|
1 /* |
|
2 * libxml2_htmltree.c : implementation of access function for an HTML tree. |
|
3 * |
|
4 * See Copyright for the status of this software. |
|
5 * |
|
6 * daniel@veillard.com |
|
7 * Portion Copyright © 2009 Nokia Corporation and/or its subsidiary(-ies). All rights reserved. |
|
8 */ |
|
9 |
|
10 #define IN_LIBXML |
|
11 #include "xmlenglibxml.h" |
|
12 |
|
13 #include <string.h> /* for memset() only ! */ |
|
14 |
|
15 #ifdef HAVE_CTYPE_H |
|
16 #include <ctype.h> |
|
17 #endif |
|
18 #ifdef HAVE_STDLIB_H |
|
19 #include <stdlib.h> |
|
20 #endif |
|
21 |
|
22 #include <stdapis/libxml2/libxml2_xmlmemory.h> |
|
23 #include "libxml2_htmlparser.h" |
|
24 #include "libxml2_htmltree.h" |
|
25 #include <stdapis/libxml2/libxml2_entities.h> |
|
26 #include <stdapis/libxml2/libxml2_valid.h> |
|
27 #include <stdapis/libxml2/libxml2_xmlerror.h> |
|
28 #include "libxml2_xmlerror2.h" |
|
29 #include <stdapis/libxml2/libxml2_xmlsave.h> |
|
30 #include <stdapis/libxml2/libxml2_parserinternals.h> |
|
31 #include <stdapis/libxml2/libxml2_globals.h> |
|
32 #include <stdapis/libxml2/libxml2_uri.h> |
|
33 |
|
34 #ifdef LIBXML_HTML_ENABLED |
|
35 |
|
36 /************************************************************************ |
|
37 * * |
|
38 * Getting/Setting encoding meta tags * |
|
39 * * |
|
40 ************************************************************************/ |
|
41 |
|
42 /** |
|
43 * htmlGetMetaEncoding: |
|
44 * @param doc the document |
|
45 * |
|
46 * Encoding definition lookup in the Meta tags |
|
47 * |
|
48 * Returns the current encoding as flagged in the HTML source |
|
49 */ |
|
50 const xmlChar * |
|
51 htmlGetMetaEncoding(htmlDocPtr doc) { |
|
52 htmlNodePtr cur; |
|
53 const xmlChar *content; |
|
54 const xmlChar *encoding; |
|
55 |
|
56 if (doc == NULL) |
|
57 return(NULL); |
|
58 cur = doc->children; |
|
59 |
|
60 /* |
|
61 * Search the html |
|
62 */ |
|
63 while (cur != NULL) { |
|
64 if ((cur->type == XML_ELEMENT_NODE) && (cur->name != NULL)) { |
|
65 if (xmlStrEqual(cur->name, BAD_CAST"html")) |
|
66 break; |
|
67 if (xmlStrEqual(cur->name, BAD_CAST"head")) |
|
68 goto found_head; |
|
69 if (xmlStrEqual(cur->name, BAD_CAST"meta")) |
|
70 goto found_meta; |
|
71 } |
|
72 cur = cur->next; |
|
73 } |
|
74 if (cur == NULL) |
|
75 return(NULL); |
|
76 cur = cur->children; |
|
77 |
|
78 /* |
|
79 * Search the head |
|
80 */ |
|
81 while (cur != NULL) { |
|
82 if ((cur->type == XML_ELEMENT_NODE) && (cur->name != NULL)) { |
|
83 if (xmlStrEqual(cur->name, BAD_CAST"head")) |
|
84 break; |
|
85 if (xmlStrEqual(cur->name, BAD_CAST"meta")) |
|
86 goto found_meta; |
|
87 } |
|
88 cur = cur->next; |
|
89 } |
|
90 if (cur == NULL) |
|
91 return(NULL); |
|
92 found_head: |
|
93 cur = cur->children; |
|
94 |
|
95 /* |
|
96 * Search the meta elements |
|
97 */ |
|
98 found_meta: |
|
99 while (cur != NULL) { |
|
100 if ((cur->type == XML_ELEMENT_NODE) && (cur->name != NULL)) { |
|
101 if (xmlStrEqual(cur->name, BAD_CAST"meta")) { |
|
102 xmlAttrPtr attr = cur->properties; |
|
103 int http; |
|
104 const xmlChar *value; |
|
105 |
|
106 content = NULL; |
|
107 http = 0; |
|
108 while (attr != NULL) { |
|
109 if ((attr->children != NULL) && |
|
110 (attr->children->type == XML_TEXT_NODE) && |
|
111 (attr->children->next == NULL)) { |
|
112 value = attr->children->content; |
|
113 if ((!xmlStrcasecmp(attr->name, BAD_CAST"http-equiv")) |
|
114 && (!xmlStrcasecmp(value, BAD_CAST"Content-Type"))) |
|
115 http = 1; |
|
116 else if ((value != NULL) |
|
117 && (!xmlStrcasecmp(attr->name, BAD_CAST"content"))) |
|
118 content = value; |
|
119 if ((http != 0) && (content != NULL)) |
|
120 goto found_content; |
|
121 } |
|
122 attr = attr->next; |
|
123 } |
|
124 } |
|
125 } |
|
126 cur = cur->next; |
|
127 } |
|
128 return(NULL); |
|
129 |
|
130 found_content: |
|
131 encoding = xmlStrstr(content, BAD_CAST"charset="); |
|
132 if (encoding == NULL) |
|
133 encoding = xmlStrstr(content, BAD_CAST"Charset="); |
|
134 if (encoding == NULL) |
|
135 encoding = xmlStrstr(content, BAD_CAST"CHARSET="); |
|
136 if (encoding != NULL) { |
|
137 encoding += 8; |
|
138 } else { |
|
139 encoding = xmlStrstr(content, BAD_CAST"charset ="); |
|
140 if (encoding == NULL) |
|
141 encoding = xmlStrstr(content, BAD_CAST"Charset ="); |
|
142 if (encoding == NULL) |
|
143 encoding = xmlStrstr(content, BAD_CAST"CHARSET ="); |
|
144 if (encoding != NULL) |
|
145 encoding += 9; |
|
146 } |
|
147 if (encoding != NULL) { |
|
148 while ((*encoding == ' ') || (*encoding == '\t')) encoding++; |
|
149 } |
|
150 return(encoding); |
|
151 } |
|
152 |
|
153 |
|
154 #endif /* LIBXML_HTML_ENABLED */ |
|
155 |
|
156 #if defined(LIBXML_HTML_ENABLED) || defined(XMLENGINE_XSLT) |
|
157 /** |
|
158 * htmlSetMetaEncoding: |
|
159 * @param doc the document |
|
160 * @param encoding the encoding string |
|
161 * |
|
162 * Sets the current encoding in the Meta tags |
|
163 * NOTE: this will not change the document content encoding, just |
|
164 * the META flag associated. |
|
165 * |
|
166 * Returns 0 in case of success and -1 in case of error |
|
167 */ |
|
168 XMLPUBFUNEXPORT int |
|
169 htmlSetMetaEncoding(htmlDocPtr doc, const xmlChar *encoding) { |
|
170 htmlNodePtr cur, meta; |
|
171 const xmlChar *content; |
|
172 char newcontent[100]; |
|
173 LOAD_GS_SAFE_DOC(doc) |
|
174 |
|
175 if (doc == NULL) |
|
176 return(-1); |
|
177 |
|
178 if (encoding != NULL) { |
|
179 snprintf(newcontent, sizeof(newcontent), "text/html; charset=%s", |
|
180 encoding); |
|
181 newcontent[sizeof(newcontent) - 1] = 0; |
|
182 } |
|
183 |
|
184 cur = doc->children; |
|
185 |
|
186 /* |
|
187 * Search the html |
|
188 */ |
|
189 while (cur != NULL) { |
|
190 if ((cur->type == XML_ELEMENT_NODE) && (cur->name != NULL)) { |
|
191 if (xmlStrcasecmp(cur->name, BAD_CAST"html") == 0) |
|
192 break; |
|
193 if (xmlStrcasecmp(cur->name, BAD_CAST"head") == 0) |
|
194 goto found_head; |
|
195 if (xmlStrcasecmp(cur->name, BAD_CAST"meta") == 0) |
|
196 goto found_meta; |
|
197 } |
|
198 cur = cur->next; |
|
199 } |
|
200 if (cur == NULL) |
|
201 return(-1); |
|
202 cur = cur->children; |
|
203 |
|
204 /* |
|
205 * Search the head |
|
206 */ |
|
207 while (cur != NULL) { |
|
208 if ((cur->type == XML_ELEMENT_NODE) && (cur->name != NULL)) { |
|
209 if (xmlStrcasecmp(cur->name, BAD_CAST"head") == 0) |
|
210 break; |
|
211 if (xmlStrcasecmp(cur->name, BAD_CAST"meta") == 0) |
|
212 goto found_meta; |
|
213 } |
|
214 cur = cur->next; |
|
215 } |
|
216 if (cur == NULL) |
|
217 return(-1); |
|
218 found_head: |
|
219 if (cur->children == NULL) { |
|
220 if (encoding == NULL) |
|
221 return(0); |
|
222 meta = xmlNewDocNode(doc, NULL, BAD_CAST"meta", NULL); |
|
223 xmlAddChild(cur, meta); |
|
224 xmlNewProp(meta, BAD_CAST"http-equiv", BAD_CAST"Content-Type"); |
|
225 xmlNewProp(meta, BAD_CAST"content", BAD_CAST newcontent); |
|
226 if ( OOM_FLAG ) //oom set in xmlNewProp |
|
227 return(-1); |
|
228 return(0); |
|
229 } |
|
230 cur = cur->children; |
|
231 |
|
232 found_meta: |
|
233 if (encoding != NULL) { |
|
234 /* |
|
235 * Create a new Meta element with the right attributes |
|
236 */ |
|
237 |
|
238 meta = xmlNewDocNode(doc, NULL, BAD_CAST"meta", NULL); |
|
239 xmlAddPrevSibling(cur, meta); |
|
240 xmlNewProp(meta, BAD_CAST"http-equiv", BAD_CAST"Content-Type"); |
|
241 xmlNewProp(meta, BAD_CAST"content", BAD_CAST newcontent); |
|
242 } |
|
243 |
|
244 /* |
|
245 * Search and destroy all the remaining the meta elements carrying |
|
246 * encoding informations |
|
247 */ |
|
248 while (cur != NULL) { |
|
249 if ((cur->type == XML_ELEMENT_NODE) && (cur->name != NULL)) { |
|
250 if (xmlStrcasecmp(cur->name, BAD_CAST"meta") == 0) { |
|
251 xmlAttrPtr attr = cur->properties; |
|
252 int http; |
|
253 const xmlChar *value; |
|
254 |
|
255 content = NULL; |
|
256 http = 0; |
|
257 while (attr != NULL) { |
|
258 if ((attr->children != NULL) && |
|
259 (attr->children->type == XML_TEXT_NODE) && |
|
260 (attr->children->next == NULL)) { |
|
261 value = attr->children->content; |
|
262 if ((!xmlStrcasecmp(attr->name, BAD_CAST"http-equiv")) |
|
263 && (!xmlStrcasecmp(value, BAD_CAST"Content-Type"))) |
|
264 http = 1; |
|
265 else |
|
266 { |
|
267 if ((value != NULL) && |
|
268 (!xmlStrcasecmp(attr->name, BAD_CAST"content"))) |
|
269 content = value; |
|
270 } |
|
271 if ((http != 0) && (content != NULL)) |
|
272 break; |
|
273 } |
|
274 attr = attr->next; |
|
275 } |
|
276 if ((http != 0) && (content != NULL)) { |
|
277 meta = cur; |
|
278 cur = cur->next; |
|
279 xmlUnlinkNode(meta); |
|
280 xmlFreeNode(meta); |
|
281 continue; |
|
282 } |
|
283 |
|
284 } |
|
285 } |
|
286 cur = cur->next; |
|
287 } |
|
288 return(0); |
|
289 } |
|
290 |
|
291 /** |
|
292 * booleanHTMLAttrs: |
|
293 * |
|
294 * These are the HTML attributes which will be output |
|
295 * in minimized form, i.e. <option selected="selected"> will be |
|
296 * output as <option selected>, as per XSLT 1.0 16.2 "HTML Output Method" |
|
297 * |
|
298 */ |
|
299 static const char* const htmlBooleanAttrs[] = { |
|
300 "checked", "compact", "declare", "defer", "disabled", "ismap", |
|
301 "multiple", "nohref", "noresize", "noshade", "nowrap", "readonly", |
|
302 "selected", NULL |
|
303 }; |
|
304 |
|
305 |
|
306 /** |
|
307 * htmlIsBooleanAttr: |
|
308 * @param name the name of the attribute to check |
|
309 * |
|
310 * Determine if a given attribute is a boolean attribute. |
|
311 * |
|
312 * returns: false if the attribute is not boolean, true otherwise. |
|
313 */ |
|
314 XMLPUBFUNEXPORT int |
|
315 htmlIsBooleanAttr(const xmlChar *name) |
|
316 { |
|
317 int i = 0; |
|
318 |
|
319 while (htmlBooleanAttrs[i] != NULL) { |
|
320 if (xmlStrcasecmp((const xmlChar *)htmlBooleanAttrs[i], name) == 0) |
|
321 return 1; |
|
322 i++; |
|
323 } |
|
324 return 0; |
|
325 } |
|
326 #endif // HTML or XSLT |
|
327 |
|
328 #ifdef LIBXML_HTML_ENABLED |
|
329 |
|
330 #ifdef LIBXML_OUTPUT_ENABLED |
|
331 /************************************************************************ |
|
332 * * |
|
333 * Output error handlers * |
|
334 * * |
|
335 ************************************************************************/ |
|
336 /** |
|
337 * htmlSaveErrMemory: |
|
338 * @param extra extra informations |
|
339 * |
|
340 * Handle an out of memory condition |
|
341 */ |
|
342 static void |
|
343 htmlSaveErrMemory(const char *extra) |
|
344 { |
|
345 __xmlSimpleError(XML_FROM_OUTPUT, XML_ERR_NO_MEMORY, NULL, NULL, extra); |
|
346 } |
|
347 |
|
348 /** |
|
349 * htmlSaveErr: |
|
350 * @param code the error number |
|
351 * @param node the location of the error. |
|
352 * @param extra extra informations |
|
353 * |
|
354 * Handle an out of memory condition |
|
355 */ |
|
356 static void |
|
357 htmlSaveErr(int code, xmlNodePtr node, const char *extra); // Moved to XSLT-enabled part of the file |
|
358 |
|
359 /************************************************************************ |
|
360 * * |
|
361 * Dumping HTML tree content to a simple buffer * |
|
362 * * |
|
363 ************************************************************************/ |
|
364 |
|
365 static int |
|
366 htmlNodeDumpFormat(xmlBufferPtr buf, xmlDocPtr doc, xmlNodePtr cur, |
|
367 int format); |
|
368 |
|
369 /** |
|
370 * htmlNodeDumpFormat: |
|
371 * @param buf the HTML buffer output |
|
372 * @param doc the document |
|
373 * @param cur the current node |
|
374 * @param format should formatting spaces been added |
|
375 * |
|
376 * Dump an HTML node, recursive behaviour,children are printed too. |
|
377 * |
|
378 * Returns the number of byte written or -1 in case of error |
|
379 */ |
|
380 static int |
|
381 htmlNodeDumpFormat(xmlBufferPtr buf, xmlDocPtr doc, xmlNodePtr cur, |
|
382 int format) { |
|
383 unsigned int use; |
|
384 int ret; |
|
385 xmlOutputBufferPtr outbuf; |
|
386 |
|
387 if (cur == NULL) { |
|
388 return (-1); |
|
389 } |
|
390 if (buf == NULL) { |
|
391 return (-1); |
|
392 } |
|
393 outbuf = (xmlOutputBufferPtr) xmlMalloc(sizeof(xmlOutputBuffer)); |
|
394 if (outbuf == NULL) { |
|
395 htmlSaveErrMemory("allocating HTML output buffer"); |
|
396 return (-1); |
|
397 } |
|
398 memset(outbuf, 0, (size_t) sizeof(xmlOutputBuffer)); |
|
399 outbuf->buffer = buf; |
|
400 outbuf->encoder = NULL; |
|
401 outbuf->writecallback = NULL; |
|
402 outbuf->closecallback = NULL; |
|
403 outbuf->context = NULL; |
|
404 outbuf->written = 0; |
|
405 |
|
406 use = buf->use; |
|
407 htmlNodeDumpFormatOutput(outbuf, doc, cur, NULL, format); |
|
408 xmlFree(outbuf); |
|
409 ret = buf->use - use; |
|
410 return (ret); |
|
411 } |
|
412 |
|
413 /** |
|
414 * htmlNodeDump: |
|
415 * @param buf the HTML buffer output |
|
416 * @param doc the document |
|
417 * @param cur the current node |
|
418 * |
|
419 * Dump an HTML node, recursive behaviour,children are printed too, |
|
420 * and formatting returns are added. |
|
421 * |
|
422 * Returns the number of byte written or -1 in case of error |
|
423 */ |
|
424 int |
|
425 htmlNodeDump(xmlBufferPtr buf, xmlDocPtr doc, xmlNodePtr cur) { |
|
426 xmlInitParser(); |
|
427 |
|
428 return(htmlNodeDumpFormat(buf, doc, cur, 1)); |
|
429 } |
|
430 |
|
431 /** |
|
432 * htmlNodeDumpFileFormat: |
|
433 * @param out the FILE pointer |
|
434 * @param doc the document |
|
435 * @param cur the current node |
|
436 * @param encoding the document encoding |
|
437 * @param format should formatting spaces been added |
|
438 * |
|
439 * Dump an HTML node, recursive behaviour,children are printed too. |
|
440 * |
|
441 |
|
442 * |
|
443 * returns: the number of byte written or -1 in case of failure. |
|
444 */ |
|
445 int |
|
446 htmlNodeDumpFileFormat(FILE *out, xmlDocPtr doc, |
|
447 xmlNodePtr cur, const char *encoding, int format) { |
|
448 xmlOutputBufferPtr buf; |
|
449 xmlCharEncodingHandlerPtr handler = NULL; |
|
450 int ret; |
|
451 |
|
452 xmlInitParser(); |
|
453 |
|
454 if (encoding != NULL) { |
|
455 xmlCharEncoding enc; |
|
456 |
|
457 enc = xmlParseCharEncoding(encoding); |
|
458 if (enc != XML_CHAR_ENCODING_UTF8) { |
|
459 handler = xmlFindCharEncodingHandler(encoding); |
|
460 if (handler == NULL) |
|
461 return(-1); |
|
462 } |
|
463 } |
|
464 |
|
465 /* |
|
466 * Fallback to HTML or ASCII when the encoding is unspecified |
|
467 */ |
|
468 if (handler == NULL) |
|
469 handler = xmlFindCharEncodingHandler("HTML"); |
|
470 if (handler == NULL) |
|
471 handler = xmlFindCharEncodingHandler("ascii"); |
|
472 |
|
473 /* |
|
474 * save the content to a temp buffer. |
|
475 */ |
|
476 buf = xmlOutputBufferCreateFile(out, handler); |
|
477 if (buf == NULL) return(0); |
|
478 |
|
479 htmlNodeDumpFormatOutput(buf, doc, cur, encoding, format); |
|
480 |
|
481 ret = xmlOutputBufferClose(buf); |
|
482 return(ret); |
|
483 } |
|
484 |
|
485 /** |
|
486 * htmlNodeDumpFile: |
|
487 * @param out the FILE pointer |
|
488 * @param doc the document |
|
489 * @param cur the current node |
|
490 * |
|
491 * Dump an HTML node, recursive behaviour,children are printed too, |
|
492 * and formatting returns are added. |
|
493 */ |
|
494 void |
|
495 htmlNodeDumpFile(FILE *out, xmlDocPtr doc, xmlNodePtr cur) { |
|
496 htmlNodeDumpFileFormat(out, doc, cur, NULL, 1); |
|
497 } |
|
498 |
|
499 /** |
|
500 * htmlDocDumpMemory: |
|
501 * @param cur the document |
|
502 * @param mem OUT: the memory pointer |
|
503 * @param size OUT: the memory length |
|
504 * |
|
505 * Dump an HTML document in memory and return the xmlChar * and it's size. |
|
506 * It's up to the caller to free the memory. |
|
507 */ |
|
508 void |
|
509 htmlDocDumpMemory(xmlDocPtr cur, xmlChar**mem, int *size) { |
|
510 xmlOutputBufferPtr buf; |
|
511 xmlCharEncodingHandlerPtr handler = NULL; |
|
512 const char *encoding; |
|
513 |
|
514 xmlInitParser(); |
|
515 |
|
516 if (cur == NULL) { |
|
517 *mem = NULL; |
|
518 *size = 0; |
|
519 return; |
|
520 } |
|
521 |
|
522 encoding = (const char *) htmlGetMetaEncoding(cur); |
|
523 |
|
524 if (encoding != NULL) { |
|
525 xmlCharEncoding enc; |
|
526 |
|
527 enc = xmlParseCharEncoding(encoding); |
|
528 if (enc != cur->charset) { |
|
529 if (cur->charset != XML_CHAR_ENCODING_UTF8) { |
|
530 /* |
|
531 * Not supported yet |
|
532 */ |
|
533 *mem = NULL; |
|
534 *size = 0; |
|
535 return; |
|
536 } |
|
537 |
|
538 handler = xmlFindCharEncodingHandler(encoding); |
|
539 if (handler == NULL) { |
|
540 *mem = NULL; |
|
541 *size = 0; |
|
542 return; |
|
543 } |
|
544 } |
|
545 } |
|
546 |
|
547 /* |
|
548 * Fallback to HTML or ASCII when the encoding is unspecified |
|
549 */ |
|
550 if (handler == NULL) |
|
551 handler = xmlFindCharEncodingHandler("HTML"); |
|
552 if (handler == NULL) |
|
553 handler = xmlFindCharEncodingHandler("ascii"); |
|
554 |
|
555 buf = xmlAllocOutputBuffer(handler); |
|
556 if (buf == NULL) { |
|
557 *mem = NULL; |
|
558 *size = 0; |
|
559 return; |
|
560 } |
|
561 |
|
562 htmlDocContentDumpOutput(buf, cur, NULL); |
|
563 xmlOutputBufferFlush(buf); |
|
564 if (buf->conv != NULL) { |
|
565 *size = buf->conv->use; |
|
566 *mem = xmlStrndup(buf->conv->content, *size); |
|
567 } else { |
|
568 *size = buf->buffer->use; |
|
569 *mem = xmlStrndup(buf->buffer->content, *size); |
|
570 } |
|
571 (void)xmlOutputBufferClose(buf); |
|
572 } |
|
573 |
|
574 |
|
575 /************************************************************************ |
|
576 * * |
|
577 * Dumping HTML tree content to an I/O output buffer * |
|
578 * * |
|
579 ************************************************************************/ |
|
580 |
|
581 /** |
|
582 * htmlNodeDumpOutput: |
|
583 * @param buf the HTML buffer output |
|
584 * @param doc the document |
|
585 * @param cur the current node |
|
586 * @param encoding the encoding string |
|
587 * |
|
588 * Dump an HTML node, recursive behaviour,children are printed too, |
|
589 * and formatting returns/spaces are added. |
|
590 */ |
|
591 void |
|
592 htmlNodeDumpOutput(xmlOutputBufferPtr buf, xmlDocPtr doc, |
|
593 xmlNodePtr cur, const char *encoding) { |
|
594 htmlNodeDumpFormatOutput(buf, doc, cur, encoding, 1); |
|
595 } |
|
596 #endif /* LIBXML_OUTPUT_ENABLED */ |
|
597 #endif /* defined(LIBXML_HTML_ENABLED) */ |
|
598 |
|
599 #if defined(LIBXML_HTML_ENABLED) || defined(XMLENGINE_XSLT) |
|
600 #ifdef LIBXML_OUTPUT_ENABLED |
|
601 /** |
|
602 * htmlSaveErr: |
|
603 * @param code the error number |
|
604 * @param node the location of the error. |
|
605 * @param extra extra informations |
|
606 * |
|
607 * Handle an out of memory condition |
|
608 */ |
|
609 static void |
|
610 htmlSaveErr(int code, xmlNodePtr node, const char *extra) |
|
611 { |
|
612 const char *msg = NULL; |
|
613 |
|
614 switch(code) { |
|
615 case XML_SAVE_NOT_UTF8: |
|
616 msg = "string is not in UTF-8"; |
|
617 break; |
|
618 case XML_SAVE_CHAR_INVALID: |
|
619 msg = "invalid character value"; |
|
620 break; |
|
621 case XML_SAVE_UNKNOWN_ENCODING: |
|
622 msg = "unknown encoding %s"; |
|
623 break; |
|
624 case XML_SAVE_NO_DOCTYPE: |
|
625 msg = "HTML has no DOCTYPE"; |
|
626 break; |
|
627 default: |
|
628 msg = "unexpected error number"; |
|
629 } |
|
630 __xmlSimpleError(XML_FROM_OUTPUT, code, node, msg, extra); |
|
631 } |
|
632 |
|
633 /** |
|
634 * htmlDtdDumpOutput: |
|
635 * @param buf the HTML buffer output |
|
636 * @param doc the document |
|
637 * @param encoding the encoding string |
|
638 * |
|
639 |
|
640 * |
|
641 * Dump the HTML document DTD, if any. |
|
642 */ |
|
643 static void |
|
644 htmlDtdDumpOutput(xmlOutputBufferPtr buf, xmlDocPtr doc, |
|
645 const char *encoding ATTRIBUTE_UNUSED) { |
|
646 xmlDtdPtr cur = doc->intSubset; |
|
647 |
|
648 if (cur == NULL) { |
|
649 htmlSaveErr(XML_SAVE_NO_DOCTYPE, (xmlNodePtr) doc, NULL); |
|
650 return; |
|
651 } |
|
652 xmlOutputBufferWriteString(buf, "<!DOCTYPE "); |
|
653 xmlOutputBufferWriteString(buf, (const char *)cur->name); |
|
654 if (cur->ExternalID != NULL) { |
|
655 xmlOutputBufferWriteString(buf, " PUBLIC "); |
|
656 xmlBufferWriteQuotedString(buf->buffer, cur->ExternalID); |
|
657 if (cur->SystemID != NULL) { |
|
658 xmlOutputBufferWriteString(buf, " "); |
|
659 xmlBufferWriteQuotedString(buf->buffer, cur->SystemID); |
|
660 } |
|
661 } else if (cur->SystemID != NULL) { |
|
662 xmlOutputBufferWriteString(buf, " SYSTEM "); |
|
663 xmlBufferWriteQuotedString(buf->buffer, cur->SystemID); |
|
664 } |
|
665 xmlOutputBufferWriteString(buf, ">\n"); |
|
666 } |
|
667 |
|
668 /** |
|
669 * htmlAttrDumpOutput: |
|
670 * @param buf the HTML buffer output |
|
671 * @param doc the document |
|
672 * @param cur the attribute pointer |
|
673 * @param encoding the encoding string |
|
674 * |
|
675 * Dump an HTML attribute |
|
676 */ |
|
677 static void |
|
678 htmlAttrDumpOutput(xmlOutputBufferPtr buf, xmlDocPtr doc, xmlAttrPtr cur, |
|
679 const char *encoding ATTRIBUTE_UNUSED) { |
|
680 xmlChar *value; |
|
681 |
|
682 /* |
|
683 |
|
684 |
|
685 |
|
686 */ |
|
687 |
|
688 if (cur == NULL) { |
|
689 return; |
|
690 } |
|
691 xmlOutputBufferWriteString(buf, " "); |
|
692 if ((cur->ns != NULL) && (cur->ns->prefix != NULL)) { |
|
693 xmlOutputBufferWriteString(buf, (const char *)cur->ns->prefix); |
|
694 xmlOutputBufferWriteString(buf, ":"); |
|
695 } |
|
696 xmlOutputBufferWriteString(buf, (const char *)cur->name); |
|
697 if ((cur->children != NULL) && (!htmlIsBooleanAttr(cur->name))) { |
|
698 value = xmlNodeListGetString(doc, cur->children, 0); |
|
699 if (value) { |
|
700 xmlOutputBufferWriteString(buf, "="); |
|
701 if ((cur->ns == NULL) && (cur->parent != NULL) && |
|
702 (cur->parent->ns == NULL) && |
|
703 ((!xmlStrcasecmp(cur->name, BAD_CAST "href")) || |
|
704 (!xmlStrcasecmp(cur->name, BAD_CAST "action")) || |
|
705 (!xmlStrcasecmp(cur->name, BAD_CAST "src")))) { |
|
706 xmlChar *escaped; |
|
707 xmlChar *tmp = value; |
|
708 |
|
709 while (IS_BLANK_CH(*tmp)) tmp++; |
|
710 |
|
711 escaped = xmlURIEscapeStr(tmp, BAD_CAST"@/:=?;#%&,+"); |
|
712 if (escaped != NULL) { |
|
713 xmlBufferWriteQuotedString(buf->buffer, escaped); |
|
714 xmlFree(escaped); |
|
715 } else { |
|
716 xmlBufferWriteQuotedString(buf->buffer, value); |
|
717 } |
|
718 } else { |
|
719 xmlBufferWriteQuotedString(buf->buffer, value); |
|
720 } |
|
721 xmlFree(value); |
|
722 } else { |
|
723 xmlOutputBufferWriteString(buf, "=\"\""); |
|
724 } |
|
725 } |
|
726 } |
|
727 |
|
728 /** |
|
729 * htmlAttrListDumpOutput: |
|
730 * @param buf the HTML buffer output |
|
731 * @param doc the document |
|
732 * @param cur the first attribute pointer |
|
733 * @param encoding the encoding string |
|
734 * |
|
735 * Dump a list of HTML attributes |
|
736 */ |
|
737 static void |
|
738 htmlAttrListDumpOutput(xmlOutputBufferPtr buf, xmlDocPtr doc, xmlAttrPtr cur, const char *encoding) { |
|
739 if (cur == NULL) { |
|
740 return; |
|
741 } |
|
742 while (cur != NULL) { |
|
743 htmlAttrDumpOutput(buf, doc, cur, encoding); |
|
744 cur = cur->next; |
|
745 } |
|
746 } |
|
747 |
|
748 /** |
|
749 * htmlNodeListDumpOutput: |
|
750 * @param buf the HTML buffer output |
|
751 * @param doc the document |
|
752 * @param cur the first node |
|
753 * @param encoding the encoding string |
|
754 * @param format should formatting spaces been added |
|
755 * |
|
756 * Dump an HTML node list, recursive behaviour,children are printed too. |
|
757 */ |
|
758 static void |
|
759 htmlNodeListDumpOutput(xmlOutputBufferPtr buf, xmlDocPtr doc, |
|
760 xmlNodePtr cur, const char *encoding, int format) { |
|
761 if (cur == NULL) { |
|
762 return; |
|
763 } |
|
764 while (cur != NULL) { |
|
765 htmlNodeDumpFormatOutput(buf, doc, cur, encoding, format); |
|
766 cur = cur->next; |
|
767 } |
|
768 } |
|
769 |
|
770 /** |
|
771 * htmlNodeDumpFormatOutput: |
|
772 * @param buf the HTML buffer output |
|
773 * @param doc the document |
|
774 * @param cur the current node |
|
775 * @param encoding the encoding string |
|
776 * @param format should formatting spaces been added |
|
777 * |
|
778 * Dump an HTML node, recursive behaviour,children are printed too. |
|
779 */ |
|
780 XMLPUBFUNEXPORT void |
|
781 htmlNodeDumpFormatOutput(xmlOutputBufferPtr buf, xmlDocPtr doc, |
|
782 xmlNodePtr cur, const char *encoding, int format) { |
|
783 const htmlElemDesc * info; |
|
784 |
|
785 xmlInitParser(); |
|
786 |
|
787 if (cur == NULL) { |
|
788 return; |
|
789 } |
|
790 /* |
|
791 * Special cases. |
|
792 */ |
|
793 if (cur->type == XML_DTD_NODE) |
|
794 return; |
|
795 if (cur->type == XML_HTML_DOCUMENT_NODE) { |
|
796 htmlDocContentDumpOutput(buf, (xmlDocPtr) cur, encoding); |
|
797 return; |
|
798 } |
|
799 if (cur->type == HTML_TEXT_NODE) { |
|
800 if (cur->content) { |
|
801 if ( |
|
802 ( |
|
803 (cur->name == (const xmlChar*) xmlStringText ) || |
|
804 (cur->name != (const xmlChar*) xmlStringTextNoenc) |
|
805 ) |
|
806 && |
|
807 (!cur->parent || |
|
808 ( |
|
809 xmlStrcasecmp(cur->parent->name, BAD_CAST "script") |
|
810 && |
|
811 xmlStrcasecmp(cur->parent->name, BAD_CAST "style") |
|
812 ) |
|
813 ) |
|
814 ) |
|
815 { |
|
816 xmlChar* buffer; |
|
817 |
|
818 buffer = xmlEncodeEntitiesReentrant(doc, cur->content); |
|
819 if (buffer) { |
|
820 xmlOutputBufferWriteString(buf, (const char *)buffer); |
|
821 xmlFree(buffer); |
|
822 } |
|
823 } else { |
|
824 xmlOutputBufferWriteString(buf, (const char *)cur->content); |
|
825 } |
|
826 } |
|
827 return; |
|
828 } |
|
829 if (cur->type == HTML_COMMENT_NODE) { |
|
830 if (cur->content != NULL) { |
|
831 xmlOutputBufferWriteString(buf, "<!--"); |
|
832 xmlOutputBufferWriteString(buf, (const char *)cur->content); |
|
833 xmlOutputBufferWriteString(buf, "-->"); |
|
834 } |
|
835 return; |
|
836 } |
|
837 |
|
838 if (cur->type == HTML_PI_NODE) { |
|
839 if (cur->name == NULL) |
|
840 return; |
|
841 xmlOutputBufferWriteString(buf, "<?"); |
|
842 xmlOutputBufferWriteString(buf, (const char *)cur->name); |
|
843 if (cur->content != NULL) { |
|
844 xmlOutputBufferWriteString(buf, " "); |
|
845 xmlOutputBufferWriteString(buf, (const char *)cur->content); |
|
846 } |
|
847 xmlOutputBufferWriteString(buf, ">"); |
|
848 return; |
|
849 } |
|
850 |
|
851 if (cur->type == HTML_ENTITY_REF_NODE) { |
|
852 xmlOutputBufferWriteString(buf, "&"); |
|
853 xmlOutputBufferWriteString(buf, (const char *)cur->name); |
|
854 xmlOutputBufferWriteString(buf, ";"); |
|
855 return; |
|
856 } |
|
857 |
|
858 if (cur->type == HTML_PRESERVE_NODE) { |
|
859 if (cur->content != NULL) { |
|
860 xmlOutputBufferWriteString(buf, (const char *)cur->content); |
|
861 } |
|
862 return; |
|
863 } |
|
864 |
|
865 /* |
|
866 * Get specific HTML info for that node. |
|
867 */ |
|
868 info = cur->ns ? NULL : htmlTagLookup(cur->name); |
|
869 |
|
870 xmlOutputBufferWriteString(buf, "<"); |
|
871 if ((cur->ns != NULL) && (cur->ns->prefix != NULL)) { |
|
872 xmlOutputBufferWriteString(buf, (const char *)cur->ns->prefix); |
|
873 xmlOutputBufferWriteString(buf, ":"); |
|
874 } |
|
875 xmlOutputBufferWriteString(buf, (const char *)cur->name); |
|
876 if (cur->nsDef) |
|
877 xmlNsListDumpOutput(buf, cur->nsDef); |
|
878 if (cur->properties != NULL) |
|
879 htmlAttrListDumpOutput(buf, doc, cur->properties, encoding); |
|
880 |
|
881 if ((info != NULL) && (info->empty)) { |
|
882 xmlOutputBufferWriteString(buf, ">"); |
|
883 if ((format) && (!info->isinline) && (cur->next != NULL)) { |
|
884 if ((cur->next->type != HTML_TEXT_NODE) && |
|
885 (cur->next->type != HTML_ENTITY_REF_NODE) && |
|
886 (cur->parent != NULL) && |
|
887 (cur->parent->name != NULL) && |
|
888 (cur->parent->name[0] != 'p')) /* p, pre, param */ |
|
889 xmlOutputBufferWriteString(buf, "\n"); |
|
890 } |
|
891 return; |
|
892 } |
|
893 |
|
894 if (((cur->type == XML_ELEMENT_NODE) || (cur->content == NULL)) && |
|
895 (cur->children == NULL)) |
|
896 { |
|
897 if ((info != NULL) && (info->saveEndTag != 0) && |
|
898 (xmlStrcmp(BAD_CAST info->name, BAD_CAST "html")) && |
|
899 (xmlStrcmp(BAD_CAST info->name, BAD_CAST "body"))) |
|
900 { |
|
901 xmlOutputBufferWriteString(buf, ">"); |
|
902 } else { |
|
903 xmlOutputBufferWriteString(buf, "></"); |
|
904 if ((cur->ns != NULL) && (cur->ns->prefix != NULL)) { |
|
905 xmlOutputBufferWriteString(buf, (const char *)cur->ns->prefix); |
|
906 xmlOutputBufferWriteString(buf, ":"); |
|
907 } |
|
908 xmlOutputBufferWriteString(buf, (const char *)cur->name); |
|
909 xmlOutputBufferWriteString(buf, ">"); |
|
910 } |
|
911 if ((format) && (cur->next != NULL) && |
|
912 (info != NULL) && (!info->isinline)) |
|
913 { |
|
914 if ((cur->next->type != HTML_TEXT_NODE) && |
|
915 (cur->next->type != HTML_ENTITY_REF_NODE) && |
|
916 (cur->parent != NULL) && |
|
917 (cur->parent->name != NULL) && |
|
918 (cur->parent->name[0] != 'p')) /* p, pre, param */ |
|
919 xmlOutputBufferWriteString(buf, "\n"); |
|
920 } |
|
921 return; |
|
922 } |
|
923 xmlOutputBufferWriteString(buf, ">"); |
|
924 if ((cur->type != XML_ELEMENT_NODE) && |
|
925 (cur->content != NULL)) { |
|
926 /* |
|
927 * Uses the OutputBuffer property to automatically convert |
|
928 * invalids to charrefs |
|
929 */ |
|
930 |
|
931 xmlOutputBufferWriteString(buf, (const char *) cur->content); |
|
932 } |
|
933 if (cur->children != NULL) { |
|
934 if ((format) && (info != NULL) && (!info->isinline) && |
|
935 (cur->children->type != HTML_TEXT_NODE) && |
|
936 (cur->children->type != HTML_ENTITY_REF_NODE) && |
|
937 (cur->children != cur->last) && |
|
938 (cur->name != NULL) && |
|
939 (cur->name[0] != 'p')) /* p, pre, param */ |
|
940 xmlOutputBufferWriteString(buf, "\n"); |
|
941 htmlNodeListDumpOutput(buf, doc, cur->children, encoding, format); |
|
942 if ((format) && (info != NULL) && (!info->isinline) && |
|
943 (cur->last->type != HTML_TEXT_NODE) && |
|
944 (cur->last->type != HTML_ENTITY_REF_NODE) && |
|
945 (cur->children != cur->last) && |
|
946 (cur->name != NULL) && |
|
947 (cur->name[0] != 'p')) /* p, pre, param */ |
|
948 xmlOutputBufferWriteString(buf, "\n"); |
|
949 } |
|
950 xmlOutputBufferWriteString(buf, "</"); |
|
951 if ((cur->ns != NULL) && (cur->ns->prefix != NULL)) { |
|
952 xmlOutputBufferWriteString(buf, (const char *)cur->ns->prefix); |
|
953 xmlOutputBufferWriteString(buf, ":"); |
|
954 } |
|
955 xmlOutputBufferWriteString(buf, (const char *)cur->name); |
|
956 xmlOutputBufferWriteString(buf, ">"); |
|
957 if ((format) && (info != NULL) && (!info->isinline) && |
|
958 (cur->next != NULL)) { |
|
959 if ((cur->next->type != HTML_TEXT_NODE) && |
|
960 (cur->next->type != HTML_ENTITY_REF_NODE) && |
|
961 (cur->parent != NULL) && |
|
962 (cur->parent->name != NULL) && |
|
963 (cur->parent->name[0] != 'p')) /* p, pre, param */ |
|
964 xmlOutputBufferWriteString(buf, "\n"); |
|
965 } |
|
966 } |
|
967 |
|
968 |
|
969 /** |
|
970 * htmlDocContentDumpFormatOutput: |
|
971 * @param buf the HTML buffer output |
|
972 * @param cur the document |
|
973 * @param encoding the encoding string |
|
974 * @param format should formatting spaces been added |
|
975 * |
|
976 * Dump an HTML document. |
|
977 */ |
|
978 XMLPUBFUNEXPORT void |
|
979 htmlDocContentDumpFormatOutput(xmlOutputBufferPtr buf, xmlDocPtr cur, |
|
980 const char *encoding, int format) { |
|
981 int type; |
|
982 |
|
983 xmlInitParser(); |
|
984 |
|
985 /* |
|
986 * force to output the stuff as HTML, especially for entities |
|
987 */ |
|
988 type = cur->type; |
|
989 cur->type = XML_HTML_DOCUMENT_NODE; |
|
990 if (cur->intSubset != NULL) { |
|
991 htmlDtdDumpOutput(buf, cur, NULL); |
|
992 } |
|
993 if (cur->children != NULL) { |
|
994 htmlNodeListDumpOutput(buf, cur, cur->children, encoding, format); |
|
995 } |
|
996 xmlOutputBufferWriteString(buf, "\n"); |
|
997 cur->type = (xmlElementType) type; |
|
998 } |
|
999 |
|
1000 /** |
|
1001 * htmlDocContentDumpOutput: |
|
1002 * @param buf the HTML buffer output |
|
1003 * @param cur the document |
|
1004 * @param encoding the encoding string |
|
1005 * |
|
1006 * Dump an HTML document. Formating return/spaces are added. |
|
1007 */ |
|
1008 XMLPUBFUNEXPORT void |
|
1009 htmlDocContentDumpOutput(xmlOutputBufferPtr buf, xmlDocPtr cur, |
|
1010 const char *encoding) { |
|
1011 htmlDocContentDumpFormatOutput(buf, cur, encoding, 1); |
|
1012 } |
|
1013 |
|
1014 #endif /* LIBXML_OUTPUT_ENABLED */ |
|
1015 #endif /* defined(IBXML_HTML_ENABLED) || defined(XMLENGINE_XSLT) */ |
|
1016 |
|
1017 #ifdef LIBXML_HTML_ENABLED |
|
1018 #ifdef LIBXML_OUTPUT_ENABLED |
|
1019 |
|
1020 /************************************************************************ |
|
1021 * * |
|
1022 * Saving functions front-ends * |
|
1023 * * |
|
1024 ************************************************************************/ |
|
1025 |
|
1026 /** |
|
1027 * htmlDocDump: |
|
1028 * @param f the FILE* |
|
1029 * @param cur the document |
|
1030 * |
|
1031 * Dump an HTML document to an open FILE. |
|
1032 * |
|
1033 * returns: the number of byte written or -1 in case of failure. |
|
1034 */ |
|
1035 int |
|
1036 htmlDocDump(FILE *f, xmlDocPtr cur) { |
|
1037 xmlOutputBufferPtr buf; |
|
1038 xmlCharEncodingHandlerPtr handler = NULL; |
|
1039 const char *encoding; |
|
1040 int ret; |
|
1041 |
|
1042 xmlInitParser(); |
|
1043 |
|
1044 if (cur == NULL) { |
|
1045 return(-1); |
|
1046 } |
|
1047 |
|
1048 encoding = (const char *) htmlGetMetaEncoding(cur); |
|
1049 |
|
1050 if (encoding != NULL) { |
|
1051 xmlCharEncoding enc; |
|
1052 |
|
1053 enc = xmlParseCharEncoding(encoding); |
|
1054 if (enc != cur->charset) { |
|
1055 if (cur->charset != XML_CHAR_ENCODING_UTF8) { |
|
1056 /* |
|
1057 * Not supported yet |
|
1058 */ |
|
1059 return(-1); |
|
1060 } |
|
1061 |
|
1062 handler = xmlFindCharEncodingHandler(encoding); |
|
1063 if (handler == NULL) |
|
1064 return(-1); |
|
1065 } |
|
1066 } |
|
1067 |
|
1068 /* |
|
1069 * Fallback to HTML or ASCII when the encoding is unspecified |
|
1070 */ |
|
1071 if (handler == NULL) |
|
1072 handler = xmlFindCharEncodingHandler("HTML"); |
|
1073 if (handler == NULL) |
|
1074 handler = xmlFindCharEncodingHandler("ascii"); |
|
1075 |
|
1076 buf = xmlOutputBufferCreateFile(f, handler); |
|
1077 if (buf == NULL) return(-1); |
|
1078 htmlDocContentDumpOutput(buf, cur, NULL); |
|
1079 |
|
1080 ret = xmlOutputBufferClose(buf); |
|
1081 return(ret); |
|
1082 } |
|
1083 |
|
1084 /** |
|
1085 * htmlSaveFile: |
|
1086 * @param filename the filename (or URL) |
|
1087 * @param cur the document |
|
1088 * |
|
1089 * Dump an HTML document to a file. If filename is "-" the stdout file is |
|
1090 * used. |
|
1091 * returns: the number of byte written or -1 in case of failure. |
|
1092 */ |
|
1093 int |
|
1094 htmlSaveFile(const char *filename, xmlDocPtr cur) { |
|
1095 xmlOutputBufferPtr buf; |
|
1096 xmlCharEncodingHandlerPtr handler = NULL; |
|
1097 const char *encoding; |
|
1098 int ret; |
|
1099 |
|
1100 xmlInitParser(); |
|
1101 |
|
1102 encoding = (const char *) htmlGetMetaEncoding(cur); |
|
1103 |
|
1104 if (encoding != NULL) { |
|
1105 xmlCharEncoding enc; |
|
1106 |
|
1107 enc = xmlParseCharEncoding(encoding); |
|
1108 if (enc != cur->charset) { |
|
1109 if (cur->charset != XML_CHAR_ENCODING_UTF8) { |
|
1110 /* |
|
1111 * Not supported yet |
|
1112 */ |
|
1113 return(-1); |
|
1114 } |
|
1115 |
|
1116 handler = xmlFindCharEncodingHandler(encoding); |
|
1117 if (handler == NULL) |
|
1118 return(-1); |
|
1119 } |
|
1120 } |
|
1121 |
|
1122 /* |
|
1123 * Fallback to HTML or ASCII when the encoding is unspecified |
|
1124 */ |
|
1125 if (handler == NULL) |
|
1126 handler = xmlFindCharEncodingHandler("HTML"); |
|
1127 if (handler == NULL) |
|
1128 handler = xmlFindCharEncodingHandler("ascii"); |
|
1129 |
|
1130 /* |
|
1131 * save the content to a temp buffer. |
|
1132 */ |
|
1133 buf = xmlOutputBufferCreateFilename(filename, handler, cur->compression); |
|
1134 if (buf == NULL) return(0); |
|
1135 |
|
1136 htmlDocContentDumpOutput(buf, cur, NULL); |
|
1137 |
|
1138 ret = xmlOutputBufferClose(buf); |
|
1139 return(ret); |
|
1140 } |
|
1141 |
|
1142 /** |
|
1143 * htmlSaveFileFormat: |
|
1144 * @param filename the filename |
|
1145 * @param cur the document |
|
1146 * @param format should formatting spaces been added |
|
1147 * @param encoding the document encoding |
|
1148 * |
|
1149 * Dump an HTML document to a file using a given encoding. |
|
1150 * |
|
1151 * returns: the number of byte written or -1 in case of failure. |
|
1152 */ |
|
1153 int |
|
1154 htmlSaveFileFormat(const char *filename, xmlDocPtr cur, |
|
1155 const char *encoding, int format) { |
|
1156 xmlOutputBufferPtr buf; |
|
1157 xmlCharEncodingHandlerPtr handler = NULL; |
|
1158 int ret; |
|
1159 |
|
1160 xmlInitParser(); |
|
1161 |
|
1162 if (encoding != NULL) { |
|
1163 xmlCharEncoding enc; |
|
1164 |
|
1165 enc = xmlParseCharEncoding(encoding); |
|
1166 if (enc != cur->charset) { |
|
1167 if (cur->charset != XML_CHAR_ENCODING_UTF8) { |
|
1168 /* |
|
1169 * Not supported yet |
|
1170 */ |
|
1171 return(-1); |
|
1172 } |
|
1173 |
|
1174 handler = xmlFindCharEncodingHandler(encoding); |
|
1175 if (handler == NULL) |
|
1176 return(-1); |
|
1177 htmlSetMetaEncoding(cur, (const xmlChar *) encoding); |
|
1178 } |
|
1179 } else { |
|
1180 htmlSetMetaEncoding(cur, (const xmlChar *) "UTF-8"); |
|
1181 } |
|
1182 |
|
1183 /* |
|
1184 * Fallback to HTML or ASCII when the encoding is unspecified |
|
1185 */ |
|
1186 if (handler == NULL){ |
|
1187 handler = xmlFindCharEncodingHandler("HTML"); |
|
1188 if (handler == NULL) |
|
1189 handler = xmlFindCharEncodingHandler("ascii"); |
|
1190 } |
|
1191 /* |
|
1192 * save the content to a temp buffer. |
|
1193 */ |
|
1194 buf = xmlOutputBufferCreateFilename(filename, handler, 0); |
|
1195 if (buf == NULL) return(0); |
|
1196 |
|
1197 htmlDocContentDumpFormatOutput(buf, cur, encoding, format); |
|
1198 |
|
1199 ret = xmlOutputBufferClose(buf); |
|
1200 return(ret); |
|
1201 } |
|
1202 |
|
1203 /** |
|
1204 * htmlSaveFileEnc: |
|
1205 * @param filename the filename |
|
1206 * @param cur the document |
|
1207 * @param encoding the document encoding |
|
1208 * |
|
1209 * Dump an HTML document to a file using a given encoding |
|
1210 * and formatting returns/spaces are added. |
|
1211 * |
|
1212 * returns: the number of byte written or -1 in case of failure. |
|
1213 */ |
|
1214 int |
|
1215 htmlSaveFileEnc(const char *filename, xmlDocPtr cur, const char *encoding) { |
|
1216 return(htmlSaveFileFormat(filename, cur, encoding, 1)); |
|
1217 } |
|
1218 |
|
1219 #endif /* LIBXML_OUTPUT_ENABLED */ |
|
1220 |
|
1221 #endif /* LIBXML_HTML_ENABLED */ |
|
1222 |