1 /*
2 * entities.c : implementation for the XML entities handling
3 *
4 * See Copyright for the status of this software.
5 *
6 * daniel@veillard.com
7 */
8
9 /* To avoid EBCDIC trouble when parsing on zOS */
10 #if defined(__MVS__)
11 #pragma convert("ISO8859-1")
12 #endif
13
14 #define IN_LIBXML
15 #include "libxml.h"
16
17 #include <string.h>
18 #include <stdlib.h>
19
20 #include <libxml/xmlmemory.h>
21 #include <libxml/hash.h>
22 #include <libxml/entities.h>
23 #include <libxml/parser.h>
24 #include <libxml/parserInternals.h>
25 #include <libxml/xmlerror.h>
26 #include <libxml/dict.h>
27
28 #include "private/entities.h"
29 #include "private/error.h"
30
31 /*
32 * The XML predefined entities.
33 */
34
35 static xmlEntity xmlEntityLt = {
36 NULL, XML_ENTITY_DECL, BAD_CAST "lt",
37 NULL, NULL, NULL, NULL, NULL, NULL,
38 BAD_CAST "<", BAD_CAST "<", 1,
39 XML_INTERNAL_PREDEFINED_ENTITY,
40 NULL, NULL, NULL, NULL, 0, 0, 0
41 };
42 static xmlEntity xmlEntityGt = {
43 NULL, XML_ENTITY_DECL, BAD_CAST "gt",
44 NULL, NULL, NULL, NULL, NULL, NULL,
45 BAD_CAST ">", BAD_CAST ">", 1,
46 XML_INTERNAL_PREDEFINED_ENTITY,
47 NULL, NULL, NULL, NULL, 0, 0, 0
48 };
49 static xmlEntity xmlEntityAmp = {
50 NULL, XML_ENTITY_DECL, BAD_CAST "amp",
51 NULL, NULL, NULL, NULL, NULL, NULL,
52 BAD_CAST "&", BAD_CAST "&", 1,
53 XML_INTERNAL_PREDEFINED_ENTITY,
54 NULL, NULL, NULL, NULL, 0, 0, 0
55 };
56 static xmlEntity xmlEntityQuot = {
57 NULL, XML_ENTITY_DECL, BAD_CAST "quot",
58 NULL, NULL, NULL, NULL, NULL, NULL,
59 BAD_CAST "\"", BAD_CAST "\"", 1,
60 XML_INTERNAL_PREDEFINED_ENTITY,
61 NULL, NULL, NULL, NULL, 0, 0, 0
62 };
63 static xmlEntity xmlEntityApos = {
64 NULL, XML_ENTITY_DECL, BAD_CAST "apos",
65 NULL, NULL, NULL, NULL, NULL, NULL,
66 BAD_CAST "'", BAD_CAST "'", 1,
67 XML_INTERNAL_PREDEFINED_ENTITY,
68 NULL, NULL, NULL, NULL, 0, 0, 0
69 };
70
71 /**
72 * xmlEntitiesErrMemory:
73 * @extra: extra information
74 *
75 * Handle an out of memory condition
76 */
77 static void
xmlEntitiesErrMemory(const char * extra)78 xmlEntitiesErrMemory(const char *extra)
79 {
80 __xmlSimpleError(XML_FROM_TREE, XML_ERR_NO_MEMORY, NULL, NULL, extra);
81 }
82
83 /**
84 * xmlEntitiesErr:
85 * @code: the error code
86 * @msg: the message
87 *
88 * Raise an error.
89 */
90 static void LIBXML_ATTR_FORMAT(2,0)
xmlEntitiesErr(xmlParserErrors code,const char * msg)91 xmlEntitiesErr(xmlParserErrors code, const char *msg)
92 {
93 __xmlSimpleError(XML_FROM_TREE, code, NULL, msg, NULL);
94 }
95
96 /**
97 * xmlEntitiesWarn:
98 * @code: the error code
99 * @msg: the message
100 *
101 * Raise a warning.
102 */
103 static void LIBXML_ATTR_FORMAT(2,0)
xmlEntitiesWarn(xmlParserErrors code,const char * msg,const xmlChar * str1)104 xmlEntitiesWarn(xmlParserErrors code, const char *msg, const xmlChar *str1)
105 {
106 __xmlRaiseError(NULL, NULL, NULL,
107 NULL, NULL, XML_FROM_TREE, code,
108 XML_ERR_WARNING, NULL, 0,
109 (const char *)str1, NULL, NULL, 0, 0,
110 msg, (const char *)str1, NULL);
111 }
112
113 /*
114 * xmlFreeEntity : clean-up an entity record.
115 */
116 void
xmlFreeEntity(xmlEntityPtr entity)117 xmlFreeEntity(xmlEntityPtr entity)
118 {
119 xmlDictPtr dict = NULL;
120
121 if (entity == NULL)
122 return;
123
124 if (entity->doc != NULL)
125 dict = entity->doc->dict;
126
127
128 if ((entity->children) && (entity->owner == 1) &&
129 (entity == (xmlEntityPtr) entity->children->parent))
130 xmlFreeNodeList(entity->children);
131 if ((entity->name != NULL) &&
132 ((dict == NULL) || (!xmlDictOwns(dict, entity->name))))
133 xmlFree((char *) entity->name);
134 if (entity->ExternalID != NULL)
135 xmlFree((char *) entity->ExternalID);
136 if (entity->SystemID != NULL)
137 xmlFree((char *) entity->SystemID);
138 if (entity->URI != NULL)
139 xmlFree((char *) entity->URI);
140 if (entity->content != NULL)
141 xmlFree((char *) entity->content);
142 if (entity->orig != NULL)
143 xmlFree((char *) entity->orig);
144 xmlFree(entity);
145 }
146
147 /*
148 * xmlCreateEntity:
149 *
150 * internal routine doing the entity node structures allocations
151 */
152 static xmlEntityPtr
xmlCreateEntity(xmlDictPtr dict,const xmlChar * name,int type,const xmlChar * ExternalID,const xmlChar * SystemID,const xmlChar * content)153 xmlCreateEntity(xmlDictPtr dict, const xmlChar *name, int type,
154 const xmlChar *ExternalID, const xmlChar *SystemID,
155 const xmlChar *content) {
156 xmlEntityPtr ret;
157
158 ret = (xmlEntityPtr) xmlMalloc(sizeof(xmlEntity));
159 if (ret == NULL) {
160 xmlEntitiesErrMemory("xmlCreateEntity: malloc failed");
161 return(NULL);
162 }
163 memset(ret, 0, sizeof(xmlEntity));
164 ret->type = XML_ENTITY_DECL;
165
166 /*
167 * fill the structure.
168 */
169 ret->etype = (xmlEntityType) type;
170 if (dict == NULL) {
171 ret->name = xmlStrdup(name);
172 if (ExternalID != NULL)
173 ret->ExternalID = xmlStrdup(ExternalID);
174 if (SystemID != NULL)
175 ret->SystemID = xmlStrdup(SystemID);
176 } else {
177 ret->name = xmlDictLookup(dict, name, -1);
178 ret->ExternalID = xmlStrdup(ExternalID);
179 ret->SystemID = xmlStrdup(SystemID);
180 }
181 if (content != NULL) {
182 ret->length = xmlStrlen(content);
183 ret->content = xmlStrndup(content, ret->length);
184 } else {
185 ret->length = 0;
186 ret->content = NULL;
187 }
188 ret->URI = NULL; /* to be computed by the layer knowing
189 the defining entity */
190 ret->orig = NULL;
191 ret->owner = 0;
192
193 return(ret);
194 }
195
196 /*
197 * xmlAddEntity : register a new entity for an entities table.
198 */
199 static xmlEntityPtr
xmlAddEntity(xmlDtdPtr dtd,const xmlChar * name,int type,const xmlChar * ExternalID,const xmlChar * SystemID,const xmlChar * content)200 xmlAddEntity(xmlDtdPtr dtd, const xmlChar *name, int type,
201 const xmlChar *ExternalID, const xmlChar *SystemID,
202 const xmlChar *content) {
203 xmlDictPtr dict = NULL;
204 xmlEntitiesTablePtr table = NULL;
205 xmlEntityPtr ret, predef;
206
207 if (name == NULL)
208 return(NULL);
209 if (dtd == NULL)
210 return(NULL);
211 if (dtd->doc != NULL)
212 dict = dtd->doc->dict;
213
214 switch (type) {
215 case XML_INTERNAL_GENERAL_ENTITY:
216 case XML_EXTERNAL_GENERAL_PARSED_ENTITY:
217 case XML_EXTERNAL_GENERAL_UNPARSED_ENTITY:
218 predef = xmlGetPredefinedEntity(name);
219 if (predef != NULL) {
220 int valid = 0;
221
222 /* 4.6 Predefined Entities */
223 if ((type == XML_INTERNAL_GENERAL_ENTITY) &&
224 (content != NULL)) {
225 int c = predef->content[0];
226
227 if (((content[0] == c) && (content[1] == 0)) &&
228 ((c == '>') || (c == '\'') || (c == '"'))) {
229 valid = 1;
230 } else if ((content[0] == '&') && (content[1] == '#')) {
231 if (content[2] == 'x') {
232 xmlChar *hex = BAD_CAST "0123456789ABCDEF";
233 xmlChar ref[] = "00;";
234
235 ref[0] = hex[c / 16 % 16];
236 ref[1] = hex[c % 16];
237 if (xmlStrcasecmp(&content[3], ref) == 0)
238 valid = 1;
239 } else {
240 xmlChar ref[] = "00;";
241
242 ref[0] = '0' + c / 10 % 10;
243 ref[1] = '0' + c % 10;
244 if (xmlStrEqual(&content[2], ref))
245 valid = 1;
246 }
247 }
248 }
249 if (!valid) {
250 xmlEntitiesWarn(XML_ERR_ENTITY_PROCESSING,
251 "xmlAddEntity: invalid redeclaration of predefined"
252 " entity '%s'", name);
253 return(NULL);
254 }
255 }
256 if (dtd->entities == NULL)
257 dtd->entities = xmlHashCreateDict(0, dict);
258 table = dtd->entities;
259 break;
260 case XML_INTERNAL_PARAMETER_ENTITY:
261 case XML_EXTERNAL_PARAMETER_ENTITY:
262 if (dtd->pentities == NULL)
263 dtd->pentities = xmlHashCreateDict(0, dict);
264 table = dtd->pentities;
265 break;
266 case XML_INTERNAL_PREDEFINED_ENTITY:
267 return(NULL);
268 }
269 if (table == NULL)
270 return(NULL);
271 ret = xmlCreateEntity(dict, name, type, ExternalID, SystemID, content);
272 if (ret == NULL)
273 return(NULL);
274 ret->doc = dtd->doc;
275
276 if (xmlHashAddEntry(table, name, ret)) {
277 /*
278 * entity was already defined at another level.
279 */
280 xmlFreeEntity(ret);
281 return(NULL);
282 }
283 return(ret);
284 }
285
286 /**
287 * xmlGetPredefinedEntity:
288 * @name: the entity name
289 *
290 * Check whether this name is an predefined entity.
291 *
292 * Returns NULL if not, otherwise the entity
293 */
294 xmlEntityPtr
xmlGetPredefinedEntity(const xmlChar * name)295 xmlGetPredefinedEntity(const xmlChar *name) {
296 if (name == NULL) return(NULL);
297 switch (name[0]) {
298 case 'l':
299 if (xmlStrEqual(name, BAD_CAST "lt"))
300 return(&xmlEntityLt);
301 break;
302 case 'g':
303 if (xmlStrEqual(name, BAD_CAST "gt"))
304 return(&xmlEntityGt);
305 break;
306 case 'a':
307 if (xmlStrEqual(name, BAD_CAST "amp"))
308 return(&xmlEntityAmp);
309 if (xmlStrEqual(name, BAD_CAST "apos"))
310 return(&xmlEntityApos);
311 break;
312 case 'q':
313 if (xmlStrEqual(name, BAD_CAST "quot"))
314 return(&xmlEntityQuot);
315 break;
316 default:
317 break;
318 }
319 return(NULL);
320 }
321
322 /**
323 * xmlAddDtdEntity:
324 * @doc: the document
325 * @name: the entity name
326 * @type: the entity type XML_xxx_yyy_ENTITY
327 * @ExternalID: the entity external ID if available
328 * @SystemID: the entity system ID if available
329 * @content: the entity content
330 *
331 * Register a new entity for this document DTD external subset.
332 *
333 * Returns a pointer to the entity or NULL in case of error
334 */
335 xmlEntityPtr
xmlAddDtdEntity(xmlDocPtr doc,const xmlChar * name,int type,const xmlChar * ExternalID,const xmlChar * SystemID,const xmlChar * content)336 xmlAddDtdEntity(xmlDocPtr doc, const xmlChar *name, int type,
337 const xmlChar *ExternalID, const xmlChar *SystemID,
338 const xmlChar *content) {
339 xmlEntityPtr ret;
340 xmlDtdPtr dtd;
341
342 if (doc == NULL) {
343 xmlEntitiesErr(XML_DTD_NO_DOC,
344 "xmlAddDtdEntity: document is NULL");
345 return(NULL);
346 }
347 if (doc->extSubset == NULL) {
348 xmlEntitiesErr(XML_DTD_NO_DTD,
349 "xmlAddDtdEntity: document without external subset");
350 return(NULL);
351 }
352 dtd = doc->extSubset;
353 ret = xmlAddEntity(dtd, name, type, ExternalID, SystemID, content);
354 if (ret == NULL) return(NULL);
355
356 /*
357 * Link it to the DTD
358 */
359 ret->parent = dtd;
360 ret->doc = dtd->doc;
361 if (dtd->last == NULL) {
362 dtd->children = dtd->last = (xmlNodePtr) ret;
363 } else {
364 dtd->last->next = (xmlNodePtr) ret;
365 ret->prev = dtd->last;
366 dtd->last = (xmlNodePtr) ret;
367 }
368 return(ret);
369 }
370
371 /**
372 * xmlAddDocEntity:
373 * @doc: the document
374 * @name: the entity name
375 * @type: the entity type XML_xxx_yyy_ENTITY
376 * @ExternalID: the entity external ID if available
377 * @SystemID: the entity system ID if available
378 * @content: the entity content
379 *
380 * Register a new entity for this document.
381 *
382 * Returns a pointer to the entity or NULL in case of error
383 */
384 xmlEntityPtr
xmlAddDocEntity(xmlDocPtr doc,const xmlChar * name,int type,const xmlChar * ExternalID,const xmlChar * SystemID,const xmlChar * content)385 xmlAddDocEntity(xmlDocPtr doc, const xmlChar *name, int type,
386 const xmlChar *ExternalID, const xmlChar *SystemID,
387 const xmlChar *content) {
388 xmlEntityPtr ret;
389 xmlDtdPtr dtd;
390
391 if (doc == NULL) {
392 xmlEntitiesErr(XML_DTD_NO_DOC,
393 "xmlAddDocEntity: document is NULL");
394 return(NULL);
395 }
396 if (doc->intSubset == NULL) {
397 xmlEntitiesErr(XML_DTD_NO_DTD,
398 "xmlAddDocEntity: document without internal subset");
399 return(NULL);
400 }
401 dtd = doc->intSubset;
402 ret = xmlAddEntity(dtd, name, type, ExternalID, SystemID, content);
403 if (ret == NULL) return(NULL);
404
405 /*
406 * Link it to the DTD
407 */
408 ret->parent = dtd;
409 ret->doc = dtd->doc;
410 if (dtd->last == NULL) {
411 dtd->children = dtd->last = (xmlNodePtr) ret;
412 } else {
413 dtd->last->next = (xmlNodePtr) ret;
414 ret->prev = dtd->last;
415 dtd->last = (xmlNodePtr) ret;
416 }
417 return(ret);
418 }
419
420 /**
421 * xmlNewEntity:
422 * @doc: the document
423 * @name: the entity name
424 * @type: the entity type XML_xxx_yyy_ENTITY
425 * @ExternalID: the entity external ID if available
426 * @SystemID: the entity system ID if available
427 * @content: the entity content
428 *
429 * Create a new entity, this differs from xmlAddDocEntity() that if
430 * the document is NULL or has no internal subset defined, then an
431 * unlinked entity structure will be returned, it is then the responsibility
432 * of the caller to link it to the document later or free it when not needed
433 * anymore.
434 *
435 * Returns a pointer to the entity or NULL in case of error
436 */
437 xmlEntityPtr
xmlNewEntity(xmlDocPtr doc,const xmlChar * name,int type,const xmlChar * ExternalID,const xmlChar * SystemID,const xmlChar * content)438 xmlNewEntity(xmlDocPtr doc, const xmlChar *name, int type,
439 const xmlChar *ExternalID, const xmlChar *SystemID,
440 const xmlChar *content) {
441 xmlEntityPtr ret;
442 xmlDictPtr dict;
443
444 if ((doc != NULL) && (doc->intSubset != NULL)) {
445 return(xmlAddDocEntity(doc, name, type, ExternalID, SystemID, content));
446 }
447 if (doc != NULL)
448 dict = doc->dict;
449 else
450 dict = NULL;
451 ret = xmlCreateEntity(dict, name, type, ExternalID, SystemID, content);
452 if (ret == NULL)
453 return(NULL);
454 ret->doc = doc;
455 return(ret);
456 }
457
458 /**
459 * xmlGetEntityFromTable:
460 * @table: an entity table
461 * @name: the entity name
462 * @parameter: look for parameter entities
463 *
464 * Do an entity lookup in the table.
465 * returns the corresponding parameter entity, if found.
466 *
467 * Returns A pointer to the entity structure or NULL if not found.
468 */
469 static xmlEntityPtr
xmlGetEntityFromTable(xmlEntitiesTablePtr table,const xmlChar * name)470 xmlGetEntityFromTable(xmlEntitiesTablePtr table, const xmlChar *name) {
471 return((xmlEntityPtr) xmlHashLookup(table, name));
472 }
473
474 /**
475 * xmlGetParameterEntity:
476 * @doc: the document referencing the entity
477 * @name: the entity name
478 *
479 * Do an entity lookup in the internal and external subsets and
480 * returns the corresponding parameter entity, if found.
481 *
482 * Returns A pointer to the entity structure or NULL if not found.
483 */
484 xmlEntityPtr
xmlGetParameterEntity(xmlDocPtr doc,const xmlChar * name)485 xmlGetParameterEntity(xmlDocPtr doc, const xmlChar *name) {
486 xmlEntitiesTablePtr table;
487 xmlEntityPtr ret;
488
489 if (doc == NULL)
490 return(NULL);
491 if ((doc->intSubset != NULL) && (doc->intSubset->pentities != NULL)) {
492 table = (xmlEntitiesTablePtr) doc->intSubset->pentities;
493 ret = xmlGetEntityFromTable(table, name);
494 if (ret != NULL)
495 return(ret);
496 }
497 if ((doc->extSubset != NULL) && (doc->extSubset->pentities != NULL)) {
498 table = (xmlEntitiesTablePtr) doc->extSubset->pentities;
499 return(xmlGetEntityFromTable(table, name));
500 }
501 return(NULL);
502 }
503
504 /**
505 * xmlGetDtdEntity:
506 * @doc: the document referencing the entity
507 * @name: the entity name
508 *
509 * Do an entity lookup in the DTD entity hash table and
510 * returns the corresponding entity, if found.
511 * Note: the first argument is the document node, not the DTD node.
512 *
513 * Returns A pointer to the entity structure or NULL if not found.
514 */
515 xmlEntityPtr
xmlGetDtdEntity(xmlDocPtr doc,const xmlChar * name)516 xmlGetDtdEntity(xmlDocPtr doc, const xmlChar *name) {
517 xmlEntitiesTablePtr table;
518
519 if (doc == NULL)
520 return(NULL);
521 if ((doc->extSubset != NULL) && (doc->extSubset->entities != NULL)) {
522 table = (xmlEntitiesTablePtr) doc->extSubset->entities;
523 return(xmlGetEntityFromTable(table, name));
524 }
525 return(NULL);
526 }
527
528 /**
529 * xmlGetDocEntity:
530 * @doc: the document referencing the entity
531 * @name: the entity name
532 *
533 * Do an entity lookup in the document entity hash table and
534 * returns the corresponding entity, otherwise a lookup is done
535 * in the predefined entities too.
536 *
537 * Returns A pointer to the entity structure or NULL if not found.
538 */
539 xmlEntityPtr
xmlGetDocEntity(const xmlDoc * doc,const xmlChar * name)540 xmlGetDocEntity(const xmlDoc *doc, const xmlChar *name) {
541 xmlEntityPtr cur;
542 xmlEntitiesTablePtr table;
543
544 if (doc != NULL) {
545 if ((doc->intSubset != NULL) && (doc->intSubset->entities != NULL)) {
546 table = (xmlEntitiesTablePtr) doc->intSubset->entities;
547 cur = xmlGetEntityFromTable(table, name);
548 if (cur != NULL)
549 return(cur);
550 }
551 if (doc->standalone != 1) {
552 if ((doc->extSubset != NULL) &&
553 (doc->extSubset->entities != NULL)) {
554 table = (xmlEntitiesTablePtr) doc->extSubset->entities;
555 cur = xmlGetEntityFromTable(table, name);
556 if (cur != NULL)
557 return(cur);
558 }
559 }
560 }
561 return(xmlGetPredefinedEntity(name));
562 }
563
564 /*
565 * Macro used to grow the current buffer.
566 */
567 #define growBufferReentrant() { \
568 xmlChar *tmp; \
569 size_t new_size = buffer_size * 2; \
570 if (new_size < buffer_size) goto mem_error; \
571 tmp = (xmlChar *) xmlRealloc(buffer, new_size); \
572 if (tmp == NULL) goto mem_error; \
573 buffer = tmp; \
574 buffer_size = new_size; \
575 }
576
577 /**
578 * xmlEncodeEntitiesInternal:
579 * @doc: the document containing the string
580 * @input: A string to convert to XML.
581 * @attr: are we handling an attribute value
582 *
583 * Do a global encoding of a string, replacing the predefined entities
584 * and non ASCII values with their entities and CharRef counterparts.
585 * Contrary to xmlEncodeEntities, this routine is reentrant, and result
586 * must be deallocated.
587 *
588 * Returns A newly allocated string with the substitution done.
589 */
590 static xmlChar *
xmlEncodeEntitiesInternal(xmlDocPtr doc,const xmlChar * input,int attr)591 xmlEncodeEntitiesInternal(xmlDocPtr doc, const xmlChar *input, int attr) {
592 const xmlChar *cur = input;
593 xmlChar *buffer = NULL;
594 xmlChar *out = NULL;
595 size_t buffer_size = 0;
596 int html = 0;
597
598 if (input == NULL) return(NULL);
599 if (doc != NULL)
600 html = (doc->type == XML_HTML_DOCUMENT_NODE);
601
602 /*
603 * allocate an translation buffer.
604 */
605 buffer_size = 1000;
606 buffer = (xmlChar *) xmlMalloc(buffer_size);
607 if (buffer == NULL) {
608 xmlEntitiesErrMemory("xmlEncodeEntities: malloc failed");
609 return(NULL);
610 }
611 out = buffer;
612
613 while (*cur != '\0') {
614 size_t indx = out - buffer;
615 if (indx + 100 > buffer_size) {
616
617 growBufferReentrant();
618 out = &buffer[indx];
619 }
620
621 /*
622 * By default one have to encode at least '<', '>', '"' and '&' !
623 */
624 if (*cur == '<') {
625 const xmlChar *end;
626
627 /*
628 * Special handling of server side include in HTML attributes
629 */
630 if (html && attr &&
631 (cur[1] == '!') && (cur[2] == '-') && (cur[3] == '-') &&
632 ((end = xmlStrstr(cur, BAD_CAST "-->")) != NULL)) {
633 while (cur != end) {
634 *out++ = *cur++;
635 indx = out - buffer;
636 if (indx + 100 > buffer_size) {
637 growBufferReentrant();
638 out = &buffer[indx];
639 }
640 }
641 *out++ = *cur++;
642 *out++ = *cur++;
643 *out++ = *cur++;
644 continue;
645 }
646 *out++ = '&';
647 *out++ = 'l';
648 *out++ = 't';
649 *out++ = ';';
650 } else if (*cur == '>') {
651 *out++ = '&';
652 *out++ = 'g';
653 *out++ = 't';
654 *out++ = ';';
655 } else if (*cur == '&') {
656 /*
657 * Special handling of &{...} construct from HTML 4, see
658 * http://www.w3.org/TR/html401/appendix/notes.html#h-B.7.1
659 */
660 if (html && attr && (cur[1] == '{') &&
661 (strchr((const char *) cur, '}'))) {
662 while (*cur != '}') {
663 *out++ = *cur++;
664 indx = out - buffer;
665 if (indx + 100 > buffer_size) {
666 growBufferReentrant();
667 out = &buffer[indx];
668 }
669 }
670 *out++ = *cur++;
671 continue;
672 }
673 *out++ = '&';
674 *out++ = 'a';
675 *out++ = 'm';
676 *out++ = 'p';
677 *out++ = ';';
678 } else if (((*cur >= 0x20) && (*cur < 0x80)) ||
679 (*cur == '\n') || (*cur == '\t') || ((html) && (*cur == '\r'))) {
680 /*
681 * default case, just copy !
682 */
683 *out++ = *cur;
684 } else if (*cur >= 0x80) {
685 if (((doc != NULL) && (doc->encoding != NULL)) || (html)) {
686 /*
687 * Bjørn Reese <br@sseusa.com> provided the patch
688 xmlChar xc;
689 xc = (*cur & 0x3F) << 6;
690 if (cur[1] != 0) {
691 xc += *(++cur) & 0x3F;
692 *out++ = xc;
693 } else
694 */
695 *out++ = *cur;
696 } else {
697 /*
698 * We assume we have UTF-8 input.
699 * It must match either:
700 * 110xxxxx 10xxxxxx
701 * 1110xxxx 10xxxxxx 10xxxxxx
702 * 11110xxx 10xxxxxx 10xxxxxx 10xxxxxx
703 * That is:
704 * cur[0] is 11xxxxxx
705 * cur[1] is 10xxxxxx
706 * cur[2] is 10xxxxxx if cur[0] is 111xxxxx
707 * cur[3] is 10xxxxxx if cur[0] is 1111xxxx
708 * cur[0] is not 11111xxx
709 */
710 char buf[11], *ptr;
711 int val = 0, l = 1;
712
713 if (((cur[0] & 0xC0) != 0xC0) ||
714 ((cur[1] & 0xC0) != 0x80) ||
715 (((cur[0] & 0xE0) == 0xE0) && ((cur[2] & 0xC0) != 0x80)) ||
716 (((cur[0] & 0xF0) == 0xF0) && ((cur[3] & 0xC0) != 0x80)) ||
717 (((cur[0] & 0xF8) == 0xF8))) {
718 xmlEntitiesErr(XML_CHECK_NOT_UTF8,
719 "xmlEncodeEntities: input not UTF-8");
720 snprintf(buf, sizeof(buf), "&#%d;", *cur);
721 buf[sizeof(buf) - 1] = 0;
722 ptr = buf;
723 while (*ptr != 0) *out++ = *ptr++;
724 cur++;
725 continue;
726 } else if (*cur < 0xE0) {
727 val = (cur[0]) & 0x1F;
728 val <<= 6;
729 val |= (cur[1]) & 0x3F;
730 l = 2;
731 } else if (*cur < 0xF0) {
732 val = (cur[0]) & 0x0F;
733 val <<= 6;
734 val |= (cur[1]) & 0x3F;
735 val <<= 6;
736 val |= (cur[2]) & 0x3F;
737 l = 3;
738 } else if (*cur < 0xF8) {
739 val = (cur[0]) & 0x07;
740 val <<= 6;
741 val |= (cur[1]) & 0x3F;
742 val <<= 6;
743 val |= (cur[2]) & 0x3F;
744 val <<= 6;
745 val |= (cur[3]) & 0x3F;
746 l = 4;
747 }
748 if ((l == 1) || (!IS_CHAR(val))) {
749 xmlEntitiesErr(XML_ERR_INVALID_CHAR,
750 "xmlEncodeEntities: char out of range\n");
751 snprintf(buf, sizeof(buf), "&#%d;", *cur);
752 buf[sizeof(buf) - 1] = 0;
753 ptr = buf;
754 while (*ptr != 0) *out++ = *ptr++;
755 cur++;
756 continue;
757 }
758 /*
759 * We could do multiple things here. Just save as a char ref
760 */
761 snprintf(buf, sizeof(buf), "&#x%X;", val);
762 buf[sizeof(buf) - 1] = 0;
763 ptr = buf;
764 while (*ptr != 0) *out++ = *ptr++;
765 cur += l;
766 continue;
767 }
768 } else if (IS_BYTE_CHAR(*cur)) {
769 char buf[11], *ptr;
770
771 snprintf(buf, sizeof(buf), "&#%d;", *cur);
772 buf[sizeof(buf) - 1] = 0;
773 ptr = buf;
774 while (*ptr != 0) *out++ = *ptr++;
775 }
776 cur++;
777 }
778 *out = 0;
779 return(buffer);
780
781 mem_error:
782 xmlEntitiesErrMemory("xmlEncodeEntities: realloc failed");
783 xmlFree(buffer);
784 return(NULL);
785 }
786
787 /**
788 * xmlEncodeAttributeEntities:
789 * @doc: the document containing the string
790 * @input: A string to convert to XML.
791 *
792 * Do a global encoding of a string, replacing the predefined entities
793 * and non ASCII values with their entities and CharRef counterparts for
794 * attribute values.
795 *
796 * Returns A newly allocated string with the substitution done.
797 */
798 xmlChar *
xmlEncodeAttributeEntities(xmlDocPtr doc,const xmlChar * input)799 xmlEncodeAttributeEntities(xmlDocPtr doc, const xmlChar *input) {
800 return xmlEncodeEntitiesInternal(doc, input, 1);
801 }
802
803 /**
804 * xmlEncodeEntitiesReentrant:
805 * @doc: the document containing the string
806 * @input: A string to convert to XML.
807 *
808 * Do a global encoding of a string, replacing the predefined entities
809 * and non ASCII values with their entities and CharRef counterparts.
810 * Contrary to xmlEncodeEntities, this routine is reentrant, and result
811 * must be deallocated.
812 *
813 * Returns A newly allocated string with the substitution done.
814 */
815 xmlChar *
xmlEncodeEntitiesReentrant(xmlDocPtr doc,const xmlChar * input)816 xmlEncodeEntitiesReentrant(xmlDocPtr doc, const xmlChar *input) {
817 return xmlEncodeEntitiesInternal(doc, input, 0);
818 }
819
820 /**
821 * xmlEncodeSpecialChars:
822 * @doc: the document containing the string
823 * @input: A string to convert to XML.
824 *
825 * Do a global encoding of a string, replacing the predefined entities
826 * this routine is reentrant, and result must be deallocated.
827 *
828 * Returns A newly allocated string with the substitution done.
829 */
830 xmlChar *
xmlEncodeSpecialChars(const xmlDoc * doc ATTRIBUTE_UNUSED,const xmlChar * input)831 xmlEncodeSpecialChars(const xmlDoc *doc ATTRIBUTE_UNUSED, const xmlChar *input) {
832 const xmlChar *cur = input;
833 xmlChar *buffer = NULL;
834 xmlChar *out = NULL;
835 size_t buffer_size = 0;
836 if (input == NULL) return(NULL);
837
838 /*
839 * allocate an translation buffer.
840 */
841 buffer_size = 1000;
842 buffer = (xmlChar *) xmlMalloc(buffer_size);
843 if (buffer == NULL) {
844 xmlEntitiesErrMemory("xmlEncodeSpecialChars: malloc failed");
845 return(NULL);
846 }
847 out = buffer;
848
849 while (*cur != '\0') {
850 size_t indx = out - buffer;
851 if (indx + 10 > buffer_size) {
852
853 growBufferReentrant();
854 out = &buffer[indx];
855 }
856
857 /*
858 * By default one have to encode at least '<', '>', '"' and '&' !
859 */
860 if (*cur == '<') {
861 *out++ = '&';
862 *out++ = 'l';
863 *out++ = 't';
864 *out++ = ';';
865 } else if (*cur == '>') {
866 *out++ = '&';
867 *out++ = 'g';
868 *out++ = 't';
869 *out++ = ';';
870 } else if (*cur == '&') {
871 *out++ = '&';
872 *out++ = 'a';
873 *out++ = 'm';
874 *out++ = 'p';
875 *out++ = ';';
876 } else if (*cur == '"') {
877 *out++ = '&';
878 *out++ = 'q';
879 *out++ = 'u';
880 *out++ = 'o';
881 *out++ = 't';
882 *out++ = ';';
883 } else if (*cur == '\r') {
884 *out++ = '&';
885 *out++ = '#';
886 *out++ = '1';
887 *out++ = '3';
888 *out++ = ';';
889 } else {
890 /*
891 * Works because on UTF-8, all extended sequences cannot
892 * result in bytes in the ASCII range.
893 */
894 *out++ = *cur;
895 }
896 cur++;
897 }
898 *out = 0;
899 return(buffer);
900
901 mem_error:
902 xmlEntitiesErrMemory("xmlEncodeSpecialChars: realloc failed");
903 xmlFree(buffer);
904 return(NULL);
905 }
906
907 /**
908 * xmlCreateEntitiesTable:
909 *
910 * create and initialize an empty entities hash table.
911 * This really doesn't make sense and should be deprecated
912 *
913 * Returns the xmlEntitiesTablePtr just created or NULL in case of error.
914 */
915 xmlEntitiesTablePtr
xmlCreateEntitiesTable(void)916 xmlCreateEntitiesTable(void) {
917 return((xmlEntitiesTablePtr) xmlHashCreate(0));
918 }
919
920 /**
921 * xmlFreeEntityWrapper:
922 * @entity: An entity
923 * @name: its name
924 *
925 * Deallocate the memory used by an entities in the hash table.
926 */
927 static void
xmlFreeEntityWrapper(void * entity,const xmlChar * name ATTRIBUTE_UNUSED)928 xmlFreeEntityWrapper(void *entity, const xmlChar *name ATTRIBUTE_UNUSED) {
929 if (entity != NULL)
930 xmlFreeEntity((xmlEntityPtr) entity);
931 }
932
933 /**
934 * xmlFreeEntitiesTable:
935 * @table: An entity table
936 *
937 * Deallocate the memory used by an entities hash table.
938 */
939 void
xmlFreeEntitiesTable(xmlEntitiesTablePtr table)940 xmlFreeEntitiesTable(xmlEntitiesTablePtr table) {
941 xmlHashFree(table, xmlFreeEntityWrapper);
942 }
943
944 #ifdef LIBXML_TREE_ENABLED
945 /**
946 * xmlCopyEntity:
947 * @ent: An entity
948 *
949 * Build a copy of an entity
950 *
951 * Returns the new xmlEntitiesPtr or NULL in case of error.
952 */
953 static void *
xmlCopyEntity(void * payload,const xmlChar * name ATTRIBUTE_UNUSED)954 xmlCopyEntity(void *payload, const xmlChar *name ATTRIBUTE_UNUSED) {
955 xmlEntityPtr ent = (xmlEntityPtr) payload;
956 xmlEntityPtr cur;
957
958 cur = (xmlEntityPtr) xmlMalloc(sizeof(xmlEntity));
959 if (cur == NULL) {
960 xmlEntitiesErrMemory("xmlCopyEntity:: malloc failed");
961 return(NULL);
962 }
963 memset(cur, 0, sizeof(xmlEntity));
964 cur->type = XML_ENTITY_DECL;
965
966 cur->etype = ent->etype;
967 if (ent->name != NULL)
968 cur->name = xmlStrdup(ent->name);
969 if (ent->ExternalID != NULL)
970 cur->ExternalID = xmlStrdup(ent->ExternalID);
971 if (ent->SystemID != NULL)
972 cur->SystemID = xmlStrdup(ent->SystemID);
973 if (ent->content != NULL)
974 cur->content = xmlStrdup(ent->content);
975 if (ent->orig != NULL)
976 cur->orig = xmlStrdup(ent->orig);
977 if (ent->URI != NULL)
978 cur->URI = xmlStrdup(ent->URI);
979 return(cur);
980 }
981
982 /**
983 * xmlCopyEntitiesTable:
984 * @table: An entity table
985 *
986 * Build a copy of an entity table.
987 *
988 * Returns the new xmlEntitiesTablePtr or NULL in case of error.
989 */
990 xmlEntitiesTablePtr
xmlCopyEntitiesTable(xmlEntitiesTablePtr table)991 xmlCopyEntitiesTable(xmlEntitiesTablePtr table) {
992 return(xmlHashCopy(table, xmlCopyEntity));
993 }
994 #endif /* LIBXML_TREE_ENABLED */
995
996 #ifdef LIBXML_OUTPUT_ENABLED
997
998 /**
999 * xmlDumpEntityContent:
1000 * @buf: An XML buffer.
1001 * @content: The entity content.
1002 *
1003 * This will dump the quoted string value, taking care of the special
1004 * treatment required by %
1005 */
1006 static void
xmlDumpEntityContent(xmlBufferPtr buf,const xmlChar * content)1007 xmlDumpEntityContent(xmlBufferPtr buf, const xmlChar *content) {
1008 if (xmlStrchr(content, '%')) {
1009 const xmlChar * base, *cur;
1010
1011 xmlBufferCCat(buf, "\"");
1012 base = cur = content;
1013 while (*cur != 0) {
1014 if (*cur == '"') {
1015 if (base != cur)
1016 xmlBufferAdd(buf, base, cur - base);
1017 xmlBufferAdd(buf, BAD_CAST """, 6);
1018 cur++;
1019 base = cur;
1020 } else if (*cur == '%') {
1021 if (base != cur)
1022 xmlBufferAdd(buf, base, cur - base);
1023 xmlBufferAdd(buf, BAD_CAST "%", 6);
1024 cur++;
1025 base = cur;
1026 } else {
1027 cur++;
1028 }
1029 }
1030 if (base != cur)
1031 xmlBufferAdd(buf, base, cur - base);
1032 xmlBufferCCat(buf, "\"");
1033 } else {
1034 xmlBufferWriteQuotedString(buf, content);
1035 }
1036 }
1037
1038 /**
1039 * xmlDumpEntityDecl:
1040 * @buf: An XML buffer.
1041 * @ent: An entity table
1042 *
1043 * This will dump the content of the entity table as an XML DTD definition
1044 */
1045 void
xmlDumpEntityDecl(xmlBufferPtr buf,xmlEntityPtr ent)1046 xmlDumpEntityDecl(xmlBufferPtr buf, xmlEntityPtr ent) {
1047 if ((buf == NULL) || (ent == NULL)) return;
1048 switch (ent->etype) {
1049 case XML_INTERNAL_GENERAL_ENTITY:
1050 xmlBufferWriteChar(buf, "<!ENTITY ");
1051 xmlBufferWriteCHAR(buf, ent->name);
1052 xmlBufferWriteChar(buf, " ");
1053 if (ent->orig != NULL)
1054 xmlBufferWriteQuotedString(buf, ent->orig);
1055 else
1056 xmlDumpEntityContent(buf, ent->content);
1057 xmlBufferWriteChar(buf, ">\n");
1058 break;
1059 case XML_EXTERNAL_GENERAL_PARSED_ENTITY:
1060 xmlBufferWriteChar(buf, "<!ENTITY ");
1061 xmlBufferWriteCHAR(buf, ent->name);
1062 if (ent->ExternalID != NULL) {
1063 xmlBufferWriteChar(buf, " PUBLIC ");
1064 xmlBufferWriteQuotedString(buf, ent->ExternalID);
1065 xmlBufferWriteChar(buf, " ");
1066 xmlBufferWriteQuotedString(buf, ent->SystemID);
1067 } else {
1068 xmlBufferWriteChar(buf, " SYSTEM ");
1069 xmlBufferWriteQuotedString(buf, ent->SystemID);
1070 }
1071 xmlBufferWriteChar(buf, ">\n");
1072 break;
1073 case XML_EXTERNAL_GENERAL_UNPARSED_ENTITY:
1074 xmlBufferWriteChar(buf, "<!ENTITY ");
1075 xmlBufferWriteCHAR(buf, ent->name);
1076 if (ent->ExternalID != NULL) {
1077 xmlBufferWriteChar(buf, " PUBLIC ");
1078 xmlBufferWriteQuotedString(buf, ent->ExternalID);
1079 xmlBufferWriteChar(buf, " ");
1080 xmlBufferWriteQuotedString(buf, ent->SystemID);
1081 } else {
1082 xmlBufferWriteChar(buf, " SYSTEM ");
1083 xmlBufferWriteQuotedString(buf, ent->SystemID);
1084 }
1085 if (ent->content != NULL) { /* Should be true ! */
1086 xmlBufferWriteChar(buf, " NDATA ");
1087 if (ent->orig != NULL)
1088 xmlBufferWriteCHAR(buf, ent->orig);
1089 else
1090 xmlBufferWriteCHAR(buf, ent->content);
1091 }
1092 xmlBufferWriteChar(buf, ">\n");
1093 break;
1094 case XML_INTERNAL_PARAMETER_ENTITY:
1095 xmlBufferWriteChar(buf, "<!ENTITY % ");
1096 xmlBufferWriteCHAR(buf, ent->name);
1097 xmlBufferWriteChar(buf, " ");
1098 if (ent->orig == NULL)
1099 xmlDumpEntityContent(buf, ent->content);
1100 else
1101 xmlBufferWriteQuotedString(buf, ent->orig);
1102 xmlBufferWriteChar(buf, ">\n");
1103 break;
1104 case XML_EXTERNAL_PARAMETER_ENTITY:
1105 xmlBufferWriteChar(buf, "<!ENTITY % ");
1106 xmlBufferWriteCHAR(buf, ent->name);
1107 if (ent->ExternalID != NULL) {
1108 xmlBufferWriteChar(buf, " PUBLIC ");
1109 xmlBufferWriteQuotedString(buf, ent->ExternalID);
1110 xmlBufferWriteChar(buf, " ");
1111 xmlBufferWriteQuotedString(buf, ent->SystemID);
1112 } else {
1113 xmlBufferWriteChar(buf, " SYSTEM ");
1114 xmlBufferWriteQuotedString(buf, ent->SystemID);
1115 }
1116 xmlBufferWriteChar(buf, ">\n");
1117 break;
1118 default:
1119 xmlEntitiesErr(XML_DTD_UNKNOWN_ENTITY,
1120 "xmlDumpEntitiesDecl: internal: unknown type entity type");
1121 }
1122 }
1123
1124 /**
1125 * xmlDumpEntityDeclScan:
1126 * @ent: An entity table
1127 * @buf: An XML buffer.
1128 *
1129 * When using the hash table scan function, arguments need to be reversed
1130 */
1131 static void
xmlDumpEntityDeclScan(void * ent,void * buf,const xmlChar * name ATTRIBUTE_UNUSED)1132 xmlDumpEntityDeclScan(void *ent, void *buf,
1133 const xmlChar *name ATTRIBUTE_UNUSED) {
1134 xmlDumpEntityDecl((xmlBufferPtr) buf, (xmlEntityPtr) ent);
1135 }
1136
1137 /**
1138 * xmlDumpEntitiesTable:
1139 * @buf: An XML buffer.
1140 * @table: An entity table
1141 *
1142 * This will dump the content of the entity table as an XML DTD definition
1143 */
1144 void
xmlDumpEntitiesTable(xmlBufferPtr buf,xmlEntitiesTablePtr table)1145 xmlDumpEntitiesTable(xmlBufferPtr buf, xmlEntitiesTablePtr table) {
1146 xmlHashScan(table, xmlDumpEntityDeclScan, buf);
1147 }
1148 #endif /* LIBXML_OUTPUT_ENABLED */
1149