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 SAX.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/xmlmemory.h> |
55 | | #include <libxml/threads.h> |
56 | | #include <libxml/globals.h> |
57 | | #include <libxml/tree.h> |
58 | | #include <libxml/parser.h> |
59 | | #include <libxml/parserInternals.h> |
60 | | #include <libxml/HTMLparser.h> |
61 | | #include <libxml/valid.h> |
62 | | #include <libxml/entities.h> |
63 | | #include <libxml/xmlerror.h> |
64 | | #include <libxml/encoding.h> |
65 | | #include <libxml/xmlIO.h> |
66 | | #include <libxml/uri.h> |
67 | | #ifdef LIBXML_CATALOG_ENABLED |
68 | | #include <libxml/catalog.h> |
69 | | #endif |
70 | | #ifdef LIBXML_SCHEMAS_ENABLED |
71 | | #include <libxml/xmlschemastypes.h> |
72 | | #include <libxml/relaxng.h> |
73 | | #endif |
74 | | #if defined(LIBXML_XPATH_ENABLED) || defined(LIBXML_SCHEMAS_ENABLED) |
75 | | #include <libxml/xpath.h> |
76 | | #endif |
77 | | |
78 | | #include "private/buf.h" |
79 | | #include "private/dict.h" |
80 | | #include "private/enc.h" |
81 | | #include "private/entities.h" |
82 | | #include "private/error.h" |
83 | | #include "private/globals.h" |
84 | | #include "private/html.h" |
85 | | #include "private/io.h" |
86 | | #include "private/memory.h" |
87 | | #include "private/parser.h" |
88 | | #include "private/threads.h" |
89 | | #include "private/xpath.h" |
90 | | |
91 | | struct _xmlStartTag { |
92 | | const xmlChar *prefix; |
93 | | const xmlChar *URI; |
94 | | int line; |
95 | | int nsNr; |
96 | | }; |
97 | | |
98 | | static xmlParserCtxtPtr |
99 | | xmlCreateEntityParserCtxtInternal(xmlSAXHandlerPtr sax, void *userData, |
100 | | const xmlChar *URL, const xmlChar *ID, const xmlChar *base, |
101 | | xmlParserCtxtPtr pctx); |
102 | | |
103 | | static int |
104 | | xmlParseElementStart(xmlParserCtxtPtr ctxt); |
105 | | |
106 | | static void |
107 | | xmlParseElementEnd(xmlParserCtxtPtr ctxt); |
108 | | |
109 | | /************************************************************************ |
110 | | * * |
111 | | * Arbitrary limits set in the parser. See XML_PARSE_HUGE * |
112 | | * * |
113 | | ************************************************************************/ |
114 | | |
115 | | #define XML_PARSER_BIG_ENTITY 1000 |
116 | | #define XML_PARSER_LOT_ENTITY 5000 |
117 | | |
118 | | /* |
119 | | * Constants for protection against abusive entity expansion |
120 | | * ("billion laughs"). |
121 | | */ |
122 | | |
123 | | /* |
124 | | * XML_PARSER_NON_LINEAR is roughly the maximum allowed amplification factor |
125 | | * of serialized output after entity expansion. |
126 | | */ |
127 | 135 | #define XML_PARSER_NON_LINEAR 5 |
128 | | |
129 | | /* |
130 | | * A certain amount is always allowed. |
131 | | */ |
132 | 1.12k | #define XML_PARSER_ALLOWED_EXPANSION 1000000 |
133 | | |
134 | | /* |
135 | | * Fixed cost for each entity reference. This crudely models processing time |
136 | | * as well to protect, for example, against exponential expansion of empty |
137 | | * or very short entities. |
138 | | */ |
139 | 1.12k | #define XML_ENT_FIXED_COST 20 |
140 | | |
141 | | /** |
142 | | * xmlParserMaxDepth: |
143 | | * |
144 | | * arbitrary depth limit for the XML documents that we allow to |
145 | | * process. This is not a limitation of the parser but a safety |
146 | | * boundary feature. It can be disabled with the XML_PARSE_HUGE |
147 | | * parser option. |
148 | | */ |
149 | | unsigned int xmlParserMaxDepth = 256; |
150 | | |
151 | | |
152 | | |
153 | | #define SAX2 1 |
154 | 23.3M | #define XML_PARSER_BIG_BUFFER_SIZE 300 |
155 | 15.2M | #define XML_PARSER_BUFFER_SIZE 100 |
156 | 21.5k | #define SAX_COMPAT_MODE BAD_CAST "SAX compatibility mode document" |
157 | | |
158 | | /** |
159 | | * XML_PARSER_CHUNK_SIZE |
160 | | * |
161 | | * When calling GROW that's the minimal amount of data |
162 | | * the parser expected to have received. It is not a hard |
163 | | * limit but an optimization when reading strings like Names |
164 | | * It is not strictly needed as long as inputs available characters |
165 | | * are followed by 0, which should be provided by the I/O level |
166 | | */ |
167 | | #define XML_PARSER_CHUNK_SIZE 100 |
168 | | |
169 | | /* |
170 | | * List of XML prefixed PI allowed by W3C specs |
171 | | */ |
172 | | |
173 | | static const char* const xmlW3CPIs[] = { |
174 | | "xml-stylesheet", |
175 | | "xml-model", |
176 | | NULL |
177 | | }; |
178 | | |
179 | | |
180 | | /* DEPR void xmlParserHandleReference(xmlParserCtxtPtr ctxt); */ |
181 | | static xmlEntityPtr xmlParseStringPEReference(xmlParserCtxtPtr ctxt, |
182 | | const xmlChar **str); |
183 | | |
184 | | static xmlParserErrors |
185 | | xmlParseExternalEntityPrivate(xmlDocPtr doc, xmlParserCtxtPtr oldctxt, |
186 | | xmlSAXHandlerPtr sax, |
187 | | void *user_data, int depth, const xmlChar *URL, |
188 | | const xmlChar *ID, xmlNodePtr *list); |
189 | | |
190 | | static int |
191 | | xmlCtxtUseOptionsInternal(xmlParserCtxtPtr ctxt, int options, |
192 | | const char *encoding); |
193 | | #ifdef LIBXML_LEGACY_ENABLED |
194 | | static void |
195 | | xmlAddEntityReference(xmlEntityPtr ent, xmlNodePtr firstNode, |
196 | | xmlNodePtr lastNode); |
197 | | #endif /* LIBXML_LEGACY_ENABLED */ |
198 | | |
199 | | static xmlParserErrors |
200 | | xmlParseBalancedChunkMemoryInternal(xmlParserCtxtPtr oldctxt, |
201 | | const xmlChar *string, void *user_data, xmlNodePtr *lst); |
202 | | |
203 | | static int |
204 | | xmlLoadEntityContent(xmlParserCtxtPtr ctxt, xmlEntityPtr entity); |
205 | | |
206 | | /************************************************************************ |
207 | | * * |
208 | | * Some factorized error routines * |
209 | | * * |
210 | | ************************************************************************/ |
211 | | |
212 | | /** |
213 | | * xmlErrAttributeDup: |
214 | | * @ctxt: an XML parser context |
215 | | * @prefix: the attribute prefix |
216 | | * @localname: the attribute localname |
217 | | * |
218 | | * Handle a redefinition of attribute error |
219 | | */ |
220 | | static void |
221 | | xmlErrAttributeDup(xmlParserCtxtPtr ctxt, const xmlChar * prefix, |
222 | | const xmlChar * localname) |
223 | 106 | { |
224 | 106 | if ((ctxt != NULL) && (ctxt->disableSAX != 0) && |
225 | 106 | (ctxt->instate == XML_PARSER_EOF)) |
226 | 0 | return; |
227 | 106 | if (ctxt != NULL) |
228 | 106 | ctxt->errNo = XML_ERR_ATTRIBUTE_REDEFINED; |
229 | | |
230 | 106 | if (prefix == NULL) |
231 | 106 | __xmlRaiseError(NULL, NULL, NULL, ctxt, NULL, XML_FROM_PARSER, |
232 | 106 | XML_ERR_ATTRIBUTE_REDEFINED, XML_ERR_FATAL, NULL, 0, |
233 | 106 | (const char *) localname, NULL, NULL, 0, 0, |
234 | 106 | "Attribute %s redefined\n", localname); |
235 | 0 | else |
236 | 0 | __xmlRaiseError(NULL, NULL, NULL, ctxt, NULL, XML_FROM_PARSER, |
237 | 0 | XML_ERR_ATTRIBUTE_REDEFINED, XML_ERR_FATAL, NULL, 0, |
238 | 0 | (const char *) prefix, (const char *) localname, |
239 | 0 | NULL, 0, 0, "Attribute %s:%s redefined\n", prefix, |
240 | 0 | localname); |
241 | 106 | if (ctxt != NULL) { |
242 | 106 | ctxt->wellFormed = 0; |
243 | 106 | if (ctxt->recovery == 0) |
244 | 0 | ctxt->disableSAX = 1; |
245 | 106 | } |
246 | 106 | } |
247 | | |
248 | | /** |
249 | | * xmlFatalErrMsg: |
250 | | * @ctxt: an XML parser context |
251 | | * @error: the error number |
252 | | * @msg: the error message |
253 | | * |
254 | | * Handle a fatal parser error, i.e. violating Well-Formedness constraints |
255 | | */ |
256 | | static void LIBXML_ATTR_FORMAT(3,0) |
257 | | xmlFatalErrMsg(xmlParserCtxtPtr ctxt, xmlParserErrors error, |
258 | | const char *msg) |
259 | 1.41M | { |
260 | 1.41M | if ((ctxt != NULL) && (ctxt->disableSAX != 0) && |
261 | 1.41M | (ctxt->instate == XML_PARSER_EOF)) |
262 | 0 | return; |
263 | 1.41M | if (ctxt != NULL) |
264 | 1.41M | ctxt->errNo = error; |
265 | 1.41M | __xmlRaiseError(NULL, NULL, NULL, ctxt, NULL, XML_FROM_PARSER, error, |
266 | 1.41M | XML_ERR_FATAL, NULL, 0, NULL, NULL, NULL, 0, 0, "%s", msg); |
267 | 1.41M | if (ctxt != NULL) { |
268 | 1.41M | ctxt->wellFormed = 0; |
269 | 1.41M | if (ctxt->recovery == 0) |
270 | 1.76k | ctxt->disableSAX = 1; |
271 | 1.41M | } |
272 | 1.41M | } |
273 | | |
274 | | /** |
275 | | * xmlWarningMsg: |
276 | | * @ctxt: an XML parser context |
277 | | * @error: the error number |
278 | | * @msg: the error message |
279 | | * @str1: extra data |
280 | | * @str2: extra data |
281 | | * |
282 | | * Handle a warning. |
283 | | */ |
284 | | static void LIBXML_ATTR_FORMAT(3,0) |
285 | | xmlWarningMsg(xmlParserCtxtPtr ctxt, xmlParserErrors error, |
286 | | const char *msg, const xmlChar *str1, const xmlChar *str2) |
287 | 1.02k | { |
288 | 1.02k | xmlStructuredErrorFunc schannel = NULL; |
289 | | |
290 | 1.02k | if ((ctxt != NULL) && (ctxt->disableSAX != 0) && |
291 | 1.02k | (ctxt->instate == XML_PARSER_EOF)) |
292 | 0 | return; |
293 | 1.02k | if ((ctxt != NULL) && (ctxt->sax != NULL) && |
294 | 1.02k | (ctxt->sax->initialized == XML_SAX2_MAGIC)) |
295 | 1.02k | schannel = ctxt->sax->serror; |
296 | 1.02k | if (ctxt != NULL) { |
297 | 1.02k | __xmlRaiseError(schannel, |
298 | 1.02k | (ctxt->sax) ? ctxt->sax->warning : NULL, |
299 | 1.02k | ctxt->userData, |
300 | 1.02k | ctxt, NULL, XML_FROM_PARSER, error, |
301 | 1.02k | XML_ERR_WARNING, NULL, 0, |
302 | 1.02k | (const char *) str1, (const char *) str2, NULL, 0, 0, |
303 | 1.02k | msg, (const char *) str1, (const char *) str2); |
304 | 1.02k | } else { |
305 | 0 | __xmlRaiseError(schannel, NULL, NULL, |
306 | 0 | ctxt, NULL, XML_FROM_PARSER, error, |
307 | 0 | XML_ERR_WARNING, NULL, 0, |
308 | 0 | (const char *) str1, (const char *) str2, NULL, 0, 0, |
309 | 0 | msg, (const char *) str1, (const char *) str2); |
310 | 0 | } |
311 | 1.02k | } |
312 | | |
313 | | /** |
314 | | * xmlValidityError: |
315 | | * @ctxt: an XML parser context |
316 | | * @error: the error number |
317 | | * @msg: the error message |
318 | | * @str1: extra data |
319 | | * |
320 | | * Handle a validity error. |
321 | | */ |
322 | | static void LIBXML_ATTR_FORMAT(3,0) |
323 | | xmlValidityError(xmlParserCtxtPtr ctxt, xmlParserErrors error, |
324 | | const char *msg, const xmlChar *str1, const xmlChar *str2) |
325 | 0 | { |
326 | 0 | xmlStructuredErrorFunc schannel = NULL; |
327 | |
|
328 | 0 | if ((ctxt != NULL) && (ctxt->disableSAX != 0) && |
329 | 0 | (ctxt->instate == XML_PARSER_EOF)) |
330 | 0 | return; |
331 | 0 | if (ctxt != NULL) { |
332 | 0 | ctxt->errNo = error; |
333 | 0 | if ((ctxt->sax != NULL) && (ctxt->sax->initialized == XML_SAX2_MAGIC)) |
334 | 0 | schannel = ctxt->sax->serror; |
335 | 0 | } |
336 | 0 | if (ctxt != NULL) { |
337 | 0 | __xmlRaiseError(schannel, |
338 | 0 | ctxt->vctxt.error, ctxt->vctxt.userData, |
339 | 0 | ctxt, NULL, XML_FROM_DTD, error, |
340 | 0 | XML_ERR_ERROR, NULL, 0, (const char *) str1, |
341 | 0 | (const char *) str2, NULL, 0, 0, |
342 | 0 | msg, (const char *) str1, (const char *) str2); |
343 | 0 | ctxt->valid = 0; |
344 | 0 | } else { |
345 | 0 | __xmlRaiseError(schannel, NULL, NULL, |
346 | 0 | ctxt, NULL, XML_FROM_DTD, error, |
347 | 0 | XML_ERR_ERROR, NULL, 0, (const char *) str1, |
348 | 0 | (const char *) str2, NULL, 0, 0, |
349 | 0 | msg, (const char *) str1, (const char *) str2); |
350 | 0 | } |
351 | 0 | } |
352 | | |
353 | | /** |
354 | | * xmlFatalErrMsgInt: |
355 | | * @ctxt: an XML parser context |
356 | | * @error: the error number |
357 | | * @msg: the error message |
358 | | * @val: an integer value |
359 | | * |
360 | | * Handle a fatal parser error, i.e. violating Well-Formedness constraints |
361 | | */ |
362 | | static void LIBXML_ATTR_FORMAT(3,0) |
363 | | xmlFatalErrMsgInt(xmlParserCtxtPtr ctxt, xmlParserErrors error, |
364 | | const char *msg, int val) |
365 | 95.0k | { |
366 | 95.0k | if ((ctxt != NULL) && (ctxt->disableSAX != 0) && |
367 | 95.0k | (ctxt->instate == XML_PARSER_EOF)) |
368 | 0 | return; |
369 | 95.0k | if (ctxt != NULL) |
370 | 95.0k | ctxt->errNo = error; |
371 | 95.0k | __xmlRaiseError(NULL, NULL, NULL, |
372 | 95.0k | ctxt, NULL, XML_FROM_PARSER, error, XML_ERR_FATAL, |
373 | 95.0k | NULL, 0, NULL, NULL, NULL, val, 0, msg, val); |
374 | 95.0k | if (ctxt != NULL) { |
375 | 95.0k | ctxt->wellFormed = 0; |
376 | 95.0k | if (ctxt->recovery == 0) |
377 | 0 | ctxt->disableSAX = 1; |
378 | 95.0k | } |
379 | 95.0k | } |
380 | | |
381 | | /** |
382 | | * xmlFatalErrMsgStrIntStr: |
383 | | * @ctxt: an XML parser context |
384 | | * @error: the error number |
385 | | * @msg: the error message |
386 | | * @str1: an string info |
387 | | * @val: an integer value |
388 | | * @str2: an string info |
389 | | * |
390 | | * Handle a fatal parser error, i.e. violating Well-Formedness constraints |
391 | | */ |
392 | | static void LIBXML_ATTR_FORMAT(3,0) |
393 | | xmlFatalErrMsgStrIntStr(xmlParserCtxtPtr ctxt, xmlParserErrors error, |
394 | | const char *msg, const xmlChar *str1, int val, |
395 | | const xmlChar *str2) |
396 | 1.32M | { |
397 | 1.32M | if ((ctxt != NULL) && (ctxt->disableSAX != 0) && |
398 | 1.32M | (ctxt->instate == XML_PARSER_EOF)) |
399 | 0 | return; |
400 | 1.32M | if (ctxt != NULL) |
401 | 1.32M | ctxt->errNo = error; |
402 | 1.32M | __xmlRaiseError(NULL, NULL, NULL, |
403 | 1.32M | ctxt, NULL, XML_FROM_PARSER, error, XML_ERR_FATAL, |
404 | 1.32M | NULL, 0, (const char *) str1, (const char *) str2, |
405 | 1.32M | NULL, val, 0, msg, str1, val, str2); |
406 | 1.32M | if (ctxt != NULL) { |
407 | 1.32M | ctxt->wellFormed = 0; |
408 | 1.32M | if (ctxt->recovery == 0) |
409 | 6 | ctxt->disableSAX = 1; |
410 | 1.32M | } |
411 | 1.32M | } |
412 | | |
413 | | /** |
414 | | * xmlFatalErrMsgStr: |
415 | | * @ctxt: an XML parser context |
416 | | * @error: the error number |
417 | | * @msg: the error message |
418 | | * @val: a string value |
419 | | * |
420 | | * Handle a fatal parser error, i.e. violating Well-Formedness constraints |
421 | | */ |
422 | | static void LIBXML_ATTR_FORMAT(3,0) |
423 | | xmlFatalErrMsgStr(xmlParserCtxtPtr ctxt, xmlParserErrors error, |
424 | | const char *msg, const xmlChar * val) |
425 | 25.6k | { |
426 | 25.6k | if ((ctxt != NULL) && (ctxt->disableSAX != 0) && |
427 | 25.6k | (ctxt->instate == XML_PARSER_EOF)) |
428 | 0 | return; |
429 | 25.6k | if (ctxt != NULL) |
430 | 25.6k | ctxt->errNo = error; |
431 | 25.6k | __xmlRaiseError(NULL, NULL, NULL, ctxt, NULL, |
432 | 25.6k | XML_FROM_PARSER, error, XML_ERR_FATAL, |
433 | 25.6k | NULL, 0, (const char *) val, NULL, NULL, 0, 0, msg, |
434 | 25.6k | val); |
435 | 25.6k | if (ctxt != NULL) { |
436 | 25.6k | ctxt->wellFormed = 0; |
437 | 25.6k | if (ctxt->recovery == 0) |
438 | 1.12k | ctxt->disableSAX = 1; |
439 | 25.6k | } |
440 | 25.6k | } |
441 | | |
442 | | /** |
443 | | * xmlErrMsgStr: |
444 | | * @ctxt: an XML parser context |
445 | | * @error: the error number |
446 | | * @msg: the error message |
447 | | * @val: a string value |
448 | | * |
449 | | * Handle a non fatal parser error |
450 | | */ |
451 | | static void LIBXML_ATTR_FORMAT(3,0) |
452 | | xmlErrMsgStr(xmlParserCtxtPtr ctxt, xmlParserErrors error, |
453 | | const char *msg, const xmlChar * val) |
454 | 1.64k | { |
455 | 1.64k | if ((ctxt != NULL) && (ctxt->disableSAX != 0) && |
456 | 1.64k | (ctxt->instate == XML_PARSER_EOF)) |
457 | 0 | return; |
458 | 1.64k | if (ctxt != NULL) |
459 | 1.64k | ctxt->errNo = error; |
460 | 1.64k | __xmlRaiseError(NULL, NULL, NULL, ctxt, NULL, |
461 | 1.64k | XML_FROM_PARSER, error, XML_ERR_ERROR, |
462 | 1.64k | NULL, 0, (const char *) val, NULL, NULL, 0, 0, msg, |
463 | 1.64k | val); |
464 | 1.64k | } |
465 | | |
466 | | /** |
467 | | * xmlNsErr: |
468 | | * @ctxt: an XML parser context |
469 | | * @error: the error number |
470 | | * @msg: the message |
471 | | * @info1: extra information string |
472 | | * @info2: extra information string |
473 | | * |
474 | | * Handle a fatal parser error, i.e. violating Well-Formedness constraints |
475 | | */ |
476 | | static void LIBXML_ATTR_FORMAT(3,0) |
477 | | xmlNsErr(xmlParserCtxtPtr ctxt, xmlParserErrors error, |
478 | | const char *msg, |
479 | | const xmlChar * info1, const xmlChar * info2, |
480 | | const xmlChar * info3) |
481 | 39.4k | { |
482 | 39.4k | if ((ctxt != NULL) && (ctxt->disableSAX != 0) && |
483 | 39.4k | (ctxt->instate == XML_PARSER_EOF)) |
484 | 0 | return; |
485 | 39.4k | if (ctxt != NULL) |
486 | 39.4k | ctxt->errNo = error; |
487 | 39.4k | __xmlRaiseError(NULL, NULL, NULL, ctxt, NULL, XML_FROM_NAMESPACE, error, |
488 | 39.4k | XML_ERR_ERROR, NULL, 0, (const char *) info1, |
489 | 39.4k | (const char *) info2, (const char *) info3, 0, 0, msg, |
490 | 39.4k | info1, info2, info3); |
491 | 39.4k | if (ctxt != NULL) |
492 | 39.4k | ctxt->nsWellFormed = 0; |
493 | 39.4k | } |
494 | | |
495 | | /** |
496 | | * xmlNsWarn |
497 | | * @ctxt: an XML parser context |
498 | | * @error: the error number |
499 | | * @msg: the message |
500 | | * @info1: extra information string |
501 | | * @info2: extra information string |
502 | | * |
503 | | * Handle a namespace warning error |
504 | | */ |
505 | | static void LIBXML_ATTR_FORMAT(3,0) |
506 | | xmlNsWarn(xmlParserCtxtPtr ctxt, xmlParserErrors error, |
507 | | const char *msg, |
508 | | const xmlChar * info1, const xmlChar * info2, |
509 | | const xmlChar * info3) |
510 | 659 | { |
511 | 659 | if ((ctxt != NULL) && (ctxt->disableSAX != 0) && |
512 | 659 | (ctxt->instate == XML_PARSER_EOF)) |
513 | 0 | return; |
514 | 659 | __xmlRaiseError(NULL, NULL, NULL, ctxt, NULL, XML_FROM_NAMESPACE, error, |
515 | 659 | XML_ERR_WARNING, NULL, 0, (const char *) info1, |
516 | 659 | (const char *) info2, (const char *) info3, 0, 0, msg, |
517 | 659 | info1, info2, info3); |
518 | 659 | } |
519 | | |
520 | | static void |
521 | 4.49k | xmlSaturatedAdd(unsigned long *dst, unsigned long val) { |
522 | 4.49k | if (val > ULONG_MAX - *dst) |
523 | 0 | *dst = ULONG_MAX; |
524 | 4.49k | else |
525 | 4.49k | *dst += val; |
526 | 4.49k | } |
527 | | |
528 | | static void |
529 | 1.12k | xmlSaturatedAddSizeT(unsigned long *dst, unsigned long val) { |
530 | 1.12k | if (val > ULONG_MAX - *dst) |
531 | 0 | *dst = ULONG_MAX; |
532 | 1.12k | else |
533 | 1.12k | *dst += val; |
534 | 1.12k | } |
535 | | |
536 | | /** |
537 | | * xmlParserEntityCheck: |
538 | | * @ctxt: parser context |
539 | | * @extra: sum of unexpanded entity sizes |
540 | | * |
541 | | * Check for non-linear entity expansion behaviour. |
542 | | * |
543 | | * In some cases like xmlStringDecodeEntities, this function is called |
544 | | * for each, possibly nested entity and its unexpanded content length. |
545 | | * |
546 | | * In other cases like xmlParseReference, it's only called for each |
547 | | * top-level entity with its unexpanded content length plus the sum of |
548 | | * the unexpanded content lengths (plus fixed cost) of all nested |
549 | | * entities. |
550 | | * |
551 | | * Summing the unexpanded lengths also adds the length of the reference. |
552 | | * This is by design. Taking the length of the entity name into account |
553 | | * discourages attacks that try to waste CPU time with abusively long |
554 | | * entity names. See test/recurse/lol6.xml for example. Each call also |
555 | | * adds some fixed cost XML_ENT_FIXED_COST to discourage attacks with |
556 | | * short entities. |
557 | | * |
558 | | * Returns 1 on error, 0 on success. |
559 | | */ |
560 | | static int |
561 | | xmlParserEntityCheck(xmlParserCtxtPtr ctxt, unsigned long extra) |
562 | 1.12k | { |
563 | 1.12k | unsigned long consumed; |
564 | 1.12k | xmlParserInputPtr input = ctxt->input; |
565 | 1.12k | xmlEntityPtr entity = input->entity; |
566 | | |
567 | | /* |
568 | | * Compute total consumed bytes so far, including input streams of |
569 | | * external entities. |
570 | | */ |
571 | 1.12k | consumed = input->parentConsumed; |
572 | 1.12k | if ((entity == NULL) || |
573 | 1.12k | ((entity->etype == XML_EXTERNAL_PARAMETER_ENTITY) && |
574 | 1.12k | ((entity->flags & XML_ENT_PARSED) == 0))) { |
575 | 1.12k | xmlSaturatedAdd(&consumed, input->consumed); |
576 | 1.12k | xmlSaturatedAddSizeT(&consumed, input->cur - input->base); |
577 | 1.12k | } |
578 | 1.12k | xmlSaturatedAdd(&consumed, ctxt->sizeentities); |
579 | | |
580 | | /* |
581 | | * Add extra cost and some fixed cost. |
582 | | */ |
583 | 1.12k | xmlSaturatedAdd(&ctxt->sizeentcopy, extra); |
584 | 1.12k | xmlSaturatedAdd(&ctxt->sizeentcopy, XML_ENT_FIXED_COST); |
585 | | |
586 | | /* |
587 | | * It's important to always use saturation arithmetic when tracking |
588 | | * entity sizes to make the size checks reliable. If "sizeentcopy" |
589 | | * overflows, we have to abort. |
590 | | */ |
591 | 1.12k | if ((ctxt->sizeentcopy > XML_PARSER_ALLOWED_EXPANSION) && |
592 | 1.12k | ((ctxt->sizeentcopy >= ULONG_MAX) || |
593 | 135 | (ctxt->sizeentcopy / XML_PARSER_NON_LINEAR > consumed))) { |
594 | 23 | xmlFatalErrMsg(ctxt, XML_ERR_ENTITY_LOOP, |
595 | 23 | "Maximum entity amplification factor exceeded"); |
596 | 23 | xmlHaltParser(ctxt); |
597 | 23 | return(1); |
598 | 23 | } |
599 | | |
600 | 1.09k | return(0); |
601 | 1.12k | } |
602 | | |
603 | | /************************************************************************ |
604 | | * * |
605 | | * Library wide options * |
606 | | * * |
607 | | ************************************************************************/ |
608 | | |
609 | | /** |
610 | | * xmlHasFeature: |
611 | | * @feature: the feature to be examined |
612 | | * |
613 | | * Examines if the library has been compiled with a given feature. |
614 | | * |
615 | | * Returns a non-zero value if the feature exist, otherwise zero. |
616 | | * Returns zero (0) if the feature does not exist or an unknown |
617 | | * unknown feature is requested, non-zero otherwise. |
618 | | */ |
619 | | int |
620 | | xmlHasFeature(xmlFeature feature) |
621 | 0 | { |
622 | 0 | switch (feature) { |
623 | 0 | case XML_WITH_THREAD: |
624 | 0 | #ifdef LIBXML_THREAD_ENABLED |
625 | 0 | return(1); |
626 | | #else |
627 | | return(0); |
628 | | #endif |
629 | 0 | case XML_WITH_TREE: |
630 | 0 | #ifdef LIBXML_TREE_ENABLED |
631 | 0 | return(1); |
632 | | #else |
633 | | return(0); |
634 | | #endif |
635 | 0 | case XML_WITH_OUTPUT: |
636 | 0 | #ifdef LIBXML_OUTPUT_ENABLED |
637 | 0 | return(1); |
638 | | #else |
639 | | return(0); |
640 | | #endif |
641 | 0 | case XML_WITH_PUSH: |
642 | | #ifdef LIBXML_PUSH_ENABLED |
643 | | return(1); |
644 | | #else |
645 | 0 | return(0); |
646 | 0 | #endif |
647 | 0 | case XML_WITH_READER: |
648 | | #ifdef LIBXML_READER_ENABLED |
649 | | return(1); |
650 | | #else |
651 | 0 | return(0); |
652 | 0 | #endif |
653 | 0 | case XML_WITH_PATTERN: |
654 | 0 | #ifdef LIBXML_PATTERN_ENABLED |
655 | 0 | return(1); |
656 | | #else |
657 | | return(0); |
658 | | #endif |
659 | 0 | case XML_WITH_WRITER: |
660 | | #ifdef LIBXML_WRITER_ENABLED |
661 | | return(1); |
662 | | #else |
663 | 0 | return(0); |
664 | 0 | #endif |
665 | 0 | case XML_WITH_SAX1: |
666 | | #ifdef LIBXML_SAX1_ENABLED |
667 | | return(1); |
668 | | #else |
669 | 0 | return(0); |
670 | 0 | #endif |
671 | 0 | case XML_WITH_FTP: |
672 | | #ifdef LIBXML_FTP_ENABLED |
673 | | return(1); |
674 | | #else |
675 | 0 | return(0); |
676 | 0 | #endif |
677 | 0 | case XML_WITH_HTTP: |
678 | 0 | #ifdef LIBXML_HTTP_ENABLED |
679 | 0 | return(1); |
680 | | #else |
681 | | return(0); |
682 | | #endif |
683 | 0 | case XML_WITH_VALID: |
684 | | #ifdef LIBXML_VALID_ENABLED |
685 | | return(1); |
686 | | #else |
687 | 0 | return(0); |
688 | 0 | #endif |
689 | 0 | case XML_WITH_HTML: |
690 | 0 | #ifdef LIBXML_HTML_ENABLED |
691 | 0 | return(1); |
692 | | #else |
693 | | return(0); |
694 | | #endif |
695 | 0 | case XML_WITH_LEGACY: |
696 | | #ifdef LIBXML_LEGACY_ENABLED |
697 | | return(1); |
698 | | #else |
699 | 0 | return(0); |
700 | 0 | #endif |
701 | 0 | case XML_WITH_C14N: |
702 | | #ifdef LIBXML_C14N_ENABLED |
703 | | return(1); |
704 | | #else |
705 | 0 | return(0); |
706 | 0 | #endif |
707 | 0 | case XML_WITH_CATALOG: |
708 | 0 | #ifdef LIBXML_CATALOG_ENABLED |
709 | 0 | return(1); |
710 | | #else |
711 | | return(0); |
712 | | #endif |
713 | 0 | case XML_WITH_XPATH: |
714 | 0 | #ifdef LIBXML_XPATH_ENABLED |
715 | 0 | return(1); |
716 | | #else |
717 | | return(0); |
718 | | #endif |
719 | 0 | case XML_WITH_XPTR: |
720 | 0 | #ifdef LIBXML_XPTR_ENABLED |
721 | 0 | return(1); |
722 | | #else |
723 | | return(0); |
724 | | #endif |
725 | 0 | case XML_WITH_XINCLUDE: |
726 | 0 | #ifdef LIBXML_XINCLUDE_ENABLED |
727 | 0 | return(1); |
728 | | #else |
729 | | return(0); |
730 | | #endif |
731 | 0 | case XML_WITH_ICONV: |
732 | 0 | #ifdef LIBXML_ICONV_ENABLED |
733 | 0 | return(1); |
734 | | #else |
735 | | return(0); |
736 | | #endif |
737 | 0 | case XML_WITH_ISO8859X: |
738 | 0 | #ifdef LIBXML_ISO8859X_ENABLED |
739 | 0 | return(1); |
740 | | #else |
741 | | return(0); |
742 | | #endif |
743 | 0 | case XML_WITH_UNICODE: |
744 | | #ifdef LIBXML_UNICODE_ENABLED |
745 | | return(1); |
746 | | #else |
747 | 0 | return(0); |
748 | 0 | #endif |
749 | 0 | case XML_WITH_REGEXP: |
750 | | #ifdef LIBXML_REGEXP_ENABLED |
751 | | return(1); |
752 | | #else |
753 | 0 | return(0); |
754 | 0 | #endif |
755 | 0 | case XML_WITH_AUTOMATA: |
756 | | #ifdef LIBXML_AUTOMATA_ENABLED |
757 | | return(1); |
758 | | #else |
759 | 0 | return(0); |
760 | 0 | #endif |
761 | 0 | case XML_WITH_EXPR: |
762 | | #ifdef LIBXML_EXPR_ENABLED |
763 | | return(1); |
764 | | #else |
765 | 0 | return(0); |
766 | 0 | #endif |
767 | 0 | case XML_WITH_SCHEMAS: |
768 | | #ifdef LIBXML_SCHEMAS_ENABLED |
769 | | return(1); |
770 | | #else |
771 | 0 | return(0); |
772 | 0 | #endif |
773 | 0 | case XML_WITH_SCHEMATRON: |
774 | | #ifdef LIBXML_SCHEMATRON_ENABLED |
775 | | return(1); |
776 | | #else |
777 | 0 | return(0); |
778 | 0 | #endif |
779 | 0 | case XML_WITH_MODULES: |
780 | 0 | #ifdef LIBXML_MODULES_ENABLED |
781 | 0 | return(1); |
782 | | #else |
783 | | return(0); |
784 | | #endif |
785 | 0 | case XML_WITH_DEBUG: |
786 | 0 | #ifdef LIBXML_DEBUG_ENABLED |
787 | 0 | return(1); |
788 | | #else |
789 | | return(0); |
790 | | #endif |
791 | 0 | case XML_WITH_DEBUG_MEM: |
792 | | #ifdef DEBUG_MEMORY_LOCATION |
793 | | return(1); |
794 | | #else |
795 | 0 | return(0); |
796 | 0 | #endif |
797 | 0 | case XML_WITH_DEBUG_RUN: |
798 | 0 | return(0); |
799 | 0 | case XML_WITH_ZLIB: |
800 | | #ifdef LIBXML_ZLIB_ENABLED |
801 | | return(1); |
802 | | #else |
803 | 0 | return(0); |
804 | 0 | #endif |
805 | 0 | case XML_WITH_LZMA: |
806 | | #ifdef LIBXML_LZMA_ENABLED |
807 | | return(1); |
808 | | #else |
809 | 0 | return(0); |
810 | 0 | #endif |
811 | 0 | case XML_WITH_ICU: |
812 | | #ifdef LIBXML_ICU_ENABLED |
813 | | return(1); |
814 | | #else |
815 | 0 | return(0); |
816 | 0 | #endif |
817 | 0 | default: |
818 | 0 | break; |
819 | 0 | } |
820 | 0 | return(0); |
821 | 0 | } |
822 | | |
823 | | /************************************************************************ |
824 | | * * |
825 | | * SAX2 defaulted attributes handling * |
826 | | * * |
827 | | ************************************************************************/ |
828 | | |
829 | | /** |
830 | | * xmlDetectSAX2: |
831 | | * @ctxt: an XML parser context |
832 | | * |
833 | | * Do the SAX2 detection and specific initialization |
834 | | */ |
835 | | static void |
836 | 410 | xmlDetectSAX2(xmlParserCtxtPtr ctxt) { |
837 | 410 | xmlSAXHandlerPtr sax; |
838 | | |
839 | | /* Avoid unused variable warning if features are disabled. */ |
840 | 410 | (void) sax; |
841 | | |
842 | 410 | if (ctxt == NULL) return; |
843 | 410 | sax = ctxt->sax; |
844 | | #ifdef LIBXML_SAX1_ENABLED |
845 | | if ((sax) && (sax->initialized == XML_SAX2_MAGIC)) |
846 | | ctxt->sax2 = 1; |
847 | | #else |
848 | 410 | ctxt->sax2 = 1; |
849 | 410 | #endif /* LIBXML_SAX1_ENABLED */ |
850 | | |
851 | 410 | ctxt->str_xml = xmlDictLookup(ctxt->dict, BAD_CAST "xml", 3); |
852 | 410 | ctxt->str_xmlns = xmlDictLookup(ctxt->dict, BAD_CAST "xmlns", 5); |
853 | 410 | ctxt->str_xml_ns = xmlDictLookup(ctxt->dict, XML_XML_NAMESPACE, 36); |
854 | 410 | if ((ctxt->str_xml==NULL) || (ctxt->str_xmlns==NULL) || |
855 | 410 | (ctxt->str_xml_ns == NULL)) { |
856 | 0 | xmlErrMemory(ctxt, NULL); |
857 | 0 | } |
858 | 410 | } |
859 | | |
860 | | typedef struct _xmlDefAttrs xmlDefAttrs; |
861 | | typedef xmlDefAttrs *xmlDefAttrsPtr; |
862 | | struct _xmlDefAttrs { |
863 | | int nbAttrs; /* number of defaulted attributes on that element */ |
864 | | int maxAttrs; /* the size of the array */ |
865 | | #if __STDC_VERSION__ >= 199901L |
866 | | /* Using a C99 flexible array member avoids UBSan errors. */ |
867 | | const xmlChar *values[]; /* array of localname/prefix/values/external */ |
868 | | #else |
869 | | const xmlChar *values[5]; |
870 | | #endif |
871 | | }; |
872 | | |
873 | | /** |
874 | | * xmlAttrNormalizeSpace: |
875 | | * @src: the source string |
876 | | * @dst: the target string |
877 | | * |
878 | | * Normalize the space in non CDATA attribute values: |
879 | | * If the attribute type is not CDATA, then the XML processor MUST further |
880 | | * process the normalized attribute value by discarding any leading and |
881 | | * trailing space (#x20) characters, and by replacing sequences of space |
882 | | * (#x20) characters by a single space (#x20) character. |
883 | | * Note that the size of dst need to be at least src, and if one doesn't need |
884 | | * to preserve dst (and it doesn't come from a dictionary or read-only) then |
885 | | * passing src as dst is just fine. |
886 | | * |
887 | | * Returns a pointer to the normalized value (dst) or NULL if no conversion |
888 | | * is needed. |
889 | | */ |
890 | | static xmlChar * |
891 | | xmlAttrNormalizeSpace(const xmlChar *src, xmlChar *dst) |
892 | 2.07k | { |
893 | 2.07k | if ((src == NULL) || (dst == NULL)) |
894 | 0 | return(NULL); |
895 | | |
896 | 6.69k | while (*src == 0x20) src++; |
897 | 724k | while (*src != 0) { |
898 | 722k | if (*src == 0x20) { |
899 | 108k | while (*src == 0x20) src++; |
900 | 5.54k | if (*src != 0) |
901 | 3.47k | *dst++ = 0x20; |
902 | 716k | } else { |
903 | 716k | *dst++ = *src++; |
904 | 716k | } |
905 | 722k | } |
906 | 2.07k | *dst = 0; |
907 | 2.07k | if (dst == src) |
908 | 0 | return(NULL); |
909 | 2.07k | return(dst); |
910 | 2.07k | } |
911 | | |
912 | | /** |
913 | | * xmlAttrNormalizeSpace2: |
914 | | * @src: the source string |
915 | | * |
916 | | * Normalize the space in non CDATA attribute values, a slightly more complex |
917 | | * front end to avoid allocation problems when running on attribute values |
918 | | * coming from the input. |
919 | | * |
920 | | * Returns a pointer to the normalized value (dst) or NULL if no conversion |
921 | | * is needed. |
922 | | */ |
923 | | static const xmlChar * |
924 | | xmlAttrNormalizeSpace2(xmlParserCtxtPtr ctxt, xmlChar *src, int *len) |
925 | 367 | { |
926 | 367 | int i; |
927 | 367 | int remove_head = 0; |
928 | 367 | int need_realloc = 0; |
929 | 367 | const xmlChar *cur; |
930 | | |
931 | 367 | if ((ctxt == NULL) || (src == NULL) || (len == NULL)) |
932 | 0 | return(NULL); |
933 | 367 | i = *len; |
934 | 367 | if (i <= 0) |
935 | 0 | return(NULL); |
936 | | |
937 | 367 | cur = src; |
938 | 367 | while (*cur == 0x20) { |
939 | 0 | cur++; |
940 | 0 | remove_head++; |
941 | 0 | } |
942 | 7.48k | while (*cur != 0) { |
943 | 7.11k | if (*cur == 0x20) { |
944 | 670 | cur++; |
945 | 670 | if ((*cur == 0x20) || (*cur == 0)) { |
946 | 0 | need_realloc = 1; |
947 | 0 | break; |
948 | 0 | } |
949 | 670 | } else |
950 | 6.44k | cur++; |
951 | 7.11k | } |
952 | 367 | if (need_realloc) { |
953 | 0 | xmlChar *ret; |
954 | |
|
955 | 0 | ret = xmlStrndup(src + remove_head, i - remove_head + 1); |
956 | 0 | if (ret == NULL) { |
957 | 0 | xmlErrMemory(ctxt, NULL); |
958 | 0 | return(NULL); |
959 | 0 | } |
960 | 0 | xmlAttrNormalizeSpace(ret, ret); |
961 | 0 | *len = strlen((const char *)ret); |
962 | 0 | return(ret); |
963 | 367 | } else if (remove_head) { |
964 | 0 | *len -= remove_head; |
965 | 0 | memmove(src, src + remove_head, 1 + *len); |
966 | 0 | return(src); |
967 | 0 | } |
968 | 367 | return(NULL); |
969 | 367 | } |
970 | | |
971 | | /** |
972 | | * xmlAddDefAttrs: |
973 | | * @ctxt: an XML parser context |
974 | | * @fullname: the element fullname |
975 | | * @fullattr: the attribute fullname |
976 | | * @value: the attribute value |
977 | | * |
978 | | * Add a defaulted attribute for an element |
979 | | */ |
980 | | static void |
981 | | xmlAddDefAttrs(xmlParserCtxtPtr ctxt, |
982 | | const xmlChar *fullname, |
983 | | const xmlChar *fullattr, |
984 | 1.79k | const xmlChar *value) { |
985 | 1.79k | xmlDefAttrsPtr defaults; |
986 | 1.79k | int len; |
987 | 1.79k | const xmlChar *name; |
988 | 1.79k | const xmlChar *prefix; |
989 | | |
990 | | /* |
991 | | * Allows to detect attribute redefinitions |
992 | | */ |
993 | 1.79k | if (ctxt->attsSpecial != NULL) { |
994 | 1.78k | if (xmlHashLookup2(ctxt->attsSpecial, fullname, fullattr) != NULL) |
995 | 1.57k | return; |
996 | 1.78k | } |
997 | | |
998 | 222 | if (ctxt->attsDefault == NULL) { |
999 | 14 | ctxt->attsDefault = xmlHashCreateDict(10, ctxt->dict); |
1000 | 14 | if (ctxt->attsDefault == NULL) |
1001 | 0 | goto mem_error; |
1002 | 14 | } |
1003 | | |
1004 | | /* |
1005 | | * split the element name into prefix:localname , the string found |
1006 | | * are within the DTD and then not associated to namespace names. |
1007 | | */ |
1008 | 222 | name = xmlSplitQName3(fullname, &len); |
1009 | 222 | if (name == NULL) { |
1010 | 222 | name = xmlDictLookup(ctxt->dict, fullname, -1); |
1011 | 222 | prefix = NULL; |
1012 | 222 | } else { |
1013 | 0 | name = xmlDictLookup(ctxt->dict, name, -1); |
1014 | 0 | prefix = xmlDictLookup(ctxt->dict, fullname, len); |
1015 | 0 | } |
1016 | | |
1017 | | /* |
1018 | | * make sure there is some storage |
1019 | | */ |
1020 | 222 | defaults = xmlHashLookup2(ctxt->attsDefault, name, prefix); |
1021 | 222 | if (defaults == NULL) { |
1022 | 14 | defaults = (xmlDefAttrsPtr) xmlMalloc(sizeof(xmlDefAttrs) + |
1023 | 14 | (4 * 5) * sizeof(const xmlChar *)); |
1024 | 14 | if (defaults == NULL) |
1025 | 0 | goto mem_error; |
1026 | 14 | defaults->nbAttrs = 0; |
1027 | 14 | defaults->maxAttrs = 4; |
1028 | 14 | if (xmlHashUpdateEntry2(ctxt->attsDefault, name, prefix, |
1029 | 14 | defaults, NULL) < 0) { |
1030 | 0 | xmlFree(defaults); |
1031 | 0 | goto mem_error; |
1032 | 0 | } |
1033 | 208 | } else if (defaults->nbAttrs >= defaults->maxAttrs) { |
1034 | 25 | xmlDefAttrsPtr temp; |
1035 | | |
1036 | 25 | temp = (xmlDefAttrsPtr) xmlRealloc(defaults, sizeof(xmlDefAttrs) + |
1037 | 25 | (2 * defaults->maxAttrs * 5) * sizeof(const xmlChar *)); |
1038 | 25 | if (temp == NULL) |
1039 | 0 | goto mem_error; |
1040 | 25 | defaults = temp; |
1041 | 25 | defaults->maxAttrs *= 2; |
1042 | 25 | if (xmlHashUpdateEntry2(ctxt->attsDefault, name, prefix, |
1043 | 25 | defaults, NULL) < 0) { |
1044 | 0 | xmlFree(defaults); |
1045 | 0 | goto mem_error; |
1046 | 0 | } |
1047 | 25 | } |
1048 | | |
1049 | | /* |
1050 | | * Split the element name into prefix:localname , the string found |
1051 | | * are within the DTD and hen not associated to namespace names. |
1052 | | */ |
1053 | 222 | name = xmlSplitQName3(fullattr, &len); |
1054 | 222 | if (name == NULL) { |
1055 | 94 | name = xmlDictLookup(ctxt->dict, fullattr, -1); |
1056 | 94 | prefix = NULL; |
1057 | 128 | } else { |
1058 | 128 | name = xmlDictLookup(ctxt->dict, name, -1); |
1059 | 128 | prefix = xmlDictLookup(ctxt->dict, fullattr, len); |
1060 | 128 | } |
1061 | | |
1062 | 222 | defaults->values[5 * defaults->nbAttrs] = name; |
1063 | 222 | defaults->values[5 * defaults->nbAttrs + 1] = prefix; |
1064 | | /* intern the string and precompute the end */ |
1065 | 222 | len = xmlStrlen(value); |
1066 | 222 | value = xmlDictLookup(ctxt->dict, value, len); |
1067 | 222 | if (value == NULL) |
1068 | 0 | goto mem_error; |
1069 | 222 | defaults->values[5 * defaults->nbAttrs + 2] = value; |
1070 | 222 | defaults->values[5 * defaults->nbAttrs + 3] = value + len; |
1071 | 222 | if (ctxt->external) |
1072 | 0 | defaults->values[5 * defaults->nbAttrs + 4] = BAD_CAST "external"; |
1073 | 222 | else |
1074 | 222 | defaults->values[5 * defaults->nbAttrs + 4] = NULL; |
1075 | 222 | defaults->nbAttrs++; |
1076 | | |
1077 | 222 | return; |
1078 | | |
1079 | 0 | mem_error: |
1080 | 0 | xmlErrMemory(ctxt, NULL); |
1081 | 0 | return; |
1082 | 222 | } |
1083 | | |
1084 | | /** |
1085 | | * xmlAddSpecialAttr: |
1086 | | * @ctxt: an XML parser context |
1087 | | * @fullname: the element fullname |
1088 | | * @fullattr: the attribute fullname |
1089 | | * @type: the attribute type |
1090 | | * |
1091 | | * Register this attribute type |
1092 | | */ |
1093 | | static void |
1094 | | xmlAddSpecialAttr(xmlParserCtxtPtr ctxt, |
1095 | | const xmlChar *fullname, |
1096 | | const xmlChar *fullattr, |
1097 | | int type) |
1098 | 1.79k | { |
1099 | 1.79k | if (ctxt->attsSpecial == NULL) { |
1100 | 14 | ctxt->attsSpecial = xmlHashCreateDict(10, ctxt->dict); |
1101 | 14 | if (ctxt->attsSpecial == NULL) |
1102 | 0 | goto mem_error; |
1103 | 14 | } |
1104 | | |
1105 | 1.79k | if (xmlHashLookup2(ctxt->attsSpecial, fullname, fullattr) != NULL) |
1106 | 1.57k | return; |
1107 | | |
1108 | 222 | xmlHashAddEntry2(ctxt->attsSpecial, fullname, fullattr, |
1109 | 222 | (void *) (ptrdiff_t) type); |
1110 | 222 | return; |
1111 | | |
1112 | 0 | mem_error: |
1113 | 0 | xmlErrMemory(ctxt, NULL); |
1114 | 0 | return; |
1115 | 1.79k | } |
1116 | | |
1117 | | /** |
1118 | | * xmlCleanSpecialAttrCallback: |
1119 | | * |
1120 | | * Removes CDATA attributes from the special attribute table |
1121 | | */ |
1122 | | static void |
1123 | | xmlCleanSpecialAttrCallback(void *payload, void *data, |
1124 | | const xmlChar *fullname, const xmlChar *fullattr, |
1125 | 2 | const xmlChar *unused ATTRIBUTE_UNUSED) { |
1126 | 2 | xmlParserCtxtPtr ctxt = (xmlParserCtxtPtr) data; |
1127 | | |
1128 | 2 | if (((ptrdiff_t) payload) == XML_ATTRIBUTE_CDATA) { |
1129 | 0 | xmlHashRemoveEntry2(ctxt->attsSpecial, fullname, fullattr, NULL); |
1130 | 0 | } |
1131 | 2 | } |
1132 | | |
1133 | | /** |
1134 | | * xmlCleanSpecialAttr: |
1135 | | * @ctxt: an XML parser context |
1136 | | * |
1137 | | * Trim the list of attributes defined to remove all those of type |
1138 | | * CDATA as they are not special. This call should be done when finishing |
1139 | | * to parse the DTD and before starting to parse the document root. |
1140 | | */ |
1141 | | static void |
1142 | | xmlCleanSpecialAttr(xmlParserCtxtPtr ctxt) |
1143 | 49 | { |
1144 | 49 | if (ctxt->attsSpecial == NULL) |
1145 | 47 | return; |
1146 | | |
1147 | 2 | xmlHashScanFull(ctxt->attsSpecial, xmlCleanSpecialAttrCallback, ctxt); |
1148 | | |
1149 | 2 | if (xmlHashSize(ctxt->attsSpecial) == 0) { |
1150 | 0 | xmlHashFree(ctxt->attsSpecial, NULL); |
1151 | 0 | ctxt->attsSpecial = NULL; |
1152 | 0 | } |
1153 | 2 | return; |
1154 | 49 | } |
1155 | | |
1156 | | /** |
1157 | | * xmlCheckLanguageID: |
1158 | | * @lang: pointer to the string value |
1159 | | * |
1160 | | * DEPRECATED: Internal function, do not use. |
1161 | | * |
1162 | | * Checks that the value conforms to the LanguageID production: |
1163 | | * |
1164 | | * NOTE: this is somewhat deprecated, those productions were removed from |
1165 | | * the XML Second edition. |
1166 | | * |
1167 | | * [33] LanguageID ::= Langcode ('-' Subcode)* |
1168 | | * [34] Langcode ::= ISO639Code | IanaCode | UserCode |
1169 | | * [35] ISO639Code ::= ([a-z] | [A-Z]) ([a-z] | [A-Z]) |
1170 | | * [36] IanaCode ::= ('i' | 'I') '-' ([a-z] | [A-Z])+ |
1171 | | * [37] UserCode ::= ('x' | 'X') '-' ([a-z] | [A-Z])+ |
1172 | | * [38] Subcode ::= ([a-z] | [A-Z])+ |
1173 | | * |
1174 | | * The current REC reference the successors of RFC 1766, currently 5646 |
1175 | | * |
1176 | | * http://www.rfc-editor.org/rfc/rfc5646.txt |
1177 | | * langtag = language |
1178 | | * ["-" script] |
1179 | | * ["-" region] |
1180 | | * *("-" variant) |
1181 | | * *("-" extension) |
1182 | | * ["-" privateuse] |
1183 | | * language = 2*3ALPHA ; shortest ISO 639 code |
1184 | | * ["-" extlang] ; sometimes followed by |
1185 | | * ; extended language subtags |
1186 | | * / 4ALPHA ; or reserved for future use |
1187 | | * / 5*8ALPHA ; or registered language subtag |
1188 | | * |
1189 | | * extlang = 3ALPHA ; selected ISO 639 codes |
1190 | | * *2("-" 3ALPHA) ; permanently reserved |
1191 | | * |
1192 | | * script = 4ALPHA ; ISO 15924 code |
1193 | | * |
1194 | | * region = 2ALPHA ; ISO 3166-1 code |
1195 | | * / 3DIGIT ; UN M.49 code |
1196 | | * |
1197 | | * variant = 5*8alphanum ; registered variants |
1198 | | * / (DIGIT 3alphanum) |
1199 | | * |
1200 | | * extension = singleton 1*("-" (2*8alphanum)) |
1201 | | * |
1202 | | * ; Single alphanumerics |
1203 | | * ; "x" reserved for private use |
1204 | | * singleton = DIGIT ; 0 - 9 |
1205 | | * / %x41-57 ; A - W |
1206 | | * / %x59-5A ; Y - Z |
1207 | | * / %x61-77 ; a - w |
1208 | | * / %x79-7A ; y - z |
1209 | | * |
1210 | | * it sounds right to still allow Irregular i-xxx IANA and user codes too |
1211 | | * The parser below doesn't try to cope with extension or privateuse |
1212 | | * that could be added but that's not interoperable anyway |
1213 | | * |
1214 | | * Returns 1 if correct 0 otherwise |
1215 | | **/ |
1216 | | int |
1217 | | xmlCheckLanguageID(const xmlChar * lang) |
1218 | 0 | { |
1219 | 0 | const xmlChar *cur = lang, *nxt; |
1220 | |
|
1221 | 0 | if (cur == NULL) |
1222 | 0 | return (0); |
1223 | 0 | if (((cur[0] == 'i') && (cur[1] == '-')) || |
1224 | 0 | ((cur[0] == 'I') && (cur[1] == '-')) || |
1225 | 0 | ((cur[0] == 'x') && (cur[1] == '-')) || |
1226 | 0 | ((cur[0] == 'X') && (cur[1] == '-'))) { |
1227 | | /* |
1228 | | * Still allow IANA code and user code which were coming |
1229 | | * from the previous version of the XML-1.0 specification |
1230 | | * it's deprecated but we should not fail |
1231 | | */ |
1232 | 0 | cur += 2; |
1233 | 0 | while (((cur[0] >= 'A') && (cur[0] <= 'Z')) || |
1234 | 0 | ((cur[0] >= 'a') && (cur[0] <= 'z'))) |
1235 | 0 | cur++; |
1236 | 0 | return(cur[0] == 0); |
1237 | 0 | } |
1238 | 0 | nxt = cur; |
1239 | 0 | while (((nxt[0] >= 'A') && (nxt[0] <= 'Z')) || |
1240 | 0 | ((nxt[0] >= 'a') && (nxt[0] <= 'z'))) |
1241 | 0 | nxt++; |
1242 | 0 | if (nxt - cur >= 4) { |
1243 | | /* |
1244 | | * Reserved |
1245 | | */ |
1246 | 0 | if ((nxt - cur > 8) || (nxt[0] != 0)) |
1247 | 0 | return(0); |
1248 | 0 | return(1); |
1249 | 0 | } |
1250 | 0 | if (nxt - cur < 2) |
1251 | 0 | return(0); |
1252 | | /* we got an ISO 639 code */ |
1253 | 0 | if (nxt[0] == 0) |
1254 | 0 | return(1); |
1255 | 0 | if (nxt[0] != '-') |
1256 | 0 | return(0); |
1257 | | |
1258 | 0 | nxt++; |
1259 | 0 | cur = nxt; |
1260 | | /* now we can have extlang or script or region or variant */ |
1261 | 0 | if ((nxt[0] >= '0') && (nxt[0] <= '9')) |
1262 | 0 | goto region_m49; |
1263 | | |
1264 | 0 | while (((nxt[0] >= 'A') && (nxt[0] <= 'Z')) || |
1265 | 0 | ((nxt[0] >= 'a') && (nxt[0] <= 'z'))) |
1266 | 0 | nxt++; |
1267 | 0 | if (nxt - cur == 4) |
1268 | 0 | goto script; |
1269 | 0 | if (nxt - cur == 2) |
1270 | 0 | goto region; |
1271 | 0 | if ((nxt - cur >= 5) && (nxt - cur <= 8)) |
1272 | 0 | goto variant; |
1273 | 0 | if (nxt - cur != 3) |
1274 | 0 | return(0); |
1275 | | /* we parsed an extlang */ |
1276 | 0 | if (nxt[0] == 0) |
1277 | 0 | return(1); |
1278 | 0 | if (nxt[0] != '-') |
1279 | 0 | return(0); |
1280 | | |
1281 | 0 | nxt++; |
1282 | 0 | cur = nxt; |
1283 | | /* now we can have script or region or variant */ |
1284 | 0 | if ((nxt[0] >= '0') && (nxt[0] <= '9')) |
1285 | 0 | goto region_m49; |
1286 | | |
1287 | 0 | while (((nxt[0] >= 'A') && (nxt[0] <= 'Z')) || |
1288 | 0 | ((nxt[0] >= 'a') && (nxt[0] <= 'z'))) |
1289 | 0 | nxt++; |
1290 | 0 | if (nxt - cur == 2) |
1291 | 0 | goto region; |
1292 | 0 | if ((nxt - cur >= 5) && (nxt - cur <= 8)) |
1293 | 0 | goto variant; |
1294 | 0 | if (nxt - cur != 4) |
1295 | 0 | return(0); |
1296 | | /* we parsed a script */ |
1297 | 0 | script: |
1298 | 0 | if (nxt[0] == 0) |
1299 | 0 | return(1); |
1300 | 0 | if (nxt[0] != '-') |
1301 | 0 | return(0); |
1302 | | |
1303 | 0 | nxt++; |
1304 | 0 | cur = nxt; |
1305 | | /* now we can have region or variant */ |
1306 | 0 | if ((nxt[0] >= '0') && (nxt[0] <= '9')) |
1307 | 0 | goto region_m49; |
1308 | | |
1309 | 0 | while (((nxt[0] >= 'A') && (nxt[0] <= 'Z')) || |
1310 | 0 | ((nxt[0] >= 'a') && (nxt[0] <= 'z'))) |
1311 | 0 | nxt++; |
1312 | |
|
1313 | 0 | if ((nxt - cur >= 5) && (nxt - cur <= 8)) |
1314 | 0 | goto variant; |
1315 | 0 | if (nxt - cur != 2) |
1316 | 0 | return(0); |
1317 | | /* we parsed a region */ |
1318 | 0 | region: |
1319 | 0 | if (nxt[0] == 0) |
1320 | 0 | return(1); |
1321 | 0 | if (nxt[0] != '-') |
1322 | 0 | return(0); |
1323 | | |
1324 | 0 | nxt++; |
1325 | 0 | cur = nxt; |
1326 | | /* now we can just have a variant */ |
1327 | 0 | while (((nxt[0] >= 'A') && (nxt[0] <= 'Z')) || |
1328 | 0 | ((nxt[0] >= 'a') && (nxt[0] <= 'z'))) |
1329 | 0 | nxt++; |
1330 | |
|
1331 | 0 | if ((nxt - cur < 5) || (nxt - cur > 8)) |
1332 | 0 | return(0); |
1333 | | |
1334 | | /* we parsed a variant */ |
1335 | 0 | variant: |
1336 | 0 | if (nxt[0] == 0) |
1337 | 0 | return(1); |
1338 | 0 | if (nxt[0] != '-') |
1339 | 0 | return(0); |
1340 | | /* extensions and private use subtags not checked */ |
1341 | 0 | return (1); |
1342 | | |
1343 | 0 | region_m49: |
1344 | 0 | if (((nxt[1] >= '0') && (nxt[1] <= '9')) && |
1345 | 0 | ((nxt[2] >= '0') && (nxt[2] <= '9'))) { |
1346 | 0 | nxt += 3; |
1347 | 0 | goto region; |
1348 | 0 | } |
1349 | 0 | return(0); |
1350 | 0 | } |
1351 | | |
1352 | | /************************************************************************ |
1353 | | * * |
1354 | | * Parser stacks related functions and macros * |
1355 | | * * |
1356 | | ************************************************************************/ |
1357 | | |
1358 | | static xmlEntityPtr xmlParseStringEntityRef(xmlParserCtxtPtr ctxt, |
1359 | | const xmlChar ** str); |
1360 | | |
1361 | | #ifdef SAX2 |
1362 | | /** |
1363 | | * nsPush: |
1364 | | * @ctxt: an XML parser context |
1365 | | * @prefix: the namespace prefix or NULL |
1366 | | * @URL: the namespace name |
1367 | | * |
1368 | | * Pushes a new parser namespace on top of the ns stack |
1369 | | * |
1370 | | * Returns -1 in case of error, -2 if the namespace should be discarded |
1371 | | * and the index in the stack otherwise. |
1372 | | */ |
1373 | | static int |
1374 | | nsPush(xmlParserCtxtPtr ctxt, const xmlChar *prefix, const xmlChar *URL) |
1375 | 6.63k | { |
1376 | 6.63k | if (ctxt->options & XML_PARSE_NSCLEAN) { |
1377 | 0 | int i; |
1378 | 0 | for (i = ctxt->nsNr - 2;i >= 0;i -= 2) { |
1379 | 0 | if (ctxt->nsTab[i] == prefix) { |
1380 | | /* in scope */ |
1381 | 0 | if (ctxt->nsTab[i + 1] == URL) |
1382 | 0 | return(-2); |
1383 | | /* out of scope keep it */ |
1384 | 0 | break; |
1385 | 0 | } |
1386 | 0 | } |
1387 | 0 | } |
1388 | 6.63k | if ((ctxt->nsMax == 0) || (ctxt->nsTab == NULL)) { |
1389 | 73 | ctxt->nsMax = 10; |
1390 | 73 | ctxt->nsNr = 0; |
1391 | 73 | ctxt->nsTab = (const xmlChar **) |
1392 | 73 | xmlMalloc(ctxt->nsMax * sizeof(xmlChar *)); |
1393 | 73 | if (ctxt->nsTab == NULL) { |
1394 | 0 | xmlErrMemory(ctxt, NULL); |
1395 | 0 | ctxt->nsMax = 0; |
1396 | 0 | return (-1); |
1397 | 0 | } |
1398 | 6.56k | } else if (ctxt->nsNr >= ctxt->nsMax) { |
1399 | 43 | const xmlChar ** tmp; |
1400 | 43 | ctxt->nsMax *= 2; |
1401 | 43 | tmp = (const xmlChar **) xmlRealloc((char *) ctxt->nsTab, |
1402 | 43 | ctxt->nsMax * sizeof(ctxt->nsTab[0])); |
1403 | 43 | if (tmp == NULL) { |
1404 | 0 | xmlErrMemory(ctxt, NULL); |
1405 | 0 | ctxt->nsMax /= 2; |
1406 | 0 | return (-1); |
1407 | 0 | } |
1408 | 43 | ctxt->nsTab = tmp; |
1409 | 43 | } |
1410 | 6.63k | ctxt->nsTab[ctxt->nsNr++] = prefix; |
1411 | 6.63k | ctxt->nsTab[ctxt->nsNr++] = URL; |
1412 | 6.63k | return (ctxt->nsNr); |
1413 | 6.63k | } |
1414 | | /** |
1415 | | * nsPop: |
1416 | | * @ctxt: an XML parser context |
1417 | | * @nr: the number to pop |
1418 | | * |
1419 | | * Pops the top @nr parser prefix/namespace from the ns stack |
1420 | | * |
1421 | | * Returns the number of namespaces removed |
1422 | | */ |
1423 | | static int |
1424 | | nsPop(xmlParserCtxtPtr ctxt, int nr) |
1425 | 5.76k | { |
1426 | 5.76k | int i; |
1427 | | |
1428 | 5.76k | if (ctxt->nsTab == NULL) return(0); |
1429 | 5.76k | if (ctxt->nsNr < nr) { |
1430 | 0 | xmlGenericError(xmlGenericErrorContext, "Pbm popping %d NS\n", nr); |
1431 | 0 | nr = ctxt->nsNr; |
1432 | 0 | } |
1433 | 5.76k | if (ctxt->nsNr <= 0) |
1434 | 0 | return (0); |
1435 | | |
1436 | 18.1k | for (i = 0;i < nr;i++) { |
1437 | 12.3k | ctxt->nsNr--; |
1438 | 12.3k | ctxt->nsTab[ctxt->nsNr] = NULL; |
1439 | 12.3k | } |
1440 | 5.76k | return(nr); |
1441 | 5.76k | } |
1442 | | #endif |
1443 | | |
1444 | | static int |
1445 | 88 | xmlCtxtGrowAttrs(xmlParserCtxtPtr ctxt, int nr) { |
1446 | 88 | const xmlChar **atts; |
1447 | 88 | int *attallocs; |
1448 | 88 | int maxatts; |
1449 | | |
1450 | 88 | if (nr + 5 > ctxt->maxatts) { |
1451 | 88 | maxatts = ctxt->maxatts == 0 ? 55 : (nr + 5) * 2; |
1452 | 88 | atts = (const xmlChar **) xmlMalloc( |
1453 | 88 | maxatts * sizeof(const xmlChar *)); |
1454 | 88 | if (atts == NULL) goto mem_error; |
1455 | 88 | attallocs = (int *) xmlRealloc((void *) ctxt->attallocs, |
1456 | 88 | (maxatts / 5) * sizeof(int)); |
1457 | 88 | if (attallocs == NULL) { |
1458 | 0 | xmlFree(atts); |
1459 | 0 | goto mem_error; |
1460 | 0 | } |
1461 | 88 | if (ctxt->maxatts > 0) |
1462 | 0 | memcpy(atts, ctxt->atts, ctxt->maxatts * sizeof(const xmlChar *)); |
1463 | 88 | xmlFree(ctxt->atts); |
1464 | 88 | ctxt->atts = atts; |
1465 | 88 | ctxt->attallocs = attallocs; |
1466 | 88 | ctxt->maxatts = maxatts; |
1467 | 88 | } |
1468 | 88 | return(ctxt->maxatts); |
1469 | 0 | mem_error: |
1470 | 0 | xmlErrMemory(ctxt, NULL); |
1471 | 0 | return(-1); |
1472 | 88 | } |
1473 | | |
1474 | | /** |
1475 | | * inputPush: |
1476 | | * @ctxt: an XML parser context |
1477 | | * @value: the parser input |
1478 | | * |
1479 | | * Pushes a new parser input on top of the input stack |
1480 | | * |
1481 | | * Returns -1 in case of error, the index in the stack otherwise |
1482 | | */ |
1483 | | int |
1484 | | inputPush(xmlParserCtxtPtr ctxt, xmlParserInputPtr value) |
1485 | 410 | { |
1486 | 410 | if ((ctxt == NULL) || (value == NULL)) |
1487 | 0 | return(-1); |
1488 | 410 | if (ctxt->inputNr >= ctxt->inputMax) { |
1489 | 0 | size_t newSize = ctxt->inputMax * 2; |
1490 | 0 | xmlParserInputPtr *tmp; |
1491 | |
|
1492 | 0 | tmp = (xmlParserInputPtr *) xmlRealloc(ctxt->inputTab, |
1493 | 0 | newSize * sizeof(*tmp)); |
1494 | 0 | if (tmp == NULL) { |
1495 | 0 | xmlErrMemory(ctxt, NULL); |
1496 | 0 | return (-1); |
1497 | 0 | } |
1498 | 0 | ctxt->inputTab = tmp; |
1499 | 0 | ctxt->inputMax = newSize; |
1500 | 0 | } |
1501 | 410 | ctxt->inputTab[ctxt->inputNr] = value; |
1502 | 410 | ctxt->input = value; |
1503 | 410 | return (ctxt->inputNr++); |
1504 | 410 | } |
1505 | | /** |
1506 | | * inputPop: |
1507 | | * @ctxt: an XML parser context |
1508 | | * |
1509 | | * Pops the top parser input from the input stack |
1510 | | * |
1511 | | * Returns the input just removed |
1512 | | */ |
1513 | | xmlParserInputPtr |
1514 | | inputPop(xmlParserCtxtPtr ctxt) |
1515 | 1.23k | { |
1516 | 1.23k | xmlParserInputPtr ret; |
1517 | | |
1518 | 1.23k | if (ctxt == NULL) |
1519 | 0 | return(NULL); |
1520 | 1.23k | if (ctxt->inputNr <= 0) |
1521 | 820 | return (NULL); |
1522 | 410 | ctxt->inputNr--; |
1523 | 410 | if (ctxt->inputNr > 0) |
1524 | 0 | ctxt->input = ctxt->inputTab[ctxt->inputNr - 1]; |
1525 | 410 | else |
1526 | 410 | ctxt->input = NULL; |
1527 | 410 | ret = ctxt->inputTab[ctxt->inputNr]; |
1528 | 410 | ctxt->inputTab[ctxt->inputNr] = NULL; |
1529 | 410 | return (ret); |
1530 | 1.23k | } |
1531 | | /** |
1532 | | * nodePush: |
1533 | | * @ctxt: an XML parser context |
1534 | | * @value: the element node |
1535 | | * |
1536 | | * DEPRECATED: Internal function, do not use. |
1537 | | * |
1538 | | * Pushes a new element node on top of the node stack |
1539 | | * |
1540 | | * Returns -1 in case of error, the index in the stack otherwise |
1541 | | */ |
1542 | | int |
1543 | | nodePush(xmlParserCtxtPtr ctxt, xmlNodePtr value) |
1544 | 1.34M | { |
1545 | 1.34M | if (ctxt == NULL) return(0); |
1546 | 1.34M | if (ctxt->nodeNr >= ctxt->nodeMax) { |
1547 | 476 | xmlNodePtr *tmp; |
1548 | | |
1549 | 476 | tmp = (xmlNodePtr *) xmlRealloc(ctxt->nodeTab, |
1550 | 476 | ctxt->nodeMax * 2 * |
1551 | 476 | sizeof(ctxt->nodeTab[0])); |
1552 | 476 | if (tmp == NULL) { |
1553 | 0 | xmlErrMemory(ctxt, NULL); |
1554 | 0 | return (-1); |
1555 | 0 | } |
1556 | 476 | ctxt->nodeTab = tmp; |
1557 | 476 | ctxt->nodeMax *= 2; |
1558 | 476 | } |
1559 | 1.34M | if ((((unsigned int) ctxt->nodeNr) > xmlParserMaxDepth) && |
1560 | 1.34M | ((ctxt->options & XML_PARSE_HUGE) == 0)) { |
1561 | 0 | xmlFatalErrMsgInt(ctxt, XML_ERR_INTERNAL_ERROR, |
1562 | 0 | "Excessive depth in document: %d use XML_PARSE_HUGE option\n", |
1563 | 0 | xmlParserMaxDepth); |
1564 | 0 | xmlHaltParser(ctxt); |
1565 | 0 | return(-1); |
1566 | 0 | } |
1567 | 1.34M | ctxt->nodeTab[ctxt->nodeNr] = value; |
1568 | 1.34M | ctxt->node = value; |
1569 | 1.34M | return (ctxt->nodeNr++); |
1570 | 1.34M | } |
1571 | | |
1572 | | /** |
1573 | | * nodePop: |
1574 | | * @ctxt: an XML parser context |
1575 | | * |
1576 | | * DEPRECATED: Internal function, do not use. |
1577 | | * |
1578 | | * Pops the top element node from the node stack |
1579 | | * |
1580 | | * Returns the node just removed |
1581 | | */ |
1582 | | xmlNodePtr |
1583 | | nodePop(xmlParserCtxtPtr ctxt) |
1584 | 1.33M | { |
1585 | 1.33M | xmlNodePtr ret; |
1586 | | |
1587 | 1.33M | if (ctxt == NULL) return(NULL); |
1588 | 1.33M | if (ctxt->nodeNr <= 0) |
1589 | 0 | return (NULL); |
1590 | 1.33M | ctxt->nodeNr--; |
1591 | 1.33M | if (ctxt->nodeNr > 0) |
1592 | 1.33M | ctxt->node = ctxt->nodeTab[ctxt->nodeNr - 1]; |
1593 | 3 | else |
1594 | 3 | ctxt->node = NULL; |
1595 | 1.33M | ret = ctxt->nodeTab[ctxt->nodeNr]; |
1596 | 1.33M | ctxt->nodeTab[ctxt->nodeNr] = NULL; |
1597 | 1.33M | return (ret); |
1598 | 1.33M | } |
1599 | | |
1600 | | /** |
1601 | | * nameNsPush: |
1602 | | * @ctxt: an XML parser context |
1603 | | * @value: the element name |
1604 | | * @prefix: the element prefix |
1605 | | * @URI: the element namespace name |
1606 | | * @line: the current line number for error messages |
1607 | | * @nsNr: the number of namespaces pushed on the namespace table |
1608 | | * |
1609 | | * Pushes a new element name/prefix/URL on top of the name stack |
1610 | | * |
1611 | | * Returns -1 in case of error, the index in the stack otherwise |
1612 | | */ |
1613 | | static int |
1614 | | nameNsPush(xmlParserCtxtPtr ctxt, const xmlChar * value, |
1615 | | const xmlChar *prefix, const xmlChar *URI, int line, int nsNr) |
1616 | 1.34M | { |
1617 | 1.34M | xmlStartTag *tag; |
1618 | | |
1619 | 1.34M | if (ctxt->nameNr >= ctxt->nameMax) { |
1620 | 476 | const xmlChar * *tmp; |
1621 | 476 | xmlStartTag *tmp2; |
1622 | 476 | ctxt->nameMax *= 2; |
1623 | 476 | tmp = (const xmlChar * *) xmlRealloc((xmlChar * *)ctxt->nameTab, |
1624 | 476 | ctxt->nameMax * |
1625 | 476 | sizeof(ctxt->nameTab[0])); |
1626 | 476 | if (tmp == NULL) { |
1627 | 0 | ctxt->nameMax /= 2; |
1628 | 0 | goto mem_error; |
1629 | 0 | } |
1630 | 476 | ctxt->nameTab = tmp; |
1631 | 476 | tmp2 = (xmlStartTag *) xmlRealloc((void * *)ctxt->pushTab, |
1632 | 476 | ctxt->nameMax * |
1633 | 476 | sizeof(ctxt->pushTab[0])); |
1634 | 476 | if (tmp2 == NULL) { |
1635 | 0 | ctxt->nameMax /= 2; |
1636 | 0 | goto mem_error; |
1637 | 0 | } |
1638 | 476 | ctxt->pushTab = tmp2; |
1639 | 1.34M | } else if (ctxt->pushTab == NULL) { |
1640 | 344 | ctxt->pushTab = (xmlStartTag *) xmlMalloc(ctxt->nameMax * |
1641 | 344 | sizeof(ctxt->pushTab[0])); |
1642 | 344 | if (ctxt->pushTab == NULL) |
1643 | 0 | goto mem_error; |
1644 | 344 | } |
1645 | 1.34M | ctxt->nameTab[ctxt->nameNr] = value; |
1646 | 1.34M | ctxt->name = value; |
1647 | 1.34M | tag = &ctxt->pushTab[ctxt->nameNr]; |
1648 | 1.34M | tag->prefix = prefix; |
1649 | 1.34M | tag->URI = URI; |
1650 | 1.34M | tag->line = line; |
1651 | 1.34M | tag->nsNr = nsNr; |
1652 | 1.34M | return (ctxt->nameNr++); |
1653 | 0 | mem_error: |
1654 | 0 | xmlErrMemory(ctxt, NULL); |
1655 | 0 | return (-1); |
1656 | 1.34M | } |
1657 | | #ifdef LIBXML_PUSH_ENABLED |
1658 | | /** |
1659 | | * nameNsPop: |
1660 | | * @ctxt: an XML parser context |
1661 | | * |
1662 | | * Pops the top element/prefix/URI name from the name stack |
1663 | | * |
1664 | | * Returns the name just removed |
1665 | | */ |
1666 | | static const xmlChar * |
1667 | | nameNsPop(xmlParserCtxtPtr ctxt) |
1668 | | { |
1669 | | const xmlChar *ret; |
1670 | | |
1671 | | if (ctxt->nameNr <= 0) |
1672 | | return (NULL); |
1673 | | ctxt->nameNr--; |
1674 | | if (ctxt->nameNr > 0) |
1675 | | ctxt->name = ctxt->nameTab[ctxt->nameNr - 1]; |
1676 | | else |
1677 | | ctxt->name = NULL; |
1678 | | ret = ctxt->nameTab[ctxt->nameNr]; |
1679 | | ctxt->nameTab[ctxt->nameNr] = NULL; |
1680 | | return (ret); |
1681 | | } |
1682 | | #endif /* LIBXML_PUSH_ENABLED */ |
1683 | | |
1684 | | /** |
1685 | | * namePush: |
1686 | | * @ctxt: an XML parser context |
1687 | | * @value: the element name |
1688 | | * |
1689 | | * DEPRECATED: Internal function, do not use. |
1690 | | * |
1691 | | * Pushes a new element name on top of the name stack |
1692 | | * |
1693 | | * Returns -1 in case of error, the index in the stack otherwise |
1694 | | */ |
1695 | | int |
1696 | | namePush(xmlParserCtxtPtr ctxt, const xmlChar * value) |
1697 | 0 | { |
1698 | 0 | if (ctxt == NULL) return (-1); |
1699 | | |
1700 | 0 | if (ctxt->nameNr >= ctxt->nameMax) { |
1701 | 0 | const xmlChar * *tmp; |
1702 | 0 | tmp = (const xmlChar * *) xmlRealloc((xmlChar * *)ctxt->nameTab, |
1703 | 0 | ctxt->nameMax * 2 * |
1704 | 0 | sizeof(ctxt->nameTab[0])); |
1705 | 0 | if (tmp == NULL) { |
1706 | 0 | goto mem_error; |
1707 | 0 | } |
1708 | 0 | ctxt->nameTab = tmp; |
1709 | 0 | ctxt->nameMax *= 2; |
1710 | 0 | } |
1711 | 0 | ctxt->nameTab[ctxt->nameNr] = value; |
1712 | 0 | ctxt->name = value; |
1713 | 0 | return (ctxt->nameNr++); |
1714 | 0 | mem_error: |
1715 | 0 | xmlErrMemory(ctxt, NULL); |
1716 | 0 | return (-1); |
1717 | 0 | } |
1718 | | |
1719 | | /** |
1720 | | * namePop: |
1721 | | * @ctxt: an XML parser context |
1722 | | * |
1723 | | * DEPRECATED: Internal function, do not use. |
1724 | | * |
1725 | | * Pops the top element name from the name stack |
1726 | | * |
1727 | | * Returns the name just removed |
1728 | | */ |
1729 | | const xmlChar * |
1730 | | namePop(xmlParserCtxtPtr ctxt) |
1731 | 1.33M | { |
1732 | 1.33M | const xmlChar *ret; |
1733 | | |
1734 | 1.33M | if ((ctxt == NULL) || (ctxt->nameNr <= 0)) |
1735 | 0 | return (NULL); |
1736 | 1.33M | ctxt->nameNr--; |
1737 | 1.33M | if (ctxt->nameNr > 0) |
1738 | 1.33M | ctxt->name = ctxt->nameTab[ctxt->nameNr - 1]; |
1739 | 3 | else |
1740 | 3 | ctxt->name = NULL; |
1741 | 1.33M | ret = ctxt->nameTab[ctxt->nameNr]; |
1742 | 1.33M | ctxt->nameTab[ctxt->nameNr] = NULL; |
1743 | 1.33M | return (ret); |
1744 | 1.33M | } |
1745 | | |
1746 | 1.36M | static int spacePush(xmlParserCtxtPtr ctxt, int val) { |
1747 | 1.36M | if (ctxt->spaceNr >= ctxt->spaceMax) { |
1748 | 480 | int *tmp; |
1749 | | |
1750 | 480 | ctxt->spaceMax *= 2; |
1751 | 480 | tmp = (int *) xmlRealloc(ctxt->spaceTab, |
1752 | 480 | ctxt->spaceMax * sizeof(ctxt->spaceTab[0])); |
1753 | 480 | if (tmp == NULL) { |
1754 | 0 | xmlErrMemory(ctxt, NULL); |
1755 | 0 | ctxt->spaceMax /=2; |
1756 | 0 | return(-1); |
1757 | 0 | } |
1758 | 480 | ctxt->spaceTab = tmp; |
1759 | 480 | } |
1760 | 1.36M | ctxt->spaceTab[ctxt->spaceNr] = val; |
1761 | 1.36M | ctxt->space = &ctxt->spaceTab[ctxt->spaceNr]; |
1762 | 1.36M | return(ctxt->spaceNr++); |
1763 | 1.36M | } |
1764 | | |
1765 | 1.35M | static int spacePop(xmlParserCtxtPtr ctxt) { |
1766 | 1.35M | int ret; |
1767 | 1.35M | if (ctxt->spaceNr <= 0) return(0); |
1768 | 1.35M | ctxt->spaceNr--; |
1769 | 1.35M | if (ctxt->spaceNr > 0) |
1770 | 1.35M | ctxt->space = &ctxt->spaceTab[ctxt->spaceNr - 1]; |
1771 | 0 | else |
1772 | 0 | ctxt->space = &ctxt->spaceTab[0]; |
1773 | 1.35M | ret = ctxt->spaceTab[ctxt->spaceNr]; |
1774 | 1.35M | ctxt->spaceTab[ctxt->spaceNr] = -1; |
1775 | 1.35M | return(ret); |
1776 | 1.35M | } |
1777 | | |
1778 | | /* |
1779 | | * Macros for accessing the content. Those should be used only by the parser, |
1780 | | * and not exported. |
1781 | | * |
1782 | | * Dirty macros, i.e. one often need to make assumption on the context to |
1783 | | * use them |
1784 | | * |
1785 | | * CUR_PTR return the current pointer to the xmlChar to be parsed. |
1786 | | * To be used with extreme caution since operations consuming |
1787 | | * characters may move the input buffer to a different location ! |
1788 | | * CUR returns the current xmlChar value, i.e. a 8 bit value if compiled |
1789 | | * This should be used internally by the parser |
1790 | | * only to compare to ASCII values otherwise it would break when |
1791 | | * running with UTF-8 encoding. |
1792 | | * RAW same as CUR but in the input buffer, bypass any token |
1793 | | * extraction that may have been done |
1794 | | * NXT(n) returns the n'th next xmlChar. Same as CUR is should be used only |
1795 | | * to compare on ASCII based substring. |
1796 | | * SKIP(n) Skip n xmlChar, and must also be used only to skip ASCII defined |
1797 | | * strings without newlines within the parser. |
1798 | | * NEXT1(l) Skip 1 xmlChar, and must also be used only to skip 1 non-newline ASCII |
1799 | | * defined char within the parser. |
1800 | | * Clean macros, not dependent of an ASCII context, expect UTF-8 encoding |
1801 | | * |
1802 | | * NEXT Skip to the next character, this does the proper decoding |
1803 | | * in UTF-8 mode. It also pop-up unfinished entities on the fly. |
1804 | | * NEXTL(l) Skip the current unicode character of l xmlChars long. |
1805 | | * CUR_CHAR(l) returns the current unicode character (int), set l |
1806 | | * to the number of xmlChars used for the encoding [0-5]. |
1807 | | * CUR_SCHAR same but operate on a string instead of the context |
1808 | | * COPY_BUF copy the current unicode char to the target buffer, increment |
1809 | | * the index |
1810 | | * GROW, SHRINK handling of input buffers |
1811 | | */ |
1812 | | |
1813 | 8.89M | #define RAW (*ctxt->input->cur) |
1814 | 7.82M | #define CUR (*ctxt->input->cur) |
1815 | 11.9M | #define NXT(val) ctxt->input->cur[(val)] |
1816 | 1.39M | #define CUR_PTR ctxt->input->cur |
1817 | 1.39M | #define BASE_PTR ctxt->input->base |
1818 | | |
1819 | | #define CMP4( s, c1, c2, c3, c4 ) \ |
1820 | 3.43M | ( ((unsigned char *) s)[ 0 ] == c1 && ((unsigned char *) s)[ 1 ] == c2 && \ |
1821 | 1.72M | ((unsigned char *) s)[ 2 ] == c3 && ((unsigned char *) s)[ 3 ] == c4 ) |
1822 | | #define CMP5( s, c1, c2, c3, c4, c5 ) \ |
1823 | 3.43M | ( CMP4( s, c1, c2, c3, c4 ) && ((unsigned char *) s)[ 4 ] == c5 ) |
1824 | | #define CMP6( s, c1, c2, c3, c4, c5, c6 ) \ |
1825 | 3.38M | ( CMP5( s, c1, c2, c3, c4, c5 ) && ((unsigned char *) s)[ 5 ] == c6 ) |
1826 | | #define CMP7( s, c1, c2, c3, c4, c5, c6, c7 ) \ |
1827 | 3.33M | ( CMP6( s, c1, c2, c3, c4, c5, c6 ) && ((unsigned char *) s)[ 6 ] == c7 ) |
1828 | | #define CMP8( s, c1, c2, c3, c4, c5, c6, c7, c8 ) \ |
1829 | 3.32M | ( CMP7( s, c1, c2, c3, c4, c5, c6, c7 ) && ((unsigned char *) s)[ 7 ] == c8 ) |
1830 | | #define CMP9( s, c1, c2, c3, c4, c5, c6, c7, c8, c9 ) \ |
1831 | 1.65M | ( CMP8( s, c1, c2, c3, c4, c5, c6, c7, c8 ) && \ |
1832 | 1.65M | ((unsigned char *) s)[ 8 ] == c9 ) |
1833 | | #define CMP10( s, c1, c2, c3, c4, c5, c6, c7, c8, c9, c10 ) \ |
1834 | 96 | ( CMP9( s, c1, c2, c3, c4, c5, c6, c7, c8, c9 ) && \ |
1835 | 96 | ((unsigned char *) s)[ 9 ] == c10 ) |
1836 | | |
1837 | 87.8k | #define SKIP(val) do { \ |
1838 | 87.8k | ctxt->input->cur += (val),ctxt->input->col+=(val); \ |
1839 | 87.8k | if (*ctxt->input->cur == 0) \ |
1840 | 87.8k | xmlParserGrow(ctxt); \ |
1841 | 87.8k | } while (0) |
1842 | | |
1843 | | #define SKIPL(val) do { \ |
1844 | | int skipl; \ |
1845 | | for(skipl=0; skipl<val; skipl++) { \ |
1846 | | if (*(ctxt->input->cur) == '\n') { \ |
1847 | | ctxt->input->line++; ctxt->input->col = 1; \ |
1848 | | } else ctxt->input->col++; \ |
1849 | | ctxt->input->cur++; \ |
1850 | | } \ |
1851 | | if (*ctxt->input->cur == 0) \ |
1852 | | xmlParserGrow(ctxt); \ |
1853 | | } while (0) |
1854 | | |
1855 | 1.96M | #define SHRINK if ((ctxt->progressive == 0) && \ |
1856 | 1.96M | (ctxt->input->cur - ctxt->input->base > 2 * INPUT_CHUNK) && \ |
1857 | 1.96M | (ctxt->input->end - ctxt->input->cur < 2 * INPUT_CHUNK)) \ |
1858 | 1.96M | xmlParserShrink(ctxt); |
1859 | | |
1860 | 27.2M | #define GROW if ((ctxt->progressive == 0) && \ |
1861 | 27.2M | (ctxt->input->end - ctxt->input->cur < INPUT_CHUNK)) \ |
1862 | 27.2M | xmlParserGrow(ctxt); |
1863 | | |
1864 | 1.54M | #define SKIP_BLANKS xmlSkipBlankChars(ctxt) |
1865 | | |
1866 | 5.33M | #define NEXT xmlNextChar(ctxt) |
1867 | | |
1868 | 1.38M | #define NEXT1 { \ |
1869 | 1.38M | ctxt->input->col++; \ |
1870 | 1.38M | ctxt->input->cur++; \ |
1871 | 1.38M | if (*ctxt->input->cur == 0) \ |
1872 | 1.38M | xmlParserGrow(ctxt); \ |
1873 | 1.38M | } |
1874 | | |
1875 | 56.6M | #define NEXTL(l) do { \ |
1876 | 56.6M | if (*(ctxt->input->cur) == '\n') { \ |
1877 | 1.59M | ctxt->input->line++; ctxt->input->col = 1; \ |
1878 | 55.0M | } else ctxt->input->col++; \ |
1879 | 56.6M | ctxt->input->cur += l; \ |
1880 | 56.6M | } while (0) |
1881 | | |
1882 | 58.1M | #define CUR_CHAR(l) xmlCurrentChar(ctxt, &l) |
1883 | 15.4M | #define CUR_SCHAR(s, l) xmlStringCurrentChar(ctxt, s, &l) |
1884 | | |
1885 | | #define COPY_BUF(l,b,i,v) \ |
1886 | 64.2M | if (l == 1) b[i++] = v; \ |
1887 | 64.2M | else i += xmlCopyCharMultiByte(&b[i],v) |
1888 | | |
1889 | | /** |
1890 | | * xmlSkipBlankChars: |
1891 | | * @ctxt: the XML parser context |
1892 | | * |
1893 | | * DEPRECATED: Internal function, do not use. |
1894 | | * |
1895 | | * skip all blanks character found at that point in the input streams. |
1896 | | * It pops up finished entities in the process if allowable at that point. |
1897 | | * |
1898 | | * Returns the number of space chars skipped |
1899 | | */ |
1900 | | |
1901 | | int |
1902 | 1.54M | xmlSkipBlankChars(xmlParserCtxtPtr ctxt) { |
1903 | 1.54M | int res = 0; |
1904 | | |
1905 | | /* |
1906 | | * It's Okay to use CUR/NEXT here since all the blanks are on |
1907 | | * the ASCII range. |
1908 | | */ |
1909 | 1.54M | if (((ctxt->inputNr == 1) && (ctxt->instate != XML_PARSER_DTD)) || |
1910 | 1.54M | (ctxt->instate == XML_PARSER_START)) { |
1911 | 1.44M | const xmlChar *cur; |
1912 | | /* |
1913 | | * if we are in the document content, go really fast |
1914 | | */ |
1915 | 1.44M | cur = ctxt->input->cur; |
1916 | 1.44M | while (IS_BLANK_CH(*cur)) { |
1917 | 55.6k | if (*cur == '\n') { |
1918 | 2.58k | ctxt->input->line++; ctxt->input->col = 1; |
1919 | 53.0k | } else { |
1920 | 53.0k | ctxt->input->col++; |
1921 | 53.0k | } |
1922 | 55.6k | cur++; |
1923 | 55.6k | if (res < INT_MAX) |
1924 | 55.6k | res++; |
1925 | 55.6k | if (*cur == 0) { |
1926 | 0 | ctxt->input->cur = cur; |
1927 | 0 | xmlParserGrow(ctxt); |
1928 | 0 | cur = ctxt->input->cur; |
1929 | 0 | } |
1930 | 55.6k | } |
1931 | 1.44M | ctxt->input->cur = cur; |
1932 | 1.44M | } else { |
1933 | 102k | int expandPE = ((ctxt->external != 0) || (ctxt->inputNr != 1)); |
1934 | | |
1935 | 365k | while (ctxt->instate != XML_PARSER_EOF) { |
1936 | 365k | if (IS_BLANK_CH(CUR)) { /* CHECKED tstblanks.xml */ |
1937 | 263k | NEXT; |
1938 | 263k | } else if (CUR == '%') { |
1939 | | /* |
1940 | | * Need to handle support of entities branching here |
1941 | | */ |
1942 | 3.96k | if ((expandPE == 0) || (IS_BLANK_CH(NXT(1))) || (NXT(1) == 0)) |
1943 | 3.96k | break; |
1944 | 0 | xmlParsePEReference(ctxt); |
1945 | 98.5k | } else if (CUR == 0) { |
1946 | 16 | unsigned long consumed; |
1947 | 16 | xmlEntityPtr ent; |
1948 | | |
1949 | 16 | if (ctxt->inputNr <= 1) |
1950 | 16 | break; |
1951 | | |
1952 | 0 | consumed = ctxt->input->consumed; |
1953 | 0 | xmlSaturatedAddSizeT(&consumed, |
1954 | 0 | ctxt->input->cur - ctxt->input->base); |
1955 | | |
1956 | | /* |
1957 | | * Add to sizeentities when parsing an external entity |
1958 | | * for the first time. |
1959 | | */ |
1960 | 0 | ent = ctxt->input->entity; |
1961 | 0 | if ((ent->etype == XML_EXTERNAL_PARAMETER_ENTITY) && |
1962 | 0 | ((ent->flags & XML_ENT_PARSED) == 0)) { |
1963 | 0 | ent->flags |= XML_ENT_PARSED; |
1964 | |
|
1965 | 0 | xmlSaturatedAdd(&ctxt->sizeentities, consumed); |
1966 | 0 | } |
1967 | |
|
1968 | 0 | xmlParserEntityCheck(ctxt, consumed); |
1969 | |
|
1970 | 0 | xmlPopInput(ctxt); |
1971 | 98.5k | } else { |
1972 | 98.5k | break; |
1973 | 98.5k | } |
1974 | | |
1975 | | /* |
1976 | | * Also increase the counter when entering or exiting a PERef. |
1977 | | * The spec says: "When a parameter-entity reference is recognized |
1978 | | * in the DTD and included, its replacement text MUST be enlarged |
1979 | | * by the attachment of one leading and one following space (#x20) |
1980 | | * character." |
1981 | | */ |
1982 | 263k | if (res < INT_MAX) |
1983 | 263k | res++; |
1984 | 263k | } |
1985 | 102k | } |
1986 | 1.54M | return(res); |
1987 | 1.54M | } |
1988 | | |
1989 | | /************************************************************************ |
1990 | | * * |
1991 | | * Commodity functions to handle entities * |
1992 | | * * |
1993 | | ************************************************************************/ |
1994 | | |
1995 | | /** |
1996 | | * xmlPopInput: |
1997 | | * @ctxt: an XML parser context |
1998 | | * |
1999 | | * xmlPopInput: the current input pointed by ctxt->input came to an end |
2000 | | * pop it and return the next char. |
2001 | | * |
2002 | | * Returns the current xmlChar in the parser context |
2003 | | */ |
2004 | | xmlChar |
2005 | 0 | xmlPopInput(xmlParserCtxtPtr ctxt) { |
2006 | 0 | xmlParserInputPtr input; |
2007 | |
|
2008 | 0 | if ((ctxt == NULL) || (ctxt->inputNr <= 1)) return(0); |
2009 | 0 | if (xmlParserDebugEntities) |
2010 | 0 | xmlGenericError(xmlGenericErrorContext, |
2011 | 0 | "Popping input %d\n", ctxt->inputNr); |
2012 | 0 | if ((ctxt->inputNr > 1) && (ctxt->inSubset == 0) && |
2013 | 0 | (ctxt->instate != XML_PARSER_EOF)) |
2014 | 0 | xmlFatalErr(ctxt, XML_ERR_INTERNAL_ERROR, |
2015 | 0 | "Unfinished entity outside the DTD"); |
2016 | 0 | input = inputPop(ctxt); |
2017 | 0 | if (input->entity != NULL) |
2018 | 0 | input->entity->flags &= ~XML_ENT_EXPANDING; |
2019 | 0 | xmlFreeInputStream(input); |
2020 | 0 | if (*ctxt->input->cur == 0) |
2021 | 0 | xmlParserGrow(ctxt); |
2022 | 0 | return(CUR); |
2023 | 0 | } |
2024 | | |
2025 | | /** |
2026 | | * xmlPushInput: |
2027 | | * @ctxt: an XML parser context |
2028 | | * @input: an XML parser input fragment (entity, XML fragment ...). |
2029 | | * |
2030 | | * xmlPushInput: switch to a new input stream which is stacked on top |
2031 | | * of the previous one(s). |
2032 | | * Returns -1 in case of error or the index in the input stack |
2033 | | */ |
2034 | | int |
2035 | 0 | xmlPushInput(xmlParserCtxtPtr ctxt, xmlParserInputPtr input) { |
2036 | 0 | int ret; |
2037 | 0 | if (input == NULL) return(-1); |
2038 | | |
2039 | 0 | if (xmlParserDebugEntities) { |
2040 | 0 | if ((ctxt->input != NULL) && (ctxt->input->filename)) |
2041 | 0 | xmlGenericError(xmlGenericErrorContext, |
2042 | 0 | "%s(%d): ", ctxt->input->filename, |
2043 | 0 | ctxt->input->line); |
2044 | 0 | xmlGenericError(xmlGenericErrorContext, |
2045 | 0 | "Pushing input %d : %.30s\n", ctxt->inputNr+1, input->cur); |
2046 | 0 | } |
2047 | 0 | if (((ctxt->inputNr > 40) && ((ctxt->options & XML_PARSE_HUGE) == 0)) || |
2048 | 0 | (ctxt->inputNr > 100)) { |
2049 | 0 | xmlFatalErr(ctxt, XML_ERR_ENTITY_LOOP, NULL); |
2050 | 0 | while (ctxt->inputNr > 1) |
2051 | 0 | xmlFreeInputStream(inputPop(ctxt)); |
2052 | 0 | return(-1); |
2053 | 0 | } |
2054 | 0 | ret = inputPush(ctxt, input); |
2055 | 0 | if (ctxt->instate == XML_PARSER_EOF) |
2056 | 0 | return(-1); |
2057 | 0 | GROW; |
2058 | 0 | return(ret); |
2059 | 0 | } |
2060 | | |
2061 | | /** |
2062 | | * xmlParseCharRef: |
2063 | | * @ctxt: an XML parser context |
2064 | | * |
2065 | | * DEPRECATED: Internal function, don't use. |
2066 | | * |
2067 | | * Parse a numeric character reference. Always consumes '&'. |
2068 | | * |
2069 | | * [66] CharRef ::= '&#' [0-9]+ ';' | |
2070 | | * '&#x' [0-9a-fA-F]+ ';' |
2071 | | * |
2072 | | * [ WFC: Legal Character ] |
2073 | | * Characters referred to using character references must match the |
2074 | | * production for Char. |
2075 | | * |
2076 | | * Returns the value parsed (as an int), 0 in case of error |
2077 | | */ |
2078 | | int |
2079 | 7.35k | xmlParseCharRef(xmlParserCtxtPtr ctxt) { |
2080 | 7.35k | int val = 0; |
2081 | 7.35k | int count = 0; |
2082 | | |
2083 | | /* |
2084 | | * Using RAW/CUR/NEXT is okay since we are working on ASCII range here |
2085 | | */ |
2086 | 7.35k | if ((RAW == '&') && (NXT(1) == '#') && |
2087 | 7.35k | (NXT(2) == 'x')) { |
2088 | 6.06k | SKIP(3); |
2089 | 6.06k | GROW; |
2090 | 20.4k | while (RAW != ';') { /* loop blocked by count */ |
2091 | 16.0k | if (count++ > 20) { |
2092 | 0 | count = 0; |
2093 | 0 | GROW; |
2094 | 0 | if (ctxt->instate == XML_PARSER_EOF) |
2095 | 0 | return(0); |
2096 | 0 | } |
2097 | 16.0k | if ((RAW >= '0') && (RAW <= '9')) |
2098 | 4.74k | val = val * 16 + (CUR - '0'); |
2099 | 11.2k | else if ((RAW >= 'a') && (RAW <= 'f') && (count < 20)) |
2100 | 9.06k | val = val * 16 + (CUR - 'a') + 10; |
2101 | 2.22k | else if ((RAW >= 'A') && (RAW <= 'F') && (count < 20)) |
2102 | 577 | val = val * 16 + (CUR - 'A') + 10; |
2103 | 1.65k | else { |
2104 | 1.65k | xmlFatalErr(ctxt, XML_ERR_INVALID_HEX_CHARREF, NULL); |
2105 | 1.65k | val = 0; |
2106 | 1.65k | break; |
2107 | 1.65k | } |
2108 | 14.3k | if (val > 0x110000) |
2109 | 3.01k | val = 0x110000; |
2110 | | |
2111 | 14.3k | NEXT; |
2112 | 14.3k | count++; |
2113 | 14.3k | } |
2114 | 6.06k | if (RAW == ';') { |
2115 | | /* on purpose to avoid reentrancy problems with NEXT and SKIP */ |
2116 | 4.41k | ctxt->input->col++; |
2117 | 4.41k | ctxt->input->cur++; |
2118 | 4.41k | } |
2119 | 6.06k | } else if ((RAW == '&') && (NXT(1) == '#')) { |
2120 | 1.28k | SKIP(2); |
2121 | 1.28k | GROW; |
2122 | 4.70k | while (RAW != ';') { /* loop blocked by count */ |
2123 | 4.08k | if (count++ > 20) { |
2124 | 0 | count = 0; |
2125 | 0 | GROW; |
2126 | 0 | if (ctxt->instate == XML_PARSER_EOF) |
2127 | 0 | return(0); |
2128 | 0 | } |
2129 | 4.08k | if ((RAW >= '0') && (RAW <= '9')) |
2130 | 3.42k | val = val * 10 + (CUR - '0'); |
2131 | 666 | else { |
2132 | 666 | xmlFatalErr(ctxt, XML_ERR_INVALID_DEC_CHARREF, NULL); |
2133 | 666 | val = 0; |
2134 | 666 | break; |
2135 | 666 | } |
2136 | 3.42k | if (val > 0x110000) |
2137 | 0 | val = 0x110000; |
2138 | | |
2139 | 3.42k | NEXT; |
2140 | 3.42k | count++; |
2141 | 3.42k | } |
2142 | 1.28k | if (RAW == ';') { |
2143 | | /* on purpose to avoid reentrancy problems with NEXT and SKIP */ |
2144 | 620 | ctxt->input->col++; |
2145 | 620 | ctxt->input->cur++; |
2146 | 620 | } |
2147 | 1.28k | } else { |
2148 | 0 | if (RAW == '&') |
2149 | 0 | SKIP(1); |
2150 | 0 | xmlFatalErr(ctxt, XML_ERR_INVALID_CHARREF, NULL); |
2151 | 0 | } |
2152 | | |
2153 | | /* |
2154 | | * [ WFC: Legal Character ] |
2155 | | * Characters referred to using character references must match the |
2156 | | * production for Char. |
2157 | | */ |
2158 | 7.35k | if (val >= 0x110000) { |
2159 | 0 | xmlFatalErrMsgInt(ctxt, XML_ERR_INVALID_CHAR, |
2160 | 0 | "xmlParseCharRef: character reference out of bounds\n", |
2161 | 0 | val); |
2162 | 7.35k | } else if (IS_CHAR(val)) { |
2163 | 5.03k | return(val); |
2164 | 5.03k | } else { |
2165 | 2.32k | xmlFatalErrMsgInt(ctxt, XML_ERR_INVALID_CHAR, |
2166 | 2.32k | "xmlParseCharRef: invalid xmlChar value %d\n", |
2167 | 2.32k | val); |
2168 | 2.32k | } |
2169 | 2.32k | return(0); |
2170 | 7.35k | } |
2171 | | |
2172 | | /** |
2173 | | * xmlParseStringCharRef: |
2174 | | * @ctxt: an XML parser context |
2175 | | * @str: a pointer to an index in the string |
2176 | | * |
2177 | | * parse Reference declarations, variant parsing from a string rather |
2178 | | * than an an input flow. |
2179 | | * |
2180 | | * [66] CharRef ::= '&#' [0-9]+ ';' | |
2181 | | * '&#x' [0-9a-fA-F]+ ';' |
2182 | | * |
2183 | | * [ WFC: Legal Character ] |
2184 | | * Characters referred to using character references must match the |
2185 | | * production for Char. |
2186 | | * |
2187 | | * Returns the value parsed (as an int), 0 in case of error, str will be |
2188 | | * updated to the current value of the index |
2189 | | */ |
2190 | | static int |
2191 | 40.6k | xmlParseStringCharRef(xmlParserCtxtPtr ctxt, const xmlChar **str) { |
2192 | 40.6k | const xmlChar *ptr; |
2193 | 40.6k | xmlChar cur; |
2194 | 40.6k | int val = 0; |
2195 | | |
2196 | 40.6k | if ((str == NULL) || (*str == NULL)) return(0); |
2197 | 40.6k | ptr = *str; |
2198 | 40.6k | cur = *ptr; |
2199 | 40.6k | if ((cur == '&') && (ptr[1] == '#') && (ptr[2] == 'x')) { |
2200 | 24.2k | ptr += 3; |
2201 | 24.2k | cur = *ptr; |
2202 | 131k | while (cur != ';') { /* Non input consuming loop */ |
2203 | 110k | if ((cur >= '0') && (cur <= '9')) |
2204 | 1.25k | val = val * 16 + (cur - '0'); |
2205 | 109k | else if ((cur >= 'a') && (cur <= 'f')) |
2206 | 105k | val = val * 16 + (cur - 'a') + 10; |
2207 | 3.49k | else if ((cur >= 'A') && (cur <= 'F')) |
2208 | 6 | val = val * 16 + (cur - 'A') + 10; |
2209 | 3.48k | else { |
2210 | 3.48k | xmlFatalErr(ctxt, XML_ERR_INVALID_HEX_CHARREF, NULL); |
2211 | 3.48k | val = 0; |
2212 | 3.48k | break; |
2213 | 3.48k | } |
2214 | 107k | if (val > 0x110000) |
2215 | 68.4k | val = 0x110000; |
2216 | | |
2217 | 107k | ptr++; |
2218 | 107k | cur = *ptr; |
2219 | 107k | } |
2220 | 24.2k | if (cur == ';') |
2221 | 20.7k | ptr++; |
2222 | 24.2k | } else if ((cur == '&') && (ptr[1] == '#')){ |
2223 | 16.3k | ptr += 2; |
2224 | 16.3k | cur = *ptr; |
2225 | 63.8k | while (cur != ';') { /* Non input consuming loops */ |
2226 | 48.7k | if ((cur >= '0') && (cur <= '9')) |
2227 | 47.4k | val = val * 10 + (cur - '0'); |
2228 | 1.32k | else { |
2229 | 1.32k | xmlFatalErr(ctxt, XML_ERR_INVALID_DEC_CHARREF, NULL); |
2230 | 1.32k | val = 0; |
2231 | 1.32k | break; |
2232 | 1.32k | } |
2233 | 47.4k | if (val > 0x110000) |
2234 | 523 | val = 0x110000; |
2235 | | |
2236 | 47.4k | ptr++; |
2237 | 47.4k | cur = *ptr; |
2238 | 47.4k | } |
2239 | 16.3k | if (cur == ';') |
2240 | 15.0k | ptr++; |
2241 | 16.3k | } else { |
2242 | 0 | xmlFatalErr(ctxt, XML_ERR_INVALID_CHARREF, NULL); |
2243 | 0 | return(0); |
2244 | 0 | } |
2245 | 40.6k | *str = ptr; |
2246 | | |
2247 | | /* |
2248 | | * [ WFC: Legal Character ] |
2249 | | * Characters referred to using character references must match the |
2250 | | * production for Char. |
2251 | | */ |
2252 | 40.6k | if (val >= 0x110000) { |
2253 | 136 | xmlFatalErrMsgInt(ctxt, XML_ERR_INVALID_CHAR, |
2254 | 136 | "xmlParseStringCharRef: character reference out of bounds\n", |
2255 | 136 | val); |
2256 | 40.5k | } else if (IS_CHAR(val)) { |
2257 | 35.2k | return(val); |
2258 | 35.2k | } else { |
2259 | 5.26k | xmlFatalErrMsgInt(ctxt, XML_ERR_INVALID_CHAR, |
2260 | 5.26k | "xmlParseStringCharRef: invalid xmlChar value %d\n", |
2261 | 5.26k | val); |
2262 | 5.26k | } |
2263 | 5.39k | return(0); |
2264 | 40.6k | } |
2265 | | |
2266 | | /** |
2267 | | * xmlParserHandlePEReference: |
2268 | | * @ctxt: the parser context |
2269 | | * |
2270 | | * DEPRECATED: Internal function, do not use. |
2271 | | * |
2272 | | * [69] PEReference ::= '%' Name ';' |
2273 | | * |
2274 | | * [ WFC: No Recursion ] |
2275 | | * A parsed entity must not contain a recursive |
2276 | | * reference to itself, either directly or indirectly. |
2277 | | * |
2278 | | * [ WFC: Entity Declared ] |
2279 | | * In a document without any DTD, a document with only an internal DTD |
2280 | | * subset which contains no parameter entity references, or a document |
2281 | | * with "standalone='yes'", ... ... The declaration of a parameter |
2282 | | * entity must precede any reference to it... |
2283 | | * |
2284 | | * [ VC: Entity Declared ] |
2285 | | * In a document with an external subset or external parameter entities |
2286 | | * with "standalone='no'", ... ... The declaration of a parameter entity |
2287 | | * must precede any reference to it... |
2288 | | * |
2289 | | * [ WFC: In DTD ] |
2290 | | * Parameter-entity references may only appear in the DTD. |
2291 | | * NOTE: misleading but this is handled. |
2292 | | * |
2293 | | * A PEReference may have been detected in the current input stream |
2294 | | * the handling is done accordingly to |
2295 | | * http://www.w3.org/TR/REC-xml#entproc |
2296 | | * i.e. |
2297 | | * - Included in literal in entity values |
2298 | | * - Included as Parameter Entity reference within DTDs |
2299 | | */ |
2300 | | void |
2301 | 0 | xmlParserHandlePEReference(xmlParserCtxtPtr ctxt) { |
2302 | 0 | switch(ctxt->instate) { |
2303 | 0 | case XML_PARSER_CDATA_SECTION: |
2304 | 0 | return; |
2305 | 0 | case XML_PARSER_COMMENT: |
2306 | 0 | return; |
2307 | 0 | case XML_PARSER_START_TAG: |
2308 | 0 | return; |
2309 | 0 | case XML_PARSER_END_TAG: |
2310 | 0 | return; |
2311 | 0 | case XML_PARSER_EOF: |
2312 | 0 | xmlFatalErr(ctxt, XML_ERR_PEREF_AT_EOF, NULL); |
2313 | 0 | return; |
2314 | 0 | case XML_PARSER_PROLOG: |
2315 | 0 | case XML_PARSER_START: |
2316 | 0 | case XML_PARSER_MISC: |
2317 | 0 | xmlFatalErr(ctxt, XML_ERR_PEREF_IN_PROLOG, NULL); |
2318 | 0 | return; |
2319 | 0 | case XML_PARSER_ENTITY_DECL: |
2320 | 0 | case XML_PARSER_CONTENT: |
2321 | 0 | case XML_PARSER_ATTRIBUTE_VALUE: |
2322 | 0 | case XML_PARSER_PI: |
2323 | 0 | case XML_PARSER_SYSTEM_LITERAL: |
2324 | 0 | case XML_PARSER_PUBLIC_LITERAL: |
2325 | | /* we just ignore it there */ |
2326 | 0 | return; |
2327 | 0 | case XML_PARSER_EPILOG: |
2328 | 0 | xmlFatalErr(ctxt, XML_ERR_PEREF_IN_EPILOG, NULL); |
2329 | 0 | return; |
2330 | 0 | case XML_PARSER_ENTITY_VALUE: |
2331 | | /* |
2332 | | * NOTE: in the case of entity values, we don't do the |
2333 | | * substitution here since we need the literal |
2334 | | * entity value to be able to save the internal |
2335 | | * subset of the document. |
2336 | | * This will be handled by xmlStringDecodeEntities |
2337 | | */ |
2338 | 0 | return; |
2339 | 0 | case XML_PARSER_DTD: |
2340 | | /* |
2341 | | * [WFC: Well-Formedness Constraint: PEs in Internal Subset] |
2342 | | * In the internal DTD subset, parameter-entity references |
2343 | | * can occur only where markup declarations can occur, not |
2344 | | * within markup declarations. |
2345 | | * In that case this is handled in xmlParseMarkupDecl |
2346 | | */ |
2347 | 0 | if ((ctxt->external == 0) && (ctxt->inputNr == 1)) |
2348 | 0 | return; |
2349 | 0 | if (IS_BLANK_CH(NXT(1)) || NXT(1) == 0) |
2350 | 0 | return; |
2351 | 0 | break; |
2352 | 0 | case XML_PARSER_IGNORE: |
2353 | 0 | return; |
2354 | 0 | } |
2355 | | |
2356 | 0 | xmlParsePEReference(ctxt); |
2357 | 0 | } |
2358 | | |
2359 | | /* |
2360 | | * Macro used to grow the current buffer. |
2361 | | * buffer##_size is expected to be a size_t |
2362 | | * mem_error: is expected to handle memory allocation failures |
2363 | | */ |
2364 | 10.1k | #define growBuffer(buffer, n) { \ |
2365 | 10.1k | xmlChar *tmp; \ |
2366 | 10.1k | size_t new_size = buffer##_size * 2 + n; \ |
2367 | 10.1k | if (new_size < buffer##_size) goto mem_error; \ |
2368 | 10.1k | tmp = (xmlChar *) xmlRealloc(buffer, new_size); \ |
2369 | 10.1k | if (tmp == NULL) goto mem_error; \ |
2370 | 10.1k | buffer = tmp; \ |
2371 | 10.1k | buffer##_size = new_size; \ |
2372 | 10.1k | } |
2373 | | |
2374 | | /** |
2375 | | * xmlStringDecodeEntitiesInt: |
2376 | | * @ctxt: the parser context |
2377 | | * @str: the input string |
2378 | | * @len: the string length |
2379 | | * @what: combination of XML_SUBSTITUTE_REF and XML_SUBSTITUTE_PEREF |
2380 | | * @end: an end marker xmlChar, 0 if none |
2381 | | * @end2: an end marker xmlChar, 0 if none |
2382 | | * @end3: an end marker xmlChar, 0 if none |
2383 | | * @check: whether to perform entity checks |
2384 | | */ |
2385 | | static xmlChar * |
2386 | | xmlStringDecodeEntitiesInt(xmlParserCtxtPtr ctxt, const xmlChar *str, int len, |
2387 | | int what, xmlChar end, xmlChar end2, xmlChar end3, |
2388 | 19.2k | int check) { |
2389 | 19.2k | xmlChar *buffer = NULL; |
2390 | 19.2k | size_t buffer_size = 0; |
2391 | 19.2k | size_t nbchars = 0; |
2392 | | |
2393 | 19.2k | xmlChar *current = NULL; |
2394 | 19.2k | xmlChar *rep = NULL; |
2395 | 19.2k | const xmlChar *last; |
2396 | 19.2k | xmlEntityPtr ent; |
2397 | 19.2k | int c,l; |
2398 | | |
2399 | 19.2k | if (str == NULL) |
2400 | 0 | return(NULL); |
2401 | 19.2k | last = str + len; |
2402 | | |
2403 | 19.2k | if (((ctxt->depth > 40) && |
2404 | 19.2k | ((ctxt->options & XML_PARSE_HUGE) == 0)) || |
2405 | 19.2k | (ctxt->depth > 100)) { |
2406 | 0 | xmlFatalErrMsg(ctxt, XML_ERR_ENTITY_LOOP, |
2407 | 0 | "Maximum entity nesting depth exceeded"); |
2408 | 0 | return(NULL); |
2409 | 0 | } |
2410 | | |
2411 | | /* |
2412 | | * allocate a translation buffer. |
2413 | | */ |
2414 | 19.2k | buffer_size = XML_PARSER_BIG_BUFFER_SIZE; |
2415 | 19.2k | buffer = (xmlChar *) xmlMallocAtomic(buffer_size); |
2416 | 19.2k | if (buffer == NULL) goto mem_error; |
2417 | | |
2418 | | /* |
2419 | | * OK loop until we reach one of the ending char or a size limit. |
2420 | | * we are operating on already parsed values. |
2421 | | */ |
2422 | 19.2k | if (str < last) |
2423 | 19.2k | c = CUR_SCHAR(str, l); |
2424 | 0 | else |
2425 | 0 | c = 0; |
2426 | 15.1M | while ((c != 0) && (c != end) && /* non input consuming loop */ |
2427 | 15.1M | (c != end2) && (c != end3) && |
2428 | 15.1M | (ctxt->instate != XML_PARSER_EOF)) { |
2429 | | |
2430 | 15.1M | if (c == 0) break; |
2431 | 15.1M | if ((c == '&') && (str[1] == '#')) { |
2432 | 40.6k | int val = xmlParseStringCharRef(ctxt, &str); |
2433 | 40.6k | if (val == 0) |
2434 | 5.39k | goto int_error; |
2435 | 35.2k | COPY_BUF(0,buffer,nbchars,val); |
2436 | 35.2k | if (nbchars + XML_PARSER_BUFFER_SIZE > buffer_size) { |
2437 | 5.03k | growBuffer(buffer, XML_PARSER_BUFFER_SIZE); |
2438 | 5.03k | } |
2439 | 15.1M | } else if ((c == '&') && (what & XML_SUBSTITUTE_REF)) { |
2440 | 11.9k | if (xmlParserDebugEntities) |
2441 | 0 | xmlGenericError(xmlGenericErrorContext, |
2442 | 0 | "String decoding Entity Reference: %.30s\n", |
2443 | 0 | str); |
2444 | 11.9k | ent = xmlParseStringEntityRef(ctxt, &str); |
2445 | 11.9k | if ((ent != NULL) && |
2446 | 11.9k | (ent->etype == XML_INTERNAL_PREDEFINED_ENTITY)) { |
2447 | 0 | if (ent->content != NULL) { |
2448 | 0 | COPY_BUF(0,buffer,nbchars,ent->content[0]); |
2449 | 0 | if (nbchars + XML_PARSER_BUFFER_SIZE > buffer_size) { |
2450 | 0 | growBuffer(buffer, XML_PARSER_BUFFER_SIZE); |
2451 | 0 | } |
2452 | 0 | } else { |
2453 | 0 | xmlFatalErrMsg(ctxt, XML_ERR_INTERNAL_ERROR, |
2454 | 0 | "predefined entity has no content\n"); |
2455 | 0 | goto int_error; |
2456 | 0 | } |
2457 | 11.9k | } else if ((ent != NULL) && (ent->content != NULL)) { |
2458 | 0 | if ((check) && (xmlParserEntityCheck(ctxt, ent->length))) |
2459 | 0 | goto int_error; |
2460 | | |
2461 | 0 | if (ent->flags & XML_ENT_EXPANDING) { |
2462 | 0 | xmlFatalErr(ctxt, XML_ERR_ENTITY_LOOP, NULL); |
2463 | 0 | xmlHaltParser(ctxt); |
2464 | 0 | ent->content[0] = 0; |
2465 | 0 | goto int_error; |
2466 | 0 | } |
2467 | | |
2468 | 0 | ent->flags |= XML_ENT_EXPANDING; |
2469 | 0 | ctxt->depth++; |
2470 | 0 | rep = xmlStringDecodeEntitiesInt(ctxt, ent->content, |
2471 | 0 | ent->length, what, 0, 0, 0, check); |
2472 | 0 | ctxt->depth--; |
2473 | 0 | ent->flags &= ~XML_ENT_EXPANDING; |
2474 | |
|
2475 | 0 | if (rep == NULL) { |
2476 | 0 | ent->content[0] = 0; |
2477 | 0 | goto int_error; |
2478 | 0 | } |
2479 | | |
2480 | 0 | current = rep; |
2481 | 0 | while (*current != 0) { /* non input consuming loop */ |
2482 | 0 | buffer[nbchars++] = *current++; |
2483 | 0 | if (nbchars + XML_PARSER_BUFFER_SIZE > buffer_size) { |
2484 | 0 | growBuffer(buffer, XML_PARSER_BUFFER_SIZE); |
2485 | 0 | } |
2486 | 0 | } |
2487 | 0 | xmlFree(rep); |
2488 | 0 | rep = NULL; |
2489 | 11.9k | } else if (ent != NULL) { |
2490 | 0 | int i = xmlStrlen(ent->name); |
2491 | 0 | const xmlChar *cur = ent->name; |
2492 | |
|
2493 | 0 | buffer[nbchars++] = '&'; |
2494 | 0 | if (nbchars + i + XML_PARSER_BUFFER_SIZE > buffer_size) { |
2495 | 0 | growBuffer(buffer, i + XML_PARSER_BUFFER_SIZE); |
2496 | 0 | } |
2497 | 0 | for (;i > 0;i--) |
2498 | 0 | buffer[nbchars++] = *cur++; |
2499 | 0 | buffer[nbchars++] = ';'; |
2500 | 0 | } |
2501 | 15.1M | } else if (c == '%' && (what & XML_SUBSTITUTE_PEREF)) { |
2502 | 0 | if (xmlParserDebugEntities) |
2503 | 0 | xmlGenericError(xmlGenericErrorContext, |
2504 | 0 | "String decoding PE Reference: %.30s\n", str); |
2505 | 0 | ent = xmlParseStringPEReference(ctxt, &str); |
2506 | 0 | if (ent != NULL) { |
2507 | 0 | if (ent->content == NULL) { |
2508 | | /* |
2509 | | * Note: external parsed entities will not be loaded, |
2510 | | * it is not required for a non-validating parser to |
2511 | | * complete external PEReferences coming from the |
2512 | | * internal subset |
2513 | | */ |
2514 | 0 | if (((ctxt->options & XML_PARSE_NOENT) != 0) || |
2515 | 0 | ((ctxt->options & XML_PARSE_DTDVALID) != 0) || |
2516 | 0 | (ctxt->validate != 0)) { |
2517 | 0 | xmlLoadEntityContent(ctxt, ent); |
2518 | 0 | } else { |
2519 | 0 | xmlWarningMsg(ctxt, XML_ERR_ENTITY_PROCESSING, |
2520 | 0 | "not validating will not read content for PE entity %s\n", |
2521 | 0 | ent->name, NULL); |
2522 | 0 | } |
2523 | 0 | } |
2524 | |
|
2525 | 0 | if ((check) && (xmlParserEntityCheck(ctxt, ent->length))) |
2526 | 0 | goto int_error; |
2527 | | |
2528 | 0 | if (ent->flags & XML_ENT_EXPANDING) { |
2529 | 0 | xmlFatalErr(ctxt, XML_ERR_ENTITY_LOOP, NULL); |
2530 | 0 | xmlHaltParser(ctxt); |
2531 | 0 | if (ent->content != NULL) |
2532 | 0 | ent->content[0] = 0; |
2533 | 0 | goto int_error; |
2534 | 0 | } |
2535 | | |
2536 | 0 | ent->flags |= XML_ENT_EXPANDING; |
2537 | 0 | ctxt->depth++; |
2538 | 0 | rep = xmlStringDecodeEntitiesInt(ctxt, ent->content, |
2539 | 0 | ent->length, what, 0, 0, 0, check); |
2540 | 0 | ctxt->depth--; |
2541 | 0 | ent->flags &= ~XML_ENT_EXPANDING; |
2542 | |
|
2543 | 0 | if (rep == NULL) { |
2544 | 0 | if (ent->content != NULL) |
2545 | 0 | ent->content[0] = 0; |
2546 | 0 | goto int_error; |
2547 | 0 | } |
2548 | 0 | current = rep; |
2549 | 0 | while (*current != 0) { /* non input consuming loop */ |
2550 | 0 | buffer[nbchars++] = *current++; |
2551 | 0 | if (nbchars + XML_PARSER_BUFFER_SIZE > buffer_size) { |
2552 | 0 | growBuffer(buffer, XML_PARSER_BUFFER_SIZE); |
2553 | 0 | } |
2554 | 0 | } |
2555 | 0 | xmlFree(rep); |
2556 | 0 | rep = NULL; |
2557 | 0 | } |
2558 | 15.1M | } else { |
2559 | 15.1M | COPY_BUF(l,buffer,nbchars,c); |
2560 | 15.1M | str += l; |
2561 | 15.1M | if (nbchars + XML_PARSER_BUFFER_SIZE > buffer_size) { |
2562 | 4.62k | growBuffer(buffer, XML_PARSER_BUFFER_SIZE); |
2563 | 4.62k | } |
2564 | 15.1M | } |
2565 | 15.1M | if (str < last) |
2566 | 15.1M | c = CUR_SCHAR(str, l); |
2567 | 13.8k | else |
2568 | 13.8k | c = 0; |
2569 | 15.1M | } |
2570 | 13.8k | buffer[nbchars] = 0; |
2571 | 13.8k | return(buffer); |
2572 | | |
2573 | 0 | mem_error: |
2574 | 0 | xmlErrMemory(ctxt, NULL); |
2575 | 5.39k | int_error: |
2576 | 5.39k | if (rep != NULL) |
2577 | 0 | xmlFree(rep); |
2578 | 5.39k | if (buffer != NULL) |
2579 | 5.39k | xmlFree(buffer); |
2580 | 5.39k | return(NULL); |
2581 | 0 | } |
2582 | | |
2583 | | /** |
2584 | | * xmlStringLenDecodeEntities: |
2585 | | * @ctxt: the parser context |
2586 | | * @str: the input string |
2587 | | * @len: the string length |
2588 | | * @what: combination of XML_SUBSTITUTE_REF and XML_SUBSTITUTE_PEREF |
2589 | | * @end: an end marker xmlChar, 0 if none |
2590 | | * @end2: an end marker xmlChar, 0 if none |
2591 | | * @end3: an end marker xmlChar, 0 if none |
2592 | | * |
2593 | | * DEPRECATED: Internal function, don't use. |
2594 | | * |
2595 | | * Takes a entity string content and process to do the adequate substitutions. |
2596 | | * |
2597 | | * [67] Reference ::= EntityRef | CharRef |
2598 | | * |
2599 | | * [69] PEReference ::= '%' Name ';' |
2600 | | * |
2601 | | * Returns A newly allocated string with the substitution done. The caller |
2602 | | * must deallocate it ! |
2603 | | */ |
2604 | | xmlChar * |
2605 | | xmlStringLenDecodeEntities(xmlParserCtxtPtr ctxt, const xmlChar *str, int len, |
2606 | | int what, xmlChar end, xmlChar end2, |
2607 | 0 | xmlChar end3) { |
2608 | 0 | if ((ctxt == NULL) || (str == NULL) || (len < 0)) |
2609 | 0 | return(NULL); |
2610 | 0 | return(xmlStringDecodeEntitiesInt(ctxt, str, len, what, |
2611 | 0 | end, end2, end3, 0)); |
2612 | 0 | } |
2613 | | |
2614 | | /** |
2615 | | * xmlStringDecodeEntities: |
2616 | | * @ctxt: the parser context |
2617 | | * @str: the input string |
2618 | | * @what: combination of XML_SUBSTITUTE_REF and XML_SUBSTITUTE_PEREF |
2619 | | * @end: an end marker xmlChar, 0 if none |
2620 | | * @end2: an end marker xmlChar, 0 if none |
2621 | | * @end3: an end marker xmlChar, 0 if none |
2622 | | * |
2623 | | * DEPRECATED: Internal function, don't use. |
2624 | | * |
2625 | | * Takes a entity string content and process to do the adequate substitutions. |
2626 | | * |
2627 | | * [67] Reference ::= EntityRef | CharRef |
2628 | | * |
2629 | | * [69] PEReference ::= '%' Name ';' |
2630 | | * |
2631 | | * Returns A newly allocated string with the substitution done. The caller |
2632 | | * must deallocate it ! |
2633 | | */ |
2634 | | xmlChar * |
2635 | | xmlStringDecodeEntities(xmlParserCtxtPtr ctxt, const xmlChar *str, int what, |
2636 | 0 | xmlChar end, xmlChar end2, xmlChar end3) { |
2637 | 0 | if ((ctxt == NULL) || (str == NULL)) return(NULL); |
2638 | 0 | return(xmlStringDecodeEntitiesInt(ctxt, str, xmlStrlen(str), what, |
2639 | 0 | end, end2, end3, 0)); |
2640 | 0 | } |
2641 | | |
2642 | | /************************************************************************ |
2643 | | * * |
2644 | | * Commodity functions, cleanup needed ? * |
2645 | | * * |
2646 | | ************************************************************************/ |
2647 | | |
2648 | | /** |
2649 | | * areBlanks: |
2650 | | * @ctxt: an XML parser context |
2651 | | * @str: a xmlChar * |
2652 | | * @len: the size of @str |
2653 | | * @blank_chars: we know the chars are blanks |
2654 | | * |
2655 | | * Is this a sequence of blank chars that one can ignore ? |
2656 | | * |
2657 | | * Returns 1 if ignorable 0 otherwise. |
2658 | | */ |
2659 | | |
2660 | | static int areBlanks(xmlParserCtxtPtr ctxt, const xmlChar *str, int len, |
2661 | 204k | int blank_chars) { |
2662 | 204k | int i, ret; |
2663 | 204k | xmlNodePtr lastChild; |
2664 | | |
2665 | | /* |
2666 | | * Don't spend time trying to differentiate them, the same callback is |
2667 | | * used ! |
2668 | | */ |
2669 | 204k | if (ctxt->sax->ignorableWhitespace == ctxt->sax->characters) |
2670 | 204k | return(0); |
2671 | | |
2672 | | /* |
2673 | | * Check for xml:space value. |
2674 | | */ |
2675 | 0 | if ((ctxt->space == NULL) || (*(ctxt->space) == 1) || |
2676 | 0 | (*(ctxt->space) == -2)) |
2677 | 0 | return(0); |
2678 | | |
2679 | | /* |
2680 | | * Check that the string is made of blanks |
2681 | | */ |
2682 | 0 | if (blank_chars == 0) { |
2683 | 0 | for (i = 0;i < len;i++) |
2684 | 0 | if (!(IS_BLANK_CH(str[i]))) return(0); |
2685 | 0 | } |
2686 | | |
2687 | | /* |
2688 | | * Look if the element is mixed content in the DTD if available |
2689 | | */ |
2690 | 0 | if (ctxt->node == NULL) return(0); |
2691 | 0 | if (ctxt->myDoc != NULL) { |
2692 | 0 | ret = xmlIsMixedElement(ctxt->myDoc, ctxt->node->name); |
2693 | 0 | if (ret == 0) return(1); |
2694 | 0 | if (ret == 1) return(0); |
2695 | 0 | } |
2696 | | |
2697 | | /* |
2698 | | * Otherwise, heuristic :-\ |
2699 | | */ |
2700 | 0 | if ((RAW != '<') && (RAW != 0xD)) return(0); |
2701 | 0 | if ((ctxt->node->children == NULL) && |
2702 | 0 | (RAW == '<') && (NXT(1) == '/')) return(0); |
2703 | | |
2704 | 0 | lastChild = xmlGetLastChild(ctxt->node); |
2705 | 0 | if (lastChild == NULL) { |
2706 | 0 | if ((ctxt->node->type != XML_ELEMENT_NODE) && |
2707 | 0 | (ctxt->node->content != NULL)) return(0); |
2708 | 0 | } else if (xmlNodeIsText(lastChild)) |
2709 | 0 | return(0); |
2710 | 0 | else if ((ctxt->node->children != NULL) && |
2711 | 0 | (xmlNodeIsText(ctxt->node->children))) |
2712 | 0 | return(0); |
2713 | 0 | return(1); |
2714 | 0 | } |
2715 | | |
2716 | | /************************************************************************ |
2717 | | * * |
2718 | | * Extra stuff for namespace support * |
2719 | | * Relates to http://www.w3.org/TR/WD-xml-names * |
2720 | | * * |
2721 | | ************************************************************************/ |
2722 | | |
2723 | | /** |
2724 | | * xmlSplitQName: |
2725 | | * @ctxt: an XML parser context |
2726 | | * @name: an XML parser context |
2727 | | * @prefix: a xmlChar ** |
2728 | | * |
2729 | | * parse an UTF8 encoded XML qualified name string |
2730 | | * |
2731 | | * [NS 5] QName ::= (Prefix ':')? LocalPart |
2732 | | * |
2733 | | * [NS 6] Prefix ::= NCName |
2734 | | * |
2735 | | * [NS 7] LocalPart ::= NCName |
2736 | | * |
2737 | | * Returns the local part, and prefix is updated |
2738 | | * to get the Prefix if any. |
2739 | | */ |
2740 | | |
2741 | | xmlChar * |
2742 | 1.79k | xmlSplitQName(xmlParserCtxtPtr ctxt, const xmlChar *name, xmlChar **prefix) { |
2743 | 1.79k | xmlChar buf[XML_MAX_NAMELEN + 5]; |
2744 | 1.79k | xmlChar *buffer = NULL; |
2745 | 1.79k | int len = 0; |
2746 | 1.79k | int max = XML_MAX_NAMELEN; |
2747 | 1.79k | xmlChar *ret = NULL; |
2748 | 1.79k | const xmlChar *cur = name; |
2749 | 1.79k | int c; |
2750 | | |
2751 | 1.79k | if (prefix == NULL) return(NULL); |
2752 | 1.79k | *prefix = NULL; |
2753 | | |
2754 | 1.79k | if (cur == NULL) return(NULL); |
2755 | | |
2756 | | #ifndef XML_XML_NAMESPACE |
2757 | | /* xml: prefix is not really a namespace */ |
2758 | | if ((cur[0] == 'x') && (cur[1] == 'm') && |
2759 | | (cur[2] == 'l') && (cur[3] == ':')) |
2760 | | return(xmlStrdup(name)); |
2761 | | #endif |
2762 | | |
2763 | | /* nasty but well=formed */ |
2764 | 1.79k | if (cur[0] == ':') |
2765 | 0 | return(xmlStrdup(name)); |
2766 | | |
2767 | 1.79k | c = *cur++; |
2768 | 130k | while ((c != 0) && (c != ':') && (len < max)) { /* tested bigname.xml */ |
2769 | 128k | buf[len++] = c; |
2770 | 128k | c = *cur++; |
2771 | 128k | } |
2772 | 1.79k | if (len >= max) { |
2773 | | /* |
2774 | | * Okay someone managed to make a huge name, so he's ready to pay |
2775 | | * for the processing speed. |
2776 | | */ |
2777 | 937 | max = len * 2; |
2778 | | |
2779 | 937 | buffer = (xmlChar *) xmlMallocAtomic(max); |
2780 | 937 | if (buffer == NULL) { |
2781 | 0 | xmlErrMemory(ctxt, NULL); |
2782 | 0 | return(NULL); |
2783 | 0 | } |
2784 | 937 | memcpy(buffer, buf, len); |
2785 | 506k | while ((c != 0) && (c != ':')) { /* tested bigname.xml */ |
2786 | 505k | if (len + 10 > max) { |
2787 | 2.04k | xmlChar *tmp; |
2788 | | |
2789 | 2.04k | max *= 2; |
2790 | 2.04k | tmp = (xmlChar *) xmlRealloc(buffer, max); |
2791 | 2.04k | if (tmp == NULL) { |
2792 | 0 | xmlFree(buffer); |
2793 | 0 | xmlErrMemory(ctxt, NULL); |
2794 | 0 | return(NULL); |
2795 | 0 | } |
2796 | 2.04k | buffer = tmp; |
2797 | 2.04k | } |
2798 | 505k | buffer[len++] = c; |
2799 | 505k | c = *cur++; |
2800 | 505k | } |
2801 | 937 | buffer[len] = 0; |
2802 | 937 | } |
2803 | | |
2804 | 1.79k | if ((c == ':') && (*cur == 0)) { |
2805 | 0 | if (buffer != NULL) |
2806 | 0 | xmlFree(buffer); |
2807 | 0 | *prefix = NULL; |
2808 | 0 | return(xmlStrdup(name)); |
2809 | 0 | } |
2810 | | |
2811 | 1.79k | if (buffer == NULL) |
2812 | 861 | ret = xmlStrndup(buf, len); |
2813 | 937 | else { |
2814 | 937 | ret = buffer; |
2815 | 937 | buffer = NULL; |
2816 | 937 | max = XML_MAX_NAMELEN; |
2817 | 937 | } |
2818 | | |
2819 | | |
2820 | 1.79k | if (c == ':') { |
2821 | 972 | c = *cur; |
2822 | 972 | *prefix = ret; |
2823 | 972 | if (c == 0) { |
2824 | 0 | return(xmlStrndup(BAD_CAST "", 0)); |
2825 | 0 | } |
2826 | 972 | len = 0; |
2827 | | |
2828 | | /* |
2829 | | * Check that the first character is proper to start |
2830 | | * a new name |
2831 | | */ |
2832 | 972 | if (!(((c >= 0x61) && (c <= 0x7A)) || |
2833 | 972 | ((c >= 0x41) && (c <= 0x5A)) || |
2834 | 972 | (c == '_') || (c == ':'))) { |
2835 | 6 | int l; |
2836 | 6 | int first = CUR_SCHAR(cur, l); |
2837 | | |
2838 | 6 | if (!IS_LETTER(first) && (first != '_')) { |
2839 | 0 | xmlFatalErrMsgStr(ctxt, XML_NS_ERR_QNAME, |
2840 | 0 | "Name %s is not XML Namespace compliant\n", |
2841 | 0 | name); |
2842 | 0 | } |
2843 | 6 | } |
2844 | 972 | cur++; |
2845 | | |
2846 | 75.6k | while ((c != 0) && (len < max)) { /* tested bigname2.xml */ |
2847 | 74.7k | buf[len++] = c; |
2848 | 74.7k | c = *cur++; |
2849 | 74.7k | } |
2850 | 972 | if (len >= max) { |
2851 | | /* |
2852 | | * Okay someone managed to make a huge name, so he's ready to pay |
2853 | | * for the processing speed. |
2854 | | */ |
2855 | 655 | max = len * 2; |
2856 | | |
2857 | 655 | buffer = (xmlChar *) xmlMallocAtomic(max); |
2858 | 655 | if (buffer == NULL) { |
2859 | 0 | xmlErrMemory(ctxt, NULL); |
2860 | 0 | return(NULL); |
2861 | 0 | } |
2862 | 655 | memcpy(buffer, buf, len); |
2863 | 446k | while (c != 0) { /* tested bigname2.xml */ |
2864 | 445k | if (len + 10 > max) { |
2865 | 1.39k | xmlChar *tmp; |
2866 | | |
2867 | 1.39k | max *= 2; |
2868 | 1.39k | tmp = (xmlChar *) xmlRealloc(buffer, max); |
2869 | 1.39k | if (tmp == NULL) { |
2870 | 0 | xmlErrMemory(ctxt, NULL); |
2871 | 0 | xmlFree(buffer); |
2872 | 0 | return(NULL); |
2873 | 0 | } |
2874 | 1.39k | buffer = tmp; |
2875 | 1.39k | } |
2876 | 445k | buffer[len++] = c; |
2877 | 445k | c = *cur++; |
2878 | 445k | } |
2879 | 655 | buffer[len] = 0; |
2880 | 655 | } |
2881 | | |
2882 | 972 | if (buffer == NULL) |
2883 | 317 | ret = xmlStrndup(buf, len); |
2884 | 655 | else { |
2885 | 655 | ret = buffer; |
2886 | 655 | } |
2887 | 972 | } |
2888 | | |
2889 | 1.79k | return(ret); |
2890 | 1.79k | } |
2891 | | |
2892 | | /************************************************************************ |
2893 | | * * |
2894 | | * The parser itself * |
2895 | | * Relates to http://www.w3.org/TR/REC-xml * |
2896 | | * * |
2897 | | ************************************************************************/ |
2898 | | |
2899 | | /************************************************************************ |
2900 | | * * |
2901 | | * Routines to parse Name, NCName and NmToken * |
2902 | | * * |
2903 | | ************************************************************************/ |
2904 | | #ifdef DEBUG |
2905 | | static unsigned long nbParseName = 0; |
2906 | | static unsigned long nbParseNmToken = 0; |
2907 | | static unsigned long nbParseNCName = 0; |
2908 | | static unsigned long nbParseNCNameComplex = 0; |
2909 | | static unsigned long nbParseNameComplex = 0; |
2910 | | static unsigned long nbParseStringName = 0; |
2911 | | #endif |
2912 | | |
2913 | | /* |
2914 | | * The two following functions are related to the change of accepted |
2915 | | * characters for Name and NmToken in the Revision 5 of XML-1.0 |
2916 | | * They correspond to the modified production [4] and the new production [4a] |
2917 | | * changes in that revision. Also note that the macros used for the |
2918 | | * productions Letter, Digit, CombiningChar and Extender are not needed |
2919 | | * anymore. |
2920 | | * We still keep compatibility to pre-revision5 parsing semantic if the |
2921 | | * new XML_PARSE_OLD10 option is given to the parser. |
2922 | | */ |
2923 | | static int |
2924 | 1.38M | xmlIsNameStartChar(xmlParserCtxtPtr ctxt, int c) { |
2925 | 1.38M | if ((ctxt->options & XML_PARSE_OLD10) == 0) { |
2926 | | /* |
2927 | | * Use the new checks of production [4] [4a] amd [5] of the |
2928 | | * Update 5 of XML-1.0 |
2929 | | */ |
2930 | 1.38M | if ((c != ' ') && (c != '>') && (c != '/') && /* accelerators */ |
2931 | 1.38M | (((c >= 'a') && (c <= 'z')) || |
2932 | 1.38M | ((c >= 'A') && (c <= 'Z')) || |
2933 | 1.38M | (c == '_') || (c == ':') || |
2934 | 1.38M | ((c >= 0xC0) && (c <= 0xD6)) || |
2935 | 1.38M | ((c >= 0xD8) && (c <= 0xF6)) || |
2936 | 1.38M | ((c >= 0xF8) && (c <= 0x2FF)) || |
2937 | 1.38M | ((c >= 0x370) && (c <= 0x37D)) || |
2938 | 1.38M | ((c >= 0x37F) && (c <= 0x1FFF)) || |
2939 | 1.38M | ((c >= 0x200C) && (c <= 0x200D)) || |
2940 | 1.38M | ((c >= 0x2070) && (c <= 0x218F)) || |
2941 | 1.38M | ((c >= 0x2C00) && (c <= 0x2FEF)) || |
2942 | 1.38M | ((c >= 0x3001) && (c <= 0xD7FF)) || |
2943 | 1.38M | ((c >= 0xF900) && (c <= 0xFDCF)) || |
2944 | 1.38M | ((c >= 0xFDF0) && (c <= 0xFFFD)) || |
2945 | 1.38M | ((c >= 0x10000) && (c <= 0xEFFFF)))) |
2946 | 42.0k | return(1); |
2947 | 1.38M | } else { |
2948 | 0 | if (IS_LETTER(c) || (c == '_') || (c == ':')) |
2949 | 0 | return(1); |
2950 | 0 | } |
2951 | 1.34M | return(0); |
2952 | 1.38M | } |
2953 | | |
2954 | | static int |
2955 | 2.42M | xmlIsNameChar(xmlParserCtxtPtr ctxt, int c) { |
2956 | 2.42M | if ((ctxt->options & XML_PARSE_OLD10) == 0) { |
2957 | | /* |
2958 | | * Use the new checks of production [4] [4a] amd [5] of the |
2959 | | * Update 5 of XML-1.0 |
2960 | | */ |
2961 | 2.42M | if ((c != ' ') && (c != '>') && (c != '/') && /* accelerators */ |
2962 | 2.42M | (((c >= 'a') && (c <= 'z')) || |
2963 | 2.41M | ((c >= 'A') && (c <= 'Z')) || |
2964 | 2.41M | ((c >= '0') && (c <= '9')) || /* !start */ |
2965 | 2.41M | (c == '_') || (c == ':') || |
2966 | 2.41M | (c == '-') || (c == '.') || (c == 0xB7) || /* !start */ |
2967 | 2.41M | ((c >= 0xC0) && (c <= 0xD6)) || |
2968 | 2.41M | ((c >= 0xD8) && (c <= 0xF6)) || |
2969 | 2.41M | ((c >= 0xF8) && (c <= 0x2FF)) || |
2970 | 2.41M | ((c >= 0x300) && (c <= 0x36F)) || /* !start */ |
2971 | 2.41M | ((c >= 0x370) && (c <= 0x37D)) || |
2972 | 2.41M | ((c >= 0x37F) && (c <= 0x1FFF)) || |
2973 | 2.41M | ((c >= 0x200C) && (c <= 0x200D)) || |
2974 | 2.41M | ((c >= 0x203F) && (c <= 0x2040)) || /* !start */ |
2975 | 2.41M | ((c >= 0x2070) && (c <= 0x218F)) || |
2976 | 2.41M | ((c >= 0x2C00) && (c <= 0x2FEF)) || |
2977 | 2.41M | ((c >= 0x3001) && (c <= 0xD7FF)) || |
2978 | 2.41M | ((c >= 0xF900) && (c <= 0xFDCF)) || |
2979 | 2.41M | ((c >= 0xFDF0) && (c <= 0xFFFD)) || |
2980 | 2.41M | ((c >= 0x10000) && (c <= 0xEFFFF)))) |
2981 | 2.39M | return(1); |
2982 | 2.42M | } else { |
2983 | 0 | if ((IS_LETTER(c)) || (IS_DIGIT(c)) || |
2984 | 0 | (c == '.') || (c == '-') || |
2985 | 0 | (c == '_') || (c == ':') || |
2986 | 0 | (IS_COMBINING(c)) || |
2987 | 0 | (IS_EXTENDER(c))) |
2988 | 0 | return(1); |
2989 | 0 | } |
2990 | 27.4k | return(0); |
2991 | 2.42M | } |
2992 | | |
2993 | | static xmlChar * xmlParseAttValueInternal(xmlParserCtxtPtr ctxt, |
2994 | | int *len, int *alloc, int normalize); |
2995 | | |
2996 | | static const xmlChar * |
2997 | 56.3k | xmlParseNameComplex(xmlParserCtxtPtr ctxt) { |
2998 | 56.3k | int len = 0, l; |
2999 | 56.3k | int c; |
3000 | 56.3k | int maxLength = (ctxt->options & XML_PARSE_HUGE) ? |
3001 | 0 | XML_MAX_TEXT_LENGTH : |
3002 | 56.3k | XML_MAX_NAME_LENGTH; |
3003 | | |
3004 | | #ifdef DEBUG |
3005 | | nbParseNameComplex++; |
3006 | | #endif |
3007 | | |
3008 | | /* |
3009 | | * Handler for more complex cases |
3010 | | */ |
3011 | 56.3k | c = CUR_CHAR(l); |
3012 | 56.3k | if ((ctxt->options & XML_PARSE_OLD10) == 0) { |
3013 | | /* |
3014 | | * Use the new checks of production [4] [4a] amd [5] of the |
3015 | | * Update 5 of XML-1.0 |
3016 | | */ |
3017 | 56.3k | if ((c == ' ') || (c == '>') || (c == '/') || /* accelerators */ |
3018 | 56.3k | (!(((c >= 'a') && (c <= 'z')) || |
3019 | 55.8k | ((c >= 'A') && (c <= 'Z')) || |
3020 | 55.8k | (c == '_') || (c == ':') || |
3021 | 55.8k | ((c >= 0xC0) && (c <= 0xD6)) || |
3022 | 55.8k | ((c >= 0xD8) && (c <= 0xF6)) || |
3023 | 55.8k | ((c >= 0xF8) && (c <= 0x2FF)) || |
3024 | 55.8k | ((c >= 0x370) && (c <= 0x37D)) || |
3025 | 55.8k | ((c >= 0x37F) && (c <= 0x1FFF)) || |
3026 | 55.8k | ((c >= 0x200C) && (c <= 0x200D)) || |
3027 | 55.8k | ((c >= 0x2070) && (c <= 0x218F)) || |
3028 | 55.8k | ((c >= 0x2C00) && (c <= 0x2FEF)) || |
3029 | 55.8k | ((c >= 0x3001) && (c <= 0xD7FF)) || |
3030 | 55.8k | ((c >= 0xF900) && (c <= 0xFDCF)) || |
3031 | 55.8k | ((c >= 0xFDF0) && (c <= 0xFFFD)) || |
3032 | 55.8k | ((c >= 0x10000) && (c <= 0xEFFFF))))) { |
3033 | 43.0k | return(NULL); |
3034 | 43.0k | } |
3035 | 13.3k | len += l; |
3036 | 13.3k | NEXTL(l); |
3037 | 13.3k | c = CUR_CHAR(l); |
3038 | 6.00M | while ((c != ' ') && (c != '>') && (c != '/') && /* accelerators */ |
3039 | 6.00M | (((c >= 'a') && (c <= 'z')) || |
3040 | 6.00M | ((c >= 'A') && (c <= 'Z')) || |
3041 | 6.00M | ((c >= '0') && (c <= '9')) || /* !start */ |
3042 | 6.00M | (c == '_') || (c == ':') || |
3043 | 6.00M | (c == '-') || (c == '.') || (c == 0xB7) || /* !start */ |
3044 | 6.00M | ((c >= 0xC0) && (c <= 0xD6)) || |
3045 | 6.00M | ((c >= 0xD8) && (c <= 0xF6)) || |
3046 | 6.00M | ((c >= 0xF8) && (c <= 0x2FF)) || |
3047 | 6.00M | ((c >= 0x300) && (c <= 0x36F)) || /* !start */ |
3048 | 6.00M | ((c >= 0x370) && (c <= 0x37D)) || |
3049 | 6.00M | ((c >= 0x37F) && (c <= 0x1FFF)) || |
3050 | 6.00M | ((c >= 0x200C) && (c <= 0x200D)) || |
3051 | 6.00M | ((c >= 0x203F) && (c <= 0x2040)) || /* !start */ |
3052 | 6.00M | ((c >= 0x2070) && (c <= 0x218F)) || |
3053 | 6.00M | ((c >= 0x2C00) && (c <= 0x2FEF)) || |
3054 | 6.00M | ((c >= 0x3001) && (c <= 0xD7FF)) || |
3055 | 6.00M | ((c >= 0xF900) && (c <= 0xFDCF)) || |
3056 | 6.00M | ((c >= 0xFDF0) && (c <= 0xFFFD)) || |
3057 | 6.00M | ((c >= 0x10000) && (c <= 0xEFFFF)) |
3058 | 6.00M | )) { |
3059 | 5.99M | if (len <= INT_MAX - l) |
3060 | 5.99M | len += l; |
3061 | 5.99M | NEXTL(l); |
3062 | 5.99M | c = CUR_CHAR(l); |
3063 | 5.99M | } |
3064 | 13.3k | } else { |
3065 | 0 | if ((c == ' ') || (c == '>') || (c == '/') || /* accelerators */ |
3066 | 0 | (!IS_LETTER(c) && (c != '_') && |
3067 | 0 | (c != ':'))) { |
3068 | 0 | return(NULL); |
3069 | 0 | } |
3070 | 0 | len += l; |
3071 | 0 | NEXTL(l); |
3072 | 0 | c = CUR_CHAR(l); |
3073 | |
|
3074 | 0 | while ((c != ' ') && (c != '>') && (c != '/') && /* test bigname.xml */ |
3075 | 0 | ((IS_LETTER(c)) || (IS_DIGIT(c)) || |
3076 | 0 | (c == '.') || (c == '-') || |
3077 | 0 | (c == '_') || (c == ':') || |
3078 | 0 | (IS_COMBINING(c)) || |
3079 | 0 | (IS_EXTENDER(c)))) { |
3080 | 0 | if (len <= INT_MAX - l) |
3081 | 0 | len += l; |
3082 | 0 | NEXTL(l); |
3083 | 0 | c = CUR_CHAR(l); |
3084 | 0 | } |
3085 | 0 | } |
3086 | 13.3k | if (ctxt->instate == XML_PARSER_EOF) |
3087 | 1 | return(NULL); |
3088 | 13.3k | if (len > maxLength) { |
3089 | 44 | xmlFatalErr(ctxt, XML_ERR_NAME_TOO_LONG, "Name"); |
3090 | 44 | return(NULL); |
3091 | 44 | } |
3092 | 13.2k | if (ctxt->input->cur - ctxt->input->base < len) { |
3093 | | /* |
3094 | | * There were a couple of bugs where PERefs lead to to a change |
3095 | | * of the buffer. Check the buffer size to avoid passing an invalid |
3096 | | * pointer to xmlDictLookup. |
3097 | | */ |
3098 | 0 | xmlFatalErr(ctxt, XML_ERR_INTERNAL_ERROR, |
3099 | 0 | "unexpected change of input buffer"); |
3100 | 0 | return (NULL); |
3101 | 0 | } |
3102 | 13.2k | if ((*ctxt->input->cur == '\n') && (ctxt->input->cur[-1] == '\r')) |
3103 | 1 | return(xmlDictLookup(ctxt->dict, ctxt->input->cur - (len + 1), len)); |
3104 | 13.2k | return(xmlDictLookup(ctxt->dict, ctxt->input->cur - len, len)); |
3105 | 13.2k | } |
3106 | | |
3107 | | /** |
3108 | | * xmlParseName: |
3109 | | * @ctxt: an XML parser context |
3110 | | * |
3111 | | * DEPRECATED: Internal function, don't use. |
3112 | | * |
3113 | | * parse an XML name. |
3114 | | * |
3115 | | * [4] NameChar ::= Letter | Digit | '.' | '-' | '_' | ':' | |
3116 | | * CombiningChar | Extender |
3117 | | * |
3118 | | * [5] Name ::= (Letter | '_' | ':') (NameChar)* |
3119 | | * |
3120 | | * [6] Names ::= Name (#x20 Name)* |
3121 | | * |
3122 | | * Returns the Name parsed or NULL |
3123 | | */ |
3124 | | |
3125 | | const xmlChar * |
3126 | 113k | xmlParseName(xmlParserCtxtPtr ctxt) { |
3127 | 113k | const xmlChar *in; |
3128 | 113k | const xmlChar *ret; |
3129 | 113k | size_t count = 0; |
3130 | 113k | size_t maxLength = (ctxt->options & XML_PARSE_HUGE) ? |
3131 | 0 | XML_MAX_TEXT_LENGTH : |
3132 | 113k | XML_MAX_NAME_LENGTH; |
3133 | | |
3134 | 113k | GROW; |
3135 | 113k | if (ctxt->instate == XML_PARSER_EOF) |
3136 | 0 | return(NULL); |
3137 | | |
3138 | | #ifdef DEBUG |
3139 | | nbParseName++; |
3140 | | #endif |
3141 | | |
3142 | | /* |
3143 | | * Accelerator for simple ASCII names |
3144 | | */ |
3145 | 113k | in = ctxt->input->cur; |
3146 | 113k | if (((*in >= 0x61) && (*in <= 0x7A)) || |
3147 | 113k | ((*in >= 0x41) && (*in <= 0x5A)) || |
3148 | 113k | (*in == '_') || (*in == ':')) { |
3149 | 67.8k | in++; |
3150 | 3.76M | while (((*in >= 0x61) && (*in <= 0x7A)) || |
3151 | 3.76M | ((*in >= 0x41) && (*in <= 0x5A)) || |
3152 | 3.76M | ((*in >= 0x30) && (*in <= 0x39)) || |
3153 | 3.76M | (*in == '_') || (*in == '-') || |
3154 | 3.76M | (*in == ':') || (*in == '.')) |
3155 | 3.69M | in++; |
3156 | 67.8k | if ((*in > 0) && (*in < 0x80)) { |
3157 | 57.5k | count = in - ctxt->input->cur; |
3158 | 57.5k | if (count > maxLength) { |
3159 | 31 | xmlFatalErr(ctxt, XML_ERR_NAME_TOO_LONG, "Name"); |
3160 | 31 | return(NULL); |
3161 | 31 | } |
3162 | 57.5k | ret = xmlDictLookup(ctxt->dict, ctxt->input->cur, count); |
3163 | 57.5k | ctxt->input->cur = in; |
3164 | 57.5k | ctxt->input->col += count; |
3165 | 57.5k | if (ret == NULL) |
3166 | 0 | xmlErrMemory(ctxt, NULL); |
3167 | 57.5k | return(ret); |
3168 | 57.5k | } |
3169 | 67.8k | } |
3170 | | /* accelerator for special cases */ |
3171 | 56.3k | return(xmlParseNameComplex(ctxt)); |
3172 | 113k | } |
3173 | | |
3174 | | static const xmlChar * |
3175 | 1.36M | xmlParseNCNameComplex(xmlParserCtxtPtr ctxt) { |
3176 | 1.36M | int len = 0, l; |
3177 | 1.36M | int c; |
3178 | 1.36M | int maxLength = (ctxt->options & XML_PARSE_HUGE) ? |
3179 | 0 | XML_MAX_TEXT_LENGTH : |
3180 | 1.36M | XML_MAX_NAME_LENGTH; |
3181 | 1.36M | size_t startPosition = 0; |
3182 | | |
3183 | | #ifdef DEBUG |
3184 | | nbParseNCNameComplex++; |
3185 | | #endif |
3186 | | |
3187 | | /* |
3188 | | * Handler for more complex cases |
3189 | | */ |
3190 | 1.36M | startPosition = CUR_PTR - BASE_PTR; |
3191 | 1.36M | c = CUR_CHAR(l); |
3192 | 1.36M | if ((c == ' ') || (c == '>') || (c == '/') || /* accelerators */ |
3193 | 1.36M | (!xmlIsNameStartChar(ctxt, c) || (c == ':'))) { |
3194 | 1.34M | return(NULL); |
3195 | 1.34M | } |
3196 | | |
3197 | 1.66M | while ((c != ' ') && (c != '>') && (c != '/') && /* test bigname.xml */ |
3198 | 1.66M | (xmlIsNameChar(ctxt, c) && (c != ':'))) { |
3199 | 1.64M | if (len <= INT_MAX - l) |
3200 | 1.64M | len += l; |
3201 | 1.64M | NEXTL(l); |
3202 | 1.64M | c = CUR_CHAR(l); |
3203 | 1.64M | } |
3204 | 23.3k | if (ctxt->instate == XML_PARSER_EOF) |
3205 | 0 | return(NULL); |
3206 | 23.3k | if (len > maxLength) { |
3207 | 25 | xmlFatalErr(ctxt, XML_ERR_NAME_TOO_LONG, "NCName"); |
3208 | 25 | return(NULL); |
3209 | 25 | } |
3210 | 23.3k | return(xmlDictLookup(ctxt->dict, (BASE_PTR + startPosition), len)); |
3211 | 23.3k | } |
3212 | | |
3213 | | /** |
3214 | | * xmlParseNCName: |
3215 | | * @ctxt: an XML parser context |
3216 | | * @len: length of the string parsed |
3217 | | * |
3218 | | * parse an XML name. |
3219 | | * |
3220 | | * [4NS] NCNameChar ::= Letter | Digit | '.' | '-' | '_' | |
3221 | | * CombiningChar | Extender |
3222 | | * |
3223 | | * [5NS] NCName ::= (Letter | '_') (NCNameChar)* |
3224 | | * |
3225 | | * Returns the Name parsed or NULL |
3226 | | */ |
3227 | | |
3228 | | static const xmlChar * |
3229 | 2.72M | xmlParseNCName(xmlParserCtxtPtr ctxt) { |
3230 | 2.72M | const xmlChar *in, *e; |
3231 | 2.72M | const xmlChar *ret; |
3232 | 2.72M | size_t count = 0; |
3233 | 2.72M | size_t maxLength = (ctxt->options & XML_PARSE_HUGE) ? |
3234 | 0 | XML_MAX_TEXT_LENGTH : |
3235 | 2.72M | XML_MAX_NAME_LENGTH; |
3236 | | |
3237 | | #ifdef DEBUG |
3238 | | nbParseNCName++; |
3239 | | #endif |
3240 | | |
3241 | | /* |
3242 | | * Accelerator for simple ASCII names |
3243 | | */ |
3244 | 2.72M | in = ctxt->input->cur; |
3245 | 2.72M | e = ctxt->input->end; |
3246 | 2.72M | if ((((*in >= 0x61) && (*in <= 0x7A)) || |
3247 | 2.72M | ((*in >= 0x41) && (*in <= 0x5A)) || |
3248 | 2.72M | (*in == '_')) && (in < e)) { |
3249 | 1.36M | in++; |
3250 | 4.90M | while ((((*in >= 0x61) && (*in <= 0x7A)) || |
3251 | 4.90M | ((*in >= 0x41) && (*in <= 0x5A)) || |
3252 | 4.90M | ((*in >= 0x30) && (*in <= 0x39)) || |
3253 | 4.90M | (*in == '_') || (*in == '-') || |
3254 | 4.90M | (*in == '.')) && (in < e)) |
3255 | 3.53M | in++; |
3256 | 1.36M | if (in >= e) |
3257 | 14 | goto complex; |
3258 | 1.36M | if ((*in > 0) && (*in < 0x80)) { |
3259 | 1.36M | count = in - ctxt->input->cur; |
3260 | 1.36M | if (count > maxLength) { |
3261 | 30 | xmlFatalErr(ctxt, XML_ERR_NAME_TOO_LONG, "NCName"); |
3262 | 30 | return(NULL); |
3263 | 30 | } |
3264 | 1.36M | ret = xmlDictLookup(ctxt->dict, ctxt->input->cur, count); |
3265 | 1.36M | ctxt->input->cur = in; |
3266 | 1.36M | ctxt->input->col += count; |
3267 | 1.36M | if (ret == NULL) { |
3268 | 0 | xmlErrMemory(ctxt, NULL); |
3269 | 0 | } |
3270 | 1.36M | return(ret); |
3271 | 1.36M | } |
3272 | 1.36M | } |
3273 | 1.36M | complex: |
3274 | 1.36M | return(xmlParseNCNameComplex(ctxt)); |
3275 | 2.72M | } |
3276 | | |
3277 | | /** |
3278 | | * xmlParseNameAndCompare: |
3279 | | * @ctxt: an XML parser context |
3280 | | * |
3281 | | * parse an XML name and compares for match |
3282 | | * (specialized for endtag parsing) |
3283 | | * |
3284 | | * Returns NULL for an illegal name, (xmlChar*) 1 for success |
3285 | | * and the name for mismatch |
3286 | | */ |
3287 | | |
3288 | | static const xmlChar * |
3289 | 1.71k | xmlParseNameAndCompare(xmlParserCtxtPtr ctxt, xmlChar const *other) { |
3290 | 1.71k | register const xmlChar *cmp = other; |
3291 | 1.71k | register const xmlChar *in; |
3292 | 1.71k | const xmlChar *ret; |
3293 | | |
3294 | 1.71k | GROW; |
3295 | 1.71k | if (ctxt->instate == XML_PARSER_EOF) |
3296 | 0 | return(NULL); |
3297 | | |
3298 | 1.71k | in = ctxt->input->cur; |
3299 | 2.53k | while (*in != 0 && *in == *cmp) { |
3300 | 819 | ++in; |
3301 | 819 | ++cmp; |
3302 | 819 | } |
3303 | 1.71k | if (*cmp == 0 && (*in == '>' || IS_BLANK_CH (*in))) { |
3304 | | /* success */ |
3305 | 574 | ctxt->input->col += in - ctxt->input->cur; |
3306 | 574 | ctxt->input->cur = in; |
3307 | 574 | return (const xmlChar*) 1; |
3308 | 574 | } |
3309 | | /* failure (or end of input buffer), check with full function */ |
3310 | 1.14k | ret = xmlParseName (ctxt); |
3311 | | /* strings coming from the dictionary direct compare possible */ |
3312 | 1.14k | if (ret == other) { |
3313 | 0 | return (const xmlChar*) 1; |
3314 | 0 | } |
3315 | 1.14k | return ret; |
3316 | 1.14k | } |
3317 | | |
3318 | | /** |
3319 | | * xmlParseStringName: |
3320 | | * @ctxt: an XML parser context |
3321 | | * @str: a pointer to the string pointer (IN/OUT) |
3322 | | * |
3323 | | * parse an XML name. |
3324 | | * |
3325 | | * [4] NameChar ::= Letter | Digit | '.' | '-' | '_' | ':' | |
3326 | | * CombiningChar | Extender |
3327 | | * |
3328 | | * [5] Name ::= (Letter | '_' | ':') (NameChar)* |
3329 | | * |
3330 | | * [6] Names ::= Name (#x20 Name)* |
3331 | | * |
3332 | | * Returns the Name parsed or NULL. The @str pointer |
3333 | | * is updated to the current location in the string. |
3334 | | */ |
3335 | | |
3336 | | static xmlChar * |
3337 | 18.2k | xmlParseStringName(xmlParserCtxtPtr ctxt, const xmlChar** str) { |
3338 | 18.2k | xmlChar buf[XML_MAX_NAMELEN + 5]; |
3339 | 18.2k | const xmlChar *cur = *str; |
3340 | 18.2k | int len = 0, l; |
3341 | 18.2k | int c; |
3342 | 18.2k | int maxLength = (ctxt->options & XML_PARSE_HUGE) ? |
3343 | 0 | XML_MAX_TEXT_LENGTH : |
3344 | 18.2k | XML_MAX_NAME_LENGTH; |
3345 | | |
3346 | | #ifdef DEBUG |
3347 | | nbParseStringName++; |
3348 | | #endif |
3349 | | |
3350 | 18.2k | c = CUR_SCHAR(cur, l); |
3351 | 18.2k | if (!xmlIsNameStartChar(ctxt, c)) { |
3352 | 6.66k | return(NULL); |
3353 | 6.66k | } |
3354 | | |
3355 | 11.6k | COPY_BUF(l,buf,len,c); |
3356 | 11.6k | cur += l; |
3357 | 11.6k | c = CUR_SCHAR(cur, l); |
3358 | 96.2k | while (xmlIsNameChar(ctxt, c)) { |
3359 | 84.7k | COPY_BUF(l,buf,len,c); |
3360 | 84.7k | cur += l; |
3361 | 84.7k | c = CUR_SCHAR(cur, l); |
3362 | 84.7k | if (len >= XML_MAX_NAMELEN) { /* test bigentname.xml */ |
3363 | | /* |
3364 | | * Okay someone managed to make a huge name, so he's ready to pay |
3365 | | * for the processing speed. |
3366 | | */ |
3367 | 158 | xmlChar *buffer; |
3368 | 158 | int max = len * 2; |
3369 | | |
3370 | 158 | buffer = (xmlChar *) xmlMallocAtomic(max); |
3371 | 158 | if (buffer == NULL) { |
3372 | 0 | xmlErrMemory(ctxt, NULL); |
3373 | 0 | return(NULL); |
3374 | 0 | } |
3375 | 158 | memcpy(buffer, buf, len); |
3376 | 136k | while (xmlIsNameChar(ctxt, c)) { |
3377 | 136k | if (len + 10 > max) { |
3378 | 338 | xmlChar *tmp; |
3379 | | |
3380 | 338 | max *= 2; |
3381 | 338 | tmp = (xmlChar *) xmlRealloc(buffer, max); |
3382 | 338 | if (tmp == NULL) { |
3383 | 0 | xmlErrMemory(ctxt, NULL); |
3384 | 0 | xmlFree(buffer); |
3385 | 0 | return(NULL); |
3386 | 0 | } |
3387 | 338 | buffer = tmp; |
3388 | 338 | } |
3389 | 136k | COPY_BUF(l,buffer,len,c); |
3390 | 136k | cur += l; |
3391 | 136k | c = CUR_SCHAR(cur, l); |
3392 | 136k | if (len > maxLength) { |
3393 | 1 | xmlFatalErr(ctxt, XML_ERR_NAME_TOO_LONG, "NCName"); |
3394 | 1 | xmlFree(buffer); |
3395 | 1 | return(NULL); |
3396 | 1 | } |
3397 | 136k | } |
3398 | 157 | buffer[len] = 0; |
3399 | 157 | *str = cur; |
3400 | 157 | return(buffer); |
3401 | 158 | } |
3402 | 84.7k | } |
3403 | 11.4k | if (len > maxLength) { |
3404 | 0 | xmlFatalErr(ctxt, XML_ERR_NAME_TOO_LONG, "NCName"); |
3405 | 0 | return(NULL); |
3406 | 0 | } |
3407 | 11.4k | *str = cur; |
3408 | 11.4k | return(xmlStrndup(buf, len)); |
3409 | 11.4k | } |
3410 | | |
3411 | | /** |
3412 | | * xmlParseNmtoken: |
3413 | | * @ctxt: an XML parser context |
3414 | | * |
3415 | | * DEPRECATED: Internal function, don't use. |
3416 | | * |
3417 | | * parse an XML Nmtoken. |
3418 | | * |
3419 | | * [7] Nmtoken ::= (NameChar)+ |
3420 | | * |
3421 | | * [8] Nmtokens ::= Nmtoken (#x20 Nmtoken)* |
3422 | | * |
3423 | | * Returns the Nmtoken parsed or NULL |
3424 | | */ |
3425 | | |
3426 | | xmlChar * |
3427 | 6.75k | xmlParseNmtoken(xmlParserCtxtPtr ctxt) { |
3428 | 6.75k | xmlChar buf[XML_MAX_NAMELEN + 5]; |
3429 | 6.75k | int len = 0, l; |
3430 | 6.75k | int c; |
3431 | 6.75k | int maxLength = (ctxt->options & XML_PARSE_HUGE) ? |
3432 | 0 | XML_MAX_TEXT_LENGTH : |
3433 | 6.75k | XML_MAX_NAME_LENGTH; |
3434 | | |
3435 | | #ifdef DEBUG |
3436 | | nbParseNmToken++; |
3437 | | #endif |
3438 | | |
3439 | 6.75k | c = CUR_CHAR(l); |
3440 | | |
3441 | 35.1k | while (xmlIsNameChar(ctxt, c)) { |
3442 | 28.4k | COPY_BUF(l,buf,len,c); |
3443 | 28.4k | NEXTL(l); |
3444 | 28.4k | c = CUR_CHAR(l); |
3445 | 28.4k | if (len >= XML_MAX_NAMELEN) { |
3446 | | /* |
3447 | | * Okay someone managed to make a huge token, so he's ready to pay |
3448 | | * for the processing speed. |
3449 | | */ |
3450 | 32 | xmlChar *buffer; |
3451 | 32 | int max = len * 2; |
3452 | | |
3453 | 32 | buffer = (xmlChar *) xmlMallocAtomic(max); |
3454 | 32 | if (buffer == NULL) { |
3455 | 0 | xmlErrMemory(ctxt, NULL); |
3456 | 0 | return(NULL); |
3457 | 0 | } |
3458 | 32 | memcpy(buffer, buf, len); |
3459 | 495k | while (xmlIsNameChar(ctxt, c)) { |
3460 | 495k | if (len + 10 > max) { |
3461 | 97 | xmlChar *tmp; |
3462 | | |
3463 | 97 | max *= 2; |
3464 | 97 | tmp = (xmlChar *) xmlRealloc(buffer, max); |
3465 | 97 | if (tmp == NULL) { |
3466 | 0 | xmlErrMemory(ctxt, NULL); |
3467 | 0 | xmlFree(buffer); |
3468 | 0 | return(NULL); |
3469 | 0 | } |
3470 | 97 | buffer = tmp; |
3471 | 97 | } |
3472 | 495k | COPY_BUF(l,buffer,len,c); |
3473 | 495k | if (len > maxLength) { |
3474 | 9 | xmlFatalErr(ctxt, XML_ERR_NAME_TOO_LONG, "NmToken"); |
3475 | 9 | xmlFree(buffer); |
3476 | 9 | return(NULL); |
3477 | 9 | } |
3478 | 495k | NEXTL(l); |
3479 | 495k | c = CUR_CHAR(l); |
3480 | 495k | } |
3481 | 23 | buffer[len] = 0; |
3482 | 23 | if (ctxt->instate == XML_PARSER_EOF) { |
3483 | 0 | xmlFree(buffer); |
3484 | 0 | return(NULL); |
3485 | 0 | } |
3486 | 23 | return(buffer); |
3487 | 23 | } |
3488 | 28.4k | } |
3489 | 6.71k | if (ctxt->instate == XML_PARSER_EOF) |
3490 | 0 | return(NULL); |
3491 | 6.71k | if (len == 0) |
3492 | 1.09k | return(NULL); |
3493 | 5.62k | if (len > maxLength) { |
3494 | 0 | xmlFatalErr(ctxt, XML_ERR_NAME_TOO_LONG, "NmToken"); |
3495 | 0 | return(NULL); |
3496 | 0 | } |
3497 | 5.62k | return(xmlStrndup(buf, len)); |
3498 | 5.62k | } |
3499 | | |
3500 | | /** |
3501 | | * xmlParseEntityValue: |
3502 | | * @ctxt: an XML parser context |
3503 | | * @orig: if non-NULL store a copy of the original entity value |
3504 | | * |
3505 | | * DEPRECATED: Internal function, don't use. |
3506 | | * |
3507 | | * parse a value for ENTITY declarations |
3508 | | * |
3509 | | * [9] EntityValue ::= '"' ([^%&"] | PEReference | Reference)* '"' | |
3510 | | * "'" ([^%&'] | PEReference | Reference)* "'" |
3511 | | * |
3512 | | * Returns the EntityValue parsed with reference substituted or NULL |
3513 | | */ |
3514 | | |
3515 | | xmlChar * |
3516 | 21.1k | xmlParseEntityValue(xmlParserCtxtPtr ctxt, xmlChar **orig) { |
3517 | 21.1k | xmlChar *buf = NULL; |
3518 | 21.1k | int len = 0; |
3519 | 21.1k | int size = XML_PARSER_BUFFER_SIZE; |
3520 | 21.1k | int c, l; |
3521 | 21.1k | int maxLength = (ctxt->options & XML_PARSE_HUGE) ? |
3522 | 0 | XML_MAX_HUGE_LENGTH : |
3523 | 21.1k | XML_MAX_TEXT_LENGTH; |
3524 | 21.1k | xmlChar stop; |
3525 | 21.1k | xmlChar *ret = NULL; |
3526 | 21.1k | const xmlChar *cur = NULL; |
3527 | 21.1k | xmlParserInputPtr input; |
3528 | | |
3529 | 21.1k | if (RAW == '"') stop = '"'; |
3530 | 0 | else if (RAW == '\'') stop = '\''; |
3531 | 0 | else { |
3532 | 0 | xmlFatalErr(ctxt, XML_ERR_ENTITY_NOT_STARTED, NULL); |
3533 | 0 | return(NULL); |
3534 | 0 | } |
3535 | 21.1k | buf = (xmlChar *) xmlMallocAtomic(size); |
3536 | 21.1k | if (buf == NULL) { |
3537 | 0 | xmlErrMemory(ctxt, NULL); |
3538 | 0 | return(NULL); |
3539 | 0 | } |
3540 | | |
3541 | | /* |
3542 | | * The content of the entity definition is copied in a buffer. |
3543 | | */ |
3544 | | |
3545 | 21.1k | ctxt->instate = XML_PARSER_ENTITY_VALUE; |
3546 | 21.1k | input = ctxt->input; |
3547 | 21.1k | GROW; |
3548 | 21.1k | if (ctxt->instate == XML_PARSER_EOF) |
3549 | 0 | goto error; |
3550 | 21.1k | NEXT; |
3551 | 21.1k | c = CUR_CHAR(l); |
3552 | | /* |
3553 | | * NOTE: 4.4.5 Included in Literal |
3554 | | * When a parameter entity reference appears in a literal entity |
3555 | | * value, ... a single or double quote character in the replacement |
3556 | | * text is always treated as a normal data character and will not |
3557 | | * terminate the literal. |
3558 | | * In practice it means we stop the loop only when back at parsing |
3559 | | * the initial entity and the quote is found |
3560 | | */ |
3561 | 10.7M | while (((IS_CHAR(c)) && ((c != stop) || /* checked */ |
3562 | 10.7M | (ctxt->input != input))) && (ctxt->instate != XML_PARSER_EOF)) { |
3563 | 10.6M | if (len + 5 >= size) { |
3564 | 18.5k | xmlChar *tmp; |
3565 | | |
3566 | 18.5k | size *= 2; |
3567 | 18.5k | tmp = (xmlChar *) xmlRealloc(buf, size); |
3568 | 18.5k | if (tmp == NULL) { |
3569 | 0 | xmlErrMemory(ctxt, NULL); |
3570 | 0 | goto error; |
3571 | 0 | } |
3572 | 18.5k | buf = tmp; |
3573 | 18.5k | } |
3574 | 10.6M | COPY_BUF(l,buf,len,c); |
3575 | 10.6M | NEXTL(l); |
3576 | | |
3577 | 10.6M | GROW; |
3578 | 10.6M | c = CUR_CHAR(l); |
3579 | 10.6M | if (c == 0) { |
3580 | 9 | GROW; |
3581 | 9 | c = CUR_CHAR(l); |
3582 | 9 | } |
3583 | | |
3584 | 10.6M | if (len > maxLength) { |
3585 | 0 | xmlFatalErrMsg(ctxt, XML_ERR_ENTITY_NOT_FINISHED, |
3586 | 0 | "entity value too long\n"); |
3587 | 0 | goto error; |
3588 | 0 | } |
3589 | 10.6M | } |
3590 | 21.1k | buf[len] = 0; |
3591 | 21.1k | if (ctxt->instate == XML_PARSER_EOF) |
3592 | 0 | goto error; |
3593 | 21.1k | if (c != stop) { |
3594 | 10 | xmlFatalErr(ctxt, XML_ERR_ENTITY_NOT_FINISHED, NULL); |
3595 | 10 | goto error; |
3596 | 10 | } |
3597 | 21.1k | NEXT; |
3598 | | |
3599 | | /* |
3600 | | * Raise problem w.r.t. '&' and '%' being used in non-entities |
3601 | | * reference constructs. Note Charref will be handled in |
3602 | | * xmlStringDecodeEntities() |
3603 | | */ |
3604 | 21.1k | cur = buf; |
3605 | 10.1M | while (*cur != 0) { /* non input consuming */ |
3606 | 10.1M | if ((*cur == '%') || ((*cur == '&') && (cur[1] != '#'))) { |
3607 | 6.30k | xmlChar *name; |
3608 | 6.30k | xmlChar tmp = *cur; |
3609 | 6.30k | int nameOk = 0; |
3610 | | |
3611 | 6.30k | cur++; |
3612 | 6.30k | name = xmlParseStringName(ctxt, &cur); |
3613 | 6.30k | if (name != NULL) { |
3614 | 6.24k | nameOk = 1; |
3615 | 6.24k | xmlFree(name); |
3616 | 6.24k | } |
3617 | 6.30k | if ((nameOk == 0) || (*cur != ';')) { |
3618 | 1.89k | xmlFatalErrMsgInt(ctxt, XML_ERR_ENTITY_CHAR_ERROR, |
3619 | 1.89k | "EntityValue: '%c' forbidden except for entities references\n", |
3620 | 1.89k | tmp); |
3621 | 1.89k | goto error; |
3622 | 1.89k | } |
3623 | 4.40k | if ((tmp == '%') && (ctxt->inSubset == 1) && |
3624 | 4.40k | (ctxt->inputNr == 1)) { |
3625 | 0 | xmlFatalErr(ctxt, XML_ERR_ENTITY_PE_INTERNAL, NULL); |
3626 | 0 | goto error; |
3627 | 0 | } |
3628 | 4.40k | if (*cur == 0) |
3629 | 0 | break; |
3630 | 4.40k | } |
3631 | 10.1M | cur++; |
3632 | 10.1M | } |
3633 | | |
3634 | | /* |
3635 | | * Then PEReference entities are substituted. |
3636 | | * |
3637 | | * NOTE: 4.4.7 Bypassed |
3638 | | * When a general entity reference appears in the EntityValue in |
3639 | | * an entity declaration, it is bypassed and left as is. |
3640 | | * so XML_SUBSTITUTE_REF is not set here. |
3641 | | */ |
3642 | 19.2k | ++ctxt->depth; |
3643 | 19.2k | ret = xmlStringDecodeEntitiesInt(ctxt, buf, len, XML_SUBSTITUTE_PEREF, |
3644 | 19.2k | 0, 0, 0, /* check */ 1); |
3645 | 19.2k | --ctxt->depth; |
3646 | | |
3647 | 19.2k | if (orig != NULL) { |
3648 | 19.2k | *orig = buf; |
3649 | 19.2k | buf = NULL; |
3650 | 19.2k | } |
3651 | | |
3652 | 21.1k | error: |
3653 | 21.1k | if (buf != NULL) |
3654 | 1.90k | xmlFree(buf); |
3655 | 21.1k | return(ret); |
3656 | 19.2k | } |
3657 | | |
3658 | | /** |
3659 | | * xmlParseAttValueComplex: |
3660 | | * @ctxt: an XML parser context |
3661 | | * @len: the resulting attribute len |
3662 | | * @normalize: whether to apply the inner normalization |
3663 | | * |
3664 | | * parse a value for an attribute, this is the fallback function |
3665 | | * of xmlParseAttValue() when the attribute parsing requires handling |
3666 | | * of non-ASCII characters, or normalization compaction. |
3667 | | * |
3668 | | * Returns the AttValue parsed or NULL. The value has to be freed by the caller. |
3669 | | */ |
3670 | | static xmlChar * |
3671 | 10.1k | xmlParseAttValueComplex(xmlParserCtxtPtr ctxt, int *attlen, int normalize) { |
3672 | 10.1k | xmlChar limit = 0; |
3673 | 10.1k | xmlChar *buf = NULL; |
3674 | 10.1k | xmlChar *rep = NULL; |
3675 | 10.1k | size_t len = 0; |
3676 | 10.1k | size_t buf_size = 0; |
3677 | 10.1k | size_t maxLength = (ctxt->options & XML_PARSE_HUGE) ? |
3678 | 0 | XML_MAX_HUGE_LENGTH : |
3679 | 10.1k | XML_MAX_TEXT_LENGTH; |
3680 | 10.1k | int c, l, in_space = 0; |
3681 | 10.1k | xmlChar *current = NULL; |
3682 | 10.1k | xmlEntityPtr ent; |
3683 | | |
3684 | 10.1k | if (NXT(0) == '"') { |
3685 | 940 | ctxt->instate = XML_PARSER_ATTRIBUTE_VALUE; |
3686 | 940 | limit = '"'; |
3687 | 940 | NEXT; |
3688 | 9.23k | } else if (NXT(0) == '\'') { |
3689 | 9.23k | limit = '\''; |
3690 | 9.23k | ctxt->instate = XML_PARSER_ATTRIBUTE_VALUE; |
3691 | 9.23k | NEXT; |
3692 | 9.23k | } else { |
3693 | 0 | xmlFatalErr(ctxt, XML_ERR_ATTRIBUTE_NOT_STARTED, NULL); |
3694 | 0 | return(NULL); |
3695 | 0 | } |
3696 | | |
3697 | | /* |
3698 | | * allocate a translation buffer. |
3699 | | */ |
3700 | 10.1k | buf_size = XML_PARSER_BUFFER_SIZE; |
3701 | 10.1k | buf = (xmlChar *) xmlMallocAtomic(buf_size); |
3702 | 10.1k | if (buf == NULL) goto mem_error; |
3703 | | |
3704 | | /* |
3705 | | * OK loop until we reach one of the ending char or a size limit. |
3706 | | */ |
3707 | 10.1k | c = CUR_CHAR(l); |
3708 | 8.85M | while (((NXT(0) != limit) && /* checked */ |
3709 | 8.85M | (IS_CHAR(c)) && (c != '<')) && |
3710 | 8.85M | (ctxt->instate != XML_PARSER_EOF)) { |
3711 | 8.84M | if (c == '&') { |
3712 | 47.2k | in_space = 0; |
3713 | 47.2k | if (NXT(1) == '#') { |
3714 | 504 | int val = xmlParseCharRef(ctxt); |
3715 | | |
3716 | 504 | if (val == '&') { |
3717 | 0 | if (ctxt->replaceEntities) { |
3718 | 0 | if (len + 10 > buf_size) { |
3719 | 0 | growBuffer(buf, 10); |
3720 | 0 | } |
3721 | 0 | buf[len++] = '&'; |
3722 | 0 | } else { |
3723 | | /* |
3724 | | * The reparsing will be done in xmlStringGetNodeList() |
3725 | | * called by the attribute() function in SAX.c |
3726 | | */ |
3727 | 0 | if (len + 10 > buf_size) { |
3728 | 0 | growBuffer(buf, 10); |
3729 | 0 | } |
3730 | 0 | buf[len++] = '&'; |
3731 | 0 | buf[len++] = '#'; |
3732 | 0 | buf[len++] = '3'; |
3733 | 0 | buf[len++] = '8'; |
3734 | 0 | buf[len++] = ';'; |
3735 | 0 | } |
3736 | 504 | } else if (val != 0) { |
3737 | 500 | if (len + 10 > buf_size) { |
3738 | 2 | growBuffer(buf, 10); |
3739 | 2 | } |
3740 | 500 | len += xmlCopyChar(0, &buf[len], val); |
3741 | 500 | } |
3742 | 46.7k | } else { |
3743 | 46.7k | ent = xmlParseEntityRef(ctxt); |
3744 | 46.7k | if ((ent != NULL) && |
3745 | 46.7k | (ent->etype == XML_INTERNAL_PREDEFINED_ENTITY)) { |
3746 | 9.56k | if (len + 10 > buf_size) { |
3747 | 24 | growBuffer(buf, 10); |
3748 | 24 | } |
3749 | 9.56k | if ((ctxt->replaceEntities == 0) && |
3750 | 9.56k | (ent->content[0] == '&')) { |
3751 | 9.53k | buf[len++] = '&'; |
3752 | 9.53k | buf[len++] = '#'; |
3753 | 9.53k | buf[len++] = '3'; |
3754 | 9.53k | buf[len++] = '8'; |
3755 | 9.53k | buf[len++] = ';'; |
3756 | 9.53k | } else { |
3757 | 29 | buf[len++] = ent->content[0]; |
3758 | 29 | } |
3759 | 37.1k | } else if ((ent != NULL) && |
3760 | 37.1k | (ctxt->replaceEntities != 0)) { |
3761 | 0 | if (ent->etype != XML_INTERNAL_PREDEFINED_ENTITY) { |
3762 | 0 | if (xmlParserEntityCheck(ctxt, ent->length)) |
3763 | 0 | goto error; |
3764 | | |
3765 | 0 | ++ctxt->depth; |
3766 | 0 | rep = xmlStringDecodeEntitiesInt(ctxt, ent->content, |
3767 | 0 | ent->length, XML_SUBSTITUTE_REF, 0, 0, 0, |
3768 | 0 | /* check */ 1); |
3769 | 0 | --ctxt->depth; |
3770 | 0 | if (rep != NULL) { |
3771 | 0 | current = rep; |
3772 | 0 | while (*current != 0) { /* non input consuming */ |
3773 | 0 | if ((*current == 0xD) || (*current == 0xA) || |
3774 | 0 | (*current == 0x9)) { |
3775 | 0 | buf[len++] = 0x20; |
3776 | 0 | current++; |
3777 | 0 | } else |
3778 | 0 | buf[len++] = *current++; |
3779 | 0 | if (len + 10 > buf_size) { |
3780 | 0 | growBuffer(buf, 10); |
3781 | 0 | } |
3782 | 0 | } |
3783 | 0 | xmlFree(rep); |
3784 | 0 | rep = NULL; |
3785 | 0 | } |
3786 | 0 | } else { |
3787 | 0 | if (len + 10 > buf_size) { |
3788 | 0 | growBuffer(buf, 10); |
3789 | 0 | } |
3790 | 0 | if (ent->content != NULL) |
3791 | 0 | buf[len++] = ent->content[0]; |
3792 | 0 | } |
3793 | 37.1k | } else if (ent != NULL) { |
3794 | 7.80k | int i = xmlStrlen(ent->name); |
3795 | 7.80k | const xmlChar *cur = ent->name; |
3796 | | |
3797 | | /* |
3798 | | * We also check for recursion and amplification |
3799 | | * when entities are not substituted. They're |
3800 | | * often expanded later. |
3801 | | */ |
3802 | 7.80k | if ((ent->etype != XML_INTERNAL_PREDEFINED_ENTITY) && |
3803 | 7.80k | (ent->content != NULL)) { |
3804 | 1.11k | if ((ent->flags & XML_ENT_CHECKED) == 0) { |
3805 | 36 | unsigned long oldCopy = ctxt->sizeentcopy; |
3806 | | |
3807 | 36 | ctxt->sizeentcopy = ent->length; |
3808 | | |
3809 | 36 | ++ctxt->depth; |
3810 | 36 | rep = xmlStringDecodeEntitiesInt(ctxt, |
3811 | 36 | ent->content, ent->length, |
3812 | 36 | XML_SUBSTITUTE_REF, 0, 0, 0, |
3813 | 36 | /* check */ 1); |
3814 | 36 | --ctxt->depth; |
3815 | | |
3816 | | /* |
3817 | | * If we're parsing DTD content, the entity |
3818 | | * might reference other entities which |
3819 | | * weren't defined yet, so the check isn't |
3820 | | * reliable. |
3821 | | */ |
3822 | 36 | if (ctxt->inSubset == 0) { |
3823 | 36 | ent->flags |= XML_ENT_CHECKED; |
3824 | 36 | ent->expandedSize = ctxt->sizeentcopy; |
3825 | 36 | } |
3826 | | |
3827 | 36 | if (rep != NULL) { |
3828 | 36 | xmlFree(rep); |
3829 | 36 | rep = NULL; |
3830 | 36 | } else { |
3831 | 0 | ent->content[0] = 0; |
3832 | 0 | } |
3833 | | |
3834 | 36 | if (xmlParserEntityCheck(ctxt, oldCopy)) |
3835 | 0 | goto error; |
3836 | 1.08k | } else { |
3837 | 1.08k | if (xmlParserEntityCheck(ctxt, ent->expandedSize)) |
3838 | 23 | goto error; |
3839 | 1.08k | } |
3840 | 1.11k | } |
3841 | | |
3842 | | /* |
3843 | | * Just output the reference |
3844 | | */ |
3845 | 7.78k | buf[len++] = '&'; |
3846 | 7.91k | while (len + i + 10 > buf_size) { |
3847 | 266 | growBuffer(buf, i + 10); |
3848 | 266 | } |
3849 | 15.5k | for (;i > 0;i--) |
3850 | 7.78k | buf[len++] = *cur++; |
3851 | 7.78k | buf[len++] = ';'; |
3852 | 7.78k | } |
3853 | 46.7k | } |
3854 | 8.80M | } else { |
3855 | 8.80M | if ((c == 0x20) || (c == 0xD) || (c == 0xA) || (c == 0x9)) { |
3856 | 1.24M | if ((len != 0) || (!normalize)) { |
3857 | 1.24M | if ((!normalize) || (!in_space)) { |
3858 | 1.23M | COPY_BUF(l,buf,len,0x20); |
3859 | 1.23M | while (len + 10 > buf_size) { |
3860 | 1.45k | growBuffer(buf, 10); |
3861 | 1.45k | } |
3862 | 1.23M | } |
3863 | 1.24M | in_space = 1; |
3864 | 1.24M | } |
3865 | 7.56M | } else { |
3866 | 7.56M | in_space = 0; |
3867 | 7.56M | COPY_BUF(l,buf,len,c); |
3868 | 7.56M | if (len + 10 > buf_size) { |
3869 | 8.93k | growBuffer(buf, 10); |
3870 | 8.93k | } |
3871 | 7.56M | } |
3872 | 8.80M | NEXTL(l); |
3873 | 8.80M | } |
3874 | 8.84M | GROW; |
3875 | 8.84M | c = CUR_CHAR(l); |
3876 | 8.84M | if (len > maxLength) { |
3877 | 0 | xmlFatalErrMsg(ctxt, XML_ERR_ATTRIBUTE_NOT_FINISHED, |
3878 | 0 | "AttValue length too long\n"); |
3879 | 0 | goto mem_error; |
3880 | 0 | } |
3881 | 8.84M | } |
3882 | 10.1k | if (ctxt->instate == XML_PARSER_EOF) |
3883 | 0 | goto error; |
3884 | | |
3885 | 10.1k | if ((in_space) && (normalize)) { |
3886 | 74 | while ((len > 0) && (buf[len - 1] == 0x20)) len--; |
3887 | 37 | } |
3888 | 10.1k | buf[len] = 0; |
3889 | 10.1k | if (RAW == '<') { |
3890 | 5.49k | xmlFatalErr(ctxt, XML_ERR_LT_IN_ATTRIBUTE, NULL); |
3891 | 5.49k | } else if (RAW != limit) { |
3892 | 1.62k | if ((c != 0) && (!IS_CHAR(c))) { |
3893 | 1.60k | xmlFatalErrMsg(ctxt, XML_ERR_INVALID_CHAR, |
3894 | 1.60k | "invalid character in attribute value\n"); |
3895 | 1.60k | } else { |
3896 | 16 | xmlFatalErrMsg(ctxt, XML_ERR_ATTRIBUTE_NOT_FINISHED, |
3897 | 16 | "AttValue: ' expected\n"); |
3898 | 16 | } |
3899 | 1.62k | } else |
3900 | 3.04k | NEXT; |
3901 | | |
3902 | 10.1k | if (attlen != NULL) *attlen = len; |
3903 | 10.1k | return(buf); |
3904 | | |
3905 | 0 | mem_error: |
3906 | 0 | xmlErrMemory(ctxt, NULL); |
3907 | 23 | error: |
3908 | 23 | if (buf != NULL) |
3909 | 23 | xmlFree(buf); |
3910 | 23 | if (rep != NULL) |
3911 | 0 | xmlFree(rep); |
3912 | 23 | return(NULL); |
3913 | 0 | } |
3914 | | |
3915 | | /** |
3916 | | * xmlParseAttValue: |
3917 | | * @ctxt: an XML parser context |
3918 | | * |
3919 | | * DEPRECATED: Internal function, don't use. |
3920 | | * |
3921 | | * parse a value for an attribute |
3922 | | * Note: the parser won't do substitution of entities here, this |
3923 | | * will be handled later in xmlStringGetNodeList |
3924 | | * |
3925 | | * [10] AttValue ::= '"' ([^<&"] | Reference)* '"' | |
3926 | | * "'" ([^<&'] | Reference)* "'" |
3927 | | * |
3928 | | * 3.3.3 Attribute-Value Normalization: |
3929 | | * Before the value of an attribute is passed to the application or |
3930 | | * checked for validity, the XML processor must normalize it as follows: |
3931 | | * - a character reference is processed by appending the referenced |
3932 | | * character to the attribute value |
3933 | | * - an entity reference is processed by recursively processing the |
3934 | | * replacement text of the entity |
3935 | | * - a whitespace character (#x20, #xD, #xA, #x9) is processed by |
3936 | | * appending #x20 to the normalized value, except that only a single |
3937 | | * #x20 is appended for a "#xD#xA" sequence that is part of an external |
3938 | | * parsed entity or the literal entity value of an internal parsed entity |
3939 | | * - other characters are processed by appending them to the normalized value |
3940 | | * If the declared value is not CDATA, then the XML processor must further |
3941 | | * process the normalized attribute value by discarding any leading and |
3942 | | * trailing space (#x20) characters, and by replacing sequences of space |
3943 | | * (#x20) characters by a single space (#x20) character. |
3944 | | * All attributes for which no declaration has been read should be treated |
3945 | | * by a non-validating parser as if declared CDATA. |
3946 | | * |
3947 | | * Returns the AttValue parsed or NULL. The value has to be freed by the caller. |
3948 | | */ |
3949 | | |
3950 | | |
3951 | | xmlChar * |
3952 | 2.56k | xmlParseAttValue(xmlParserCtxtPtr ctxt) { |
3953 | 2.56k | if ((ctxt == NULL) || (ctxt->input == NULL)) return(NULL); |
3954 | 2.56k | return(xmlParseAttValueInternal(ctxt, NULL, NULL, 0)); |
3955 | 2.56k | } |
3956 | | |
3957 | | /** |
3958 | | * xmlParseSystemLiteral: |
3959 | | * @ctxt: an XML parser context |
3960 | | * |
3961 | | * DEPRECATED: Internal function, don't use. |
3962 | | * |
3963 | | * parse an XML Literal |
3964 | | * |
3965 | | * [11] SystemLiteral ::= ('"' [^"]* '"') | ("'" [^']* "'") |
3966 | | * |
3967 | | * Returns the SystemLiteral parsed or NULL |
3968 | | */ |
3969 | | |
3970 | | xmlChar * |
3971 | 4.02k | xmlParseSystemLiteral(xmlParserCtxtPtr ctxt) { |
3972 | 4.02k | xmlChar *buf = NULL; |
3973 | 4.02k | int len = 0; |
3974 | 4.02k | int size = XML_PARSER_BUFFER_SIZE; |
3975 | 4.02k | int cur, l; |
3976 | 4.02k | int maxLength = (ctxt->options & XML_PARSE_HUGE) ? |
3977 | 0 | XML_MAX_TEXT_LENGTH : |
3978 | 4.02k | XML_MAX_NAME_LENGTH; |
3979 | 4.02k | xmlChar stop; |
3980 | 4.02k | int state = ctxt->instate; |
3981 | | |
3982 | 4.02k | if (RAW == '"') { |
3983 | 3.97k | NEXT; |
3984 | 3.97k | stop = '"'; |
3985 | 3.97k | } else if (RAW == '\'') { |
3986 | 0 | NEXT; |
3987 | 0 | stop = '\''; |
3988 | 57 | } else { |
3989 | 57 | xmlFatalErr(ctxt, XML_ERR_LITERAL_NOT_STARTED, NULL); |
3990 | 57 | return(NULL); |
3991 | 57 | } |
3992 | | |
3993 | 3.97k | buf = (xmlChar *) xmlMallocAtomic(size); |
3994 | 3.97k | if (buf == NULL) { |
3995 | 0 | xmlErrMemory(ctxt, NULL); |
3996 | 0 | return(NULL); |
3997 | 0 | } |
3998 | 3.97k | ctxt->instate = XML_PARSER_SYSTEM_LITERAL; |
3999 | 3.97k | cur = CUR_CHAR(l); |
4000 | 943k | while ((IS_CHAR(cur)) && (cur != stop)) { /* checked */ |
4001 | 939k | if (len + 5 >= size) { |
4002 | 6.86k | xmlChar *tmp; |
4003 | | |
4004 | 6.86k | size *= 2; |
4005 | 6.86k | tmp = (xmlChar *) xmlRealloc(buf, size); |
4006 | 6.86k | if (tmp == NULL) { |
4007 | 0 | xmlFree(buf); |
4008 | 0 | xmlErrMemory(ctxt, NULL); |
4009 | 0 | ctxt->instate = (xmlParserInputState) state; |
4010 | 0 | return(NULL); |
4011 | 0 | } |
4012 | 6.86k | buf = tmp; |
4013 | 6.86k | } |
4014 | 939k | COPY_BUF(l,buf,len,cur); |
4015 | 939k | if (len > maxLength) { |
4016 | 0 | xmlFatalErr(ctxt, XML_ERR_NAME_TOO_LONG, "SystemLiteral"); |
4017 | 0 | xmlFree(buf); |
4018 | 0 | ctxt->instate = (xmlParserInputState) state; |
4019 | 0 | return(NULL); |
4020 | 0 | } |
4021 | 939k | NEXTL(l); |
4022 | 939k | cur = CUR_CHAR(l); |
4023 | 939k | } |
4024 | 3.97k | buf[len] = 0; |
4025 | 3.97k | if (ctxt->instate == XML_PARSER_EOF) { |
4026 | 0 | xmlFree(buf); |
4027 | 0 | return(NULL); |
4028 | 0 | } |
4029 | 3.97k | ctxt->instate = (xmlParserInputState) state; |
4030 | 3.97k | if (!IS_CHAR(cur)) { |
4031 | 1 | xmlFatalErr(ctxt, XML_ERR_LITERAL_NOT_FINISHED, NULL); |
4032 | 3.96k | } else { |
4033 | 3.96k | NEXT; |
4034 | 3.96k | } |
4035 | 3.97k | return(buf); |
4036 | 3.97k | } |
4037 | | |
4038 | | /** |
4039 | | * xmlParsePubidLiteral: |
4040 | | * @ctxt: an XML parser context |
4041 | | * |
4042 | | * DEPRECATED: Internal function, don't use. |
4043 | | * |
4044 | | * parse an XML public literal |
4045 | | * |
4046 | | * [12] PubidLiteral ::= '"' PubidChar* '"' | "'" (PubidChar - "'")* "'" |
4047 | | * |
4048 | | * Returns the PubidLiteral parsed or NULL. |
4049 | | */ |
4050 | | |
4051 | | xmlChar * |
4052 | 4.02k | xmlParsePubidLiteral(xmlParserCtxtPtr ctxt) { |
4053 | 4.02k | xmlChar *buf = NULL; |
4054 | 4.02k | int len = 0; |
4055 | 4.02k | int size = XML_PARSER_BUFFER_SIZE; |
4056 | 4.02k | int maxLength = (ctxt->options & XML_PARSE_HUGE) ? |
4057 | 0 | XML_MAX_TEXT_LENGTH : |
4058 | 4.02k | XML_MAX_NAME_LENGTH; |
4059 | 4.02k | xmlChar cur; |
4060 | 4.02k | xmlChar stop; |
4061 | 4.02k | xmlParserInputState oldstate = ctxt->instate; |
4062 | | |
4063 | 4.02k | if (RAW == '"') { |
4064 | 4.02k | NEXT; |
4065 | 4.02k | stop = '"'; |
4066 | 4.02k | } else if (RAW == '\'') { |
4067 | 0 | NEXT; |
4068 | 0 | stop = '\''; |
4069 | 0 | } else { |
4070 | 0 | xmlFatalErr(ctxt, XML_ERR_LITERAL_NOT_STARTED, NULL); |
4071 | 0 | return(NULL); |
4072 | 0 | } |
4073 | 4.02k | buf = (xmlChar *) xmlMallocAtomic(size); |
4074 | 4.02k | if (buf == NULL) { |
4075 | 0 | xmlErrMemory(ctxt, NULL); |
4076 | 0 | return(NULL); |
4077 | 0 | } |
4078 | 4.02k | ctxt->instate = XML_PARSER_PUBLIC_LITERAL; |
4079 | 4.02k | cur = CUR; |
4080 | 118k | while ((IS_PUBIDCHAR_CH(cur)) && (cur != stop)) { /* checked */ |
4081 | 114k | if (len + 1 >= size) { |
4082 | 128 | xmlChar *tmp; |
4083 | | |
4084 | 128 | size *= 2; |
4085 | 128 | tmp = (xmlChar *) xmlRealloc(buf, size); |
4086 | 128 | if (tmp == NULL) { |
4087 | 0 | xmlErrMemory(ctxt, NULL); |
4088 | 0 | xmlFree(buf); |
4089 | 0 | return(NULL); |
4090 | 0 | } |
4091 | 128 | buf = tmp; |
4092 | 128 | } |
4093 | 114k | buf[len++] = cur; |
4094 | 114k | if (len > maxLength) { |
4095 | 2 | xmlFatalErr(ctxt, XML_ERR_NAME_TOO_LONG, "Public ID"); |
4096 | 2 | xmlFree(buf); |
4097 | 2 | return(NULL); |
4098 | 2 | } |
4099 | 114k | NEXT; |
4100 | 114k | cur = CUR; |
4101 | 114k | } |
4102 | 4.02k | buf[len] = 0; |
4103 | 4.02k | if (ctxt->instate == XML_PARSER_EOF) { |
4104 | 0 | xmlFree(buf); |
4105 | 0 | return(NULL); |
4106 | 0 | } |
4107 | 4.02k | if (cur != stop) { |
4108 | 0 | xmlFatalErr(ctxt, XML_ERR_LITERAL_NOT_FINISHED, NULL); |
4109 | 4.02k | } else { |
4110 | 4.02k | NEXTL(1); |
4111 | 4.02k | } |
4112 | 4.02k | ctxt->instate = oldstate; |
4113 | 4.02k | return(buf); |
4114 | 4.02k | } |
4115 | | |
4116 | | static void xmlParseCharDataComplex(xmlParserCtxtPtr ctxt, int partial); |
4117 | | |
4118 | | /* |
4119 | | * used for the test in the inner loop of the char data testing |
4120 | | */ |
4121 | | static const unsigned char test_char_data[256] = { |
4122 | | 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, |
4123 | | 0x00, 0x09, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x9, CR/LF separated */ |
4124 | | 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, |
4125 | | 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, |
4126 | | 0x20, 0x21, 0x22, 0x23, 0x24, 0x25, 0x00, 0x27, /* & */ |
4127 | | 0x28, 0x29, 0x2A, 0x2B, 0x2C, 0x2D, 0x2E, 0x2F, |
4128 | | 0x30, 0x31, 0x32, 0x33, 0x34, 0x35, 0x36, 0x37, |
4129 | | 0x38, 0x39, 0x3A, 0x3B, 0x00, 0x3D, 0x3E, 0x3F, /* < */ |
4130 | | 0x40, 0x41, 0x42, 0x43, 0x44, 0x45, 0x46, 0x47, |
4131 | | 0x48, 0x49, 0x4A, 0x4B, 0x4C, 0x4D, 0x4E, 0x4F, |
4132 | | 0x50, 0x51, 0x52, 0x53, 0x54, 0x55, 0x56, 0x57, |
4133 | | 0x58, 0x59, 0x5A, 0x5B, 0x5C, 0x00, 0x5E, 0x5F, /* ] */ |
4134 | | 0x60, 0x61, 0x62, 0x63, 0x64, 0x65, 0x66, 0x67, |
4135 | | 0x68, 0x69, 0x6A, 0x6B, 0x6C, 0x6D, 0x6E, 0x6F, |
4136 | | 0x70, 0x71, 0x72, 0x73, 0x74, 0x75, 0x76, 0x77, |
4137 | | 0x78, 0x79, 0x7A, 0x7B, 0x7C, 0x7D, 0x7E, 0x7F, |
4138 | | 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* non-ascii */ |
4139 | | 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, |
4140 | | 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, |
4141 | | 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, |
4142 | | 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, |
4143 | | 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, |
4144 | | 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, |
4145 | | 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, |
4146 | | 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, |
4147 | | 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, |
4148 | | 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, |
4149 | | 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, |
4150 | | 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, |
4151 | | 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, |
4152 | | 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, |
4153 | | 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00 |
4154 | | }; |
4155 | | |
4156 | | /** |
4157 | | * xmlParseCharDataInternal: |
4158 | | * @ctxt: an XML parser context |
4159 | | * @partial: buffer may contain partial UTF-8 sequences |
4160 | | * |
4161 | | * Parse character data. Always makes progress if the first char isn't |
4162 | | * '<' or '&'. |
4163 | | * |
4164 | | * The right angle bracket (>) may be represented using the string ">", |
4165 | | * and must, for compatibility, be escaped using ">" or a character |
4166 | | * reference when it appears in the string "]]>" in content, when that |
4167 | | * string is not marking the end of a CDATA section. |
4168 | | * |
4169 | | * [14] CharData ::= [^<&]* - ([^<&]* ']]>' [^<&]*) |
4170 | | */ |
4171 | | static void |
4172 | 252k | xmlParseCharDataInternal(xmlParserCtxtPtr ctxt, int partial) { |
4173 | 252k | const xmlChar *in; |
4174 | 252k | int nbchar = 0; |
4175 | 252k | int line = ctxt->input->line; |
4176 | 252k | int col = ctxt->input->col; |
4177 | 252k | int ccol; |
4178 | | |
4179 | 252k | GROW; |
4180 | | /* |
4181 | | * Accelerated common case where input don't need to be |
4182 | | * modified before passing it to the handler. |
4183 | | */ |
4184 | 252k | in = ctxt->input->cur; |
4185 | 252k | do { |
4186 | 261k | get_more_space: |
4187 | 284k | while (*in == 0x20) { in++; ctxt->input->col++; } |
4188 | 261k | if (*in == 0xA) { |
4189 | 73.7k | do { |
4190 | 73.7k | ctxt->input->line++; ctxt->input->col = 1; |
4191 | 73.7k | in++; |
4192 | 73.7k | } while (*in == 0xA); |
4193 | 9.97k | goto get_more_space; |
4194 | 9.97k | } |
4195 | 252k | if (*in == '<') { |
4196 | 8.79k | nbchar = in - ctxt->input->cur; |
4197 | 8.79k | if (nbchar > 0) { |
4198 | 8.79k | const xmlChar *tmp = ctxt->input->cur; |
4199 | 8.79k | ctxt->input->cur = in; |
4200 | | |
4201 | 8.79k | if ((ctxt->sax != NULL) && |
4202 | 8.79k | (ctxt->sax->ignorableWhitespace != |
4203 | 8.79k | ctxt->sax->characters)) { |
4204 | 0 | if (areBlanks(ctxt, tmp, nbchar, 1)) { |
4205 | 0 | if (ctxt->sax->ignorableWhitespace != NULL) |
4206 | 0 | ctxt->sax->ignorableWhitespace(ctxt->userData, |
4207 | 0 | tmp, nbchar); |
4208 | 0 | } else { |
4209 | 0 | if (ctxt->sax->characters != NULL) |
4210 | 0 | ctxt->sax->characters(ctxt->userData, |
4211 | 0 | tmp, nbchar); |
4212 | 0 | if (*ctxt->space == -1) |
4213 | 0 | *ctxt->space = -2; |
4214 | 0 | } |
4215 | 8.79k | } else if ((ctxt->sax != NULL) && |
4216 | 8.79k | (ctxt->sax->characters != NULL)) { |
4217 | 8.79k | ctxt->sax->characters(ctxt->userData, |
4218 | 8.79k | tmp, nbchar); |
4219 | 8.79k | } |
4220 | 8.79k | } |
4221 | 8.79k | return; |
4222 | 8.79k | } |
4223 | | |
4224 | 255k | get_more: |
4225 | 255k | ccol = ctxt->input->col; |
4226 | 25.3M | while (test_char_data[*in]) { |
4227 | 25.0M | in++; |
4228 | 25.0M | ccol++; |
4229 | 25.0M | } |
4230 | 255k | ctxt->input->col = ccol; |
4231 | 255k | if (*in == 0xA) { |
4232 | 81.7k | do { |
4233 | 81.7k | ctxt->input->line++; ctxt->input->col = 1; |
4234 | 81.7k | in++; |
4235 | 81.7k | } while (*in == 0xA); |
4236 | 8.15k | goto get_more; |
4237 | 8.15k | } |
4238 | 247k | if (*in == ']') { |
4239 | 3.94k | if ((in[1] == ']') && (in[2] == '>')) { |
4240 | 5 | xmlFatalErr(ctxt, XML_ERR_MISPLACED_CDATA_END, NULL); |
4241 | 5 | if (ctxt->instate != XML_PARSER_EOF) |
4242 | 5 | ctxt->input->cur = in + 1; |
4243 | 5 | return; |
4244 | 5 | } |
4245 | 3.93k | in++; |
4246 | 3.93k | ctxt->input->col++; |
4247 | 3.93k | goto get_more; |
4248 | 3.94k | } |
4249 | 243k | nbchar = in - ctxt->input->cur; |
4250 | 243k | if (nbchar > 0) { |
4251 | 154k | if ((ctxt->sax != NULL) && |
4252 | 154k | (ctxt->sax->ignorableWhitespace != |
4253 | 154k | ctxt->sax->characters) && |
4254 | 154k | (IS_BLANK_CH(*ctxt->input->cur))) { |
4255 | 0 | const xmlChar *tmp = ctxt->input->cur; |
4256 | 0 | ctxt->input->cur = in; |
4257 | |
|
4258 | 0 | if (areBlanks(ctxt, tmp, nbchar, 0)) { |
4259 | 0 | if (ctxt->sax->ignorableWhitespace != NULL) |
4260 | 0 | ctxt->sax->ignorableWhitespace(ctxt->userData, |
4261 | 0 | tmp, nbchar); |
4262 | 0 | } else { |
4263 | 0 | if (ctxt->sax->characters != NULL) |
4264 | 0 | ctxt->sax->characters(ctxt->userData, |
4265 | 0 | tmp, nbchar); |
4266 | 0 | if (*ctxt->space == -1) |
4267 | 0 | *ctxt->space = -2; |
4268 | 0 | } |
4269 | 0 | line = ctxt->input->line; |
4270 | 0 | col = ctxt->input->col; |
4271 | 154k | } else if (ctxt->sax != NULL) { |
4272 | 154k | if (ctxt->sax->characters != NULL) |
4273 | 154k | ctxt->sax->characters(ctxt->userData, |
4274 | 154k | ctxt->input->cur, nbchar); |
4275 | 154k | line = ctxt->input->line; |
4276 | 154k | col = ctxt->input->col; |
4277 | 154k | } |
4278 | 154k | } |
4279 | 243k | ctxt->input->cur = in; |
4280 | 243k | if (*in == 0xD) { |
4281 | 402 | in++; |
4282 | 402 | if (*in == 0xA) { |
4283 | 3 | ctxt->input->cur = in; |
4284 | 3 | in++; |
4285 | 3 | ctxt->input->line++; ctxt->input->col = 1; |
4286 | 3 | continue; /* while */ |
4287 | 3 | } |
4288 | 399 | in--; |
4289 | 399 | } |
4290 | 243k | if (*in == '<') { |
4291 | 120k | return; |
4292 | 120k | } |
4293 | 123k | if (*in == '&') { |
4294 | 5.28k | return; |
4295 | 5.28k | } |
4296 | 117k | SHRINK; |
4297 | 117k | GROW; |
4298 | 117k | if (ctxt->instate == XML_PARSER_EOF) |
4299 | 0 | return; |
4300 | 117k | in = ctxt->input->cur; |
4301 | 117k | } while (((*in >= 0x20) && (*in <= 0x7F)) || |
4302 | 117k | (*in == 0x09) || (*in == 0x0a)); |
4303 | 117k | ctxt->input->line = line; |
4304 | 117k | ctxt->input->col = col; |
4305 | 117k | xmlParseCharDataComplex(ctxt, partial); |
4306 | 117k | } |
4307 | | |
4308 | | /** |
4309 | | * xmlParseCharDataComplex: |
4310 | | * @ctxt: an XML parser context |
4311 | | * @cdata: int indicating whether we are within a CDATA section |
4312 | | * |
4313 | | * Always makes progress if the first char isn't '<' or '&'. |
4314 | | * |
4315 | | * parse a CharData section.this is the fallback function |
4316 | | * of xmlParseCharData() when the parsing requires handling |
4317 | | * of non-ASCII characters. |
4318 | | */ |
4319 | | static void |
4320 | 117k | xmlParseCharDataComplex(xmlParserCtxtPtr ctxt, int partial) { |
4321 | 117k | xmlChar buf[XML_PARSER_BIG_BUFFER_SIZE + 5]; |
4322 | 117k | int nbchar = 0; |
4323 | 117k | int cur, l; |
4324 | | |
4325 | 117k | cur = CUR_CHAR(l); |
4326 | 23.4M | while ((cur != '<') && /* checked */ |
4327 | 23.4M | (cur != '&') && |
4328 | 23.4M | (IS_CHAR(cur))) /* test also done in xmlCurrentChar() */ { |
4329 | 23.3M | if ((cur == ']') && (NXT(1) == ']') && (NXT(2) == '>')) { |
4330 | 282 | xmlFatalErr(ctxt, XML_ERR_MISPLACED_CDATA_END, NULL); |
4331 | 282 | } |
4332 | 23.3M | COPY_BUF(l,buf,nbchar,cur); |
4333 | | /* move current position before possible calling of ctxt->sax->characters */ |
4334 | 23.3M | NEXTL(l); |
4335 | 23.3M | if (nbchar >= XML_PARSER_BIG_BUFFER_SIZE) { |
4336 | 157k | buf[nbchar] = 0; |
4337 | | |
4338 | | /* |
4339 | | * OK the segment is to be consumed as chars. |
4340 | | */ |
4341 | 157k | if ((ctxt->sax != NULL) && (!ctxt->disableSAX)) { |
4342 | 157k | if (areBlanks(ctxt, buf, nbchar, 0)) { |
4343 | 0 | if (ctxt->sax->ignorableWhitespace != NULL) |
4344 | 0 | ctxt->sax->ignorableWhitespace(ctxt->userData, |
4345 | 0 | buf, nbchar); |
4346 | 157k | } else { |
4347 | 157k | if (ctxt->sax->characters != NULL) |
4348 | 157k | ctxt->sax->characters(ctxt->userData, buf, nbchar); |
4349 | 157k | if ((ctxt->sax->characters != |
4350 | 157k | ctxt->sax->ignorableWhitespace) && |
4351 | 157k | (*ctxt->space == -1)) |
4352 | 0 | *ctxt->space = -2; |
4353 | 157k | } |
4354 | 157k | } |
4355 | 157k | nbchar = 0; |
4356 | | /* something really bad happened in the SAX callback */ |
4357 | 157k | if (ctxt->instate != XML_PARSER_CONTENT) |
4358 | 0 | return; |
4359 | 157k | SHRINK; |
4360 | 157k | } |
4361 | 23.3M | cur = CUR_CHAR(l); |
4362 | 23.3M | } |
4363 | 117k | if (ctxt->instate == XML_PARSER_EOF) |
4364 | 9 | return; |
4365 | 117k | if (nbchar != 0) { |
4366 | 47.2k | buf[nbchar] = 0; |
4367 | | /* |
4368 | | * OK the segment is to be consumed as chars. |
4369 | | */ |
4370 | 47.2k | if ((ctxt->sax != NULL) && (!ctxt->disableSAX)) { |
4371 | 47.2k | if (areBlanks(ctxt, buf, nbchar, 0)) { |
4372 | 0 | if (ctxt->sax->ignorableWhitespace != NULL) |
4373 | 0 | ctxt->sax->ignorableWhitespace(ctxt->userData, buf, nbchar); |
4374 | 47.2k | } else { |
4375 | 47.2k | if (ctxt->sax->characters != NULL) |
4376 | 47.2k | ctxt->sax->characters(ctxt->userData, buf, nbchar); |
4377 | 47.2k | if ((ctxt->sax->characters != ctxt->sax->ignorableWhitespace) && |
4378 | 47.2k | (*ctxt->space == -1)) |
4379 | 0 | *ctxt->space = -2; |
4380 | 47.2k | } |
4381 | 47.2k | } |
4382 | 47.2k | } |
4383 | | /* |
4384 | | * cur == 0 can mean |
4385 | | * |
4386 | | * - XML_PARSER_EOF or memory error. This is checked above. |
4387 | | * - An actual 0 character. |
4388 | | * - End of buffer. |
4389 | | * - An incomplete UTF-8 sequence. This is allowed if partial is set. |
4390 | | */ |
4391 | 117k | if (ctxt->input->cur < ctxt->input->end) { |
4392 | 117k | if ((cur == 0) && (CUR != 0)) { |
4393 | 0 | if (partial == 0) { |
4394 | 0 | xmlFatalErrMsgInt(ctxt, XML_ERR_INVALID_CHAR, |
4395 | 0 | "Incomplete UTF-8 sequence starting with %02X\n", CUR); |
4396 | 0 | NEXTL(1); |
4397 | 0 | } |
4398 | 117k | } else if ((cur != '<') && (cur != '&')) { |
4399 | | /* Generate the error and skip the offending character */ |
4400 | 85.1k | xmlFatalErrMsgInt(ctxt, XML_ERR_INVALID_CHAR, |
4401 | 85.1k | "PCDATA invalid Char value %d\n", cur); |
4402 | 85.1k | NEXTL(l); |
4403 | 85.1k | } |
4404 | 117k | } |
4405 | 117k | } |
4406 | | |
4407 | | /** |
4408 | | * xmlParseCharData: |
4409 | | * @ctxt: an XML parser context |
4410 | | * @cdata: unused |
4411 | | * |
4412 | | * DEPRECATED: Internal function, don't use. |
4413 | | */ |
4414 | | void |
4415 | 0 | xmlParseCharData(xmlParserCtxtPtr ctxt, ATTRIBUTE_UNUSED int cdata) { |
4416 | 0 | xmlParseCharDataInternal(ctxt, 0); |
4417 | 0 | } |
4418 | | |
4419 | | /** |
4420 | | * xmlParseExternalID: |
4421 | | * @ctxt: an XML parser context |
4422 | | * @publicID: a xmlChar** receiving PubidLiteral |
4423 | | * @strict: indicate whether we should restrict parsing to only |
4424 | | * production [75], see NOTE below |
4425 | | * |
4426 | | * DEPRECATED: Internal function, don't use. |
4427 | | * |
4428 | | * Parse an External ID or a Public ID |
4429 | | * |
4430 | | * NOTE: Productions [75] and [83] interact badly since [75] can generate |
4431 | | * 'PUBLIC' S PubidLiteral S SystemLiteral |
4432 | | * |
4433 | | * [75] ExternalID ::= 'SYSTEM' S SystemLiteral |
4434 | | * | 'PUBLIC' S PubidLiteral S SystemLiteral |
4435 | | * |
4436 | | * [83] PublicID ::= 'PUBLIC' S PubidLiteral |
4437 | | * |
4438 | | * Returns the function returns SystemLiteral and in the second |
4439 | | * case publicID receives PubidLiteral, is strict is off |
4440 | | * it is possible to return NULL and have publicID set. |
4441 | | */ |
4442 | | |
4443 | | xmlChar * |
4444 | 4.10k | xmlParseExternalID(xmlParserCtxtPtr ctxt, xmlChar **publicID, int strict) { |
4445 | 4.10k | xmlChar *URI = NULL; |
4446 | | |
4447 | 4.10k | *publicID = NULL; |
4448 | 4.10k | if (CMP6(CUR_PTR, 'S', 'Y', 'S', 'T', 'E', 'M')) { |
4449 | 0 | SKIP(6); |
4450 | 0 | if (SKIP_BLANKS == 0) { |
4451 | 0 | xmlFatalErrMsg(ctxt, XML_ERR_SPACE_REQUIRED, |
4452 | 0 | "Space required after 'SYSTEM'\n"); |
4453 | 0 | } |
4454 | 0 | URI = xmlParseSystemLiteral(ctxt); |
4455 | 0 | if (URI == NULL) { |
4456 | 0 | xmlFatalErr(ctxt, XML_ERR_URI_REQUIRED, NULL); |
4457 | 0 | } |
4458 | 4.10k | } else if (CMP6(CUR_PTR, 'P', 'U', 'B', 'L', 'I', 'C')) { |
4459 | 4.02k | SKIP(6); |
4460 | 4.02k | if (SKIP_BLANKS == 0) { |
4461 | 0 | xmlFatalErrMsg(ctxt, XML_ERR_SPACE_REQUIRED, |
4462 | 0 | "Space required after 'PUBLIC'\n"); |
4463 | 0 | } |
4464 | 4.02k | *publicID = xmlParsePubidLiteral(ctxt); |
4465 | 4.02k | if (*publicID == NULL) { |
4466 | 2 | xmlFatalErr(ctxt, XML_ERR_PUBID_REQUIRED, NULL); |
4467 | 2 | } |
4468 | 4.02k | if (strict) { |
4469 | | /* |
4470 | | * We don't handle [83] so "S SystemLiteral" is required. |
4471 | | */ |
4472 | 4.02k | if (SKIP_BLANKS == 0) { |
4473 | 57 | xmlFatalErrMsg(ctxt, XML_ERR_SPACE_REQUIRED, |
4474 | 57 | "Space required after the Public Identifier\n"); |
4475 | 57 | } |
4476 | 4.02k | } else { |
4477 | | /* |
4478 | | * We handle [83] so we return immediately, if |
4479 | | * "S SystemLiteral" is not detected. We skip blanks if no |
4480 | | * system literal was found, but this is harmless since we must |
4481 | | * be at the end of a NotationDecl. |
4482 | | */ |
4483 | 0 | if (SKIP_BLANKS == 0) return(NULL); |
4484 | 0 | if ((CUR != '\'') && (CUR != '"')) return(NULL); |
4485 | 0 | } |
4486 | 4.02k | URI = xmlParseSystemLiteral(ctxt); |
4487 | 4.02k | if (URI == NULL) { |
4488 | 57 | xmlFatalErr(ctxt, XML_ERR_URI_REQUIRED, NULL); |
4489 | 57 | } |
4490 | 4.02k | } |
4491 | 4.10k | return(URI); |
4492 | 4.10k | } |
4493 | | |
4494 | | /** |
4495 | | * xmlParseCommentComplex: |
4496 | | * @ctxt: an XML parser context |
4497 | | * @buf: the already parsed part of the buffer |
4498 | | * @len: number of bytes in the buffer |
4499 | | * @size: allocated size of the buffer |
4500 | | * |
4501 | | * Skip an XML (SGML) comment <!-- .... --> |
4502 | | * The spec says that "For compatibility, the string "--" (double-hyphen) |
4503 | | * must not occur within comments. " |
4504 | | * This is the slow routine in case the accelerator for ascii didn't work |
4505 | | * |
4506 | | * [15] Comment ::= '<!--' ((Char - '-') | ('-' (Char - '-')))* '-->' |
4507 | | */ |
4508 | | static void |
4509 | | xmlParseCommentComplex(xmlParserCtxtPtr ctxt, xmlChar *buf, |
4510 | 377 | size_t len, size_t size) { |
4511 | 377 | int q, ql; |
4512 | 377 | int r, rl; |
4513 | 377 | int cur, l; |
4514 | 377 | size_t maxLength = (ctxt->options & XML_PARSE_HUGE) ? |
4515 | 0 | XML_MAX_HUGE_LENGTH : |
4516 | 377 | XML_MAX_TEXT_LENGTH; |
4517 | 377 | int inputid; |
4518 | | |
4519 | 377 | inputid = ctxt->input->id; |
4520 | | |
4521 | 377 | if (buf == NULL) { |
4522 | 90 | len = 0; |
4523 | 90 | size = XML_PARSER_BUFFER_SIZE; |
4524 | 90 | buf = (xmlChar *) xmlMallocAtomic(size); |
4525 | 90 | if (buf == NULL) { |
4526 | 0 | xmlErrMemory(ctxt, NULL); |
4527 | 0 | return; |
4528 | 0 | } |
4529 | 90 | } |
4530 | 377 | q = CUR_CHAR(ql); |
4531 | 377 | if (q == 0) |
4532 | 2 | goto not_terminated; |
4533 | 375 | if (!IS_CHAR(q)) { |
4534 | 73 | xmlFatalErrMsgInt(ctxt, XML_ERR_INVALID_CHAR, |
4535 | 73 | "xmlParseComment: invalid xmlChar value %d\n", |
4536 | 73 | q); |
4537 | 73 | xmlFree (buf); |
4538 | 73 | return; |
4539 | 73 | } |
4540 | 302 | NEXTL(ql); |
4541 | 302 | r = CUR_CHAR(rl); |
4542 | 302 | if (r == 0) |
4543 | 0 | goto not_terminated; |
4544 | 302 | if (!IS_CHAR(r)) { |
4545 | 0 | xmlFatalErrMsgInt(ctxt, XML_ERR_INVALID_CHAR, |
4546 | 0 | "xmlParseComment: invalid xmlChar value %d\n", |
4547 | 0 | r); |
4548 | 0 | xmlFree (buf); |
4549 | 0 | return; |
4550 | 0 | } |
4551 | 302 | NEXTL(rl); |
4552 | 302 | cur = CUR_CHAR(l); |
4553 | 302 | if (cur == 0) |
4554 | 1 | goto not_terminated; |
4555 | 590k | while (IS_CHAR(cur) && /* checked */ |
4556 | 590k | ((cur != '>') || |
4557 | 590k | (r != '-') || (q != '-'))) { |
4558 | 589k | if ((r == '-') && (q == '-')) { |
4559 | 290 | xmlFatalErr(ctxt, XML_ERR_HYPHEN_IN_COMMENT, NULL); |
4560 | 290 | } |
4561 | 589k | if (len + 5 >= size) { |
4562 | 336 | xmlChar *new_buf; |
4563 | 336 | size_t new_size; |
4564 | | |
4565 | 336 | new_size = size * 2; |
4566 | 336 | new_buf = (xmlChar *) xmlRealloc(buf, new_size); |
4567 | 336 | if (new_buf == NULL) { |
4568 | 0 | xmlFree (buf); |
4569 | 0 | xmlErrMemory(ctxt, NULL); |
4570 | 0 | return; |
4571 | 0 | } |
4572 | 336 | buf = new_buf; |
4573 | 336 | size = new_size; |
4574 | 336 | } |
4575 | 589k | COPY_BUF(ql,buf,len,q); |
4576 | 589k | if (len > maxLength) { |
4577 | 0 | xmlFatalErrMsgStr(ctxt, XML_ERR_COMMENT_NOT_FINISHED, |
4578 | 0 | "Comment too big found", NULL); |
4579 | 0 | xmlFree (buf); |
4580 | 0 | return; |
4581 | 0 | } |
4582 | | |
4583 | 589k | q = r; |
4584 | 589k | ql = rl; |
4585 | 589k | r = cur; |
4586 | 589k | rl = l; |
4587 | | |
4588 | 589k | NEXTL(l); |
4589 | 589k | cur = CUR_CHAR(l); |
4590 | | |
4591 | 589k | } |
4592 | 301 | buf[len] = 0; |
4593 | 301 | if (ctxt->instate == XML_PARSER_EOF) { |
4594 | 0 | xmlFree(buf); |
4595 | 0 | return; |
4596 | 0 | } |
4597 | 301 | if (cur == 0) { |
4598 | 4 | xmlFatalErrMsgStr(ctxt, XML_ERR_COMMENT_NOT_FINISHED, |
4599 | 4 | "Comment not terminated \n<!--%.50s\n", buf); |
4600 | 297 | } else if (!IS_CHAR(cur)) { |
4601 | 154 | xmlFatalErrMsgInt(ctxt, XML_ERR_INVALID_CHAR, |
4602 | 154 | "xmlParseComment: invalid xmlChar value %d\n", |
4603 | 154 | cur); |
4604 | 154 | } else { |
4605 | 143 | if (inputid != ctxt->input->id) { |
4606 | 0 | xmlFatalErrMsg(ctxt, XML_ERR_ENTITY_BOUNDARY, |
4607 | 0 | "Comment doesn't start and stop in the same" |
4608 | 0 | " entity\n"); |
4609 | 0 | } |
4610 | 143 | NEXT; |
4611 | 143 | if ((ctxt->sax != NULL) && (ctxt->sax->comment != NULL) && |
4612 | 143 | (!ctxt->disableSAX)) |
4613 | 143 | ctxt->sax->comment(ctxt->userData, buf); |
4614 | 143 | } |
4615 | 301 | xmlFree(buf); |
4616 | 301 | return; |
4617 | 3 | not_terminated: |
4618 | 3 | xmlFatalErrMsgStr(ctxt, XML_ERR_COMMENT_NOT_FINISHED, |
4619 | 3 | "Comment not terminated\n", NULL); |
4620 | 3 | xmlFree(buf); |
4621 | 3 | return; |
4622 | 301 | } |
4623 | | |
4624 | | /** |
4625 | | * xmlParseComment: |
4626 | | * @ctxt: an XML parser context |
4627 | | * |
4628 | | * DEPRECATED: Internal function, don't use. |
4629 | | * |
4630 | | * Parse an XML (SGML) comment. Always consumes '<!'. |
4631 | | * |
4632 | | * The spec says that "For compatibility, the string "--" (double-hyphen) |
4633 | | * must not occur within comments. " |
4634 | | * |
4635 | | * [15] Comment ::= '<!--' ((Char - '-') | ('-' (Char - '-')))* '-->' |
4636 | | */ |
4637 | | void |
4638 | 1.09k | xmlParseComment(xmlParserCtxtPtr ctxt) { |
4639 | 1.09k | xmlChar *buf = NULL; |
4640 | 1.09k | size_t size = XML_PARSER_BUFFER_SIZE; |
4641 | 1.09k | size_t len = 0; |
4642 | 1.09k | size_t maxLength = (ctxt->options & XML_PARSE_HUGE) ? |
4643 | 0 | XML_MAX_HUGE_LENGTH : |
4644 | 1.09k | XML_MAX_TEXT_LENGTH; |
4645 | 1.09k | xmlParserInputState state; |
4646 | 1.09k | const xmlChar *in; |
4647 | 1.09k | size_t nbchar = 0; |
4648 | 1.09k | int ccol; |
4649 | 1.09k | int inputid; |
4650 | | |
4651 | | /* |
4652 | | * Check that there is a comment right here. |
4653 | | */ |
4654 | 1.09k | if ((RAW != '<') || (NXT(1) != '!')) |
4655 | 0 | return; |
4656 | 1.09k | SKIP(2); |
4657 | 1.09k | if ((RAW != '-') || (NXT(1) != '-')) |
4658 | 0 | return; |
4659 | 1.09k | state = ctxt->instate; |
4660 | 1.09k | ctxt->instate = XML_PARSER_COMMENT; |
4661 | 1.09k | inputid = ctxt->input->id; |
4662 | 1.09k | SKIP(2); |
4663 | 1.09k | GROW; |
4664 | | |
4665 | | /* |
4666 | | * Accelerated common case where input don't need to be |
4667 | | * modified before passing it to the handler. |
4668 | | */ |
4669 | 1.09k | in = ctxt->input->cur; |
4670 | 1.09k | do { |
4671 | 1.09k | if (*in == 0xA) { |
4672 | 24 | do { |
4673 | 24 | ctxt->input->line++; ctxt->input->col = 1; |
4674 | 24 | in++; |
4675 | 24 | } while (*in == 0xA); |
4676 | 1 | } |
4677 | 1.57k | get_more: |
4678 | 1.57k | ccol = ctxt->input->col; |
4679 | 374k | while (((*in > '-') && (*in <= 0x7F)) || |
4680 | 374k | ((*in >= 0x20) && (*in < '-')) || |
4681 | 374k | (*in == 0x09)) { |
4682 | 372k | in++; |
4683 | 372k | ccol++; |
4684 | 372k | } |
4685 | 1.57k | ctxt->input->col = ccol; |
4686 | 1.57k | if (*in == 0xA) { |
4687 | 10.8k | do { |
4688 | 10.8k | ctxt->input->line++; ctxt->input->col = 1; |
4689 | 10.8k | in++; |
4690 | 10.8k | } while (*in == 0xA); |
4691 | 242 | goto get_more; |
4692 | 242 | } |
4693 | 1.32k | nbchar = in - ctxt->input->cur; |
4694 | | /* |
4695 | | * save current set of data |
4696 | | */ |
4697 | 1.32k | if (nbchar > 0) { |
4698 | 1.19k | if ((ctxt->sax != NULL) && |
4699 | 1.19k | (ctxt->sax->comment != NULL)) { |
4700 | 1.19k | if (buf == NULL) { |
4701 | 971 | if ((*in == '-') && (in[1] == '-')) |
4702 | 640 | size = nbchar + 1; |
4703 | 331 | else |
4704 | 331 | size = XML_PARSER_BUFFER_SIZE + nbchar; |
4705 | 971 | buf = (xmlChar *) xmlMallocAtomic(size); |
4706 | 971 | if (buf == NULL) { |
4707 | 0 | xmlErrMemory(ctxt, NULL); |
4708 | 0 | ctxt->instate = state; |
4709 | 0 | return; |
4710 | 0 | } |
4711 | 971 | len = 0; |
4712 | 971 | } else if (len + nbchar + 1 >= size) { |
4713 | 80 | xmlChar *new_buf; |
4714 | 80 | size += len + nbchar + XML_PARSER_BUFFER_SIZE; |
4715 | 80 | new_buf = (xmlChar *) xmlRealloc(buf, size); |
4716 | 80 | if (new_buf == NULL) { |
4717 | 0 | xmlFree (buf); |
4718 | 0 | xmlErrMemory(ctxt, NULL); |
4719 | 0 | ctxt->instate = state; |
4720 | 0 | return; |
4721 | 0 | } |
4722 | 80 | buf = new_buf; |
4723 | 80 | } |
4724 | 1.19k | memcpy(&buf[len], ctxt->input->cur, nbchar); |
4725 | 1.19k | len += nbchar; |
4726 | 1.19k | buf[len] = 0; |
4727 | 1.19k | } |
4728 | 1.19k | } |
4729 | 1.32k | if (len > maxLength) { |
4730 | 0 | xmlFatalErrMsgStr(ctxt, XML_ERR_COMMENT_NOT_FINISHED, |
4731 | 0 | "Comment too big found", NULL); |
4732 | 0 | xmlFree (buf); |
4733 | 0 | return; |
4734 | 0 | } |
4735 | 1.32k | ctxt->input->cur = in; |
4736 | 1.32k | if (*in == 0xA) { |
4737 | 0 | in++; |
4738 | 0 | ctxt->input->line++; ctxt->input->col = 1; |
4739 | 0 | } |
4740 | 1.32k | if (*in == 0xD) { |
4741 | 0 | in++; |
4742 | 0 | if (*in == 0xA) { |
4743 | 0 | ctxt->input->cur = in; |
4744 | 0 | in++; |
4745 | 0 | ctxt->input->line++; ctxt->input->col = 1; |
4746 | 0 | goto get_more; |
4747 | 0 | } |
4748 | 0 | in--; |
4749 | 0 | } |
4750 | 1.32k | SHRINK; |
4751 | 1.32k | GROW; |
4752 | 1.32k | if (ctxt->instate == XML_PARSER_EOF) { |
4753 | 0 | xmlFree(buf); |
4754 | 0 | return; |
4755 | 0 | } |
4756 | 1.32k | in = ctxt->input->cur; |
4757 | 1.32k | if (*in == '-') { |
4758 | 951 | if (in[1] == '-') { |
4759 | 829 | if (in[2] == '>') { |
4760 | 716 | if (ctxt->input->id != inputid) { |
4761 | 0 | xmlFatalErrMsg(ctxt, XML_ERR_ENTITY_BOUNDARY, |
4762 | 0 | "comment doesn't start and stop in the" |
4763 | 0 | " same entity\n"); |
4764 | 0 | } |
4765 | 716 | SKIP(3); |
4766 | 716 | if ((ctxt->sax != NULL) && (ctxt->sax->comment != NULL) && |
4767 | 716 | (!ctxt->disableSAX)) { |
4768 | 668 | if (buf != NULL) |
4769 | 664 | ctxt->sax->comment(ctxt->userData, buf); |
4770 | 4 | else |
4771 | 4 | ctxt->sax->comment(ctxt->userData, BAD_CAST ""); |
4772 | 668 | } |
4773 | 716 | if (buf != NULL) |
4774 | 684 | xmlFree(buf); |
4775 | 716 | if (ctxt->instate != XML_PARSER_EOF) |
4776 | 716 | ctxt->instate = state; |
4777 | 716 | return; |
4778 | 716 | } |
4779 | 113 | if (buf != NULL) { |
4780 | 107 | xmlFatalErrMsgStr(ctxt, XML_ERR_HYPHEN_IN_COMMENT, |
4781 | 107 | "Double hyphen within comment: " |
4782 | 107 | "<!--%.50s\n", |
4783 | 107 | buf); |
4784 | 107 | } else |
4785 | 6 | xmlFatalErrMsgStr(ctxt, XML_ERR_HYPHEN_IN_COMMENT, |
4786 | 6 | "Double hyphen within comment\n", NULL); |
4787 | 113 | if (ctxt->instate == XML_PARSER_EOF) { |
4788 | 0 | xmlFree(buf); |
4789 | 0 | return; |
4790 | 0 | } |
4791 | 113 | in++; |
4792 | 113 | ctxt->input->col++; |
4793 | 113 | } |
4794 | 235 | in++; |
4795 | 235 | ctxt->input->col++; |
4796 | 235 | goto get_more; |
4797 | 951 | } |
4798 | 1.32k | } while (((*in >= 0x20) && (*in <= 0x7F)) || (*in == 0x09) || (*in == 0x0a)); |
4799 | 377 | xmlParseCommentComplex(ctxt, buf, len, size); |
4800 | 377 | ctxt->instate = state; |
4801 | 377 | return; |
4802 | 1.09k | } |
4803 | | |
4804 | | |
4805 | | /** |
4806 | | * xmlParsePITarget: |
4807 | | * @ctxt: an XML parser context |
4808 | | * |
4809 | | * DEPRECATED: Internal function, don't use. |
4810 | | * |
4811 | | * parse the name of a PI |
4812 | | * |
4813 | | * [17] PITarget ::= Name - (('X' | 'x') ('M' | 'm') ('L' | 'l')) |
4814 | | * |
4815 | | * Returns the PITarget name or NULL |
4816 | | */ |
4817 | | |
4818 | | const xmlChar * |
4819 | 9.13k | xmlParsePITarget(xmlParserCtxtPtr ctxt) { |
4820 | 9.13k | const xmlChar *name; |
4821 | | |
4822 | 9.13k | name = xmlParseName(ctxt); |
4823 | 9.13k | if ((name != NULL) && |
4824 | 9.13k | ((name[0] == 'x') || (name[0] == 'X')) && |
4825 | 9.13k | ((name[1] == 'm') || (name[1] == 'M')) && |
4826 | 9.13k | ((name[2] == 'l') || (name[2] == 'L'))) { |
4827 | 4.97k | int i; |
4828 | 4.97k | if ((name[0] == 'x') && (name[1] == 'm') && |
4829 | 4.97k | (name[2] == 'l') && (name[3] == 0)) { |
4830 | 2.55k | xmlFatalErrMsg(ctxt, XML_ERR_RESERVED_XML_NAME, |
4831 | 2.55k | "XML declaration allowed only at the start of the document\n"); |
4832 | 2.55k | return(name); |
4833 | 2.55k | } else if (name[3] == 0) { |
4834 | 1.40k | xmlFatalErr(ctxt, XML_ERR_RESERVED_XML_NAME, NULL); |
4835 | 1.40k | return(name); |
4836 | 1.40k | } |
4837 | 3.05k | for (i = 0;;i++) { |
4838 | 3.05k | if (xmlW3CPIs[i] == NULL) break; |
4839 | 2.03k | if (xmlStrEqual(name, (const xmlChar *)xmlW3CPIs[i])) |
4840 | 0 | return(name); |
4841 | 2.03k | } |
4842 | 1.01k | xmlWarningMsg(ctxt, XML_ERR_RESERVED_XML_NAME, |
4843 | 1.01k | "xmlParsePITarget: invalid name prefix 'xml'\n", |
4844 | 1.01k | NULL, NULL); |
4845 | 1.01k | } |
4846 | 5.17k | if ((name != NULL) && (xmlStrchr(name, ':') != NULL)) { |
4847 | 751 | xmlNsErr(ctxt, XML_NS_ERR_COLON, |
4848 | 751 | "colons are forbidden from PI names '%s'\n", name, NULL, NULL); |
4849 | 751 | } |
4850 | 5.17k | return(name); |
4851 | 9.13k | } |
4852 | | |
4853 | | #ifdef LIBXML_CATALOG_ENABLED |
4854 | | /** |
4855 | | * xmlParseCatalogPI: |
4856 | | * @ctxt: an XML parser context |
4857 | | * @catalog: the PI value string |
4858 | | * |
4859 | | * parse an XML Catalog Processing Instruction. |
4860 | | * |
4861 | | * <?oasis-xml-catalog catalog="http://example.com/catalog.xml"?> |
4862 | | * |
4863 | | * Occurs only if allowed by the user and if happening in the Misc |
4864 | | * part of the document before any doctype information |
4865 | | * This will add the given catalog to the parsing context in order |
4866 | | * to be used if there is a resolution need further down in the document |
4867 | | */ |
4868 | | |
4869 | | static void |
4870 | 9 | xmlParseCatalogPI(xmlParserCtxtPtr ctxt, const xmlChar *catalog) { |
4871 | 9 | xmlChar *URL = NULL; |
4872 | 9 | const xmlChar *tmp, *base; |
4873 | 9 | xmlChar marker; |
4874 | | |
4875 | 9 | tmp = catalog; |
4876 | 9 | while (IS_BLANK_CH(*tmp)) tmp++; |
4877 | 9 | if (xmlStrncmp(tmp, BAD_CAST"catalog", 7)) |
4878 | 2 | goto error; |
4879 | 7 | tmp += 7; |
4880 | 7 | while (IS_BLANK_CH(*tmp)) tmp++; |
4881 | 7 | if (*tmp != '=') { |
4882 | 0 | return; |
4883 | 0 | } |
4884 | 7 | tmp++; |
4885 | 7 | while (IS_BLANK_CH(*tmp)) tmp++; |
4886 | 7 | marker = *tmp; |
4887 | 7 | if ((marker != '\'') && (marker != '"')) |
4888 | 0 | goto error; |
4889 | 7 | tmp++; |
4890 | 7 | base = tmp; |
4891 | 514 | while ((*tmp != 0) && (*tmp != marker)) tmp++; |
4892 | 7 | if (*tmp == 0) |
4893 | 0 | goto error; |
4894 | 7 | URL = xmlStrndup(base, tmp - base); |
4895 | 7 | tmp++; |
4896 | 7 | while (IS_BLANK_CH(*tmp)) tmp++; |
4897 | 7 | if (*tmp != 0) |
4898 | 7 | goto error; |
4899 | | |
4900 | 0 | if (URL != NULL) { |
4901 | 0 | ctxt->catalogs = xmlCatalogAddLocal(ctxt->catalogs, URL); |
4902 | 0 | xmlFree(URL); |
4903 | 0 | } |
4904 | 0 | return; |
4905 | | |
4906 | 9 | error: |
4907 | 9 | xmlWarningMsg(ctxt, XML_WAR_CATALOG_PI, |
4908 | 9 | "Catalog PI syntax error: %s\n", |
4909 | 9 | catalog, NULL); |
4910 | 9 | if (URL != NULL) |
4911 | 7 | xmlFree(URL); |
4912 | 9 | } |
4913 | | #endif |
4914 | | |
4915 | | /** |
4916 | | * xmlParsePI: |
4917 | | * @ctxt: an XML parser context |
4918 | | * |
4919 | | * DEPRECATED: Internal function, don't use. |
4920 | | * |
4921 | | * parse an XML Processing Instruction. |
4922 | | * |
4923 | | * [16] PI ::= '<?' PITarget (S (Char* - (Char* '?>' Char*)))? '?>' |
4924 | | * |
4925 | | * The processing is transferred to SAX once parsed. |
4926 | | */ |
4927 | | |
4928 | | void |
4929 | 9.13k | xmlParsePI(xmlParserCtxtPtr ctxt) { |
4930 | 9.13k | xmlChar *buf = NULL; |
4931 | 9.13k | size_t len = 0; |
4932 | 9.13k | size_t size = XML_PARSER_BUFFER_SIZE; |
4933 | 9.13k | size_t maxLength = (ctxt->options & XML_PARSE_HUGE) ? |
4934 | 0 | XML_MAX_HUGE_LENGTH : |
4935 | 9.13k | XML_MAX_TEXT_LENGTH; |
4936 | 9.13k | int cur, l; |
4937 | 9.13k | const xmlChar *target; |
4938 | 9.13k | xmlParserInputState state; |
4939 | | |
4940 | 9.13k | if ((RAW == '<') && (NXT(1) == '?')) { |
4941 | 9.13k | int inputid = ctxt->input->id; |
4942 | 9.13k | state = ctxt->instate; |
4943 | 9.13k | ctxt->instate = XML_PARSER_PI; |
4944 | | /* |
4945 | | * this is a Processing Instruction. |
4946 | | */ |
4947 | 9.13k | SKIP(2); |
4948 | | |
4949 | | /* |
4950 | | * Parse the target name and check for special support like |
4951 | | * namespace. |
4952 | | */ |
4953 | 9.13k | target = xmlParsePITarget(ctxt); |
4954 | 9.13k | if (target != NULL) { |
4955 | 8.61k | if ((RAW == '?') && (NXT(1) == '>')) { |
4956 | 960 | if (inputid != ctxt->input->id) { |
4957 | 0 | xmlFatalErrMsg(ctxt, XML_ERR_ENTITY_BOUNDARY, |
4958 | 0 | "PI declaration doesn't start and stop in" |
4959 | 0 | " the same entity\n"); |
4960 | 0 | } |
4961 | 960 | SKIP(2); |
4962 | | |
4963 | | /* |
4964 | | * SAX: PI detected. |
4965 | | */ |
4966 | 960 | if ((ctxt->sax) && (!ctxt->disableSAX) && |
4967 | 960 | (ctxt->sax->processingInstruction != NULL)) |
4968 | 501 | ctxt->sax->processingInstruction(ctxt->userData, |
4969 | 501 | target, NULL); |
4970 | 960 | if (ctxt->instate != XML_PARSER_EOF) |
4971 | 960 | ctxt->instate = state; |
4972 | 960 | return; |
4973 | 960 | } |
4974 | 7.65k | buf = (xmlChar *) xmlMallocAtomic(size); |
4975 | 7.65k | if (buf == NULL) { |
4976 | 0 | xmlErrMemory(ctxt, NULL); |
4977 | 0 | ctxt->instate = state; |
4978 | 0 | return; |
4979 | 0 | } |
4980 | 7.65k | if (SKIP_BLANKS == 0) { |
4981 | 5.44k | xmlFatalErrMsgStr(ctxt, XML_ERR_SPACE_REQUIRED, |
4982 | 5.44k | "ParsePI: PI %s space expected\n", target); |
4983 | 5.44k | } |
4984 | 7.65k | cur = CUR_CHAR(l); |
4985 | 1.00M | while (IS_CHAR(cur) && /* checked */ |
4986 | 1.00M | ((cur != '?') || (NXT(1) != '>'))) { |
4987 | 998k | if (len + 5 >= size) { |
4988 | 1.47k | xmlChar *tmp; |
4989 | 1.47k | size_t new_size = size * 2; |
4990 | 1.47k | tmp = (xmlChar *) xmlRealloc(buf, new_size); |
4991 | 1.47k | if (tmp == NULL) { |
4992 | 0 | xmlErrMemory(ctxt, NULL); |
4993 | 0 | xmlFree(buf); |
4994 | 0 | ctxt->instate = state; |
4995 | 0 | return; |
4996 | 0 | } |
4997 | 1.47k | buf = tmp; |
4998 | 1.47k | size = new_size; |
4999 | 1.47k | } |
5000 | 998k | COPY_BUF(l,buf,len,cur); |
5001 | 998k | if (len > maxLength) { |
5002 | 0 | xmlFatalErrMsgStr(ctxt, XML_ERR_PI_NOT_FINISHED, |
5003 | 0 | "PI %s too big found", target); |
5004 | 0 | xmlFree(buf); |
5005 | 0 | ctxt->instate = state; |
5006 | 0 | return; |
5007 | 0 | } |
5008 | 998k | NEXTL(l); |
5009 | 998k | cur = CUR_CHAR(l); |
5010 | 998k | } |
5011 | 7.65k | buf[len] = 0; |
5012 | 7.65k | if (ctxt->instate == XML_PARSER_EOF) { |
5013 | 0 | xmlFree(buf); |
5014 | 0 | return; |
5015 | 0 | } |
5016 | 7.65k | if (cur != '?') { |
5017 | 4.14k | xmlFatalErrMsgStr(ctxt, XML_ERR_PI_NOT_FINISHED, |
5018 | 4.14k | "ParsePI: PI %s never end ...\n", target); |
5019 | 4.14k | } else { |
5020 | 3.51k | if (inputid != ctxt->input->id) { |
5021 | 0 | xmlFatalErrMsg(ctxt, XML_ERR_ENTITY_BOUNDARY, |
5022 | 0 | "PI declaration doesn't start and stop in" |
5023 | 0 | " the same entity\n"); |
5024 | 0 | } |
5025 | 3.51k | SKIP(2); |
5026 | | |
5027 | 3.51k | #ifdef LIBXML_CATALOG_ENABLED |
5028 | 3.51k | if (((state == XML_PARSER_MISC) || |
5029 | 3.51k | (state == XML_PARSER_START)) && |
5030 | 3.51k | (xmlStrEqual(target, XML_CATALOG_PI))) { |
5031 | 9 | xmlCatalogAllow allow = xmlCatalogGetDefaults(); |
5032 | 9 | if ((allow == XML_CATA_ALLOW_DOCUMENT) || |
5033 | 9 | (allow == XML_CATA_ALLOW_ALL)) |
5034 | 9 | xmlParseCatalogPI(ctxt, buf); |
5035 | 9 | } |
5036 | 3.51k | #endif |
5037 | | |
5038 | | |
5039 | | /* |
5040 | | * SAX: PI detected. |
5041 | | */ |
5042 | 3.51k | if ((ctxt->sax) && (!ctxt->disableSAX) && |
5043 | 3.51k | (ctxt->sax->processingInstruction != NULL)) |
5044 | 1.15k | ctxt->sax->processingInstruction(ctxt->userData, |
5045 | 1.15k | target, buf); |
5046 | 3.51k | } |
5047 | 7.65k | xmlFree(buf); |
5048 | 7.65k | } else { |
5049 | 512 | xmlFatalErr(ctxt, XML_ERR_PI_NOT_STARTED, NULL); |
5050 | 512 | } |
5051 | 8.17k | if (ctxt->instate != XML_PARSER_EOF) |
5052 | 8.16k | ctxt->instate = state; |
5053 | 8.17k | } |
5054 | 9.13k | } |
5055 | | |
5056 | | /** |
5057 | | * xmlParseNotationDecl: |
5058 | | * @ctxt: an XML parser context |
5059 | | * |
5060 | | * DEPRECATED: Internal function, don't use. |
5061 | | * |
5062 | | * Parse a notation declaration. Always consumes '<!'. |
5063 | | * |
5064 | | * [82] NotationDecl ::= '<!NOTATION' S Name S (ExternalID | PublicID) S? '>' |
5065 | | * |
5066 | | * Hence there is actually 3 choices: |
5067 | | * 'PUBLIC' S PubidLiteral |
5068 | | * 'PUBLIC' S PubidLiteral S SystemLiteral |
5069 | | * and 'SYSTEM' S SystemLiteral |
5070 | | * |
5071 | | * See the NOTE on xmlParseExternalID(). |
5072 | | */ |
5073 | | |
5074 | | void |
5075 | 0 | xmlParseNotationDecl(xmlParserCtxtPtr ctxt) { |
5076 | 0 | const xmlChar *name; |
5077 | 0 | xmlChar *Pubid; |
5078 | 0 | xmlChar *Systemid; |
5079 | |
|
5080 | 0 | if ((CUR != '<') || (NXT(1) != '!')) |
5081 | 0 | return; |
5082 | 0 | SKIP(2); |
5083 | |
|
5084 | 0 | if (CMP8(CUR_PTR, 'N', 'O', 'T', 'A', 'T', 'I', 'O', 'N')) { |
5085 | 0 | int inputid = ctxt->input->id; |
5086 | 0 | SKIP(8); |
5087 | 0 | if (SKIP_BLANKS == 0) { |
5088 | 0 | xmlFatalErrMsg(ctxt, XML_ERR_SPACE_REQUIRED, |
5089 | 0 | "Space required after '<!NOTATION'\n"); |
5090 | 0 | return; |
5091 | 0 | } |
5092 | | |
5093 | 0 | name = xmlParseName(ctxt); |
5094 | 0 | if (name == NULL) { |
5095 | 0 | xmlFatalErr(ctxt, XML_ERR_NOTATION_NOT_STARTED, NULL); |
5096 | 0 | return; |
5097 | 0 | } |
5098 | 0 | if (xmlStrchr(name, ':') != NULL) { |
5099 | 0 | xmlNsErr(ctxt, XML_NS_ERR_COLON, |
5100 | 0 | "colons are forbidden from notation names '%s'\n", |
5101 | 0 | name, NULL, NULL); |
5102 | 0 | } |
5103 | 0 | if (SKIP_BLANKS == 0) { |
5104 | 0 | xmlFatalErrMsg(ctxt, XML_ERR_SPACE_REQUIRED, |
5105 | 0 | "Space required after the NOTATION name'\n"); |
5106 | 0 | return; |
5107 | 0 | } |
5108 | | |
5109 | | /* |
5110 | | * Parse the IDs. |
5111 | | */ |
5112 | 0 | Systemid = xmlParseExternalID(ctxt, &Pubid, 0); |
5113 | 0 | SKIP_BLANKS; |
5114 | |
|
5115 | 0 | if (RAW == '>') { |
5116 | 0 | if (inputid != ctxt->input->id) { |
5117 | 0 | xmlFatalErrMsg(ctxt, XML_ERR_ENTITY_BOUNDARY, |
5118 | 0 | "Notation declaration doesn't start and stop" |
5119 | 0 | " in the same entity\n"); |
5120 | 0 | } |
5121 | 0 | NEXT; |
5122 | 0 | if ((ctxt->sax != NULL) && (!ctxt->disableSAX) && |
5123 | 0 | (ctxt->sax->notationDecl != NULL)) |
5124 | 0 | ctxt->sax->notationDecl(ctxt->userData, name, Pubid, Systemid); |
5125 | 0 | } else { |
5126 | 0 | xmlFatalErr(ctxt, XML_ERR_NOTATION_NOT_FINISHED, NULL); |
5127 | 0 | } |
5128 | 0 | if (Systemid != NULL) xmlFree(Systemid); |
5129 | 0 | if (Pubid != NULL) xmlFree(Pubid); |
5130 | 0 | } |
5131 | 0 | } |
5132 | | |
5133 | | /** |
5134 | | * xmlParseEntityDecl: |
5135 | | * @ctxt: an XML parser context |
5136 | | * |
5137 | | * DEPRECATED: Internal function, don't use. |
5138 | | * |
5139 | | * Parse an entity declaration. Always consumes '<!'. |
5140 | | * |
5141 | | * [70] EntityDecl ::= GEDecl | PEDecl |
5142 | | * |
5143 | | * [71] GEDecl ::= '<!ENTITY' S Name S EntityDef S? '>' |
5144 | | * |
5145 | | * [72] PEDecl ::= '<!ENTITY' S '%' S Name S PEDef S? '>' |
5146 | | * |
5147 | | * [73] EntityDef ::= EntityValue | (ExternalID NDataDecl?) |
5148 | | * |
5149 | | * [74] PEDef ::= EntityValue | ExternalID |
5150 | | * |
5151 | | * [76] NDataDecl ::= S 'NDATA' S Name |
5152 | | * |
5153 | | * [ VC: Notation Declared ] |
5154 | | * The Name must match the declared name of a notation. |
5155 | | */ |
5156 | | |
5157 | | void |
5158 | 25.1k | xmlParseEntityDecl(xmlParserCtxtPtr ctxt) { |
5159 | 25.1k | const xmlChar *name = NULL; |
5160 | 25.1k | xmlChar *value = NULL; |
5161 | 25.1k | xmlChar *URI = NULL, *literal = NULL; |
5162 | 25.1k | const xmlChar *ndata = NULL; |
5163 | 25.1k | int isParameter = 0; |
5164 | 25.1k | xmlChar *orig = NULL; |
5165 | | |
5166 | 25.1k | if ((CUR != '<') || (NXT(1) != '!')) |
5167 | 0 | return; |
5168 | 25.1k | SKIP(2); |
5169 | | |
5170 | | /* GROW; done in the caller */ |
5171 | 25.1k | if (CMP6(CUR_PTR, 'E', 'N', 'T', 'I', 'T', 'Y')) { |
5172 | 25.1k | int inputid = ctxt->input->id; |
5173 | 25.1k | SKIP(6); |
5174 | 25.1k | if (SKIP_BLANKS == 0) { |
5175 | 3.96k | xmlFatalErrMsg(ctxt, XML_ERR_SPACE_REQUIRED, |
5176 | 3.96k | "Space required after '<!ENTITY'\n"); |
5177 | 3.96k | } |
5178 | | |
5179 | 25.1k | if (RAW == '%') { |
5180 | 3.96k | NEXT; |
5181 | 3.96k | if (SKIP_BLANKS == 0) { |
5182 | 3.96k | xmlFatalErrMsg(ctxt, XML_ERR_SPACE_REQUIRED, |
5183 | 3.96k | "Space required after '%%'\n"); |
5184 | 3.96k | } |
5185 | 3.96k | isParameter = 1; |
5186 | 3.96k | } |
5187 | | |
5188 | 25.1k | name = xmlParseName(ctxt); |
5189 | 25.1k | if (name == NULL) { |
5190 | 1 | xmlFatalErrMsg(ctxt, XML_ERR_NAME_REQUIRED, |
5191 | 1 | "xmlParseEntityDecl: no name\n"); |
5192 | 1 | return; |
5193 | 1 | } |
5194 | 25.1k | if (xmlStrchr(name, ':') != NULL) { |
5195 | 13.8k | xmlNsErr(ctxt, XML_NS_ERR_COLON, |
5196 | 13.8k | "colons are forbidden from entities names '%s'\n", |
5197 | 13.8k | name, NULL, NULL); |
5198 | 13.8k | } |
5199 | 25.1k | if (SKIP_BLANKS == 0) { |
5200 | 14 | xmlFatalErrMsg(ctxt, XML_ERR_SPACE_REQUIRED, |
5201 | 14 | "Space required after the entity name\n"); |
5202 | 14 | } |
5203 | | |
5204 | 25.1k | ctxt->instate = XML_PARSER_ENTITY_DECL; |
5205 | | /* |
5206 | | * handle the various case of definitions... |
5207 | | */ |
5208 | 25.1k | if (isParameter) { |
5209 | 3.96k | if ((RAW == '"') || (RAW == '\'')) { |
5210 | 0 | value = xmlParseEntityValue(ctxt, &orig); |
5211 | 0 | if (value) { |
5212 | 0 | if ((ctxt->sax != NULL) && |
5213 | 0 | (!ctxt->disableSAX) && (ctxt->sax->entityDecl != NULL)) |
5214 | 0 | ctxt->sax->entityDecl(ctxt->userData, name, |
5215 | 0 | XML_INTERNAL_PARAMETER_ENTITY, |
5216 | 0 | NULL, NULL, value); |
5217 | 0 | } |
5218 | 3.96k | } else { |
5219 | 3.96k | URI = xmlParseExternalID(ctxt, &literal, 1); |
5220 | 3.96k | if ((URI == NULL) && (literal == NULL)) { |
5221 | 0 | xmlFatalErr(ctxt, XML_ERR_VALUE_REQUIRED, NULL); |
5222 | 0 | } |
5223 | 3.96k | if (URI) { |
5224 | 3.90k | xmlURIPtr uri; |
5225 | | |
5226 | 3.90k | uri = xmlParseURI((const char *) URI); |
5227 | 3.90k | if (uri == NULL) { |
5228 | 1.58k | xmlErrMsgStr(ctxt, XML_ERR_INVALID_URI, |
5229 | 1.58k | "Invalid URI: %s\n", URI); |
5230 | | /* |
5231 | | * This really ought to be a well formedness error |
5232 | | * but the XML Core WG decided otherwise c.f. issue |
5233 | | * E26 of the XML erratas. |
5234 | | */ |
5235 | 2.32k | } else { |
5236 | 2.32k | if (uri->fragment != NULL) { |
5237 | | /* |
5238 | | * Okay this is foolish to block those but not |
5239 | | * invalid URIs. |
5240 | | */ |
5241 | 919 | xmlFatalErr(ctxt, XML_ERR_URI_FRAGMENT, NULL); |
5242 | 1.40k | } else { |
5243 | 1.40k | if ((ctxt->sax != NULL) && |
5244 | 1.40k | (!ctxt->disableSAX) && |
5245 | 1.40k | (ctxt->sax->entityDecl != NULL)) |
5246 | 1.40k | ctxt->sax->entityDecl(ctxt->userData, name, |
5247 | 1.40k | XML_EXTERNAL_PARAMETER_ENTITY, |
5248 | 1.40k | literal, URI, NULL); |
5249 | 1.40k | } |
5250 | 2.32k | xmlFreeURI(uri); |
5251 | 2.32k | } |
5252 | 3.90k | } |
5253 | 3.96k | } |
5254 | 21.2k | } else { |
5255 | 21.2k | if ((RAW == '"') || (RAW == '\'')) { |
5256 | 21.1k | value = xmlParseEntityValue(ctxt, &orig); |
5257 | 21.1k | if ((ctxt->sax != NULL) && |
5258 | 21.1k | (!ctxt->disableSAX) && (ctxt->sax->entityDecl != NULL)) |
5259 | 21.1k | ctxt->sax->entityDecl(ctxt->userData, name, |
5260 | 21.1k | XML_INTERNAL_GENERAL_ENTITY, |
5261 | 21.1k | NULL, NULL, value); |
5262 | | /* |
5263 | | * For expat compatibility in SAX mode. |
5264 | | */ |
5265 | 21.1k | if ((ctxt->myDoc == NULL) || |
5266 | 21.1k | (xmlStrEqual(ctxt->myDoc->version, SAX_COMPAT_MODE))) { |
5267 | 0 | if (ctxt->myDoc == NULL) { |
5268 | 0 | ctxt->myDoc = xmlNewDoc(SAX_COMPAT_MODE); |
5269 | 0 | if (ctxt->myDoc == NULL) { |
5270 | 0 | xmlErrMemory(ctxt, "New Doc failed"); |
5271 | 0 | goto done; |
5272 | 0 | } |
5273 | 0 | ctxt->myDoc->properties = XML_DOC_INTERNAL; |
5274 | 0 | } |
5275 | 0 | if (ctxt->myDoc->intSubset == NULL) |
5276 | 0 | ctxt->myDoc->intSubset = xmlNewDtd(ctxt->myDoc, |
5277 | 0 | BAD_CAST "fake", NULL, NULL); |
5278 | |
|
5279 | 0 | xmlSAX2EntityDecl(ctxt, name, XML_INTERNAL_GENERAL_ENTITY, |
5280 | 0 | NULL, NULL, value); |
5281 | 0 | } |
5282 | 21.1k | } else { |
5283 | 64 | URI = xmlParseExternalID(ctxt, &literal, 1); |
5284 | 64 | if ((URI == NULL) && (literal == NULL)) { |
5285 | 0 | xmlFatalErr(ctxt, XML_ERR_VALUE_REQUIRED, NULL); |
5286 | 0 | } |
5287 | 64 | if (URI) { |
5288 | 64 | xmlURIPtr uri; |
5289 | | |
5290 | 64 | uri = xmlParseURI((const char *)URI); |
5291 | 64 | if (uri == NULL) { |
5292 | 59 | xmlErrMsgStr(ctxt, XML_ERR_INVALID_URI, |
5293 | 59 | "Invalid URI: %s\n", URI); |
5294 | | /* |
5295 | | * This really ought to be a well formedness error |
5296 | | * but the XML Core WG decided otherwise c.f. issue |
5297 | | * E26 of the XML erratas. |
5298 | | */ |
5299 | 59 | } else { |
5300 | 5 | if (uri->fragment != NULL) { |
5301 | | /* |
5302 | | * Okay this is foolish to block those but not |
5303 | | * invalid URIs. |
5304 | | */ |
5305 | 0 | xmlFatalErr(ctxt, XML_ERR_URI_FRAGMENT, NULL); |
5306 | 0 | } |
5307 | 5 | xmlFreeURI(uri); |
5308 | 5 | } |
5309 | 64 | } |
5310 | 64 | if ((RAW != '>') && (SKIP_BLANKS == 0)) { |
5311 | 0 | xmlFatalErrMsg(ctxt, XML_ERR_SPACE_REQUIRED, |
5312 | 0 | "Space required before 'NDATA'\n"); |
5313 | 0 | } |
5314 | 64 | if (CMP5(CUR_PTR, 'N', 'D', 'A', 'T', 'A')) { |
5315 | 0 | SKIP(5); |
5316 | 0 | if (SKIP_BLANKS == 0) { |
5317 | 0 | xmlFatalErrMsg(ctxt, XML_ERR_SPACE_REQUIRED, |
5318 | 0 | "Space required after 'NDATA'\n"); |
5319 | 0 | } |
5320 | 0 | ndata = xmlParseName(ctxt); |
5321 | 0 | if ((ctxt->sax != NULL) && (!ctxt->disableSAX) && |
5322 | 0 | (ctxt->sax->unparsedEntityDecl != NULL)) |
5323 | 0 | ctxt->sax->unparsedEntityDecl(ctxt->userData, name, |
5324 | 0 | literal, URI, ndata); |
5325 | 64 | } else { |
5326 | 64 | if ((ctxt->sax != NULL) && |
5327 | 64 | (!ctxt->disableSAX) && (ctxt->sax->entityDecl != NULL)) |
5328 | 64 | ctxt->sax->entityDecl(ctxt->userData, name, |
5329 | 64 | XML_EXTERNAL_GENERAL_PARSED_ENTITY, |
5330 | 64 | literal, URI, NULL); |
5331 | | /* |
5332 | | * For expat compatibility in SAX mode. |
5333 | | * assuming the entity replacement was asked for |
5334 | | */ |
5335 | 64 | if ((ctxt->replaceEntities != 0) && |
5336 | 64 | ((ctxt->myDoc == NULL) || |
5337 | 0 | (xmlStrEqual(ctxt->myDoc->version, SAX_COMPAT_MODE)))) { |
5338 | 0 | if (ctxt->myDoc == NULL) { |
5339 | 0 | ctxt->myDoc = xmlNewDoc(SAX_COMPAT_MODE); |
5340 | 0 | if (ctxt->myDoc == NULL) { |
5341 | 0 | xmlErrMemory(ctxt, "New Doc failed"); |
5342 | 0 | goto done; |
5343 | 0 | } |
5344 | 0 | ctxt->myDoc->properties = XML_DOC_INTERNAL; |
5345 | 0 | } |
5346 | | |
5347 | 0 | if (ctxt->myDoc->intSubset == NULL) |
5348 | 0 | ctxt->myDoc->intSubset = xmlNewDtd(ctxt->myDoc, |
5349 | 0 | BAD_CAST "fake", NULL, NULL); |
5350 | 0 | xmlSAX2EntityDecl(ctxt, name, |
5351 | 0 | XML_EXTERNAL_GENERAL_PARSED_ENTITY, |
5352 | 0 | literal, URI, NULL); |
5353 | 0 | } |
5354 | 64 | } |
5355 | 64 | } |
5356 | 21.2k | } |
5357 | 25.1k | if (ctxt->instate == XML_PARSER_EOF) |
5358 | 0 | goto done; |
5359 | 25.1k | SKIP_BLANKS; |
5360 | 25.1k | if (RAW != '>') { |
5361 | 17 | xmlFatalErrMsgStr(ctxt, XML_ERR_ENTITY_NOT_FINISHED, |
5362 | 17 | "xmlParseEntityDecl: entity %s not terminated\n", name); |
5363 | 17 | xmlHaltParser(ctxt); |
5364 | 25.1k | } else { |
5365 | 25.1k | if (inputid != ctxt->input->id) { |
5366 | 0 | xmlFatalErrMsg(ctxt, XML_ERR_ENTITY_BOUNDARY, |
5367 | 0 | "Entity declaration doesn't start and stop in" |
5368 | 0 | " the same entity\n"); |
5369 | 0 | } |
5370 | 25.1k | NEXT; |
5371 | 25.1k | } |
5372 | 25.1k | if (orig != NULL) { |
5373 | | /* |
5374 | | * Ugly mechanism to save the raw entity value. |
5375 | | */ |
5376 | 19.2k | xmlEntityPtr cur = NULL; |
5377 | | |
5378 | 19.2k | if (isParameter) { |
5379 | 0 | if ((ctxt->sax != NULL) && |
5380 | 0 | (ctxt->sax->getParameterEntity != NULL)) |
5381 | 0 | cur = ctxt->sax->getParameterEntity(ctxt->userData, name); |
5382 | 19.2k | } else { |
5383 | 19.2k | if ((ctxt->sax != NULL) && |
5384 | 19.2k | (ctxt->sax->getEntity != NULL)) |
5385 | 19.2k | cur = ctxt->sax->getEntity(ctxt->userData, name); |
5386 | 19.2k | if ((cur == NULL) && (ctxt->userData==ctxt)) { |
5387 | 0 | cur = xmlSAX2GetEntity(ctxt, name); |
5388 | 0 | } |
5389 | 19.2k | } |
5390 | 19.2k | if ((cur != NULL) && (cur->orig == NULL)) { |
5391 | 86 | cur->orig = orig; |
5392 | 86 | orig = NULL; |
5393 | 86 | } |
5394 | 19.2k | } |
5395 | | |
5396 | 25.1k | done: |
5397 | 25.1k | if (value != NULL) xmlFree(value); |
5398 | 25.1k | if (URI != NULL) xmlFree(URI); |
5399 | 25.1k | if (literal != NULL) xmlFree(literal); |
5400 | 25.1k | if (orig != NULL) xmlFree(orig); |
5401 | 25.1k | } |
5402 | 25.1k | } |
5403 | | |
5404 | | /** |
5405 | | * xmlParseDefaultDecl: |
5406 | | * @ctxt: an XML parser context |
5407 | | * @value: Receive a possible fixed default value for the attribute |
5408 | | * |
5409 | | * DEPRECATED: Internal function, don't use. |
5410 | | * |
5411 | | * Parse an attribute default declaration |
5412 | | * |
5413 | | * [60] DefaultDecl ::= '#REQUIRED' | '#IMPLIED' | (('#FIXED' S)? AttValue) |
5414 | | * |
5415 | | * [ VC: Required Attribute ] |
5416 | | * if the default declaration is the keyword #REQUIRED, then the |
5417 | | * attribute must be specified for all elements of the type in the |
5418 | | * attribute-list declaration. |
5419 | | * |
5420 | | * [ VC: Attribute Default Legal ] |
5421 | | * The declared default value must meet the lexical constraints of |
5422 | | * the declared attribute type c.f. xmlValidateAttributeDecl() |
5423 | | * |
5424 | | * [ VC: Fixed Attribute Default ] |
5425 | | * if an attribute has a default value declared with the #FIXED |
5426 | | * keyword, instances of that attribute must match the default value. |
5427 | | * |
5428 | | * [ WFC: No < in Attribute Values ] |
5429 | | * handled in xmlParseAttValue() |
5430 | | * |
5431 | | * returns: XML_ATTRIBUTE_NONE, XML_ATTRIBUTE_REQUIRED, XML_ATTRIBUTE_IMPLIED |
5432 | | * or XML_ATTRIBUTE_FIXED. |
5433 | | */ |
5434 | | |
5435 | | int |
5436 | 2.56k | xmlParseDefaultDecl(xmlParserCtxtPtr ctxt, xmlChar **value) { |
5437 | 2.56k | int val; |
5438 | 2.56k | xmlChar *ret; |
5439 | | |
5440 | 2.56k | *value = NULL; |
5441 | 2.56k | if (CMP9(CUR_PTR, '#', 'R', 'E', 'Q', 'U', 'I', 'R', 'E', 'D')) { |
5442 | 0 | SKIP(9); |
5443 | 0 | return(XML_ATTRIBUTE_REQUIRED); |
5444 | 0 | } |
5445 | 2.56k | if (CMP8(CUR_PTR, '#', 'I', 'M', 'P', 'L', 'I', 'E', 'D')) { |
5446 | 0 | SKIP(8); |
5447 | 0 | return(XML_ATTRIBUTE_IMPLIED); |
5448 | 0 | } |
5449 | 2.56k | val = XML_ATTRIBUTE_NONE; |
5450 | 2.56k | if (CMP6(CUR_PTR, '#', 'F', 'I', 'X', 'E', 'D')) { |
5451 | 0 | SKIP(6); |
5452 | 0 | val = XML_ATTRIBUTE_FIXED; |
5453 | 0 | if (SKIP_BLANKS == 0) { |
5454 | 0 | xmlFatalErrMsg(ctxt, XML_ERR_SPACE_REQUIRED, |
5455 | 0 | "Space required after '#FIXED'\n"); |
5456 | 0 | } |
5457 | 0 | } |
5458 | 2.56k | ret = xmlParseAttValue(ctxt); |
5459 | 2.56k | ctxt->instate = XML_PARSER_DTD; |
5460 | 2.56k | if (ret == NULL) { |
5461 | 485 | xmlFatalErrMsg(ctxt, (xmlParserErrors)ctxt->errNo, |
5462 | 485 | "Attribute default value declaration error\n"); |
5463 | 485 | } else |
5464 | 2.07k | *value = ret; |
5465 | 2.56k | return(val); |
5466 | 2.56k | } |
5467 | | |
5468 | | /** |
5469 | | * xmlParseNotationType: |
5470 | | * @ctxt: an XML parser context |
5471 | | * |
5472 | | * DEPRECATED: Internal function, don't use. |
5473 | | * |
5474 | | * parse an Notation attribute type. |
5475 | | * |
5476 | | * Note: the leading 'NOTATION' S part has already being parsed... |
5477 | | * |
5478 | | * [58] NotationType ::= 'NOTATION' S '(' S? Name (S? '|' S? Name)* S? ')' |
5479 | | * |
5480 | | * [ VC: Notation Attributes ] |
5481 | | * Values of this type must match one of the notation names included |
5482 | | * in the declaration; all notation names in the declaration must be declared. |
5483 | | * |
5484 | | * Returns: the notation attribute tree built while parsing |
5485 | | */ |
5486 | | |
5487 | | xmlEnumerationPtr |
5488 | 0 | xmlParseNotationType(xmlParserCtxtPtr ctxt) { |
5489 | 0 | const xmlChar *name; |
5490 | 0 | xmlEnumerationPtr ret = NULL, last = NULL, cur, tmp; |
5491 | |
|
5492 | 0 | if (RAW != '(') { |
5493 | 0 | xmlFatalErr(ctxt, XML_ERR_NOTATION_NOT_STARTED, NULL); |
5494 | 0 | return(NULL); |
5495 | 0 | } |
5496 | 0 | do { |
5497 | 0 | NEXT; |
5498 | 0 | SKIP_BLANKS; |
5499 | 0 | name = xmlParseName(ctxt); |
5500 | 0 | if (name == NULL) { |
5501 | 0 | xmlFatalErrMsg(ctxt, XML_ERR_NAME_REQUIRED, |
5502 | 0 | "Name expected in NOTATION declaration\n"); |
5503 | 0 | xmlFreeEnumeration(ret); |
5504 | 0 | return(NULL); |
5505 | 0 | } |
5506 | 0 | tmp = ret; |
5507 | 0 | while (tmp != NULL) { |
5508 | 0 | if (xmlStrEqual(name, tmp->name)) { |
5509 | 0 | xmlValidityError(ctxt, XML_DTD_DUP_TOKEN, |
5510 | 0 | "standalone: attribute notation value token %s duplicated\n", |
5511 | 0 | name, NULL); |
5512 | 0 | if (!xmlDictOwns(ctxt->dict, name)) |
5513 | 0 | xmlFree((xmlChar *) name); |
5514 | 0 | break; |
5515 | 0 | } |
5516 | 0 | tmp = tmp->next; |
5517 | 0 | } |
5518 | 0 | if (tmp == NULL) { |
5519 | 0 | cur = xmlCreateEnumeration(name); |
5520 | 0 | if (cur == NULL) { |
5521 | 0 | xmlFreeEnumeration(ret); |
5522 | 0 | return(NULL); |
5523 | 0 | } |
5524 | 0 | if (last == NULL) ret = last = cur; |
5525 | 0 | else { |
5526 | 0 | last->next = cur; |
5527 | 0 | last = cur; |
5528 | 0 | } |
5529 | 0 | } |
5530 | 0 | SKIP_BLANKS; |
5531 | 0 | } while (RAW == '|'); |
5532 | 0 | if (RAW != ')') { |
5533 | 0 | xmlFatalErr(ctxt, XML_ERR_NOTATION_NOT_FINISHED, NULL); |
5534 | 0 | xmlFreeEnumeration(ret); |
5535 | 0 | return(NULL); |
5536 | 0 | } |
5537 | 0 | NEXT; |
5538 | 0 | return(ret); |
5539 | 0 | } |
5540 | | |
5541 | | /** |
5542 | | * xmlParseEnumerationType: |
5543 | | * @ctxt: an XML parser context |
5544 | | * |
5545 | | * DEPRECATED: Internal function, don't use. |
5546 | | * |
5547 | | * parse an Enumeration attribute type. |
5548 | | * |
5549 | | * [59] Enumeration ::= '(' S? Nmtoken (S? '|' S? Nmtoken)* S? ')' |
5550 | | * |
5551 | | * [ VC: Enumeration ] |
5552 | | * Values of this type must match one of the Nmtoken tokens in |
5553 | | * the declaration |
5554 | | * |
5555 | | * Returns: the enumeration attribute tree built while parsing |
5556 | | */ |
5557 | | |
5558 | | xmlEnumerationPtr |
5559 | 2.82k | xmlParseEnumerationType(xmlParserCtxtPtr ctxt) { |
5560 | 2.82k | xmlChar *name; |
5561 | 2.82k | xmlEnumerationPtr ret = NULL, last = NULL, cur, tmp; |
5562 | | |
5563 | 2.82k | if (RAW != '(') { |
5564 | 2 | xmlFatalErr(ctxt, XML_ERR_ATTLIST_NOT_STARTED, NULL); |
5565 | 2 | return(NULL); |
5566 | 2 | } |
5567 | 5.38k | do { |
5568 | 5.38k | NEXT; |
5569 | 5.38k | SKIP_BLANKS; |
5570 | 5.38k | name = xmlParseNmtoken(ctxt); |
5571 | 5.38k | if (name == NULL) { |
5572 | 0 | xmlFatalErr(ctxt, XML_ERR_NMTOKEN_REQUIRED, NULL); |
5573 | 0 | return(ret); |
5574 | 0 | } |
5575 | 5.38k | tmp = ret; |
5576 | 7.94k | while (tmp != NULL) { |
5577 | 2.56k | if (xmlStrEqual(name, tmp->name)) { |
5578 | 0 | xmlValidityError(ctxt, XML_DTD_DUP_TOKEN, |
5579 | 0 | "standalone: attribute enumeration value token %s duplicated\n", |
5580 | 0 | name, NULL); |
5581 | 0 | if (!xmlDictOwns(ctxt->dict, name)) |
5582 | 0 | xmlFree(name); |
5583 | 0 | break; |
5584 | 0 | } |
5585 | 2.56k | tmp = tmp->next; |
5586 | 2.56k | } |
5587 | 5.38k | if (tmp == NULL) { |
5588 | 5.38k | cur = xmlCreateEnumeration(name); |
5589 | 5.38k | if (!xmlDictOwns(ctxt->dict, name)) |
5590 | 5.38k | xmlFree(name); |
5591 | 5.38k | if (cur == NULL) { |
5592 | 0 | xmlFreeEnumeration(ret); |
5593 | 0 | return(NULL); |
5594 | 0 | } |
5595 | 5.38k | if (last == NULL) ret = last = cur; |
5596 | 2.56k | else { |
5597 | 2.56k | last->next = cur; |
5598 | 2.56k | last = cur; |
5599 | 2.56k | } |
5600 | 5.38k | } |
5601 | 5.38k | SKIP_BLANKS; |
5602 | 5.38k | } while (RAW == '|'); |
5603 | 2.82k | if (RAW != ')') { |
5604 | 264 | xmlFatalErr(ctxt, XML_ERR_ATTLIST_NOT_FINISHED, NULL); |
5605 | 264 | return(ret); |
5606 | 264 | } |
5607 | 2.56k | NEXT; |
5608 | 2.56k | return(ret); |
5609 | 2.82k | } |
5610 | | |
5611 | | /** |
5612 | | * xmlParseEnumeratedType: |
5613 | | * @ctxt: an XML parser context |
5614 | | * @tree: the enumeration tree built while parsing |
5615 | | * |
5616 | | * DEPRECATED: Internal function, don't use. |
5617 | | * |
5618 | | * parse an Enumerated attribute type. |
5619 | | * |
5620 | | * [57] EnumeratedType ::= NotationType | Enumeration |
5621 | | * |
5622 | | * [58] NotationType ::= 'NOTATION' S '(' S? Name (S? '|' S? Name)* S? ')' |
5623 | | * |
5624 | | * |
5625 | | * Returns: XML_ATTRIBUTE_ENUMERATION or XML_ATTRIBUTE_NOTATION |
5626 | | */ |
5627 | | |
5628 | | int |
5629 | 2.82k | xmlParseEnumeratedType(xmlParserCtxtPtr ctxt, xmlEnumerationPtr *tree) { |
5630 | 2.82k | if (CMP8(CUR_PTR, 'N', 'O', 'T', 'A', 'T', 'I', 'O', 'N')) { |
5631 | 0 | SKIP(8); |
5632 | 0 | if (SKIP_BLANKS == 0) { |
5633 | 0 | xmlFatalErrMsg(ctxt, XML_ERR_SPACE_REQUIRED, |
5634 | 0 | "Space required after 'NOTATION'\n"); |
5635 | 0 | return(0); |
5636 | 0 | } |
5637 | 0 | *tree = xmlParseNotationType(ctxt); |
5638 | 0 | if (*tree == NULL) return(0); |
5639 | 0 | return(XML_ATTRIBUTE_NOTATION); |
5640 | 0 | } |
5641 | 2.82k | *tree = xmlParseEnumerationType(ctxt); |
5642 | 2.82k | if (*tree == NULL) return(0); |
5643 | 2.82k | return(XML_ATTRIBUTE_ENUMERATION); |
5644 | 2.82k | } |
5645 | | |
5646 | | /** |
5647 | | * xmlParseAttributeType: |
5648 | | * @ctxt: an XML parser context |
5649 | | * @tree: the enumeration tree built while parsing |
5650 | | * |
5651 | | * DEPRECATED: Internal function, don't use. |
5652 | | * |
5653 | | * parse the Attribute list def for an element |
5654 | | * |
5655 | | * [54] AttType ::= StringType | TokenizedType | EnumeratedType |
5656 | | * |
5657 | | * [55] StringType ::= 'CDATA' |
5658 | | * |
5659 | | * [56] TokenizedType ::= 'ID' | 'IDREF' | 'IDREFS' | 'ENTITY' | |
5660 | | * 'ENTITIES' | 'NMTOKEN' | 'NMTOKENS' |
5661 | | * |
5662 | | * Validity constraints for attribute values syntax are checked in |
5663 | | * xmlValidateAttributeValue() |
5664 | | * |
5665 | | * [ VC: ID ] |
5666 | | * Values of type ID must match the Name production. A name must not |
5667 | | * appear more than once in an XML document as a value of this type; |
5668 | | * i.e., ID values must uniquely identify the elements which bear them. |
5669 | | * |
5670 | | * [ VC: One ID per Element Type ] |
5671 | | * No element type may have more than one ID attribute specified. |
5672 | | * |
5673 | | * [ VC: ID Attribute Default ] |
5674 | | * An ID attribute must have a declared default of #IMPLIED or #REQUIRED. |
5675 | | * |
5676 | | * [ VC: IDREF ] |
5677 | | * Values of type IDREF must match the Name production, and values |
5678 | | * of type IDREFS must match Names; each IDREF Name must match the value |
5679 | | * of an ID attribute on some element in the XML document; i.e. IDREF |
5680 | | * values must match the value of some ID attribute. |
5681 | | * |
5682 | | * [ VC: Entity Name ] |
5683 | | * Values of type ENTITY must match the Name production, values |
5684 | | * of type ENTITIES must match Names; each Entity Name must match the |
5685 | | * name of an unparsed entity declared in the DTD. |
5686 | | * |
5687 | | * [ VC: Name Token ] |
5688 | | * Values of type NMTOKEN must match the Nmtoken production; values |
5689 | | * of type NMTOKENS must match Nmtokens. |
5690 | | * |
5691 | | * Returns the attribute type |
5692 | | */ |
5693 | | int |
5694 | 2.82k | xmlParseAttributeType(xmlParserCtxtPtr ctxt, xmlEnumerationPtr *tree) { |
5695 | 2.82k | if (CMP5(CUR_PTR, 'C', 'D', 'A', 'T', 'A')) { |
5696 | 0 | SKIP(5); |
5697 | 0 | return(XML_ATTRIBUTE_CDATA); |
5698 | 2.82k | } else if (CMP6(CUR_PTR, 'I', 'D', 'R', 'E', 'F', 'S')) { |
5699 | 0 | SKIP(6); |
5700 | 0 | return(XML_ATTRIBUTE_IDREFS); |
5701 | 2.82k | } else if (CMP5(CUR_PTR, 'I', 'D', 'R', 'E', 'F')) { |
5702 | 0 | SKIP(5); |
5703 | 0 | return(XML_ATTRIBUTE_IDREF); |
5704 | 2.82k | } else if ((RAW == 'I') && (NXT(1) == 'D')) { |
5705 | 0 | SKIP(2); |
5706 | 0 | return(XML_ATTRIBUTE_ID); |
5707 | 2.82k | } else if (CMP6(CUR_PTR, 'E', 'N', 'T', 'I', 'T', 'Y')) { |
5708 | 0 | SKIP(6); |
5709 | 0 | return(XML_ATTRIBUTE_ENTITY); |
5710 | 2.82k | } else if (CMP8(CUR_PTR, 'E', 'N', 'T', 'I', 'T', 'I', 'E', 'S')) { |
5711 | 0 | SKIP(8); |
5712 | 0 | return(XML_ATTRIBUTE_ENTITIES); |
5713 | 2.82k | } else if (CMP8(CUR_PTR, 'N', 'M', 'T', 'O', 'K', 'E', 'N', 'S')) { |
5714 | 0 | SKIP(8); |
5715 | 0 | return(XML_ATTRIBUTE_NMTOKENS); |
5716 | 2.82k | } else if (CMP7(CUR_PTR, 'N', 'M', 'T', 'O', 'K', 'E', 'N')) { |
5717 | 0 | SKIP(7); |
5718 | 0 | return(XML_ATTRIBUTE_NMTOKEN); |
5719 | 0 | } |
5720 | 2.82k | return(xmlParseEnumeratedType(ctxt, tree)); |
5721 | 2.82k | } |
5722 | | |
5723 | | /** |
5724 | | * xmlParseAttributeListDecl: |
5725 | | * @ctxt: an XML parser context |
5726 | | * |
5727 | | * DEPRECATED: Internal function, don't use. |
5728 | | * |
5729 | | * Parse an attribute list declaration for an element. Always consumes '<!'. |
5730 | | * |
5731 | | * [52] AttlistDecl ::= '<!ATTLIST' S Name AttDef* S? '>' |
5732 | | * |
5733 | | * [53] AttDef ::= S Name S AttType S DefaultDecl |
5734 | | * |
5735 | | */ |
5736 | | void |
5737 | 1.16k | xmlParseAttributeListDecl(xmlParserCtxtPtr ctxt) { |
5738 | 1.16k | const xmlChar *elemName; |
5739 | 1.16k | const xmlChar *attrName; |
5740 | 1.16k | xmlEnumerationPtr tree; |
5741 | | |
5742 | 1.16k | if ((CUR != '<') || (NXT(1) != '!')) |
5743 | 0 | return; |
5744 | 1.16k | SKIP(2); |
5745 | | |
5746 | 1.16k | if (CMP7(CUR_PTR, 'A', 'T', 'T', 'L', 'I', 'S', 'T')) { |
5747 | 1.16k | int inputid = ctxt->input->id; |
5748 | | |
5749 | 1.16k | SKIP(7); |
5750 | 1.16k | if (SKIP_BLANKS == 0) { |
5751 | 1.16k | xmlFatalErrMsg(ctxt, XML_ERR_SPACE_REQUIRED, |
5752 | 1.16k | "Space required after '<!ATTLIST'\n"); |
5753 | 1.16k | } |
5754 | 1.16k | elemName = xmlParseName(ctxt); |
5755 | 1.16k | if (elemName == NULL) { |
5756 | 0 | xmlFatalErrMsg(ctxt, XML_ERR_NAME_REQUIRED, |
5757 | 0 | "ATTLIST: no name for Element\n"); |
5758 | 0 | return; |
5759 | 0 | } |
5760 | 1.16k | SKIP_BLANKS; |
5761 | 1.16k | GROW; |
5762 | 2.96k | while ((RAW != '>') && (ctxt->instate != XML_PARSER_EOF)) { |
5763 | 2.96k | int type; |
5764 | 2.96k | int def; |
5765 | 2.96k | xmlChar *defaultValue = NULL; |
5766 | | |
5767 | 2.96k | GROW; |
5768 | 2.96k | tree = NULL; |
5769 | 2.96k | attrName = xmlParseName(ctxt); |
5770 | 2.96k | if (attrName == NULL) { |
5771 | 0 | xmlFatalErrMsg(ctxt, XML_ERR_NAME_REQUIRED, |
5772 | 0 | "ATTLIST: no name for Attribute\n"); |
5773 | 0 | break; |
5774 | 0 | } |
5775 | 2.96k | GROW; |
5776 | 2.96k | if (SKIP_BLANKS == 0) { |
5777 | 135 | xmlFatalErrMsg(ctxt, XML_ERR_SPACE_REQUIRED, |
5778 | 135 | "Space required after the attribute name\n"); |
5779 | 135 | break; |
5780 | 135 | } |
5781 | | |
5782 | 2.82k | type = xmlParseAttributeType(ctxt, &tree); |
5783 | 2.82k | if (type <= 0) { |
5784 | 2 | break; |
5785 | 2 | } |
5786 | | |
5787 | 2.82k | GROW; |
5788 | 2.82k | if (SKIP_BLANKS == 0) { |
5789 | 264 | xmlFatalErrMsg(ctxt, XML_ERR_SPACE_REQUIRED, |
5790 | 264 | "Space required after the attribute type\n"); |
5791 | 264 | if (tree != NULL) |
5792 | 264 | xmlFreeEnumeration(tree); |
5793 | 264 | break; |
5794 | 264 | } |
5795 | | |
5796 | 2.56k | def = xmlParseDefaultDecl(ctxt, &defaultValue); |
5797 | 2.56k | if (def <= 0) { |
5798 | 0 | if (defaultValue != NULL) |
5799 | 0 | xmlFree(defaultValue); |
5800 | 0 | if (tree != NULL) |
5801 | 0 | xmlFreeEnumeration(tree); |
5802 | 0 | break; |
5803 | 0 | } |
5804 | 2.56k | if ((type != XML_ATTRIBUTE_CDATA) && (defaultValue != NULL)) |
5805 | 2.07k | xmlAttrNormalizeSpace(defaultValue, defaultValue); |
5806 | | |
5807 | 2.56k | GROW; |
5808 | 2.56k | if (RAW != '>') { |
5809 | 2.55k | if (SKIP_BLANKS == 0) { |
5810 | 763 | xmlFatalErrMsg(ctxt, XML_ERR_SPACE_REQUIRED, |
5811 | 763 | "Space required after the attribute default value\n"); |
5812 | 763 | if (defaultValue != NULL) |
5813 | 278 | xmlFree(defaultValue); |
5814 | 763 | if (tree != NULL) |
5815 | 763 | xmlFreeEnumeration(tree); |
5816 | 763 | break; |
5817 | 763 | } |
5818 | 2.55k | } |
5819 | 1.79k | if ((ctxt->sax != NULL) && (!ctxt->disableSAX) && |
5820 | 1.79k | (ctxt->sax->attributeDecl != NULL)) |
5821 | 1.79k | ctxt->sax->attributeDecl(ctxt->userData, elemName, attrName, |
5822 | 1.79k | type, def, defaultValue, tree); |
5823 | 0 | else if (tree != NULL) |
5824 | 0 | xmlFreeEnumeration(tree); |
5825 | | |
5826 | 1.79k | if ((ctxt->sax2) && (defaultValue != NULL) && |
5827 | 1.79k | (def != XML_ATTRIBUTE_IMPLIED) && |
5828 | 1.79k | (def != XML_ATTRIBUTE_REQUIRED)) { |
5829 | 1.79k | xmlAddDefAttrs(ctxt, elemName, attrName, defaultValue); |
5830 | 1.79k | } |
5831 | 1.79k | if (ctxt->sax2) { |
5832 | 1.79k | xmlAddSpecialAttr(ctxt, elemName, attrName, type); |
5833 | 1.79k | } |
5834 | 1.79k | if (defaultValue != NULL) |
5835 | 1.79k | xmlFree(defaultValue); |
5836 | 1.79k | GROW; |
5837 | 1.79k | } |
5838 | 1.16k | if (RAW == '>') { |
5839 | 2 | if (inputid != ctxt->input->id) { |
5840 | 0 | xmlFatalErrMsg(ctxt, XML_ERR_ENTITY_BOUNDARY, |
5841 | 0 | "Attribute list declaration doesn't start and" |
5842 | 0 | " stop in the same entity\n"); |
5843 | 0 | } |
5844 | 2 | NEXT; |
5845 | 2 | } |
5846 | 1.16k | } |
5847 | 1.16k | } |
5848 | | |
5849 | | /** |
5850 | | * xmlParseElementMixedContentDecl: |
5851 | | * @ctxt: an XML parser context |
5852 | | * @inputchk: the input used for the current entity, needed for boundary checks |
5853 | | * |
5854 | | * DEPRECATED: Internal function, don't use. |
5855 | | * |
5856 | | * parse the declaration for a Mixed Element content |
5857 | | * The leading '(' and spaces have been skipped in xmlParseElementContentDecl |
5858 | | * |
5859 | | * [51] Mixed ::= '(' S? '#PCDATA' (S? '|' S? Name)* S? ')*' | |
5860 | | * '(' S? '#PCDATA' S? ')' |
5861 | | * |
5862 | | * [ VC: Proper Group/PE Nesting ] applies to [51] too (see [49]) |
5863 | | * |
5864 | | * [ VC: No Duplicate Types ] |
5865 | | * The same name must not appear more than once in a single |
5866 | | * mixed-content declaration. |
5867 | | * |
5868 | | * returns: the list of the xmlElementContentPtr describing the element choices |
5869 | | */ |
5870 | | xmlElementContentPtr |
5871 | 0 | xmlParseElementMixedContentDecl(xmlParserCtxtPtr ctxt, int inputchk) { |
5872 | 0 | xmlElementContentPtr ret = NULL, cur = NULL, n; |
5873 | 0 | const xmlChar *elem = NULL; |
5874 | |
|
5875 | 0 | GROW; |
5876 | 0 | if (CMP7(CUR_PTR, '#', 'P', 'C', 'D', 'A', 'T', 'A')) { |
5877 | 0 | SKIP(7); |
5878 | 0 | SKIP_BLANKS; |
5879 | 0 | if (RAW == ')') { |
5880 | 0 | if (ctxt->input->id != inputchk) { |
5881 | 0 | xmlFatalErrMsg(ctxt, XML_ERR_ENTITY_BOUNDARY, |
5882 | 0 | "Element content declaration doesn't start and" |
5883 | 0 | " stop in the same entity\n"); |
5884 | 0 | } |
5885 | 0 | NEXT; |
5886 | 0 | ret = xmlNewDocElementContent(ctxt->myDoc, NULL, XML_ELEMENT_CONTENT_PCDATA); |
5887 | 0 | if (ret == NULL) |
5888 | 0 | return(NULL); |
5889 | 0 | if (RAW == '*') { |
5890 | 0 | ret->ocur = XML_ELEMENT_CONTENT_MULT; |
5891 | 0 | NEXT; |
5892 | 0 | } |
5893 | 0 | return(ret); |
5894 | 0 | } |
5895 | 0 | if ((RAW == '(') || (RAW == '|')) { |
5896 | 0 | ret = cur = xmlNewDocElementContent(ctxt->myDoc, NULL, XML_ELEMENT_CONTENT_PCDATA); |
5897 | 0 | if (ret == NULL) return(NULL); |
5898 | 0 | } |
5899 | 0 | while ((RAW == '|') && (ctxt->instate != XML_PARSER_EOF)) { |
5900 | 0 | NEXT; |
5901 | 0 | if (elem == NULL) { |
5902 | 0 | ret = xmlNewDocElementContent(ctxt->myDoc, NULL, XML_ELEMENT_CONTENT_OR); |
5903 | 0 | if (ret == NULL) { |
5904 | 0 | xmlFreeDocElementContent(ctxt->myDoc, cur); |
5905 | 0 | return(NULL); |
5906 | 0 | } |
5907 | 0 | ret->c1 = cur; |
5908 | 0 | if (cur != NULL) |
5909 | 0 | cur->parent = ret; |
5910 | 0 | cur = ret; |
5911 | 0 | } else { |
5912 | 0 | n = xmlNewDocElementContent(ctxt->myDoc, NULL, XML_ELEMENT_CONTENT_OR); |
5913 | 0 | if (n == NULL) { |
5914 | 0 | xmlFreeDocElementContent(ctxt->myDoc, ret); |
5915 | 0 | return(NULL); |
5916 | 0 | } |
5917 | 0 | n->c1 = xmlNewDocElementContent(ctxt->myDoc, elem, XML_ELEMENT_CONTENT_ELEMENT); |
5918 | 0 | if (n->c1 != NULL) |
5919 | 0 | n->c1->parent = n; |
5920 | 0 | cur->c2 = n; |
5921 | 0 | if (n != NULL) |
5922 | 0 | n->parent = cur; |
5923 | 0 | cur = n; |
5924 | 0 | } |
5925 | 0 | SKIP_BLANKS; |
5926 | 0 | elem = xmlParseName(ctxt); |
5927 | 0 | if (elem == NULL) { |
5928 | 0 | xmlFatalErrMsg(ctxt, XML_ERR_NAME_REQUIRED, |
5929 | 0 | "xmlParseElementMixedContentDecl : Name expected\n"); |
5930 | 0 | xmlFreeDocElementContent(ctxt->myDoc, ret); |
5931 | 0 | return(NULL); |
5932 | 0 | } |
5933 | 0 | SKIP_BLANKS; |
5934 | 0 | GROW; |
5935 | 0 | } |
5936 | 0 | if ((RAW == ')') && (NXT(1) == '*')) { |
5937 | 0 | if (elem != NULL) { |
5938 | 0 | cur->c2 = xmlNewDocElementContent(ctxt->myDoc, elem, |
5939 | 0 | XML_ELEMENT_CONTENT_ELEMENT); |
5940 | 0 | if (cur->c2 != NULL) |
5941 | 0 | cur->c2->parent = cur; |
5942 | 0 | } |
5943 | 0 | if (ret != NULL) |
5944 | 0 | ret->ocur = XML_ELEMENT_CONTENT_MULT; |
5945 | 0 | if (ctxt->input->id != inputchk) { |
5946 | 0 | xmlFatalErrMsg(ctxt, XML_ERR_ENTITY_BOUNDARY, |
5947 | 0 | "Element content declaration doesn't start and" |
5948 | 0 | " stop in the same entity\n"); |
5949 | 0 | } |
5950 | 0 | SKIP(2); |
5951 | 0 | } else { |
5952 | 0 | xmlFreeDocElementContent(ctxt->myDoc, ret); |
5953 | 0 | xmlFatalErr(ctxt, XML_ERR_MIXED_NOT_STARTED, NULL); |
5954 | 0 | return(NULL); |
5955 | 0 | } |
5956 | |
|
5957 | 0 | } else { |
5958 | 0 | xmlFatalErr(ctxt, XML_ERR_PCDATA_REQUIRED, NULL); |
5959 | 0 | } |
5960 | 0 | return(ret); |
5961 | 0 | } |
5962 | | |
5963 | | /** |
5964 | | * xmlParseElementChildrenContentDeclPriv: |
5965 | | * @ctxt: an XML parser context |
5966 | | * @inputchk: the input used for the current entity, needed for boundary checks |
5967 | | * @depth: the level of recursion |
5968 | | * |
5969 | | * parse the declaration for a Mixed Element content |
5970 | | * The leading '(' and spaces have been skipped in xmlParseElementContentDecl |
5971 | | * |
5972 | | * |
5973 | | * [47] children ::= (choice | seq) ('?' | '*' | '+')? |
5974 | | * |
5975 | | * [48] cp ::= (Name | choice | seq) ('?' | '*' | '+')? |
5976 | | * |
5977 | | * [49] choice ::= '(' S? cp ( S? '|' S? cp )* S? ')' |
5978 | | * |
5979 | | * [50] seq ::= '(' S? cp ( S? ',' S? cp )* S? ')' |
5980 | | * |
5981 | | * [ VC: Proper Group/PE Nesting ] applies to [49] and [50] |
5982 | | * TODO Parameter-entity replacement text must be properly nested |
5983 | | * with parenthesized groups. That is to say, if either of the |
5984 | | * opening or closing parentheses in a choice, seq, or Mixed |
5985 | | * construct is contained in the replacement text for a parameter |
5986 | | * entity, both must be contained in the same replacement text. For |
5987 | | * interoperability, if a parameter-entity reference appears in a |
5988 | | * choice, seq, or Mixed construct, its replacement text should not |
5989 | | * be empty, and neither the first nor last non-blank character of |
5990 | | * the replacement text should be a connector (| or ,). |
5991 | | * |
5992 | | * Returns the tree of xmlElementContentPtr describing the element |
5993 | | * hierarchy. |
5994 | | */ |
5995 | | static xmlElementContentPtr |
5996 | | xmlParseElementChildrenContentDeclPriv(xmlParserCtxtPtr ctxt, int inputchk, |
5997 | 0 | int depth) { |
5998 | 0 | xmlElementContentPtr ret = NULL, cur = NULL, last = NULL, op = NULL; |
5999 | 0 | const xmlChar *elem; |
6000 | 0 | xmlChar type = 0; |
6001 | |
|
6002 | 0 | if (((depth > 128) && ((ctxt->options & XML_PARSE_HUGE) == 0)) || |
6003 | 0 | (depth > 2048)) { |
6004 | 0 | xmlFatalErrMsgInt(ctxt, XML_ERR_ELEMCONTENT_NOT_FINISHED, |
6005 | 0 | "xmlParseElementChildrenContentDecl : depth %d too deep, use XML_PARSE_HUGE\n", |
6006 | 0 | depth); |
6007 | 0 | return(NULL); |
6008 | 0 | } |
6009 | 0 | SKIP_BLANKS; |
6010 | 0 | GROW; |
6011 | 0 | if (RAW == '(') { |
6012 | 0 | int inputid = ctxt->input->id; |
6013 | | |
6014 | | /* Recurse on first child */ |
6015 | 0 | NEXT; |
6016 | 0 | SKIP_BLANKS; |
6017 | 0 | cur = ret = xmlParseElementChildrenContentDeclPriv(ctxt, inputid, |
6018 | 0 | depth + 1); |
6019 | 0 | if (cur == NULL) |
6020 | 0 | return(NULL); |
6021 | 0 | SKIP_BLANKS; |
6022 | 0 | GROW; |
6023 | 0 | } else { |
6024 | 0 | elem = xmlParseName(ctxt); |
6025 | 0 | if (elem == NULL) { |
6026 | 0 | xmlFatalErr(ctxt, XML_ERR_ELEMCONTENT_NOT_STARTED, NULL); |
6027 | 0 | return(NULL); |
6028 | 0 | } |
6029 | 0 | cur = ret = xmlNewDocElementContent(ctxt->myDoc, elem, XML_ELEMENT_CONTENT_ELEMENT); |
6030 | 0 | if (cur == NULL) { |
6031 | 0 | xmlErrMemory(ctxt, NULL); |
6032 | 0 | return(NULL); |
6033 | 0 | } |
6034 | 0 | GROW; |
6035 | 0 | if (RAW == '?') { |
6036 | 0 | cur->ocur = XML_ELEMENT_CONTENT_OPT; |
6037 | 0 | NEXT; |
6038 | 0 | } else if (RAW == '*') { |
6039 | 0 | cur->ocur = XML_ELEMENT_CONTENT_MULT; |
6040 | 0 | NEXT; |
6041 | 0 | } else if (RAW == '+') { |
6042 | 0 | cur->ocur = XML_ELEMENT_CONTENT_PLUS; |
6043 | 0 | NEXT; |
6044 | 0 | } else { |
6045 | 0 | cur->ocur = XML_ELEMENT_CONTENT_ONCE; |
6046 | 0 | } |
6047 | 0 | GROW; |
6048 | 0 | } |
6049 | 0 | SKIP_BLANKS; |
6050 | 0 | while ((RAW != ')') && (ctxt->instate != XML_PARSER_EOF)) { |
6051 | | /* |
6052 | | * Each loop we parse one separator and one element. |
6053 | | */ |
6054 | 0 | if (RAW == ',') { |
6055 | 0 | if (type == 0) type = CUR; |
6056 | | |
6057 | | /* |
6058 | | * Detect "Name | Name , Name" error |
6059 | | */ |
6060 | 0 | else if (type != CUR) { |
6061 | 0 | xmlFatalErrMsgInt(ctxt, XML_ERR_SEPARATOR_REQUIRED, |
6062 | 0 | "xmlParseElementChildrenContentDecl : '%c' expected\n", |
6063 | 0 | type); |
6064 | 0 | if ((last != NULL) && (last != ret)) |
6065 | 0 | xmlFreeDocElementContent(ctxt->myDoc, last); |
6066 | 0 | if (ret != NULL) |
6067 | 0 | xmlFreeDocElementContent(ctxt->myDoc, ret); |
6068 | 0 | return(NULL); |
6069 | 0 | } |
6070 | 0 | NEXT; |
6071 | |
|
6072 | 0 | op = xmlNewDocElementContent(ctxt->myDoc, NULL, XML_ELEMENT_CONTENT_SEQ); |
6073 | 0 | if (op == NULL) { |
6074 | 0 | if ((last != NULL) && (last != ret)) |
6075 | 0 | xmlFreeDocElementContent(ctxt->myDoc, last); |
6076 | 0 | xmlFreeDocElementContent(ctxt->myDoc, ret); |
6077 | 0 | return(NULL); |
6078 | 0 | } |
6079 | 0 | if (last == NULL) { |
6080 | 0 | op->c1 = ret; |
6081 | 0 | if (ret != NULL) |
6082 | 0 | ret->parent = op; |
6083 | 0 | ret = cur = op; |
6084 | 0 | } else { |
6085 | 0 | cur->c2 = op; |
6086 | 0 | if (op != NULL) |
6087 | 0 | op->parent = cur; |
6088 | 0 | op->c1 = last; |
6089 | 0 | if (last != NULL) |
6090 | 0 | last->parent = op; |
6091 | 0 | cur =op; |
6092 | 0 | last = NULL; |
6093 | 0 | } |
6094 | 0 | } else if (RAW == '|') { |
6095 | 0 | if (type == 0) type = CUR; |
6096 | | |
6097 | | /* |
6098 | | * Detect "Name , Name | Name" error |
6099 | | */ |
6100 | 0 | else if (type != CUR) { |
6101 | 0 | xmlFatalErrMsgInt(ctxt, XML_ERR_SEPARATOR_REQUIRED, |
6102 | 0 | "xmlParseElementChildrenContentDecl : '%c' expected\n", |
6103 | 0 | type); |
6104 | 0 | if ((last != NULL) && (last != ret)) |
6105 | 0 | xmlFreeDocElementContent(ctxt->myDoc, last); |
6106 | 0 | if (ret != NULL) |
6107 | 0 | xmlFreeDocElementContent(ctxt->myDoc, ret); |
6108 | 0 | return(NULL); |
6109 | 0 | } |
6110 | 0 | NEXT; |
6111 | |
|
6112 | 0 | op = xmlNewDocElementContent(ctxt->myDoc, NULL, XML_ELEMENT_CONTENT_OR); |
6113 | 0 | if (op == NULL) { |
6114 | 0 | if ((last != NULL) && (last != ret)) |
6115 | 0 | xmlFreeDocElementContent(ctxt->myDoc, last); |
6116 | 0 | if (ret != NULL) |
6117 | 0 | xmlFreeDocElementContent(ctxt->myDoc, ret); |
6118 | 0 | return(NULL); |
6119 | 0 | } |
6120 | 0 | if (last == NULL) { |
6121 | 0 | op->c1 = ret; |
6122 | 0 | if (ret != NULL) |
6123 | 0 | ret->parent = op; |
6124 | 0 | ret = cur = op; |
6125 | 0 | } else { |
6126 | 0 | cur->c2 = op; |
6127 | 0 | if (op != NULL) |
6128 | 0 | op->parent = cur; |
6129 | 0 | op->c1 = last; |
6130 | 0 | if (last != NULL) |
6131 | 0 | last->parent = op; |
6132 | 0 | cur =op; |
6133 | 0 | last = NULL; |
6134 | 0 | } |
6135 | 0 | } else { |
6136 | 0 | xmlFatalErr(ctxt, XML_ERR_ELEMCONTENT_NOT_FINISHED, NULL); |
6137 | 0 | if ((last != NULL) && (last != ret)) |
6138 | 0 | xmlFreeDocElementContent(ctxt->myDoc, last); |
6139 | 0 | if (ret != NULL) |
6140 | 0 | xmlFreeDocElementContent(ctxt->myDoc, ret); |
6141 | 0 | return(NULL); |
6142 | 0 | } |
6143 | 0 | GROW; |
6144 | 0 | SKIP_BLANKS; |
6145 | 0 | GROW; |
6146 | 0 | if (RAW == '(') { |
6147 | 0 | int inputid = ctxt->input->id; |
6148 | | /* Recurse on second child */ |
6149 | 0 | NEXT; |
6150 | 0 | SKIP_BLANKS; |
6151 | 0 | last = xmlParseElementChildrenContentDeclPriv(ctxt, inputid, |
6152 | 0 | depth + 1); |
6153 | 0 | if (last == NULL) { |
6154 | 0 | if (ret != NULL) |
6155 | 0 | xmlFreeDocElementContent(ctxt->myDoc, ret); |
6156 | 0 | return(NULL); |
6157 | 0 | } |
6158 | 0 | SKIP_BLANKS; |
6159 | 0 | } else { |
6160 | 0 | elem = xmlParseName(ctxt); |
6161 | 0 | if (elem == NULL) { |
6162 | 0 | xmlFatalErr(ctxt, XML_ERR_ELEMCONTENT_NOT_STARTED, NULL); |
6163 | 0 | if (ret != NULL) |
6164 | 0 | xmlFreeDocElementContent(ctxt->myDoc, ret); |
6165 | 0 | return(NULL); |
6166 | 0 | } |
6167 | 0 | last = xmlNewDocElementContent(ctxt->myDoc, elem, XML_ELEMENT_CONTENT_ELEMENT); |
6168 | 0 | if (last == NULL) { |
6169 | 0 | if (ret != NULL) |
6170 | 0 | xmlFreeDocElementContent(ctxt->myDoc, ret); |
6171 | 0 | return(NULL); |
6172 | 0 | } |
6173 | 0 | if (RAW == '?') { |
6174 | 0 | last->ocur = XML_ELEMENT_CONTENT_OPT; |
6175 | 0 | NEXT; |
6176 | 0 | } else if (RAW == '*') { |
6177 | 0 | last->ocur = XML_ELEMENT_CONTENT_MULT; |
6178 | 0 | NEXT; |
6179 | 0 | } else if (RAW == '+') { |
6180 | 0 | last->ocur = XML_ELEMENT_CONTENT_PLUS; |
6181 | 0 | NEXT; |
6182 | 0 | } else { |
6183 | 0 | last->ocur = XML_ELEMENT_CONTENT_ONCE; |
6184 | 0 | } |
6185 | 0 | } |
6186 | 0 | SKIP_BLANKS; |
6187 | 0 | GROW; |
6188 | 0 | } |
6189 | 0 | if ((cur != NULL) && (last != NULL)) { |
6190 | 0 | cur->c2 = last; |
6191 | 0 | if (last != NULL) |
6192 | 0 | last->parent = cur; |
6193 | 0 | } |
6194 | 0 | if (ctxt->input->id != inputchk) { |
6195 | 0 | xmlFatalErrMsg(ctxt, XML_ERR_ENTITY_BOUNDARY, |
6196 | 0 | "Element content declaration doesn't start and stop in" |
6197 | 0 | " the same entity\n"); |
6198 | 0 | } |
6199 | 0 | NEXT; |
6200 | 0 | if (RAW == '?') { |
6201 | 0 | if (ret != NULL) { |
6202 | 0 | if ((ret->ocur == XML_ELEMENT_CONTENT_PLUS) || |
6203 | 0 | (ret->ocur == XML_ELEMENT_CONTENT_MULT)) |
6204 | 0 | ret->ocur = XML_ELEMENT_CONTENT_MULT; |
6205 | 0 | else |
6206 | 0 | ret->ocur = XML_ELEMENT_CONTENT_OPT; |
6207 | 0 | } |
6208 | 0 | NEXT; |
6209 | 0 | } else if (RAW == '*') { |
6210 | 0 | if (ret != NULL) { |
6211 | 0 | ret->ocur = XML_ELEMENT_CONTENT_MULT; |
6212 | 0 | cur = ret; |
6213 | | /* |
6214 | | * Some normalization: |
6215 | | * (a | b* | c?)* == (a | b | c)* |
6216 | | */ |
6217 | 0 | while ((cur != NULL) && (cur->type == XML_ELEMENT_CONTENT_OR)) { |
6218 | 0 | if ((cur->c1 != NULL) && |
6219 | 0 | ((cur->c1->ocur == XML_ELEMENT_CONTENT_OPT) || |
6220 | 0 | (cur->c1->ocur == XML_ELEMENT_CONTENT_MULT))) |
6221 | 0 | cur->c1->ocur = XML_ELEMENT_CONTENT_ONCE; |
6222 | 0 | if ((cur->c2 != NULL) && |
6223 | 0 | ((cur->c2->ocur == XML_ELEMENT_CONTENT_OPT) || |
6224 | 0 | (cur->c2->ocur == XML_ELEMENT_CONTENT_MULT))) |
6225 | 0 | cur->c2->ocur = XML_ELEMENT_CONTENT_ONCE; |
6226 | 0 | cur = cur->c2; |
6227 | 0 | } |
6228 | 0 | } |
6229 | 0 | NEXT; |
6230 | 0 | } else if (RAW == '+') { |
6231 | 0 | if (ret != NULL) { |
6232 | 0 | int found = 0; |
6233 | |
|
6234 | 0 | if ((ret->ocur == XML_ELEMENT_CONTENT_OPT) || |
6235 | 0 | (ret->ocur == XML_ELEMENT_CONTENT_MULT)) |
6236 | 0 | ret->ocur = XML_ELEMENT_CONTENT_MULT; |
6237 | 0 | else |
6238 | 0 | ret->ocur = XML_ELEMENT_CONTENT_PLUS; |
6239 | | /* |
6240 | | * Some normalization: |
6241 | | * (a | b*)+ == (a | b)* |
6242 | | * (a | b?)+ == (a | b)* |
6243 | | */ |
6244 | 0 | while ((cur != NULL) && (cur->type == XML_ELEMENT_CONTENT_OR)) { |
6245 | 0 | if ((cur->c1 != NULL) && |
6246 | 0 | ((cur->c1->ocur == XML_ELEMENT_CONTENT_OPT) || |
6247 | 0 | (cur->c1->ocur == XML_ELEMENT_CONTENT_MULT))) { |
6248 | 0 | cur->c1->ocur = XML_ELEMENT_CONTENT_ONCE; |
6249 | 0 | found = 1; |
6250 | 0 | } |
6251 | 0 | if ((cur->c2 != NULL) && |
6252 | 0 | ((cur->c2->ocur == XML_ELEMENT_CONTENT_OPT) || |
6253 | 0 | (cur->c2->ocur == XML_ELEMENT_CONTENT_MULT))) { |
6254 | 0 | cur->c2->ocur = XML_ELEMENT_CONTENT_ONCE; |
6255 | 0 | found = 1; |
6256 | 0 | } |
6257 | 0 | cur = cur->c2; |
6258 | 0 | } |
6259 | 0 | if (found) |
6260 | 0 | ret->ocur = XML_ELEMENT_CONTENT_MULT; |
6261 | 0 | } |
6262 | 0 | NEXT; |
6263 | 0 | } |
6264 | 0 | return(ret); |
6265 | 0 | } |
6266 | | |
6267 | | /** |
6268 | | * xmlParseElementChildrenContentDecl: |
6269 | | * @ctxt: an XML parser context |
6270 | | * @inputchk: the input used for the current entity, needed for boundary checks |
6271 | | * |
6272 | | * DEPRECATED: Internal function, don't use. |
6273 | | * |
6274 | | * parse the declaration for a Mixed Element content |
6275 | | * The leading '(' and spaces have been skipped in xmlParseElementContentDecl |
6276 | | * |
6277 | | * [47] children ::= (choice | seq) ('?' | '*' | '+')? |
6278 | | * |
6279 | | * [48] cp ::= (Name | choice | seq) ('?' | '*' | '+')? |
6280 | | * |
6281 | | * [49] choice ::= '(' S? cp ( S? '|' S? cp )* S? ')' |
6282 | | * |
6283 | | * [50] seq ::= '(' S? cp ( S? ',' S? cp )* S? ')' |
6284 | | * |
6285 | | * [ VC: Proper Group/PE Nesting ] applies to [49] and [50] |
6286 | | * TODO Parameter-entity replacement text must be properly nested |
6287 | | * with parenthesized groups. That is to say, if either of the |
6288 | | * opening or closing parentheses in a choice, seq, or Mixed |
6289 | | * construct is contained in the replacement text for a parameter |
6290 | | * entity, both must be contained in the same replacement text. For |
6291 | | * interoperability, if a parameter-entity reference appears in a |
6292 | | * choice, seq, or Mixed construct, its replacement text should not |
6293 | | * be empty, and neither the first nor last non-blank character of |
6294 | | * the replacement text should be a connector (| or ,). |
6295 | | * |
6296 | | * Returns the tree of xmlElementContentPtr describing the element |
6297 | | * hierarchy. |
6298 | | */ |
6299 | | xmlElementContentPtr |
6300 | 0 | xmlParseElementChildrenContentDecl(xmlParserCtxtPtr ctxt, int inputchk) { |
6301 | | /* stub left for API/ABI compat */ |
6302 | 0 | return(xmlParseElementChildrenContentDeclPriv(ctxt, inputchk, 1)); |
6303 | 0 | } |
6304 | | |
6305 | | /** |
6306 | | * xmlParseElementContentDecl: |
6307 | | * @ctxt: an XML parser context |
6308 | | * @name: the name of the element being defined. |
6309 | | * @result: the Element Content pointer will be stored here if any |
6310 | | * |
6311 | | * DEPRECATED: Internal function, don't use. |
6312 | | * |
6313 | | * parse the declaration for an Element content either Mixed or Children, |
6314 | | * the cases EMPTY and ANY are handled directly in xmlParseElementDecl |
6315 | | * |
6316 | | * [46] contentspec ::= 'EMPTY' | 'ANY' | Mixed | children |
6317 | | * |
6318 | | * returns: the type of element content XML_ELEMENT_TYPE_xxx |
6319 | | */ |
6320 | | |
6321 | | int |
6322 | | xmlParseElementContentDecl(xmlParserCtxtPtr ctxt, const xmlChar *name, |
6323 | 0 | xmlElementContentPtr *result) { |
6324 | |
|
6325 | 0 | xmlElementContentPtr tree = NULL; |
6326 | 0 | int inputid = ctxt->input->id; |
6327 | 0 | int res; |
6328 | |
|
6329 | 0 | *result = NULL; |
6330 | |
|
6331 | 0 | if (RAW != '(') { |
6332 | 0 | xmlFatalErrMsgStr(ctxt, XML_ERR_ELEMCONTENT_NOT_STARTED, |
6333 | 0 | "xmlParseElementContentDecl : %s '(' expected\n", name); |
6334 | 0 | return(-1); |
6335 | 0 | } |
6336 | 0 | NEXT; |
6337 | 0 | GROW; |
6338 | 0 | if (ctxt->instate == XML_PARSER_EOF) |
6339 | 0 | return(-1); |
6340 | 0 | SKIP_BLANKS; |
6341 | 0 | if (CMP7(CUR_PTR, '#', 'P', 'C', 'D', 'A', 'T', 'A')) { |
6342 | 0 | tree = xmlParseElementMixedContentDecl(ctxt, inputid); |
6343 | 0 | res = XML_ELEMENT_TYPE_MIXED; |
6344 | 0 | } else { |
6345 | 0 | tree = xmlParseElementChildrenContentDeclPriv(ctxt, inputid, 1); |
6346 | 0 | res = XML_ELEMENT_TYPE_ELEMENT; |
6347 | 0 | } |
6348 | 0 | SKIP_BLANKS; |
6349 | 0 | *result = tree; |
6350 | 0 | return(res); |
6351 | 0 | } |
6352 | | |
6353 | | /** |
6354 | | * xmlParseElementDecl: |
6355 | | * @ctxt: an XML parser context |
6356 | | * |
6357 | | * DEPRECATED: Internal function, don't use. |
6358 | | * |
6359 | | * Parse an element declaration. Always consumes '<!'. |
6360 | | * |
6361 | | * [45] elementdecl ::= '<!ELEMENT' S Name S contentspec S? '>' |
6362 | | * |
6363 | | * [ VC: Unique Element Type Declaration ] |
6364 | | * No element type may be declared more than once |
6365 | | * |
6366 | | * Returns the type of the element, or -1 in case of error |
6367 | | */ |
6368 | | int |
6369 | 0 | xmlParseElementDecl(xmlParserCtxtPtr ctxt) { |
6370 | 0 | const xmlChar *name; |
6371 | 0 | int ret = -1; |
6372 | 0 | xmlElementContentPtr content = NULL; |
6373 | |
|
6374 | 0 | if ((CUR != '<') || (NXT(1) != '!')) |
6375 | 0 | return(ret); |
6376 | 0 | SKIP(2); |
6377 | | |
6378 | | /* GROW; done in the caller */ |
6379 | 0 | if (CMP7(CUR_PTR, 'E', 'L', 'E', 'M', 'E', 'N', 'T')) { |
6380 | 0 | int inputid = ctxt->input->id; |
6381 | |
|
6382 | 0 | SKIP(7); |
6383 | 0 | if (SKIP_BLANKS == 0) { |
6384 | 0 | xmlFatalErrMsg(ctxt, XML_ERR_SPACE_REQUIRED, |
6385 | 0 | "Space required after 'ELEMENT'\n"); |
6386 | 0 | return(-1); |
6387 | 0 | } |
6388 | 0 | name = xmlParseName(ctxt); |
6389 | 0 | if (name == NULL) { |
6390 | 0 | xmlFatalErrMsg(ctxt, XML_ERR_NAME_REQUIRED, |
6391 | 0 | "xmlParseElementDecl: no name for Element\n"); |
6392 | 0 | return(-1); |
6393 | 0 | } |
6394 | 0 | if (SKIP_BLANKS == 0) { |
6395 | 0 | xmlFatalErrMsg(ctxt, XML_ERR_SPACE_REQUIRED, |
6396 | 0 | "Space required after the element name\n"); |
6397 | 0 | } |
6398 | 0 | if (CMP5(CUR_PTR, 'E', 'M', 'P', 'T', 'Y')) { |
6399 | 0 | SKIP(5); |
6400 | | /* |
6401 | | * Element must always be empty. |
6402 | | */ |
6403 | 0 | ret = XML_ELEMENT_TYPE_EMPTY; |
6404 | 0 | } else if ((RAW == 'A') && (NXT(1) == 'N') && |
6405 | 0 | (NXT(2) == 'Y')) { |
6406 | 0 | SKIP(3); |
6407 | | /* |
6408 | | * Element is a generic container. |
6409 | | */ |
6410 | 0 | ret = XML_ELEMENT_TYPE_ANY; |
6411 | 0 | } else if (RAW == '(') { |
6412 | 0 | ret = xmlParseElementContentDecl(ctxt, name, &content); |
6413 | 0 | } else { |
6414 | | /* |
6415 | | * [ WFC: PEs in Internal Subset ] error handling. |
6416 | | */ |
6417 | 0 | if ((RAW == '%') && (ctxt->external == 0) && |
6418 | 0 | (ctxt->inputNr == 1)) { |
6419 | 0 | xmlFatalErrMsg(ctxt, XML_ERR_PEREF_IN_INT_SUBSET, |
6420 | 0 | "PEReference: forbidden within markup decl in internal subset\n"); |
6421 | 0 | } else { |
6422 | 0 | xmlFatalErrMsg(ctxt, XML_ERR_ELEMCONTENT_NOT_STARTED, |
6423 | 0 | "xmlParseElementDecl: 'EMPTY', 'ANY' or '(' expected\n"); |
6424 | 0 | } |
6425 | 0 | return(-1); |
6426 | 0 | } |
6427 | | |
6428 | 0 | SKIP_BLANKS; |
6429 | |
|
6430 | 0 | if (RAW != '>') { |
6431 | 0 | xmlFatalErr(ctxt, XML_ERR_GT_REQUIRED, NULL); |
6432 | 0 | if (content != NULL) { |
6433 | 0 | xmlFreeDocElementContent(ctxt->myDoc, content); |
6434 | 0 | } |
6435 | 0 | } else { |
6436 | 0 | if (inputid != ctxt->input->id) { |
6437 | 0 | xmlFatalErrMsg(ctxt, XML_ERR_ENTITY_BOUNDARY, |
6438 | 0 | "Element declaration doesn't start and stop in" |
6439 | 0 | " the same entity\n"); |
6440 | 0 | } |
6441 | |
|
6442 | 0 | NEXT; |
6443 | 0 | if ((ctxt->sax != NULL) && (!ctxt->disableSAX) && |
6444 | 0 | (ctxt->sax->elementDecl != NULL)) { |
6445 | 0 | if (content != NULL) |
6446 | 0 | content->parent = NULL; |
6447 | 0 | ctxt->sax->elementDecl(ctxt->userData, name, ret, |
6448 | 0 | content); |
6449 | 0 | if ((content != NULL) && (content->parent == NULL)) { |
6450 | | /* |
6451 | | * this is a trick: if xmlAddElementDecl is called, |
6452 | | * instead of copying the full tree it is plugged directly |
6453 | | * if called from the parser. Avoid duplicating the |
6454 | | * interfaces or change the API/ABI |
6455 | | */ |
6456 | 0 | xmlFreeDocElementContent(ctxt->myDoc, content); |
6457 | 0 | } |
6458 | 0 | } else if (content != NULL) { |
6459 | 0 | xmlFreeDocElementContent(ctxt->myDoc, content); |
6460 | 0 | } |
6461 | 0 | } |
6462 | 0 | } |
6463 | 0 | return(ret); |
6464 | 0 | } |
6465 | | |
6466 | | /** |
6467 | | * xmlParseConditionalSections |
6468 | | * @ctxt: an XML parser context |
6469 | | * |
6470 | | * Parse a conditional section. Always consumes '<!['. |
6471 | | * |
6472 | | * [61] conditionalSect ::= includeSect | ignoreSect |
6473 | | * [62] includeSect ::= '<![' S? 'INCLUDE' S? '[' extSubsetDecl ']]>' |
6474 | | * [63] ignoreSect ::= '<![' S? 'IGNORE' S? '[' ignoreSectContents* ']]>' |
6475 | | * [64] ignoreSectContents ::= Ignore ('<![' ignoreSectContents ']]>' Ignore)* |
6476 | | * [65] Ignore ::= Char* - (Char* ('<![' | ']]>') Char*) |
6477 | | */ |
6478 | | |
6479 | | static void |
6480 | 0 | xmlParseConditionalSections(xmlParserCtxtPtr ctxt) { |
6481 | 0 | int *inputIds = NULL; |
6482 | 0 | size_t inputIdsSize = 0; |
6483 | 0 | size_t depth = 0; |
6484 | |
|
6485 | 0 | while (ctxt->instate != XML_PARSER_EOF) { |
6486 | 0 | if ((RAW == '<') && (NXT(1) == '!') && (NXT(2) == '[')) { |
6487 | 0 | int id = ctxt->input->id; |
6488 | |
|
6489 | 0 | SKIP(3); |
6490 | 0 | SKIP_BLANKS; |
6491 | |
|
6492 | 0 | if (CMP7(CUR_PTR, 'I', 'N', 'C', 'L', 'U', 'D', 'E')) { |
6493 | 0 | SKIP(7); |
6494 | 0 | SKIP_BLANKS; |
6495 | 0 | if (RAW != '[') { |
6496 | 0 | xmlFatalErr(ctxt, XML_ERR_CONDSEC_INVALID, NULL); |
6497 | 0 | xmlHaltParser(ctxt); |
6498 | 0 | goto error; |
6499 | 0 | } |
6500 | 0 | if (ctxt->input->id != id) { |
6501 | 0 | xmlFatalErrMsg(ctxt, XML_ERR_ENTITY_BOUNDARY, |
6502 | 0 | "All markup of the conditional section is" |
6503 | 0 | " not in the same entity\n"); |
6504 | 0 | } |
6505 | 0 | NEXT; |
6506 | |
|
6507 | 0 | if (inputIdsSize <= depth) { |
6508 | 0 | int *tmp; |
6509 | |
|
6510 | 0 | inputIdsSize = (inputIdsSize == 0 ? 4 : inputIdsSize * 2); |
6511 | 0 | tmp = (int *) xmlRealloc(inputIds, |
6512 | 0 | inputIdsSize * sizeof(int)); |
6513 | 0 | if (tmp == NULL) { |
6514 | 0 | xmlErrMemory(ctxt, NULL); |
6515 | 0 | goto error; |
6516 | 0 | } |
6517 | 0 | inputIds = tmp; |
6518 | 0 | } |
6519 | 0 | inputIds[depth] = id; |
6520 | 0 | depth++; |
6521 | 0 | } else if (CMP6(CUR_PTR, 'I', 'G', 'N', 'O', 'R', 'E')) { |
6522 | 0 | size_t ignoreDepth = 0; |
6523 | |
|
6524 | 0 | SKIP(6); |
6525 | 0 | SKIP_BLANKS; |
6526 | 0 | if (RAW != '[') { |
6527 | 0 | xmlFatalErr(ctxt, XML_ERR_CONDSEC_INVALID, NULL); |
6528 | 0 | xmlHaltParser(ctxt); |
6529 | 0 | goto error; |
6530 | 0 | } |
6531 | 0 | if (ctxt->input->id != id) { |
6532 | 0 | xmlFatalErrMsg(ctxt, XML_ERR_ENTITY_BOUNDARY, |
6533 | 0 | "All markup of the conditional section is" |
6534 | 0 | " not in the same entity\n"); |
6535 | 0 | } |
6536 | 0 | NEXT; |
6537 | |
|
6538 | 0 | while (RAW != 0) { |
6539 | 0 | if ((RAW == '<') && (NXT(1) == '!') && (NXT(2) == '[')) { |
6540 | 0 | SKIP(3); |
6541 | 0 | ignoreDepth++; |
6542 | | /* Check for integer overflow */ |
6543 | 0 | if (ignoreDepth == 0) { |
6544 | 0 | xmlErrMemory(ctxt, NULL); |
6545 | 0 | goto error; |
6546 | 0 | } |
6547 | 0 | } else if ((RAW == ']') && (NXT(1) == ']') && |
6548 | 0 | (NXT(2) == '>')) { |
6549 | 0 | if (ignoreDepth == 0) |
6550 | 0 | break; |
6551 | 0 | SKIP(3); |
6552 | 0 | ignoreDepth--; |
6553 | 0 | } else { |
6554 | 0 | NEXT; |
6555 | 0 | } |
6556 | 0 | } |
6557 | | |
6558 | 0 | if (RAW == 0) { |
6559 | 0 | xmlFatalErr(ctxt, XML_ERR_CONDSEC_NOT_FINISHED, NULL); |
6560 | 0 | goto error; |
6561 | 0 | } |
6562 | 0 | if (ctxt->input->id != id) { |
6563 | 0 | xmlFatalErrMsg(ctxt, XML_ERR_ENTITY_BOUNDARY, |
6564 | 0 | "All markup of the conditional section is" |
6565 | 0 | " not in the same entity\n"); |
6566 | 0 | } |
6567 | 0 | SKIP(3); |
6568 | 0 | } else { |
6569 | 0 | xmlFatalErr(ctxt, XML_ERR_CONDSEC_INVALID_KEYWORD, NULL); |
6570 | 0 | xmlHaltParser(ctxt); |
6571 | 0 | goto error; |
6572 | 0 | } |
6573 | 0 | } else if ((depth > 0) && |
6574 | 0 | (RAW == ']') && (NXT(1) == ']') && (NXT(2) == '>')) { |
6575 | 0 | depth--; |
6576 | 0 | if (ctxt->input->id != inputIds[depth]) { |
6577 | 0 | xmlFatalErrMsg(ctxt, XML_ERR_ENTITY_BOUNDARY, |
6578 | 0 | "All markup of the conditional section is not" |
6579 | 0 | " in the same entity\n"); |
6580 | 0 | } |
6581 | 0 | SKIP(3); |
6582 | 0 | } else if ((RAW == '<') && ((NXT(1) == '!') || (NXT(1) == '?'))) { |
6583 | 0 | xmlParseMarkupDecl(ctxt); |
6584 | 0 | } else { |
6585 | 0 | xmlFatalErr(ctxt, XML_ERR_EXT_SUBSET_NOT_FINISHED, NULL); |
6586 | 0 | xmlHaltParser(ctxt); |
6587 | 0 | goto error; |
6588 | 0 | } |
6589 | | |
6590 | 0 | if (depth == 0) |
6591 | 0 | break; |
6592 | | |
6593 | 0 | SKIP_BLANKS; |
6594 | 0 | SHRINK; |
6595 | 0 | GROW; |
6596 | 0 | } |
6597 | | |
6598 | 0 | error: |
6599 | 0 | xmlFree(inputIds); |
6600 | 0 | } |
6601 | | |
6602 | | /** |
6603 | | * xmlParseMarkupDecl: |
6604 | | * @ctxt: an XML parser context |
6605 | | * |
6606 | | * DEPRECATED: Internal function, don't use. |
6607 | | * |
6608 | | * Parse markup declarations. Always consumes '<!' or '<?'. |
6609 | | * |
6610 | | * [29] markupdecl ::= elementdecl | AttlistDecl | EntityDecl | |
6611 | | * NotationDecl | PI | Comment |
6612 | | * |
6613 | | * [ VC: Proper Declaration/PE Nesting ] |
6614 | | * Parameter-entity replacement text must be properly nested with |
6615 | | * markup declarations. That is to say, if either the first character |
6616 | | * or the last character of a markup declaration (markupdecl above) is |
6617 | | * contained in the replacement text for a parameter-entity reference, |
6618 | | * both must be contained in the same replacement text. |
6619 | | * |
6620 | | * [ WFC: PEs in Internal Subset ] |
6621 | | * In the internal DTD subset, parameter-entity references can occur |
6622 | | * only where markup declarations can occur, not within markup declarations. |
6623 | | * (This does not apply to references that occur in external parameter |
6624 | | * entities or to the external subset.) |
6625 | | */ |
6626 | | void |
6627 | 26.5k | xmlParseMarkupDecl(xmlParserCtxtPtr ctxt) { |
6628 | 26.5k | GROW; |
6629 | 26.5k | if (CUR == '<') { |
6630 | 26.5k | if (NXT(1) == '!') { |
6631 | 26.3k | switch (NXT(2)) { |
6632 | 25.1k | case 'E': |
6633 | 25.1k | if (NXT(3) == 'L') |
6634 | 0 | xmlParseElementDecl(ctxt); |
6635 | 25.1k | else if (NXT(3) == 'N') |
6636 | 25.1k | xmlParseEntityDecl(ctxt); |
6637 | 0 | else |
6638 | 0 | SKIP(2); |
6639 | 25.1k | break; |
6640 | 1.16k | case 'A': |
6641 | 1.16k | xmlParseAttributeListDecl(ctxt); |
6642 | 1.16k | break; |
6643 | 0 | case 'N': |
6644 | 0 | xmlParseNotationDecl(ctxt); |
6645 | 0 | break; |
6646 | 0 | case '-': |
6647 | 0 | xmlParseComment(ctxt); |
6648 | 0 | break; |
6649 | 2 | default: |
6650 | | /* there is an error but it will be detected later */ |
6651 | 2 | SKIP(2); |
6652 | 2 | break; |
6653 | 26.3k | } |
6654 | 26.3k | } else if (NXT(1) == '?') { |
6655 | 245 | xmlParsePI(ctxt); |
6656 | 245 | } |
6657 | 26.5k | } |
6658 | | |
6659 | | /* |
6660 | | * detect requirement to exit there and act accordingly |
6661 | | * and avoid having instate overridden later on |
6662 | | */ |
6663 | 26.5k | if (ctxt->instate == XML_PARSER_EOF) |
6664 | 17 | return; |
6665 | | |
6666 | 26.5k | ctxt->instate = XML_PARSER_DTD; |
6667 | 26.5k | } |
6668 | | |
6669 | | /** |
6670 | | * xmlParseTextDecl: |
6671 | | * @ctxt: an XML parser context |
6672 | | * |
6673 | | * DEPRECATED: Internal function, don't use. |
6674 | | * |
6675 | | * parse an XML declaration header for external entities |
6676 | | * |
6677 | | * [77] TextDecl ::= '<?xml' VersionInfo? EncodingDecl S? '?>' |
6678 | | */ |
6679 | | |
6680 | | void |
6681 | 0 | xmlParseTextDecl(xmlParserCtxtPtr ctxt) { |
6682 | 0 | xmlChar *version; |
6683 | 0 | const xmlChar *encoding; |
6684 | 0 | int oldstate; |
6685 | | |
6686 | | /* |
6687 | | * We know that '<?xml' is here. |
6688 | | */ |
6689 | 0 | if ((CMP5(CUR_PTR, '<', '?', 'x', 'm', 'l')) && (IS_BLANK_CH(NXT(5)))) { |
6690 | 0 | SKIP(5); |
6691 | 0 | } else { |
6692 | 0 | xmlFatalErr(ctxt, XML_ERR_XMLDECL_NOT_STARTED, NULL); |
6693 | 0 | return; |
6694 | 0 | } |
6695 | | |
6696 | | /* Avoid expansion of parameter entities when skipping blanks. */ |
6697 | 0 | oldstate = ctxt->instate; |
6698 | 0 | ctxt->instate = XML_PARSER_START; |
6699 | |
|
6700 | 0 | if (SKIP_BLANKS == 0) { |
6701 | 0 | xmlFatalErrMsg(ctxt, XML_ERR_SPACE_REQUIRED, |
6702 | 0 | "Space needed after '<?xml'\n"); |
6703 | 0 | } |
6704 | | |
6705 | | /* |
6706 | | * We may have the VersionInfo here. |
6707 | | */ |
6708 | 0 | version = xmlParseVersionInfo(ctxt); |
6709 | 0 | if (version == NULL) |
6710 | 0 | version = xmlCharStrdup(XML_DEFAULT_VERSION); |
6711 | 0 | else { |
6712 | 0 | if (SKIP_BLANKS == 0) { |
6713 | 0 | xmlFatalErrMsg(ctxt, XML_ERR_SPACE_REQUIRED, |
6714 | 0 | "Space needed here\n"); |
6715 | 0 | } |
6716 | 0 | } |
6717 | 0 | ctxt->input->version = version; |
6718 | | |
6719 | | /* |
6720 | | * We must have the encoding declaration |
6721 | | */ |
6722 | 0 | encoding = xmlParseEncodingDecl(ctxt); |
6723 | 0 | if (ctxt->instate == XML_PARSER_EOF) |
6724 | 0 | return; |
6725 | 0 | if (ctxt->errNo == XML_ERR_UNSUPPORTED_ENCODING) { |
6726 | | /* |
6727 | | * The XML REC instructs us to stop parsing right here |
6728 | | */ |
6729 | 0 | ctxt->instate = oldstate; |
6730 | 0 | return; |
6731 | 0 | } |
6732 | 0 | if ((encoding == NULL) && (ctxt->errNo == XML_ERR_OK)) { |
6733 | 0 | xmlFatalErrMsg(ctxt, XML_ERR_MISSING_ENCODING, |
6734 | 0 | "Missing encoding in text declaration\n"); |
6735 | 0 | } |
6736 | |
|
6737 | 0 | SKIP_BLANKS; |
6738 | 0 | if ((RAW == '?') && (NXT(1) == '>')) { |
6739 | 0 | SKIP(2); |
6740 | 0 | } else if (RAW == '>') { |
6741 | | /* Deprecated old WD ... */ |
6742 | 0 | xmlFatalErr(ctxt, XML_ERR_XMLDECL_NOT_FINISHED, NULL); |
6743 | 0 | NEXT; |
6744 | 0 | } else { |
6745 | 0 | int c; |
6746 | |
|
6747 | 0 | xmlFatalErr(ctxt, XML_ERR_XMLDECL_NOT_FINISHED, NULL); |
6748 | 0 | while ((c = CUR) != 0) { |
6749 | 0 | NEXT; |
6750 | 0 | if (c == '>') |
6751 | 0 | break; |
6752 | 0 | } |
6753 | 0 | } |
6754 | |
|
6755 | 0 | ctxt->instate = oldstate; |
6756 | 0 | } |
6757 | | |
6758 | | /** |
6759 | | * xmlParseExternalSubset: |
6760 | | * @ctxt: an XML parser context |
6761 | | * @ExternalID: the external identifier |
6762 | | * @SystemID: the system identifier (or URL) |
6763 | | * |
6764 | | * parse Markup declarations from an external subset |
6765 | | * |
6766 | | * [30] extSubset ::= textDecl? extSubsetDecl |
6767 | | * |
6768 | | * [31] extSubsetDecl ::= (markupdecl | conditionalSect | PEReference | S) * |
6769 | | */ |
6770 | | void |
6771 | | xmlParseExternalSubset(xmlParserCtxtPtr ctxt, const xmlChar *ExternalID, |
6772 | 0 | const xmlChar *SystemID) { |
6773 | 0 | xmlDetectSAX2(ctxt); |
6774 | 0 | GROW; |
6775 | |
|
6776 | 0 | if ((ctxt->encoding == NULL) && |
6777 | 0 | (ctxt->input->end - ctxt->input->cur >= 4)) { |
6778 | 0 | xmlChar start[4]; |
6779 | 0 | xmlCharEncoding enc; |
6780 | |
|
6781 | 0 | start[0] = RAW; |
6782 | 0 | start[1] = NXT(1); |
6783 | 0 | start[2] = NXT(2); |
6784 | 0 | start[3] = NXT(3); |
6785 | 0 | enc = xmlDetectCharEncoding(start, 4); |
6786 | 0 | if (enc != XML_CHAR_ENCODING_NONE) |
6787 | 0 | xmlSwitchEncoding(ctxt, enc); |
6788 | 0 | } |
6789 | |
|
6790 | 0 | if (CMP5(CUR_PTR, '<', '?', 'x', 'm', 'l')) { |
6791 | 0 | xmlParseTextDecl(ctxt); |
6792 | 0 | if (ctxt->errNo == XML_ERR_UNSUPPORTED_ENCODING) { |
6793 | | /* |
6794 | | * The XML REC instructs us to stop parsing right here |
6795 | | */ |
6796 | 0 | xmlHaltParser(ctxt); |
6797 | 0 | return; |
6798 | 0 | } |
6799 | 0 | } |
6800 | 0 | if (ctxt->myDoc == NULL) { |
6801 | 0 | ctxt->myDoc = xmlNewDoc(BAD_CAST "1.0"); |
6802 | 0 | if (ctxt->myDoc == NULL) { |
6803 | 0 | xmlErrMemory(ctxt, "New Doc failed"); |
6804 | 0 | return; |
6805 | 0 | } |
6806 | 0 | ctxt->myDoc->properties = XML_DOC_INTERNAL; |
6807 | 0 | } |
6808 | 0 | if ((ctxt->myDoc != NULL) && (ctxt->myDoc->intSubset == NULL)) |
6809 | 0 | xmlCreateIntSubset(ctxt->myDoc, NULL, ExternalID, SystemID); |
6810 | |
|
6811 | 0 | ctxt->instate = XML_PARSER_DTD; |
6812 | 0 | ctxt->external = 1; |
6813 | 0 | SKIP_BLANKS; |
6814 | 0 | while ((ctxt->instate != XML_PARSER_EOF) && (RAW != 0)) { |
6815 | 0 | GROW; |
6816 | 0 | if ((RAW == '<') && (NXT(1) == '!') && (NXT(2) == '[')) { |
6817 | 0 | xmlParseConditionalSections(ctxt); |
6818 | 0 | } else if ((RAW == '<') && ((NXT(1) == '!') || (NXT(1) == '?'))) { |
6819 | 0 | xmlParseMarkupDecl(ctxt); |
6820 | 0 | } else { |
6821 | 0 | xmlFatalErr(ctxt, XML_ERR_EXT_SUBSET_NOT_FINISHED, NULL); |
6822 | 0 | xmlHaltParser(ctxt); |
6823 | 0 | return; |
6824 | 0 | } |
6825 | 0 | SKIP_BLANKS; |
6826 | 0 | SHRINK; |
6827 | 0 | } |
6828 | | |
6829 | 0 | if (RAW != 0) { |
6830 | 0 | xmlFatalErr(ctxt, XML_ERR_EXT_SUBSET_NOT_FINISHED, NULL); |
6831 | 0 | } |
6832 | |
|
6833 | 0 | } |
6834 | | |
6835 | | /** |
6836 | | * xmlParseReference: |
6837 | | * @ctxt: an XML parser context |
6838 | | * |
6839 | | * DEPRECATED: Internal function, don't use. |
6840 | | * |
6841 | | * parse and handle entity references in content, depending on the SAX |
6842 | | * interface, this may end-up in a call to character() if this is a |
6843 | | * CharRef, a predefined entity, if there is no reference() callback. |
6844 | | * or if the parser was asked to switch to that mode. |
6845 | | * |
6846 | | * Always consumes '&'. |
6847 | | * |
6848 | | * [67] Reference ::= EntityRef | CharRef |
6849 | | */ |
6850 | | void |
6851 | 24.5k | xmlParseReference(xmlParserCtxtPtr ctxt) { |
6852 | 24.5k | xmlEntityPtr ent; |
6853 | 24.5k | xmlChar *val; |
6854 | 24.5k | int was_checked; |
6855 | 24.5k | xmlNodePtr list = NULL; |
6856 | 24.5k | xmlParserErrors ret = XML_ERR_OK; |
6857 | | |
6858 | | |
6859 | 24.5k | if (RAW != '&') |
6860 | 0 | return; |
6861 | | |
6862 | | /* |
6863 | | * Simple case of a CharRef |
6864 | | */ |
6865 | 24.5k | if (NXT(1) == '#') { |
6866 | 6.84k | int i = 0; |
6867 | 6.84k | xmlChar out[16]; |
6868 | 6.84k | int hex = NXT(2); |
6869 | 6.84k | int value = xmlParseCharRef(ctxt); |
6870 | | |
6871 | 6.84k | if (value == 0) |
6872 | 2.31k | return; |
6873 | 4.53k | if (ctxt->charset != XML_CHAR_ENCODING_UTF8) { |
6874 | | /* |
6875 | | * So we are using non-UTF-8 buffers |
6876 | | * Check that the char fit on 8bits, if not |
6877 | | * generate a CharRef. |
6878 | | */ |
6879 | 3.92k | if (value <= 0xFF) { |
6880 | 3.28k | out[0] = value; |
6881 | 3.28k | out[1] = 0; |
6882 | 3.28k | if ((ctxt->sax != NULL) && (ctxt->sax->characters != NULL) && |
6883 | 3.28k | (!ctxt->disableSAX)) |
6884 | 3.28k | ctxt->sax->characters(ctxt->userData, out, 1); |
6885 | 3.28k | } else { |
6886 | 633 | if ((hex == 'x') || (hex == 'X')) |
6887 | 187 | snprintf((char *)out, sizeof(out), "#x%X", value); |
6888 | 446 | else |
6889 | 446 | snprintf((char *)out, sizeof(out), "#%d", value); |
6890 | 633 | if ((ctxt->sax != NULL) && (ctxt->sax->reference != NULL) && |
6891 | 633 | (!ctxt->disableSAX)) |
6892 | 633 | ctxt->sax->reference(ctxt->userData, out); |
6893 | 633 | } |
6894 | 3.92k | } else { |
6895 | | /* |
6896 | | * Just encode the value in UTF-8 |
6897 | | */ |
6898 | 610 | COPY_BUF(0 ,out, i, value); |
6899 | 610 | out[i] = 0; |
6900 | 610 | if ((ctxt->sax != NULL) && (ctxt->sax->characters != NULL) && |
6901 | 610 | (!ctxt->disableSAX)) |
6902 | 610 | ctxt->sax->characters(ctxt->userData, out, i); |
6903 | 610 | } |
6904 | 4.53k | return; |
6905 | 6.84k | } |
6906 | | |
6907 | | /* |
6908 | | * We are seeing an entity reference |
6909 | | */ |
6910 | 17.6k | ent = xmlParseEntityRef(ctxt); |
6911 | 17.6k | if (ent == NULL) return; |
6912 | 1.81k | if (!ctxt->wellFormed) |
6913 | 1.80k | return; |
6914 | 4 | was_checked = ent->flags & XML_ENT_PARSED; |
6915 | | |
6916 | | /* special case of predefined entities */ |
6917 | 4 | if ((ent->name == NULL) || |
6918 | 4 | (ent->etype == XML_INTERNAL_PREDEFINED_ENTITY)) { |
6919 | 0 | val = ent->content; |
6920 | 0 | if (val == NULL) return; |
6921 | | /* |
6922 | | * inline the entity. |
6923 | | */ |
6924 | 0 | if ((ctxt->sax != NULL) && (ctxt->sax->characters != NULL) && |
6925 | 0 | (!ctxt->disableSAX)) |
6926 | 0 | ctxt->sax->characters(ctxt->userData, val, xmlStrlen(val)); |
6927 | 0 | return; |
6928 | 0 | } |
6929 | | |
6930 | | /* |
6931 | | * The first reference to the entity trigger a parsing phase |
6932 | | * where the ent->children is filled with the result from |
6933 | | * the parsing. |
6934 | | * Note: external parsed entities will not be loaded, it is not |
6935 | | * required for a non-validating parser, unless the parsing option |
6936 | | * of validating, or substituting entities were given. Doing so is |
6937 | | * far more secure as the parser will only process data coming from |
6938 | | * the document entity by default. |
6939 | | */ |
6940 | 4 | if (((ent->flags & XML_ENT_PARSED) == 0) && |
6941 | 4 | ((ent->etype != XML_EXTERNAL_GENERAL_PARSED_ENTITY) || |
6942 | 4 | (ctxt->options & (XML_PARSE_NOENT | XML_PARSE_DTDVALID)))) { |
6943 | 4 | unsigned long oldsizeentcopy = ctxt->sizeentcopy; |
6944 | | |
6945 | | /* |
6946 | | * This is a bit hackish but this seems the best |
6947 | | * way to make sure both SAX and DOM entity support |
6948 | | * behaves okay. |
6949 | | */ |
6950 | 4 | void *user_data; |
6951 | 4 | if (ctxt->userData == ctxt) |
6952 | 4 | user_data = NULL; |
6953 | 0 | else |
6954 | 0 | user_data = ctxt->userData; |
6955 | | |
6956 | | /* Avoid overflow as much as possible */ |
6957 | 4 | ctxt->sizeentcopy = 0; |
6958 | | |
6959 | 4 | if (ent->flags & XML_ENT_EXPANDING) { |
6960 | 0 | xmlFatalErr(ctxt, XML_ERR_ENTITY_LOOP, NULL); |
6961 | 0 | xmlHaltParser(ctxt); |
6962 | 0 | return; |
6963 | 0 | } |
6964 | | |
6965 | 4 | ent->flags |= XML_ENT_EXPANDING; |
6966 | | |
6967 | | /* |
6968 | | * Check that this entity is well formed |
6969 | | * 4.3.2: An internal general parsed entity is well-formed |
6970 | | * if its replacement text matches the production labeled |
6971 | | * content. |
6972 | | */ |
6973 | 4 | if (ent->etype == XML_INTERNAL_GENERAL_ENTITY) { |
6974 | 4 | ctxt->depth++; |
6975 | 4 | ret = xmlParseBalancedChunkMemoryInternal(ctxt, ent->content, |
6976 | 4 | user_data, &list); |
6977 | 4 | ctxt->depth--; |
6978 | | |
6979 | 4 | } else if (ent->etype == XML_EXTERNAL_GENERAL_PARSED_ENTITY) { |
6980 | 0 | ctxt->depth++; |
6981 | 0 | ret = xmlParseExternalEntityPrivate(ctxt->myDoc, ctxt, ctxt->sax, |
6982 | 0 | user_data, ctxt->depth, ent->URI, |
6983 | 0 | ent->ExternalID, &list); |
6984 | 0 | ctxt->depth--; |
6985 | 0 | } else { |
6986 | 0 | ret = XML_ERR_ENTITY_PE_INTERNAL; |
6987 | 0 | xmlErrMsgStr(ctxt, XML_ERR_INTERNAL_ERROR, |
6988 | 0 | "invalid entity type found\n", NULL); |
6989 | 0 | } |
6990 | | |
6991 | 4 | ent->flags &= ~XML_ENT_EXPANDING; |
6992 | 4 | ent->flags |= XML_ENT_PARSED | XML_ENT_CHECKED; |
6993 | 4 | ent->expandedSize = ctxt->sizeentcopy; |
6994 | 4 | if (ret == XML_ERR_ENTITY_LOOP) { |
6995 | 0 | xmlHaltParser(ctxt); |
6996 | 0 | xmlFreeNodeList(list); |
6997 | 0 | return; |
6998 | 0 | } |
6999 | 4 | if (xmlParserEntityCheck(ctxt, oldsizeentcopy)) { |
7000 | 0 | xmlFreeNodeList(list); |
7001 | 0 | return; |
7002 | 0 | } |
7003 | | |
7004 | 4 | if ((ret == XML_ERR_OK) && (list != NULL)) { |
7005 | 1 | ent->children = list; |
7006 | | /* |
7007 | | * Prune it directly in the generated document |
7008 | | * except for single text nodes. |
7009 | | */ |
7010 | 1 | if ((ctxt->replaceEntities == 0) || |
7011 | 1 | (ctxt->parseMode == XML_PARSE_READER) || |
7012 | 1 | ((list->type == XML_TEXT_NODE) && |
7013 | 1 | (list->next == NULL))) { |
7014 | 1 | ent->owner = 1; |
7015 | 3 | while (list != NULL) { |
7016 | 2 | list->parent = (xmlNodePtr) ent; |
7017 | 2 | if (list->doc != ent->doc) |
7018 | 0 | xmlSetTreeDoc(list, ent->doc); |
7019 | 2 | if (list->next == NULL) |
7020 | 1 | ent->last = list; |
7021 | 2 | list = list->next; |
7022 | 2 | } |
7023 | 1 | list = NULL; |
7024 | 1 | } else { |
7025 | 0 | ent->owner = 0; |
7026 | 0 | while (list != NULL) { |
7027 | 0 | list->parent = (xmlNodePtr) ctxt->node; |
7028 | 0 | list->doc = ctxt->myDoc; |
7029 | 0 | if (list->next == NULL) |
7030 | 0 | ent->last = list; |
7031 | 0 | list = list->next; |
7032 | 0 | } |
7033 | 0 | list = ent->children; |
7034 | | #ifdef LIBXML_LEGACY_ENABLED |
7035 | | if (ent->etype == XML_EXTERNAL_GENERAL_PARSED_ENTITY) |
7036 | | xmlAddEntityReference(ent, list, NULL); |
7037 | | #endif /* LIBXML_LEGACY_ENABLED */ |
7038 | 0 | } |
7039 | 3 | } else if ((ret != XML_ERR_OK) && |
7040 | 3 | (ret != XML_WAR_UNDECLARED_ENTITY)) { |
7041 | 3 | xmlFatalErrMsgStr(ctxt, XML_ERR_UNDECLARED_ENTITY, |
7042 | 3 | "Entity '%s' failed to parse\n", ent->name); |
7043 | 3 | if (ent->content != NULL) |
7044 | 3 | ent->content[0] = 0; |
7045 | 3 | } else if (list != NULL) { |
7046 | 0 | xmlFreeNodeList(list); |
7047 | 0 | list = NULL; |
7048 | 0 | } |
7049 | | |
7050 | | /* Prevent entity from being parsed and expanded twice (Bug 760367). */ |
7051 | 4 | was_checked = 0; |
7052 | 4 | } |
7053 | | |
7054 | | /* |
7055 | | * Now that the entity content has been gathered |
7056 | | * provide it to the application, this can take different forms based |
7057 | | * on the parsing modes. |
7058 | | */ |
7059 | 4 | if (ent->children == NULL) { |
7060 | | /* |
7061 | | * Probably running in SAX mode and the callbacks don't |
7062 | | * build the entity content. So unless we already went |
7063 | | * though parsing for first checking go though the entity |
7064 | | * content to generate callbacks associated to the entity |
7065 | | */ |
7066 | 3 | if (was_checked != 0) { |
7067 | 0 | void *user_data; |
7068 | | /* |
7069 | | * This is a bit hackish but this seems the best |
7070 | | * way to make sure both SAX and DOM entity support |
7071 | | * behaves okay. |
7072 | | */ |
7073 | 0 | if (ctxt->userData == ctxt) |
7074 | 0 | user_data = NULL; |
7075 | 0 | else |
7076 | 0 | user_data = ctxt->userData; |
7077 | |
|
7078 | 0 | if (ent->etype == XML_INTERNAL_GENERAL_ENTITY) { |
7079 | 0 | ctxt->depth++; |
7080 | 0 | ret = xmlParseBalancedChunkMemoryInternal(ctxt, |
7081 | 0 | ent->content, user_data, NULL); |
7082 | 0 | ctxt->depth--; |
7083 | 0 | } else if (ent->etype == |
7084 | 0 | XML_EXTERNAL_GENERAL_PARSED_ENTITY) { |
7085 | 0 | unsigned long oldsizeentities = ctxt->sizeentities; |
7086 | |
|
7087 | 0 | ctxt->depth++; |
7088 | 0 | ret = xmlParseExternalEntityPrivate(ctxt->myDoc, ctxt, |
7089 | 0 | ctxt->sax, user_data, ctxt->depth, |
7090 | 0 | ent->URI, ent->ExternalID, NULL); |
7091 | 0 | ctxt->depth--; |
7092 | | |
7093 | | /* Undo the change to sizeentities */ |
7094 | 0 | ctxt->sizeentities = oldsizeentities; |
7095 | 0 | } else { |
7096 | 0 | ret = XML_ERR_ENTITY_PE_INTERNAL; |
7097 | 0 | xmlErrMsgStr(ctxt, XML_ERR_INTERNAL_ERROR, |
7098 | 0 | "invalid entity type found\n", NULL); |
7099 | 0 | } |
7100 | 0 | if (ret == XML_ERR_ENTITY_LOOP) { |
7101 | 0 | xmlFatalErr(ctxt, XML_ERR_ENTITY_LOOP, NULL); |
7102 | 0 | return; |
7103 | 0 | } |
7104 | 0 | if (xmlParserEntityCheck(ctxt, 0)) |
7105 | 0 | return; |
7106 | 0 | } |
7107 | 3 | if ((ctxt->sax != NULL) && (ctxt->sax->reference != NULL) && |
7108 | 3 | (ctxt->replaceEntities == 0) && (!ctxt->disableSAX)) { |
7109 | | /* |
7110 | | * Entity reference callback comes second, it's somewhat |
7111 | | * superfluous but a compatibility to historical behaviour |
7112 | | */ |
7113 | 3 | ctxt->sax->reference(ctxt->userData, ent->name); |
7114 | 3 | } |
7115 | 3 | return; |
7116 | 3 | } |
7117 | | |
7118 | | /* |
7119 | | * We also check for amplification if entities aren't substituted. |
7120 | | * They might be expanded later. |
7121 | | */ |
7122 | 1 | if ((was_checked != 0) && |
7123 | 1 | (xmlParserEntityCheck(ctxt, ent->expandedSize))) |
7124 | 0 | return; |
7125 | | |
7126 | | /* |
7127 | | * If we didn't get any children for the entity being built |
7128 | | */ |
7129 | 1 | if ((ctxt->sax != NULL) && (ctxt->sax->reference != NULL) && |
7130 | 1 | (ctxt->replaceEntities == 0) && (!ctxt->disableSAX)) { |
7131 | | /* |
7132 | | * Create a node. |
7133 | | */ |
7134 | 1 | ctxt->sax->reference(ctxt->userData, ent->name); |
7135 | 1 | return; |
7136 | 1 | } |
7137 | | |
7138 | 0 | if (ctxt->replaceEntities) { |
7139 | | /* |
7140 | | * There is a problem on the handling of _private for entities |
7141 | | * (bug 155816): Should we copy the content of the field from |
7142 | | * the entity (possibly overwriting some value set by the user |
7143 | | * when a copy is created), should we leave it alone, or should |
7144 | | * we try to take care of different situations? The problem |
7145 | | * is exacerbated by the usage of this field by the xmlReader. |
7146 | | * To fix this bug, we look at _private on the created node |
7147 | | * and, if it's NULL, we copy in whatever was in the entity. |
7148 | | * If it's not NULL we leave it alone. This is somewhat of a |
7149 | | * hack - maybe we should have further tests to determine |
7150 | | * what to do. |
7151 | | */ |
7152 | 0 | if (ctxt->node != NULL) { |
7153 | | /* |
7154 | | * Seems we are generating the DOM content, do |
7155 | | * a simple tree copy for all references except the first |
7156 | | * In the first occurrence list contains the replacement. |
7157 | | */ |
7158 | 0 | if (((list == NULL) && (ent->owner == 0)) || |
7159 | 0 | (ctxt->parseMode == XML_PARSE_READER)) { |
7160 | 0 | xmlNodePtr nw = NULL, cur, firstChild = NULL; |
7161 | | |
7162 | | /* |
7163 | | * when operating on a reader, the entities definitions |
7164 | | * are always owning the entities subtree. |
7165 | | if (ctxt->parseMode == XML_PARSE_READER) |
7166 | | ent->owner = 1; |
7167 | | */ |
7168 | |
|
7169 | 0 | cur = ent->children; |
7170 | 0 | while (cur != NULL) { |
7171 | 0 | nw = xmlDocCopyNode(cur, ctxt->myDoc, 1); |
7172 | 0 | if (nw != NULL) { |
7173 | 0 | if (nw->_private == NULL) |
7174 | 0 | nw->_private = cur->_private; |
7175 | 0 | if (firstChild == NULL){ |
7176 | 0 | firstChild = nw; |
7177 | 0 | } |
7178 | 0 | nw = xmlAddChild(ctxt->node, nw); |
7179 | 0 | } |
7180 | 0 | if (cur == ent->last) { |
7181 | | /* |
7182 | | * needed to detect some strange empty |
7183 | | * node cases in the reader tests |
7184 | | */ |
7185 | 0 | if ((ctxt->parseMode == XML_PARSE_READER) && |
7186 | 0 | (nw != NULL) && |
7187 | 0 | (nw->type == XML_ELEMENT_NODE) && |
7188 | 0 | (nw->children == NULL)) |
7189 | 0 | nw->extra = 1; |
7190 | |
|
7191 | 0 | break; |
7192 | 0 | } |
7193 | 0 | cur = cur->next; |
7194 | 0 | } |
7195 | | #ifdef LIBXML_LEGACY_ENABLED |
7196 | | if (ent->etype == XML_EXTERNAL_GENERAL_PARSED_ENTITY) |
7197 | | xmlAddEntityReference(ent, firstChild, nw); |
7198 | | #endif /* LIBXML_LEGACY_ENABLED */ |
7199 | 0 | } else if ((list == NULL) || (ctxt->inputNr > 0)) { |
7200 | 0 | xmlNodePtr nw = NULL, cur, next, last, |
7201 | 0 | firstChild = NULL; |
7202 | | |
7203 | | /* |
7204 | | * Copy the entity child list and make it the new |
7205 | | * entity child list. The goal is to make sure any |
7206 | | * ID or REF referenced will be the one from the |
7207 | | * document content and not the entity copy. |
7208 | | */ |
7209 | 0 | cur = ent->children; |
7210 | 0 | ent->children = NULL; |
7211 | 0 | last = ent->last; |
7212 | 0 | ent->last = NULL; |
7213 | 0 | while (cur != NULL) { |
7214 | 0 | next = cur->next; |
7215 | 0 | cur->next = NULL; |
7216 | 0 | cur->parent = NULL; |
7217 | 0 | nw = xmlDocCopyNode(cur, ctxt->myDoc, 1); |
7218 | 0 | if (nw != NULL) { |
7219 | 0 | if (nw->_private == NULL) |
7220 | 0 | nw->_private = cur->_private; |
7221 | 0 | if (firstChild == NULL){ |
7222 | 0 | firstChild = cur; |
7223 | 0 | } |
7224 | 0 | xmlAddChild((xmlNodePtr) ent, nw); |
7225 | 0 | } |
7226 | 0 | xmlAddChild(ctxt->node, cur); |
7227 | 0 | if (cur == last) |
7228 | 0 | break; |
7229 | 0 | cur = next; |
7230 | 0 | } |
7231 | 0 | if (ent->owner == 0) |
7232 | 0 | ent->owner = 1; |
7233 | | #ifdef LIBXML_LEGACY_ENABLED |
7234 | | if (ent->etype == XML_EXTERNAL_GENERAL_PARSED_ENTITY) |
7235 | | xmlAddEntityReference(ent, firstChild, nw); |
7236 | | #endif /* LIBXML_LEGACY_ENABLED */ |
7237 | 0 | } else { |
7238 | 0 | const xmlChar *nbktext; |
7239 | | |
7240 | | /* |
7241 | | * the name change is to avoid coalescing of the |
7242 | | * node with a possible previous text one which |
7243 | | * would make ent->children a dangling pointer |
7244 | | */ |
7245 | 0 | nbktext = xmlDictLookup(ctxt->dict, BAD_CAST "nbktext", |
7246 | 0 | -1); |
7247 | 0 | if (ent->children->type == XML_TEXT_NODE) |
7248 | 0 | ent->children->name = nbktext; |
7249 | 0 | if ((ent->last != ent->children) && |
7250 | 0 | (ent->last->type == XML_TEXT_NODE)) |
7251 | 0 | ent->last->name = nbktext; |
7252 | 0 | xmlAddChildList(ctxt->node, ent->children); |
7253 | 0 | } |
7254 | | |
7255 | | /* |
7256 | | * This is to avoid a nasty side effect, see |
7257 | | * characters() in SAX.c |
7258 | | */ |
7259 | 0 | ctxt->nodemem = 0; |
7260 | 0 | ctxt->nodelen = 0; |
7261 | 0 | return; |
7262 | 0 | } |
7263 | 0 | } |
7264 | 0 | } |
7265 | | |
7266 | | /** |
7267 | | * xmlParseEntityRef: |
7268 | | * @ctxt: an XML parser context |
7269 | | * |
7270 | | * DEPRECATED: Internal function, don't use. |
7271 | | * |
7272 | | * Parse an entitiy reference. Always consumes '&'. |
7273 | | * |
7274 | | * [68] EntityRef ::= '&' Name ';' |
7275 | | * |
7276 | | * [ WFC: Entity Declared ] |
7277 | | * In a document without any DTD, a document with only an internal DTD |
7278 | | * subset which contains no parameter entity references, or a document |
7279 | | * with "standalone='yes'", the Name given in the entity reference |
7280 | | * must match that in an entity declaration, except that well-formed |
7281 | | * documents need not declare any of the following entities: amp, lt, |
7282 | | * gt, apos, quot. The declaration of a parameter entity must precede |
7283 | | * any reference to it. Similarly, the declaration of a general entity |
7284 | | * must precede any reference to it which appears in a default value in an |
7285 | | * attribute-list declaration. Note that if entities are declared in the |
7286 | | * external subset or in external parameter entities, a non-validating |
7287 | | * processor is not obligated to read and process their declarations; |
7288 | | * for such documents, the rule that an entity must be declared is a |
7289 | | * well-formedness constraint only if standalone='yes'. |
7290 | | * |
7291 | | * [ WFC: Parsed Entity ] |
7292 | | * An entity reference must not contain the name of an unparsed entity |
7293 | | * |
7294 | | * Returns the xmlEntityPtr if found, or NULL otherwise. |
7295 | | */ |
7296 | | xmlEntityPtr |
7297 | 64.4k | xmlParseEntityRef(xmlParserCtxtPtr ctxt) { |
7298 | 64.4k | const xmlChar *name; |
7299 | 64.4k | xmlEntityPtr ent = NULL; |
7300 | | |
7301 | 64.4k | GROW; |
7302 | 64.4k | if (ctxt->instate == XML_PARSER_EOF) |
7303 | 0 | return(NULL); |
7304 | | |
7305 | 64.4k | if (RAW != '&') |
7306 | 0 | return(NULL); |
7307 | 64.4k | NEXT; |
7308 | 64.4k | name = xmlParseName(ctxt); |
7309 | 64.4k | if (name == NULL) { |
7310 | 41.5k | xmlFatalErrMsg(ctxt, XML_ERR_NAME_REQUIRED, |
7311 | 41.5k | "xmlParseEntityRef: no name\n"); |
7312 | 41.5k | return(NULL); |
7313 | 41.5k | } |
7314 | 22.8k | if (RAW != ';') { |
7315 | 2.87k | xmlFatalErr(ctxt, XML_ERR_ENTITYREF_SEMICOL_MISSING, NULL); |
7316 | 2.87k | return(NULL); |
7317 | 2.87k | } |
7318 | 20.0k | NEXT; |
7319 | | |
7320 | | /* |
7321 | | * Predefined entities override any extra definition |
7322 | | */ |
7323 | 20.0k | if ((ctxt->options & XML_PARSE_OLDSAX) == 0) { |
7324 | 20.0k | ent = xmlGetPredefinedEntity(name); |
7325 | 20.0k | if (ent != NULL) |
7326 | 9.57k | return(ent); |
7327 | 20.0k | } |
7328 | | |
7329 | | /* |
7330 | | * Ask first SAX for entity resolution, otherwise try the |
7331 | | * entities which may have stored in the parser context. |
7332 | | */ |
7333 | 10.4k | if (ctxt->sax != NULL) { |
7334 | 10.4k | if (ctxt->sax->getEntity != NULL) |
7335 | 10.4k | ent = ctxt->sax->getEntity(ctxt->userData, name); |
7336 | 10.4k | if ((ctxt->wellFormed == 1 ) && (ent == NULL) && |
7337 | 10.4k | (ctxt->options & XML_PARSE_OLDSAX)) |
7338 | 0 | ent = xmlGetPredefinedEntity(name); |
7339 | 10.4k | if ((ctxt->wellFormed == 1 ) && (ent == NULL) && |
7340 | 10.4k | (ctxt->userData==ctxt)) { |
7341 | 0 | ent = xmlSAX2GetEntity(ctxt, name); |
7342 | 0 | } |
7343 | 10.4k | } |
7344 | 10.4k | if (ctxt->instate == XML_PARSER_EOF) |
7345 | 0 | return(NULL); |
7346 | | /* |
7347 | | * [ WFC: Entity Declared ] |
7348 | | * In a document without any DTD, a document with only an |
7349 | | * internal DTD subset which contains no parameter entity |
7350 | | * references, or a document with "standalone='yes'", the |
7351 | | * Name given in the entity reference must match that in an |
7352 | | * entity declaration, except that well-formed documents |
7353 | | * need not declare any of the following entities: amp, lt, |
7354 | | * gt, apos, quot. |
7355 | | * The declaration of a parameter entity must precede any |
7356 | | * reference to it. |
7357 | | * Similarly, the declaration of a general entity must |
7358 | | * precede any reference to it which appears in a default |
7359 | | * value in an attribute-list declaration. Note that if |
7360 | | * entities are declared in the external subset or in |
7361 | | * external parameter entities, a non-validating processor |
7362 | | * is not obligated to read and process their declarations; |
7363 | | * for such documents, the rule that an entity must be |
7364 | | * declared is a well-formedness constraint only if |
7365 | | * standalone='yes'. |
7366 | | */ |
7367 | 10.4k | if (ent == NULL) { |
7368 | 821 | if ((ctxt->standalone == 1) || |
7369 | 821 | ((ctxt->hasExternalSubset == 0) && |
7370 | 821 | (ctxt->hasPErefs == 0))) { |
7371 | 821 | xmlFatalErrMsgStr(ctxt, XML_ERR_UNDECLARED_ENTITY, |
7372 | 821 | "Entity '%s' not defined\n", name); |
7373 | 821 | } else { |
7374 | 0 | xmlErrMsgStr(ctxt, XML_WAR_UNDECLARED_ENTITY, |
7375 | 0 | "Entity '%s' not defined\n", name); |
7376 | 0 | if ((ctxt->inSubset == 0) && |
7377 | 0 | (ctxt->sax != NULL) && |
7378 | 0 | (ctxt->sax->reference != NULL)) { |
7379 | 0 | ctxt->sax->reference(ctxt->userData, name); |
7380 | 0 | } |
7381 | 0 | } |
7382 | 821 | ctxt->valid = 0; |
7383 | 821 | } |
7384 | | |
7385 | | /* |
7386 | | * [ WFC: Parsed Entity ] |
7387 | | * An entity reference must not contain the name of an |
7388 | | * unparsed entity |
7389 | | */ |
7390 | 9.60k | else if (ent->etype == XML_EXTERNAL_GENERAL_UNPARSED_ENTITY) { |
7391 | 0 | xmlFatalErrMsgStr(ctxt, XML_ERR_UNPARSED_ENTITY, |
7392 | 0 | "Entity reference to unparsed entity %s\n", name); |
7393 | 0 | } |
7394 | | |
7395 | | /* |
7396 | | * [ WFC: No External Entity References ] |
7397 | | * Attribute values cannot contain direct or indirect |
7398 | | * entity references to external entities. |
7399 | | */ |
7400 | 9.60k | else if ((ctxt->instate == XML_PARSER_ATTRIBUTE_VALUE) && |
7401 | 9.60k | (ent->etype == XML_EXTERNAL_GENERAL_PARSED_ENTITY)) { |
7402 | 6.68k | xmlFatalErrMsgStr(ctxt, XML_ERR_ENTITY_IS_EXTERNAL, |
7403 | 6.68k | "Attribute references external entity '%s'\n", name); |
7404 | 6.68k | } |
7405 | | /* |
7406 | | * [ WFC: No < in Attribute Values ] |
7407 | | * The replacement text of any entity referred to directly or |
7408 | | * indirectly in an attribute value (other than "<") must |
7409 | | * not contain a <. |
7410 | | */ |
7411 | 2.91k | else if ((ctxt->instate == XML_PARSER_ATTRIBUTE_VALUE) && |
7412 | 2.91k | (ent->etype != XML_INTERNAL_PREDEFINED_ENTITY)) { |
7413 | 1.11k | if ((ent->flags & XML_ENT_CHECKED_LT) == 0) { |
7414 | 37 | if ((ent->content != NULL) && (xmlStrchr(ent->content, '<'))) |
7415 | 37 | ent->flags |= XML_ENT_CONTAINS_LT; |
7416 | 37 | ent->flags |= XML_ENT_CHECKED_LT; |
7417 | 37 | } |
7418 | 1.11k | if (ent->flags & XML_ENT_CONTAINS_LT) |
7419 | 1.11k | xmlFatalErrMsgStr(ctxt, XML_ERR_LT_IN_ATTRIBUTE, |
7420 | 1.11k | "'<' in entity '%s' is not allowed in attributes " |
7421 | 1.11k | "values\n", name); |
7422 | 1.11k | } |
7423 | | |
7424 | | /* |
7425 | | * Internal check, no parameter entities here ... |
7426 | | */ |
7427 | 1.79k | else { |
7428 | 1.79k | switch (ent->etype) { |
7429 | 0 | case XML_INTERNAL_PARAMETER_ENTITY: |
7430 | 0 | case XML_EXTERNAL_PARAMETER_ENTITY: |
7431 | 0 | xmlFatalErrMsgStr(ctxt, XML_ERR_ENTITY_IS_PARAMETER, |
7432 | 0 | "Attempt to reference the parameter entity '%s'\n", |
7433 | 0 | name); |
7434 | 0 | break; |
7435 | 1.79k | default: |
7436 | 1.79k | break; |
7437 | 1.79k | } |
7438 | 1.79k | } |
7439 | | |
7440 | | /* |
7441 | | * [ WFC: No Recursion ] |
7442 | | * A parsed entity must not contain a recursive reference |
7443 | | * to itself, either directly or indirectly. |
7444 | | * Done somewhere else |
7445 | | */ |
7446 | 10.4k | return(ent); |
7447 | 10.4k | } |
7448 | | |
7449 | | /** |
7450 | | * xmlParseStringEntityRef: |
7451 | | * @ctxt: an XML parser context |
7452 | | * @str: a pointer to an index in the string |
7453 | | * |
7454 | | * parse ENTITY references declarations, but this version parses it from |
7455 | | * a string value. |
7456 | | * |
7457 | | * [68] EntityRef ::= '&' Name ';' |
7458 | | * |
7459 | | * [ WFC: Entity Declared ] |
7460 | | * In a document without any DTD, a document with only an internal DTD |
7461 | | * subset which contains no parameter entity references, or a document |
7462 | | * with "standalone='yes'", the Name given in the entity reference |
7463 | | * must match that in an entity declaration, except that well-formed |
7464 | | * documents need not declare any of the following entities: amp, lt, |
7465 | | * gt, apos, quot. The declaration of a parameter entity must precede |
7466 | | * any reference to it. Similarly, the declaration of a general entity |
7467 | | * must precede any reference to it which appears in a default value in an |
7468 | | * attribute-list declaration. Note that if entities are declared in the |
7469 | | * external subset or in external parameter entities, a non-validating |
7470 | | * processor is not obligated to read and process their declarations; |
7471 | | * for such documents, the rule that an entity must be declared is a |
7472 | | * well-formedness constraint only if standalone='yes'. |
7473 | | * |
7474 | | * [ WFC: Parsed Entity ] |
7475 | | * An entity reference must not contain the name of an unparsed entity |
7476 | | * |
7477 | | * Returns the xmlEntityPtr if found, or NULL otherwise. The str pointer |
7478 | | * is updated to the current location in the string. |
7479 | | */ |
7480 | | static xmlEntityPtr |
7481 | 11.9k | xmlParseStringEntityRef(xmlParserCtxtPtr ctxt, const xmlChar ** str) { |
7482 | 11.9k | xmlChar *name; |
7483 | 11.9k | const xmlChar *ptr; |
7484 | 11.9k | xmlChar cur; |
7485 | 11.9k | xmlEntityPtr ent = NULL; |
7486 | | |
7487 | 11.9k | if ((str == NULL) || (*str == NULL)) |
7488 | 0 | return(NULL); |
7489 | 11.9k | ptr = *str; |
7490 | 11.9k | cur = *ptr; |
7491 | 11.9k | if (cur != '&') |
7492 | 0 | return(NULL); |
7493 | | |
7494 | 11.9k | ptr++; |
7495 | 11.9k | name = xmlParseStringName(ctxt, &ptr); |
7496 | 11.9k | if (name == NULL) { |
7497 | 6.60k | xmlFatalErrMsg(ctxt, XML_ERR_NAME_REQUIRED, |
7498 | 6.60k | "xmlParseStringEntityRef: no name\n"); |
7499 | 6.60k | *str = ptr; |
7500 | 6.60k | return(NULL); |
7501 | 6.60k | } |
7502 | 5.35k | if (*ptr != ';') { |
7503 | 1.42k | xmlFatalErr(ctxt, XML_ERR_ENTITYREF_SEMICOL_MISSING, NULL); |
7504 | 1.42k | xmlFree(name); |
7505 | 1.42k | *str = ptr; |
7506 | 1.42k | return(NULL); |
7507 | 1.42k | } |
7508 | 3.93k | ptr++; |
7509 | | |
7510 | | |
7511 | | /* |
7512 | | * Predefined entities override any extra definition |
7513 | | */ |
7514 | 3.93k | if ((ctxt->options & XML_PARSE_OLDSAX) == 0) { |
7515 | 3.93k | ent = xmlGetPredefinedEntity(name); |
7516 | 3.93k | if (ent != NULL) { |
7517 | 0 | xmlFree(name); |
7518 | 0 | *str = ptr; |
7519 | 0 | return(ent); |
7520 | 0 | } |
7521 | 3.93k | } |
7522 | | |
7523 | | /* |
7524 | | * Ask first SAX for entity resolution, otherwise try the |
7525 | | * entities which may have stored in the parser context. |
7526 | | */ |
7527 | 3.93k | if (ctxt->sax != NULL) { |
7528 | 3.93k | if (ctxt->sax->getEntity != NULL) |
7529 | 3.93k | ent = ctxt->sax->getEntity(ctxt->userData, name); |
7530 | 3.93k | if ((ent == NULL) && (ctxt->options & XML_PARSE_OLDSAX)) |
7531 | 0 | ent = xmlGetPredefinedEntity(name); |
7532 | 3.93k | if ((ent == NULL) && (ctxt->userData==ctxt)) { |
7533 | 3.93k | ent = xmlSAX2GetEntity(ctxt, name); |
7534 | 3.93k | } |
7535 | 3.93k | } |
7536 | 3.93k | if (ctxt->instate == XML_PARSER_EOF) { |
7537 | 0 | xmlFree(name); |
7538 | 0 | return(NULL); |
7539 | 0 | } |
7540 | | |
7541 | | /* |
7542 | | * [ WFC: Entity Declared ] |
7543 | | * In a document without any DTD, a document with only an |
7544 | | * internal DTD subset which contains no parameter entity |
7545 | | * references, or a document with "standalone='yes'", the |
7546 | | * Name given in the entity reference must match that in an |
7547 | | * entity declaration, except that well-formed documents |
7548 | | * need not declare any of the following entities: amp, lt, |
7549 | | * gt, apos, quot. |
7550 | | * The declaration of a parameter entity must precede any |
7551 | | * reference to it. |
7552 | | * Similarly, the declaration of a general entity must |
7553 | | * precede any reference to it which appears in a default |
7554 | | * value in an attribute-list declaration. Note that if |
7555 | | * entities are declared in the external subset or in |
7556 | | * external parameter entities, a non-validating processor |
7557 | | * is not obligated to read and process their declarations; |
7558 | | * for such documents, the rule that an entity must be |
7559 | | * declared is a well-formedness constraint only if |
7560 | | * standalone='yes'. |
7561 | | */ |
7562 | 3.93k | if (ent == NULL) { |
7563 | 3.93k | if ((ctxt->standalone == 1) || |
7564 | 3.93k | ((ctxt->hasExternalSubset == 0) && |
7565 | 3.93k | (ctxt->hasPErefs == 0))) { |
7566 | 3.93k | xmlFatalErrMsgStr(ctxt, XML_ERR_UNDECLARED_ENTITY, |
7567 | 3.93k | "Entity '%s' not defined\n", name); |
7568 | 3.93k | } else { |
7569 | 0 | xmlErrMsgStr(ctxt, XML_WAR_UNDECLARED_ENTITY, |
7570 | 0 | "Entity '%s' not defined\n", |
7571 | 0 | name); |
7572 | 0 | } |
7573 | | /* TODO ? check regressions ctxt->valid = 0; */ |
7574 | 3.93k | } |
7575 | | |
7576 | | /* |
7577 | | * [ WFC: Parsed Entity ] |
7578 | | * An entity reference must not contain the name of an |
7579 | | * unparsed entity |
7580 | | */ |
7581 | 0 | else if (ent->etype == XML_EXTERNAL_GENERAL_UNPARSED_ENTITY) { |
7582 | 0 | xmlFatalErrMsgStr(ctxt, XML_ERR_UNPARSED_ENTITY, |
7583 | 0 | "Entity reference to unparsed entity %s\n", name); |
7584 | 0 | } |
7585 | | |
7586 | | /* |
7587 | | * [ WFC: No External Entity References ] |
7588 | | * Attribute values cannot contain direct or indirect |
7589 | | * entity references to external entities. |
7590 | | */ |
7591 | 0 | else if ((ctxt->instate == XML_PARSER_ATTRIBUTE_VALUE) && |
7592 | 0 | (ent->etype == XML_EXTERNAL_GENERAL_PARSED_ENTITY)) { |
7593 | 0 | xmlFatalErrMsgStr(ctxt, XML_ERR_ENTITY_IS_EXTERNAL, |
7594 | 0 | "Attribute references external entity '%s'\n", name); |
7595 | 0 | } |
7596 | | /* |
7597 | | * [ WFC: No < in Attribute Values ] |
7598 | | * The replacement text of any entity referred to directly or |
7599 | | * indirectly in an attribute value (other than "<") must |
7600 | | * not contain a <. |
7601 | | */ |
7602 | 0 | else if ((ctxt->instate == XML_PARSER_ATTRIBUTE_VALUE) && |
7603 | 0 | (ent->etype != XML_INTERNAL_PREDEFINED_ENTITY)) { |
7604 | 0 | if ((ent->flags & XML_ENT_CHECKED_LT) == 0) { |
7605 | 0 | if ((ent->content != NULL) && (xmlStrchr(ent->content, '<'))) |
7606 | 0 | ent->flags |= XML_ENT_CONTAINS_LT; |
7607 | 0 | ent->flags |= XML_ENT_CHECKED_LT; |
7608 | 0 | } |
7609 | 0 | if (ent->flags & XML_ENT_CONTAINS_LT) |
7610 | 0 | xmlFatalErrMsgStr(ctxt, XML_ERR_LT_IN_ATTRIBUTE, |
7611 | 0 | "'<' in entity '%s' is not allowed in attributes " |
7612 | 0 | "values\n", name); |
7613 | 0 | } |
7614 | | |
7615 | | /* |
7616 | | * Internal check, no parameter entities here ... |
7617 | | */ |
7618 | 0 | else { |
7619 | 0 | switch (ent->etype) { |
7620 | 0 | case XML_INTERNAL_PARAMETER_ENTITY: |
7621 | 0 | case XML_EXTERNAL_PARAMETER_ENTITY: |
7622 | 0 | xmlFatalErrMsgStr(ctxt, XML_ERR_ENTITY_IS_PARAMETER, |
7623 | 0 | "Attempt to reference the parameter entity '%s'\n", |
7624 | 0 | name); |
7625 | 0 | break; |
7626 | 0 | default: |
7627 | 0 | break; |
7628 | 0 | } |
7629 | 0 | } |
7630 | | |
7631 | | /* |
7632 | | * [ WFC: No Recursion ] |
7633 | | * A parsed entity must not contain a recursive reference |
7634 | | * to itself, either directly or indirectly. |
7635 | | * Done somewhere else |
7636 | | */ |
7637 | | |
7638 | 3.93k | xmlFree(name); |
7639 | 3.93k | *str = ptr; |
7640 | 3.93k | return(ent); |
7641 | 3.93k | } |
7642 | | |
7643 | | /** |
7644 | | * xmlParsePEReference: |
7645 | | * @ctxt: an XML parser context |
7646 | | * |
7647 | | * DEPRECATED: Internal function, don't use. |
7648 | | * |
7649 | | * Parse a parameter entity reference. Always consumes '%'. |
7650 | | * |
7651 | | * The entity content is handled directly by pushing it's content as |
7652 | | * a new input stream. |
7653 | | * |
7654 | | * [69] PEReference ::= '%' Name ';' |
7655 | | * |
7656 | | * [ WFC: No Recursion ] |
7657 | | * A parsed entity must not contain a recursive |
7658 | | * reference to itself, either directly or indirectly. |
7659 | | * |
7660 | | * [ WFC: Entity Declared ] |
7661 | | * In a document without any DTD, a document with only an internal DTD |
7662 | | * subset which contains no parameter entity references, or a document |
7663 | | * with "standalone='yes'", ... ... The declaration of a parameter |
7664 | | * entity must precede any reference to it... |
7665 | | * |
7666 | | * [ VC: Entity Declared ] |
7667 | | * In a document with an external subset or external parameter entities |
7668 | | * with "standalone='no'", ... ... The declaration of a parameter entity |
7669 | | * must precede any reference to it... |
7670 | | * |
7671 | | * [ WFC: In DTD ] |
7672 | | * Parameter-entity references may only appear in the DTD. |
7673 | | * NOTE: misleading but this is handled. |
7674 | | */ |
7675 | | void |
7676 | | xmlParsePEReference(xmlParserCtxtPtr ctxt) |
7677 | 0 | { |
7678 | 0 | const xmlChar *name; |
7679 | 0 | xmlEntityPtr entity = NULL; |
7680 | 0 | xmlParserInputPtr input; |
7681 | |
|
7682 | 0 | if (RAW != '%') |
7683 | 0 | return; |
7684 | 0 | NEXT; |
7685 | 0 | name = xmlParseName(ctxt); |
7686 | 0 | if (name == NULL) { |
7687 | 0 | xmlFatalErrMsg(ctxt, XML_ERR_PEREF_NO_NAME, "PEReference: no name\n"); |
7688 | 0 | return; |
7689 | 0 | } |
7690 | 0 | if (xmlParserDebugEntities) |
7691 | 0 | xmlGenericError(xmlGenericErrorContext, |
7692 | 0 | "PEReference: %s\n", name); |
7693 | 0 | if (RAW != ';') { |
7694 | 0 | xmlFatalErr(ctxt, XML_ERR_PEREF_SEMICOL_MISSING, NULL); |
7695 | 0 | return; |
7696 | 0 | } |
7697 | | |
7698 | 0 | NEXT; |
7699 | | |
7700 | | /* |
7701 | | * Request the entity from SAX |
7702 | | */ |
7703 | 0 | if ((ctxt->sax != NULL) && |
7704 | 0 | (ctxt->sax->getParameterEntity != NULL)) |
7705 | 0 | entity = ctxt->sax->getParameterEntity(ctxt->userData, name); |
7706 | 0 | if (ctxt->instate == XML_PARSER_EOF) |
7707 | 0 | return; |
7708 | 0 | if (entity == NULL) { |
7709 | | /* |
7710 | | * [ WFC: Entity Declared ] |
7711 | | * In a document without any DTD, a document with only an |
7712 | | * internal DTD subset which contains no parameter entity |
7713 | | * references, or a document with "standalone='yes'", ... |
7714 | | * ... The declaration of a parameter entity must precede |
7715 | | * any reference to it... |
7716 | | */ |
7717 | 0 | if ((ctxt->standalone == 1) || |
7718 | 0 | ((ctxt->hasExternalSubset == 0) && |
7719 | 0 | (ctxt->hasPErefs == 0))) { |
7720 | 0 | xmlFatalErrMsgStr(ctxt, XML_ERR_UNDECLARED_ENTITY, |
7721 | 0 | "PEReference: %%%s; not found\n", |
7722 | 0 | name); |
7723 | 0 | } else { |
7724 | | /* |
7725 | | * [ VC: Entity Declared ] |
7726 | | * In a document with an external subset or external |
7727 | | * parameter entities with "standalone='no'", ... |
7728 | | * ... The declaration of a parameter entity must |
7729 | | * precede any reference to it... |
7730 | | */ |
7731 | 0 | if ((ctxt->validate) && (ctxt->vctxt.error != NULL)) { |
7732 | 0 | xmlValidityError(ctxt, XML_WAR_UNDECLARED_ENTITY, |
7733 | 0 | "PEReference: %%%s; not found\n", |
7734 | 0 | name, NULL); |
7735 | 0 | } else |
7736 | 0 | xmlWarningMsg(ctxt, XML_WAR_UNDECLARED_ENTITY, |
7737 | 0 | "PEReference: %%%s; not found\n", |
7738 | 0 | name, NULL); |
7739 | 0 | ctxt->valid = 0; |
7740 | 0 | } |
7741 | 0 | } else { |
7742 | | /* |
7743 | | * Internal checking in case the entity quest barfed |
7744 | | */ |
7745 | 0 | if ((entity->etype != XML_INTERNAL_PARAMETER_ENTITY) && |
7746 | 0 | (entity->etype != XML_EXTERNAL_PARAMETER_ENTITY)) { |
7747 | 0 | xmlWarningMsg(ctxt, XML_WAR_UNDECLARED_ENTITY, |
7748 | 0 | "Internal: %%%s; is not a parameter entity\n", |
7749 | 0 | name, NULL); |
7750 | 0 | } else { |
7751 | 0 | xmlChar start[4]; |
7752 | 0 | xmlCharEncoding enc; |
7753 | 0 | unsigned long parentConsumed; |
7754 | 0 | xmlEntityPtr oldEnt; |
7755 | |
|
7756 | 0 | if ((entity->etype == XML_EXTERNAL_PARAMETER_ENTITY) && |
7757 | 0 | ((ctxt->options & XML_PARSE_NOENT) == 0) && |
7758 | 0 | ((ctxt->options & XML_PARSE_DTDVALID) == 0) && |
7759 | 0 | ((ctxt->options & XML_PARSE_DTDLOAD) == 0) && |
7760 | 0 | ((ctxt->options & XML_PARSE_DTDATTR) == 0) && |
7761 | 0 | (ctxt->replaceEntities == 0) && |
7762 | 0 | (ctxt->validate == 0)) |
7763 | 0 | return; |
7764 | | |
7765 | 0 | if (entity->flags & XML_ENT_EXPANDING) { |
7766 | 0 | xmlFatalErr(ctxt, XML_ERR_ENTITY_LOOP, NULL); |
7767 | 0 | xmlHaltParser(ctxt); |
7768 | 0 | return; |
7769 | 0 | } |
7770 | | |
7771 | | /* Must be computed from old input before pushing new input. */ |
7772 | 0 | parentConsumed = ctxt->input->parentConsumed; |
7773 | 0 | oldEnt = ctxt->input->entity; |
7774 | 0 | if ((oldEnt == NULL) || |
7775 | 0 | ((oldEnt->etype == XML_EXTERNAL_PARAMETER_ENTITY) && |
7776 | 0 | ((oldEnt->flags & XML_ENT_PARSED) == 0))) { |
7777 | 0 | xmlSaturatedAdd(&parentConsumed, ctxt->input->consumed); |
7778 | 0 | xmlSaturatedAddSizeT(&parentConsumed, |
7779 | 0 | ctxt->input->cur - ctxt->input->base); |
7780 | 0 | } |
7781 | |
|
7782 | 0 | input = xmlNewEntityInputStream(ctxt, entity); |
7783 | 0 | if (xmlPushInput(ctxt, input) < 0) { |
7784 | 0 | xmlFreeInputStream(input); |
7785 | 0 | return; |
7786 | 0 | } |
7787 | | |
7788 | 0 | entity->flags |= XML_ENT_EXPANDING; |
7789 | |
|
7790 | 0 | input->parentConsumed = parentConsumed; |
7791 | |
|
7792 | 0 | if (entity->etype == XML_EXTERNAL_PARAMETER_ENTITY) { |
7793 | | /* |
7794 | | * Get the 4 first bytes and decode the charset |
7795 | | * if enc != XML_CHAR_ENCODING_NONE |
7796 | | * plug some encoding conversion routines. |
7797 | | * Note that, since we may have some non-UTF8 |
7798 | | * encoding (like UTF16, bug 135229), the 'length' |
7799 | | * is not known, but we can calculate based upon |
7800 | | * the amount of data in the buffer. |
7801 | | */ |
7802 | 0 | GROW |
7803 | 0 | if (ctxt->instate == XML_PARSER_EOF) |
7804 | 0 | return; |
7805 | 0 | if ((ctxt->input->end - ctxt->input->cur)>=4) { |
7806 | 0 | start[0] = RAW; |
7807 | 0 | start[1] = NXT(1); |
7808 | 0 | start[2] = NXT(2); |
7809 | 0 | start[3] = NXT(3); |
7810 | 0 | enc = xmlDetectCharEncoding(start, 4); |
7811 | 0 | if (enc != XML_CHAR_ENCODING_NONE) { |
7812 | 0 | xmlSwitchEncoding(ctxt, enc); |
7813 | 0 | } |
7814 | 0 | } |
7815 | |
|
7816 | 0 | if ((CMP5(CUR_PTR, '<', '?', 'x', 'm', 'l')) && |
7817 | 0 | (IS_BLANK_CH(NXT(5)))) { |
7818 | 0 | xmlParseTextDecl(ctxt); |
7819 | 0 | } |
7820 | 0 | } |
7821 | 0 | } |
7822 | 0 | } |
7823 | 0 | ctxt->hasPErefs = 1; |
7824 | 0 | } |
7825 | | |
7826 | | /** |
7827 | | * xmlLoadEntityContent: |
7828 | | * @ctxt: an XML parser context |
7829 | | * @entity: an unloaded system entity |
7830 | | * |
7831 | | * Load the original content of the given system entity from the |
7832 | | * ExternalID/SystemID given. This is to be used for Included in Literal |
7833 | | * http://www.w3.org/TR/REC-xml/#inliteral processing of entities references |
7834 | | * |
7835 | | * Returns 0 in case of success and -1 in case of failure |
7836 | | */ |
7837 | | static int |
7838 | 0 | xmlLoadEntityContent(xmlParserCtxtPtr ctxt, xmlEntityPtr entity) { |
7839 | 0 | xmlParserInputPtr input; |
7840 | 0 | xmlBufferPtr buf; |
7841 | 0 | int l, c; |
7842 | |
|
7843 | 0 | if ((ctxt == NULL) || (entity == NULL) || |
7844 | 0 | ((entity->etype != XML_EXTERNAL_PARAMETER_ENTITY) && |
7845 | 0 | (entity->etype != XML_EXTERNAL_GENERAL_PARSED_ENTITY)) || |
7846 | 0 | (entity->content != NULL)) { |
7847 | 0 | xmlFatalErr(ctxt, XML_ERR_INTERNAL_ERROR, |
7848 | 0 | "xmlLoadEntityContent parameter error"); |
7849 | 0 | return(-1); |
7850 | 0 | } |
7851 | | |
7852 | 0 | if (xmlParserDebugEntities) |
7853 | 0 | xmlGenericError(xmlGenericErrorContext, |
7854 | 0 | "Reading %s entity content input\n", entity->name); |
7855 | |
|
7856 | 0 | buf = xmlBufferCreate(); |
7857 | 0 | if (buf == NULL) { |
7858 | 0 | xmlFatalErr(ctxt, XML_ERR_INTERNAL_ERROR, |
7859 | 0 | "xmlLoadEntityContent parameter error"); |
7860 | 0 | return(-1); |
7861 | 0 | } |
7862 | 0 | xmlBufferSetAllocationScheme(buf, XML_BUFFER_ALLOC_DOUBLEIT); |
7863 | |
|
7864 | 0 | input = xmlNewEntityInputStream(ctxt, entity); |
7865 | 0 | if (input == NULL) { |
7866 | 0 | xmlFatalErr(ctxt, XML_ERR_INTERNAL_ERROR, |
7867 | 0 | "xmlLoadEntityContent input error"); |
7868 | 0 | xmlBufferFree(buf); |
7869 | 0 | return(-1); |
7870 | 0 | } |
7871 | | |
7872 | | /* |
7873 | | * Push the entity as the current input, read char by char |
7874 | | * saving to the buffer until the end of the entity or an error |
7875 | | */ |
7876 | 0 | if (xmlPushInput(ctxt, input) < 0) { |
7877 | 0 | xmlBufferFree(buf); |
7878 | 0 | xmlFreeInputStream(input); |
7879 | 0 | return(-1); |
7880 | 0 | } |
7881 | | |
7882 | 0 | GROW; |
7883 | 0 | c = CUR_CHAR(l); |
7884 | 0 | while ((ctxt->input == input) && (ctxt->input->cur < ctxt->input->end) && |
7885 | 0 | (IS_CHAR(c))) { |
7886 | 0 | xmlBufferAdd(buf, ctxt->input->cur, l); |
7887 | 0 | NEXTL(l); |
7888 | 0 | c = CUR_CHAR(l); |
7889 | 0 | } |
7890 | 0 | if (ctxt->instate == XML_PARSER_EOF) { |
7891 | 0 | xmlBufferFree(buf); |
7892 | 0 | return(-1); |
7893 | 0 | } |
7894 | | |
7895 | 0 | if ((ctxt->input == input) && (ctxt->input->cur >= ctxt->input->end)) { |
7896 | 0 | xmlSaturatedAdd(&ctxt->sizeentities, ctxt->input->consumed); |
7897 | 0 | xmlPopInput(ctxt); |
7898 | 0 | } else if (!IS_CHAR(c)) { |
7899 | 0 | xmlFatalErrMsgInt(ctxt, XML_ERR_INVALID_CHAR, |
7900 | 0 | "xmlLoadEntityContent: invalid char value %d\n", |
7901 | 0 | c); |
7902 | 0 | xmlBufferFree(buf); |
7903 | 0 | return(-1); |
7904 | 0 | } |
7905 | 0 | entity->content = buf->content; |
7906 | 0 | entity->length = buf->use; |
7907 | 0 | buf->content = NULL; |
7908 | 0 | xmlBufferFree(buf); |
7909 | |
|
7910 | 0 | return(0); |
7911 | 0 | } |
7912 | | |
7913 | | /** |
7914 | | * xmlParseStringPEReference: |
7915 | | * @ctxt: an XML parser context |
7916 | | * @str: a pointer to an index in the string |
7917 | | * |
7918 | | * parse PEReference declarations |
7919 | | * |
7920 | | * [69] PEReference ::= '%' Name ';' |
7921 | | * |
7922 | | * [ WFC: No Recursion ] |
7923 | | * A parsed entity must not contain a recursive |
7924 | | * reference to itself, either directly or indirectly. |
7925 | | * |
7926 | | * [ WFC: Entity Declared ] |
7927 | | * In a document without any DTD, a document with only an internal DTD |
7928 | | * subset which contains no parameter entity references, or a document |
7929 | | * with "standalone='yes'", ... ... The declaration of a parameter |
7930 | | * entity must precede any reference to it... |
7931 | | * |
7932 | | * [ VC: Entity Declared ] |
7933 | | * In a document with an external subset or external parameter entities |
7934 | | * with "standalone='no'", ... ... The declaration of a parameter entity |
7935 | | * must precede any reference to it... |
7936 | | * |
7937 | | * [ WFC: In DTD ] |
7938 | | * Parameter-entity references may only appear in the DTD. |
7939 | | * NOTE: misleading but this is handled. |
7940 | | * |
7941 | | * Returns the string of the entity content. |
7942 | | * str is updated to the current value of the index |
7943 | | */ |
7944 | | static xmlEntityPtr |
7945 | 0 | xmlParseStringPEReference(xmlParserCtxtPtr ctxt, const xmlChar **str) { |
7946 | 0 | const xmlChar *ptr; |
7947 | 0 | xmlChar cur; |
7948 | 0 | xmlChar *name; |
7949 | 0 | xmlEntityPtr entity = NULL; |
7950 | |
|
7951 | 0 | if ((str == NULL) || (*str == NULL)) return(NULL); |
7952 | 0 | ptr = *str; |
7953 | 0 | cur = *ptr; |
7954 | 0 | if (cur != '%') |
7955 | 0 | return(NULL); |
7956 | 0 | ptr++; |
7957 | 0 | name = xmlParseStringName(ctxt, &ptr); |
7958 | 0 | if (name == NULL) { |
7959 | 0 | xmlFatalErrMsg(ctxt, XML_ERR_NAME_REQUIRED, |
7960 | 0 | "xmlParseStringPEReference: no name\n"); |
7961 | 0 | *str = ptr; |
7962 | 0 | return(NULL); |
7963 | 0 | } |
7964 | 0 | cur = *ptr; |
7965 | 0 | if (cur != ';') { |
7966 | 0 | xmlFatalErr(ctxt, XML_ERR_ENTITYREF_SEMICOL_MISSING, NULL); |
7967 | 0 | xmlFree(name); |
7968 | 0 | *str = ptr; |
7969 | 0 | return(NULL); |
7970 | 0 | } |
7971 | 0 | ptr++; |
7972 | | |
7973 | | /* |
7974 | | * Request the entity from SAX |
7975 | | */ |
7976 | 0 | if ((ctxt->sax != NULL) && |
7977 | 0 | (ctxt->sax->getParameterEntity != NULL)) |
7978 | 0 | entity = ctxt->sax->getParameterEntity(ctxt->userData, name); |
7979 | 0 | if (ctxt->instate == XML_PARSER_EOF) { |
7980 | 0 | xmlFree(name); |
7981 | 0 | *str = ptr; |
7982 | 0 | return(NULL); |
7983 | 0 | } |
7984 | 0 | if (entity == NULL) { |
7985 | | /* |
7986 | | * [ WFC: Entity Declared ] |
7987 | | * In a document without any DTD, a document with only an |
7988 | | * internal DTD subset which contains no parameter entity |
7989 | | * references, or a document with "standalone='yes'", ... |
7990 | | * ... The declaration of a parameter entity must precede |
7991 | | * any reference to it... |
7992 | | */ |
7993 | 0 | if ((ctxt->standalone == 1) || |
7994 | 0 | ((ctxt->hasExternalSubset == 0) && (ctxt->hasPErefs == 0))) { |
7995 | 0 | xmlFatalErrMsgStr(ctxt, XML_ERR_UNDECLARED_ENTITY, |
7996 | 0 | "PEReference: %%%s; not found\n", name); |
7997 | 0 | } else { |
7998 | | /* |
7999 | | * [ VC: Entity Declared ] |
8000 | | * In a document with an external subset or external |
8001 | | * parameter entities with "standalone='no'", ... |
8002 | | * ... The declaration of a parameter entity must |
8003 | | * precede any reference to it... |
8004 | | */ |
8005 | 0 | xmlWarningMsg(ctxt, XML_WAR_UNDECLARED_ENTITY, |
8006 | 0 | "PEReference: %%%s; not found\n", |
8007 | 0 | name, NULL); |
8008 | 0 | ctxt->valid = 0; |
8009 | 0 | } |
8010 | 0 | } else { |
8011 | | /* |
8012 | | * Internal checking in case the entity quest barfed |
8013 | | */ |
8014 | 0 | if ((entity->etype != XML_INTERNAL_PARAMETER_ENTITY) && |
8015 | 0 | (entity->etype != XML_EXTERNAL_PARAMETER_ENTITY)) { |
8016 | 0 | xmlWarningMsg(ctxt, XML_WAR_UNDECLARED_ENTITY, |
8017 | 0 | "%%%s; is not a parameter entity\n", |
8018 | 0 | name, NULL); |
8019 | 0 | } |
8020 | 0 | } |
8021 | 0 | ctxt->hasPErefs = 1; |
8022 | 0 | xmlFree(name); |
8023 | 0 | *str = ptr; |
8024 | 0 | return(entity); |
8025 | 0 | } |
8026 | | |
8027 | | /** |
8028 | | * xmlParseDocTypeDecl: |
8029 | | * @ctxt: an XML parser context |
8030 | | * |
8031 | | * DEPRECATED: Internal function, don't use. |
8032 | | * |
8033 | | * parse a DOCTYPE declaration |
8034 | | * |
8035 | | * [28] doctypedecl ::= '<!DOCTYPE' S Name (S ExternalID)? S? |
8036 | | * ('[' (markupdecl | PEReference | S)* ']' S?)? '>' |
8037 | | * |
8038 | | * [ VC: Root Element Type ] |
8039 | | * The Name in the document type declaration must match the element |
8040 | | * type of the root element. |
8041 | | */ |
8042 | | |
8043 | | void |
8044 | 83 | xmlParseDocTypeDecl(xmlParserCtxtPtr ctxt) { |
8045 | 83 | const xmlChar *name = NULL; |
8046 | 83 | xmlChar *ExternalID = NULL; |
8047 | 83 | xmlChar *URI = NULL; |
8048 | | |
8049 | | /* |
8050 | | * We know that '<!DOCTYPE' has been detected. |
8051 | | */ |
8052 | 83 | SKIP(9); |
8053 | | |
8054 | 83 | SKIP_BLANKS; |
8055 | | |
8056 | | /* |
8057 | | * Parse the DOCTYPE name. |
8058 | | */ |
8059 | 83 | name = xmlParseName(ctxt); |
8060 | 83 | if (name == NULL) { |
8061 | 0 | xmlFatalErrMsg(ctxt, XML_ERR_NAME_REQUIRED, |
8062 | 0 | "xmlParseDocTypeDecl : no DOCTYPE name !\n"); |
8063 | 0 | } |
8064 | 83 | ctxt->intSubName = name; |
8065 | | |
8066 | 83 | SKIP_BLANKS; |
8067 | | |
8068 | | /* |
8069 | | * Check for SystemID and ExternalID |
8070 | | */ |
8071 | 83 | URI = xmlParseExternalID(ctxt, &ExternalID, 1); |
8072 | | |
8073 | 83 | if ((URI != NULL) || (ExternalID != NULL)) { |
8074 | 0 | ctxt->hasExternalSubset = 1; |
8075 | 0 | } |
8076 | 83 | ctxt->extSubURI = URI; |
8077 | 83 | ctxt->extSubSystem = ExternalID; |
8078 | | |
8079 | 83 | SKIP_BLANKS; |
8080 | | |
8081 | | /* |
8082 | | * Create and update the internal subset. |
8083 | | */ |
8084 | 83 | if ((ctxt->sax != NULL) && (ctxt->sax->internalSubset != NULL) && |
8085 | 83 | (!ctxt->disableSAX)) |
8086 | 83 | ctxt->sax->internalSubset(ctxt->userData, name, ExternalID, URI); |
8087 | 83 | if (ctxt->instate == XML_PARSER_EOF) |
8088 | 0 | return; |
8089 | | |
8090 | | /* |
8091 | | * Is there any internal subset declarations ? |
8092 | | * they are handled separately in xmlParseInternalSubset() |
8093 | | */ |
8094 | 83 | if (RAW == '[') |
8095 | 81 | return; |
8096 | | |
8097 | | /* |
8098 | | * We should be at the end of the DOCTYPE declaration. |
8099 | | */ |
8100 | 2 | if (RAW != '>') { |
8101 | 2 | xmlFatalErr(ctxt, XML_ERR_DOCTYPE_NOT_FINISHED, NULL); |
8102 | 2 | } |
8103 | 2 | NEXT; |
8104 | 2 | } |
8105 | | |
8106 | | /** |
8107 | | * xmlParseInternalSubset: |
8108 | | * @ctxt: an XML parser context |
8109 | | * |
8110 | | * parse the internal subset declaration |
8111 | | * |
8112 | | * [28 end] ('[' (markupdecl | PEReference | S)* ']' S?)? '>' |
8113 | | */ |
8114 | | |
8115 | | static void |
8116 | 81 | xmlParseInternalSubset(xmlParserCtxtPtr ctxt) { |
8117 | | /* |
8118 | | * Is there any DTD definition ? |
8119 | | */ |
8120 | 81 | if (RAW == '[') { |
8121 | 81 | int baseInputNr = ctxt->inputNr; |
8122 | 81 | ctxt->instate = XML_PARSER_DTD; |
8123 | 81 | NEXT; |
8124 | | /* |
8125 | | * Parse the succession of Markup declarations and |
8126 | | * PEReferences. |
8127 | | * Subsequence (markupdecl | PEReference | S)* |
8128 | | */ |
8129 | 81 | SKIP_BLANKS; |
8130 | 26.6k | while (((RAW != ']') || (ctxt->inputNr > baseInputNr)) && |
8131 | 26.6k | (ctxt->instate != XML_PARSER_EOF)) { |
8132 | | |
8133 | | /* |
8134 | | * Conditional sections are allowed from external entities included |
8135 | | * by PE References in the internal subset. |
8136 | | */ |
8137 | 26.6k | if ((ctxt->inputNr > 1) && (ctxt->input->filename != NULL) && |
8138 | 26.6k | (RAW == '<') && (NXT(1) == '!') && (NXT(2) == '[')) { |
8139 | 0 | xmlParseConditionalSections(ctxt); |
8140 | 26.6k | } else if ((RAW == '<') && ((NXT(1) == '!') || (NXT(1) == '?'))) { |
8141 | 26.5k | xmlParseMarkupDecl(ctxt); |
8142 | 26.5k | } else if (RAW == '%') { |
8143 | 0 | xmlParsePEReference(ctxt); |
8144 | 17 | } else { |
8145 | 17 | xmlFatalErr(ctxt, XML_ERR_INTERNAL_ERROR, |
8146 | 17 | "xmlParseInternalSubset: error detected in" |
8147 | 17 | " Markup declaration\n"); |
8148 | 17 | xmlHaltParser(ctxt); |
8149 | 17 | return; |
8150 | 17 | } |
8151 | 26.5k | SKIP_BLANKS; |
8152 | 26.5k | SHRINK; |
8153 | 26.5k | GROW; |
8154 | 26.5k | } |
8155 | 64 | if (RAW == ']') { |
8156 | 47 | NEXT; |
8157 | 47 | SKIP_BLANKS; |
8158 | 47 | } |
8159 | 64 | } |
8160 | | |
8161 | | /* |
8162 | | * We should be at the end of the DOCTYPE declaration. |
8163 | | */ |
8164 | 64 | if (RAW != '>') { |
8165 | 17 | xmlFatalErr(ctxt, XML_ERR_DOCTYPE_NOT_FINISHED, NULL); |
8166 | 17 | return; |
8167 | 17 | } |
8168 | 47 | NEXT; |
8169 | 47 | } |
8170 | | |
8171 | | #ifdef LIBXML_SAX1_ENABLED |
8172 | | /** |
8173 | | * xmlParseAttribute: |
8174 | | * @ctxt: an XML parser context |
8175 | | * @value: a xmlChar ** used to store the value of the attribute |
8176 | | * |
8177 | | * DEPRECATED: Internal function, don't use. |
8178 | | * |
8179 | | * parse an attribute |
8180 | | * |
8181 | | * [41] Attribute ::= Name Eq AttValue |
8182 | | * |
8183 | | * [ WFC: No External Entity References ] |
8184 | | * Attribute values cannot contain direct or indirect entity references |
8185 | | * to external entities. |
8186 | | * |
8187 | | * [ WFC: No < in Attribute Values ] |
8188 | | * The replacement text of any entity referred to directly or indirectly in |
8189 | | * an attribute value (other than "<") must not contain a <. |
8190 | | * |
8191 | | * [ VC: Attribute Value Type ] |
8192 | | * The attribute must have been declared; the value must be of the type |
8193 | | * declared for it. |
8194 | | * |
8195 | | * [25] Eq ::= S? '=' S? |
8196 | | * |
8197 | | * With namespace: |
8198 | | * |
8199 | | * [NS 11] Attribute ::= QName Eq AttValue |
8200 | | * |
8201 | | * Also the case QName == xmlns:??? is handled independently as a namespace |
8202 | | * definition. |
8203 | | * |
8204 | | * Returns the attribute name, and the value in *value. |
8205 | | */ |
8206 | | |
8207 | | const xmlChar * |
8208 | | xmlParseAttribute(xmlParserCtxtPtr ctxt, xmlChar **value) { |
8209 | | const xmlChar *name; |
8210 | | xmlChar *val; |
8211 | | |
8212 | | *value = NULL; |
8213 | | GROW; |
8214 | | name = xmlParseName(ctxt); |
8215 | | if (name == NULL) { |
8216 | | xmlFatalErrMsg(ctxt, XML_ERR_NAME_REQUIRED, |
8217 | | "error parsing attribute name\n"); |
8218 | | return(NULL); |
8219 | | } |
8220 | | |
8221 | | /* |
8222 | | * read the value |
8223 | | */ |
8224 | | SKIP_BLANKS; |
8225 | | if (RAW == '=') { |
8226 | | NEXT; |
8227 | | SKIP_BLANKS; |
8228 | | val = xmlParseAttValue(ctxt); |
8229 | | ctxt->instate = XML_PARSER_CONTENT; |
8230 | | } else { |
8231 | | xmlFatalErrMsgStr(ctxt, XML_ERR_ATTRIBUTE_WITHOUT_VALUE, |
8232 | | "Specification mandates value for attribute %s\n", name); |
8233 | | return(name); |
8234 | | } |
8235 | | |
8236 | | /* |
8237 | | * Check that xml:lang conforms to the specification |
8238 | | * No more registered as an error, just generate a warning now |
8239 | | * since this was deprecated in XML second edition |
8240 | | */ |
8241 | | if ((ctxt->pedantic) && (xmlStrEqual(name, BAD_CAST "xml:lang"))) { |
8242 | | if (!xmlCheckLanguageID(val)) { |
8243 | | xmlWarningMsg(ctxt, XML_WAR_LANG_VALUE, |
8244 | | "Malformed value for xml:lang : %s\n", |
8245 | | val, NULL); |
8246 | | } |
8247 | | } |
8248 | | |
8249 | | /* |
8250 | | * Check that xml:space conforms to the specification |
8251 | | */ |
8252 | | if (xmlStrEqual(name, BAD_CAST "xml:space")) { |
8253 | | if (xmlStrEqual(val, BAD_CAST "default")) |
8254 | | *(ctxt->space) = 0; |
8255 | | else if (xmlStrEqual(val, BAD_CAST "preserve")) |
8256 | | *(ctxt->space) = 1; |
8257 | | else { |
8258 | | xmlWarningMsg(ctxt, XML_WAR_SPACE_VALUE, |
8259 | | "Invalid value \"%s\" for xml:space : \"default\" or \"preserve\" expected\n", |
8260 | | val, NULL); |
8261 | | } |
8262 | | } |
8263 | | |
8264 | | *value = val; |
8265 | | return(name); |
8266 | | } |
8267 | | |
8268 | | /** |
8269 | | * xmlParseStartTag: |
8270 | | * @ctxt: an XML parser context |
8271 | | * |
8272 | | * DEPRECATED: Internal function, don't use. |
8273 | | * |
8274 | | * Parse a start tag. Always consumes '<'. |
8275 | | * |
8276 | | * [40] STag ::= '<' Name (S Attribute)* S? '>' |
8277 | | * |
8278 | | * [ WFC: Unique Att Spec ] |
8279 | | * No attribute name may appear more than once in the same start-tag or |
8280 | | * empty-element tag. |
8281 | | * |
8282 | | * [44] EmptyElemTag ::= '<' Name (S Attribute)* S? '/>' |
8283 | | * |
8284 | | * [ WFC: Unique Att Spec ] |
8285 | | * No attribute name may appear more than once in the same start-tag or |
8286 | | * empty-element tag. |
8287 | | * |
8288 | | * With namespace: |
8289 | | * |
8290 | | * [NS 8] STag ::= '<' QName (S Attribute)* S? '>' |
8291 | | * |
8292 | | * [NS 10] EmptyElement ::= '<' QName (S Attribute)* S? '/>' |
8293 | | * |
8294 | | * Returns the element name parsed |
8295 | | */ |
8296 | | |
8297 | | const xmlChar * |
8298 | | xmlParseStartTag(xmlParserCtxtPtr ctxt) { |
8299 | | const xmlChar *name; |
8300 | | const xmlChar *attname; |
8301 | | xmlChar *attvalue; |
8302 | | const xmlChar **atts = ctxt->atts; |
8303 | | int nbatts = 0; |
8304 | | int maxatts = ctxt->maxatts; |
8305 | | int i; |
8306 | | |
8307 | | if (RAW != '<') return(NULL); |
8308 | | NEXT1; |
8309 | | |
8310 | | name = xmlParseName(ctxt); |
8311 | | if (name == NULL) { |
8312 | | xmlFatalErrMsg(ctxt, XML_ERR_NAME_REQUIRED, |
8313 | | "xmlParseStartTag: invalid element name\n"); |
8314 | | return(NULL); |
8315 | | } |
8316 | | |
8317 | | /* |
8318 | | * Now parse the attributes, it ends up with the ending |
8319 | | * |
8320 | | * (S Attribute)* S? |
8321 | | */ |
8322 | | SKIP_BLANKS; |
8323 | | GROW; |
8324 | | |
8325 | | while (((RAW != '>') && |
8326 | | ((RAW != '/') || (NXT(1) != '>')) && |
8327 | | (IS_BYTE_CHAR(RAW))) && (ctxt->instate != XML_PARSER_EOF)) { |
8328 | | attname = xmlParseAttribute(ctxt, &attvalue); |
8329 | | if (attname == NULL) { |
8330 | | xmlFatalErrMsg(ctxt, XML_ERR_INTERNAL_ERROR, |
8331 | | "xmlParseStartTag: problem parsing attributes\n"); |
8332 | | break; |
8333 | | } |
8334 | | if (attvalue != NULL) { |
8335 | | /* |
8336 | | * [ WFC: Unique Att Spec ] |
8337 | | * No attribute name may appear more than once in the same |
8338 | | * start-tag or empty-element tag. |
8339 | | */ |
8340 | | for (i = 0; i < nbatts;i += 2) { |
8341 | | if (xmlStrEqual(atts[i], attname)) { |
8342 | | xmlErrAttributeDup(ctxt, NULL, attname); |
8343 | | xmlFree(attvalue); |
8344 | | goto failed; |
8345 | | } |
8346 | | } |
8347 | | /* |
8348 | | * Add the pair to atts |
8349 | | */ |
8350 | | if (atts == NULL) { |
8351 | | maxatts = 22; /* allow for 10 attrs by default */ |
8352 | | atts = (const xmlChar **) |
8353 | | xmlMalloc(maxatts * sizeof(xmlChar *)); |
8354 | | if (atts == NULL) { |
8355 | | xmlErrMemory(ctxt, NULL); |
8356 | | if (attvalue != NULL) |
8357 | | xmlFree(attvalue); |
8358 | | goto failed; |
8359 | | } |
8360 | | ctxt->atts = atts; |
8361 | | ctxt->maxatts = maxatts; |
8362 | | } else if (nbatts + 4 > maxatts) { |
8363 | | const xmlChar **n; |
8364 | | |
8365 | | maxatts *= 2; |
8366 | | n = (const xmlChar **) xmlRealloc((void *) atts, |
8367 | | maxatts * sizeof(const xmlChar *)); |
8368 | | if (n == NULL) { |
8369 | | xmlErrMemory(ctxt, NULL); |
8370 | | if (attvalue != NULL) |
8371 | | xmlFree(attvalue); |
8372 | | goto failed; |
8373 | | } |
8374 | | atts = n; |
8375 | | ctxt->atts = atts; |
8376 | | ctxt->maxatts = maxatts; |
8377 | | } |
8378 | | atts[nbatts++] = attname; |
8379 | | atts[nbatts++] = attvalue; |
8380 | | atts[nbatts] = NULL; |
8381 | | atts[nbatts + 1] = NULL; |
8382 | | } else { |
8383 | | if (attvalue != NULL) |
8384 | | xmlFree(attvalue); |
8385 | | } |
8386 | | |
8387 | | failed: |
8388 | | |
8389 | | GROW |
8390 | | if ((RAW == '>') || (((RAW == '/') && (NXT(1) == '>')))) |
8391 | | break; |
8392 | | if (SKIP_BLANKS == 0) { |
8393 | | xmlFatalErrMsg(ctxt, XML_ERR_SPACE_REQUIRED, |
8394 | | "attributes construct error\n"); |
8395 | | } |
8396 | | SHRINK; |
8397 | | GROW; |
8398 | | } |
8399 | | |
8400 | | /* |
8401 | | * SAX: Start of Element ! |
8402 | | */ |
8403 | | if ((ctxt->sax != NULL) && (ctxt->sax->startElement != NULL) && |
8404 | | (!ctxt->disableSAX)) { |
8405 | | if (nbatts > 0) |
8406 | | ctxt->sax->startElement(ctxt->userData, name, atts); |
8407 | | else |
8408 | | ctxt->sax->startElement(ctxt->userData, name, NULL); |
8409 | | } |
8410 | | |
8411 | | if (atts != NULL) { |
8412 | | /* Free only the content strings */ |
8413 | | for (i = 1;i < nbatts;i+=2) |
8414 | | if (atts[i] != NULL) |
8415 | | xmlFree((xmlChar *) atts[i]); |
8416 | | } |
8417 | | return(name); |
8418 | | } |
8419 | | |
8420 | | /** |
8421 | | * xmlParseEndTag1: |
8422 | | * @ctxt: an XML parser context |
8423 | | * @line: line of the start tag |
8424 | | * @nsNr: number of namespaces on the start tag |
8425 | | * |
8426 | | * Parse an end tag. Always consumes '</'. |
8427 | | * |
8428 | | * [42] ETag ::= '</' Name S? '>' |
8429 | | * |
8430 | | * With namespace |
8431 | | * |
8432 | | * [NS 9] ETag ::= '</' QName S? '>' |
8433 | | */ |
8434 | | |
8435 | | static void |
8436 | | xmlParseEndTag1(xmlParserCtxtPtr ctxt, int line) { |
8437 | | const xmlChar *name; |
8438 | | |
8439 | | GROW; |
8440 | | if ((RAW != '<') || (NXT(1) != '/')) { |
8441 | | xmlFatalErrMsg(ctxt, XML_ERR_LTSLASH_REQUIRED, |
8442 | | "xmlParseEndTag: '</' not found\n"); |
8443 | | return; |
8444 | | } |
8445 | | SKIP(2); |
8446 | | |
8447 | | name = xmlParseNameAndCompare(ctxt,ctxt->name); |
8448 | | |
8449 | | /* |
8450 | | * We should definitely be at the ending "S? '>'" part |
8451 | | */ |
8452 | | GROW; |
8453 | | SKIP_BLANKS; |
8454 | | if ((!IS_BYTE_CHAR(RAW)) || (RAW != '>')) { |
8455 | | xmlFatalErr(ctxt, XML_ERR_GT_REQUIRED, NULL); |
8456 | | } else |
8457 | | NEXT1; |
8458 | | |
8459 | | /* |
8460 | | * [ WFC: Element Type Match ] |
8461 | | * The Name in an element's end-tag must match the element type in the |
8462 | | * start-tag. |
8463 | | * |
8464 | | */ |
8465 | | if (name != (xmlChar*)1) { |
8466 | | if (name == NULL) name = BAD_CAST "unparsable"; |
8467 | | xmlFatalErrMsgStrIntStr(ctxt, XML_ERR_TAG_NAME_MISMATCH, |
8468 | | "Opening and ending tag mismatch: %s line %d and %s\n", |
8469 | | ctxt->name, line, name); |
8470 | | } |
8471 | | |
8472 | | /* |
8473 | | * SAX: End of Tag |
8474 | | */ |
8475 | | if ((ctxt->sax != NULL) && (ctxt->sax->endElement != NULL) && |
8476 | | (!ctxt->disableSAX)) |
8477 | | ctxt->sax->endElement(ctxt->userData, ctxt->name); |
8478 | | |
8479 | | namePop(ctxt); |
8480 | | spacePop(ctxt); |
8481 | | return; |
8482 | | } |
8483 | | |
8484 | | /** |
8485 | | * xmlParseEndTag: |
8486 | | * @ctxt: an XML parser context |
8487 | | * |
8488 | | * DEPRECATED: Internal function, don't use. |
8489 | | * |
8490 | | * parse an end of tag |
8491 | | * |
8492 | | * [42] ETag ::= '</' Name S? '>' |
8493 | | * |
8494 | | * With namespace |
8495 | | * |
8496 | | * [NS 9] ETag ::= '</' QName S? '>' |
8497 | | */ |
8498 | | |
8499 | | void |
8500 | | xmlParseEndTag(xmlParserCtxtPtr ctxt) { |
8501 | | xmlParseEndTag1(ctxt, 0); |
8502 | | } |
8503 | | #endif /* LIBXML_SAX1_ENABLED */ |
8504 | | |
8505 | | /************************************************************************ |
8506 | | * * |
8507 | | * SAX 2 specific operations * |
8508 | | * * |
8509 | | ************************************************************************/ |
8510 | | |
8511 | | /* |
8512 | | * xmlGetNamespace: |
8513 | | * @ctxt: an XML parser context |
8514 | | * @prefix: the prefix to lookup |
8515 | | * |
8516 | | * Lookup the namespace name for the @prefix (which ca be NULL) |
8517 | | * The prefix must come from the @ctxt->dict dictionary |
8518 | | * |
8519 | | * Returns the namespace name or NULL if not bound |
8520 | | */ |
8521 | | static const xmlChar * |
8522 | 1.34M | xmlGetNamespace(xmlParserCtxtPtr ctxt, const xmlChar *prefix) { |
8523 | 1.34M | int i; |
8524 | | |
8525 | 1.34M | if (prefix == ctxt->str_xml) return(ctxt->str_xml_ns); |
8526 | 1.44M | for (i = ctxt->nsNr - 2;i >= 0;i-=2) |
8527 | 977k | if (ctxt->nsTab[i] == prefix) { |
8528 | 876k | if ((prefix == NULL) && (*ctxt->nsTab[i + 1] == 0)) |
8529 | 869k | return(NULL); |
8530 | 6.96k | return(ctxt->nsTab[i + 1]); |
8531 | 876k | } |
8532 | 467k | return(NULL); |
8533 | 1.34M | } |
8534 | | |
8535 | | /** |
8536 | | * xmlParseQName: |
8537 | | * @ctxt: an XML parser context |
8538 | | * @prefix: pointer to store the prefix part |
8539 | | * |
8540 | | * parse an XML Namespace QName |
8541 | | * |
8542 | | * [6] QName ::= (Prefix ':')? LocalPart |
8543 | | * [7] Prefix ::= NCName |
8544 | | * [8] LocalPart ::= NCName |
8545 | | * |
8546 | | * Returns the Name parsed or NULL |
8547 | | */ |
8548 | | |
8549 | | static const xmlChar * |
8550 | 2.70M | xmlParseQName(xmlParserCtxtPtr ctxt, const xmlChar **prefix) { |
8551 | 2.70M | const xmlChar *l, *p; |
8552 | | |
8553 | 2.70M | GROW; |
8554 | 2.70M | if (ctxt->instate == XML_PARSER_EOF) |
8555 | 0 | return(NULL); |
8556 | | |
8557 | 2.70M | l = xmlParseNCName(ctxt); |
8558 | 2.70M | if (l == NULL) { |
8559 | 1.34M | if (CUR == ':') { |
8560 | 6.81k | l = xmlParseName(ctxt); |
8561 | 6.81k | if (l != NULL) { |
8562 | 6.80k | xmlNsErr(ctxt, XML_NS_ERR_QNAME, |
8563 | 6.80k | "Failed to parse QName '%s'\n", l, NULL, NULL); |
8564 | 6.80k | *prefix = NULL; |
8565 | 6.80k | return(l); |
8566 | 6.80k | } |
8567 | 6.81k | } |
8568 | 1.33M | return(NULL); |
8569 | 1.34M | } |
8570 | 1.35M | if (CUR == ':') { |
8571 | 27.2k | NEXT; |
8572 | 27.2k | p = l; |
8573 | 27.2k | l = xmlParseNCName(ctxt); |
8574 | 27.2k | if (l == NULL) { |
8575 | 1.36k | xmlChar *tmp; |
8576 | | |
8577 | 1.36k | if (ctxt->instate == XML_PARSER_EOF) |
8578 | 0 | return(NULL); |
8579 | 1.36k | xmlNsErr(ctxt, XML_NS_ERR_QNAME, |
8580 | 1.36k | "Failed to parse QName '%s:'\n", p, NULL, NULL); |
8581 | 1.36k | l = xmlParseNmtoken(ctxt); |
8582 | 1.36k | if (l == NULL) { |
8583 | 1.10k | if (ctxt->instate == XML_PARSER_EOF) |
8584 | 0 | return(NULL); |
8585 | 1.10k | tmp = xmlBuildQName(BAD_CAST "", p, NULL, 0); |
8586 | 1.10k | } else { |
8587 | 258 | tmp = xmlBuildQName(l, p, NULL, 0); |
8588 | 258 | xmlFree((char *)l); |
8589 | 258 | } |
8590 | 1.36k | p = xmlDictLookup(ctxt->dict, tmp, -1); |
8591 | 1.36k | if (tmp != NULL) xmlFree(tmp); |
8592 | 1.36k | *prefix = NULL; |
8593 | 1.36k | return(p); |
8594 | 1.36k | } |
8595 | 25.8k | if (CUR == ':') { |
8596 | 3.04k | xmlChar *tmp; |
8597 | | |
8598 | 3.04k | xmlNsErr(ctxt, XML_NS_ERR_QNAME, |
8599 | 3.04k | "Failed to parse QName '%s:%s:'\n", p, l, NULL); |
8600 | 3.04k | NEXT; |
8601 | 3.04k | tmp = (xmlChar *) xmlParseName(ctxt); |
8602 | 3.04k | if (tmp != NULL) { |
8603 | 2.51k | tmp = xmlBuildQName(tmp, l, NULL, 0); |
8604 | 2.51k | l = xmlDictLookup(ctxt->dict, tmp, -1); |
8605 | 2.51k | if (tmp != NULL) xmlFree(tmp); |
8606 | 2.51k | *prefix = p; |
8607 | 2.51k | return(l); |
8608 | 2.51k | } |
8609 | 522 | if (ctxt->instate == XML_PARSER_EOF) |
8610 | 0 | return(NULL); |
8611 | 522 | tmp = xmlBuildQName(BAD_CAST "", l, NULL, 0); |
8612 | 522 | l = xmlDictLookup(ctxt->dict, tmp, -1); |
8613 | 522 | if (tmp != NULL) xmlFree(tmp); |
8614 | 522 | *prefix = p; |
8615 | 522 | return(l); |
8616 | 522 | } |
8617 | 22.8k | *prefix = p; |
8618 | 22.8k | } else |
8619 | 1.33M | *prefix = NULL; |
8620 | 1.35M | return(l); |
8621 | 1.35M | } |
8622 | | |
8623 | | /** |
8624 | | * xmlParseQNameAndCompare: |
8625 | | * @ctxt: an XML parser context |
8626 | | * @name: the localname |
8627 | | * @prefix: the prefix, if any. |
8628 | | * |
8629 | | * parse an XML name and compares for match |
8630 | | * (specialized for endtag parsing) |
8631 | | * |
8632 | | * Returns NULL for an illegal name, (xmlChar*) 1 for success |
8633 | | * and the name for mismatch |
8634 | | */ |
8635 | | |
8636 | | static const xmlChar * |
8637 | | xmlParseQNameAndCompare(xmlParserCtxtPtr ctxt, xmlChar const *name, |
8638 | 2.48k | xmlChar const *prefix) { |
8639 | 2.48k | const xmlChar *cmp; |
8640 | 2.48k | const xmlChar *in; |
8641 | 2.48k | const xmlChar *ret; |
8642 | 2.48k | const xmlChar *prefix2; |
8643 | | |
8644 | 2.48k | if (prefix == NULL) return(xmlParseNameAndCompare(ctxt, name)); |
8645 | | |
8646 | 2.48k | GROW; |
8647 | 2.48k | in = ctxt->input->cur; |
8648 | | |
8649 | 2.48k | cmp = prefix; |
8650 | 3.84k | while (*in != 0 && *in == *cmp) { |
8651 | 1.36k | ++in; |
8652 | 1.36k | ++cmp; |
8653 | 1.36k | } |
8654 | 2.48k | if ((*cmp == 0) && (*in == ':')) { |
8655 | 1.26k | in++; |
8656 | 1.26k | cmp = name; |
8657 | 2.21k | while (*in != 0 && *in == *cmp) { |
8658 | 955 | ++in; |
8659 | 955 | ++cmp; |
8660 | 955 | } |
8661 | 1.26k | if (*cmp == 0 && (*in == '>' || IS_BLANK_CH (*in))) { |
8662 | | /* success */ |
8663 | 945 | ctxt->input->col += in - ctxt->input->cur; |
8664 | 945 | ctxt->input->cur = in; |
8665 | 945 | return((const xmlChar*) 1); |
8666 | 945 | } |
8667 | 1.26k | } |
8668 | | /* |
8669 | | * all strings coms from the dictionary, equality can be done directly |
8670 | | */ |
8671 | 1.54k | ret = xmlParseQName (ctxt, &prefix2); |
8672 | 1.54k | if ((ret == name) && (prefix == prefix2)) |
8673 | 6 | return((const xmlChar*) 1); |
8674 | 1.53k | return ret; |
8675 | 1.54k | } |
8676 | | |
8677 | | /** |
8678 | | * xmlParseAttValueInternal: |
8679 | | * @ctxt: an XML parser context |
8680 | | * @len: attribute len result |
8681 | | * @alloc: whether the attribute was reallocated as a new string |
8682 | | * @normalize: if 1 then further non-CDATA normalization must be done |
8683 | | * |
8684 | | * parse a value for an attribute. |
8685 | | * NOTE: if no normalization is needed, the routine will return pointers |
8686 | | * directly from the data buffer. |
8687 | | * |
8688 | | * 3.3.3 Attribute-Value Normalization: |
8689 | | * Before the value of an attribute is passed to the application or |
8690 | | * checked for validity, the XML processor must normalize it as follows: |
8691 | | * - a character reference is processed by appending the referenced |
8692 | | * character to the attribute value |
8693 | | * - an entity reference is processed by recursively processing the |
8694 | | * replacement text of the entity |
8695 | | * - a whitespace character (#x20, #xD, #xA, #x9) is processed by |
8696 | | * appending #x20 to the normalized value, except that only a single |
8697 | | * #x20 is appended for a "#xD#xA" sequence that is part of an external |
8698 | | * parsed entity or the literal entity value of an internal parsed entity |
8699 | | * - other characters are processed by appending them to the normalized value |
8700 | | * If the declared value is not CDATA, then the XML processor must further |
8701 | | * process the normalized attribute value by discarding any leading and |
8702 | | * trailing space (#x20) characters, and by replacing sequences of space |
8703 | | * (#x20) characters by a single space (#x20) character. |
8704 | | * All attributes for which no declaration has been read should be treated |
8705 | | * by a non-validating parser as if declared CDATA. |
8706 | | * |
8707 | | * Returns the AttValue parsed or NULL. The value has to be freed by the |
8708 | | * caller if it was copied, this can be detected by val[*len] == 0. |
8709 | | */ |
8710 | | |
8711 | | #define GROW_PARSE_ATT_VALUE_INTERNAL(ctxt, in, start, end) \ |
8712 | 1 | const xmlChar *oldbase = ctxt->input->base;\ |
8713 | 1 | GROW;\ |
8714 | 1 | if (ctxt->instate == XML_PARSER_EOF)\ |
8715 | 1 | return(NULL);\ |
8716 | 1 | if (oldbase != ctxt->input->base) {\ |
8717 | 0 | ptrdiff_t delta = ctxt->input->base - oldbase;\ |
8718 | 0 | start = start + delta;\ |
8719 | 0 | in = in + delta;\ |
8720 | 0 | }\ |
8721 | 1 | end = ctxt->input->end; |
8722 | | |
8723 | | static xmlChar * |
8724 | | xmlParseAttValueInternal(xmlParserCtxtPtr ctxt, int *len, int *alloc, |
8725 | | int normalize) |
8726 | 19.5k | { |
8727 | 19.5k | xmlChar limit = 0; |
8728 | 19.5k | const xmlChar *in = NULL, *start, *end, *last; |
8729 | 19.5k | xmlChar *ret = NULL; |
8730 | 19.5k | int line, col; |
8731 | 19.5k | int maxLength = (ctxt->options & XML_PARSE_HUGE) ? |
8732 | 0 | XML_MAX_HUGE_LENGTH : |
8733 | 19.5k | XML_MAX_TEXT_LENGTH; |
8734 | | |
8735 | 19.5k | GROW; |
8736 | 19.5k | in = (xmlChar *) CUR_PTR; |
8737 | 19.5k | line = ctxt->input->line; |
8738 | 19.5k | col = ctxt->input->col; |
8739 | 19.5k | if (*in != '"' && *in != '\'') { |
8740 | 1.55k | xmlFatalErr(ctxt, XML_ERR_ATTRIBUTE_NOT_STARTED, NULL); |
8741 | 1.55k | return (NULL); |
8742 | 1.55k | } |
8743 | 17.9k | ctxt->instate = XML_PARSER_ATTRIBUTE_VALUE; |
8744 | | |
8745 | | /* |
8746 | | * try to handle in this routine the most common case where no |
8747 | | * allocation of a new string is required and where content is |
8748 | | * pure ASCII. |
8749 | | */ |
8750 | 17.9k | limit = *in++; |
8751 | 17.9k | col++; |
8752 | 17.9k | end = ctxt->input->end; |
8753 | 17.9k | start = in; |
8754 | 17.9k | if (in >= end) { |
8755 | 0 | GROW_PARSE_ATT_VALUE_INTERNAL(ctxt, in, start, end) |
8756 | 0 | } |
8757 | 17.9k | if (normalize) { |
8758 | | /* |
8759 | | * Skip any leading spaces |
8760 | | */ |
8761 | 1.06k | while ((in < end) && (*in != limit) && |
8762 | 1.06k | ((*in == 0x20) || (*in == 0x9) || |
8763 | 920 | (*in == 0xA) || (*in == 0xD))) { |
8764 | 0 | if (*in == 0xA) { |
8765 | 0 | line++; col = 1; |
8766 | 0 | } else { |
8767 | 0 | col++; |
8768 | 0 | } |
8769 | 0 | in++; |
8770 | 0 | start = in; |
8771 | 0 | if (in >= end) { |
8772 | 0 | GROW_PARSE_ATT_VALUE_INTERNAL(ctxt, in, start, end) |
8773 | 0 | if ((in - start) > maxLength) { |
8774 | 0 | xmlFatalErrMsg(ctxt, XML_ERR_ATTRIBUTE_NOT_FINISHED, |
8775 | 0 | "AttValue length too long\n"); |
8776 | 0 | return(NULL); |
8777 | 0 | } |
8778 | 0 | } |
8779 | 0 | } |
8780 | 3.09k | while ((in < end) && (*in != limit) && (*in >= 0x20) && |
8781 | 3.09k | (*in <= 0x7f) && (*in != '&') && (*in != '<')) { |
8782 | 2.45k | col++; |
8783 | 2.45k | if ((*in++ == 0x20) && (*in == 0x20)) break; |
8784 | 2.03k | if (in >= end) { |
8785 | 0 | GROW_PARSE_ATT_VALUE_INTERNAL(ctxt, in, start, end) |
8786 | 0 | if ((in - start) > maxLength) { |
8787 | 0 | xmlFatalErrMsg(ctxt, XML_ERR_ATTRIBUTE_NOT_FINISHED, |
8788 | 0 | "AttValue length too long\n"); |
8789 | 0 | return(NULL); |
8790 | 0 | } |
8791 | 0 | } |
8792 | 2.03k | } |
8793 | 1.06k | last = in; |
8794 | | /* |
8795 | | * skip the trailing blanks |
8796 | | */ |
8797 | 1.49k | while ((last[-1] == 0x20) && (last > start)) last--; |
8798 | 3.97k | while ((in < end) && (*in != limit) && |
8799 | 3.97k | ((*in == 0x20) || (*in == 0x9) || |
8800 | 3.28k | (*in == 0xA) || (*in == 0xD))) { |
8801 | 2.91k | if (*in == 0xA) { |
8802 | 193 | line++, col = 1; |
8803 | 2.72k | } else { |
8804 | 2.72k | col++; |
8805 | 2.72k | } |
8806 | 2.91k | in++; |
8807 | 2.91k | if (in >= end) { |
8808 | 0 | const xmlChar *oldbase = ctxt->input->base; |
8809 | 0 | GROW; |
8810 | 0 | if (ctxt->instate == XML_PARSER_EOF) |
8811 | 0 | return(NULL); |
8812 | 0 | if (oldbase != ctxt->input->base) { |
8813 | 0 | ptrdiff_t delta = ctxt->input->base - oldbase; |
8814 | 0 | start = start + delta; |
8815 | 0 | in = in + delta; |
8816 | 0 | last = last + delta; |
8817 | 0 | } |
8818 | 0 | end = ctxt->input->end; |
8819 | 0 | if ((in - start) > maxLength) { |
8820 | 0 | xmlFatalErrMsg(ctxt, XML_ERR_ATTRIBUTE_NOT_FINISHED, |
8821 | 0 | "AttValue length too long\n"); |
8822 | 0 | return(NULL); |
8823 | 0 | } |
8824 | 0 | } |
8825 | 2.91k | } |
8826 | 1.06k | if ((in - start) > maxLength) { |
8827 | 0 | xmlFatalErrMsg(ctxt, XML_ERR_ATTRIBUTE_NOT_FINISHED, |
8828 | 0 | "AttValue length too long\n"); |
8829 | 0 | return(NULL); |
8830 | 0 | } |
8831 | 1.06k | if (*in != limit) goto need_complex; |
8832 | 16.9k | } else { |
8833 | 1.12M | while ((in < end) && (*in != limit) && (*in >= 0x20) && |
8834 | 1.12M | (*in <= 0x7f) && (*in != '&') && (*in != '<')) { |
8835 | 1.10M | in++; |
8836 | 1.10M | col++; |
8837 | 1.10M | if (in >= end) { |
8838 | 1 | GROW_PARSE_ATT_VALUE_INTERNAL(ctxt, in, start, end) |
8839 | 1 | if ((in - start) > maxLength) { |
8840 | 0 | xmlFatalErrMsg(ctxt, XML_ERR_ATTRIBUTE_NOT_FINISHED, |
8841 | 0 | "AttValue length too long\n"); |
8842 | 0 | return(NULL); |
8843 | 0 | } |
8844 | 1 | } |
8845 | 1.10M | } |
8846 | 16.9k | last = in; |
8847 | 16.9k | if ((in - start) > maxLength) { |
8848 | 0 | xmlFatalErrMsg(ctxt, XML_ERR_ATTRIBUTE_NOT_FINISHED, |
8849 | 0 | "AttValue length too long\n"); |
8850 | 0 | return(NULL); |
8851 | 0 | } |
8852 | 16.9k | if (*in != limit) goto need_complex; |
8853 | 16.9k | } |
8854 | 7.81k | in++; |
8855 | 7.81k | col++; |
8856 | 7.81k | if (len != NULL) { |
8857 | 6.60k | if (alloc) *alloc = 0; |
8858 | 6.60k | *len = last - start; |
8859 | 6.60k | ret = (xmlChar *) start; |
8860 | 6.60k | } else { |
8861 | 1.21k | if (alloc) *alloc = 1; |
8862 | 1.21k | ret = xmlStrndup(start, last - start); |
8863 | 1.21k | } |
8864 | 7.81k | CUR_PTR = in; |
8865 | 7.81k | ctxt->input->line = line; |
8866 | 7.81k | ctxt->input->col = col; |
8867 | 7.81k | return ret; |
8868 | 10.1k | need_complex: |
8869 | 10.1k | if (alloc) *alloc = 1; |
8870 | 10.1k | return xmlParseAttValueComplex(ctxt, len, normalize); |
8871 | 17.9k | } |
8872 | | |
8873 | | /** |
8874 | | * xmlParseAttribute2: |
8875 | | * @ctxt: an XML parser context |
8876 | | * @pref: the element prefix |
8877 | | * @elem: the element name |
8878 | | * @prefix: a xmlChar ** used to store the value of the attribute prefix |
8879 | | * @value: a xmlChar ** used to store the value of the attribute |
8880 | | * @len: an int * to save the length of the attribute |
8881 | | * @alloc: an int * to indicate if the attribute was allocated |
8882 | | * |
8883 | | * parse an attribute in the new SAX2 framework. |
8884 | | * |
8885 | | * Returns the attribute name, and the value in *value, . |
8886 | | */ |
8887 | | |
8888 | | static const xmlChar * |
8889 | | xmlParseAttribute2(xmlParserCtxtPtr ctxt, |
8890 | | const xmlChar * pref, const xmlChar * elem, |
8891 | | const xmlChar ** prefix, xmlChar ** value, |
8892 | | int *len, int *alloc) |
8893 | 1.33M | { |
8894 | 1.33M | const xmlChar *name; |
8895 | 1.33M | xmlChar *val, *internal_val = NULL; |
8896 | 1.33M | int normalize = 0; |
8897 | | |
8898 | 1.33M | *value = NULL; |
8899 | 1.33M | GROW; |
8900 | 1.33M | name = xmlParseQName(ctxt, prefix); |
8901 | 1.33M | if (name == NULL) { |
8902 | 1.30M | xmlFatalErrMsg(ctxt, XML_ERR_NAME_REQUIRED, |
8903 | 1.30M | "error parsing attribute name\n"); |
8904 | 1.30M | return (NULL); |
8905 | 1.30M | } |
8906 | | |
8907 | | /* |
8908 | | * get the type if needed |
8909 | | */ |
8910 | 20.2k | if (ctxt->attsSpecial != NULL) { |
8911 | 1.78k | int type; |
8912 | | |
8913 | 1.78k | type = (int) (ptrdiff_t) xmlHashQLookup2(ctxt->attsSpecial, |
8914 | 1.78k | pref, elem, *prefix, name); |
8915 | 1.78k | if (type != 0) |
8916 | 1.26k | normalize = 1; |
8917 | 1.78k | } |
8918 | | |
8919 | | /* |
8920 | | * read the value |
8921 | | */ |
8922 | 20.2k | SKIP_BLANKS; |
8923 | 20.2k | if (RAW == '=') { |
8924 | 16.9k | NEXT; |
8925 | 16.9k | SKIP_BLANKS; |
8926 | 16.9k | val = xmlParseAttValueInternal(ctxt, len, alloc, normalize); |
8927 | 16.9k | if (val == NULL) |
8928 | 1.08k | return (NULL); |
8929 | 15.8k | if (normalize) { |
8930 | | /* |
8931 | | * Sometimes a second normalisation pass for spaces is needed |
8932 | | * but that only happens if charrefs or entities references |
8933 | | * have been used in the attribute value, i.e. the attribute |
8934 | | * value have been extracted in an allocated string already. |
8935 | | */ |
8936 | 1.06k | if (*alloc) { |
8937 | 367 | const xmlChar *val2; |
8938 | | |
8939 | 367 | val2 = xmlAttrNormalizeSpace2(ctxt, val, len); |
8940 | 367 | if ((val2 != NULL) && (val2 != val)) { |
8941 | 0 | xmlFree(val); |
8942 | 0 | val = (xmlChar *) val2; |
8943 | 0 | } |
8944 | 367 | } |
8945 | 1.06k | } |
8946 | 15.8k | ctxt->instate = XML_PARSER_CONTENT; |
8947 | 15.8k | } else { |
8948 | 3.30k | xmlFatalErrMsgStr(ctxt, XML_ERR_ATTRIBUTE_WITHOUT_VALUE, |
8949 | 3.30k | "Specification mandates value for attribute %s\n", |
8950 | 3.30k | name); |
8951 | 3.30k | return (name); |
8952 | 3.30k | } |
8953 | | |
8954 | 15.8k | if (*prefix == ctxt->str_xml) { |
8955 | | /* |
8956 | | * Check that xml:lang conforms to the specification |
8957 | | * No more registered as an error, just generate a warning now |
8958 | | * since this was deprecated in XML second edition |
8959 | | */ |
8960 | 4.79k | if ((ctxt->pedantic) && (xmlStrEqual(name, BAD_CAST "lang"))) { |
8961 | 0 | internal_val = xmlStrndup(val, *len); |
8962 | 0 | if (!xmlCheckLanguageID(internal_val)) { |
8963 | 0 | xmlWarningMsg(ctxt, XML_WAR_LANG_VALUE, |
8964 | 0 | "Malformed value for xml:lang : %s\n", |
8965 | 0 | internal_val, NULL); |
8966 | 0 | } |
8967 | 0 | } |
8968 | | |
8969 | | /* |
8970 | | * Check that xml:space conforms to the specification |
8971 | | */ |
8972 | 4.79k | if (xmlStrEqual(name, BAD_CAST "space")) { |
8973 | 0 | internal_val = xmlStrndup(val, *len); |
8974 | 0 | if (xmlStrEqual(internal_val, BAD_CAST "default")) |
8975 | 0 | *(ctxt->space) = 0; |
8976 | 0 | else if (xmlStrEqual(internal_val, BAD_CAST "preserve")) |
8977 | 0 | *(ctxt->space) = 1; |
8978 | 0 | else { |
8979 | 0 | xmlWarningMsg(ctxt, XML_WAR_SPACE_VALUE, |
8980 | 0 | "Invalid value \"%s\" for xml:space : \"default\" or \"preserve\" expected\n", |
8981 | 0 | internal_val, NULL); |
8982 | 0 | } |
8983 | 0 | } |
8984 | 4.79k | if (internal_val) { |
8985 | 0 | xmlFree(internal_val); |
8986 | 0 | } |
8987 | 4.79k | } |
8988 | | |
8989 | 15.8k | *value = val; |
8990 | 15.8k | return (name); |
8991 | 20.2k | } |
8992 | | /** |
8993 | | * xmlParseStartTag2: |
8994 | | * @ctxt: an XML parser context |
8995 | | * |
8996 | | * Parse a start tag. Always consumes '<'. |
8997 | | * |
8998 | | * This routine is called when running SAX2 parsing |
8999 | | * |
9000 | | * [40] STag ::= '<' Name (S Attribute)* S? '>' |
9001 | | * |
9002 | | * [ WFC: Unique Att Spec ] |
9003 | | * No attribute name may appear more than once in the same start-tag or |
9004 | | * empty-element tag. |
9005 | | * |
9006 | | * [44] EmptyElemTag ::= '<' Name (S Attribute)* S? '/>' |
9007 | | * |
9008 | | * [ WFC: Unique Att Spec ] |
9009 | | * No attribute name may appear more than once in the same start-tag or |
9010 | | * empty-element tag. |
9011 | | * |
9012 | | * With namespace: |
9013 | | * |
9014 | | * [NS 8] STag ::= '<' QName (S Attribute)* S? '>' |
9015 | | * |
9016 | | * [NS 10] EmptyElement ::= '<' QName (S Attribute)* S? '/>' |
9017 | | * |
9018 | | * Returns the element name parsed |
9019 | | */ |
9020 | | |
9021 | | static const xmlChar * |
9022 | | xmlParseStartTag2(xmlParserCtxtPtr ctxt, const xmlChar **pref, |
9023 | 1.36M | const xmlChar **URI, int *tlen) { |
9024 | 1.36M | const xmlChar *localname; |
9025 | 1.36M | const xmlChar *prefix; |
9026 | 1.36M | const xmlChar *attname; |
9027 | 1.36M | const xmlChar *aprefix; |
9028 | 1.36M | const xmlChar *nsname; |
9029 | 1.36M | xmlChar *attvalue; |
9030 | 1.36M | const xmlChar **atts = ctxt->atts; |
9031 | 1.36M | int maxatts = ctxt->maxatts; |
9032 | 1.36M | int nratts, nbatts, nbdef, inputid; |
9033 | 1.36M | int i, j, nbNs, attval; |
9034 | 1.36M | size_t cur; |
9035 | 1.36M | int nsNr = ctxt->nsNr; |
9036 | | |
9037 | 1.36M | if (RAW != '<') return(NULL); |
9038 | 1.36M | NEXT1; |
9039 | | |
9040 | 1.36M | cur = ctxt->input->cur - ctxt->input->base; |
9041 | 1.36M | inputid = ctxt->input->id; |
9042 | 1.36M | nbatts = 0; |
9043 | 1.36M | nratts = 0; |
9044 | 1.36M | nbdef = 0; |
9045 | 1.36M | nbNs = 0; |
9046 | 1.36M | attval = 0; |
9047 | | /* Forget any namespaces added during an earlier parse of this element. */ |
9048 | 1.36M | ctxt->nsNr = nsNr; |
9049 | | |
9050 | 1.36M | localname = xmlParseQName(ctxt, &prefix); |
9051 | 1.36M | if (localname == NULL) { |
9052 | 26.3k | xmlFatalErrMsg(ctxt, XML_ERR_NAME_REQUIRED, |
9053 | 26.3k | "StartTag: invalid element name\n"); |
9054 | 26.3k | return(NULL); |
9055 | 26.3k | } |
9056 | 1.34M | *tlen = ctxt->input->cur - ctxt->input->base - cur; |
9057 | | |
9058 | | /* |
9059 | | * Now parse the attributes, it ends up with the ending |
9060 | | * |
9061 | | * (S Attribute)* S? |
9062 | | */ |
9063 | 1.34M | SKIP_BLANKS; |
9064 | 1.34M | GROW; |
9065 | | |
9066 | 1.34M | while (((RAW != '>') && |
9067 | 1.34M | ((RAW != '/') || (NXT(1) != '>')) && |
9068 | 1.34M | (IS_BYTE_CHAR(RAW))) && (ctxt->instate != XML_PARSER_EOF)) { |
9069 | 1.33M | int len = -1, alloc = 0; |
9070 | | |
9071 | 1.33M | attname = xmlParseAttribute2(ctxt, prefix, localname, |
9072 | 1.33M | &aprefix, &attvalue, &len, &alloc); |
9073 | 1.33M | if (attname == NULL) { |
9074 | 1.31M | xmlFatalErr(ctxt, XML_ERR_INTERNAL_ERROR, |
9075 | 1.31M | "xmlParseStartTag: problem parsing attributes\n"); |
9076 | 1.31M | break; |
9077 | 1.31M | } |
9078 | 19.2k | if (attvalue == NULL) |
9079 | 3.30k | goto next_attr; |
9080 | 15.8k | if (len < 0) len = xmlStrlen(attvalue); |
9081 | | |
9082 | 15.8k | if ((attname == ctxt->str_xmlns) && (aprefix == NULL)) { |
9083 | 1.87k | const xmlChar *URL = xmlDictLookup(ctxt->dict, attvalue, len); |
9084 | 1.87k | xmlURIPtr uri; |
9085 | | |
9086 | 1.87k | if (URL == NULL) { |
9087 | 0 | xmlErrMemory(ctxt, "dictionary allocation failure"); |
9088 | 0 | if ((attvalue != NULL) && (alloc != 0)) |
9089 | 0 | xmlFree(attvalue); |
9090 | 0 | localname = NULL; |
9091 | 0 | goto done; |
9092 | 0 | } |
9093 | 1.87k | if (*URL != 0) { |
9094 | 1.67k | uri = xmlParseURI((const char *) URL); |
9095 | 1.67k | if (uri == NULL) { |
9096 | 971 | xmlNsErr(ctxt, XML_WAR_NS_URI, |
9097 | 971 | "xmlns: '%s' is not a valid URI\n", |
9098 | 971 | URL, NULL, NULL); |
9099 | 971 | } else { |
9100 | 707 | if (uri->scheme == NULL) { |
9101 | 659 | xmlNsWarn(ctxt, XML_WAR_NS_URI_RELATIVE, |
9102 | 659 | "xmlns: URI %s is not absolute\n", |
9103 | 659 | URL, NULL, NULL); |
9104 | 659 | } |
9105 | 707 | xmlFreeURI(uri); |
9106 | 707 | } |
9107 | 1.67k | if (URL == ctxt->str_xml_ns) { |
9108 | 0 | if (attname != ctxt->str_xml) { |
9109 | 0 | xmlNsErr(ctxt, XML_NS_ERR_XML_NAMESPACE, |
9110 | 0 | "xml namespace URI cannot be the default namespace\n", |
9111 | 0 | NULL, NULL, NULL); |
9112 | 0 | } |
9113 | 0 | goto next_attr; |
9114 | 0 | } |
9115 | 1.67k | if ((len == 29) && |
9116 | 1.67k | (xmlStrEqual(URL, |
9117 | 44 | BAD_CAST "http://www.w3.org/2000/xmlns/"))) { |
9118 | 0 | xmlNsErr(ctxt, XML_NS_ERR_XML_NAMESPACE, |
9119 | 0 | "reuse of the xmlns namespace name is forbidden\n", |
9120 | 0 | NULL, NULL, NULL); |
9121 | 0 | goto next_attr; |
9122 | 0 | } |
9123 | 1.67k | } |
9124 | | /* |
9125 | | * check that it's not a defined namespace |
9126 | | */ |
9127 | 2.25k | for (j = 1;j <= nbNs;j++) |
9128 | 484 | if (ctxt->nsTab[ctxt->nsNr - 2 * j] == NULL) |
9129 | 106 | break; |
9130 | 1.87k | if (j <= nbNs) |
9131 | 106 | xmlErrAttributeDup(ctxt, NULL, attname); |
9132 | 1.76k | else |
9133 | 1.76k | if (nsPush(ctxt, NULL, URL) > 0) nbNs++; |
9134 | | |
9135 | 14.0k | } else if (aprefix == ctxt->str_xmlns) { |
9136 | 5.13k | const xmlChar *URL = xmlDictLookup(ctxt->dict, attvalue, len); |
9137 | 5.13k | xmlURIPtr uri; |
9138 | | |
9139 | 5.13k | if (attname == ctxt->str_xml) { |
9140 | 28 | if (URL != ctxt->str_xml_ns) { |
9141 | 28 | xmlNsErr(ctxt, XML_NS_ERR_XML_NAMESPACE, |
9142 | 28 | "xml namespace prefix mapped to wrong URI\n", |
9143 | 28 | NULL, NULL, NULL); |
9144 | 28 | } |
9145 | | /* |
9146 | | * Do not keep a namespace definition node |
9147 | | */ |
9148 | 28 | goto next_attr; |
9149 | 28 | } |
9150 | 5.10k | if (URL == ctxt->str_xml_ns) { |
9151 | 0 | if (attname != ctxt->str_xml) { |
9152 | 0 | xmlNsErr(ctxt, XML_NS_ERR_XML_NAMESPACE, |
9153 | 0 | "xml namespace URI mapped to wrong prefix\n", |
9154 | 0 | NULL, NULL, NULL); |
9155 | 0 | } |
9156 | 0 | goto next_attr; |
9157 | 0 | } |
9158 | 5.10k | if (attname == ctxt->str_xmlns) { |
9159 | 0 | xmlNsErr(ctxt, XML_NS_ERR_XML_NAMESPACE, |
9160 | 0 | "redefinition of the xmlns prefix is forbidden\n", |
9161 | 0 | NULL, NULL, NULL); |
9162 | 0 | goto next_attr; |
9163 | 0 | } |
9164 | 5.10k | if ((len == 29) && |
9165 | 5.10k | (xmlStrEqual(URL, |
9166 | 1 | BAD_CAST "http://www.w3.org/2000/xmlns/"))) { |
9167 | 0 | xmlNsErr(ctxt, XML_NS_ERR_XML_NAMESPACE, |
9168 | 0 | "reuse of the xmlns namespace name is forbidden\n", |
9169 | 0 | NULL, NULL, NULL); |
9170 | 0 | goto next_attr; |
9171 | 0 | } |
9172 | 5.10k | if ((URL == NULL) || (URL[0] == 0)) { |
9173 | 238 | xmlNsErr(ctxt, XML_NS_ERR_XML_NAMESPACE, |
9174 | 238 | "xmlns:%s: Empty XML namespace is not allowed\n", |
9175 | 238 | attname, NULL, NULL); |
9176 | 238 | goto next_attr; |
9177 | 4.87k | } else { |
9178 | 4.87k | uri = xmlParseURI((const char *) URL); |
9179 | 4.87k | if (uri == NULL) { |
9180 | 1.54k | xmlNsErr(ctxt, XML_WAR_NS_URI, |
9181 | 1.54k | "xmlns:%s: '%s' is not a valid URI\n", |
9182 | 1.54k | attname, URL, NULL); |
9183 | 3.32k | } else { |
9184 | 3.32k | if ((ctxt->pedantic) && (uri->scheme == NULL)) { |
9185 | 0 | xmlNsWarn(ctxt, XML_WAR_NS_URI_RELATIVE, |
9186 | 0 | "xmlns:%s: URI %s is not absolute\n", |
9187 | 0 | attname, URL, NULL); |
9188 | 0 | } |
9189 | 3.32k | xmlFreeURI(uri); |
9190 | 3.32k | } |
9191 | 4.87k | } |
9192 | | |
9193 | | /* |
9194 | | * check that it's not a defined namespace |
9195 | | */ |
9196 | 4.95k | for (j = 1;j <= nbNs;j++) |
9197 | 85 | if (ctxt->nsTab[ctxt->nsNr - 2 * j] == attname) |
9198 | 0 | break; |
9199 | 4.87k | if (j <= nbNs) |
9200 | 0 | xmlErrAttributeDup(ctxt, aprefix, attname); |
9201 | 4.87k | else |
9202 | 4.87k | if (nsPush(ctxt, attname, URL) > 0) nbNs++; |
9203 | | |
9204 | 8.88k | } else { |
9205 | | /* |
9206 | | * Add the pair to atts |
9207 | | */ |
9208 | 8.88k | if ((atts == NULL) || (nbatts + 5 > maxatts)) { |
9209 | 88 | if (xmlCtxtGrowAttrs(ctxt, nbatts + 5) < 0) { |
9210 | 0 | goto next_attr; |
9211 | 0 | } |
9212 | 88 | maxatts = ctxt->maxatts; |
9213 | 88 | atts = ctxt->atts; |
9214 | 88 | } |
9215 | 8.88k | ctxt->attallocs[nratts++] = alloc; |
9216 | 8.88k | atts[nbatts++] = attname; |
9217 | 8.88k | atts[nbatts++] = aprefix; |
9218 | | /* |
9219 | | * The namespace URI field is used temporarily to point at the |
9220 | | * base of the current input buffer for non-alloced attributes. |
9221 | | * When the input buffer is reallocated, all the pointers become |
9222 | | * invalid, but they can be reconstructed later. |
9223 | | */ |
9224 | 8.88k | if (alloc) |
9225 | 5.82k | atts[nbatts++] = NULL; |
9226 | 3.06k | else |
9227 | 3.06k | atts[nbatts++] = ctxt->input->base; |
9228 | 8.88k | atts[nbatts++] = attvalue; |
9229 | 8.88k | attvalue += len; |
9230 | 8.88k | atts[nbatts++] = attvalue; |
9231 | | /* |
9232 | | * tag if some deallocation is needed |
9233 | | */ |
9234 | 8.88k | if (alloc != 0) attval = 1; |
9235 | 8.88k | attvalue = NULL; /* moved into atts */ |
9236 | 8.88k | } |
9237 | | |
9238 | 19.2k | next_attr: |
9239 | 19.2k | if ((attvalue != NULL) && (alloc != 0)) { |
9240 | 3.47k | xmlFree(attvalue); |
9241 | 3.47k | attvalue = NULL; |
9242 | 3.47k | } |
9243 | | |
9244 | 19.2k | GROW |
9245 | 19.2k | if (ctxt->instate == XML_PARSER_EOF) |
9246 | 0 | break; |
9247 | 19.2k | if ((RAW == '>') || (((RAW == '/') && (NXT(1) == '>')))) |
9248 | 2.72k | break; |
9249 | 16.4k | if (SKIP_BLANKS == 0) { |
9250 | 12.9k | xmlFatalErrMsg(ctxt, XML_ERR_SPACE_REQUIRED, |
9251 | 12.9k | "attributes construct error\n"); |
9252 | 12.9k | break; |
9253 | 12.9k | } |
9254 | 3.54k | GROW; |
9255 | 3.54k | } |
9256 | | |
9257 | 1.34M | if (ctxt->input->id != inputid) { |
9258 | 0 | xmlFatalErr(ctxt, XML_ERR_INTERNAL_ERROR, |
9259 | 0 | "Unexpected change of input\n"); |
9260 | 0 | localname = NULL; |
9261 | 0 | goto done; |
9262 | 0 | } |
9263 | | |
9264 | | /* Reconstruct attribute value pointers. */ |
9265 | 1.35M | for (i = 0, j = 0; j < nratts; i += 5, j++) { |
9266 | 8.88k | if (atts[i+2] != NULL) { |
9267 | | /* |
9268 | | * Arithmetic on dangling pointers is technically undefined |
9269 | | * behavior, but well... |
9270 | | */ |
9271 | 3.06k | const xmlChar *old = atts[i+2]; |
9272 | 3.06k | atts[i+2] = NULL; /* Reset repurposed namespace URI */ |
9273 | 3.06k | atts[i+3] = ctxt->input->base + (atts[i+3] - old); /* value */ |
9274 | 3.06k | atts[i+4] = ctxt->input->base + (atts[i+4] - old); /* valuend */ |
9275 | 3.06k | } |
9276 | 8.88k | } |
9277 | | |
9278 | | /* |
9279 | | * The attributes defaulting |
9280 | | */ |
9281 | 1.34M | if (ctxt->attsDefault != NULL) { |
9282 | 4.13k | xmlDefAttrsPtr defaults; |
9283 | | |
9284 | 4.13k | defaults = xmlHashLookup2(ctxt->attsDefault, localname, prefix); |
9285 | 4.13k | if (defaults != NULL) { |
9286 | 2.57k | for (i = 0;i < defaults->nbAttrs;i++) { |
9287 | 1.28k | attname = defaults->values[5 * i]; |
9288 | 1.28k | aprefix = defaults->values[5 * i + 1]; |
9289 | | |
9290 | | /* |
9291 | | * special work for namespaces defaulted defs |
9292 | | */ |
9293 | 1.28k | if ((attname == ctxt->str_xmlns) && (aprefix == NULL)) { |
9294 | | /* |
9295 | | * check that it's not a defined namespace |
9296 | | */ |
9297 | 0 | for (j = 1;j <= nbNs;j++) |
9298 | 0 | if (ctxt->nsTab[ctxt->nsNr - 2 * j] == NULL) |
9299 | 0 | break; |
9300 | 0 | if (j <= nbNs) continue; |
9301 | | |
9302 | 0 | nsname = xmlGetNamespace(ctxt, NULL); |
9303 | 0 | if (nsname != defaults->values[5 * i + 2]) { |
9304 | 0 | if (nsPush(ctxt, NULL, |
9305 | 0 | defaults->values[5 * i + 2]) > 0) |
9306 | 0 | nbNs++; |
9307 | 0 | } |
9308 | 1.28k | } else if (aprefix == ctxt->str_xmlns) { |
9309 | | /* |
9310 | | * check that it's not a defined namespace |
9311 | | */ |
9312 | 0 | for (j = 1;j <= nbNs;j++) |
9313 | 0 | if (ctxt->nsTab[ctxt->nsNr - 2 * j] == attname) |
9314 | 0 | break; |
9315 | 0 | if (j <= nbNs) continue; |
9316 | | |
9317 | 0 | nsname = xmlGetNamespace(ctxt, attname); |
9318 | 0 | if (nsname != defaults->values[5 * i + 2]) { |
9319 | 0 | if (nsPush(ctxt, attname, |
9320 | 0 | defaults->values[5 * i + 2]) > 0) |
9321 | 0 | nbNs++; |
9322 | 0 | } |
9323 | 1.28k | } else { |
9324 | | /* |
9325 | | * check that it's not a defined attribute |
9326 | | */ |
9327 | 1.28k | for (j = 0;j < nbatts;j+=5) { |
9328 | 1.06k | if ((attname == atts[j]) && (aprefix == atts[j+1])) |
9329 | 1.06k | break; |
9330 | 1.06k | } |
9331 | 1.28k | if (j < nbatts) continue; |
9332 | | |
9333 | 226 | if ((atts == NULL) || (nbatts + 5 > maxatts)) { |
9334 | 0 | if (xmlCtxtGrowAttrs(ctxt, nbatts + 5) < 0) { |
9335 | 0 | localname = NULL; |
9336 | 0 | goto done; |
9337 | 0 | } |
9338 | 0 | maxatts = ctxt->maxatts; |
9339 | 0 | atts = ctxt->atts; |
9340 | 0 | } |
9341 | 226 | atts[nbatts++] = attname; |
9342 | 226 | atts[nbatts++] = aprefix; |
9343 | 226 | if (aprefix == NULL) |
9344 | 226 | atts[nbatts++] = NULL; |
9345 | 0 | else |
9346 | 0 | atts[nbatts++] = xmlGetNamespace(ctxt, aprefix); |
9347 | 226 | atts[nbatts++] = defaults->values[5 * i + 2]; |
9348 | 226 | atts[nbatts++] = defaults->values[5 * i + 3]; |
9349 | 226 | if ((ctxt->standalone == 1) && |
9350 | 226 | (defaults->values[5 * i + 4] != NULL)) { |
9351 | 0 | xmlValidityError(ctxt, XML_DTD_STANDALONE_DEFAULTED, |
9352 | 0 | "standalone: attribute %s on %s defaulted from external subset\n", |
9353 | 0 | attname, localname); |
9354 | 0 | } |
9355 | 226 | nbdef++; |
9356 | 226 | } |
9357 | 1.28k | } |
9358 | 1.28k | } |
9359 | 4.13k | } |
9360 | | |
9361 | | /* |
9362 | | * The attributes checkings |
9363 | | */ |
9364 | 1.35M | for (i = 0; i < nbatts;i += 5) { |
9365 | | /* |
9366 | | * The default namespace does not apply to attribute names. |
9367 | | */ |
9368 | 9.11k | if (atts[i + 1] != NULL) { |
9369 | 5.12k | nsname = xmlGetNamespace(ctxt, atts[i + 1]); |
9370 | 5.12k | if (nsname == NULL) { |
9371 | 334 | xmlNsErr(ctxt, XML_NS_ERR_UNDEFINED_NAMESPACE, |
9372 | 334 | "Namespace prefix %s for %s on %s is not defined\n", |
9373 | 334 | atts[i + 1], atts[i], localname); |
9374 | 334 | } |
9375 | 5.12k | atts[i + 2] = nsname; |
9376 | 5.12k | } else |
9377 | 3.98k | nsname = NULL; |
9378 | | /* |
9379 | | * [ WFC: Unique Att Spec ] |
9380 | | * No attribute name may appear more than once in the same |
9381 | | * start-tag or empty-element tag. |
9382 | | * As extended by the Namespace in XML REC. |
9383 | | */ |
9384 | 9.54k | for (j = 0; j < i;j += 5) { |
9385 | 425 | if (atts[i] == atts[j]) { |
9386 | 0 | if (atts[i+1] == atts[j+1]) { |
9387 | 0 | xmlErrAttributeDup(ctxt, atts[i+1], atts[i]); |
9388 | 0 | break; |
9389 | 0 | } |
9390 | 0 | if ((nsname != NULL) && (atts[j + 2] == nsname)) { |
9391 | 0 | xmlNsErr(ctxt, XML_NS_ERR_ATTRIBUTE_REDEFINED, |
9392 | 0 | "Namespaced Attribute %s in '%s' redefined\n", |
9393 | 0 | atts[i], nsname, NULL); |
9394 | 0 | break; |
9395 | 0 | } |
9396 | 0 | } |
9397 | 425 | } |
9398 | 9.11k | } |
9399 | | |
9400 | 1.34M | nsname = xmlGetNamespace(ctxt, prefix); |
9401 | 1.34M | if ((prefix != NULL) && (nsname == NULL)) { |
9402 | 10.4k | xmlNsErr(ctxt, XML_NS_ERR_UNDEFINED_NAMESPACE, |
9403 | 10.4k | "Namespace prefix %s on %s is not defined\n", |
9404 | 10.4k | prefix, localname, NULL); |
9405 | 10.4k | } |
9406 | 1.34M | *pref = prefix; |
9407 | 1.34M | *URI = nsname; |
9408 | | |
9409 | | /* |
9410 | | * SAX: Start of Element ! |
9411 | | */ |
9412 | 1.34M | if ((ctxt->sax != NULL) && (ctxt->sax->startElementNs != NULL) && |
9413 | 1.34M | (!ctxt->disableSAX)) { |
9414 | 1.34M | if (nbNs > 0) |
9415 | 6.23k | ctxt->sax->startElementNs(ctxt->userData, localname, prefix, |
9416 | 6.23k | nsname, nbNs, &ctxt->nsTab[ctxt->nsNr - 2 * nbNs], |
9417 | 6.23k | nbatts / 5, nbdef, atts); |
9418 | 1.33M | else |
9419 | 1.33M | ctxt->sax->startElementNs(ctxt->userData, localname, prefix, |
9420 | 1.33M | nsname, 0, NULL, nbatts / 5, nbdef, atts); |
9421 | 1.34M | } |
9422 | | |
9423 | 1.34M | done: |
9424 | | /* |
9425 | | * Free up attribute allocated strings if needed |
9426 | | */ |
9427 | 1.34M | if (attval != 0) { |
9428 | 11.6k | for (i = 3,j = 0; j < nratts;i += 5,j++) |
9429 | 5.82k | if ((ctxt->attallocs[j] != 0) && (atts[i] != NULL)) |
9430 | 5.82k | xmlFree((xmlChar *) atts[i]); |
9431 | 5.82k | } |
9432 | | |
9433 | 1.34M | return(localname); |
9434 | 1.34M | } |
9435 | | |
9436 | | /** |
9437 | | * xmlParseEndTag2: |
9438 | | * @ctxt: an XML parser context |
9439 | | * @line: line of the start tag |
9440 | | * @nsNr: number of namespaces on the start tag |
9441 | | * |
9442 | | * Parse an end tag. Always consumes '</'. |
9443 | | * |
9444 | | * [42] ETag ::= '</' Name S? '>' |
9445 | | * |
9446 | | * With namespace |
9447 | | * |
9448 | | * [NS 9] ETag ::= '</' QName S? '>' |
9449 | | */ |
9450 | | |
9451 | | static void |
9452 | 4.20k | xmlParseEndTag2(xmlParserCtxtPtr ctxt, const xmlStartTag *tag) { |
9453 | 4.20k | const xmlChar *name; |
9454 | | |
9455 | 4.20k | GROW; |
9456 | 4.20k | if ((RAW != '<') || (NXT(1) != '/')) { |
9457 | 0 | xmlFatalErr(ctxt, XML_ERR_LTSLASH_REQUIRED, NULL); |
9458 | 0 | return; |
9459 | 0 | } |
9460 | 4.20k | SKIP(2); |
9461 | | |
9462 | 4.20k | if (tag->prefix == NULL) |
9463 | 1.71k | name = xmlParseNameAndCompare(ctxt, ctxt->name); |
9464 | 2.48k | else |
9465 | 2.48k | name = xmlParseQNameAndCompare(ctxt, ctxt->name, tag->prefix); |
9466 | | |
9467 | | /* |
9468 | | * We should definitely be at the ending "S? '>'" part |
9469 | | */ |
9470 | 4.20k | GROW; |
9471 | 4.20k | if (ctxt->instate == XML_PARSER_EOF) |
9472 | 0 | return; |
9473 | 4.20k | SKIP_BLANKS; |
9474 | 4.20k | if ((!IS_BYTE_CHAR(RAW)) || (RAW != '>')) { |
9475 | 1.82k | xmlFatalErr(ctxt, XML_ERR_GT_REQUIRED, NULL); |
9476 | 1.82k | } else |
9477 | 2.37k | NEXT1; |
9478 | | |
9479 | | /* |
9480 | | * [ WFC: Element Type Match ] |
9481 | | * The Name in an element's end-tag must match the element type in the |
9482 | | * start-tag. |
9483 | | * |
9484 | | */ |
9485 | 4.20k | if (name != (xmlChar*)1) { |
9486 | 2.67k | if (name == NULL) name = BAD_CAST "unparsable"; |
9487 | 2.67k | xmlFatalErrMsgStrIntStr(ctxt, XML_ERR_TAG_NAME_MISMATCH, |
9488 | 2.67k | "Opening and ending tag mismatch: %s line %d and %s\n", |
9489 | 2.67k | ctxt->name, tag->line, name); |
9490 | 2.67k | } |
9491 | | |
9492 | | /* |
9493 | | * SAX: End of Tag |
9494 | | */ |
9495 | 4.20k | if ((ctxt->sax != NULL) && (ctxt->sax->endElementNs != NULL) && |
9496 | 4.20k | (!ctxt->disableSAX)) |
9497 | 4.18k | ctxt->sax->endElementNs(ctxt->userData, ctxt->name, tag->prefix, |
9498 | 4.18k | tag->URI); |
9499 | | |
9500 | 4.20k | spacePop(ctxt); |
9501 | 4.20k | if (tag->nsNr != 0) |
9502 | 607 | nsPop(ctxt, tag->nsNr); |
9503 | 4.20k | } |
9504 | | |
9505 | | /** |
9506 | | * xmlParseCDSect: |
9507 | | * @ctxt: an XML parser context |
9508 | | * |
9509 | | * DEPRECATED: Internal function, don't use. |
9510 | | * |
9511 | | * Parse escaped pure raw content. Always consumes '<!['. |
9512 | | * |
9513 | | * [18] CDSect ::= CDStart CData CDEnd |
9514 | | * |
9515 | | * [19] CDStart ::= '<![CDATA[' |
9516 | | * |
9517 | | * [20] Data ::= (Char* - (Char* ']]>' Char*)) |
9518 | | * |
9519 | | * [21] CDEnd ::= ']]>' |
9520 | | */ |
9521 | | void |
9522 | 979 | xmlParseCDSect(xmlParserCtxtPtr ctxt) { |
9523 | 979 | xmlChar *buf = NULL; |
9524 | 979 | int len = 0; |
9525 | 979 | int size = XML_PARSER_BUFFER_SIZE; |
9526 | 979 | int r, rl; |
9527 | 979 | int s, sl; |
9528 | 979 | int cur, l; |
9529 | 979 | int maxLength = (ctxt->options & XML_PARSE_HUGE) ? |
9530 | 0 | XML_MAX_HUGE_LENGTH : |
9531 | 979 | XML_MAX_TEXT_LENGTH; |
9532 | | |
9533 | 979 | if ((CUR != '<') || (NXT(1) != '!') || (NXT(2) != '[')) |
9534 | 0 | return; |
9535 | 979 | SKIP(3); |
9536 | | |
9537 | 979 | if (!CMP6(CUR_PTR, 'C', 'D', 'A', 'T', 'A', '[')) |
9538 | 0 | return; |
9539 | 979 | SKIP(6); |
9540 | | |
9541 | 979 | ctxt->instate = XML_PARSER_CDATA_SECTION; |
9542 | 979 | r = CUR_CHAR(rl); |
9543 | 979 | if (!IS_CHAR(r)) { |
9544 | 0 | xmlFatalErr(ctxt, XML_ERR_CDATA_NOT_FINISHED, NULL); |
9545 | 0 | goto out; |
9546 | 0 | } |
9547 | 979 | NEXTL(rl); |
9548 | 979 | s = CUR_CHAR(sl); |
9549 | 979 | if (!IS_CHAR(s)) { |
9550 | 4 | xmlFatalErr(ctxt, XML_ERR_CDATA_NOT_FINISHED, NULL); |
9551 | 4 | goto out; |
9552 | 4 | } |
9553 | 975 | NEXTL(sl); |
9554 | 975 | cur = CUR_CHAR(l); |
9555 | 975 | buf = (xmlChar *) xmlMallocAtomic(size); |
9556 | 975 | if (buf == NULL) { |
9557 | 0 | xmlErrMemory(ctxt, NULL); |
9558 | 0 | goto out; |
9559 | 0 | } |
9560 | 3.01M | while (IS_CHAR(cur) && |
9561 | 3.01M | ((r != ']') || (s != ']') || (cur != '>'))) { |
9562 | 3.01M | if (len + 5 >= size) { |
9563 | 362 | xmlChar *tmp; |
9564 | | |
9565 | 362 | tmp = (xmlChar *) xmlRealloc(buf, size * 2); |
9566 | 362 | if (tmp == NULL) { |
9567 | 0 | xmlErrMemory(ctxt, NULL); |
9568 | 0 | goto out; |
9569 | 0 | } |
9570 | 362 | buf = tmp; |
9571 | 362 | size *= 2; |
9572 | 362 | } |
9573 | 3.01M | COPY_BUF(rl,buf,len,r); |
9574 | 3.01M | if (len > maxLength) { |
9575 | 0 | xmlFatalErrMsg(ctxt, XML_ERR_CDATA_NOT_FINISHED, |
9576 | 0 | "CData section too big found\n"); |
9577 | 0 | goto out; |
9578 | 0 | } |
9579 | 3.01M | r = s; |
9580 | 3.01M | rl = sl; |
9581 | 3.01M | s = cur; |
9582 | 3.01M | sl = l; |
9583 | 3.01M | NEXTL(l); |
9584 | 3.01M | cur = CUR_CHAR(l); |
9585 | 3.01M | } |
9586 | 975 | buf[len] = 0; |
9587 | 975 | if (ctxt->instate == XML_PARSER_EOF) { |
9588 | 3 | xmlFree(buf); |
9589 | 3 | return; |
9590 | 3 | } |
9591 | 972 | if (cur != '>') { |
9592 | 45 | xmlFatalErrMsgStr(ctxt, XML_ERR_CDATA_NOT_FINISHED, |
9593 | 45 | "CData section not finished\n%.50s\n", buf); |
9594 | 45 | goto out; |
9595 | 45 | } |
9596 | 927 | NEXTL(l); |
9597 | | |
9598 | | /* |
9599 | | * OK the buffer is to be consumed as cdata. |
9600 | | */ |
9601 | 927 | if ((ctxt->sax != NULL) && (!ctxt->disableSAX)) { |
9602 | 927 | if (ctxt->sax->cdataBlock != NULL) |
9603 | 927 | ctxt->sax->cdataBlock(ctxt->userData, buf, len); |
9604 | 0 | else if (ctxt->sax->characters != NULL) |
9605 | 0 | ctxt->sax->characters(ctxt->userData, buf, len); |
9606 | 927 | } |
9607 | | |
9608 | 976 | out: |
9609 | 976 | if (ctxt->instate != XML_PARSER_EOF) |
9610 | 976 | ctxt->instate = XML_PARSER_CONTENT; |
9611 | 976 | xmlFree(buf); |
9612 | 976 | } |
9613 | | |
9614 | | /** |
9615 | | * xmlParseContentInternal: |
9616 | | * @ctxt: an XML parser context |
9617 | | * |
9618 | | * Parse a content sequence. Stops at EOF or '</'. Leaves checking of |
9619 | | * unexpected EOF to the caller. |
9620 | | */ |
9621 | | |
9622 | | static void |
9623 | 344 | xmlParseContentInternal(xmlParserCtxtPtr ctxt) { |
9624 | 344 | int nameNr = ctxt->nameNr; |
9625 | | |
9626 | 344 | GROW; |
9627 | 1.66M | while ((RAW != 0) && |
9628 | 1.66M | (ctxt->instate != XML_PARSER_EOF)) { |
9629 | 1.66M | const xmlChar *cur = ctxt->input->cur; |
9630 | | |
9631 | | /* |
9632 | | * First case : a Processing Instruction. |
9633 | | */ |
9634 | 1.66M | if ((*cur == '<') && (cur[1] == '?')) { |
9635 | 8.81k | xmlParsePI(ctxt); |
9636 | 8.81k | } |
9637 | | |
9638 | | /* |
9639 | | * Second case : a CDSection |
9640 | | */ |
9641 | | /* 2.6.0 test was *cur not RAW */ |
9642 | 1.65M | else if (CMP9(CUR_PTR, '<', '!', '[', 'C', 'D', 'A', 'T', 'A', '[')) { |
9643 | 979 | xmlParseCDSect(ctxt); |
9644 | 979 | } |
9645 | | |
9646 | | /* |
9647 | | * Third case : a comment |
9648 | | */ |
9649 | 1.65M | else if ((*cur == '<') && (NXT(1) == '!') && |
9650 | 1.65M | (NXT(2) == '-') && (NXT(3) == '-')) { |
9651 | 1.09k | xmlParseComment(ctxt); |
9652 | 1.09k | ctxt->instate = XML_PARSER_CONTENT; |
9653 | 1.09k | } |
9654 | | |
9655 | | /* |
9656 | | * Fourth case : a sub-element. |
9657 | | */ |
9658 | 1.65M | else if (*cur == '<') { |
9659 | 1.37M | if (NXT(1) == '/') { |
9660 | 4.20k | if (ctxt->nameNr <= nameNr) |
9661 | 1 | break; |
9662 | 4.20k | xmlParseElementEnd(ctxt); |
9663 | 1.36M | } else { |
9664 | 1.36M | xmlParseElementStart(ctxt); |
9665 | 1.36M | } |
9666 | 1.37M | } |
9667 | | |
9668 | | /* |
9669 | | * Fifth case : a reference. If if has not been resolved, |
9670 | | * parsing returns it's Name, create the node |
9671 | | */ |
9672 | | |
9673 | 276k | else if (*cur == '&') { |
9674 | 24.5k | xmlParseReference(ctxt); |
9675 | 24.5k | } |
9676 | | |
9677 | | /* |
9678 | | * Last case, text. Note that References are handled directly. |
9679 | | */ |
9680 | 252k | else { |
9681 | 252k | xmlParseCharDataInternal(ctxt, 0); |
9682 | 252k | } |
9683 | | |
9684 | 1.66M | SHRINK; |
9685 | 1.66M | GROW; |
9686 | 1.66M | } |
9687 | 344 | } |
9688 | | |
9689 | | /** |
9690 | | * xmlParseContent: |
9691 | | * @ctxt: an XML parser context |
9692 | | * |
9693 | | * Parse a content sequence. Stops at EOF or '</'. |
9694 | | * |
9695 | | * [43] content ::= (element | CharData | Reference | CDSect | PI | Comment)* |
9696 | | */ |
9697 | | |
9698 | | void |
9699 | 4 | xmlParseContent(xmlParserCtxtPtr ctxt) { |
9700 | 4 | int nameNr = ctxt->nameNr; |
9701 | | |
9702 | 4 | xmlParseContentInternal(ctxt); |
9703 | | |
9704 | 4 | if ((ctxt->instate != XML_PARSER_EOF) && (ctxt->nameNr > nameNr)) { |
9705 | 2 | const xmlChar *name = ctxt->nameTab[ctxt->nameNr - 1]; |
9706 | 2 | int line = ctxt->pushTab[ctxt->nameNr - 1].line; |
9707 | 2 | xmlFatalErrMsgStrIntStr(ctxt, XML_ERR_TAG_NOT_FINISHED, |
9708 | 2 | "Premature end of data in tag %s line %d\n", |
9709 | 2 | name, line, NULL); |
9710 | 2 | } |
9711 | 4 | } |
9712 | | |
9713 | | /** |
9714 | | * xmlParseElement: |
9715 | | * @ctxt: an XML parser context |
9716 | | * |
9717 | | * DEPRECATED: Internal function, don't use. |
9718 | | * |
9719 | | * parse an XML element |
9720 | | * |
9721 | | * [39] element ::= EmptyElemTag | STag content ETag |
9722 | | * |
9723 | | * [ WFC: Element Type Match ] |
9724 | | * The Name in an element's end-tag must match the element type in the |
9725 | | * start-tag. |
9726 | | * |
9727 | | */ |
9728 | | |
9729 | | void |
9730 | 342 | xmlParseElement(xmlParserCtxtPtr ctxt) { |
9731 | 342 | if (xmlParseElementStart(ctxt) != 0) |
9732 | 2 | return; |
9733 | | |
9734 | 340 | xmlParseContentInternal(ctxt); |
9735 | 340 | if (ctxt->instate == XML_PARSER_EOF) |
9736 | 42 | return; |
9737 | | |
9738 | 298 | if (CUR == 0) { |
9739 | 297 | const xmlChar *name = ctxt->nameTab[ctxt->nameNr - 1]; |
9740 | 297 | int line = ctxt->pushTab[ctxt->nameNr - 1].line; |
9741 | 297 | xmlFatalErrMsgStrIntStr(ctxt, XML_ERR_TAG_NOT_FINISHED, |
9742 | 297 | "Premature end of data in tag %s line %d\n", |
9743 | 297 | name, line, NULL); |
9744 | 297 | return; |
9745 | 297 | } |
9746 | | |
9747 | 1 | xmlParseElementEnd(ctxt); |
9748 | 1 | } |
9749 | | |
9750 | | /** |
9751 | | * xmlParseElementStart: |
9752 | | * @ctxt: an XML parser context |
9753 | | * |
9754 | | * Parse the start of an XML element. Returns -1 in case of error, 0 if an |
9755 | | * opening tag was parsed, 1 if an empty element was parsed. |
9756 | | * |
9757 | | * Always consumes '<'. |
9758 | | */ |
9759 | | static int |
9760 | 1.36M | xmlParseElementStart(xmlParserCtxtPtr ctxt) { |
9761 | 1.36M | const xmlChar *name; |
9762 | 1.36M | const xmlChar *prefix = NULL; |
9763 | 1.36M | const xmlChar *URI = NULL; |
9764 | 1.36M | xmlParserNodeInfo node_info; |
9765 | 1.36M | int line, tlen = 0; |
9766 | 1.36M | xmlNodePtr cur; |
9767 | 1.36M | int nsNr = ctxt->nsNr; |
9768 | | |
9769 | 1.36M | if (((unsigned int) ctxt->nameNr > xmlParserMaxDepth) && |
9770 | 1.36M | ((ctxt->options & XML_PARSE_HUGE) == 0)) { |
9771 | 6 | xmlFatalErrMsgInt(ctxt, XML_ERR_INTERNAL_ERROR, |
9772 | 6 | "Excessive depth in document: %d use XML_PARSE_HUGE option\n", |
9773 | 6 | xmlParserMaxDepth); |
9774 | 6 | xmlHaltParser(ctxt); |
9775 | 6 | return(-1); |
9776 | 6 | } |
9777 | | |
9778 | | /* Capture start position */ |
9779 | 1.36M | if (ctxt->record_info) { |
9780 | 0 | node_info.begin_pos = ctxt->input->consumed + |
9781 | 0 | (CUR_PTR - ctxt->input->base); |
9782 | 0 | node_info.begin_line = ctxt->input->line; |
9783 | 0 | } |
9784 | | |
9785 | 1.36M | if (ctxt->spaceNr == 0) |
9786 | 0 | spacePush(ctxt, -1); |
9787 | 1.36M | else if (*ctxt->space == -2) |
9788 | 0 | spacePush(ctxt, -1); |
9789 | 1.36M | else |
9790 | 1.36M | spacePush(ctxt, *ctxt->space); |
9791 | | |
9792 | 1.36M | line = ctxt->input->line; |
9793 | | #ifdef LIBXML_SAX1_ENABLED |
9794 | | if (ctxt->sax2) |
9795 | | #endif /* LIBXML_SAX1_ENABLED */ |
9796 | 1.36M | name = xmlParseStartTag2(ctxt, &prefix, &URI, &tlen); |
9797 | | #ifdef LIBXML_SAX1_ENABLED |
9798 | | else |
9799 | | name = xmlParseStartTag(ctxt); |
9800 | | #endif /* LIBXML_SAX1_ENABLED */ |
9801 | 1.36M | if (ctxt->instate == XML_PARSER_EOF) |
9802 | 23 | return(-1); |
9803 | 1.36M | if (name == NULL) { |
9804 | 26.3k | spacePop(ctxt); |
9805 | 26.3k | return(-1); |
9806 | 26.3k | } |
9807 | 1.34M | nameNsPush(ctxt, name, prefix, URI, line, ctxt->nsNr - nsNr); |
9808 | 1.34M | cur = ctxt->node; |
9809 | | |
9810 | | #ifdef LIBXML_VALID_ENABLED |
9811 | | /* |
9812 | | * [ VC: Root Element Type ] |
9813 | | * The Name in the document type declaration must match the element |
9814 | | * type of the root element. |
9815 | | */ |
9816 | | if (ctxt->validate && ctxt->wellFormed && ctxt->myDoc && |
9817 | | ctxt->node && (ctxt->node == ctxt->myDoc->children)) |
9818 | | ctxt->valid &= xmlValidateRoot(&ctxt->vctxt, ctxt->myDoc); |
9819 | | #endif /* LIBXML_VALID_ENABLED */ |
9820 | | |
9821 | | /* |
9822 | | * Check for an Empty Element. |
9823 | | */ |
9824 | 1.34M | if ((RAW == '/') && (NXT(1) == '>')) { |
9825 | 828 | SKIP(2); |
9826 | 828 | if (ctxt->sax2) { |
9827 | 828 | if ((ctxt->sax != NULL) && (ctxt->sax->endElementNs != NULL) && |
9828 | 828 | (!ctxt->disableSAX)) |
9829 | 828 | ctxt->sax->endElementNs(ctxt->userData, name, prefix, URI); |
9830 | | #ifdef LIBXML_SAX1_ENABLED |
9831 | | } else { |
9832 | | if ((ctxt->sax != NULL) && (ctxt->sax->endElement != NULL) && |
9833 | | (!ctxt->disableSAX)) |
9834 | | ctxt->sax->endElement(ctxt->userData, name); |
9835 | | #endif /* LIBXML_SAX1_ENABLED */ |
9836 | 828 | } |
9837 | 828 | namePop(ctxt); |
9838 | 828 | spacePop(ctxt); |
9839 | 828 | if (nsNr != ctxt->nsNr) |
9840 | 0 | nsPop(ctxt, ctxt->nsNr - nsNr); |
9841 | 828 | if (cur != NULL && ctxt->record_info) { |
9842 | 0 | node_info.node = cur; |
9843 | 0 | node_info.end_pos = ctxt->input->consumed + |
9844 | 0 | (CUR_PTR - ctxt->input->base); |
9845 | 0 | node_info.end_line = ctxt->input->line; |
9846 | 0 | xmlParserAddNodeInfo(ctxt, &node_info); |
9847 | 0 | } |
9848 | 828 | return(1); |
9849 | 828 | } |
9850 | 1.34M | if (RAW == '>') { |
9851 | 17.3k | NEXT1; |
9852 | 17.3k | if (cur != NULL && ctxt->record_info) { |
9853 | 0 | node_info.node = cur; |
9854 | 0 | node_info.end_pos = 0; |
9855 | 0 | node_info.end_line = 0; |
9856 | 0 | xmlParserAddNodeInfo(ctxt, &node_info); |
9857 | 0 | } |
9858 | 1.32M | } else { |
9859 | 1.32M | xmlFatalErrMsgStrIntStr(ctxt, XML_ERR_GT_REQUIRED, |
9860 | 1.32M | "Couldn't find end of Start Tag %s line %d\n", |
9861 | 1.32M | name, line, NULL); |
9862 | | |
9863 | | /* |
9864 | | * end of parsing of this node. |
9865 | | */ |
9866 | 1.32M | nodePop(ctxt); |
9867 | 1.32M | namePop(ctxt); |
9868 | 1.32M | spacePop(ctxt); |
9869 | 1.32M | if (nsNr != ctxt->nsNr) |
9870 | 5.16k | nsPop(ctxt, ctxt->nsNr - nsNr); |
9871 | 1.32M | return(-1); |
9872 | 1.32M | } |
9873 | | |
9874 | 17.3k | return(0); |
9875 | 1.34M | } |
9876 | | |
9877 | | /** |
9878 | | * xmlParseElementEnd: |
9879 | | * @ctxt: an XML parser context |
9880 | | * |
9881 | | * Parse the end of an XML element. Always consumes '</'. |
9882 | | */ |
9883 | | static void |
9884 | 4.20k | xmlParseElementEnd(xmlParserCtxtPtr ctxt) { |
9885 | 4.20k | xmlNodePtr cur = ctxt->node; |
9886 | | |
9887 | 4.20k | if (ctxt->nameNr <= 0) { |
9888 | 0 | if ((RAW == '<') && (NXT(1) == '/')) |
9889 | 0 | SKIP(2); |
9890 | 0 | return; |
9891 | 0 | } |
9892 | | |
9893 | | /* |
9894 | | * parse the end of tag: '</' should be here. |
9895 | | */ |
9896 | 4.20k | if (ctxt->sax2) { |
9897 | 4.20k | xmlParseEndTag2(ctxt, &ctxt->pushTab[ctxt->nameNr - 1]); |
9898 | 4.20k | namePop(ctxt); |
9899 | 4.20k | } |
9900 | | #ifdef LIBXML_SAX1_ENABLED |
9901 | | else |
9902 | | xmlParseEndTag1(ctxt, 0); |
9903 | | #endif /* LIBXML_SAX1_ENABLED */ |
9904 | | |
9905 | | /* |
9906 | | * Capture end position |
9907 | | */ |
9908 | 4.20k | if (cur != NULL && ctxt->record_info) { |
9909 | 0 | xmlParserNodeInfoPtr node_info; |
9910 | |
|
9911 | 0 | node_info = (xmlParserNodeInfoPtr) xmlParserFindNodeInfo(ctxt, cur); |
9912 | 0 | if (node_info != NULL) { |
9913 | 0 | node_info->end_pos = ctxt->input->consumed + |
9914 | 0 | (CUR_PTR - ctxt->input->base); |
9915 | 0 | node_info->end_line = ctxt->input->line; |
9916 | 0 | } |
9917 | 0 | } |
9918 | 4.20k | } |
9919 | | |
9920 | | /** |
9921 | | * xmlParseVersionNum: |
9922 | | * @ctxt: an XML parser context |
9923 | | * |
9924 | | * DEPRECATED: Internal function, don't use. |
9925 | | * |
9926 | | * parse the XML version value. |
9927 | | * |
9928 | | * [26] VersionNum ::= '1.' [0-9]+ |
9929 | | * |
9930 | | * In practice allow [0-9].[0-9]+ at that level |
9931 | | * |
9932 | | * Returns the string giving the XML version number, or NULL |
9933 | | */ |
9934 | | xmlChar * |
9935 | 5 | xmlParseVersionNum(xmlParserCtxtPtr ctxt) { |
9936 | 5 | xmlChar *buf = NULL; |
9937 | 5 | int len = 0; |
9938 | 5 | int size = 10; |
9939 | 5 | xmlChar cur; |
9940 | | |
9941 | 5 | buf = (xmlChar *) xmlMallocAtomic(size); |
9942 | 5 | if (buf == NULL) { |
9943 | 0 | xmlErrMemory(ctxt, NULL); |
9944 | 0 | return(NULL); |
9945 | 0 | } |
9946 | 5 | cur = CUR; |
9947 | 5 | if (!((cur >= '0') && (cur <= '9'))) { |
9948 | 0 | xmlFree(buf); |
9949 | 0 | return(NULL); |
9950 | 0 | } |
9951 | 5 | buf[len++] = cur; |
9952 | 5 | NEXT; |
9953 | 5 | cur=CUR; |
9954 | 5 | if (cur != '.') { |
9955 | 0 | xmlFree(buf); |
9956 | 0 | return(NULL); |
9957 | 0 | } |
9958 | 5 | buf[len++] = cur; |
9959 | 5 | NEXT; |
9960 | 5 | cur=CUR; |
9961 | 778k | while ((cur >= '0') && (cur <= '9')) { |
9962 | 778k | if (len + 1 >= size) { |
9963 | 45 | xmlChar *tmp; |
9964 | | |
9965 | 45 | size *= 2; |
9966 | 45 | tmp = (xmlChar *) xmlRealloc(buf, size); |
9967 | 45 | if (tmp == NULL) { |
9968 | 0 | xmlFree(buf); |
9969 | 0 | xmlErrMemory(ctxt, NULL); |
9970 | 0 | return(NULL); |
9971 | 0 | } |
9972 | 45 | buf = tmp; |
9973 | 45 | } |
9974 | 778k | buf[len++] = cur; |
9975 | 778k | NEXT; |
9976 | 778k | cur=CUR; |
9977 | 778k | } |
9978 | 5 | buf[len] = 0; |
9979 | 5 | return(buf); |
9980 | 5 | } |
9981 | | |
9982 | | /** |
9983 | | * xmlParseVersionInfo: |
9984 | | * @ctxt: an XML parser context |
9985 | | * |
9986 | | * DEPRECATED: Internal function, don't use. |
9987 | | * |
9988 | | * parse the XML version. |
9989 | | * |
9990 | | * [24] VersionInfo ::= S 'version' Eq (' VersionNum ' | " VersionNum ") |
9991 | | * |
9992 | | * [25] Eq ::= S? '=' S? |
9993 | | * |
9994 | | * Returns the version string, e.g. "1.0" |
9995 | | */ |
9996 | | |
9997 | | xmlChar * |
9998 | 96 | xmlParseVersionInfo(xmlParserCtxtPtr ctxt) { |
9999 | 96 | xmlChar *version = NULL; |
10000 | | |
10001 | 96 | if (CMP7(CUR_PTR, 'v', 'e', 'r', 's', 'i', 'o', 'n')) { |
10002 | 5 | SKIP(7); |
10003 | 5 | SKIP_BLANKS; |
10004 | 5 | if (RAW != '=') { |
10005 | 0 | xmlFatalErr(ctxt, XML_ERR_EQUAL_REQUIRED, NULL); |
10006 | 0 | return(NULL); |
10007 | 0 | } |
10008 | 5 | NEXT; |
10009 | 5 | SKIP_BLANKS; |
10010 | 5 | if (RAW == '"') { |
10011 | 5 | NEXT; |
10012 | 5 | version = xmlParseVersionNum(ctxt); |
10013 | 5 | if (RAW != '"') { |
10014 | 3 | xmlFatalErr(ctxt, XML_ERR_STRING_NOT_CLOSED, NULL); |
10015 | 3 | } else |
10016 | 2 | NEXT; |
10017 | 5 | } else if (RAW == '\''){ |
10018 | 0 | NEXT; |
10019 | 0 | version = xmlParseVersionNum(ctxt); |
10020 | 0 | if (RAW != '\'') { |
10021 | 0 | xmlFatalErr(ctxt, XML_ERR_STRING_NOT_CLOSED, NULL); |
10022 | 0 | } else |
10023 | 0 | NEXT; |
10024 | 0 | } else { |
10025 | 0 | xmlFatalErr(ctxt, XML_ERR_STRING_NOT_STARTED, NULL); |
10026 | 0 | } |
10027 | 5 | } |
10028 | 96 | return(version); |
10029 | 96 | } |
10030 | | |
10031 | | /** |
10032 | | * xmlParseEncName: |
10033 | | * @ctxt: an XML parser context |
10034 | | * |
10035 | | * DEPRECATED: Internal function, don't use. |
10036 | | * |
10037 | | * parse the XML encoding name |
10038 | | * |
10039 | | * [81] EncName ::= [A-Za-z] ([A-Za-z0-9._] | '-')* |
10040 | | * |
10041 | | * Returns the encoding name value or NULL |
10042 | | */ |
10043 | | xmlChar * |
10044 | 91 | xmlParseEncName(xmlParserCtxtPtr ctxt) { |
10045 | 91 | xmlChar *buf = NULL; |
10046 | 91 | int len = 0; |
10047 | 91 | int size = 10; |
10048 | 91 | int maxLength = (ctxt->options & XML_PARSE_HUGE) ? |
10049 | 0 | XML_MAX_TEXT_LENGTH : |
10050 | 91 | XML_MAX_NAME_LENGTH; |
10051 | 91 | xmlChar cur; |
10052 | | |
10053 | 91 | cur = CUR; |
10054 | 91 | if (((cur >= 'a') && (cur <= 'z')) || |
10055 | 91 | ((cur >= 'A') && (cur <= 'Z'))) { |
10056 | 91 | buf = (xmlChar *) xmlMallocAtomic(size); |
10057 | 91 | if (buf == NULL) { |
10058 | 0 | xmlErrMemory(ctxt, NULL); |
10059 | 0 | return(NULL); |
10060 | 0 | } |
10061 | | |
10062 | 91 | buf[len++] = cur; |
10063 | 91 | NEXT; |
10064 | 91 | cur = CUR; |
10065 | 955 | while (((cur >= 'a') && (cur <= 'z')) || |
10066 | 955 | ((cur >= 'A') && (cur <= 'Z')) || |
10067 | 955 | ((cur >= '0') && (cur <= '9')) || |
10068 | 955 | (cur == '.') || (cur == '_') || |
10069 | 955 | (cur == '-')) { |
10070 | 864 | if (len + 1 >= size) { |
10071 | 89 | xmlChar *tmp; |
10072 | | |
10073 | 89 | size *= 2; |
10074 | 89 | tmp = (xmlChar *) xmlRealloc(buf, size); |
10075 | 89 | if (tmp == NULL) { |
10076 | 0 | xmlErrMemory(ctxt, NULL); |
10077 | 0 | xmlFree(buf); |
10078 | 0 | return(NULL); |
10079 | 0 | } |
10080 | 89 | buf = tmp; |
10081 | 89 | } |
10082 | 864 | buf[len++] = cur; |
10083 | 864 | if (len > maxLength) { |
10084 | 0 | xmlFatalErr(ctxt, XML_ERR_NAME_TOO_LONG, "EncName"); |
10085 | 0 | xmlFree(buf); |
10086 | 0 | return(NULL); |
10087 | 0 | } |
10088 | 864 | NEXT; |
10089 | 864 | cur = CUR; |
10090 | 864 | } |
10091 | 91 | buf[len] = 0; |
10092 | 91 | } else { |
10093 | 0 | xmlFatalErr(ctxt, XML_ERR_ENCODING_NAME, NULL); |
10094 | 0 | } |
10095 | 91 | return(buf); |
10096 | 91 | } |
10097 | | |
10098 | | /** |
10099 | | * xmlParseEncodingDecl: |
10100 | | * @ctxt: an XML parser context |
10101 | | * |
10102 | | * DEPRECATED: Internal function, don't use. |
10103 | | * |
10104 | | * parse the XML encoding declaration |
10105 | | * |
10106 | | * [80] EncodingDecl ::= S 'encoding' Eq ('"' EncName '"' | "'" EncName "'") |
10107 | | * |
10108 | | * this setups the conversion filters. |
10109 | | * |
10110 | | * Returns the encoding value or NULL |
10111 | | */ |
10112 | | |
10113 | | const xmlChar * |
10114 | 96 | xmlParseEncodingDecl(xmlParserCtxtPtr ctxt) { |
10115 | 96 | xmlChar *encoding = NULL; |
10116 | | |
10117 | 96 | SKIP_BLANKS; |
10118 | 96 | if (CMP8(CUR_PTR, 'e', 'n', 'c', 'o', 'd', 'i', 'n', 'g')) { |
10119 | 91 | SKIP(8); |
10120 | 91 | SKIP_BLANKS; |
10121 | 91 | if (RAW != '=') { |
10122 | 0 | xmlFatalErr(ctxt, XML_ERR_EQUAL_REQUIRED, NULL); |
10123 | 0 | return(NULL); |
10124 | 0 | } |
10125 | 91 | NEXT; |
10126 | 91 | SKIP_BLANKS; |
10127 | 91 | if (RAW == '"') { |
10128 | 2 | NEXT; |
10129 | 2 | encoding = xmlParseEncName(ctxt); |
10130 | 2 | if (RAW != '"') { |
10131 | 0 | xmlFatalErr(ctxt, XML_ERR_STRING_NOT_CLOSED, NULL); |
10132 | 0 | xmlFree((xmlChar *) encoding); |
10133 | 0 | return(NULL); |
10134 | 0 | } else |
10135 | 2 | NEXT; |
10136 | 89 | } else if (RAW == '\''){ |
10137 | 89 | NEXT; |
10138 | 89 | encoding = xmlParseEncName(ctxt); |
10139 | 89 | if (RAW != '\'') { |
10140 | 3 | xmlFatalErr(ctxt, XML_ERR_STRING_NOT_CLOSED, NULL); |
10141 | 3 | xmlFree((xmlChar *) encoding); |
10142 | 3 | return(NULL); |
10143 | 3 | } else |
10144 | 86 | NEXT; |
10145 | 89 | } else { |
10146 | 0 | xmlFatalErr(ctxt, XML_ERR_STRING_NOT_STARTED, NULL); |
10147 | 0 | } |
10148 | | |
10149 | | /* |
10150 | | * Non standard parsing, allowing the user to ignore encoding |
10151 | | */ |
10152 | 88 | if (ctxt->options & XML_PARSE_IGNORE_ENC) { |
10153 | 0 | xmlFree((xmlChar *) encoding); |
10154 | 0 | return(NULL); |
10155 | 0 | } |
10156 | | |
10157 | | /* |
10158 | | * UTF-16 encoding switch has already taken place at this stage, |
10159 | | * more over the little-endian/big-endian selection is already done |
10160 | | */ |
10161 | 88 | if ((encoding != NULL) && |
10162 | 88 | ((!xmlStrcasecmp(encoding, BAD_CAST "UTF-16")) || |
10163 | 88 | (!xmlStrcasecmp(encoding, BAD_CAST "UTF16")))) { |
10164 | | /* |
10165 | | * If no encoding was passed to the parser, that we are |
10166 | | * using UTF-16 and no decoder is present i.e. the |
10167 | | * document is apparently UTF-8 compatible, then raise an |
10168 | | * encoding mismatch fatal error |
10169 | | */ |
10170 | 0 | if ((ctxt->encoding == NULL) && |
10171 | 0 | (ctxt->input->buf != NULL) && |
10172 | 0 | (ctxt->input->buf->encoder == NULL)) { |
10173 | 0 | xmlFatalErrMsg(ctxt, XML_ERR_INVALID_ENCODING, |
10174 | 0 | "Document labelled UTF-16 but has UTF-8 content\n"); |
10175 | 0 | } |
10176 | 0 | if (ctxt->encoding != NULL) |
10177 | 0 | xmlFree((xmlChar *) ctxt->encoding); |
10178 | 0 | ctxt->encoding = encoding; |
10179 | 0 | } |
10180 | | /* |
10181 | | * UTF-8 encoding is handled natively |
10182 | | */ |
10183 | 88 | else if ((encoding != NULL) && |
10184 | 88 | ((!xmlStrcasecmp(encoding, BAD_CAST "UTF-8")) || |
10185 | 88 | (!xmlStrcasecmp(encoding, BAD_CAST "UTF8")))) { |
10186 | | /* TODO: Check for encoding mismatch. */ |
10187 | 0 | if (ctxt->encoding != NULL) |
10188 | 0 | xmlFree((xmlChar *) ctxt->encoding); |
10189 | 0 | ctxt->encoding = encoding; |
10190 | 0 | } |
10191 | 88 | else if (encoding != NULL) { |
10192 | 88 | xmlCharEncodingHandlerPtr handler; |
10193 | | |
10194 | 88 | if (ctxt->input->encoding != NULL) |
10195 | 0 | xmlFree((xmlChar *) ctxt->input->encoding); |
10196 | 88 | ctxt->input->encoding = encoding; |
10197 | | |
10198 | 88 | handler = xmlFindCharEncodingHandler((const char *) encoding); |
10199 | 88 | if (handler != NULL) { |
10200 | 88 | if (xmlSwitchToEncoding(ctxt, handler) < 0) { |
10201 | | /* failed to convert */ |
10202 | 0 | ctxt->errNo = XML_ERR_UNSUPPORTED_ENCODING; |
10203 | 0 | return(NULL); |
10204 | 0 | } |
10205 | 88 | } else { |
10206 | 0 | xmlFatalErrMsgStr(ctxt, XML_ERR_UNSUPPORTED_ENCODING, |
10207 | 0 | "Unsupported encoding %s\n", encoding); |
10208 | 0 | return(NULL); |
10209 | 0 | } |
10210 | 88 | } |
10211 | 88 | } |
10212 | 93 | return(encoding); |
10213 | 96 | } |
10214 | | |
10215 | | /** |
10216 | | * xmlParseSDDecl: |
10217 | | * @ctxt: an XML parser context |
10218 | | * |
10219 | | * DEPRECATED: Internal function, don't use. |
10220 | | * |
10221 | | * parse the XML standalone declaration |
10222 | | * |
10223 | | * [32] SDDecl ::= S 'standalone' Eq |
10224 | | * (("'" ('yes' | 'no') "'") | ('"' ('yes' | 'no')'"')) |
10225 | | * |
10226 | | * [ VC: Standalone Document Declaration ] |
10227 | | * TODO The standalone document declaration must have the value "no" |
10228 | | * if any external markup declarations contain declarations of: |
10229 | | * - attributes with default values, if elements to which these |
10230 | | * attributes apply appear in the document without specifications |
10231 | | * of values for these attributes, or |
10232 | | * - entities (other than amp, lt, gt, apos, quot), if references |
10233 | | * to those entities appear in the document, or |
10234 | | * - attributes with values subject to normalization, where the |
10235 | | * attribute appears in the document with a value which will change |
10236 | | * as a result of normalization, or |
10237 | | * - element types with element content, if white space occurs directly |
10238 | | * within any instance of those types. |
10239 | | * |
10240 | | * Returns: |
10241 | | * 1 if standalone="yes" |
10242 | | * 0 if standalone="no" |
10243 | | * -2 if standalone attribute is missing or invalid |
10244 | | * (A standalone value of -2 means that the XML declaration was found, |
10245 | | * but no value was specified for the standalone attribute). |
10246 | | */ |
10247 | | |
10248 | | int |
10249 | 96 | xmlParseSDDecl(xmlParserCtxtPtr ctxt) { |
10250 | 96 | int standalone = -2; |
10251 | | |
10252 | 96 | SKIP_BLANKS; |
10253 | 96 | if (CMP10(CUR_PTR, 's', 't', 'a', 'n', 'd', 'a', 'l', 'o', 'n', 'e')) { |
10254 | 0 | SKIP(10); |
10255 | 0 | SKIP_BLANKS; |
10256 | 0 | if (RAW != '=') { |
10257 | 0 | xmlFatalErr(ctxt, XML_ERR_EQUAL_REQUIRED, NULL); |
10258 | 0 | return(standalone); |
10259 | 0 | } |
10260 | 0 | NEXT; |
10261 | 0 | SKIP_BLANKS; |
10262 | 0 | if (RAW == '\''){ |
10263 | 0 | NEXT; |
10264 | 0 | if ((RAW == 'n') && (NXT(1) == 'o')) { |
10265 | 0 | standalone = 0; |
10266 | 0 | SKIP(2); |
10267 | 0 | } else if ((RAW == 'y') && (NXT(1) == 'e') && |
10268 | 0 | (NXT(2) == 's')) { |
10269 | 0 | standalone = 1; |
10270 | 0 | SKIP(3); |
10271 | 0 | } else { |
10272 | 0 | xmlFatalErr(ctxt, XML_ERR_STANDALONE_VALUE, NULL); |
10273 | 0 | } |
10274 | 0 | if (RAW != '\'') { |
10275 | 0 | xmlFatalErr(ctxt, XML_ERR_STRING_NOT_CLOSED, NULL); |
10276 | 0 | } else |
10277 | 0 | NEXT; |
10278 | 0 | } else if (RAW == '"'){ |
10279 | 0 | NEXT; |
10280 | 0 | if ((RAW == 'n') && (NXT(1) == 'o')) { |
10281 | 0 | standalone = 0; |
10282 | 0 | SKIP(2); |
10283 | 0 | } else if ((RAW == 'y') && (NXT(1) == 'e') && |
10284 | 0 | (NXT(2) == 's')) { |
10285 | 0 | standalone = 1; |
10286 | 0 | SKIP(3); |
10287 | 0 | } else { |
10288 | 0 | xmlFatalErr(ctxt, XML_ERR_STANDALONE_VALUE, NULL); |
10289 | 0 | } |
10290 | 0 | if (RAW != '"') { |
10291 | 0 | xmlFatalErr(ctxt, XML_ERR_STRING_NOT_CLOSED, NULL); |
10292 | 0 | } else |
10293 | 0 | NEXT; |
10294 | 0 | } else { |
10295 | 0 | xmlFatalErr(ctxt, XML_ERR_STRING_NOT_STARTED, NULL); |
10296 | 0 | } |
10297 | 0 | } |
10298 | 96 | return(standalone); |
10299 | 96 | } |
10300 | | |
10301 | | /** |
10302 | | * xmlParseXMLDecl: |
10303 | | * @ctxt: an XML parser context |
10304 | | * |
10305 | | * DEPRECATED: Internal function, don't use. |
10306 | | * |
10307 | | * parse an XML declaration header |
10308 | | * |
10309 | | * [23] XMLDecl ::= '<?xml' VersionInfo EncodingDecl? SDDecl? S? '?>' |
10310 | | */ |
10311 | | |
10312 | | void |
10313 | 96 | xmlParseXMLDecl(xmlParserCtxtPtr ctxt) { |
10314 | 96 | xmlChar *version; |
10315 | | |
10316 | | /* |
10317 | | * This value for standalone indicates that the document has an |
10318 | | * XML declaration but it does not have a standalone attribute. |
10319 | | * It will be overwritten later if a standalone attribute is found. |
10320 | | */ |
10321 | 96 | ctxt->input->standalone = -2; |
10322 | | |
10323 | | /* |
10324 | | * We know that '<?xml' is here. |
10325 | | */ |
10326 | 96 | SKIP(5); |
10327 | | |
10328 | 96 | if (!IS_BLANK_CH(RAW)) { |
10329 | 0 | xmlFatalErrMsg(ctxt, XML_ERR_SPACE_REQUIRED, |
10330 | 0 | "Blank needed after '<?xml'\n"); |
10331 | 0 | } |
10332 | 96 | SKIP_BLANKS; |
10333 | | |
10334 | | /* |
10335 | | * We must have the VersionInfo here. |
10336 | | */ |
10337 | 96 | version = xmlParseVersionInfo(ctxt); |
10338 | 96 | if (version == NULL) { |
10339 | 91 | xmlFatalErr(ctxt, XML_ERR_VERSION_MISSING, NULL); |
10340 | 91 | } else { |
10341 | 5 | if (!xmlStrEqual(version, (const xmlChar *) XML_DEFAULT_VERSION)) { |
10342 | | /* |
10343 | | * Changed here for XML-1.0 5th edition |
10344 | | */ |
10345 | 5 | if (ctxt->options & XML_PARSE_OLD10) { |
10346 | 0 | xmlFatalErrMsgStr(ctxt, XML_ERR_UNKNOWN_VERSION, |
10347 | 0 | "Unsupported version '%s'\n", |
10348 | 0 | version); |
10349 | 5 | } else { |
10350 | 5 | if ((version[0] == '1') && ((version[1] == '.'))) { |
10351 | 0 | xmlWarningMsg(ctxt, XML_WAR_UNKNOWN_VERSION, |
10352 | 0 | "Unsupported version '%s'\n", |
10353 | 0 | version, NULL); |
10354 | 5 | } else { |
10355 | 5 | xmlFatalErrMsgStr(ctxt, XML_ERR_UNKNOWN_VERSION, |
10356 | 5 | "Unsupported version '%s'\n", |
10357 | 5 | version); |
10358 | 5 | } |
10359 | 5 | } |
10360 | 5 | } |
10361 | 5 | if (ctxt->version != NULL) |
10362 | 0 | xmlFree((void *) ctxt->version); |
10363 | 5 | ctxt->version = version; |
10364 | 5 | } |
10365 | | |
10366 | | /* |
10367 | | * We may have the encoding declaration |
10368 | | */ |
10369 | 96 | if (!IS_BLANK_CH(RAW)) { |
10370 | 94 | if ((RAW == '?') && (NXT(1) == '>')) { |
10371 | 0 | SKIP(2); |
10372 | 0 | return; |
10373 | 0 | } |
10374 | 94 | xmlFatalErrMsg(ctxt, XML_ERR_SPACE_REQUIRED, "Blank needed here\n"); |
10375 | 94 | } |
10376 | 96 | xmlParseEncodingDecl(ctxt); |
10377 | 96 | if ((ctxt->errNo == XML_ERR_UNSUPPORTED_ENCODING) || |
10378 | 96 | (ctxt->instate == XML_PARSER_EOF)) { |
10379 | | /* |
10380 | | * The XML REC instructs us to stop parsing right here |
10381 | | */ |
10382 | 0 | return; |
10383 | 0 | } |
10384 | | |
10385 | | /* |
10386 | | * We may have the standalone status. |
10387 | | */ |
10388 | 96 | if ((ctxt->input->encoding != NULL) && (!IS_BLANK_CH(RAW))) { |
10389 | 88 | if ((RAW == '?') && (NXT(1) == '>')) { |
10390 | 0 | SKIP(2); |
10391 | 0 | return; |
10392 | 0 | } |
10393 | 88 | xmlFatalErrMsg(ctxt, XML_ERR_SPACE_REQUIRED, "Blank needed here\n"); |
10394 | 88 | } |
10395 | | |
10396 | | /* |
10397 | | * We can grow the input buffer freely at that point |
10398 | | */ |
10399 | 96 | GROW; |
10400 | | |
10401 | 96 | SKIP_BLANKS; |
10402 | 96 | ctxt->input->standalone = xmlParseSDDecl(ctxt); |
10403 | | |
10404 | 96 | SKIP_BLANKS; |
10405 | 96 | if ((RAW == '?') && (NXT(1) == '>')) { |
10406 | 0 | SKIP(2); |
10407 | 96 | } else if (RAW == '>') { |
10408 | | /* Deprecated old WD ... */ |
10409 | 0 | xmlFatalErr(ctxt, XML_ERR_XMLDECL_NOT_FINISHED, NULL); |
10410 | 0 | NEXT; |
10411 | 96 | } else { |
10412 | 96 | int c; |
10413 | | |
10414 | 96 | xmlFatalErr(ctxt, XML_ERR_XMLDECL_NOT_FINISHED, NULL); |
10415 | 3.92M | while ((c = CUR) != 0) { |
10416 | 3.92M | NEXT; |
10417 | 3.92M | if (c == '>') |
10418 | 82 | break; |
10419 | 3.92M | } |
10420 | 96 | } |
10421 | 96 | } |
10422 | | |
10423 | | /** |
10424 | | * xmlParseMisc: |
10425 | | * @ctxt: an XML parser context |
10426 | | * |
10427 | | * DEPRECATED: Internal function, don't use. |
10428 | | * |
10429 | | * parse an XML Misc* optional field. |
10430 | | * |
10431 | | * [27] Misc ::= Comment | PI | S |
10432 | | */ |
10433 | | |
10434 | | void |
10435 | 790 | xmlParseMisc(xmlParserCtxtPtr ctxt) { |
10436 | 863 | while (ctxt->instate != XML_PARSER_EOF) { |
10437 | 863 | SKIP_BLANKS; |
10438 | 863 | GROW; |
10439 | 863 | if ((RAW == '<') && (NXT(1) == '?')) { |
10440 | 73 | xmlParsePI(ctxt); |
10441 | 790 | } else if (CMP4(CUR_PTR, '<', '!', '-', '-')) { |
10442 | 0 | xmlParseComment(ctxt); |
10443 | 790 | } else { |
10444 | 790 | break; |
10445 | 790 | } |
10446 | 863 | } |
10447 | 790 | } |
10448 | | |
10449 | | /** |
10450 | | * xmlParseDocument: |
10451 | | * @ctxt: an XML parser context |
10452 | | * |
10453 | | * parse an XML document (and build a tree if using the standard SAX |
10454 | | * interface). |
10455 | | * |
10456 | | * [1] document ::= prolog element Misc* |
10457 | | * |
10458 | | * [22] prolog ::= XMLDecl? Misc* (doctypedecl Misc*)? |
10459 | | * |
10460 | | * Returns 0, -1 in case of error. the parser context is augmented |
10461 | | * as a result of the parsing. |
10462 | | */ |
10463 | | |
10464 | | int |
10465 | 406 | xmlParseDocument(xmlParserCtxtPtr ctxt) { |
10466 | 406 | xmlChar start[4]; |
10467 | 406 | xmlCharEncoding enc; |
10468 | | |
10469 | 406 | xmlInitParser(); |
10470 | | |
10471 | 406 | if ((ctxt == NULL) || (ctxt->input == NULL)) |
10472 | 0 | return(-1); |
10473 | | |
10474 | 406 | GROW; |
10475 | | |
10476 | | /* |
10477 | | * SAX: detecting the level. |
10478 | | */ |
10479 | 406 | xmlDetectSAX2(ctxt); |
10480 | | |
10481 | | /* |
10482 | | * SAX: beginning of the document processing. |
10483 | | */ |
10484 | 406 | if ((ctxt->sax) && (ctxt->sax->setDocumentLocator)) |
10485 | 406 | ctxt->sax->setDocumentLocator(ctxt->userData, &xmlDefaultSAXLocator); |
10486 | 406 | if (ctxt->instate == XML_PARSER_EOF) |
10487 | 0 | return(-1); |
10488 | | |
10489 | 406 | if ((ctxt->encoding == NULL) && |
10490 | 406 | ((ctxt->input->end - ctxt->input->cur) >= 4)) { |
10491 | | /* |
10492 | | * Get the 4 first bytes and decode the charset |
10493 | | * if enc != XML_CHAR_ENCODING_NONE |
10494 | | * plug some encoding conversion routines. |
10495 | | */ |
10496 | 406 | start[0] = RAW; |
10497 | 406 | start[1] = NXT(1); |
10498 | 406 | start[2] = NXT(2); |
10499 | 406 | start[3] = NXT(3); |
10500 | 406 | enc = xmlDetectCharEncoding(&start[0], 4); |
10501 | 406 | if (enc != XML_CHAR_ENCODING_NONE) { |
10502 | 149 | xmlSwitchEncoding(ctxt, enc); |
10503 | 149 | } |
10504 | 406 | } |
10505 | | |
10506 | | |
10507 | 406 | if (CUR == 0) { |
10508 | 1 | xmlFatalErr(ctxt, XML_ERR_DOCUMENT_EMPTY, NULL); |
10509 | 1 | return(-1); |
10510 | 1 | } |
10511 | | |
10512 | 405 | GROW; |
10513 | 405 | if ((CMP5(CUR_PTR, '<', '?', 'x', 'm', 'l')) && (IS_BLANK_CH(NXT(5)))) { |
10514 | | |
10515 | | /* |
10516 | | * Note that we will switch encoding on the fly. |
10517 | | */ |
10518 | 96 | xmlParseXMLDecl(ctxt); |
10519 | 96 | if ((ctxt->errNo == XML_ERR_UNSUPPORTED_ENCODING) || |
10520 | 96 | (ctxt->instate == XML_PARSER_EOF)) { |
10521 | | /* |
10522 | | * The XML REC instructs us to stop parsing right here |
10523 | | */ |
10524 | 6 | return(-1); |
10525 | 6 | } |
10526 | 90 | ctxt->standalone = ctxt->input->standalone; |
10527 | 90 | SKIP_BLANKS; |
10528 | 309 | } else { |
10529 | 309 | ctxt->version = xmlCharStrdup(XML_DEFAULT_VERSION); |
10530 | 309 | } |
10531 | 399 | if ((ctxt->sax) && (ctxt->sax->startDocument) && (!ctxt->disableSAX)) |
10532 | 399 | ctxt->sax->startDocument(ctxt->userData); |
10533 | 399 | if (ctxt->instate == XML_PARSER_EOF) |
10534 | 0 | return(-1); |
10535 | 399 | if ((ctxt->myDoc != NULL) && (ctxt->input != NULL) && |
10536 | 399 | (ctxt->input->buf != NULL) && (ctxt->input->buf->compressed >= 0)) { |
10537 | 0 | ctxt->myDoc->compression = ctxt->input->buf->compressed; |
10538 | 0 | } |
10539 | | |
10540 | | /* |
10541 | | * The Misc part of the Prolog |
10542 | | */ |
10543 | 399 | xmlParseMisc(ctxt); |
10544 | | |
10545 | | /* |
10546 | | * Then possibly doc type declaration(s) and more Misc |
10547 | | * (doctypedecl Misc*)? |
10548 | | */ |
10549 | 399 | GROW; |
10550 | 399 | if (CMP9(CUR_PTR, '<', '!', 'D', 'O', 'C', 'T', 'Y', 'P', 'E')) { |
10551 | | |
10552 | 83 | ctxt->inSubset = 1; |
10553 | 83 | xmlParseDocTypeDecl(ctxt); |
10554 | 83 | if (RAW == '[') { |
10555 | 81 | ctxt->instate = XML_PARSER_DTD; |
10556 | 81 | xmlParseInternalSubset(ctxt); |
10557 | 81 | if (ctxt->instate == XML_PARSER_EOF) |
10558 | 34 | return(-1); |
10559 | 81 | } |
10560 | | |
10561 | | /* |
10562 | | * Create and update the external subset. |
10563 | | */ |
10564 | 49 | ctxt->inSubset = 2; |
10565 | 49 | if ((ctxt->sax != NULL) && (ctxt->sax->externalSubset != NULL) && |
10566 | 49 | (!ctxt->disableSAX)) |
10567 | 49 | ctxt->sax->externalSubset(ctxt->userData, ctxt->intSubName, |
10568 | 49 | ctxt->extSubSystem, ctxt->extSubURI); |
10569 | 49 | if (ctxt->instate == XML_PARSER_EOF) |
10570 | 0 | return(-1); |
10571 | 49 | ctxt->inSubset = 0; |
10572 | | |
10573 | 49 | xmlCleanSpecialAttr(ctxt); |
10574 | | |
10575 | 49 | ctxt->instate = XML_PARSER_PROLOG; |
10576 | 49 | xmlParseMisc(ctxt); |
10577 | 49 | } |
10578 | | |
10579 | | /* |
10580 | | * Time to start parsing the tree itself |
10581 | | */ |
10582 | 365 | GROW; |
10583 | 365 | if (RAW != '<') { |
10584 | 23 | xmlFatalErrMsg(ctxt, XML_ERR_DOCUMENT_EMPTY, |
10585 | 23 | "Start tag expected, '<' not found\n"); |
10586 | 342 | } else { |
10587 | 342 | ctxt->instate = XML_PARSER_CONTENT; |
10588 | 342 | xmlParseElement(ctxt); |
10589 | 342 | ctxt->instate = XML_PARSER_EPILOG; |
10590 | | |
10591 | | |
10592 | | /* |
10593 | | * The Misc part at the end |
10594 | | */ |
10595 | 342 | xmlParseMisc(ctxt); |
10596 | | |
10597 | 342 | if (RAW != 0) { |
10598 | 1 | xmlFatalErr(ctxt, XML_ERR_DOCUMENT_END, NULL); |
10599 | 1 | } |
10600 | 342 | ctxt->instate = XML_PARSER_EOF; |
10601 | 342 | } |
10602 | | |
10603 | | /* |
10604 | | * SAX: end of the document processing. |
10605 | | */ |
10606 | 365 | if ((ctxt->sax) && (ctxt->sax->endDocument != NULL)) |
10607 | 365 | ctxt->sax->endDocument(ctxt->userData); |
10608 | | |
10609 | | /* |
10610 | | * Remove locally kept entity definitions if the tree was not built |
10611 | | */ |
10612 | 365 | if ((ctxt->myDoc != NULL) && |
10613 | 365 | (xmlStrEqual(ctxt->myDoc->version, SAX_COMPAT_MODE))) { |
10614 | 0 | xmlFreeDoc(ctxt->myDoc); |
10615 | 0 | ctxt->myDoc = NULL; |
10616 | 0 | } |
10617 | | |
10618 | 365 | if ((ctxt->wellFormed) && (ctxt->myDoc != NULL)) { |
10619 | 0 | ctxt->myDoc->properties |= XML_DOC_WELLFORMED; |
10620 | 0 | if (ctxt->valid) |
10621 | 0 | ctxt->myDoc->properties |= XML_DOC_DTDVALID; |
10622 | 0 | if (ctxt->nsWellFormed) |
10623 | 0 | ctxt->myDoc->properties |= XML_DOC_NSVALID; |
10624 | 0 | if (ctxt->options & XML_PARSE_OLD10) |
10625 | 0 | ctxt->myDoc->properties |= XML_DOC_OLD10; |
10626 | 0 | } |
10627 | 365 | if (! ctxt->wellFormed) { |
10628 | 365 | ctxt->valid = 0; |
10629 | 365 | return(-1); |
10630 | 365 | } |
10631 | 0 | return(0); |
10632 | 365 | } |
10633 | | |
10634 | | /** |
10635 | | * xmlParseExtParsedEnt: |
10636 | | * @ctxt: an XML parser context |
10637 | | * |
10638 | | * parse a general parsed entity |
10639 | | * An external general parsed entity is well-formed if it matches the |
10640 | | * production labeled extParsedEnt. |
10641 | | * |
10642 | | * [78] extParsedEnt ::= TextDecl? content |
10643 | | * |
10644 | | * Returns 0, -1 in case of error. the parser context is augmented |
10645 | | * as a result of the parsing. |
10646 | | */ |
10647 | | |
10648 | | int |
10649 | 0 | xmlParseExtParsedEnt(xmlParserCtxtPtr ctxt) { |
10650 | 0 | xmlChar start[4]; |
10651 | 0 | xmlCharEncoding enc; |
10652 | |
|
10653 | 0 | if ((ctxt == NULL) || (ctxt->input == NULL)) |
10654 | 0 | return(-1); |
10655 | | |
10656 | 0 | xmlDetectSAX2(ctxt); |
10657 | |
|
10658 | 0 | GROW; |
10659 | | |
10660 | | /* |
10661 | | * SAX: beginning of the document processing. |
10662 | | */ |
10663 | 0 | if ((ctxt->sax) && (ctxt->sax->setDocumentLocator)) |
10664 | 0 | ctxt->sax->setDocumentLocator(ctxt->userData, &xmlDefaultSAXLocator); |
10665 | | |
10666 | | /* |
10667 | | * Get the 4 first bytes and decode the charset |
10668 | | * if enc != XML_CHAR_ENCODING_NONE |
10669 | | * plug some encoding conversion routines. |
10670 | | */ |
10671 | 0 | if ((ctxt->input->end - ctxt->input->cur) >= 4) { |
10672 | 0 | start[0] = RAW; |
10673 | 0 | start[1] = NXT(1); |
10674 | 0 | start[2] = NXT(2); |
10675 | 0 | start[3] = NXT(3); |
10676 | 0 | enc = xmlDetectCharEncoding(start, 4); |
10677 | 0 | if (enc != XML_CHAR_ENCODING_NONE) { |
10678 | 0 | xmlSwitchEncoding(ctxt, enc); |
10679 | 0 | } |
10680 | 0 | } |
10681 | | |
10682 | |
|
10683 | 0 | if (CUR == 0) { |
10684 | 0 | xmlFatalErr(ctxt, XML_ERR_DOCUMENT_EMPTY, NULL); |
10685 | 0 | } |
10686 | | |
10687 | | /* |
10688 | | * Check for the XMLDecl in the Prolog. |
10689 | | */ |
10690 | 0 | GROW; |
10691 | 0 | if ((CMP5(CUR_PTR, '<', '?', 'x', 'm', 'l')) && (IS_BLANK_CH(NXT(5)))) { |
10692 | | |
10693 | | /* |
10694 | | * Note that we will switch encoding on the fly. |
10695 | | */ |
10696 | 0 | xmlParseXMLDecl(ctxt); |
10697 | 0 | if (ctxt->errNo == XML_ERR_UNSUPPORTED_ENCODING) { |
10698 | | /* |
10699 | | * The XML REC instructs us to stop parsing right here |
10700 | | */ |
10701 | 0 | return(-1); |
10702 | 0 | } |
10703 | 0 | SKIP_BLANKS; |
10704 | 0 | } else { |
10705 | 0 | ctxt->version = xmlCharStrdup(XML_DEFAULT_VERSION); |
10706 | 0 | } |
10707 | 0 | if ((ctxt->sax) && (ctxt->sax->startDocument) && (!ctxt->disableSAX)) |
10708 | 0 | ctxt->sax->startDocument(ctxt->userData); |
10709 | 0 | if (ctxt->instate == XML_PARSER_EOF) |
10710 | 0 | return(-1); |
10711 | | |
10712 | | /* |
10713 | | * Doing validity checking on chunk doesn't make sense |
10714 | | */ |
10715 | 0 | ctxt->instate = XML_PARSER_CONTENT; |
10716 | 0 | ctxt->validate = 0; |
10717 | 0 | ctxt->loadsubset = 0; |
10718 | 0 | ctxt->depth = 0; |
10719 | |
|
10720 | 0 | xmlParseContent(ctxt); |
10721 | 0 | if (ctxt->instate == XML_PARSER_EOF) |
10722 | 0 | return(-1); |
10723 | | |
10724 | 0 | if ((RAW == '<') && (NXT(1) == '/')) { |
10725 | 0 | xmlFatalErr(ctxt, XML_ERR_NOT_WELL_BALANCED, NULL); |
10726 | 0 | } else if (RAW != 0) { |
10727 | 0 | xmlFatalErr(ctxt, XML_ERR_EXTRA_CONTENT, NULL); |
10728 | 0 | } |
10729 | | |
10730 | | /* |
10731 | | * SAX: end of the document processing. |
10732 | | */ |
10733 | 0 | if ((ctxt->sax) && (ctxt->sax->endDocument != NULL)) |
10734 | 0 | ctxt->sax->endDocument(ctxt->userData); |
10735 | |
|
10736 | 0 | if (! ctxt->wellFormed) return(-1); |
10737 | 0 | return(0); |
10738 | 0 | } |
10739 | | |
10740 | | #ifdef LIBXML_PUSH_ENABLED |
10741 | | /************************************************************************ |
10742 | | * * |
10743 | | * Progressive parsing interfaces * |
10744 | | * * |
10745 | | ************************************************************************/ |
10746 | | |
10747 | | /** |
10748 | | * xmlParseLookupChar: |
10749 | | * @ctxt: an XML parser context |
10750 | | * @c: character |
10751 | | * |
10752 | | * Check whether the input buffer contains a character. |
10753 | | */ |
10754 | | static int |
10755 | | xmlParseLookupChar(xmlParserCtxtPtr ctxt, int c) { |
10756 | | const xmlChar *cur; |
10757 | | |
10758 | | if (ctxt->checkIndex == 0) { |
10759 | | cur = ctxt->input->cur + 1; |
10760 | | } else { |
10761 | | cur = ctxt->input->cur + ctxt->checkIndex; |
10762 | | } |
10763 | | |
10764 | | if (memchr(cur, c, ctxt->input->end - cur) == NULL) { |
10765 | | size_t index = ctxt->input->end - ctxt->input->cur; |
10766 | | |
10767 | | if (index > LONG_MAX) { |
10768 | | ctxt->checkIndex = 0; |
10769 | | return(1); |
10770 | | } |
10771 | | ctxt->checkIndex = index; |
10772 | | return(0); |
10773 | | } else { |
10774 | | ctxt->checkIndex = 0; |
10775 | | return(1); |
10776 | | } |
10777 | | } |
10778 | | |
10779 | | /** |
10780 | | * xmlParseLookupString: |
10781 | | * @ctxt: an XML parser context |
10782 | | * @startDelta: delta to apply at the start |
10783 | | * @str: string |
10784 | | * @strLen: length of string |
10785 | | * |
10786 | | * Check whether the input buffer contains a string. |
10787 | | */ |
10788 | | static const xmlChar * |
10789 | | xmlParseLookupString(xmlParserCtxtPtr ctxt, size_t startDelta, |
10790 | | const char *str, size_t strLen) { |
10791 | | const xmlChar *cur, *term; |
10792 | | |
10793 | | if (ctxt->checkIndex == 0) { |
10794 | | cur = ctxt->input->cur + startDelta; |
10795 | | } else { |
10796 | | cur = ctxt->input->cur + ctxt->checkIndex; |
10797 | | } |
10798 | | |
10799 | | term = BAD_CAST strstr((const char *) cur, str); |
10800 | | if (term == NULL) { |
10801 | | const xmlChar *end = ctxt->input->end; |
10802 | | size_t index; |
10803 | | |
10804 | | /* Rescan (strLen - 1) characters. */ |
10805 | | if ((size_t) (end - cur) < strLen) |
10806 | | end = cur; |
10807 | | else |
10808 | | end -= strLen - 1; |
10809 | | index = end - ctxt->input->cur; |
10810 | | if (index > LONG_MAX) { |
10811 | | ctxt->checkIndex = 0; |
10812 | | return(ctxt->input->end - strLen); |
10813 | | } |
10814 | | ctxt->checkIndex = index; |
10815 | | } else { |
10816 | | ctxt->checkIndex = 0; |
10817 | | } |
10818 | | |
10819 | | return(term); |
10820 | | } |
10821 | | |
10822 | | /** |
10823 | | * xmlParseLookupCharData: |
10824 | | * @ctxt: an XML parser context |
10825 | | * |
10826 | | * Check whether the input buffer contains terminated char data. |
10827 | | */ |
10828 | | static int |
10829 | | xmlParseLookupCharData(xmlParserCtxtPtr ctxt) { |
10830 | | const xmlChar *cur = ctxt->input->cur + ctxt->checkIndex; |
10831 | | const xmlChar *end = ctxt->input->end; |
10832 | | size_t index; |
10833 | | |
10834 | | while (cur < end) { |
10835 | | if ((*cur == '<') || (*cur == '&')) { |
10836 | | ctxt->checkIndex = 0; |
10837 | | return(1); |
10838 | | } |
10839 | | cur++; |
10840 | | } |
10841 | | |
10842 | | index = cur - ctxt->input->cur; |
10843 | | if (index > LONG_MAX) { |
10844 | | ctxt->checkIndex = 0; |
10845 | | return(1); |
10846 | | } |
10847 | | ctxt->checkIndex = index; |
10848 | | return(0); |
10849 | | } |
10850 | | |
10851 | | /** |
10852 | | * xmlParseLookupGt: |
10853 | | * @ctxt: an XML parser context |
10854 | | * |
10855 | | * Check whether there's enough data in the input buffer to finish parsing |
10856 | | * a start tag. This has to take quotes into account. |
10857 | | */ |
10858 | | static int |
10859 | | xmlParseLookupGt(xmlParserCtxtPtr ctxt) { |
10860 | | const xmlChar *cur; |
10861 | | const xmlChar *end = ctxt->input->end; |
10862 | | int state = ctxt->endCheckState; |
10863 | | size_t index; |
10864 | | |
10865 | | if (ctxt->checkIndex == 0) |
10866 | | cur = ctxt->input->cur + 1; |
10867 | | else |
10868 | | cur = ctxt->input->cur + ctxt->checkIndex; |
10869 | | |
10870 | | while (cur < end) { |
10871 | | if (state) { |
10872 | | if (*cur == state) |
10873 | | state = 0; |
10874 | | } else if (*cur == '\'' || *cur == '"') { |
10875 | | state = *cur; |
10876 | | } else if (*cur == '>') { |
10877 | | ctxt->checkIndex = 0; |
10878 | | ctxt->endCheckState = 0; |
10879 | | return(1); |
10880 | | } |
10881 | | cur++; |
10882 | | } |
10883 | | |
10884 | | index = cur - ctxt->input->cur; |
10885 | | if (index > LONG_MAX) { |
10886 | | ctxt->checkIndex = 0; |
10887 | | ctxt->endCheckState = 0; |
10888 | | return(1); |
10889 | | } |
10890 | | ctxt->checkIndex = index; |
10891 | | ctxt->endCheckState = state; |
10892 | | return(0); |
10893 | | } |
10894 | | |
10895 | | /** |
10896 | | * xmlParseLookupInternalSubset: |
10897 | | * @ctxt: an XML parser context |
10898 | | * |
10899 | | * Check whether there's enough data in the input buffer to finish parsing |
10900 | | * the internal subset. |
10901 | | */ |
10902 | | static int |
10903 | | xmlParseLookupInternalSubset(xmlParserCtxtPtr ctxt) { |
10904 | | /* |
10905 | | * Sorry, but progressive parsing of the internal subset is not |
10906 | | * supported. We first check that the full content of the internal |
10907 | | * subset is available and parsing is launched only at that point. |
10908 | | * Internal subset ends with "']' S? '>'" in an unescaped section and |
10909 | | * not in a ']]>' sequence which are conditional sections. |
10910 | | */ |
10911 | | const xmlChar *cur, *start; |
10912 | | const xmlChar *end = ctxt->input->end; |
10913 | | int state = ctxt->endCheckState; |
10914 | | size_t index; |
10915 | | |
10916 | | if (ctxt->checkIndex == 0) { |
10917 | | cur = ctxt->input->cur + 1; |
10918 | | } else { |
10919 | | cur = ctxt->input->cur + ctxt->checkIndex; |
10920 | | } |
10921 | | start = cur; |
10922 | | |
10923 | | while (cur < end) { |
10924 | | if (state == '-') { |
10925 | | if ((*cur == '-') && |
10926 | | (cur[1] == '-') && |
10927 | | (cur[2] == '>')) { |
10928 | | state = 0; |
10929 | | cur += 3; |
10930 | | start = cur; |
10931 | | continue; |
10932 | | } |
10933 | | } |
10934 | | else if (state == ']') { |
10935 | | if (*cur == '>') { |
10936 | | ctxt->checkIndex = 0; |
10937 | | ctxt->endCheckState = 0; |
10938 | | return(1); |
10939 | | } |
10940 | | if (IS_BLANK_CH(*cur)) { |
10941 | | state = ' '; |
10942 | | } else if (*cur != ']') { |
10943 | | state = 0; |
10944 | | start = cur; |
10945 | | continue; |
10946 | | } |
10947 | | } |
10948 | | else if (state == ' ') { |
10949 | | if (*cur == '>') { |
10950 | | ctxt->checkIndex = 0; |
10951 | | ctxt->endCheckState = 0; |
10952 | | return(1); |
10953 | | } |
10954 | | if (!IS_BLANK_CH(*cur)) { |
10955 | | state = 0; |
10956 | | start = cur; |
10957 | | continue; |
10958 | | } |
10959 | | } |
10960 | | else if (state != 0) { |
10961 | | if (*cur == state) { |
10962 | | state = 0; |
10963 | | start = cur + 1; |
10964 | | } |
10965 | | } |
10966 | | else if (*cur == '<') { |
10967 | | if ((cur[1] == '!') && |
10968 | | (cur[2] == '-') && |
10969 | | (cur[3] == '-')) { |
10970 | | state = '-'; |
10971 | | cur += 4; |
10972 | | /* Don't treat <!--> as comment */ |
10973 | | start = cur; |
10974 | | continue; |
10975 | | } |
10976 | | } |
10977 | | else if ((*cur == '"') || (*cur == '\'') || (*cur == ']')) { |
10978 | | state = *cur; |
10979 | | } |
10980 | | |
10981 | | cur++; |
10982 | | } |
10983 | | |
10984 | | /* |
10985 | | * Rescan the three last characters to detect "<!--" and "-->" |
10986 | | * split across chunks. |
10987 | | */ |
10988 | | if ((state == 0) || (state == '-')) { |
10989 | | if (cur - start < 3) |
10990 | | cur = start; |
10991 | | else |
10992 | | cur -= 3; |
10993 | | } |
10994 | | index = cur - ctxt->input->cur; |
10995 | | if (index > LONG_MAX) { |
10996 | | ctxt->checkIndex = 0; |
10997 | | ctxt->endCheckState = 0; |
10998 | | return(1); |
10999 | | } |
11000 | | ctxt->checkIndex = index; |
11001 | | ctxt->endCheckState = state; |
11002 | | return(0); |
11003 | | } |
11004 | | |
11005 | | /** |
11006 | | * xmlCheckCdataPush: |
11007 | | * @cur: pointer to the block of characters |
11008 | | * @len: length of the block in bytes |
11009 | | * @complete: 1 if complete CDATA block is passed in, 0 if partial block |
11010 | | * |
11011 | | * Check that the block of characters is okay as SCdata content [20] |
11012 | | * |
11013 | | * Returns the number of bytes to pass if okay, a negative index where an |
11014 | | * UTF-8 error occurred otherwise |
11015 | | */ |
11016 | | static int |
11017 | | xmlCheckCdataPush(const xmlChar *utf, int len, int complete) { |
11018 | | int ix; |
11019 | | unsigned char c; |
11020 | | int codepoint; |
11021 | | |
11022 | | if ((utf == NULL) || (len <= 0)) |
11023 | | return(0); |
11024 | | |
11025 | | for (ix = 0; ix < len;) { /* string is 0-terminated */ |
11026 | | c = utf[ix]; |
11027 | | if ((c & 0x80) == 0x00) { /* 1-byte code, starts with 10 */ |
11028 | | if (c >= 0x20) |
11029 | | ix++; |
11030 | | else if ((c == 0xA) || (c == 0xD) || (c == 0x9)) |
11031 | | ix++; |
11032 | | else |
11033 | | return(-ix); |
11034 | | } else if ((c & 0xe0) == 0xc0) {/* 2-byte code, starts with 110 */ |
11035 | | if (ix + 2 > len) return(complete ? -ix : ix); |
11036 | | if ((utf[ix+1] & 0xc0 ) != 0x80) |
11037 | | return(-ix); |
11038 | | codepoint = (utf[ix] & 0x1f) << 6; |
11039 | | codepoint |= utf[ix+1] & 0x3f; |
11040 | | if (!xmlIsCharQ(codepoint)) |
11041 | | return(-ix); |
11042 | | ix += 2; |
11043 | | } else if ((c & 0xf0) == 0xe0) {/* 3-byte code, starts with 1110 */ |
11044 | | if (ix + 3 > len) return(complete ? -ix : ix); |
11045 | | if (((utf[ix+1] & 0xc0) != 0x80) || |
11046 | | ((utf[ix+2] & 0xc0) != 0x80)) |
11047 | | return(-ix); |
11048 | | codepoint = (utf[ix] & 0xf) << 12; |
11049 | | codepoint |= (utf[ix+1] & 0x3f) << 6; |
11050 | | codepoint |= utf[ix+2] & 0x3f; |
11051 | | if (!xmlIsCharQ(codepoint)) |
11052 | | return(-ix); |
11053 | | ix += 3; |
11054 | | } else if ((c & 0xf8) == 0xf0) {/* 4-byte code, starts with 11110 */ |
11055 | | if (ix + 4 > len) return(complete ? -ix : ix); |
11056 | | if (((utf[ix+1] & 0xc0) != 0x80) || |
11057 | | ((utf[ix+2] & 0xc0) != 0x80) || |
11058 | | ((utf[ix+3] & 0xc0) != 0x80)) |
11059 | | return(-ix); |
11060 | | codepoint = (utf[ix] & 0x7) << 18; |
11061 | | codepoint |= (utf[ix+1] & 0x3f) << 12; |
11062 | | codepoint |= (utf[ix+2] & 0x3f) << 6; |
11063 | | codepoint |= utf[ix+3] & 0x3f; |
11064 | | if (!xmlIsCharQ(codepoint)) |
11065 | | return(-ix); |
11066 | | ix += 4; |
11067 | | } else /* unknown encoding */ |
11068 | | return(-ix); |
11069 | | } |
11070 | | return(ix); |
11071 | | } |
11072 | | |
11073 | | /** |
11074 | | * xmlParseTryOrFinish: |
11075 | | * @ctxt: an XML parser context |
11076 | | * @terminate: last chunk indicator |
11077 | | * |
11078 | | * Try to progress on parsing |
11079 | | * |
11080 | | * Returns zero if no parsing was possible |
11081 | | */ |
11082 | | static int |
11083 | | xmlParseTryOrFinish(xmlParserCtxtPtr ctxt, int terminate) { |
11084 | | int ret = 0; |
11085 | | int tlen; |
11086 | | size_t avail; |
11087 | | xmlChar cur, next; |
11088 | | |
11089 | | if (ctxt->input == NULL) |
11090 | | return(0); |
11091 | | |
11092 | | #ifdef DEBUG_PUSH |
11093 | | switch (ctxt->instate) { |
11094 | | case XML_PARSER_EOF: |
11095 | | xmlGenericError(xmlGenericErrorContext, |
11096 | | "PP: try EOF\n"); break; |
11097 | | case XML_PARSER_START: |
11098 | | xmlGenericError(xmlGenericErrorContext, |
11099 | | "PP: try START\n"); break; |
11100 | | case XML_PARSER_MISC: |
11101 | | xmlGenericError(xmlGenericErrorContext, |
11102 | | "PP: try MISC\n");break; |
11103 | | case XML_PARSER_COMMENT: |
11104 | | xmlGenericError(xmlGenericErrorContext, |
11105 | | "PP: try COMMENT\n");break; |
11106 | | case XML_PARSER_PROLOG: |
11107 | | xmlGenericError(xmlGenericErrorContext, |
11108 | | "PP: try PROLOG\n");break; |
11109 | | case XML_PARSER_START_TAG: |
11110 | | xmlGenericError(xmlGenericErrorContext, |
11111 | | "PP: try START_TAG\n");break; |
11112 | | case XML_PARSER_CONTENT: |
11113 | | xmlGenericError(xmlGenericErrorContext, |
11114 | | "PP: try CONTENT\n");break; |
11115 | | case XML_PARSER_CDATA_SECTION: |
11116 | | xmlGenericError(xmlGenericErrorContext, |
11117 | | "PP: try CDATA_SECTION\n");break; |
11118 | | case XML_PARSER_END_TAG: |
11119 | | xmlGenericError(xmlGenericErrorContext, |
11120 | | "PP: try END_TAG\n");break; |
11121 | | case XML_PARSER_ENTITY_DECL: |
11122 | | xmlGenericError(xmlGenericErrorContext, |
11123 | | "PP: try ENTITY_DECL\n");break; |
11124 | | case XML_PARSER_ENTITY_VALUE: |
11125 | | xmlGenericError(xmlGenericErrorContext, |
11126 | | "PP: try ENTITY_VALUE\n");break; |
11127 | | case XML_PARSER_ATTRIBUTE_VALUE: |
11128 | | xmlGenericError(xmlGenericErrorContext, |
11129 | | "PP: try ATTRIBUTE_VALUE\n");break; |
11130 | | case XML_PARSER_DTD: |
11131 | | xmlGenericError(xmlGenericErrorContext, |
11132 | | "PP: try DTD\n");break; |
11133 | | case XML_PARSER_EPILOG: |
11134 | | xmlGenericError(xmlGenericErrorContext, |
11135 | | "PP: try EPILOG\n");break; |
11136 | | case XML_PARSER_PI: |
11137 | | xmlGenericError(xmlGenericErrorContext, |
11138 | | "PP: try PI\n");break; |
11139 | | case XML_PARSER_IGNORE: |
11140 | | xmlGenericError(xmlGenericErrorContext, |
11141 | | "PP: try IGNORE\n");break; |
11142 | | } |
11143 | | #endif |
11144 | | |
11145 | | if ((ctxt->input != NULL) && |
11146 | | (ctxt->input->cur - ctxt->input->base > 4096)) { |
11147 | | xmlParserShrink(ctxt); |
11148 | | } |
11149 | | |
11150 | | while (ctxt->instate != XML_PARSER_EOF) { |
11151 | | if ((ctxt->errNo != XML_ERR_OK) && (ctxt->disableSAX == 1)) |
11152 | | return(0); |
11153 | | |
11154 | | if (ctxt->input == NULL) break; |
11155 | | if (ctxt->input->buf != NULL) { |
11156 | | /* |
11157 | | * If we are operating on converted input, try to flush |
11158 | | * remaining chars to avoid them stalling in the non-converted |
11159 | | * buffer. |
11160 | | */ |
11161 | | if ((ctxt->input->buf->raw != NULL) && |
11162 | | (xmlBufIsEmpty(ctxt->input->buf->raw) == 0)) { |
11163 | | size_t base = xmlBufGetInputBase(ctxt->input->buf->buffer, |
11164 | | ctxt->input); |
11165 | | size_t current = ctxt->input->cur - ctxt->input->base; |
11166 | | int res; |
11167 | | |
11168 | | res = xmlParserInputBufferPush(ctxt->input->buf, 0, ""); |
11169 | | xmlBufSetInputBaseCur(ctxt->input->buf->buffer, ctxt->input, |
11170 | | base, current); |
11171 | | if (res < 0) { |
11172 | | xmlFatalErr(ctxt, ctxt->input->buf->error, NULL); |
11173 | | xmlHaltParser(ctxt); |
11174 | | return(0); |
11175 | | } |
11176 | | } |
11177 | | } |
11178 | | avail = ctxt->input->end - ctxt->input->cur; |
11179 | | if (avail < 1) |
11180 | | goto done; |
11181 | | switch (ctxt->instate) { |
11182 | | case XML_PARSER_EOF: |
11183 | | /* |
11184 | | * Document parsing is done ! |
11185 | | */ |
11186 | | goto done; |
11187 | | case XML_PARSER_START: |
11188 | | if (ctxt->charset == XML_CHAR_ENCODING_NONE) { |
11189 | | xmlChar start[4]; |
11190 | | xmlCharEncoding enc; |
11191 | | |
11192 | | /* |
11193 | | * Very first chars read from the document flow. |
11194 | | */ |
11195 | | if (avail < 4) |
11196 | | goto done; |
11197 | | |
11198 | | /* |
11199 | | * Get the 4 first bytes and decode the charset |
11200 | | * if enc != XML_CHAR_ENCODING_NONE |
11201 | | * plug some encoding conversion routines, |
11202 | | * else xmlSwitchEncoding will set to (default) |
11203 | | * UTF8. |
11204 | | */ |
11205 | | start[0] = RAW; |
11206 | | start[1] = NXT(1); |
11207 | | start[2] = NXT(2); |
11208 | | start[3] = NXT(3); |
11209 | | enc = xmlDetectCharEncoding(start, 4); |
11210 | | /* |
11211 | | * We need more bytes to detect EBCDIC code pages. |
11212 | | * See xmlDetectEBCDIC. |
11213 | | */ |
11214 | | if ((enc == XML_CHAR_ENCODING_EBCDIC) && |
11215 | | (!terminate) && (avail < 200)) |
11216 | | goto done; |
11217 | | xmlSwitchEncoding(ctxt, enc); |
11218 | | break; |
11219 | | } |
11220 | | |
11221 | | if (avail < 2) |
11222 | | goto done; |
11223 | | cur = ctxt->input->cur[0]; |
11224 | | next = ctxt->input->cur[1]; |
11225 | | if (cur == 0) { |
11226 | | if ((ctxt->sax) && (ctxt->sax->setDocumentLocator)) |
11227 | | ctxt->sax->setDocumentLocator(ctxt->userData, |
11228 | | &xmlDefaultSAXLocator); |
11229 | | xmlFatalErr(ctxt, XML_ERR_DOCUMENT_EMPTY, NULL); |
11230 | | xmlHaltParser(ctxt); |
11231 | | #ifdef DEBUG_PUSH |
11232 | | xmlGenericError(xmlGenericErrorContext, |
11233 | | "PP: entering EOF\n"); |
11234 | | #endif |
11235 | | if ((ctxt->sax) && (ctxt->sax->endDocument != NULL)) |
11236 | | ctxt->sax->endDocument(ctxt->userData); |
11237 | | goto done; |
11238 | | } |
11239 | | if ((cur == '<') && (next == '?')) { |
11240 | | /* PI or XML decl */ |
11241 | | if (avail < 5) goto done; |
11242 | | if ((!terminate) && |
11243 | | (!xmlParseLookupString(ctxt, 2, "?>", 2))) |
11244 | | goto done; |
11245 | | if ((ctxt->sax) && (ctxt->sax->setDocumentLocator)) |
11246 | | ctxt->sax->setDocumentLocator(ctxt->userData, |
11247 | | &xmlDefaultSAXLocator); |
11248 | | if ((ctxt->input->cur[2] == 'x') && |
11249 | | (ctxt->input->cur[3] == 'm') && |
11250 | | (ctxt->input->cur[4] == 'l') && |
11251 | | (IS_BLANK_CH(ctxt->input->cur[5]))) { |
11252 | | ret += 5; |
11253 | | #ifdef DEBUG_PUSH |
11254 | | xmlGenericError(xmlGenericErrorContext, |
11255 | | "PP: Parsing XML Decl\n"); |
11256 | | #endif |
11257 | | xmlParseXMLDecl(ctxt); |
11258 | | if (ctxt->errNo == XML_ERR_UNSUPPORTED_ENCODING) { |
11259 | | /* |
11260 | | * The XML REC instructs us to stop parsing right |
11261 | | * here |
11262 | | */ |
11263 | | xmlHaltParser(ctxt); |
11264 | | return(0); |
11265 | | } |
11266 | | ctxt->standalone = ctxt->input->standalone; |
11267 | | if ((ctxt->encoding == NULL) && |
11268 | | (ctxt->input->encoding != NULL)) |
11269 | | ctxt->encoding = xmlStrdup(ctxt->input->encoding); |
11270 | | if ((ctxt->sax) && (ctxt->sax->startDocument) && |
11271 | | (!ctxt->disableSAX)) |
11272 | | ctxt->sax->startDocument(ctxt->userData); |
11273 | | ctxt->instate = XML_PARSER_MISC; |
11274 | | #ifdef DEBUG_PUSH |
11275 | | xmlGenericError(xmlGenericErrorContext, |
11276 | | "PP: entering MISC\n"); |
11277 | | #endif |
11278 | | } else { |
11279 | | ctxt->version = xmlCharStrdup(XML_DEFAULT_VERSION); |
11280 | | if ((ctxt->sax) && (ctxt->sax->startDocument) && |
11281 | | (!ctxt->disableSAX)) |
11282 | | ctxt->sax->startDocument(ctxt->userData); |
11283 | | ctxt->instate = XML_PARSER_MISC; |
11284 | | #ifdef DEBUG_PUSH |
11285 | | xmlGenericError(xmlGenericErrorContext, |
11286 | | "PP: entering MISC\n"); |
11287 | | #endif |
11288 | | } |
11289 | | } else { |
11290 | | if ((ctxt->sax) && (ctxt->sax->setDocumentLocator)) |
11291 | | ctxt->sax->setDocumentLocator(ctxt->userData, |
11292 | | &xmlDefaultSAXLocator); |
11293 | | ctxt->version = xmlCharStrdup(XML_DEFAULT_VERSION); |
11294 | | if (ctxt->version == NULL) { |
11295 | | xmlErrMemory(ctxt, NULL); |
11296 | | break; |
11297 | | } |
11298 | | if ((ctxt->sax) && (ctxt->sax->startDocument) && |
11299 | | (!ctxt->disableSAX)) |
11300 | | ctxt->sax->startDocument(ctxt->userData); |
11301 | | ctxt->instate = XML_PARSER_MISC; |
11302 | | #ifdef DEBUG_PUSH |
11303 | | xmlGenericError(xmlGenericErrorContext, |
11304 | | "PP: entering MISC\n"); |
11305 | | #endif |
11306 | | } |
11307 | | break; |
11308 | | case XML_PARSER_START_TAG: { |
11309 | | const xmlChar *name; |
11310 | | const xmlChar *prefix = NULL; |
11311 | | const xmlChar *URI = NULL; |
11312 | | int line = ctxt->input->line; |
11313 | | int nsNr = ctxt->nsNr; |
11314 | | |
11315 | | if ((avail < 2) && (ctxt->inputNr == 1)) |
11316 | | goto done; |
11317 | | cur = ctxt->input->cur[0]; |
11318 | | if (cur != '<') { |
11319 | | xmlFatalErr(ctxt, XML_ERR_DOCUMENT_EMPTY, NULL); |
11320 | | xmlHaltParser(ctxt); |
11321 | | if ((ctxt->sax) && (ctxt->sax->endDocument != NULL)) |
11322 | | ctxt->sax->endDocument(ctxt->userData); |
11323 | | goto done; |
11324 | | } |
11325 | | if ((!terminate) && (!xmlParseLookupGt(ctxt))) |
11326 | | goto done; |
11327 | | if (ctxt->spaceNr == 0) |
11328 | | spacePush(ctxt, -1); |
11329 | | else if (*ctxt->space == -2) |
11330 | | spacePush(ctxt, -1); |
11331 | | else |
11332 | | spacePush(ctxt, *ctxt->space); |
11333 | | #ifdef LIBXML_SAX1_ENABLED |
11334 | | if (ctxt->sax2) |
11335 | | #endif /* LIBXML_SAX1_ENABLED */ |
11336 | | name = xmlParseStartTag2(ctxt, &prefix, &URI, &tlen); |
11337 | | #ifdef LIBXML_SAX1_ENABLED |
11338 | | else |
11339 | | name = xmlParseStartTag(ctxt); |
11340 | | #endif /* LIBXML_SAX1_ENABLED */ |
11341 | | if (ctxt->instate == XML_PARSER_EOF) |
11342 | | goto done; |
11343 | | if (name == NULL) { |
11344 | | spacePop(ctxt); |
11345 | | xmlHaltParser(ctxt); |
11346 | | if ((ctxt->sax) && (ctxt->sax->endDocument != NULL)) |
11347 | | ctxt->sax->endDocument(ctxt->userData); |
11348 | | goto done; |
11349 | | } |
11350 | | #ifdef LIBXML_VALID_ENABLED |
11351 | | /* |
11352 | | * [ VC: Root Element Type ] |
11353 | | * The Name in the document type declaration must match |
11354 | | * the element type of the root element. |
11355 | | */ |
11356 | | if (ctxt->validate && ctxt->wellFormed && ctxt->myDoc && |
11357 | | ctxt->node && (ctxt->node == ctxt->myDoc->children)) |
11358 | | ctxt->valid &= xmlValidateRoot(&ctxt->vctxt, ctxt->myDoc); |
11359 | | #endif /* LIBXML_VALID_ENABLED */ |
11360 | | |
11361 | | /* |
11362 | | * Check for an Empty Element. |
11363 | | */ |
11364 | | if ((RAW == '/') && (NXT(1) == '>')) { |
11365 | | SKIP(2); |
11366 | | |
11367 | | if (ctxt->sax2) { |
11368 | | if ((ctxt->sax != NULL) && |
11369 | | (ctxt->sax->endElementNs != NULL) && |
11370 | | (!ctxt->disableSAX)) |
11371 | | ctxt->sax->endElementNs(ctxt->userData, name, |
11372 | | prefix, URI); |
11373 | | if (ctxt->nsNr - nsNr > 0) |
11374 | | nsPop(ctxt, ctxt->nsNr - nsNr); |
11375 | | #ifdef LIBXML_SAX1_ENABLED |
11376 | | } else { |
11377 | | if ((ctxt->sax != NULL) && |
11378 | | (ctxt->sax->endElement != NULL) && |
11379 | | (!ctxt->disableSAX)) |
11380 | | ctxt->sax->endElement(ctxt->userData, name); |
11381 | | #endif /* LIBXML_SAX1_ENABLED */ |
11382 | | } |
11383 | | if (ctxt->instate == XML_PARSER_EOF) |
11384 | | goto done; |
11385 | | spacePop(ctxt); |
11386 | | if (ctxt->nameNr == 0) { |
11387 | | ctxt->instate = XML_PARSER_EPILOG; |
11388 | | } else { |
11389 | | ctxt->instate = XML_PARSER_CONTENT; |
11390 | | } |
11391 | | break; |
11392 | | } |
11393 | | if (RAW == '>') { |
11394 | | NEXT; |
11395 | | } else { |
11396 | | xmlFatalErrMsgStr(ctxt, XML_ERR_GT_REQUIRED, |
11397 | | "Couldn't find end of Start Tag %s\n", |
11398 | | name); |
11399 | | nodePop(ctxt); |
11400 | | spacePop(ctxt); |
11401 | | } |
11402 | | nameNsPush(ctxt, name, prefix, URI, line, ctxt->nsNr - nsNr); |
11403 | | |
11404 | | ctxt->instate = XML_PARSER_CONTENT; |
11405 | | break; |
11406 | | } |
11407 | | case XML_PARSER_CONTENT: { |
11408 | | if ((avail < 2) && (ctxt->inputNr == 1)) |
11409 | | goto done; |
11410 | | cur = ctxt->input->cur[0]; |
11411 | | next = ctxt->input->cur[1]; |
11412 | | |
11413 | | if ((cur == '<') && (next == '/')) { |
11414 | | ctxt->instate = XML_PARSER_END_TAG; |
11415 | | break; |
11416 | | } else if ((cur == '<') && (next == '?')) { |
11417 | | if ((!terminate) && |
11418 | | (!xmlParseLookupString(ctxt, 2, "?>", 2))) |
11419 | | goto done; |
11420 | | xmlParsePI(ctxt); |
11421 | | ctxt->instate = XML_PARSER_CONTENT; |
11422 | | } else if ((cur == '<') && (next != '!')) { |
11423 | | ctxt->instate = XML_PARSER_START_TAG; |
11424 | | break; |
11425 | | } else if ((cur == '<') && (next == '!') && |
11426 | | (ctxt->input->cur[2] == '-') && |
11427 | | (ctxt->input->cur[3] == '-')) { |
11428 | | if ((!terminate) && |
11429 | | (!xmlParseLookupString(ctxt, 4, "-->", 3))) |
11430 | | goto done; |
11431 | | xmlParseComment(ctxt); |
11432 | | ctxt->instate = XML_PARSER_CONTENT; |
11433 | | } else if ((cur == '<') && (ctxt->input->cur[1] == '!') && |
11434 | | (ctxt->input->cur[2] == '[') && |
11435 | | (ctxt->input->cur[3] == 'C') && |
11436 | | (ctxt->input->cur[4] == 'D') && |
11437 | | (ctxt->input->cur[5] == 'A') && |
11438 | | (ctxt->input->cur[6] == 'T') && |
11439 | | (ctxt->input->cur[7] == 'A') && |
11440 | | (ctxt->input->cur[8] == '[')) { |
11441 | | SKIP(9); |
11442 | | ctxt->instate = XML_PARSER_CDATA_SECTION; |
11443 | | break; |
11444 | | } else if ((cur == '<') && (next == '!') && |
11445 | | (avail < 9)) { |
11446 | | goto done; |
11447 | | } else if (cur == '<') { |
11448 | | xmlFatalErr(ctxt, XML_ERR_INTERNAL_ERROR, |
11449 | | "detected an error in element content\n"); |
11450 | | SKIP(1); |
11451 | | } else if (cur == '&') { |
11452 | | if ((!terminate) && (!xmlParseLookupChar(ctxt, ';'))) |
11453 | | goto done; |
11454 | | xmlParseReference(ctxt); |
11455 | | } else { |
11456 | | /* TODO Avoid the extra copy, handle directly !!! */ |
11457 | | /* |
11458 | | * Goal of the following test is: |
11459 | | * - minimize calls to the SAX 'character' callback |
11460 | | * when they are mergeable |
11461 | | * - handle an problem for isBlank when we only parse |
11462 | | * a sequence of blank chars and the next one is |
11463 | | * not available to check against '<' presence. |
11464 | | * - tries to homogenize the differences in SAX |
11465 | | * callbacks between the push and pull versions |
11466 | | * of the parser. |
11467 | | */ |
11468 | | if ((ctxt->inputNr == 1) && |
11469 | | (avail < XML_PARSER_BIG_BUFFER_SIZE)) { |
11470 | | if ((!terminate) && (!xmlParseLookupCharData(ctxt))) |
11471 | | goto done; |
11472 | | } |
11473 | | ctxt->checkIndex = 0; |
11474 | | xmlParseCharDataInternal(ctxt, !terminate); |
11475 | | } |
11476 | | break; |
11477 | | } |
11478 | | case XML_PARSER_END_TAG: |
11479 | | if (avail < 2) |
11480 | | goto done; |
11481 | | if ((!terminate) && (!xmlParseLookupChar(ctxt, '>'))) |
11482 | | goto done; |
11483 | | if (ctxt->sax2) { |
11484 | | xmlParseEndTag2(ctxt, &ctxt->pushTab[ctxt->nameNr - 1]); |
11485 | | nameNsPop(ctxt); |
11486 | | } |
11487 | | #ifdef LIBXML_SAX1_ENABLED |
11488 | | else |
11489 | | xmlParseEndTag1(ctxt, 0); |
11490 | | #endif /* LIBXML_SAX1_ENABLED */ |
11491 | | if (ctxt->instate == XML_PARSER_EOF) { |
11492 | | /* Nothing */ |
11493 | | } else if (ctxt->nameNr == 0) { |
11494 | | ctxt->instate = XML_PARSER_EPILOG; |
11495 | | } else { |
11496 | | ctxt->instate = XML_PARSER_CONTENT; |
11497 | | } |
11498 | | break; |
11499 | | case XML_PARSER_CDATA_SECTION: { |
11500 | | /* |
11501 | | * The Push mode need to have the SAX callback for |
11502 | | * cdataBlock merge back contiguous callbacks. |
11503 | | */ |
11504 | | const xmlChar *term; |
11505 | | |
11506 | | if (terminate) { |
11507 | | /* |
11508 | | * Don't call xmlParseLookupString. If 'terminate' |
11509 | | * is set, checkIndex is invalid. |
11510 | | */ |
11511 | | term = BAD_CAST strstr((const char *) ctxt->input->cur, |
11512 | | "]]>"); |
11513 | | } else { |
11514 | | term = xmlParseLookupString(ctxt, 0, "]]>", 3); |
11515 | | } |
11516 | | |
11517 | | if (term == NULL) { |
11518 | | int tmp, size; |
11519 | | |
11520 | | if (terminate) { |
11521 | | /* Unfinished CDATA section */ |
11522 | | size = ctxt->input->end - ctxt->input->cur; |
11523 | | } else { |
11524 | | if (avail < XML_PARSER_BIG_BUFFER_SIZE + 2) |
11525 | | goto done; |
11526 | | ctxt->checkIndex = 0; |
11527 | | /* XXX: Why don't we pass the full buffer? */ |
11528 | | size = XML_PARSER_BIG_BUFFER_SIZE; |
11529 | | } |
11530 | | tmp = xmlCheckCdataPush(ctxt->input->cur, size, 0); |
11531 | | if (tmp <= 0) { |
11532 | | tmp = -tmp; |
11533 | | ctxt->input->cur += tmp; |
11534 | | goto encoding_error; |
11535 | | } |
11536 | | if ((ctxt->sax != NULL) && (!ctxt->disableSAX)) { |
11537 | | if (ctxt->sax->cdataBlock != NULL) |
11538 | | ctxt->sax->cdataBlock(ctxt->userData, |
11539 | | ctxt->input->cur, tmp); |
11540 | | else if (ctxt->sax->characters != NULL) |
11541 | | ctxt->sax->characters(ctxt->userData, |
11542 | | ctxt->input->cur, tmp); |
11543 | | } |
11544 | | if (ctxt->instate == XML_PARSER_EOF) |
11545 | | goto done; |
11546 | | SKIPL(tmp); |
11547 | | } else { |
11548 | | int base = term - CUR_PTR; |
11549 | | int tmp; |
11550 | | |
11551 | | tmp = xmlCheckCdataPush(ctxt->input->cur, base, 1); |
11552 | | if ((tmp < 0) || (tmp != base)) { |
11553 | | tmp = -tmp; |
11554 | | ctxt->input->cur += tmp; |
11555 | | goto encoding_error; |
11556 | | } |
11557 | | if ((ctxt->sax != NULL) && (base == 0) && |
11558 | | (ctxt->sax->cdataBlock != NULL) && |
11559 | | (!ctxt->disableSAX)) { |
11560 | | /* |
11561 | | * Special case to provide identical behaviour |
11562 | | * between pull and push parsers on enpty CDATA |
11563 | | * sections |
11564 | | */ |
11565 | | if ((ctxt->input->cur - ctxt->input->base >= 9) && |
11566 | | (!strncmp((const char *)&ctxt->input->cur[-9], |
11567 | | "<![CDATA[", 9))) |
11568 | | ctxt->sax->cdataBlock(ctxt->userData, |
11569 | | BAD_CAST "", 0); |
11570 | | } else if ((ctxt->sax != NULL) && (base > 0) && |
11571 | | (!ctxt->disableSAX)) { |
11572 | | if (ctxt->sax->cdataBlock != NULL) |
11573 | | ctxt->sax->cdataBlock(ctxt->userData, |
11574 | | ctxt->input->cur, base); |
11575 | | else if (ctxt->sax->characters != NULL) |
11576 | | ctxt->sax->characters(ctxt->userData, |
11577 | | ctxt->input->cur, base); |
11578 | | } |
11579 | | if (ctxt->instate == XML_PARSER_EOF) |
11580 | | goto done; |
11581 | | SKIPL(base + 3); |
11582 | | ctxt->instate = XML_PARSER_CONTENT; |
11583 | | #ifdef DEBUG_PUSH |
11584 | | xmlGenericError(xmlGenericErrorContext, |
11585 | | "PP: entering CONTENT\n"); |
11586 | | #endif |
11587 | | } |
11588 | | break; |
11589 | | } |
11590 | | case XML_PARSER_MISC: |
11591 | | case XML_PARSER_PROLOG: |
11592 | | case XML_PARSER_EPILOG: |
11593 | | SKIP_BLANKS; |
11594 | | avail = ctxt->input->end - ctxt->input->cur; |
11595 | | if (avail < 2) |
11596 | | goto done; |
11597 | | cur = ctxt->input->cur[0]; |
11598 | | next = ctxt->input->cur[1]; |
11599 | | if ((cur == '<') && (next == '?')) { |
11600 | | if ((!terminate) && |
11601 | | (!xmlParseLookupString(ctxt, 2, "?>", 2))) |
11602 | | goto done; |
11603 | | #ifdef DEBUG_PUSH |
11604 | | xmlGenericError(xmlGenericErrorContext, |
11605 | | "PP: Parsing PI\n"); |
11606 | | #endif |
11607 | | xmlParsePI(ctxt); |
11608 | | if (ctxt->instate == XML_PARSER_EOF) |
11609 | | goto done; |
11610 | | } else if ((cur == '<') && (next == '!') && |
11611 | | (ctxt->input->cur[2] == '-') && |
11612 | | (ctxt->input->cur[3] == '-')) { |
11613 | | if ((!terminate) && |
11614 | | (!xmlParseLookupString(ctxt, 4, "-->", 3))) |
11615 | | goto done; |
11616 | | #ifdef DEBUG_PUSH |
11617 | | xmlGenericError(xmlGenericErrorContext, |
11618 | | "PP: Parsing Comment\n"); |
11619 | | #endif |
11620 | | xmlParseComment(ctxt); |
11621 | | if (ctxt->instate == XML_PARSER_EOF) |
11622 | | goto done; |
11623 | | } else if ((ctxt->instate == XML_PARSER_MISC) && |
11624 | | (cur == '<') && (next == '!') && |
11625 | | (ctxt->input->cur[2] == 'D') && |
11626 | | (ctxt->input->cur[3] == 'O') && |
11627 | | (ctxt->input->cur[4] == 'C') && |
11628 | | (ctxt->input->cur[5] == 'T') && |
11629 | | (ctxt->input->cur[6] == 'Y') && |
11630 | | (ctxt->input->cur[7] == 'P') && |
11631 | | (ctxt->input->cur[8] == 'E')) { |
11632 | | if ((!terminate) && (!xmlParseLookupGt(ctxt))) |
11633 | | goto done; |
11634 | | #ifdef DEBUG_PUSH |
11635 | | xmlGenericError(xmlGenericErrorContext, |
11636 | | "PP: Parsing internal subset\n"); |
11637 | | #endif |
11638 | | ctxt->inSubset = 1; |
11639 | | xmlParseDocTypeDecl(ctxt); |
11640 | | if (ctxt->instate == XML_PARSER_EOF) |
11641 | | goto done; |
11642 | | if (RAW == '[') { |
11643 | | ctxt->instate = XML_PARSER_DTD; |
11644 | | #ifdef DEBUG_PUSH |
11645 | | xmlGenericError(xmlGenericErrorContext, |
11646 | | "PP: entering DTD\n"); |
11647 | | #endif |
11648 | | } else { |
11649 | | /* |
11650 | | * Create and update the external subset. |
11651 | | */ |
11652 | | ctxt->inSubset = 2; |
11653 | | if ((ctxt->sax != NULL) && (!ctxt->disableSAX) && |
11654 | | (ctxt->sax->externalSubset != NULL)) |
11655 | | ctxt->sax->externalSubset(ctxt->userData, |
11656 | | ctxt->intSubName, ctxt->extSubSystem, |
11657 | | ctxt->extSubURI); |
11658 | | ctxt->inSubset = 0; |
11659 | | xmlCleanSpecialAttr(ctxt); |
11660 | | ctxt->instate = XML_PARSER_PROLOG; |
11661 | | #ifdef DEBUG_PUSH |
11662 | | xmlGenericError(xmlGenericErrorContext, |
11663 | | "PP: entering PROLOG\n"); |
11664 | | #endif |
11665 | | } |
11666 | | } else if ((cur == '<') && (next == '!') && |
11667 | | (avail < |
11668 | | (ctxt->instate == XML_PARSER_MISC ? 9 : 4))) { |
11669 | | goto done; |
11670 | | } else if (ctxt->instate == XML_PARSER_EPILOG) { |
11671 | | xmlFatalErr(ctxt, XML_ERR_DOCUMENT_END, NULL); |
11672 | | xmlHaltParser(ctxt); |
11673 | | #ifdef DEBUG_PUSH |
11674 | | xmlGenericError(xmlGenericErrorContext, |
11675 | | "PP: entering EOF\n"); |
11676 | | #endif |
11677 | | if ((ctxt->sax) && (ctxt->sax->endDocument != NULL)) |
11678 | | ctxt->sax->endDocument(ctxt->userData); |
11679 | | goto done; |
11680 | | } else { |
11681 | | ctxt->instate = XML_PARSER_START_TAG; |
11682 | | #ifdef DEBUG_PUSH |
11683 | | xmlGenericError(xmlGenericErrorContext, |
11684 | | "PP: entering START_TAG\n"); |
11685 | | #endif |
11686 | | } |
11687 | | break; |
11688 | | case XML_PARSER_DTD: { |
11689 | | if ((!terminate) && (!xmlParseLookupInternalSubset(ctxt))) |
11690 | | goto done; |
11691 | | xmlParseInternalSubset(ctxt); |
11692 | | if (ctxt->instate == XML_PARSER_EOF) |
11693 | | goto done; |
11694 | | ctxt->inSubset = 2; |
11695 | | if ((ctxt->sax != NULL) && (!ctxt->disableSAX) && |
11696 | | (ctxt->sax->externalSubset != NULL)) |
11697 | | ctxt->sax->externalSubset(ctxt->userData, ctxt->intSubName, |
11698 | | ctxt->extSubSystem, ctxt->extSubURI); |
11699 | | ctxt->inSubset = 0; |
11700 | | xmlCleanSpecialAttr(ctxt); |
11701 | | if (ctxt->instate == XML_PARSER_EOF) |
11702 | | goto done; |
11703 | | ctxt->instate = XML_PARSER_PROLOG; |
11704 | | #ifdef DEBUG_PUSH |
11705 | | xmlGenericError(xmlGenericErrorContext, |
11706 | | "PP: entering PROLOG\n"); |
11707 | | #endif |
11708 | | break; |
11709 | | } |
11710 | | case XML_PARSER_COMMENT: |
11711 | | xmlGenericError(xmlGenericErrorContext, |
11712 | | "PP: internal error, state == COMMENT\n"); |
11713 | | ctxt->instate = XML_PARSER_CONTENT; |
11714 | | #ifdef DEBUG_PUSH |
11715 | | xmlGenericError(xmlGenericErrorContext, |
11716 | | "PP: entering CONTENT\n"); |
11717 | | #endif |
11718 | | break; |
11719 | | case XML_PARSER_IGNORE: |
11720 | | xmlGenericError(xmlGenericErrorContext, |
11721 | | "PP: internal error, state == IGNORE"); |
11722 | | ctxt->instate = XML_PARSER_DTD; |
11723 | | #ifdef DEBUG_PUSH |
11724 | | xmlGenericError(xmlGenericErrorContext, |
11725 | | "PP: entering DTD\n"); |
11726 | | #endif |
11727 | | break; |
11728 | | case XML_PARSER_PI: |
11729 | | xmlGenericError(xmlGenericErrorContext, |
11730 | | "PP: internal error, state == PI\n"); |
11731 | | ctxt->instate = XML_PARSER_CONTENT; |
11732 | | #ifdef DEBUG_PUSH |
11733 | | xmlGenericError(xmlGenericErrorContext, |
11734 | | "PP: entering CONTENT\n"); |
11735 | | #endif |
11736 | | break; |
11737 | | case XML_PARSER_ENTITY_DECL: |
11738 | | xmlGenericError(xmlGenericErrorContext, |
11739 | | "PP: internal error, state == ENTITY_DECL\n"); |
11740 | | ctxt->instate = XML_PARSER_DTD; |
11741 | | #ifdef DEBUG_PUSH |
11742 | | xmlGenericError(xmlGenericErrorContext, |
11743 | | "PP: entering DTD\n"); |
11744 | | #endif |
11745 | | break; |
11746 | | case XML_PARSER_ENTITY_VALUE: |
11747 | | xmlGenericError(xmlGenericErrorContext, |
11748 | | "PP: internal error, state == ENTITY_VALUE\n"); |
11749 | | ctxt->instate = XML_PARSER_CONTENT; |
11750 | | #ifdef DEBUG_PUSH |
11751 | | xmlGenericError(xmlGenericErrorContext, |
11752 | | "PP: entering DTD\n"); |
11753 | | #endif |
11754 | | break; |
11755 | | case XML_PARSER_ATTRIBUTE_VALUE: |
11756 | | xmlGenericError(xmlGenericErrorContext, |
11757 | | "PP: internal error, state == ATTRIBUTE_VALUE\n"); |
11758 | | ctxt->instate = XML_PARSER_START_TAG; |
11759 | | #ifdef DEBUG_PUSH |
11760 | | xmlGenericError(xmlGenericErrorContext, |
11761 | | "PP: entering START_TAG\n"); |
11762 | | #endif |
11763 | | break; |
11764 | | case XML_PARSER_SYSTEM_LITERAL: |
11765 | | xmlGenericError(xmlGenericErrorContext, |
11766 | | "PP: internal error, state == SYSTEM_LITERAL\n"); |
11767 | | ctxt->instate = XML_PARSER_START_TAG; |
11768 | | #ifdef DEBUG_PUSH |
11769 | | xmlGenericError(xmlGenericErrorContext, |
11770 | | "PP: entering START_TAG\n"); |
11771 | | #endif |
11772 | | break; |
11773 | | case XML_PARSER_PUBLIC_LITERAL: |
11774 | | xmlGenericError(xmlGenericErrorContext, |
11775 | | "PP: internal error, state == PUBLIC_LITERAL\n"); |
11776 | | ctxt->instate = XML_PARSER_START_TAG; |
11777 | | #ifdef DEBUG_PUSH |
11778 | | xmlGenericError(xmlGenericErrorContext, |
11779 | | "PP: entering START_TAG\n"); |
11780 | | #endif |
11781 | | break; |
11782 | | } |
11783 | | } |
11784 | | done: |
11785 | | #ifdef DEBUG_PUSH |
11786 | | xmlGenericError(xmlGenericErrorContext, "PP: done %d\n", ret); |
11787 | | #endif |
11788 | | return(ret); |
11789 | | encoding_error: |
11790 | | if (ctxt->input->end - ctxt->input->cur < 4) { |
11791 | | __xmlErrEncoding(ctxt, XML_ERR_INVALID_CHAR, |
11792 | | "Input is not proper UTF-8, indicate encoding !\n", |
11793 | | NULL, NULL); |
11794 | | } else { |
11795 | | char buffer[150]; |
11796 | | |
11797 | | snprintf(buffer, 149, "Bytes: 0x%02X 0x%02X 0x%02X 0x%02X\n", |
11798 | | ctxt->input->cur[0], ctxt->input->cur[1], |
11799 | | ctxt->input->cur[2], ctxt->input->cur[3]); |
11800 | | __xmlErrEncoding(ctxt, XML_ERR_INVALID_CHAR, |
11801 | | "Input is not proper UTF-8, indicate encoding !\n%s", |
11802 | | BAD_CAST buffer, NULL); |
11803 | | } |
11804 | | return(0); |
11805 | | } |
11806 | | |
11807 | | /** |
11808 | | * xmlParseChunk: |
11809 | | * @ctxt: an XML parser context |
11810 | | * @chunk: an char array |
11811 | | * @size: the size in byte of the chunk |
11812 | | * @terminate: last chunk indicator |
11813 | | * |
11814 | | * Parse a Chunk of memory |
11815 | | * |
11816 | | * Returns zero if no error, the xmlParserErrors otherwise. |
11817 | | */ |
11818 | | int |
11819 | | xmlParseChunk(xmlParserCtxtPtr ctxt, const char *chunk, int size, |
11820 | | int terminate) { |
11821 | | int end_in_lf = 0; |
11822 | | |
11823 | | if (ctxt == NULL) |
11824 | | return(XML_ERR_INTERNAL_ERROR); |
11825 | | if ((ctxt->errNo != XML_ERR_OK) && (ctxt->disableSAX == 1)) |
11826 | | return(ctxt->errNo); |
11827 | | if (ctxt->instate == XML_PARSER_EOF) |
11828 | | return(-1); |
11829 | | if (ctxt->input == NULL) |
11830 | | return(-1); |
11831 | | |
11832 | | ctxt->progressive = 1; |
11833 | | if (ctxt->instate == XML_PARSER_START) |
11834 | | xmlDetectSAX2(ctxt); |
11835 | | if ((size > 0) && (chunk != NULL) && (!terminate) && |
11836 | | (chunk[size - 1] == '\r')) { |
11837 | | end_in_lf = 1; |
11838 | | size--; |
11839 | | } |
11840 | | |
11841 | | if ((size > 0) && (chunk != NULL) && (ctxt->input != NULL) && |
11842 | | (ctxt->input->buf != NULL) && (ctxt->instate != XML_PARSER_EOF)) { |
11843 | | size_t base = xmlBufGetInputBase(ctxt->input->buf->buffer, ctxt->input); |
11844 | | size_t cur = ctxt->input->cur - ctxt->input->base; |
11845 | | int res; |
11846 | | |
11847 | | res = xmlParserInputBufferPush(ctxt->input->buf, size, chunk); |
11848 | | xmlBufSetInputBaseCur(ctxt->input->buf->buffer, ctxt->input, base, cur); |
11849 | | if (res < 0) { |
11850 | | xmlFatalErr(ctxt, ctxt->input->buf->error, NULL); |
11851 | | xmlHaltParser(ctxt); |
11852 | | return(ctxt->errNo); |
11853 | | } |
11854 | | #ifdef DEBUG_PUSH |
11855 | | xmlGenericError(xmlGenericErrorContext, "PP: pushed %d\n", size); |
11856 | | #endif |
11857 | | |
11858 | | } else if (ctxt->instate != XML_PARSER_EOF) { |
11859 | | if ((ctxt->input != NULL) && ctxt->input->buf != NULL) { |
11860 | | xmlParserInputBufferPtr in = ctxt->input->buf; |
11861 | | if ((in->encoder != NULL) && (in->buffer != NULL) && |
11862 | | (in->raw != NULL)) { |
11863 | | int nbchars; |
11864 | | size_t base = xmlBufGetInputBase(in->buffer, ctxt->input); |
11865 | | size_t current = ctxt->input->cur - ctxt->input->base; |
11866 | | |
11867 | | nbchars = xmlCharEncInput(in, terminate); |
11868 | | xmlBufSetInputBaseCur(in->buffer, ctxt->input, base, current); |
11869 | | if (nbchars < 0) { |
11870 | | xmlFatalErr(ctxt, in->error, NULL); |
11871 | | xmlHaltParser(ctxt); |
11872 | | return(ctxt->errNo); |
11873 | | } |
11874 | | } |
11875 | | } |
11876 | | } |
11877 | | |
11878 | | xmlParseTryOrFinish(ctxt, terminate); |
11879 | | if (ctxt->instate == XML_PARSER_EOF) |
11880 | | return(ctxt->errNo); |
11881 | | |
11882 | | if ((ctxt->input != NULL) && |
11883 | | (((ctxt->input->end - ctxt->input->cur) > XML_MAX_LOOKUP_LIMIT) || |
11884 | | ((ctxt->input->cur - ctxt->input->base) > XML_MAX_LOOKUP_LIMIT)) && |
11885 | | ((ctxt->options & XML_PARSE_HUGE) == 0)) { |
11886 | | xmlFatalErr(ctxt, XML_ERR_INTERNAL_ERROR, "Huge input lookup"); |
11887 | | xmlHaltParser(ctxt); |
11888 | | } |
11889 | | if ((ctxt->errNo != XML_ERR_OK) && (ctxt->disableSAX == 1)) |
11890 | | return(ctxt->errNo); |
11891 | | |
11892 | | if ((end_in_lf == 1) && (ctxt->input != NULL) && |
11893 | | (ctxt->input->buf != NULL)) { |
11894 | | size_t base = xmlBufGetInputBase(ctxt->input->buf->buffer, |
11895 | | ctxt->input); |
11896 | | size_t current = ctxt->input->cur - ctxt->input->base; |
11897 | | int res; |
11898 | | |
11899 | | res = xmlParserInputBufferPush(ctxt->input->buf, 1, "\r"); |
11900 | | xmlBufSetInputBaseCur(ctxt->input->buf->buffer, ctxt->input, |
11901 | | base, current); |
11902 | | if (res < 0) { |
11903 | | xmlFatalErr(ctxt, ctxt->input->buf->error, NULL); |
11904 | | xmlHaltParser(ctxt); |
11905 | | return(ctxt->errNo); |
11906 | | } |
11907 | | } |
11908 | | if (terminate) { |
11909 | | /* |
11910 | | * Check for termination |
11911 | | */ |
11912 | | if ((ctxt->instate != XML_PARSER_EOF) && |
11913 | | (ctxt->instate != XML_PARSER_EPILOG)) { |
11914 | | xmlFatalErr(ctxt, XML_ERR_DOCUMENT_END, NULL); |
11915 | | } |
11916 | | if ((ctxt->instate == XML_PARSER_EPILOG) && |
11917 | | (ctxt->input->cur < ctxt->input->end)) { |
11918 | | xmlFatalErr(ctxt, XML_ERR_DOCUMENT_END, NULL); |
11919 | | } |
11920 | | if (ctxt->instate != XML_PARSER_EOF) { |
11921 | | if ((ctxt->sax) && (ctxt->sax->endDocument != NULL)) |
11922 | | ctxt->sax->endDocument(ctxt->userData); |
11923 | | } |
11924 | | ctxt->instate = XML_PARSER_EOF; |
11925 | | } |
11926 | | if (ctxt->wellFormed == 0) |
11927 | | return((xmlParserErrors) ctxt->errNo); |
11928 | | else |
11929 | | return(0); |
11930 | | } |
11931 | | |
11932 | | /************************************************************************ |
11933 | | * * |
11934 | | * I/O front end functions to the parser * |
11935 | | * * |
11936 | | ************************************************************************/ |
11937 | | |
11938 | | /** |
11939 | | * xmlCreatePushParserCtxt: |
11940 | | * @sax: a SAX handler |
11941 | | * @user_data: The user data returned on SAX callbacks |
11942 | | * @chunk: a pointer to an array of chars |
11943 | | * @size: number of chars in the array |
11944 | | * @filename: an optional file name or URI |
11945 | | * |
11946 | | * Create a parser context for using the XML parser in push mode. |
11947 | | * If @buffer and @size are non-NULL, the data is used to detect |
11948 | | * the encoding. The remaining characters will be parsed so they |
11949 | | * don't need to be fed in again through xmlParseChunk. |
11950 | | * To allow content encoding detection, @size should be >= 4 |
11951 | | * The value of @filename is used for fetching external entities |
11952 | | * and error/warning reports. |
11953 | | * |
11954 | | * Returns the new parser context or NULL |
11955 | | */ |
11956 | | |
11957 | | xmlParserCtxtPtr |
11958 | | xmlCreatePushParserCtxt(xmlSAXHandlerPtr sax, void *user_data, |
11959 | | const char *chunk, int size, const char *filename) { |
11960 | | xmlParserCtxtPtr ctxt; |
11961 | | xmlParserInputPtr inputStream; |
11962 | | xmlParserInputBufferPtr buf; |
11963 | | |
11964 | | buf = xmlAllocParserInputBuffer(XML_CHAR_ENCODING_NONE); |
11965 | | if (buf == NULL) return(NULL); |
11966 | | |
11967 | | ctxt = xmlNewSAXParserCtxt(sax, user_data); |
11968 | | if (ctxt == NULL) { |
11969 | | xmlErrMemory(NULL, "creating parser: out of memory\n"); |
11970 | | xmlFreeParserInputBuffer(buf); |
11971 | | return(NULL); |
11972 | | } |
11973 | | ctxt->dictNames = 1; |
11974 | | if (filename == NULL) { |
11975 | | ctxt->directory = NULL; |
11976 | | } else { |
11977 | | ctxt->directory = xmlParserGetDirectory(filename); |
11978 | | } |
11979 | | |
11980 | | inputStream = xmlNewInputStream(ctxt); |
11981 | | if (inputStream == NULL) { |
11982 | | xmlFreeParserCtxt(ctxt); |
11983 | | xmlFreeParserInputBuffer(buf); |
11984 | | return(NULL); |
11985 | | } |
11986 | | |
11987 | | if (filename == NULL) |
11988 | | inputStream->filename = NULL; |
11989 | | else { |
11990 | | inputStream->filename = (char *) |
11991 | | xmlCanonicPath((const xmlChar *) filename); |
11992 | | if (inputStream->filename == NULL) { |
11993 | | xmlFreeInputStream(inputStream); |
11994 | | xmlFreeParserCtxt(ctxt); |
11995 | | xmlFreeParserInputBuffer(buf); |
11996 | | return(NULL); |
11997 | | } |
11998 | | } |
11999 | | inputStream->buf = buf; |
12000 | | xmlBufResetInput(inputStream->buf->buffer, inputStream); |
12001 | | inputPush(ctxt, inputStream); |
12002 | | |
12003 | | /* |
12004 | | * If the caller didn't provide an initial 'chunk' for determining |
12005 | | * the encoding, we set the context to XML_CHAR_ENCODING_NONE so |
12006 | | * that it can be automatically determined later |
12007 | | */ |
12008 | | ctxt->charset = XML_CHAR_ENCODING_NONE; |
12009 | | |
12010 | | if ((size != 0) && (chunk != NULL) && |
12011 | | (ctxt->input != NULL) && (ctxt->input->buf != NULL)) { |
12012 | | size_t base = xmlBufGetInputBase(ctxt->input->buf->buffer, ctxt->input); |
12013 | | size_t cur = ctxt->input->cur - ctxt->input->base; |
12014 | | int res; |
12015 | | |
12016 | | res = xmlParserInputBufferPush(ctxt->input->buf, size, chunk); |
12017 | | xmlBufSetInputBaseCur(ctxt->input->buf->buffer, ctxt->input, base, cur); |
12018 | | if (res < 0) { |
12019 | | xmlFatalErr(ctxt, ctxt->input->buf->error, NULL); |
12020 | | xmlHaltParser(ctxt); |
12021 | | } |
12022 | | #ifdef DEBUG_PUSH |
12023 | | xmlGenericError(xmlGenericErrorContext, "PP: pushed %d\n", size); |
12024 | | #endif |
12025 | | } |
12026 | | |
12027 | | return(ctxt); |
12028 | | } |
12029 | | #endif /* LIBXML_PUSH_ENABLED */ |
12030 | | |
12031 | | /** |
12032 | | * xmlStopParser: |
12033 | | * @ctxt: an XML parser context |
12034 | | * |
12035 | | * Blocks further parser processing |
12036 | | */ |
12037 | | void |
12038 | 253k | xmlStopParser(xmlParserCtxtPtr ctxt) { |
12039 | 253k | if (ctxt == NULL) |
12040 | 253k | return; |
12041 | 0 | xmlHaltParser(ctxt); |
12042 | 0 | ctxt->errNo = XML_ERR_USER_STOP; |
12043 | 0 | } |
12044 | | |
12045 | | /** |
12046 | | * xmlCreateIOParserCtxt: |
12047 | | * @sax: a SAX handler |
12048 | | * @user_data: The user data returned on SAX callbacks |
12049 | | * @ioread: an I/O read function |
12050 | | * @ioclose: an I/O close function |
12051 | | * @ioctx: an I/O handler |
12052 | | * @enc: the charset encoding if known |
12053 | | * |
12054 | | * Create a parser context for using the XML parser with an existing |
12055 | | * I/O stream |
12056 | | * |
12057 | | * Returns the new parser context or NULL |
12058 | | */ |
12059 | | xmlParserCtxtPtr |
12060 | | xmlCreateIOParserCtxt(xmlSAXHandlerPtr sax, void *user_data, |
12061 | | xmlInputReadCallback ioread, xmlInputCloseCallback ioclose, |
12062 | 0 | void *ioctx, xmlCharEncoding enc) { |
12063 | 0 | xmlParserCtxtPtr ctxt; |
12064 | 0 | xmlParserInputPtr inputStream; |
12065 | 0 | xmlParserInputBufferPtr buf; |
12066 | |
|
12067 | 0 | if (ioread == NULL) return(NULL); |
12068 | | |
12069 | 0 | buf = xmlParserInputBufferCreateIO(ioread, ioclose, ioctx, enc); |
12070 | 0 | if (buf == NULL) { |
12071 | 0 | if (ioclose != NULL) |
12072 | 0 | ioclose(ioctx); |
12073 | 0 | return (NULL); |
12074 | 0 | } |
12075 | | |
12076 | 0 | ctxt = xmlNewSAXParserCtxt(sax, user_data); |
12077 | 0 | if (ctxt == NULL) { |
12078 | 0 | xmlFreeParserInputBuffer(buf); |
12079 | 0 | return(NULL); |
12080 | 0 | } |
12081 | | |
12082 | 0 | inputStream = xmlNewIOInputStream(ctxt, buf, enc); |
12083 | 0 | if (inputStream == NULL) { |
12084 | 0 | xmlFreeParserCtxt(ctxt); |
12085 | 0 | return(NULL); |
12086 | 0 | } |
12087 | 0 | inputPush(ctxt, inputStream); |
12088 | |
|
12089 | 0 | return(ctxt); |
12090 | 0 | } |
12091 | | |
12092 | | #ifdef LIBXML_VALID_ENABLED |
12093 | | /************************************************************************ |
12094 | | * * |
12095 | | * Front ends when parsing a DTD * |
12096 | | * * |
12097 | | ************************************************************************/ |
12098 | | |
12099 | | /** |
12100 | | * xmlIOParseDTD: |
12101 | | * @sax: the SAX handler block or NULL |
12102 | | * @input: an Input Buffer |
12103 | | * @enc: the charset encoding if known |
12104 | | * |
12105 | | * Load and parse a DTD |
12106 | | * |
12107 | | * Returns the resulting xmlDtdPtr or NULL in case of error. |
12108 | | * @input will be freed by the function in any case. |
12109 | | */ |
12110 | | |
12111 | | xmlDtdPtr |
12112 | | xmlIOParseDTD(xmlSAXHandlerPtr sax, xmlParserInputBufferPtr input, |
12113 | | xmlCharEncoding enc) { |
12114 | | xmlDtdPtr ret = NULL; |
12115 | | xmlParserCtxtPtr ctxt; |
12116 | | xmlParserInputPtr pinput = NULL; |
12117 | | xmlChar start[4]; |
12118 | | |
12119 | | if (input == NULL) |
12120 | | return(NULL); |
12121 | | |
12122 | | ctxt = xmlNewSAXParserCtxt(sax, NULL); |
12123 | | if (ctxt == NULL) { |
12124 | | xmlFreeParserInputBuffer(input); |
12125 | | return(NULL); |
12126 | | } |
12127 | | |
12128 | | /* We are loading a DTD */ |
12129 | | ctxt->options |= XML_PARSE_DTDLOAD; |
12130 | | |
12131 | | xmlDetectSAX2(ctxt); |
12132 | | |
12133 | | /* |
12134 | | * generate a parser input from the I/O handler |
12135 | | */ |
12136 | | |
12137 | | pinput = xmlNewIOInputStream(ctxt, input, XML_CHAR_ENCODING_NONE); |
12138 | | if (pinput == NULL) { |
12139 | | xmlFreeParserInputBuffer(input); |
12140 | | xmlFreeParserCtxt(ctxt); |
12141 | | return(NULL); |
12142 | | } |
12143 | | |
12144 | | /* |
12145 | | * plug some encoding conversion routines here. |
12146 | | */ |
12147 | | if (xmlPushInput(ctxt, pinput) < 0) { |
12148 | | xmlFreeParserCtxt(ctxt); |
12149 | | return(NULL); |
12150 | | } |
12151 | | if (enc != XML_CHAR_ENCODING_NONE) { |
12152 | | xmlSwitchEncoding(ctxt, enc); |
12153 | | } |
12154 | | |
12155 | | pinput->filename = NULL; |
12156 | | pinput->line = 1; |
12157 | | pinput->col = 1; |
12158 | | pinput->base = ctxt->input->cur; |
12159 | | pinput->cur = ctxt->input->cur; |
12160 | | pinput->free = NULL; |
12161 | | |
12162 | | /* |
12163 | | * let's parse that entity knowing it's an external subset. |
12164 | | */ |
12165 | | ctxt->inSubset = 2; |
12166 | | ctxt->myDoc = xmlNewDoc(BAD_CAST "1.0"); |
12167 | | if (ctxt->myDoc == NULL) { |
12168 | | xmlErrMemory(ctxt, "New Doc failed"); |
12169 | | return(NULL); |
12170 | | } |
12171 | | ctxt->myDoc->properties = XML_DOC_INTERNAL; |
12172 | | ctxt->myDoc->extSubset = xmlNewDtd(ctxt->myDoc, BAD_CAST "none", |
12173 | | BAD_CAST "none", BAD_CAST "none"); |
12174 | | |
12175 | | if ((enc == XML_CHAR_ENCODING_NONE) && |
12176 | | ((ctxt->input->end - ctxt->input->cur) >= 4)) { |
12177 | | /* |
12178 | | * Get the 4 first bytes and decode the charset |
12179 | | * if enc != XML_CHAR_ENCODING_NONE |
12180 | | * plug some encoding conversion routines. |
12181 | | */ |
12182 | | start[0] = RAW; |
12183 | | start[1] = NXT(1); |
12184 | | start[2] = NXT(2); |
12185 | | start[3] = NXT(3); |
12186 | | enc = xmlDetectCharEncoding(start, 4); |
12187 | | if (enc != XML_CHAR_ENCODING_NONE) { |
12188 | | xmlSwitchEncoding(ctxt, enc); |
12189 | | } |
12190 | | } |
12191 | | |
12192 | | xmlParseExternalSubset(ctxt, BAD_CAST "none", BAD_CAST "none"); |
12193 | | |
12194 | | if (ctxt->myDoc != NULL) { |
12195 | | if (ctxt->wellFormed) { |
12196 | | ret = ctxt->myDoc->extSubset; |
12197 | | ctxt->myDoc->extSubset = NULL; |
12198 | | if (ret != NULL) { |
12199 | | xmlNodePtr tmp; |
12200 | | |
12201 | | ret->doc = NULL; |
12202 | | tmp = ret->children; |
12203 | | while (tmp != NULL) { |
12204 | | tmp->doc = NULL; |
12205 | | tmp = tmp->next; |
12206 | | } |
12207 | | } |
12208 | | } else { |
12209 | | ret = NULL; |
12210 | | } |
12211 | | xmlFreeDoc(ctxt->myDoc); |
12212 | | ctxt->myDoc = NULL; |
12213 | | } |
12214 | | xmlFreeParserCtxt(ctxt); |
12215 | | |
12216 | | return(ret); |
12217 | | } |
12218 | | |
12219 | | /** |
12220 | | * xmlSAXParseDTD: |
12221 | | * @sax: the SAX handler block |
12222 | | * @ExternalID: a NAME* containing the External ID of the DTD |
12223 | | * @SystemID: a NAME* containing the URL to the DTD |
12224 | | * |
12225 | | * DEPRECATED: Don't use. |
12226 | | * |
12227 | | * Load and parse an external subset. |
12228 | | * |
12229 | | * Returns the resulting xmlDtdPtr or NULL in case of error. |
12230 | | */ |
12231 | | |
12232 | | xmlDtdPtr |
12233 | | xmlSAXParseDTD(xmlSAXHandlerPtr sax, const xmlChar *ExternalID, |
12234 | | const xmlChar *SystemID) { |
12235 | | xmlDtdPtr ret = NULL; |
12236 | | xmlParserCtxtPtr ctxt; |
12237 | | xmlParserInputPtr input = NULL; |
12238 | | xmlCharEncoding enc; |
12239 | | xmlChar* systemIdCanonic; |
12240 | | |
12241 | | if ((ExternalID == NULL) && (SystemID == NULL)) return(NULL); |
12242 | | |
12243 | | ctxt = xmlNewSAXParserCtxt(sax, NULL); |
12244 | | if (ctxt == NULL) { |
12245 | | return(NULL); |
12246 | | } |
12247 | | |
12248 | | /* We are loading a DTD */ |
12249 | | ctxt->options |= XML_PARSE_DTDLOAD; |
12250 | | |
12251 | | /* |
12252 | | * Canonicalise the system ID |
12253 | | */ |
12254 | | systemIdCanonic = xmlCanonicPath(SystemID); |
12255 | | if ((SystemID != NULL) && (systemIdCanonic == NULL)) { |
12256 | | xmlFreeParserCtxt(ctxt); |
12257 | | return(NULL); |
12258 | | } |
12259 | | |
12260 | | /* |
12261 | | * Ask the Entity resolver to load the damn thing |
12262 | | */ |
12263 | | |
12264 | | if ((ctxt->sax != NULL) && (ctxt->sax->resolveEntity != NULL)) |
12265 | | input = ctxt->sax->resolveEntity(ctxt->userData, ExternalID, |
12266 | | systemIdCanonic); |
12267 | | if (input == NULL) { |
12268 | | xmlFreeParserCtxt(ctxt); |
12269 | | if (systemIdCanonic != NULL) |
12270 | | xmlFree(systemIdCanonic); |
12271 | | return(NULL); |
12272 | | } |
12273 | | |
12274 | | /* |
12275 | | * plug some encoding conversion routines here. |
12276 | | */ |
12277 | | if (xmlPushInput(ctxt, input) < 0) { |
12278 | | xmlFreeParserCtxt(ctxt); |
12279 | | if (systemIdCanonic != NULL) |
12280 | | xmlFree(systemIdCanonic); |
12281 | | return(NULL); |
12282 | | } |
12283 | | if ((ctxt->input->end - ctxt->input->cur) >= 4) { |
12284 | | enc = xmlDetectCharEncoding(ctxt->input->cur, 4); |
12285 | | xmlSwitchEncoding(ctxt, enc); |
12286 | | } |
12287 | | |
12288 | | if (input->filename == NULL) |
12289 | | input->filename = (char *) systemIdCanonic; |
12290 | | else |
12291 | | xmlFree(systemIdCanonic); |
12292 | | input->line = 1; |
12293 | | input->col = 1; |
12294 | | input->base = ctxt->input->cur; |
12295 | | input->cur = ctxt->input->cur; |
12296 | | input->free = NULL; |
12297 | | |
12298 | | /* |
12299 | | * let's parse that entity knowing it's an external subset. |
12300 | | */ |
12301 | | ctxt->inSubset = 2; |
12302 | | ctxt->myDoc = xmlNewDoc(BAD_CAST "1.0"); |
12303 | | if (ctxt->myDoc == NULL) { |
12304 | | xmlErrMemory(ctxt, "New Doc failed"); |
12305 | | xmlFreeParserCtxt(ctxt); |
12306 | | return(NULL); |
12307 | | } |
12308 | | ctxt->myDoc->properties = XML_DOC_INTERNAL; |
12309 | | ctxt->myDoc->extSubset = xmlNewDtd(ctxt->myDoc, BAD_CAST "none", |
12310 | | ExternalID, SystemID); |
12311 | | xmlParseExternalSubset(ctxt, ExternalID, SystemID); |
12312 | | |
12313 | | if (ctxt->myDoc != NULL) { |
12314 | | if (ctxt->wellFormed) { |
12315 | | ret = ctxt->myDoc->extSubset; |
12316 | | ctxt->myDoc->extSubset = NULL; |
12317 | | if (ret != NULL) { |
12318 | | xmlNodePtr tmp; |
12319 | | |
12320 | | ret->doc = NULL; |
12321 | | tmp = ret->children; |
12322 | | while (tmp != NULL) { |
12323 | | tmp->doc = NULL; |
12324 | | tmp = tmp->next; |
12325 | | } |
12326 | | } |
12327 | | } else { |
12328 | | ret = NULL; |
12329 | | } |
12330 | | xmlFreeDoc(ctxt->myDoc); |
12331 | | ctxt->myDoc = NULL; |
12332 | | } |
12333 | | xmlFreeParserCtxt(ctxt); |
12334 | | |
12335 | | return(ret); |
12336 | | } |
12337 | | |
12338 | | |
12339 | | /** |
12340 | | * xmlParseDTD: |
12341 | | * @ExternalID: a NAME* containing the External ID of the DTD |
12342 | | * @SystemID: a NAME* containing the URL to the DTD |
12343 | | * |
12344 | | * Load and parse an external subset. |
12345 | | * |
12346 | | * Returns the resulting xmlDtdPtr or NULL in case of error. |
12347 | | */ |
12348 | | |
12349 | | xmlDtdPtr |
12350 | | xmlParseDTD(const xmlChar *ExternalID, const xmlChar *SystemID) { |
12351 | | return(xmlSAXParseDTD(NULL, ExternalID, SystemID)); |
12352 | | } |
12353 | | #endif /* LIBXML_VALID_ENABLED */ |
12354 | | |
12355 | | /************************************************************************ |
12356 | | * * |
12357 | | * Front ends when parsing an Entity * |
12358 | | * * |
12359 | | ************************************************************************/ |
12360 | | |
12361 | | /** |
12362 | | * xmlParseCtxtExternalEntity: |
12363 | | * @ctx: the existing parsing context |
12364 | | * @URL: the URL for the entity to load |
12365 | | * @ID: the System ID for the entity to load |
12366 | | * @lst: the return value for the set of parsed nodes |
12367 | | * |
12368 | | * Parse an external general entity within an existing parsing context |
12369 | | * An external general parsed entity is well-formed if it matches the |
12370 | | * production labeled extParsedEnt. |
12371 | | * |
12372 | | * [78] extParsedEnt ::= TextDecl? content |
12373 | | * |
12374 | | * Returns 0 if the entity is well formed, -1 in case of args problem and |
12375 | | * the parser error code otherwise |
12376 | | */ |
12377 | | |
12378 | | int |
12379 | | xmlParseCtxtExternalEntity(xmlParserCtxtPtr ctx, const xmlChar *URL, |
12380 | 0 | const xmlChar *ID, xmlNodePtr *lst) { |
12381 | 0 | void *userData; |
12382 | |
|
12383 | 0 | if (ctx == NULL) return(-1); |
12384 | | /* |
12385 | | * If the user provided their own SAX callbacks, then reuse the |
12386 | | * userData callback field, otherwise the expected setup in a |
12387 | | * DOM builder is to have userData == ctxt |
12388 | | */ |
12389 | 0 | if (ctx->userData == ctx) |
12390 | 0 | userData = NULL; |
12391 | 0 | else |
12392 | 0 | userData = ctx->userData; |
12393 | 0 | return xmlParseExternalEntityPrivate(ctx->myDoc, ctx, ctx->sax, |
12394 | 0 | userData, ctx->depth + 1, |
12395 | 0 | URL, ID, lst); |
12396 | 0 | } |
12397 | | |
12398 | | /** |
12399 | | * xmlParseExternalEntityPrivate: |
12400 | | * @doc: the document the chunk pertains to |
12401 | | * @oldctxt: the previous parser context if available |
12402 | | * @sax: the SAX handler block (possibly NULL) |
12403 | | * @user_data: The user data returned on SAX callbacks (possibly NULL) |
12404 | | * @depth: Used for loop detection, use 0 |
12405 | | * @URL: the URL for the entity to load |
12406 | | * @ID: the System ID for the entity to load |
12407 | | * @list: the return value for the set of parsed nodes |
12408 | | * |
12409 | | * Private version of xmlParseExternalEntity() |
12410 | | * |
12411 | | * Returns 0 if the entity is well formed, -1 in case of args problem and |
12412 | | * the parser error code otherwise |
12413 | | */ |
12414 | | |
12415 | | static xmlParserErrors |
12416 | | xmlParseExternalEntityPrivate(xmlDocPtr doc, xmlParserCtxtPtr oldctxt, |
12417 | | xmlSAXHandlerPtr sax, |
12418 | | void *user_data, int depth, const xmlChar *URL, |
12419 | 0 | const xmlChar *ID, xmlNodePtr *list) { |
12420 | 0 | xmlParserCtxtPtr ctxt; |
12421 | 0 | xmlDocPtr newDoc; |
12422 | 0 | xmlNodePtr newRoot; |
12423 | 0 | xmlParserErrors ret = XML_ERR_OK; |
12424 | 0 | xmlChar start[4]; |
12425 | 0 | xmlCharEncoding enc; |
12426 | |
|
12427 | 0 | if (((depth > 40) && |
12428 | 0 | ((oldctxt == NULL) || (oldctxt->options & XML_PARSE_HUGE) == 0)) || |
12429 | 0 | (depth > 100)) { |
12430 | 0 | xmlFatalErrMsg(oldctxt, XML_ERR_ENTITY_LOOP, |
12431 | 0 | "Maximum entity nesting depth exceeded"); |
12432 | 0 | return(XML_ERR_ENTITY_LOOP); |
12433 | 0 | } |
12434 | | |
12435 | 0 | if (list != NULL) |
12436 | 0 | *list = NULL; |
12437 | 0 | if ((URL == NULL) && (ID == NULL)) |
12438 | 0 | return(XML_ERR_INTERNAL_ERROR); |
12439 | 0 | if (doc == NULL) |
12440 | 0 | return(XML_ERR_INTERNAL_ERROR); |
12441 | | |
12442 | 0 | ctxt = xmlCreateEntityParserCtxtInternal(sax, user_data, URL, ID, NULL, |
12443 | 0 | oldctxt); |
12444 | 0 | if (ctxt == NULL) return(XML_WAR_UNDECLARED_ENTITY); |
12445 | 0 | if (oldctxt != NULL) { |
12446 | 0 | ctxt->nbErrors = oldctxt->nbErrors; |
12447 | 0 | ctxt->nbWarnings = oldctxt->nbWarnings; |
12448 | 0 | } |
12449 | 0 | xmlDetectSAX2(ctxt); |
12450 | |
|
12451 | 0 | newDoc = xmlNewDoc(BAD_CAST "1.0"); |
12452 | 0 | if (newDoc == NULL) { |
12453 | 0 | xmlFreeParserCtxt(ctxt); |
12454 | 0 | return(XML_ERR_INTERNAL_ERROR); |
12455 | 0 | } |
12456 | 0 | newDoc->properties = XML_DOC_INTERNAL; |
12457 | 0 | if (doc) { |
12458 | 0 | newDoc->intSubset = doc->intSubset; |
12459 | 0 | newDoc->extSubset = doc->extSubset; |
12460 | 0 | if (doc->dict) { |
12461 | 0 | newDoc->dict = doc->dict; |
12462 | 0 | xmlDictReference(newDoc->dict); |
12463 | 0 | } |
12464 | 0 | if (doc->URL != NULL) { |
12465 | 0 | newDoc->URL = xmlStrdup(doc->URL); |
12466 | 0 | } |
12467 | 0 | } |
12468 | 0 | newRoot = xmlNewDocNode(newDoc, NULL, BAD_CAST "pseudoroot", NULL); |
12469 | 0 | if (newRoot == NULL) { |
12470 | 0 | if (sax != NULL) |
12471 | 0 | xmlFreeParserCtxt(ctxt); |
12472 | 0 | newDoc->intSubset = NULL; |
12473 | 0 | newDoc->extSubset = NULL; |
12474 | 0 | xmlFreeDoc(newDoc); |
12475 | 0 | return(XML_ERR_INTERNAL_ERROR); |
12476 | 0 | } |
12477 | 0 | xmlAddChild((xmlNodePtr) newDoc, newRoot); |
12478 | 0 | nodePush(ctxt, newDoc->children); |
12479 | 0 | if (doc == NULL) { |
12480 | 0 | ctxt->myDoc = newDoc; |
12481 | 0 | } else { |
12482 | 0 | ctxt->myDoc = doc; |
12483 | 0 | newRoot->doc = doc; |
12484 | 0 | } |
12485 | | |
12486 | | /* |
12487 | | * Get the 4 first bytes and decode the charset |
12488 | | * if enc != XML_CHAR_ENCODING_NONE |
12489 | | * plug some encoding conversion routines. |
12490 | | */ |
12491 | 0 | GROW; |
12492 | 0 | if ((ctxt->input->end - ctxt->input->cur) >= 4) { |
12493 | 0 | start[0] = RAW; |
12494 | 0 | start[1] = NXT(1); |
12495 | 0 | start[2] = NXT(2); |
12496 | 0 | start[3] = NXT(3); |
12497 | 0 | enc = xmlDetectCharEncoding(start, 4); |
12498 | 0 | if (enc != XML_CHAR_ENCODING_NONE) { |
12499 | 0 | xmlSwitchEncoding(ctxt, enc); |
12500 | 0 | } |
12501 | 0 | } |
12502 | | |
12503 | | /* |
12504 | | * Parse a possible text declaration first |
12505 | | */ |
12506 | 0 | if ((CMP5(CUR_PTR, '<', '?', 'x', 'm', 'l')) && (IS_BLANK_CH(NXT(5)))) { |
12507 | 0 | xmlParseTextDecl(ctxt); |
12508 | | /* |
12509 | | * An XML-1.0 document can't reference an entity not XML-1.0 |
12510 | | */ |
12511 | 0 | if ((xmlStrEqual(oldctxt->version, BAD_CAST "1.0")) && |
12512 | 0 | (!xmlStrEqual(ctxt->input->version, BAD_CAST "1.0"))) { |
12513 | 0 | xmlFatalErrMsg(ctxt, XML_ERR_VERSION_MISMATCH, |
12514 | 0 | "Version mismatch between document and entity\n"); |
12515 | 0 | } |
12516 | 0 | } |
12517 | |
|
12518 | 0 | ctxt->instate = XML_PARSER_CONTENT; |
12519 | 0 | ctxt->depth = depth; |
12520 | 0 | if (oldctxt != NULL) { |
12521 | 0 | ctxt->_private = oldctxt->_private; |
12522 | 0 | ctxt->loadsubset = oldctxt->loadsubset; |
12523 | 0 | ctxt->validate = oldctxt->validate; |
12524 | 0 | ctxt->valid = oldctxt->valid; |
12525 | 0 | ctxt->replaceEntities = oldctxt->replaceEntities; |
12526 | 0 | if (oldctxt->validate) { |
12527 | 0 | ctxt->vctxt.error = oldctxt->vctxt.error; |
12528 | 0 | ctxt->vctxt.warning = oldctxt->vctxt.warning; |
12529 | 0 | ctxt->vctxt.userData = oldctxt->vctxt.userData; |
12530 | 0 | ctxt->vctxt.flags = oldctxt->vctxt.flags; |
12531 | 0 | } |
12532 | 0 | ctxt->external = oldctxt->external; |
12533 | 0 | if (ctxt->dict) xmlDictFree(ctxt->dict); |
12534 | 0 | ctxt->dict = oldctxt->dict; |
12535 | 0 | ctxt->str_xml = xmlDictLookup(ctxt->dict, BAD_CAST "xml", 3); |
12536 | 0 | ctxt->str_xmlns = xmlDictLookup(ctxt->dict, BAD_CAST "xmlns", 5); |
12537 | 0 | ctxt->str_xml_ns = xmlDictLookup(ctxt->dict, XML_XML_NAMESPACE, 36); |
12538 | 0 | ctxt->dictNames = oldctxt->dictNames; |
12539 | 0 | ctxt->attsDefault = oldctxt->attsDefault; |
12540 | 0 | ctxt->attsSpecial = oldctxt->attsSpecial; |
12541 | 0 | ctxt->linenumbers = oldctxt->linenumbers; |
12542 | 0 | ctxt->record_info = oldctxt->record_info; |
12543 | 0 | ctxt->node_seq.maximum = oldctxt->node_seq.maximum; |
12544 | 0 | ctxt->node_seq.length = oldctxt->node_seq.length; |
12545 | 0 | ctxt->node_seq.buffer = oldctxt->node_seq.buffer; |
12546 | 0 | } else { |
12547 | | /* |
12548 | | * Doing validity checking on chunk without context |
12549 | | * doesn't make sense |
12550 | | */ |
12551 | 0 | ctxt->_private = NULL; |
12552 | 0 | ctxt->validate = 0; |
12553 | 0 | ctxt->external = 2; |
12554 | 0 | ctxt->loadsubset = 0; |
12555 | 0 | } |
12556 | |
|
12557 | 0 | xmlParseContent(ctxt); |
12558 | |
|
12559 | 0 | if ((RAW == '<') && (NXT(1) == '/')) { |
12560 | 0 | xmlFatalErr(ctxt, XML_ERR_NOT_WELL_BALANCED, NULL); |
12561 | 0 | } else if (RAW != 0) { |
12562 | 0 | xmlFatalErr(ctxt, XML_ERR_EXTRA_CONTENT, NULL); |
12563 | 0 | } |
12564 | 0 | if (ctxt->node != newDoc->children) { |
12565 | 0 | xmlFatalErr(ctxt, XML_ERR_NOT_WELL_BALANCED, NULL); |
12566 | 0 | } |
12567 | |
|
12568 | 0 | if (!ctxt->wellFormed) { |
12569 | 0 | ret = (xmlParserErrors)ctxt->errNo; |
12570 | 0 | if (oldctxt != NULL) { |
12571 | 0 | oldctxt->errNo = ctxt->errNo; |
12572 | 0 | oldctxt->wellFormed = 0; |
12573 | 0 | xmlCopyError(&ctxt->lastError, &oldctxt->lastError); |
12574 | 0 | } |
12575 | 0 | } else { |
12576 | 0 | if (list != NULL) { |
12577 | 0 | xmlNodePtr cur; |
12578 | | |
12579 | | /* |
12580 | | * Return the newly created nodeset after unlinking it from |
12581 | | * they pseudo parent. |
12582 | | */ |
12583 | 0 | cur = newDoc->children->children; |
12584 | 0 | *list = cur; |
12585 | 0 | while (cur != NULL) { |
12586 | 0 | cur->parent = NULL; |
12587 | 0 | cur = cur->next; |
12588 | 0 | } |
12589 | 0 | newDoc->children->children = NULL; |
12590 | 0 | } |
12591 | 0 | ret = XML_ERR_OK; |
12592 | 0 | } |
12593 | | |
12594 | | /* |
12595 | | * Also record the size of the entity parsed |
12596 | | */ |
12597 | 0 | if (ctxt->input != NULL && oldctxt != NULL) { |
12598 | 0 | unsigned long consumed = ctxt->input->consumed; |
12599 | |
|
12600 | 0 | xmlSaturatedAddSizeT(&consumed, ctxt->input->cur - ctxt->input->base); |
12601 | |
|
12602 | 0 | xmlSaturatedAdd(&oldctxt->sizeentities, consumed); |
12603 | 0 | xmlSaturatedAdd(&oldctxt->sizeentities, ctxt->sizeentities); |
12604 | |
|
12605 | 0 | xmlSaturatedAdd(&oldctxt->sizeentcopy, consumed); |
12606 | 0 | xmlSaturatedAdd(&oldctxt->sizeentcopy, ctxt->sizeentcopy); |
12607 | 0 | } |
12608 | |
|
12609 | 0 | if (oldctxt != NULL) { |
12610 | 0 | ctxt->dict = NULL; |
12611 | 0 | ctxt->attsDefault = NULL; |
12612 | 0 | ctxt->attsSpecial = NULL; |
12613 | 0 | oldctxt->nbErrors = ctxt->nbErrors; |
12614 | 0 | oldctxt->nbWarnings = ctxt->nbWarnings; |
12615 | 0 | oldctxt->validate = ctxt->validate; |
12616 | 0 | oldctxt->valid = ctxt->valid; |
12617 | 0 | oldctxt->node_seq.maximum = ctxt->node_seq.maximum; |
12618 | 0 | oldctxt->node_seq.length = ctxt->node_seq.length; |
12619 | 0 | oldctxt->node_seq.buffer = ctxt->node_seq.buffer; |
12620 | 0 | } |
12621 | 0 | ctxt->node_seq.maximum = 0; |
12622 | 0 | ctxt->node_seq.length = 0; |
12623 | 0 | ctxt->node_seq.buffer = NULL; |
12624 | 0 | xmlFreeParserCtxt(ctxt); |
12625 | 0 | newDoc->intSubset = NULL; |
12626 | 0 | newDoc->extSubset = NULL; |
12627 | 0 | xmlFreeDoc(newDoc); |
12628 | |
|
12629 | 0 | return(ret); |
12630 | 0 | } |
12631 | | |
12632 | | #ifdef LIBXML_SAX1_ENABLED |
12633 | | /** |
12634 | | * xmlParseExternalEntity: |
12635 | | * @doc: the document the chunk pertains to |
12636 | | * @sax: the SAX handler block (possibly NULL) |
12637 | | * @user_data: The user data returned on SAX callbacks (possibly NULL) |
12638 | | * @depth: Used for loop detection, use 0 |
12639 | | * @URL: the URL for the entity to load |
12640 | | * @ID: the System ID for the entity to load |
12641 | | * @lst: the return value for the set of parsed nodes |
12642 | | * |
12643 | | * Parse an external general entity |
12644 | | * An external general parsed entity is well-formed if it matches the |
12645 | | * production labeled extParsedEnt. |
12646 | | * |
12647 | | * [78] extParsedEnt ::= TextDecl? content |
12648 | | * |
12649 | | * Returns 0 if the entity is well formed, -1 in case of args problem and |
12650 | | * the parser error code otherwise |
12651 | | */ |
12652 | | |
12653 | | int |
12654 | | xmlParseExternalEntity(xmlDocPtr doc, xmlSAXHandlerPtr sax, void *user_data, |
12655 | | int depth, const xmlChar *URL, const xmlChar *ID, xmlNodePtr *lst) { |
12656 | | return(xmlParseExternalEntityPrivate(doc, NULL, sax, user_data, depth, URL, |
12657 | | ID, lst)); |
12658 | | } |
12659 | | |
12660 | | /** |
12661 | | * xmlParseBalancedChunkMemory: |
12662 | | * @doc: the document the chunk pertains to (must not be NULL) |
12663 | | * @sax: the SAX handler block (possibly NULL) |
12664 | | * @user_data: The user data returned on SAX callbacks (possibly NULL) |
12665 | | * @depth: Used for loop detection, use 0 |
12666 | | * @string: the input string in UTF8 or ISO-Latin (zero terminated) |
12667 | | * @lst: the return value for the set of parsed nodes |
12668 | | * |
12669 | | * Parse a well-balanced chunk of an XML document |
12670 | | * called by the parser |
12671 | | * The allowed sequence for the Well Balanced Chunk is the one defined by |
12672 | | * the content production in the XML grammar: |
12673 | | * |
12674 | | * [43] content ::= (element | CharData | Reference | CDSect | PI | Comment)* |
12675 | | * |
12676 | | * Returns 0 if the chunk is well balanced, -1 in case of args problem and |
12677 | | * the parser error code otherwise |
12678 | | */ |
12679 | | |
12680 | | int |
12681 | | xmlParseBalancedChunkMemory(xmlDocPtr doc, xmlSAXHandlerPtr sax, |
12682 | | void *user_data, int depth, const xmlChar *string, xmlNodePtr *lst) { |
12683 | | return xmlParseBalancedChunkMemoryRecover( doc, sax, user_data, |
12684 | | depth, string, lst, 0 ); |
12685 | | } |
12686 | | #endif /* LIBXML_SAX1_ENABLED */ |
12687 | | |
12688 | | /** |
12689 | | * xmlParseBalancedChunkMemoryInternal: |
12690 | | * @oldctxt: the existing parsing context |
12691 | | * @string: the input string in UTF8 or ISO-Latin (zero terminated) |
12692 | | * @user_data: the user data field for the parser context |
12693 | | * @lst: the return value for the set of parsed nodes |
12694 | | * |
12695 | | * |
12696 | | * Parse a well-balanced chunk of an XML document |
12697 | | * called by the parser |
12698 | | * The allowed sequence for the Well Balanced Chunk is the one defined by |
12699 | | * the content production in the XML grammar: |
12700 | | * |
12701 | | * [43] content ::= (element | CharData | Reference | CDSect | PI | Comment)* |
12702 | | * |
12703 | | * Returns XML_ERR_OK if the chunk is well balanced, and the parser |
12704 | | * error code otherwise |
12705 | | * |
12706 | | * In case recover is set to 1, the nodelist will not be empty even if |
12707 | | * the parsed chunk is not well balanced. |
12708 | | */ |
12709 | | static xmlParserErrors |
12710 | | xmlParseBalancedChunkMemoryInternal(xmlParserCtxtPtr oldctxt, |
12711 | 4 | const xmlChar *string, void *user_data, xmlNodePtr *lst) { |
12712 | 4 | xmlParserCtxtPtr ctxt; |
12713 | 4 | xmlDocPtr newDoc = NULL; |
12714 | 4 | xmlNodePtr newRoot; |
12715 | 4 | xmlSAXHandlerPtr oldsax = NULL; |
12716 | 4 | xmlNodePtr content = NULL; |
12717 | 4 | xmlNodePtr last = NULL; |
12718 | 4 | int size; |
12719 | 4 | xmlParserErrors ret = XML_ERR_OK; |
12720 | 4 | #ifdef SAX2 |
12721 | 4 | int i; |
12722 | 4 | #endif |
12723 | | |
12724 | 4 | if (((oldctxt->depth > 40) && ((oldctxt->options & XML_PARSE_HUGE) == 0)) || |
12725 | 4 | (oldctxt->depth > 100)) { |
12726 | 0 | xmlFatalErrMsg(oldctxt, XML_ERR_ENTITY_LOOP, |
12727 | 0 | "Maximum entity nesting depth exceeded"); |
12728 | 0 | return(XML_ERR_ENTITY_LOOP); |
12729 | 0 | } |
12730 | | |
12731 | | |
12732 | 4 | if (lst != NULL) |
12733 | 4 | *lst = NULL; |
12734 | 4 | if (string == NULL) |
12735 | 0 | return(XML_ERR_INTERNAL_ERROR); |
12736 | | |
12737 | 4 | size = xmlStrlen(string); |
12738 | | |
12739 | 4 | ctxt = xmlCreateMemoryParserCtxt((char *) string, size); |
12740 | 4 | if (ctxt == NULL) return(XML_WAR_UNDECLARED_ENTITY); |
12741 | 4 | ctxt->nbErrors = oldctxt->nbErrors; |
12742 | 4 | ctxt->nbWarnings = oldctxt->nbWarnings; |
12743 | 4 | if (user_data != NULL) |
12744 | 0 | ctxt->userData = user_data; |
12745 | 4 | else |
12746 | 4 | ctxt->userData = ctxt; |
12747 | 4 | if (ctxt->dict != NULL) xmlDictFree(ctxt->dict); |
12748 | 4 | ctxt->dict = oldctxt->dict; |
12749 | 4 | ctxt->input_id = oldctxt->input_id; |
12750 | 4 | ctxt->str_xml = xmlDictLookup(ctxt->dict, BAD_CAST "xml", 3); |
12751 | 4 | ctxt->str_xmlns = xmlDictLookup(ctxt->dict, BAD_CAST "xmlns", 5); |
12752 | 4 | ctxt->str_xml_ns = xmlDictLookup(ctxt->dict, XML_XML_NAMESPACE, 36); |
12753 | | |
12754 | 4 | #ifdef SAX2 |
12755 | | /* propagate namespaces down the entity */ |
12756 | 5 | for (i = 0;i < oldctxt->nsNr;i += 2) { |
12757 | 1 | nsPush(ctxt, oldctxt->nsTab[i], oldctxt->nsTab[i+1]); |
12758 | 1 | } |
12759 | 4 | #endif |
12760 | | |
12761 | 4 | oldsax = ctxt->sax; |
12762 | 4 | ctxt->sax = oldctxt->sax; |
12763 | 4 | xmlDetectSAX2(ctxt); |
12764 | 4 | ctxt->replaceEntities = oldctxt->replaceEntities; |
12765 | 4 | ctxt->options = oldctxt->options; |
12766 | | |
12767 | 4 | ctxt->_private = oldctxt->_private; |
12768 | 4 | if (oldctxt->myDoc == NULL) { |
12769 | 0 | newDoc = xmlNewDoc(BAD_CAST "1.0"); |
12770 | 0 | if (newDoc == NULL) { |
12771 | 0 | ctxt->sax = oldsax; |
12772 | 0 | ctxt->dict = NULL; |
12773 | 0 | xmlFreeParserCtxt(ctxt); |
12774 | 0 | return(XML_ERR_INTERNAL_ERROR); |
12775 | 0 | } |
12776 | 0 | newDoc->properties = XML_DOC_INTERNAL; |
12777 | 0 | newDoc->dict = ctxt->dict; |
12778 | 0 | xmlDictReference(newDoc->dict); |
12779 | 0 | ctxt->myDoc = newDoc; |
12780 | 4 | } else { |
12781 | 4 | ctxt->myDoc = oldctxt->myDoc; |
12782 | 4 | content = ctxt->myDoc->children; |
12783 | 4 | last = ctxt->myDoc->last; |
12784 | 4 | } |
12785 | 4 | newRoot = xmlNewDocNode(ctxt->myDoc, NULL, BAD_CAST "pseudoroot", NULL); |
12786 | 4 | if (newRoot == NULL) { |
12787 | 0 | ctxt->sax = oldsax; |
12788 | 0 | ctxt->dict = NULL; |
12789 | 0 | xmlFreeParserCtxt(ctxt); |
12790 | 0 | if (newDoc != NULL) { |
12791 | 0 | xmlFreeDoc(newDoc); |
12792 | 0 | } |
12793 | 0 | return(XML_ERR_INTERNAL_ERROR); |
12794 | 0 | } |
12795 | 4 | ctxt->myDoc->children = NULL; |
12796 | 4 | ctxt->myDoc->last = NULL; |
12797 | 4 | xmlAddChild((xmlNodePtr) ctxt->myDoc, newRoot); |
12798 | 4 | nodePush(ctxt, ctxt->myDoc->children); |
12799 | 4 | ctxt->instate = XML_PARSER_CONTENT; |
12800 | 4 | ctxt->depth = oldctxt->depth; |
12801 | | |
12802 | 4 | ctxt->validate = 0; |
12803 | 4 | ctxt->loadsubset = oldctxt->loadsubset; |
12804 | 4 | if ((oldctxt->validate) || (oldctxt->replaceEntities != 0)) { |
12805 | | /* |
12806 | | * ID/IDREF registration will be done in xmlValidateElement below |
12807 | | */ |
12808 | 0 | ctxt->loadsubset |= XML_SKIP_IDS; |
12809 | 0 | } |
12810 | 4 | ctxt->dictNames = oldctxt->dictNames; |
12811 | 4 | ctxt->attsDefault = oldctxt->attsDefault; |
12812 | 4 | ctxt->attsSpecial = oldctxt->attsSpecial; |
12813 | | |
12814 | 4 | xmlParseContent(ctxt); |
12815 | 4 | if ((RAW == '<') && (NXT(1) == '/')) { |
12816 | 0 | xmlFatalErr(ctxt, XML_ERR_NOT_WELL_BALANCED, NULL); |
12817 | 4 | } else if (RAW != 0) { |
12818 | 0 | xmlFatalErr(ctxt, XML_ERR_EXTRA_CONTENT, NULL); |
12819 | 0 | } |
12820 | 4 | if (ctxt->node != ctxt->myDoc->children) { |
12821 | 2 | xmlFatalErr(ctxt, XML_ERR_NOT_WELL_BALANCED, NULL); |
12822 | 2 | } |
12823 | | |
12824 | 4 | if (!ctxt->wellFormed) { |
12825 | 3 | ret = (xmlParserErrors)ctxt->errNo; |
12826 | 3 | oldctxt->errNo = ctxt->errNo; |
12827 | 3 | oldctxt->wellFormed = 0; |
12828 | 3 | xmlCopyError(&ctxt->lastError, &oldctxt->lastError); |
12829 | 3 | } else { |
12830 | 1 | ret = XML_ERR_OK; |
12831 | 1 | } |
12832 | | |
12833 | 4 | if ((lst != NULL) && (ret == XML_ERR_OK)) { |
12834 | 1 | xmlNodePtr cur; |
12835 | | |
12836 | | /* |
12837 | | * Return the newly created nodeset after unlinking it from |
12838 | | * they pseudo parent. |
12839 | | */ |
12840 | 1 | cur = ctxt->myDoc->children->children; |
12841 | 1 | *lst = cur; |
12842 | 3 | while (cur != NULL) { |
12843 | | #ifdef LIBXML_VALID_ENABLED |
12844 | | if ((oldctxt->validate) && (oldctxt->wellFormed) && |
12845 | | (oldctxt->myDoc) && (oldctxt->myDoc->intSubset) && |
12846 | | (cur->type == XML_ELEMENT_NODE)) { |
12847 | | oldctxt->valid &= xmlValidateElement(&oldctxt->vctxt, |
12848 | | oldctxt->myDoc, cur); |
12849 | | } |
12850 | | #endif /* LIBXML_VALID_ENABLED */ |
12851 | 2 | cur->parent = NULL; |
12852 | 2 | cur = cur->next; |
12853 | 2 | } |
12854 | 1 | ctxt->myDoc->children->children = NULL; |
12855 | 1 | } |
12856 | 4 | if (ctxt->myDoc != NULL) { |
12857 | 4 | xmlFreeNode(ctxt->myDoc->children); |
12858 | 4 | ctxt->myDoc->children = content; |
12859 | 4 | ctxt->myDoc->last = last; |
12860 | 4 | } |
12861 | | |
12862 | | /* |
12863 | | * Also record the size of the entity parsed |
12864 | | */ |
12865 | 4 | if (ctxt->input != NULL && oldctxt != NULL) { |
12866 | 4 | unsigned long consumed = ctxt->input->consumed; |
12867 | | |
12868 | 4 | xmlSaturatedAddSizeT(&consumed, ctxt->input->cur - ctxt->input->base); |
12869 | | |
12870 | 4 | xmlSaturatedAdd(&oldctxt->sizeentcopy, consumed); |
12871 | 4 | xmlSaturatedAdd(&oldctxt->sizeentcopy, ctxt->sizeentcopy); |
12872 | 4 | } |
12873 | | |
12874 | 4 | oldctxt->nbErrors = ctxt->nbErrors; |
12875 | 4 | oldctxt->nbWarnings = ctxt->nbWarnings; |
12876 | 4 | ctxt->sax = oldsax; |
12877 | 4 | ctxt->dict = NULL; |
12878 | 4 | ctxt->attsDefault = NULL; |
12879 | 4 | ctxt->attsSpecial = NULL; |
12880 | 4 | xmlFreeParserCtxt(ctxt); |
12881 | 4 | if (newDoc != NULL) { |
12882 | 0 | xmlFreeDoc(newDoc); |
12883 | 0 | } |
12884 | | |
12885 | 4 | return(ret); |
12886 | 4 | } |
12887 | | |
12888 | | /** |
12889 | | * xmlParseInNodeContext: |
12890 | | * @node: the context node |
12891 | | * @data: the input string |
12892 | | * @datalen: the input string length in bytes |
12893 | | * @options: a combination of xmlParserOption |
12894 | | * @lst: the return value for the set of parsed nodes |
12895 | | * |
12896 | | * Parse a well-balanced chunk of an XML document |
12897 | | * within the context (DTD, namespaces, etc ...) of the given node. |
12898 | | * |
12899 | | * The allowed sequence for the data is a Well Balanced Chunk defined by |
12900 | | * the content production in the XML grammar: |
12901 | | * |
12902 | | * [43] content ::= (element | CharData | Reference | CDSect | PI | Comment)* |
12903 | | * |
12904 | | * Returns XML_ERR_OK if the chunk is well balanced, and the parser |
12905 | | * error code otherwise |
12906 | | */ |
12907 | | xmlParserErrors |
12908 | | xmlParseInNodeContext(xmlNodePtr node, const char *data, int datalen, |
12909 | 0 | int options, xmlNodePtr *lst) { |
12910 | 0 | #ifdef SAX2 |
12911 | 0 | xmlParserCtxtPtr ctxt; |
12912 | 0 | xmlDocPtr doc = NULL; |
12913 | 0 | xmlNodePtr fake, cur; |
12914 | 0 | int nsnr = 0; |
12915 | |
|
12916 | 0 | xmlParserErrors ret = XML_ERR_OK; |
12917 | | |
12918 | | /* |
12919 | | * check all input parameters, grab the document |
12920 | | */ |
12921 | 0 | if ((lst == NULL) || (node == NULL) || (data == NULL) || (datalen < 0)) |
12922 | 0 | return(XML_ERR_INTERNAL_ERROR); |
12923 | 0 | switch (node->type) { |
12924 | 0 | case XML_ELEMENT_NODE: |
12925 | 0 | case XML_ATTRIBUTE_NODE: |
12926 | 0 | case XML_TEXT_NODE: |
12927 | 0 | case XML_CDATA_SECTION_NODE: |
12928 | 0 | case XML_ENTITY_REF_NODE: |
12929 | 0 | case XML_PI_NODE: |
12930 | 0 | case XML_COMMENT_NODE: |
12931 | 0 | case XML_DOCUMENT_NODE: |
12932 | 0 | case XML_HTML_DOCUMENT_NODE: |
12933 | 0 | break; |
12934 | 0 | default: |
12935 | 0 | return(XML_ERR_INTERNAL_ERROR); |
12936 | |
|
12937 | 0 | } |
12938 | 0 | while ((node != NULL) && (node->type != XML_ELEMENT_NODE) && |
12939 | 0 | (node->type != XML_DOCUMENT_NODE) && |
12940 | 0 | (node->type != XML_HTML_DOCUMENT_NODE)) |
12941 | 0 | node = node->parent; |
12942 | 0 | if (node == NULL) |
12943 | 0 | return(XML_ERR_INTERNAL_ERROR); |
12944 | 0 | if (node->type == XML_ELEMENT_NODE) |
12945 | 0 | doc = node->doc; |
12946 | 0 | else |
12947 | 0 | doc = (xmlDocPtr) node; |
12948 | 0 | if (doc == NULL) |
12949 | 0 | return(XML_ERR_INTERNAL_ERROR); |
12950 | | |
12951 | | /* |
12952 | | * allocate a context and set-up everything not related to the |
12953 | | * node position in the tree |
12954 | | */ |
12955 | 0 | if (doc->type == XML_DOCUMENT_NODE) |
12956 | 0 | ctxt = xmlCreateMemoryParserCtxt((char *) data, datalen); |
12957 | 0 | #ifdef LIBXML_HTML_ENABLED |
12958 | 0 | else if (doc->type == XML_HTML_DOCUMENT_NODE) { |
12959 | 0 | ctxt = htmlCreateMemoryParserCtxt((char *) data, datalen); |
12960 | | /* |
12961 | | * When parsing in context, it makes no sense to add implied |
12962 | | * elements like html/body/etc... |
12963 | | */ |
12964 | 0 | options |= HTML_PARSE_NOIMPLIED; |
12965 | 0 | } |
12966 | 0 | #endif |
12967 | 0 | else |
12968 | 0 | return(XML_ERR_INTERNAL_ERROR); |
12969 | | |
12970 | 0 | if (ctxt == NULL) |
12971 | 0 | return(XML_ERR_NO_MEMORY); |
12972 | | |
12973 | | /* |
12974 | | * Use input doc's dict if present, else assure XML_PARSE_NODICT is set. |
12975 | | * We need a dictionary for xmlDetectSAX2, so if there's no doc dict |
12976 | | * we must wait until the last moment to free the original one. |
12977 | | */ |
12978 | 0 | if (doc->dict != NULL) { |
12979 | 0 | if (ctxt->dict != NULL) |
12980 | 0 | xmlDictFree(ctxt->dict); |
12981 | 0 | ctxt->dict = doc->dict; |
12982 | 0 | } else |
12983 | 0 | options |= XML_PARSE_NODICT; |
12984 | |
|
12985 | 0 | if (doc->encoding != NULL) { |
12986 | 0 | xmlCharEncodingHandlerPtr hdlr; |
12987 | |
|
12988 | 0 | if (ctxt->encoding != NULL) |
12989 | 0 | xmlFree((xmlChar *) ctxt->encoding); |
12990 | 0 | ctxt->encoding = xmlStrdup((const xmlChar *) doc->encoding); |
12991 | |
|
12992 | 0 | hdlr = xmlFindCharEncodingHandler((const char *) doc->encoding); |
12993 | 0 | if (hdlr != NULL) { |
12994 | 0 | xmlSwitchToEncoding(ctxt, hdlr); |
12995 | 0 | } else { |
12996 | 0 | return(XML_ERR_UNSUPPORTED_ENCODING); |
12997 | 0 | } |
12998 | 0 | } |
12999 | | |
13000 | 0 | xmlCtxtUseOptionsInternal(ctxt, options, NULL); |
13001 | 0 | xmlDetectSAX2(ctxt); |
13002 | 0 | ctxt->myDoc = doc; |
13003 | | /* parsing in context, i.e. as within existing content */ |
13004 | 0 | ctxt->input_id = 2; |
13005 | 0 | ctxt->instate = XML_PARSER_CONTENT; |
13006 | |
|
13007 | 0 | fake = xmlNewDocComment(node->doc, NULL); |
13008 | 0 | if (fake == NULL) { |
13009 | 0 | xmlFreeParserCtxt(ctxt); |
13010 | 0 | return(XML_ERR_NO_MEMORY); |
13011 | 0 | } |
13012 | 0 | xmlAddChild(node, fake); |
13013 | |
|
13014 | 0 | if (node->type == XML_ELEMENT_NODE) { |
13015 | 0 | nodePush(ctxt, node); |
13016 | | /* |
13017 | | * initialize the SAX2 namespaces stack |
13018 | | */ |
13019 | 0 | cur = node; |
13020 | 0 | while ((cur != NULL) && (cur->type == XML_ELEMENT_NODE)) { |
13021 | 0 | xmlNsPtr ns = cur->nsDef; |
13022 | 0 | const xmlChar *iprefix, *ihref; |
13023 | |
|
13024 | 0 | while (ns != NULL) { |
13025 | 0 | if (ctxt->dict) { |
13026 | 0 | iprefix = xmlDictLookup(ctxt->dict, ns->prefix, -1); |
13027 | 0 | ihref = xmlDictLookup(ctxt->dict, ns->href, -1); |
13028 | 0 | } else { |
13029 | 0 | iprefix = ns->prefix; |
13030 | 0 | ihref = ns->href; |
13031 | 0 | } |
13032 | |
|
13033 | 0 | if (xmlGetNamespace(ctxt, iprefix) == NULL) { |
13034 | 0 | nsPush(ctxt, iprefix, ihref); |
13035 | 0 | nsnr++; |
13036 | 0 | } |
13037 | 0 | ns = ns->next; |
13038 | 0 | } |
13039 | 0 | cur = cur->parent; |
13040 | 0 | } |
13041 | 0 | } |
13042 | |
|
13043 | 0 | if ((ctxt->validate) || (ctxt->replaceEntities != 0)) { |
13044 | | /* |
13045 | | * ID/IDREF registration will be done in xmlValidateElement below |
13046 | | */ |
13047 | 0 | ctxt->loadsubset |= XML_SKIP_IDS; |
13048 | 0 | } |
13049 | |
|
13050 | 0 | #ifdef LIBXML_HTML_ENABLED |
13051 | 0 | if (doc->type == XML_HTML_DOCUMENT_NODE) |
13052 | 0 | __htmlParseContent(ctxt); |
13053 | 0 | else |
13054 | 0 | #endif |
13055 | 0 | xmlParseContent(ctxt); |
13056 | |
|
13057 | 0 | nsPop(ctxt, nsnr); |
13058 | 0 | if ((RAW == '<') && (NXT(1) == '/')) { |
13059 | 0 | xmlFatalErr(ctxt, XML_ERR_NOT_WELL_BALANCED, NULL); |
13060 | 0 | } else if (RAW != 0) { |
13061 | 0 | xmlFatalErr(ctxt, XML_ERR_EXTRA_CONTENT, NULL); |
13062 | 0 | } |
13063 | 0 | if ((ctxt->node != NULL) && (ctxt->node != node)) { |
13064 | 0 | xmlFatalErr(ctxt, XML_ERR_NOT_WELL_BALANCED, NULL); |
13065 | 0 | ctxt->wellFormed = 0; |
13066 | 0 | } |
13067 | |
|
13068 | 0 | if (!ctxt->wellFormed) { |
13069 | 0 | if (ctxt->errNo == 0) |
13070 | 0 | ret = XML_ERR_INTERNAL_ERROR; |
13071 | 0 | else |
13072 | 0 | ret = (xmlParserErrors)ctxt->errNo; |
13073 | 0 | } else { |
13074 | 0 | ret = XML_ERR_OK; |
13075 | 0 | } |
13076 | | |
13077 | | /* |
13078 | | * Return the newly created nodeset after unlinking it from |
13079 | | * the pseudo sibling. |
13080 | | */ |
13081 | |
|
13082 | 0 | cur = fake->next; |
13083 | 0 | fake->next = NULL; |
13084 | 0 | node->last = fake; |
13085 | |
|
13086 | 0 | if (cur != NULL) { |
13087 | 0 | cur->prev = NULL; |
13088 | 0 | } |
13089 | |
|
13090 | 0 | *lst = cur; |
13091 | |
|
13092 | 0 | while (cur != NULL) { |
13093 | 0 | cur->parent = NULL; |
13094 | 0 | cur = cur->next; |
13095 | 0 | } |
13096 | |
|
13097 | 0 | xmlUnlinkNode(fake); |
13098 | 0 | xmlFreeNode(fake); |
13099 | | |
13100 | |
|
13101 | 0 | if (ret != XML_ERR_OK) { |
13102 | 0 | xmlFreeNodeList(*lst); |
13103 | 0 | *lst = NULL; |
13104 | 0 | } |
13105 | |
|
13106 | 0 | if (doc->dict != NULL) |
13107 | 0 | ctxt->dict = NULL; |
13108 | 0 | xmlFreeParserCtxt(ctxt); |
13109 | |
|
13110 | 0 | return(ret); |
13111 | | #else /* !SAX2 */ |
13112 | | return(XML_ERR_INTERNAL_ERROR); |
13113 | | #endif |
13114 | 0 | } |
13115 | | |
13116 | | #ifdef LIBXML_SAX1_ENABLED |
13117 | | /** |
13118 | | * xmlParseBalancedChunkMemoryRecover: |
13119 | | * @doc: the document the chunk pertains to (must not be NULL) |
13120 | | * @sax: the SAX handler block (possibly NULL) |
13121 | | * @user_data: The user data returned on SAX callbacks (possibly NULL) |
13122 | | * @depth: Used for loop detection, use 0 |
13123 | | * @string: the input string in UTF8 or ISO-Latin (zero terminated) |
13124 | | * @lst: the return value for the set of parsed nodes |
13125 | | * @recover: return nodes even if the data is broken (use 0) |
13126 | | * |
13127 | | * |
13128 | | * Parse a well-balanced chunk of an XML document |
13129 | | * called by the parser |
13130 | | * The allowed sequence for the Well Balanced Chunk is the one defined by |
13131 | | * the content production in the XML grammar: |
13132 | | * |
13133 | | * [43] content ::= (element | CharData | Reference | CDSect | PI | Comment)* |
13134 | | * |
13135 | | * Returns 0 if the chunk is well balanced, -1 in case of args problem and |
13136 | | * the parser error code otherwise |
13137 | | * |
13138 | | * In case recover is set to 1, the nodelist will not be empty even if |
13139 | | * the parsed chunk is not well balanced, assuming the parsing succeeded to |
13140 | | * some extent. |
13141 | | */ |
13142 | | int |
13143 | | xmlParseBalancedChunkMemoryRecover(xmlDocPtr doc, xmlSAXHandlerPtr sax, |
13144 | | void *user_data, int depth, const xmlChar *string, xmlNodePtr *lst, |
13145 | | int recover) { |
13146 | | xmlParserCtxtPtr ctxt; |
13147 | | xmlDocPtr newDoc; |
13148 | | xmlSAXHandlerPtr oldsax = NULL; |
13149 | | xmlNodePtr content, newRoot; |
13150 | | int size; |
13151 | | int ret = 0; |
13152 | | |
13153 | | if (depth > 40) { |
13154 | | return(XML_ERR_ENTITY_LOOP); |
13155 | | } |
13156 | | |
13157 | | |
13158 | | if (lst != NULL) |
13159 | | *lst = NULL; |
13160 | | if (string == NULL) |
13161 | | return(-1); |
13162 | | |
13163 | | size = xmlStrlen(string); |
13164 | | |
13165 | | ctxt = xmlCreateMemoryParserCtxt((char *) string, size); |
13166 | | if (ctxt == NULL) return(-1); |
13167 | | ctxt->userData = ctxt; |
13168 | | if (sax != NULL) { |
13169 | | oldsax = ctxt->sax; |
13170 | | ctxt->sax = sax; |
13171 | | if (user_data != NULL) |
13172 | | ctxt->userData = user_data; |
13173 | | } |
13174 | | newDoc = xmlNewDoc(BAD_CAST "1.0"); |
13175 | | if (newDoc == NULL) { |
13176 | | xmlFreeParserCtxt(ctxt); |
13177 | | return(-1); |
13178 | | } |
13179 | | newDoc->properties = XML_DOC_INTERNAL; |
13180 | | if ((doc != NULL) && (doc->dict != NULL)) { |
13181 | | xmlDictFree(ctxt->dict); |
13182 | | ctxt->dict = doc->dict; |
13183 | | xmlDictReference(ctxt->dict); |
13184 | | ctxt->str_xml = xmlDictLookup(ctxt->dict, BAD_CAST "xml", 3); |
13185 | | ctxt->str_xmlns = xmlDictLookup(ctxt->dict, BAD_CAST "xmlns", 5); |
13186 | | ctxt->str_xml_ns = xmlDictLookup(ctxt->dict, XML_XML_NAMESPACE, 36); |
13187 | | ctxt->dictNames = 1; |
13188 | | } else { |
13189 | | xmlCtxtUseOptionsInternal(ctxt, XML_PARSE_NODICT, NULL); |
13190 | | } |
13191 | | /* doc == NULL is only supported for historic reasons */ |
13192 | | if (doc != NULL) { |
13193 | | newDoc->intSubset = doc->intSubset; |
13194 | | newDoc->extSubset = doc->extSubset; |
13195 | | } |
13196 | | newRoot = xmlNewDocNode(newDoc, NULL, BAD_CAST "pseudoroot", NULL); |
13197 | | if (newRoot == NULL) { |
13198 | | if (sax != NULL) |
13199 | | ctxt->sax = oldsax; |
13200 | | xmlFreeParserCtxt(ctxt); |
13201 | | newDoc->intSubset = NULL; |
13202 | | newDoc->extSubset = NULL; |
13203 | | xmlFreeDoc(newDoc); |
13204 | | return(-1); |
13205 | | } |
13206 | | xmlAddChild((xmlNodePtr) newDoc, newRoot); |
13207 | | nodePush(ctxt, newRoot); |
13208 | | /* doc == NULL is only supported for historic reasons */ |
13209 | | if (doc == NULL) { |
13210 | | ctxt->myDoc = newDoc; |
13211 | | } else { |
13212 | | ctxt->myDoc = newDoc; |
13213 | | newDoc->children->doc = doc; |
13214 | | /* Ensure that doc has XML spec namespace */ |
13215 | | xmlSearchNsByHref(doc, (xmlNodePtr)doc, XML_XML_NAMESPACE); |
13216 | | newDoc->oldNs = doc->oldNs; |
13217 | | } |
13218 | | ctxt->instate = XML_PARSER_CONTENT; |
13219 | | ctxt->input_id = 2; |
13220 | | ctxt->depth = depth; |
13221 | | |
13222 | | /* |
13223 | | * Doing validity checking on chunk doesn't make sense |
13224 | | */ |
13225 | | ctxt->validate = 0; |
13226 | | ctxt->loadsubset = 0; |
13227 | | xmlDetectSAX2(ctxt); |
13228 | | |
13229 | | if ( doc != NULL ){ |
13230 | | content = doc->children; |
13231 | | doc->children = NULL; |
13232 | | xmlParseContent(ctxt); |
13233 | | doc->children = content; |
13234 | | } |
13235 | | else { |
13236 | | xmlParseContent(ctxt); |
13237 | | } |
13238 | | if ((RAW == '<') && (NXT(1) == '/')) { |
13239 | | xmlFatalErr(ctxt, XML_ERR_NOT_WELL_BALANCED, NULL); |
13240 | | } else if (RAW != 0) { |
13241 | | xmlFatalErr(ctxt, XML_ERR_EXTRA_CONTENT, NULL); |
13242 | | } |
13243 | | if (ctxt->node != newDoc->children) { |
13244 | | xmlFatalErr(ctxt, XML_ERR_NOT_WELL_BALANCED, NULL); |
13245 | | } |
13246 | | |
13247 | | if (!ctxt->wellFormed) { |
13248 | | if (ctxt->errNo == 0) |
13249 | | ret = 1; |
13250 | | else |
13251 | | ret = ctxt->errNo; |
13252 | | } else { |
13253 | | ret = 0; |
13254 | | } |
13255 | | |
13256 | | if ((lst != NULL) && ((ret == 0) || (recover == 1))) { |
13257 | | xmlNodePtr cur; |
13258 | | |
13259 | | /* |
13260 | | * Return the newly created nodeset after unlinking it from |
13261 | | * they pseudo parent. |
13262 | | */ |
13263 | | cur = newDoc->children->children; |
13264 | | *lst = cur; |
13265 | | while (cur != NULL) { |
13266 | | xmlSetTreeDoc(cur, doc); |
13267 | | cur->parent = NULL; |
13268 | | cur = cur->next; |
13269 | | } |
13270 | | newDoc->children->children = NULL; |
13271 | | } |
13272 | | |
13273 | | if (sax != NULL) |
13274 | | ctxt->sax = oldsax; |
13275 | | xmlFreeParserCtxt(ctxt); |
13276 | | newDoc->intSubset = NULL; |
13277 | | newDoc->extSubset = NULL; |
13278 | | /* This leaks the namespace list if doc == NULL */ |
13279 | | newDoc->oldNs = NULL; |
13280 | | xmlFreeDoc(newDoc); |
13281 | | |
13282 | | return(ret); |
13283 | | } |
13284 | | |
13285 | | /** |
13286 | | * xmlSAXParseEntity: |
13287 | | * @sax: the SAX handler block |
13288 | | * @filename: the filename |
13289 | | * |
13290 | | * DEPRECATED: Don't use. |
13291 | | * |
13292 | | * parse an XML external entity out of context and build a tree. |
13293 | | * It use the given SAX function block to handle the parsing callback. |
13294 | | * If sax is NULL, fallback to the default DOM tree building routines. |
13295 | | * |
13296 | | * [78] extParsedEnt ::= TextDecl? content |
13297 | | * |
13298 | | * This correspond to a "Well Balanced" chunk |
13299 | | * |
13300 | | * Returns the resulting document tree |
13301 | | */ |
13302 | | |
13303 | | xmlDocPtr |
13304 | | xmlSAXParseEntity(xmlSAXHandlerPtr sax, const char *filename) { |
13305 | | xmlDocPtr ret; |
13306 | | xmlParserCtxtPtr ctxt; |
13307 | | |
13308 | | ctxt = xmlCreateFileParserCtxt(filename); |
13309 | | if (ctxt == NULL) { |
13310 | | return(NULL); |
13311 | | } |
13312 | | if (sax != NULL) { |
13313 | | if (ctxt->sax != NULL) |
13314 | | xmlFree(ctxt->sax); |
13315 | | ctxt->sax = sax; |
13316 | | ctxt->userData = NULL; |
13317 | | } |
13318 | | |
13319 | | xmlParseExtParsedEnt(ctxt); |
13320 | | |
13321 | | if (ctxt->wellFormed) |
13322 | | ret = ctxt->myDoc; |
13323 | | else { |
13324 | | ret = NULL; |
13325 | | xmlFreeDoc(ctxt->myDoc); |
13326 | | ctxt->myDoc = NULL; |
13327 | | } |
13328 | | if (sax != NULL) |
13329 | | ctxt->sax = NULL; |
13330 | | xmlFreeParserCtxt(ctxt); |
13331 | | |
13332 | | return(ret); |
13333 | | } |
13334 | | |
13335 | | /** |
13336 | | * xmlParseEntity: |
13337 | | * @filename: the filename |
13338 | | * |
13339 | | * parse an XML external entity out of context and build a tree. |
13340 | | * |
13341 | | * [78] extParsedEnt ::= TextDecl? content |
13342 | | * |
13343 | | * This correspond to a "Well Balanced" chunk |
13344 | | * |
13345 | | * Returns the resulting document tree |
13346 | | */ |
13347 | | |
13348 | | xmlDocPtr |
13349 | | xmlParseEntity(const char *filename) { |
13350 | | return(xmlSAXParseEntity(NULL, filename)); |
13351 | | } |
13352 | | #endif /* LIBXML_SAX1_ENABLED */ |
13353 | | |
13354 | | /** |
13355 | | * xmlCreateEntityParserCtxtInternal: |
13356 | | * @URL: the entity URL |
13357 | | * @ID: the entity PUBLIC ID |
13358 | | * @base: a possible base for the target URI |
13359 | | * @pctx: parser context used to set options on new context |
13360 | | * |
13361 | | * Create a parser context for an external entity |
13362 | | * Automatic support for ZLIB/Compress compressed document is provided |
13363 | | * by default if found at compile-time. |
13364 | | * |
13365 | | * Returns the new parser context or NULL |
13366 | | */ |
13367 | | static xmlParserCtxtPtr |
13368 | | xmlCreateEntityParserCtxtInternal(xmlSAXHandlerPtr sax, void *userData, |
13369 | | const xmlChar *URL, const xmlChar *ID, const xmlChar *base, |
13370 | 0 | xmlParserCtxtPtr pctx) { |
13371 | 0 | xmlParserCtxtPtr ctxt; |
13372 | 0 | xmlParserInputPtr inputStream; |
13373 | 0 | char *directory = NULL; |
13374 | 0 | xmlChar *uri; |
13375 | |
|
13376 | 0 | ctxt = xmlNewSAXParserCtxt(sax, userData); |
13377 | 0 | if (ctxt == NULL) { |
13378 | 0 | return(NULL); |
13379 | 0 | } |
13380 | | |
13381 | 0 | if (pctx != NULL) { |
13382 | 0 | ctxt->options = pctx->options; |
13383 | 0 | ctxt->_private = pctx->_private; |
13384 | 0 | ctxt->input_id = pctx->input_id; |
13385 | 0 | } |
13386 | | |
13387 | | /* Don't read from stdin. */ |
13388 | 0 | if (xmlStrcmp(URL, BAD_CAST "-") == 0) |
13389 | 0 | URL = BAD_CAST "./-"; |
13390 | |
|
13391 | 0 | uri = xmlBuildURI(URL, base); |
13392 | |
|
13393 | 0 | if (uri == NULL) { |
13394 | 0 | inputStream = xmlLoadExternalEntity((char *)URL, (char *)ID, ctxt); |
13395 | 0 | if (inputStream == NULL) { |
13396 | 0 | xmlFreeParserCtxt(ctxt); |
13397 | 0 | return(NULL); |
13398 | 0 | } |
13399 | | |
13400 | 0 | inputPush(ctxt, inputStream); |
13401 | |
|
13402 | 0 | if ((ctxt->directory == NULL) && (directory == NULL)) |
13403 | 0 | directory = xmlParserGetDirectory((char *)URL); |
13404 | 0 | if ((ctxt->directory == NULL) && (directory != NULL)) |
13405 | 0 | ctxt->directory = directory; |
13406 | 0 | } else { |
13407 | 0 | inputStream = xmlLoadExternalEntity((char *)uri, (char *)ID, ctxt); |
13408 | 0 | if (inputStream == NULL) { |
13409 | 0 | xmlFree(uri); |
13410 | 0 | xmlFreeParserCtxt(ctxt); |
13411 | 0 | return(NULL); |
13412 | 0 | } |
13413 | | |
13414 | 0 | inputPush(ctxt, inputStream); |
13415 | |
|
13416 | 0 | if ((ctxt->directory == NULL) && (directory == NULL)) |
13417 | 0 | directory = xmlParserGetDirectory((char *)uri); |
13418 | 0 | if ((ctxt->directory == NULL) && (directory != NULL)) |
13419 | 0 | ctxt->directory = directory; |
13420 | 0 | xmlFree(uri); |
13421 | 0 | } |
13422 | 0 | return(ctxt); |
13423 | 0 | } |
13424 | | |
13425 | | /** |
13426 | | * xmlCreateEntityParserCtxt: |
13427 | | * @URL: the entity URL |
13428 | | * @ID: the entity PUBLIC ID |
13429 | | * @base: a possible base for the target URI |
13430 | | * |
13431 | | * Create a parser context for an external entity |
13432 | | * Automatic support for ZLIB/Compress compressed document is provided |
13433 | | * by default if found at compile-time. |
13434 | | * |
13435 | | * Returns the new parser context or NULL |
13436 | | */ |
13437 | | xmlParserCtxtPtr |
13438 | | xmlCreateEntityParserCtxt(const xmlChar *URL, const xmlChar *ID, |
13439 | 0 | const xmlChar *base) { |
13440 | 0 | return xmlCreateEntityParserCtxtInternal(NULL, NULL, URL, ID, base, NULL); |
13441 | |
|
13442 | 0 | } |
13443 | | |
13444 | | /************************************************************************ |
13445 | | * * |
13446 | | * Front ends when parsing from a file * |
13447 | | * * |
13448 | | ************************************************************************/ |
13449 | | |
13450 | | /** |
13451 | | * xmlCreateURLParserCtxt: |
13452 | | * @filename: the filename or URL |
13453 | | * @options: a combination of xmlParserOption |
13454 | | * |
13455 | | * Create a parser context for a file or URL content. |
13456 | | * Automatic support for ZLIB/Compress compressed document is provided |
13457 | | * by default if found at compile-time and for file accesses |
13458 | | * |
13459 | | * Returns the new parser context or NULL |
13460 | | */ |
13461 | | xmlParserCtxtPtr |
13462 | | xmlCreateURLParserCtxt(const char *filename, int options) |
13463 | 0 | { |
13464 | 0 | xmlParserCtxtPtr ctxt; |
13465 | 0 | xmlParserInputPtr inputStream; |
13466 | 0 | char *directory = NULL; |
13467 | |
|
13468 | 0 | ctxt = xmlNewParserCtxt(); |
13469 | 0 | if (ctxt == NULL) { |
13470 | 0 | xmlErrMemory(NULL, "cannot allocate parser context"); |
13471 | 0 | return(NULL); |
13472 | 0 | } |
13473 | | |
13474 | 0 | if (options) |
13475 | 0 | xmlCtxtUseOptionsInternal(ctxt, options, NULL); |
13476 | 0 | ctxt->linenumbers = 1; |
13477 | |
|
13478 | 0 | inputStream = xmlLoadExternalEntity(filename, NULL, ctxt); |
13479 | 0 | if (inputStream == NULL) { |
13480 | 0 | xmlFreeParserCtxt(ctxt); |
13481 | 0 | return(NULL); |
13482 | 0 | } |
13483 | | |
13484 | 0 | inputPush(ctxt, inputStream); |
13485 | 0 | if ((ctxt->directory == NULL) && (directory == NULL)) |
13486 | 0 | directory = xmlParserGetDirectory(filename); |
13487 | 0 | if ((ctxt->directory == NULL) && (directory != NULL)) |
13488 | 0 | ctxt->directory = directory; |
13489 | |
|
13490 | 0 | return(ctxt); |
13491 | 0 | } |
13492 | | |
13493 | | /** |
13494 | | * xmlCreateFileParserCtxt: |
13495 | | * @filename: the filename |
13496 | | * |
13497 | | * Create a parser context for a file content. |
13498 | | * Automatic support for ZLIB/Compress compressed document is provided |
13499 | | * by default if found at compile-time. |
13500 | | * |
13501 | | * Returns the new parser context or NULL |
13502 | | */ |
13503 | | xmlParserCtxtPtr |
13504 | | xmlCreateFileParserCtxt(const char *filename) |
13505 | 0 | { |
13506 | 0 | return(xmlCreateURLParserCtxt(filename, 0)); |
13507 | 0 | } |
13508 | | |
13509 | | #ifdef LIBXML_SAX1_ENABLED |
13510 | | /** |
13511 | | * xmlSAXParseFileWithData: |
13512 | | * @sax: the SAX handler block |
13513 | | * @filename: the filename |
13514 | | * @recovery: work in recovery mode, i.e. tries to read no Well Formed |
13515 | | * documents |
13516 | | * @data: the userdata |
13517 | | * |
13518 | | * DEPRECATED: Use xmlNewSAXParserCtxt and xmlCtxtReadFile. |
13519 | | * |
13520 | | * parse an XML file and build a tree. Automatic support for ZLIB/Compress |
13521 | | * compressed document is provided by default if found at compile-time. |
13522 | | * It use the given SAX function block to handle the parsing callback. |
13523 | | * If sax is NULL, fallback to the default DOM tree building routines. |
13524 | | * |
13525 | | * User data (void *) is stored within the parser context in the |
13526 | | * context's _private member, so it is available nearly everywhere in libxml |
13527 | | * |
13528 | | * Returns the resulting document tree |
13529 | | */ |
13530 | | |
13531 | | xmlDocPtr |
13532 | | xmlSAXParseFileWithData(xmlSAXHandlerPtr sax, const char *filename, |
13533 | | int recovery, void *data) { |
13534 | | xmlDocPtr ret; |
13535 | | xmlParserCtxtPtr ctxt; |
13536 | | |
13537 | | xmlInitParser(); |
13538 | | |
13539 | | ctxt = xmlCreateFileParserCtxt(filename); |
13540 | | if (ctxt == NULL) { |
13541 | | return(NULL); |
13542 | | } |
13543 | | if (sax != NULL) { |
13544 | | if (ctxt->sax != NULL) |
13545 | | xmlFree(ctxt->sax); |
13546 | | ctxt->sax = sax; |
13547 | | } |
13548 | | xmlDetectSAX2(ctxt); |
13549 | | if (data!=NULL) { |
13550 | | ctxt->_private = data; |
13551 | | } |
13552 | | |
13553 | | if (ctxt->directory == NULL) |
13554 | | ctxt->directory = xmlParserGetDirectory(filename); |
13555 | | |
13556 | | ctxt->recovery = recovery; |
13557 | | |
13558 | | xmlParseDocument(ctxt); |
13559 | | |
13560 | | if ((ctxt->wellFormed) || recovery) { |
13561 | | ret = ctxt->myDoc; |
13562 | | if ((ret != NULL) && (ctxt->input->buf != NULL)) { |
13563 | | if (ctxt->input->buf->compressed > 0) |
13564 | | ret->compression = 9; |
13565 | | else |
13566 | | ret->compression = ctxt->input->buf->compressed; |
13567 | | } |
13568 | | } |
13569 | | else { |
13570 | | ret = NULL; |
13571 | | xmlFreeDoc(ctxt->myDoc); |
13572 | | ctxt->myDoc = NULL; |
13573 | | } |
13574 | | if (sax != NULL) |
13575 | | ctxt->sax = NULL; |
13576 | | xmlFreeParserCtxt(ctxt); |
13577 | | |
13578 | | return(ret); |
13579 | | } |
13580 | | |
13581 | | /** |
13582 | | * xmlSAXParseFile: |
13583 | | * @sax: the SAX handler block |
13584 | | * @filename: the filename |
13585 | | * @recovery: work in recovery mode, i.e. tries to read no Well Formed |
13586 | | * documents |
13587 | | * |
13588 | | * DEPRECATED: Use xmlNewSAXParserCtxt and xmlCtxtReadFile. |
13589 | | * |
13590 | | * parse an XML file and build a tree. Automatic support for ZLIB/Compress |
13591 | | * compressed document is provided by default if found at compile-time. |
13592 | | * It use the given SAX function block to handle the parsing callback. |
13593 | | * If sax is NULL, fallback to the default DOM tree building routines. |
13594 | | * |
13595 | | * Returns the resulting document tree |
13596 | | */ |
13597 | | |
13598 | | xmlDocPtr |
13599 | | xmlSAXParseFile(xmlSAXHandlerPtr sax, const char *filename, |
13600 | | int recovery) { |
13601 | | return(xmlSAXParseFileWithData(sax,filename,recovery,NULL)); |
13602 | | } |
13603 | | |
13604 | | /** |
13605 | | * xmlRecoverDoc: |
13606 | | * @cur: a pointer to an array of xmlChar |
13607 | | * |
13608 | | * DEPRECATED: Use xmlReadDoc with XML_PARSE_RECOVER. |
13609 | | * |
13610 | | * parse an XML in-memory document and build a tree. |
13611 | | * In the case the document is not Well Formed, a attempt to build a |
13612 | | * tree is tried anyway |
13613 | | * |
13614 | | * Returns the resulting document tree or NULL in case of failure |
13615 | | */ |
13616 | | |
13617 | | xmlDocPtr |
13618 | | xmlRecoverDoc(const xmlChar *cur) { |
13619 | | return(xmlSAXParseDoc(NULL, cur, 1)); |
13620 | | } |
13621 | | |
13622 | | /** |
13623 | | * xmlParseFile: |
13624 | | * @filename: the filename |
13625 | | * |
13626 | | * DEPRECATED: Use xmlReadFile. |
13627 | | * |
13628 | | * parse an XML file and build a tree. Automatic support for ZLIB/Compress |
13629 | | * compressed document is provided by default if found at compile-time. |
13630 | | * |
13631 | | * Returns the resulting document tree if the file was wellformed, |
13632 | | * NULL otherwise. |
13633 | | */ |
13634 | | |
13635 | | xmlDocPtr |
13636 | | xmlParseFile(const char *filename) { |
13637 | | return(xmlSAXParseFile(NULL, filename, 0)); |
13638 | | } |
13639 | | |
13640 | | /** |
13641 | | * xmlRecoverFile: |
13642 | | * @filename: the filename |
13643 | | * |
13644 | | * DEPRECATED: Use xmlReadFile with XML_PARSE_RECOVER. |
13645 | | * |
13646 | | * parse an XML file and build a tree. Automatic support for ZLIB/Compress |
13647 | | * compressed document is provided by default if found at compile-time. |
13648 | | * In the case the document is not Well Formed, it attempts to build |
13649 | | * a tree anyway |
13650 | | * |
13651 | | * Returns the resulting document tree or NULL in case of failure |
13652 | | */ |
13653 | | |
13654 | | xmlDocPtr |
13655 | | xmlRecoverFile(const char *filename) { |
13656 | | return(xmlSAXParseFile(NULL, filename, 1)); |
13657 | | } |
13658 | | |
13659 | | |
13660 | | /** |
13661 | | * xmlSetupParserForBuffer: |
13662 | | * @ctxt: an XML parser context |
13663 | | * @buffer: a xmlChar * buffer |
13664 | | * @filename: a file name |
13665 | | * |
13666 | | * DEPRECATED: Don't use. |
13667 | | * |
13668 | | * Setup the parser context to parse a new buffer; Clears any prior |
13669 | | * contents from the parser context. The buffer parameter must not be |
13670 | | * NULL, but the filename parameter can be |
13671 | | */ |
13672 | | void |
13673 | | xmlSetupParserForBuffer(xmlParserCtxtPtr ctxt, const xmlChar* buffer, |
13674 | | const char* filename) |
13675 | | { |
13676 | | xmlParserInputPtr input; |
13677 | | |
13678 | | if ((ctxt == NULL) || (buffer == NULL)) |
13679 | | return; |
13680 | | |
13681 | | input = xmlNewInputStream(ctxt); |
13682 | | if (input == NULL) { |
13683 | | xmlErrMemory(NULL, "parsing new buffer: out of memory\n"); |
13684 | | xmlClearParserCtxt(ctxt); |
13685 | | return; |
13686 | | } |
13687 | | |
13688 | | xmlClearParserCtxt(ctxt); |
13689 | | if (filename != NULL) |
13690 | | input->filename = (char *) xmlCanonicPath((const xmlChar *)filename); |
13691 | | input->base = buffer; |
13692 | | input->cur = buffer; |
13693 | | input->end = &buffer[xmlStrlen(buffer)]; |
13694 | | inputPush(ctxt, input); |
13695 | | } |
13696 | | |
13697 | | /** |
13698 | | * xmlSAXUserParseFile: |
13699 | | * @sax: a SAX handler |
13700 | | * @user_data: The user data returned on SAX callbacks |
13701 | | * @filename: a file name |
13702 | | * |
13703 | | * DEPRECATED: Use xmlNewSAXParserCtxt and xmlCtxtReadFile. |
13704 | | * |
13705 | | * parse an XML file and call the given SAX handler routines. |
13706 | | * Automatic support for ZLIB/Compress compressed document is provided |
13707 | | * |
13708 | | * Returns 0 in case of success or a error number otherwise |
13709 | | */ |
13710 | | int |
13711 | | xmlSAXUserParseFile(xmlSAXHandlerPtr sax, void *user_data, |
13712 | | const char *filename) { |
13713 | | int ret = 0; |
13714 | | xmlParserCtxtPtr ctxt; |
13715 | | |
13716 | | ctxt = xmlCreateFileParserCtxt(filename); |
13717 | | if (ctxt == NULL) return -1; |
13718 | | if (ctxt->sax != (xmlSAXHandlerPtr) &xmlDefaultSAXHandler) |
13719 | | xmlFree(ctxt->sax); |
13720 | | ctxt->sax = sax; |
13721 | | xmlDetectSAX2(ctxt); |
13722 | | |
13723 | | if (user_data != NULL) |
13724 | | ctxt->userData = user_data; |
13725 | | |
13726 | | xmlParseDocument(ctxt); |
13727 | | |
13728 | | if (ctxt->wellFormed) |
13729 | | ret = 0; |
13730 | | else { |
13731 | | if (ctxt->errNo != 0) |
13732 | | ret = ctxt->errNo; |
13733 | | else |
13734 | | ret = -1; |
13735 | | } |
13736 | | if (sax != NULL) |
13737 | | ctxt->sax = NULL; |
13738 | | if (ctxt->myDoc != NULL) { |
13739 | | xmlFreeDoc(ctxt->myDoc); |
13740 | | ctxt->myDoc = NULL; |
13741 | | } |
13742 | | xmlFreeParserCtxt(ctxt); |
13743 | | |
13744 | | return ret; |
13745 | | } |
13746 | | #endif /* LIBXML_SAX1_ENABLED */ |
13747 | | |
13748 | | /************************************************************************ |
13749 | | * * |
13750 | | * Front ends when parsing from memory * |
13751 | | * * |
13752 | | ************************************************************************/ |
13753 | | |
13754 | | /** |
13755 | | * xmlCreateMemoryParserCtxt: |
13756 | | * @buffer: a pointer to a char array |
13757 | | * @size: the size of the array |
13758 | | * |
13759 | | * Create a parser context for an XML in-memory document. |
13760 | | * |
13761 | | * Returns the new parser context or NULL |
13762 | | */ |
13763 | | xmlParserCtxtPtr |
13764 | 414 | xmlCreateMemoryParserCtxt(const char *buffer, int size) { |
13765 | 414 | xmlParserCtxtPtr ctxt; |
13766 | 414 | xmlParserInputPtr input; |
13767 | 414 | xmlParserInputBufferPtr buf; |
13768 | | |
13769 | 414 | if (buffer == NULL) |
13770 | 4 | return(NULL); |
13771 | 410 | if (size <= 0) |
13772 | 0 | return(NULL); |
13773 | | |
13774 | 410 | ctxt = xmlNewParserCtxt(); |
13775 | 410 | if (ctxt == NULL) |
13776 | 0 | return(NULL); |
13777 | | |
13778 | 410 | buf = xmlParserInputBufferCreateMem(buffer, size, XML_CHAR_ENCODING_NONE); |
13779 | 410 | if (buf == NULL) { |
13780 | 0 | xmlFreeParserCtxt(ctxt); |
13781 | 0 | return(NULL); |
13782 | 0 | } |
13783 | | |
13784 | 410 | input = xmlNewInputStream(ctxt); |
13785 | 410 | if (input == NULL) { |
13786 | 0 | xmlFreeParserInputBuffer(buf); |
13787 | 0 | xmlFreeParserCtxt(ctxt); |
13788 | 0 | return(NULL); |
13789 | 0 | } |
13790 | | |
13791 | 410 | input->filename = NULL; |
13792 | 410 | input->buf = buf; |
13793 | 410 | xmlBufResetInput(input->buf->buffer, input); |
13794 | | |
13795 | 410 | inputPush(ctxt, input); |
13796 | 410 | return(ctxt); |
13797 | 410 | } |
13798 | | |
13799 | | #ifdef LIBXML_SAX1_ENABLED |
13800 | | /** |
13801 | | * xmlSAXParseMemoryWithData: |
13802 | | * @sax: the SAX handler block |
13803 | | * @buffer: an pointer to a char array |
13804 | | * @size: the size of the array |
13805 | | * @recovery: work in recovery mode, i.e. tries to read no Well Formed |
13806 | | * documents |
13807 | | * @data: the userdata |
13808 | | * |
13809 | | * DEPRECATED: Use xmlNewSAXParserCtxt and xmlCtxtReadMemory. |
13810 | | * |
13811 | | * parse an XML in-memory block and use the given SAX function block |
13812 | | * to handle the parsing callback. If sax is NULL, fallback to the default |
13813 | | * DOM tree building routines. |
13814 | | * |
13815 | | * User data (void *) is stored within the parser context in the |
13816 | | * context's _private member, so it is available nearly everywhere in libxml |
13817 | | * |
13818 | | * Returns the resulting document tree |
13819 | | */ |
13820 | | |
13821 | | xmlDocPtr |
13822 | | xmlSAXParseMemoryWithData(xmlSAXHandlerPtr sax, const char *buffer, |
13823 | | int size, int recovery, void *data) { |
13824 | | xmlDocPtr ret; |
13825 | | xmlParserCtxtPtr ctxt; |
13826 | | |
13827 | | xmlInitParser(); |
13828 | | |
13829 | | ctxt = xmlCreateMemoryParserCtxt(buffer, size); |
13830 | | if (ctxt == NULL) return(NULL); |
13831 | | if (sax != NULL) { |
13832 | | if (ctxt->sax != NULL) |
13833 | | xmlFree(ctxt->sax); |
13834 | | ctxt->sax = sax; |
13835 | | } |
13836 | | xmlDetectSAX2(ctxt); |
13837 | | if (data!=NULL) { |
13838 | | ctxt->_private=data; |
13839 | | } |
13840 | | |
13841 | | ctxt->recovery = recovery; |
13842 | | |
13843 | | xmlParseDocument(ctxt); |
13844 | | |
13845 | | if ((ctxt->wellFormed) || recovery) ret = ctxt->myDoc; |
13846 | | else { |
13847 | | ret = NULL; |
13848 | | xmlFreeDoc(ctxt->myDoc); |
13849 | | ctxt->myDoc = NULL; |
13850 | | } |
13851 | | if (sax != NULL) |
13852 | | ctxt->sax = NULL; |
13853 | | xmlFreeParserCtxt(ctxt); |
13854 | | |
13855 | | return(ret); |
13856 | | } |
13857 | | |
13858 | | /** |
13859 | | * xmlSAXParseMemory: |
13860 | | * @sax: the SAX handler block |
13861 | | * @buffer: an pointer to a char array |
13862 | | * @size: the size of the array |
13863 | | * @recovery: work in recovery mode, i.e. tries to read not Well Formed |
13864 | | * documents |
13865 | | * |
13866 | | * DEPRECATED: Use xmlNewSAXParserCtxt and xmlCtxtReadMemory. |
13867 | | * |
13868 | | * parse an XML in-memory block and use the given SAX function block |
13869 | | * to handle the parsing callback. If sax is NULL, fallback to the default |
13870 | | * DOM tree building routines. |
13871 | | * |
13872 | | * Returns the resulting document tree |
13873 | | */ |
13874 | | xmlDocPtr |
13875 | | xmlSAXParseMemory(xmlSAXHandlerPtr sax, const char *buffer, |
13876 | | int size, int recovery) { |
13877 | | return xmlSAXParseMemoryWithData(sax, buffer, size, recovery, NULL); |
13878 | | } |
13879 | | |
13880 | | /** |
13881 | | * xmlParseMemory: |
13882 | | * @buffer: an pointer to a char array |
13883 | | * @size: the size of the array |
13884 | | * |
13885 | | * DEPRECATED: Use xmlReadMemory. |
13886 | | * |
13887 | | * parse an XML in-memory block and build a tree. |
13888 | | * |
13889 | | * Returns the resulting document tree |
13890 | | */ |
13891 | | |
13892 | | xmlDocPtr xmlParseMemory(const char *buffer, int size) { |
13893 | | return(xmlSAXParseMemory(NULL, buffer, size, 0)); |
13894 | | } |
13895 | | |
13896 | | /** |
13897 | | * xmlRecoverMemory: |
13898 | | * @buffer: an pointer to a char array |
13899 | | * @size: the size of the array |
13900 | | * |
13901 | | * DEPRECATED: Use xmlReadMemory with XML_PARSE_RECOVER. |
13902 | | * |
13903 | | * parse an XML in-memory block and build a tree. |
13904 | | * In the case the document is not Well Formed, an attempt to |
13905 | | * build a tree is tried anyway |
13906 | | * |
13907 | | * Returns the resulting document tree or NULL in case of error |
13908 | | */ |
13909 | | |
13910 | | xmlDocPtr xmlRecoverMemory(const char *buffer, int size) { |
13911 | | return(xmlSAXParseMemory(NULL, buffer, size, 1)); |
13912 | | } |
13913 | | |
13914 | | /** |
13915 | | * xmlSAXUserParseMemory: |
13916 | | * @sax: a SAX handler |
13917 | | * @user_data: The user data returned on SAX callbacks |
13918 | | * @buffer: an in-memory XML document input |
13919 | | * @size: the length of the XML document in bytes |
13920 | | * |
13921 | | * DEPRECATED: Use xmlNewSAXParserCtxt and xmlCtxtReadMemory. |
13922 | | * |
13923 | | * parse an XML in-memory buffer and call the given SAX handler routines. |
13924 | | * |
13925 | | * Returns 0 in case of success or a error number otherwise |
13926 | | */ |
13927 | | int xmlSAXUserParseMemory(xmlSAXHandlerPtr sax, void *user_data, |
13928 | | const char *buffer, int size) { |
13929 | | int ret = 0; |
13930 | | xmlParserCtxtPtr ctxt; |
13931 | | |
13932 | | xmlInitParser(); |
13933 | | |
13934 | | ctxt = xmlCreateMemoryParserCtxt(buffer, size); |
13935 | | if (ctxt == NULL) return -1; |
13936 | | if (ctxt->sax != (xmlSAXHandlerPtr) &xmlDefaultSAXHandler) |
13937 | | xmlFree(ctxt->sax); |
13938 | | ctxt->sax = sax; |
13939 | | xmlDetectSAX2(ctxt); |
13940 | | |
13941 | | if (user_data != NULL) |
13942 | | ctxt->userData = user_data; |
13943 | | |
13944 | | xmlParseDocument(ctxt); |
13945 | | |
13946 | | if (ctxt->wellFormed) |
13947 | | ret = 0; |
13948 | | else { |
13949 | | if (ctxt->errNo != 0) |
13950 | | ret = ctxt->errNo; |
13951 | | else |
13952 | | ret = -1; |
13953 | | } |
13954 | | if (sax != NULL) |
13955 | | ctxt->sax = NULL; |
13956 | | if (ctxt->myDoc != NULL) { |
13957 | | xmlFreeDoc(ctxt->myDoc); |
13958 | | ctxt->myDoc = NULL; |
13959 | | } |
13960 | | xmlFreeParserCtxt(ctxt); |
13961 | | |
13962 | | return ret; |
13963 | | } |
13964 | | #endif /* LIBXML_SAX1_ENABLED */ |
13965 | | |
13966 | | /** |
13967 | | * xmlCreateDocParserCtxt: |
13968 | | * @cur: a pointer to an array of xmlChar |
13969 | | * |
13970 | | * Creates a parser context for an XML in-memory document. |
13971 | | * |
13972 | | * Returns the new parser context or NULL |
13973 | | */ |
13974 | | xmlParserCtxtPtr |
13975 | 0 | xmlCreateDocParserCtxt(const xmlChar *cur) { |
13976 | 0 | int len; |
13977 | |
|
13978 | 0 | if (cur == NULL) |
13979 | 0 | return(NULL); |
13980 | 0 | len = xmlStrlen(cur); |
13981 | 0 | return(xmlCreateMemoryParserCtxt((const char *)cur, len)); |
13982 | 0 | } |
13983 | | |
13984 | | #ifdef LIBXML_SAX1_ENABLED |
13985 | | /** |
13986 | | * xmlSAXParseDoc: |
13987 | | * @sax: the SAX handler block |
13988 | | * @cur: a pointer to an array of xmlChar |
13989 | | * @recovery: work in recovery mode, i.e. tries to read no Well Formed |
13990 | | * documents |
13991 | | * |
13992 | | * DEPRECATED: Use xmlNewSAXParserCtxt and xmlCtxtReadDoc. |
13993 | | * |
13994 | | * parse an XML in-memory document and build a tree. |
13995 | | * It use the given SAX function block to handle the parsing callback. |
13996 | | * If sax is NULL, fallback to the default DOM tree building routines. |
13997 | | * |
13998 | | * Returns the resulting document tree |
13999 | | */ |
14000 | | |
14001 | | xmlDocPtr |
14002 | | xmlSAXParseDoc(xmlSAXHandlerPtr sax, const xmlChar *cur, int recovery) { |
14003 | | xmlDocPtr ret; |
14004 | | xmlParserCtxtPtr ctxt; |
14005 | | xmlSAXHandlerPtr oldsax = NULL; |
14006 | | |
14007 | | if (cur == NULL) return(NULL); |
14008 | | |
14009 | | |
14010 | | ctxt = xmlCreateDocParserCtxt(cur); |
14011 | | if (ctxt == NULL) return(NULL); |
14012 | | if (sax != NULL) { |
14013 | | oldsax = ctxt->sax; |
14014 | | ctxt->sax = sax; |
14015 | | ctxt->userData = NULL; |
14016 | | } |
14017 | | xmlDetectSAX2(ctxt); |
14018 | | |
14019 | | xmlParseDocument(ctxt); |
14020 | | if ((ctxt->wellFormed) || recovery) ret = ctxt->myDoc; |
14021 | | else { |
14022 | | ret = NULL; |
14023 | | xmlFreeDoc(ctxt->myDoc); |
14024 | | ctxt->myDoc = NULL; |
14025 | | } |
14026 | | if (sax != NULL) |
14027 | | ctxt->sax = oldsax; |
14028 | | xmlFreeParserCtxt(ctxt); |
14029 | | |
14030 | | return(ret); |
14031 | | } |
14032 | | |
14033 | | /** |
14034 | | * xmlParseDoc: |
14035 | | * @cur: a pointer to an array of xmlChar |
14036 | | * |
14037 | | * DEPRECATED: Use xmlReadDoc. |
14038 | | * |
14039 | | * parse an XML in-memory document and build a tree. |
14040 | | * |
14041 | | * Returns the resulting document tree |
14042 | | */ |
14043 | | |
14044 | | xmlDocPtr |
14045 | | xmlParseDoc(const xmlChar *cur) { |
14046 | | return(xmlSAXParseDoc(NULL, cur, 0)); |
14047 | | } |
14048 | | #endif /* LIBXML_SAX1_ENABLED */ |
14049 | | |
14050 | | #ifdef LIBXML_LEGACY_ENABLED |
14051 | | /************************************************************************ |
14052 | | * * |
14053 | | * Specific function to keep track of entities references * |
14054 | | * and used by the XSLT debugger * |
14055 | | * * |
14056 | | ************************************************************************/ |
14057 | | |
14058 | | static xmlEntityReferenceFunc xmlEntityRefFunc = NULL; |
14059 | | |
14060 | | /** |
14061 | | * xmlAddEntityReference: |
14062 | | * @ent : A valid entity |
14063 | | * @firstNode : A valid first node for children of entity |
14064 | | * @lastNode : A valid last node of children entity |
14065 | | * |
14066 | | * Notify of a reference to an entity of type XML_EXTERNAL_GENERAL_PARSED_ENTITY |
14067 | | */ |
14068 | | static void |
14069 | | xmlAddEntityReference(xmlEntityPtr ent, xmlNodePtr firstNode, |
14070 | | xmlNodePtr lastNode) |
14071 | | { |
14072 | | if (xmlEntityRefFunc != NULL) { |
14073 | | (*xmlEntityRefFunc) (ent, firstNode, lastNode); |
14074 | | } |
14075 | | } |
14076 | | |
14077 | | |
14078 | | /** |
14079 | | * xmlSetEntityReferenceFunc: |
14080 | | * @func: A valid function |
14081 | | * |
14082 | | * Set the function to call call back when a xml reference has been made |
14083 | | */ |
14084 | | void |
14085 | | xmlSetEntityReferenceFunc(xmlEntityReferenceFunc func) |
14086 | | { |
14087 | | xmlEntityRefFunc = func; |
14088 | | } |
14089 | | #endif /* LIBXML_LEGACY_ENABLED */ |
14090 | | |
14091 | | /************************************************************************ |
14092 | | * * |
14093 | | * Miscellaneous * |
14094 | | * * |
14095 | | ************************************************************************/ |
14096 | | |
14097 | | static int xmlParserInitialized = 0; |
14098 | | |
14099 | | /** |
14100 | | * xmlInitParser: |
14101 | | * |
14102 | | * Initialization function for the XML parser. |
14103 | | * This is not reentrant. Call once before processing in case of |
14104 | | * use in multithreaded programs. |
14105 | | */ |
14106 | | |
14107 | | void |
14108 | 11.4M | xmlInitParser(void) { |
14109 | | /* |
14110 | | * Note that the initialization code must not make memory allocations. |
14111 | | */ |
14112 | 11.4M | if (xmlParserInitialized != 0) |
14113 | 11.4M | return; |
14114 | | |
14115 | 2 | #ifdef LIBXML_THREAD_ENABLED |
14116 | 2 | __xmlGlobalInitMutexLock(); |
14117 | 2 | if (xmlParserInitialized == 0) { |
14118 | 2 | #endif |
14119 | | #if defined(_WIN32) && (!defined(LIBXML_STATIC) || defined(LIBXML_STATIC_FOR_DLL)) |
14120 | | if (xmlFree == free) |
14121 | | atexit(xmlCleanupParser); |
14122 | | #endif |
14123 | | |
14124 | 2 | xmlInitThreadsInternal(); |
14125 | 2 | xmlInitGlobalsInternal(); |
14126 | 2 | xmlInitMemoryInternal(); |
14127 | 2 | __xmlInitializeDict(); |
14128 | 2 | xmlInitEncodingInternal(); |
14129 | 2 | xmlRegisterDefaultInputCallbacks(); |
14130 | 2 | #ifdef LIBXML_OUTPUT_ENABLED |
14131 | 2 | xmlRegisterDefaultOutputCallbacks(); |
14132 | 2 | #endif /* LIBXML_OUTPUT_ENABLED */ |
14133 | 2 | #if defined(LIBXML_XPATH_ENABLED) || defined(LIBXML_SCHEMAS_ENABLED) |
14134 | 2 | xmlInitXPathInternal(); |
14135 | 2 | #endif |
14136 | 2 | xmlParserInitialized = 1; |
14137 | 2 | #ifdef LIBXML_THREAD_ENABLED |
14138 | 2 | } |
14139 | 2 | __xmlGlobalInitMutexUnlock(); |
14140 | 2 | #endif |
14141 | 2 | } |
14142 | | |
14143 | | /** |
14144 | | * xmlCleanupParser: |
14145 | | * |
14146 | | * This function name is somewhat misleading. It does not clean up |
14147 | | * parser state, it cleans up memory allocated by the library itself. |
14148 | | * It is a cleanup function for the XML library. It tries to reclaim all |
14149 | | * related global memory allocated for the library processing. |
14150 | | * It doesn't deallocate any document related memory. One should |
14151 | | * call xmlCleanupParser() only when the process has finished using |
14152 | | * the library and all XML/HTML documents built with it. |
14153 | | * See also xmlInitParser() which has the opposite function of preparing |
14154 | | * the library for operations. |
14155 | | * |
14156 | | * WARNING: if your application is multithreaded or has plugin support |
14157 | | * calling this may crash the application if another thread or |
14158 | | * a plugin is still using libxml2. It's sometimes very hard to |
14159 | | * guess if libxml2 is in use in the application, some libraries |
14160 | | * or plugins may use it without notice. In case of doubt abstain |
14161 | | * from calling this function or do it just before calling exit() |
14162 | | * to avoid leak reports from valgrind ! |
14163 | | */ |
14164 | | |
14165 | | void |
14166 | 0 | xmlCleanupParser(void) { |
14167 | 0 | if (!xmlParserInitialized) |
14168 | 0 | return; |
14169 | | |
14170 | 0 | xmlCleanupCharEncodingHandlers(); |
14171 | 0 | #ifdef LIBXML_CATALOG_ENABLED |
14172 | 0 | xmlCatalogCleanup(); |
14173 | 0 | #endif |
14174 | 0 | xmlCleanupDictInternal(); |
14175 | 0 | xmlCleanupInputCallbacks(); |
14176 | 0 | #ifdef LIBXML_OUTPUT_ENABLED |
14177 | 0 | xmlCleanupOutputCallbacks(); |
14178 | 0 | #endif |
14179 | | #ifdef LIBXML_SCHEMAS_ENABLED |
14180 | | xmlSchemaCleanupTypes(); |
14181 | | xmlRelaxNGCleanupTypes(); |
14182 | | #endif |
14183 | 0 | xmlCleanupGlobalsInternal(); |
14184 | 0 | xmlCleanupThreadsInternal(); |
14185 | 0 | xmlCleanupMemoryInternal(); |
14186 | 0 | xmlParserInitialized = 0; |
14187 | 0 | } |
14188 | | |
14189 | | #if defined(HAVE_ATTRIBUTE_DESTRUCTOR) && !defined(LIBXML_STATIC) && \ |
14190 | | !defined(_WIN32) |
14191 | | static void |
14192 | | ATTRIBUTE_DESTRUCTOR |
14193 | 0 | xmlDestructor(void) { |
14194 | | /* |
14195 | | * Calling custom deallocation functions in a destructor can cause |
14196 | | * problems, for example with Nokogiri. |
14197 | | */ |
14198 | 0 | if (xmlFree == free) |
14199 | 0 | xmlCleanupParser(); |
14200 | 0 | } |
14201 | | #endif |
14202 | | |
14203 | | /************************************************************************ |
14204 | | * * |
14205 | | * New set (2.6.0) of simpler and more flexible APIs * |
14206 | | * * |
14207 | | ************************************************************************/ |
14208 | | |
14209 | | /** |
14210 | | * DICT_FREE: |
14211 | | * @str: a string |
14212 | | * |
14213 | | * Free a string if it is not owned by the "dict" dictionary in the |
14214 | | * current scope |
14215 | | */ |
14216 | | #define DICT_FREE(str) \ |
14217 | 0 | if ((str) && ((!dict) || \ |
14218 | 0 | (xmlDictOwns(dict, (const xmlChar *)(str)) == 0))) \ |
14219 | 0 | xmlFree((char *)(str)); |
14220 | | |
14221 | | /** |
14222 | | * xmlCtxtReset: |
14223 | | * @ctxt: an XML parser context |
14224 | | * |
14225 | | * Reset a parser context |
14226 | | */ |
14227 | | void |
14228 | | xmlCtxtReset(xmlParserCtxtPtr ctxt) |
14229 | 0 | { |
14230 | 0 | xmlParserInputPtr input; |
14231 | 0 | xmlDictPtr dict; |
14232 | |
|
14233 | 0 | if (ctxt == NULL) |
14234 | 0 | return; |
14235 | | |
14236 | 0 | dict = ctxt->dict; |
14237 | |
|
14238 | 0 | while ((input = inputPop(ctxt)) != NULL) { /* Non consuming */ |
14239 | 0 | xmlFreeInputStream(input); |
14240 | 0 | } |
14241 | 0 | ctxt->inputNr = 0; |
14242 | 0 | ctxt->input = NULL; |
14243 | |
|
14244 | 0 | ctxt->spaceNr = 0; |
14245 | 0 | if (ctxt->spaceTab != NULL) { |
14246 | 0 | ctxt->spaceTab[0] = -1; |
14247 | 0 | ctxt->space = &ctxt->spaceTab[0]; |
14248 | 0 | } else { |
14249 | 0 | ctxt->space = NULL; |
14250 | 0 | } |
14251 | | |
14252 | |
|
14253 | 0 | ctxt->nodeNr = 0; |
14254 | 0 | ctxt->node = NULL; |
14255 | |
|
14256 | 0 | ctxt->nameNr = 0; |
14257 | 0 | ctxt->name = NULL; |
14258 | |
|
14259 | 0 | ctxt->nsNr = 0; |
14260 | |
|
14261 | 0 | DICT_FREE(ctxt->version); |
14262 | 0 | ctxt->version = NULL; |
14263 | 0 | DICT_FREE(ctxt->encoding); |
14264 | 0 | ctxt->encoding = NULL; |
14265 | 0 | DICT_FREE(ctxt->directory); |
14266 | 0 | ctxt->directory = NULL; |
14267 | 0 | DICT_FREE(ctxt->extSubURI); |
14268 | 0 | ctxt->extSubURI = NULL; |
14269 | 0 | DICT_FREE(ctxt->extSubSystem); |
14270 | 0 | ctxt->extSubSystem = NULL; |
14271 | 0 | if (ctxt->myDoc != NULL) |
14272 | 0 | xmlFreeDoc(ctxt->myDoc); |
14273 | 0 | ctxt->myDoc = NULL; |
14274 | |
|
14275 | 0 | ctxt->standalone = -1; |
14276 | 0 | ctxt->hasExternalSubset = 0; |
14277 | 0 | ctxt->hasPErefs = 0; |
14278 | 0 | ctxt->html = 0; |
14279 | 0 | ctxt->external = 0; |
14280 | 0 | ctxt->instate = XML_PARSER_START; |
14281 | 0 | ctxt->token = 0; |
14282 | |
|
14283 | 0 | ctxt->wellFormed = 1; |
14284 | 0 | ctxt->nsWellFormed = 1; |
14285 | 0 | ctxt->disableSAX = 0; |
14286 | 0 | ctxt->valid = 1; |
14287 | | #if 0 |
14288 | | ctxt->vctxt.userData = ctxt; |
14289 | | ctxt->vctxt.error = xmlParserValidityError; |
14290 | | ctxt->vctxt.warning = xmlParserValidityWarning; |
14291 | | #endif |
14292 | 0 | ctxt->record_info = 0; |
14293 | 0 | ctxt->checkIndex = 0; |
14294 | 0 | ctxt->endCheckState = 0; |
14295 | 0 | ctxt->inSubset = 0; |
14296 | 0 | ctxt->errNo = XML_ERR_OK; |
14297 | 0 | ctxt->depth = 0; |
14298 | 0 | ctxt->charset = XML_CHAR_ENCODING_UTF8; |
14299 | 0 | ctxt->catalogs = NULL; |
14300 | 0 | ctxt->sizeentities = 0; |
14301 | 0 | ctxt->sizeentcopy = 0; |
14302 | 0 | xmlInitNodeInfoSeq(&ctxt->node_seq); |
14303 | |
|
14304 | 0 | if (ctxt->attsDefault != NULL) { |
14305 | 0 | xmlHashFree(ctxt->attsDefault, xmlHashDefaultDeallocator); |
14306 | 0 | ctxt->attsDefault = NULL; |
14307 | 0 | } |
14308 | 0 | if (ctxt->attsSpecial != NULL) { |
14309 | 0 | xmlHashFree(ctxt->attsSpecial, NULL); |
14310 | 0 | ctxt->attsSpecial = NULL; |
14311 | 0 | } |
14312 | |
|
14313 | 0 | #ifdef LIBXML_CATALOG_ENABLED |
14314 | 0 | if (ctxt->catalogs != NULL) |
14315 | 0 | xmlCatalogFreeLocal(ctxt->catalogs); |
14316 | 0 | #endif |
14317 | 0 | ctxt->nbErrors = 0; |
14318 | 0 | ctxt->nbWarnings = 0; |
14319 | 0 | if (ctxt->lastError.code != XML_ERR_OK) |
14320 | 0 | xmlResetError(&ctxt->lastError); |
14321 | 0 | } |
14322 | | |
14323 | | /** |
14324 | | * xmlCtxtResetPush: |
14325 | | * @ctxt: an XML parser context |
14326 | | * @chunk: a pointer to an array of chars |
14327 | | * @size: number of chars in the array |
14328 | | * @filename: an optional file name or URI |
14329 | | * @encoding: the document encoding, or NULL |
14330 | | * |
14331 | | * Reset a push parser context |
14332 | | * |
14333 | | * Returns 0 in case of success and 1 in case of error |
14334 | | */ |
14335 | | int |
14336 | | xmlCtxtResetPush(xmlParserCtxtPtr ctxt, const char *chunk, |
14337 | | int size, const char *filename, const char *encoding) |
14338 | 0 | { |
14339 | 0 | xmlParserInputPtr inputStream; |
14340 | 0 | xmlParserInputBufferPtr buf; |
14341 | 0 | xmlCharEncoding enc = XML_CHAR_ENCODING_NONE; |
14342 | |
|
14343 | 0 | if (ctxt == NULL) |
14344 | 0 | return(1); |
14345 | | |
14346 | 0 | if ((encoding == NULL) && (chunk != NULL) && (size >= 4)) |
14347 | 0 | enc = xmlDetectCharEncoding((const xmlChar *) chunk, size); |
14348 | |
|
14349 | 0 | buf = xmlAllocParserInputBuffer(enc); |
14350 | 0 | if (buf == NULL) |
14351 | 0 | return(1); |
14352 | | |
14353 | 0 | if (ctxt == NULL) { |
14354 | 0 | xmlFreeParserInputBuffer(buf); |
14355 | 0 | return(1); |
14356 | 0 | } |
14357 | | |
14358 | 0 | xmlCtxtReset(ctxt); |
14359 | |
|
14360 | 0 | if (filename == NULL) { |
14361 | 0 | ctxt->directory = NULL; |
14362 | 0 | } else { |
14363 | 0 | ctxt->directory = xmlParserGetDirectory(filename); |
14364 | 0 | } |
14365 | |
|
14366 | 0 | inputStream = xmlNewInputStream(ctxt); |
14367 | 0 | if (inputStream == NULL) { |
14368 | 0 | xmlFreeParserInputBuffer(buf); |
14369 | 0 | return(1); |
14370 | 0 | } |
14371 | | |
14372 | 0 | if (filename == NULL) |
14373 | 0 | inputStream->filename = NULL; |
14374 | 0 | else |
14375 | 0 | inputStream->filename = (char *) |
14376 | 0 | xmlCanonicPath((const xmlChar *) filename); |
14377 | 0 | inputStream->buf = buf; |
14378 | 0 | xmlBufResetInput(buf->buffer, inputStream); |
14379 | |
|
14380 | 0 | inputPush(ctxt, inputStream); |
14381 | |
|
14382 | 0 | if ((size > 0) && (chunk != NULL) && (ctxt->input != NULL) && |
14383 | 0 | (ctxt->input->buf != NULL)) { |
14384 | 0 | size_t base = xmlBufGetInputBase(ctxt->input->buf->buffer, ctxt->input); |
14385 | 0 | size_t cur = ctxt->input->cur - ctxt->input->base; |
14386 | 0 | int res; |
14387 | |
|
14388 | 0 | res = xmlParserInputBufferPush(ctxt->input->buf, size, chunk); |
14389 | 0 | xmlBufSetInputBaseCur(ctxt->input->buf->buffer, ctxt->input, base, cur); |
14390 | 0 | if (res < 0) { |
14391 | 0 | xmlFatalErr(ctxt, ctxt->input->buf->error, NULL); |
14392 | 0 | xmlHaltParser(ctxt); |
14393 | 0 | return(1); |
14394 | 0 | } |
14395 | | #ifdef DEBUG_PUSH |
14396 | | xmlGenericError(xmlGenericErrorContext, "PP: pushed %d\n", size); |
14397 | | #endif |
14398 | 0 | } |
14399 | | |
14400 | 0 | if (encoding != NULL) { |
14401 | 0 | xmlCharEncodingHandlerPtr hdlr; |
14402 | |
|
14403 | 0 | if (ctxt->encoding != NULL) |
14404 | 0 | xmlFree((xmlChar *) ctxt->encoding); |
14405 | 0 | ctxt->encoding = xmlStrdup((const xmlChar *) encoding); |
14406 | |
|
14407 | 0 | hdlr = xmlFindCharEncodingHandler(encoding); |
14408 | 0 | if (hdlr != NULL) { |
14409 | 0 | xmlSwitchToEncoding(ctxt, hdlr); |
14410 | 0 | } else { |
14411 | 0 | xmlFatalErrMsgStr(ctxt, XML_ERR_UNSUPPORTED_ENCODING, |
14412 | 0 | "Unsupported encoding %s\n", BAD_CAST encoding); |
14413 | 0 | } |
14414 | 0 | } else if (enc != XML_CHAR_ENCODING_NONE) { |
14415 | 0 | xmlSwitchEncoding(ctxt, enc); |
14416 | 0 | } |
14417 | |
|
14418 | 0 | return(0); |
14419 | 0 | } |
14420 | | |
14421 | | |
14422 | | /** |
14423 | | * xmlCtxtUseOptionsInternal: |
14424 | | * @ctxt: an XML parser context |
14425 | | * @options: a combination of xmlParserOption |
14426 | | * @encoding: the user provided encoding to use |
14427 | | * |
14428 | | * Applies the options to the parser context |
14429 | | * |
14430 | | * Returns 0 in case of success, the set of unknown or unimplemented options |
14431 | | * in case of error. |
14432 | | */ |
14433 | | static int |
14434 | | xmlCtxtUseOptionsInternal(xmlParserCtxtPtr ctxt, int options, const char *encoding) |
14435 | 406 | { |
14436 | 406 | if (ctxt == NULL) |
14437 | 0 | return(-1); |
14438 | 406 | if (encoding != NULL) { |
14439 | 0 | if (ctxt->encoding != NULL) |
14440 | 0 | xmlFree((xmlChar *) ctxt->encoding); |
14441 | 0 | ctxt->encoding = xmlStrdup((const xmlChar *) encoding); |
14442 | 0 | } |
14443 | 406 | if (options & XML_PARSE_RECOVER) { |
14444 | 406 | ctxt->recovery = 1; |
14445 | 406 | options -= XML_PARSE_RECOVER; |
14446 | 406 | ctxt->options |= XML_PARSE_RECOVER; |
14447 | 406 | } else |
14448 | 0 | ctxt->recovery = 0; |
14449 | 406 | if (options & XML_PARSE_DTDLOAD) { |
14450 | 0 | ctxt->loadsubset = XML_DETECT_IDS; |
14451 | 0 | options -= XML_PARSE_DTDLOAD; |
14452 | 0 | ctxt->options |= XML_PARSE_DTDLOAD; |
14453 | 0 | } else |
14454 | 406 | ctxt->loadsubset = 0; |
14455 | 406 | if (options & XML_PARSE_DTDATTR) { |
14456 | 0 | ctxt->loadsubset |= XML_COMPLETE_ATTRS; |
14457 | 0 | options -= XML_PARSE_DTDATTR; |
14458 | 0 | ctxt->options |= XML_PARSE_DTDATTR; |
14459 | 0 | } |
14460 | 406 | if (options & XML_PARSE_NOENT) { |
14461 | 0 | ctxt->replaceEntities = 1; |
14462 | | /* ctxt->loadsubset |= XML_DETECT_IDS; */ |
14463 | 0 | options -= XML_PARSE_NOENT; |
14464 | 0 | ctxt->options |= XML_PARSE_NOENT; |
14465 | 0 | } else |
14466 | 406 | ctxt->replaceEntities = 0; |
14467 | 406 | if (options & XML_PARSE_PEDANTIC) { |
14468 | 0 | ctxt->pedantic = 1; |
14469 | 0 | options -= XML_PARSE_PEDANTIC; |
14470 | 0 | ctxt->options |= XML_PARSE_PEDANTIC; |
14471 | 0 | } else |
14472 | 406 | ctxt->pedantic = 0; |
14473 | 406 | if (options & XML_PARSE_NOBLANKS) { |
14474 | 0 | ctxt->keepBlanks = 0; |
14475 | 0 | ctxt->sax->ignorableWhitespace = xmlSAX2IgnorableWhitespace; |
14476 | 0 | options -= XML_PARSE_NOBLANKS; |
14477 | 0 | ctxt->options |= XML_PARSE_NOBLANKS; |
14478 | 0 | } else |
14479 | 406 | ctxt->keepBlanks = 1; |
14480 | 406 | if (options & XML_PARSE_DTDVALID) { |
14481 | 0 | ctxt->validate = 1; |
14482 | 0 | if (options & XML_PARSE_NOWARNING) |
14483 | 0 | ctxt->vctxt.warning = NULL; |
14484 | 0 | if (options & XML_PARSE_NOERROR) |
14485 | 0 | ctxt->vctxt.error = NULL; |
14486 | 0 | options -= XML_PARSE_DTDVALID; |
14487 | 0 | ctxt->options |= XML_PARSE_DTDVALID; |
14488 | 0 | } else |
14489 | 406 | ctxt->validate = 0; |
14490 | 406 | if (options & XML_PARSE_NOWARNING) { |
14491 | 0 | ctxt->sax->warning = NULL; |
14492 | 0 | options -= XML_PARSE_NOWARNING; |
14493 | 0 | } |
14494 | 406 | if (options & XML_PARSE_NOERROR) { |
14495 | 0 | ctxt->sax->error = NULL; |
14496 | 0 | ctxt->sax->fatalError = NULL; |
14497 | 0 | options -= XML_PARSE_NOERROR; |
14498 | 0 | } |
14499 | | #ifdef LIBXML_SAX1_ENABLED |
14500 | | if (options & XML_PARSE_SAX1) { |
14501 | | ctxt->sax->startElementNs = NULL; |
14502 | | ctxt->sax->endElementNs = NULL; |
14503 | | ctxt->sax->initialized = 1; |
14504 | | options -= XML_PARSE_SAX1; |
14505 | | ctxt->options |= XML_PARSE_SAX1; |
14506 | | } |
14507 | | #endif /* LIBXML_SAX1_ENABLED */ |
14508 | 406 | if (options & XML_PARSE_NODICT) { |
14509 | 0 | ctxt->dictNames = 0; |
14510 | 0 | options -= XML_PARSE_NODICT; |
14511 | 0 | ctxt->options |= XML_PARSE_NODICT; |
14512 | 406 | } else { |
14513 | 406 | ctxt->dictNames = 1; |
14514 | 406 | } |
14515 | 406 | if (options & XML_PARSE_NOCDATA) { |
14516 | 0 | ctxt->sax->cdataBlock = NULL; |
14517 | 0 | options -= XML_PARSE_NOCDATA; |
14518 | 0 | ctxt->options |= XML_PARSE_NOCDATA; |
14519 | 0 | } |
14520 | 406 | if (options & XML_PARSE_NSCLEAN) { |
14521 | 0 | ctxt->options |= XML_PARSE_NSCLEAN; |
14522 | 0 | options -= XML_PARSE_NSCLEAN; |
14523 | 0 | } |
14524 | 406 | if (options & XML_PARSE_NONET) { |
14525 | 0 | ctxt->options |= XML_PARSE_NONET; |
14526 | 0 | options -= XML_PARSE_NONET; |
14527 | 0 | } |
14528 | 406 | if (options & XML_PARSE_COMPACT) { |
14529 | 0 | ctxt->options |= XML_PARSE_COMPACT; |
14530 | 0 | options -= XML_PARSE_COMPACT; |
14531 | 0 | } |
14532 | 406 | if (options & XML_PARSE_OLD10) { |
14533 | 0 | ctxt->options |= XML_PARSE_OLD10; |
14534 | 0 | options -= XML_PARSE_OLD10; |
14535 | 0 | } |
14536 | 406 | if (options & XML_PARSE_NOBASEFIX) { |
14537 | 0 | ctxt->options |= XML_PARSE_NOBASEFIX; |
14538 | 0 | options -= XML_PARSE_NOBASEFIX; |
14539 | 0 | } |
14540 | 406 | if (options & XML_PARSE_HUGE) { |
14541 | 0 | ctxt->options |= XML_PARSE_HUGE; |
14542 | 0 | options -= XML_PARSE_HUGE; |
14543 | 0 | if (ctxt->dict != NULL) |
14544 | 0 | xmlDictSetLimit(ctxt->dict, 0); |
14545 | 0 | } |
14546 | 406 | if (options & XML_PARSE_OLDSAX) { |
14547 | 0 | ctxt->options |= XML_PARSE_OLDSAX; |
14548 | 0 | options -= XML_PARSE_OLDSAX; |
14549 | 0 | } |
14550 | 406 | if (options & XML_PARSE_IGNORE_ENC) { |
14551 | 0 | ctxt->options |= XML_PARSE_IGNORE_ENC; |
14552 | 0 | options -= XML_PARSE_IGNORE_ENC; |
14553 | 0 | } |
14554 | 406 | if (options & XML_PARSE_BIG_LINES) { |
14555 | 0 | ctxt->options |= XML_PARSE_BIG_LINES; |
14556 | 0 | options -= XML_PARSE_BIG_LINES; |
14557 | 0 | } |
14558 | 406 | ctxt->linenumbers = 1; |
14559 | 406 | return (options); |
14560 | 406 | } |
14561 | | |
14562 | | /** |
14563 | | * xmlCtxtUseOptions: |
14564 | | * @ctxt: an XML parser context |
14565 | | * @options: a combination of xmlParserOption |
14566 | | * |
14567 | | * Applies the options to the parser context |
14568 | | * |
14569 | | * Returns 0 in case of success, the set of unknown or unimplemented options |
14570 | | * in case of error. |
14571 | | */ |
14572 | | int |
14573 | | xmlCtxtUseOptions(xmlParserCtxtPtr ctxt, int options) |
14574 | 0 | { |
14575 | 0 | return(xmlCtxtUseOptionsInternal(ctxt, options, NULL)); |
14576 | 0 | } |
14577 | | |
14578 | | /** |
14579 | | * xmlDoRead: |
14580 | | * @ctxt: an XML parser context |
14581 | | * @URL: the base URL to use for the document |
14582 | | * @encoding: the document encoding, or NULL |
14583 | | * @options: a combination of xmlParserOption |
14584 | | * @reuse: keep the context for reuse |
14585 | | * |
14586 | | * Common front-end for the xmlRead functions |
14587 | | * |
14588 | | * Returns the resulting document tree or NULL |
14589 | | */ |
14590 | | static xmlDocPtr |
14591 | | xmlDoRead(xmlParserCtxtPtr ctxt, const char *URL, const char *encoding, |
14592 | | int options, int reuse) |
14593 | 406 | { |
14594 | 406 | xmlDocPtr ret; |
14595 | | |
14596 | 406 | xmlCtxtUseOptionsInternal(ctxt, options, encoding); |
14597 | 406 | if (encoding != NULL) { |
14598 | 0 | xmlCharEncodingHandlerPtr hdlr; |
14599 | | |
14600 | | /* |
14601 | | * TODO: We should consider to set XML_PARSE_IGNORE_ENC if the |
14602 | | * caller provided an encoding. Otherwise, we might switch to |
14603 | | * the encoding from the XML declaration which is likely to |
14604 | | * break things. Also see xmlSwitchInputEncoding. |
14605 | | */ |
14606 | 0 | hdlr = xmlFindCharEncodingHandler(encoding); |
14607 | 0 | if (hdlr != NULL) |
14608 | 0 | xmlSwitchToEncoding(ctxt, hdlr); |
14609 | 0 | } |
14610 | 406 | if ((URL != NULL) && (ctxt->input != NULL) && |
14611 | 406 | (ctxt->input->filename == NULL)) |
14612 | 0 | ctxt->input->filename = (char *) xmlStrdup((const xmlChar *) URL); |
14613 | 406 | xmlParseDocument(ctxt); |
14614 | 406 | if ((ctxt->wellFormed) || ctxt->recovery) |
14615 | 406 | ret = ctxt->myDoc; |
14616 | 0 | else { |
14617 | 0 | ret = NULL; |
14618 | 0 | if (ctxt->myDoc != NULL) { |
14619 | 0 | xmlFreeDoc(ctxt->myDoc); |
14620 | 0 | } |
14621 | 0 | } |
14622 | 406 | ctxt->myDoc = NULL; |
14623 | 406 | if (!reuse) { |
14624 | 406 | xmlFreeParserCtxt(ctxt); |
14625 | 406 | } |
14626 | | |
14627 | 406 | return (ret); |
14628 | 406 | } |
14629 | | |
14630 | | /** |
14631 | | * xmlReadDoc: |
14632 | | * @cur: a pointer to a zero terminated string |
14633 | | * @URL: the base URL to use for the document |
14634 | | * @encoding: the document encoding, or NULL |
14635 | | * @options: a combination of xmlParserOption |
14636 | | * |
14637 | | * parse an XML in-memory document and build a tree. |
14638 | | * |
14639 | | * Returns the resulting document tree |
14640 | | */ |
14641 | | xmlDocPtr |
14642 | | xmlReadDoc(const xmlChar * cur, const char *URL, const char *encoding, int options) |
14643 | 0 | { |
14644 | 0 | xmlParserCtxtPtr ctxt; |
14645 | |
|
14646 | 0 | if (cur == NULL) |
14647 | 0 | return (NULL); |
14648 | 0 | xmlInitParser(); |
14649 | |
|
14650 | 0 | ctxt = xmlCreateDocParserCtxt(cur); |
14651 | 0 | if (ctxt == NULL) |
14652 | 0 | return (NULL); |
14653 | 0 | return (xmlDoRead(ctxt, URL, encoding, options, 0)); |
14654 | 0 | } |
14655 | | |
14656 | | /** |
14657 | | * xmlReadFile: |
14658 | | * @filename: a file or URL |
14659 | | * @encoding: the document encoding, or NULL |
14660 | | * @options: a combination of xmlParserOption |
14661 | | * |
14662 | | * parse an XML file from the filesystem or the network. |
14663 | | * |
14664 | | * Returns the resulting document tree |
14665 | | */ |
14666 | | xmlDocPtr |
14667 | | xmlReadFile(const char *filename, const char *encoding, int options) |
14668 | 0 | { |
14669 | 0 | xmlParserCtxtPtr ctxt; |
14670 | |
|
14671 | 0 | xmlInitParser(); |
14672 | 0 | ctxt = xmlCreateURLParserCtxt(filename, options); |
14673 | 0 | if (ctxt == NULL) |
14674 | 0 | return (NULL); |
14675 | 0 | return (xmlDoRead(ctxt, NULL, encoding, options, 0)); |
14676 | 0 | } |
14677 | | |
14678 | | /** |
14679 | | * xmlReadMemory: |
14680 | | * @buffer: a pointer to a char array |
14681 | | * @size: the size of the array |
14682 | | * @URL: the base URL to use for the document |
14683 | | * @encoding: the document encoding, or NULL |
14684 | | * @options: a combination of xmlParserOption |
14685 | | * |
14686 | | * parse an XML in-memory document and build a tree. |
14687 | | * |
14688 | | * Returns the resulting document tree |
14689 | | */ |
14690 | | xmlDocPtr |
14691 | | xmlReadMemory(const char *buffer, int size, const char *URL, const char *encoding, int options) |
14692 | 410 | { |
14693 | 410 | xmlParserCtxtPtr ctxt; |
14694 | | |
14695 | 410 | xmlInitParser(); |
14696 | 410 | ctxt = xmlCreateMemoryParserCtxt(buffer, size); |
14697 | 410 | if (ctxt == NULL) |
14698 | 4 | return (NULL); |
14699 | 406 | return (xmlDoRead(ctxt, URL, encoding, options, 0)); |
14700 | 410 | } |
14701 | | |
14702 | | /** |
14703 | | * xmlReadFd: |
14704 | | * @fd: an open file descriptor |
14705 | | * @URL: the base URL to use for the document |
14706 | | * @encoding: the document encoding, or NULL |
14707 | | * @options: a combination of xmlParserOption |
14708 | | * |
14709 | | * parse an XML from a file descriptor and build a tree. |
14710 | | * NOTE that the file descriptor will not be closed when the |
14711 | | * reader is closed or reset. |
14712 | | * |
14713 | | * Returns the resulting document tree |
14714 | | */ |
14715 | | xmlDocPtr |
14716 | | xmlReadFd(int fd, const char *URL, const char *encoding, int options) |
14717 | 0 | { |
14718 | 0 | xmlParserCtxtPtr ctxt; |
14719 | 0 | xmlParserInputBufferPtr input; |
14720 | 0 | xmlParserInputPtr stream; |
14721 | |
|
14722 | 0 | if (fd < 0) |
14723 | 0 | return (NULL); |
14724 | 0 | xmlInitParser(); |
14725 | |
|
14726 | 0 | input = xmlParserInputBufferCreateFd(fd, XML_CHAR_ENCODING_NONE); |
14727 | 0 | if (input == NULL) |
14728 | 0 | return (NULL); |
14729 | 0 | input->closecallback = NULL; |
14730 | 0 | ctxt = xmlNewParserCtxt(); |
14731 | 0 | if (ctxt == NULL) { |
14732 | 0 | xmlFreeParserInputBuffer(input); |
14733 | 0 | return (NULL); |
14734 | 0 | } |
14735 | 0 | stream = xmlNewIOInputStream(ctxt, input, XML_CHAR_ENCODING_NONE); |
14736 | 0 | if (stream == NULL) { |
14737 | 0 | xmlFreeParserInputBuffer(input); |
14738 | 0 | xmlFreeParserCtxt(ctxt); |
14739 | 0 | return (NULL); |
14740 | 0 | } |
14741 | 0 | inputPush(ctxt, stream); |
14742 | 0 | return (xmlDoRead(ctxt, URL, encoding, options, 0)); |
14743 | 0 | } |
14744 | | |
14745 | | /** |
14746 | | * xmlReadIO: |
14747 | | * @ioread: an I/O read function |
14748 | | * @ioclose: an I/O close function |
14749 | | * @ioctx: an I/O handler |
14750 | | * @URL: the base URL to use for the document |
14751 | | * @encoding: the document encoding, or NULL |
14752 | | * @options: a combination of xmlParserOption |
14753 | | * |
14754 | | * parse an XML document from I/O functions and source and build a tree. |
14755 | | * |
14756 | | * Returns the resulting document tree |
14757 | | */ |
14758 | | xmlDocPtr |
14759 | | xmlReadIO(xmlInputReadCallback ioread, xmlInputCloseCallback ioclose, |
14760 | | void *ioctx, const char *URL, const char *encoding, int options) |
14761 | 0 | { |
14762 | 0 | xmlParserCtxtPtr ctxt; |
14763 | 0 | xmlParserInputBufferPtr input; |
14764 | 0 | xmlParserInputPtr stream; |
14765 | |
|
14766 | 0 | if (ioread == NULL) |
14767 | 0 | return (NULL); |
14768 | 0 | xmlInitParser(); |
14769 | |
|
14770 | 0 | input = xmlParserInputBufferCreateIO(ioread, ioclose, ioctx, |
14771 | 0 | XML_CHAR_ENCODING_NONE); |
14772 | 0 | if (input == NULL) { |
14773 | 0 | if (ioclose != NULL) |
14774 | 0 | ioclose(ioctx); |
14775 | 0 | return (NULL); |
14776 | 0 | } |
14777 | 0 | ctxt = xmlNewParserCtxt(); |
14778 | 0 | if (ctxt == NULL) { |
14779 | 0 | xmlFreeParserInputBuffer(input); |
14780 | 0 | return (NULL); |
14781 | 0 | } |
14782 | 0 | stream = xmlNewIOInputStream(ctxt, input, XML_CHAR_ENCODING_NONE); |
14783 | 0 | if (stream == NULL) { |
14784 | 0 | xmlFreeParserInputBuffer(input); |
14785 | 0 | xmlFreeParserCtxt(ctxt); |
14786 | 0 | return (NULL); |
14787 | 0 | } |
14788 | 0 | inputPush(ctxt, stream); |
14789 | 0 | return (xmlDoRead(ctxt, URL, encoding, options, 0)); |
14790 | 0 | } |
14791 | | |
14792 | | /** |
14793 | | * xmlCtxtReadDoc: |
14794 | | * @ctxt: an XML parser context |
14795 | | * @cur: a pointer to a zero terminated string |
14796 | | * @URL: the base URL to use for the document |
14797 | | * @encoding: the document encoding, or NULL |
14798 | | * @options: a combination of xmlParserOption |
14799 | | * |
14800 | | * parse an XML in-memory document and build a tree. |
14801 | | * This reuses the existing @ctxt parser context |
14802 | | * |
14803 | | * Returns the resulting document tree |
14804 | | */ |
14805 | | xmlDocPtr |
14806 | | xmlCtxtReadDoc(xmlParserCtxtPtr ctxt, const xmlChar * cur, |
14807 | | const char *URL, const char *encoding, int options) |
14808 | 0 | { |
14809 | 0 | if (cur == NULL) |
14810 | 0 | return (NULL); |
14811 | 0 | return (xmlCtxtReadMemory(ctxt, (const char *) cur, xmlStrlen(cur), URL, |
14812 | 0 | encoding, options)); |
14813 | 0 | } |
14814 | | |
14815 | | /** |
14816 | | * xmlCtxtReadFile: |
14817 | | * @ctxt: an XML parser context |
14818 | | * @filename: a file or URL |
14819 | | * @encoding: the document encoding, or NULL |
14820 | | * @options: a combination of xmlParserOption |
14821 | | * |
14822 | | * parse an XML file from the filesystem or the network. |
14823 | | * This reuses the existing @ctxt parser context |
14824 | | * |
14825 | | * Returns the resulting document tree |
14826 | | */ |
14827 | | xmlDocPtr |
14828 | | xmlCtxtReadFile(xmlParserCtxtPtr ctxt, const char *filename, |
14829 | | const char *encoding, int options) |
14830 | 0 | { |
14831 | 0 | xmlParserInputPtr stream; |
14832 | |
|
14833 | 0 | if (filename == NULL) |
14834 | 0 | return (NULL); |
14835 | 0 | if (ctxt == NULL) |
14836 | 0 | return (NULL); |
14837 | 0 | xmlInitParser(); |
14838 | |
|
14839 | 0 | xmlCtxtReset(ctxt); |
14840 | |
|
14841 | 0 | stream = xmlLoadExternalEntity(filename, NULL, ctxt); |
14842 | 0 | if (stream == NULL) { |
14843 | 0 | return (NULL); |
14844 | 0 | } |
14845 | 0 | inputPush(ctxt, stream); |
14846 | 0 | return (xmlDoRead(ctxt, NULL, encoding, options, 1)); |
14847 | 0 | } |
14848 | | |
14849 | | /** |
14850 | | * xmlCtxtReadMemory: |
14851 | | * @ctxt: an XML parser context |
14852 | | * @buffer: a pointer to a char array |
14853 | | * @size: the size of the array |
14854 | | * @URL: the base URL to use for the document |
14855 | | * @encoding: the document encoding, or NULL |
14856 | | * @options: a combination of xmlParserOption |
14857 | | * |
14858 | | * parse an XML in-memory document and build a tree. |
14859 | | * This reuses the existing @ctxt parser context |
14860 | | * |
14861 | | * Returns the resulting document tree |
14862 | | */ |
14863 | | xmlDocPtr |
14864 | | xmlCtxtReadMemory(xmlParserCtxtPtr ctxt, const char *buffer, int size, |
14865 | | const char *URL, const char *encoding, int options) |
14866 | 0 | { |
14867 | 0 | xmlParserInputBufferPtr input; |
14868 | 0 | xmlParserInputPtr stream; |
14869 | |
|
14870 | 0 | if (ctxt == NULL) |
14871 | 0 | return (NULL); |
14872 | 0 | if (buffer == NULL) |
14873 | 0 | return (NULL); |
14874 | 0 | xmlInitParser(); |
14875 | |
|
14876 | 0 | xmlCtxtReset(ctxt); |
14877 | |
|
14878 | 0 | input = xmlParserInputBufferCreateMem(buffer, size, XML_CHAR_ENCODING_NONE); |
14879 | 0 | if (input == NULL) { |
14880 | 0 | return(NULL); |
14881 | 0 | } |
14882 | | |
14883 | 0 | stream = xmlNewIOInputStream(ctxt, input, XML_CHAR_ENCODING_NONE); |
14884 | 0 | if (stream == NULL) { |
14885 | 0 | xmlFreeParserInputBuffer(input); |
14886 | 0 | return(NULL); |
14887 | 0 | } |
14888 | | |
14889 | 0 | inputPush(ctxt, stream); |
14890 | 0 | return (xmlDoRead(ctxt, URL, encoding, options, 1)); |
14891 | 0 | } |
14892 | | |
14893 | | /** |
14894 | | * xmlCtxtReadFd: |
14895 | | * @ctxt: an XML parser context |
14896 | | * @fd: an open file descriptor |
14897 | | * @URL: the base URL to use for the document |
14898 | | * @encoding: the document encoding, or NULL |
14899 | | * @options: a combination of xmlParserOption |
14900 | | * |
14901 | | * parse an XML from a file descriptor and build a tree. |
14902 | | * This reuses the existing @ctxt parser context |
14903 | | * NOTE that the file descriptor will not be closed when the |
14904 | | * reader is closed or reset. |
14905 | | * |
14906 | | * Returns the resulting document tree |
14907 | | */ |
14908 | | xmlDocPtr |
14909 | | xmlCtxtReadFd(xmlParserCtxtPtr ctxt, int fd, |
14910 | | const char *URL, const char *encoding, int options) |
14911 | 0 | { |
14912 | 0 | xmlParserInputBufferPtr input; |
14913 | 0 | xmlParserInputPtr stream; |
14914 | |
|
14915 | 0 | if (fd < 0) |
14916 | 0 | return (NULL); |
14917 | 0 | if (ctxt == NULL) |
14918 | 0 | return (NULL); |
14919 | 0 | xmlInitParser(); |
14920 | |
|
14921 | 0 | xmlCtxtReset(ctxt); |
14922 | | |
14923 | |
|
14924 | 0 | input = xmlParserInputBufferCreateFd(fd, XML_CHAR_ENCODING_NONE); |
14925 | 0 | if (input == NULL) |
14926 | 0 | return (NULL); |
14927 | 0 | input->closecallback = NULL; |
14928 | 0 | stream = xmlNewIOInputStream(ctxt, input, XML_CHAR_ENCODING_NONE); |
14929 | 0 | if (stream == NULL) { |
14930 | 0 | xmlFreeParserInputBuffer(input); |
14931 | 0 | return (NULL); |
14932 | 0 | } |
14933 | 0 | inputPush(ctxt, stream); |
14934 | 0 | return (xmlDoRead(ctxt, URL, encoding, options, 1)); |
14935 | 0 | } |
14936 | | |
14937 | | /** |
14938 | | * xmlCtxtReadIO: |
14939 | | * @ctxt: an XML parser context |
14940 | | * @ioread: an I/O read function |
14941 | | * @ioclose: an I/O close function |
14942 | | * @ioctx: an I/O handler |
14943 | | * @URL: the base URL to use for the document |
14944 | | * @encoding: the document encoding, or NULL |
14945 | | * @options: a combination of xmlParserOption |
14946 | | * |
14947 | | * parse an XML document from I/O functions and source and build a tree. |
14948 | | * This reuses the existing @ctxt parser context |
14949 | | * |
14950 | | * Returns the resulting document tree |
14951 | | */ |
14952 | | xmlDocPtr |
14953 | | xmlCtxtReadIO(xmlParserCtxtPtr ctxt, xmlInputReadCallback ioread, |
14954 | | xmlInputCloseCallback ioclose, void *ioctx, |
14955 | | const char *URL, |
14956 | | const char *encoding, int options) |
14957 | 0 | { |
14958 | 0 | xmlParserInputBufferPtr input; |
14959 | 0 | xmlParserInputPtr stream; |
14960 | |
|
14961 | 0 | if (ioread == NULL) |
14962 | 0 | return (NULL); |
14963 | 0 | if (ctxt == NULL) |
14964 | 0 | return (NULL); |
14965 | 0 | xmlInitParser(); |
14966 | |
|
14967 | 0 | xmlCtxtReset(ctxt); |
14968 | |
|
14969 | 0 | input = xmlParserInputBufferCreateIO(ioread, ioclose, ioctx, |
14970 | 0 | XML_CHAR_ENCODING_NONE); |
14971 | 0 | if (input == NULL) { |
14972 | 0 | if (ioclose != NULL) |
14973 | 0 | ioclose(ioctx); |
14974 | 0 | return (NULL); |
14975 | 0 | } |
14976 | 0 | stream = xmlNewIOInputStream(ctxt, input, XML_CHAR_ENCODING_NONE); |
14977 | 0 | if (stream == NULL) { |
14978 | 0 | xmlFreeParserInputBuffer(input); |
14979 | 0 | return (NULL); |
14980 | 0 | } |
14981 | 0 | inputPush(ctxt, stream); |
14982 | 0 | return (xmlDoRead(ctxt, URL, encoding, options, 1)); |
14983 | 0 | } |
14984 | | |