "Entity '%s' not defined\n", name); |
7619 | 20.9k | } else { |
7620 | 0 | xmlWarningMsg(ctxt, XML_WAR_UNDECLARED_ENTITY, |
7621 | 0 | "Entity '%s' not defined\n", name, NULL); |
7622 | 0 | } |
7623 | | |
7624 | 386k | ctxt->valid = 0; |
7625 | 386k | } |
7626 | | |
7627 | | static xmlEntityPtr |
7628 | 1.46M | xmlLookupGeneralEntity(xmlParserCtxtPtr ctxt, const xmlChar *name, int inAttr) { |
7629 | 1.46M | xmlEntityPtr ent = NULL; |
7630 | | |
7631 | | /* |
7632 | | * Predefined entities override any extra definition |
7633 | | */ |
7634 | 1.46M | if ((ctxt->options & XML_PARSE_OLDSAX) == 0) { |
7635 | 1.46M | ent = xmlGetPredefinedEntity(name); |
7636 | 1.46M | if (ent != NULL) |
7637 | 133k | return(ent); |
7638 | 1.46M | } |
7639 | | |
7640 | | /* |
7641 | | * Ask first SAX for entity resolution, otherwise try the |
7642 | | * entities which may have stored in the parser context. |
7643 | | */ |
7644 | 1.32M | if (ctxt->sax != NULL) { |
7645 | 1.32M | if (ctxt->sax->getEntity != NULL) |
7646 | 1.32M | ent = ctxt->sax->getEntity(ctxt->userData, name); |
7647 | 1.32M | if ((ctxt->wellFormed == 1 ) && (ent == NULL) && |
7648 | 1.32M | (ctxt->options & XML_PARSE_OLDSAX)) |
7649 | 0 | ent = xmlGetPredefinedEntity(name); |
7650 | 1.32M | if ((ctxt->wellFormed == 1 ) && (ent == NULL) && |
7651 | 1.32M | (ctxt->userData==ctxt)) { |
7652 | 1.10k | ent = xmlSAX2GetEntity(ctxt, name); |
7653 | 1.10k | } |
7654 | 1.32M | } |
7655 | | |
7656 | 1.32M | if (ent == NULL) { |
7657 | 366k | xmlHandleUndeclaredEntity(ctxt, name); |
7658 | 366k | } |
7659 | | |
7660 | | /* |
7661 | | * [ WFC: Parsed Entity ] |
7662 | | * An entity reference must not contain the name of an |
7663 | | * unparsed entity |
7664 | | */ |
7665 | 961k | 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 | 961k | else if (ent->etype == XML_EXTERNAL_GENERAL_PARSED_ENTITY) { |
7677 | 20.0k | if (inAttr) { |
7678 | 1.74k | xmlFatalErrMsgStr(ctxt, XML_ERR_ENTITY_IS_EXTERNAL, |
7679 | 1.74k | "Attribute references external entity '%s'\n", name); |
7680 | 1.74k | ent = NULL; |
7681 | 1.74k | } |
7682 | 20.0k | } |
7683 | | |
7684 | 1.32M | return(ent); |
7685 | 1.46M | } |
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 | 793k | xmlParseEntityRefInternal(xmlParserCtxtPtr ctxt) { |
7700 | 793k | const xmlChar *name; |
7701 | | |
7702 | 793k | GROW; |
7703 | | |
7704 | 793k | if (RAW != '&') |
7705 | 0 | return(NULL); |
7706 | 793k | NEXT; |
7707 | 793k | name = xmlParseName(ctxt); |
7708 | 793k | if (name == NULL) { |
7709 | 173k | xmlFatalErrMsg(ctxt, XML_ERR_NAME_REQUIRED, |
7710 | 173k | "xmlParseEntityRef: no name\n"); |
7711 | 173k | return(NULL); |
7712 | 173k | } |
7713 | 619k | if (RAW != ';') { |
7714 | 143k | xmlFatalErr(ctxt, XML_ERR_ENTITYREF_SEMICOL_MISSING, NULL); |
7715 | 143k | return(NULL); |
7716 | 143k | } |
7717 | 476k | NEXT; |
7718 | | |
7719 | 476k | return(name); |
7720 | 619k | } |
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 | 984k | xmlParseStringEntityRef(xmlParserCtxtPtr ctxt, const xmlChar ** str) { |
7777 | 984k | xmlChar *name; |
7778 | 984k | const xmlChar *ptr; |
7779 | 984k | xmlChar cur; |
7780 | | |
7781 | 984k | if ((str == NULL) || (*str == NULL)) |
7782 | 0 | return(NULL); |
7783 | 984k | ptr = *str; |
7784 | 984k | cur = *ptr; |
7785 | 984k | if (cur != '&') |
7786 | 0 | return(NULL); |
7787 | | |
7788 | 984k | ptr++; |
7789 | 984k | name = xmlParseStringName(ctxt, &ptr); |
7790 | 984k | if (name == NULL) { |
7791 | 574 | xmlFatalErrMsg(ctxt, XML_ERR_NAME_REQUIRED, |
7792 | 574 | "xmlParseStringEntityRef: no name\n"); |
7793 | 574 | *str = ptr; |
7794 | 574 | return(NULL); |
7795 | 574 | } |
7796 | 984k | if (*ptr != ';') { |
7797 | 289 | xmlFatalErr(ctxt, XML_ERR_ENTITYREF_SEMICOL_MISSING, NULL); |
7798 | 289 | xmlFree(name); |
7799 | 289 | *str = ptr; |
7800 | 289 | return(NULL); |
7801 | 289 | } |
7802 | 983k | ptr++; |
7803 | | |
7804 | 983k | *str = ptr; |
7805 | 983k | return(name); |
7806 | 984k | } |
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 | 70.5k | { |
7843 | 70.5k | const xmlChar *name; |
7844 | 70.5k | xmlEntityPtr entity = NULL; |
7845 | 70.5k | xmlParserInputPtr input; |
7846 | | |
7847 | 70.5k | if (RAW != '%') |
7848 | 0 | return; |
7849 | 70.5k | NEXT; |
7850 | 70.5k | name = xmlParseName(ctxt); |
7851 | 70.5k | if (name == NULL) { |
7852 | 3.47k | xmlFatalErrMsg(ctxt, XML_ERR_PEREF_NO_NAME, "PEReference: no name\n"); |
7853 | 3.47k | return; |
7854 | 3.47k | } |
7855 | 67.0k | if (RAW != ';') { |
7856 | 3.35k | xmlFatalErr(ctxt, XML_ERR_PEREF_SEMICOL_MISSING, NULL); |
7857 | 3.35k | return; |
7858 | 3.35k | } |
7859 | | |
7860 | 63.7k | NEXT; |
7861 | | |
7862 | | /* Must be set before xmlHandleUndeclaredEntity */ |
7863 | 63.7k | ctxt->hasPErefs = 1; |
7864 | | |
7865 | | /* |
7866 | | * Request the entity from SAX |
7867 | | */ |
7868 | 63.7k | if ((ctxt->sax != NULL) && |
7869 | 63.7k | (ctxt->sax->getParameterEntity != NULL)) |
7870 | 63.7k | entity = ctxt->sax->getParameterEntity(ctxt->userData, name); |
7871 | | |
7872 | 63.7k | if (entity == NULL) { |
7873 | 18.9k | xmlHandleUndeclaredEntity(ctxt, name); |
7874 | 44.8k | } else { |
7875 | | /* |
7876 | | * Internal checking in case the entity quest barfed |
7877 | | */ |
7878 | 44.8k | if ((entity->etype != XML_INTERNAL_PARAMETER_ENTITY) && |
7879 | 44.8k | (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 | 44.8k | } else { |
7884 | 44.8k | if ((entity->etype == XML_EXTERNAL_PARAMETER_ENTITY) && |
7885 | 44.8k | ((ctxt->options & XML_PARSE_NO_XXE) || |
7886 | 37.4k | ((ctxt->loadsubset == 0) && |
7887 | 37.4k | (ctxt->replaceEntities == 0) && |
7888 | 37.4k | (ctxt->validate == 0)))) |
7889 | 0 | return; |
7890 | | |
7891 | 44.8k | if (entity->flags & XML_ENT_EXPANDING) { |
7892 | 816 | xmlFatalErr(ctxt, XML_ERR_ENTITY_LOOP, NULL); |
7893 | 816 | xmlHaltParser(ctxt); |
7894 | 816 | return; |
7895 | 816 | } |
7896 | | |
7897 | 43.9k | input = xmlNewEntityInputStream(ctxt, entity); |
7898 | 43.9k | if (xmlCtxtPushInput(ctxt, input) < 0) { |
7899 | 9.05k | xmlFreeInputStream(input); |
7900 | 9.05k | return; |
7901 | 9.05k | } |
7902 | | |
7903 | 34.9k | entity->flags |= XML_ENT_EXPANDING; |
7904 | | |
7905 | 34.9k | GROW; |
7906 | | |
7907 | 34.9k | if (entity->etype == XML_EXTERNAL_PARAMETER_ENTITY) { |
7908 | 27.6k | xmlDetectEncoding(ctxt); |
7909 | | |
7910 | 27.6k | if ((CMP5(CUR_PTR, '<', '?', 'x', 'm', 'l')) && |
7911 | 27.6k | (IS_BLANK_CH(NXT(5)))) { |
7912 | 5.51k | xmlParseTextDecl(ctxt); |
7913 | 5.51k | } |
7914 | 27.6k | } |
7915 | 34.9k | } |
7916 | 44.8k | } |
7917 | 63.7k | } |
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 | 9.36k | xmlLoadEntityContent(xmlParserCtxtPtr ctxt, xmlEntityPtr entity) { |
7930 | 9.36k | xmlParserInputPtr oldinput, input = NULL; |
7931 | 9.36k | xmlParserInputPtr *oldinputTab; |
7932 | 9.36k | const xmlChar *oldencoding; |
7933 | 9.36k | xmlChar *content = NULL; |
7934 | 9.36k | xmlResourceType rtype; |
7935 | 9.36k | size_t length, i; |
7936 | 9.36k | int oldinputNr, oldinputMax; |
7937 | 9.36k | int ret = -1; |
7938 | 9.36k | int res; |
7939 | | |
7940 | 9.36k | if ((ctxt == NULL) || (entity == NULL) || |
7941 | 9.36k | ((entity->etype != XML_EXTERNAL_PARAMETER_ENTITY) && |
7942 | 9.36k | (entity->etype != XML_EXTERNAL_GENERAL_PARSED_ENTITY)) || |
7943 | 9.36k | (entity->content != NULL)) { |
7944 | 0 | xmlFatalErr(ctxt, XML_ERR_ARGUMENT, |
7945 | 0 | "xmlLoadEntityContent parameter error"); |
7946 | 0 | return(-1); |
7947 | 0 | } |
7948 | | |
7949 | 9.36k | if (entity->etype == XML_EXTERNAL_PARAMETER_ENTITY) |
7950 | 9.36k | rtype = XML_RESOURCE_PARAMETER_ENTITY; |
7951 | 0 | else |
7952 | 0 | rtype = XML_RESOURCE_GENERAL_ENTITY; |
7953 | | |
7954 | 9.36k | input = xmlLoadResource(ctxt, (char *) entity->URI, |
7955 | 9.36k | (char *) entity->ExternalID, rtype); |
7956 | 9.36k | if (input == NULL) |
7957 | 957 | return(-1); |
7958 | | |
7959 | 8.40k | oldinput = ctxt->input; |
7960 | 8.40k | oldinputNr = ctxt->inputNr; |
7961 | 8.40k | oldinputMax = ctxt->inputMax; |
7962 | 8.40k | oldinputTab = ctxt->inputTab; |
7963 | 8.40k | oldencoding = ctxt->encoding; |
7964 | | |
7965 | 8.40k | ctxt->input = NULL; |
7966 | 8.40k | ctxt->inputNr = 0; |
7967 | 8.40k | ctxt->inputMax = 1; |
7968 | 8.40k | ctxt->encoding = NULL; |
7969 | 8.40k | ctxt->inputTab = xmlMalloc(sizeof(xmlParserInputPtr)); |
7970 | 8.40k | if (ctxt->inputTab == NULL) { |
7971 | 1 | xmlErrMemory(ctxt); |
7972 | 1 | xmlFreeInputStream(input); |
7973 | 1 | goto error; |
7974 | 1 | } |
7975 | | |
7976 | 8.40k | xmlBufResetInput(input->buf->buffer, input); |
7977 | | |
7978 | 8.40k | if (xmlCtxtPushInput(ctxt, input) < 0) { |
7979 | 0 | xmlFreeInputStream(input); |
7980 | 0 | goto error; |
7981 | 0 | } |
7982 | | |
7983 | 8.40k | xmlDetectEncoding(ctxt); |
7984 | | |
7985 | | /* |
7986 | | * Parse a possible text declaration first |
7987 | | */ |
7988 | 8.40k | if ((CMP5(CUR_PTR, '<', '?', 'x', 'm', 'l')) && (IS_BLANK_CH(NXT(5)))) { |
7989 | 4.11k | xmlParseTextDecl(ctxt); |
7990 | | /* |
7991 | | * An XML-1.0 document can't reference an entity not XML-1.0 |
7992 | | */ |
7993 | 4.11k | if ((xmlStrEqual(ctxt->version, BAD_CAST "1.0")) && |
7994 | 4.11k | (!xmlStrEqual(ctxt->input->version, BAD_CAST "1.0"))) { |
7995 | 1.84k | xmlFatalErrMsg(ctxt, XML_ERR_VERSION_MISMATCH, |
7996 | 1.84k | "Version mismatch between document and entity\n"); |
7997 | 1.84k | } |
7998 | 4.11k | } |
7999 | | |
8000 | 8.40k | length = input->cur - input->base; |
8001 | 8.40k | xmlBufShrink(input->buf->buffer, length); |
8002 | 8.40k | xmlSaturatedAdd(&ctxt->sizeentities, length); |
8003 | | |
8004 | 11.5k | while ((res = xmlParserInputBufferGrow(input->buf, 4096)) > 0) |
8005 | 3.15k | ; |
8006 | | |
8007 | 8.40k | xmlBufResetInput(input->buf->buffer, input); |
8008 | | |
8009 | 8.40k | if (res < 0) { |
8010 | 265 | xmlCtxtErrIO(ctxt, input->buf->error, NULL); |
8011 | 265 | goto error; |
8012 | 265 | } |
8013 | | |
8014 | 8.13k | length = xmlBufUse(input->buf->buffer); |
8015 | 8.13k | if (length > INT_MAX) { |
8016 | 0 | xmlErrMemory(ctxt); |
8017 | 0 | goto error; |
8018 | 0 | } |
8019 | | |
8020 | 8.13k | content = xmlStrndup(xmlBufContent(input->buf->buffer), length); |
8021 | 8.13k | if (content == NULL) { |
8022 | 2 | xmlErrMemory(ctxt); |
8023 | 2 | goto error; |
8024 | 2 | } |
8025 | | |
8026 | 3.49M | for (i = 0; i < length; ) { |
8027 | 3.49M | int clen = length - i; |
8028 | 3.49M | int c = xmlGetUTF8Char(content + i, &clen); |
8029 | | |
8030 | 3.49M | if ((c < 0) || (!IS_CHAR(c))) { |
8031 | 7.85k | xmlFatalErrMsgInt(ctxt, XML_ERR_INVALID_CHAR, |
8032 | 7.85k | "xmlLoadEntityContent: invalid char value %d\n", |
8033 | 7.85k | content[i]); |
8034 | 7.85k | goto error; |
8035 | 7.85k | } |
8036 | 3.48M | i += clen; |
8037 | 3.48M | } |
8038 | | |
8039 | 283 | xmlSaturatedAdd(&ctxt->sizeentities, length); |
8040 | 283 | entity->content = content; |
8041 | 283 | entity->length = length; |
8042 | 283 | content = NULL; |
8043 | 283 | ret = 0; |
8044 | | |
8045 | 8.40k | error: |
8046 | 16.8k | while (ctxt->inputNr > 0) |
8047 | 8.40k | xmlFreeInputStream(xmlCtxtPopInput(ctxt)); |
8048 | 8.40k | xmlFree(ctxt->inputTab); |
8049 | 8.40k | xmlFree((xmlChar *) ctxt->encoding); |
8050 | | |
8051 | 8.40k | ctxt->input = oldinput; |
8052 | 8.40k | ctxt->inputNr = oldinputNr; |
8053 | 8.40k | ctxt->inputMax = oldinputMax; |
8054 | 8.40k | ctxt->inputTab = oldinputTab; |
8055 | 8.40k | ctxt->encoding = oldencoding; |
8056 | | |
8057 | 8.40k | xmlFree(content); |
8058 | | |
8059 | 8.40k | return(ret); |
8060 | 283 | } |
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 | 24.9k | xmlParseStringPEReference(xmlParserCtxtPtr ctxt, const xmlChar **str) { |
8095 | 24.9k | const xmlChar *ptr; |
8096 | 24.9k | xmlChar cur; |
8097 | 24.9k | xmlChar *name; |
8098 | 24.9k | xmlEntityPtr entity = NULL; |
8099 | | |
8100 | 24.9k | if ((str == NULL) || (*str == NULL)) return(NULL); |
8101 | 24.9k | ptr = *str; |
8102 | 24.9k | cur = *ptr; |
8103 | 24.9k | if (cur != '%') |
8104 | 0 | return(NULL); |
8105 | 24.9k | ptr++; |
8106 | 24.9k | name = xmlParseStringName(ctxt, &ptr); |
8107 | 24.9k | if (name == NULL) { |
8108 | 3.29k | xmlFatalErrMsg(ctxt, XML_ERR_NAME_REQUIRED, |
8109 | 3.29k | "xmlParseStringPEReference: no name\n"); |
8110 | 3.29k | *str = ptr; |
8111 | 3.29k | return(NULL); |
8112 | 3.29k | } |
8113 | 21.6k | cur = *ptr; |
8114 | 21.6k | if (cur != ';') { |
8115 | 1.23k | xmlFatalErr(ctxt, XML_ERR_ENTITYREF_SEMICOL_MISSING, NULL); |
8116 | 1.23k | xmlFree(name); |
8117 | 1.23k | *str = ptr; |
8118 | 1.23k | return(NULL); |
8119 | 1.23k | } |
8120 | 20.4k | ptr++; |
8121 | | |
8122 | | /* Must be set before xmlHandleUndeclaredEntity */ |
8123 | 20.4k | ctxt->hasPErefs = 1; |
8124 | | |
8125 | | /* |
8126 | | * Request the entity from SAX |
8127 | | */ |
8128 | 20.4k | if ((ctxt->sax != NULL) && |
8129 | 20.4k | (ctxt->sax->getParameterEntity != NULL)) |
8130 | 20.4k | entity = ctxt->sax->getParameterEntity(ctxt->userData, name); |
8131 | | |
8132 | 20.4k | if (entity == NULL) { |
8133 | 1.92k | xmlHandleUndeclaredEntity(ctxt, name); |
8134 | 18.4k | } else { |
8135 | | /* |
8136 | | * Internal checking in case the entity quest barfed |
8137 | | */ |
8138 | 18.4k | if ((entity->etype != XML_INTERNAL_PARAMETER_ENTITY) && |
8139 | 18.4k | (entity->etype != XML_EXTERNAL_PARAMETER_ENTITY)) { |
8140 | 0 | xmlWarningMsg(ctxt, XML_WAR_UNDECLARED_ENTITY, |
8141 | 0 | "%%%s; is not a parameter entity\n", |
8142 | 0 | name, NULL); |
8143 | 0 | } |
8144 | 18.4k | } |
8145 | | |
8146 | 20.4k | xmlFree(name); |
8147 | 20.4k | *str = ptr; |
8148 | 20.4k | return(entity); |
8149 | 21.6k | } |
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 | 154k | xmlParseDocTypeDecl(xmlParserCtxtPtr ctxt) { |
8169 | 154k | const xmlChar *name = NULL; |
8170 | 154k | xmlChar *ExternalID = NULL; |
8171 | 154k | xmlChar *URI = NULL; |
8172 | | |
8173 | | /* |
8174 | | * We know that '<!DOCTYPE' has been detected. |
8175 | | */ |
8176 | 154k | SKIP(9); |
8177 | | |
8178 | 154k | if (SKIP_BLANKS == 0) { |
8179 | 23.9k | xmlFatalErrMsg(ctxt, XML_ERR_SPACE_REQUIRED, |
8180 | 23.9k | "Space required after 'DOCTYPE'\n"); |
8181 | 23.9k | } |
8182 | | |
8183 | | /* |
8184 | | * Parse the DOCTYPE name. |
8185 | | */ |
8186 | 154k | name = xmlParseName(ctxt); |
8187 | 154k | if (name == NULL) { |
8188 | 5.75k | xmlFatalErrMsg(ctxt, XML_ERR_NAME_REQUIRED, |
8189 | 5.75k | "xmlParseDocTypeDecl : no DOCTYPE name !\n"); |
8190 | 5.75k | } |
8191 | 154k | ctxt->intSubName = name; |
8192 | | |
8193 | 154k | SKIP_BLANKS; |
8194 | | |
8195 | | /* |
8196 | | * Check for SystemID and ExternalID |
8197 | | */ |
8198 | 154k | URI = xmlParseExternalID(ctxt, &ExternalID, 1); |
8199 | | |
8200 | 154k | if ((URI != NULL) || (ExternalID != NULL)) { |
8201 | 34.1k | ctxt->hasExternalSubset = 1; |
8202 | 34.1k | } |
8203 | 154k | ctxt->extSubURI = URI; |
8204 | 154k | ctxt->extSubSystem = ExternalID; |
8205 | | |
8206 | 154k | SKIP_BLANKS; |
8207 | | |
8208 | | /* |
8209 | | * Create and update the internal subset. |
8210 | | */ |
8211 | 154k | if ((ctxt->sax != NULL) && (ctxt->sax->internalSubset != NULL) && |
8212 | 154k | (!ctxt->disableSAX)) |
8213 | 113k | ctxt->sax->internalSubset(ctxt->userData, name, ExternalID, URI); |
8214 | | |
8215 | 154k | if ((RAW != '[') && (RAW != '>')) { |
8216 | 4.47k | xmlFatalErr(ctxt, XML_ERR_DOCTYPE_NOT_FINISHED, NULL); |
8217 | 4.47k | } |
8218 | 154k | } |
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 | 144k | xmlParseInternalSubset(xmlParserCtxtPtr ctxt) { |
8231 | | /* |
8232 | | * Is there any DTD definition ? |
8233 | | */ |
8234 | 144k | if (RAW == '[') { |
8235 | 144k | int oldInputNr = ctxt->inputNr; |
8236 | | |
8237 | 144k | NEXT; |
8238 | | /* |
8239 | | * Parse the succession of Markup declarations and |
8240 | | * PEReferences. |
8241 | | * Subsequence (markupdecl | PEReference | S)* |
8242 | | */ |
8243 | 144k | SKIP_BLANKS; |
8244 | 546k | while (((RAW != ']') || (ctxt->inputNr > oldInputNr)) && |
8245 | 546k | (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 | 474k | if ((PARSER_EXTERNAL(ctxt)) && |
8252 | 474k | (RAW == '<') && (NXT(1) == '!') && (NXT(2) == '[')) { |
8253 | 3.52k | xmlParseConditionalSections(ctxt); |
8254 | 470k | } else if ((RAW == '<') && ((NXT(1) == '!') || (NXT(1) == '?'))) { |
8255 | 363k | xmlParseMarkupDecl(ctxt); |
8256 | 363k | } else if (RAW == '%') { |
8257 | 35.6k | xmlParsePEReference(ctxt); |
8258 | 71.6k | } else { |
8259 | 71.6k | xmlFatalErr(ctxt, XML_ERR_INT_SUBSET_NOT_FINISHED, NULL); |
8260 | 71.6k | break; |
8261 | 71.6k | } |
8262 | 402k | SKIP_BLANKS_PE; |
8263 | 402k | SHRINK; |
8264 | 402k | GROW; |
8265 | 402k | } |
8266 | | |
8267 | 161k | while (ctxt->inputNr > oldInputNr) |
8268 | 17.3k | xmlPopPE(ctxt); |
8269 | | |
8270 | 144k | if (RAW == ']') { |
8271 | 43.9k | NEXT; |
8272 | 43.9k | SKIP_BLANKS; |
8273 | 43.9k | } |
8274 | 144k | } |
8275 | | |
8276 | | /* |
8277 | | * We should be at the end of the DOCTYPE declaration. |
8278 | | */ |
8279 | 144k | if ((ctxt->wellFormed) && (RAW != '>')) { |
8280 | 175 | xmlFatalErr(ctxt, XML_ERR_DOCTYPE_NOT_FINISHED, NULL); |
8281 | 175 | return; |
8282 | 175 | } |
8283 | 144k | NEXT; |
8284 | 144k | } |
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 "<") 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 | 9.96M | xmlParseQNameHashed(xmlParserCtxtPtr ctxt, xmlHashedString *prefix) { |
8635 | 9.96M | xmlHashedString l, p; |
8636 | 9.96M | int start, isNCName = 0; |
8637 | | |
8638 | 9.96M | l.name = NULL; |
8639 | 9.96M | p.name = NULL; |
8640 | | |
8641 | 9.96M | GROW; |
8642 | 9.96M | start = CUR_PTR - BASE_PTR; |
8643 | | |
8644 | 9.96M | l = xmlParseNCName(ctxt); |
8645 | 9.96M | if (l.name != NULL) { |
8646 | 9.43M | isNCName = 1; |
8647 | 9.43M | if (CUR == ':') { |
8648 | 4.45M | NEXT; |
8649 | 4.45M | p = l; |
8650 | 4.45M | l = xmlParseNCName(ctxt); |
8651 | 4.45M | } |
8652 | 9.43M | } |
8653 | 9.96M | if ((l.name == NULL) || (CUR == ':')) { |
8654 | 603k | xmlChar *tmp; |
8655 | | |
8656 | 603k | l.name = NULL; |
8657 | 603k | p.name = NULL; |
8658 | 603k | if ((isNCName == 0) && (CUR != ':')) |
8659 | 514k | return(l); |
8660 | 89.0k | tmp = xmlParseNmtoken(ctxt); |
8661 | 89.0k | if (tmp != NULL) |
8662 | 43.4k | xmlFree(tmp); |
8663 | 89.0k | l = xmlDictLookupHashed(ctxt->dict, BASE_PTR + start, |
8664 | 89.0k | CUR_PTR - (BASE_PTR + start)); |
8665 | 89.0k | if (l.name == NULL) { |
8666 | 5 | xmlErrMemory(ctxt); |
8667 | 5 | return(l); |
8668 | 5 | } |
8669 | 89.0k | xmlNsErr(ctxt, XML_NS_ERR_QNAME, |
8670 | 89.0k | "Failed to parse QName '%s'\n", l.name, NULL, NULL); |
8671 | 89.0k | } |
8672 | | |
8673 | 9.45M | *prefix = p; |
8674 | 9.45M | return(l); |
8675 | 9.96M | } |
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 | 36.4k | xmlParseQName(xmlParserCtxtPtr ctxt, const xmlChar **prefix) { |
8693 | 36.4k | xmlHashedString n, p; |
8694 | | |
8695 | 36.4k | n = xmlParseQNameHashed(ctxt, &p); |
8696 | 36.4k | if (n.name == NULL) |
8697 | 2.50k | return(NULL); |
8698 | 33.9k | *prefix = p.name; |
8699 | 33.9k | return(n.name); |
8700 | 36.4k | } |
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 | 1.07M | xmlChar const *prefix) { |
8718 | 1.07M | const xmlChar *cmp; |
8719 | 1.07M | const xmlChar *in; |
8720 | 1.07M | const xmlChar *ret; |
8721 | 1.07M | const xmlChar *prefix2; |
8722 | | |
8723 | 1.07M | if (prefix == NULL) return(xmlParseNameAndCompare(ctxt, name)); |
8724 | | |
8725 | 1.07M | GROW; |
8726 | 1.07M | in = ctxt->input->cur; |
8727 | | |
8728 | 1.07M | cmp = prefix; |
8729 | 3.89M | while (*in != 0 && *in == *cmp) { |
8730 | 2.82M | ++in; |
8731 | 2.82M | ++cmp; |
8732 | 2.82M | } |
8733 | 1.07M | if ((*cmp == 0) && (*in == ':')) { |
8734 | 1.06M | in++; |
8735 | 1.06M | cmp = name; |
8736 | 10.4M | while (*in != 0 && *in == *cmp) { |
8737 | 9.42M | ++in; |
8738 | 9.42M | ++cmp; |
8739 | 9.42M | } |
8740 | 1.06M | if (*cmp == 0 && (*in == '>' || IS_BLANK_CH (*in))) { |
8741 | | /* success */ |
8742 | 1.04M | ctxt->input->col += in - ctxt->input->cur; |
8743 | 1.04M | ctxt->input->cur = in; |
8744 | 1.04M | return((const xmlChar*) 1); |
8745 | 1.04M | } |
8746 | 1.06M | } |
8747 | | /* |
8748 | | * all strings coms from the dictionary, equality can be done directly |
8749 | | */ |
8750 | 36.4k | ret = xmlParseQName (ctxt, &prefix2); |
8751 | 36.4k | if (ret == NULL) |
8752 | 2.50k | return(NULL); |
8753 | 33.9k | if ((ret == name) && (prefix == prefix2)) |
8754 | 16.4k | return((const xmlChar*) 1); |
8755 | 17.4k | return ret; |
8756 | 33.9k | } |
8757 | | |
8758 | | /** |
8759 | | * xmlParseAttribute2: |
8760 | | * @ctxt: an XML parser context |
8761 | | * @pref: the element prefix |
8762 | | * @elem: the element name |
8763 | | * @prefix: a xmlChar ** used to store the value of the attribute prefix |
8764 | | * @value: a xmlChar ** used to store the value of the attribute |
8765 | | * @len: an int * to save the length of the attribute |
8766 | | * @alloc: an int * to indicate if the attribute was allocated |
8767 | | * |
8768 | | * parse an attribute in the new SAX2 framework. |
8769 | | * |
8770 | | * Returns the attribute name, and the value in *value, . |
8771 | | */ |
8772 | | |
8773 | | static xmlHashedString |
8774 | | xmlParseAttribute2(xmlParserCtxtPtr ctxt, |
8775 | | const xmlChar * pref, const xmlChar * elem, |
8776 | | xmlHashedString * hprefix, xmlChar ** value, |
8777 | | int *len, int *alloc) |
8778 | 4.87M | { |
8779 | 4.87M | xmlHashedString hname; |
8780 | 4.87M | const xmlChar *prefix, *name; |
8781 | 4.87M | xmlChar *val = NULL, *internal_val = NULL; |
8782 | 4.87M | int normalize = 0; |
8783 | 4.87M | int isNamespace; |
8784 | | |
8785 | 4.87M | *value = NULL; |
8786 | 4.87M | GROW; |
8787 | 4.87M | hname = xmlParseQNameHashed(ctxt, hprefix); |
8788 | 4.87M | if (hname.name == NULL) { |
8789 | 94.6k | xmlFatalErrMsg(ctxt, XML_ERR_NAME_REQUIRED, |
8790 | 94.6k | "error parsing attribute name\n"); |
8791 | 94.6k | return(hname); |
8792 | 94.6k | } |
8793 | 4.78M | name = hname.name; |
8794 | 4.78M | prefix = hprefix->name; |
8795 | | |
8796 | | /* |
8797 | | * get the type if needed |
8798 | | */ |
8799 | 4.78M | if (ctxt->attsSpecial != NULL) { |
8800 | 53.3k | int type; |
8801 | | |
8802 | 53.3k | type = XML_PTR_TO_INT(xmlHashQLookup2(ctxt->attsSpecial, pref, elem, |
8803 | 53.3k | prefix, name)); |
8804 | 53.3k | if (type != 0) |
8805 | 25.5k | normalize = 1; |
8806 | 53.3k | } |
8807 | | |
8808 | | /* |
8809 | | * read the value |
8810 | | */ |
8811 | 4.78M | SKIP_BLANKS; |
8812 | 4.78M | if (RAW == '=') { |
8813 | 4.73M | NEXT; |
8814 | 4.73M | SKIP_BLANKS; |
8815 | 4.73M | isNamespace = (((prefix == NULL) && (name == ctxt->str_xmlns)) || |
8816 | 4.73M | (prefix == ctxt->str_xmlns)); |
8817 | 4.73M | val = xmlParseAttValueInternal(ctxt, len, alloc, normalize, |
8818 | 4.73M | isNamespace); |
8819 | 4.73M | if (val == NULL) |
8820 | 20.8k | goto error; |
8821 | 4.73M | } else { |
8822 | 41.0k | xmlFatalErrMsgStr(ctxt, XML_ERR_ATTRIBUTE_WITHOUT_VALUE, |
8823 | 41.0k | "Specification mandates value for attribute %s\n", |
8824 | 41.0k | name); |
8825 | 41.0k | goto error; |
8826 | 41.0k | } |
8827 | | |
8828 | 4.71M | 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 | 87.0k | 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 | 87.0k | if (xmlStrEqual(name, BAD_CAST "space")) { |
8849 | 2.17k | internal_val = xmlStrndup(val, *len); |
8850 | 2.17k | if (internal_val == NULL) |
8851 | 2 | goto mem_error; |
8852 | 2.17k | if (xmlStrEqual(internal_val, BAD_CAST "default")) |
8853 | 324 | *(ctxt->space) = 0; |
8854 | 1.84k | else if (xmlStrEqual(internal_val, BAD_CAST "preserve")) |
8855 | 511 | *(ctxt->space) = 1; |
8856 | 1.33k | else { |
8857 | 1.33k | xmlWarningMsg(ctxt, XML_WAR_SPACE_VALUE, |
8858 | 1.33k | "Invalid value \"%s\" for xml:space : \"default\" or \"preserve\" expected\n", |
8859 | 1.33k | internal_val, NULL); |
8860 | 1.33k | } |
8861 | 2.17k | } |
8862 | 87.0k | if (internal_val) { |
8863 | 2.17k | xmlFree(internal_val); |
8864 | 2.17k | } |
8865 | 87.0k | } |
8866 | | |
8867 | 4.71M | *value = val; |
8868 | 4.71M | return (hname); |
8869 | | |
8870 | 2 | mem_error: |
8871 | 2 | xmlErrMemory(ctxt); |
8872 | 61.9k | error: |
8873 | 61.9k | if ((val != NULL) && (*alloc != 0)) |
8874 | 1 | xmlFree(val); |
8875 | 61.9k | return(hname); |
8876 | 2 | } |
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 | 1.01M | const xmlChar *uri, unsigned hashValue, int aindex) { |
8895 | 1.01M | xmlAttrHashBucket *table = ctxt->attrHash; |
8896 | 1.01M | xmlAttrHashBucket *bucket; |
8897 | 1.01M | unsigned hindex; |
8898 | | |
8899 | 1.01M | hindex = hashValue & (size - 1); |
8900 | 1.01M | bucket = &table[hindex]; |
8901 | | |
8902 | 1.16M | while (bucket->index >= 0) { |
8903 | 182k | const xmlChar **atts = &ctxt->atts[bucket->index]; |
8904 | | |
8905 | 182k | if (name == atts[0]) { |
8906 | 30.1k | int nsIndex = XML_PTR_TO_INT(atts[2]); |
8907 | | |
8908 | 30.1k | if ((nsIndex == NS_INDEX_EMPTY) ? (uri == NULL) : |
8909 | 30.1k | (nsIndex == NS_INDEX_XML) ? (uri == ctxt->str_xml_ns) : |
8910 | 4.68k | (uri == ctxt->nsTab[nsIndex * 2 + 1])) |
8911 | 26.2k | return(bucket->index); |
8912 | 30.1k | } |
8913 | | |
8914 | 155k | hindex++; |
8915 | 155k | bucket++; |
8916 | 155k | if (hindex >= size) { |
8917 | 24.9k | hindex = 0; |
8918 | 24.9k | bucket = table; |
8919 | 24.9k | } |
8920 | 155k | } |
8921 | | |
8922 | 987k | bucket->index = aindex; |
8923 | | |
8924 | 987k | return(INT_MAX); |
8925 | 1.01M | } |
8926 | | |
8927 | | static int |
8928 | | xmlAttrHashInsertQName(xmlParserCtxtPtr ctxt, unsigned size, |
8929 | | const xmlChar *name, const xmlChar *prefix, |
8930 | 5.02k | unsigned hashValue, int aindex) { |
8931 | 5.02k | xmlAttrHashBucket *table = ctxt->attrHash; |
8932 | 5.02k | xmlAttrHashBucket *bucket; |
8933 | 5.02k | unsigned hindex; |
8934 | | |
8935 | 5.02k | hindex = hashValue & (size - 1); |
8936 | 5.02k | bucket = &table[hindex]; |
8937 | | |
8938 | 8.29k | while (bucket->index >= 0) { |
8939 | 4.42k | const xmlChar **atts = &ctxt->atts[bucket->index]; |
8940 | | |
8941 | 4.42k | if ((name == atts[0]) && (prefix == atts[1])) |
8942 | 1.15k | return(bucket->index); |
8943 | | |
8944 | 3.27k | hindex++; |
8945 | 3.27k | bucket++; |
8946 | 3.27k | if (hindex >= size) { |
8947 | 420 | hindex = 0; |
8948 | 420 | bucket = table; |
8949 | 420 | } |
8950 | 3.27k | } |
8951 | | |
8952 | 3.87k | bucket->index = aindex; |
8953 | | |
8954 | 3.87k | return(INT_MAX); |
8955 | 5.02k | } |
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 | 5.05M | const xmlChar **URI, int *nbNsPtr) { |
8988 | 5.05M | xmlHashedString hlocalname; |
8989 | 5.05M | xmlHashedString hprefix; |
8990 | 5.05M | xmlHashedString hattname; |
8991 | 5.05M | xmlHashedString haprefix; |
8992 | 5.05M | const xmlChar *localname; |
8993 | 5.05M | const xmlChar *prefix; |
8994 | 5.05M | const xmlChar *attname; |
8995 | 5.05M | const xmlChar *aprefix; |
8996 | 5.05M | const xmlChar *uri; |
8997 | 5.05M | xmlChar *attvalue = NULL; |
8998 | 5.05M | const xmlChar **atts = ctxt->atts; |
8999 | 5.05M | unsigned attrHashSize = 0; |
9000 | 5.05M | int maxatts = ctxt->maxatts; |
9001 | 5.05M | int nratts, nbatts, nbdef; |
9002 | 5.05M | int i, j, nbNs, nbTotalDef, attval, nsIndex, maxAtts; |
9003 | 5.05M | int alloc = 0; |
9004 | 5.05M | int numNsErr = 0; |
9005 | 5.05M | int numDupErr = 0; |
9006 | | |
9007 | 5.05M | if (RAW != '<') return(NULL); |
9008 | 5.05M | NEXT1; |
9009 | | |
9010 | 5.05M | nbatts = 0; |
9011 | 5.05M | nratts = 0; |
9012 | 5.05M | nbdef = 0; |
9013 | 5.05M | nbNs = 0; |
9014 | 5.05M | nbTotalDef = 0; |
9015 | 5.05M | attval = 0; |
9016 | | |
9017 | 5.05M | if (xmlParserNsStartElement(ctxt->nsdb) < 0) { |
9018 | 0 | xmlErrMemory(ctxt); |
9019 | 0 | return(NULL); |
9020 | 0 | } |
9021 | | |
9022 | 5.05M | hlocalname = xmlParseQNameHashed(ctxt, &hprefix); |
9023 | 5.05M | if (hlocalname.name == NULL) { |
9024 | 417k | xmlFatalErrMsg(ctxt, XML_ERR_NAME_REQUIRED, |
9025 | 417k | "StartTag: invalid element name\n"); |
9026 | 417k | return(NULL); |
9027 | 417k | } |
9028 | 4.63M | localname = hlocalname.name; |
9029 | 4.63M | prefix = hprefix.name; |
9030 | | |
9031 | | /* |
9032 | | * Now parse the attributes, it ends up with the ending |
9033 | | * |
9034 | | * (S Attribute)* S? |
9035 | | */ |
9036 | 4.63M | SKIP_BLANKS; |
9037 | 4.63M | 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 | 6.47M | while (((RAW != '>') && |
9064 | 6.47M | ((RAW != '/') || (NXT(1) != '>')) && |
9065 | 6.47M | (IS_BYTE_CHAR(RAW))) && (PARSER_STOPPED(ctxt) == 0)) { |
9066 | 4.87M | int len = -1; |
9067 | | |
9068 | 4.87M | hattname = xmlParseAttribute2(ctxt, prefix, localname, |
9069 | 4.87M | &haprefix, &attvalue, &len, |
9070 | 4.87M | &alloc); |
9071 | 4.87M | if (hattname.name == NULL) |
9072 | 94.6k | break; |
9073 | 4.78M | if (attvalue == NULL) |
9074 | 61.9k | goto next_attr; |
9075 | 4.71M | attname = hattname.name; |
9076 | 4.71M | aprefix = haprefix.name; |
9077 | 4.71M | if (len < 0) len = xmlStrlen(attvalue); |
9078 | | |
9079 | 4.71M | if ((attname == ctxt->str_xmlns) && (aprefix == NULL)) { |
9080 | 49.7k | xmlHashedString huri; |
9081 | 49.7k | xmlURIPtr parsedUri; |
9082 | | |
9083 | 49.7k | huri = xmlDictLookupHashed(ctxt->dict, attvalue, len); |
9084 | 49.7k | uri = huri.name; |
9085 | 49.7k | if (uri == NULL) { |
9086 | 1 | xmlErrMemory(ctxt); |
9087 | 1 | goto next_attr; |
9088 | 1 | } |
9089 | 49.7k | if (*uri != 0) { |
9090 | 49.1k | if (xmlParseURISafe((const char *) uri, &parsedUri) < 0) { |
9091 | 4 | xmlErrMemory(ctxt); |
9092 | 4 | goto next_attr; |
9093 | 4 | } |
9094 | 49.1k | if (parsedUri == NULL) { |
9095 | 27.5k | xmlNsErr(ctxt, XML_WAR_NS_URI, |
9096 | 27.5k | "xmlns: '%s' is not a valid URI\n", |
9097 | 27.5k | uri, NULL, NULL); |
9098 | 27.5k | } else { |
9099 | 21.6k | if (parsedUri->scheme == NULL) { |
9100 | 17.5k | xmlNsWarn(ctxt, XML_WAR_NS_URI_RELATIVE, |
9101 | 17.5k | "xmlns: URI %s is not absolute\n", |
9102 | 17.5k | uri, NULL, NULL); |
9103 | 17.5k | } |
9104 | 21.6k | xmlFreeURI(parsedUri); |
9105 | 21.6k | } |
9106 | 49.1k | if (uri == ctxt->str_xml_ns) { |
9107 | 344 | if (attname != ctxt->str_xml) { |
9108 | 344 | xmlNsErr(ctxt, XML_NS_ERR_XML_NAMESPACE, |
9109 | 344 | "xml namespace URI cannot be the default namespace\n", |
9110 | 344 | NULL, NULL, NULL); |
9111 | 344 | } |
9112 | 344 | goto next_attr; |
9113 | 344 | } |
9114 | 48.8k | if ((len == 29) && |
9115 | 48.8k | (xmlStrEqual(uri, |
9116 | 1.42k | BAD_CAST "http://www.w3.org/2000/xmlns/"))) { |
9117 | 600 | xmlNsErr(ctxt, XML_NS_ERR_XML_NAMESPACE, |
9118 | 600 | "reuse of the xmlns namespace name is forbidden\n", |
9119 | 600 | NULL, NULL, NULL); |
9120 | 600 | goto next_attr; |
9121 | 600 | } |
9122 | 48.8k | } |
9123 | | |
9124 | 48.8k | if (xmlParserNsPush(ctxt, NULL, &huri, NULL, 0) > 0) |
9125 | 48.2k | nbNs++; |
9126 | 4.66M | } else if (aprefix == ctxt->str_xmlns) { |
9127 | 765k | xmlHashedString huri; |
9128 | 765k | xmlURIPtr parsedUri; |
9129 | | |
9130 | 765k | huri = xmlDictLookupHashed(ctxt->dict, attvalue, len); |
9131 | 765k | uri = huri.name; |
9132 | 765k | if (uri == NULL) { |
9133 | 1 | xmlErrMemory(ctxt); |
9134 | 1 | goto next_attr; |
9135 | 1 | } |
9136 | | |
9137 | 765k | if (attname == ctxt->str_xml) { |
9138 | 561 | if (uri != ctxt->str_xml_ns) { |
9139 | 240 | xmlNsErr(ctxt, XML_NS_ERR_XML_NAMESPACE, |
9140 | 240 | "xml namespace prefix mapped to wrong URI\n", |
9141 | 240 | NULL, NULL, NULL); |
9142 | 240 | } |
9143 | | /* |
9144 | | * Do not keep a namespace definition node |
9145 | | */ |
9146 | 561 | goto next_attr; |
9147 | 561 | } |
9148 | 764k | if (uri == ctxt->str_xml_ns) { |
9149 | 270 | if (attname != ctxt->str_xml) { |
9150 | 270 | xmlNsErr(ctxt, XML_NS_ERR_XML_NAMESPACE, |
9151 | 270 | "xml namespace URI mapped to wrong prefix\n", |
9152 | 270 | NULL, NULL, NULL); |
9153 | 270 | } |
9154 | 270 | goto next_attr; |
9155 | 270 | } |
9156 | 764k | if (attname == ctxt->str_xmlns) { |
9157 | 389 | xmlNsErr(ctxt, XML_NS_ERR_XML_NAMESPACE, |
9158 | 389 | "redefinition of the xmlns prefix is forbidden\n", |
9159 | 389 | NULL, NULL, NULL); |
9160 | 389 | goto next_attr; |
9161 | 389 | } |
9162 | 763k | if ((len == 29) && |
9163 | 763k | (xmlStrEqual(uri, |
9164 | 2.16k | BAD_CAST "http://www.w3.org/2000/xmlns/"))) { |
9165 | 257 | xmlNsErr(ctxt, XML_NS_ERR_XML_NAMESPACE, |
9166 | 257 | "reuse of the xmlns namespace name is forbidden\n", |
9167 | 257 | NULL, NULL, NULL); |
9168 | 257 | goto next_attr; |
9169 | 257 | } |
9170 | 763k | if ((uri == NULL) || (uri[0] == 0)) { |
9171 | 1.01k | xmlNsErr(ctxt, XML_NS_ERR_XML_NAMESPACE, |
9172 | 1.01k | "xmlns:%s: Empty XML namespace is not allowed\n", |
9173 | 1.01k | attname, NULL, NULL); |
9174 | 1.01k | goto next_attr; |
9175 | 762k | } else { |
9176 | 762k | if (xmlParseURISafe((const char *) uri, &parsedUri) < 0) { |
9177 | 126 | xmlErrMemory(ctxt); |
9178 | 126 | goto next_attr; |
9179 | 126 | } |
9180 | 762k | if (parsedUri == NULL) { |
9181 | 66.3k | xmlNsErr(ctxt, XML_WAR_NS_URI, |
9182 | 66.3k | "xmlns:%s: '%s' is not a valid URI\n", |
9183 | 66.3k | attname, uri, NULL); |
9184 | 696k | } else { |
9185 | 696k | 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 | 696k | xmlFreeURI(parsedUri); |
9191 | 696k | } |
9192 | 762k | } |
9193 | | |
9194 | 762k | if (xmlParserNsPush(ctxt, &hattname, &huri, NULL, 0) > 0) |
9195 | 757k | nbNs++; |
9196 | 3.90M | } else { |
9197 | | /* |
9198 | | * Populate attributes array, see above for repurposing |
9199 | | * of xmlChar pointers. |
9200 | | */ |
9201 | 3.90M | if ((atts == NULL) || (nbatts + 5 > maxatts)) { |
9202 | 861k | int res = xmlCtxtGrowAttrs(ctxt); |
9203 | | |
9204 | 861k | maxatts = ctxt->maxatts; |
9205 | 861k | atts = ctxt->atts; |
9206 | | |
9207 | 861k | if (res < 0) |
9208 | 91 | goto next_attr; |
9209 | 861k | } |
9210 | 3.90M | ctxt->attallocs[nratts++] = (hattname.hashValue & 0x7FFFFFFF) | |
9211 | 3.90M | ((unsigned) alloc << 31); |
9212 | 3.90M | atts[nbatts++] = attname; |
9213 | 3.90M | atts[nbatts++] = aprefix; |
9214 | 3.90M | atts[nbatts++] = (const xmlChar *) (size_t) haprefix.hashValue; |
9215 | 3.90M | if (alloc) { |
9216 | 152k | atts[nbatts++] = attvalue; |
9217 | 152k | attvalue += len; |
9218 | 152k | atts[nbatts++] = attvalue; |
9219 | 3.75M | } 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 | 3.75M | atts[nbatts++] = (void *) (attvalue - BASE_PTR); |
9226 | 3.75M | attvalue += len; |
9227 | 3.75M | atts[nbatts++] = (void *) (attvalue - BASE_PTR); |
9228 | 3.75M | } |
9229 | | /* |
9230 | | * tag if some deallocation is needed |
9231 | | */ |
9232 | 3.90M | if (alloc != 0) attval = 1; |
9233 | 3.90M | attvalue = NULL; /* moved into atts */ |
9234 | 3.90M | } |
9235 | | |
9236 | 4.78M | next_attr: |
9237 | 4.78M | if ((attvalue != NULL) && (alloc != 0)) { |
9238 | 59.3k | xmlFree(attvalue); |
9239 | 59.3k | attvalue = NULL; |
9240 | 59.3k | } |
9241 | | |
9242 | 4.78M | GROW |
9243 | 4.78M | if ((RAW == '>') || (((RAW == '/') && (NXT(1) == '>')))) |
9244 | 2.84M | break; |
9245 | 1.93M | if (SKIP_BLANKS == 0) { |
9246 | 103k | xmlFatalErrMsg(ctxt, XML_ERR_SPACE_REQUIRED, |
9247 | 103k | "attributes construct error\n"); |
9248 | 103k | break; |
9249 | 103k | } |
9250 | 1.83M | GROW; |
9251 | 1.83M | } |
9252 | | |
9253 | | /* |
9254 | | * Namespaces from default attributes |
9255 | | */ |
9256 | 4.63M | if (ctxt->attsDefault != NULL) { |
9257 | 100k | xmlDefAttrsPtr defaults; |
9258 | | |
9259 | 100k | defaults = xmlHashLookup2(ctxt->attsDefault, localname, prefix); |
9260 | 100k | if (defaults != NULL) { |
9261 | 406k | for (i = 0; i < defaults->nbAttrs; i++) { |
9262 | 344k | xmlDefAttr *attr = &defaults->attrs[i]; |
9263 | | |
9264 | 344k | attname = attr->name.name; |
9265 | 344k | aprefix = attr->prefix.name; |
9266 | | |
9267 | 344k | if ((attname == ctxt->str_xmlns) && (aprefix == NULL)) { |
9268 | 24.8k | xmlParserEntityCheck(ctxt, attr->expandedSize); |
9269 | | |
9270 | 24.8k | if (xmlParserNsPush(ctxt, NULL, &attr->value, NULL, 1) > 0) |
9271 | 22.9k | nbNs++; |
9272 | 319k | } else if (aprefix == ctxt->str_xmlns) { |
9273 | 130k | xmlParserEntityCheck(ctxt, attr->expandedSize); |
9274 | | |
9275 | 130k | if (xmlParserNsPush(ctxt, &attr->name, &attr->value, |
9276 | 130k | NULL, 1) > 0) |
9277 | 129k | nbNs++; |
9278 | 189k | } else { |
9279 | 189k | 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 | 189k | nbTotalDef += 1; |
9285 | 189k | } |
9286 | 344k | } |
9287 | 61.6k | } |
9288 | 100k | } |
9289 | | |
9290 | | /* |
9291 | | * Resolve attribute namespaces |
9292 | | */ |
9293 | 8.54M | for (i = 0; i < nbatts; i += 5) { |
9294 | 3.90M | attname = atts[i]; |
9295 | 3.90M | aprefix = atts[i+1]; |
9296 | | |
9297 | | /* |
9298 | | * The default namespace does not apply to attribute names. |
9299 | | */ |
9300 | 3.90M | if (aprefix == NULL) { |
9301 | 3.77M | nsIndex = NS_INDEX_EMPTY; |
9302 | 3.77M | } else if (aprefix == ctxt->str_xml) { |
9303 | 87.0k | nsIndex = NS_INDEX_XML; |
9304 | 87.0k | } else { |
9305 | 46.4k | haprefix.name = aprefix; |
9306 | 46.4k | haprefix.hashValue = (size_t) atts[i+2]; |
9307 | 46.4k | nsIndex = xmlParserNsLookup(ctxt, &haprefix, NULL); |
9308 | | |
9309 | 46.4k | if ((nsIndex == INT_MAX) || (nsIndex < ctxt->nsdb->minNsIndex)) { |
9310 | 29.7k | xmlNsErr(ctxt, XML_NS_ERR_UNDEFINED_NAMESPACE, |
9311 | 29.7k | "Namespace prefix %s for %s on %s is not defined\n", |
9312 | 29.7k | aprefix, attname, localname); |
9313 | 29.7k | nsIndex = NS_INDEX_EMPTY; |
9314 | 29.7k | } |
9315 | 46.4k | } |
9316 | | |
9317 | 3.90M | atts[i+2] = XML_INT_TO_PTR(nsIndex); |
9318 | 3.90M | } |
9319 | | |
9320 | | /* |
9321 | | * Maximum number of attributes including default attributes. |
9322 | | */ |
9323 | 4.63M | maxAtts = nratts + nbTotalDef; |
9324 | | |
9325 | | /* |
9326 | | * Verify that attribute names are unique. |
9327 | | */ |
9328 | 4.63M | if (maxAtts > 1) { |
9329 | 400k | attrHashSize = 4; |
9330 | 566k | while (attrHashSize / 2 < (unsigned) maxAtts) |
9331 | 165k | attrHashSize *= 2; |
9332 | | |
9333 | 400k | if (attrHashSize > ctxt->attrHashMax) { |
9334 | 176k | xmlAttrHashBucket *tmp; |
9335 | | |
9336 | 176k | tmp = xmlRealloc(ctxt->attrHash, attrHashSize * sizeof(tmp[0])); |
9337 | 176k | if (tmp == NULL) { |
9338 | 35 | xmlErrMemory(ctxt); |
9339 | 35 | goto done; |
9340 | 35 | } |
9341 | | |
9342 | 176k | ctxt->attrHash = tmp; |
9343 | 176k | ctxt->attrHashMax = attrHashSize; |
9344 | 176k | } |
9345 | | |
9346 | 400k | memset(ctxt->attrHash, -1, attrHashSize * sizeof(ctxt->attrHash[0])); |
9347 | | |
9348 | 1.26M | for (i = 0, j = 0; j < nratts; i += 5, j++) { |
9349 | 866k | const xmlChar *nsuri; |
9350 | 866k | unsigned hashValue, nameHashValue, uriHashValue; |
9351 | 866k | int res; |
9352 | | |
9353 | 866k | attname = atts[i]; |
9354 | 866k | aprefix = atts[i+1]; |
9355 | 866k | nsIndex = XML_PTR_TO_INT(atts[i+2]); |
9356 | | /* Hash values always have bit 31 set, see dict.c */ |
9357 | 866k | nameHashValue = ctxt->attallocs[j] | 0x80000000; |
9358 | | |
9359 | 866k | if (nsIndex == NS_INDEX_EMPTY) { |
9360 | | /* |
9361 | | * Prefix with empty namespace means an undeclared |
9362 | | * prefix which was already reported above. |
9363 | | */ |
9364 | 766k | if (aprefix != NULL) |
9365 | 24.3k | continue; |
9366 | 741k | nsuri = NULL; |
9367 | 741k | uriHashValue = URI_HASH_EMPTY; |
9368 | 741k | } else if (nsIndex == NS_INDEX_XML) { |
9369 | 84.6k | nsuri = ctxt->str_xml_ns; |
9370 | 84.6k | uriHashValue = URI_HASH_XML; |
9371 | 84.6k | } else { |
9372 | 16.0k | nsuri = ctxt->nsTab[nsIndex * 2 + 1]; |
9373 | 16.0k | uriHashValue = ctxt->nsdb->extra[nsIndex].uriHashValue; |
9374 | 16.0k | } |
9375 | | |
9376 | 842k | hashValue = xmlDictCombineHash(nameHashValue, uriHashValue); |
9377 | 842k | res = xmlAttrHashInsert(ctxt, attrHashSize, attname, nsuri, |
9378 | 842k | hashValue, i); |
9379 | 842k | 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 | 842k | if (res < INT_MAX) { |
9389 | 6.33k | if (aprefix == atts[res+1]) { |
9390 | 3.42k | xmlErrAttributeDup(ctxt, aprefix, attname); |
9391 | 3.42k | numDupErr += 1; |
9392 | 3.42k | } else { |
9393 | 2.91k | xmlNsErr(ctxt, XML_NS_ERR_ATTRIBUTE_REDEFINED, |
9394 | 2.91k | "Namespaced Attribute %s in '%s' redefined\n", |
9395 | 2.91k | attname, nsuri, NULL); |
9396 | 2.91k | numNsErr += 1; |
9397 | 2.91k | } |
9398 | 6.33k | } |
9399 | 842k | } |
9400 | 400k | } |
9401 | | |
9402 | | /* |
9403 | | * Default attributes |
9404 | | */ |
9405 | 4.63M | if (ctxt->attsDefault != NULL) { |
9406 | 100k | xmlDefAttrsPtr defaults; |
9407 | | |
9408 | 100k | defaults = xmlHashLookup2(ctxt->attsDefault, localname, prefix); |
9409 | 100k | if (defaults != NULL) { |
9410 | 406k | for (i = 0; i < defaults->nbAttrs; i++) { |
9411 | 344k | xmlDefAttr *attr = &defaults->attrs[i]; |
9412 | 344k | const xmlChar *nsuri = NULL; |
9413 | 344k | unsigned hashValue, uriHashValue = 0; |
9414 | 344k | int res; |
9415 | | |
9416 | 344k | attname = attr->name.name; |
9417 | 344k | aprefix = attr->prefix.name; |
9418 | | |
9419 | 344k | if ((attname == ctxt->str_xmlns) && (aprefix == NULL)) |
9420 | 24.8k | continue; |
9421 | 319k | if (aprefix == ctxt->str_xmlns) |
9422 | 130k | continue; |
9423 | | |
9424 | 189k | if (aprefix == NULL) { |
9425 | 83.9k | nsIndex = NS_INDEX_EMPTY; |
9426 | 83.9k | nsuri = NULL; |
9427 | 83.9k | uriHashValue = URI_HASH_EMPTY; |
9428 | 105k | } else if (aprefix == ctxt->str_xml) { |
9429 | 22.3k | nsIndex = NS_INDEX_XML; |
9430 | 22.3k | nsuri = ctxt->str_xml_ns; |
9431 | 22.3k | uriHashValue = URI_HASH_XML; |
9432 | 82.9k | } else { |
9433 | 82.9k | nsIndex = xmlParserNsLookup(ctxt, &attr->prefix, NULL); |
9434 | 82.9k | if ((nsIndex == INT_MAX) || |
9435 | 82.9k | (nsIndex < ctxt->nsdb->minNsIndex)) { |
9436 | 80.6k | xmlNsErr(ctxt, XML_NS_ERR_UNDEFINED_NAMESPACE, |
9437 | 80.6k | "Namespace prefix %s for %s on %s is not " |
9438 | 80.6k | "defined\n", |
9439 | 80.6k | aprefix, attname, localname); |
9440 | 80.6k | nsIndex = NS_INDEX_EMPTY; |
9441 | 80.6k | nsuri = NULL; |
9442 | 80.6k | uriHashValue = URI_HASH_EMPTY; |
9443 | 80.6k | } else { |
9444 | 2.37k | nsuri = ctxt->nsTab[nsIndex * 2 + 1]; |
9445 | 2.37k | uriHashValue = ctxt->nsdb->extra[nsIndex].uriHashValue; |
9446 | 2.37k | } |
9447 | 82.9k | } |
9448 | | |
9449 | | /* |
9450 | | * Check whether the attribute exists |
9451 | | */ |
9452 | 189k | if (maxAtts > 1) { |
9453 | 171k | hashValue = xmlDictCombineHash(attr->name.hashValue, |
9454 | 171k | uriHashValue); |
9455 | 171k | res = xmlAttrHashInsert(ctxt, attrHashSize, attname, nsuri, |
9456 | 171k | hashValue, nbatts); |
9457 | 171k | if (res < 0) |
9458 | 0 | continue; |
9459 | 171k | if (res < INT_MAX) { |
9460 | 19.9k | if (aprefix == atts[res+1]) |
9461 | 1.38k | continue; |
9462 | 18.5k | xmlNsErr(ctxt, XML_NS_ERR_ATTRIBUTE_REDEFINED, |
9463 | 18.5k | "Namespaced Attribute %s in '%s' redefined\n", |
9464 | 18.5k | attname, nsuri, NULL); |
9465 | 18.5k | } |
9466 | 171k | } |
9467 | | |
9468 | 187k | xmlParserEntityCheck(ctxt, attr->expandedSize); |
9469 | | |
9470 | 187k | if ((atts == NULL) || (nbatts + 5 > maxatts)) { |
9471 | 8.66k | res = xmlCtxtGrowAttrs(ctxt); |
9472 | | |
9473 | 8.66k | maxatts = ctxt->maxatts; |
9474 | 8.66k | atts = ctxt->atts; |
9475 | | |
9476 | 8.66k | if (res < 0) { |
9477 | 2 | localname = NULL; |
9478 | 2 | goto done; |
9479 | 2 | } |
9480 | 8.66k | } |
9481 | | |
9482 | 187k | atts[nbatts++] = attname; |
9483 | 187k | atts[nbatts++] = aprefix; |
9484 | 187k | atts[nbatts++] = XML_INT_TO_PTR(nsIndex); |
9485 | 187k | atts[nbatts++] = attr->value.name; |
9486 | 187k | atts[nbatts++] = attr->valueEnd; |
9487 | 187k | 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 | 187k | nbdef++; |
9494 | 187k | } |
9495 | 61.6k | } |
9496 | 100k | } |
9497 | | |
9498 | | /* |
9499 | | * Using a single hash table for nsUri/localName pairs cannot |
9500 | | * detect duplicate QNames reliably. The following example will |
9501 | | * only result in two namespace errors. |
9502 | | * |
9503 | | * <doc xmlns:a="a" xmlns:b="a"> |
9504 | | * <elem a:a="" b:a="" b:a=""/> |
9505 | | * </doc> |
9506 | | * |
9507 | | * If we saw more than one namespace error but no duplicate QNames |
9508 | | * were found, we have to scan for duplicate QNames. |
9509 | | */ |
9510 | 4.63M | if ((numDupErr == 0) && (numNsErr > 1)) { |
9511 | 1.07k | memset(ctxt->attrHash, -1, |
9512 | 1.07k | attrHashSize * sizeof(ctxt->attrHash[0])); |
9513 | | |
9514 | 8.30k | for (i = 0, j = 0; j < nratts; i += 5, j++) { |
9515 | 7.23k | unsigned hashValue, nameHashValue, prefixHashValue; |
9516 | 7.23k | int res; |
9517 | | |
9518 | 7.23k | aprefix = atts[i+1]; |
9519 | 7.23k | if (aprefix == NULL) |
9520 | 2.20k | continue; |
9521 | | |
9522 | 5.02k | attname = atts[i]; |
9523 | | /* Hash values always have bit 31 set, see dict.c */ |
9524 | 5.02k | nameHashValue = ctxt->attallocs[j] | 0x80000000; |
9525 | 5.02k | prefixHashValue = xmlDictComputeHash(ctxt->dict, aprefix); |
9526 | | |
9527 | 5.02k | hashValue = xmlDictCombineHash(nameHashValue, prefixHashValue); |
9528 | 5.02k | res = xmlAttrHashInsertQName(ctxt, attrHashSize, attname, |
9529 | 5.02k | aprefix, hashValue, i); |
9530 | 5.02k | if (res < INT_MAX) |
9531 | 1.15k | xmlErrAttributeDup(ctxt, aprefix, attname); |
9532 | 5.02k | } |
9533 | 1.07k | } |
9534 | | |
9535 | | /* |
9536 | | * Reconstruct attribute pointers |
9537 | | */ |
9538 | 8.73M | for (i = 0, j = 0; i < nbatts; i += 5, j++) { |
9539 | | /* namespace URI */ |
9540 | 4.09M | nsIndex = XML_PTR_TO_INT(atts[i+2]); |
9541 | 4.09M | if (nsIndex == INT_MAX) |
9542 | 3.96M | atts[i+2] = NULL; |
9543 | 128k | else if (nsIndex == INT_MAX - 1) |
9544 | 109k | atts[i+2] = ctxt->str_xml_ns; |
9545 | 19.0k | else |
9546 | 19.0k | atts[i+2] = ctxt->nsTab[nsIndex * 2 + 1]; |
9547 | | |
9548 | 4.09M | if ((j < nratts) && (ctxt->attallocs[j] & 0x80000000) == 0) { |
9549 | 3.75M | atts[i+3] = BASE_PTR + XML_PTR_TO_INT(atts[i+3]); /* value */ |
9550 | 3.75M | atts[i+4] = BASE_PTR + XML_PTR_TO_INT(atts[i+4]); /* valuend */ |
9551 | 3.75M | } |
9552 | 4.09M | } |
9553 | | |
9554 | 4.63M | uri = xmlParserNsLookupUri(ctxt, &hprefix); |
9555 | 4.63M | if ((prefix != NULL) && (uri == NULL)) { |
9556 | 258k | xmlNsErr(ctxt, XML_NS_ERR_UNDEFINED_NAMESPACE, |
9557 | 258k | "Namespace prefix %s on %s is not defined\n", |
9558 | 258k | prefix, localname, NULL); |
9559 | 258k | } |
9560 | 4.63M | *pref = prefix; |
9561 | 4.63M | *URI = uri; |
9562 | | |
9563 | | /* |
9564 | | * SAX callback |
9565 | | */ |
9566 | 4.63M | if ((ctxt->sax != NULL) && (ctxt->sax->startElementNs != NULL) && |
9567 | 4.63M | (!ctxt->disableSAX)) { |
9568 | 3.93M | if (nbNs > 0) |
9569 | 629k | ctxt->sax->startElementNs(ctxt->userData, localname, prefix, uri, |
9570 | 629k | nbNs, ctxt->nsTab + 2 * (ctxt->nsNr - nbNs), |
9571 | 629k | nbatts / 5, nbdef, atts); |
9572 | 3.30M | else |
9573 | 3.30M | ctxt->sax->startElementNs(ctxt->userData, localname, prefix, uri, |
9574 | 3.30M | 0, NULL, nbatts / 5, nbdef, atts); |
9575 | 3.93M | } |
9576 | | |
9577 | 4.63M | done: |
9578 | | /* |
9579 | | * Free allocated attribute values |
9580 | | */ |
9581 | 4.63M | if (attval != 0) { |
9582 | 361k | for (i = 0, j = 0; j < nratts; i += 5, j++) |
9583 | 211k | if (ctxt->attallocs[j] & 0x80000000) |
9584 | 152k | xmlFree((xmlChar *) atts[i+3]); |
9585 | 150k | } |
9586 | | |
9587 | 4.63M | *nbNsPtr = nbNs; |
9588 | 4.63M | return(localname); |
9589 | 4.63M | } |
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 | 1.43M | xmlParseEndTag2(xmlParserCtxtPtr ctxt, const xmlStartTag *tag) { |
9608 | 1.43M | const xmlChar *name; |
9609 | | |
9610 | 1.43M | GROW; |
9611 | 1.43M | if ((RAW != '<') || (NXT(1) != '/')) { |
9612 | 1.80k | xmlFatalErr(ctxt, XML_ERR_LTSLASH_REQUIRED, NULL); |
9613 | 1.80k | return; |
9614 | 1.80k | } |
9615 | 1.43M | SKIP(2); |
9616 | | |
9617 | 1.43M | if (tag->prefix == NULL) |
9618 | 356k | name = xmlParseNameAndCompare(ctxt, ctxt->name); |
9619 | 1.07M | else |
9620 | 1.07M | name = xmlParseQNameAndCompare(ctxt, ctxt->name, tag->prefix); |
9621 | | |
9622 | | /* |
9623 | | * We should definitely be at the ending "S? '>'" part |
9624 | | */ |
9625 | 1.43M | GROW; |
9626 | 1.43M | SKIP_BLANKS; |
9627 | 1.43M | if ((!IS_BYTE_CHAR(RAW)) || (RAW != '>')) { |
9628 | 64.8k | xmlFatalErr(ctxt, XML_ERR_GT_REQUIRED, NULL); |
9629 | 64.8k | } else |
9630 | 1.36M | 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 | 1.43M | if (name != (xmlChar*)1) { |
9639 | 97.8k | if (name == NULL) name = BAD_CAST "unparsable"; |
9640 | 97.8k | xmlFatalErrMsgStrIntStr(ctxt, XML_ERR_TAG_NAME_MISMATCH, |
9641 | 97.8k | "Opening and ending tag mismatch: %s line %d and %s\n", |
9642 | 97.8k | ctxt->name, tag->line, name); |
9643 | 97.8k | } |
9644 | | |
9645 | | /* |
9646 | | * SAX: End of Tag |
9647 | | */ |
9648 | 1.43M | if ((ctxt->sax != NULL) && (ctxt->sax->endElementNs != NULL) && |
9649 | 1.43M | (!ctxt->disableSAX)) |
9650 | 1.20M | ctxt->sax->endElementNs(ctxt->userData, ctxt->name, tag->prefix, |
9651 | 1.20M | tag->URI); |
9652 | | |
9653 | 1.43M | spacePop(ctxt); |
9654 | 1.43M | if (tag->nsNr != 0) |
9655 | 607k | xmlParserNsPop(ctxt, tag->nsNr); |
9656 | 1.43M | } |
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 | 61.2k | xmlParseCDSect(xmlParserCtxtPtr ctxt) { |
9676 | 61.2k | xmlChar *buf = NULL; |
9677 | 61.2k | int len = 0; |
9678 | 61.2k | int size = XML_PARSER_BUFFER_SIZE; |
9679 | 61.2k | int r, rl; |
9680 | 61.2k | int s, sl; |
9681 | 61.2k | int cur, l; |
9682 | 61.2k | int maxLength = (ctxt->options & XML_PARSE_HUGE) ? |
9683 | 0 | XML_MAX_HUGE_LENGTH : |
9684 | 61.2k | XML_MAX_TEXT_LENGTH; |
9685 | | |
9686 | 61.2k | if ((CUR != '<') || (NXT(1) != '!') || (NXT(2) != '[')) |
9687 | 0 | return; |
9688 | 61.2k | SKIP(3); |
9689 | | |
9690 | 61.2k | if (!CMP6(CUR_PTR, 'C', 'D', 'A', 'T', 'A', '[')) |
9691 | 0 | return; |
9692 | 61.2k | SKIP(6); |
9693 | | |
9694 | 61.2k | r = xmlCurrentCharRecover(ctxt, &rl); |
9695 | 61.2k | if (!IS_CHAR(r)) { |
9696 | 787 | xmlFatalErr(ctxt, XML_ERR_CDATA_NOT_FINISHED, NULL); |
9697 | 787 | goto out; |
9698 | 787 | } |
9699 | 60.4k | NEXTL(rl); |
9700 | 60.4k | s = xmlCurrentCharRecover(ctxt, &sl); |
9701 | 60.4k | if (!IS_CHAR(s)) { |
9702 | 1.82k | xmlFatalErr(ctxt, XML_ERR_CDATA_NOT_FINISHED, NULL); |
9703 | 1.82k | goto out; |
9704 | 1.82k | } |
9705 | 58.5k | NEXTL(sl); |
9706 | 58.5k | cur = xmlCurrentCharRecover(ctxt, &l); |
9707 | 58.5k | buf = xmlMalloc(size); |
9708 | 58.5k | if (buf == NULL) { |
9709 | 5 | xmlErrMemory(ctxt); |
9710 | 5 | goto out; |
9711 | 5 | } |
9712 | 20.7M | while (IS_CHAR(cur) && |
9713 | 20.7M | ((r != ']') || (s != ']') || (cur != '>'))) { |
9714 | 20.6M | if (len + 5 >= size) { |
9715 | 3.57k | xmlChar *tmp; |
9716 | 3.57k | int newSize; |
9717 | | |
9718 | 3.57k | newSize = xmlGrowCapacity(size, 1, 1, maxLength); |
9719 | 3.57k | 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 | 3.57k | tmp = xmlRealloc(buf, newSize); |
9725 | 3.57k | if (tmp == NULL) { |
9726 | 1 | xmlErrMemory(ctxt); |
9727 | 1 | goto out; |
9728 | 1 | } |
9729 | 3.57k | buf = tmp; |
9730 | 3.57k | size = newSize; |
9731 | 3.57k | } |
9732 | 20.6M | COPY_BUF(buf, len, r); |
9733 | 20.6M | r = s; |
9734 | 20.6M | rl = sl; |
9735 | 20.6M | s = cur; |
9736 | 20.6M | sl = l; |
9737 | 20.6M | NEXTL(l); |
9738 | 20.6M | cur = xmlCurrentCharRecover(ctxt, &l); |
9739 | 20.6M | } |
9740 | 58.5k | buf[len] = 0; |
9741 | 58.5k | if (cur != '>') { |
9742 | 4.16k | xmlFatalErrMsgStr(ctxt, XML_ERR_CDATA_NOT_FINISHED, |
9743 | 4.16k | "CData section not finished\n%.50s\n", buf); |
9744 | 4.16k | goto out; |
9745 | 4.16k | } |
9746 | 54.4k | NEXTL(l); |
9747 | | |
9748 | | /* |
9749 | | * OK the buffer is to be consumed as cdata. |
9750 | | */ |
9751 | 54.4k | if ((ctxt->sax != NULL) && (!ctxt->disableSAX)) { |
9752 | 53.4k | if ((ctxt->sax->cdataBlock != NULL) && |
9753 | 53.4k | ((ctxt->options & XML_PARSE_NOCDATA) == 0)) { |
9754 | 0 | ctxt->sax->cdataBlock(ctxt->userData, buf, len); |
9755 | 53.4k | } else if (ctxt->sax->characters != NULL) { |
9756 | 53.4k | ctxt->sax->characters(ctxt->userData, buf, len); |
9757 | 53.4k | } |
9758 | 53.4k | } |
9759 | | |
9760 | 61.2k | out: |
9761 | 61.2k | xmlFree(buf); |
9762 | 61.2k | } |
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 | 671k | xmlParseContentInternal(xmlParserCtxtPtr ctxt) { |
9774 | 671k | int oldNameNr = ctxt->nameNr; |
9775 | 671k | int oldSpaceNr = ctxt->spaceNr; |
9776 | 671k | int oldNodeNr = ctxt->nodeNr; |
9777 | | |
9778 | 671k | GROW; |
9779 | 16.0M | while ((ctxt->input->cur < ctxt->input->end) && |
9780 | 16.0M | (PARSER_STOPPED(ctxt) == 0)) { |
9781 | 15.9M | const xmlChar *cur = ctxt->input->cur; |
9782 | | |
9783 | | /* |
9784 | | * First case : a Processing Instruction. |
9785 | | */ |
9786 | 15.9M | if ((*cur == '<') && (cur[1] == '?')) { |
9787 | 40.6k | xmlParsePI(ctxt); |
9788 | 40.6k | } |
9789 | | |
9790 | | /* |
9791 | | * Second case : a CDSection |
9792 | | */ |
9793 | | /* 2.6.0 test was *cur not RAW */ |
9794 | 15.9M | else if (CMP9(CUR_PTR, '<', '!', '[', 'C', 'D', 'A', 'T', 'A', '[')) { |
9795 | 61.2k | xmlParseCDSect(ctxt); |
9796 | 61.2k | } |
9797 | | |
9798 | | /* |
9799 | | * Third case : a comment |
9800 | | */ |
9801 | 15.8M | else if ((*cur == '<') && (NXT(1) == '!') && |
9802 | 15.8M | (NXT(2) == '-') && (NXT(3) == '-')) { |
9803 | 102k | xmlParseComment(ctxt); |
9804 | 102k | } |
9805 | | |
9806 | | /* |
9807 | | * Fourth case : a sub-element. |
9808 | | */ |
9809 | 15.7M | else if (*cur == '<') { |
9810 | 5.78M | if (NXT(1) == '/') { |
9811 | 1.43M | if (ctxt->nameNr <= oldNameNr) |
9812 | 615k | break; |
9813 | 820k | xmlParseElementEnd(ctxt); |
9814 | 4.34M | } else { |
9815 | 4.34M | xmlParseElementStart(ctxt); |
9816 | 4.34M | } |
9817 | 5.78M | } |
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 | 9.96M | else if (*cur == '&') { |
9825 | 284k | xmlParseReference(ctxt); |
9826 | 284k | } |
9827 | | |
9828 | | /* |
9829 | | * Last case, text. Note that References are handled directly. |
9830 | | */ |
9831 | 9.67M | else { |
9832 | 9.67M | xmlParseCharDataInternal(ctxt, 0); |
9833 | 9.67M | } |
9834 | | |
9835 | 15.3M | SHRINK; |
9836 | 15.3M | GROW; |
9837 | 15.3M | } |
9838 | | |
9839 | 671k | if ((ctxt->nameNr > oldNameNr) && |
9840 | 671k | (ctxt->input->cur >= ctxt->input->end) && |
9841 | 671k | (ctxt->wellFormed)) { |
9842 | 509 | const xmlChar *name = ctxt->nameTab[ctxt->nameNr - 1]; |
9843 | 509 | int line = ctxt->pushTab[ctxt->nameNr - 1].line; |
9844 | 509 | xmlFatalErrMsgStrIntStr(ctxt, XML_ERR_TAG_NOT_FINISHED, |
9845 | 509 | "Premature end of data in tag %s line %d\n", |
9846 | 509 | name, line, NULL); |
9847 | 509 | } |
9848 | | |
9849 | | /* |
9850 | | * Clean up in error case |
9851 | | */ |
9852 | | |
9853 | 857k | while (ctxt->nodeNr > oldNodeNr) |
9854 | 185k | nodePop(ctxt); |
9855 | | |
9856 | 1.04M | while (ctxt->nameNr > oldNameNr) { |
9857 | 374k | xmlStartTag *tag = &ctxt->pushTab[ctxt->nameNr - 1]; |
9858 | | |
9859 | 374k | if (tag->nsNr != 0) |
9860 | 45.8k | xmlParserNsPop(ctxt, tag->nsNr); |
9861 | | |
9862 | 374k | namePop(ctxt); |
9863 | 374k | } |
9864 | | |
9865 | 1.04M | while (ctxt->spaceNr > oldSpaceNr) |
9866 | 374k | spacePop(ctxt); |
9867 | 671k | } |
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 | 706k | xmlParseElement(xmlParserCtxtPtr ctxt) { |
9907 | 706k | if (xmlParseElementStart(ctxt) != 0) |
9908 | 44.1k | return; |
9909 | | |
9910 | 662k | xmlParseContentInternal(ctxt); |
9911 | | |
9912 | 662k | if (ctxt->input->cur >= ctxt->input->end) { |
9913 | 46.1k | if (ctxt->wellFormed) { |
9914 | 550 | const xmlChar *name = ctxt->nameTab[ctxt->nameNr - 1]; |
9915 | 550 | int line = ctxt->pushTab[ctxt->nameNr - 1].line; |
9916 | 550 | xmlFatalErrMsgStrIntStr(ctxt, XML_ERR_TAG_NOT_FINISHED, |
9917 | 550 | "Premature end of data in tag %s line %d\n", |
9918 | 550 | name, line, NULL); |
9919 | 550 | } |
9920 | 46.1k | return; |
9921 | 46.1k | } |
9922 | | |
9923 | 616k | xmlParseElementEnd(ctxt); |
9924 | 616k | } |
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 | 5.05M | xmlParseElementStart(xmlParserCtxtPtr ctxt) { |
9937 | 5.05M | int maxDepth = (ctxt->options & XML_PARSE_HUGE) ? 2048 : 256; |
9938 | 5.05M | const xmlChar *name; |
9939 | 5.05M | const xmlChar *prefix = NULL; |
9940 | 5.05M | const xmlChar *URI = NULL; |
9941 | 5.05M | xmlParserNodeInfo node_info; |
9942 | 5.05M | int line; |
9943 | 5.05M | xmlNodePtr cur; |
9944 | 5.05M | int nbNs = 0; |
9945 | | |
9946 | 5.05M | if (ctxt->nameNr > maxDepth) { |
9947 | 308 | xmlFatalErrMsgInt(ctxt, XML_ERR_RESOURCE_LIMIT, |
9948 | 308 | "Excessive depth in document: %d use XML_PARSE_HUGE option\n", |
9949 | 308 | ctxt->nameNr); |
9950 | 308 | xmlHaltParser(ctxt); |
9951 | 308 | return(-1); |
9952 | 308 | } |
9953 | | |
9954 | | /* Capture start position */ |
9955 | 5.05M | 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 | 5.05M | if (ctxt->spaceNr == 0) |
9962 | 0 | spacePush(ctxt, -1); |
9963 | 5.05M | else if (*ctxt->space == -2) |
9964 | 0 | spacePush(ctxt, -1); |
9965 | 5.05M | else |
9966 | 5.05M | spacePush(ctxt, *ctxt->space); |
9967 | | |
9968 | 5.05M | line = ctxt->input->line; |
9969 | | #ifdef LIBXML_SAX1_ENABLED |
9970 | | if (ctxt->sax2) |
9971 | | #endif /* LIBXML_SAX1_ENABLED */ |
9972 | 5.05M | name = xmlParseStartTag2(ctxt, &prefix, &URI, &nbNs); |
9973 | | #ifdef LIBXML_SAX1_ENABLED |
9974 | | else |
9975 | | name = xmlParseStartTag(ctxt); |
9976 | | #endif /* LIBXML_SAX1_ENABLED */ |
9977 | 5.05M | if (name == NULL) { |
9978 | 417k | spacePop(ctxt); |
9979 | 417k | return(-1); |
9980 | 417k | } |
9981 | 4.63M | nameNsPush(ctxt, name, prefix, URI, line, nbNs); |
9982 | 4.63M | cur = ctxt->node; |
9983 | | |
9984 | | #ifdef LIBXML_VALID_ENABLED |
9985 | | /* |
9986 | | * [ VC: Root Element Type ] |
9987 | | * The Name in the document type declaration must match the element |
9988 | | * type of the root element. |
9989 | | */ |
9990 | | if (ctxt->validate && ctxt->wellFormed && ctxt->myDoc && |
9991 | | ctxt->node && (ctxt->node == ctxt->myDoc->children)) |
9992 | | ctxt->valid &= xmlValidateRoot(&ctxt->vctxt, ctxt->myDoc); |
9993 | | #endif /* LIBXML_VALID_ENABLED */ |
9994 | | |
9995 | | /* |
9996 | | * Check for an Empty Element. |
9997 | | */ |
9998 | 4.63M | if ((RAW == '/') && (NXT(1) == '>')) { |
9999 | 2.56M | SKIP(2); |
10000 | 2.56M | if (ctxt->sax2) { |
10001 | 2.56M | if ((ctxt->sax != NULL) && (ctxt->sax->endElementNs != NULL) && |
10002 | 2.56M | (!ctxt->disableSAX)) |
10003 | 2.47M | 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 | 2.56M | } |
10011 | 2.56M | namePop(ctxt); |
10012 | 2.56M | spacePop(ctxt); |
10013 | 2.56M | if (nbNs > 0) |
10014 | 14.6k | xmlParserNsPop(ctxt, nbNs); |
10015 | 2.56M | 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 | 2.56M | return(1); |
10023 | 2.56M | } |
10024 | 2.07M | if (RAW == '>') { |
10025 | 1.85M | NEXT1; |
10026 | 1.85M | 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 | 1.85M | } else { |
10033 | 215k | xmlFatalErrMsgStrIntStr(ctxt, XML_ERR_GT_REQUIRED, |
10034 | 215k | "Couldn't find end of Start Tag %s line %d\n", |
10035 | 215k | name, line, NULL); |
10036 | | |
10037 | | /* |
10038 | | * end of parsing of this node. |
10039 | | */ |
10040 | 215k | nodePop(ctxt); |
10041 | 215k | namePop(ctxt); |
10042 | 215k | spacePop(ctxt); |
10043 | 215k | if (nbNs > 0) |
10044 | 26.8k | xmlParserNsPop(ctxt, nbNs); |
10045 | 215k | return(-1); |
10046 | 215k | } |
10047 | | |
10048 | 1.85M | return(0); |
10049 | 2.07M | } |
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 | 1.43M | xmlParseElementEnd(xmlParserCtxtPtr ctxt) { |
10059 | 1.43M | xmlNodePtr cur = ctxt->node; |
10060 | | |
10061 | 1.43M | if (ctxt->nameNr <= 0) { |
10062 | 678 | if ((RAW == '<') && (NXT(1) == '/')) |
10063 | 3 | SKIP(2); |
10064 | 678 | return; |
10065 | 678 | } |
10066 | | |
10067 | | /* |
10068 | | * parse the end of tag: '</' should be here. |
10069 | | */ |
10070 | 1.43M | if (ctxt->sax2) { |
10071 | 1.43M | xmlParseEndTag2(ctxt, &ctxt->pushTab[ctxt->nameNr - 1]); |
10072 | 1.43M | namePop(ctxt); |
10073 | 1.43M | } |
10074 | | #ifdef LIBXML_SAX1_ENABLED |
10075 | | else |
10076 | | xmlParseEndTag1(ctxt, 0); |
10077 | | #endif /* LIBXML_SAX1_ENABLED */ |
10078 | | |
10079 | | /* |
10080 | | * Capture end position |
10081 | | */ |
10082 | 1.43M | 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 | 1.43M | } |
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 | 174k | xmlParseVersionNum(xmlParserCtxtPtr ctxt) { |
10110 | 174k | xmlChar *buf = NULL; |
10111 | 174k | int len = 0; |
10112 | 174k | int size = 10; |
10113 | 174k | int maxLength = (ctxt->options & XML_PARSE_HUGE) ? |
10114 | 0 | XML_MAX_TEXT_LENGTH : |
10115 | 174k | XML_MAX_NAME_LENGTH; |
10116 | 174k | xmlChar cur; |
10117 | | |
10118 | 174k | buf = xmlMalloc(size); |
10119 | 174k | if (buf == NULL) { |
10120 | 11 | xmlErrMemory(ctxt); |
10121 | 11 | return(NULL); |
10122 | 11 | } |
10123 | 174k | cur = CUR; |
10124 | 174k | if (!((cur >= '0') && (cur <= '9'))) { |
10125 | 1.66k | xmlFree(buf); |
10126 | 1.66k | return(NULL); |
10127 | 1.66k | } |
10128 | 172k | buf[len++] = cur; |
10129 | 172k | NEXT; |
10130 | 172k | cur=CUR; |
10131 | 172k | if (cur != '.') { |
10132 | 5.77k | xmlFree(buf); |
10133 | 5.77k | return(NULL); |
10134 | 5.77k | } |
10135 | 166k | buf[len++] = cur; |
10136 | 166k | NEXT; |
10137 | 166k | cur=CUR; |
10138 | 305k | while ((cur >= '0') && (cur <= '9')) { |
10139 | 138k | if (len + 1 >= size) { |
10140 | 654 | xmlChar *tmp; |
10141 | 654 | int newSize; |
10142 | | |
10143 | 654 | newSize = xmlGrowCapacity(size, 1, 1, maxLength); |
10144 | 654 | if (newSize < 0) { |
10145 | 0 | xmlFatalErr(ctxt, XML_ERR_NAME_TOO_LONG, "VersionNum"); |
10146 | 0 | xmlFree(buf); |
10147 | 0 | return(NULL); |
10148 | 0 | } |
10149 | 654 | tmp = xmlRealloc(buf, newSize); |
10150 | 654 | if (tmp == NULL) { |
10151 | 1 | xmlErrMemory(ctxt); |
10152 | 1 | xmlFree(buf); |
10153 | 1 | return(NULL); |
10154 | 1 | } |
10155 | 653 | buf = tmp; |
10156 | 653 | size = newSize; |
10157 | 653 | } |
10158 | 138k | buf[len++] = cur; |
10159 | 138k | NEXT; |
10160 | 138k | cur=CUR; |
10161 | 138k | } |
10162 | 166k | buf[len] = 0; |
10163 | 166k | return(buf); |
10164 | 166k | } |
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 | 201k | xmlParseVersionInfo(xmlParserCtxtPtr ctxt) { |
10183 | 201k | xmlChar *version = NULL; |
10184 | | |
10185 | 201k | if (CMP7(CUR_PTR, 'v', 'e', 'r', 's', 'i', 'o', 'n')) { |
10186 | 179k | SKIP(7); |
10187 | 179k | SKIP_BLANKS; |
10188 | 179k | if (RAW != '=') { |
10189 | 2.07k | xmlFatalErr(ctxt, XML_ERR_EQUAL_REQUIRED, NULL); |
10190 | 2.07k | return(NULL); |
10191 | 2.07k | } |
10192 | 177k | NEXT; |
10193 | 177k | SKIP_BLANKS; |
10194 | 177k | if (RAW == '"') { |
10195 | 168k | NEXT; |
10196 | 168k | version = xmlParseVersionNum(ctxt); |
10197 | 168k | if (RAW != '"') { |
10198 | 12.9k | xmlFatalErr(ctxt, XML_ERR_STRING_NOT_CLOSED, NULL); |
10199 | 12.9k | } else |
10200 | 155k | NEXT; |
10201 | 168k | } else if (RAW == '\''){ |
10202 | 5.88k | NEXT; |
10203 | 5.88k | version = xmlParseVersionNum(ctxt); |
10204 | 5.88k | if (RAW != '\'') { |
10205 | 992 | xmlFatalErr(ctxt, XML_ERR_STRING_NOT_CLOSED, NULL); |
10206 | 992 | } else |
10207 | 4.88k | NEXT; |
10208 | 5.88k | } else { |
10209 | 3.38k | xmlFatalErr(ctxt, XML_ERR_STRING_NOT_STARTED, NULL); |
10210 | 3.38k | } |
10211 | 177k | } |
10212 | 199k | return(version); |
10213 | 201k | } |
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 | 127k | xmlParseEncName(xmlParserCtxtPtr ctxt) { |
10229 | 127k | xmlChar *buf = NULL; |
10230 | 127k | int len = 0; |
10231 | 127k | int size = 10; |
10232 | 127k | int maxLength = (ctxt->options & XML_PARSE_HUGE) ? |
10233 | 0 | XML_MAX_TEXT_LENGTH : |
10234 | 127k | XML_MAX_NAME_LENGTH; |
10235 | 127k | xmlChar cur; |
10236 | | |
10237 | 127k | cur = CUR; |
10238 | 127k | if (((cur >= 'a') && (cur <= 'z')) || |
10239 | 127k | ((cur >= 'A') && (cur <= 'Z'))) { |
10240 | 126k | buf = xmlMalloc(size); |
10241 | 126k | if (buf == NULL) { |
10242 | 10 | xmlErrMemory(ctxt); |
10243 | 10 | return(NULL); |
10244 | 10 | } |
10245 | | |
10246 | 126k | buf[len++] = cur; |
10247 | 126k | NEXT; |
10248 | 126k | cur = CUR; |
10249 | 15.2M | while (((cur >= 'a') && (cur <= 'z')) || |
10250 | 15.2M | ((cur >= 'A') && (cur <= 'Z')) || |
10251 | 15.2M | ((cur >= '0') && (cur <= '9')) || |
10252 | 15.2M | (cur == '.') || (cur == '_') || |
10253 | 15.2M | (cur == '-')) { |
10254 | 15.0M | if (len + 1 >= size) { |
10255 | 76.7k | xmlChar *tmp; |
10256 | 76.7k | int newSize; |
10257 | | |
10258 | 76.7k | newSize = xmlGrowCapacity(size, 1, 1, maxLength); |
10259 | 76.7k | if (newSize < 0) { |
10260 | 234 | xmlFatalErr(ctxt, XML_ERR_NAME_TOO_LONG, "EncName"); |
10261 | 234 | xmlFree(buf); |
10262 | 234 | return(NULL); |
10263 | 234 | } |
10264 | 76.4k | tmp = xmlRealloc(buf, newSize); |
10265 | 76.4k | if (tmp == NULL) { |
10266 | 3 | xmlErrMemory(ctxt); |
10267 | 3 | xmlFree(buf); |
10268 | 3 | return(NULL); |
10269 | 3 | } |
10270 | 76.4k | buf = tmp; |
10271 | 76.4k | size = newSize; |
10272 | 76.4k | } |
10273 | 15.0M | buf[len++] = cur; |
10274 | 15.0M | NEXT; |
10275 | 15.0M | cur = CUR; |
10276 | 15.0M | } |
10277 | 125k | buf[len] = 0; |
10278 | 125k | } else { |
10279 | 1.79k | xmlFatalErr(ctxt, XML_ERR_ENCODING_NAME, NULL); |
10280 | 1.79k | } |
10281 | 127k | return(buf); |
10282 | 127k | } |
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 | 177k | xmlParseEncodingDecl(xmlParserCtxtPtr ctxt) { |
10301 | 177k | xmlChar *encoding = NULL; |
10302 | | |
10303 | 177k | SKIP_BLANKS; |
10304 | 177k | if (CMP8(CUR_PTR, 'e', 'n', 'c', 'o', 'd', 'i', 'n', 'g') == 0) |
10305 | 48.7k | return(NULL); |
10306 | | |
10307 | 128k | SKIP(8); |
10308 | 128k | SKIP_BLANKS; |
10309 | 128k | if (RAW != '=') { |
10310 | 469 | xmlFatalErr(ctxt, XML_ERR_EQUAL_REQUIRED, NULL); |
10311 | 469 | return(NULL); |
10312 | 469 | } |
10313 | 128k | NEXT; |
10314 | 128k | SKIP_BLANKS; |
10315 | 128k | if (RAW == '"') { |
10316 | 125k | NEXT; |
10317 | 125k | encoding = xmlParseEncName(ctxt); |
10318 | 125k | if (RAW != '"') { |
10319 | 3.58k | xmlFatalErr(ctxt, XML_ERR_STRING_NOT_CLOSED, NULL); |
10320 | 3.58k | xmlFree((xmlChar *) encoding); |
10321 | 3.58k | return(NULL); |
10322 | 3.58k | } else |
10323 | 121k | NEXT; |
10324 | 125k | } else if (RAW == '\''){ |
10325 | 2.69k | NEXT; |
10326 | 2.69k | encoding = xmlParseEncName(ctxt); |
10327 | 2.69k | if (RAW != '\'') { |
10328 | 306 | xmlFatalErr(ctxt, XML_ERR_STRING_NOT_CLOSED, NULL); |
10329 | 306 | xmlFree((xmlChar *) encoding); |
10330 | 306 | return(NULL); |
10331 | 306 | } else |
10332 | 2.38k | NEXT; |
10333 | 2.69k | } else { |
10334 | 497 | xmlFatalErr(ctxt, XML_ERR_STRING_NOT_STARTED, NULL); |
10335 | 497 | } |
10336 | | |
10337 | 124k | if (encoding == NULL) |
10338 | 504 | return(NULL); |
10339 | | |
10340 | 124k | xmlSetDeclaredEncoding(ctxt, encoding); |
10341 | | |
10342 | 124k | return(ctxt->encoding); |
10343 | 124k | } |
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 | 80.8k | xmlParseSDDecl(xmlParserCtxtPtr ctxt) { |
10380 | 80.8k | int standalone = -2; |
10381 | | |
10382 | 80.8k | SKIP_BLANKS; |
10383 | 80.8k | if (CMP10(CUR_PTR, 's', 't', 'a', 'n', 'd', 'a', 'l', 'o', 'n', 'e')) { |
10384 | 11.2k | SKIP(10); |
10385 | 11.2k | SKIP_BLANKS; |
10386 | 11.2k | if (RAW != '=') { |
10387 | 2.02k | xmlFatalErr(ctxt, XML_ERR_EQUAL_REQUIRED, NULL); |
10388 | 2.02k | return(standalone); |
10389 | 2.02k | } |
10390 | 9.18k | NEXT; |
10391 | 9.18k | SKIP_BLANKS; |
10392 | 9.18k | if (RAW == '\''){ |
10393 | 3.31k | NEXT; |
10394 | 3.31k | if ((RAW == 'n') && (NXT(1) == 'o')) { |
10395 | 1.40k | standalone = 0; |
10396 | 1.40k | SKIP(2); |
10397 | 1.90k | } else if ((RAW == 'y') && (NXT(1) == 'e') && |
10398 | 1.90k | (NXT(2) == 's')) { |
10399 | 754 | standalone = 1; |
10400 | 754 | SKIP(3); |
10401 | 1.15k | } else { |
10402 | 1.15k | xmlFatalErr(ctxt, XML_ERR_STANDALONE_VALUE, NULL); |
10403 | 1.15k | } |
10404 | 3.31k | if (RAW != '\'') { |
10405 | 2.75k | xmlFatalErr(ctxt, XML_ERR_STRING_NOT_CLOSED, NULL); |
10406 | 2.75k | } else |
10407 | 562 | NEXT; |
10408 | 5.87k | } else if (RAW == '"'){ |
10409 | 5.53k | NEXT; |
10410 | 5.53k | if ((RAW == 'n') && (NXT(1) == 'o')) { |
10411 | 3.53k | standalone = 0; |
10412 | 3.53k | SKIP(2); |
10413 | 3.53k | } else if ((RAW == 'y') && (NXT(1) == 'e') && |
10414 | 1.99k | (NXT(2) == 's')) { |
10415 | 1.00k | standalone = 1; |
10416 | 1.00k | SKIP(3); |
10417 | 1.00k | } else { |
10418 | 993 | xmlFatalErr(ctxt, XML_ERR_STANDALONE_VALUE, NULL); |
10419 | 993 | } |
10420 | 5.53k | if (RAW != '"') { |
10421 | 2.21k | xmlFatalErr(ctxt, XML_ERR_STRING_NOT_CLOSED, NULL); |
10422 | 2.21k | } else |
10423 | 3.31k | NEXT; |
10424 | 5.53k | } else { |
10425 | 340 | xmlFatalErr(ctxt, XML_ERR_STRING_NOT_STARTED, NULL); |
10426 | 340 | } |
10427 | 9.18k | } |
10428 | 78.8k | return(standalone); |
10429 | 80.8k | } |
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 | 181k | xmlParseXMLDecl(xmlParserCtxtPtr ctxt) { |
10444 | 181k | 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 | 181k | ctxt->standalone = -2; |
10453 | | |
10454 | | /* |
10455 | | * We know that '<?xml' is here. |
10456 | | */ |
10457 | 181k | SKIP(5); |
10458 | | |
10459 | 181k | if (!IS_BLANK_CH(RAW)) { |
10460 | 0 | xmlFatalErrMsg(ctxt, XML_ERR_SPACE_REQUIRED, |
10461 | 0 | "Blank needed after '<?xml'\n"); |
10462 | 0 | } |
10463 | 181k | SKIP_BLANKS; |
10464 | | |
10465 | | /* |
10466 | | * We must have the VersionInfo here. |
10467 | | */ |
10468 | 181k | version = xmlParseVersionInfo(ctxt); |
10469 | 181k | if (version == NULL) { |
10470 | 26.4k | xmlFatalErr(ctxt, XML_ERR_VERSION_MISSING, NULL); |
10471 | 155k | } else { |
10472 | 155k | if (!xmlStrEqual(version, (const xmlChar *) XML_DEFAULT_VERSION)) { |
10473 | | /* |
10474 | | * Changed here for XML-1.0 5th edition |
10475 | | */ |
10476 | 66.1k | if (ctxt->options & XML_PARSE_OLD10) { |
10477 | 0 | xmlFatalErrMsgStr(ctxt, XML_ERR_UNKNOWN_VERSION, |
10478 | 0 | "Unsupported version '%s'\n", |
10479 | 0 | version); |
10480 | 66.1k | } else { |
10481 | 66.1k | if ((version[0] == '1') && ((version[1] == '.'))) { |
10482 | 56.2k | xmlWarningMsg(ctxt, XML_WAR_UNKNOWN_VERSION, |
10483 | 56.2k | "Unsupported version '%s'\n", |
10484 | 56.2k | version, NULL); |
10485 | 56.2k | } else { |
10486 | 9.94k | xmlFatalErrMsgStr(ctxt, XML_ERR_UNKNOWN_VERSION, |
10487 | 9.94k | "Unsupported version '%s'\n", |
10488 | 9.94k | version); |
10489 | 9.94k | } |
10490 | 66.1k | } |
10491 | 66.1k | } |
10492 | 155k | if (ctxt->version != NULL) |
10493 | 0 | xmlFree((void *) ctxt->version); |
10494 | 155k | ctxt->version = version; |
10495 | 155k | } |
10496 | | |
10497 | | /* |
10498 | | * We may have the encoding declaration |
10499 | | */ |
10500 | 181k | if (!IS_BLANK_CH(RAW)) { |
10501 | 52.5k | if ((RAW == '?') && (NXT(1) == '>')) { |
10502 | 24.1k | SKIP(2); |
10503 | 24.1k | return; |
10504 | 24.1k | } |
10505 | 28.3k | xmlFatalErrMsg(ctxt, XML_ERR_SPACE_REQUIRED, "Blank needed here\n"); |
10506 | 28.3k | } |
10507 | 157k | xmlParseEncodingDecl(ctxt); |
10508 | | |
10509 | | /* |
10510 | | * We may have the standalone status. |
10511 | | */ |
10512 | 157k | if ((ctxt->encoding != NULL) && (!IS_BLANK_CH(RAW))) { |
10513 | 78.6k | if ((RAW == '?') && (NXT(1) == '>')) { |
10514 | 76.5k | SKIP(2); |
10515 | 76.5k | return; |
10516 | 76.5k | } |
10517 | 2.15k | xmlFatalErrMsg(ctxt, XML_ERR_SPACE_REQUIRED, "Blank needed here\n"); |
10518 | 2.15k | } |
10519 | | |
10520 | | /* |
10521 | | * We can grow the input buffer freely at that point |
10522 | | */ |
10523 | 80.8k | GROW; |
10524 | | |
10525 | 80.8k | SKIP_BLANKS; |
10526 | 80.8k | ctxt->standalone = xmlParseSDDecl(ctxt); |
10527 | | |
10528 | 80.8k | SKIP_BLANKS; |
10529 | 80.8k | if ((RAW == '?') && (NXT(1) == '>')) { |
10530 | 29.3k | SKIP(2); |
10531 | 51.5k | } else if (RAW == '>') { |
10532 | | /* Deprecated old WD ... */ |
10533 | 1.44k | xmlFatalErr(ctxt, XML_ERR_XMLDECL_NOT_FINISHED, NULL); |
10534 | 1.44k | NEXT; |
10535 | 50.0k | } else { |
10536 | 50.0k | int c; |
10537 | | |
10538 | 50.0k | xmlFatalErr(ctxt, XML_ERR_XMLDECL_NOT_FINISHED, NULL); |
10539 | 2.55M | while ((PARSER_STOPPED(ctxt) == 0) && |
10540 | 2.55M | ((c = CUR) != 0)) { |
10541 | 2.53M | NEXT; |
10542 | 2.53M | if (c == '>') |
10543 | 37.5k | break; |
10544 | 2.53M | } |
10545 | 50.0k | } |
10546 | 80.8k | } |
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 | 1.71M | xmlParseMisc(xmlParserCtxtPtr ctxt) { |
10593 | 1.80M | while (PARSER_STOPPED(ctxt) == 0) { |
10594 | 1.76M | SKIP_BLANKS; |
10595 | 1.76M | GROW; |
10596 | 1.76M | if ((RAW == '<') && (NXT(1) == '?')) { |
10597 | 64.4k | xmlParsePI(ctxt); |
10598 | 1.69M | } else if (CMP4(CUR_PTR, '<', '!', '-', '-')) { |
10599 | 22.8k | xmlParseComment(ctxt); |
10600 | 1.67M | } else { |
10601 | 1.67M | break; |
10602 | 1.67M | } |
10603 | 1.76M | } |
10604 | 1.71M | } |
10605 | | |
10606 | | static void |
10607 | 856k | xmlFinishDocument(xmlParserCtxtPtr ctxt) { |
10608 | 856k | xmlDocPtr doc; |
10609 | | |
10610 | | /* |
10611 | | * SAX: end of the document processing. |
10612 | | */ |
10613 | 856k | if ((ctxt->sax) && (ctxt->sax->endDocument != NULL)) |
10614 | 856k | ctxt->sax->endDocument(ctxt->userData); |
10615 | | |
10616 | 856k | doc = ctxt->myDoc; |
10617 | 856k | if (doc != NULL) { |
10618 | 814k | if (ctxt->wellFormed) { |
10619 | 616k | doc->properties |= XML_DOC_WELLFORMED; |
10620 | 616k | if (ctxt->valid) |
10621 | 616k | doc->properties |= XML_DOC_DTDVALID; |
10622 | 616k | if (ctxt->nsWellFormed) |
10623 | 453k | doc->properties |= XML_DOC_NSVALID; |
10624 | 616k | } |
10625 | | |
10626 | 814k | 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 | 814k | if (xmlStrEqual(doc->version, SAX_COMPAT_MODE)) { |
10633 | 15.3k | xmlFreeDoc(doc); |
10634 | 15.3k | ctxt->myDoc = NULL; |
10635 | 15.3k | } |
10636 | 814k | } |
10637 | 856k | } |
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 | 858k | xmlParseDocument(xmlParserCtxtPtr ctxt) { |
10652 | 858k | if ((ctxt == NULL) || (ctxt->input == NULL)) |
10653 | 0 | return(-1); |
10654 | | |
10655 | 858k | GROW; |
10656 | | |
10657 | | /* |
10658 | | * SAX: detecting the level. |
10659 | | */ |
10660 | 858k | xmlCtxtInitializeLate(ctxt); |
10661 | | |
10662 | 858k | if ((ctxt->sax) && (ctxt->sax->setDocumentLocator)) { |
10663 | 858k | ctxt->sax->setDocumentLocator(ctxt->userData, |
10664 | 858k | (xmlSAXLocator *) &xmlDefaultSAXLocator); |
10665 | 858k | } |
10666 | | |
10667 | 858k | xmlDetectEncoding(ctxt); |
10668 | | |
10669 | 858k | if (CUR == 0) { |
10670 | 1.95k | xmlFatalErr(ctxt, XML_ERR_DOCUMENT_EMPTY, NULL); |
10671 | 1.95k | return(-1); |
10672 | 1.95k | } |
10673 | | |
10674 | 856k | GROW; |
10675 | 856k | 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 | 181k | xmlParseXMLDecl(ctxt); |
10681 | 181k | SKIP_BLANKS; |
10682 | 675k | } else { |
10683 | 675k | ctxt->version = xmlCharStrdup(XML_DEFAULT_VERSION); |
10684 | 675k | if (ctxt->version == NULL) { |
10685 | 43 | xmlErrMemory(ctxt); |
10686 | 43 | return(-1); |
10687 | 43 | } |
10688 | 675k | } |
10689 | 856k | if ((ctxt->sax) && (ctxt->sax->startDocument) && (!ctxt->disableSAX)) |
10690 | 798k | ctxt->sax->startDocument(ctxt->userData); |
10691 | 856k | if ((ctxt->myDoc != NULL) && (ctxt->input != NULL) && |
10692 | 856k | (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 | 856k | xmlParseMisc(ctxt); |
10700 | | |
10701 | | /* |
10702 | | * Then possibly doc type declaration(s) and more Misc |
10703 | | * (doctypedecl Misc*)? |
10704 | | */ |
10705 | 856k | GROW; |
10706 | 856k | if (CMP9(CUR_PTR, '<', '!', 'D', 'O', 'C', 'T', 'Y', 'P', 'E')) { |
10707 | | |
10708 | 154k | ctxt->inSubset = 1; |
10709 | 154k | xmlParseDocTypeDecl(ctxt); |
10710 | 154k | if (RAW == '[') { |
10711 | 144k | xmlParseInternalSubset(ctxt); |
10712 | 144k | } else if (RAW == '>') { |
10713 | 6.16k | NEXT; |
10714 | 6.16k | } |
10715 | | |
10716 | | /* |
10717 | | * Create and update the external subset. |
10718 | | */ |
10719 | 154k | ctxt->inSubset = 2; |
10720 | 154k | if ((ctxt->sax != NULL) && (ctxt->sax->externalSubset != NULL) && |
10721 | 154k | (!ctxt->disableSAX)) |
10722 | 33.7k | ctxt->sax->externalSubset(ctxt->userData, ctxt->intSubName, |
10723 | 33.7k | ctxt->extSubSystem, ctxt->extSubURI); |
10724 | 154k | ctxt->inSubset = 0; |
10725 | | |
10726 | 154k | xmlCleanSpecialAttr(ctxt); |
10727 | | |
10728 | 154k | xmlParseMisc(ctxt); |
10729 | 154k | } |
10730 | | |
10731 | | /* |
10732 | | * Time to start parsing the tree itself |
10733 | | */ |
10734 | 856k | GROW; |
10735 | 856k | if (RAW != '<') { |
10736 | 150k | if (ctxt->wellFormed) |
10737 | 4.59k | xmlFatalErrMsg(ctxt, XML_ERR_DOCUMENT_EMPTY, |
10738 | 4.59k | "Start tag expected, '<' not found\n"); |
10739 | 706k | } else { |
10740 | 706k | xmlParseElement(ctxt); |
10741 | | |
10742 | | /* |
10743 | | * The Misc part at the end |
10744 | | */ |
10745 | 706k | xmlParseMisc(ctxt); |
10746 | | |
10747 | 706k | xmlParserCheckEOF(ctxt, XML_ERR_DOCUMENT_END); |
10748 | 706k | } |
10749 | | |
10750 | 856k | ctxt->instate = XML_PARSER_EOF; |
10751 | 856k | xmlFinishDocument(ctxt); |
10752 | | |
10753 | 856k | if (! ctxt->wellFormed) { |
10754 | 240k | ctxt->valid = 0; |
10755 | 240k | return(-1); |
10756 | 240k | } |
10757 | | |
10758 | 616k | return(0); |
10759 | 856k | } |
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 | 24.0M | xmlStopParser(xmlParserCtxtPtr ctxt) { |
11676 | 24.0M | if (ctxt == NULL) |
11677 | 24.0M | 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 | 9.13k | int hasTextDecl, int buildTree) { |
11953 | 9.13k | xmlNodePtr root = NULL; |
11954 | 9.13k | xmlNodePtr list = NULL; |
11955 | 9.13k | xmlChar *rootName = BAD_CAST "#root"; |
11956 | 9.13k | int result; |
11957 | | |
11958 | 9.13k | if (buildTree) { |
11959 | 9.13k | root = xmlNewDocNode(ctxt->myDoc, NULL, rootName, NULL); |
11960 | 9.13k | if (root == NULL) { |
11961 | 2 | xmlErrMemory(ctxt); |
11962 | 2 | goto error; |
11963 | 2 | } |
11964 | 9.13k | } |
11965 | | |
11966 | 9.12k | if (xmlCtxtPushInput(ctxt, input) < 0) |
11967 | 1 | goto error; |
11968 | | |
11969 | 9.12k | nameNsPush(ctxt, rootName, NULL, NULL, 0, 0); |
11970 | 9.12k | spacePush(ctxt, -1); |
11971 | | |
11972 | 9.12k | if (buildTree) |
11973 | 9.12k | nodePush(ctxt, root); |
11974 | | |
11975 | 9.12k | if (hasTextDecl) { |
11976 | 8.11k | xmlDetectEncoding(ctxt); |
11977 | | |
11978 | | /* |
11979 | | * Parse a possible text declaration first |
11980 | | */ |
11981 | 8.11k | if ((CMP5(CUR_PTR, '<', '?', 'x', 'm', 'l')) && |
11982 | 8.11k | (IS_BLANK_CH(NXT(5)))) { |
11983 | 1.97k | xmlParseTextDecl(ctxt); |
11984 | | /* |
11985 | | * An XML-1.0 document can't reference an entity not XML-1.0 |
11986 | | */ |
11987 | 1.97k | if ((xmlStrEqual(ctxt->version, BAD_CAST "1.0")) && |
11988 | 1.97k | (!xmlStrEqual(ctxt->input->version, BAD_CAST "1.0"))) { |
11989 | 957 | xmlFatalErrMsg(ctxt, XML_ERR_VERSION_MISMATCH, |
11990 | 957 | "Version mismatch between document and " |
11991 | 957 | "entity\n"); |
11992 | 957 | } |
11993 | 1.97k | } |
11994 | 8.11k | } |
11995 | | |
11996 | 9.12k | xmlParseContentInternal(ctxt); |
11997 | | |
11998 | 9.12k | if (ctxt->input->cur < ctxt->input->end) |
11999 | 1.58k | xmlFatalErr(ctxt, XML_ERR_NOT_WELL_BALANCED, NULL); |
12000 | | |
12001 | 9.12k | if ((ctxt->wellFormed) || |
12002 | 9.12k | ((ctxt->recovery) && (!xmlCtxtIsCatastrophicError(ctxt)))) { |
12003 | 2.89k | if (root != NULL) { |
12004 | 2.89k | xmlNodePtr cur; |
12005 | | |
12006 | | /* |
12007 | | * Unlink newly created node list. |
12008 | | */ |
12009 | 2.89k | list = root->children; |
12010 | 2.89k | root->children = NULL; |
12011 | 2.89k | root->last = NULL; |
12012 | 7.88k | for (cur = list; cur != NULL; cur = cur->next) |
12013 | 4.99k | cur->parent = NULL; |
12014 | 2.89k | } |
12015 | 2.89k | } |
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 | 10.1k | do { |
12022 | 10.1k | ctxt->input->cur = ctxt->input->end; |
12023 | 10.1k | xmlParserShrink(ctxt); |
12024 | 10.1k | result = xmlParserGrow(ctxt); |
12025 | 10.1k | } while (result > 0); |
12026 | | |
12027 | 9.12k | if (buildTree) |
12028 | 9.12k | nodePop(ctxt); |
12029 | | |
12030 | 9.12k | namePop(ctxt); |
12031 | 9.12k | spacePop(ctxt); |
12032 | | |
12033 | 9.12k | xmlCtxtPopInput(ctxt); |
12034 | | |
12035 | 9.13k | error: |
12036 | 9.13k | xmlFreeNode(root); |
12037 | | |
12038 | 9.13k | return(list); |
12039 | 9.12k | } |
12040 | | |
12041 | | static void |
12042 | 11.1k | xmlCtxtParseEntity(xmlParserCtxtPtr ctxt, xmlEntityPtr ent) { |
12043 | 11.1k | xmlParserInputPtr input; |
12044 | 11.1k | xmlNodePtr list; |
12045 | 11.1k | unsigned long consumed; |
12046 | 11.1k | int isExternal; |
12047 | 11.1k | int buildTree; |
12048 | 11.1k | int oldMinNsIndex; |
12049 | 11.1k | int oldNodelen, oldNodemem; |
12050 | | |
12051 | 11.1k | isExternal = (ent->etype == XML_EXTERNAL_GENERAL_PARSED_ENTITY); |
12052 | 11.1k | buildTree = (ctxt->node != NULL); |
12053 | | |
12054 | | /* |
12055 | | * Recursion check |
12056 | | */ |
12057 | 11.1k | if (ent->flags & XML_ENT_EXPANDING) { |
12058 | 322 | xmlFatalErr(ctxt, XML_ERR_ENTITY_LOOP, NULL); |
12059 | 322 | xmlHaltParser(ctxt); |
12060 | 322 | goto error; |
12061 | 322 | } |
12062 | | |
12063 | | /* |
12064 | | * Load entity |
12065 | | */ |
12066 | 10.7k | input = xmlNewEntityInputStream(ctxt, ent); |
12067 | 10.7k | if (input == NULL) |
12068 | 1.64k | 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 | 9.13k | oldMinNsIndex = ctxt->nsdb->minNsIndex; |
12076 | 9.13k | if (buildTree) |
12077 | 9.13k | ctxt->nsdb->minNsIndex = ctxt->nsNr; |
12078 | | |
12079 | 9.13k | oldNodelen = ctxt->nodelen; |
12080 | 9.13k | oldNodemem = ctxt->nodemem; |
12081 | 9.13k | ctxt->nodelen = 0; |
12082 | 9.13k | 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 | 9.13k | ent->flags |= XML_ENT_EXPANDING; |
12102 | | |
12103 | 9.13k | list = xmlCtxtParseContentInternal(ctxt, input, isExternal, buildTree); |
12104 | | |
12105 | 9.13k | ent->flags &= ~XML_ENT_EXPANDING; |
12106 | | |
12107 | 9.13k | ctxt->nsdb->minNsIndex = oldMinNsIndex; |
12108 | 9.13k | ctxt->nodelen = oldNodelen; |
12109 | 9.13k | ctxt->nodemem = oldNodemem; |
12110 | | |
12111 | | /* |
12112 | | * Entity size accounting |
12113 | | */ |
12114 | 9.13k | consumed = input->consumed; |
12115 | 9.13k | xmlSaturatedAddSizeT(&consumed, input->end - input->base); |
12116 | | |
12117 | 9.13k | if ((ent->flags & XML_ENT_CHECKED) == 0) |
12118 | 8.74k | xmlSaturatedAdd(&ent->expandedSize, consumed); |
12119 | | |
12120 | 9.13k | if ((ent->flags & XML_ENT_PARSED) == 0) { |
12121 | 8.74k | if (isExternal) |
12122 | 7.80k | xmlSaturatedAdd(&ctxt->sizeentities, consumed); |
12123 | | |
12124 | 8.74k | ent->children = list; |
12125 | | |
12126 | 13.7k | while (list != NULL) { |
12127 | 4.99k | 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 | 4.99k | if (list->doc != ent->doc) |
12135 | 0 | xmlSetTreeDoc(list, ent->doc); |
12136 | | |
12137 | 4.99k | if (list->next == NULL) |
12138 | 2.39k | ent->last = list; |
12139 | 4.99k | list = list->next; |
12140 | 4.99k | } |
12141 | 8.74k | } else { |
12142 | 384 | xmlFreeNodeList(list); |
12143 | 384 | } |
12144 | | |
12145 | 9.13k | xmlFreeInputStream(input); |
12146 | | |
12147 | 11.1k | error: |
12148 | 11.1k | ent->flags |= XML_ENT_PARSED | XML_ENT_CHECKED; |
12149 | 11.1k | } |
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 | 1.02M | { |
13429 | 1.02M | int allMask; |
13430 | | |
13431 | 1.02M | 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 | 1.02M | allMask = XML_PARSE_RECOVER | |
13442 | 1.02M | XML_PARSE_NOENT | |
13443 | 1.02M | XML_PARSE_DTDLOAD | |
13444 | 1.02M | XML_PARSE_DTDATTR | |
13445 | 1.02M | XML_PARSE_DTDVALID | |
13446 | 1.02M | XML_PARSE_NOERROR | |
13447 | 1.02M | XML_PARSE_NOWARNING | |
13448 | 1.02M | XML_PARSE_PEDANTIC | |
13449 | 1.02M | XML_PARSE_NOBLANKS | |
13450 | | #ifdef LIBXML_SAX1_ENABLED |
13451 | | XML_PARSE_SAX1 | |
13452 | | #endif |
13453 | 1.02M | XML_PARSE_NONET | |
13454 | 1.02M | XML_PARSE_NODICT | |
13455 | 1.02M | XML_PARSE_NSCLEAN | |
13456 | 1.02M | XML_PARSE_NOCDATA | |
13457 | 1.02M | XML_PARSE_COMPACT | |
13458 | 1.02M | XML_PARSE_OLD10 | |
13459 | 1.02M | XML_PARSE_HUGE | |
13460 | 1.02M | XML_PARSE_OLDSAX | |
13461 | 1.02M | XML_PARSE_IGNORE_ENC | |
13462 | 1.02M | XML_PARSE_BIG_LINES | |
13463 | 1.02M | XML_PARSE_NO_XXE | |
13464 | 1.02M | XML_PARSE_UNZIP | |
13465 | 1.02M | XML_PARSE_NO_SYS_CATALOG | |
13466 | 1.02M | XML_PARSE_CATALOG_PI; |
13467 | | |
13468 | 1.02M | 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 | 1.02M | ctxt->recovery = (options & XML_PARSE_RECOVER) ? 1 : 0; |
13485 | 1.02M | ctxt->replaceEntities = (options & XML_PARSE_NOENT) ? 1 : 0; |
13486 | 1.02M | ctxt->loadsubset = (options & XML_PARSE_DTDLOAD) ? XML_DETECT_IDS : 0; |
13487 | 1.02M | ctxt->loadsubset |= (options & XML_PARSE_DTDATTR) ? XML_COMPLETE_ATTRS : 0; |
13488 | 1.02M | ctxt->validate = (options & XML_PARSE_DTDVALID) ? 1 : 0; |
13489 | 1.02M | ctxt->pedantic = (options & XML_PARSE_PEDANTIC) ? 1 : 0; |
13490 | 1.02M | ctxt->keepBlanks = (options & XML_PARSE_NOBLANKS) ? 0 : 1; |
13491 | 1.02M | ctxt->dictNames = (options & XML_PARSE_NODICT) ? 0 : 1; |
13492 | | |
13493 | 1.02M | if (options & XML_PARSE_HUGE) { |
13494 | 0 | if (ctxt->dict != NULL) |
13495 | 0 | xmlDictSetLimit(ctxt->dict, 0); |
13496 | 0 | } |
13497 | | |
13498 | 1.02M | ctxt->linenumbers = 1; |
13499 | | |
13500 | 1.02M | return(options & ~allMask); |
13501 | 1.02M | } |
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 | 1.02M | { |
13734 | 1.02M | int keepMask; |
13735 | | |
13736 | 1.02M | #ifdef LIBXML_HTML_ENABLED |
13737 | 1.02M | if ((ctxt != NULL) && (ctxt->html)) |
13738 | 0 | return(htmlCtxtUseOptions(ctxt, options)); |
13739 | 1.02M | #endif |
13740 | | |
13741 | | /* |
13742 | | * For historic reasons, some options can only be enabled. |
13743 | | */ |
13744 | 1.02M | keepMask = XML_PARSE_NOERROR | |
13745 | 1.02M | XML_PARSE_NOWARNING | |
13746 | 1.02M | XML_PARSE_NONET | |
13747 | 1.02M | XML_PARSE_NSCLEAN | |
13748 | 1.02M | XML_PARSE_NOCDATA | |
13749 | 1.02M | XML_PARSE_COMPACT | |
13750 | 1.02M | XML_PARSE_OLD10 | |
13751 | 1.02M | XML_PARSE_HUGE | |
13752 | 1.02M | XML_PARSE_OLDSAX | |
13753 | 1.02M | XML_PARSE_IGNORE_ENC | |
13754 | 1.02M | XML_PARSE_BIG_LINES; |
13755 | | |
13756 | 1.02M | return(xmlCtxtSetOptionsInternal(ctxt, options, keepMask)); |
13757 | 1.02M | } |
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 | 858k | { |
13793 | 858k | xmlDocPtr ret = NULL; |
13794 | | |
13795 | 858k | 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 | 858k | while (ctxt->inputNr > 0) |
13803 | 0 | xmlFreeInputStream(xmlCtxtPopInput(ctxt)); |
13804 | | |
13805 | 858k | if (xmlCtxtPushInput(ctxt, input) < 0) { |
13806 | 0 | xmlFreeInputStream(input); |
13807 | 0 | return(NULL); |
13808 | 0 | } |
13809 | | |
13810 | 858k | xmlParseDocument(ctxt); |
13811 | | |
13812 | 858k | ret = xmlCtxtGetDocument(ctxt); |
13813 | | |
13814 | | /* assert(ctxt->inputNr == 1); */ |
13815 | 1.71M | while (ctxt->inputNr > 0) |
13816 | 858k | xmlFreeInputStream(xmlCtxtPopInput(ctxt)); |
13817 | | |
13818 | 858k | return(ret); |
13819 | 858k | } |
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 | 65.4k | { |
13929 | 65.4k | xmlParserCtxtPtr ctxt; |
13930 | 65.4k | xmlParserInputPtr input; |
13931 | 65.4k | xmlDocPtr doc = NULL; |
13932 | | |
13933 | 65.4k | if (size < 0) |
13934 | 0 | return(NULL); |
13935 | | |
13936 | 65.4k | ctxt = xmlNewParserCtxt(); |
13937 | 65.4k | if (ctxt == NULL) |
13938 | 0 | return(NULL); |
13939 | | |
13940 | 65.4k | xmlCtxtUseOptions(ctxt, options); |
13941 | | |
13942 | 65.4k | input = xmlCtxtNewInputFromMemory(ctxt, url, buffer, size, encoding, |
13943 | 65.4k | XML_INPUT_BUF_STATIC); |
13944 | | |
13945 | 65.4k | if (input != NULL) |
13946 | 65.4k | doc = xmlCtxtParseDocument(ctxt, input); |
13947 | | |
13948 | 65.4k | xmlFreeParserCtxt(ctxt); |
13949 | 65.4k | return(doc); |
13950 | 65.4k | } |
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 | | |