?  search:
summary | log | graphiclog1 | graphiclog2 | commit | commitdiff | tree | refs | edit | fork
blame | history | raw | HEAD
dsrc isn't necessary for this repo
[client-tools.git] / src / external / 3rd / library / libxml / DOCBparser.c
blob6f381510afc50598bcd9682c6766bce68c05d46f
1 /*
2 * DOCBparser.c : an attempt to parse SGML Docbook documents
3 *
4 * This is extremely hackish. It also adds one extension
5 * <?sgml-declaration encoding="ISO-8859-1"?>
6 * allowing to store the encoding of the document within the instance.
7 *
8 * See Copyright for the status of this software.
9 *
10 * daniel@veillard.com
11 */
12
13 #define IN_LIBXML
14 #include "libxml.h"
15 #ifdef LIBXML_DOCB_ENABLED
16
17 #include <string.h>
18 #ifdef HAVE_CTYPE_H
19 #include <ctype.h>
20 #endif
21 #ifdef HAVE_STDLIB_H
22 #include <stdlib.h>
23 #endif
24 #ifdef HAVE_SYS_STAT_H
25 #include <sys/stat.h>
26 #endif
27 #ifdef HAVE_FCNTL_H
28 #include <fcntl.h>
29 #endif
30 #ifdef HAVE_UNISTD_H
31 #include <unistd.h>
32 #endif
33 #ifdef HAVE_ZLIB_H
34 #include <zlib.h>
35 #endif
36
37 #include <libxml/xmlmemory.h>
38 #include <libxml/tree.h>
39 #include <libxml/SAX.h>
40 #include <libxml/parser.h>
41 #include <libxml/parserInternals.h>
42 #include <libxml/xmlerror.h>
43 #include <libxml/DOCBparser.h>
44 #include <libxml/entities.h>
45 #include <libxml/encoding.h>
46 #include <libxml/valid.h>
47 #include <libxml/xmlIO.h>
48 #include <libxml/uri.h>
49 #include <libxml/globals.h>
50
51 /*
52 * DocBook XML current versions
53 */
54
55 #define XML_DOCBOOK_XML_PUBLIC (const xmlChar *) \
56 "-//OASIS//DTD DocBook XML V4.1.2//EN"
57 #define XML_DOCBOOK_XML_SYSTEM (const xmlChar *) \
58 "http://www.oasis-open.org/docbook/xml/4.1.2/docbookx.dtd"
59
60 /*
61 * Internal description of an SGML entity
62 */
63 typedef struct _docbEntityDesc docbEntityDesc;
64 typedef docbEntityDesc *docbEntityDescPtr;
65 struct _docbEntityDesc {
66 int value; /* the UNICODE value for the character */
67 const char *name; /* The entity name */
68 const char *desc; /* the description */
69 };
70
71 #if 0
72 docbElemDescPtr docbTagLookup (const xmlChar *tag);
73 docbEntityDescPtr docbEntityLookup(const xmlChar *name);
74 docbEntityDescPtr docbEntityValueLookup(int value);
75
76 int docbIsAutoClosed(docbDocPtr doc,
77 docbNodePtr elem);
78 int docbAutoCloseTag(docbDocPtr doc,
79 const xmlChar *name,
80 docbNodePtr elem);
81
82 #endif
83 static int docbParseCharRef(docbParserCtxtPtr ctxt);
84 static xmlEntityPtr docbParseEntityRef(docbParserCtxtPtr ctxt,
85 xmlChar **str);
86 static void docbParseElement(docbParserCtxtPtr ctxt);
87 static void docbParseContent(docbParserCtxtPtr ctxt);
88
89 /*
90 * Internal description of an SGML element
91 */
92 typedef struct _docbElemDesc docbElemDesc;
93 typedef docbElemDesc *docbElemDescPtr;
94 struct _docbElemDesc {
95 const char *name; /* The tag name */
96 int startTag; /* Whether the start tag can be implied */
97 int endTag; /* Whether the end tag can be implied */
98 int empty; /* Is this an empty element ? */
99 int depr; /* Is this a deprecated element ? */
100 int dtd; /* 1: only in Loose DTD, 2: only Frameset one */
101 const char *desc; /* the description */
102 };
103
104
105 #define DOCB_MAX_NAMELEN 1000
106 #define DOCB_PARSER_BIG_BUFFER_SIZE 1000
107 #define DOCB_PARSER_BUFFER_SIZE 100
108
109 /* #define DEBUG */
110 /* #define DEBUG_PUSH */
111
112 /************************************************************************
113 * *
114 * Parser stacks related functions and macros *
115 * *
116 ************************************************************************/
117
118 /*
119 * Generic function for accessing stacks in the Parser Context
120 */
121
122 #define PUSH_AND_POP(scope, type, name) \
123 scope int docb##name##Push(docbParserCtxtPtr ctxt, type value) { \
124 if (ctxt->name##Nr >= ctxt->name##Max) { \
125 ctxt->name##Max *= 2; \
126 ctxt->name##Tab = (type *) xmlRealloc(ctxt->name##Tab, \
127 ctxt->name##Max * sizeof(ctxt->name##Tab[0])); \
128 if (ctxt->name##Tab == NULL) { \
129 xmlGenericError(xmlGenericErrorContext, \
130 "realloc failed !\n"); \
131 return(0); \
132 } \
133 } \
134 ctxt->name##Tab[ctxt->name##Nr] = value; \
135 ctxt->name = value; \
136 return(ctxt->name##Nr++); \
137 } \
138 scope type docb##name##Pop(docbParserCtxtPtr ctxt) { \
139 type ret; \
140 if (ctxt->name##Nr < 0) return(0); \
141 ctxt->name##Nr--; \
142 if (ctxt->name##Nr < 0) return(0); \
143 if (ctxt->name##Nr > 0) \
144 ctxt->name = ctxt->name##Tab[ctxt->name##Nr - 1]; \
145 else \
146 ctxt->name = NULL; \
147 ret = ctxt->name##Tab[ctxt->name##Nr]; \
148 ctxt->name##Tab[ctxt->name##Nr] = 0; \
149 return(ret); \
150 } \
151
152 /* PUSH_AND_POP(static, xmlNodePtr, node) */
153 PUSH_AND_POP(static, xmlChar*, name)
154
155 /*
156 * Macros for accessing the content. Those should be used only by the parser,
157 * and not exported.
158 *
159 * Dirty macros, i.e. one need to make assumption on the context to use them
160 *
161 * CUR_PTR return the current pointer to the xmlChar to be parsed.
162 * CUR returns the current xmlChar value, i.e. a 8 bit value if compiled
163 * in ISO-Latin or UTF-8, and the current 16 bit value if compiled
164 * in UNICODE mode. This should be used internally by the parser
165 * only to compare to ASCII values otherwise it would break when
166 * running with UTF-8 encoding.
167 * NXT(n) returns the n'th next xmlChar. Same as CUR is should be used only
168 * to compare on ASCII based substring.
169 * UPP(n) returns the n'th next xmlChar converted to uppercase. Same as CUR
170 * it should be used only to compare on ASCII based substring.
171 * SKIP(n) Skip n xmlChar, and must also be used only to skip ASCII defined
172 * strings within the parser.
173 *
174 * Clean macros, not dependent of an ASCII context, expect UTF-8 encoding
175 *
176 * CURRENT Returns the current char value, with the full decoding of
177 * UTF-8 if we are using this mode. It returns an int.
178 * NEXT Skip to the next character, this does the proper decoding
179 * in UTF-8 mode. It also pop-up unfinished entities on the fly.
180 * COPY(to) copy one char to *to, increment CUR_PTR and to accordingly
181 */
182
183 #define UPPER (toupper(*ctxt->input->cur))
184
185 #define SKIP(val) ctxt->nbChars += (val),ctxt->input->cur += (val)
186
187 #define NXT(val) ctxt->input->cur[(val)]
188
189 #define UPP(val) (toupper(ctxt->input->cur[(val)]))
190
191 #define CUR_PTR ctxt->input->cur
192
193 #define SHRINK xmlParserInputShrink(ctxt->input)
194
195 #define GROW xmlParserInputGrow(ctxt->input, INPUT_CHUNK)
196
197 #define CURRENT ((int) (*ctxt->input->cur))
198
199 #define SKIP_BLANKS docbSkipBlankChars(ctxt)
200
201 /* Imported from XML */
202
203 /* #define CUR (ctxt->token ? ctxt->token : (int) (*ctxt->input->cur)) */
204 #define CUR ((int) (*ctxt->input->cur))
205 #define NEXT xmlNextChar(ctxt),ctxt->nbChars++
206
207 #define RAW (ctxt->token ? -1 : (*ctxt->input->cur))
208 #define NXT(val) ctxt->input->cur[(val)]
209 #define CUR_PTR ctxt->input->cur
210
211
212 #define NEXTL(l) do { \
213 if (*(ctxt->input->cur) == '\n') { \
214 ctxt->input->line++; ctxt->input->col = 1; \
215 } else ctxt->input->col++; \
216 ctxt->token = 0; ctxt->input->cur += l; ctxt->nbChars++; \
217 } while (0)
218
219 /************
220 \
221 if (*ctxt->input->cur == '%') xmlParserHandlePEReference(ctxt); \
222 if (*ctxt->input->cur == '&') xmlParserHandleReference(ctxt);
223 ************/
224
225 #define CUR_CHAR(l) docbCurrentChar(ctxt, &l)
226 #define CUR_SCHAR(s, l) xmlStringCurrentChar(ctxt, s, &l)
227
228 #define COPY_BUF(l,b,i,v) \
229 if (l == 1) b[i++] = (xmlChar) v; \
230 else i += xmlCopyChar(l,&b[i],v)
231
232 /**
233 * docbCurrentChar:
234 * @ctxt: the DocBook SGML parser context
235 * @len: pointer to the length of the char read
236 *
237 * The current char value, if using UTF-8 this may actually span multiple
238 * bytes in the input buffer. Implement the end of line normalization:
239 * 2.11 End-of-Line Handling
240 * If the encoding is unspecified, in the case we find an ISO-Latin-1
241 * char, then the encoding converter is plugged in automatically.
242 *
243 * Returns the current char value and its length
244 */
245
246 static int
247 docbCurrentChar(xmlParserCtxtPtr ctxt, int *len) {
248 if (ctxt->instate == XML_PARSER_EOF)
249 return(0);
250
251 if (ctxt->token != 0) {
252 *len = 0;
253 return(ctxt->token);
254 }
255 if (ctxt->charset == XML_CHAR_ENCODING_UTF8) {
256 /*
257 * We are supposed to handle UTF8, check it's valid
258 * From rfc2044: encoding of the Unicode values on UTF-8:
259 *
260 * UCS-4 range (hex.) UTF-8 octet sequence (binary)
261 * 0000 0000-0000 007F 0xxxxxxx
262 * 0000 0080-0000 07FF 110xxxxx 10xxxxxx
263 * 0000 0800-0000 FFFF 1110xxxx 10xxxxxx 10xxxxxx
264 *
265 * Check for the 0x110000 limit too
266 */
267 const unsigned char *cur = ctxt->input->cur;
268 unsigned char c;
269 unsigned int val;
270
271 c = *cur;
272 if (c & 0x80) {
273 if (cur[1] == 0)
274 xmlParserInputGrow(ctxt->input, INPUT_CHUNK);
275 if ((cur[1] & 0xc0) != 0x80)
276 goto encoding_error;
277 if ((c & 0xe0) == 0xe0) {
278
279 if (cur[2] == 0)
280 xmlParserInputGrow(ctxt->input, INPUT_CHUNK);
281 if ((cur[2] & 0xc0) != 0x80)
282 goto encoding_error;
283 if ((c & 0xf0) == 0xf0) {
284 if (cur[3] == 0)
285 xmlParserInputGrow(ctxt->input, INPUT_CHUNK);
286 if (((c & 0xf8) != 0xf0) ||
287 ((cur[3] & 0xc0) != 0x80))
288 goto encoding_error;
289 /* 4-byte code */
290 *len = 4;
291 val = (cur[0] & 0x7) << 18;
292 val |= (cur[1] & 0x3f) << 12;
293 val |= (cur[2] & 0x3f) << 6;
294 val |= cur[3] & 0x3f;
295 } else {
296 /* 3-byte code */
297 *len = 3;
298 val = (cur[0] & 0xf) << 12;
299 val |= (cur[1] & 0x3f) << 6;
300 val |= cur[2] & 0x3f;
301 }
302 } else {
303 /* 2-byte code */
304 *len = 2;
305 val = (cur[0] & 0x1f) << 6;
306 val |= cur[1] & 0x3f;
307 }
308 if (!IS_CHAR(val)) {
309 ctxt->errNo = XML_ERR_INVALID_ENCODING;
310 if ((ctxt->sax != NULL) &&
311 (ctxt->sax->error != NULL))
312 ctxt->sax->error(ctxt->userData,
313 "Char 0x%X out of allowed range\n", val);
314 ctxt->wellFormed = 0;
315 if (ctxt->recovery == 0) ctxt->disableSAX = 1;
316 }
317 return(val);
318 } else {
319 /* 1-byte code */
320 *len = 1;
321 return((int) *ctxt->input->cur);
322 }
323 }
324 /*
325 * Assume it's a fixed length encoding (1) with
326 * a compatible encoding for the ASCII set, since
327 * XML constructs only use < 128 chars
328 */
329 *len = 1;
330 if ((int) *ctxt->input->cur < 0x80)
331 return((int) *ctxt->input->cur);
332
333 /*
334 * Humm this is bad, do an automatic flow conversion
335 */
336 xmlSwitchEncoding(ctxt, XML_CHAR_ENCODING_8859_1);
337 ctxt->charset = XML_CHAR_ENCODING_UTF8;
338 return(xmlCurrentChar(ctxt, len));
339
340 encoding_error:
341 /*
342 * If we detect an UTF8 error that probably mean that the
343 * input encoding didn't get properly advertized in the
344 * declaration header. Report the error and switch the encoding
345 * to ISO-Latin-1 (if you don't like this policy, just declare the
346 * encoding !)
347 */
348 ctxt->errNo = XML_ERR_INVALID_ENCODING;
349 if ((ctxt->sax != NULL) && (ctxt->sax->error != NULL)) {
350 ctxt->sax->error(ctxt->userData,
351 "Input is not proper UTF-8, indicate encoding !\n");
352 ctxt->sax->error(ctxt->userData, "Bytes: 0x%02X 0x%02X 0x%02X 0x%02X\n",
353 ctxt->input->cur[0], ctxt->input->cur[1],
354 ctxt->input->cur[2], ctxt->input->cur[3]);
355 }
356
357 ctxt->charset = XML_CHAR_ENCODING_8859_1;
358 *len = 1;
359 return((int) *ctxt->input->cur);
360 }
361
362 #if 0
363 /**
364 * sgmlNextChar:
365 * @ctxt: the DocBook SGML parser context
366 *
367 * Skip to the next char input char.
368 */
369
370 static void
371 sgmlNextChar(docbParserCtxtPtr ctxt) {
372 if (ctxt->instate == XML_PARSER_EOF)
373 return;
374 if ((*ctxt->input->cur == 0) &&
375 (xmlParserInputGrow(ctxt->input, INPUT_CHUNK) <= 0)) {
376 xmlPopInput(ctxt);
377 } else {
378 if (*(ctxt->input->cur) == '\n') {
379 ctxt->input->line++; ctxt->input->col = 1;
380 } else ctxt->input->col++;
381 ctxt->input->cur++;
382 ctxt->nbChars++;
383 if (*ctxt->input->cur == 0)
384 xmlParserInputGrow(ctxt->input, INPUT_CHUNK);
385 }
386 }
387 #endif
388
389 /**
390 * docbSkipBlankChars:
391 * @ctxt: the DocBook SGML parser context
392 *
393 * skip all blanks character found at that point in the input streams.
394 *
395 * Returns the number of space chars skipped
396 */
397
398 static int
399 docbSkipBlankChars(xmlParserCtxtPtr ctxt) {
400 int res = 0;
401
402 while (IS_BLANK(*(ctxt->input->cur))) {
403 if ((*ctxt->input->cur == 0) &&
404 (xmlParserInputGrow(ctxt->input, INPUT_CHUNK) <= 0)) {
405 xmlPopInput(ctxt);
406 } else {
407 if (*(ctxt->input->cur) == '\n') {
408 ctxt->input->line++; ctxt->input->col = 1;
409 } else ctxt->input->col++;
410 ctxt->input->cur++;
411 ctxt->nbChars++;
412 if (*ctxt->input->cur == 0)
413 xmlParserInputGrow(ctxt->input, INPUT_CHUNK);
414 }
415 res++;
416 }
417 return(res);
418 }
419
420
421
422 /************************************************************************
423 * *
424 * The list of SGML elements and their properties *
425 * *
426 ************************************************************************/
427
428 /*
429 * Start Tag: 1 means the start tag can be ommited
430 * End Tag: 1 means the end tag can be ommited
431 * 2 means it's forbidden (empty elements)
432 * Depr: this element is deprecated
433 * DTD: 1 means that this element is valid only in the Loose DTD
434 * 2 means that this element is valid only in the Frameset DTD
435 *
436 * Name,Start Tag,End Tag, Empty, Depr., DTD, Description
437 */
438 static docbElemDesc
439 docbookElementTable[] = {
440 { "abbrev", 0, 0, 0, 3, 0, "" }, /* word */
441 { "abstract", 0, 0, 0, 9, 0, "" }, /* title */
442 { "accel", 0, 0, 0, 7, 0, "" }, /* smallcptr */
443 { "ackno", 0, 0, 0, 4, 0, "" }, /* docinfo */
444 { "acronym", 0, 0, 0, 3, 0, "" }, /* word */
445 { "action", 0, 0, 0, 7, 0, "" }, /* smallcptr */
446 { "address", 0, 0, 0, 1, 0, "" },
447 { "affiliation",0, 0, 0, 9, 0, "" }, /* shortaffil */
448 { "alt", 0, 0, 0, 1, 0, "" },
449 { "anchor", 0, 2, 1, 0, 0, "" },
450 { "answer", 0, 0, 0, 9, 0, "" }, /* label */
451 { "appendix", 0, 0, 0, 9, 0, "" }, /* appendixinfo */
452 { "appendixinfo",0, 0, 0, 9, 0, "" }, /* graphic */
453 { "application",0, 0, 0, 2, 0, "" }, /* para */
454 { "area", 0, 2, 1, 0, 0, "" },
455 { "areaset", 0, 0, 0, 9, 0, "" }, /* area */
456 { "areaspec", 0, 0, 0, 9, 0, "" }, /* area */
457 { "arg", 0, 0, 0, 1, 0, "" },
458 { "artheader", 0, 0, 0, 9, 0, "" },
459 { "article", 0, 0, 0, 9, 0, "" }, /* div.title.content */
460 { "articleinfo",0, 0, 0, 9, 0, "" }, /* graphic */
461 { "artpagenums",0, 0, 0, 4, 0, "" }, /* docinfo */
462 { "attribution",0, 0, 0, 2, 0, "" }, /* para */
463 { "audiodata", 0, 2, 1, 0, 0, "" },
464 { "audioobject",0, 0, 0, 9, 0, "" }, /* objectinfo */
465 { "authorblurb",0, 0, 0, 9, 0, "" }, /* title */
466 { "authorgroup",0, 0, 0, 9, 0, "" }, /* author */
467 { "authorinitials",0, 0, 0, 4, 0, "" }, /* docinfo */
468 { "author", 0, 0, 0, 9, 0, "" }, /* person.ident.mix */
469 { "beginpage", 0, 2, 1, 0, 0, "" },
470 { "bibliodiv", 0, 0, 0, 9, 0, "" }, /* sect.title.content */
471 { "biblioentry",0, 0, 0, 9, 0, "" }, /* articleinfo */
472 { "bibliography",0, 0, 0, 9, 0, "" }, /* bibliographyinfo */
473 { "bibliographyinfo",0, 0, 0, 9, 0, "" }, /* graphic */
474 { "bibliomisc", 0, 0, 0, 2, 0, "" }, /* para */
475 { "bibliomixed",0, 0, 0, 1, 0, "" }, /* %bibliocomponent.mix, bibliomset) */
476 { "bibliomset", 0, 0, 0, 1, 0, "" }, /* %bibliocomponent.mix; | bibliomset) */
477 { "biblioset", 0, 0, 0, 9, 0, "" }, /* bibliocomponent.mix */
478 { "blockquote", 0, 0, 0, 9, 0, "" }, /* title */
479 { "book", 0, 0, 0, 9, 0, "" }, /* div.title.content */
480 { "bookinfo", 0, 0, 0, 9, 0, "" }, /* graphic */
481 { "bridgehead", 0, 0, 0, 8, 0, "" }, /* title */
482 { "callout", 0, 0, 0, 9, 0, "" }, /* component.mix */
483 { "calloutlist",0, 0, 0, 9, 0, "" }, /* formalobject.title.content */
484 { "caption", 0, 0, 0, 9, 0, "" }, /* textobject.mix */
485 { "caution", 0, 0, 0, 9, 0, "" }, /* title */
486 { "chapter", 0, 0, 0, 9, 0, "" }, /* chapterinfo */
487 { "chapterinfo",0, 0, 0, 9, 0, "" }, /* graphic */
488 { "citation", 0, 0, 0, 2, 0, "" }, /* para */
489 { "citerefentry",0, 0, 0, 9, 0, "" }, /* refentrytitle */
490 { "citetitle", 0, 0, 0, 2, 0, "" }, /* para */
491 { "city", 0, 0, 0, 4, 0, "" }, /* docinfo */
492 { "classname", 0, 0, 0, 7, 0, "" }, /* smallcptr */
493 { "classsynopsisinfo",0,0, 0, 9, 0, "" }, /* cptr */
494 { "classsynopsis",0, 0, 0, 9, 0, "" }, /* ooclass */
495 { "cmdsynopsis",0, 0, 0, 9, 0, "" }, /* command */
496 { "co", 0, 2, 1, 0, 0, "" },
497 { "collab", 0, 0, 0, 9, 0, "" }, /* collabname */
498 { "collabname", 0, 0, 0, 4, 0, "" }, /* docinfo */
499 { "colophon", 0, 0, 0, 9, 0, "" }, /* sect.title.content */
500 { "colspec", 0, 2, 1, 0, 0, "" },
501 { "colspec", 0, 2, 1, 0, 0, "" },
502 { "command", 0, 0, 0, 9, 0, "" }, /* cptr */
503 { "computeroutput",0, 0, 0, 9, 0, "" }, /* cptr */
504 { "confdates", 0, 0, 0, 4, 0, "" }, /* docinfo */
505 { "confgroup", 0, 0, 0, 9, 0, "" }, /* confdates */
506 { "confnum", 0, 0, 0, 4, 0, "" }, /* docinfo */
507 { "confsponsor",0, 0, 0, 4, 0, "" }, /* docinfo */
508 { "conftitle", 0, 0, 0, 4, 0, "" }, /* docinfo */
509 { "constant", 0, 0, 0, 7, 0, "" }, /* smallcptr */
510 { "constructorsynopsis",0,0, 0, 9, 0, "" }, /* modifier */
511 { "contractnum",0, 0, 0, 4, 0, "" }, /* docinfo */
512 { "contractsponsor",0, 0, 0, 4, 0, "" }, /* docinfo */
513 { "contrib", 0, 0, 0, 4, 0, "" }, /* docinfo */
514 { "copyright", 0, 0, 0, 9, 0, "" }, /* year */
515 { "corpauthor", 0, 0, 0, 4, 0, "" }, /* docinfo */
516 { "corpname", 0, 0, 0, 4, 0, "" }, /* docinfo */
517 { "country", 0, 0, 0, 4, 0, "" }, /* docinfo */
518 { "database", 0, 0, 0, 7, 0, "" }, /* smallcptr */
519 { "date", 0, 0, 0, 4, 0, "" }, /* docinfo */
520 { "dedication", 0, 0, 0, 9, 0, "" }, /* sect.title.content */
521 { "destructorsynopsis",0,0, 0, 9, 0, "" }, /* modifier */
522 { "docinfo", 0, 0, 0, 9, 0, "" },
523 { "edition", 0, 0, 0, 4, 0, "" }, /* docinfo */
524 { "editor", 0, 0, 0, 9, 0, "" }, /* person.ident.mix */
525 { "email", 0, 0, 0, 4, 0, "" }, /* docinfo */
526 { "emphasis", 0, 0, 0, 2, 0, "" }, /* para */
527 { "entry", 0, 0, 0, 9, 0, "" }, /* tbl.entry.mdl */
528 { "entrytbl", 0, 0, 0, 9, 0, "" }, /* tbl.entrytbl.mdl */
529 { "envar", 0, 0, 0, 7, 0, "" }, /* smallcptr */
530 { "epigraph", 0, 0, 0, 9, 0, "" }, /* attribution */
531 { "equation", 0, 0, 0, 9, 0, "" }, /* formalobject.title.content */
532 { "errorcode", 0, 0, 0, 7, 0, "" }, /* smallcptr */
533 { "errorname", 0, 0, 0, 7, 0, "" }, /* smallcptr */
534 { "errortype", 0, 0, 0, 7, 0, "" }, /* smallcptr */
535 { "example", 0, 0, 0, 9, 0, "" }, /* formalobject.title.content */
536 { "exceptionname",0, 0, 0, 7, 0, "" }, /* smallcptr */
537 { "fax", 0, 0, 0, 4, 0, "" }, /* docinfo */
538 { "fieldsynopsis", 0, 0, 0, 9, 0, "" }, /* modifier */
539 { "figure", 0, 0, 0, 9, 0, "" }, /* formalobject.title.content */
540 { "filename", 0, 0, 0, 7, 0, "" }, /* smallcptr */
541 { "firstname", 0, 0, 0, 4, 0, "" }, /* docinfo */
542 { "firstterm", 0, 0, 0, 3, 0, "" }, /* word */
543 { "footnote", 0, 0, 0, 9, 0, "" }, /* footnote.mix */
544 { "footnoteref",0, 2, 1, 0, 0, "" },
545 { "foreignphrase",0, 0, 0, 2, 0, "" }, /* para */
546 { "formalpara", 0, 0, 0, 9, 0, "" }, /* title */
547 { "funcdef", 0, 0, 0, 1, 0, "" },
548 { "funcparams", 0, 0, 0, 9, 0, "" }, /* cptr */
549 { "funcprototype",0, 0, 0, 9, 0, "" }, /* funcdef */
550 { "funcsynopsis",0, 0, 0, 9, 0, "" }, /* funcsynopsisinfo */
551 { "funcsynopsisinfo", 0, 0, 0, 9, 0, "" }, /* cptr */
552 { "function", 0, 0, 0, 9, 0, "" }, /* cptr */
553 { "glossary", 0, 0, 0, 9, 0, "" }, /* glossaryinfo */
554 { "glossaryinfo",0, 0, 0, 9, 0, "" }, /* graphic */
555 { "glossdef", 0, 0, 0, 9, 0, "" }, /* glossdef.mix */
556 { "glossdiv", 0, 0, 0, 9, 0, "" }, /* sect.title.content */
557 { "glossentry", 0, 0, 0, 9, 0, "" }, /* glossterm */
558 { "glosslist", 0, 0, 0, 9, 0, "" }, /* glossentry */
559 { "glossseealso",0, 0, 1, 2, 0, "" }, /* para */
560 { "glosssee", 0, 0, 1, 2, 0, "" }, /* para */
561 { "glossterm", 0, 0, 0, 2, 0, "" }, /* para */
562 { "graphic", 0, 0, 0, 9, 0, "" },
563 { "graphicco", 0, 0, 0, 9, 0, "" }, /* areaspec */
564 { "group", 0, 0, 0, 9, 0, "" }, /* arg */
565 { "guibutton", 0, 0, 0, 7, 0, "" }, /* smallcptr */
566 { "guiicon", 0, 0, 0, 7, 0, "" }, /* smallcptr */
567 { "guilabel", 0, 0, 0, 7, 0, "" }, /* smallcptr */
568 { "guimenuitem",0, 0, 0, 7, 0, "" }, /* smallcptr */
569 { "guimenu", 0, 0, 0, 7, 0, "" }, /* smallcptr */
570 { "guisubmenu", 0, 0, 0, 7, 0, "" }, /* smallcptr */
571 { "hardware", 0, 0, 0, 7, 0, "" }, /* smallcptr */
572 { "highlights", 0, 0, 0, 9, 0, "" }, /* highlights.mix */
573 { "holder", 0, 0, 0, 4, 0, "" }, /* docinfo */
574 { "honorific", 0, 0, 0, 4, 0, "" }, /* docinfo */
575 { "imagedata", 0, 2, 1, 0, 0, "" },
576 { "imageobjectco",0, 0, 0, 9, 0, "" }, /* areaspec */
577 { "imageobject",0, 0, 0, 9, 0, "" }, /* objectinfo */
578 { "important", 0, 0, 0, 9, 0, "" }, /* title */
579 { "indexdiv", 0, 0, 0, 9, 0, "" }, /* sect.title.content */
580 { "indexentry", 0, 0, 0, 9, 0, "" }, /* primaryie */
581 { "index", 0, 0, 0, 9, 0, "" }, /* indexinfo */
582 { "indexinfo", 0, 0, 0, 9, 0, "" }, /* graphic */
583 { "indexterm", 0, 0, 0, 9, 0, "" }, /* primary */
584 { "informalequation",0, 0, 0, 9, 0, "" }, /* equation.content */
585 { "informalexample",0, 0, 0, 9, 0, "" }, /* example.mix */
586 { "informalfigure",0, 0, 0, 9, 0, "" }, /* figure.mix */
587 { "informaltable",0, 0, 0, 9, 0, "" }, /* graphic */
588 { "initializer",0, 0, 0, 7, 0, "" }, /* smallcptr */
589 { "inlineequation",0, 0, 0, 9, 0, "" }, /* inlineequation.content */
590 { "inlinegraphic",0, 0, 0, 9, 0, "" },
591 { "inlinemediaobject",0,0, 0, 9, 0, "" }, /* objectinfo */
592 { "interfacename",0, 0, 0, 7, 0, "" }, /* smallcptr */
593 { "interface", 0, 0, 0, 7, 0, "" }, /* smallcptr */
594 { "invpartnumber",0, 0, 0, 4, 0, "" }, /* docinfo */
595 { "isbn", 0, 0, 0, 4, 0, "" }, /* docinfo */
596 { "issn", 0, 0, 0, 4, 0, "" }, /* docinfo */
597 { "issuenum", 0, 0, 0, 4, 0, "" }, /* docinfo */
598 { "itemizedlist",0, 0, 0, 9, 0, "" }, /* formalobject.title.content */
599 { "itermset", 0, 0, 0, 9, 0, "" }, /* indexterm */
600 { "jobtitle", 0, 0, 0, 4, 0, "" }, /* docinfo */
601 { "keycap", 0, 0, 0, 7, 0, "" }, /* smallcptr */
602 { "keycode", 0, 0, 0, 7, 0, "" }, /* smallcptr */
603 { "keycombo", 0, 0, 0, 9, 0, "" }, /* keycap */
604 { "keysym", 0, 0, 0, 7, 0, "" }, /* smallcptr */
605 { "keyword", 0, 0, 0, 1, 0, "" },
606 { "keywordset", 0, 0, 0, 9, 0, "" }, /* keyword */
607 { "label", 0, 0, 0, 3, 0, "" }, /* word */
608 { "legalnotice",0, 0, 0, 9, 0, "" }, /* title */
609 { "lineage", 0, 0, 0, 4, 0, "" }, /* docinfo */
610 { "lineannotation",0, 0, 0, 2, 0, "" }, /* para */
611 { "link", 0, 0, 0, 2, 0, "" }, /* para */
612 { "listitem", 0, 0, 0, 9, 0, "" }, /* component.mix */
613 { "literal", 0, 0, 0, 9, 0, "" }, /* cptr */
614 { "literallayout",0, 0, 0, 2, 0, "" }, /* para */
615 { "lot", 0, 0, 0, 9, 0, "" }, /* bookcomponent.title.content */
616 { "lotentry", 0, 0, 0, 2, 0, "" }, /* para */
617 { "manvolnum", 0, 0, 0, 3, 0, "" }, /* word */
618 { "markup", 0, 0, 0, 7, 0, "" }, /* smallcptr */
619 { "medialabel", 0, 0, 0, 7, 0, "" }, /* smallcptr */
620 { "mediaobjectco",0, 0, 0, 9, 0, "" }, /* objectinfo */
621 { "mediaobject",0, 0, 0, 9, 0, "" }, /* objectinfo */
622 { "member", 0, 0, 0, 2, 0, "" }, /* para */
623 { "menuchoice", 0, 0, 0, 9, 0, "" }, /* shortcut */
624 { "methodname", 0, 0, 0, 7, 0, "" }, /* smallcptr */
625 { "methodparam",0, 0, 0, 9, 0, "" }, /* modifier */
626 { "methodsynopsis",0, 0, 0, 9, 0, "" }, /* modifier */
627 { "modespec", 0, 0, 0, 4, 0, "" }, /* docinfo */
628 { "modifier", 0, 0, 0, 7, 0, "" }, /* smallcptr */
629 { "mousebutton",0, 0, 0, 7, 0, "" }, /* smallcptr */
630 { "msgaud", 0, 0, 0, 2, 0, "" }, /* para */
631 { "msgentry", 0, 0, 0, 9, 0, "" }, /* msg */
632 { "msgexplan", 0, 0, 0, 9, 0, "" }, /* title */
633 { "msginfo", 0, 0, 0, 9, 0, "" }, /* msglevel */
634 { "msglevel", 0, 0, 0, 7, 0, "" }, /* smallcptr */
635 { "msgmain", 0, 0, 0, 9, 0, "" }, /* title */
636 { "msgorig", 0, 0, 0, 7, 0, "" }, /* smallcptr */
637 { "msgrel", 0, 0, 0, 9, 0, "" }, /* title */
638 { "msgset", 0, 0, 0, 9, 0, "" }, /* formalobject.title.content */
639 { "msgsub", 0, 0, 0, 9, 0, "" }, /* title */
640 { "msgtext", 0, 0, 0, 9, 0, "" }, /* component.mix */
641 { "msg", 0, 0, 0, 9, 0, "" }, /* title */
642 { "note", 0, 0, 0, 9, 0, "" }, /* title */
643 { "objectinfo", 0, 0, 0, 9, 0, "" }, /* graphic */
644 { "olink", 0, 0, 0, 2, 0, "" }, /* para */
645 { "ooclass", 0, 0, 0, 9, 0, "" }, /* modifier */
646 { "ooexception",0, 0, 0, 9, 0, "" }, /* modifier */
647 { "oointerface",0, 0, 0, 9, 0, "" }, /* modifier */
648 { "optional", 0, 0, 0, 9, 0, "" }, /* cptr */
649 { "option", 0, 0, 0, 7, 0, "" }, /* smallcptr */
650 { "orderedlist",0, 0, 0, 9, 0, "" }, /* formalobject.title.content */
651 { "orgdiv", 0, 0, 0, 4, 0, "" }, /* docinfo */
652 { "orgname", 0, 0, 0, 4, 0, "" }, /* docinfo */
653 { "otheraddr", 0, 0, 0, 4, 0, "" }, /* docinfo */
654 { "othercredit",0, 0, 0, 9, 0, "" }, /* person.ident.mix */
655 { "othername", 0, 0, 0, 4, 0, "" }, /* docinfo */
656 { "pagenums", 0, 0, 0, 4, 0, "" }, /* docinfo */
657 { "paramdef", 0, 0, 0, 1, 0, "" },
658 { "parameter", 0, 0, 0, 7, 0, "" }, /* smallcptr */
659 { "para", 0, 0, 0, 2, 0, "" }, /* para */
660 { "partinfo", 0, 0, 0, 9, 0, "" }, /* graphic */
661 { "partintro", 0, 0, 0, 9, 0, "" }, /* div.title.content */
662 { "part", 0, 0, 0, 9, 0, "" }, /* partinfo */
663 { "phone", 0, 0, 0, 4, 0, "" }, /* docinfo */
664 { "phrase", 0, 0, 0, 2, 0, "" }, /* para */
665 { "pob", 0, 0, 0, 4, 0, "" }, /* docinfo */
666 { "postcode", 0, 0, 0, 4, 0, "" }, /* docinfo */
667 { "prefaceinfo",0, 0, 0, 9, 0, "" }, /* graphic */
668 { "preface", 0, 0, 0, 9, 0, "" }, /* prefaceinfo */
669 { "primaryie", 0, 0, 0, 4, 0, "" }, /* ndxterm */
670 { "primary", 0, 0, 0, 9, 0, "" }, /* ndxterm */
671 { "printhistory",0, 0, 0, 9, 0, "" }, /* para.class */
672 { "procedure", 0, 0, 0, 9, 0, "" }, /* formalobject.title.content */
673 { "productname",0, 0, 0, 2, 0, "" }, /* para */
674 { "productnumber",0, 0, 0, 4, 0, "" }, /* docinfo */
675 { "programlistingco",0, 0, 0, 9, 0, "" }, /* areaspec */
676 { "programlisting",0, 0, 0, 2, 0, "" }, /* para */
677 { "prompt", 0, 0, 0, 7, 0, "" }, /* smallcptr */
678 { "property", 0, 0, 0, 7, 0, "" }, /* smallcptr */
679 { "pubdate", 0, 0, 0, 4, 0, "" }, /* docinfo */
680 { "publishername",0, 0, 0, 4, 0, "" }, /* docinfo */
681 { "publisher", 0, 0, 0, 9, 0, "" }, /* publishername */
682 { "pubsnumber", 0, 0, 0, 4, 0, "" }, /* docinfo */
683 { "qandadiv", 0, 0, 0, 9, 0, "" }, /* formalobject.title.content */
684 { "qandaentry", 0, 0, 0, 9, 0, "" }, /* revhistory */
685 { "qandaset", 0, 0, 0, 9, 0, "" }, /* formalobject.title.content */
686 { "question", 0, 0, 0, 9, 0, "" }, /* label */
687 { "quote", 0, 0, 0, 2, 0, "" }, /* para */
688 { "refclass", 0, 0, 0, 9, 0, "" }, /* refclass.char.mix */
689 { "refdescriptor",0, 0, 0, 9, 0, "" }, /* refname.char.mix */
690 { "refentryinfo",0, 0, 0, 9, 0, "" }, /* graphic */
691 { "refentry", 0, 0, 0, 9, 0, "" }, /* ndxterm.class */
692 { "refentrytitle",0, 0, 0, 2, 0, "" }, /* para */
693 { "referenceinfo",0, 0, 0, 9, 0, "" }, /* graphic */
694 { "reference", 0, 0, 0, 9, 0, "" }, /* referenceinfo */
695 { "refmeta", 0, 0, 0, 9, 0, "" }, /* ndxterm.class */
696 { "refmiscinfo",0, 0, 0, 4, 0, "" }, /* docinfo */
697 { "refnamediv", 0, 0, 0, 9, 0, "" }, /* refdescriptor */
698 { "refname", 0, 0, 0, 9, 0, "" }, /* refname.char.mix */
699 { "refpurpose", 0, 0, 0, 9, 0, "" }, /* refinline.char.mix */
700 { "refsect1info",0, 0, 0, 9, 0, "" }, /* graphic */
701 { "refsect1", 0, 0, 0, 9, 0, "" }, /* refsect */
702 { "refsect2info",0, 0, 0, 9, 0, "" }, /* graphic */
703 { "refsect2", 0, 0, 0, 9, 0, "" }, /* refsect */
704 { "refsect3info",0, 0, 0, 9, 0, "" }, /* graphic */
705 { "refsect3", 0, 0, 0, 9, 0, "" }, /* refsect */
706 { "refsynopsisdivinfo",0,0, 0, 9, 0, "" }, /* graphic */
707 { "refsynopsisdiv",0, 0, 0, 9, 0, "" }, /* refsynopsisdivinfo */
708 { "releaseinfo",0, 0, 0, 4, 0, "" }, /* docinfo */
709 { "remark", 0, 0, 0, 2, 0, "" }, /* para */
710 { "replaceable",0, 0, 0, 1, 0, "" },
711 { "returnvalue",0, 0, 0, 7, 0, "" }, /* smallcptr */
712 { "revdescription",0, 0, 0, 9, 0, "" }, /* revdescription.mix */
713 { "revhistory", 0, 0, 0, 9, 0, "" }, /* revision */
714 { "revision", 0, 0, 0, 9, 0, "" }, /* revnumber */
715 { "revnumber", 0, 0, 0, 4, 0, "" }, /* docinfo */
716 { "revremark", 0, 0, 0, 4, 0, "" }, /* docinfo */
717 { "row", 0, 0, 0, 9, 0, "" }, /* tbl.row.mdl */
718 { "row", 0, 0, 0, 9, 0, "" }, /* tbl.row.mdl */
719 { "sbr", 0, 2, 1, 0, 0, "" },
720 { "screenco", 0, 0, 0, 9, 0, "" }, /* areaspec */
721 { "screeninfo", 0, 0, 0, 2, 0, "" }, /* para */
722 { "screen", 0, 0, 0, 2, 0, "" }, /* para */
723 { "screenshot", 0, 0, 0, 9, 0, "" }, /* screeninfo */
724 { "secondaryie",0, 0, 0, 4, 0, "" }, /* ndxterm */
725 { "secondary", 0, 0, 0, 4, 0, "" }, /* ndxterm */
726 { "sect1info", 0, 0, 0, 9, 0, "" }, /* graphic */
727 { "sect1", 0, 0, 0, 9, 0, "" }, /* sect */
728 { "sect2info", 0, 0, 0, 9, 0, "" }, /* graphic */
729 { "sect2", 0, 0, 0, 9, 0, "" }, /* sect */
730 { "sect3info", 0, 0, 0, 9, 0, "" }, /* graphic */
731 { "sect3", 0, 0, 0, 9, 0, "" }, /* sect */
732 { "sect4info", 0, 0, 0, 9, 0, "" }, /* graphic */
733 { "sect4", 0, 0, 0, 9, 0, "" }, /* sect */
734 { "sect5info", 0, 0, 0, 9, 0, "" }, /* graphic */
735 { "sect5", 0, 0, 0, 9, 0, "" }, /* sect */
736 { "sectioninfo",0, 0, 0, 9, 0, "" }, /* graphic */
737 { "section", 0, 0, 0, 9, 0, "" }, /* sectioninfo */
738 { "seealsoie", 0, 0, 0, 4, 0, "" }, /* ndxterm */
739 { "seealso", 0, 0, 0, 4, 0, "" }, /* ndxterm */
740 { "seeie", 0, 0, 0, 4, 0, "" }, /* ndxterm */
741 { "see", 0, 0, 0, 4, 0, "" }, /* ndxterm */
742 { "seglistitem",0, 0, 0, 9, 0, "" }, /* seg */
743 { "segmentedlist",0, 0, 0, 9, 0, "" }, /* formalobject.title.content */
744 { "seg", 0, 0, 0, 2, 0, "" }, /* para */
745 { "segtitle", 0, 0, 0, 8, 0, "" }, /* title */
746 { "seriesvolnums", 0, 0, 0, 4, 0, "" }, /* docinfo */
747 { "set", 0, 0, 0, 9, 0, "" }, /* div.title.content */
748 { "setindexinfo",0, 0, 0, 9, 0, "" }, /* graphic */
749 { "setindex", 0, 0, 0, 9, 0, "" }, /* setindexinfo */
750 { "setinfo", 0, 0, 0, 9, 0, "" }, /* graphic */
751 { "sgmltag", 0, 0, 0, 7, 0, "" }, /* smallcptr */
752 { "shortaffil", 0, 0, 0, 4, 0, "" }, /* docinfo */
753 { "shortcut", 0, 0, 0, 9, 0, "" }, /* keycap */
754 { "sidebarinfo",0, 0, 0, 9, 0, "" }, /* graphic */
755 { "sidebar", 0, 0, 0, 9, 0, "" }, /* sidebarinfo */
756 { "simpara", 0, 0, 0, 2, 0, "" }, /* para */
757 { "simplelist", 0, 0, 0, 9, 0, "" }, /* member */
758 { "simplemsgentry", 0, 0, 0, 9, 0, "" }, /* msgtext */
759 { "simplesect", 0, 0, 0, 9, 0, "" }, /* sect.title.content */
760 { "spanspec", 0, 2, 1, 0, 0, "" },
761 { "state", 0, 0, 0, 4, 0, "" }, /* docinfo */
762 { "step", 0, 0, 0, 9, 0, "" }, /* title */
763 { "street", 0, 0, 0, 4, 0, "" }, /* docinfo */
764 { "structfield",0, 0, 0, 7, 0, "" }, /* smallcptr */
765 { "structname", 0, 0, 0, 7, 0, "" }, /* smallcptr */
766 { "subjectset", 0, 0, 0, 9, 0, "" }, /* subject */
767 { "subject", 0, 0, 0, 9, 0, "" }, /* subjectterm */
768 { "subjectterm",0, 0, 0, 1, 0, "" },
769 { "subscript", 0, 0, 0, 1, 0, "" },
770 { "substeps", 0, 0, 0, 9, 0, "" }, /* step */
771 { "subtitle", 0, 0, 0, 8, 0, "" }, /* title */
772 { "superscript", 0, 0, 0, 1, 0, "" },
773 { "surname", 0, 0, 0, 4, 0, "" }, /* docinfo */
774 { "symbol", 0, 0, 0, 7, 0, "" }, /* smallcptr */
775 { "synopfragment", 0, 0, 0, 9, 0, "" }, /* arg */
776 { "synopfragmentref", 0, 0, 0, 1, 0, "" },
777 { "synopsis", 0, 0, 0, 2, 0, "" }, /* para */
778 { "systemitem", 0, 0, 0, 7, 0, "" }, /* smallcptr */
779 { "table", 0, 0, 0, 9, 0, "" }, /* tbl.table.mdl */
780 /* { "%tbl.table.name;", 0, 0, 0, 9, 0, "" },*/ /* tbl.table.mdl */
781 { "tbody", 0, 0, 0, 9, 0, "" }, /* row */
782 { "tbody", 0, 0, 0, 9, 0, "" }, /* row */
783 { "term", 0, 0, 0, 2, 0, "" }, /* para */
784 { "tertiaryie", 0, 0, 0, 4, 0, "" }, /* ndxterm */
785 { "tertiary ", 0, 0, 0, 4, 0, "" }, /* ndxterm */
786 { "textobject", 0, 0, 0, 9, 0, "" }, /* objectinfo */
787 { "tfoot", 0, 0, 0, 9, 0, "" }, /* tbl.hdft.mdl */
788 { "tgroup", 0, 0, 0, 9, 0, "" }, /* tbl.tgroup.mdl */
789 { "tgroup", 0, 0, 0, 9, 0, "" }, /* tbl.tgroup.mdl */
790 { "thead", 0, 0, 0, 9, 0, "" }, /* row */
791 { "thead", 0, 0, 0, 9, 0, "" }, /* tbl.hdft.mdl */
792 { "tip", 0, 0, 0, 9, 0, "" }, /* title */
793 { "titleabbrev",0, 0, 0, 8, 0, "" }, /* title */
794 { "title", 0, 0, 0, 8, 0, "" }, /* title */
795 { "tocback", 0, 0, 0, 2, 0, "" }, /* para */
796 { "toc", 0, 0, 0, 9, 0, "" }, /* bookcomponent.title.content */
797 { "tocchap", 0, 0, 0, 9, 0, "" }, /* tocentry */
798 { "tocentry", 0, 0, 0, 2, 0, "" }, /* para */
799 { "tocfront", 0, 0, 0, 2, 0, "" }, /* para */
800 { "toclevel1", 0, 0, 0, 9, 0, "" }, /* tocentry */
801 { "toclevel2", 0, 0, 0, 9, 0, "" }, /* tocentry */
802 { "toclevel3", 0, 0, 0, 9, 0, "" }, /* tocentry */
803 { "toclevel4", 0, 0, 0, 9, 0, "" }, /* tocentry */
804 { "toclevel5", 0, 0, 0, 9, 0, "" }, /* tocentry */
805 { "tocpart", 0, 0, 0, 9, 0, "" }, /* tocentry */
806 { "token", 0, 0, 0, 7, 0, "" }, /* smallcptr */
807 { "trademark", 0, 0, 0, 1, 0, "" },
808 { "type", 0, 0, 0, 7, 0, "" }, /* smallcptr */
809 { "ulink", 0, 0, 0, 2, 0, "" }, /* para */
810 { "userinput", 0, 0, 0, 9, 0, "" }, /* cptr */
811 { "varargs", 0, 2, 1, 0, 0, "" },
812 { "variablelist",0, 0, 0, 9, 0, "" }, /* formalobject.title.content */
813 { "varlistentry",0, 0, 0, 9, 0, "" }, /* term */
814 { "varname", 0, 0, 0, 7, 0, "" }, /* smallcptr */
815 { "videodata", 0, 2, 1, 0, 0, "" },
816 { "videoobject",0, 0, 0, 9, 0, "" }, /* objectinfo */
817 { "void", 0, 2, 1, 0, 0, "" },
818 { "volumenum", 0, 0, 0, 4, 0, "" }, /* docinfo */
819 { "warning", 0, 0, 0, 9, 0, "" }, /* title */
820 { "wordasword", 0, 0, 0, 3, 0, "" }, /* word */
821 { "xref", 0, 2, 1, 0, 0, "" },
822 { "year", 0, 0, 0, 4, 0, "" }, /* docinfo */
823 };
824
825 #if 0
826 /*
827 * start tags that imply the end of a current element
828 * any tag of each line implies the end of the current element if the type of
829 * that element is in the same line
830 */
831 static const char *docbEquEnd[] = {
832 "dt", "dd", "li", "option", NULL,
833 "h1", "h2", "h3", "h4", "h5", "h6", NULL,
834 "ol", "menu", "dir", "address", "pre", "listing", "xmp", NULL,
835 NULL
836 };
837 #endif
838
839 /*
840 * according the SGML DTD, HR should be added to the 2nd line above, as it
841 * is not allowed within a H1, H2, H3, etc. But we should tolerate that case
842 * because many documents contain rules in headings...
843 */
844
845 /*
846 * start tags that imply the end of current element
847 */
848 static const char *docbStartClose[] = {
849 NULL
850 };
851
852 static const char** docbStartCloseIndex[100];
853 static int docbStartCloseIndexinitialized = 0;
854
855 /************************************************************************
856 * *
857 * functions to handle SGML specific data *
858 * *
859 ************************************************************************/
860
861 /**
862 * docbInitAutoClose:
863 *
864 * Initialize the docbStartCloseIndex for fast lookup of closing tags names.
865 *
866 */
867 static void
868 docbInitAutoClose(void) {
869 int indx, i = 0;
870
871 if (docbStartCloseIndexinitialized) return;
872
873 for (indx = 0;indx < 100;indx ++) docbStartCloseIndex[indx] = NULL;
874 indx = 0;
875 while ((docbStartClose[i] != NULL) && (indx < 100 - 1)) {
876 docbStartCloseIndex[indx++] = &docbStartClose[i];
877 while (docbStartClose[i] != NULL) i++;
878 i++;
879 }
880 }
881
882 /**
883 * docbTagLookup:
884 * @tag: The tag name
885 *
886 * Lookup the SGML tag in the ElementTable
887 *
888 * Returns the related docbElemDescPtr or NULL if not found.
889 */
890 static docbElemDescPtr
891 docbTagLookup(const xmlChar *tag) {
892 unsigned int i;
893
894 for (i = 0; i < (sizeof(docbookElementTable) /
895 sizeof(docbookElementTable[0]));i++) {
896 if (xmlStrEqual(tag, BAD_CAST docbookElementTable[i].name))
897 return(&docbookElementTable[i]);
898 }
899 return(NULL);
900 }
901
902 /**
903 * docbCheckAutoClose:
904 * @newtag: The new tag name
905 * @oldtag: The old tag name
906 *
907 * Checks whether the new tag is one of the registered valid tags for
908 * closing old.
909 * Initialize the docbStartCloseIndex for fast lookup of closing tags names.
910 *
911 * Returns 0 if no, 1 if yes.
912 */
913 static int
914 docbCheckAutoClose(const xmlChar *newtag, const xmlChar *oldtag) {
915 int i, indx;
916 const char **closed = NULL;
917
918 if (docbStartCloseIndexinitialized == 0) docbInitAutoClose();
919
920 /* inefficient, but not a big deal */
921 for (indx = 0; indx < 100;indx++) {
922 closed = docbStartCloseIndex[indx];
923 if (closed == NULL) return(0);
924 if (xmlStrEqual(BAD_CAST *closed, newtag)) break;
925 }
926
927 i = closed - docbStartClose;
928 i++;
929 while (docbStartClose[i] != NULL) {
930 if (xmlStrEqual(BAD_CAST docbStartClose[i], oldtag)) {
931 return(1);
932 }
933 i++;
934 }
935 return(0);
936 }
937
938 /**
939 * docbAutoCloseOnClose:
940 * @ctxt: an SGML parser context
941 * @newtag: The new tag name
942 *
943 * The DocBook DTD allows an ending tag to implicitly close other tags.
944 */
945 static void
946 docbAutoCloseOnClose(docbParserCtxtPtr ctxt, const xmlChar *newtag) {
947 docbElemDescPtr info;
948 xmlChar *oldname;
949 int i;
950
951 if ((newtag[0] == '/') && (newtag[1] == 0))
952 return;
953
954 #ifdef DEBUG
955 xmlGenericError(xmlGenericErrorContext,"Close of %s stack: %d elements\n", newtag, ctxt->nameNr);
956 for (i = 0;i < ctxt->nameNr;i++)
957 xmlGenericError(xmlGenericErrorContext,"%d : %s\n", i, ctxt->nameTab[i]);
958 #endif
959
960 for (i = (ctxt->nameNr - 1);i >= 0;i--) {
961 if (xmlStrEqual(newtag, ctxt->nameTab[i])) break;
962 }
963 if (i < 0) return;
964
965 while (!xmlStrEqual(newtag, ctxt->name)) {
966 info = docbTagLookup(ctxt->name);
967 if ((info == NULL) || (info->endTag == 1)) {
968 #ifdef DEBUG
969 xmlGenericError(xmlGenericErrorContext,"docbAutoCloseOnClose: %s closes %s\n", newtag, ctxt->name);
970 #endif
971 } else {
972 if ((ctxt->sax != NULL) && (ctxt->sax->error != NULL))
973 ctxt->sax->error(ctxt->userData,
974 "Opening and ending tag mismatch: %s and %s\n",
975 newtag, ctxt->name);
976 ctxt->wellFormed = 0;
977 }
978 if ((ctxt->sax != NULL) && (ctxt->sax->endElement != NULL))
979 ctxt->sax->endElement(ctxt->userData, ctxt->name);
980 oldname = docbnamePop(ctxt);
981 if (oldname != NULL) {
982 #ifdef DEBUG
983 xmlGenericError(xmlGenericErrorContext,"docbAutoCloseOnClose: popped %s\n", oldname);
984 #endif
985 xmlFree(oldname);
986 }
987 }
988 }
989
990 /**
991 * docbAutoClose:
992 * @ctxt: an SGML parser context
993 * @newtag: The new tag name or NULL
994 *
995 * The DocBook DTD allows a tag to implicitly close other tags.
996 * The list is kept in docbStartClose array. This function is
997 * called when a new tag has been detected and generates the
998 * appropriates closes if possible/needed.
999 * If newtag is NULL this mean we are at the end of the resource
1000 * and we should check
1001 */
1002 static void
1003 docbAutoClose(docbParserCtxtPtr ctxt, const xmlChar *newtag) {
1004 xmlChar *oldname;
1005 while ((newtag != NULL) && (ctxt->name != NULL) &&
1006 (docbCheckAutoClose(newtag, ctxt->name))) {
1007 #ifdef DEBUG
1008 xmlGenericError(xmlGenericErrorContext,"docbAutoClose: %s closes %s\n", newtag, ctxt->name);
1009 #endif
1010 if ((ctxt->sax != NULL) && (ctxt->sax->endElement != NULL))
1011 ctxt->sax->endElement(ctxt->userData, ctxt->name);
1012 oldname = docbnamePop(ctxt);
1013 if (oldname != NULL) {
1014 #ifdef DEBUG
1015 xmlGenericError(xmlGenericErrorContext,"docbAutoClose: popped %s\n", oldname);
1016 #endif
1017 xmlFree(oldname);
1018 }
1019 }
1020 }
1021
1022 /**
1023 * docbAutoCloseTag:
1024 * @doc: the SGML document
1025 * @name: The tag name
1026 * @elem: the SGML element
1027 *
1028 * The DocBook DTD allows a tag to implicitly close other tags.
1029 * The list is kept in docbStartClose array. This function checks
1030 * if the element or one of it's children would autoclose the
1031 * given tag.
1032 *
1033 * Returns 1 if autoclose, 0 otherwise
1034 */
1035 static int
1036 docbAutoCloseTag(docbDocPtr doc, const xmlChar *name, docbNodePtr elem) {
1037 docbNodePtr child;
1038
1039 if (elem == NULL) return(1);
1040 if (xmlStrEqual(name, elem->name)) return(0);
1041 if (docbCheckAutoClose(elem->name, name)) return(1);
1042 child = elem->children;
1043 while (child != NULL) {
1044 if (docbAutoCloseTag(doc, name, child)) return(1);
1045 child = child->next;
1046 }
1047 return(0);
1048 }
1049
1050 /************************************************************************
1051 * *
1052 * The list of SGML predefined entities *
1053 * *
1054 ************************************************************************/
1055
1056
1057 static docbEntityDesc
1058 docbookEntitiesTable[] = {
1059 /*
1060 * the 4 absolute ones, plus apostrophe.
1061 */
1062 { 0x0026, "amp", "AMPERSAND" },
1063 { 0x003C, "lt", "LESS-THAN SIGN" },
1064
1065 /*
1066 * Converted with VI macros from docbook ent files
1067 */
1068 { 0x0021, "excl", "EXCLAMATION MARK" },
1069 { 0x0022, "quot", "QUOTATION MARK" },
1070 { 0x0023, "num", "NUMBER SIGN" },
1071 { 0x0024, "dollar", "DOLLAR SIGN" },
1072 { 0x0025, "percnt", "PERCENT SIGN" },
1073 { 0x0027, "apos", "APOSTROPHE" },
1074 { 0x0028, "lpar", "LEFT PARENTHESIS" },
1075 { 0x0029, "rpar", "RIGHT PARENTHESIS" },
1076 { 0x002A, "ast", "ASTERISK OPERATOR" },
1077 { 0x002B, "plus", "PLUS SIGN" },
1078 { 0x002C, "comma", "COMMA" },
1079 { 0x002D, "hyphen", "HYPHEN-MINUS" },
1080 { 0x002E, "period", "FULL STOP" },
1081 { 0x002F, "sol", "SOLIDUS" },
1082 { 0x003A, "colon", "COLON" },
1083 { 0x003B, "semi", "SEMICOLON" },
1084 { 0x003D, "equals", "EQUALS SIGN" },
1085 { 0x003E, "gt", "GREATER-THAN SIGN" },
1086 { 0x003F, "quest", "QUESTION MARK" },
1087 { 0x0040, "commat", "COMMERCIAL AT" },
1088 { 0x005B, "lsqb", "LEFT SQUARE BRACKET" },
1089 { 0x005C, "bsol", "REVERSE SOLIDUS" },
1090 { 0x005D, "rsqb", "RIGHT SQUARE BRACKET" },
1091 { 0x005E, "circ", "RING OPERATOR" },
1092 { 0x005F, "lowbar", "LOW LINE" },
1093 { 0x0060, "grave", "GRAVE ACCENT" },
1094 { 0x007B, "lcub", "LEFT CURLY BRACKET" },
1095 { 0x007C, "verbar", "VERTICAL LINE" },
1096 { 0x007D, "rcub", "RIGHT CURLY BRACKET" },
1097 { 0x00A0, "nbsp", "NO-BREAK SPACE" },
1098 { 0x00A1, "iexcl", "INVERTED EXCLAMATION MARK" },
1099 { 0x00A2, "cent", "CENT SIGN" },
1100 { 0x00A3, "pound", "POUND SIGN" },
1101 { 0x00A4, "curren", "CURRENCY SIGN" },
1102 { 0x00A5, "yen", "YEN SIGN" },
1103 { 0x00A6, "brvbar", "BROKEN BAR" },
1104 { 0x00A7, "sect", "SECTION SIGN" },
1105 { 0x00A8, "die", "" },
1106 { 0x00A8, "Dot", "" },
1107 { 0x00A8, "uml", "" },
1108 { 0x00A9, "copy", "COPYRIGHT SIGN" },
1109 { 0x00AA, "ordf", "FEMININE ORDINAL INDICATOR" },
1110 { 0x00AB, "laquo", "LEFT-POINTING DOUBLE ANGLE QUOTATION MARK" },
1111 { 0x00AC, "not", "NOT SIGN" },
1112 { 0x00AD, "shy", "SOFT HYPHEN" },
1113 { 0x00AE, "reg", "REG TRADE MARK SIGN" },
1114 { 0x00AF, "macr", "MACRON" },
1115 { 0x00B0, "deg", "DEGREE SIGN" },
1116 { 0x00B1, "plusmn", "PLUS-MINUS SIGN" },
1117 { 0x00B2, "sup2", "SUPERSCRIPT TWO" },
1118 { 0x00B3, "sup3", "SUPERSCRIPT THREE" },
1119 { 0x00B4, "acute", "ACUTE ACCENT" },
1120 { 0x00B5, "micro", "MICRO SIGN" },
1121 { 0x00B6, "para", "PILCROW SIGN" },
1122 { 0x00B7, "middot", "MIDDLE DOT" },
1123 { 0x00B8, "cedil", "CEDILLA" },
1124 { 0x00B9, "sup1", "SUPERSCRIPT ONE" },
1125 { 0x00BA, "ordm", "MASCULINE ORDINAL INDICATOR" },
1126 { 0x00BB, "raquo", "RIGHT-POINTING DOUBLE ANGLE QUOTATION MARK" },
1127 { 0x00BC, "frac14", "VULGAR FRACTION ONE QUARTER" },
1128 { 0x00BD, "frac12", "VULGAR FRACTION ONE HALF" },
1129 { 0x00BD, "half", "VULGAR FRACTION ONE HALF" },
1130 { 0x00BE, "frac34", "VULGAR FRACTION THREE QUARTERS" },
1131 { 0x00BF, "iquest", "INVERTED QUESTION MARK" },
1132 { 0x00C0, "Agrave", "LATIN CAPITAL LETTER A WITH GRAVE" },
1133 { 0x00C1, "Aacute", "LATIN CAPITAL LETTER A WITH ACUTE" },
1134 { 0x00C2, "Acirc", "LATIN CAPITAL LETTER A WITH CIRCUMFLEX" },
1135 { 0x00C3, "Atilde", "LATIN CAPITAL LETTER A WITH TILDE" },
1136 { 0x00C4, "Auml", "LATIN CAPITAL LETTER A WITH DIAERESIS" },
1137 { 0x00C5, "Aring", "LATIN CAPITAL LETTER A WITH RING ABOVE" },
1138 { 0x00C6, "AElig", "LATIN CAPITAL LETTER AE" },
1139 { 0x00C7, "Ccedil", "LATIN CAPITAL LETTER C WITH CEDILLA" },
1140 { 0x00C8, "Egrave", "LATIN CAPITAL LETTER E WITH GRAVE" },
1141 { 0x00C9, "Eacute", "LATIN CAPITAL LETTER E WITH ACUTE" },
1142 { 0x00CA, "Ecirc", "LATIN CAPITAL LETTER E WITH CIRCUMFLEX" },
1143 { 0x00CB, "Euml", "LATIN CAPITAL LETTER E WITH DIAERESIS" },
1144 { 0x00CC, "Igrave", "LATIN CAPITAL LETTER I WITH GRAVE" },
1145 { 0x00CD, "Iacute", "LATIN CAPITAL LETTER I WITH ACUTE" },
1146 { 0x00CE, "Icirc", "LATIN CAPITAL LETTER I WITH CIRCUMFLEX" },
1147 { 0x00CF, "Iuml", "LATIN CAPITAL LETTER I WITH DIAERESIS" },
1148 { 0x00D0, "ETH", "LATIN CAPITAL LETTER ETH" },
1149 { 0x00D1, "Ntilde", "LATIN CAPITAL LETTER N WITH TILDE" },
1150 { 0x00D2, "Ograve", "LATIN CAPITAL LETTER O WITH GRAVE" },
1151 { 0x00D3, "Oacute", "LATIN CAPITAL LETTER O WITH ACUTE" },
1152 { 0x00D4, "Ocirc", "LATIN CAPITAL LETTER O WITH CIRCUMFLEX" },
1153 { 0x00D5, "Otilde", "LATIN CAPITAL LETTER O WITH TILDE" },
1154 { 0x00D6, "Ouml", "LATIN CAPITAL LETTER O WITH DIAERESIS" },
1155 { 0x00D7, "times", "MULTIPLICATION SIGN" },
1156 { 0x00D8, "Oslash", "LATIN CAPITAL LETTER O WITH STROKE" },
1157 { 0x00D9, "Ugrave", "LATIN CAPITAL LETTER U WITH GRAVE" },
1158 { 0x00DA, "Uacute", "LATIN CAPITAL LETTER U WITH ACUTE" },
1159 { 0x00DB, "Ucirc", "LATIN CAPITAL LETTER U WITH CIRCUMFLEX" },
1160 { 0x00DC, "Uuml", "LATIN CAPITAL LETTER U WITH DIAERESIS" },
1161 { 0x00DD, "Yacute", "LATIN CAPITAL LETTER Y WITH ACUTE" },
1162 { 0x00DE, "THORN", "LATIN CAPITAL LETTER THORN" },
1163 { 0x00DF, "szlig", "LATIN SMALL LETTER SHARP S" },
1164 { 0x00E0, "agrave", "LATIN SMALL LETTER A WITH GRAVE" },
1165 { 0x00E1, "aacute", "LATIN SMALL LETTER A WITH ACUTE" },
1166 { 0x00E2, "acirc", "LATIN SMALL LETTER A WITH CIRCUMFLEX" },
1167 { 0x00E3, "atilde", "LATIN SMALL LETTER A WITH TILDE" },
1168 { 0x00E4, "auml", "LATIN SMALL LETTER A WITH DIAERESIS" },
1169 { 0x00E5, "aring", "LATIN SMALL LETTER A WITH RING ABOVE" },
1170 { 0x00E6, "aelig", "LATIN SMALL LETTER AE" },
1171 { 0x00E7, "ccedil", "LATIN SMALL LETTER C WITH CEDILLA" },
1172 { 0x00E8, "egrave", "LATIN SMALL LETTER E WITH GRAVE" },
1173 { 0x00E9, "eacute", "LATIN SMALL LETTER E WITH ACUTE" },
1174 { 0x00EA, "ecirc", "LATIN SMALL LETTER E WITH CIRCUMFLEX" },
1175 { 0x00EB, "euml", "LATIN SMALL LETTER E WITH DIAERESIS" },
1176 { 0x00EC, "igrave", "LATIN SMALL LETTER I WITH GRAVE" },
1177 { 0x00ED, "iacute", "LATIN SMALL LETTER I WITH ACUTE" },
1178 { 0x00EE, "icirc", "LATIN SMALL LETTER I WITH CIRCUMFLEX" },
1179 { 0x00EF, "iuml", "LATIN SMALL LETTER I WITH DIAERESIS" },
1180 { 0x00F0, "eth", "LATIN SMALL LETTER ETH" },
1181 { 0x00F1, "ntilde", "LATIN SMALL LETTER N WITH TILDE" },
1182 { 0x00F2, "ograve", "LATIN SMALL LETTER O WITH GRAVE" },
1183 { 0x00F3, "oacute", "LATIN SMALL LETTER O WITH ACUTE" },
1184 { 0x00F4, "ocirc", "LATIN SMALL LETTER O WITH CIRCUMFLEX" },
1185 { 0x00F5, "otilde", "LATIN SMALL LETTER O WITH TILDE" },
1186 { 0x00F6, "ouml", "LATIN SMALL LETTER O WITH DIAERESIS" },
1187 { 0x00F7, "divide", "DIVISION SIGN" },
1188 { 0x00F8, "oslash", "CIRCLED DIVISION SLASH" },
1189 { 0x00F9, "ugrave", "LATIN SMALL LETTER U WITH GRAVE" },
1190 { 0x00FA, "uacute", "LATIN SMALL LETTER U WITH ACUTE" },
1191 { 0x00FB, "ucirc", "LATIN SMALL LETTER U WITH CIRCUMFLEX" },
1192 { 0x00FC, "uuml", "LATIN SMALL LETTER U WITH DIAERESIS" },
1193 { 0x00FD, "yacute", "LATIN SMALL LETTER Y WITH ACUTE" },
1194 { 0x00FE, "thorn", "LATIN SMALL LETTER THORN" },
1195 { 0x00FF, "yuml", "LATIN SMALL LETTER Y WITH DIAERESIS" },
1196 { 0x0100, "Amacr", "LATIN CAPITAL LETTER A WITH MACRON" },
1197 { 0x0101, "amacr", "LATIN SMALL LETTER A WITH MACRON" },
1198 { 0x0102, "Abreve", "LATIN CAPITAL LETTER A WITH BREVE" },
1199 { 0x0103, "abreve", "LATIN SMALL LETTER A WITH BREVE" },
1200 { 0x0104, "Aogon", "LATIN CAPITAL LETTER A WITH OGONEK" },
1201 { 0x0105, "aogon", "LATIN SMALL LETTER A WITH OGONEK" },
1202 { 0x0106, "Cacute", "LATIN CAPITAL LETTER C WITH ACUTE" },
1203 { 0x0107, "cacute", "LATIN SMALL LETTER C WITH ACUTE" },
1204 { 0x0108, "Ccirc", "LATIN CAPITAL LETTER C WITH CIRCUMFLEX" },
1205 { 0x0109, "ccirc", "LATIN SMALL LETTER C WITH CIRCUMFLEX" },
1206 { 0x010A, "Cdot", "LATIN CAPITAL LETTER C WITH DOT ABOVE" },
1207 { 0x010B, "cdot", "DOT OPERATOR" },
1208 { 0x010C, "Ccaron", "LATIN CAPITAL LETTER C WITH CARON" },
1209 { 0x010D, "ccaron", "LATIN SMALL LETTER C WITH CARON" },
1210 { 0x010E, "Dcaron", "LATIN CAPITAL LETTER D WITH CARON" },
1211 { 0x010F, "dcaron", "LATIN SMALL LETTER D WITH CARON" },
1212 { 0x0110, "Dstrok", "LATIN CAPITAL LETTER D WITH STROKE" },
1213 { 0x0111, "dstrok", "LATIN SMALL LETTER D WITH STROKE" },
1214 { 0x0112, "Emacr", "LATIN CAPITAL LETTER E WITH MACRON" },
1215 { 0x0113, "emacr", "LATIN SMALL LETTER E WITH MACRON" },
1216 { 0x0116, "Edot", "LATIN CAPITAL LETTER E WITH DOT ABOVE" },
1217 { 0x0117, "edot", "LATIN SMALL LETTER E WITH DOT ABOVE" },
1218 { 0x0118, "Eogon", "LATIN CAPITAL LETTER E WITH OGONEK" },
1219 { 0x0119, "eogon", "LATIN SMALL LETTER E WITH OGONEK" },
1220 { 0x011A, "Ecaron", "LATIN CAPITAL LETTER E WITH CARON" },
1221 { 0x011B, "ecaron", "LATIN SMALL LETTER E WITH CARON" },
1222 { 0x011C, "Gcirc", "LATIN CAPITAL LETTER G WITH CIRCUMFLEX" },
1223 { 0x011D, "gcirc", "LATIN SMALL LETTER G WITH CIRCUMFLEX" },
1224 { 0x011E, "Gbreve", "LATIN CAPITAL LETTER G WITH BREVE" },
1225 { 0x011F, "gbreve", "LATIN SMALL LETTER G WITH BREVE" },
1226 { 0x0120, "Gdot", "LATIN CAPITAL LETTER G WITH DOT ABOVE" },
1227 { 0x0121, "gdot", "LATIN SMALL LETTER G WITH DOT ABOVE" },
1228 { 0x0122, "Gcedil", "LATIN CAPITAL LETTER G WITH CEDILLA" },
1229 { 0x0124, "Hcirc", "LATIN CAPITAL LETTER H WITH CIRCUMFLEX" },
1230 { 0x0125, "hcirc", "LATIN SMALL LETTER H WITH CIRCUMFLEX" },
1231 { 0x0126, "Hstrok", "LATIN CAPITAL LETTER H WITH STROKE" },
1232 { 0x0127, "hstrok", "LATIN SMALL LETTER H WITH STROKE" },
1233 { 0x0128, "Itilde", "LATIN CAPITAL LETTER I WITH TILDE" },
1234 { 0x0129, "itilde", "LATIN SMALL LETTER I WITH TILDE" },
1235 { 0x012A, "Imacr", "LATIN CAPITAL LETTER I WITH MACRON" },
1236 { 0x012B, "imacr", "LATIN SMALL LETTER I WITH MACRON" },
1237 { 0x012E, "Iogon", "LATIN CAPITAL LETTER I WITH OGONEK" },
1238 { 0x012F, "iogon", "LATIN SMALL LETTER I WITH OGONEK" },
1239 { 0x0130, "Idot", "LATIN CAPITAL LETTER I WITH DOT ABOVE" },
1240 { 0x0131, "inodot", "LATIN SMALL LETTER DOTLESS I" },
1241 { 0x0131, "inodot", "LATIN SMALL LETTER DOTLESS I" },
1242 { 0x0132, "IJlig", "LATIN CAPITAL LIGATURE IJ" },
1243 { 0x0133, "ijlig", "LATIN SMALL LIGATURE IJ" },
1244 { 0x0134, "Jcirc", "LATIN CAPITAL LETTER J WITH CIRCUMFLEX" },
1245 { 0x0135, "jcirc", "LATIN SMALL LETTER J WITH CIRCUMFLEX" },
1246 { 0x0136, "Kcedil", "LATIN CAPITAL LETTER K WITH CEDILLA" },
1247 { 0x0137, "kcedil", "LATIN SMALL LETTER K WITH CEDILLA" },
1248 { 0x0138, "kgreen", "LATIN SMALL LETTER KRA" },
1249 { 0x0139, "Lacute", "LATIN CAPITAL LETTER L WITH ACUTE" },
1250 { 0x013A, "lacute", "LATIN SMALL LETTER L WITH ACUTE" },
1251 { 0x013B, "Lcedil", "LATIN CAPITAL LETTER L WITH CEDILLA" },
1252 { 0x013C, "lcedil", "LATIN SMALL LETTER L WITH CEDILLA" },
1253 { 0x013D, "Lcaron", "LATIN CAPITAL LETTER L WITH CARON" },
1254 { 0x013E, "lcaron", "LATIN SMALL LETTER L WITH CARON" },
1255 { 0x013F, "Lmidot", "LATIN CAPITAL LETTER L WITH MIDDLE DOT" },
1256 { 0x0140, "lmidot", "LATIN SMALL LETTER L WITH MIDDLE DOT" },
1257 { 0x0141, "Lstrok", "LATIN CAPITAL LETTER L WITH STROKE" },
1258 { 0x0142, "lstrok", "LATIN SMALL LETTER L WITH STROKE" },
1259 { 0x0143, "Nacute", "LATIN CAPITAL LETTER N WITH ACUTE" },
1260 { 0x0144, "nacute", "LATIN SMALL LETTER N WITH ACUTE" },
1261 { 0x0145, "Ncedil", "LATIN CAPITAL LETTER N WITH CEDILLA" },
1262 { 0x0146, "ncedil", "LATIN SMALL LETTER N WITH CEDILLA" },
1263 { 0x0147, "Ncaron", "LATIN CAPITAL LETTER N WITH CARON" },
1264 { 0x0148, "ncaron", "LATIN SMALL LETTER N WITH CARON" },
1265 { 0x0149, "napos", "LATIN SMALL LETTER N PRECEDED BY APOSTROPHE" },
1266 { 0x014A, "ENG", "LATIN CAPITAL LETTER ENG" },
1267 { 0x014B, "eng", "LATIN SMALL LETTER ENG" },
1268 { 0x014C, "Omacr", "LATIN CAPITAL LETTER O WITH MACRON" },
1269 { 0x014D, "omacr", "LATIN SMALL LETTER O WITH MACRON" },
1270 { 0x0150, "Odblac", "LATIN CAPITAL LETTER O WITH DOUBLE ACUTE" },
1271 { 0x0151, "odblac", "LATIN SMALL LETTER O WITH DOUBLE ACUTE" },
1272 { 0x0152, "OElig", "LATIN CAPITAL LIGATURE OE" },
1273 { 0x0153, "oelig", "LATIN SMALL LIGATURE OE" },
1274 { 0x0154, "Racute", "LATIN CAPITAL LETTER R WITH ACUTE" },
1275 { 0x0155, "racute", "LATIN SMALL LETTER R WITH ACUTE" },
1276 { 0x0156, "Rcedil", "LATIN CAPITAL LETTER R WITH CEDILLA" },
1277 { 0x0157, "rcedil", "LATIN SMALL LETTER R WITH CEDILLA" },
1278 { 0x0158, "Rcaron", "LATIN CAPITAL LETTER R WITH CARON" },
1279 { 0x0159, "rcaron", "LATIN SMALL LETTER R WITH CARON" },
1280 { 0x015A, "Sacute", "LATIN CAPITAL LETTER S WITH ACUTE" },
1281 { 0x015B, "sacute", "LATIN SMALL LETTER S WITH ACUTE" },
1282 { 0x015C, "Scirc", "LATIN CAPITAL LETTER S WITH CIRCUMFLEX" },
1283 { 0x015D, "scirc", "LATIN SMALL LETTER S WITH CIRCUMFLEX" },
1284 { 0x015E, "Scedil", "LATIN CAPITAL LETTER S WITH CEDILLA" },
1285 { 0x015F, "scedil", "LATIN SMALL LETTER S WITH CEDILLA" },
1286 { 0x0160, "Scaron", "LATIN CAPITAL LETTER S WITH CARON" },
1287 { 0x0161, "scaron", "LATIN SMALL LETTER S WITH CARON" },
1288 { 0x0162, "Tcedil", "LATIN CAPITAL LETTER T WITH CEDILLA" },
1289 { 0x0163, "tcedil", "LATIN SMALL LETTER T WITH CEDILLA" },
1290 { 0x0164, "Tcaron", "LATIN CAPITAL LETTER T WITH CARON" },
1291 { 0x0165, "tcaron", "LATIN SMALL LETTER T WITH CARON" },
1292 { 0x0166, "Tstrok", "LATIN CAPITAL LETTER T WITH STROKE" },
1293 { 0x0167, "tstrok", "LATIN SMALL LETTER T WITH STROKE" },
1294 { 0x0168, "Utilde", "LATIN CAPITAL LETTER U WITH TILDE" },
1295 { 0x0169, "utilde", "LATIN SMALL LETTER U WITH TILDE" },
1296 { 0x016A, "Umacr", "LATIN CAPITAL LETTER U WITH MACRON" },
1297 { 0x016B, "umacr", "LATIN SMALL LETTER U WITH MACRON" },
1298 { 0x016C, "Ubreve", "LATIN CAPITAL LETTER U WITH BREVE" },
1299 { 0x016D, "ubreve", "LATIN SMALL LETTER U WITH BREVE" },
1300 { 0x016E, "Uring", "LATIN CAPITAL LETTER U WITH RING ABOVE" },
1301 { 0x016F, "uring", "LATIN SMALL LETTER U WITH RING ABOVE" },
1302 { 0x0170, "Udblac", "LATIN CAPITAL LETTER U WITH DOUBLE ACUTE" },
1303 { 0x0171, "udblac", "LATIN SMALL LETTER U WITH DOUBLE ACUTE" },
1304 { 0x0172, "Uogon", "LATIN CAPITAL LETTER U WITH OGONEK" },
1305 { 0x0173, "uogon", "LATIN SMALL LETTER U WITH OGONEK" },
1306 { 0x0174, "Wcirc", "LATIN CAPITAL LETTER W WITH CIRCUMFLEX" },
1307 { 0x0175, "wcirc", "LATIN SMALL LETTER W WITH CIRCUMFLEX" },
1308 { 0x0176, "Ycirc", "LATIN CAPITAL LETTER Y WITH CIRCUMFLEX" },
1309 { 0x0177, "ycirc", "LATIN SMALL LETTER Y WITH CIRCUMFLEX" },
1310 { 0x0178, "Yuml", "LATIN CAPITAL LETTER Y WITH DIAERESIS" },
1311 { 0x0179, "Zacute", "LATIN CAPITAL LETTER Z WITH ACUTE" },
1312 { 0x017A, "zacute", "LATIN SMALL LETTER Z WITH ACUTE" },
1313 { 0x017B, "Zdot", "LATIN CAPITAL LETTER Z WITH DOT ABOVE" },
1314 { 0x017C, "zdot", "LATIN SMALL LETTER Z WITH DOT ABOVE" },
1315 { 0x017D, "Zcaron", "LATIN CAPITAL LETTER Z WITH CARON" },
1316 { 0x017E, "zcaron", "LATIN SMALL LETTER Z WITH CARON" },
1317 { 0x0192, "fnof", "LATIN SMALL LETTER F WITH HOOK" },
1318 { 0x01F5, "gacute", "LATIN SMALL LETTER G WITH ACUTE" },
1319 { 0x02C7, "caron", "CARON" },
1320 { 0x02D8, "breve", "BREVE" },
1321 { 0x02D9, "dot", "DOT ABOVE" },
1322 { 0x02DA, "ring", "RING ABOVE" },
1323 { 0x02DB, "ogon", "OGONEK" },
1324 { 0x02DC, "tilde", "TILDE" },
1325 { 0x02DD, "dblac", "DOUBLE ACUTE ACCENT" },
1326 { 0x0386, "Aacgr", "GREEK CAPITAL LETTER ALPHA WITH TONOS" },
1327 { 0x0388, "Eacgr", "GREEK CAPITAL LETTER EPSILON WITH TONOS" },
1328 { 0x0389, "EEacgr", "GREEK CAPITAL LETTER ETA WITH TONOS" },
1329 { 0x038A, "Iacgr", "GREEK CAPITAL LETTER IOTA WITH TONOS" },
1330 { 0x038C, "Oacgr", "GREEK CAPITAL LETTER OMICRON WITH TONOS" },
1331 { 0x038E, "Uacgr", "GREEK CAPITAL LETTER UPSILON WITH TONOS" },
1332 { 0x038F, "OHacgr", "GREEK CAPITAL LETTER OMEGA WITH TONOS" },
1333 { 0x0390, "idiagr", "GREEK SMALL LETTER IOTA WITH DIALYTIKA AND TONOS" },
1334 { 0x0391, "Agr", "GREEK CAPITAL LETTER ALPHA" },
1335 { 0x0392, "Bgr", "GREEK CAPITAL LETTER BETA" },
1336 { 0x0393, "b.Gamma", "GREEK CAPITAL LETTER GAMMA" },
1337 { 0x0393, "Gamma", "GREEK CAPITAL LETTER GAMMA" },
1338 { 0x0393, "Ggr", "GREEK CAPITAL LETTER GAMMA" },
1339 { 0x0394, "b.Delta", "GREEK CAPITAL LETTER DELTA" },
1340 { 0x0394, "Delta", "GREEK CAPITAL LETTER DELTA" },
1341 { 0x0394, "Dgr", "GREEK CAPITAL LETTER DELTA" },
1342 { 0x0395, "Egr", "GREEK CAPITAL LETTER EPSILON" },
1343 { 0x0396, "Zgr", "GREEK CAPITAL LETTER ZETA" },
1344 { 0x0397, "EEgr", "GREEK CAPITAL LETTER ETA" },
1345 { 0x0398, "b.Theta", "GREEK CAPITAL LETTER THETA" },
1346 { 0x0398, "Theta", "GREEK CAPITAL LETTER THETA" },
1347 { 0x0398, "THgr", "GREEK CAPITAL LETTER THETA" },
1348 { 0x0399, "Igr", "GREEK CAPITAL LETTER IOTA" },
1349 { 0x039A, "Kgr", "GREEK CAPITAL LETTER KAPPA" },
1350 { 0x039B, "b.Lambda", "GREEK CAPITAL LETTER LAMDA" },
1351 { 0x039B, "Lambda", "GREEK CAPITAL LETTER LAMDA" },
1352 { 0x039B, "Lgr", "GREEK CAPITAL LETTER LAMDA" },
1353 { 0x039C, "Mgr", "GREEK CAPITAL LETTER MU" },
1354 { 0x039D, "Ngr", "GREEK CAPITAL LETTER NU" },
1355 { 0x039E, "b.Xi", "GREEK CAPITAL LETTER XI" },
1356 { 0x039E, "Xgr", "GREEK CAPITAL LETTER XI" },
1357 { 0x039E, "Xi", "GREEK CAPITAL LETTER XI" },
1358 { 0x039F, "Ogr", "GREEK CAPITAL LETTER OMICRON" },
1359 { 0x03A0, "b.Pi", "GREEK CAPITAL LETTER PI" },
1360 { 0x03A0, "Pgr", "GREEK CAPITAL LETTER PI" },
1361 { 0x03A0, "Pi", "GREEK CAPITAL LETTER PI" },
1362 { 0x03A1, "Rgr", "GREEK CAPITAL LETTER RHO" },
1363 { 0x03A3, "b.Sigma", "GREEK CAPITAL LETTER SIGMA" },
1364 { 0x03A3, "Sgr", "GREEK CAPITAL LETTER SIGMA" },
1365 { 0x03A3, "Sigma", "GREEK CAPITAL LETTER SIGMA" },
1366 { 0x03A4, "Tgr", "GREEK CAPITAL LETTER TAU" },
1367 { 0x03A5, "Ugr", "" },
1368 { 0x03A6, "b.Phi", "GREEK CAPITAL LETTER PHI" },
1369 { 0x03A6, "PHgr", "GREEK CAPITAL LETTER PHI" },
1370 { 0x03A6, "Phi", "GREEK CAPITAL LETTER PHI" },
1371 { 0x03A7, "KHgr", "GREEK CAPITAL LETTER CHI" },
1372 { 0x03A8, "b.Psi", "GREEK CAPITAL LETTER PSI" },
1373 { 0x03A8, "PSgr", "GREEK CAPITAL LETTER PSI" },
1374 { 0x03A8, "Psi", "GREEK CAPITAL LETTER PSI" },
1375 { 0x03A9, "b.Omega", "GREEK CAPITAL LETTER OMEGA" },
1376 { 0x03A9, "OHgr", "GREEK CAPITAL LETTER OMEGA" },
1377 { 0x03A9, "Omega", "GREEK CAPITAL LETTER OMEGA" },
1378 { 0x03AA, "Idigr", "GREEK CAPITAL LETTER IOTA WITH DIALYTIKA" },
1379 { 0x03AB, "Udigr", "GREEK CAPITAL LETTER UPSILON WITH DIALYTIKA" },
1380 { 0x03AC, "aacgr", "GREEK SMALL LETTER ALPHA WITH TONOS" },
1381 { 0x03AD, "eacgr", "GREEK SMALL LETTER EPSILON WITH TONOS" },
1382 { 0x03AE, "eeacgr", "GREEK SMALL LETTER ETA WITH TONOS" },
1383 { 0x03AF, "iacgr", "GREEK SMALL LETTER IOTA WITH TONOS" },
1384 { 0x03B0, "udiagr", "GREEK SMALL LETTER UPSILON WITH DIALYTIKA AND TONOS" },
1385 { 0x03B1, "agr", "" },
1386 { 0x03B1, "alpha", "" },
1387 { 0x03B1, "b.alpha", "" },
1388 { 0x03B2, "b.beta", "GREEK SMALL LETTER BETA" },
1389 { 0x03B2, "beta", "GREEK SMALL LETTER BETA" },
1390 { 0x03B2, "bgr", "GREEK SMALL LETTER BETA" },
1391 { 0x03B3, "b.gamma", "GREEK SMALL LETTER GAMMA" },
1392 { 0x03B3, "gamma", "GREEK SMALL LETTER GAMMA" },
1393 { 0x03B3, "ggr", "GREEK SMALL LETTER GAMMA" },
1394 { 0x03B4, "b.delta", "GREEK SMALL LETTER DELTA" },
1395 { 0x03B4, "delta", "GREEK SMALL LETTER DELTA" },
1396 { 0x03B4, "dgr", "GREEK SMALL LETTER DELTA" },
1397 { 0x03B5, "b.epsi", "" },
1398 { 0x03B5, "b.epsis", "" },
1399 { 0x03B5, "b.epsiv", "" },
1400 { 0x03B5, "egr", "" },
1401 { 0x03B5, "epsiv", "" },
1402 { 0x03B6, "b.zeta", "GREEK SMALL LETTER ZETA" },
1403 { 0x03B6, "zeta", "GREEK SMALL LETTER ZETA" },
1404 { 0x03B6, "zgr", "GREEK SMALL LETTER ZETA" },
1405 { 0x03B7, "b.eta", "GREEK SMALL LETTER ETA" },
1406 { 0x03B7, "eegr", "GREEK SMALL LETTER ETA" },
1407 { 0x03B7, "eta", "GREEK SMALL LETTER ETA" },
1408 { 0x03B8, "b.thetas", "" },
1409 { 0x03B8, "thetas", "" },
1410 { 0x03B8, "thgr", "" },
1411 { 0x03B9, "b.iota", "GREEK SMALL LETTER IOTA" },
1412 { 0x03B9, "igr", "GREEK SMALL LETTER IOTA" },
1413 { 0x03B9, "iota", "GREEK SMALL LETTER IOTA" },
1414 { 0x03BA, "b.kappa", "GREEK SMALL LETTER KAPPA" },
1415 { 0x03BA, "kappa", "GREEK SMALL LETTER KAPPA" },
1416 { 0x03BA, "kgr", "GREEK SMALL LETTER KAPPA" },
1417 { 0x03BB, "b.lambda", "GREEK SMALL LETTER LAMDA" },
1418 { 0x03BB, "lambda", "GREEK SMALL LETTER LAMDA" },
1419 { 0x03BB, "lgr", "GREEK SMALL LETTER LAMDA" },
1420 { 0x03BC, "b.mu", "GREEK SMALL LETTER MU" },
1421 { 0x03BC, "mgr", "GREEK SMALL LETTER MU" },
1422 { 0x03BC, "mu", "GREEK SMALL LETTER MU" },
1423 { 0x03BD, "b.nu", "GREEK SMALL LETTER NU" },
1424 { 0x03BD, "ngr", "GREEK SMALL LETTER NU" },
1425 { 0x03BD, "nu", "GREEK SMALL LETTER NU" },
1426 { 0x03BE, "b.xi", "GREEK SMALL LETTER XI" },
1427 { 0x03BE, "xgr", "GREEK SMALL LETTER XI" },
1428 { 0x03BE, "xi", "GREEK SMALL LETTER XI" },
1429 { 0x03BF, "ogr", "GREEK SMALL LETTER OMICRON" },
1430 { 0x03C0, "b.pi", "GREEK SMALL LETTER PI" },
1431 { 0x03C0, "pgr", "GREEK SMALL LETTER PI" },
1432 { 0x03C0, "pi", "GREEK SMALL LETTER PI" },
1433 { 0x03C1, "b.rho", "GREEK SMALL LETTER RHO" },
1434 { 0x03C1, "rgr", "GREEK SMALL LETTER RHO" },
1435 { 0x03C1, "rho", "GREEK SMALL LETTER RHO" },
1436 { 0x03C2, "b.sigmav", "" },
1437 { 0x03C2, "sfgr", "" },
1438 { 0x03C2, "sigmav", "" },
1439 { 0x03C3, "b.sigma", "GREEK SMALL LETTER SIGMA" },
1440 { 0x03C3, "sgr", "GREEK SMALL LETTER SIGMA" },
1441 { 0x03C3, "sigma", "GREEK SMALL LETTER SIGMA" },
1442 { 0x03C4, "b.tau", "GREEK SMALL LETTER TAU" },
1443 { 0x03C4, "tau", "GREEK SMALL LETTER TAU" },
1444 { 0x03C4, "tgr", "GREEK SMALL LETTER TAU" },
1445 { 0x03C5, "b.upsi", "GREEK SMALL LETTER UPSILON" },
1446 { 0x03C5, "ugr", "GREEK SMALL LETTER UPSILON" },
1447 { 0x03C5, "upsi", "GREEK SMALL LETTER UPSILON" },
1448 { 0x03C6, "b.phis", "GREEK SMALL LETTER PHI" },
1449 { 0x03C6, "phgr", "GREEK SMALL LETTER PHI" },
1450 { 0x03C6, "phis", "GREEK SMALL LETTER PHI" },
1451 { 0x03C7, "b.chi", "GREEK SMALL LETTER CHI" },
1452 { 0x03C7, "chi", "GREEK SMALL LETTER CHI" },
1453 { 0x03C7, "khgr", "GREEK SMALL LETTER CHI" },
1454 { 0x03C8, "b.psi", "GREEK SMALL LETTER PSI" },
1455 { 0x03C8, "psgr", "GREEK SMALL LETTER PSI" },
1456 { 0x03C8, "psi", "GREEK SMALL LETTER PSI" },
1457 { 0x03C9, "b.omega", "GREEK SMALL LETTER OMEGA" },
1458 { 0x03C9, "ohgr", "GREEK SMALL LETTER OMEGA" },
1459 { 0x03C9, "omega", "GREEK SMALL LETTER OMEGA" },
1460 { 0x03CA, "idigr", "GREEK SMALL LETTER IOTA WITH DIALYTIKA" },
1461 { 0x03CB, "udigr", "GREEK SMALL LETTER UPSILON WITH DIALYTIKA" },
1462 { 0x03CC, "oacgr", "GREEK SMALL LETTER OMICRON WITH TONOS" },
1463 { 0x03CD, "uacgr", "GREEK SMALL LETTER UPSILON WITH TONOS" },
1464 { 0x03CE, "ohacgr", "GREEK SMALL LETTER OMEGA WITH TONOS" },
1465 { 0x03D1, "b.thetav", "" },
1466 { 0x03D1, "thetav", "" },
1467 { 0x03D2, "b.Upsi", "" },
1468 { 0x03D2, "Upsi", "" },
1469 { 0x03D5, "b.phiv", "GREEK PHI SYMBOL" },
1470 { 0x03D5, "phiv", "GREEK PHI SYMBOL" },
1471 { 0x03D6, "b.piv", "GREEK PI SYMBOL" },
1472 { 0x03D6, "piv", "GREEK PI SYMBOL" },
1473 { 0x03DC, "b.gammad", "GREEK LETTER DIGAMMA" },
1474 { 0x03DC, "gammad", "GREEK LETTER DIGAMMA" },
1475 { 0x03F0, "b.kappav", "GREEK KAPPA SYMBOL" },
1476 { 0x03F0, "kappav", "GREEK KAPPA SYMBOL" },
1477 { 0x03F1, "b.rhov", "GREEK RHO SYMBOL" },
1478 { 0x03F1, "rhov", "GREEK RHO SYMBOL" },
1479 { 0x0401, "IOcy", "CYRILLIC CAPITAL LETTER IO" },
1480 { 0x0402, "DJcy", "CYRILLIC CAPITAL LETTER DJE" },
1481 { 0x0403, "GJcy", "CYRILLIC CAPITAL LETTER GJE" },
1482 { 0x0404, "Jukcy", "CYRILLIC CAPITAL LETTER UKRAINIAN IE" },
1483 { 0x0405, "DScy", "CYRILLIC CAPITAL LETTER DZE" },
1484 { 0x0406, "Iukcy", "CYRILLIC CAPITAL LETTER BYELORUSSIAN-UKRAINIAN I" },
1485 { 0x0407, "YIcy", "CYRILLIC CAPITAL LETTER YI" },
1486 { 0x0408, "Jsercy", "CYRILLIC CAPITAL LETTER JE" },
1487 { 0x0409, "LJcy", "CYRILLIC CAPITAL LETTER LJE" },
1488 { 0x040A, "NJcy", "CYRILLIC CAPITAL LETTER NJE" },
1489 { 0x040B, "TSHcy", "CYRILLIC CAPITAL LETTER TSHE" },
1490 { 0x040C, "KJcy", "CYRILLIC CAPITAL LETTER KJE" },
1491 { 0x040E, "Ubrcy", "CYRILLIC CAPITAL LETTER SHORT U" },
1492 { 0x040F, "DZcy", "CYRILLIC CAPITAL LETTER DZHE" },
1493 { 0x0410, "Acy", "CYRILLIC CAPITAL LETTER A" },
1494 { 0x0411, "Bcy", "CYRILLIC CAPITAL LETTER BE" },
1495 { 0x0412, "Vcy", "CYRILLIC CAPITAL LETTER VE" },
1496 { 0x0413, "Gcy", "CYRILLIC CAPITAL LETTER GHE" },
1497 { 0x0414, "Dcy", "CYRILLIC CAPITAL LETTER DE" },
1498 { 0x0415, "IEcy", "CYRILLIC CAPITAL LETTER IE" },
1499 { 0x0416, "ZHcy", "CYRILLIC CAPITAL LETTER ZHE" },
1500 { 0x0417, "Zcy", "CYRILLIC CAPITAL LETTER ZE" },
1501 { 0x0418, "Icy", "CYRILLIC CAPITAL LETTER I" },
1502 { 0x0419, "Jcy", "CYRILLIC CAPITAL LETTER SHORT I" },
1503 { 0x041A, "Kcy", "CYRILLIC CAPITAL LETTER KA" },
1504 { 0x041B, "Lcy", "CYRILLIC CAPITAL LETTER EL" },
1505 { 0x041C, "Mcy", "CYRILLIC CAPITAL LETTER EM" },
1506 { 0x041D, "Ncy", "CYRILLIC CAPITAL LETTER EN" },
1507 { 0x041E, "Ocy", "CYRILLIC CAPITAL LETTER O" },
1508 { 0x041F, "Pcy", "CYRILLIC CAPITAL LETTER PE" },
1509 { 0x0420, "Rcy", "CYRILLIC CAPITAL LETTER ER" },
1510 { 0x0421, "Scy", "CYRILLIC CAPITAL LETTER ES" },
1511 { 0x0422, "Tcy", "CYRILLIC CAPITAL LETTER TE" },
1512 { 0x0423, "Ucy", "CYRILLIC CAPITAL LETTER U" },
1513 { 0x0424, "Fcy", "CYRILLIC CAPITAL LETTER EF" },
1514 { 0x0425, "KHcy", "CYRILLIC CAPITAL LETTER HA" },
1515 { 0x0426, "TScy", "CYRILLIC CAPITAL LETTER TSE" },
1516 { 0x0427, "CHcy", "CYRILLIC CAPITAL LETTER CHE" },
1517 { 0x0428, "SHcy", "CYRILLIC CAPITAL LETTER SHA" },
1518 { 0x0429, "SHCHcy", "CYRILLIC CAPITAL LETTER SHCHA" },
1519 { 0x042A, "HARDcy", "CYRILLIC CAPITAL LETTER HARD SIGN" },
1520 { 0x042B, "Ycy", "CYRILLIC CAPITAL LETTER YERU" },
1521 { 0x042C, "SOFTcy", "CYRILLIC CAPITAL LETTER SOFT SIGN" },
1522 { 0x042D, "Ecy", "CYRILLIC CAPITAL LETTER E" },
1523 { 0x042E, "YUcy", "CYRILLIC CAPITAL LETTER YU" },
1524 { 0x042F, "YAcy", "CYRILLIC CAPITAL LETTER YA" },
1525 { 0x0430, "acy", "CYRILLIC SMALL LETTER A" },
1526 { 0x0431, "bcy", "CYRILLIC SMALL LETTER BE" },
1527 { 0x0432, "vcy", "CYRILLIC SMALL LETTER VE" },
1528 { 0x0433, "gcy", "CYRILLIC SMALL LETTER GHE" },
1529 { 0x0434, "dcy", "CYRILLIC SMALL LETTER DE" },
1530 { 0x0435, "iecy", "CYRILLIC SMALL LETTER IE" },
1531 { 0x0436, "zhcy", "CYRILLIC SMALL LETTER ZHE" },
1532 { 0x0437, "zcy", "CYRILLIC SMALL LETTER ZE" },
1533 { 0x0438, "icy", "CYRILLIC SMALL LETTER I" },
1534 { 0x0439, "jcy", "CYRILLIC SMALL LETTER SHORT I" },
1535 { 0x043A, "kcy", "CYRILLIC SMALL LETTER KA" },
1536 { 0x043B, "lcy", "CYRILLIC SMALL LETTER EL" },
1537 { 0x043C, "mcy", "CYRILLIC SMALL LETTER EM" },
1538 { 0x043D, "ncy", "CYRILLIC SMALL LETTER EN" },
1539 { 0x043E, "ocy", "CYRILLIC SMALL LETTER O" },
1540 { 0x043F, "pcy", "CYRILLIC SMALL LETTER PE" },
1541 { 0x0440, "rcy", "CYRILLIC SMALL LETTER ER" },
1542 { 0x0441, "scy", "CYRILLIC SMALL LETTER ES" },
1543 { 0x0442, "tcy", "CYRILLIC SMALL LETTER TE" },
1544 { 0x0443, "ucy", "CYRILLIC SMALL LETTER U" },
1545 { 0x0444, "fcy", "CYRILLIC SMALL LETTER EF" },
1546 { 0x0445, "khcy", "CYRILLIC SMALL LETTER HA" },
1547 { 0x0446, "tscy", "CYRILLIC SMALL LETTER TSE" },
1548 { 0x0447, "chcy", "CYRILLIC SMALL LETTER CHE" },
1549 { 0x0448, "shcy", "CYRILLIC SMALL LETTER SHA" },
1550 { 0x0449, "shchcy", "CYRILLIC SMALL LETTER SHCHA" },
1551 { 0x044A, "hardcy", "CYRILLIC SMALL LETTER HARD SIGN" },
1552 { 0x044B, "ycy", "CYRILLIC SMALL LETTER YERU" },
1553 { 0x044C, "softcy", "CYRILLIC SMALL LETTER SOFT SIGN" },
1554 { 0x044D, "ecy", "CYRILLIC SMALL LETTER E" },
1555 { 0x044E, "yucy", "CYRILLIC SMALL LETTER YU" },
1556 { 0x044F, "yacy", "CYRILLIC SMALL LETTER YA" },
1557 { 0x0451, "iocy", "CYRILLIC SMALL LETTER IO" },
1558 { 0x0452, "djcy", "CYRILLIC SMALL LETTER DJE" },
1559 { 0x0453, "gjcy", "CYRILLIC SMALL LETTER GJE" },
1560 { 0x0454, "jukcy", "CYRILLIC SMALL LETTER UKRAINIAN IE" },
1561 { 0x0455, "dscy", "CYRILLIC SMALL LETTER DZE" },
1562 { 0x0456, "iukcy", "CYRILLIC SMALL LETTER BYELORUSSIAN-UKRAINIAN I" },
1563 { 0x0457, "yicy", "CYRILLIC SMALL LETTER YI" },
1564 { 0x0458, "jsercy", "CYRILLIC SMALL LETTER JE" },
1565 { 0x0459, "ljcy", "CYRILLIC SMALL LETTER LJE" },
1566 { 0x045A, "njcy", "CYRILLIC SMALL LETTER NJE" },
1567 { 0x045B, "tshcy", "CYRILLIC SMALL LETTER TSHE" },
1568 { 0x045C, "kjcy", "CYRILLIC SMALL LETTER KJE" },
1569 { 0x045E, "ubrcy", "CYRILLIC SMALL LETTER SHORT U" },
1570 { 0x045F, "dzcy", "CYRILLIC SMALL LETTER DZHE" },
1571 { 0x2002, "ensp", "EN SPACE" },
1572 { 0x2003, "emsp", "EM SPACE" },
1573 { 0x2004, "emsp13", "THREE-PER-EM SPACE" },
1574 { 0x2005, "emsp14", "FOUR-PER-EM SPACE" },
1575 { 0x2007, "numsp", "FIGURE SPACE" },
1576 { 0x2008, "puncsp", "PUNCTUATION SPACE" },
1577 { 0x2009, "thinsp", "THIN SPACE" },
1578 { 0x200A, "hairsp", "HAIR SPACE" },
1579 { 0x2010, "dash", "HYPHEN" },
1580 { 0x2013, "ndash", "EN DASH" },
1581 { 0x2014, "mdash", "EM DASH" },
1582 { 0x2015, "horbar", "HORIZONTAL BAR" },
1583 { 0x2016, "Verbar", "DOUBLE VERTICAL LINE" },
1584 { 0x2018, "lsquo", "" },
1585 { 0x2018, "rsquor", "" },
1586 { 0x2019, "rsquo", "RIGHT SINGLE QUOTATION MARK" },
1587 { 0x201A, "lsquor", "SINGLE LOW-9 QUOTATION MARK" },
1588 { 0x201C, "ldquo", "" },
1589 { 0x201C, "rdquor", "" },
1590 { 0x201D, "rdquo", "RIGHT DOUBLE QUOTATION MARK" },
1591 { 0x201E, "ldquor", "DOUBLE LOW-9 QUOTATION MARK" },
1592 { 0x2020, "dagger", "DAGGER" },
1593 { 0x2021, "Dagger", "DOUBLE DAGGER" },
1594 { 0x2022, "bull", "BULLET" },
1595 { 0x2025, "nldr", "TWO DOT LEADER" },
1596 { 0x2026, "hellip", "HORIZONTAL ELLIPSIS" },
1597 { 0x2026, "mldr", "HORIZONTAL ELLIPSIS" },
1598 { 0x2030, "permil", "PER MILLE SIGN" },
1599 { 0x2032, "prime", "PRIME" },
1600 { 0x2032, "vprime", "PRIME" },
1601 { 0x2033, "Prime", "DOUBLE PRIME" },
1602 { 0x2034, "tprime", "TRIPLE PRIME" },
1603 { 0x2035, "bprime", "REVERSED PRIME" },
1604 { 0x2041, "caret", "CARET" },
1605 { 0x2043, "hybull", "HYPHEN BULLET" },
1606 { 0x20DB, "tdot", "COMBINING THREE DOTS ABOVE" },
1607 { 0x20DC, "DotDot", "COMBINING FOUR DOTS ABOVE" },
1608 { 0x2105, "incare", "CARE OF" },
1609 { 0x210B, "hamilt", "SCRIPT CAPITAL H" },
1610 { 0x210F, "planck", "PLANCK CONSTANT OVER TWO PI" },
1611 { 0x2111, "image", "BLACK-LETTER CAPITAL I" },
1612 { 0x2112, "lagran", "SCRIPT CAPITAL L" },
1613 { 0x2113, "ell", "SCRIPT SMALL L" },
1614 { 0x2116, "numero", "NUMERO SIGN" },
1615 { 0x2117, "copysr", "SOUND RECORDING COPYRIGHT" },
1616 { 0x2118, "weierp", "SCRIPT CAPITAL P" },
1617 { 0x211C, "real", "BLACK-LETTER CAPITAL R" },
1618 { 0x211E, "rx", "PRESCRIPTION TAKE" },
1619 { 0x2122, "trade", "TRADE MARK SIGN" },
1620 { 0x2126, "ohm", "OHM SIGN" },
1621 { 0x212B, "angst", "ANGSTROM SIGN" },
1622 { 0x212C, "bernou", "SCRIPT CAPITAL B" },
1623 { 0x2133, "phmmat", "SCRIPT CAPITAL M" },
1624 { 0x2134, "order", "SCRIPT SMALL O" },
1625 { 0x2135, "aleph", "ALEF SYMBOL" },
1626 { 0x2136, "beth", "BET SYMBOL" },
1627 { 0x2137, "gimel", "GIMEL SYMBOL" },
1628 { 0x2138, "daleth", "DALET SYMBOL" },
1629 { 0x2153, "frac13", "VULGAR FRACTION ONE THIRD" },
1630 { 0x2154, "frac23", "VULGAR FRACTION TWO THIRDS" },
1631 { 0x2155, "frac15", "VULGAR FRACTION ONE FIFTH" },
1632 { 0x2156, "frac25", "VULGAR FRACTION TWO FIFTHS" },
1633 { 0x2157, "frac35", "VULGAR FRACTION THREE FIFTHS" },
1634 { 0x2158, "frac45", "VULGAR FRACTION FOUR FIFTHS" },
1635 { 0x2159, "frac16", "VULGAR FRACTION ONE SIXTH" },
1636 { 0x215A, "frac56", "VULGAR FRACTION FIVE SIXTHS" },
1637 { 0x215B, "frac18", "" },
1638 { 0x215C, "frac38", "" },
1639 { 0x215D, "frac58", "" },
1640 { 0x215E, "frac78", "" },
1641 { 0x2190, "larr", "LEFTWARDS DOUBLE ARROW" },
1642 { 0x2191, "uarr", "UPWARDS ARROW" },
1643 { 0x2192, "rarr", "RIGHTWARDS DOUBLE ARROW" },
1644 { 0x2193, "darr", "DOWNWARDS ARROW" },
1645 { 0x2194, "harr", "LEFT RIGHT ARROW" },
1646 { 0x2194, "xhArr", "LEFT RIGHT ARROW" },
1647 { 0x2194, "xharr", "LEFT RIGHT ARROW" },
1648 { 0x2195, "varr", "UP DOWN ARROW" },
1649 { 0x2196, "nwarr", "NORTH WEST ARROW" },
1650 { 0x2197, "nearr", "NORTH EAST ARROW" },
1651 { 0x2198, "drarr", "SOUTH EAST ARROW" },
1652 { 0x2199, "dlarr", "SOUTH WEST ARROW" },
1653 { 0x219A, "nlarr", "LEFTWARDS ARROW WITH STROKE" },
1654 { 0x219B, "nrarr", "RIGHTWARDS ARROW WITH STROKE" },
1655 { 0x219D, "rarrw", "RIGHTWARDS SQUIGGLE ARROW" },
1656 { 0x219E, "Larr", "LEFTWARDS TWO HEADED ARROW" },
1657 { 0x21A0, "Rarr", "RIGHTWARDS TWO HEADED ARROW" },
1658 { 0x21A2, "larrtl", "LEFTWARDS ARROW WITH TAIL" },
1659 { 0x21A3, "rarrtl", "RIGHTWARDS ARROW WITH TAIL" },
1660 { 0x21A6, "map", "RIGHTWARDS ARROW FROM BAR" },
1661 { 0x21A9, "larrhk", "LEFTWARDS ARROW WITH HOOK" },
1662 { 0x21AA, "rarrhk", "RIGHTWARDS ARROW WITH HOOK" },
1663 { 0x21AB, "larrlp", "LEFTWARDS ARROW WITH LOOP" },
1664 { 0x21AC, "rarrlp", "RIGHTWARDS ARROW WITH LOOP" },
1665 { 0x21AD, "harrw", "LEFT RIGHT WAVE ARROW" },
1666 { 0x21AE, "nharr", "LEFT RIGHT ARROW WITH STROKE" },
1667 { 0x21B0, "lsh", "UPWARDS ARROW WITH TIP LEFTWARDS" },
1668 { 0x21B1, "rsh", "UPWARDS ARROW WITH TIP RIGHTWARDS" },
1669 { 0x21B6, "cularr", "ANTICLOCKWISE TOP SEMICIRCLE ARROW" },
1670 { 0x21B7, "curarr", "CLOCKWISE TOP SEMICIRCLE ARROW" },
1671 { 0x21BA, "olarr", "ANTICLOCKWISE OPEN CIRCLE ARROW" },
1672 { 0x21BB, "orarr", "CLOCKWISE OPEN CIRCLE ARROW" },
1673 { 0x21BC, "lharu", "LEFTWARDS HARPOON WITH BARB UPWARDS" },
1674 { 0x21BD, "lhard", "LEFTWARDS HARPOON WITH BARB DOWNWARDS" },
1675 { 0x21BE, "uharr", "UPWARDS HARPOON WITH BARB RIGHTWARDS" },
1676 { 0x21BF, "uharl", "UPWARDS HARPOON WITH BARB LEFTWARDS" },
1677 { 0x21C0, "rharu", "RIGHTWARDS HARPOON WITH BARB UPWARDS" },
1678 { 0x21C1, "rhard", "RIGHTWARDS HARPOON WITH BARB DOWNWARDS" },
1679 { 0x21C2, "dharr", "DOWNWARDS HARPOON WITH BARB RIGHTWARDS" },
1680 { 0x21C3, "dharl", "DOWNWARDS HARPOON WITH BARB LEFTWARDS" },
1681 { 0x21C4, "rlarr2", "RIGHTWARDS ARROW OVER LEFTWARDS ARROW" },
1682 { 0x21C6, "lrarr2", "LEFTWARDS ARROW OVER RIGHTWARDS ARROW" },
1683 { 0x21C7, "larr2", "LEFTWARDS PAIRED ARROWS" },
1684 { 0x21C8, "uarr2", "UPWARDS PAIRED ARROWS" },
1685 { 0x21C9, "rarr2", "RIGHTWARDS PAIRED ARROWS" },
1686 { 0x21CA, "darr2", "DOWNWARDS PAIRED ARROWS" },
1687 { 0x21CB, "lrhar2", "LEFTWARDS HARPOON OVER RIGHTWARDS HARPOON" },
1688 { 0x21CC, "rlhar2", "RIGHTWARDS HARPOON OVER LEFTWARDS HARPOON" },
1689 { 0x21CD, "nlArr", "LEFTWARDS DOUBLE ARROW WITH STROKE" },
1690 { 0x21CE, "nhArr", "LEFT RIGHT DOUBLE ARROW WITH STROKE" },
1691 { 0x21CF, "nrArr", "RIGHTWARDS DOUBLE ARROW WITH STROKE" },
1692 { 0x21D0, "lArr", "LEFTWARDS ARROW" },
1693 { 0x21D0, "xlArr", "LEFTWARDS DOUBLE ARROW" },
1694 { 0x21D1, "uArr", "UPWARDS DOUBLE ARROW" },
1695 { 0x21D2, "rArr", "RIGHTWARDS ARROW" },
1696 { 0x21D2, "xrArr", "RIGHTWARDS DOUBLE ARROW" },
1697 { 0x21D3, "dArr", "DOWNWARDS DOUBLE ARROW" },
1698 { 0x21D4, "hArr", "" },
1699 { 0x21D4, "iff", "LEFT RIGHT DOUBLE ARROW" },
1700 { 0x21D5, "vArr", "UP DOWN DOUBLE ARROW" },
1701 { 0x21DA, "lAarr", "LEFTWARDS TRIPLE ARROW" },
1702 { 0x21DB, "rAarr", "RIGHTWARDS TRIPLE ARROW" },
1703 { 0x2200, "forall", "" },
1704 { 0x2201, "comp", "COMPLEMENT" },
1705 { 0x2202, "part", "" },
1706 { 0x2203, "exist", "" },
1707 { 0x2204, "nexist", "THERE DOES NOT EXIST" },
1708 { 0x2205, "empty", "" },
1709 { 0x2207, "nabla", "NABLA" },
1710 { 0x2209, "notin", "" },
1711 { 0x220A, "epsi", "" },
1712 { 0x220A, "epsis", "" },
1713 { 0x220A, "isin", "" },
1714 { 0x220D, "bepsi", "SMALL CONTAINS AS MEMBER" },
1715 { 0x220D, "ni", "" },
1716 { 0x220F, "prod", "N-ARY PRODUCT" },
1717 { 0x2210, "amalg", "N-ARY COPRODUCT" },
1718 { 0x2210, "coprod", "N-ARY COPRODUCT" },
1719 { 0x2210, "samalg", "" },
1720 { 0x2211, "sum", "N-ARY SUMMATION" },
1721 { 0x2212, "minus", "MINUS SIGN" },
1722 { 0x2213, "mnplus", "" },
1723 { 0x2214, "plusdo", "DOT PLUS" },
1724 { 0x2216, "setmn", "SET MINUS" },
1725 { 0x2216, "ssetmn", "SET MINUS" },
1726 { 0x2217, "lowast", "ASTERISK OPERATOR" },
1727 { 0x2218, "compfn", "RING OPERATOR" },
1728 { 0x221A, "radic", "" },
1729 { 0x221D, "prop", "" },
1730 { 0x221D, "vprop", "" },
1731 { 0x221E, "infin", "" },
1732 { 0x221F, "ang90", "RIGHT ANGLE" },
1733 { 0x2220, "ang", "ANGLE" },
1734 { 0x2221, "angmsd", "MEASURED ANGLE" },
1735 { 0x2222, "angsph", "" },
1736 { 0x2223, "mid", "" },
1737 { 0x2224, "nmid", "DOES NOT DIVIDE" },
1738 { 0x2225, "par", "PARALLEL TO" },
1739 { 0x2225, "spar", "PARALLEL TO" },
1740 { 0x2226, "npar", "NOT PARALLEL TO" },
1741 { 0x2226, "nspar", "NOT PARALLEL TO" },
1742 { 0x2227, "and", "" },
1743 { 0x2228, "or", "" },
1744 { 0x2229, "cap", "" },
1745 { 0x222A, "cup", "" },
1746 { 0x222B, "int", "" },
1747 { 0x222E, "conint", "" },
1748 { 0x2234, "there4", "" },
1749 { 0x2235, "becaus", "BECAUSE" },
1750 { 0x223C, "sim", "" },
1751 { 0x223C, "thksim", "TILDE OPERATOR" },
1752 { 0x223D, "bsim", "" },
1753 { 0x2240, "wreath", "WREATH PRODUCT" },
1754 { 0x2241, "nsim", "" },
1755 { 0x2243, "sime", "" },
1756 { 0x2244, "nsime", "" },
1757 { 0x2245, "cong", "" },
1758 { 0x2247, "ncong", "NEITHER APPROXIMATELY NOR ACTUALLY EQUAL TO" },
1759 { 0x2248, "ap", "" },
1760 { 0x2248, "thkap", "ALMOST EQUAL TO" },
1761 { 0x2249, "nap", "NOT ALMOST EQUAL TO" },
1762 { 0x224A, "ape", "" },
1763 { 0x224C, "bcong", "ALL EQUAL TO" },
1764 { 0x224D, "asymp", "EQUIVALENT TO" },
1765 { 0x224E, "bump", "" },
1766 { 0x224F, "bumpe", "" },
1767 { 0x2250, "esdot", "" },
1768 { 0x2251, "eDot", "" },
1769 { 0x2252, "efDot", "" },
1770 { 0x2253, "erDot", "" },
1771 { 0x2254, "colone", "" },
1772 { 0x2255, "ecolon", "" },
1773 { 0x2256, "ecir", "" },
1774 { 0x2257, "cire", "" },
1775 { 0x2259, "wedgeq", "ESTIMATES" },
1776 { 0x225C, "trie", "" },
1777 { 0x2260, "ne", "" },
1778 { 0x2261, "equiv", "" },
1779 { 0x2262, "nequiv", "NOT IDENTICAL TO" },
1780 { 0x2264, "le", "" },
1781 { 0x2264, "les", "LESS-THAN OR EQUAL TO" },
1782 { 0x2265, "ge", "GREATER-THAN OR EQUAL TO" },
1783 { 0x2265, "ges", "GREATER-THAN OR EQUAL TO" },
1784 { 0x2266, "lE", "" },
1785 { 0x2267, "gE", "" },
1786 { 0x2268, "lnE", "" },
1787 { 0x2268, "lne", "" },
1788 { 0x2268, "lvnE", "LESS-THAN BUT NOT EQUAL TO" },
1789 { 0x2269, "gnE", "" },
1790 { 0x2269, "gne", "" },
1791 { 0x2269, "gvnE", "GREATER-THAN BUT NOT EQUAL TO" },
1792 { 0x226A, "Lt", "MUCH LESS-THAN" },
1793 { 0x226B, "Gt", "MUCH GREATER-THAN" },
1794 { 0x226C, "twixt", "BETWEEN" },
1795 { 0x226E, "nlt", "NOT LESS-THAN" },
1796 { 0x226F, "ngt", "NOT GREATER-THAN" },
1797 { 0x2270, "nlE", "" },
1798 { 0x2270, "nle", "NEITHER LESS-THAN NOR EQUAL TO" },
1799 { 0x2270, "nles", "" },
1800 { 0x2271, "ngE", "" },
1801 { 0x2271, "nge", "NEITHER GREATER-THAN NOR EQUAL TO" },
1802 { 0x2271, "nges", "" },
1803 { 0x2272, "lap", "LESS-THAN OR EQUIVALENT TO" },
1804 { 0x2272, "lsim", "LESS-THAN OR EQUIVALENT TO" },
1805 { 0x2273, "gap", "GREATER-THAN OR EQUIVALENT TO" },
1806 { 0x2273, "gsim", "GREATER-THAN OR EQUIVALENT TO" },
1807 { 0x2276, "lg", "LESS-THAN OR GREATER-THAN" },
1808 { 0x2277, "gl", "" },
1809 { 0x227A, "pr", "" },
1810 { 0x227B, "sc", "" },
1811 { 0x227C, "cupre", "" },
1812 { 0x227C, "pre", "" },
1813 { 0x227D, "sccue", "" },
1814 { 0x227D, "sce", "" },
1815 { 0x227E, "prap", "" },
1816 { 0x227E, "prsim", "" },
1817 { 0x227F, "scap", "" },
1818 { 0x227F, "scsim", "" },
1819 { 0x2280, "npr", "DOES NOT PRECEDE" },
1820 { 0x2281, "nsc", "DOES NOT SUCCEED" },
1821 { 0x2282, "sub", "" },
1822 { 0x2283, "sup", "" },
1823 { 0x2284, "nsub", "NOT A SUBSET OF" },
1824 { 0x2285, "nsup", "NOT A SUPERSET OF" },
1825 { 0x2286, "subE", "" },
1826 { 0x2286, "sube", "" },
1827 { 0x2287, "supE", "" },
1828 { 0x2287, "supe", "" },
1829 { 0x2288, "nsubE", "" },
1830 { 0x2288, "nsube", "" },
1831 { 0x2289, "nsupE", "" },
1832 { 0x2289, "nsupe", "" },
1833 { 0x228A, "subne", "" },
1834 { 0x228A, "subnE", "SUBSET OF WITH NOT EQUAL TO" },
1835 { 0x228A, "vsubne", "SUBSET OF WITH NOT EQUAL TO" },
1836 { 0x228B, "supnE", "" },
1837 { 0x228B, "supne", "" },
1838 { 0x228B, "vsupnE", "SUPERSET OF WITH NOT EQUAL TO" },
1839 { 0x228B, "vsupne", "SUPERSET OF WITH NOT EQUAL TO" },
1840 { 0x228E, "uplus", "MULTISET UNION" },
1841 { 0x228F, "sqsub", "" },
1842 { 0x2290, "sqsup", "" },
1843 { 0x2291, "sqsube", "" },
1844 { 0x2292, "sqsupe", "" },
1845 { 0x2293, "sqcap", "SQUARE CAP" },
1846 { 0x2294, "sqcup", "SQUARE CUP" },
1847 { 0x2295, "oplus", "CIRCLED PLUS" },
1848 { 0x2296, "ominus", "CIRCLED MINUS" },
1849 { 0x2297, "otimes", "CIRCLED TIMES" },
1850 { 0x2298, "osol", "CIRCLED DIVISION SLASH" },
1851 { 0x2299, "odot", "CIRCLED DOT OPERATOR" },
1852 { 0x229A, "ocir", "CIRCLED RING OPERATOR" },
1853 { 0x229B, "oast", "CIRCLED ASTERISK OPERATOR" },
1854 { 0x229D, "odash", "CIRCLED DASH" },
1855 { 0x229E, "plusb", "SQUARED PLUS" },
1856 { 0x229F, "minusb", "SQUARED MINUS" },
1857 { 0x22A0, "timesb", "SQUARED TIMES" },
1858 { 0x22A1, "sdotb", "SQUARED DOT OPERATOR" },
1859 { 0x22A2, "vdash", "" },
1860 { 0x22A3, "dashv", "" },
1861 { 0x22A4, "top", "DOWN TACK" },
1862 { 0x22A5, "bottom", "" },
1863 { 0x22A5, "perp", "" },
1864 { 0x22A7, "models", "MODELS" },
1865 { 0x22A8, "vDash", "" },
1866 { 0x22A9, "Vdash", "" },
1867 { 0x22AA, "Vvdash", "" },
1868 { 0x22AC, "nvdash", "DOES NOT PROVE" },
1869 { 0x22AD, "nvDash", "NOT TRUE" },
1870 { 0x22AE, "nVdash", "DOES NOT FORCE" },
1871 { 0x22AF, "nVDash", "NEGATED DOUBLE VERTICAL BAR DOUBLE RIGHT TURNSTILE" },
1872 { 0x22B2, "vltri", "" },
1873 { 0x22B3, "vrtri", "" },
1874 { 0x22B4, "ltrie", "" },
1875 { 0x22B5, "rtrie", "" },
1876 { 0x22B8, "mumap", "MULTIMAP" },
1877 { 0x22BA, "intcal", "INTERCALATE" },
1878 { 0x22BB, "veebar", "" },
1879 { 0x22BC, "barwed", "NAND" },
1880 { 0x22C4, "diam", "DIAMOND OPERATOR" },
1881 { 0x22C5, "sdot", "DOT OPERATOR" },
1882 { 0x22C6, "sstarf", "STAR OPERATOR" },
1883 { 0x22C6, "star", "STAR OPERATOR" },
1884 { 0x22C7, "divonx", "DIVISION TIMES" },
1885 { 0x22C8, "bowtie", "" },
1886 { 0x22C9, "ltimes", "LEFT NORMAL FACTOR SEMIDIRECT PRODUCT" },
1887 { 0x22CA, "rtimes", "RIGHT NORMAL FACTOR SEMIDIRECT PRODUCT" },
1888 { 0x22CB, "lthree", "LEFT SEMIDIRECT PRODUCT" },
1889 { 0x22CC, "rthree", "RIGHT SEMIDIRECT PRODUCT" },
1890 { 0x22CD, "bsime", "" },
1891 { 0x22CE, "cuvee", "CURLY LOGICAL OR" },
1892 { 0x22CF, "cuwed", "CURLY LOGICAL AND" },
1893 { 0x22D0, "Sub", "" },
1894 { 0x22D1, "Sup", "" },
1895 { 0x22D2, "Cap", "DOUBLE INTERSECTION" },
1896 { 0x22D3, "Cup", "DOUBLE UNION" },
1897 { 0x22D4, "fork", "" },
1898 { 0x22D6, "ldot", "" },
1899 { 0x22D7, "gsdot", "" },
1900 { 0x22D8, "Ll", "" },
1901 { 0x22D9, "Gg", "VERY MUCH GREATER-THAN" },
1902 { 0x22DA, "lEg", "" },
1903 { 0x22DA, "leg", "" },
1904 { 0x22DB, "gEl", "" },
1905 { 0x22DB, "gel", "" },
1906 { 0x22DC, "els", "" },
1907 { 0x22DD, "egs", "" },
1908 { 0x22DE, "cuepr", "" },
1909 { 0x22DF, "cuesc", "" },
1910 { 0x22E0, "npre", "DOES NOT PRECEDE OR EQUAL" },
1911 { 0x22E1, "nsce", "DOES NOT SUCCEED OR EQUAL" },
1912 { 0x22E6, "lnsim", "" },
1913 { 0x22E7, "gnsim", "GREATER-THAN BUT NOT EQUIVALENT TO" },
1914 { 0x22E8, "prnap", "" },
1915 { 0x22E8, "prnsim", "" },
1916 { 0x22E9, "scnap", "" },
1917 { 0x22E9, "scnsim", "" },
1918 { 0x22EA, "nltri", "NOT NORMAL SUBGROUP OF" },
1919 { 0x22EB, "nrtri", "DOES NOT CONTAIN AS NORMAL SUBGROUP" },
1920 { 0x22EC, "nltrie", "NOT NORMAL SUBGROUP OF OR EQUAL TO" },
1921 { 0x22ED, "nrtrie", "DOES NOT CONTAIN AS NORMAL SUBGROUP OR EQUAL" },
1922 { 0x22EE, "vellip", "" },
1923 { 0x2306, "Barwed", "PERSPECTIVE" },
1924 { 0x2308, "lceil", "LEFT CEILING" },
1925 { 0x2309, "rceil", "RIGHT CEILING" },
1926 { 0x230A, "lfloor", "LEFT FLOOR" },
1927 { 0x230B, "rfloor", "RIGHT FLOOR" },
1928 { 0x230C, "drcrop", "BOTTOM RIGHT CROP" },
1929 { 0x230D, "dlcrop", "BOTTOM LEFT CROP" },
1930 { 0x230E, "urcrop", "TOP RIGHT CROP" },
1931 { 0x230F, "ulcrop", "TOP LEFT CROP" },
1932 { 0x2315, "telrec", "TELEPHONE RECORDER" },
1933 { 0x2316, "target", "POSITION INDICATOR" },
1934 { 0x231C, "ulcorn", "TOP LEFT CORNER" },
1935 { 0x231D, "urcorn", "TOP RIGHT CORNER" },
1936 { 0x231E, "dlcorn", "BOTTOM LEFT CORNER" },
1937 { 0x231F, "drcorn", "BOTTOM RIGHT CORNER" },
1938 { 0x2322, "frown", "" },
1939 { 0x2322, "sfrown", "FROWN" },
1940 { 0x2323, "smile", "" },
1941 { 0x2323, "ssmile", "SMILE" },
1942 { 0x2423, "blank", "OPEN BOX" },
1943 { 0x24C8, "oS", "CIRCLED LATIN CAPITAL LETTER S" },
1944 { 0x2500, "boxh", "BOX DRAWINGS LIGHT HORIZONTAL" },
1945 { 0x2502, "boxv", "BOX DRAWINGS LIGHT VERTICAL" },
1946 { 0x250C, "boxdr", "BOX DRAWINGS LIGHT DOWN AND RIGHT" },
1947 { 0x2510, "boxdl", "BOX DRAWINGS LIGHT DOWN AND LEFT" },
1948 { 0x2514, "boxur", "BOX DRAWINGS LIGHT UP AND RIGHT" },
1949 { 0x2518, "boxul", "BOX DRAWINGS LIGHT UP AND LEFT" },
1950 { 0x251C, "boxvr", "BOX DRAWINGS LIGHT VERTICAL AND RIGHT" },
1951 { 0x2524, "boxvl", "BOX DRAWINGS LIGHT VERTICAL AND LEFT" },
1952 { 0x252C, "boxhd", "BOX DRAWINGS LIGHT DOWN AND HORIZONTAL" },
1953 { 0x2534, "boxhu", "BOX DRAWINGS LIGHT UP AND HORIZONTAL" },
1954 { 0x253C, "boxvh", "BOX DRAWINGS LIGHT VERTICAL AND HORIZONTAL" },
1955 { 0x2550, "boxH", "BOX DRAWINGS DOUBLE HORIZONTAL" },
1956 { 0x2551, "boxV", "BOX DRAWINGS DOUBLE VERTICAL" },
1957 { 0x2552, "boxDR", "BOX DRAWINGS DOWN SINGLE AND RIGHT DOUBLE" },
1958 { 0x2553, "boxDr", "BOX DRAWINGS DOWN DOUBLE AND RIGHT SINGLE" },
1959 { 0x2554, "boxdR", "BOX DRAWINGS DOUBLE DOWN AND RIGHT" },
1960 { 0x2555, "boxDL", "BOX DRAWINGS DOWN SINGLE AND LEFT DOUBLE" },
1961 { 0x2556, "boxdL", "BOX DRAWINGS DOWN DOUBLE AND LEFT SINGLE" },
1962 { 0x2557, "boxDl", "BOX DRAWINGS DOUBLE DOWN AND LEFT" },
1963 { 0x2558, "boxUR", "BOX DRAWINGS UP SINGLE AND RIGHT DOUBLE" },
1964 { 0x2559, "boxuR", "BOX DRAWINGS UP DOUBLE AND RIGHT SINGLE" },
1965 { 0x255A, "boxUr", "BOX DRAWINGS DOUBLE UP AND RIGHT" },
1966 { 0x255B, "boxUL", "BOX DRAWINGS UP SINGLE AND LEFT DOUBLE" },
1967 { 0x255C, "boxUl", "BOX DRAWINGS UP DOUBLE AND LEFT SINGLE" },
1968 { 0x255D, "boxuL", "BOX DRAWINGS DOUBLE UP AND LEFT" },
1969 { 0x255E, "boxvR", "BOX DRAWINGS VERTICAL SINGLE AND RIGHT DOUBLE" },
1970 { 0x255F, "boxVR", "BOX DRAWINGS VERTICAL DOUBLE AND RIGHT SINGLE" },
1971 { 0x2560, "boxVr", "BOX DRAWINGS DOUBLE VERTICAL AND RIGHT" },
1972 { 0x2561, "boxvL", "BOX DRAWINGS VERTICAL SINGLE AND LEFT DOUBLE" },
1973 { 0x2562, "boxVL", "BOX DRAWINGS VERTICAL DOUBLE AND LEFT SINGLE" },
1974 { 0x2563, "boxVl", "BOX DRAWINGS DOUBLE VERTICAL AND LEFT" },
1975 { 0x2564, "boxhD", "BOX DRAWINGS DOWN SINGLE AND HORIZONTAL DOUBLE" },
1976 { 0x2565, "boxHD", "BOX DRAWINGS DOWN DOUBLE AND HORIZONTAL SINGLE" },
1977 { 0x2566, "boxHd", "BOX DRAWINGS DOUBLE DOWN AND HORIZONTAL" },
1978 { 0x2567, "boxhU", "BOX DRAWINGS UP SINGLE AND HORIZONTAL DOUBLE" },
1979 { 0x2568, "boxHU", "BOX DRAWINGS UP DOUBLE AND HORIZONTAL SINGLE" },
1980 { 0x2569, "boxHu", "BOX DRAWINGS DOUBLE UP AND HORIZONTAL" },
1981 { 0x256A, "boxvH", "BOX DRAWINGS VERTICAL SINGLE AND HORIZONTAL DOUBLE" },
1982 { 0x256B, "boxVH", "BOX DRAWINGS VERTICAL DOUBLE AND HORIZONTAL SINGLE" },
1983 { 0x256C, "boxVh", "BOX DRAWINGS DOUBLE VERTICAL AND HORIZONTAL" },
1984 { 0x2580, "uhblk", "UPPER HALF BLOCK" },
1985 { 0x2584, "lhblk", "LOWER HALF BLOCK" },
1986 { 0x2588, "block", "FULL BLOCK" },
1987 { 0x2591, "blk14", "LIGHT SHADE" },
1988 { 0x2592, "blk12", "MEDIUM SHADE" },
1989 { 0x2593, "blk34", "DARK SHADE" },
1990 { 0x25A1, "square", "WHITE SQUARE" },
1991 { 0x25A1, "squ", "WHITE SQUARE" },
1992 { 0x25AA, "squf", "" },
1993 { 0x25AD, "rect", "WHITE RECTANGLE" },
1994 { 0x25AE, "marker", "BLACK VERTICAL RECTANGLE" },
1995 { 0x25B3, "xutri", "WHITE UP-POINTING TRIANGLE" },
1996 { 0x25B4, "utrif", "BLACK UP-POINTING TRIANGLE" },
1997 { 0x25B5, "utri", "WHITE UP-POINTING TRIANGLE" },
1998 { 0x25B8, "rtrif", "BLACK RIGHT-POINTING TRIANGLE" },
1999 { 0x25B9, "rtri", "WHITE RIGHT-POINTING TRIANGLE" },
2000 { 0x25BD, "xdtri", "WHITE DOWN-POINTING TRIANGLE" },
2001 { 0x25BE, "dtrif", "BLACK DOWN-POINTING TRIANGLE" },
2002 { 0x25BF, "dtri", "WHITE DOWN-POINTING TRIANGLE" },
2003 { 0x25C2, "ltrif", "BLACK LEFT-POINTING TRIANGLE" },
2004 { 0x25C3, "ltri", "WHITE LEFT-POINTING TRIANGLE" },
2005 { 0x25CA, "loz", "LOZENGE" },
2006 { 0x25CB, "cir", "WHITE CIRCLE" },
2007 { 0x25CB, "xcirc", "WHITE CIRCLE" },
2008 { 0x2605, "starf", "BLACK STAR" },
2009 { 0x260E, "phone", "TELEPHONE SIGN" },
2010 { 0x2640, "female", "" },
2011 { 0x2642, "male", "MALE SIGN" },
2012 { 0x2660, "spades", "BLACK SPADE SUIT" },
2013 { 0x2663, "clubs", "BLACK CLUB SUIT" },
2014 { 0x2665, "hearts", "BLACK HEART SUIT" },
2015 { 0x2666, "diams", "BLACK DIAMOND SUIT" },
2016 { 0x2669, "sung", "" },
2017 { 0x266D, "flat", "MUSIC FLAT SIGN" },
2018 { 0x266E, "natur", "MUSIC NATURAL SIGN" },
2019 { 0x266F, "sharp", "MUSIC SHARP SIGN" },
2020 { 0x2713, "check", "CHECK MARK" },
2021 { 0x2717, "cross", "BALLOT X" },
2022 { 0x2720, "malt", "MALTESE CROSS" },
2023 { 0x2726, "lozf", "" },
2024 { 0x2736, "sext", "SIX POINTED BLACK STAR" },
2025 { 0x3008, "lang", "" },
2026 { 0x3009, "rang", "" },
2027 { 0xE291, "rpargt", "" },
2028 { 0xE2A2, "lnap", "" },
2029 { 0xE2AA, "nsmid", "" },
2030 { 0xE2B3, "prnE", "" },
2031 { 0xE2B5, "scnE", "" },
2032 { 0xE2B8, "vsubnE", "" },
2033 { 0xE301, "smid", "" },
2034 { 0xE411, "gnap", "" },
2035 { 0xFB00, "fflig", "" },
2036 { 0xFB01, "filig", "" },
2037 { 0xFB02, "fllig", "" },
2038 { 0xFB03, "ffilig", "" },
2039 { 0xFB04, "ffllig", "" },
2040 { 0xFE68, "sbsol", "SMALL REVERSE SOLIDUS" },
2041 };
2042
2043 /************************************************************************
2044 * *
2045 * Commodity functions to handle entities *
2046 * *
2047 ************************************************************************/
2048
2049 /*
2050 * Macro used to grow the current buffer.
2051 */
2052 #define growBuffer(buffer) { \
2053 buffer##_size *= 2; \
2054 buffer = (xmlChar *) xmlRealloc(buffer, buffer##_size * sizeof(xmlChar)); \
2055 if (buffer == NULL) { \
2056 xmlGenericError(xmlGenericErrorContext, "realloc failed"); \
2057 return(NULL); \
2058 } \
2059 }
2060
2061 /**
2062 * docbEntityLookup:
2063 * @name: the entity name
2064 *
2065 * Lookup the given entity in EntitiesTable
2066 *
2067 * TODO: the linear scan is really ugly, an hash table is really needed.
2068 *
2069 * Returns the associated docbEntityDescPtr if found, NULL otherwise.
2070 */
2071 static docbEntityDescPtr
2072 docbEntityLookup(const xmlChar *name) {
2073 unsigned int i;
2074
2075 for (i = 0;i < (sizeof(docbookEntitiesTable)/
2076 sizeof(docbookEntitiesTable[0]));i++) {
2077 if (xmlStrEqual(name, BAD_CAST docbookEntitiesTable[i].name)) {
2078 #ifdef DEBUG
2079 xmlGenericError(xmlGenericErrorContext,"Found entity %s\n", name);
2080 #endif
2081 return(&docbookEntitiesTable[i]);
2082 }
2083 }
2084 return(NULL);
2085 }
2086
2087 /**
2088 * docbEntityValueLookup:
2089 * @value: the entity's unicode value
2090 *
2091 * Lookup the given entity in EntitiesTable
2092 *
2093 * TODO: the linear scan is really ugly, an hash table is really needed.
2094 *
2095 * Returns the associated docbEntityDescPtr if found, NULL otherwise.
2096 */
2097 static docbEntityDescPtr
2098 docbEntityValueLookup(int value) {
2099 unsigned int i;
2100 #ifdef DEBUG
2101 int lv = 0;
2102 #endif
2103
2104 for (i = 0;i < (sizeof(docbookEntitiesTable)/
2105 sizeof(docbookEntitiesTable[0]));i++) {
2106 if (docbookEntitiesTable[i].value >= value) {
2107 if (docbookEntitiesTable[i].value > value)
2108 break;
2109 #ifdef DEBUG
2110 xmlGenericError(xmlGenericErrorContext,"Found entity %s\n", docbookEntitiesTable[i].name);
2111 #endif
2112 return(&docbookEntitiesTable[i]);
2113 }
2114 #ifdef DEBUG
2115 if (lv > docbookEntitiesTable[i].value) {
2116 xmlGenericError(xmlGenericErrorContext,
2117 "docbookEntitiesTable[] is not sorted (%d > %d)!\n",
2118 lv, docbookEntitiesTable[i].value);
2119 }
2120 lv = docbookEntitiesTable[i].value;
2121 #endif
2122 }
2123 return(NULL);
2124 }
2125
2126 #if 0
2127 /**
2128 * UTF8ToSgml:
2129 * @out: a pointer to an array of bytes to store the result
2130 * @outlen: the length of @out
2131 * @in: a pointer to an array of UTF-8 chars
2132 * @inlen: the length of @in
2133 *
2134 * Take a block of UTF-8 chars in and try to convert it to an ASCII
2135 * plus SGML entities block of chars out.
2136 *
2137 * Returns 0 if success, -2 if the transcoding fails, or -1 otherwise
2138 * The value of @inlen after return is the number of octets consumed
2139 * as the return value is positive, else unpredictable.
2140 * The value of @outlen after return is the number of octets consumed.
2141 */
2142 int
2143 UTF8ToSgml(unsigned char* out, int *outlen,
2144 const unsigned char* in, int *inlen) {
2145 const unsigned char* processed = in;
2146 const unsigned char* outend;
2147 const unsigned char* outstart = out;
2148 const unsigned char* instart = in;
2149 const unsigned char* inend;
2150 unsigned int c, d;
2151 int trailing;
2152
2153 if (in == NULL) {
2154 /*
2155 * initialization nothing to do
2156 */
2157 *outlen = 0;
2158 *inlen = 0;
2159 return(0);
2160 }
2161 inend = in + (*inlen);
2162 outend = out + (*outlen);
2163 while (in < inend) {
2164 d = *in++;
2165 if (d < 0x80) { c= d; trailing= 0; }
2166 else if (d < 0xC0) {
2167 /* trailing byte in leading position */
2168 *outlen = out - outstart;
2169 *inlen = processed - instart;
2170 return(-2);
2171 } else if (d < 0xE0) { c= d & 0x1F; trailing= 1; }
2172 else if (d < 0xF0) { c= d & 0x0F; trailing= 2; }
2173 else if (d < 0xF8) { c= d & 0x07; trailing= 3; }
2174 else {
2175 /* no chance for this in Ascii */
2176 *outlen = out - outstart;
2177 *inlen = processed - instart;
2178 return(-2);
2179 }
2180
2181 if (inend - in < trailing) {
2182 break;
2183 }
2184
2185 for ( ; trailing; trailing--) {
2186 if ((in >= inend) || (((d= *in++) & 0xC0) != 0x80))
2187 break;
2188 c <<= 6;
2189 c |= d & 0x3F;
2190 }
2191
2192 /* assertion: c is a single UTF-4 value */
2193 if (c < 0x80) {
2194 if (out + 1 >= outend)
2195 break;
2196 *out++ = c;
2197 } else {
2198 int len;
2199 docbEntityDescPtr ent;
2200
2201 /*
2202 * Try to lookup a predefined SGML entity for it
2203 */
2204
2205 ent = docbEntityValueLookup(c);
2206 if (ent == NULL) {
2207 /* no chance for this in Ascii */
2208 *outlen = out - outstart;
2209 *inlen = processed - instart;
2210 return(-2);
2211 }
2212 len = strlen(ent->name);
2213 if (out + 2 + len >= outend)
2214 break;
2215 *out++ = '&';
2216 memcpy(out, ent->name, len);
2217 out += len;
2218 *out++ = ';';
2219 }
2220 processed = in;
2221 }
2222 *outlen = out - outstart;
2223 *inlen = processed - instart;
2224 return(0);
2225 }
2226 #endif
2227
2228 /**
2229 * docbEncodeEntities:
2230 * @out: a pointer to an array of bytes to store the result
2231 * @outlen: the length of @out
2232 * @in: a pointer to an array of UTF-8 chars
2233 * @inlen: the length of @in
2234 * @quoteChar: the quote character to escape (' or ") or zero.
2235 *
2236 * Take a block of UTF-8 chars in and try to convert it to an ASCII
2237 * plus SGML entities block of chars out.
2238 *
2239 * Returns 0 if success, -2 if the transcoding fails, or -1 otherwise
2240 * The value of @inlen after return is the number of octets consumed
2241 * as the return value is positive, else unpredictable.
2242 * The value of @outlen after return is the number of octets consumed.
2243 */
2244 int
2245 docbEncodeEntities(unsigned char* out, int *outlen,
2246 const unsigned char* in, int *inlen, int quoteChar) {
2247 const unsigned char* processed = in;
2248 const unsigned char* outend = out + (*outlen);
2249 const unsigned char* outstart = out;
2250 const unsigned char* instart = in;
2251 const unsigned char* inend = in + (*inlen);
2252 unsigned int c, d;
2253 int trailing;
2254
2255 while (in < inend) {
2256 d = *in++;
2257 if (d < 0x80) { c= d; trailing= 0; }
2258 else if (d < 0xC0) {
2259 /* trailing byte in leading position */
2260 *outlen = out - outstart;
2261 *inlen = processed - instart;
2262 return(-2);
2263 } else if (d < 0xE0) { c= d & 0x1F; trailing= 1; }
2264 else if (d < 0xF0) { c= d & 0x0F; trailing= 2; }
2265 else if (d < 0xF8) { c= d & 0x07; trailing= 3; }
2266 else {
2267 /* no chance for this in Ascii */
2268 *outlen = out - outstart;
2269 *inlen = processed - instart;
2270 return(-2);
2271 }
2272
2273 if (inend - in < trailing)
2274 break;
2275
2276 while (trailing--) {
2277 if (((d= *in++) & 0xC0) != 0x80) {
2278 *outlen = out - outstart;
2279 *inlen = processed - instart;
2280 return(-2);
2281 }
2282 c <<= 6;
2283 c |= d & 0x3F;
2284 }
2285
2286 /* assertion: c is a single UTF-4 value */
2287 if (c < 0x80 && c != (unsigned int) quoteChar && c != '&' && c != '<' && c != '>') {
2288 if (out >= outend)
2289 break;
2290 *out++ = c;
2291 } else {
2292 docbEntityDescPtr ent;
2293 const char *cp;
2294 char nbuf[16];
2295 int len;
2296
2297 /*
2298 * Try to lookup a predefined SGML entity for it
2299 */
2300 ent = docbEntityValueLookup(c);
2301 if (ent == NULL) {
2302 snprintf(nbuf, sizeof(nbuf), "#%u", c);
2303 cp = nbuf;
2304 }
2305 else
2306 cp = ent->name;
2307 len = strlen(cp);
2308 if (out + 2 + len > outend)
2309 break;
2310 *out++ = '&';
2311 memcpy(out, cp, len);
2312 out += len;
2313 *out++ = ';';
2314 }
2315 processed = in;
2316 }
2317 *outlen = out - outstart;
2318 *inlen = processed - instart;
2319 return(0);
2320 }
2321
2322
2323 /************************************************************************
2324 * *
2325 * Commodity functions to handle streams *
2326 * *
2327 ************************************************************************/
2328
2329 /**
2330 * docbNewInputStream:
2331 * @ctxt: an SGML parser context
2332 *
2333 * Create a new input stream structure
2334 * Returns the new input stream or NULL
2335 */
2336 static docbParserInputPtr
2337 docbNewInputStream(docbParserCtxtPtr ctxt) {
2338 docbParserInputPtr input;
2339
2340 input = (xmlParserInputPtr) xmlMalloc(sizeof(docbParserInput));
2341 if (input == NULL) {
2342 ctxt->errNo = XML_ERR_NO_MEMORY;
2343 if ((ctxt->sax != NULL) && (ctxt->sax->error != NULL))
2344 ctxt->sax->error(ctxt->userData,
2345 "malloc: couldn't allocate a new input stream\n");
2346 return(NULL);
2347 }
2348 memset(input, 0, sizeof(docbParserInput));
2349 input->filename = NULL;
2350 input->directory = NULL;
2351 input->base = NULL;
2352 input->cur = NULL;
2353 input->buf = NULL;
2354 input->line = 1;
2355 input->col = 1;
2356 input->buf = NULL;
2357 input->free = NULL;
2358 input->version = NULL;
2359 input->consumed = 0;
2360 input->length = 0;
2361 return(input);
2362 }
2363
2364
2365 /************************************************************************
2366 * *
2367 * Commodity functions, cleanup needed ? *
2368 * *
2369 ************************************************************************/
2370
2371 /**
2372 * areBlanks:
2373 * @ctxt: an SGML parser context
2374 * @str: a xmlChar *
2375 * @len: the size of @str
2376 *
2377 * Is this a sequence of blank chars that one can ignore ?
2378 *
2379 * Returns 1 if ignorable 0 otherwise.
2380 */
2381
2382 static int areBlanks(docbParserCtxtPtr ctxt, const xmlChar *str, int len) {
2383 int i;
2384 xmlNodePtr lastChild;
2385
2386 for (i = 0;i < len;i++)
2387 if (!(IS_BLANK(str[i]))) return(0);
2388
2389 if (CUR == 0) return(1);
2390 if (CUR != '<') return(0);
2391 if (ctxt->name == NULL)
2392 return(1);
2393 if (ctxt->node == NULL) return(0);
2394 lastChild = xmlGetLastChild(ctxt->node);
2395 if (lastChild == NULL) {
2396 if ((ctxt->node->type != XML_ELEMENT_NODE) &&
2397 (ctxt->node->content != NULL)) return(0);
2398 } else if (xmlNodeIsText(lastChild))
2399 return(0);
2400 return(1);
2401 }
2402
2403 /************************************************************************
2404 * *
2405 * External entities support *
2406 * *
2407 ************************************************************************/
2408
2409 /**
2410 * docbParseCtxtExternalEntity:
2411 * @ctx: the existing parsing context
2412 * @URL: the URL for the entity to load
2413 * @ID: the System ID for the entity to load
2414 * @list: the return value for the set of parsed nodes
2415 *
2416 * Parse an external general entity within an existing parsing context
2417 *
2418 * Returns 0 if the entity is well formed, -1 in case of args problem and
2419 * the parser error code otherwise
2420 */
2421
2422 static int
2423 docbParseCtxtExternalEntity(xmlParserCtxtPtr ctx, const xmlChar *URL,
2424 const xmlChar *ID, xmlNodePtr *list) {
2425 xmlParserCtxtPtr ctxt;
2426 xmlDocPtr newDoc;
2427 xmlSAXHandlerPtr oldsax = NULL;
2428 int ret = 0;
2429
2430 if (ctx->depth > 40) {
2431 return(XML_ERR_ENTITY_LOOP);
2432 }
2433
2434 if (list != NULL)
2435 *list = NULL;
2436 if ((URL == NULL) && (ID == NULL))
2437 return(-1);
2438 if (ctx->myDoc == NULL) /* @@ relax but check for dereferences */
2439 return(-1);
2440
2441
2442 ctxt = xmlCreateEntityParserCtxt(URL, ID, ctx->myDoc->URL);
2443 if (ctxt == NULL) return(-1);
2444 ctxt->userData = ctxt;
2445 oldsax = ctxt->sax;
2446 ctxt->sax = ctx->sax;
2447 newDoc = xmlNewDoc(BAD_CAST "1.0");
2448 if (newDoc == NULL) {
2449 xmlFreeParserCtxt(ctxt);
2450 return(-1);
2451 }
2452 if (ctx->myDoc != NULL) {
2453 newDoc->intSubset = ctx->myDoc->intSubset;
2454 newDoc->extSubset = ctx->myDoc->extSubset;
2455 }
2456 if (ctx->myDoc->URL != NULL) {
2457 newDoc->URL = xmlStrdup(ctx->myDoc->URL);
2458 }
2459 newDoc->children = xmlNewDocNode(newDoc, NULL, BAD_CAST "pseudoroot", NULL);
2460 if (newDoc->children == NULL) {
2461 ctxt->sax = oldsax;
2462 xmlFreeParserCtxt(ctxt);
2463 newDoc->intSubset = NULL;
2464 newDoc->extSubset = NULL;
2465 xmlFreeDoc(newDoc);
2466 return(-1);
2467 }
2468 nodePush(ctxt, newDoc->children);
2469 if (ctx->myDoc == NULL) {
2470 ctxt->myDoc = newDoc;
2471 } else {
2472 ctxt->myDoc = ctx->myDoc;
2473 newDoc->children->doc = ctx->myDoc;
2474 }
2475
2476 /*
2477 * Parse a possible text declaration first
2478 */
2479 GROW;
2480 if ((RAW == '<') && (NXT(1) == '?') &&
2481 (NXT(2) == 'x') && (NXT(3) == 'm') &&
2482 (NXT(4) == 'l') && (IS_BLANK(NXT(5)))) {
2483 xmlParseTextDecl(ctxt);
2484 }
2485
2486 /*
2487 * Doing validity checking on chunk doesn't make sense
2488 */
2489 ctxt->instate = XML_PARSER_CONTENT;
2490 ctxt->validate = ctx->validate;
2491 ctxt->loadsubset = ctx->loadsubset;
2492 ctxt->depth = ctx->depth + 1;
2493 ctxt->replaceEntities = ctx->replaceEntities;
2494 if (ctxt->validate) {
2495 ctxt->vctxt.error = ctx->vctxt.error;
2496 ctxt->vctxt.warning = ctx->vctxt.warning;
2497 /* Allocate the Node stack */
2498 ctxt->vctxt.nodeTab = (xmlNodePtr *) xmlMalloc(4 * sizeof(xmlNodePtr));
2499 if (ctxt->vctxt.nodeTab == NULL) {
2500 xmlGenericError(xmlGenericErrorContext,
2501 "docbParseCtxtExternalEntity: out of memory\n");
2502 ctxt->validate = 0;
2503 ctxt->vctxt.error = NULL;
2504 ctxt->vctxt.warning = NULL;
2505 } else {
2506 ctxt->vctxt.nodeNr = 0;
2507 ctxt->vctxt.nodeMax = 4;
2508 ctxt->vctxt.node = NULL;
2509 }
2510 } else {
2511 ctxt->vctxt.error = NULL;
2512 ctxt->vctxt.warning = NULL;
2513 }
2514
2515 docbParseContent(ctxt);
2516
2517 if ((RAW == '<') && (NXT(1) == '/')) {
2518 ctxt->errNo = XML_ERR_NOT_WELL_BALANCED;
2519 if ((ctxt->sax != NULL) && (ctxt->sax->error != NULL))
2520 ctxt->sax->error(ctxt->userData,
2521 "chunk is not well balanced\n");
2522 ctxt->wellFormed = 0;
2523 if (ctxt->recovery == 0) ctxt->disableSAX = 1;
2524 } else if (RAW != 0) {
2525 ctxt->errNo = XML_ERR_EXTRA_CONTENT;
2526 if ((ctxt->sax != NULL) && (ctxt->sax->error != NULL))
2527 ctxt->sax->error(ctxt->userData,
2528 "extra content at the end of well balanced chunk\n");
2529 ctxt->wellFormed = 0;
2530 if (ctxt->recovery == 0) ctxt->disableSAX = 1;
2531 }
2532 if (ctxt->node != newDoc->children) {
2533 ctxt->errNo = XML_ERR_NOT_WELL_BALANCED;
2534 if ((ctxt->sax != NULL) && (ctxt->sax->error != NULL))
2535 ctxt->sax->error(ctxt->userData,
2536 "chunk is not well balanced\n");
2537 ctxt->wellFormed = 0;
2538 if (ctxt->recovery == 0) ctxt->disableSAX = 1;
2539 }
2540
2541 if (!ctxt->wellFormed) {
2542 if (ctxt->errNo == 0)
2543 ret = 1;
2544 else
2545 ret = ctxt->errNo;
2546 } else {
2547 if (list != NULL) {
2548 xmlNodePtr cur;
2549
2550 /*
2551 * Return the newly created nodeset after unlinking it from
2552 * they pseudo parent.
2553 */
2554 cur = newDoc->children->children;
2555 *list = cur;
2556 while (cur != NULL) {
2557 cur->parent = NULL;
2558 cur = cur->next;
2559 }
2560 newDoc->children->children = NULL;
2561 }
2562 ret = 0;
2563 }
2564 ctxt->sax = oldsax;
2565 xmlFreeParserCtxt(ctxt);
2566 newDoc->intSubset = NULL;
2567 newDoc->extSubset = NULL;
2568 xmlFreeDoc(newDoc);
2569
2570 return(ret);
2571 }
2572
2573 /************************************************************************
2574 * *
2575 * The parser itself *
2576 * *
2577 ************************************************************************/
2578
2579 /**
2580 * docbParseSGMLName:
2581 * @ctxt: an SGML parser context
2582 *
2583 * parse an SGML tag or attribute name, note that we convert it to lowercase
2584 * since SGML names are not case-sensitive.
2585 *
2586 * Returns the Tag Name parsed or NULL
2587 */
2588
2589 static xmlChar *
2590 docbParseSGMLName(docbParserCtxtPtr ctxt) {
2591 xmlChar *ret = NULL;
2592 int i = 0;
2593 xmlChar loc[DOCB_PARSER_BUFFER_SIZE];
2594
2595 if (!IS_LETTER(CUR) && (CUR != '_') &&
2596 (CUR != ':')) return(NULL);
2597
2598 while ((i < DOCB_PARSER_BUFFER_SIZE) &&
2599 ((IS_LETTER(CUR)) || (IS_DIGIT(CUR)) ||
2600 (CUR == ':') || (CUR == '_'))) {
2601 if ((CUR >= 'A') && (CUR <= 'Z')) loc[i] = CUR + 0x20;
2602 else loc[i] = CUR;
2603 i++;
2604
2605 NEXT;
2606 }
2607
2608 ret = xmlStrndup(loc, i);
2609
2610 return(ret);
2611 }
2612
2613 /**
2614 * docbParseName:
2615 * @ctxt: an SGML parser context
2616 *
2617 * parse an SGML name, this routine is case sensitive.
2618 *
2619 * Returns the Name parsed or NULL
2620 */
2621
2622 static xmlChar *
2623 docbParseName(docbParserCtxtPtr ctxt) {
2624 xmlChar buf[DOCB_MAX_NAMELEN];
2625 int len = 0;
2626
2627 GROW;
2628 if (!IS_LETTER(CUR) && (CUR != '_')) {
2629 return(NULL);
2630 }
2631
2632 while ((IS_LETTER(CUR)) || (IS_DIGIT(CUR)) ||
2633 (CUR == '.') || (CUR == '-') ||
2634 (CUR == '_') || (CUR == ':') ||
2635 (IS_COMBINING(CUR)) ||
2636 (IS_EXTENDER(CUR))) {
2637 buf[len++] = CUR;
2638 NEXT;
2639 if (len >= DOCB_MAX_NAMELEN) {
2640 xmlGenericError(xmlGenericErrorContext,
2641 "docbParseName: reached DOCB_MAX_NAMELEN limit\n");
2642 while ((IS_LETTER(CUR)) || (IS_DIGIT(CUR)) ||
2643 (CUR == '.') || (CUR == '-') ||
2644 (CUR == '_') || (CUR == ':') ||
2645 (IS_COMBINING(CUR)) ||
2646 (IS_EXTENDER(CUR)))
2647 NEXT;
2648 break;
2649 }
2650 }
2651 return(xmlStrndup(buf, len));
2652 }
2653
2654 /**
2655 * docbParseSGMLAttribute:
2656 * @ctxt: an SGML parser context
2657 * @stop: a char stop value
2658 *
2659 * parse an SGML attribute value till the stop (quote), if
2660 * stop is 0 then it stops at the first space
2661 *
2662 * Returns the attribute parsed or NULL
2663 */
2664
2665 static xmlChar *
2666 docbParseSGMLAttribute(docbParserCtxtPtr ctxt, const xmlChar stop) {
2667 xmlChar *buffer = NULL;
2668 int buffer_size = 0;
2669 xmlChar *out = NULL;
2670 xmlChar *name = NULL;
2671
2672 xmlChar *cur = NULL;
2673 xmlEntityPtr xent;
2674 docbEntityDescPtr ent;
2675
2676 /*
2677 * allocate a translation buffer.
2678 */
2679 buffer_size = DOCB_PARSER_BIG_BUFFER_SIZE;
2680 buffer = (xmlChar *) xmlMalloc(buffer_size * sizeof(xmlChar));
2681 if (buffer == NULL) {
2682 xmlGenericError(xmlGenericErrorContext,
2683 "docbParseSGMLAttribute: malloc failed");
2684 return(NULL);
2685 }
2686 out = buffer;
2687
2688 /*
2689 * Ok loop until we reach one of the ending chars
2690 */
2691 while ((CUR != 0) && (CUR != stop) && (CUR != '>')) {
2692 if ((stop == 0) && (IS_BLANK(CUR))) break;
2693 if (CUR == '&') {
2694 if (NXT(1) == '#') {
2695 unsigned int c;
2696 int bits;
2697
2698 c = docbParseCharRef(ctxt);
2699 if (c < 0x80)
2700 { *out++ = c; bits= -6; }
2701 else if (c < 0x800)
2702 { *out++ =((c >> 6) & 0x1F) | 0xC0; bits= 0; }
2703 else if (c < 0x10000)
2704 { *out++ =((c >> 12) & 0x0F) | 0xE0; bits= 6; }
2705 else
2706 { *out++ =((c >> 18) & 0x07) | 0xF0; bits= 12; }
2707
2708 for ( ; bits >= 0; bits-= 6) {
2709 *out++ = ((c >> bits) & 0x3F) | 0x80;
2710 }
2711 } else {
2712 xent = docbParseEntityRef(ctxt, &name);
2713 if (name == NULL) {
2714 *out++ = '&';
2715 if (out - buffer > buffer_size - 100) {
2716 int indx = out - buffer;
2717
2718 growBuffer(buffer);
2719 out = &buffer[indx];
2720 }
2721 *out++ = '&';
2722 } else {
2723 ent = docbEntityLookup(name);
2724 if (ent == NULL) {
2725 *out++ = '&';
2726 cur = name;
2727 while (*cur != 0) {
2728 if (out - buffer > buffer_size - 100) {
2729 int indx = out - buffer;
2730
2731 growBuffer(buffer);
2732 out = &buffer[indx];
2733 }
2734 *out++ = *cur++;
2735 }
2736 xmlFree(name);
2737 } else {
2738 unsigned int c;
2739 int bits;
2740
2741 if (out - buffer > buffer_size - 100) {
2742 int indx = out - buffer;
2743
2744 growBuffer(buffer);
2745 out = &buffer[indx];
2746 }
2747 c = (xmlChar)ent->value;
2748 if (c < 0x80)
2749 { *out++ = c; bits= -6; }
2750 else if (c < 0x800)
2751 { *out++ =((c >> 6) & 0x1F) | 0xC0; bits= 0; }
2752 else if (c < 0x10000)
2753 { *out++ =((c >> 12) & 0x0F) | 0xE0; bits= 6; }
2754 else
2755 { *out++ =((c >> 18) & 0x07) | 0xF0; bits= 12; }
2756
2757 for ( ; bits >= 0; bits-= 6) {
2758 *out++ = ((c >> bits) & 0x3F) | 0x80;
2759 }
2760 xmlFree(name);
2761 }
2762 }
2763 }
2764 } else {
2765 unsigned int c;
2766 int bits;
2767
2768 if (out - buffer > buffer_size - 100) {
2769 int indx = out - buffer;
2770
2771 growBuffer(buffer);
2772 out = &buffer[indx];
2773 }
2774 c = CUR;
2775 if (c < 0x80)
2776 { *out++ = c; bits= -6; }
2777 else if (c < 0x800)
2778 { *out++ =((c >> 6) & 0x1F) | 0xC0; bits= 0; }
2779 else if (c < 0x10000)
2780 { *out++ =((c >> 12) & 0x0F) | 0xE0; bits= 6; }
2781 else
2782 { *out++ =((c >> 18) & 0x07) | 0xF0; bits= 12; }
2783
2784 for ( ; bits >= 0; bits-= 6) {
2785 *out++ = ((c >> bits) & 0x3F) | 0x80;
2786 }
2787 NEXT;
2788 }
2789 }
2790 *out++ = 0;
2791 return(buffer);
2792 }
2793
2794
2795 /**
2796 * docbParseEntityRef:
2797 * @ctxt: an SGML parser context
2798 * @str: location to store the entity name
2799 *
2800 * parse an SGML ENTITY references
2801 *
2802 * [68] EntityRef ::= '&' Name ';'
2803 *
2804 * Returns the associated xmlEntityPtr if found, or NULL otherwise,
2805 * if non-NULL *str will have to be freed by the caller.
2806 */
2807 static xmlEntityPtr
2808 docbParseEntityRef(docbParserCtxtPtr ctxt, xmlChar **str) {
2809 xmlChar *name;
2810 xmlEntityPtr ent = NULL;
2811 *str = NULL;
2812
2813 if (CUR == '&') {
2814 NEXT;
2815 name = docbParseName(ctxt);
2816 if (name == NULL) {
2817 if ((ctxt->sax != NULL) && (ctxt->sax->error != NULL))
2818 ctxt->sax->error(ctxt->userData,
2819 "docbParseEntityRef: no name\n");
2820 ctxt->wellFormed = 0;
2821 } else {
2822 GROW;
2823 if (CUR == ';') {
2824 *str = name;
2825
2826 /*
2827 * Ask first SAX for entity resolution, otherwise try the
2828 * predefined set.
2829 */
2830 if (ctxt->sax != NULL) {
2831 if (ctxt->sax->getEntity != NULL)
2832 ent = ctxt->sax->getEntity(ctxt->userData, name);
2833 if (ent == NULL)
2834 ent = xmlGetPredefinedEntity(name);
2835 }
2836 NEXT;
2837 } else {
2838 if ((ctxt->sax != NULL) && (ctxt->sax->error != NULL))
2839 ctxt->sax->error(ctxt->userData,
2840 "docbParseEntityRef: expecting ';'\n");
2841 *str = name;
2842 }
2843 }
2844 }
2845 return(ent);
2846 }
2847
2848 /**
2849 * docbParseAttValue:
2850 * @ctxt: an SGML parser context
2851 *
2852 * parse a value for an attribute
2853 * Note: the parser won't do substitution of entities here, this
2854 * will be handled later in xmlStringGetNodeList, unless it was
2855 * asked for ctxt->replaceEntities != 0
2856 *
2857 * Returns the AttValue parsed or NULL.
2858 */
2859
2860 static xmlChar *
2861 docbParseAttValue(docbParserCtxtPtr ctxt) {
2862 xmlChar *ret = NULL;
2863
2864 if (CUR == '"') {
2865 NEXT;
2866 ret = docbParseSGMLAttribute(ctxt, '"');
2867 if (CUR != '"') {
2868 if ((ctxt->sax != NULL) && (ctxt->sax->error != NULL))
2869 ctxt->sax->error(ctxt->userData, "AttValue: ' expected\n");
2870 ctxt->wellFormed = 0;
2871 } else
2872 NEXT;
2873 } else if (CUR == '\'') {
2874 NEXT;
2875 ret = docbParseSGMLAttribute(ctxt, '\'');
2876 if (CUR != '\'') {
2877 if ((ctxt->sax != NULL) && (ctxt->sax->error != NULL))
2878 ctxt->sax->error(ctxt->userData, "AttValue: ' expected\n");
2879 ctxt->wellFormed = 0;
2880 } else
2881 NEXT;
2882 } else {
2883 /*
2884 * That's an SGMLism, the attribute value may not be quoted
2885 */
2886 ret = docbParseSGMLAttribute(ctxt, 0);
2887 if (ret == NULL) {
2888 if ((ctxt->sax != NULL) && (ctxt->sax->error != NULL))
2889 ctxt->sax->error(ctxt->userData, "AttValue: no value found\n");
2890 ctxt->wellFormed = 0;
2891 }
2892 }
2893 return(ret);
2894 }
2895
2896 /**
2897 * docbParseSystemLiteral:
2898 * @ctxt: an SGML parser context
2899 *
2900 * parse an SGML Literal
2901 *
2902 * [11] SystemLiteral ::= ('"' [^"]* '"') | ("'" [^']* "'")
2903 *
2904 * Returns the SystemLiteral parsed or NULL
2905 */
2906
2907 static xmlChar *
2908 docbParseSystemLiteral(docbParserCtxtPtr ctxt) {
2909 const xmlChar *q;
2910 xmlChar *ret = NULL;
2911
2912 if (CUR == '"') {
2913 NEXT;
2914 q = CUR_PTR;
2915 while ((IS_CHAR(CUR)) && (CUR != '"'))
2916 NEXT;
2917 if (!IS_CHAR(CUR)) {
2918 if ((ctxt->sax != NULL) && (ctxt->sax->error != NULL))
2919 ctxt->sax->error(ctxt->userData, "Unfinished SystemLiteral\n");
2920 ctxt->wellFormed = 0;
2921 } else {
2922 ret = xmlStrndup(q, CUR_PTR - q);
2923 NEXT;
2924 }
2925 } else if (CUR == '\'') {
2926 NEXT;
2927 q = CUR_PTR;
2928 while ((IS_CHAR(CUR)) && (CUR != '\''))
2929 NEXT;
2930 if (!IS_CHAR(CUR)) {
2931 if ((ctxt->sax != NULL) && (ctxt->sax->error != NULL))
2932 ctxt->sax->error(ctxt->userData, "Unfinished SystemLiteral\n");
2933 ctxt->wellFormed = 0;
2934 } else {
2935 ret = xmlStrndup(q, CUR_PTR - q);
2936 NEXT;
2937 }
2938 } else {
2939 if ((ctxt->sax != NULL) && (ctxt->sax->error != NULL))
2940 ctxt->sax->error(ctxt->userData,
2941 "SystemLiteral \" or ' expected\n");
2942 ctxt->wellFormed = 0;
2943 }
2944
2945 return(ret);
2946 }
2947
2948 /**
2949 * docbParsePubidLiteral:
2950 * @ctxt: an SGML parser context
2951 *
2952 * parse an SGML public literal
2953 *
2954 * [12] PubidLiteral ::= '"' PubidChar* '"' | "'" (PubidChar - "'")* "'"
2955 *
2956 * Returns the PubidLiteral parsed or NULL.
2957 */
2958
2959 static xmlChar *
2960 docbParsePubidLiteral(docbParserCtxtPtr ctxt) {
2961 const xmlChar *q;
2962 xmlChar *ret = NULL;
2963 /*
2964 * Name ::= (Letter | '_') (NameChar)*
2965 */
2966 if (CUR == '"') {
2967 NEXT;
2968 q = CUR_PTR;
2969 while (IS_PUBIDCHAR(CUR)) NEXT;
2970 if (CUR != '"') {
2971 if ((ctxt->sax != NULL) && (ctxt->sax->error != NULL))
2972 ctxt->sax->error(ctxt->userData, "Unfinished PubidLiteral\n");
2973 ctxt->wellFormed = 0;
2974 } else {
2975 ret = xmlStrndup(q, CUR_PTR - q);
2976 NEXT;
2977 }
2978 } else if (CUR == '\'') {
2979 NEXT;
2980 q = CUR_PTR;
2981 while ((IS_LETTER(CUR)) && (CUR != '\''))
2982 NEXT;
2983 if (!IS_LETTER(CUR)) {
2984 if ((ctxt->sax != NULL) && (ctxt->sax->error != NULL))
2985 ctxt->sax->error(ctxt->userData, "Unfinished PubidLiteral\n");
2986 ctxt->wellFormed = 0;
2987 } else {
2988 ret = xmlStrndup(q, CUR_PTR - q);
2989 NEXT;
2990 }
2991 } else {
2992 if ((ctxt->sax != NULL) && (ctxt->sax->error != NULL))
2993 ctxt->sax->error(ctxt->userData, "SystemLiteral \" or ' expected\n");
2994 ctxt->wellFormed = 0;
2995 }
2996
2997 return(ret);
2998 }
2999
3000 /**
3001 * docbParseCharData:
3002 * @ctxt: an SGML parser context
3003 * @cdata: int indicating whether we are within a CDATA section
3004 *
3005 * parse a CharData section.
3006 * if we are within a CDATA section ']]>' marks an end of section.
3007 *
3008 * [14] CharData ::= [^<&]* - ([^<&]* ']]>' [^<&]*)
3009 */
3010
3011 static void
3012 docbParseCharData(docbParserCtxtPtr ctxt) {
3013 xmlChar buf[DOCB_PARSER_BIG_BUFFER_SIZE + 5];
3014 int nbchar = 0;
3015 int cur, l;
3016
3017 SHRINK;
3018 cur = CUR_CHAR(l);
3019 while (((cur != '<') || (ctxt->token == '<')) &&
3020 ((cur != '&') || (ctxt->token == '&')) &&
3021 (IS_CHAR(cur))) {
3022 COPY_BUF(l,buf,nbchar,cur);
3023 if (nbchar >= DOCB_PARSER_BIG_BUFFER_SIZE) {
3024 /*
3025 * Ok the segment is to be consumed as chars.
3026 */
3027 if ((ctxt->sax != NULL) && (!ctxt->disableSAX)) {
3028 if (areBlanks(ctxt, buf, nbchar)) {
3029 if (ctxt->sax->ignorableWhitespace != NULL)
3030 ctxt->sax->ignorableWhitespace(ctxt->userData,
3031 buf, nbchar);
3032 } else {
3033 if (ctxt->sax->characters != NULL)
3034 ctxt->sax->characters(ctxt->userData, buf, nbchar);
3035 }
3036 }
3037 nbchar = 0;
3038 }
3039 NEXTL(l);
3040 cur = CUR_CHAR(l);
3041 }
3042 if (nbchar != 0) {
3043 /*
3044 * Ok the segment is to be consumed as chars.
3045 */
3046 if ((ctxt->sax != NULL) && (!ctxt->disableSAX)) {
3047 if (areBlanks(ctxt, buf, nbchar)) {
3048 if (ctxt->sax->ignorableWhitespace != NULL)
3049 ctxt->sax->ignorableWhitespace(ctxt->userData, buf, nbchar);
3050 } else {
3051 if (ctxt->sax->characters != NULL)
3052 ctxt->sax->characters(ctxt->userData, buf, nbchar);
3053 }
3054 }
3055 }
3056 }
3057
3058 /**
3059 * docbParseExternalID:
3060 * @ctxt: an SGML parser context
3061 * @publicID: a xmlChar** receiving PubidLiteral
3062 *
3063 * Parse an External ID or a Public ID
3064 *
3065 * Returns the function returns SystemLiteral and in the second
3066 * case publicID receives PubidLiteral,
3067 * it is possible to return NULL and have publicID set.
3068 */
3069
3070 static xmlChar *
3071 docbParseExternalID(docbParserCtxtPtr ctxt, xmlChar **publicID) {
3072 xmlChar *URI = NULL;
3073
3074 if ((UPPER == 'S') && (UPP(1) == 'Y') &&
3075 (UPP(2) == 'S') && (UPP(3) == 'T') &&
3076 (UPP(4) == 'E') && (UPP(5) == 'M')) {
3077 SKIP(6);
3078 if (!IS_BLANK(CUR)) {
3079 if ((ctxt->sax != NULL) && (ctxt->sax->error != NULL))
3080 ctxt->sax->error(ctxt->userData,
3081 "Space required after 'SYSTEM'\n");
3082 ctxt->wellFormed = 0;
3083 }
3084 SKIP_BLANKS;
3085 URI = docbParseSystemLiteral(ctxt);
3086 if (URI == NULL) {
3087 if ((ctxt->sax != NULL) && (ctxt->sax->error != NULL))
3088 ctxt->sax->error(ctxt->userData,
3089 "docbParseExternalID: SYSTEM, no URI\n");
3090 ctxt->wellFormed = 0;
3091 }
3092 } else if ((UPPER == 'P') && (UPP(1) == 'U') &&
3093 (UPP(2) == 'B') && (UPP(3) == 'L') &&
3094 (UPP(4) == 'I') && (UPP(5) == 'C')) {
3095 SKIP(6);
3096 if (!IS_BLANK(CUR)) {
3097 if ((ctxt->sax != NULL) && (ctxt->sax->error != NULL))
3098 ctxt->sax->error(ctxt->userData,
3099 "Space required after 'PUBLIC'\n");
3100 ctxt->wellFormed = 0;
3101 }
3102 SKIP_BLANKS;
3103 *publicID = docbParsePubidLiteral(ctxt);
3104 if (*publicID == NULL) {
3105 if ((ctxt->sax != NULL) && (ctxt->sax->error != NULL))
3106 ctxt->sax->error(ctxt->userData,
3107 "docbParseExternalID: PUBLIC, no Public Identifier\n");
3108 ctxt->wellFormed = 0;
3109 }
3110 SKIP_BLANKS;
3111 if ((CUR == '"') || (CUR == '\'')) {
3112 URI = docbParseSystemLiteral(ctxt);
3113 }
3114 }
3115 return(URI);
3116 }
3117
3118 /**
3119 * docbParsePI:
3120 * @ctxt: an XML parser context
3121 *
3122 * parse an XML Processing Instruction.
3123 *
3124 * [16] PI ::= '<?' PITarget (S (Char* - (Char* '?>' Char*)))? '?>'
3125 *
3126 * The processing is transfered to SAX once parsed.
3127 */
3128
3129 static void
3130 docbParsePI(xmlParserCtxtPtr ctxt) {
3131 xmlChar *buf = NULL;
3132 int len = 0;
3133 int size = DOCB_PARSER_BUFFER_SIZE;
3134 int cur, l;
3135 xmlChar *target;
3136 xmlParserInputState state;
3137 int count = 0;
3138
3139 if ((RAW == '<') && (NXT(1) == '?')) {
3140 xmlParserInputPtr input = ctxt->input;
3141 state = ctxt->instate;
3142 ctxt->instate = XML_PARSER_PI;
3143 /*
3144 * this is a Processing Instruction.
3145 */
3146 SKIP(2);
3147 SHRINK;
3148
3149 /*
3150 * Parse the target name and check for special support like
3151 * namespace.
3152 */
3153 target = xmlParseName(ctxt);
3154 if (target != NULL) {
3155 xmlChar *encoding = NULL;
3156
3157 if ((RAW == '?') && (NXT(1) == '>')) {
3158 if (input != ctxt->input) {
3159 ctxt->errNo = XML_ERR_ENTITY_BOUNDARY;
3160 if ((ctxt->sax != NULL) && (ctxt->sax->error != NULL))
3161 ctxt->sax->error(ctxt->userData,
3162 "PI declaration doesn't start and stop in the same entity\n");
3163 ctxt->wellFormed = 0;
3164 if (ctxt->recovery == 0) ctxt->disableSAX = 1;
3165 }
3166 SKIP(2);
3167
3168 /*
3169 * SAX: PI detected.
3170 */
3171 if ((ctxt->sax) && (!ctxt->disableSAX) &&
3172 (ctxt->sax->processingInstruction != NULL))
3173 ctxt->sax->processingInstruction(ctxt->userData,
3174 target, NULL);
3175 ctxt->instate = state;
3176 xmlFree(target);
3177 return;
3178 }
3179 if (xmlStrEqual(target, BAD_CAST "sgml-declaration")) {
3180
3181 encoding = xmlParseEncodingDecl(ctxt);
3182 if (encoding == NULL) {
3183 xmlGenericError(xmlGenericErrorContext,
3184 "sgml-declaration: failed to find/handle encoding\n");
3185 #ifdef DEBUG
3186 } else {
3187 xmlGenericError(xmlGenericErrorContext,
3188 "switched to encoding %s\n", encoding);
3189 #endif
3190 }
3191
3192 }
3193 buf = (xmlChar *) xmlMalloc(size * sizeof(xmlChar));
3194 if (buf == NULL) {
3195 xmlGenericError(xmlGenericErrorContext,
3196 "malloc of %d byte failed\n", size);
3197 ctxt->instate = state;
3198 return;
3199 }
3200 cur = CUR;
3201 if (encoding != NULL) {
3202 len = snprintf((char *) buf, size - 1,
3203 " encoding = \"%s\"", encoding);
3204 if (len < 0)
3205 len = size;
3206 } else {
3207 if (!IS_BLANK(cur)) {
3208 ctxt->errNo = XML_ERR_SPACE_REQUIRED;
3209 if ((ctxt->sax != NULL) && (ctxt->sax->error != NULL))
3210 ctxt->sax->error(ctxt->userData,
3211 "docbParsePI: PI %s space expected\n", target);
3212 ctxt->wellFormed = 0;
3213 if (ctxt->recovery == 0) ctxt->disableSAX = 1;
3214 }
3215 SKIP_BLANKS;
3216 }
3217 cur = CUR_CHAR(l);
3218 while (IS_CHAR(cur) && /* checked */
3219 ((cur != '?') || (NXT(1) != '>'))) {
3220 if (len + 5 >= size) {
3221 size *= 2;
3222 buf = (xmlChar *) xmlRealloc(buf, size * sizeof(xmlChar));
3223 if (buf == NULL) {
3224 xmlGenericError(xmlGenericErrorContext,
3225 "realloc of %d byte failed\n", size);
3226 ctxt->instate = state;
3227 return;
3228 }
3229 }
3230 count++;
3231 if (count > 50) {
3232 GROW;
3233 count = 0;
3234 }
3235 COPY_BUF(l,buf,len,cur);
3236 NEXTL(l);
3237 cur = CUR_CHAR(l);
3238 if (cur == 0) {
3239 SHRINK;
3240 GROW;
3241 cur = CUR_CHAR(l);
3242 }
3243 }
3244 buf[len] = 0;
3245 if (cur != '?') {
3246 ctxt->errNo = XML_ERR_PI_NOT_FINISHED;
3247 if ((ctxt->sax != NULL) && (ctxt->sax->error != NULL))
3248 ctxt->sax->error(ctxt->userData,
3249 "docbParsePI: PI %s never end ...\n", target);
3250 ctxt->wellFormed = 0;
3251 if (ctxt->recovery == 0) ctxt->disableSAX = 1;
3252 } else {
3253 if (input != ctxt->input) {
3254 ctxt->errNo = XML_ERR_ENTITY_BOUNDARY;
3255 if ((ctxt->sax != NULL) && (ctxt->sax->error != NULL))
3256 ctxt->sax->error(ctxt->userData,
3257 "PI declaration doesn't start and stop in the same entity\n");
3258 ctxt->wellFormed = 0;
3259 if (ctxt->recovery == 0) ctxt->disableSAX = 1;
3260 }
3261 SKIP(2);
3262
3263 /*
3264 * SAX: PI detected.
3265 */
3266 if ((ctxt->sax) && (!ctxt->disableSAX) &&
3267 (ctxt->sax->processingInstruction != NULL))
3268 ctxt->sax->processingInstruction(ctxt->userData,
3269 target, buf);
3270 }
3271 xmlFree(buf);
3272 xmlFree(target);
3273 } else {
3274 ctxt->errNo = XML_ERR_PI_NOT_STARTED;
3275 if ((ctxt->sax != NULL) && (ctxt->sax->error != NULL))
3276 ctxt->sax->error(ctxt->userData,
3277 "docbParsePI : no target name\n");
3278 ctxt->wellFormed = 0;
3279 if (ctxt->recovery == 0) ctxt->disableSAX = 1;
3280 }
3281 ctxt->instate = state;
3282 }
3283 }
3284
3285 /**
3286 * docbParseComment:
3287 * @ctxt: an SGML parser context
3288 *
3289 * Parse an XML (SGML) comment <!-- .... -->
3290 *
3291 * [15] Comment ::= '<!--' ((Char - '-') | ('-' (Char - '-')))* '-->'
3292 */
3293 static void
3294 docbParseComment(docbParserCtxtPtr ctxt) {
3295 xmlChar *buf = NULL;
3296 int len;
3297 int size = DOCB_PARSER_BUFFER_SIZE;
3298 int q, ql;
3299 int r, rl;
3300 int cur, l;
3301 xmlParserInputState state;
3302
3303 /*
3304 * Check that there is a comment right here.
3305 */
3306 if ((RAW != '<') || (NXT(1) != '!') ||
3307 (NXT(2) != '-') || (NXT(3) != '-')) return;
3308
3309 state = ctxt->instate;
3310 ctxt->instate = XML_PARSER_COMMENT;
3311 SHRINK;
3312 SKIP(4);
3313 buf = (xmlChar *) xmlMalloc(size * sizeof(xmlChar));
3314 if (buf == NULL) {
3315 xmlGenericError(xmlGenericErrorContext,
3316 "malloc of %d byte failed\n", size);
3317 ctxt->instate = state;
3318 return;
3319 }
3320 q = CUR_CHAR(ql);
3321 NEXTL(ql);
3322 r = CUR_CHAR(rl);
3323 NEXTL(rl);
3324 cur = CUR_CHAR(l);
3325 len = 0;
3326 while (IS_CHAR(cur) &&
3327 ((cur != '>') ||
3328 (r != '-') || (q != '-'))) {
3329 if (len + 5 >= size) {
3330 size *= 2;
3331 buf = (xmlChar *) xmlRealloc(buf, size * sizeof(xmlChar));
3332 if (buf == NULL) {
3333 xmlGenericError(xmlGenericErrorContext,
3334 "realloc of %d byte failed\n", size);
3335 ctxt->instate = state;
3336 return;
3337 }
3338 }
3339 COPY_BUF(ql,buf,len,q);
3340 q = r;
3341 ql = rl;
3342 r = cur;
3343 rl = l;
3344 NEXTL(l);
3345 cur = CUR_CHAR(l);
3346 if (cur == 0) {
3347 SHRINK;
3348 GROW;
3349 cur = CUR_CHAR(l);
3350 }
3351 }
3352 buf[len] = 0;
3353 if (!IS_CHAR(cur)) {
3354 ctxt->errNo = XML_ERR_COMMENT_NOT_FINISHED;
3355 if ((ctxt->sax != NULL) && (ctxt->sax->error != NULL))
3356 ctxt->sax->error(ctxt->userData,
3357 "Comment not terminated \n<!--%.50s\n", buf);
3358 ctxt->wellFormed = 0;
3359 xmlFree(buf);
3360 } else {
3361 NEXT;
3362 if ((ctxt->sax != NULL) && (ctxt->sax->comment != NULL) &&
3363 (!ctxt->disableSAX))
3364 ctxt->sax->comment(ctxt->userData, buf);
3365 xmlFree(buf);
3366 }
3367 ctxt->instate = state;
3368 }
3369
3370 /**
3371 * docbParseCharRef:
3372 * @ctxt: an SGML parser context
3373 *
3374 * parse Reference declarations
3375 *
3376 * [66] CharRef ::= '&#' [0-9]+ ';' |
3377 * '&#x' [0-9a-fA-F]+ ';'
3378 *
3379 * Returns the value parsed (as an int)
3380 */
3381 static int
3382 docbParseCharRef(docbParserCtxtPtr ctxt) {
3383 int val = 0;
3384
3385 if ((CUR == '&') && (NXT(1) == '#') &&
3386 (NXT(2) == 'x')) {
3387 SKIP(3);
3388 while (CUR != ';') {
3389 if ((CUR >= '0') && (CUR <= '9'))
3390 val = val * 16 + (CUR - '0');
3391 else if ((CUR >= 'a') && (CUR <= 'f'))
3392 val = val * 16 + (CUR - 'a') + 10;
3393 else if ((CUR >= 'A') && (CUR <= 'F'))
3394 val = val * 16 + (CUR - 'A') + 10;
3395 else {
3396 if ((ctxt->sax != NULL) && (ctxt->sax->error != NULL))
3397 ctxt->sax->error(ctxt->userData,
3398 "docbParseCharRef: invalid hexadecimal value\n");
3399 ctxt->wellFormed = 0;
3400 val = 0;
3401 break;
3402 }
3403 NEXT;
3404 }
3405 if (CUR == ';')
3406 NEXT;
3407 } else if ((CUR == '&') && (NXT(1) == '#')) {
3408 SKIP(2);
3409 while (CUR != ';') {
3410 if ((CUR >= '0') && (CUR <= '9'))
3411 val = val * 10 + (CUR - '0');
3412 else {
3413 if ((ctxt->sax != NULL) && (ctxt->sax->error != NULL))
3414 ctxt->sax->error(ctxt->userData,
3415 "docbParseCharRef: invalid decimal value\n");
3416 ctxt->wellFormed = 0;
3417 val = 0;
3418 break;
3419 }
3420 NEXT;
3421 }
3422 if (CUR == ';')
3423 NEXT;
3424 } else {
3425 if ((ctxt->sax != NULL) && (ctxt->sax->error != NULL))
3426 ctxt->sax->error(ctxt->userData, "docbParseCharRef: invalid value\n");
3427 ctxt->wellFormed = 0;
3428 }
3429 /*
3430 * Check the value IS_CHAR ...
3431 */
3432 if (IS_CHAR(val)) {
3433 return(val);
3434 } else {
3435 if ((ctxt->sax != NULL) && (ctxt->sax->error != NULL))
3436 ctxt->sax->error(ctxt->userData, "docbParseCharRef: invalid xmlChar value %d\n",
3437 val);
3438 ctxt->wellFormed = 0;
3439 }
3440 return(0);
3441 }
3442
3443
3444 /**
3445 * docbParseDocTypeDecl :
3446 * @ctxt: an SGML parser context
3447 *
3448 * parse a DOCTYPE declaration
3449 *
3450 * [28] doctypedecl ::= '<!DOCTYPE' S Name (S ExternalID)? S?
3451 * ('[' (markupdecl | PEReference | S)* ']' S?)? '>'
3452 */
3453
3454 static void
3455 docbParseDocTypeDecl(docbParserCtxtPtr ctxt) {
3456 xmlChar *name;
3457 xmlChar *ExternalID = NULL;
3458 xmlChar *URI = NULL;
3459
3460 /*
3461 * We know that '<!DOCTYPE' has been detected.
3462 */
3463 SKIP(9);
3464
3465 SKIP_BLANKS;
3466
3467 /*
3468 * Parse the DOCTYPE name.
3469 */
3470 name = docbParseName(ctxt);
3471 if (name == NULL) {
3472 if ((ctxt->sax != NULL) && (ctxt->sax->error != NULL))
3473 ctxt->sax->error(ctxt->userData, "docbParseDocTypeDecl : no DOCTYPE name !\n");
3474 ctxt->wellFormed = 0;
3475 }
3476 /*
3477 * Check that upper(name) == "SGML" !!!!!!!!!!!!!
3478 */
3479
3480 SKIP_BLANKS;
3481
3482 /*
3483 * Check for SystemID and ExternalID
3484 */
3485 URI = docbParseExternalID(ctxt, &ExternalID);
3486 SKIP_BLANKS;
3487
3488 /*
3489 * Create or update the document accordingly to the DOCTYPE
3490 * But use the predefined PUBLIC and SYSTEM ID of DocBook XML
3491 */
3492 if ((ctxt->sax != NULL) && (ctxt->sax->internalSubset != NULL) &&
3493 (!ctxt->disableSAX))
3494 ctxt->sax->internalSubset(ctxt->userData, name,
3495 XML_DOCBOOK_XML_PUBLIC,
3496 XML_DOCBOOK_XML_SYSTEM);
3497
3498 if (RAW != '>') {
3499 if ((ctxt->sax != NULL) && (ctxt->sax->error != NULL))
3500 ctxt->sax->error(ctxt->userData,
3501 "docbParseDocTypeDecl : internal subset not handled\n");
3502 } else {
3503 NEXT;
3504 }
3505
3506 /*
3507 * Cleanup, since we don't use all those identifiers
3508 */
3509 if (URI != NULL) xmlFree(URI);
3510 if (ExternalID != NULL) xmlFree(ExternalID);
3511 if (name != NULL) xmlFree(name);
3512 }
3513
3514 /**
3515 * docbParseAttribute:
3516 * @ctxt: an SGML parser context
3517 * @value: a xmlChar ** used to store the value of the attribute
3518 *
3519 * parse an attribute
3520 *
3521 * [41] Attribute ::= Name Eq AttValue
3522 *
3523 * [25] Eq ::= S? '=' S?
3524 *
3525 * With namespace:
3526 *
3527 * [NS 11] Attribute ::= QName Eq AttValue
3528 *
3529 * Also the case QName == xmlns:??? is handled independently as a namespace
3530 * definition.
3531 *
3532 * Returns the attribute name, and the value in *value.
3533 */
3534
3535 static xmlChar *
3536 docbParseAttribute(docbParserCtxtPtr ctxt, xmlChar **value) {
3537 xmlChar *name, *val = NULL;
3538
3539 *value = NULL;
3540 name = docbParseName(ctxt);
3541 if (name == NULL) {
3542 if ((ctxt->sax != NULL) && (ctxt->sax->error != NULL))
3543 ctxt->sax->error(ctxt->userData, "error parsing attribute name\n");
3544 ctxt->wellFormed = 0;
3545 return(NULL);
3546 }
3547
3548 /*
3549 * read the value
3550 */
3551 SKIP_BLANKS;
3552 if (CUR == '=') {
3553 NEXT;
3554 SKIP_BLANKS;
3555 val = docbParseAttValue(ctxt);
3556 /******
3557 } else {
3558 * TODO : some attribute must have values, some may not
3559 if ((ctxt->sax != NULL) && (ctxt->sax->error != NULL))
3560 ctxt->sax->warning(ctxt->userData,
3561 "No value for attribute %s\n", name); */
3562 }
3563
3564 *value = val;
3565 return(name);
3566 }
3567
3568 /**
3569 * docbCheckEncoding:
3570 * @ctxt: an SGML parser context
3571 * @attvalue: the attribute value
3572 *
3573 * Checks an http-equiv attribute from a Meta tag to detect
3574 * the encoding
3575 * If a new encoding is detected the parser is switched to decode
3576 * it and pass UTF8
3577 */
3578 static void
3579 docbCheckEncoding(docbParserCtxtPtr ctxt, const xmlChar *attvalue) {
3580 const xmlChar *encoding;
3581
3582 if ((ctxt == NULL) || (attvalue == NULL))
3583 return;
3584
3585 encoding = xmlStrstr(attvalue, BAD_CAST"charset=");
3586 if (encoding == NULL)
3587 encoding = xmlStrstr(attvalue, BAD_CAST"Charset=");
3588 if (encoding == NULL)
3589 encoding = xmlStrstr(attvalue, BAD_CAST"CHARSET=");
3590 if (encoding != NULL) {
3591 encoding += 8;
3592 } else {
3593 encoding = xmlStrstr(attvalue, BAD_CAST"charset =");
3594 if (encoding == NULL)
3595 encoding = xmlStrstr(attvalue, BAD_CAST"Charset =");
3596 if (encoding == NULL)
3597 encoding = xmlStrstr(attvalue, BAD_CAST"CHARSET =");
3598 if (encoding != NULL)
3599 encoding += 9;
3600 }
3601 /*
3602 * Restricted from 2.3.5 */
3603 if (encoding != NULL) {
3604 xmlCharEncoding enc;
3605
3606 if (ctxt->input->encoding != NULL)
3607 xmlFree((xmlChar *) ctxt->input->encoding);
3608 ctxt->input->encoding = encoding;
3609
3610 enc = xmlParseCharEncoding((const char *) encoding);
3611 if (enc == XML_CHAR_ENCODING_8859_1) {
3612 ctxt->charset = XML_CHAR_ENCODING_8859_1;
3613 } else if (enc != XML_CHAR_ENCODING_UTF8) {
3614 if ((ctxt->sax != NULL) && (ctxt->sax->error != NULL))
3615 ctxt->sax->error(ctxt->userData,
3616 "Unsupported encoding %s\n", encoding);
3617 /* xmlFree(encoding); */
3618 ctxt->wellFormed = 0;
3619 if (ctxt->recovery == 0) ctxt->disableSAX = 1;
3620 ctxt->errNo = XML_ERR_UNSUPPORTED_ENCODING;
3621 }
3622 }
3623 }
3624
3625 /**
3626 * docbCheckMeta:
3627 * @ctxt: an SGML parser context
3628 * @atts: the attributes values
3629 *
3630 * Checks an attributes from a Meta tag
3631 */
3632 static void
3633 docbCheckMeta(docbParserCtxtPtr ctxt, const xmlChar **atts) {
3634 int i;
3635 const xmlChar *att, *value;
3636 int http = 0;
3637 const xmlChar *content = NULL;
3638
3639 if ((ctxt == NULL) || (atts == NULL))
3640 return;
3641
3642 i = 0;
3643 att = atts[i++];
3644 while (att != NULL) {
3645 value = atts[i++];
3646 if ((value != NULL) &&
3647 ((xmlStrEqual(att, BAD_CAST"http-equiv")) ||
3648 (xmlStrEqual(att, BAD_CAST"Http-Equiv")) ||
3649 (xmlStrEqual(att, BAD_CAST"HTTP-EQUIV"))) &&
3650 ((xmlStrEqual(value, BAD_CAST"Content-Type")) ||
3651 (xmlStrEqual(value, BAD_CAST"content-type")) ||
3652 (xmlStrEqual(value, BAD_CAST"CONTENT-TYPE"))))
3653 http = 1;
3654 else if ((value != NULL) &&
3655 ((xmlStrEqual(att, BAD_CAST"content")) ||
3656 (xmlStrEqual(att, BAD_CAST"Content")) ||
3657 (xmlStrEqual(att, BAD_CAST"CONTENT"))))
3658 content = value;
3659 att = atts[i++];
3660 }
3661 if ((http) && (content != NULL))
3662 docbCheckEncoding(ctxt, content);
3663
3664 }
3665
3666 /**
3667 * docbParseStartTag:
3668 * @ctxt: an SGML parser context
3669 *
3670 * parse a start of tag either for rule element or
3671 * EmptyElement. In both case we don't parse the tag closing chars.
3672 *
3673 * [40] STag ::= '<' Name (S Attribute)* S? '>'
3674 *
3675 * [44] EmptyElemTag ::= '<' Name (S Attribute)* S? '/>'
3676 *
3677 * With namespace:
3678 *
3679 * [NS 8] STag ::= '<' QName (S Attribute)* S? '>'
3680 *
3681 * [NS 10] EmptyElement ::= '<' QName (S Attribute)* S? '/>'
3682 *
3683 */
3684
3685 static void
3686 docbParseStartTag(docbParserCtxtPtr ctxt) {
3687 xmlChar *name;
3688 xmlChar *attname;
3689 xmlChar *attvalue;
3690 const xmlChar **atts = NULL;
3691 int nbatts = 0;
3692 int maxatts = 0;
3693 int meta = 0;
3694 int i;
3695
3696 if (CUR != '<') return;
3697 NEXT;
3698
3699 GROW;
3700 name = docbParseSGMLName(ctxt);
3701 if (name == NULL) {
3702 if ((ctxt->sax != NULL) && (ctxt->sax->error != NULL))
3703 ctxt->sax->error(ctxt->userData,
3704 "docbParseStartTag: invalid element name\n");
3705 ctxt->wellFormed = 0;
3706 return;
3707 }
3708 if (xmlStrEqual(name, BAD_CAST"meta"))
3709 meta = 1;
3710
3711 /*
3712 * Check for auto-closure of SGML elements.
3713 */
3714 docbAutoClose(ctxt, name);
3715
3716 /*
3717 * Now parse the attributes, it ends up with the ending
3718 *
3719 * (S Attribute)* S?
3720 */
3721 SKIP_BLANKS;
3722 while ((IS_CHAR(CUR)) &&
3723 (CUR != '>') &&
3724 ((CUR != '/') || (NXT(1) != '>'))) {
3725 long cons = ctxt->nbChars;
3726
3727 GROW;
3728 attname = docbParseAttribute(ctxt, &attvalue);
3729 if (attname != NULL) {
3730
3731 /*
3732 * Well formedness requires at most one declaration of an attribute
3733 */
3734 for (i = 0; i < nbatts;i += 2) {
3735 if (xmlStrEqual(atts[i], attname)) {
3736 if ((ctxt->sax != NULL) && (ctxt->sax->error != NULL))
3737 ctxt->sax->error(ctxt->userData,
3738 "Attribute %s redefined\n",
3739 attname);
3740 ctxt->wellFormed = 0;
3741 xmlFree(attname);
3742 if (attvalue != NULL)
3743 xmlFree(attvalue);
3744 goto failed;
3745 }
3746 }
3747
3748 /*
3749 * Add the pair to atts
3750 */
3751 if (atts == NULL) {
3752 maxatts = 10;
3753 atts = (const xmlChar **) xmlMalloc(maxatts * sizeof(xmlChar *));
3754 if (atts == NULL) {
3755 xmlGenericError(xmlGenericErrorContext,
3756 "malloc of %ld byte failed\n",
3757 maxatts * (long)sizeof(xmlChar *));
3758 if (name != NULL) xmlFree(name);
3759 return;
3760 }
3761 } else if (nbatts + 4 > maxatts) {
3762 maxatts *= 2;
3763 atts = (const xmlChar **) xmlRealloc((void *)atts, maxatts * sizeof(xmlChar *));
3764 if (atts == NULL) {
3765 xmlGenericError(xmlGenericErrorContext,
3766 "realloc of %ld byte failed\n",
3767 maxatts * (long)sizeof(xmlChar *));
3768 if (name != NULL) xmlFree(name);
3769 return;
3770 }
3771 }
3772 atts[nbatts++] = attname;
3773 atts[nbatts++] = attvalue;
3774 atts[nbatts] = NULL;
3775 atts[nbatts + 1] = NULL;
3776 }
3777
3778 failed:
3779 SKIP_BLANKS;
3780 if (cons == ctxt->nbChars) {
3781 if ((ctxt->sax != NULL) && (ctxt->sax->error != NULL))
3782 ctxt->sax->error(ctxt->userData,
3783 "docbParseStartTag: problem parsing attributes\n");
3784 ctxt->wellFormed = 0;
3785 break;
3786 }
3787 }
3788
3789 /*
3790 * Handle specific association to the META tag
3791 */
3792 if (meta)
3793 docbCheckMeta(ctxt, atts);
3794
3795 /*
3796 * SAX: Start of Element !
3797 */
3798 docbnamePush(ctxt, xmlStrdup(name));
3799 #ifdef DEBUG
3800 xmlGenericError(xmlGenericErrorContext,"Start of element %s: pushed %s\n", name, ctxt->name);
3801 #endif
3802 if ((ctxt->sax != NULL) && (ctxt->sax->startElement != NULL))
3803 ctxt->sax->startElement(ctxt->userData, name, atts);
3804
3805 if (atts != NULL) {
3806 for (i = 0;i < nbatts;i++) {
3807 if (atts[i] != NULL)
3808 xmlFree((xmlChar *) atts[i]);
3809 }
3810 xmlFree((void *) atts);
3811 }
3812 if (name != NULL) xmlFree(name);
3813 }
3814
3815 /**
3816 * docbParseEndTag:
3817 * @ctxt: an SGML parser context
3818 *
3819 * parse an end of tag
3820 *
3821 * [42] ETag ::= '</' Name S? '>'
3822 *
3823 * With namespace
3824 *
3825 * [NS 9] ETag ::= '</' QName S? '>'
3826 */
3827
3828 static void
3829 docbParseEndTag(docbParserCtxtPtr ctxt) {
3830 xmlChar *name;
3831 xmlChar *oldname;
3832 int i;
3833
3834 if ((CUR != '<') || (NXT(1) != '/')) {
3835 if ((ctxt->sax != NULL) && (ctxt->sax->error != NULL))
3836 ctxt->sax->error(ctxt->userData, "docbParseEndTag: '</' not found\n");
3837 ctxt->wellFormed = 0;
3838 return;
3839 }
3840 SKIP(2);
3841
3842 name = docbParseSGMLName(ctxt);
3843 if (name == NULL) {
3844 if (CUR == '>') {
3845 NEXT;
3846 oldname = docbnamePop(ctxt);
3847 if (oldname != NULL) {
3848 if ((ctxt->sax != NULL) && (ctxt->sax->endElement != NULL))
3849 ctxt->sax->endElement(ctxt->userData, name);
3850 #ifdef DEBUG
3851 xmlGenericError(xmlGenericErrorContext,"End of tag </>: popping out %s\n", oldname);
3852 #endif
3853 xmlFree(oldname);
3854 #ifdef DEBUG
3855 } else {
3856 xmlGenericError(xmlGenericErrorContext,"End of tag </>: stack empty !!!\n");
3857 #endif
3858 }
3859 return;
3860 } else
3861 return;
3862 }
3863
3864 /*
3865 * We should definitely be at the ending "S? '>'" part
3866 */
3867 SKIP_BLANKS;
3868 if ((!IS_CHAR(CUR)) || (CUR != '>')) {
3869 if ((ctxt->sax != NULL) && (ctxt->sax->error != NULL))
3870 ctxt->sax->error(ctxt->userData, "End tag : expected '>'\n");
3871 ctxt->wellFormed = 0;
3872 } else
3873 NEXT;
3874
3875 /*
3876 * If the name read is not one of the element in the parsing stack
3877 * then return, it's just an error.
3878 */
3879 for (i = (ctxt->nameNr - 1);i >= 0;i--) {
3880 if (xmlStrEqual(name, ctxt->nameTab[i])) break;
3881 }
3882 if (i < 0) {
3883 if ((ctxt->sax != NULL) && (ctxt->sax->error != NULL))
3884 ctxt->sax->error(ctxt->userData,
3885 "Unexpected end tag : %s\n", name);
3886 xmlFree(name);
3887 ctxt->wellFormed = 0;
3888 return;
3889 }
3890
3891
3892 /*
3893 * Check for auto-closure of SGML elements.
3894 */
3895
3896 docbAutoCloseOnClose(ctxt, name);
3897
3898 /*
3899 * Well formedness constraints, opening and closing must match.
3900 * With the exception that the autoclose may have popped stuff out
3901 * of the stack.
3902 */
3903 if (((name[0] != '/') || (name[1] != 0)) &&
3904 (!xmlStrEqual(name, ctxt->name))) {
3905 #ifdef DEBUG
3906 xmlGenericError(xmlGenericErrorContext,"End of tag %s: expecting %s\n", name, ctxt->name);
3907 #endif
3908 if ((ctxt->name != NULL) &&
3909 (!xmlStrEqual(ctxt->name, name))) {
3910 if ((ctxt->sax != NULL) && (ctxt->sax->error != NULL))
3911 ctxt->sax->error(ctxt->userData,
3912 "Opening and ending tag mismatch: %s and %s\n",
3913 name, ctxt->name);
3914 ctxt->wellFormed = 0;
3915 }
3916 }
3917
3918 /*
3919 * SAX: End of Tag
3920 */
3921 oldname = ctxt->name;
3922 if (((name[0] == '/') && (name[1] == 0)) ||
3923 ((oldname != NULL) && (xmlStrEqual(oldname, name)))) {
3924 if ((ctxt->sax != NULL) && (ctxt->sax->endElement != NULL))
3925 ctxt->sax->endElement(ctxt->userData, name);
3926 oldname = docbnamePop(ctxt);
3927 if (oldname != NULL) {
3928 #ifdef DEBUG
3929 xmlGenericError(xmlGenericErrorContext,"End of tag %s: popping out %s\n", name, oldname);
3930 #endif
3931 xmlFree(oldname);
3932 #ifdef DEBUG
3933 } else {
3934 xmlGenericError(xmlGenericErrorContext,"End of tag %s: stack empty !!!\n", name);
3935 #endif
3936 }
3937 }
3938
3939 if (name != NULL)
3940 xmlFree(name);
3941
3942 return;
3943 }
3944
3945
3946 /**
3947 * docbParseReference:
3948 * @ctxt: an SGML parser context
3949 *
3950 * parse and handle entity references in content,
3951 * this will end-up in a call to character() since this is either a
3952 * CharRef, or a predefined entity.
3953 */
3954 static void
3955 docbParseReference(docbParserCtxtPtr ctxt) {
3956 docbEntityDescPtr ent;
3957 xmlEntityPtr xent;
3958 xmlChar out[6];
3959 xmlChar *name;
3960 if (CUR != '&') return;
3961
3962 if (NXT(1) == '#') {
3963 unsigned int c;
3964 int bits, i = 0;
3965
3966 c = docbParseCharRef(ctxt);
3967 if (c < 0x80) { out[i++]= c; bits= -6; }
3968 else if (c < 0x800) { out[i++]=((c >> 6) & 0x1F) | 0xC0; bits= 0; }
3969 else if (c < 0x10000) { out[i++]=((c >> 12) & 0x0F) | 0xE0; bits= 6; }
3970 else { out[i++]=((c >> 18) & 0x07) | 0xF0; bits= 12; }
3971
3972 for ( ; bits >= 0; bits-= 6) {
3973 out[i++]= ((c >> bits) & 0x3F) | 0x80;
3974 }
3975 out[i] = 0;
3976
3977 if ((ctxt->sax != NULL) && (ctxt->sax->characters != NULL))
3978 ctxt->sax->characters(ctxt->userData, out, i);
3979 } else {
3980 /*
3981 * Lookup the entity in the table.
3982 */
3983 xent = docbParseEntityRef(ctxt, &name);
3984 if (xent != NULL) {
3985 if (((ctxt->replaceEntities) || (ctxt->loadsubset)) &&
3986 ((xent->children == NULL) &&
3987 (xent->etype == XML_EXTERNAL_GENERAL_PARSED_ENTITY))) {
3988 /*
3989 * we really need to fetch and parse the external entity
3990 */
3991 int parse;
3992 xmlNodePtr children = NULL;
3993
3994 parse = docbParseCtxtExternalEntity(ctxt,
3995 xent->SystemID, xent->ExternalID, &children);
3996 xmlAddChildList((xmlNodePtr) xent, children);
3997 }
3998 if (ctxt->replaceEntities) {
3999 if ((ctxt->node != NULL) && (xent->children != NULL)) {
4000 /*
4001 * Seems we are generating the DOM content, do
4002 * a simple tree copy
4003 */
4004 xmlNodePtr new;
4005 new = xmlCopyNodeList(xent->children);
4006
4007 xmlAddChildList(ctxt->node, new);
4008 /*
4009 * This is to avoid a nasty side effect, see
4010 * characters() in SAX.c
4011 */
4012 ctxt->nodemem = 0;
4013 ctxt->nodelen = 0;
4014 }
4015 } else {
4016 if ((ctxt->sax != NULL) && (ctxt->sax->reference != NULL) &&
4017 (ctxt->replaceEntities == 0) && (!ctxt->disableSAX)) {
4018 /*
4019 * Create a node.
4020 */
4021 ctxt->sax->reference(ctxt->userData, xent->name);
4022 }
4023 }
4024 } else if (name != NULL) {
4025 ent = docbEntityLookup(name);
4026 if ((ent == NULL) || (ent->value <= 0)) {
4027 if ((ctxt->sax != NULL) && (ctxt->sax->characters != NULL)) {
4028 ctxt->sax->characters(ctxt->userData, BAD_CAST "&", 1);
4029 ctxt->sax->characters(ctxt->userData, name, xmlStrlen(name));
4030 /* ctxt->sax->characters(ctxt->userData, BAD_CAST ";", 1); */
4031 }
4032 } else {
4033 unsigned int c;
4034 int bits, i = 0;
4035
4036 c = ent->value;
4037 if (c < 0x80)
4038 { out[i++]= c; bits= -6; }
4039 else if (c < 0x800)
4040 { out[i++]=((c >> 6) & 0x1F) | 0xC0; bits= 0; }
4041 else if (c < 0x10000)
4042 { out[i++]=((c >> 12) & 0x0F) | 0xE0; bits= 6; }
4043 else
4044 { out[i++]=((c >> 18) & 0x07) | 0xF0; bits= 12; }
4045
4046 for ( ; bits >= 0; bits-= 6) {
4047 out[i++]= ((c >> bits) & 0x3F) | 0x80;
4048 }
4049 out[i] = 0;
4050
4051 if ((ctxt->sax != NULL) && (ctxt->sax->characters != NULL))
4052 ctxt->sax->characters(ctxt->userData, out, i);
4053 }
4054 } else {
4055 if ((ctxt->sax != NULL) && (ctxt->sax->characters != NULL))
4056 ctxt->sax->characters(ctxt->userData, BAD_CAST "&", 1);
4057 return;
4058 }
4059 if (name != NULL)
4060 xmlFree(name);
4061 }
4062 }
4063
4064 /**
4065 * docbParseContent:
4066 * @ctxt: an SGML parser context
4067 * @name: the node name
4068 *
4069 * Parse a content: comment, sub-element, reference or text.
4070 *
4071 */
4072 static void
4073 docbParseContent(docbParserCtxtPtr ctxt)
4074 {
4075 xmlChar *currentNode;
4076 int depth;
4077
4078 currentNode = xmlStrdup(ctxt->name);
4079 depth = ctxt->nameNr;
4080 while (1) {
4081 long cons = ctxt->nbChars;
4082
4083 GROW;
4084 /*
4085 * Our tag or one of it's parent or children is ending.
4086 */
4087 if ((CUR == '<') && (NXT(1) == '/')) {
4088 docbParseEndTag(ctxt);
4089 if (currentNode != NULL)
4090 xmlFree(currentNode);
4091 return;
4092 }
4093
4094 /*
4095 * Has this node been popped out during parsing of
4096 * the next element
4097 */
4098 if ((!xmlStrEqual(currentNode, ctxt->name)) &&
4099 (depth >= ctxt->nameNr)) {
4100 if (currentNode != NULL)
4101 xmlFree(currentNode);
4102 return;
4103 }
4104
4105 /*
4106 * Sometimes DOCTYPE arrives in the middle of the document
4107 */
4108 if ((CUR == '<') && (NXT(1) == '!') &&
4109 (UPP(2) == 'D') && (UPP(3) == 'O') &&
4110 (UPP(4) == 'C') && (UPP(5) == 'T') &&
4111 (UPP(6) == 'Y') && (UPP(7) == 'P') && (UPP(8) == 'E')) {
4112 if ((ctxt->sax != NULL) && (ctxt->sax->error != NULL))
4113 ctxt->sax->error(ctxt->userData,
4114 "Misplaced DOCTYPE declaration\n");
4115 ctxt->wellFormed = 0;
4116 docbParseDocTypeDecl(ctxt);
4117 }
4118
4119 /*
4120 * First case : a comment
4121 */
4122 if ((CUR == '<') && (NXT(1) == '!') &&
4123 (NXT(2) == '-') && (NXT(3) == '-')) {
4124 docbParseComment(ctxt);
4125 }
4126
4127 /*
4128 * Second case : a PI
4129 */
4130 else if ((RAW == '<') && (NXT(1) == '?')) {
4131 docbParsePI(ctxt);
4132 }
4133
4134 /*
4135 * Third case : a sub-element.
4136 */
4137 else if (CUR == '<') {
4138 docbParseElement(ctxt);
4139 }
4140
4141 /*
4142 * Fourth case : a reference. If if has not been resolved,
4143 * parsing returns it's Name, create the node
4144 */
4145 else if (CUR == '&') {
4146 docbParseReference(ctxt);
4147 }
4148
4149 /*
4150 * Fifth : end of the resource
4151 */
4152 else if (CUR == 0) {
4153 docbAutoClose(ctxt, NULL);
4154 if (ctxt->nameNr == 0)
4155 break;
4156 }
4157
4158 /*
4159 * Last case, text. Note that References are handled directly.
4160 */
4161 else {
4162 docbParseCharData(ctxt);
4163 }
4164
4165 if (cons == ctxt->nbChars) {
4166 if (ctxt->node != NULL) {
4167 if ((ctxt->sax != NULL) && (ctxt->sax->error != NULL))
4168 ctxt->sax->error(ctxt->userData,
4169 "detected an error in element content\n");
4170 ctxt->wellFormed = 0;
4171 }
4172 break;
4173 }
4174
4175 GROW;
4176 }
4177 if (currentNode != NULL)
4178 xmlFree(currentNode);
4179 }
4180
4181 /**
4182 * docbParseElement:
4183 * @ctxt: an SGML parser context
4184 *
4185 * parse an SGML element, this is highly recursive
4186 *
4187 * [39] element ::= EmptyElemTag | STag content ETag
4188 *
4189 * [41] Attribute ::= Name Eq AttValue
4190 */
4191
4192 static void
4193 docbParseElement(docbParserCtxtPtr ctxt) {
4194 xmlChar *name;
4195 xmlChar *currentNode = NULL;
4196 docbElemDescPtr info;
4197 docbParserNodeInfo node_info;
4198 xmlChar *oldname;
4199 int depth = ctxt->nameNr;
4200
4201 /* Capture start position */
4202 if (ctxt->record_info) {
4203 node_info.begin_pos = ctxt->input->consumed +
4204 (CUR_PTR - ctxt->input->base);
4205 node_info.begin_line = ctxt->input->line;
4206 }
4207
4208 oldname = xmlStrdup(ctxt->name);
4209 docbParseStartTag(ctxt);
4210 name = ctxt->name;
4211 #ifdef DEBUG
4212 if (oldname == NULL)
4213 xmlGenericError(xmlGenericErrorContext,
4214 "Start of element %s\n", name);
4215 else if (name == NULL)
4216 xmlGenericError(xmlGenericErrorContext,
4217 "Start of element failed, was %s\n", oldname);
4218 else
4219 xmlGenericError(xmlGenericErrorContext,
4220 "Start of element %s, was %s\n", name, oldname);
4221 #endif
4222 if (((depth == ctxt->nameNr) && (xmlStrEqual(oldname, ctxt->name))) ||
4223 (name == NULL)) {
4224 if (CUR == '>')
4225 NEXT;
4226 if (oldname != NULL)
4227 xmlFree(oldname);
4228 return;
4229 }
4230 if (oldname != NULL)
4231 xmlFree(oldname);
4232
4233 /*
4234 * Lookup the info for that element.
4235 */
4236 info = docbTagLookup(name);
4237 if (info == NULL) {
4238 if ((ctxt->sax != NULL) && (ctxt->sax->error != NULL))
4239 ctxt->sax->error(ctxt->userData, "Tag %s unknown\n",
4240 name);
4241 ctxt->wellFormed = 0;
4242 } else if (info->depr) {
4243 /***************************
4244 if ((ctxt->sax != NULL) && (ctxt->sax->warning != NULL))
4245 ctxt->sax->warning(ctxt->userData, "Tag %s is deprecated\n",
4246 name);
4247 ***************************/
4248 }
4249
4250 /*
4251 * Check for an Empty Element labeled the XML/SGML way
4252 */
4253 if ((CUR == '/') && (NXT(1) == '>')) {
4254 SKIP(2);
4255 if ((ctxt->sax != NULL) && (ctxt->sax->endElement != NULL))
4256 ctxt->sax->endElement(ctxt->userData, name);
4257 oldname = docbnamePop(ctxt);
4258 #ifdef DEBUG
4259 xmlGenericError(xmlGenericErrorContext,"End of tag the XML way: popping out %s\n", oldname);
4260 #endif
4261 if (oldname != NULL)
4262 xmlFree(oldname);
4263 return;
4264 }
4265
4266 if (CUR == '>') {
4267 NEXT;
4268 } else {
4269 if ((ctxt->sax != NULL) && (ctxt->sax->error != NULL))
4270 ctxt->sax->error(ctxt->userData,
4271 "Couldn't find end of Start Tag %s\n",
4272 name);
4273 ctxt->wellFormed = 0;
4274
4275 /*
4276 * end of parsing of this node.
4277 */
4278 if (xmlStrEqual(name, ctxt->name)) {
4279 nodePop(ctxt);
4280 oldname = docbnamePop(ctxt);
4281 #ifdef DEBUG
4282 xmlGenericError(xmlGenericErrorContext,"End of start tag problem: popping out %s\n", oldname);
4283 #endif
4284 if (oldname != NULL)
4285 xmlFree(oldname);
4286 }
4287
4288 /*
4289 * Capture end position and add node
4290 */
4291 if ( currentNode != NULL && ctxt->record_info ) {
4292 node_info.end_pos = ctxt->input->consumed +
4293 (CUR_PTR - ctxt->input->base);
4294 node_info.end_line = ctxt->input->line;
4295 node_info.node = ctxt->node;
4296 xmlParserAddNodeInfo(ctxt, &node_info);
4297 }
4298 return;
4299 }
4300
4301 /*
4302 * Check for an Empty Element from DTD definition
4303 */
4304 if ((info != NULL) && (info->empty)) {
4305 if ((ctxt->sax != NULL) && (ctxt->sax->endElement != NULL))
4306 ctxt->sax->endElement(ctxt->userData, name);
4307 oldname = docbnamePop(ctxt);
4308 #ifdef DEBUG
4309 xmlGenericError(xmlGenericErrorContext,"End of empty tag %s : popping out %s\n", name, oldname);
4310 #endif
4311 if (oldname != NULL)
4312 xmlFree(oldname);
4313 return;
4314 }
4315
4316 /*
4317 * Parse the content of the element:
4318 */
4319 currentNode = xmlStrdup(ctxt->name);
4320 depth = ctxt->nameNr;
4321 while (IS_CHAR(CUR)) {
4322 docbParseContent(ctxt);
4323 if (ctxt->nameNr < depth) break;
4324 }
4325
4326 if (!IS_CHAR(CUR)) {
4327 /************
4328 if ((ctxt->sax != NULL) && (ctxt->sax->error != NULL))
4329 ctxt->sax->error(ctxt->userData,
4330 "Premature end of data in tag %s\n", currentNode);
4331 ctxt->wellFormed = 0;
4332 *************/
4333
4334 /*
4335 * end of parsing of this node.
4336 */
4337 nodePop(ctxt);
4338 oldname = docbnamePop(ctxt);
4339 #ifdef DEBUG
4340 xmlGenericError(xmlGenericErrorContext,"Premature end of tag %s : popping out %s\n", name, oldname);
4341 #endif
4342 if (oldname != NULL)
4343 xmlFree(oldname);
4344 if (currentNode != NULL)
4345 xmlFree(currentNode);
4346 return;
4347 }
4348
4349 /*
4350 * Capture end position and add node
4351 */
4352 if ( currentNode != NULL && ctxt->record_info ) {
4353 node_info.end_pos = ctxt->input->consumed +
4354 (CUR_PTR - ctxt->input->base);
4355 node_info.end_line = ctxt->input->line;
4356 node_info.node = ctxt->node;
4357 xmlParserAddNodeInfo(ctxt, &node_info);
4358 }
4359 if (currentNode != NULL)
4360 xmlFree(currentNode);
4361 }
4362
4363 /**
4364 * docbParseEntityDecl:
4365 * @ctxt: an SGML parser context
4366 *
4367 * parse <!ENTITY declarations
4368 *
4369 */
4370
4371 static void
4372 docbParseEntityDecl(xmlParserCtxtPtr ctxt) {
4373 xmlChar *name = NULL;
4374 xmlChar *value = NULL;
4375 xmlChar *URI = NULL, *literal = NULL;
4376 xmlChar *ndata = NULL;
4377 int isParameter = 0;
4378 xmlChar *orig = NULL;
4379
4380 GROW;
4381 if ((RAW == '<') && (NXT(1) == '!') &&
4382 (UPP(2) == 'E') && (UPP(3) == 'N') &&
4383 (UPP(4) == 'T') && (UPP(5) == 'I') &&
4384 (UPP(6) == 'T') && (UPP(7) == 'Y')) {
4385 xmlParserInputPtr input = ctxt->input;
4386 ctxt->instate = XML_PARSER_ENTITY_DECL;
4387 SHRINK;
4388 SKIP(8);
4389 if (!IS_BLANK(CUR)) {
4390 ctxt->errNo = XML_ERR_SPACE_REQUIRED;
4391 if ((ctxt->sax != NULL) && (ctxt->sax->error != NULL))
4392 ctxt->sax->error(ctxt->userData,
4393 "Space required after '<!ENTITY'\n");
4394 ctxt->wellFormed = 0;
4395 if (ctxt->recovery == 0) ctxt->disableSAX = 1;
4396 }
4397 SKIP_BLANKS;
4398
4399 if (RAW == '%') {
4400 NEXT;
4401 if (!IS_BLANK(CUR)) {
4402 ctxt->errNo = XML_ERR_SPACE_REQUIRED;
4403 if ((ctxt->sax != NULL) && (ctxt->sax->error != NULL))
4404 ctxt->sax->error(ctxt->userData,
4405 "Space required after '%'\n");
4406 ctxt->wellFormed = 0;
4407 if (ctxt->recovery == 0) ctxt->disableSAX = 1;
4408 }
4409 SKIP_BLANKS;
4410 isParameter = 1;
4411 }
4412
4413 name = xmlParseName(ctxt);
4414 if (name == NULL) {
4415 ctxt->errNo = XML_ERR_NAME_REQUIRED;
4416 if ((ctxt->sax != NULL) && (ctxt->sax->error != NULL))
4417 ctxt->sax->error(ctxt->userData, "sgmlarseEntityDecl: no name\n");
4418 ctxt->wellFormed = 0;
4419 if (ctxt->recovery == 0) ctxt->disableSAX = 1;
4420 return;
4421 }
4422 if (!IS_BLANK(CUR)) {
4423 ctxt->errNo = XML_ERR_SPACE_REQUIRED;
4424 if ((ctxt->sax != NULL) && (ctxt->sax->error != NULL))
4425 ctxt->sax->error(ctxt->userData,
4426 "Space required after the entity name\n");
4427 ctxt->wellFormed = 0;
4428 if (ctxt->recovery == 0) ctxt->disableSAX = 1;
4429 }
4430 SKIP_BLANKS;
4431
4432 /*
4433 * handle the various case of definitions...
4434 */
4435 if (isParameter) {
4436 if ((RAW == '"') || (RAW == '\'')) {
4437 value = xmlParseEntityValue(ctxt, &orig);
4438 if (value) {
4439 if ((ctxt->sax != NULL) &&
4440 (!ctxt->disableSAX) && (ctxt->sax->entityDecl != NULL))
4441 ctxt->sax->entityDecl(ctxt->userData, name,
4442 XML_INTERNAL_PARAMETER_ENTITY,
4443 NULL, NULL, value);
4444 }
4445 } else {
4446 URI = xmlParseExternalID(ctxt, &literal, 1);
4447 if ((URI == NULL) && (literal == NULL)) {
4448 ctxt->errNo = XML_ERR_VALUE_REQUIRED;
4449 if ((ctxt->sax != NULL) && (ctxt->sax->error != NULL))
4450 ctxt->sax->error(ctxt->userData,
4451 "Entity value required\n");
4452 ctxt->wellFormed = 0;
4453 if (ctxt->recovery == 0) ctxt->disableSAX = 1;
4454 }
4455 if (URI) {
4456 xmlURIPtr uri;
4457
4458 uri = xmlParseURI((const char *) URI);
4459 if (uri == NULL) {
4460 ctxt->errNo = XML_ERR_INVALID_URI;
4461 if ((ctxt->sax != NULL) &&
4462 (!ctxt->disableSAX) &&
4463 (ctxt->sax->error != NULL))
4464 ctxt->sax->error(ctxt->userData,
4465 "Invalid URI: %s\n", URI);
4466 ctxt->wellFormed = 0;
4467 } else {
4468 if (uri->fragment != NULL) {
4469 ctxt->errNo = XML_ERR_URI_FRAGMENT;
4470 if ((ctxt->sax != NULL) &&
4471 (!ctxt->disableSAX) &&
4472 (ctxt->sax->error != NULL))
4473 ctxt->sax->error(ctxt->userData,
4474 "Fragment not allowed: %s\n", URI);
4475 ctxt->wellFormed = 0;
4476 } else {
4477 if ((ctxt->sax != NULL) &&
4478 (!ctxt->disableSAX) &&
4479 (ctxt->sax->entityDecl != NULL))
4480 ctxt->sax->entityDecl(ctxt->userData, name,
4481 XML_EXTERNAL_PARAMETER_ENTITY,
4482 literal, URI, NULL);
4483 }
4484 xmlFreeURI(uri);
4485 }
4486 }
4487 }
4488 } else {
4489 if ((RAW == '"') || (RAW == '\'')) {
4490 value = xmlParseEntityValue(ctxt, &orig);
4491 if ((ctxt->sax != NULL) &&
4492 (!ctxt->disableSAX) && (ctxt->sax->entityDecl != NULL))
4493 ctxt->sax->entityDecl(ctxt->userData, name,
4494 XML_INTERNAL_GENERAL_ENTITY,
4495 NULL, NULL, value);
4496 } else {
4497 URI = xmlParseExternalID(ctxt, &literal, 1);
4498 if ((URI == NULL) && (literal == NULL)) {
4499 ctxt->errNo = XML_ERR_VALUE_REQUIRED;
4500 if ((ctxt->sax != NULL) && (ctxt->sax->error != NULL))
4501 ctxt->sax->error(ctxt->userData,
4502 "Entity value required\n");
4503 ctxt->wellFormed = 0;
4504 if (ctxt->recovery == 0) ctxt->disableSAX = 1;
4505 }
4506 if (URI) {
4507 xmlURIPtr uri;
4508
4509 uri = xmlParseURI((const char *)URI);
4510 if (uri == NULL) {
4511 ctxt->errNo = XML_ERR_INVALID_URI;
4512 if ((ctxt->sax != NULL) &&
4513 (!ctxt->disableSAX) &&
4514 (ctxt->sax->error != NULL))
4515 ctxt->sax->error(ctxt->userData,
4516 "Invalid URI: %s\n", URI);
4517 ctxt->wellFormed = 0;
4518 } else {
4519 if (uri->fragment != NULL) {
4520 ctxt->errNo = XML_ERR_URI_FRAGMENT;
4521 if ((ctxt->sax != NULL) &&
4522 (!ctxt->disableSAX) &&
4523 (ctxt->sax->error != NULL))
4524 ctxt->sax->error(ctxt->userData,
4525 "Fragment not allowed: %s\n", URI);
4526 ctxt->wellFormed = 0;
4527 }
4528 xmlFreeURI(uri);
4529 }
4530 }
4531 if ((RAW != '>') && (!IS_BLANK(CUR))) {
4532 ctxt->errNo = XML_ERR_SPACE_REQUIRED;
4533 if ((ctxt->sax != NULL) && (ctxt->sax->error != NULL))
4534 ctxt->sax->error(ctxt->userData,
4535 "Space required before content model\n");
4536 ctxt->wellFormed = 0;
4537 if (ctxt->recovery == 0) ctxt->disableSAX = 1;
4538 }
4539 SKIP_BLANKS;
4540
4541 /*
4542 * SGML specific: here we can get the content model
4543 */
4544 if (RAW != '>') {
4545 xmlChar *contmod;
4546
4547 contmod = xmlParseName(ctxt);
4548
4549 if (contmod == NULL) {
4550 ctxt->errNo = XML_ERR_SPACE_REQUIRED;
4551 if ((ctxt->sax != NULL) && (ctxt->sax->error != NULL))
4552 ctxt->sax->error(ctxt->userData,
4553 "Could not parse entity content model\n");
4554 ctxt->wellFormed = 0;
4555 if (ctxt->recovery == 0) ctxt->disableSAX = 1;
4556 } else {
4557 if (xmlStrEqual(contmod, BAD_CAST"NDATA")) {
4558 if (!IS_BLANK(CUR)) {
4559 ctxt->errNo = XML_ERR_SPACE_REQUIRED;
4560 if ((ctxt->sax != NULL) &&
4561 (ctxt->sax->error != NULL))
4562 ctxt->sax->error(ctxt->userData,
4563 "Space required after 'NDATA'\n");
4564 ctxt->wellFormed = 0;
4565 if (ctxt->recovery == 0) ctxt->disableSAX = 1;
4566 }
4567 SKIP_BLANKS;
4568 ndata = xmlParseName(ctxt);
4569 if ((ctxt->sax != NULL) && (!ctxt->disableSAX) &&
4570 (ctxt->sax->unparsedEntityDecl != NULL)) {
4571 ctxt->sax->unparsedEntityDecl(ctxt->userData,
4572 name, literal, URI, ndata);
4573 }
4574 } else if (xmlStrEqual(contmod, BAD_CAST"SUBDOC")) {
4575 if ((ctxt->sax != NULL) &&
4576 (ctxt->sax->warning != NULL))
4577 ctxt->sax->warning(ctxt->userData,
4578 "SUBDOC entities are not supported\n");
4579 SKIP_BLANKS;
4580 ndata = xmlParseName(ctxt);
4581 if ((ctxt->sax != NULL) && (!ctxt->disableSAX) &&
4582 (ctxt->sax->unparsedEntityDecl != NULL)) {
4583 ctxt->sax->unparsedEntityDecl(ctxt->userData,
4584 name, literal, URI, ndata);
4585 }
4586 } else if (xmlStrEqual(contmod, BAD_CAST"CDATA")) {
4587 if ((ctxt->sax != NULL) &&
4588 (ctxt->sax->warning != NULL))
4589 ctxt->sax->warning(ctxt->userData,
4590 "CDATA entities are not supported\n");
4591 SKIP_BLANKS;
4592 ndata = xmlParseName(ctxt);
4593 if ((ctxt->sax != NULL) && (!ctxt->disableSAX) &&
4594 (ctxt->sax->unparsedEntityDecl != NULL)) {
4595 ctxt->sax->unparsedEntityDecl(ctxt->userData,
4596 name, literal, URI, ndata);
4597 }
4598 }
4599 xmlFree(contmod);
4600 }
4601 } else {
4602 if ((ctxt->sax != NULL) &&
4603 (!ctxt->disableSAX) && (ctxt->sax->entityDecl != NULL))
4604 ctxt->sax->entityDecl(ctxt->userData, name,
4605 XML_EXTERNAL_GENERAL_PARSED_ENTITY,
4606 literal, URI, NULL);
4607 }
4608 }
4609 }
4610 SKIP_BLANKS;
4611 if (RAW != '>') {
4612 ctxt->errNo = XML_ERR_ENTITY_NOT_FINISHED;
4613 if ((ctxt->sax != NULL) && (ctxt->sax->error != NULL))
4614 ctxt->sax->error(ctxt->userData,
4615 "docbParseEntityDecl: entity %s not terminated\n", name);
4616 ctxt->wellFormed = 0;
4617 if (ctxt->recovery == 0) ctxt->disableSAX = 1;
4618 } else {
4619 if (input != ctxt->input) {
4620 ctxt->errNo = XML_ERR_ENTITY_BOUNDARY;
4621 if ((ctxt->sax != NULL) && (ctxt->sax->error != NULL))
4622 ctxt->sax->error(ctxt->userData,
4623 "Entity declaration doesn't start and stop in the same entity\n");
4624 ctxt->wellFormed = 0;
4625 if (ctxt->recovery == 0) ctxt->disableSAX = 1;
4626 }
4627 NEXT;
4628 }
4629 if (orig != NULL) {
4630 /*
4631 * Ugly mechanism to save the raw entity value.
4632 */
4633 xmlEntityPtr cur = NULL;
4634
4635 if (isParameter) {
4636 if ((ctxt->sax != NULL) &&
4637 (ctxt->sax->getParameterEntity != NULL))
4638 cur = ctxt->sax->getParameterEntity(ctxt->userData, name);
4639 } else {
4640 if ((ctxt->sax != NULL) &&
4641 (ctxt->sax->getEntity != NULL))
4642 cur = ctxt->sax->getEntity(ctxt->userData, name);
4643 }
4644 if (cur != NULL) {
4645 if (cur->orig != NULL)
4646 xmlFree(orig);
4647 else
4648 cur->orig = orig;
4649 } else
4650 xmlFree(orig);
4651 }
4652 if (name != NULL) xmlFree(name);
4653 if (value != NULL) xmlFree(value);
4654 if (URI != NULL) xmlFree(URI);
4655 if (literal != NULL) xmlFree(literal);
4656 if (ndata != NULL) xmlFree(ndata);
4657 }
4658 }
4659
4660 /**
4661 * docbParseMarkupDecl:
4662 * @ctxt: an SGML parser context
4663 *
4664 * parse Markup declarations
4665 *
4666 * [29] markupdecl ::= elementdecl | AttlistDecl | EntityDecl |
4667 * NotationDecl | PI | Comment
4668 */
4669 static void
4670 docbParseMarkupDecl(xmlParserCtxtPtr ctxt) {
4671 GROW;
4672 xmlParseElementDecl(ctxt);
4673 xmlParseAttributeListDecl(ctxt);
4674 docbParseEntityDecl(ctxt);
4675 xmlParseNotationDecl(ctxt);
4676 docbParsePI(ctxt);
4677 xmlParseComment(ctxt);
4678 /*
4679 * This is only for internal subset. On external entities,
4680 * the replacement is done before parsing stage
4681 */
4682 if ((ctxt->external == 0) && (ctxt->inputNr == 1))
4683 xmlParsePEReference(ctxt);
4684 ctxt->instate = XML_PARSER_DTD;
4685 }
4686
4687 /**
4688 * docbParseInternalSubset:
4689 * @ctxt: an SGML parser context
4690 *
4691 * parse the internal subset declaration
4692 *
4693 * [28 end] ('[' (markupdecl | PEReference | S)* ']' S?)? '>'
4694 */
4695
4696 static void
4697 docbParseInternalSubset(xmlParserCtxtPtr ctxt) {
4698 /*
4699 * Is there any DTD definition ?
4700 */
4701 if (RAW == '[') {
4702 ctxt->instate = XML_PARSER_DTD;
4703 NEXT;
4704 /*
4705 * Parse the succession of Markup declarations and
4706 * PEReferences.
4707 * Subsequence (markupdecl | PEReference | S)*
4708 */
4709 while (RAW != ']') {
4710 const xmlChar *check = CUR_PTR;
4711 int cons = ctxt->input->consumed;
4712
4713 SKIP_BLANKS;
4714 docbParseMarkupDecl(ctxt);
4715 xmlParsePEReference(ctxt);
4716
4717 /*
4718 * Pop-up of finished entities.
4719 */
4720 while ((RAW == 0) && (ctxt->inputNr > 1))
4721 xmlPopInput(ctxt);
4722
4723 if ((CUR_PTR == check) && (cons == ctxt->input->consumed)) {
4724 ctxt->errNo = XML_ERR_INTERNAL_ERROR;
4725 if ((ctxt->sax != NULL) && (ctxt->sax->error != NULL))
4726 ctxt->sax->error(ctxt->userData,
4727 "docbParseInternalSubset: error detected in Markup declaration\n");
4728 ctxt->wellFormed = 0;
4729 if (ctxt->recovery == 0) ctxt->disableSAX = 1;
4730 break;
4731 }
4732 }
4733 if (RAW == ']') {
4734 NEXT;
4735 SKIP_BLANKS;
4736 }
4737 }
4738
4739 /*
4740 * We should be at the end of the DOCTYPE declaration.
4741 */
4742 if (RAW != '>') {
4743 ctxt->errNo = XML_ERR_DOCTYPE_NOT_FINISHED;
4744 if ((ctxt->sax != NULL) && (ctxt->sax->error != NULL))
4745 ctxt->sax->error(ctxt->userData, "DOCTYPE improperly terminated\n");
4746 ctxt->wellFormed = 0;
4747 if (ctxt->recovery == 0) ctxt->disableSAX = 1;
4748 }
4749 NEXT;
4750 }
4751
4752 /**
4753 * docbParseMisc:
4754 * @ctxt: an XML parser context
4755 *
4756 * parse an XML Misc* optional field.
4757 *
4758 * [27] Misc ::= Comment | PI | S
4759 */
4760
4761 static void
4762 docbParseMisc(xmlParserCtxtPtr ctxt) {
4763 while (((RAW == '<') && (NXT(1) == '?')) ||
4764 ((RAW == '<') && (NXT(1) == '!') &&
4765 (NXT(2) == '-') && (NXT(3) == '-')) ||
4766 IS_BLANK(CUR)) {
4767 if ((RAW == '<') && (NXT(1) == '?')) {
4768 docbParsePI(ctxt);
4769 } else if (IS_BLANK(CUR)) {
4770 NEXT;
4771 } else
4772 xmlParseComment(ctxt);
4773 }
4774 }
4775
4776 /**
4777 * docbParseDocument :
4778 * @ctxt: an SGML parser context
4779 *
4780 * parse an SGML document (and build a tree if using the standard SAX
4781 * interface).
4782 *
4783 * Returns 0, -1 in case of error. the parser context is augmented
4784 * as a result of the parsing.
4785 */
4786
4787 int
4788 docbParseDocument(docbParserCtxtPtr ctxt) {
4789 xmlChar start[4];
4790 xmlCharEncoding enc;
4791 xmlDtdPtr dtd;
4792
4793 docbDefaultSAXHandlerInit();
4794 ctxt->html = 2;
4795
4796 GROW;
4797 /*
4798 * SAX: beginning of the document processing.
4799 */
4800 if ((ctxt->sax) && (ctxt->sax->setDocumentLocator))
4801 ctxt->sax->setDocumentLocator(ctxt->userData, &xmlDefaultSAXLocator);
4802
4803 /*
4804 * Get the 4 first bytes and decode the charset
4805 * if enc != XML_CHAR_ENCODING_NONE
4806 * plug some encoding conversion routines.
4807 */
4808 start[0] = RAW;
4809 start[1] = NXT(1);
4810 start[2] = NXT(2);
4811 start[3] = NXT(3);
4812 enc = xmlDetectCharEncoding(start, 4);
4813 if (enc != XML_CHAR_ENCODING_NONE) {
4814 xmlSwitchEncoding(ctxt, enc);
4815 }
4816
4817 /*
4818 * Wipe out everything which is before the first '<'
4819 */
4820 SKIP_BLANKS;
4821 if (CUR == 0) {
4822 if ((ctxt->sax != NULL) && (ctxt->sax->error != NULL))
4823 ctxt->sax->error(ctxt->userData, "Document is empty\n");
4824 ctxt->wellFormed = 0;
4825 }
4826
4827 if ((ctxt->sax) && (ctxt->sax->startDocument) && (!ctxt->disableSAX))
4828 ctxt->sax->startDocument(ctxt->userData);
4829
4830
4831 /*
4832 * The Misc part of the Prolog
4833 */
4834 GROW;
4835 docbParseMisc(ctxt);
4836
4837 /*
4838 * Then possibly doc type declaration(s) and more Misc
4839 * (doctypedecl Misc*)?
4840 */
4841 GROW;
4842 if ((RAW == '<') && (NXT(1) == '!') &&
4843 (UPP(2) == 'D') && (UPP(3) == 'O') &&
4844 (UPP(4) == 'C') && (UPP(5) == 'T') &&
4845 (UPP(6) == 'Y') && (UPP(7) == 'P') &&
4846 (UPP(8) == 'E')) {
4847
4848 ctxt->inSubset = 1;
4849 docbParseDocTypeDecl(ctxt);
4850 if (RAW == '[') {
4851 ctxt->instate = XML_PARSER_DTD;
4852 docbParseInternalSubset(ctxt);
4853 }
4854
4855 /*
4856 * Create and update the external subset.
4857 */
4858 ctxt->inSubset = 2;
4859 if ((ctxt->sax != NULL) && (ctxt->sax->internalSubset != NULL) &&
4860 (!ctxt->disableSAX))
4861 ctxt->sax->internalSubset(ctxt->userData, ctxt->intSubName,
4862 ctxt->extSubSystem, ctxt->extSubURI);
4863 ctxt->inSubset = 0;
4864
4865
4866 ctxt->instate = XML_PARSER_PROLOG;
4867 docbParseMisc(ctxt);
4868 }
4869
4870 /*
4871 * Time to start parsing the tree itself
4872 */
4873 docbParseContent(ctxt);
4874
4875 /*
4876 * autoclose
4877 */
4878 if (CUR == 0)
4879 docbAutoClose(ctxt, NULL);
4880
4881
4882 /*
4883 * SAX: end of the document processing.
4884 */
4885 if ((ctxt->sax) && (ctxt->sax->endDocument != NULL))
4886 ctxt->sax->endDocument(ctxt->userData);
4887
4888 if (ctxt->myDoc != NULL) {
4889 dtd = ctxt->myDoc->intSubset;
4890 ctxt->myDoc->standalone = -1;
4891 if (dtd == NULL)
4892 ctxt->myDoc->intSubset =
4893 xmlCreateIntSubset(ctxt->myDoc, BAD_CAST "SGML",
4894 BAD_CAST "-//W3C//DTD SGML 4.0 Transitional//EN",
4895 BAD_CAST "http://www.w3.org/TR/REC-docbook/loose.dtd");
4896 }
4897 if (! ctxt->wellFormed) return(-1);
4898 return(0);
4899 }
4900
4901
4902 /************************************************************************
4903 * *
4904 * Parser contexts handling *
4905 * *
4906 ************************************************************************/
4907
4908 /**
4909 * docbInitParserCtxt:
4910 * @ctxt: an SGML parser context
4911 *
4912 * Initialize a parser context
4913 */
4914
4915 static void
4916 docbInitParserCtxt(docbParserCtxtPtr ctxt)
4917 {
4918 docbSAXHandler *sax;
4919
4920 if (ctxt == NULL) return;
4921 memset(ctxt, 0, sizeof(docbParserCtxt));
4922
4923 sax = (docbSAXHandler *) xmlMalloc(sizeof(docbSAXHandler));
4924 if (sax == NULL) {
4925 xmlGenericError(xmlGenericErrorContext,
4926 "docbInitParserCtxt: out of memory\n");
4927 }
4928 memset(sax, 0, sizeof(docbSAXHandler));
4929
4930 /* Allocate the Input stack */
4931 ctxt->inputTab = (docbParserInputPtr *)
4932 xmlMalloc(5 * sizeof(docbParserInputPtr));
4933 if (ctxt->inputTab == NULL) {
4934 xmlGenericError(xmlGenericErrorContext,
4935 "docbInitParserCtxt: out of memory\n");
4936 }
4937 ctxt->inputNr = 0;
4938 ctxt->inputMax = 5;
4939 ctxt->input = NULL;
4940 ctxt->version = NULL;
4941 ctxt->encoding = NULL;
4942 ctxt->standalone = -1;
4943 ctxt->instate = XML_PARSER_START;
4944
4945 /* Allocate the Node stack */
4946 ctxt->nodeTab = (docbNodePtr *) xmlMalloc(10 * sizeof(docbNodePtr));
4947 ctxt->nodeNr = 0;
4948 ctxt->nodeMax = 10;
4949 ctxt->node = NULL;
4950
4951 /* Allocate the Name stack */
4952 ctxt->nameTab = (xmlChar **) xmlMalloc(10 * sizeof(xmlChar *));
4953 ctxt->nameNr = 0;
4954 ctxt->nameMax = 10;
4955 ctxt->name = NULL;
4956
4957 if (sax == NULL) ctxt->sax = &docbDefaultSAXHandler;
4958 else {
4959 ctxt->sax = sax;
4960 memcpy(sax, &docbDefaultSAXHandler, sizeof(docbSAXHandler));
4961 }
4962 ctxt->userData = ctxt;
4963 ctxt->myDoc = NULL;
4964 ctxt->wellFormed = 1;
4965 ctxt->linenumbers = xmlLineNumbersDefaultValue;
4966 ctxt->replaceEntities = xmlSubstituteEntitiesDefaultValue;
4967 ctxt->html = 2;
4968 ctxt->record_info = 0;
4969 ctxt->validate = 0;
4970 ctxt->nbChars = 0;
4971 ctxt->checkIndex = 0;
4972 xmlInitNodeInfoSeq(&ctxt->node_seq);
4973 }
4974
4975 /**
4976 * docbFreeParserCtxt:
4977 * @ctxt: an SGML parser context
4978 *
4979 * Free all the memory used by a parser context. However the parsed
4980 * document in ctxt->myDoc is not freed.
4981 */
4982
4983 void
4984 docbFreeParserCtxt(docbParserCtxtPtr ctxt)
4985 {
4986 xmlFreeParserCtxt(ctxt);
4987 }
4988
4989 /**
4990 * docbCreateDocParserCtxt :
4991 * @cur: a pointer to an array of xmlChar
4992 * @encoding: the SGML document encoding, or NULL
4993 *
4994 * Create a parser context for an SGML document.
4995 *
4996 * Returns the new parser context or NULL
4997 */
4998 static docbParserCtxtPtr
4999 docbCreateDocParserCtxt(xmlChar *cur, const char *encoding ATTRIBUTE_UNUSED) {
5000 docbParserCtxtPtr ctxt;
5001 docbParserInputPtr input;
5002 /* sgmlCharEncoding enc; */
5003
5004 ctxt = (docbParserCtxtPtr) xmlMalloc(sizeof(docbParserCtxt));
5005 if (ctxt == NULL) {
5006 xmlGenericError(xmlGenericErrorContext, "malloc failed");
5007 return(NULL);
5008 }
5009 docbInitParserCtxt(ctxt);
5010 input = (docbParserInputPtr) xmlMalloc(sizeof(docbParserInput));
5011 if (input == NULL) {
5012 xmlGenericError(xmlGenericErrorContext, "malloc failed");
5013 xmlFree(ctxt);
5014 return(NULL);
5015 }
5016 memset(input, 0, sizeof(docbParserInput));
5017
5018 input->line = 1;
5019 input->col = 1;
5020 input->base = cur;
5021 input->cur = cur;
5022
5023 inputPush(ctxt, input);
5024 return(ctxt);
5025 }
5026
5027 /************************************************************************
5028 * *
5029 * Progressive parsing interfaces *
5030 * *
5031 ************************************************************************/
5032
5033 /**
5034 * docbParseLookupSequence:
5035 * @ctxt: an SGML parser context
5036 * @first: the first char to lookup
5037 * @next: the next char to lookup or zero
5038 * @third: the next char to lookup or zero
5039 *
5040 * Try to find if a sequence (first, next, third) or just (first next) or
5041 * (first) is available in the input stream.
5042 * This function has a side effect of (possibly) incrementing ctxt->checkIndex
5043 * to avoid rescanning sequences of bytes, it DOES change the state of the
5044 * parser, do not use liberally.
5045 * This is basically similar to xmlParseLookupSequence()
5046 *
5047 * Returns the index to the current parsing point if the full sequence
5048 * is available, -1 otherwise.
5049 */
5050 static int
5051 docbParseLookupSequence(docbParserCtxtPtr ctxt, xmlChar first,
5052 xmlChar next, xmlChar third) {
5053 int base, len;
5054 docbParserInputPtr in;
5055 const xmlChar *buf;
5056
5057 in = ctxt->input;
5058 if (in == NULL) return(-1);
5059 base = in->cur - in->base;
5060 if (base < 0) return(-1);
5061 if (ctxt->checkIndex > base)
5062 base = ctxt->checkIndex;
5063 if (in->buf == NULL) {
5064 buf = in->base;
5065 len = in->length;
5066 } else {
5067 buf = in->buf->buffer->content;
5068 len = in->buf->buffer->use;
5069 }
5070 /* take into account the sequence length */
5071 if (third) len -= 2;
5072 else if (next) len --;
5073 for (;base < len;base++) {
5074 if (buf[base] == first) {
5075 if (third != 0) {
5076 if ((buf[base + 1] != next) ||
5077 (buf[base + 2] != third)) continue;
5078 } else if (next != 0) {
5079 if (buf[base + 1] != next) continue;
5080 }
5081 ctxt->checkIndex = 0;
5082 #ifdef DEBUG_PUSH
5083 if (next == 0)
5084 xmlGenericError(xmlGenericErrorContext,
5085 "HPP: lookup '%c' found at %d\n",
5086 first, base);
5087 else if (third == 0)
5088 xmlGenericError(xmlGenericErrorContext,
5089 "HPP: lookup '%c%c' found at %d\n",
5090 first, next, base);
5091 else
5092 xmlGenericError(xmlGenericErrorContext,
5093 "HPP: lookup '%c%c%c' found at %d\n",
5094 first, next, third, base);
5095 #endif
5096 return(base - (in->cur - in->base));
5097 }
5098 }
5099 ctxt->checkIndex = base;
5100 #ifdef DEBUG_PUSH
5101 if (next == 0)
5102 xmlGenericError(xmlGenericErrorContext,
5103 "HPP: lookup '%c' failed\n", first);
5104 else if (third == 0)
5105 xmlGenericError(xmlGenericErrorContext,
5106 "HPP: lookup '%c%c' failed\n", first, next);
5107 else
5108 xmlGenericError(xmlGenericErrorContext,
5109 "HPP: lookup '%c%c%c' failed\n", first, next, third);
5110 #endif
5111 return(-1);
5112 }
5113
5114 /**
5115 * docbParseTryOrFinish:
5116 * @ctxt: an SGML parser context
5117 * @terminate: last chunk indicator
5118 *
5119 * Try to progress on parsing
5120 *
5121 * Returns zero if no parsing was possible
5122 */
5123 static int
5124 docbParseTryOrFinish(docbParserCtxtPtr ctxt, int terminate) {
5125 int ret = 0;
5126 docbParserInputPtr in;
5127 int avail = 0;
5128 xmlChar cur, next;
5129
5130 #ifdef DEBUG_PUSH
5131 switch (ctxt->instate) {
5132 case XML_PARSER_EOF:
5133 xmlGenericError(xmlGenericErrorContext,
5134 "HPP: try EOF\n"); break;
5135 case XML_PARSER_START:
5136 xmlGenericError(xmlGenericErrorContext,
5137 "HPP: try START\n"); break;
5138 case XML_PARSER_MISC:
5139 xmlGenericError(xmlGenericErrorContext,
5140 "HPP: try MISC\n");break;
5141 case XML_PARSER_COMMENT:
5142 xmlGenericError(xmlGenericErrorContext,
5143 "HPP: try COMMENT\n");break;
5144 case XML_PARSER_PROLOG:
5145 xmlGenericError(xmlGenericErrorContext,
5146 "HPP: try PROLOG\n");break;
5147 case XML_PARSER_START_TAG:
5148 xmlGenericError(xmlGenericErrorContext,
5149 "HPP: try START_TAG\n");break;
5150 case XML_PARSER_CONTENT:
5151 xmlGenericError(xmlGenericErrorContext,
5152 "HPP: try CONTENT\n");break;
5153 case XML_PARSER_CDATA_SECTION:
5154 xmlGenericError(xmlGenericErrorContext,
5155 "HPP: try CDATA_SECTION\n");break;
5156 case XML_PARSER_END_TAG:
5157 xmlGenericError(xmlGenericErrorContext,
5158 "HPP: try END_TAG\n");break;
5159 case XML_PARSER_ENTITY_DECL:
5160 xmlGenericError(xmlGenericErrorContext,
5161 "HPP: try ENTITY_DECL\n");break;
5162 case XML_PARSER_ENTITY_VALUE:
5163 xmlGenericError(xmlGenericErrorContext,
5164 "HPP: try ENTITY_VALUE\n");break;
5165 case XML_PARSER_ATTRIBUTE_VALUE:
5166 xmlGenericError(xmlGenericErrorContext,
5167 "HPP: try ATTRIBUTE_VALUE\n");break;
5168 case XML_PARSER_DTD:
5169 xmlGenericError(xmlGenericErrorContext,
5170 "HPP: try DTD\n");break;
5171 case XML_PARSER_EPILOG:
5172 xmlGenericError(xmlGenericErrorContext,
5173 "HPP: try EPILOG\n");break;
5174 case XML_PARSER_PI:
5175 xmlGenericError(xmlGenericErrorContext,
5176 "HPP: try PI\n");break;
5177 }
5178 #endif
5179
5180 while (1) {
5181
5182 in = ctxt->input;
5183 if (in == NULL) break;
5184 if (in->buf == NULL)
5185 avail = in->length - (in->cur - in->base);
5186 else
5187 avail = in->buf->buffer->use - (in->cur - in->base);
5188 if ((avail == 0) && (terminate)) {
5189 docbAutoClose(ctxt, NULL);
5190 if ((ctxt->nameNr == 0) && (ctxt->instate != XML_PARSER_EOF)) {
5191 /*
5192 * SAX: end of the document processing.
5193 */
5194 ctxt->instate = XML_PARSER_EOF;
5195 if ((ctxt->sax) && (ctxt->sax->endDocument != NULL))
5196 ctxt->sax->endDocument(ctxt->userData);
5197 }
5198 }
5199 if (avail < 1)
5200 goto done;
5201 switch (ctxt->instate) {
5202 case XML_PARSER_EOF:
5203 /*
5204 * Document parsing is done !
5205 */
5206 goto done;
5207 case XML_PARSER_START:
5208 /*
5209 * Very first chars read from the document flow.
5210 */
5211 cur = in->cur[0];
5212 if (IS_BLANK(cur)) {
5213 SKIP_BLANKS;
5214 if (in->buf == NULL)
5215 avail = in->length - (in->cur - in->base);
5216 else
5217 avail = in->buf->buffer->use - (in->cur - in->base);
5218 }
5219 if ((ctxt->sax) && (ctxt->sax->setDocumentLocator))
5220 ctxt->sax->setDocumentLocator(ctxt->userData,
5221 &xmlDefaultSAXLocator);
5222 if ((ctxt->sax) && (ctxt->sax->startDocument) &&
5223 (!ctxt->disableSAX))
5224 ctxt->sax->startDocument(ctxt->userData);
5225
5226 cur = in->cur[0];
5227 next = in->cur[1];
5228 if ((cur == '<') && (next == '!') &&
5229 (UPP(2) == 'D') && (UPP(3) == 'O') &&
5230 (UPP(4) == 'C') && (UPP(5) == 'T') &&
5231 (UPP(6) == 'Y') && (UPP(7) == 'P') &&
5232 (UPP(8) == 'E')) {
5233 if ((!terminate) &&
5234 (docbParseLookupSequence(ctxt, '>', 0, 0) < 0))
5235 goto done;
5236 #ifdef DEBUG_PUSH
5237 xmlGenericError(xmlGenericErrorContext,
5238 "HPP: Parsing internal subset\n");
5239 #endif
5240 docbParseDocTypeDecl(ctxt);
5241 ctxt->instate = XML_PARSER_PROLOG;
5242 #ifdef DEBUG_PUSH
5243 xmlGenericError(xmlGenericErrorContext,
5244 "HPP: entering PROLOG\n");
5245 #endif
5246 } else {
5247 ctxt->instate = XML_PARSER_MISC;
5248 }
5249 #ifdef DEBUG_PUSH
5250 xmlGenericError(xmlGenericErrorContext,
5251 "HPP: entering MISC\n");
5252 #endif
5253 break;
5254 case XML_PARSER_MISC:
5255 SKIP_BLANKS;
5256 if (in->buf == NULL)
5257 avail = in->length - (in->cur - in->base);
5258 else
5259 avail = in->buf->buffer->use - (in->cur - in->base);
5260 if (avail < 2)
5261 goto done;
5262 cur = in->cur[0];
5263 next = in->cur[1];
5264 if ((cur == '<') && (next == '!') &&
5265 (in->cur[2] == '-') && (in->cur[3] == '-')) {
5266 if ((!terminate) &&
5267 (docbParseLookupSequence(ctxt, '-', '-', '>') < 0))
5268 goto done;
5269 #ifdef DEBUG_PUSH
5270 xmlGenericError(xmlGenericErrorContext,
5271 "HPP: Parsing Comment\n");
5272 #endif
5273 docbParseComment(ctxt);
5274 ctxt->instate = XML_PARSER_MISC;
5275 } else if ((cur == '<') && (next == '!') &&
5276 (UPP(2) == 'D') && (UPP(3) == 'O') &&
5277 (UPP(4) == 'C') && (UPP(5) == 'T') &&
5278 (UPP(6) == 'Y') && (UPP(7) == 'P') &&
5279 (UPP(8) == 'E')) {
5280 if ((!terminate) &&
5281 (docbParseLookupSequence(ctxt, '>', 0, 0) < 0))
5282 goto done;
5283 #ifdef DEBUG_PUSH
5284 xmlGenericError(xmlGenericErrorContext,
5285 "HPP: Parsing internal subset\n");
5286 #endif
5287 docbParseDocTypeDecl(ctxt);
5288 ctxt->instate = XML_PARSER_PROLOG;
5289 #ifdef DEBUG_PUSH
5290 xmlGenericError(xmlGenericErrorContext,
5291 "HPP: entering PROLOG\n");
5292 #endif
5293 } else if ((cur == '<') && (next == '!') &&
5294 (avail < 9)) {
5295 goto done;
5296 } else {
5297 ctxt->instate = XML_PARSER_START_TAG;
5298 #ifdef DEBUG_PUSH
5299 xmlGenericError(xmlGenericErrorContext,
5300 "HPP: entering START_TAG\n");
5301 #endif
5302 }
5303 break;
5304 case XML_PARSER_PROLOG:
5305 SKIP_BLANKS;
5306 if (in->buf == NULL)
5307 avail = in->length - (in->cur - in->base);
5308 else
5309 avail = in->buf->buffer->use - (in->cur - in->base);
5310 if (avail < 2)
5311 goto done;
5312 cur = in->cur[0];
5313 next = in->cur[1];
5314 if ((cur == '<') && (next == '!') &&
5315 (in->cur[2] == '-') && (in->cur[3] == '-')) {
5316 if ((!terminate) &&
5317 (docbParseLookupSequence(ctxt, '-', '-', '>') < 0))
5318 goto done;
5319 #ifdef DEBUG_PUSH
5320 xmlGenericError(xmlGenericErrorContext,
5321 "HPP: Parsing Comment\n");
5322 #endif
5323 docbParseComment(ctxt);
5324 ctxt->instate = XML_PARSER_PROLOG;
5325 } else if ((cur == '<') && (next == '!') &&
5326 (avail < 4)) {
5327 goto done;
5328 } else {
5329 ctxt->instate = XML_PARSER_START_TAG;
5330 #ifdef DEBUG_PUSH
5331 xmlGenericError(xmlGenericErrorContext,
5332 "HPP: entering START_TAG\n");
5333 #endif
5334 }
5335 break;
5336 case XML_PARSER_EPILOG:
5337 if (in->buf == NULL)
5338 avail = in->length - (in->cur - in->base);
5339 else
5340 avail = in->buf->buffer->use - (in->cur - in->base);
5341 if (avail < 1)
5342 goto done;
5343 cur = in->cur[0];
5344 if (IS_BLANK(cur)) {
5345 docbParseCharData(ctxt);
5346 goto done;
5347 }
5348 if (avail < 2)
5349 goto done;
5350 next = in->cur[1];
5351 if ((cur == '<') && (next == '!') &&
5352 (in->cur[2] == '-') && (in->cur[3] == '-')) {
5353 if ((!terminate) &&
5354 (docbParseLookupSequence(ctxt, '-', '-', '>') < 0))
5355 goto done;
5356 #ifdef DEBUG_PUSH
5357 xmlGenericError(xmlGenericErrorContext,
5358 "HPP: Parsing Comment\n");
5359 #endif
5360 docbParseComment(ctxt);
5361 ctxt->instate = XML_PARSER_EPILOG;
5362 } else if ((cur == '<') && (next == '!') &&
5363 (avail < 4)) {
5364 goto done;
5365 } else {
5366 ctxt->errNo = XML_ERR_DOCUMENT_END;
5367 if ((ctxt->sax != NULL) && (ctxt->sax->error != NULL))
5368 ctxt->sax->error(ctxt->userData,
5369 "Extra content at the end of the document\n");
5370 ctxt->wellFormed = 0;
5371 ctxt->instate = XML_PARSER_EOF;
5372 #ifdef DEBUG_PUSH
5373 xmlGenericError(xmlGenericErrorContext,
5374 "HPP: entering EOF\n");
5375 #endif
5376 if ((ctxt->sax) && (ctxt->sax->endDocument != NULL))
5377 ctxt->sax->endDocument(ctxt->userData);
5378 goto done;
5379 }
5380 break;
5381 case XML_PARSER_START_TAG: {
5382 xmlChar *name, *oldname;
5383 int depth = ctxt->nameNr;
5384 docbElemDescPtr info;
5385
5386 if (avail < 2)
5387 goto done;
5388 cur = in->cur[0];
5389 if (cur != '<') {
5390 ctxt->instate = XML_PARSER_CONTENT;
5391 #ifdef DEBUG_PUSH
5392 xmlGenericError(xmlGenericErrorContext,
5393 "HPP: entering CONTENT\n");
5394 #endif
5395 break;
5396 }
5397 if ((!terminate) &&
5398 (docbParseLookupSequence(ctxt, '>', 0, 0) < 0))
5399 goto done;
5400
5401 oldname = xmlStrdup(ctxt->name);
5402 docbParseStartTag(ctxt);
5403 name = ctxt->name;
5404 #ifdef DEBUG
5405 if (oldname == NULL)
5406 xmlGenericError(xmlGenericErrorContext,
5407 "Start of element %s\n", name);
5408 else if (name == NULL)
5409 xmlGenericError(xmlGenericErrorContext,
5410 "Start of element failed, was %s\n",
5411 oldname);
5412 else
5413 xmlGenericError(xmlGenericErrorContext,
5414 "Start of element %s, was %s\n",
5415 name, oldname);
5416 #endif
5417 if (((depth == ctxt->nameNr) &&
5418 (xmlStrEqual(oldname, ctxt->name))) ||
5419 (name == NULL)) {
5420 if (CUR == '>')
5421 NEXT;
5422 if (oldname != NULL)
5423 xmlFree(oldname);
5424 break;
5425 }
5426 if (oldname != NULL)
5427 xmlFree(oldname);
5428
5429 /*
5430 * Lookup the info for that element.
5431 */
5432 info = docbTagLookup(name);
5433 if (info == NULL) {
5434 if ((ctxt->sax != NULL) && (ctxt->sax->error != NULL))
5435 ctxt->sax->error(ctxt->userData, "Tag %s unknown\n",
5436 name);
5437 ctxt->wellFormed = 0;
5438 } else if (info->depr) {
5439 /***************************
5440 if ((ctxt->sax != NULL) && (ctxt->sax->warning != NULL))
5441 ctxt->sax->warning(ctxt->userData,
5442 "Tag %s is deprecated\n",
5443 name);
5444 ***************************/
5445 }
5446
5447 /*
5448 * Check for an Empty Element labeled the XML/SGML way
5449 */
5450 if ((CUR == '/') && (NXT(1) == '>')) {
5451 SKIP(2);
5452 if ((ctxt->sax != NULL) && (ctxt->sax->endElement != NULL))
5453 ctxt->sax->endElement(ctxt->userData, name);
5454 oldname = docbnamePop(ctxt);
5455 #ifdef DEBUG
5456 xmlGenericError(xmlGenericErrorContext,"End of tag the XML way: popping out %s\n",
5457 oldname);
5458 #endif
5459 if (oldname != NULL)
5460 xmlFree(oldname);
5461 ctxt->instate = XML_PARSER_CONTENT;
5462 #ifdef DEBUG_PUSH
5463 xmlGenericError(xmlGenericErrorContext,
5464 "HPP: entering CONTENT\n");
5465 #endif
5466 break;
5467 }
5468
5469 if (CUR == '>') {
5470 NEXT;
5471 } else {
5472 if ((ctxt->sax != NULL) && (ctxt->sax->error != NULL))
5473 ctxt->sax->error(ctxt->userData,
5474 "Couldn't find end of Start Tag %s\n",
5475 name);
5476 ctxt->wellFormed = 0;
5477
5478 /*
5479 * end of parsing of this node.
5480 */
5481 if (xmlStrEqual(name, ctxt->name)) {
5482 nodePop(ctxt);
5483 oldname = docbnamePop(ctxt);
5484 #ifdef DEBUG
5485 xmlGenericError(xmlGenericErrorContext,
5486 "End of start tag problem: popping out %s\n", oldname);
5487 #endif
5488 if (oldname != NULL)
5489 xmlFree(oldname);
5490 }
5491
5492 ctxt->instate = XML_PARSER_CONTENT;
5493 #ifdef DEBUG_PUSH
5494 xmlGenericError(xmlGenericErrorContext,
5495 "HPP: entering CONTENT\n");
5496 #endif
5497 break;
5498 }
5499
5500 /*
5501 * Check for an Empty Element from DTD definition
5502 */
5503 if ((info != NULL) && (info->empty)) {
5504 if ((ctxt->sax != NULL) && (ctxt->sax->endElement != NULL))
5505 ctxt->sax->endElement(ctxt->userData, name);
5506 oldname = docbnamePop(ctxt);
5507 #ifdef DEBUG
5508 xmlGenericError(xmlGenericErrorContext,"End of empty tag %s : popping out %s\n", name, oldname);
5509 #endif
5510 if (oldname != NULL)
5511 xmlFree(oldname);
5512 }
5513 ctxt->instate = XML_PARSER_CONTENT;
5514 #ifdef DEBUG_PUSH
5515 xmlGenericError(xmlGenericErrorContext,
5516 "HPP: entering CONTENT\n");
5517 #endif
5518 break;
5519 }
5520 case XML_PARSER_CONTENT: {
5521 long cons;
5522 /*
5523 * Handle preparsed entities and charRef
5524 */
5525 if (ctxt->token != 0) {
5526 xmlChar chr[2] = { 0 , 0 } ;
5527
5528 chr[0] = (xmlChar) ctxt->token;
5529 if ((ctxt->sax != NULL) && (ctxt->sax->characters != NULL))
5530 ctxt->sax->characters(ctxt->userData, chr, 1);
5531 ctxt->token = 0;
5532 ctxt->checkIndex = 0;
5533 }
5534 if ((avail == 1) && (terminate)) {
5535 cur = in->cur[0];
5536 if ((cur != '<') && (cur != '&')) {
5537 if (ctxt->sax != NULL) {
5538 if (IS_BLANK(cur)) {
5539 if (ctxt->sax->ignorableWhitespace != NULL)
5540 ctxt->sax->ignorableWhitespace(
5541 ctxt->userData, &cur, 1);
5542 } else {
5543 if (ctxt->sax->characters != NULL)
5544 ctxt->sax->characters(
5545 ctxt->userData, &cur, 1);
5546 }
5547 }
5548 ctxt->token = 0;
5549 ctxt->checkIndex = 0;
5550 NEXT;
5551 }
5552 break;
5553 }
5554 if (avail < 2)
5555 goto done;
5556 cur = in->cur[0];
5557 next = in->cur[1];
5558 cons = ctxt->nbChars;
5559 /*
5560 * Sometimes DOCTYPE arrives in the middle of the document
5561 */
5562 if ((cur == '<') && (next == '!') &&
5563 (UPP(2) == 'D') && (UPP(3) == 'O') &&
5564 (UPP(4) == 'C') && (UPP(5) == 'T') &&
5565 (UPP(6) == 'Y') && (UPP(7) == 'P') &&
5566 (UPP(8) == 'E')) {
5567 if ((!terminate) &&
5568 (docbParseLookupSequence(ctxt, '>', 0, 0) < 0))
5569 goto done;
5570 if ((ctxt->sax != NULL) && (ctxt->sax->error != NULL))
5571 ctxt->sax->error(ctxt->userData,
5572 "Misplaced DOCTYPE declaration\n");
5573 ctxt->wellFormed = 0;
5574 docbParseDocTypeDecl(ctxt);
5575 } else if ((cur == '<') && (next == '!') &&
5576 (in->cur[2] == '-') && (in->cur[3] == '-')) {
5577 if ((!terminate) &&
5578 (docbParseLookupSequence(ctxt, '-', '-', '>') < 0))
5579 goto done;
5580 #ifdef DEBUG_PUSH
5581 xmlGenericError(xmlGenericErrorContext,
5582 "HPP: Parsing Comment\n");
5583 #endif
5584 docbParseComment(ctxt);
5585 ctxt->instate = XML_PARSER_CONTENT;
5586 } else if ((cur == '<') && (next == '!') && (avail < 4)) {
5587 goto done;
5588 } else if ((cur == '<') && (next == '/')) {
5589 ctxt->instate = XML_PARSER_END_TAG;
5590 ctxt->checkIndex = 0;
5591 #ifdef DEBUG_PUSH
5592 xmlGenericError(xmlGenericErrorContext,
5593 "HPP: entering END_TAG\n");
5594 #endif
5595 break;
5596 } else if (cur == '<') {
5597 ctxt->instate = XML_PARSER_START_TAG;
5598 ctxt->checkIndex = 0;
5599 #ifdef DEBUG_PUSH
5600 xmlGenericError(xmlGenericErrorContext,
5601 "HPP: entering START_TAG\n");
5602 #endif
5603 break;
5604 } else if (cur == '&') {
5605 if ((!terminate) &&
5606 (docbParseLookupSequence(ctxt, ';', 0, 0) < 0))
5607 goto done;
5608 #ifdef DEBUG_PUSH
5609 xmlGenericError(xmlGenericErrorContext,
5610 "HPP: Parsing Reference\n");
5611 #endif
5612 /* TODO: check generation of subtrees if noent !!! */
5613 docbParseReference(ctxt);
5614 } else {
5615 /* TODO Avoid the extra copy, handle directly !!!!!! */
5616 /*
5617 * Goal of the following test is :
5618 * - minimize calls to the SAX 'character' callback
5619 * when they are mergeable
5620 */
5621 if ((ctxt->inputNr == 1) &&
5622 (avail < DOCB_PARSER_BIG_BUFFER_SIZE)) {
5623 if ((!terminate) &&
5624 (docbParseLookupSequence(ctxt, '<', 0, 0) < 0))
5625 goto done;
5626 }
5627 ctxt->checkIndex = 0;
5628 #ifdef DEBUG_PUSH
5629 xmlGenericError(xmlGenericErrorContext,
5630 "HPP: Parsing char data\n");
5631 #endif
5632 docbParseCharData(ctxt);
5633 }
5634 if (cons == ctxt->nbChars) {
5635 if (ctxt->node != NULL) {
5636 if ((ctxt->sax != NULL) && (ctxt->sax->error != NULL))
5637 ctxt->sax->error(ctxt->userData,
5638 "detected an error in element content\n");
5639 ctxt->wellFormed = 0;
5640 NEXT;
5641 }
5642 break;
5643 }
5644
5645 break;
5646 }
5647 case XML_PARSER_END_TAG:
5648 if (avail < 2)
5649 goto done;
5650 if ((!terminate) &&
5651 (docbParseLookupSequence(ctxt, '>', 0, 0) < 0))
5652 goto done;
5653 docbParseEndTag(ctxt);
5654 if (ctxt->nameNr == 0) {
5655 ctxt->instate = XML_PARSER_EPILOG;
5656 } else {
5657 ctxt->instate = XML_PARSER_CONTENT;
5658 }
5659 ctxt->checkIndex = 0;
5660 #ifdef DEBUG_PUSH
5661 xmlGenericError(xmlGenericErrorContext,
5662 "HPP: entering CONTENT\n");
5663 #endif
5664 break;
5665 case XML_PARSER_CDATA_SECTION:
5666 xmlGenericError(xmlGenericErrorContext,
5667 "HPP: internal error, state == CDATA\n");
5668 ctxt->instate = XML_PARSER_CONTENT;
5669 ctxt->checkIndex = 0;
5670 #ifdef DEBUG_PUSH
5671 xmlGenericError(xmlGenericErrorContext,
5672 "HPP: entering CONTENT\n");
5673 #endif
5674 break;
5675 case XML_PARSER_DTD:
5676 xmlGenericError(xmlGenericErrorContext,
5677 "HPP: internal error, state == DTD\n");
5678 ctxt->instate = XML_PARSER_CONTENT;
5679 ctxt->checkIndex = 0;
5680 #ifdef DEBUG_PUSH
5681 xmlGenericError(xmlGenericErrorContext,
5682 "HPP: entering CONTENT\n");
5683 #endif
5684 break;
5685 case XML_PARSER_COMMENT:
5686 xmlGenericError(xmlGenericErrorContext,
5687 "HPP: internal error, state == COMMENT\n");
5688 ctxt->instate = XML_PARSER_CONTENT;
5689 ctxt->checkIndex = 0;
5690 #ifdef DEBUG_PUSH
5691 xmlGenericError(xmlGenericErrorContext,
5692 "HPP: entering CONTENT\n");
5693 #endif
5694 break;
5695 case XML_PARSER_PI:
5696 xmlGenericError(xmlGenericErrorContext,
5697 "HPP: internal error, state == PI\n");
5698 ctxt->instate = XML_PARSER_CONTENT;
5699 ctxt->checkIndex = 0;
5700 #ifdef DEBUG_PUSH
5701 xmlGenericError(xmlGenericErrorContext,
5702 "HPP: entering CONTENT\n");
5703 #endif
5704 break;
5705 case XML_PARSER_ENTITY_DECL:
5706 xmlGenericError(xmlGenericErrorContext,
5707 "HPP: internal error, state == ENTITY_DECL\n");
5708 ctxt->instate = XML_PARSER_CONTENT;
5709 ctxt->checkIndex = 0;
5710 #ifdef DEBUG_PUSH
5711 xmlGenericError(xmlGenericErrorContext,
5712 "HPP: entering CONTENT\n");
5713 #endif
5714 break;
5715 case XML_PARSER_ENTITY_VALUE:
5716 xmlGenericError(xmlGenericErrorContext,
5717 "HPP: internal error, state == ENTITY_VALUE\n");
5718 ctxt->instate = XML_PARSER_CONTENT;
5719 ctxt->checkIndex = 0;
5720 #ifdef DEBUG_PUSH
5721 xmlGenericError(xmlGenericErrorContext,
5722 "HPP: entering DTD\n");
5723 #endif
5724 break;
5725 case XML_PARSER_ATTRIBUTE_VALUE:
5726 xmlGenericError(xmlGenericErrorContext,
5727 "HPP: internal error, state == ATTRIBUTE_VALUE\n");
5728 ctxt->instate = XML_PARSER_START_TAG;
5729 ctxt->checkIndex = 0;
5730 #ifdef DEBUG_PUSH
5731 xmlGenericError(xmlGenericErrorContext,
5732 "HPP: entering START_TAG\n");
5733 #endif
5734 break;
5735 case XML_PARSER_SYSTEM_LITERAL:
5736 xmlGenericError(xmlGenericErrorContext,
5737 "HPP: internal error, state == XML_PARSER_SYSTEM_LITERAL\n");
5738 ctxt->instate = XML_PARSER_CONTENT;
5739 ctxt->checkIndex = 0;
5740 #ifdef DEBUG_PUSH
5741 xmlGenericError(xmlGenericErrorContext,
5742 "HPP: entering CONTENT\n");
5743 #endif
5744 break;
5745
5746 case XML_PARSER_IGNORE:
5747 xmlGenericError(xmlGenericErrorContext,
5748 "HPP: internal error, state == XML_PARSER_IGNORE\n");
5749 ctxt->instate = XML_PARSER_CONTENT;
5750 ctxt->checkIndex = 0;
5751 #ifdef DEBUG_PUSH
5752 xmlGenericError(xmlGenericErrorContext,
5753 "HPP: entering CONTENT\n");
5754 #endif
5755 break;
5756 case XML_PARSER_PUBLIC_LITERAL:
5757 xmlGenericError(xmlGenericErrorContext,
5758 "HPP: internal error, state == XML_PARSER_LITERAL\n");
5759 ctxt->instate = XML_PARSER_CONTENT;
5760 ctxt->checkIndex = 0;
5761 #ifdef DEBUG_PUSH
5762 xmlGenericError(xmlGenericErrorContext,
5763 "HPP: entering CONTENT\n");
5764 #endif
5765 break;
5766 }
5767 }
5768 done:
5769 if ((avail == 0) && (terminate)) {
5770 docbAutoClose(ctxt, NULL);
5771 if ((ctxt->nameNr == 0) && (ctxt->instate != XML_PARSER_EOF)) {
5772 /*
5773 * SAX: end of the document processing.
5774 */
5775 ctxt->instate = XML_PARSER_EOF;
5776 if ((ctxt->sax) && (ctxt->sax->endDocument != NULL))
5777 ctxt->sax->endDocument(ctxt->userData);
5778 }
5779 }
5780 if ((ctxt->myDoc != NULL) &&
5781 ((terminate) || (ctxt->instate == XML_PARSER_EOF) ||
5782 (ctxt->instate == XML_PARSER_EPILOG))) {
5783 xmlDtdPtr dtd;
5784 dtd = ctxt->myDoc->intSubset;
5785 if (dtd == NULL)
5786 ctxt->myDoc->intSubset =
5787 xmlCreateIntSubset(ctxt->myDoc, BAD_CAST "SGML",
5788 BAD_CAST "-//W3C//DTD SGML 4.0 Transitional//EN",
5789 BAD_CAST "http://www.w3.org/TR/REC-docbook/loose.dtd");
5790 }
5791 #ifdef DEBUG_PUSH
5792 xmlGenericError(xmlGenericErrorContext, "HPP: done %d\n", ret);
5793 #endif
5794 return(ret);
5795 }
5796
5797 /**
5798 * docbParseChunk:
5799 * @ctxt: an XML parser context
5800 * @chunk: an char array
5801 * @size: the size in byte of the chunk
5802 * @terminate: last chunk indicator
5803 *
5804 * Parse a Chunk of memory
5805 *
5806 * Returns zero if no error, the xmlParserErrors otherwise.
5807 */
5808 int
5809 docbParseChunk(docbParserCtxtPtr ctxt, const char *chunk, int size,
5810 int terminate) {
5811 if ((size > 0) && (chunk != NULL) && (ctxt->input != NULL) &&
5812 (ctxt->input->buf != NULL) && (ctxt->instate != XML_PARSER_EOF)) {
5813 int base = ctxt->input->base - ctxt->input->buf->buffer->content;
5814 int cur = ctxt->input->cur - ctxt->input->base;
5815
5816 xmlParserInputBufferPush(ctxt->input->buf, size, chunk);
5817 ctxt->input->base = ctxt->input->buf->buffer->content + base;
5818 ctxt->input->cur = ctxt->input->base + cur;
5819 #ifdef DEBUG_PUSH
5820 xmlGenericError(xmlGenericErrorContext, "HPP: pushed %d\n", size);
5821 #endif
5822
5823 if ((terminate) || (ctxt->input->buf->buffer->use > 80))
5824 docbParseTryOrFinish(ctxt, terminate);
5825 } else if (ctxt->instate != XML_PARSER_EOF) {
5826 xmlParserInputBufferPush(ctxt->input->buf, 0, "");
5827 docbParseTryOrFinish(ctxt, terminate);
5828 }
5829 if (terminate) {
5830 if ((ctxt->instate != XML_PARSER_EOF) &&
5831 (ctxt->instate != XML_PARSER_EPILOG) &&
5832 (ctxt->instate != XML_PARSER_MISC)) {
5833 ctxt->errNo = XML_ERR_DOCUMENT_END;
5834 if ((ctxt->sax != NULL) && (ctxt->sax->error != NULL))
5835 ctxt->sax->error(ctxt->userData,
5836 "Extra content at the end of the document\n");
5837 ctxt->wellFormed = 0;
5838 }
5839 if (ctxt->instate != XML_PARSER_EOF) {
5840 if ((ctxt->sax) && (ctxt->sax->endDocument != NULL))
5841 ctxt->sax->endDocument(ctxt->userData);
5842 }
5843 ctxt->instate = XML_PARSER_EOF;
5844 }
5845 return((xmlParserErrors) ctxt->errNo);
5846 }
5847
5848 /************************************************************************
5849 * *
5850 * User entry points *
5851 * *
5852 ************************************************************************/
5853
5854 /**
5855 * docbCreatePushParserCtxt :
5856 * @sax: a SAX handler
5857 * @user_data: The user data returned on SAX callbacks
5858 * @chunk: a pointer to an array of chars
5859 * @size: number of chars in the array
5860 * @filename: an optional file name or URI
5861 * @enc: an optional encoding
5862 *
5863 * Create a parser context for using the DocBook SGML parser in push mode
5864 * To allow content encoding detection, @size should be >= 4
5865 * The value of @filename is used for fetching external entities
5866 * and error/warning reports.
5867 *
5868 * Returns the new parser context or NULL
5869 */
5870 docbParserCtxtPtr
5871 docbCreatePushParserCtxt(docbSAXHandlerPtr sax, void *user_data,
5872 const char *chunk, int size, const char *filename,
5873 xmlCharEncoding enc) {
5874 docbParserCtxtPtr ctxt;
5875 docbParserInputPtr inputStream;
5876 xmlParserInputBufferPtr buf;
5877
5878 buf = xmlAllocParserInputBuffer(enc);
5879 if (buf == NULL) return(NULL);
5880
5881 ctxt = (docbParserCtxtPtr) xmlMalloc(sizeof(docbParserCtxt));
5882 if (ctxt == NULL) {
5883 xmlFree(buf);
5884 return(NULL);
5885 }
5886 memset(ctxt, 0, sizeof(docbParserCtxt));
5887 docbInitParserCtxt(ctxt);
5888 if (sax != NULL) {
5889 if (ctxt->sax != &docbDefaultSAXHandler)
5890 xmlFree(ctxt->sax);
5891 ctxt->sax = (docbSAXHandlerPtr) xmlMalloc(sizeof(docbSAXHandler));
5892 if (ctxt->sax == NULL) {
5893 xmlFree(buf);
5894 xmlFree(ctxt);
5895 return(NULL);
5896 }
5897 memcpy(ctxt->sax, sax, sizeof(docbSAXHandler));
5898 if (user_data != NULL)
5899 ctxt->userData = user_data;
5900 }
5901 if (filename == NULL) {
5902 ctxt->directory = NULL;
5903 } else {
5904 ctxt->directory = xmlParserGetDirectory(filename);
5905 }
5906
5907 inputStream = docbNewInputStream(ctxt);
5908 if (inputStream == NULL) {
5909 xmlFreeParserCtxt(ctxt);
5910 return(NULL);
5911 }
5912
5913 if (filename == NULL)
5914 inputStream->filename = NULL;
5915 else
5916 inputStream->filename = xmlMemStrdup(filename);
5917 inputStream->buf = buf;
5918 inputStream->base = inputStream->buf->buffer->content;
5919 inputStream->cur = inputStream->buf->buffer->content;
5920
5921 inputPush(ctxt, inputStream);
5922
5923 if ((size > 0) && (chunk != NULL) && (ctxt->input != NULL) &&
5924 (ctxt->input->buf != NULL)) {
5925 xmlParserInputBufferPush(ctxt->input->buf, size, chunk);
5926 #ifdef DEBUG_PUSH
5927 xmlGenericError(xmlGenericErrorContext, "HPP: pushed %d\n", size);
5928 #endif
5929 }
5930
5931 return(ctxt);
5932 }
5933
5934 /**
5935 * docbSAXParseDoc :
5936 * @cur: a pointer to an array of xmlChar
5937 * @encoding: a free form C string describing the SGML document encoding, or NULL
5938 * @sax: the SAX handler block
5939 * @userData: if using SAX, this pointer will be provided on callbacks.
5940 *
5941 * parse an SGML in-memory document and build a tree.
5942 * It use the given SAX function block to handle the parsing callback.
5943 * If sax is NULL, fallback to the default DOM tree building routines.
5944 *
5945 * Returns the resulting document tree
5946 */
5947
5948 docbDocPtr
5949 docbSAXParseDoc(xmlChar *cur, const char *encoding, docbSAXHandlerPtr sax, void *userData) {
5950 docbDocPtr ret;
5951 docbParserCtxtPtr ctxt;
5952
5953 if (cur == NULL) return(NULL);
5954
5955
5956 ctxt = docbCreateDocParserCtxt(cur, encoding);
5957 if (ctxt == NULL) return(NULL);
5958 if (sax != NULL) {
5959 ctxt->sax = sax;
5960 ctxt->userData = userData;
5961 }
5962
5963 docbParseDocument(ctxt);
5964 ret = ctxt->myDoc;
5965 if (sax != NULL) {
5966 ctxt->sax = NULL;
5967 ctxt->userData = NULL;
5968 }
5969 docbFreeParserCtxt(ctxt);
5970
5971 return(ret);
5972 }
5973
5974 /**
5975 * docbParseDoc :
5976 * @cur: a pointer to an array of xmlChar
5977 * @encoding: a free form C string describing the SGML document encoding, or NULL
5978 *
5979 * parse an SGML in-memory document and build a tree.
5980 *
5981 * Returns the resulting document tree
5982 */
5983
5984 docbDocPtr
5985 docbParseDoc(xmlChar *cur, const char *encoding) {
5986 return(docbSAXParseDoc(cur, encoding, NULL, NULL));
5987 }
5988
5989
5990 /**
5991 * docbCreateFileParserCtxt :
5992 * @filename: the filename
5993 * @encoding: the SGML document encoding, or NULL
5994 *
5995 * Create a parser context for a file content.
5996 * Automatic support for ZLIB/Compress compressed document is provided
5997 * by default if found at compile-time.
5998 *
5999 * Returns the new parser context or NULL
6000 */
6001 docbParserCtxtPtr
6002 docbCreateFileParserCtxt(const char *filename,
6003 const char *encoding ATTRIBUTE_UNUSED)
6004 {
6005 docbParserCtxtPtr ctxt;
6006 docbParserInputPtr inputStream;
6007 xmlParserInputBufferPtr buf;
6008 /* sgmlCharEncoding enc; */
6009
6010 buf = xmlParserInputBufferCreateFilename(filename, XML_CHAR_ENCODING_NONE);
6011 if (buf == NULL) return(NULL);
6012
6013 ctxt = (docbParserCtxtPtr) xmlMalloc(sizeof(docbParserCtxt));
6014 if (ctxt == NULL) {
6015 xmlGenericError(xmlGenericErrorContext, "malloc failed");
6016 return(NULL);
6017 }
6018 memset(ctxt, 0, sizeof(docbParserCtxt));
6019 docbInitParserCtxt(ctxt);
6020 inputStream = (docbParserInputPtr) xmlMalloc(sizeof(docbParserInput));
6021 if (inputStream == NULL) {
6022 xmlGenericError(xmlGenericErrorContext, "malloc failed");
6023 xmlFree(ctxt);
6024 return(NULL);
6025 }
6026 memset(inputStream, 0, sizeof(docbParserInput));
6027
6028 inputStream->filename = (char *)
6029 xmlNormalizeWindowsPath((const xmlChar *)filename);
6030 inputStream->line = 1;
6031 inputStream->col = 1;
6032 inputStream->buf = buf;
6033 inputStream->directory = NULL;
6034
6035 inputStream->base = inputStream->buf->buffer->content;
6036 inputStream->cur = inputStream->buf->buffer->content;
6037 inputStream->free = NULL;
6038
6039 inputPush(ctxt, inputStream);
6040 return(ctxt);
6041 }
6042
6043 /**
6044 * docbSAXParseFile :
6045 * @filename: the filename
6046 * @encoding: a free form C string describing the SGML document encoding, or NULL
6047 * @sax: the SAX handler block
6048 * @userData: if using SAX, this pointer will be provided on callbacks.
6049 *
6050 * parse an SGML file and build a tree. Automatic support for ZLIB/Compress
6051 * compressed document is provided by default if found at compile-time.
6052 * It use the given SAX function block to handle the parsing callback.
6053 * If sax is NULL, fallback to the default DOM tree building routines.
6054 *
6055 * Returns the resulting document tree
6056 */
6057
6058 docbDocPtr
6059 docbSAXParseFile(const char *filename, const char *encoding, docbSAXHandlerPtr sax,
6060 void *userData) {
6061 docbDocPtr ret;
6062 docbParserCtxtPtr ctxt;
6063 docbSAXHandlerPtr oldsax = NULL;
6064
6065 ctxt = docbCreateFileParserCtxt(filename, encoding);
6066 if (ctxt == NULL) return(NULL);
6067 if (sax != NULL) {
6068 oldsax = ctxt->sax;
6069 ctxt->sax = sax;
6070 ctxt->userData = userData;
6071 }
6072
6073 docbParseDocument(ctxt);
6074
6075 ret = ctxt->myDoc;
6076 if (sax != NULL) {
6077 ctxt->sax = oldsax;
6078 ctxt->userData = NULL;
6079 }
6080 docbFreeParserCtxt(ctxt);
6081
6082 return(ret);
6083 }
6084
6085 /**
6086 * docbParseFile :
6087 * @filename: the filename
6088 * @encoding: a free form C string describing document encoding, or NULL
6089 *
6090 * parse a Docbook SGML file and build a tree. Automatic support for
6091 * ZLIB/Compress compressed document is provided by default if found
6092 * at compile-time.
6093 *
6094 * Returns the resulting document tree
6095 */
6096
6097 docbDocPtr
6098 docbParseFile(const char *filename, const char *encoding) {
6099 return(docbSAXParseFile(filename, encoding, NULL, NULL));
6100 }
6101
6102 #endif /* LIBXML_DOCB_ENABLED */
swg client tools