Gitiles
Code Review Sign In
gerrit-public.fairphone.software / fp2-dev / platform / external / libxml2 / 1034da2bfffb9f898ae4330c85c98728faa2308e / . / DOCBparser.c
blob: 93e17559623750cea94518acdb62a0214c75ff10 [file] [log] [blame]
Daniel Veillardeae522a2001-04-23 13:41:34 +0000[diff] [blame]1/*
2 * DOCBparser.c : an attempt to parse SGML Docbook documents
3 *
4 * See Copyright for the status of this software.
5 *
6 * Daniel.Veillard@w3.org
7 */
8
9#include "libxml.h"
10#ifdef LIBXML_DOCB_ENABLED
11
12#include <string.h>
13#ifdef HAVE_CTYPE_H
14#include <ctype.h>
15#endif
16#ifdef HAVE_STDLIB_H
17#include <stdlib.h>
18#endif
19#ifdef HAVE_SYS_STAT_H
20#include <sys/stat.h>
21#endif
22#ifdef HAVE_FCNTL_H
23#include <fcntl.h>
24#endif
25#ifdef HAVE_UNISTD_H
26#include <unistd.h>
27#endif
28#ifdef HAVE_ZLIB_H
29#include <zlib.h>
30#endif
31
32#include <libxml/xmlmemory.h>
33#include <libxml/tree.h>
34#include <libxml/SAX.h>
35#include <libxml/parser.h>
36#include <libxml/parserInternals.h>
37#include <libxml/xmlerror.h>
38#include <libxml/DOCBparser.h>
39#include <libxml/entities.h>
40#include <libxml/encoding.h>
41#include <libxml/valid.h>
42#include <libxml/xmlIO.h>
43#include <libxml/uri.h>
44
45/*
46 * Internal description of an SGML entity
47 */
48typedef struct _docbEntityDesc docbEntityDesc;
49typedef docbEntityDesc *docbEntityDescPtr;
50struct _docbEntityDesc {
51 int value; /* the UNICODE value for the character */
52 const char *name; /* The entity name */
53 const char *desc; /* the description */
54};
55
56#if 0
57docbElemDescPtr docbTagLookup (const xmlChar *tag);
58docbEntityDescPtr docbEntityLookup(const xmlChar *name);
59docbEntityDescPtr docbEntityValueLookup(int value);
60
61int docbIsAutoClosed(docbDocPtr doc,
62 docbNodePtr elem);
63int docbAutoCloseTag(docbDocPtr doc,
64 const xmlChar *name,
65 docbNodePtr elem);
66
67#endif
Daniel Veillard61b33d52001-04-24 13:55:12 +0000[diff] [blame]68static int docbParseCharRef(docbParserCtxtPtr ctxt);
69static xmlEntityPtr docbParseEntityRef(docbParserCtxtPtr ctxt,
Daniel Veillardeae522a2001-04-23 13:41:34 +0000[diff] [blame]70 xmlChar **str);
Daniel Veillard61b33d52001-04-24 13:55:12 +0000[diff] [blame]71static void docbParseElement(docbParserCtxtPtr ctxt);
Daniel Veillard1034da22001-04-25 19:06:28 +0000[diff] [blame^]72static void docbParseContent(docbParserCtxtPtr ctxt);
Daniel Veillardeae522a2001-04-23 13:41:34 +0000[diff] [blame]73
74/*
75 * Internal description of an SGML element
76 */
77typedef struct _docbElemDesc docbElemDesc;
78typedef docbElemDesc *docbElemDescPtr;
79struct _docbElemDesc {
80 const char *name; /* The tag name */
81 int startTag; /* Whether the start tag can be implied */
82 int endTag; /* Whether the end tag can be implied */
83 int empty; /* Is this an empty element ? */
84 int depr; /* Is this a deprecated element ? */
85 int dtd; /* 1: only in Loose DTD, 2: only Frameset one */
86 const char *desc; /* the description */
87};
88
89
90#define DOCB_MAX_NAMELEN 1000
91#define DOCB_PARSER_BIG_BUFFER_SIZE 1000
92#define DOCB_PARSER_BUFFER_SIZE 100
93
94/* #define DEBUG */
95/* #define DEBUG_PUSH */
96
97/************************************************************************
98 * *
99 * Parser stacks related functions and macros *
100 * *
101 ************************************************************************/
102
103/*
104 * Generic function for accessing stacks in the Parser Context
105 */
106
107#define PUSH_AND_POP(scope, type, name) \
108scope int docb##name##Push(docbParserCtxtPtr ctxt, type value) { \
109 if (ctxt->name##Nr >= ctxt->name##Max) { \
110 ctxt->name##Max *= 2; \
111 ctxt->name##Tab = (type *) xmlRealloc(ctxt->name##Tab, \
112 ctxt->name##Max * sizeof(ctxt->name##Tab[0])); \
113 if (ctxt->name##Tab == NULL) { \
114 xmlGenericError(xmlGenericErrorContext, "realloc failed !\n"); \
115 return(0); \
116 } \
117 } \
118 ctxt->name##Tab[ctxt->name##Nr] = value; \
119 ctxt->name = value; \
120 return(ctxt->name##Nr++); \
121} \
122scope type docb##name##Pop(docbParserCtxtPtr ctxt) { \
123 type ret; \
124 if (ctxt->name##Nr < 0) return(0); \
125 ctxt->name##Nr--; \
126 if (ctxt->name##Nr < 0) return(0); \
127 if (ctxt->name##Nr > 0) \
128 ctxt->name = ctxt->name##Tab[ctxt->name##Nr - 1]; \
129 else \
130 ctxt->name = NULL; \
131 ret = ctxt->name##Tab[ctxt->name##Nr]; \
132 ctxt->name##Tab[ctxt->name##Nr] = 0; \
133 return(ret); \
134} \
135
136/* PUSH_AND_POP(static, xmlNodePtr, node) */
137PUSH_AND_POP(static, xmlChar*, name)
138
139/*
140 * Macros for accessing the content. Those should be used only by the parser,
141 * and not exported.
142 *
143 * Dirty macros, i.e. one need to make assumption on the context to use them
144 *
145 * CUR_PTR return the current pointer to the xmlChar to be parsed.
146 * CUR returns the current xmlChar value, i.e. a 8 bit value if compiled
147 * in ISO-Latin or UTF-8, and the current 16 bit value if compiled
148 * in UNICODE mode. This should be used internally by the parser
149 * only to compare to ASCII values otherwise it would break when
150 * running with UTF-8 encoding.
151 * NXT(n) returns the n'th next xmlChar. Same as CUR is should be used only
152 * to compare on ASCII based substring.
153 * UPP(n) returns the n'th next xmlChar converted to uppercase. Same as CUR
154 * it should be used only to compare on ASCII based substring.
155 * SKIP(n) Skip n xmlChar, and must also be used only to skip ASCII defined
156 * strings within the parser.
157 *
158 * Clean macros, not dependent of an ASCII context, expect UTF-8 encoding
159 *
160 * CURRENT Returns the current char value, with the full decoding of
161 * UTF-8 if we are using this mode. It returns an int.
162 * NEXT Skip to the next character, this does the proper decoding
163 * in UTF-8 mode. It also pop-up unfinished entities on the fly.
164 * COPY(to) copy one char to *to, increment CUR_PTR and to accordingly
165 */
166
167#define UPPER (toupper(*ctxt->input->cur))
168
169#define SKIP(val) ctxt->nbChars += (val),ctxt->input->cur += (val)
170
171#define NXT(val) ctxt->input->cur[(val)]
172
173#define UPP(val) (toupper(ctxt->input->cur[(val)]))
174
175#define CUR_PTR ctxt->input->cur
176
177#define SHRINK xmlParserInputShrink(ctxt->input)
178
179#define GROW xmlParserInputGrow(ctxt->input, INPUT_CHUNK)
180
181#define CURRENT ((int) (*ctxt->input->cur))
182
183#define SKIP_BLANKS docbSkipBlankChars(ctxt)
184
185/* Imported from XML */
186
187/* #define CUR (ctxt->token ? ctxt->token : (int) (*ctxt->input->cur)) */
188#define CUR ((int) (*ctxt->input->cur))
189#define NEXT xmlNextChar(ctxt),ctxt->nbChars++
190
191#define RAW (ctxt->token ? -1 : (*ctxt->input->cur))
192#define NXT(val) ctxt->input->cur[(val)]
193#define CUR_PTR ctxt->input->cur
194
195
196#define NEXTL(l) do { \
197 if (*(ctxt->input->cur) == '\n') { \
198 ctxt->input->line++; ctxt->input->col = 1; \
199 } else ctxt->input->col++; \
200 ctxt->token = 0; ctxt->input->cur += l; ctxt->nbChars++; \
201 } while (0)
202
203/************
204 \
205 if (*ctxt->input->cur == '%') xmlParserHandlePEReference(ctxt); \
206 if (*ctxt->input->cur == '&') xmlParserHandleReference(ctxt);
207 ************/
208
209#define CUR_CHAR(l) docbCurrentChar(ctxt, &l)
210#define CUR_SCHAR(s, l) xmlStringCurrentChar(ctxt, s, &l)
211
212#define COPY_BUF(l,b,i,v) \
213 if (l == 1) b[i++] = (xmlChar) v; \
214 else i += xmlCopyChar(l,&b[i],v)
215
216/**
217 * docbCurrentChar:
218 * @ctxt: the DocBook SGML parser context
219 * @len: pointer to the length of the char read
220 *
221 * The current char value, if using UTF-8 this may actaully span multiple
222 * bytes in the input buffer. Implement the end of line normalization:
223 * 2.11 End-of-Line Handling
224 * If the encoding is unspecified, in the case we find an ISO-Latin-1
225 * char, then the encoding converter is plugged in automatically.
226 *
227 * Returns the current char value and its lenght
228 */
229
230static int
231docbCurrentChar(xmlParserCtxtPtr ctxt, int *len) {
232 if (ctxt->instate == XML_PARSER_EOF)
233 return(0);
234
235 if (ctxt->token != 0) {
236 *len = 0;
237 return(ctxt->token);
238 }
239 if (ctxt->charset == XML_CHAR_ENCODING_UTF8) {
240 /*
241 * We are supposed to handle UTF8, check it's valid
242 * From rfc2044: encoding of the Unicode values on UTF-8:
243 *
244 * UCS-4 range (hex.) UTF-8 octet sequence (binary)
245 * 0000 0000-0000 007F 0xxxxxxx
246 * 0000 0080-0000 07FF 110xxxxx 10xxxxxx
247 * 0000 0800-0000 FFFF 1110xxxx 10xxxxxx 10xxxxxx
248 *
249 * Check for the 0x110000 limit too
250 */
251 const unsigned char *cur = ctxt->input->cur;
252 unsigned char c;
253 unsigned int val;
254
255 c = *cur;
256 if (c & 0x80) {
257 if (cur[1] == 0)
258 xmlParserInputGrow(ctxt->input, INPUT_CHUNK);
259 if ((cur[1] & 0xc0) != 0x80)
260 goto encoding_error;
261 if ((c & 0xe0) == 0xe0) {
262
263 if (cur[2] == 0)
264 xmlParserInputGrow(ctxt->input, INPUT_CHUNK);
265 if ((cur[2] & 0xc0) != 0x80)
266 goto encoding_error;
267 if ((c & 0xf0) == 0xf0) {
268 if (cur[3] == 0)
269 xmlParserInputGrow(ctxt->input, INPUT_CHUNK);
270 if (((c & 0xf8) != 0xf0) ||
271 ((cur[3] & 0xc0) != 0x80))
272 goto encoding_error;
273 /* 4-byte code */
274 *len = 4;
275 val = (cur[0] & 0x7) << 18;
276 val |= (cur[1] & 0x3f) << 12;
277 val |= (cur[2] & 0x3f) << 6;
278 val |= cur[3] & 0x3f;
279 } else {
280 /* 3-byte code */
281 *len = 3;
282 val = (cur[0] & 0xf) << 12;
283 val |= (cur[1] & 0x3f) << 6;
284 val |= cur[2] & 0x3f;
285 }
286 } else {
287 /* 2-byte code */
288 *len = 2;
289 val = (cur[0] & 0x1f) << 6;
290 val |= cur[1] & 0x3f;
291 }
292 if (!IS_CHAR(val)) {
293 ctxt->errNo = XML_ERR_INVALID_ENCODING;
294 if ((ctxt->sax != NULL) &&
295 (ctxt->sax->error != NULL))
296 ctxt->sax->error(ctxt->userData,
297 "Char 0x%X out of allowed range\n", val);
298 ctxt->wellFormed = 0;
299 ctxt->disableSAX = 1;
300 }
301 return(val);
302 } else {
303 /* 1-byte code */
304 *len = 1;
305 return((int) *ctxt->input->cur);
306 }
307 }
308 /*
309 * Assume it's a fixed lenght encoding (1) with
310 * a compatibke encoding for the ASCII set, since
311 * XML constructs only use < 128 chars
312 */
313 *len = 1;
314 if ((int) *ctxt->input->cur < 0x80)
315 return((int) *ctxt->input->cur);
316
317 /*
318 * Humm this is bad, do an automatic flow conversion
319 */
320 xmlSwitchEncoding(ctxt, XML_CHAR_ENCODING_8859_1);
321 ctxt->charset = XML_CHAR_ENCODING_UTF8;
322 return(xmlCurrentChar(ctxt, len));
323
324encoding_error:
325 /*
326 * If we detect an UTF8 error that probably mean that the
327 * input encoding didn't get properly advertized in the
328 * declaration header. Report the error and switch the encoding
329 * to ISO-Latin-1 (if you don't like this policy, just declare the
330 * encoding !)
331 */
332 ctxt->errNo = XML_ERR_INVALID_ENCODING;
333 if ((ctxt->sax != NULL) && (ctxt->sax->error != NULL)) {
334 ctxt->sax->error(ctxt->userData,
335 "Input is not proper UTF-8, indicate encoding !\n");
336 ctxt->sax->error(ctxt->userData, "Bytes: 0x%02X 0x%02X 0x%02X 0x%02X\n",
337 ctxt->input->cur[0], ctxt->input->cur[1],
338 ctxt->input->cur[2], ctxt->input->cur[3]);
339 }
340
341 ctxt->charset = XML_CHAR_ENCODING_8859_1;
342 *len = 1;
343 return((int) *ctxt->input->cur);
344}
345
346#if 0
347/**
348 * sgmlNextChar:
349 * @ctxt: the DocBook SGML parser context
350 *
351 * Skip to the next char input char.
352 */
353
354static void
355sgmlNextChar(docbParserCtxtPtr ctxt) {
356 if (ctxt->instate == XML_PARSER_EOF)
357 return;
358 if ((*ctxt->input->cur == 0) &&
359 (xmlParserInputGrow(ctxt->input, INPUT_CHUNK) <= 0)) {
360 xmlPopInput(ctxt);
361 } else {
362 if (*(ctxt->input->cur) == '\n') {
363 ctxt->input->line++; ctxt->input->col = 1;
364 } else ctxt->input->col++;
365 ctxt->input->cur++;
366 ctxt->nbChars++;
367 if (*ctxt->input->cur == 0)
368 xmlParserInputGrow(ctxt->input, INPUT_CHUNK);
369 }
370}
371#endif
372
373/**
374 * docbSkipBlankChars:
375 * @ctxt: the DocBook SGML parser context
376 *
377 * skip all blanks character found at that point in the input streams.
378 *
379 * Returns the number of space chars skipped
380 */
381
382static int
383docbSkipBlankChars(xmlParserCtxtPtr ctxt) {
384 int res = 0;
385
386 while (IS_BLANK(*(ctxt->input->cur))) {
387 if ((*ctxt->input->cur == 0) &&
388 (xmlParserInputGrow(ctxt->input, INPUT_CHUNK) <= 0)) {
389 xmlPopInput(ctxt);
390 } else {
391 if (*(ctxt->input->cur) == '\n') {
392 ctxt->input->line++; ctxt->input->col = 1;
393 } else ctxt->input->col++;
394 ctxt->input->cur++;
395 ctxt->nbChars++;
396 if (*ctxt->input->cur == 0)
397 xmlParserInputGrow(ctxt->input, INPUT_CHUNK);
398 }
399 res++;
400 }
401 return(res);
402}
403
404
405
406/************************************************************************
407 * *
408 * The list of SGML elements and their properties *
409 * *
410 ************************************************************************/
411
412/*
413 * Start Tag: 1 means the start tag can be ommited
414 * End Tag: 1 means the end tag can be ommited
415 * 2 means it's forbidden (empty elements)
416 * Depr: this element is deprecated
417 * DTD: 1 means that this element is valid only in the Loose DTD
418 * 2 means that this element is valid only in the Frameset DTD
419 *
420 * Name,Start Tag,End Tag, Empty, Depr., DTD, Description
421 */
422static docbElemDesc
423docbookElementTable[] = {
424{ "abbrev", 0, 0, 0, 3, 0, "" }, /* word */
425{ "abstract", 0, 0, 0, 9, 0, "" }, /* title */
426{ "accel", 0, 0, 0, 7, 0, "" }, /* smallcptr */
427{ "ackno", 0, 0, 0, 4, 0, "" }, /* docinfo */
428{ "acronym", 0, 0, 0, 3, 0, "" }, /* word */
429{ "action", 0, 0, 0, 7, 0, "" }, /* smallcptr */
430{ "address", 0, 0, 0, 1, 0, "" },
431{ "affiliation",0, 0, 0, 9, 0, "" }, /* shortaffil */
432{ "alt", 0, 0, 0, 1, 0, "" },
433{ "anchor", 0, 2, 1, 0, 0, "" },
434{ "answer", 0, 0, 0, 9, 0, "" }, /* label */
435{ "appendix", 0, 0, 0, 9, 0, "" }, /* appendixinfo */
436{ "appendixinfo",0, 0, 0, 9, 0, "" }, /* graphic */
437{ "application",0, 0, 0, 2, 0, "" }, /* para */
438{ "area", 0, 2, 1, 0, 0, "" },
439{ "areaset", 0, 0, 0, 9, 0, "" }, /* area */
440{ "areaspec", 0, 0, 0, 9, 0, "" }, /* area */
441{ "arg", 0, 0, 0, 1, 0, "" },
Daniel Veillard4ec0b0f2001-04-25 15:53:40 +0000[diff] [blame]442{ "artheader", 0, 0, 0, 9, 0, "" },
Daniel Veillardeae522a2001-04-23 13:41:34 +0000[diff] [blame]443{ "article", 0, 0, 0, 9, 0, "" }, /* div.title.content */
444{ "articleinfo",0, 0, 0, 9, 0, "" }, /* graphic */
445{ "artpagenums",0, 0, 0, 4, 0, "" }, /* docinfo */
446{ "attribution",0, 0, 0, 2, 0, "" }, /* para */
447{ "audiodata", 0, 2, 1, 0, 0, "" },
448{ "audioobject",0, 0, 0, 9, 0, "" }, /* objectinfo */
449{ "authorblurb",0, 0, 0, 9, 0, "" }, /* title */
450{ "authorgroup",0, 0, 0, 9, 0, "" }, /* author */
451{ "authorinitials",0, 0, 0, 4, 0, "" }, /* docinfo */
452{ "author", 0, 0, 0, 9, 0, "" }, /* person.ident.mix */
453{ "beginpage", 0, 2, 1, 0, 0, "" },
454{ "bibliodiv", 0, 0, 0, 9, 0, "" }, /* sect.title.content */
455{ "biblioentry",0, 0, 0, 9, 0, "" }, /* articleinfo */
456{ "bibliography",0, 0, 0, 9, 0, "" }, /* bibliographyinfo */
457{ "bibliographyinfo",0, 0, 0, 9, 0, "" }, /* graphic */
458{ "bibliomisc", 0, 0, 0, 2, 0, "" }, /* para */
459{ "bibliomixed",0, 0, 0, 1, 0, "" }, /* %bibliocomponent.mix, bibliomset) */
460{ "bibliomset", 0, 0, 0, 1, 0, "" }, /* %bibliocomponent.mix; | bibliomset) */
461{ "biblioset", 0, 0, 0, 9, 0, "" }, /* bibliocomponent.mix */
462{ "blockquote", 0, 0, 0, 9, 0, "" }, /* title */
463{ "book", 0, 0, 0, 9, 0, "" }, /* div.title.content */
464{ "bookinfo", 0, 0, 0, 9, 0, "" }, /* graphic */
465{ "bridgehead", 0, 0, 0, 8, 0, "" }, /* title */
466{ "callout", 0, 0, 0, 9, 0, "" }, /* component.mix */
467{ "calloutlist",0, 0, 0, 9, 0, "" }, /* formalobject.title.content */
468{ "caption", 0, 0, 0, 9, 0, "" }, /* textobject.mix */
469{ "caution", 0, 0, 0, 9, 0, "" }, /* title */
470{ "chapter", 0, 0, 0, 9, 0, "" }, /* chapterinfo */
471{ "chapterinfo",0, 0, 0, 9, 0, "" }, /* graphic */
472{ "citation", 0, 0, 0, 2, 0, "" }, /* para */
473{ "citerefentry",0, 0, 0, 9, 0, "" }, /* refentrytitle */
474{ "citetitle", 0, 0, 0, 2, 0, "" }, /* para */
475{ "city", 0, 0, 0, 4, 0, "" }, /* docinfo */
476{ "classname", 0, 0, 0, 7, 0, "" }, /* smallcptr */
477{ "classsynopsisinfo",0,0, 0, 9, 0, "" }, /* cptr */
478{ "classsynopsis",0, 0, 0, 9, 0, "" }, /* ooclass */
479{ "cmdsynopsis",0, 0, 0, 9, 0, "" }, /* command */
480{ "co", 0, 2, 1, 0, 0, "" },
481{ "collab", 0, 0, 0, 9, 0, "" }, /* collabname */
482{ "collabname", 0, 0, 0, 4, 0, "" }, /* docinfo */
483{ "colophon", 0, 0, 0, 9, 0, "" }, /* sect.title.content */
484{ "colspec", 0, 2, 1, 0, 0, "" },
485{ "colspec", 0, 2, 1, 0, 0, "" },
486{ "command", 0, 0, 0, 9, 0, "" }, /* cptr */
487{ "computeroutput",0, 0, 0, 9, 0, "" }, /* cptr */
488{ "confdates", 0, 0, 0, 4, 0, "" }, /* docinfo */
489{ "confgroup", 0, 0, 0, 9, 0, "" }, /* confdates */
490{ "confnum", 0, 0, 0, 4, 0, "" }, /* docinfo */
491{ "confsponsor",0, 0, 0, 4, 0, "" }, /* docinfo */
492{ "conftitle", 0, 0, 0, 4, 0, "" }, /* docinfo */
493{ "constant", 0, 0, 0, 7, 0, "" }, /* smallcptr */
494{ "constructorsynopsis",0,0, 0, 9, 0, "" }, /* modifier */
495{ "contractnum",0, 0, 0, 4, 0, "" }, /* docinfo */
496{ "contractsponsor",0, 0, 0, 4, 0, "" }, /* docinfo */
497{ "contrib", 0, 0, 0, 4, 0, "" }, /* docinfo */
498{ "copyright", 0, 0, 0, 9, 0, "" }, /* year */
499{ "corpauthor", 0, 0, 0, 4, 0, "" }, /* docinfo */
500{ "corpname", 0, 0, 0, 4, 0, "" }, /* docinfo */
501{ "country", 0, 0, 0, 4, 0, "" }, /* docinfo */
502{ "database", 0, 0, 0, 7, 0, "" }, /* smallcptr */
503{ "date", 0, 0, 0, 4, 0, "" }, /* docinfo */
504{ "dedication", 0, 0, 0, 9, 0, "" }, /* sect.title.content */
505{ "destructorsynopsis",0,0, 0, 9, 0, "" }, /* modifier */
506{ "edition", 0, 0, 0, 4, 0, "" }, /* docinfo */
507{ "editor", 0, 0, 0, 9, 0, "" }, /* person.ident.mix */
508{ "email", 0, 0, 0, 4, 0, "" }, /* docinfo */
509{ "emphasis", 0, 0, 0, 2, 0, "" }, /* para */
510{ "entry", 0, 0, 0, 9, 0, "" }, /* tbl.entry.mdl */
511{ "entrytbl", 0, 0, 0, 9, 0, "" }, /* tbl.entrytbl.mdl */
512{ "envar", 0, 0, 0, 7, 0, "" }, /* smallcptr */
513{ "epigraph", 0, 0, 0, 9, 0, "" }, /* attribution */
514{ "equation", 0, 0, 0, 9, 0, "" }, /* formalobject.title.content */
515{ "errorcode", 0, 0, 0, 7, 0, "" }, /* smallcptr */
516{ "errorname", 0, 0, 0, 7, 0, "" }, /* smallcptr */
517{ "errortype", 0, 0, 0, 7, 0, "" }, /* smallcptr */
518{ "example", 0, 0, 0, 9, 0, "" }, /* formalobject.title.content */
519{ "exceptionname",0, 0, 0, 7, 0, "" }, /* smallcptr */
520{ "fax", 0, 0, 0, 4, 0, "" }, /* docinfo */
521{ "fieldsynopsis", 0, 0, 0, 9, 0, "" }, /* modifier */
522{ "figure", 0, 0, 0, 9, 0, "" }, /* formalobject.title.content */
523{ "filename", 0, 0, 0, 7, 0, "" }, /* smallcptr */
524{ "firstname", 0, 0, 0, 4, 0, "" }, /* docinfo */
525{ "firstterm", 0, 0, 0, 3, 0, "" }, /* word */
526{ "footnote", 0, 0, 0, 9, 0, "" }, /* footnote.mix */
527{ "footnoteref",0, 2, 1, 0, 0, "" },
528{ "foreignphrase",0, 0, 0, 2, 0, "" }, /* para */
529{ "formalpara", 0, 0, 0, 9, 0, "" }, /* title */
530{ "funcdef", 0, 0, 0, 1, 0, "" },
531{ "funcparams", 0, 0, 0, 9, 0, "" }, /* cptr */
532{ "funcprototype",0, 0, 0, 9, 0, "" }, /* funcdef */
533{ "funcsynopsis",0, 0, 0, 9, 0, "" }, /* funcsynopsisinfo */
534{ "funcsynopsisinfo", 0, 0, 0, 9, 0, "" }, /* cptr */
535{ "function", 0, 0, 0, 9, 0, "" }, /* cptr */
536{ "glossary", 0, 0, 0, 9, 0, "" }, /* glossaryinfo */
537{ "glossaryinfo",0, 0, 0, 9, 0, "" }, /* graphic */
538{ "glossdef", 0, 0, 0, 9, 0, "" }, /* glossdef.mix */
539{ "glossdiv", 0, 0, 0, 9, 0, "" }, /* sect.title.content */
540{ "glossentry", 0, 0, 0, 9, 0, "" }, /* glossterm */
541{ "glosslist", 0, 0, 0, 9, 0, "" }, /* glossentry */
542{ "glossseealso",0, 0, 0, 2, 0, "" }, /* para */
543{ "glosssee", 0, 0, 0, 2, 0, "" }, /* para */
544{ "glossterm", 0, 0, 0, 2, 0, "" }, /* para */
Daniel Veillard4ec0b0f2001-04-25 15:53:40 +0000[diff] [blame]545{ "graphic", 0, 0, 0, 9, 0, "" },
Daniel Veillardeae522a2001-04-23 13:41:34 +0000[diff] [blame]546{ "graphicco", 0, 0, 0, 9, 0, "" }, /* areaspec */
547{ "group", 0, 0, 0, 9, 0, "" }, /* arg */
548{ "guibutton", 0, 0, 0, 7, 0, "" }, /* smallcptr */
549{ "guiicon", 0, 0, 0, 7, 0, "" }, /* smallcptr */
550{ "guilabel", 0, 0, 0, 7, 0, "" }, /* smallcptr */
551{ "guimenuitem",0, 0, 0, 7, 0, "" }, /* smallcptr */
552{ "guimenu", 0, 0, 0, 7, 0, "" }, /* smallcptr */
553{ "guisubmenu", 0, 0, 0, 7, 0, "" }, /* smallcptr */
554{ "hardware", 0, 0, 0, 7, 0, "" }, /* smallcptr */
555{ "highlights", 0, 0, 0, 9, 0, "" }, /* highlights.mix */
556{ "holder", 0, 0, 0, 4, 0, "" }, /* docinfo */
557{ "honorific", 0, 0, 0, 4, 0, "" }, /* docinfo */
558{ "imagedata", 0, 2, 1, 0, 0, "" },
559{ "imageobjectco",0, 0, 0, 9, 0, "" }, /* areaspec */
560{ "imageobject",0, 0, 0, 9, 0, "" }, /* objectinfo */
561{ "important", 0, 0, 0, 9, 0, "" }, /* title */
562{ "indexdiv", 0, 0, 0, 9, 0, "" }, /* sect.title.content */
563{ "indexentry", 0, 0, 0, 9, 0, "" }, /* primaryie */
564{ "index", 0, 0, 0, 9, 0, "" }, /* indexinfo */
565{ "indexinfo", 0, 0, 0, 9, 0, "" }, /* graphic */
566{ "indexterm", 0, 0, 0, 9, 0, "" }, /* primary */
567{ "informalequation",0, 0, 0, 9, 0, "" }, /* equation.content */
568{ "informalexample",0, 0, 0, 9, 0, "" }, /* example.mix */
569{ "informalfigure",0, 0, 0, 9, 0, "" }, /* figure.mix */
570{ "informaltable",0, 0, 0, 9, 0, "" }, /* graphic */
571{ "initializer",0, 0, 0, 7, 0, "" }, /* smallcptr */
572{ "inlineequation",0, 0, 0, 9, 0, "" }, /* inlineequation.content */
573{ "inlinegraphic",0, 2, 1, 0, 0, "" },
574{ "inlinemediaobject",0,0, 0, 9, 0, "" }, /* objectinfo */
575{ "interfacename",0, 0, 0, 7, 0, "" }, /* smallcptr */
576{ "interface", 0, 0, 0, 7, 0, "" }, /* smallcptr */
577{ "invpartnumber",0, 0, 0, 4, 0, "" }, /* docinfo */
578{ "isbn", 0, 0, 0, 4, 0, "" }, /* docinfo */
579{ "issn", 0, 0, 0, 4, 0, "" }, /* docinfo */
580{ "issuenum", 0, 0, 0, 4, 0, "" }, /* docinfo */
581{ "itemizedlist",0, 0, 0, 9, 0, "" }, /* formalobject.title.content */
582{ "itermset", 0, 0, 0, 9, 0, "" }, /* indexterm */
583{ "jobtitle", 0, 0, 0, 4, 0, "" }, /* docinfo */
584{ "keycap", 0, 0, 0, 7, 0, "" }, /* smallcptr */
585{ "keycode", 0, 0, 0, 7, 0, "" }, /* smallcptr */
586{ "keycombo", 0, 0, 0, 9, 0, "" }, /* keycap */
587{ "keysym", 0, 0, 0, 7, 0, "" }, /* smallcptr */
588{ "keyword", 0, 0, 0, 1, 0, "" },
589{ "keywordset", 0, 0, 0, 9, 0, "" }, /* keyword */
590{ "label", 0, 0, 0, 3, 0, "" }, /* word */
591{ "legalnotice",0, 0, 0, 9, 0, "" }, /* title */
592{ "lineage", 0, 0, 0, 4, 0, "" }, /* docinfo */
593{ "lineannotation",0, 0, 0, 2, 0, "" }, /* para */
594{ "link", 0, 0, 0, 2, 0, "" }, /* para */
595{ "listitem", 0, 0, 0, 9, 0, "" }, /* component.mix */
596{ "literal", 0, 0, 0, 9, 0, "" }, /* cptr */
597{ "literallayout",0, 0, 0, 2, 0, "" }, /* para */
598{ "lot", 0, 0, 0, 9, 0, "" }, /* bookcomponent.title.content */
599{ "lotentry", 0, 0, 0, 2, 0, "" }, /* para */
600{ "manvolnum", 0, 0, 0, 3, 0, "" }, /* word */
601{ "markup", 0, 0, 0, 7, 0, "" }, /* smallcptr */
602{ "medialabel", 0, 0, 0, 7, 0, "" }, /* smallcptr */
603{ "mediaobjectco",0, 0, 0, 9, 0, "" }, /* objectinfo */
604{ "mediaobject",0, 0, 0, 9, 0, "" }, /* objectinfo */
605{ "member", 0, 0, 0, 2, 0, "" }, /* para */
606{ "menuchoice", 0, 0, 0, 9, 0, "" }, /* shortcut */
607{ "methodname", 0, 0, 0, 7, 0, "" }, /* smallcptr */
608{ "methodparam",0, 0, 0, 9, 0, "" }, /* modifier */
609{ "methodsynopsis",0, 0, 0, 9, 0, "" }, /* modifier */
610{ "modespec", 0, 0, 0, 4, 0, "" }, /* docinfo */
611{ "modifier", 0, 0, 0, 7, 0, "" }, /* smallcptr */
612{ "mousebutton",0, 0, 0, 7, 0, "" }, /* smallcptr */
613{ "msgaud", 0, 0, 0, 2, 0, "" }, /* para */
614{ "msgentry", 0, 0, 0, 9, 0, "" }, /* msg */
615{ "msgexplan", 0, 0, 0, 9, 0, "" }, /* title */
616{ "msginfo", 0, 0, 0, 9, 0, "" }, /* msglevel */
617{ "msglevel", 0, 0, 0, 7, 0, "" }, /* smallcptr */
618{ "msgmain", 0, 0, 0, 9, 0, "" }, /* title */
619{ "msgorig", 0, 0, 0, 7, 0, "" }, /* smallcptr */
620{ "msgrel", 0, 0, 0, 9, 0, "" }, /* title */
621{ "msgset", 0, 0, 0, 9, 0, "" }, /* formalobject.title.content */
622{ "msgsub", 0, 0, 0, 9, 0, "" }, /* title */
623{ "msgtext", 0, 0, 0, 9, 0, "" }, /* component.mix */
624{ "msg", 0, 0, 0, 9, 0, "" }, /* title */
625{ "note", 0, 0, 0, 9, 0, "" }, /* title */
626{ "objectinfo", 0, 0, 0, 9, 0, "" }, /* graphic */
627{ "olink", 0, 0, 0, 2, 0, "" }, /* para */
628{ "ooclass", 0, 0, 0, 9, 0, "" }, /* modifier */
629{ "ooexception",0, 0, 0, 9, 0, "" }, /* modifier */
630{ "oointerface",0, 0, 0, 9, 0, "" }, /* modifier */
631{ "optional", 0, 0, 0, 9, 0, "" }, /* cptr */
632{ "option", 0, 0, 0, 7, 0, "" }, /* smallcptr */
633{ "orderedlist",0, 0, 0, 9, 0, "" }, /* formalobject.title.content */
634{ "orgdiv", 0, 0, 0, 4, 0, "" }, /* docinfo */
635{ "orgname", 0, 0, 0, 4, 0, "" }, /* docinfo */
636{ "otheraddr", 0, 0, 0, 4, 0, "" }, /* docinfo */
637{ "othercredit",0, 0, 0, 9, 0, "" }, /* person.ident.mix */
638{ "othername", 0, 0, 0, 4, 0, "" }, /* docinfo */
639{ "pagenums", 0, 0, 0, 4, 0, "" }, /* docinfo */
640{ "paramdef", 0, 0, 0, 1, 0, "" },
641{ "parameter", 0, 0, 0, 7, 0, "" }, /* smallcptr */
642{ "para", 0, 0, 0, 2, 0, "" }, /* para */
643{ "partinfo", 0, 0, 0, 9, 0, "" }, /* graphic */
644{ "partintro", 0, 0, 0, 9, 0, "" }, /* div.title.content */
645{ "part", 0, 0, 0, 9, 0, "" }, /* partinfo */
646{ "phone", 0, 0, 0, 4, 0, "" }, /* docinfo */
647{ "phrase", 0, 0, 0, 2, 0, "" }, /* para */
648{ "pob", 0, 0, 0, 4, 0, "" }, /* docinfo */
649{ "postcode", 0, 0, 0, 4, 0, "" }, /* docinfo */
650{ "prefaceinfo",0, 0, 0, 9, 0, "" }, /* graphic */
651{ "preface", 0, 0, 0, 9, 0, "" }, /* prefaceinfo */
652{ "primaryie", 0, 0, 0, 4, 0, "" }, /* ndxterm */
653{ "primary ", 0, 0, 0, 4, 0, "" }, /* ndxterm */
654{ "printhistory",0, 0, 0, 9, 0, "" }, /* para.class */
655{ "procedure", 0, 0, 0, 9, 0, "" }, /* formalobject.title.content */
656{ "productname",0, 0, 0, 2, 0, "" }, /* para */
657{ "productnumber",0, 0, 0, 4, 0, "" }, /* docinfo */
658{ "programlistingco",0, 0, 0, 9, 0, "" }, /* areaspec */
659{ "programlisting",0, 0, 0, 2, 0, "" }, /* para */
660{ "prompt", 0, 0, 0, 7, 0, "" }, /* smallcptr */
661{ "property", 0, 0, 0, 7, 0, "" }, /* smallcptr */
662{ "pubdate", 0, 0, 0, 4, 0, "" }, /* docinfo */
663{ "publishername",0, 0, 0, 4, 0, "" }, /* docinfo */
664{ "publisher", 0, 0, 0, 9, 0, "" }, /* publishername */
665{ "pubsnumber", 0, 0, 0, 4, 0, "" }, /* docinfo */
666{ "qandadiv", 0, 0, 0, 9, 0, "" }, /* formalobject.title.content */
667{ "qandaentry", 0, 0, 0, 9, 0, "" }, /* revhistory */
668{ "qandaset", 0, 0, 0, 9, 0, "" }, /* formalobject.title.content */
669{ "question", 0, 0, 0, 9, 0, "" }, /* label */
670{ "quote", 0, 0, 0, 2, 0, "" }, /* para */
671{ "refclass", 0, 0, 0, 9, 0, "" }, /* refclass.char.mix */
672{ "refdescriptor",0, 0, 0, 9, 0, "" }, /* refname.char.mix */
673{ "refentryinfo",0, 0, 0, 9, 0, "" }, /* graphic */
674{ "refentry", 0, 0, 0, 9, 0, "" }, /* ndxterm.class */
675{ "refentrytitle",0, 0, 0, 2, 0, "" }, /* para */
676{ "referenceinfo",0, 0, 0, 9, 0, "" }, /* graphic */
677{ "reference", 0, 0, 0, 9, 0, "" }, /* referenceinfo */
678{ "refmeta", 0, 0, 0, 9, 0, "" }, /* ndxterm.class */
679{ "refmiscinfo",0, 0, 0, 4, 0, "" }, /* docinfo */
680{ "refnamediv", 0, 0, 0, 9, 0, "" }, /* refdescriptor */
681{ "refname", 0, 0, 0, 9, 0, "" }, /* refname.char.mix */
682{ "refpurpose", 0, 0, 0, 9, 0, "" }, /* refinline.char.mix */
683{ "refsect1info",0, 0, 0, 9, 0, "" }, /* graphic */
684{ "refsect1", 0, 0, 0, 9, 0, "" }, /* refsect */
685{ "refsect2info",0, 0, 0, 9, 0, "" }, /* graphic */
686{ "refsect2", 0, 0, 0, 9, 0, "" }, /* refsect */
687{ "refsect3info",0, 0, 0, 9, 0, "" }, /* graphic */
688{ "refsect3", 0, 0, 0, 9, 0, "" }, /* refsect */
689{ "refsynopsisdivinfo",0,0, 0, 9, 0, "" }, /* graphic */
690{ "refsynopsisdiv",0, 0, 0, 9, 0, "" }, /* refsynopsisdivinfo */
691{ "releaseinfo",0, 0, 0, 4, 0, "" }, /* docinfo */
692{ "remark", 0, 0, 0, 2, 0, "" }, /* para */
693{ "replaceable",0, 0, 0, 1, 0, "" },
694{ "returnvalue",0, 0, 0, 7, 0, "" }, /* smallcptr */
695{ "revdescription",0, 0, 0, 9, 0, "" }, /* revdescription.mix */
696{ "revhistory", 0, 0, 0, 9, 0, "" }, /* revision */
697{ "revision", 0, 0, 0, 9, 0, "" }, /* revnumber */
698{ "revnumber", 0, 0, 0, 4, 0, "" }, /* docinfo */
699{ "revremark", 0, 0, 0, 4, 0, "" }, /* docinfo */
700{ "row", 0, 0, 0, 9, 0, "" }, /* tbl.row.mdl */
701{ "row", 0, 0, 0, 9, 0, "" }, /* tbl.row.mdl */
702{ "sbr", 0, 2, 1, 0, 0, "" },
703{ "screenco", 0, 0, 0, 9, 0, "" }, /* areaspec */
704{ "screeninfo", 0, 0, 0, 2, 0, "" }, /* para */
705{ "screen", 0, 0, 0, 2, 0, "" }, /* para */
706{ "screenshot", 0, 0, 0, 9, 0, "" }, /* screeninfo */
707{ "secondaryie",0, 0, 0, 4, 0, "" }, /* ndxterm */
708{ "secondary", 0, 0, 0, 4, 0, "" }, /* ndxterm */
709{ "sect1info", 0, 0, 0, 9, 0, "" }, /* graphic */
710{ "sect1", 0, 0, 0, 9, 0, "" }, /* sect */
711{ "sect2info", 0, 0, 0, 9, 0, "" }, /* graphic */
712{ "sect2", 0, 0, 0, 9, 0, "" }, /* sect */
713{ "sect3info", 0, 0, 0, 9, 0, "" }, /* graphic */
714{ "sect3", 0, 0, 0, 9, 0, "" }, /* sect */
715{ "sect4info", 0, 0, 0, 9, 0, "" }, /* graphic */
716{ "sect4", 0, 0, 0, 9, 0, "" }, /* sect */
717{ "sect5info", 0, 0, 0, 9, 0, "" }, /* graphic */
718{ "sect5", 0, 0, 0, 9, 0, "" }, /* sect */
719{ "sectioninfo",0, 0, 0, 9, 0, "" }, /* graphic */
720{ "section", 0, 0, 0, 9, 0, "" }, /* sectioninfo */
721{ "seealsoie", 0, 0, 0, 4, 0, "" }, /* ndxterm */
722{ "seealso", 0, 0, 0, 4, 0, "" }, /* ndxterm */
723{ "seeie", 0, 0, 0, 4, 0, "" }, /* ndxterm */
724{ "see", 0, 0, 0, 4, 0, "" }, /* ndxterm */
725{ "seglistitem",0, 0, 0, 9, 0, "" }, /* seg */
726{ "segmentedlist",0, 0, 0, 9, 0, "" }, /* formalobject.title.content */
727{ "seg", 0, 0, 0, 2, 0, "" }, /* para */
728{ "segtitle", 0, 0, 0, 8, 0, "" }, /* title */
729{ "seriesvolnums", 0, 0, 0, 4, 0, "" }, /* docinfo */
730{ "set", 0, 0, 0, 9, 0, "" }, /* div.title.content */
731{ "setindexinfo",0, 0, 0, 9, 0, "" }, /* graphic */
732{ "setindex", 0, 0, 0, 9, 0, "" }, /* setindexinfo */
733{ "setinfo", 0, 0, 0, 9, 0, "" }, /* graphic */
734{ "sgmltag", 0, 0, 0, 7, 0, "" }, /* smallcptr */
735{ "shortaffil", 0, 0, 0, 4, 0, "" }, /* docinfo */
736{ "shortcut", 0, 0, 0, 9, 0, "" }, /* keycap */
737{ "sidebarinfo",0, 0, 0, 9, 0, "" }, /* graphic */
738{ "sidebar", 0, 0, 0, 9, 0, "" }, /* sidebarinfo */
739{ "simpara", 0, 0, 0, 2, 0, "" }, /* para */
740{ "simplelist", 0, 0, 0, 9, 0, "" }, /* member */
741{ "simplemsgentry", 0, 0, 0, 9, 0, "" }, /* msgtext */
742{ "simplesect", 0, 0, 0, 9, 0, "" }, /* sect.title.content */
743{ "spanspec", 0, 2, 1, 0, 0, "" },
744{ "state", 0, 0, 0, 4, 0, "" }, /* docinfo */
745{ "step", 0, 0, 0, 9, 0, "" }, /* title */
746{ "street", 0, 0, 0, 4, 0, "" }, /* docinfo */
747{ "structfield",0, 0, 0, 7, 0, "" }, /* smallcptr */
748{ "structname", 0, 0, 0, 7, 0, "" }, /* smallcptr */
749{ "subjectset", 0, 0, 0, 9, 0, "" }, /* subject */
750{ "subject", 0, 0, 0, 9, 0, "" }, /* subjectterm */
751{ "subjectterm",0, 0, 0, 1, 0, "" },
752{ "subscript", 0, 0, 0, 1, 0, "" },
753{ "substeps", 0, 0, 0, 9, 0, "" }, /* step */
754{ "subtitle", 0, 0, 0, 8, 0, "" }, /* title */
755{ "superscript", 0, 0, 0, 1, 0, "" },
756{ "surname", 0, 0, 0, 4, 0, "" }, /* docinfo */
757{ "symbol", 0, 0, 0, 7, 0, "" }, /* smallcptr */
758{ "synopfragment", 0, 0, 0, 9, 0, "" }, /* arg */
759{ "synopfragmentref", 0, 0, 0, 1, 0, "" },
760{ "synopsis", 0, 0, 0, 2, 0, "" }, /* para */
761{ "systemitem", 0, 0, 0, 7, 0, "" }, /* smallcptr */
762{ "table", 0, 0, 0, 9, 0, "" }, /* tbl.table.mdl */
763/* { "%tbl.table.name;", 0, 0, 0, 9, 0, "" },*/ /* tbl.table.mdl */
764{ "tbody", 0, 0, 0, 9, 0, "" }, /* row */
765{ "tbody", 0, 0, 0, 9, 0, "" }, /* row */
766{ "term", 0, 0, 0, 2, 0, "" }, /* para */
767{ "tertiaryie", 0, 0, 0, 4, 0, "" }, /* ndxterm */
768{ "tertiary ", 0, 0, 0, 4, 0, "" }, /* ndxterm */
769{ "textobject", 0, 0, 0, 9, 0, "" }, /* objectinfo */
770{ "tfoot", 0, 0, 0, 9, 0, "" }, /* tbl.hdft.mdl */
771{ "tgroup", 0, 0, 0, 9, 0, "" }, /* tbl.tgroup.mdl */
772{ "tgroup", 0, 0, 0, 9, 0, "" }, /* tbl.tgroup.mdl */
773{ "thead", 0, 0, 0, 9, 0, "" }, /* row */
774{ "thead", 0, 0, 0, 9, 0, "" }, /* tbl.hdft.mdl */
775{ "tip", 0, 0, 0, 9, 0, "" }, /* title */
776{ "titleabbrev",0, 0, 0, 8, 0, "" }, /* title */
777{ "title", 0, 0, 0, 8, 0, "" }, /* title */
778{ "tocback", 0, 0, 0, 2, 0, "" }, /* para */
779{ "toc", 0, 0, 0, 9, 0, "" }, /* bookcomponent.title.content */
780{ "tocchap", 0, 0, 0, 9, 0, "" }, /* tocentry */
781{ "tocentry", 0, 0, 0, 2, 0, "" }, /* para */
782{ "tocfront", 0, 0, 0, 2, 0, "" }, /* para */
783{ "toclevel1", 0, 0, 0, 9, 0, "" }, /* tocentry */
784{ "toclevel2", 0, 0, 0, 9, 0, "" }, /* tocentry */
785{ "toclevel3", 0, 0, 0, 9, 0, "" }, /* tocentry */
786{ "toclevel4", 0, 0, 0, 9, 0, "" }, /* tocentry */
787{ "toclevel5", 0, 0, 0, 9, 0, "" }, /* tocentry */
788{ "tocpart", 0, 0, 0, 9, 0, "" }, /* tocentry */
789{ "token", 0, 0, 0, 7, 0, "" }, /* smallcptr */
790{ "trademark", 0, 0, 0, 1, 0, "" },
791{ "type", 0, 0, 0, 7, 0, "" }, /* smallcptr */
792{ "ulink", 0, 0, 0, 2, 0, "" }, /* para */
793{ "userinput", 0, 0, 0, 9, 0, "" }, /* cptr */
794{ "varargs", 0, 2, 1, 0, 0, "" },
795{ "variablelist",0, 0, 0, 9, 0, "" }, /* formalobject.title.content */
796{ "varlistentry",0, 0, 0, 9, 0, "" }, /* term */
797{ "varname", 0, 0, 0, 7, 0, "" }, /* smallcptr */
798{ "videodata", 0, 2, 1, 0, 0, "" },
799{ "videoobject",0, 0, 0, 9, 0, "" }, /* objectinfo */
800{ "void", 0, 2, 1, 0, 0, "" },
801{ "volumenum", 0, 0, 0, 4, 0, "" }, /* docinfo */
802{ "warning", 0, 0, 0, 9, 0, "" }, /* title */
803{ "wordasword", 0, 0, 0, 3, 0, "" }, /* word */
804{ "xref", 0, 2, 1, 0, 0, "" },
805{ "year", 0, 0, 0, 4, 0, "" }, /* docinfo */
806};
807
808#if 0
809/*
810 * start tags that imply the end of a current element
811 * any tag of each line implies the end of the current element if the type of
812 * that element is in the same line
813 */
814static const char *docbEquEnd[] = {
815"dt", "dd", "li", "option", NULL,
816"h1", "h2", "h3", "h4", "h5", "h6", NULL,
817"ol", "menu", "dir", "address", "pre", "listing", "xmp", NULL,
818NULL
819};
820#endif
821
822/*
823 * acording the SGML DTD, HR should be added to the 2nd line above, as it
824 * is not allowed within a H1, H2, H3, etc. But we should tolerate that case
825 * because many documents contain rules in headings...
826 */
827
828/*
829 * start tags that imply the end of current element
830 */
831static const char *docbStartClose[] = {
832NULL
833};
834
835/*
836 * The list of SGML elements which are supposed not to have
837 * CDATA content and where a p element will be implied
838 *
839 * TODO: extend that list by reading the SGML SGML DtD on
840 * implied paragraph
841 */
842static char *docbNoContentElements[] = {
843 NULL
844};
845
846
847static const char** docbStartCloseIndex[100];
848static int docbStartCloseIndexinitialized = 0;
849
850/************************************************************************
851 * *
852 * functions to handle SGML specific data *
853 * *
854 ************************************************************************/
855
856/**
857 * docbInitAutoClose:
858 *
859 * Initialize the docbStartCloseIndex for fast lookup of closing tags names.
860 *
861 */
862static void
863docbInitAutoClose(void) {
864 int indx, i = 0;
865
866 if (docbStartCloseIndexinitialized) return;
867
868 for (indx = 0;indx < 100;indx ++) docbStartCloseIndex[indx] = NULL;
869 indx = 0;
870 while ((docbStartClose[i] != NULL) && (indx < 100 - 1)) {
871 docbStartCloseIndex[indx++] = &docbStartClose[i];
872 while (docbStartClose[i] != NULL) i++;
873 i++;
874 }
875}
876
877/**
878 * docbTagLookup:
879 * @tag: The tag name
880 *
881 * Lookup the SGML tag in the ElementTable
882 *
883 * Returns the related docbElemDescPtr or NULL if not found.
884 */
885static docbElemDescPtr
886docbTagLookup(const xmlChar *tag) {
887 unsigned int i;
888
889 for (i = 0; i < (sizeof(docbookElementTable) /
890 sizeof(docbookElementTable[0]));i++) {
891 if (xmlStrEqual(tag, BAD_CAST docbookElementTable[i].name))
892 return(&docbookElementTable[i]);
893 }
894 return(NULL);
895}
896
897/**
898 * docbCheckAutoClose:
899 * @newtag: The new tag name
900 * @oldtag: The old tag name
901 *
902 * Checks wether the new tag is one of the registered valid tags for closing old.
903 * Initialize the docbStartCloseIndex for fast lookup of closing tags names.
904 *
905 * Returns 0 if no, 1 if yes.
906 */
907static int
908docbCheckAutoClose(const xmlChar *newtag, const xmlChar *oldtag) {
909 int i, indx;
910 const char **closed = NULL;
911
912 if (docbStartCloseIndexinitialized == 0) docbInitAutoClose();
913
914 /* inefficient, but not a big deal */
915 for (indx = 0; indx < 100;indx++) {
916 closed = docbStartCloseIndex[indx];
917 if (closed == NULL) return(0);
918 if (xmlStrEqual(BAD_CAST *closed, newtag)) break;
919 }
920
921 i = closed - docbStartClose;
922 i++;
923 while (docbStartClose[i] != NULL) {
924 if (xmlStrEqual(BAD_CAST docbStartClose[i], oldtag)) {
925 return(1);
926 }
927 i++;
928 }
929 return(0);
930}
931
932/**
933 * docbAutoCloseOnClose:
934 * @ctxt: an SGML parser context
935 * @newtag: The new tag name
936 *
937 * The HTmL DtD allows an ending tag to implicitely close other tags.
938 */
939static void
940docbAutoCloseOnClose(docbParserCtxtPtr ctxt, const xmlChar *newtag) {
941 docbElemDescPtr info;
942 xmlChar *oldname;
943 int i;
944
945 if ((newtag[0] == '/') && (newtag[1] == 0))
946 return;
947
948#ifdef DEBUG
949 xmlGenericError(xmlGenericErrorContext,"Close of %s stack: %d elements\n", newtag, ctxt->nameNr);
950 for (i = 0;i < ctxt->nameNr;i++)
951 xmlGenericError(xmlGenericErrorContext,"%d : %s\n", i, ctxt->nameTab[i]);
952#endif
953
954 for (i = (ctxt->nameNr - 1);i >= 0;i--) {
955 if (xmlStrEqual(newtag, ctxt->nameTab[i])) break;
956 }
957 if (i < 0) return;
958
959 while (!xmlStrEqual(newtag, ctxt->name)) {
960 info = docbTagLookup(ctxt->name);
961 if ((info == NULL) || (info->endTag == 1)) {
962#ifdef DEBUG
963 xmlGenericError(xmlGenericErrorContext,"docbAutoCloseOnClose: %s closes %s\n", newtag, ctxt->name);
964#endif
965 } else {
966 if ((ctxt->sax != NULL) && (ctxt->sax->error != NULL))
967 ctxt->sax->error(ctxt->userData,
968 "Opening and ending tag mismatch: %s and %s\n",
969 newtag, ctxt->name);
970 ctxt->wellFormed = 0;
971 }
972 if ((ctxt->sax != NULL) && (ctxt->sax->endElement != NULL))
973 ctxt->sax->endElement(ctxt->userData, ctxt->name);
974 oldname = docbnamePop(ctxt);
975 if (oldname != NULL) {
976#ifdef DEBUG
977 xmlGenericError(xmlGenericErrorContext,"docbAutoCloseOnClose: popped %s\n", oldname);
978#endif
979 xmlFree(oldname);
980 }
981 }
982}
983
984/**
985 * docbAutoClose:
986 * @ctxt: an SGML parser context
987 * @newtag: The new tag name or NULL
988 *
989 * The HTmL DtD allows a tag to implicitely close other tags.
990 * The list is kept in docbStartClose array. This function is
991 * called when a new tag has been detected and generates the
992 * appropriates closes if possible/needed.
993 * If newtag is NULL this mean we are at the end of the resource
994 * and we should check
995 */
996static void
997docbAutoClose(docbParserCtxtPtr ctxt, const xmlChar *newtag) {
998 xmlChar *oldname;
999 while ((newtag != NULL) && (ctxt->name != NULL) &&
1000 (docbCheckAutoClose(newtag, ctxt->name))) {
1001#ifdef DEBUG
1002 xmlGenericError(xmlGenericErrorContext,"docbAutoClose: %s closes %s\n", newtag, ctxt->name);
1003#endif
1004 if ((ctxt->sax != NULL) && (ctxt->sax->endElement != NULL))
1005 ctxt->sax->endElement(ctxt->userData, ctxt->name);
1006 oldname = docbnamePop(ctxt);
1007 if (oldname != NULL) {
1008#ifdef DEBUG
1009 xmlGenericError(xmlGenericErrorContext,"docbAutoClose: popped %s\n", oldname);
1010#endif
1011 xmlFree(oldname);
1012 }
1013 }
1014}
1015
1016/**
1017 * docbAutoCloseTag:
1018 * @doc: the SGML document
1019 * @name: The tag name
1020 * @elem: the SGML element
1021 *
1022 * The HTmL DtD allows a tag to implicitely close other tags.
1023 * The list is kept in docbStartClose array. This function checks
1024 * if the element or one of it's children would autoclose the
1025 * given tag.
1026 *
1027 * Returns 1 if autoclose, 0 otherwise
1028 */
1029static int
1030docbAutoCloseTag(docbDocPtr doc, const xmlChar *name, docbNodePtr elem) {
1031 docbNodePtr child;
1032
1033 if (elem == NULL) return(1);
1034 if (xmlStrEqual(name, elem->name)) return(0);
1035 if (docbCheckAutoClose(elem->name, name)) return(1);
1036 child = elem->children;
1037 while (child != NULL) {
1038 if (docbAutoCloseTag(doc, name, child)) return(1);
1039 child = child->next;
1040 }
1041 return(0);
1042}
1043
1044#if 0
1045/**
1046 * docbIsAutoClosed:
1047 * @doc: the SGML document
1048 * @elem: the SGML element
1049 *
1050 * The list is kept in docbStartClose array. This function checks
1051 * if a tag is autoclosed by one of it's child
1052 *
1053 * Returns 1 if autoclosed, 0 otherwise
1054 */
1055static int
1056docbIsAutoClosed(docbDocPtr doc, docbNodePtr elem) {
1057 docbNodePtr child;
1058
1059 if (elem == NULL) return(1);
1060 child = elem->children;
1061 while (child != NULL) {
1062 if (docbAutoCloseTag(doc, elem->name, child)) return(1);
1063 child = child->next;
1064 }
1065 return(0);
1066}
1067#endif
1068
1069/**
1070 * docbCheckParagraph
1071 * @ctxt: an SGML parser context
1072 *
1073 * Check whether a p element need to be implied before inserting
1074 * characters in the current element.
1075 *
1076 * Returns 1 if a paragraph has been inserted, 0 if not and -1
1077 * in case of error.
1078 */
1079
1080static int
1081docbCheckParagraph(docbParserCtxtPtr ctxt) {
1082 const xmlChar *tag;
1083 int i;
1084
1085 if (ctxt == NULL)
1086 return(-1);
1087 tag = ctxt->name;
1088 if (tag == NULL) {
1089 docbAutoClose(ctxt, BAD_CAST"p");
1090 docbnamePush(ctxt, xmlStrdup(BAD_CAST"p"));
1091 if ((ctxt->sax != NULL) && (ctxt->sax->startElement != NULL))
1092 ctxt->sax->startElement(ctxt->userData, BAD_CAST"p", NULL);
1093 return(1);
1094 }
1095 for (i = 0; docbNoContentElements[i] != NULL; i++) {
1096 if (xmlStrEqual(tag, BAD_CAST docbNoContentElements[i])) {
1097#ifdef DEBUG
1098 xmlGenericError(xmlGenericErrorContext,"Implied element paragraph\n");
1099#endif
1100 docbAutoClose(ctxt, BAD_CAST"p");
1101 docbnamePush(ctxt, xmlStrdup(BAD_CAST"p"));
1102 if ((ctxt->sax != NULL) && (ctxt->sax->startElement != NULL))
1103 ctxt->sax->startElement(ctxt->userData, BAD_CAST"p", NULL);
1104 return(1);
1105 }
1106 }
1107 return(0);
1108}
1109
1110/************************************************************************
1111 * *
1112 * The list of SGML predefined entities *
1113 * *
1114 ************************************************************************/
1115
1116
1117static docbEntityDesc
1118docbookEntitiesTable[] = {
1119/*
1120 * the 4 absolute ones, plus apostrophe.
1121 */
1122{ 0x0026, "amp", "AMPERSAND" },
1123{ 0x003C, "lt", "LESS-THAN SIGN" },
1124
1125/*
1126 * Converted with VI macros from docbook ent files
1127 */
1128{ 0x0021, "excl", "EXCLAMATION MARK" },
1129{ 0x0022, "quot", "QUOTATION MARK" },
1130{ 0x0023, "num", "NUMBER SIGN" },
1131{ 0x0024, "dollar", "DOLLAR SIGN" },
1132{ 0x0025, "percnt", "PERCENT SIGN" },
1133{ 0x0027, "apos", "APOSTROPHE" },
1134{ 0x0028, "lpar", "LEFT PARENTHESIS" },
1135{ 0x0029, "rpar", "RIGHT PARENTHESIS" },
1136{ 0x002A, "ast", "ASTERISK OPERATOR" },
1137{ 0x002B, "plus", "PLUS SIGN" },
1138{ 0x002C, "comma", "COMMA" },
1139{ 0x002D, "hyphen", "HYPHEN-MINUS" },
1140{ 0x002E, "period", "FULL STOP" },
1141{ 0x002F, "sol", "SOLIDUS" },
1142{ 0x003A, "colon", "COLON" },
1143{ 0x003B, "semi", "SEMICOLON" },
1144{ 0x003D, "equals", "EQUALS SIGN" },
1145{ 0x003E, "gt", "GREATER-THAN SIGN" },
1146{ 0x003F, "quest", "QUESTION MARK" },
1147{ 0x0040, "commat", "COMMERCIAL AT" },
1148{ 0x005B, "lsqb", "LEFT SQUARE BRACKET" },
1149{ 0x005C, "bsol", "REVERSE SOLIDUS" },
1150{ 0x005D, "rsqb", "RIGHT SQUARE BRACKET" },
1151{ 0x005E, "circ", "RING OPERATOR" },
1152{ 0x005F, "lowbar", "LOW LINE" },
1153{ 0x0060, "grave", "GRAVE ACCENT" },
1154{ 0x007B, "lcub", "LEFT CURLY BRACKET" },
1155{ 0x007C, "verbar", "VERTICAL LINE" },
1156{ 0x007D, "rcub", "RIGHT CURLY BRACKET" },
1157{ 0x00A0, "nbsp", "NO-BREAK SPACE" },
1158{ 0x00A1, "iexcl", "INVERTED EXCLAMATION MARK" },
1159{ 0x00A2, "cent", "CENT SIGN" },
1160{ 0x00A3, "pound", "POUND SIGN" },
1161{ 0x00A4, "curren", "CURRENCY SIGN" },
1162{ 0x00A5, "yen", "YEN SIGN" },
1163{ 0x00A6, "brvbar", "BROKEN BAR" },
1164{ 0x00A7, "sect", "SECTION SIGN" },
1165{ 0x00A8, "die", "" },
1166{ 0x00A8, "Dot", "" },
1167{ 0x00A8, "uml", "" },
1168{ 0x00A9, "copy", "COPYRIGHT SIGN" },
1169{ 0x00AA, "ordf", "FEMININE ORDINAL INDICATOR" },
1170{ 0x00AB, "laquo", "LEFT-POINTING DOUBLE ANGLE QUOTATION MARK" },
1171{ 0x00AC, "not", "NOT SIGN" },
1172{ 0x00AD, "shy", "SOFT HYPHEN" },
1173{ 0x00AE, "reg", "REG TRADE MARK SIGN" },
1174{ 0x00AF, "macr", "MACRON" },
1175{ 0x00B0, "deg", "DEGREE SIGN" },
1176{ 0x00B1, "plusmn", "PLUS-MINUS SIGN" },
1177{ 0x00B2, "sup2", "SUPERSCRIPT TWO" },
1178{ 0x00B3, "sup3", "SUPERSCRIPT THREE" },
1179{ 0x00B4, "acute", "ACUTE ACCENT" },
1180{ 0x00B5, "micro", "MICRO SIGN" },
1181{ 0x00B6, "para", "PILCROW SIGN" },
1182{ 0x00B7, "middot", "MIDDLE DOT" },
1183{ 0x00B8, "cedil", "CEDILLA" },
1184{ 0x00B9, "sup1", "SUPERSCRIPT ONE" },
1185{ 0x00BA, "ordm", "MASCULINE ORDINAL INDICATOR" },
1186{ 0x00BB, "raquo", "RIGHT-POINTING DOUBLE ANGLE QUOTATION MARK" },
1187{ 0x00BC, "frac14", "VULGAR FRACTION ONE QUARTER" },
1188{ 0x00BD, "frac12", "VULGAR FRACTION ONE HALF" },
1189{ 0x00BD, "half", "VULGAR FRACTION ONE HALF" },
1190{ 0x00BE, "frac34", "VULGAR FRACTION THREE QUARTERS" },
1191{ 0x00BF, "iquest", "INVERTED QUESTION MARK" },
1192{ 0x00C0, "Agrave", "LATIN CAPITAL LETTER A WITH GRAVE" },
1193{ 0x00C1, "Aacute", "LATIN CAPITAL LETTER A WITH ACUTE" },
1194{ 0x00C2, "Acirc", "LATIN CAPITAL LETTER A WITH CIRCUMFLEX" },
1195{ 0x00C3, "Atilde", "LATIN CAPITAL LETTER A WITH TILDE" },
1196{ 0x00C4, "Auml", "LATIN CAPITAL LETTER A WITH DIAERESIS" },
1197{ 0x00C5, "Aring", "LATIN CAPITAL LETTER A WITH RING ABOVE" },
1198{ 0x00C6, "AElig", "LATIN CAPITAL LETTER AE" },
1199{ 0x00C7, "Ccedil", "LATIN CAPITAL LETTER C WITH CEDILLA" },
1200{ 0x00C8, "Egrave", "LATIN CAPITAL LETTER E WITH GRAVE" },
1201{ 0x00C9, "Eacute", "LATIN CAPITAL LETTER E WITH ACUTE" },
1202{ 0x00CA, "Ecirc", "LATIN CAPITAL LETTER E WITH CIRCUMFLEX" },
1203{ 0x00CB, "Euml", "LATIN CAPITAL LETTER E WITH DIAERESIS" },
1204{ 0x00CC, "Igrave", "LATIN CAPITAL LETTER I WITH GRAVE" },
1205{ 0x00CD, "Iacute", "LATIN CAPITAL LETTER I WITH ACUTE" },
1206{ 0x00CE, "Icirc", "LATIN CAPITAL LETTER I WITH CIRCUMFLEX" },
1207{ 0x00CF, "Iuml", "LATIN CAPITAL LETTER I WITH DIAERESIS" },
1208{ 0x00D0, "ETH", "LATIN CAPITAL LETTER ETH" },
1209{ 0x00D1, "Ntilde", "LATIN CAPITAL LETTER N WITH TILDE" },
1210{ 0x00D2, "Ograve", "LATIN CAPITAL LETTER O WITH GRAVE" },
1211{ 0x00D3, "Oacute", "LATIN CAPITAL LETTER O WITH ACUTE" },
1212{ 0x00D4, "Ocirc", "LATIN CAPITAL LETTER O WITH CIRCUMFLEX" },
1213{ 0x00D5, "Otilde", "LATIN CAPITAL LETTER O WITH TILDE" },
1214{ 0x00D6, "Ouml", "LATIN CAPITAL LETTER O WITH DIAERESIS" },
1215{ 0x00D7, "times", "MULTIPLICATION SIGN" },
1216{ 0x00D8, "Oslash", "LATIN CAPITAL LETTER O WITH STROKE" },
1217{ 0x00D9, "Ugrave", "LATIN CAPITAL LETTER U WITH GRAVE" },
1218{ 0x00DA, "Uacute", "LATIN CAPITAL LETTER U WITH ACUTE" },
1219{ 0x00DB, "Ucirc", "LATIN CAPITAL LETTER U WITH CIRCUMFLEX" },
1220{ 0x00DC, "Uuml", "LATIN CAPITAL LETTER U WITH DIAERESIS" },
1221{ 0x00DD, "Yacute", "LATIN CAPITAL LETTER Y WITH ACUTE" },
1222{ 0x00DE, "THORN", "LATIN CAPITAL LETTER THORN" },
1223{ 0x00DF, "szlig", "LATIN SMALL LETTER SHARP S" },
1224{ 0x00E0, "agrave", "LATIN SMALL LETTER A WITH GRAVE" },
1225{ 0x00E1, "aacute", "LATIN SMALL LETTER A WITH ACUTE" },
1226{ 0x00E2, "acirc", "LATIN SMALL LETTER A WITH CIRCUMFLEX" },
1227{ 0x00E3, "atilde", "LATIN SMALL LETTER A WITH TILDE" },
1228{ 0x00E4, "auml", "LATIN SMALL LETTER A WITH DIAERESIS" },
1229{ 0x00E5, "aring", "LATIN SMALL LETTER A WITH RING ABOVE" },
1230{ 0x00E6, "aelig", "LATIN SMALL LETTER AE" },
1231{ 0x00E7, "ccedil", "LATIN SMALL LETTER C WITH CEDILLA" },
1232{ 0x00E8, "egrave", "LATIN SMALL LETTER E WITH GRAVE" },
1233{ 0x00E9, "eacute", "LATIN SMALL LETTER E WITH ACUTE" },
1234{ 0x00EA, "ecirc", "LATIN SMALL LETTER E WITH CIRCUMFLEX" },
1235{ 0x00EB, "euml", "LATIN SMALL LETTER E WITH DIAERESIS" },
1236{ 0x00EC, "igrave", "LATIN SMALL LETTER I WITH GRAVE" },
1237{ 0x00ED, "iacute", "LATIN SMALL LETTER I WITH ACUTE" },
1238{ 0x00EE, "icirc", "LATIN SMALL LETTER I WITH CIRCUMFLEX" },
1239{ 0x00EF, "iuml", "LATIN SMALL LETTER I WITH DIAERESIS" },
1240{ 0x00F0, "eth", "LATIN SMALL LETTER ETH" },
1241{ 0x00F1, "ntilde", "LATIN SMALL LETTER N WITH TILDE" },
1242{ 0x00F2, "ograve", "LATIN SMALL LETTER O WITH GRAVE" },
1243{ 0x00F3, "oacute", "LATIN SMALL LETTER O WITH ACUTE" },
1244{ 0x00F4, "ocirc", "LATIN SMALL LETTER O WITH CIRCUMFLEX" },
1245{ 0x00F5, "otilde", "LATIN SMALL LETTER O WITH TILDE" },
1246{ 0x00F6, "ouml", "LATIN SMALL LETTER O WITH DIAERESIS" },
1247{ 0x00F7, "divide", "DIVISION SIGN" },
1248{ 0x00F8, "oslash", "CIRCLED DIVISION SLASH" },
1249{ 0x00F9, "ugrave", "LATIN SMALL LETTER U WITH GRAVE" },
1250{ 0x00FA, "uacute", "LATIN SMALL LETTER U WITH ACUTE" },
1251{ 0x00FB, "ucirc", "LATIN SMALL LETTER U WITH CIRCUMFLEX" },
1252{ 0x00FC, "uuml", "LATIN SMALL LETTER U WITH DIAERESIS" },
1253{ 0x00FD, "yacute", "LATIN SMALL LETTER Y WITH ACUTE" },
1254{ 0x00FE, "thorn", "LATIN SMALL LETTER THORN" },
1255{ 0x00FF, "yuml", "LATIN SMALL LETTER Y WITH DIAERESIS" },
1256{ 0x0100, "Amacr", "LATIN CAPITAL LETTER A WITH MACRON" },
1257{ 0x0101, "amacr", "LATIN SMALL LETTER A WITH MACRON" },
1258{ 0x0102, "Abreve", "LATIN CAPITAL LETTER A WITH BREVE" },
1259{ 0x0103, "abreve", "LATIN SMALL LETTER A WITH BREVE" },
1260{ 0x0104, "Aogon", "LATIN CAPITAL LETTER A WITH OGONEK" },
1261{ 0x0105, "aogon", "LATIN SMALL LETTER A WITH OGONEK" },
1262{ 0x0106, "Cacute", "LATIN CAPITAL LETTER C WITH ACUTE" },
1263{ 0x0107, "cacute", "LATIN SMALL LETTER C WITH ACUTE" },
1264{ 0x0108, "Ccirc", "LATIN CAPITAL LETTER C WITH CIRCUMFLEX" },
1265{ 0x0109, "ccirc", "LATIN SMALL LETTER C WITH CIRCUMFLEX" },
1266{ 0x010A, "Cdot", "LATIN CAPITAL LETTER C WITH DOT ABOVE" },
1267{ 0x010B, "cdot", "DOT OPERATOR" },
1268{ 0x010C, "Ccaron", "LATIN CAPITAL LETTER C WITH CARON" },
1269{ 0x010D, "ccaron", "LATIN SMALL LETTER C WITH CARON" },
1270{ 0x010E, "Dcaron", "LATIN CAPITAL LETTER D WITH CARON" },
1271{ 0x010F, "dcaron", "LATIN SMALL LETTER D WITH CARON" },
1272{ 0x0110, "Dstrok", "LATIN CAPITAL LETTER D WITH STROKE" },
1273{ 0x0111, "dstrok", "LATIN SMALL LETTER D WITH STROKE" },
1274{ 0x0112, "Emacr", "LATIN CAPITAL LETTER E WITH MACRON" },
1275{ 0x0113, "emacr", "LATIN SMALL LETTER E WITH MACRON" },
1276{ 0x0116, "Edot", "LATIN CAPITAL LETTER E WITH DOT ABOVE" },
1277{ 0x0117, "edot", "LATIN SMALL LETTER E WITH DOT ABOVE" },
1278{ 0x0118, "Eogon", "LATIN CAPITAL LETTER E WITH OGONEK" },
1279{ 0x0119, "eogon", "LATIN SMALL LETTER E WITH OGONEK" },
1280{ 0x011A, "Ecaron", "LATIN CAPITAL LETTER E WITH CARON" },
1281{ 0x011B, "ecaron", "LATIN SMALL LETTER E WITH CARON" },
1282{ 0x011C, "Gcirc", "LATIN CAPITAL LETTER G WITH CIRCUMFLEX" },
1283{ 0x011D, "gcirc", "LATIN SMALL LETTER G WITH CIRCUMFLEX" },
1284{ 0x011E, "Gbreve", "LATIN CAPITAL LETTER G WITH BREVE" },
1285{ 0x011F, "gbreve", "LATIN SMALL LETTER G WITH BREVE" },
1286{ 0x0120, "Gdot", "LATIN CAPITAL LETTER G WITH DOT ABOVE" },
1287{ 0x0121, "gdot", "LATIN SMALL LETTER G WITH DOT ABOVE" },
1288{ 0x0122, "Gcedil", "LATIN CAPITAL LETTER G WITH CEDILLA" },
1289{ 0x0124, "Hcirc", "LATIN CAPITAL LETTER H WITH CIRCUMFLEX" },
1290{ 0x0125, "hcirc", "LATIN SMALL LETTER H WITH CIRCUMFLEX" },
1291{ 0x0126, "Hstrok", "LATIN CAPITAL LETTER H WITH STROKE" },
1292{ 0x0127, "hstrok", "LATIN SMALL LETTER H WITH STROKE" },
1293{ 0x0128, "Itilde", "LATIN CAPITAL LETTER I WITH TILDE" },
1294{ 0x0129, "itilde", "LATIN SMALL LETTER I WITH TILDE" },
1295{ 0x012A, "Imacr", "LATIN CAPITAL LETTER I WITH MACRON" },
1296{ 0x012B, "imacr", "LATIN SMALL LETTER I WITH MACRON" },
1297{ 0x012E, "Iogon", "LATIN CAPITAL LETTER I WITH OGONEK" },
1298{ 0x012F, "iogon", "LATIN SMALL LETTER I WITH OGONEK" },
1299{ 0x0130, "Idot", "LATIN CAPITAL LETTER I WITH DOT ABOVE" },
1300{ 0x0131, "inodot", "LATIN SMALL LETTER DOTLESS I" },
1301{ 0x0131, "inodot", "LATIN SMALL LETTER DOTLESS I" },
1302{ 0x0132, "IJlig", "LATIN CAPITAL LIGATURE IJ" },
1303{ 0x0133, "ijlig", "LATIN SMALL LIGATURE IJ" },
1304{ 0x0134, "Jcirc", "LATIN CAPITAL LETTER J WITH CIRCUMFLEX" },
1305{ 0x0135, "jcirc", "LATIN SMALL LETTER J WITH CIRCUMFLEX" },
1306{ 0x0136, "Kcedil", "LATIN CAPITAL LETTER K WITH CEDILLA" },
1307{ 0x0137, "kcedil", "LATIN SMALL LETTER K WITH CEDILLA" },
1308{ 0x0138, "kgreen", "LATIN SMALL LETTER KRA" },
1309{ 0x0139, "Lacute", "LATIN CAPITAL LETTER L WITH ACUTE" },
1310{ 0x013A, "lacute", "LATIN SMALL LETTER L WITH ACUTE" },
1311{ 0x013B, "Lcedil", "LATIN CAPITAL LETTER L WITH CEDILLA" },
1312{ 0x013C, "lcedil", "LATIN SMALL LETTER L WITH CEDILLA" },
1313{ 0x013D, "Lcaron", "LATIN CAPITAL LETTER L WITH CARON" },
1314{ 0x013E, "lcaron", "LATIN SMALL LETTER L WITH CARON" },
1315{ 0x013F, "Lmidot", "LATIN CAPITAL LETTER L WITH MIDDLE DOT" },
1316{ 0x0140, "lmidot", "LATIN SMALL LETTER L WITH MIDDLE DOT" },
1317{ 0x0141, "Lstrok", "LATIN CAPITAL LETTER L WITH STROKE" },
1318{ 0x0142, "lstrok", "LATIN SMALL LETTER L WITH STROKE" },
1319{ 0x0143, "Nacute", "LATIN CAPITAL LETTER N WITH ACUTE" },
1320{ 0x0144, "nacute", "LATIN SMALL LETTER N WITH ACUTE" },
1321{ 0x0145, "Ncedil", "LATIN CAPITAL LETTER N WITH CEDILLA" },
1322{ 0x0146, "ncedil", "LATIN SMALL LETTER N WITH CEDILLA" },
1323{ 0x0147, "Ncaron", "LATIN CAPITAL LETTER N WITH CARON" },
1324{ 0x0148, "ncaron", "LATIN SMALL LETTER N WITH CARON" },
1325{ 0x0149, "napos", "LATIN SMALL LETTER N PRECEDED BY APOSTROPHE" },
1326{ 0x014A, "ENG", "LATIN CAPITAL LETTER ENG" },
1327{ 0x014B, "eng", "LATIN SMALL LETTER ENG" },
1328{ 0x014C, "Omacr", "LATIN CAPITAL LETTER O WITH MACRON" },
1329{ 0x014D, "omacr", "LATIN SMALL LETTER O WITH MACRON" },
1330{ 0x0150, "Odblac", "LATIN CAPITAL LETTER O WITH DOUBLE ACUTE" },
1331{ 0x0151, "odblac", "LATIN SMALL LETTER O WITH DOUBLE ACUTE" },
1332{ 0x0152, "OElig", "LATIN CAPITAL LIGATURE OE" },
1333{ 0x0153, "oelig", "LATIN SMALL LIGATURE OE" },
1334{ 0x0154, "Racute", "LATIN CAPITAL LETTER R WITH ACUTE" },
1335{ 0x0155, "racute", "LATIN SMALL LETTER R WITH ACUTE" },
1336{ 0x0156, "Rcedil", "LATIN CAPITAL LETTER R WITH CEDILLA" },
1337{ 0x0157, "rcedil", "LATIN SMALL LETTER R WITH CEDILLA" },
1338{ 0x0158, "Rcaron", "LATIN CAPITAL LETTER R WITH CARON" },
1339{ 0x0159, "rcaron", "LATIN SMALL LETTER R WITH CARON" },
1340{ 0x015A, "Sacute", "LATIN CAPITAL LETTER S WITH ACUTE" },
1341{ 0x015B, "sacute", "LATIN SMALL LETTER S WITH ACUTE" },
1342{ 0x015C, "Scirc", "LATIN CAPITAL LETTER S WITH CIRCUMFLEX" },
1343{ 0x015D, "scirc", "LATIN SMALL LETTER S WITH CIRCUMFLEX" },
1344{ 0x015E, "Scedil", "LATIN CAPITAL LETTER S WITH CEDILLA" },
1345{ 0x015F, "scedil", "LATIN SMALL LETTER S WITH CEDILLA" },
1346{ 0x0160, "Scaron", "LATIN CAPITAL LETTER S WITH CARON" },
1347{ 0x0161, "scaron", "LATIN SMALL LETTER S WITH CARON" },
1348{ 0x0162, "Tcedil", "LATIN CAPITAL LETTER T WITH CEDILLA" },
1349{ 0x0163, "tcedil", "LATIN SMALL LETTER T WITH CEDILLA" },
1350{ 0x0164, "Tcaron", "LATIN CAPITAL LETTER T WITH CARON" },
1351{ 0x0165, "tcaron", "LATIN SMALL LETTER T WITH CARON" },
1352{ 0x0166, "Tstrok", "LATIN CAPITAL LETTER T WITH STROKE" },
1353{ 0x0167, "tstrok", "LATIN SMALL LETTER T WITH STROKE" },
1354{ 0x0168, "Utilde", "LATIN CAPITAL LETTER U WITH TILDE" },
1355{ 0x0169, "utilde", "LATIN SMALL LETTER U WITH TILDE" },
1356{ 0x016A, "Umacr", "LATIN CAPITAL LETTER U WITH MACRON" },
1357{ 0x016B, "umacr", "LATIN SMALL LETTER U WITH MACRON" },
1358{ 0x016C, "Ubreve", "LATIN CAPITAL LETTER U WITH BREVE" },
1359{ 0x016D, "ubreve", "LATIN SMALL LETTER U WITH BREVE" },
1360{ 0x016E, "Uring", "LATIN CAPITAL LETTER U WITH RING ABOVE" },
1361{ 0x016F, "uring", "LATIN SMALL LETTER U WITH RING ABOVE" },
1362{ 0x0170, "Udblac", "LATIN CAPITAL LETTER U WITH DOUBLE ACUTE" },
1363{ 0x0171, "udblac", "LATIN SMALL LETTER U WITH DOUBLE ACUTE" },
1364{ 0x0172, "Uogon", "LATIN CAPITAL LETTER U WITH OGONEK" },
1365{ 0x0173, "uogon", "LATIN SMALL LETTER U WITH OGONEK" },
1366{ 0x0174, "Wcirc", "LATIN CAPITAL LETTER W WITH CIRCUMFLEX" },
1367{ 0x0175, "wcirc", "LATIN SMALL LETTER W WITH CIRCUMFLEX" },
1368{ 0x0176, "Ycirc", "LATIN CAPITAL LETTER Y WITH CIRCUMFLEX" },
1369{ 0x0177, "ycirc", "LATIN SMALL LETTER Y WITH CIRCUMFLEX" },
1370{ 0x0178, "Yuml", "LATIN CAPITAL LETTER Y WITH DIAERESIS" },
1371{ 0x0179, "Zacute", "LATIN CAPITAL LETTER Z WITH ACUTE" },
1372{ 0x017A, "zacute", "LATIN SMALL LETTER Z WITH ACUTE" },
1373{ 0x017B, "Zdot", "LATIN CAPITAL LETTER Z WITH DOT ABOVE" },
1374{ 0x017C, "zdot", "LATIN SMALL LETTER Z WITH DOT ABOVE" },
1375{ 0x017D, "Zcaron", "LATIN CAPITAL LETTER Z WITH CARON" },
1376{ 0x017E, "zcaron", "LATIN SMALL LETTER Z WITH CARON" },
1377{ 0x0192, "fnof", "LATIN SMALL LETTER F WITH HOOK" },
1378{ 0x01F5, "gacute", "LATIN SMALL LETTER G WITH ACUTE" },
1379{ 0x02C7, "caron", "CARON" },
1380{ 0x02D8, "breve", "BREVE" },
1381{ 0x02D9, "dot", "DOT ABOVE" },
1382{ 0x02DA, "ring", "RING ABOVE" },
1383{ 0x02DB, "ogon", "OGONEK" },
1384{ 0x02DC, "tilde", "TILDE" },
1385{ 0x02DD, "dblac", "DOUBLE ACUTE ACCENT" },
1386{ 0x0386, "Aacgr", "GREEK CAPITAL LETTER ALPHA WITH TONOS" },
1387{ 0x0388, "Eacgr", "GREEK CAPITAL LETTER EPSILON WITH TONOS" },
1388{ 0x0389, "EEacgr", "GREEK CAPITAL LETTER ETA WITH TONOS" },
1389{ 0x038A, "Iacgr", "GREEK CAPITAL LETTER IOTA WITH TONOS" },
1390{ 0x038C, "Oacgr", "GREEK CAPITAL LETTER OMICRON WITH TONOS" },
1391{ 0x038E, "Uacgr", "GREEK CAPITAL LETTER UPSILON WITH TONOS" },
1392{ 0x038F, "OHacgr", "GREEK CAPITAL LETTER OMEGA WITH TONOS" },
1393{ 0x0390, "idiagr", "GREEK SMALL LETTER IOTA WITH DIALYTIKA AND TONOS" },
1394{ 0x0391, "Agr", "GREEK CAPITAL LETTER ALPHA" },
1395{ 0x0392, "Bgr", "GREEK CAPITAL LETTER BETA" },
1396{ 0x0393, "b.Gamma", "GREEK CAPITAL LETTER GAMMA" },
1397{ 0x0393, "Gamma", "GREEK CAPITAL LETTER GAMMA" },
1398{ 0x0393, "Ggr", "GREEK CAPITAL LETTER GAMMA" },
1399{ 0x0394, "b.Delta", "GREEK CAPITAL LETTER DELTA" },
1400{ 0x0394, "Delta", "GREEK CAPITAL LETTER DELTA" },
1401{ 0x0394, "Dgr", "GREEK CAPITAL LETTER DELTA" },
1402{ 0x0395, "Egr", "GREEK CAPITAL LETTER EPSILON" },
1403{ 0x0396, "Zgr", "GREEK CAPITAL LETTER ZETA" },
1404{ 0x0397, "EEgr", "GREEK CAPITAL LETTER ETA" },
1405{ 0x0398, "b.Theta", "GREEK CAPITAL LETTER THETA" },
1406{ 0x0398, "Theta", "GREEK CAPITAL LETTER THETA" },
1407{ 0x0398, "THgr", "GREEK CAPITAL LETTER THETA" },
1408{ 0x0399, "Igr", "GREEK CAPITAL LETTER IOTA" },
1409{ 0x039A, "Kgr", "GREEK CAPITAL LETTER KAPPA" },
1410{ 0x039B, "b.Lambda", "GREEK CAPITAL LETTER LAMDA" },
1411{ 0x039B, "Lambda", "GREEK CAPITAL LETTER LAMDA" },
1412{ 0x039B, "Lgr", "GREEK CAPITAL LETTER LAMDA" },
1413{ 0x039C, "Mgr", "GREEK CAPITAL LETTER MU" },
1414{ 0x039D, "Ngr", "GREEK CAPITAL LETTER NU" },
1415{ 0x039E, "b.Xi", "GREEK CAPITAL LETTER XI" },
1416{ 0x039E, "Xgr", "GREEK CAPITAL LETTER XI" },
1417{ 0x039E, "Xi", "GREEK CAPITAL LETTER XI" },
1418{ 0x039F, "Ogr", "GREEK CAPITAL LETTER OMICRON" },
1419{ 0x03A0, "b.Pi", "GREEK CAPITAL LETTER PI" },
1420{ 0x03A0, "Pgr", "GREEK CAPITAL LETTER PI" },
1421{ 0x03A0, "Pi", "GREEK CAPITAL LETTER PI" },
1422{ 0x03A1, "Rgr", "GREEK CAPITAL LETTER RHO" },
1423{ 0x03A3, "b.Sigma", "GREEK CAPITAL LETTER SIGMA" },
1424{ 0x03A3, "Sgr", "GREEK CAPITAL LETTER SIGMA" },
1425{ 0x03A3, "Sigma", "GREEK CAPITAL LETTER SIGMA" },
1426{ 0x03A4, "Tgr", "GREEK CAPITAL LETTER TAU" },
1427{ 0x03A5, "Ugr", "" },
1428{ 0x03A6, "b.Phi", "GREEK CAPITAL LETTER PHI" },
1429{ 0x03A6, "PHgr", "GREEK CAPITAL LETTER PHI" },
1430{ 0x03A6, "Phi", "GREEK CAPITAL LETTER PHI" },
1431{ 0x03A7, "KHgr", "GREEK CAPITAL LETTER CHI" },
1432{ 0x03A8, "b.Psi", "GREEK CAPITAL LETTER PSI" },
1433{ 0x03A8, "PSgr", "GREEK CAPITAL LETTER PSI" },
1434{ 0x03A8, "Psi", "GREEK CAPITAL LETTER PSI" },
1435{ 0x03A9, "b.Omega", "GREEK CAPITAL LETTER OMEGA" },
1436{ 0x03A9, "OHgr", "GREEK CAPITAL LETTER OMEGA" },
1437{ 0x03A9, "Omega", "GREEK CAPITAL LETTER OMEGA" },
1438{ 0x03AA, "Idigr", "GREEK CAPITAL LETTER IOTA WITH DIALYTIKA" },
1439{ 0x03AB, "Udigr", "GREEK CAPITAL LETTER UPSILON WITH DIALYTIKA" },
1440{ 0x03AC, "aacgr", "GREEK SMALL LETTER ALPHA WITH TONOS" },
1441{ 0x03AD, "eacgr", "GREEK SMALL LETTER EPSILON WITH TONOS" },
1442{ 0x03AE, "eeacgr", "GREEK SMALL LETTER ETA WITH TONOS" },
1443{ 0x03AF, "iacgr", "GREEK SMALL LETTER IOTA WITH TONOS" },
1444{ 0x03B0, "udiagr", "GREEK SMALL LETTER UPSILON WITH DIALYTIKA AND TONOS" },
1445{ 0x03B1, "agr", "" },
1446{ 0x03B1, "alpha", "" },
1447{ 0x03B1, "b.alpha", "" },
1448{ 0x03B2, "b.beta", "GREEK SMALL LETTER BETA" },
1449{ 0x03B2, "beta", "GREEK SMALL LETTER BETA" },
1450{ 0x03B2, "bgr", "GREEK SMALL LETTER BETA" },
1451{ 0x03B3, "b.gamma", "GREEK SMALL LETTER GAMMA" },
1452{ 0x03B3, "gamma", "GREEK SMALL LETTER GAMMA" },
1453{ 0x03B3, "ggr", "GREEK SMALL LETTER GAMMA" },
1454{ 0x03B4, "b.delta", "GREEK SMALL LETTER DELTA" },
1455{ 0x03B4, "delta", "GREEK SMALL LETTER DELTA" },
1456{ 0x03B4, "dgr", "GREEK SMALL LETTER DELTA" },
1457{ 0x03B5, "b.epsi", "" },
1458{ 0x03B5, "b.epsis", "" },
1459{ 0x03B5, "b.epsiv", "" },
1460{ 0x03B5, "egr", "" },
1461{ 0x03B5, "epsiv", "" },
1462{ 0x03B6, "b.zeta", "GREEK SMALL LETTER ZETA" },
1463{ 0x03B6, "zeta", "GREEK SMALL LETTER ZETA" },
1464{ 0x03B6, "zgr", "GREEK SMALL LETTER ZETA" },
1465{ 0x03B7, "b.eta", "GREEK SMALL LETTER ETA" },
1466{ 0x03B7, "eegr", "GREEK SMALL LETTER ETA" },
1467{ 0x03B7, "eta", "GREEK SMALL LETTER ETA" },
1468{ 0x03B8, "b.thetas", "" },
1469{ 0x03B8, "thetas", "" },
1470{ 0x03B8, "thgr", "" },
1471{ 0x03B9, "b.iota", "GREEK SMALL LETTER IOTA" },
1472{ 0x03B9, "igr", "GREEK SMALL LETTER IOTA" },
1473{ 0x03B9, "iota", "GREEK SMALL LETTER IOTA" },
1474{ 0x03BA, "b.kappa", "GREEK SMALL LETTER KAPPA" },
1475{ 0x03BA, "kappa", "GREEK SMALL LETTER KAPPA" },
1476{ 0x03BA, "kgr", "GREEK SMALL LETTER KAPPA" },
1477{ 0x03BB, "b.lambda", "GREEK SMALL LETTER LAMDA" },
1478{ 0x03BB, "lambda", "GREEK SMALL LETTER LAMDA" },
1479{ 0x03BB, "lgr", "GREEK SMALL LETTER LAMDA" },
1480{ 0x03BC, "b.mu", "GREEK SMALL LETTER MU" },
1481{ 0x03BC, "mgr", "GREEK SMALL LETTER MU" },
1482{ 0x03BC, "mu", "GREEK SMALL LETTER MU" },
1483{ 0x03BD, "b.nu", "GREEK SMALL LETTER NU" },
1484{ 0x03BD, "ngr", "GREEK SMALL LETTER NU" },
1485{ 0x03BD, "nu", "GREEK SMALL LETTER NU" },
1486{ 0x03BE, "b.xi", "GREEK SMALL LETTER XI" },
1487{ 0x03BE, "xgr", "GREEK SMALL LETTER XI" },
1488{ 0x03BE, "xi", "GREEK SMALL LETTER XI" },
1489{ 0x03BF, "ogr", "GREEK SMALL LETTER OMICRON" },
1490{ 0x03C0, "b.pi", "GREEK SMALL LETTER PI" },
1491{ 0x03C0, "pgr", "GREEK SMALL LETTER PI" },
1492{ 0x03C0, "pi", "GREEK SMALL LETTER PI" },
1493{ 0x03C1, "b.rho", "GREEK SMALL LETTER RHO" },
1494{ 0x03C1, "rgr", "GREEK SMALL LETTER RHO" },
1495{ 0x03C1, "rho", "GREEK SMALL LETTER RHO" },
1496{ 0x03C2, "b.sigmav", "" },
1497{ 0x03C2, "sfgr", "" },
1498{ 0x03C2, "sigmav", "" },
1499{ 0x03C3, "b.sigma", "GREEK SMALL LETTER SIGMA" },
1500{ 0x03C3, "sgr", "GREEK SMALL LETTER SIGMA" },
1501{ 0x03C3, "sigma", "GREEK SMALL LETTER SIGMA" },
1502{ 0x03C4, "b.tau", "GREEK SMALL LETTER TAU" },
1503{ 0x03C4, "tau", "GREEK SMALL LETTER TAU" },
1504{ 0x03C4, "tgr", "GREEK SMALL LETTER TAU" },
1505{ 0x03C5, "b.upsi", "GREEK SMALL LETTER UPSILON" },
1506{ 0x03C5, "ugr", "GREEK SMALL LETTER UPSILON" },
1507{ 0x03C5, "upsi", "GREEK SMALL LETTER UPSILON" },
1508{ 0x03C6, "b.phis", "GREEK SMALL LETTER PHI" },
1509{ 0x03C6, "phgr", "GREEK SMALL LETTER PHI" },
1510{ 0x03C6, "phis", "GREEK SMALL LETTER PHI" },
1511{ 0x03C7, "b.chi", "GREEK SMALL LETTER CHI" },
1512{ 0x03C7, "chi", "GREEK SMALL LETTER CHI" },
1513{ 0x03C7, "khgr", "GREEK SMALL LETTER CHI" },
1514{ 0x03C8, "b.psi", "GREEK SMALL LETTER PSI" },
1515{ 0x03C8, "psgr", "GREEK SMALL LETTER PSI" },
1516{ 0x03C8, "psi", "GREEK SMALL LETTER PSI" },
1517{ 0x03C9, "b.omega", "GREEK SMALL LETTER OMEGA" },
1518{ 0x03C9, "ohgr", "GREEK SMALL LETTER OMEGA" },
1519{ 0x03C9, "omega", "GREEK SMALL LETTER OMEGA" },
1520{ 0x03CA, "idigr", "GREEK SMALL LETTER IOTA WITH DIALYTIKA" },
1521{ 0x03CB, "udigr", "GREEK SMALL LETTER UPSILON WITH DIALYTIKA" },
1522{ 0x03CC, "oacgr", "GREEK SMALL LETTER OMICRON WITH TONOS" },
1523{ 0x03CD, "uacgr", "GREEK SMALL LETTER UPSILON WITH TONOS" },
1524{ 0x03CE, "ohacgr", "GREEK SMALL LETTER OMEGA WITH TONOS" },
1525{ 0x03D1, "b.thetav", "" },
1526{ 0x03D1, "thetav", "" },
1527{ 0x03D2, "b.Upsi", "" },
1528{ 0x03D2, "Upsi", "" },
1529{ 0x03D5, "b.phiv", "GREEK PHI SYMBOL" },
1530{ 0x03D5, "phiv", "GREEK PHI SYMBOL" },
1531{ 0x03D6, "b.piv", "GREEK PI SYMBOL" },
1532{ 0x03D6, "piv", "GREEK PI SYMBOL" },
1533{ 0x03DC, "b.gammad", "GREEK LETTER DIGAMMA" },
1534{ 0x03DC, "gammad", "GREEK LETTER DIGAMMA" },
1535{ 0x03F0, "b.kappav", "GREEK KAPPA SYMBOL" },
1536{ 0x03F0, "kappav", "GREEK KAPPA SYMBOL" },
1537{ 0x03F1, "b.rhov", "GREEK RHO SYMBOL" },
1538{ 0x03F1, "rhov", "GREEK RHO SYMBOL" },
1539{ 0x0401, "IOcy", "CYRILLIC CAPITAL LETTER IO" },
1540{ 0x0402, "DJcy", "CYRILLIC CAPITAL LETTER DJE" },
1541{ 0x0403, "GJcy", "CYRILLIC CAPITAL LETTER GJE" },
1542{ 0x0404, "Jukcy", "CYRILLIC CAPITAL LETTER UKRAINIAN IE" },
1543{ 0x0405, "DScy", "CYRILLIC CAPITAL LETTER DZE" },
1544{ 0x0406, "Iukcy", "CYRILLIC CAPITAL LETTER BYELORUSSIAN-UKRAINIAN I" },
1545{ 0x0407, "YIcy", "CYRILLIC CAPITAL LETTER YI" },
1546{ 0x0408, "Jsercy", "CYRILLIC CAPITAL LETTER JE" },
1547{ 0x0409, "LJcy", "CYRILLIC CAPITAL LETTER LJE" },
1548{ 0x040A, "NJcy", "CYRILLIC CAPITAL LETTER NJE" },
1549{ 0x040B, "TSHcy", "CYRILLIC CAPITAL LETTER TSHE" },
1550{ 0x040C, "KJcy", "CYRILLIC CAPITAL LETTER KJE" },
1551{ 0x040E, "Ubrcy", "CYRILLIC CAPITAL LETTER SHORT U" },
1552{ 0x040F, "DZcy", "CYRILLIC CAPITAL LETTER DZHE" },
1553{ 0x0410, "Acy", "CYRILLIC CAPITAL LETTER A" },
1554{ 0x0411, "Bcy", "CYRILLIC CAPITAL LETTER BE" },
1555{ 0x0412, "Vcy", "CYRILLIC CAPITAL LETTER VE" },
1556{ 0x0413, "Gcy", "CYRILLIC CAPITAL LETTER GHE" },
1557{ 0x0414, "Dcy", "CYRILLIC CAPITAL LETTER DE" },
1558{ 0x0415, "IEcy", "CYRILLIC CAPITAL LETTER IE" },
1559{ 0x0416, "ZHcy", "CYRILLIC CAPITAL LETTER ZHE" },
1560{ 0x0417, "Zcy", "CYRILLIC CAPITAL LETTER ZE" },
1561{ 0x0418, "Icy", "CYRILLIC CAPITAL LETTER I" },
1562{ 0x0419, "Jcy", "CYRILLIC CAPITAL LETTER SHORT I" },
1563{ 0x041A, "Kcy", "CYRILLIC CAPITAL LETTER KA" },
1564{ 0x041B, "Lcy", "CYRILLIC CAPITAL LETTER EL" },
1565{ 0x041C, "Mcy", "CYRILLIC CAPITAL LETTER EM" },
1566{ 0x041D, "Ncy", "CYRILLIC CAPITAL LETTER EN" },
1567{ 0x041E, "Ocy", "CYRILLIC CAPITAL LETTER O" },
1568{ 0x041F, "Pcy", "CYRILLIC CAPITAL LETTER PE" },
1569{ 0x0420, "Rcy", "CYRILLIC CAPITAL LETTER ER" },
1570{ 0x0421, "Scy", "CYRILLIC CAPITAL LETTER ES" },
1571{ 0x0422, "Tcy", "CYRILLIC CAPITAL LETTER TE" },
1572{ 0x0423, "Ucy", "CYRILLIC CAPITAL LETTER U" },
1573{ 0x0424, "Fcy", "CYRILLIC CAPITAL LETTER EF" },
1574{ 0x0425, "KHcy", "CYRILLIC CAPITAL LETTER HA" },
1575{ 0x0426, "TScy", "CYRILLIC CAPITAL LETTER TSE" },
1576{ 0x0427, "CHcy", "CYRILLIC CAPITAL LETTER CHE" },
1577{ 0x0428, "SHcy", "CYRILLIC CAPITAL LETTER SHA" },
1578{ 0x0429, "SHCHcy", "CYRILLIC CAPITAL LETTER SHCHA" },
1579{ 0x042A, "HARDcy", "CYRILLIC CAPITAL LETTER HARD SIGN" },
1580{ 0x042B, "Ycy", "CYRILLIC CAPITAL LETTER YERU" },
1581{ 0x042C, "SOFTcy", "CYRILLIC CAPITAL LETTER SOFT SIGN" },
1582{ 0x042D, "Ecy", "CYRILLIC CAPITAL LETTER E" },
1583{ 0x042E, "YUcy", "CYRILLIC CAPITAL LETTER YU" },
1584{ 0x042F, "YAcy", "CYRILLIC CAPITAL LETTER YA" },
1585{ 0x0430, "acy", "CYRILLIC SMALL LETTER A" },
1586{ 0x0431, "bcy", "CYRILLIC SMALL LETTER BE" },
1587{ 0x0432, "vcy", "CYRILLIC SMALL LETTER VE" },
1588{ 0x0433, "gcy", "CYRILLIC SMALL LETTER GHE" },
1589{ 0x0434, "dcy", "CYRILLIC SMALL LETTER DE" },
1590{ 0x0435, "iecy", "CYRILLIC SMALL LETTER IE" },
1591{ 0x0436, "zhcy", "CYRILLIC SMALL LETTER ZHE" },
1592{ 0x0437, "zcy", "CYRILLIC SMALL LETTER ZE" },
1593{ 0x0438, "icy", "CYRILLIC SMALL LETTER I" },
1594{ 0x0439, "jcy", "CYRILLIC SMALL LETTER SHORT I" },
1595{ 0x043A, "kcy", "CYRILLIC SMALL LETTER KA" },
1596{ 0x043B, "lcy", "CYRILLIC SMALL LETTER EL" },
1597{ 0x043C, "mcy", "CYRILLIC SMALL LETTER EM" },
1598{ 0x043D, "ncy", "CYRILLIC SMALL LETTER EN" },
1599{ 0x043E, "ocy", "CYRILLIC SMALL LETTER O" },
1600{ 0x043F, "pcy", "CYRILLIC SMALL LETTER PE" },
1601{ 0x0440, "rcy", "CYRILLIC SMALL LETTER ER" },
1602{ 0x0441, "scy", "CYRILLIC SMALL LETTER ES" },
1603{ 0x0442, "tcy", "CYRILLIC SMALL LETTER TE" },
1604{ 0x0443, "ucy", "CYRILLIC SMALL LETTER U" },
1605{ 0x0444, "fcy", "CYRILLIC SMALL LETTER EF" },
1606{ 0x0445, "khcy", "CYRILLIC SMALL LETTER HA" },
1607{ 0x0446, "tscy", "CYRILLIC SMALL LETTER TSE" },
1608{ 0x0447, "chcy", "CYRILLIC SMALL LETTER CHE" },
1609{ 0x0448, "shcy", "CYRILLIC SMALL LETTER SHA" },
1610{ 0x0449, "shchcy", "CYRILLIC SMALL LETTER SHCHA" },
1611{ 0x044A, "hardcy", "CYRILLIC SMALL LETTER HARD SIGN" },
1612{ 0x044B, "ycy", "CYRILLIC SMALL LETTER YERU" },
1613{ 0x044C, "softcy", "CYRILLIC SMALL LETTER SOFT SIGN" },
1614{ 0x044D, "ecy", "CYRILLIC SMALL LETTER E" },
1615{ 0x044E, "yucy", "CYRILLIC SMALL LETTER YU" },
1616{ 0x044F, "yacy", "CYRILLIC SMALL LETTER YA" },
1617{ 0x0451, "iocy", "CYRILLIC SMALL LETTER IO" },
1618{ 0x0452, "djcy", "CYRILLIC SMALL LETTER DJE" },
1619{ 0x0453, "gjcy", "CYRILLIC SMALL LETTER GJE" },
1620{ 0x0454, "jukcy", "CYRILLIC SMALL LETTER UKRAINIAN IE" },
1621{ 0x0455, "dscy", "CYRILLIC SMALL LETTER DZE" },
1622{ 0x0456, "iukcy", "CYRILLIC SMALL LETTER BYELORUSSIAN-UKRAINIAN I" },
1623{ 0x0457, "yicy", "CYRILLIC SMALL LETTER YI" },
1624{ 0x0458, "jsercy", "CYRILLIC SMALL LETTER JE" },
1625{ 0x0459, "ljcy", "CYRILLIC SMALL LETTER LJE" },
1626{ 0x045A, "njcy", "CYRILLIC SMALL LETTER NJE" },
1627{ 0x045B, "tshcy", "CYRILLIC SMALL LETTER TSHE" },
1628{ 0x045C, "kjcy", "CYRILLIC SMALL LETTER KJE" },
1629{ 0x045E, "ubrcy", "CYRILLIC SMALL LETTER SHORT U" },
1630{ 0x045F, "dzcy", "CYRILLIC SMALL LETTER DZHE" },
1631{ 0x2002, "ensp", "EN SPACE" },
1632{ 0x2003, "emsp", "EM SPACE" },
1633{ 0x2004, "emsp13", "THREE-PER-EM SPACE" },
1634{ 0x2005, "emsp14", "FOUR-PER-EM SPACE" },
1635{ 0x2007, "numsp", "FIGURE SPACE" },
1636{ 0x2008, "puncsp", "PUNCTUATION SPACE" },
1637{ 0x2009, "thinsp", "THIN SPACE" },
1638{ 0x200A, "hairsp", "HAIR SPACE" },
1639{ 0x2010, "dash", "HYPHEN" },
1640{ 0x2013, "ndash", "EN DASH" },
1641{ 0x2014, "mdash", "EM DASH" },
1642{ 0x2015, "horbar", "HORIZONTAL BAR" },
1643{ 0x2016, "Verbar", "DOUBLE VERTICAL LINE" },
1644{ 0x2018, "lsquo", "" },
1645{ 0x2018, "rsquor", "" },
1646{ 0x2019, "rsquo", "RIGHT SINGLE QUOTATION MARK" },
1647{ 0x201A, "lsquor", "SINGLE LOW-9 QUOTATION MARK" },
1648{ 0x201C, "ldquo", "" },
1649{ 0x201C, "rdquor", "" },
1650{ 0x201D, "rdquo", "RIGHT DOUBLE QUOTATION MARK" },
1651{ 0x201E, "ldquor", "DOUBLE LOW-9 QUOTATION MARK" },
1652{ 0x2020, "dagger", "DAGGER" },
1653{ 0x2021, "Dagger", "DOUBLE DAGGER" },
1654{ 0x2022, "bull", "BULLET" },
1655{ 0x2025, "nldr", "TWO DOT LEADER" },
1656{ 0x2026, "hellip", "HORIZONTAL ELLIPSIS" },
1657{ 0x2026, "mldr", "HORIZONTAL ELLIPSIS" },
1658{ 0x2030, "permil", "PER MILLE SIGN" },
1659{ 0x2032, "prime", "PRIME" },
1660{ 0x2032, "vprime", "PRIME" },
1661{ 0x2033, "Prime", "DOUBLE PRIME" },
1662{ 0x2034, "tprime", "TRIPLE PRIME" },
1663{ 0x2035, "bprime", "REVERSED PRIME" },
1664{ 0x2041, "caret", "CARET" },
1665{ 0x2043, "hybull", "HYPHEN BULLET" },
1666{ 0x20DB, "tdot", "COMBINING THREE DOTS ABOVE" },
1667{ 0x20DC, "DotDot", "COMBINING FOUR DOTS ABOVE" },
1668{ 0x2105, "incare", "CARE OF" },
1669{ 0x210B, "hamilt", "SCRIPT CAPITAL H" },
1670{ 0x210F, "planck", "PLANCK CONSTANT OVER TWO PI" },
1671{ 0x2111, "image", "BLACK-LETTER CAPITAL I" },
1672{ 0x2112, "lagran", "SCRIPT CAPITAL L" },
1673{ 0x2113, "ell", "SCRIPT SMALL L" },
1674{ 0x2116, "numero", "NUMERO SIGN" },
1675{ 0x2117, "copysr", "SOUND RECORDING COPYRIGHT" },
1676{ 0x2118, "weierp", "SCRIPT CAPITAL P" },
1677{ 0x211C, "real", "BLACK-LETTER CAPITAL R" },
1678{ 0x211E, "rx", "PRESCRIPTION TAKE" },
1679{ 0x2122, "trade", "TRADE MARK SIGN" },
1680{ 0x2126, "ohm", "OHM SIGN" },
1681{ 0x212B, "angst", "ANGSTROM SIGN" },
1682{ 0x212C, "bernou", "SCRIPT CAPITAL B" },
1683{ 0x2133, "phmmat", "SCRIPT CAPITAL M" },
1684{ 0x2134, "order", "SCRIPT SMALL O" },
1685{ 0x2135, "aleph", "ALEF SYMBOL" },
1686{ 0x2136, "beth", "BET SYMBOL" },
1687{ 0x2137, "gimel", "GIMEL SYMBOL" },
1688{ 0x2138, "daleth", "DALET SYMBOL" },
1689{ 0x2153, "frac13", "VULGAR FRACTION ONE THIRD" },
1690{ 0x2154, "frac23", "VULGAR FRACTION TWO THIRDS" },
1691{ 0x2155, "frac15", "VULGAR FRACTION ONE FIFTH" },
1692{ 0x2156, "frac25", "VULGAR FRACTION TWO FIFTHS" },
1693{ 0x2157, "frac35", "VULGAR FRACTION THREE FIFTHS" },
1694{ 0x2158, "frac45", "VULGAR FRACTION FOUR FIFTHS" },
1695{ 0x2159, "frac16", "VULGAR FRACTION ONE SIXTH" },
1696{ 0x215A, "frac56", "VULGAR FRACTION FIVE SIXTHS" },
1697{ 0x215B, "frac18", "" },
1698{ 0x215C, "frac38", "" },
1699{ 0x215D, "frac58", "" },
1700{ 0x215E, "frac78", "" },
1701{ 0x2190, "larr", "LEFTWARDS DOUBLE ARROW" },
1702{ 0x2191, "uarr", "UPWARDS ARROW" },
1703{ 0x2192, "rarr", "RIGHTWARDS DOUBLE ARROW" },
1704{ 0x2193, "darr", "DOWNWARDS ARROW" },
1705{ 0x2194, "harr", "LEFT RIGHT ARROW" },
1706{ 0x2194, "xhArr", "LEFT RIGHT ARROW" },
1707{ 0x2194, "xharr", "LEFT RIGHT ARROW" },
1708{ 0x2195, "varr", "UP DOWN ARROW" },
1709{ 0x2196, "nwarr", "NORTH WEST ARROW" },
1710{ 0x2197, "nearr", "NORTH EAST ARROW" },
1711{ 0x2198, "drarr", "SOUTH EAST ARROW" },
1712{ 0x2199, "dlarr", "SOUTH WEST ARROW" },
1713{ 0x219A, "nlarr", "LEFTWARDS ARROW WITH STROKE" },
1714{ 0x219B, "nrarr", "RIGHTWARDS ARROW WITH STROKE" },
1715{ 0x219D, "rarrw", "RIGHTWARDS SQUIGGLE ARROW" },
1716{ 0x219E, "Larr", "LEFTWARDS TWO HEADED ARROW" },
1717{ 0x21A0, "Rarr", "RIGHTWARDS TWO HEADED ARROW" },
1718{ 0x21A2, "larrtl", "LEFTWARDS ARROW WITH TAIL" },
1719{ 0x21A3, "rarrtl", "RIGHTWARDS ARROW WITH TAIL" },
1720{ 0x21A6, "map", "RIGHTWARDS ARROW FROM BAR" },
1721{ 0x21A9, "larrhk", "LEFTWARDS ARROW WITH HOOK" },
1722{ 0x21AA, "rarrhk", "RIGHTWARDS ARROW WITH HOOK" },
1723{ 0x21AB, "larrlp", "LEFTWARDS ARROW WITH LOOP" },
1724{ 0x21AC, "rarrlp", "RIGHTWARDS ARROW WITH LOOP" },
1725{ 0x21AD, "harrw", "LEFT RIGHT WAVE ARROW" },
1726{ 0x21AE, "nharr", "LEFT RIGHT ARROW WITH STROKE" },
1727{ 0x21B0, "lsh", "UPWARDS ARROW WITH TIP LEFTWARDS" },
1728{ 0x21B1, "rsh", "UPWARDS ARROW WITH TIP RIGHTWARDS" },
1729{ 0x21B6, "cularr", "ANTICLOCKWISE TOP SEMICIRCLE ARROW" },
1730{ 0x21B7, "curarr", "CLOCKWISE TOP SEMICIRCLE ARROW" },
1731{ 0x21BA, "olarr", "ANTICLOCKWISE OPEN CIRCLE ARROW" },
1732{ 0x21BB, "orarr", "CLOCKWISE OPEN CIRCLE ARROW" },
1733{ 0x21BC, "lharu", "LEFTWARDS HARPOON WITH BARB UPWARDS" },
1734{ 0x21BD, "lhard", "LEFTWARDS HARPOON WITH BARB DOWNWARDS" },
1735{ 0x21BE, "uharr", "UPWARDS HARPOON WITH BARB RIGHTWARDS" },
1736{ 0x21BF, "uharl", "UPWARDS HARPOON WITH BARB LEFTWARDS" },
1737{ 0x21C0, "rharu", "RIGHTWARDS HARPOON WITH BARB UPWARDS" },
1738{ 0x21C1, "rhard", "RIGHTWARDS HARPOON WITH BARB DOWNWARDS" },
1739{ 0x21C2, "dharr", "DOWNWARDS HARPOON WITH BARB RIGHTWARDS" },
1740{ 0x21C3, "dharl", "DOWNWARDS HARPOON WITH BARB LEFTWARDS" },
1741{ 0x21C4, "rlarr2", "RIGHTWARDS ARROW OVER LEFTWARDS ARROW" },
1742{ 0x21C6, "lrarr2", "LEFTWARDS ARROW OVER RIGHTWARDS ARROW" },
1743{ 0x21C7, "larr2", "LEFTWARDS PAIRED ARROWS" },
1744{ 0x21C8, "uarr2", "UPWARDS PAIRED ARROWS" },
1745{ 0x21C9, "rarr2", "RIGHTWARDS PAIRED ARROWS" },
1746{ 0x21CA, "darr2", "DOWNWARDS PAIRED ARROWS" },
1747{ 0x21CB, "lrhar2", "LEFTWARDS HARPOON OVER RIGHTWARDS HARPOON" },
1748{ 0x21CC, "rlhar2", "RIGHTWARDS HARPOON OVER LEFTWARDS HARPOON" },
1749{ 0x21CD, "nlArr", "LEFTWARDS DOUBLE ARROW WITH STROKE" },
1750{ 0x21CE, "nhArr", "LEFT RIGHT DOUBLE ARROW WITH STROKE" },
1751{ 0x21CF, "nrArr", "RIGHTWARDS DOUBLE ARROW WITH STROKE" },
1752{ 0x21D0, "lArr", "LEFTWARDS ARROW" },
1753{ 0x21D0, "xlArr", "LEFTWARDS DOUBLE ARROW" },
1754{ 0x21D1, "uArr", "UPWARDS DOUBLE ARROW" },
1755{ 0x21D2, "rArr", "RIGHTWARDS ARROW" },
1756{ 0x21D2, "xrArr", "RIGHTWARDS DOUBLE ARROW" },
1757{ 0x21D3, "dArr", "DOWNWARDS DOUBLE ARROW" },
1758{ 0x21D4, "hArr", "" },
1759{ 0x21D4, "iff", "LEFT RIGHT DOUBLE ARROW" },
1760{ 0x21D5, "vArr", "UP DOWN DOUBLE ARROW" },
1761{ 0x21DA, "lAarr", "LEFTWARDS TRIPLE ARROW" },
1762{ 0x21DB, "rAarr", "RIGHTWARDS TRIPLE ARROW" },
1763{ 0x2200, "forall", "" },
1764{ 0x2201, "comp", "COMPLEMENT" },
1765{ 0x2202, "part", "" },
1766{ 0x2203, "exist", "" },
1767{ 0x2204, "nexist", "THERE DOES NOT EXIST" },
1768{ 0x2205, "empty", "" },
1769{ 0x2207, "nabla", "NABLA" },
1770{ 0x2209, "notin", "" },
1771{ 0x220A, "epsi", "" },
1772{ 0x220A, "epsis", "" },
1773{ 0x220A, "isin", "" },
1774{ 0x220D, "bepsi", "SMALL CONTAINS AS MEMBER" },
1775{ 0x220D, "ni", "" },
1776{ 0x220F, "prod", "N-ARY PRODUCT" },
1777{ 0x2210, "amalg", "N-ARY COPRODUCT" },
1778{ 0x2210, "coprod", "N-ARY COPRODUCT" },
1779{ 0x2210, "samalg", "" },
1780{ 0x2211, "sum", "N-ARY SUMMATION" },
1781{ 0x2212, "minus", "MINUS SIGN" },
1782{ 0x2213, "mnplus", "" },
1783{ 0x2214, "plusdo", "DOT PLUS" },
1784{ 0x2216, "setmn", "SET MINUS" },
1785{ 0x2216, "ssetmn", "SET MINUS" },
1786{ 0x2217, "lowast", "ASTERISK OPERATOR" },
1787{ 0x2218, "compfn", "RING OPERATOR" },
1788{ 0x221A, "radic", "" },
1789{ 0x221D, "prop", "" },
1790{ 0x221D, "vprop", "" },
1791{ 0x221E, "infin", "" },
1792{ 0x221F, "ang90", "RIGHT ANGLE" },
1793{ 0x2220, "ang", "ANGLE" },
1794{ 0x2221, "angmsd", "MEASURED ANGLE" },
1795{ 0x2222, "angsph", "" },
1796{ 0x2223, "mid", "" },
1797{ 0x2224, "nmid", "DOES NOT DIVIDE" },
1798{ 0x2225, "par", "PARALLEL TO" },
1799{ 0x2225, "spar", "PARALLEL TO" },
1800{ 0x2226, "npar", "NOT PARALLEL TO" },
1801{ 0x2226, "nspar", "NOT PARALLEL TO" },
1802{ 0x2227, "and", "" },
1803{ 0x2228, "or", "" },
1804{ 0x2229, "cap", "" },
1805{ 0x222A, "cup", "" },
1806{ 0x222B, "int", "" },
1807{ 0x222E, "conint", "" },
1808{ 0x2234, "there4", "" },
1809{ 0x2235, "becaus", "BECAUSE" },
1810{ 0x223C, "sim", "" },
1811{ 0x223C, "thksim", "TILDE OPERATOR" },
1812{ 0x223D, "bsim", "" },
1813{ 0x2240, "wreath", "WREATH PRODUCT" },
1814{ 0x2241, "nsim", "" },
1815{ 0x2243, "sime", "" },
1816{ 0x2244, "nsime", "" },
1817{ 0x2245, "cong", "" },
1818{ 0x2247, "ncong", "NEITHER APPROXIMATELY NOR ACTUALLY EQUAL TO" },
1819{ 0x2248, "ap", "" },
1820{ 0x2248, "thkap", "ALMOST EQUAL TO" },
1821{ 0x2249, "nap", "NOT ALMOST EQUAL TO" },
1822{ 0x224A, "ape", "" },
1823{ 0x224C, "bcong", "ALL EQUAL TO" },
1824{ 0x224D, "asymp", "EQUIVALENT TO" },
1825{ 0x224E, "bump", "" },
1826{ 0x224F, "bumpe", "" },
1827{ 0x2250, "esdot", "" },
1828{ 0x2251, "eDot", "" },
1829{ 0x2252, "efDot", "" },
1830{ 0x2253, "erDot", "" },
1831{ 0x2254, "colone", "" },
1832{ 0x2255, "ecolon", "" },
1833{ 0x2256, "ecir", "" },
1834{ 0x2257, "cire", "" },
1835{ 0x2259, "wedgeq", "ESTIMATES" },
1836{ 0x225C, "trie", "" },
1837{ 0x2260, "ne", "" },
1838{ 0x2261, "equiv", "" },
1839{ 0x2262, "nequiv", "NOT IDENTICAL TO" },
1840{ 0x2264, "le", "" },
1841{ 0x2264, "les", "LESS-THAN OR EQUAL TO" },
1842{ 0x2265, "ge", "GREATER-THAN OR EQUAL TO" },
1843{ 0x2265, "ges", "GREATER-THAN OR EQUAL TO" },
1844{ 0x2266, "lE", "" },
1845{ 0x2267, "gE", "" },
1846{ 0x2268, "lnE", "" },
1847{ 0x2268, "lne", "" },
1848{ 0x2268, "lvnE", "LESS-THAN BUT NOT EQUAL TO" },
1849{ 0x2269, "gnE", "" },
1850{ 0x2269, "gne", "" },
1851{ 0x2269, "gvnE", "GREATER-THAN BUT NOT EQUAL TO" },
1852{ 0x226A, "Lt", "MUCH LESS-THAN" },
1853{ 0x226B, "Gt", "MUCH GREATER-THAN" },
1854{ 0x226C, "twixt", "BETWEEN" },
1855{ 0x226E, "nlt", "NOT LESS-THAN" },
1856{ 0x226F, "ngt", "NOT GREATER-THAN" },
1857{ 0x2270, "nlE", "" },
1858{ 0x2270, "nle", "NEITHER LESS-THAN NOR EQUAL TO" },
1859{ 0x2270, "nles", "" },
1860{ 0x2271, "ngE", "" },
1861{ 0x2271, "nge", "NEITHER GREATER-THAN NOR EQUAL TO" },
1862{ 0x2271, "nges", "" },
1863{ 0x2272, "lap", "LESS-THAN OR EQUIVALENT TO" },
1864{ 0x2272, "lsim", "LESS-THAN OR EQUIVALENT TO" },
1865{ 0x2273, "gap", "GREATER-THAN OR EQUIVALENT TO" },
1866{ 0x2273, "gsim", "GREATER-THAN OR EQUIVALENT TO" },
1867{ 0x2276, "lg", "LESS-THAN OR GREATER-THAN" },
1868{ 0x2277, "gl", "" },
1869{ 0x227A, "pr", "" },
1870{ 0x227B, "sc", "" },
1871{ 0x227C, "cupre", "" },
1872{ 0x227C, "pre", "" },
1873{ 0x227D, "sccue", "" },
1874{ 0x227D, "sce", "" },
1875{ 0x227E, "prap", "" },
1876{ 0x227E, "prsim", "" },
1877{ 0x227F, "scap", "" },
1878{ 0x227F, "scsim", "" },
1879{ 0x2280, "npr", "DOES NOT PRECEDE" },
1880{ 0x2281, "nsc", "DOES NOT SUCCEED" },
1881{ 0x2282, "sub", "" },
1882{ 0x2283, "sup", "" },
1883{ 0x2284, "nsub", "NOT A SUBSET OF" },
1884{ 0x2285, "nsup", "NOT A SUPERSET OF" },
1885{ 0x2286, "subE", "" },
1886{ 0x2286, "sube", "" },
1887{ 0x2287, "supE", "" },
1888{ 0x2287, "supe", "" },
1889{ 0x2288, "nsubE", "" },
1890{ 0x2288, "nsube", "" },
1891{ 0x2289, "nsupE", "" },
1892{ 0x2289, "nsupe", "" },
1893{ 0x228A, "subne", "" },
1894{ 0x228A, "subnE", "SUBSET OF WITH NOT EQUAL TO" },
1895{ 0x228A, "vsubne", "SUBSET OF WITH NOT EQUAL TO" },
1896{ 0x228B, "supnE", "" },
1897{ 0x228B, "supne", "" },
1898{ 0x228B, "vsupnE", "SUPERSET OF WITH NOT EQUAL TO" },
1899{ 0x228B, "vsupne", "SUPERSET OF WITH NOT EQUAL TO" },
1900{ 0x228E, "uplus", "MULTISET UNION" },
1901{ 0x228F, "sqsub", "" },
1902{ 0x2290, "sqsup", "" },
1903{ 0x2291, "sqsube", "" },
1904{ 0x2292, "sqsupe", "" },
1905{ 0x2293, "sqcap", "SQUARE CAP" },
1906{ 0x2294, "sqcup", "SQUARE CUP" },
1907{ 0x2295, "oplus", "CIRCLED PLUS" },
1908{ 0x2296, "ominus", "CIRCLED MINUS" },
1909{ 0x2297, "otimes", "CIRCLED TIMES" },
1910{ 0x2298, "osol", "CIRCLED DIVISION SLASH" },
1911{ 0x2299, "odot", "CIRCLED DOT OPERATOR" },
1912{ 0x229A, "ocir", "CIRCLED RING OPERATOR" },
1913{ 0x229B, "oast", "CIRCLED ASTERISK OPERATOR" },
1914{ 0x229D, "odash", "CIRCLED DASH" },
1915{ 0x229E, "plusb", "SQUARED PLUS" },
1916{ 0x229F, "minusb", "SQUARED MINUS" },
1917{ 0x22A0, "timesb", "SQUARED TIMES" },
1918{ 0x22A1, "sdotb", "SQUARED DOT OPERATOR" },
1919{ 0x22A2, "vdash", "" },
1920{ 0x22A3, "dashv", "" },
1921{ 0x22A4, "top", "DOWN TACK" },
1922{ 0x22A5, "bottom", "" },
1923{ 0x22A5, "perp", "" },
1924{ 0x22A7, "models", "MODELS" },
1925{ 0x22A8, "vDash", "" },
1926{ 0x22A9, "Vdash", "" },
1927{ 0x22AA, "Vvdash", "" },
1928{ 0x22AC, "nvdash", "DOES NOT PROVE" },
1929{ 0x22AD, "nvDash", "NOT TRUE" },
1930{ 0x22AE, "nVdash", "DOES NOT FORCE" },
1931{ 0x22AF, "nVDash", "NEGATED DOUBLE VERTICAL BAR DOUBLE RIGHT TURNSTILE" },
1932{ 0x22B2, "vltri", "" },
1933{ 0x22B3, "vrtri", "" },
1934{ 0x22B4, "ltrie", "" },
1935{ 0x22B5, "rtrie", "" },
1936{ 0x22B8, "mumap", "MULTIMAP" },
1937{ 0x22BA, "intcal", "INTERCALATE" },
1938{ 0x22BB, "veebar", "" },
1939{ 0x22BC, "barwed", "NAND" },
1940{ 0x22C4, "diam", "DIAMOND OPERATOR" },
1941{ 0x22C5, "sdot", "DOT OPERATOR" },
1942{ 0x22C6, "sstarf", "STAR OPERATOR" },
1943{ 0x22C6, "star", "STAR OPERATOR" },
1944{ 0x22C7, "divonx", "DIVISION TIMES" },
1945{ 0x22C8, "bowtie", "" },
1946{ 0x22C9, "ltimes", "LEFT NORMAL FACTOR SEMIDIRECT PRODUCT" },
1947{ 0x22CA, "rtimes", "RIGHT NORMAL FACTOR SEMIDIRECT PRODUCT" },
1948{ 0x22CB, "lthree", "LEFT SEMIDIRECT PRODUCT" },
1949{ 0x22CC, "rthree", "RIGHT SEMIDIRECT PRODUCT" },
1950{ 0x22CD, "bsime", "" },
1951{ 0x22CE, "cuvee", "CURLY LOGICAL OR" },
1952{ 0x22CF, "cuwed", "CURLY LOGICAL AND" },
1953{ 0x22D0, "Sub", "" },
1954{ 0x22D1, "Sup", "" },
1955{ 0x22D2, "Cap", "DOUBLE INTERSECTION" },
1956{ 0x22D3, "Cup", "DOUBLE UNION" },
1957{ 0x22D4, "fork", "" },
1958{ 0x22D6, "ldot", "" },
1959{ 0x22D7, "gsdot", "" },
1960{ 0x22D8, "Ll", "" },
1961{ 0x22D9, "Gg", "VERY MUCH GREATER-THAN" },
1962{ 0x22DA, "lEg", "" },
1963{ 0x22DA, "leg", "" },
1964{ 0x22DB, "gEl", "" },
1965{ 0x22DB, "gel", "" },
1966{ 0x22DC, "els", "" },
1967{ 0x22DD, "egs", "" },
1968{ 0x22DE, "cuepr", "" },
1969{ 0x22DF, "cuesc", "" },
1970{ 0x22E0, "npre", "DOES NOT PRECEDE OR EQUAL" },
1971{ 0x22E1, "nsce", "DOES NOT SUCCEED OR EQUAL" },
1972{ 0x22E6, "lnsim", "" },
1973{ 0x22E7, "gnsim", "GREATER-THAN BUT NOT EQUIVALENT TO" },
1974{ 0x22E8, "prnap", "" },
1975{ 0x22E8, "prnsim", "" },
1976{ 0x22E9, "scnap", "" },
1977{ 0x22E9, "scnsim", "" },
1978{ 0x22EA, "nltri", "NOT NORMAL SUBGROUP OF" },
1979{ 0x22EB, "nrtri", "DOES NOT CONTAIN AS NORMAL SUBGROUP" },
1980{ 0x22EC, "nltrie", "NOT NORMAL SUBGROUP OF OR EQUAL TO" },
1981{ 0x22ED, "nrtrie", "DOES NOT CONTAIN AS NORMAL SUBGROUP OR EQUAL" },
1982{ 0x22EE, "vellip", "" },
1983{ 0x2306, "Barwed", "PERSPECTIVE" },
1984{ 0x2308, "lceil", "LEFT CEILING" },
1985{ 0x2309, "rceil", "RIGHT CEILING" },
1986{ 0x230A, "lfloor", "LEFT FLOOR" },
1987{ 0x230B, "rfloor", "RIGHT FLOOR" },
1988{ 0x230C, "drcrop", "BOTTOM RIGHT CROP" },
1989{ 0x230D, "dlcrop", "BOTTOM LEFT CROP" },
1990{ 0x230E, "urcrop", "TOP RIGHT CROP" },
1991{ 0x230F, "ulcrop", "TOP LEFT CROP" },
1992{ 0x2315, "telrec", "TELEPHONE RECORDER" },
1993{ 0x2316, "target", "POSITION INDICATOR" },
1994{ 0x231C, "ulcorn", "TOP LEFT CORNER" },
1995{ 0x231D, "urcorn", "TOP RIGHT CORNER" },
1996{ 0x231E, "dlcorn", "BOTTOM LEFT CORNER" },
1997{ 0x231F, "drcorn", "BOTTOM RIGHT CORNER" },
1998{ 0x2322, "frown", "" },
1999{ 0x2322, "sfrown", "FROWN" },
2000{ 0x2323, "smile", "" },
2001{ 0x2323, "ssmile", "SMILE" },
2002{ 0x2423, "blank", "OPEN BOX" },
2003{ 0x24C8, "oS", "CIRCLED LATIN CAPITAL LETTER S" },
2004{ 0x2500, "boxh", "BOX DRAWINGS LIGHT HORIZONTAL" },
2005{ 0x2502, "boxv", "BOX DRAWINGS LIGHT VERTICAL" },
2006{ 0x250C, "boxdr", "BOX DRAWINGS LIGHT DOWN AND RIGHT" },
2007{ 0x2510, "boxdl", "BOX DRAWINGS LIGHT DOWN AND LEFT" },
2008{ 0x2514, "boxur", "BOX DRAWINGS LIGHT UP AND RIGHT" },
2009{ 0x2518, "boxul", "BOX DRAWINGS LIGHT UP AND LEFT" },
2010{ 0x251C, "boxvr", "BOX DRAWINGS LIGHT VERTICAL AND RIGHT" },
2011{ 0x2524, "boxvl", "BOX DRAWINGS LIGHT VERTICAL AND LEFT" },
2012{ 0x252C, "boxhd", "BOX DRAWINGS LIGHT DOWN AND HORIZONTAL" },
2013{ 0x2534, "boxhu", "BOX DRAWINGS LIGHT UP AND HORIZONTAL" },
2014{ 0x253C, "boxvh", "BOX DRAWINGS LIGHT VERTICAL AND HORIZONTAL" },
2015{ 0x2550, "boxH", "BOX DRAWINGS DOUBLE HORIZONTAL" },
2016{ 0x2551, "boxV", "BOX DRAWINGS DOUBLE VERTICAL" },
2017{ 0x2552, "boxDR", "BOX DRAWINGS DOWN SINGLE AND RIGHT DOUBLE" },
2018{ 0x2553, "boxDr", "BOX DRAWINGS DOWN DOUBLE AND RIGHT SINGLE" },
2019{ 0x2554, "boxdR", "BOX DRAWINGS DOUBLE DOWN AND RIGHT" },
2020{ 0x2555, "boxDL", "BOX DRAWINGS DOWN SINGLE AND LEFT DOUBLE" },
2021{ 0x2556, "boxdL", "BOX DRAWINGS DOWN DOUBLE AND LEFT SINGLE" },
2022{ 0x2557, "boxDl", "BOX DRAWINGS DOUBLE DOWN AND LEFT" },
2023{ 0x2558, "boxUR", "BOX DRAWINGS UP SINGLE AND RIGHT DOUBLE" },
2024{ 0x2559, "boxuR", "BOX DRAWINGS UP DOUBLE AND RIGHT SINGLE" },
2025{ 0x255A, "boxUr", "BOX DRAWINGS DOUBLE UP AND RIGHT" },
2026{ 0x255B, "boxUL", "BOX DRAWINGS UP SINGLE AND LEFT DOUBLE" },
2027{ 0x255C, "boxUl", "BOX DRAWINGS UP DOUBLE AND LEFT SINGLE" },
2028{ 0x255D, "boxuL", "BOX DRAWINGS DOUBLE UP AND LEFT" },
2029{ 0x255E, "boxvR", "BOX DRAWINGS VERTICAL SINGLE AND RIGHT DOUBLE" },
2030{ 0x255F, "boxVR", "BOX DRAWINGS VERTICAL DOUBLE AND RIGHT SINGLE" },
2031{ 0x2560, "boxVr", "BOX DRAWINGS DOUBLE VERTICAL AND RIGHT" },
2032{ 0x2561, "boxvL", "BOX DRAWINGS VERTICAL SINGLE AND LEFT DOUBLE" },
2033{ 0x2562, "boxVL", "BOX DRAWINGS VERTICAL DOUBLE AND LEFT SINGLE" },
2034{ 0x2563, "boxVl", "BOX DRAWINGS DOUBLE VERTICAL AND LEFT" },
2035{ 0x2564, "boxhD", "BOX DRAWINGS DOWN SINGLE AND HORIZONTAL DOUBLE" },
2036{ 0x2565, "boxHD", "BOX DRAWINGS DOWN DOUBLE AND HORIZONTAL SINGLE" },
2037{ 0x2566, "boxHd", "BOX DRAWINGS DOUBLE DOWN AND HORIZONTAL" },
2038{ 0x2567, "boxhU", "BOX DRAWINGS UP SINGLE AND HORIZONTAL DOUBLE" },
2039{ 0x2568, "boxHU", "BOX DRAWINGS UP DOUBLE AND HORIZONTAL SINGLE" },
2040{ 0x2569, "boxHu", "BOX DRAWINGS DOUBLE UP AND HORIZONTAL" },
2041{ 0x256A, "boxvH", "BOX DRAWINGS VERTICAL SINGLE AND HORIZONTAL DOUBLE" },
2042{ 0x256B, "boxVH", "BOX DRAWINGS VERTICAL DOUBLE AND HORIZONTAL SINGLE" },
2043{ 0x256C, "boxVh", "BOX DRAWINGS DOUBLE VERTICAL AND HORIZONTAL" },
2044{ 0x2580, "uhblk", "UPPER HALF BLOCK" },
2045{ 0x2584, "lhblk", "LOWER HALF BLOCK" },
2046{ 0x2588, "block", "FULL BLOCK" },
2047{ 0x2591, "blk14", "LIGHT SHADE" },
2048{ 0x2592, "blk12", "MEDIUM SHADE" },
2049{ 0x2593, "blk34", "DARK SHADE" },
2050{ 0x25A1, "square", "WHITE SQUARE" },
2051{ 0x25A1, "squ", "WHITE SQUARE" },
2052{ 0x25AA, "squf", "" },
2053{ 0x25AD, "rect", "WHITE RECTANGLE" },
2054{ 0x25AE, "marker", "BLACK VERTICAL RECTANGLE" },
2055{ 0x25B3, "xutri", "WHITE UP-POINTING TRIANGLE" },
2056{ 0x25B4, "utrif", "BLACK UP-POINTING TRIANGLE" },
2057{ 0x25B5, "utri", "WHITE UP-POINTING TRIANGLE" },
2058{ 0x25B8, "rtrif", "BLACK RIGHT-POINTING TRIANGLE" },
2059{ 0x25B9, "rtri", "WHITE RIGHT-POINTING TRIANGLE" },
2060{ 0x25BD, "xdtri", "WHITE DOWN-POINTING TRIANGLE" },
2061{ 0x25BE, "dtrif", "BLACK DOWN-POINTING TRIANGLE" },
2062{ 0x25BF, "dtri", "WHITE DOWN-POINTING TRIANGLE" },
2063{ 0x25C2, "ltrif", "BLACK LEFT-POINTING TRIANGLE" },
2064{ 0x25C3, "ltri", "WHITE LEFT-POINTING TRIANGLE" },
2065{ 0x25CA, "loz", "LOZENGE" },
2066{ 0x25CB, "cir", "WHITE CIRCLE" },
2067{ 0x25CB, "xcirc", "WHITE CIRCLE" },
2068{ 0x2605, "starf", "BLACK STAR" },
2069{ 0x260E, "phone", "TELEPHONE SIGN" },
2070{ 0x2640, "female", "" },
2071{ 0x2642, "male", "MALE SIGN" },
2072{ 0x2660, "spades", "BLACK SPADE SUIT" },
2073{ 0x2663, "clubs", "BLACK CLUB SUIT" },
2074{ 0x2665, "hearts", "BLACK HEART SUIT" },
2075{ 0x2666, "diams", "BLACK DIAMOND SUIT" },
2076{ 0x2669, "sung", "" },
2077{ 0x266D, "flat", "MUSIC FLAT SIGN" },
2078{ 0x266E, "natur", "MUSIC NATURAL SIGN" },
2079{ 0x266F, "sharp", "MUSIC SHARP SIGN" },
2080{ 0x2713, "check", "CHECK MARK" },
2081{ 0x2717, "cross", "BALLOT X" },
2082{ 0x2720, "malt", "MALTESE CROSS" },
2083{ 0x2726, "lozf", "" },
2084{ 0x2736, "sext", "SIX POINTED BLACK STAR" },
2085{ 0x3008, "lang", "" },
2086{ 0x3009, "rang", "" },
2087{ 0xE291, "rpargt", "" },
2088{ 0xE2A2, "lnap", "" },
2089{ 0xE2AA, "nsmid", "" },
2090{ 0xE2B3, "prnE", "" },
2091{ 0xE2B5, "scnE", "" },
2092{ 0xE2B8, "vsubnE", "" },
2093{ 0xE301, "smid", "" },
2094{ 0xE411, "gnap", "" },
2095{ 0xFB00, "fflig", "" },
2096{ 0xFB01, "filig", "" },
2097{ 0xFB02, "fllig", "" },
2098{ 0xFB03, "ffilig", "" },
2099{ 0xFB04, "ffllig", "" },
2100{ 0xFE68, "sbsol", "SMALL REVERSE SOLIDUS" },
2101};
2102
2103/************************************************************************
2104 * *
2105 * Commodity functions to handle entities *
2106 * *
2107 ************************************************************************/
2108
2109/*
2110 * Macro used to grow the current buffer.
2111 */
2112#define growBuffer(buffer) { \
2113 buffer##_size *= 2; \
2114 buffer = (xmlChar *) xmlRealloc(buffer, buffer##_size * sizeof(xmlChar)); \
2115 if (buffer == NULL) { \
2116 perror("realloc failed"); \
2117 return(NULL); \
2118 } \
2119}
2120
2121/**
2122 * docbEntityLookup:
2123 * @name: the entity name
2124 *
2125 * Lookup the given entity in EntitiesTable
2126 *
2127 * TODO: the linear scan is really ugly, an hash table is really needed.
2128 *
2129 * Returns the associated docbEntityDescPtr if found, NULL otherwise.
2130 */
2131static docbEntityDescPtr
2132docbEntityLookup(const xmlChar *name) {
2133 unsigned int i;
2134
2135 for (i = 0;i < (sizeof(docbookEntitiesTable)/
2136 sizeof(docbookEntitiesTable[0]));i++) {
2137 if (xmlStrEqual(name, BAD_CAST docbookEntitiesTable[i].name)) {
2138#ifdef DEBUG
2139 xmlGenericError(xmlGenericErrorContext,"Found entity %s\n", name);
2140#endif
2141 return(&docbookEntitiesTable[i]);
2142 }
2143 }
2144 return(NULL);
2145}
2146
2147/**
2148 * docbEntityValueLookup:
2149 * @value: the entity's unicode value
2150 *
2151 * Lookup the given entity in EntitiesTable
2152 *
2153 * TODO: the linear scan is really ugly, an hash table is really needed.
2154 *
2155 * Returns the associated docbEntityDescPtr if found, NULL otherwise.
2156 */
2157static docbEntityDescPtr
2158docbEntityValueLookup(int value) {
2159 unsigned int i;
2160#ifdef DEBUG
2161 int lv = 0;
2162#endif
2163
2164 for (i = 0;i < (sizeof(docbookEntitiesTable)/
2165 sizeof(docbookEntitiesTable[0]));i++) {
2166 if (docbookEntitiesTable[i].value >= value) {
2167 if (docbookEntitiesTable[i].value > value)
2168 break;
2169#ifdef DEBUG
2170 xmlGenericError(xmlGenericErrorContext,"Found entity %s\n", docbookEntitiesTable[i].name);
2171#endif
2172 return(&docbookEntitiesTable[i]);
2173 }
2174#ifdef DEBUG
2175 if (lv > docbookEntitiesTable[i].value) {
2176 xmlGenericError(xmlGenericErrorContext,
2177 "docbookEntitiesTable[] is not sorted (%d > %d)!\n",
2178 lv, docbookEntitiesTable[i].value);
2179 }
2180 lv = docbookEntitiesTable[i].value;
2181#endif
2182 }
2183 return(NULL);
2184}
2185
2186#if 0
2187/**
2188 * UTF8ToSgml:
2189 * @out: a pointer to an array of bytes to store the result
2190 * @outlen: the length of @out
2191 * @in: a pointer to an array of UTF-8 chars
2192 * @inlen: the length of @in
2193 *
2194 * Take a block of UTF-8 chars in and try to convert it to an ASCII
2195 * plus SGML entities block of chars out.
2196 *
2197 * Returns 0 if success, -2 if the transcoding fails, or -1 otherwise
2198 * The value of @inlen after return is the number of octets consumed
2199 * as the return value is positive, else unpredictiable.
2200 * The value of @outlen after return is the number of octets consumed.
2201 */
2202int
2203UTF8ToSgml(unsigned char* out, int *outlen,
2204 const unsigned char* in, int *inlen) {
2205 const unsigned char* processed = in;
2206 const unsigned char* outend;
2207 const unsigned char* outstart = out;
2208 const unsigned char* instart = in;
2209 const unsigned char* inend;
2210 unsigned int c, d;
2211 int trailing;
2212
2213 if (in == NULL) {
2214 /*
2215 * initialization nothing to do
2216 */
2217 *outlen = 0;
2218 *inlen = 0;
2219 return(0);
2220 }
2221 inend = in + (*inlen);
2222 outend = out + (*outlen);
2223 while (in < inend) {
2224 d = *in++;
2225 if (d < 0x80) { c= d; trailing= 0; }
2226 else if (d < 0xC0) {
2227 /* trailing byte in leading position */
2228 *outlen = out - outstart;
2229 *inlen = processed - instart;
2230 return(-2);
2231 } else if (d < 0xE0) { c= d & 0x1F; trailing= 1; }
2232 else if (d < 0xF0) { c= d & 0x0F; trailing= 2; }
2233 else if (d < 0xF8) { c= d & 0x07; trailing= 3; }
2234 else {
2235 /* no chance for this in Ascii */
2236 *outlen = out - outstart;
2237 *inlen = processed - instart;
2238 return(-2);
2239 }
2240
2241 if (inend - in < trailing) {
2242 break;
2243 }
2244
2245 for ( ; trailing; trailing--) {
2246 if ((in >= inend) || (((d= *in++) & 0xC0) != 0x80))
2247 break;
2248 c <<= 6;
2249 c |= d & 0x3F;
2250 }
2251
2252 /* assertion: c is a single UTF-4 value */
2253 if (c < 0x80) {
2254 if (out + 1 >= outend)
2255 break;
2256 *out++ = c;
2257 } else {
2258 int len;
2259 docbEntityDescPtr ent;
2260
2261 /*
2262 * Try to lookup a predefined SGML entity for it
2263 */
2264
2265 ent = docbEntityValueLookup(c);
2266 if (ent == NULL) {
2267 /* no chance for this in Ascii */
2268 *outlen = out - outstart;
2269 *inlen = processed - instart;
2270 return(-2);
2271 }
2272 len = strlen(ent->name);
2273 if (out + 2 + len >= outend)
2274 break;
2275 *out++ = '&';
2276 memcpy(out, ent->name, len);
2277 out += len;
2278 *out++ = ';';
2279 }
2280 processed = in;
2281 }
2282 *outlen = out - outstart;
2283 *inlen = processed - instart;
2284 return(0);
2285}
2286#endif
2287
2288/**
2289 * docbEncodeEntities:
2290 * @out: a pointer to an array of bytes to store the result
2291 * @outlen: the length of @out
2292 * @in: a pointer to an array of UTF-8 chars
2293 * @inlen: the length of @in
2294 * @quoteChar: the quote character to escape (' or ") or zero.
2295 *
2296 * Take a block of UTF-8 chars in and try to convert it to an ASCII
2297 * plus SGML entities block of chars out.
2298 *
2299 * Returns 0 if success, -2 if the transcoding fails, or -1 otherwise
2300 * The value of @inlen after return is the number of octets consumed
2301 * as the return value is positive, else unpredictiable.
2302 * The value of @outlen after return is the number of octets consumed.
2303 */
2304int
2305docbEncodeEntities(unsigned char* out, int *outlen,
2306 const unsigned char* in, int *inlen, int quoteChar) {
2307 const unsigned char* processed = in;
2308 const unsigned char* outend = out + (*outlen);
2309 const unsigned char* outstart = out;
2310 const unsigned char* instart = in;
2311 const unsigned char* inend = in + (*inlen);
2312 unsigned int c, d;
2313 int trailing;
2314
2315 while (in < inend) {
2316 d = *in++;
2317 if (d < 0x80) { c= d; trailing= 0; }
2318 else if (d < 0xC0) {
2319 /* trailing byte in leading position */
2320 *outlen = out - outstart;
2321 *inlen = processed - instart;
2322 return(-2);
2323 } else if (d < 0xE0) { c= d & 0x1F; trailing= 1; }
2324 else if (d < 0xF0) { c= d & 0x0F; trailing= 2; }
2325 else if (d < 0xF8) { c= d & 0x07; trailing= 3; }
2326 else {
2327 /* no chance for this in Ascii */
2328 *outlen = out - outstart;
2329 *inlen = processed - instart;
2330 return(-2);
2331 }
2332
2333 if (inend - in < trailing)
2334 break;
2335
2336 while (trailing--) {
2337 if (((d= *in++) & 0xC0) != 0x80) {
2338 *outlen = out - outstart;
2339 *inlen = processed - instart;
2340 return(-2);
2341 }
2342 c <<= 6;
2343 c |= d & 0x3F;
2344 }
2345
2346 /* assertion: c is a single UTF-4 value */
2347 if (c < 0x80 && c != (unsigned int) quoteChar && c != '&' && c != '<' && c != '>') {
2348 if (out >= outend)
2349 break;
2350 *out++ = c;
2351 } else {
2352 docbEntityDescPtr ent;
2353 const char *cp;
2354 char nbuf[16];
2355 int len;
2356
2357 /*
2358 * Try to lookup a predefined SGML entity for it
2359 */
2360 ent = docbEntityValueLookup(c);
2361 if (ent == NULL) {
2362 sprintf(nbuf, "#%u", c);
2363 cp = nbuf;
2364 }
2365 else
2366 cp = ent->name;
2367 len = strlen(cp);
2368 if (out + 2 + len > outend)
2369 break;
2370 *out++ = '&';
2371 memcpy(out, cp, len);
2372 out += len;
2373 *out++ = ';';
2374 }
2375 processed = in;
2376 }
2377 *outlen = out - outstart;
2378 *inlen = processed - instart;
2379 return(0);
2380}
2381
2382
2383/************************************************************************
2384 * *
2385 * Commodity functions to handle streams *
2386 * *
2387 ************************************************************************/
2388
2389/**
2390 * docbNewInputStream:
2391 * @ctxt: an SGML parser context
2392 *
2393 * Create a new input stream structure
2394 * Returns the new input stream or NULL
2395 */
2396static docbParserInputPtr
2397docbNewInputStream(docbParserCtxtPtr ctxt) {
2398 docbParserInputPtr input;
2399
2400 input = (xmlParserInputPtr) xmlMalloc(sizeof(docbParserInput));
2401 if (input == NULL) {
2402 ctxt->errNo = XML_ERR_NO_MEMORY;
2403 if ((ctxt->sax != NULL) && (ctxt->sax->error != NULL))
2404 ctxt->sax->error(ctxt->userData,
2405 "malloc: couldn't allocate a new input stream\n");
2406 return(NULL);
2407 }
2408 memset(input, 0, sizeof(docbParserInput));
2409 input->filename = NULL;
2410 input->directory = NULL;
2411 input->base = NULL;
2412 input->cur = NULL;
2413 input->buf = NULL;
2414 input->line = 1;
2415 input->col = 1;
2416 input->buf = NULL;
2417 input->free = NULL;
2418 input->version = NULL;
2419 input->consumed = 0;
2420 input->length = 0;
2421 return(input);
2422}
2423
2424
2425/************************************************************************
2426 * *
2427 * Commodity functions, cleanup needed ? *
2428 * *
2429 ************************************************************************/
2430
2431/**
2432 * areBlanks:
2433 * @ctxt: an SGML parser context
2434 * @str: a xmlChar *
2435 * @len: the size of @str
2436 *
2437 * Is this a sequence of blank chars that one can ignore ?
2438 *
2439 * Returns 1 if ignorable 0 otherwise.
2440 */
2441
2442static int areBlanks(docbParserCtxtPtr ctxt, const xmlChar *str, int len) {
2443 int i;
2444 xmlNodePtr lastChild;
2445
2446 for (i = 0;i < len;i++)
2447 if (!(IS_BLANK(str[i]))) return(0);
2448
2449 if (CUR == 0) return(1);
2450 if (CUR != '<') return(0);
2451 if (ctxt->name == NULL)
2452 return(1);
2453 if (ctxt->node == NULL) return(0);
2454 lastChild = xmlGetLastChild(ctxt->node);
2455 if (lastChild == NULL) {
2456 if (ctxt->node->content != NULL) return(0);
2457 } else if (xmlNodeIsText(lastChild))
2458 return(0);
2459 return(1);
2460}
2461
2462/************************************************************************
Daniel Veillard61b33d52001-04-24 13:55:12 +0000[diff] [blame]2463 * *
2464 * External entities support *
2465 * *
2466 ************************************************************************/
2467
2468/**
2469 * docbParseCtxtExternalEntity:
2470 * @ctx: the existing parsing context
2471 * @URL: the URL for the entity to load
2472 * @ID: the System ID for the entity to load
2473 * @list: the return value for the set of parsed nodes
2474 *
2475 * Parse an external general entity within an existing parsing context
2476 *
2477 * Returns 0 if the entity is well formed, -1 in case of args problem and
2478 * the parser error code otherwise
2479 */
2480
2481static int
2482docbParseCtxtExternalEntity(xmlParserCtxtPtr ctx, const xmlChar *URL,
2483 const xmlChar *ID, xmlNodePtr *list) {
2484 xmlParserCtxtPtr ctxt;
2485 xmlDocPtr newDoc;
2486 xmlSAXHandlerPtr oldsax = NULL;
2487 int ret = 0;
2488
2489 if (ctx->depth > 40) {
2490 return(XML_ERR_ENTITY_LOOP);
2491 }
2492
2493 if (list != NULL)
2494 *list = NULL;
2495 if ((URL == NULL) && (ID == NULL))
2496 return(-1);
2497 if (ctx->myDoc == NULL) /* @@ relax but check for dereferences */
2498 return(-1);
2499
2500
2501 ctxt = xmlCreateEntityParserCtxt(URL, ID, ctx->myDoc->URL);
2502 if (ctxt == NULL) return(-1);
2503 ctxt->userData = ctxt;
2504 oldsax = ctxt->sax;
2505 ctxt->sax = ctx->sax;
2506 newDoc = xmlNewDoc(BAD_CAST "1.0");
2507 if (newDoc == NULL) {
2508 xmlFreeParserCtxt(ctxt);
2509 return(-1);
2510 }
2511 if (ctx->myDoc != NULL) {
2512 newDoc->intSubset = ctx->myDoc->intSubset;
2513 newDoc->extSubset = ctx->myDoc->extSubset;
2514 }
2515 if (ctx->myDoc->URL != NULL) {
2516 newDoc->URL = xmlStrdup(ctx->myDoc->URL);
2517 }
2518 newDoc->children = xmlNewDocNode(newDoc, NULL, BAD_CAST "pseudoroot", NULL);
2519 if (newDoc->children == NULL) {
2520 ctxt->sax = oldsax;
2521 xmlFreeParserCtxt(ctxt);
2522 newDoc->intSubset = NULL;
2523 newDoc->extSubset = NULL;
2524 xmlFreeDoc(newDoc);
2525 return(-1);
2526 }
2527 nodePush(ctxt, newDoc->children);
2528 if (ctx->myDoc == NULL) {
2529 ctxt->myDoc = newDoc;
2530 } else {
2531 ctxt->myDoc = ctx->myDoc;
2532 newDoc->children->doc = ctx->myDoc;
2533 }
2534
2535 /*
2536 * Parse a possible text declaration first
2537 */
2538 GROW;
2539 if ((RAW == '<') && (NXT(1) == '?') &&
2540 (NXT(2) == 'x') && (NXT(3) == 'm') &&
2541 (NXT(4) == 'l') && (IS_BLANK(NXT(5)))) {
2542 xmlParseTextDecl(ctxt);
2543 }
2544
2545 /*
2546 * Doing validity checking on chunk doesn't make sense
2547 */
2548 ctxt->instate = XML_PARSER_CONTENT;
2549 ctxt->validate = ctx->validate;
2550 ctxt->loadsubset = ctx->loadsubset;
2551 ctxt->depth = ctx->depth + 1;
2552 ctxt->replaceEntities = ctx->replaceEntities;
2553 if (ctxt->validate) {
2554 ctxt->vctxt.error = ctx->vctxt.error;
2555 ctxt->vctxt.warning = ctx->vctxt.warning;
2556 /* Allocate the Node stack */
2557 ctxt->vctxt.nodeTab = (xmlNodePtr *) xmlMalloc(4 * sizeof(xmlNodePtr));
2558 if (ctxt->vctxt.nodeTab == NULL) {
2559 xmlGenericError(xmlGenericErrorContext,
2560 "docbParseCtxtExternalEntity: out of memory\n");
2561 ctxt->validate = 0;
2562 ctxt->vctxt.error = NULL;
2563 ctxt->vctxt.warning = NULL;
2564 } else {
2565 ctxt->vctxt.nodeNr = 0;
2566 ctxt->vctxt.nodeMax = 4;
2567 ctxt->vctxt.node = NULL;
2568 }
2569 } else {
2570 ctxt->vctxt.error = NULL;
2571 ctxt->vctxt.warning = NULL;
2572 }
2573
2574 docbParseContent(ctxt);
2575
2576 if ((RAW == '<') && (NXT(1) == '/')) {
2577 ctxt->errNo = XML_ERR_NOT_WELL_BALANCED;
2578 if ((ctxt->sax != NULL) && (ctxt->sax->error != NULL))
2579 ctxt->sax->error(ctxt->userData,
2580 "chunk is not well balanced\n");
2581 ctxt->wellFormed = 0;
2582 ctxt->disableSAX = 1;
2583 } else if (RAW != 0) {
2584 ctxt->errNo = XML_ERR_EXTRA_CONTENT;
2585 if ((ctxt->sax != NULL) && (ctxt->sax->error != NULL))
2586 ctxt->sax->error(ctxt->userData,
2587 "extra content at the end of well balanced chunk\n");
2588 ctxt->wellFormed = 0;
2589 ctxt->disableSAX = 1;
2590 }
2591 if (ctxt->node != newDoc->children) {
2592 ctxt->errNo = XML_ERR_NOT_WELL_BALANCED;
2593 if ((ctxt->sax != NULL) && (ctxt->sax->error != NULL))
2594 ctxt->sax->error(ctxt->userData,
2595 "chunk is not well balanced\n");
2596 ctxt->wellFormed = 0;
2597 ctxt->disableSAX = 1;
2598 }
2599
2600 if (!ctxt->wellFormed) {
2601 if (ctxt->errNo == 0)
2602 ret = 1;
2603 else
2604 ret = ctxt->errNo;
2605 } else {
2606 if (list != NULL) {
2607 xmlNodePtr cur;
2608
2609 /*
2610 * Return the newly created nodeset after unlinking it from
2611 * they pseudo parent.
2612 */
2613 cur = newDoc->children->children;
2614 *list = cur;
2615 while (cur != NULL) {
2616 cur->parent = NULL;
2617 cur = cur->next;
2618 }
2619 newDoc->children->children = NULL;
2620 }
2621 ret = 0;
2622 }
2623 ctxt->sax = oldsax;
2624 xmlFreeParserCtxt(ctxt);
2625 newDoc->intSubset = NULL;
2626 newDoc->extSubset = NULL;
2627 xmlFreeDoc(newDoc);
2628
2629 return(ret);
2630}
2631
2632/************************************************************************
2633 * *
2634 * The parser itself *
2635 * *
Daniel Veillardeae522a2001-04-23 13:41:34 +0000[diff] [blame]2636 ************************************************************************/
2637
2638/**
2639 * docbParseSGMLName:
2640 * @ctxt: an SGML parser context
2641 *
2642 * parse an SGML tag or attribute name, note that we convert it to lowercase
2643 * since SGML names are not case-sensitive.
2644 *
2645 * Returns the Tag Name parsed or NULL
2646 */
2647
2648static xmlChar *
2649docbParseSGMLName(docbParserCtxtPtr ctxt) {
2650 xmlChar *ret = NULL;
2651 int i = 0;
2652 xmlChar loc[DOCB_PARSER_BUFFER_SIZE];
2653
2654 if (!IS_LETTER(CUR) && (CUR != '_') &&
2655 (CUR != ':')) return(NULL);
2656
2657 while ((i < DOCB_PARSER_BUFFER_SIZE) &&
2658 ((IS_LETTER(CUR)) || (IS_DIGIT(CUR)) ||
2659 (CUR == ':') || (CUR == '_'))) {
2660 if ((CUR >= 'A') && (CUR <= 'Z')) loc[i] = CUR + 0x20;
2661 else loc[i] = CUR;
2662 i++;
2663
2664 NEXT;
2665 }
2666
2667 ret = xmlStrndup(loc, i);
2668
2669 return(ret);
2670}
2671
2672/**
2673 * docbParseName:
2674 * @ctxt: an SGML parser context
2675 *
2676 * parse an SGML name, this routine is case sensistive.
2677 *
2678 * Returns the Name parsed or NULL
2679 */
2680
2681static xmlChar *
2682docbParseName(docbParserCtxtPtr ctxt) {
2683 xmlChar buf[DOCB_MAX_NAMELEN];
2684 int len = 0;
2685
2686 GROW;
2687 if (!IS_LETTER(CUR) && (CUR != '_')) {
2688 return(NULL);
2689 }
2690
2691 while ((IS_LETTER(CUR)) || (IS_DIGIT(CUR)) ||
2692 (CUR == '.') || (CUR == '-') ||
2693 (CUR == '_') || (CUR == ':') ||
2694 (IS_COMBINING(CUR)) ||
2695 (IS_EXTENDER(CUR))) {
2696 buf[len++] = CUR;
2697 NEXT;
2698 if (len >= DOCB_MAX_NAMELEN) {
2699 xmlGenericError(xmlGenericErrorContext,
2700 "docbParseName: reached DOCB_MAX_NAMELEN limit\n");
2701 while ((IS_LETTER(CUR)) || (IS_DIGIT(CUR)) ||
2702 (CUR == '.') || (CUR == '-') ||
2703 (CUR == '_') || (CUR == ':') ||
2704 (IS_COMBINING(CUR)) ||
2705 (IS_EXTENDER(CUR)))
2706 NEXT;
2707 break;
2708 }
2709 }
2710 return(xmlStrndup(buf, len));
2711}
2712
2713/**
2714 * docbParseSGMLAttribute:
2715 * @ctxt: an SGML parser context
2716 * @stop: a char stop value
2717 *
2718 * parse an SGML attribute value till the stop (quote), if
2719 * stop is 0 then it stops at the first space
2720 *
2721 * Returns the attribute parsed or NULL
2722 */
2723
2724static xmlChar *
2725docbParseSGMLAttribute(docbParserCtxtPtr ctxt, const xmlChar stop) {
2726 xmlChar *buffer = NULL;
2727 int buffer_size = 0;
2728 xmlChar *out = NULL;
2729 xmlChar *name = NULL;
2730
2731 xmlChar *cur = NULL;
Daniel Veillard61b33d52001-04-24 13:55:12 +0000[diff] [blame]2732 xmlEntityPtr xent;
Daniel Veillardeae522a2001-04-23 13:41:34 +0000[diff] [blame]2733 docbEntityDescPtr ent;
2734
2735 /*
2736 * allocate a translation buffer.
2737 */
2738 buffer_size = DOCB_PARSER_BIG_BUFFER_SIZE;
2739 buffer = (xmlChar *) xmlMalloc(buffer_size * sizeof(xmlChar));
2740 if (buffer == NULL) {
2741 perror("docbParseSGMLAttribute: malloc failed");
2742 return(NULL);
2743 }
2744 out = buffer;
2745
2746 /*
2747 * Ok loop until we reach one of the ending chars
2748 */
2749 while ((CUR != 0) && (CUR != stop) && (CUR != '>')) {
2750 if ((stop == 0) && (IS_BLANK(CUR))) break;
2751 if (CUR == '&') {
2752 if (NXT(1) == '#') {
2753 unsigned int c;
2754 int bits;
2755
2756 c = docbParseCharRef(ctxt);
2757 if (c < 0x80)
2758 { *out++ = c; bits= -6; }
2759 else if (c < 0x800)
2760 { *out++ =((c >> 6) & 0x1F) | 0xC0; bits= 0; }
2761 else if (c < 0x10000)
2762 { *out++ =((c >> 12) & 0x0F) | 0xE0; bits= 6; }
2763 else
2764 { *out++ =((c >> 18) & 0x07) | 0xF0; bits= 12; }
2765
2766 for ( ; bits >= 0; bits-= 6) {
2767 *out++ = ((c >> bits) & 0x3F) | 0x80;
2768 }
2769 } else {
2770 ent = docbParseEntityRef(ctxt, &name);
2771 if (name == NULL) {
2772 *out++ = '&';
2773 if (out - buffer > buffer_size - 100) {
2774 int indx = out - buffer;
2775
2776 growBuffer(buffer);
2777 out = &buffer[indx];
2778 }
2779 } else if (ent == NULL) {
2780 *out++ = '&';
2781 cur = name;
2782 while (*cur != 0) {
2783 if (out - buffer > buffer_size - 100) {
2784 int indx = out - buffer;
2785
2786 growBuffer(buffer);
2787 out = &buffer[indx];
2788 }
2789 *out++ = *cur++;
2790 }
2791 xmlFree(name);
2792 } else {
2793 unsigned int c;
2794 int bits;
2795
2796 if (out - buffer > buffer_size - 100) {
2797 int indx = out - buffer;
2798
2799 growBuffer(buffer);
2800 out = &buffer[indx];
2801 }
2802 c = (xmlChar)ent->value;
2803 if (c < 0x80)
2804 { *out++ = c; bits= -6; }
2805 else if (c < 0x800)
2806 { *out++ =((c >> 6) & 0x1F) | 0xC0; bits= 0; }
2807 else if (c < 0x10000)
2808 { *out++ =((c >> 12) & 0x0F) | 0xE0; bits= 6; }
2809 else
2810 { *out++ =((c >> 18) & 0x07) | 0xF0; bits= 12; }
2811
2812 for ( ; bits >= 0; bits-= 6) {
2813 *out++ = ((c >> bits) & 0x3F) | 0x80;
2814 }
2815 xmlFree(name);
2816 }
2817 }
2818 } else {
2819 unsigned int c;
2820 int bits;
2821
2822 if (out - buffer > buffer_size - 100) {
2823 int indx = out - buffer;
2824
2825 growBuffer(buffer);
2826 out = &buffer[indx];
2827 }
2828 c = CUR;
2829 if (c < 0x80)
2830 { *out++ = c; bits= -6; }
2831 else if (c < 0x800)
2832 { *out++ =((c >> 6) & 0x1F) | 0xC0; bits= 0; }
2833 else if (c < 0x10000)
2834 { *out++ =((c >> 12) & 0x0F) | 0xE0; bits= 6; }
2835 else
2836 { *out++ =((c >> 18) & 0x07) | 0xF0; bits= 12; }
2837
2838 for ( ; bits >= 0; bits-= 6) {
2839 *out++ = ((c >> bits) & 0x3F) | 0x80;
2840 }
2841 NEXT;
2842 }
2843 }
2844 *out++ = 0;
2845 return(buffer);
2846}
2847
2848
2849/**
2850 * docbParseEntityRef:
2851 * @ctxt: an SGML parser context
2852 * @str: location to store the entity name
2853 *
2854 * parse an SGML ENTITY references
2855 *
2856 * [68] EntityRef ::= '&' Name ';'
2857 *
Daniel Veillard61b33d52001-04-24 13:55:12 +0000[diff] [blame]2858 * Returns the associated xmlEntityPtr if found, or NULL otherwise,
Daniel Veillardeae522a2001-04-23 13:41:34 +0000[diff] [blame]2859 * if non-NULL *str will have to be freed by the caller.
2860 */
Daniel Veillard61b33d52001-04-24 13:55:12 +0000[diff] [blame]2861static xmlEntityPtr
Daniel Veillardeae522a2001-04-23 13:41:34 +0000[diff] [blame]2862docbParseEntityRef(docbParserCtxtPtr ctxt, xmlChar **str) {
2863 xmlChar *name;
Daniel Veillard61b33d52001-04-24 13:55:12 +0000[diff] [blame]2864 xmlEntityPtr ent = NULL;
Daniel Veillardeae522a2001-04-23 13:41:34 +0000[diff] [blame]2865 *str = NULL;
2866
2867 if (CUR == '&') {
2868 NEXT;
2869 name = docbParseName(ctxt);
Daniel Veillard61b33d52001-04-24 13:55:12 +0000[diff] [blame]2870 if (name == NULL) {
2871 if ((ctxt->sax != NULL) && (ctxt->sax->error != NULL))
2872 ctxt->sax->error(ctxt->userData,
2873 "docbParseEntityRef: no name\n");
2874 ctxt->wellFormed = 0;
2875 } else {
Daniel Veillardeae522a2001-04-23 13:41:34 +0000[diff] [blame]2876 GROW;
Daniel Veillard61b33d52001-04-24 13:55:12 +0000[diff] [blame]2877 if (CUR == ';') {
2878 *str = name;
Daniel Veillardeae522a2001-04-23 13:41:34 +0000[diff] [blame]2879
Daniel Veillard61b33d52001-04-24 13:55:12 +0000[diff] [blame]2880 /*
2881 * Ask first SAX for entity resolution, otherwise try the
2882 * predefined set.
2883 */
2884 if (ctxt->sax != NULL) {
2885 if (ctxt->sax->getEntity != NULL)
2886 ent = ctxt->sax->getEntity(ctxt->userData, name);
2887 if (ent == NULL)
2888 ent = xmlGetPredefinedEntity(name);
2889 }
2890 NEXT;
2891 } else {
2892 if ((ctxt->sax != NULL) && (ctxt->sax->error != NULL))
2893 ctxt->sax->error(ctxt->userData,
Daniel Veillardeae522a2001-04-23 13:41:34 +0000[diff] [blame]2894 "docbParseEntityRef: expecting ';'\n");
Daniel Veillard61b33d52001-04-24 13:55:12 +0000[diff] [blame]2895 *str = name;
2896 }
2897 }
Daniel Veillardeae522a2001-04-23 13:41:34 +0000[diff] [blame]2898 }
2899 return(ent);
2900}
2901
2902/**
2903 * docbParseAttValue:
2904 * @ctxt: an SGML parser context
2905 *
2906 * parse a value for an attribute
2907 * Note: the parser won't do substitution of entities here, this
2908 * will be handled later in xmlStringGetNodeList, unless it was
2909 * asked for ctxt->replaceEntities != 0
2910 *
2911 * Returns the AttValue parsed or NULL.
2912 */
2913
2914static xmlChar *
2915docbParseAttValue(docbParserCtxtPtr ctxt) {
2916 xmlChar *ret = NULL;
2917
2918 if (CUR == '"') {
2919 NEXT;
2920 ret = docbParseSGMLAttribute(ctxt, '"');
2921 if (CUR != '"') {
2922 if ((ctxt->sax != NULL) && (ctxt->sax->error != NULL))
2923 ctxt->sax->error(ctxt->userData, "AttValue: ' expected\n");
2924 ctxt->wellFormed = 0;
2925 } else
2926 NEXT;
2927 } else if (CUR == '\'') {
2928 NEXT;
2929 ret = docbParseSGMLAttribute(ctxt, '\'');
2930 if (CUR != '\'') {
2931 if ((ctxt->sax != NULL) && (ctxt->sax->error != NULL))
2932 ctxt->sax->error(ctxt->userData, "AttValue: ' expected\n");
2933 ctxt->wellFormed = 0;
2934 } else
2935 NEXT;
2936 } else {
2937 /*
2938 * That's an SGMLism, the attribute value may not be quoted
2939 */
2940 ret = docbParseSGMLAttribute(ctxt, 0);
2941 if (ret == NULL) {
2942 if ((ctxt->sax != NULL) && (ctxt->sax->error != NULL))
2943 ctxt->sax->error(ctxt->userData, "AttValue: no value found\n");
2944 ctxt->wellFormed = 0;
2945 }
2946 }
2947 return(ret);
2948}
2949
2950/**
2951 * docbParseSystemLiteral:
2952 * @ctxt: an SGML parser context
2953 *
2954 * parse an SGML Literal
2955 *
2956 * [11] SystemLiteral ::= ('"' [^"]* '"') | ("'" [^']* "'")
2957 *
2958 * Returns the SystemLiteral parsed or NULL
2959 */
2960
2961static xmlChar *
2962docbParseSystemLiteral(docbParserCtxtPtr ctxt) {
2963 const xmlChar *q;
2964 xmlChar *ret = NULL;
2965
2966 if (CUR == '"') {
2967 NEXT;
2968 q = CUR_PTR;
2969 while ((IS_CHAR(CUR)) && (CUR != '"'))
2970 NEXT;
2971 if (!IS_CHAR(CUR)) {
2972 if ((ctxt->sax != NULL) && (ctxt->sax->error != NULL))
2973 ctxt->sax->error(ctxt->userData, "Unfinished SystemLiteral\n");
2974 ctxt->wellFormed = 0;
2975 } else {
2976 ret = xmlStrndup(q, CUR_PTR - q);
2977 NEXT;
2978 }
2979 } else if (CUR == '\'') {
2980 NEXT;
2981 q = CUR_PTR;
2982 while ((IS_CHAR(CUR)) && (CUR != '\''))
2983 NEXT;
2984 if (!IS_CHAR(CUR)) {
2985 if ((ctxt->sax != NULL) && (ctxt->sax->error != NULL))
2986 ctxt->sax->error(ctxt->userData, "Unfinished SystemLiteral\n");
2987 ctxt->wellFormed = 0;
2988 } else {
2989 ret = xmlStrndup(q, CUR_PTR - q);
2990 NEXT;
2991 }
2992 } else {
2993 if ((ctxt->sax != NULL) && (ctxt->sax->error != NULL))
2994 ctxt->sax->error(ctxt->userData,
2995 "SystemLiteral \" or ' expected\n");
2996 ctxt->wellFormed = 0;
2997 }
2998
2999 return(ret);
3000}
3001
3002/**
3003 * docbParsePubidLiteral:
3004 * @ctxt: an SGML parser context
3005 *
3006 * parse an SGML public literal
3007 *
3008 * [12] PubidLiteral ::= '"' PubidChar* '"' | "'" (PubidChar - "'")* "'"
3009 *
3010 * Returns the PubidLiteral parsed or NULL.
3011 */
3012
3013static xmlChar *
3014docbParsePubidLiteral(docbParserCtxtPtr ctxt) {
3015 const xmlChar *q;
3016 xmlChar *ret = NULL;
3017 /*
3018 * Name ::= (Letter | '_') (NameChar)*
3019 */
3020 if (CUR == '"') {
3021 NEXT;
3022 q = CUR_PTR;
3023 while (IS_PUBIDCHAR(CUR)) NEXT;
3024 if (CUR != '"') {
3025 if ((ctxt->sax != NULL) && (ctxt->sax->error != NULL))
3026 ctxt->sax->error(ctxt->userData, "Unfinished PubidLiteral\n");
3027 ctxt->wellFormed = 0;
3028 } else {
3029 ret = xmlStrndup(q, CUR_PTR - q);
3030 NEXT;
3031 }
3032 } else if (CUR == '\'') {
3033 NEXT;
3034 q = CUR_PTR;
3035 while ((IS_LETTER(CUR)) && (CUR != '\''))
3036 NEXT;
3037 if (!IS_LETTER(CUR)) {
3038 if ((ctxt->sax != NULL) && (ctxt->sax->error != NULL))
3039 ctxt->sax->error(ctxt->userData, "Unfinished PubidLiteral\n");
3040 ctxt->wellFormed = 0;
3041 } else {
3042 ret = xmlStrndup(q, CUR_PTR - q);
3043 NEXT;
3044 }
3045 } else {
3046 if ((ctxt->sax != NULL) && (ctxt->sax->error != NULL))
3047 ctxt->sax->error(ctxt->userData, "SystemLiteral \" or ' expected\n");
3048 ctxt->wellFormed = 0;
3049 }
3050
3051 return(ret);
3052}
3053
3054/**
3055 * docbParseCharData:
3056 * @ctxt: an SGML parser context
3057 * @cdata: int indicating whether we are within a CDATA section
3058 *
3059 * parse a CharData section.
3060 * if we are within a CDATA section ']]>' marks an end of section.
3061 *
3062 * [14] CharData ::= [^<&]* - ([^<&]* ']]>' [^<&]*)
3063 */
3064
3065static void
3066docbParseCharData(docbParserCtxtPtr ctxt) {
3067 xmlChar buf[DOCB_PARSER_BIG_BUFFER_SIZE + 5];
3068 int nbchar = 0;
3069 int cur, l;
3070
3071 SHRINK;
3072 cur = CUR_CHAR(l);
3073 while (((cur != '<') || (ctxt->token == '<')) &&
3074 ((cur != '&') || (ctxt->token == '&')) &&
3075 (IS_CHAR(cur))) {
3076 COPY_BUF(l,buf,nbchar,cur);
3077 if (nbchar >= DOCB_PARSER_BIG_BUFFER_SIZE) {
3078 /*
3079 * Ok the segment is to be consumed as chars.
3080 */
3081 if ((ctxt->sax != NULL) && (!ctxt->disableSAX)) {
3082 if (areBlanks(ctxt, buf, nbchar)) {
3083 if (ctxt->sax->ignorableWhitespace != NULL)
3084 ctxt->sax->ignorableWhitespace(ctxt->userData,
3085 buf, nbchar);
3086 } else {
3087 docbCheckParagraph(ctxt);
3088 if (ctxt->sax->characters != NULL)
3089 ctxt->sax->characters(ctxt->userData, buf, nbchar);
3090 }
3091 }
3092 nbchar = 0;
3093 }
3094 NEXTL(l);
3095 cur = CUR_CHAR(l);
3096 }
3097 if (nbchar != 0) {
3098 /*
3099 * Ok the segment is to be consumed as chars.
3100 */
3101 if ((ctxt->sax != NULL) && (!ctxt->disableSAX)) {
3102 if (areBlanks(ctxt, buf, nbchar)) {
3103 if (ctxt->sax->ignorableWhitespace != NULL)
3104 ctxt->sax->ignorableWhitespace(ctxt->userData, buf, nbchar);
3105 } else {
3106 docbCheckParagraph(ctxt);
3107 if (ctxt->sax->characters != NULL)
3108 ctxt->sax->characters(ctxt->userData, buf, nbchar);
3109 }
3110 }
3111 }
3112}
3113
3114/**
3115 * docbParseExternalID:
3116 * @ctxt: an SGML parser context
3117 * @publicID: a xmlChar** receiving PubidLiteral
3118 *
3119 * Parse an External ID or a Public ID
3120 *
3121 * Returns the function returns SystemLiteral and in the second
3122 * case publicID receives PubidLiteral,
3123 * it is possible to return NULL and have publicID set.
3124 */
3125
3126static xmlChar *
3127docbParseExternalID(docbParserCtxtPtr ctxt, xmlChar **publicID) {
3128 xmlChar *URI = NULL;
3129
3130 if ((UPPER == 'S') && (UPP(1) == 'Y') &&
3131 (UPP(2) == 'S') && (UPP(3) == 'T') &&
3132 (UPP(4) == 'E') && (UPP(5) == 'M')) {
3133 SKIP(6);
3134 if (!IS_BLANK(CUR)) {
3135 if ((ctxt->sax != NULL) && (ctxt->sax->error != NULL))
3136 ctxt->sax->error(ctxt->userData,
3137 "Space required after 'SYSTEM'\n");
3138 ctxt->wellFormed = 0;
3139 }
3140 SKIP_BLANKS;
3141 URI = docbParseSystemLiteral(ctxt);
3142 if (URI == NULL) {
3143 if ((ctxt->sax != NULL) && (ctxt->sax->error != NULL))
3144 ctxt->sax->error(ctxt->userData,
3145 "docbParseExternalID: SYSTEM, no URI\n");
3146 ctxt->wellFormed = 0;
3147 }
3148 } else if ((UPPER == 'P') && (UPP(1) == 'U') &&
3149 (UPP(2) == 'B') && (UPP(3) == 'L') &&
3150 (UPP(4) == 'I') && (UPP(5) == 'C')) {
3151 SKIP(6);
3152 if (!IS_BLANK(CUR)) {
3153 if ((ctxt->sax != NULL) && (ctxt->sax->error != NULL))
3154 ctxt->sax->error(ctxt->userData,
3155 "Space required after 'PUBLIC'\n");
3156 ctxt->wellFormed = 0;
3157 }
3158 SKIP_BLANKS;
3159 *publicID = docbParsePubidLiteral(ctxt);
3160 if (*publicID == NULL) {
3161 if ((ctxt->sax != NULL) && (ctxt->sax->error != NULL))
3162 ctxt->sax->error(ctxt->userData,
3163 "docbParseExternalID: PUBLIC, no Public Identifier\n");
3164 ctxt->wellFormed = 0;
3165 }
3166 SKIP_BLANKS;
3167 if ((CUR == '"') || (CUR == '\'')) {
3168 URI = docbParseSystemLiteral(ctxt);
3169 }
3170 }
3171 return(URI);
3172}
3173
3174/**
3175 * docbParseComment:
3176 * @ctxt: an SGML parser context
3177 *
3178 * Parse an XML (SGML) comment <!-- .... -->
3179 *
3180 * [15] Comment ::= '<!--' ((Char - '-') | ('-' (Char - '-')))* '-->'
3181 */
3182static void
3183docbParseComment(docbParserCtxtPtr ctxt) {
3184 xmlChar *buf = NULL;
3185 int len;
3186 int size = DOCB_PARSER_BUFFER_SIZE;
3187 int q, ql;
3188 int r, rl;
3189 int cur, l;
3190 xmlParserInputState state;
3191
3192 /*
3193 * Check that there is a comment right here.
3194 */
3195 if ((RAW != '<') || (NXT(1) != '!') ||
3196 (NXT(2) != '-') || (NXT(3) != '-')) return;
3197
3198 state = ctxt->instate;
3199 ctxt->instate = XML_PARSER_COMMENT;
3200 SHRINK;
3201 SKIP(4);
3202 buf = (xmlChar *) xmlMalloc(size * sizeof(xmlChar));
3203 if (buf == NULL) {
3204 xmlGenericError(xmlGenericErrorContext,
3205 "malloc of %d byte failed\n", size);
3206 ctxt->instate = state;
3207 return;
3208 }
3209 q = CUR_CHAR(ql);
3210 NEXTL(ql);
3211 r = CUR_CHAR(rl);
3212 NEXTL(rl);
3213 cur = CUR_CHAR(l);
3214 len = 0;
3215 while (IS_CHAR(cur) &&
3216 ((cur != '>') ||
3217 (r != '-') || (q != '-'))) {
3218 if (len + 5 >= size) {
3219 size *= 2;
3220 buf = (xmlChar *) xmlRealloc(buf, size * sizeof(xmlChar));
3221 if (buf == NULL) {
3222 xmlGenericError(xmlGenericErrorContext,
3223 "realloc of %d byte failed\n", size);
3224 ctxt->instate = state;
3225 return;
3226 }
3227 }
3228 COPY_BUF(ql,buf,len,q);
3229 q = r;
3230 ql = rl;
3231 r = cur;
3232 rl = l;
3233 NEXTL(l);
3234 cur = CUR_CHAR(l);
3235 if (cur == 0) {
3236 SHRINK;
3237 GROW;
3238 cur = CUR_CHAR(l);
3239 }
3240 }
3241 buf[len] = 0;
3242 if (!IS_CHAR(cur)) {
3243 ctxt->errNo = XML_ERR_COMMENT_NOT_FINISHED;
3244 if ((ctxt->sax != NULL) && (ctxt->sax->error != NULL))
3245 ctxt->sax->error(ctxt->userData,
3246 "Comment not terminated \n<!--%.50s\n", buf);
3247 ctxt->wellFormed = 0;
3248 xmlFree(buf);
3249 } else {
3250 NEXT;
3251 if ((ctxt->sax != NULL) && (ctxt->sax->comment != NULL) &&
3252 (!ctxt->disableSAX))
3253 ctxt->sax->comment(ctxt->userData, buf);
3254 xmlFree(buf);
3255 }
3256 ctxt->instate = state;
3257}
3258
3259/**
3260 * docbParseCharRef:
3261 * @ctxt: an SGML parser context
3262 *
3263 * parse Reference declarations
3264 *
3265 * [66] CharRef ::= '&#' [0-9]+ ';' |
3266 * '&#x' [0-9a-fA-F]+ ';'
3267 *
3268 * Returns the value parsed (as an int)
3269 */
3270static int
3271docbParseCharRef(docbParserCtxtPtr ctxt) {
3272 int val = 0;
3273
3274 if ((CUR == '&') && (NXT(1) == '#') &&
3275 (NXT(2) == 'x')) {
3276 SKIP(3);
3277 while (CUR != ';') {
3278 if ((CUR >= '0') && (CUR <= '9'))
3279 val = val * 16 + (CUR - '0');
3280 else if ((CUR >= 'a') && (CUR <= 'f'))
3281 val = val * 16 + (CUR - 'a') + 10;
3282 else if ((CUR >= 'A') && (CUR <= 'F'))
3283 val = val * 16 + (CUR - 'A') + 10;
3284 else {
3285 if ((ctxt->sax != NULL) && (ctxt->sax->error != NULL))
3286 ctxt->sax->error(ctxt->userData,
3287 "docbParseCharRef: invalid hexadecimal value\n");
3288 ctxt->wellFormed = 0;
3289 val = 0;
3290 break;
3291 }
3292 NEXT;
3293 }
3294 if (CUR == ';')
3295 NEXT;
3296 } else if ((CUR == '&') && (NXT(1) == '#')) {
3297 SKIP(2);
3298 while (CUR != ';') {
3299 if ((CUR >= '0') && (CUR <= '9'))
3300 val = val * 10 + (CUR - '0');
3301 else {
3302 if ((ctxt->sax != NULL) && (ctxt->sax->error != NULL))
3303 ctxt->sax->error(ctxt->userData,
3304 "docbParseCharRef: invalid decimal value\n");
3305 ctxt->wellFormed = 0;
3306 val = 0;
3307 break;
3308 }
3309 NEXT;
3310 }
3311 if (CUR == ';')
3312 NEXT;
3313 } else {
3314 if ((ctxt->sax != NULL) && (ctxt->sax->error != NULL))
3315 ctxt->sax->error(ctxt->userData, "docbParseCharRef: invalid value\n");
3316 ctxt->wellFormed = 0;
3317 }
3318 /*
3319 * Check the value IS_CHAR ...
3320 */
3321 if (IS_CHAR(val)) {
3322 return(val);
3323 } else {
3324 if ((ctxt->sax != NULL) && (ctxt->sax->error != NULL))
3325 ctxt->sax->error(ctxt->userData, "docbParseCharRef: invalid xmlChar value %d\n",
3326 val);
3327 ctxt->wellFormed = 0;
3328 }
3329 return(0);
3330}
3331
3332
3333/**
3334 * docbParseDocTypeDecl :
3335 * @ctxt: an SGML parser context
3336 *
3337 * parse a DOCTYPE declaration
3338 *
3339 * [28] doctypedecl ::= '<!DOCTYPE' S Name (S ExternalID)? S?
3340 * ('[' (markupdecl | PEReference | S)* ']' S?)? '>'
3341 */
3342
3343static void
3344docbParseDocTypeDecl(docbParserCtxtPtr ctxt) {
3345 xmlChar *name;
3346 xmlChar *ExternalID = NULL;
3347 xmlChar *URI = NULL;
3348
3349 /*
3350 * We know that '<!DOCTYPE' has been detected.
3351 */
3352 SKIP(9);
3353
3354 SKIP_BLANKS;
3355
3356 /*
3357 * Parse the DOCTYPE name.
3358 */
3359 name = docbParseName(ctxt);
3360 if (name == NULL) {
3361 if ((ctxt->sax != NULL) && (ctxt->sax->error != NULL))
3362 ctxt->sax->error(ctxt->userData, "docbParseDocTypeDecl : no DOCTYPE name !\n");
3363 ctxt->wellFormed = 0;
3364 }
3365 /*
3366 * Check that upper(name) == "SGML" !!!!!!!!!!!!!
3367 */
3368
3369 SKIP_BLANKS;
3370
3371 /*
3372 * Check for SystemID and ExternalID
3373 */
3374 URI = docbParseExternalID(ctxt, &ExternalID);
3375 SKIP_BLANKS;
3376
3377 /*
3378 * Create or update the document accordingly to the DOCTYPE
3379 */
3380 if ((ctxt->sax != NULL) && (ctxt->sax->internalSubset != NULL) &&
3381 (!ctxt->disableSAX))
3382 ctxt->sax->internalSubset(ctxt->userData, name, ExternalID, URI);
3383
3384 /*
3385 * Is there any internal subset declarations ?
3386 * they are handled separately in docbParseInternalSubset()
3387 */
Daniel Veillard61b33d52001-04-24 13:55:12 +0000[diff] [blame]3388 if (RAW != '[') {
Daniel Veillardeae522a2001-04-23 13:41:34 +0000[diff] [blame]3389 return;
3390
Daniel Veillard61b33d52001-04-24 13:55:12 +0000[diff] [blame]3391 /*
3392 * We should be at the end of the DOCTYPE declaration.
3393 */
3394 if (CUR != '>') {
3395 if ((ctxt->sax != NULL) && (ctxt->sax->error != NULL))
3396 ctxt->sax->error(ctxt->userData,
3397 "DOCTYPE unproperly terminated\n");
3398 ctxt->wellFormed = 0;
3399 /* We shouldn't try to resynchronize ... */
3400 }
3401 NEXT;
Daniel Veillardeae522a2001-04-23 13:41:34 +0000[diff] [blame]3402 }
Daniel Veillardeae522a2001-04-23 13:41:34 +0000[diff] [blame]3403
3404 /*
3405 * Cleanup, since we don't use all those identifiers
3406 */
3407 if (URI != NULL) xmlFree(URI);
3408 if (ExternalID != NULL) xmlFree(ExternalID);
3409 if (name != NULL) xmlFree(name);
3410}
3411
3412/**
3413 * docbParseAttribute:
3414 * @ctxt: an SGML parser context
3415 * @value: a xmlChar ** used to store the value of the attribute
3416 *
3417 * parse an attribute
3418 *
3419 * [41] Attribute ::= Name Eq AttValue
3420 *
3421 * [25] Eq ::= S? '=' S?
3422 *
3423 * With namespace:
3424 *
3425 * [NS 11] Attribute ::= QName Eq AttValue
3426 *
3427 * Also the case QName == xmlns:??? is handled independently as a namespace
3428 * definition.
3429 *
3430 * Returns the attribute name, and the value in *value.
3431 */
3432
3433static xmlChar *
3434docbParseAttribute(docbParserCtxtPtr ctxt, xmlChar **value) {
3435 xmlChar *name, *val = NULL;
3436
3437 *value = NULL;
3438 name = docbParseName(ctxt);
3439 if (name == NULL) {
3440 if ((ctxt->sax != NULL) && (ctxt->sax->error != NULL))
3441 ctxt->sax->error(ctxt->userData, "error parsing attribute name\n");
3442 ctxt->wellFormed = 0;
3443 return(NULL);
3444 }
3445
3446 /*
3447 * read the value
3448 */
3449 SKIP_BLANKS;
3450 if (CUR == '=') {
3451 NEXT;
3452 SKIP_BLANKS;
3453 val = docbParseAttValue(ctxt);
3454 /******
3455 } else {
3456 * TODO : some attribute must have values, some may not
3457 if ((ctxt->sax != NULL) && (ctxt->sax->error != NULL))
3458 ctxt->sax->warning(ctxt->userData,
3459 "No value for attribute %s\n", name); */
3460 }
3461
3462 *value = val;
3463 return(name);
3464}
3465
3466/**
3467 * docbCheckEncoding:
3468 * @ctxt: an SGML parser context
3469 * @attvalue: the attribute value
3470 *
3471 * Checks an http-equiv attribute from a Meta tag to detect
3472 * the encoding
3473 * If a new encoding is detected the parser is switched to decode
3474 * it and pass UTF8
3475 */
3476static void
3477docbCheckEncoding(docbParserCtxtPtr ctxt, const xmlChar *attvalue) {
3478 const xmlChar *encoding;
3479
3480 if ((ctxt == NULL) || (attvalue == NULL))
3481 return;
3482
3483 encoding = xmlStrstr(attvalue, BAD_CAST"charset=");
3484 if (encoding == NULL)
3485 encoding = xmlStrstr(attvalue, BAD_CAST"Charset=");
3486 if (encoding == NULL)
3487 encoding = xmlStrstr(attvalue, BAD_CAST"CHARSET=");
3488 if (encoding != NULL) {
3489 encoding += 8;
3490 } else {
3491 encoding = xmlStrstr(attvalue, BAD_CAST"charset =");
3492 if (encoding == NULL)
3493 encoding = xmlStrstr(attvalue, BAD_CAST"Charset =");
3494 if (encoding == NULL)
3495 encoding = xmlStrstr(attvalue, BAD_CAST"CHARSET =");
3496 if (encoding != NULL)
3497 encoding += 9;
3498 }
3499 /*
3500 * Restricted from 2.3.5 */
3501 if (encoding != NULL) {
3502 xmlCharEncoding enc;
3503
3504 if (ctxt->input->encoding != NULL)
3505 xmlFree((xmlChar *) ctxt->input->encoding);
3506 ctxt->input->encoding = encoding;
3507
3508 enc = xmlParseCharEncoding((const char *) encoding);
3509 if (enc == XML_CHAR_ENCODING_8859_1) {
3510 ctxt->charset = XML_CHAR_ENCODING_8859_1;
3511 } else if (enc != XML_CHAR_ENCODING_UTF8) {
3512 if ((ctxt->sax != NULL) && (ctxt->sax->error != NULL))
3513 ctxt->sax->error(ctxt->userData,
3514 "Unsupported encoding %s\n", encoding);
3515 /* xmlFree(encoding); */
3516 ctxt->wellFormed = 0;
3517 ctxt->disableSAX = 1;
3518 ctxt->errNo = XML_ERR_UNSUPPORTED_ENCODING;
3519 }
3520 }
3521}
3522
3523/**
3524 * docbCheckMeta:
3525 * @ctxt: an SGML parser context
3526 * @atts: the attributes values
3527 *
3528 * Checks an attributes from a Meta tag
3529 */
3530static void
3531docbCheckMeta(docbParserCtxtPtr ctxt, const xmlChar **atts) {
3532 int i;
3533 const xmlChar *att, *value;
3534 int http = 0;
3535 const xmlChar *content = NULL;
3536
3537 if ((ctxt == NULL) || (atts == NULL))
3538 return;
3539
3540 i = 0;
3541 att = atts[i++];
3542 while (att != NULL) {
3543 value = atts[i++];
3544 if ((value != NULL) &&
3545 ((xmlStrEqual(att, BAD_CAST"http-equiv")) ||
3546 (xmlStrEqual(att, BAD_CAST"Http-Equiv")) ||
3547 (xmlStrEqual(att, BAD_CAST"HTTP-EQUIV"))) &&
3548 ((xmlStrEqual(value, BAD_CAST"Content-Type")) ||
3549 (xmlStrEqual(value, BAD_CAST"content-type")) ||
3550 (xmlStrEqual(value, BAD_CAST"CONTENT-TYPE"))))
3551 http = 1;
3552 else if ((value != NULL) &&
3553 ((xmlStrEqual(att, BAD_CAST"content")) ||
3554 (xmlStrEqual(att, BAD_CAST"Content")) ||
3555 (xmlStrEqual(att, BAD_CAST"CONTENT"))))
3556 content = value;
3557 att = atts[i++];
3558 }
3559 if ((http) && (content != NULL))
3560 docbCheckEncoding(ctxt, content);
3561
3562}
3563
3564/**
3565 * docbParseStartTag:
3566 * @ctxt: an SGML parser context
3567 *
3568 * parse a start of tag either for rule element or
3569 * EmptyElement. In both case we don't parse the tag closing chars.
3570 *
3571 * [40] STag ::= '<' Name (S Attribute)* S? '>'
3572 *
3573 * [44] EmptyElemTag ::= '<' Name (S Attribute)* S? '/>'
3574 *
3575 * With namespace:
3576 *
3577 * [NS 8] STag ::= '<' QName (S Attribute)* S? '>'
3578 *
3579 * [NS 10] EmptyElement ::= '<' QName (S Attribute)* S? '/>'
3580 *
3581 */
3582
3583static void
3584docbParseStartTag(docbParserCtxtPtr ctxt) {
3585 xmlChar *name;
3586 xmlChar *attname;
3587 xmlChar *attvalue;
3588 const xmlChar **atts = NULL;
3589 int nbatts = 0;
3590 int maxatts = 0;
3591 int meta = 0;
3592 int i;
3593
3594 if (CUR != '<') return;
3595 NEXT;
3596
3597 GROW;
3598 name = docbParseSGMLName(ctxt);
3599 if (name == NULL) {
3600 if ((ctxt->sax != NULL) && (ctxt->sax->error != NULL))
3601 ctxt->sax->error(ctxt->userData,
3602 "docbParseStartTag: invalid element name\n");
3603 ctxt->wellFormed = 0;
3604 return;
3605 }
3606 if (xmlStrEqual(name, BAD_CAST"meta"))
3607 meta = 1;
3608
3609 /*
3610 * Check for auto-closure of SGML elements.
3611 */
3612 docbAutoClose(ctxt, name);
3613
3614 /*
3615 * Now parse the attributes, it ends up with the ending
3616 *
3617 * (S Attribute)* S?
3618 */
3619 SKIP_BLANKS;
3620 while ((IS_CHAR(CUR)) &&
3621 (CUR != '>') &&
3622 ((CUR != '/') || (NXT(1) != '>'))) {
3623 long cons = ctxt->nbChars;
3624
3625 GROW;
3626 attname = docbParseAttribute(ctxt, &attvalue);
3627 if (attname != NULL) {
3628
3629 /*
3630 * Well formedness requires at most one declaration of an attribute
3631 */
3632 for (i = 0; i < nbatts;i += 2) {
3633 if (xmlStrEqual(atts[i], attname)) {
3634 if ((ctxt->sax != NULL) && (ctxt->sax->error != NULL))
3635 ctxt->sax->error(ctxt->userData,
3636 "Attribute %s redefined\n",
3637 attname);
3638 ctxt->wellFormed = 0;
3639 xmlFree(attname);
3640 if (attvalue != NULL)
3641 xmlFree(attvalue);
3642 goto failed;
3643 }
3644 }
3645
3646 /*
3647 * Add the pair to atts
3648 */
3649 if (atts == NULL) {
3650 maxatts = 10;
3651 atts = (const xmlChar **) xmlMalloc(maxatts * sizeof(xmlChar *));
3652 if (atts == NULL) {
3653 xmlGenericError(xmlGenericErrorContext,
3654 "malloc of %ld byte failed\n",
3655 maxatts * (long)sizeof(xmlChar *));
3656 if (name != NULL) xmlFree(name);
3657 return;
3658 }
3659 } else if (nbatts + 4 > maxatts) {
3660 maxatts *= 2;
3661 atts = (const xmlChar **) xmlRealloc(atts, maxatts * sizeof(xmlChar *));
3662 if (atts == NULL) {
3663 xmlGenericError(xmlGenericErrorContext,
3664 "realloc of %ld byte failed\n",
3665 maxatts * (long)sizeof(xmlChar *));
3666 if (name != NULL) xmlFree(name);
3667 return;
3668 }
3669 }
3670 atts[nbatts++] = attname;
3671 atts[nbatts++] = attvalue;
3672 atts[nbatts] = NULL;
3673 atts[nbatts + 1] = NULL;
3674 }
3675
3676failed:
3677 SKIP_BLANKS;
3678 if (cons == ctxt->nbChars) {
3679 if ((ctxt->sax != NULL) && (ctxt->sax->error != NULL))
3680 ctxt->sax->error(ctxt->userData,
3681 "docbParseStartTag: problem parsing attributes\n");
3682 ctxt->wellFormed = 0;
3683 break;
3684 }
3685 }
3686
3687 /*
3688 * Handle specific association to the META tag
3689 */
3690 if (meta)
3691 docbCheckMeta(ctxt, atts);
3692
3693 /*
3694 * SAX: Start of Element !
3695 */
3696 docbnamePush(ctxt, xmlStrdup(name));
3697#ifdef DEBUG
3698 xmlGenericError(xmlGenericErrorContext,"Start of element %s: pushed %s\n", name, ctxt->name);
3699#endif
3700 if ((ctxt->sax != NULL) && (ctxt->sax->startElement != NULL))
3701 ctxt->sax->startElement(ctxt->userData, name, atts);
3702
3703 if (atts != NULL) {
3704 for (i = 0;i < nbatts;i++) {
3705 if (atts[i] != NULL)
3706 xmlFree((xmlChar *) atts[i]);
3707 }
3708 xmlFree((void *) atts);
3709 }
3710 if (name != NULL) xmlFree(name);
3711}
3712
3713/**
3714 * docbParseEndTag:
3715 * @ctxt: an SGML parser context
3716 *
3717 * parse an end of tag
3718 *
3719 * [42] ETag ::= '</' Name S? '>'
3720 *
3721 * With namespace
3722 *
3723 * [NS 9] ETag ::= '</' QName S? '>'
3724 */
3725
3726static void
3727docbParseEndTag(docbParserCtxtPtr ctxt) {
3728 xmlChar *name;
3729 xmlChar *oldname;
3730 int i;
3731
3732 if ((CUR != '<') || (NXT(1) != '/')) {
3733 if ((ctxt->sax != NULL) && (ctxt->sax->error != NULL))
3734 ctxt->sax->error(ctxt->userData, "docbParseEndTag: '</' not found\n");
3735 ctxt->wellFormed = 0;
3736 return;
3737 }
3738 SKIP(2);
3739
3740 name = docbParseSGMLName(ctxt);
3741 if (name == NULL) {
3742 if (CUR == '>') {
3743 NEXT;
3744 oldname = docbnamePop(ctxt);
3745 if (oldname != NULL) {
3746 if ((ctxt->sax != NULL) && (ctxt->sax->endElement != NULL))
3747 ctxt->sax->endElement(ctxt->userData, name);
3748#ifdef DEBUG
3749 xmlGenericError(xmlGenericErrorContext,"End of tag </>: popping out %s\n", oldname);
3750#endif
3751 xmlFree(oldname);
3752#ifdef DEBUG
3753 } else {
3754 xmlGenericError(xmlGenericErrorContext,"End of tag </>: stack empty !!!\n");
3755#endif
3756 }
3757 return;
3758 } else
3759 return;
3760 }
3761
3762 /*
3763 * We should definitely be at the ending "S? '>'" part
3764 */
3765 SKIP_BLANKS;
3766 if ((!IS_CHAR(CUR)) || (CUR != '>')) {
3767 if ((ctxt->sax != NULL) && (ctxt->sax->error != NULL))
3768 ctxt->sax->error(ctxt->userData, "End tag : expected '>'\n");
3769 ctxt->wellFormed = 0;
3770 } else
3771 NEXT;
3772
3773 /*
3774 * If the name read is not one of the element in the parsing stack
3775 * then return, it's just an error.
3776 */
3777 for (i = (ctxt->nameNr - 1);i >= 0;i--) {
3778 if (xmlStrEqual(name, ctxt->nameTab[i])) break;
3779 }
3780 if (i < 0) {
3781 if ((ctxt->sax != NULL) && (ctxt->sax->error != NULL))
3782 ctxt->sax->error(ctxt->userData,
3783 "Unexpected end tag : %s\n", name);
3784 xmlFree(name);
3785 ctxt->wellFormed = 0;
3786 return;
3787 }
3788
3789
3790 /*
3791 * Check for auto-closure of SGML elements.
3792 */
3793
3794 docbAutoCloseOnClose(ctxt, name);
3795
3796 /*
3797 * Well formedness constraints, opening and closing must match.
3798 * With the exception that the autoclose may have popped stuff out
3799 * of the stack.
3800 */
3801 if (((name[0] != '/') || (name[1] != 0)) &&
3802 (!xmlStrEqual(name, ctxt->name))) {
3803#ifdef DEBUG
3804 xmlGenericError(xmlGenericErrorContext,"End of tag %s: expecting %s\n", name, ctxt->name);
3805#endif
3806 if ((ctxt->name != NULL) &&
3807 (!xmlStrEqual(ctxt->name, name))) {
3808 if ((ctxt->sax != NULL) && (ctxt->sax->error != NULL))
3809 ctxt->sax->error(ctxt->userData,
3810 "Opening and ending tag mismatch: %s and %s\n",
3811 name, ctxt->name);
3812 ctxt->wellFormed = 0;
3813 }
3814 }
3815
3816 /*
3817 * SAX: End of Tag
3818 */
3819 oldname = ctxt->name;
3820 if (((name[0] == '/') && (name[1] == 0)) ||
3821 ((oldname != NULL) && (xmlStrEqual(oldname, name)))) {
3822 if ((ctxt->sax != NULL) && (ctxt->sax->endElement != NULL))
3823 ctxt->sax->endElement(ctxt->userData, name);
3824 oldname = docbnamePop(ctxt);
3825 if (oldname != NULL) {
3826#ifdef DEBUG
3827 xmlGenericError(xmlGenericErrorContext,"End of tag %s: popping out %s\n", name, oldname);
3828#endif
3829 xmlFree(oldname);
3830#ifdef DEBUG
3831 } else {
3832 xmlGenericError(xmlGenericErrorContext,"End of tag %s: stack empty !!!\n", name);
3833#endif
3834 }
3835 }
3836
3837 if (name != NULL)
3838 xmlFree(name);
3839
3840 return;
3841}
3842
3843
3844/**
3845 * docbParseReference:
3846 * @ctxt: an SGML parser context
3847 *
3848 * parse and handle entity references in content,
3849 * this will end-up in a call to character() since this is either a
3850 * CharRef, or a predefined entity.
3851 */
3852static void
3853docbParseReference(docbParserCtxtPtr ctxt) {
3854 docbEntityDescPtr ent;
Daniel Veillard61b33d52001-04-24 13:55:12 +0000[diff] [blame]3855 xmlEntityPtr xent;
Daniel Veillardeae522a2001-04-23 13:41:34 +0000[diff] [blame]3856 xmlChar out[6];
3857 xmlChar *name;
3858 if (CUR != '&') return;
3859
3860 if (NXT(1) == '#') {
3861 unsigned int c;
3862 int bits, i = 0;
3863
3864 c = docbParseCharRef(ctxt);
3865 if (c < 0x80) { out[i++]= c; bits= -6; }
3866 else if (c < 0x800) { out[i++]=((c >> 6) & 0x1F) | 0xC0; bits= 0; }
3867 else if (c < 0x10000) { out[i++]=((c >> 12) & 0x0F) | 0xE0; bits= 6; }
3868 else { out[i++]=((c >> 18) & 0x07) | 0xF0; bits= 12; }
3869
3870 for ( ; bits >= 0; bits-= 6) {
3871 out[i++]= ((c >> bits) & 0x3F) | 0x80;
3872 }
3873 out[i] = 0;
3874
3875 docbCheckParagraph(ctxt);
3876 if ((ctxt->sax != NULL) && (ctxt->sax->characters != NULL))
3877 ctxt->sax->characters(ctxt->userData, out, i);
3878 } else {
Daniel Veillard61b33d52001-04-24 13:55:12 +0000[diff] [blame]3879 /*
3880 * Lookup the entity in the table.
3881 */
3882 xent = docbParseEntityRef(ctxt, &name);
3883 if (xent != NULL) {
Daniel Veillard1034da22001-04-25 19:06:28 +0000[diff] [blame^]3884 if (((ctxt->replaceEntities) || (ctxt->loadsubset)) &&
3885 ((xent->children == NULL) &&
3886 (xent->etype == XML_EXTERNAL_GENERAL_PARSED_ENTITY))) {
Daniel Veillard61b33d52001-04-24 13:55:12 +0000[diff] [blame]3887 /*
3888 * we really need to fetch and parse the external entity
3889 */
3890 int parse;
3891 xmlNodePtr children = NULL;
3892
3893 parse = docbParseCtxtExternalEntity(ctxt,
3894 xent->SystemID, xent->ExternalID, &children);
3895 xmlAddChildList((xmlNodePtr) xent, children);
Daniel Veillard1034da22001-04-25 19:06:28 +0000[diff] [blame^]3896 }
3897 if (ctxt->replaceEntities) {
Daniel Veillard61b33d52001-04-24 13:55:12 +0000[diff] [blame]3898 if ((ctxt->node != NULL) && (xent->children != NULL)) {
3899 /*
3900 * Seems we are generating the DOM content, do
3901 * a simple tree copy
3902 */
3903 xmlNodePtr new;
3904 new = xmlCopyNodeList(xent->children);
3905
3906 xmlAddChildList(ctxt->node, new);
3907 /*
3908 * This is to avoid a nasty side effect, see
3909 * characters() in SAX.c
3910 */
3911 ctxt->nodemem = 0;
3912 ctxt->nodelen = 0;
3913 }
Daniel Veillard1034da22001-04-25 19:06:28 +0000[diff] [blame^]3914 } else {
3915 if ((ctxt->sax != NULL) && (ctxt->sax->reference != NULL) &&
3916 (ctxt->replaceEntities == 0) && (!ctxt->disableSAX)) {
3917 /*
3918 * Create a node.
3919 */
3920 ctxt->sax->reference(ctxt->userData, xent->name);
3921 }
Daniel Veillard61b33d52001-04-24 13:55:12 +0000[diff] [blame]3922 }
3923 } else if (name != NULL) {
3924 ent = docbEntityLookup(name);
3925 if ((ent == NULL) || (ent->value <= 0)) {
3926 docbCheckParagraph(ctxt);
3927 if ((ctxt->sax != NULL) && (ctxt->sax->characters != NULL)) {
3928 ctxt->sax->characters(ctxt->userData, BAD_CAST "&", 1);
3929 ctxt->sax->characters(ctxt->userData, name, xmlStrlen(name));
3930 /* ctxt->sax->characters(ctxt->userData, BAD_CAST ";", 1); */
3931 }
3932 } else {
3933 unsigned int c;
3934 int bits, i = 0;
3935
3936 c = ent->value;
3937 if (c < 0x80)
3938 { out[i++]= c; bits= -6; }
3939 else if (c < 0x800)
3940 { out[i++]=((c >> 6) & 0x1F) | 0xC0; bits= 0; }
3941 else if (c < 0x10000)
3942 { out[i++]=((c >> 12) & 0x0F) | 0xE0; bits= 6; }
3943 else
3944 { out[i++]=((c >> 18) & 0x07) | 0xF0; bits= 12; }
3945
3946 for ( ; bits >= 0; bits-= 6) {
3947 out[i++]= ((c >> bits) & 0x3F) | 0x80;
3948 }
3949 out[i] = 0;
3950
3951 docbCheckParagraph(ctxt);
3952 if ((ctxt->sax != NULL) && (ctxt->sax->characters != NULL))
3953 ctxt->sax->characters(ctxt->userData, out, i);
3954 }
3955 } else {
Daniel Veillardeae522a2001-04-23 13:41:34 +0000[diff] [blame]3956 docbCheckParagraph(ctxt);
3957 if ((ctxt->sax != NULL) && (ctxt->sax->characters != NULL))
3958 ctxt->sax->characters(ctxt->userData, BAD_CAST "&", 1);
3959 return;
3960 }
Daniel Veillard61b33d52001-04-24 13:55:12 +0000[diff] [blame]3961 if (name != NULL)
3962 xmlFree(name);
Daniel Veillardeae522a2001-04-23 13:41:34 +0000[diff] [blame]3963 }
3964}
3965
3966/**
3967 * docbParseContent:
3968 * @ctxt: an SGML parser context
3969 * @name: the node name
3970 *
3971 * Parse a content: comment, sub-element, reference or text.
3972 *
3973 */
3974
3975static void
3976docbParseContent(docbParserCtxtPtr ctxt) {
3977 xmlChar *currentNode;
3978 int depth;
3979
3980 currentNode = xmlStrdup(ctxt->name);
3981 depth = ctxt->nameNr;
3982 while (1) {
3983 long cons = ctxt->nbChars;
3984
3985 GROW;
3986 /*
3987 * Our tag or one of it's parent or children is ending.
3988 */
3989 if ((CUR == '<') && (NXT(1) == '/')) {
3990 docbParseEndTag(ctxt);
3991 if (currentNode != NULL) xmlFree(currentNode);
3992 return;
3993 }
3994
3995 /*
3996 * Has this node been popped out during parsing of
3997 * the next element
3998 */
3999 if ((!xmlStrEqual(currentNode, ctxt->name)) &&
4000 (depth >= ctxt->nameNr)) {
4001 if (currentNode != NULL) xmlFree(currentNode);
4002 return;
4003 }
4004
4005 /*
4006 * Sometimes DOCTYPE arrives in the middle of the document
4007 */
4008 if ((CUR == '<') && (NXT(1) == '!') &&
4009 (UPP(2) == 'D') && (UPP(3) == 'O') &&
4010 (UPP(4) == 'C') && (UPP(5) == 'T') &&
4011 (UPP(6) == 'Y') && (UPP(7) == 'P') &&
4012 (UPP(8) == 'E')) {
4013 if ((ctxt->sax != NULL) && (ctxt->sax->error != NULL))
4014 ctxt->sax->error(ctxt->userData,
4015 "Misplaced DOCTYPE declaration\n");
4016 ctxt->wellFormed = 0;
4017 docbParseDocTypeDecl(ctxt);
4018 }
4019
4020 /*
4021 * First case : a comment
4022 */
4023 if ((CUR == '<') && (NXT(1) == '!') &&
4024 (NXT(2) == '-') && (NXT(3) == '-')) {
4025 docbParseComment(ctxt);
4026 }
4027
4028 /*
4029 * Second case : a sub-element.
4030 */
4031 else if (CUR == '<') {
4032 docbParseElement(ctxt);
4033 }
4034
4035 /*
4036 * Third case : a reference. If if has not been resolved,
4037 * parsing returns it's Name, create the node
4038 */
4039 else if (CUR == '&') {
4040 docbParseReference(ctxt);
4041 }
4042
4043 /*
4044 * Fourth : end of the resource
4045 */
4046 else if (CUR == 0) {
4047 docbAutoClose(ctxt, NULL);
Daniel Veillard61b33d52001-04-24 13:55:12 +0000[diff] [blame]4048 if (ctxt->nameNr == 0)
4049 break;
Daniel Veillardeae522a2001-04-23 13:41:34 +0000[diff] [blame]4050 }
4051
4052 /*
4053 * Last case, text. Note that References are handled directly.
4054 */
4055 else {
4056 docbParseCharData(ctxt);
4057 }
4058
4059 if (cons == ctxt->nbChars) {
4060 if (ctxt->node != NULL) {
4061 if ((ctxt->sax != NULL) && (ctxt->sax->error != NULL))
4062 ctxt->sax->error(ctxt->userData,
4063 "detected an error in element content\n");
4064 ctxt->wellFormed = 0;
4065 }
Daniel Veillard61b33d52001-04-24 13:55:12 +0000[diff] [blame]4066 break;
Daniel Veillardeae522a2001-04-23 13:41:34 +0000[diff] [blame]4067 }
4068
4069 GROW;
4070 }
4071 if (currentNode != NULL) xmlFree(currentNode);
4072}
4073
4074/**
4075 * docbParseElement:
4076 * @ctxt: an SGML parser context
4077 *
4078 * parse an SGML element, this is highly recursive
4079 *
4080 * [39] element ::= EmptyElemTag | STag content ETag
4081 *
4082 * [41] Attribute ::= Name Eq AttValue
4083 */
4084
4085static void
4086docbParseElement(docbParserCtxtPtr ctxt) {
4087 xmlChar *name;
4088 xmlChar *currentNode = NULL;
4089 docbElemDescPtr info;
4090 docbParserNodeInfo node_info;
4091 xmlChar *oldname;
4092 int depth = ctxt->nameNr;
4093
4094 /* Capture start position */
4095 if (ctxt->record_info) {
4096 node_info.begin_pos = ctxt->input->consumed +
4097 (CUR_PTR - ctxt->input->base);
4098 node_info.begin_line = ctxt->input->line;
4099 }
4100
4101 oldname = xmlStrdup(ctxt->name);
4102 docbParseStartTag(ctxt);
4103 name = ctxt->name;
4104#ifdef DEBUG
4105 if (oldname == NULL)
4106 xmlGenericError(xmlGenericErrorContext,
4107 "Start of element %s\n", name);
4108 else if (name == NULL)
4109 xmlGenericError(xmlGenericErrorContext,
4110 "Start of element failed, was %s\n", oldname);
4111 else
4112 xmlGenericError(xmlGenericErrorContext,
4113 "Start of element %s, was %s\n", name, oldname);
4114#endif
4115 if (((depth == ctxt->nameNr) && (xmlStrEqual(oldname, ctxt->name))) ||
4116 (name == NULL)) {
4117 if (CUR == '>')
4118 NEXT;
4119 if (oldname != NULL)
4120 xmlFree(oldname);
4121 return;
4122 }
4123 if (oldname != NULL)
4124 xmlFree(oldname);
4125
4126 /*
4127 * Lookup the info for that element.
4128 */
4129 info = docbTagLookup(name);
4130 if (info == NULL) {
4131 if ((ctxt->sax != NULL) && (ctxt->sax->error != NULL))
4132 ctxt->sax->error(ctxt->userData, "Tag %s unknown\n",
4133 name);
4134 ctxt->wellFormed = 0;
4135 } else if (info->depr) {
4136/***************************
4137 if ((ctxt->sax != NULL) && (ctxt->sax->warning != NULL))
4138 ctxt->sax->warning(ctxt->userData, "Tag %s is deprecated\n",
4139 name);
4140 ***************************/
4141 }
4142
4143 /*
4144 * Check for an Empty Element labelled the XML/SGML way
4145 */
4146 if ((CUR == '/') && (NXT(1) == '>')) {
4147 SKIP(2);
4148 if ((ctxt->sax != NULL) && (ctxt->sax->endElement != NULL))
4149 ctxt->sax->endElement(ctxt->userData, name);
4150 oldname = docbnamePop(ctxt);
4151#ifdef DEBUG
4152 xmlGenericError(xmlGenericErrorContext,"End of tag the XML way: popping out %s\n", oldname);
4153#endif
4154 if (oldname != NULL)
4155 xmlFree(oldname);
4156 return;
4157 }
4158
4159 if (CUR == '>') {
4160 NEXT;
4161 } else {
4162 if ((ctxt->sax != NULL) && (ctxt->sax->error != NULL))
4163 ctxt->sax->error(ctxt->userData,
4164 "Couldn't find end of Start Tag %s\n",
4165 name);
4166 ctxt->wellFormed = 0;
4167
4168 /*
4169 * end of parsing of this node.
4170 */
4171 if (xmlStrEqual(name, ctxt->name)) {
4172 nodePop(ctxt);
4173 oldname = docbnamePop(ctxt);
4174#ifdef DEBUG
4175 xmlGenericError(xmlGenericErrorContext,"End of start tag problem: popping out %s\n", oldname);
4176#endif
4177 if (oldname != NULL)
4178 xmlFree(oldname);
4179 }
4180
4181 /*
4182 * Capture end position and add node
4183 */
4184 if ( currentNode != NULL && ctxt->record_info ) {
4185 node_info.end_pos = ctxt->input->consumed +
4186 (CUR_PTR - ctxt->input->base);
4187 node_info.end_line = ctxt->input->line;
4188 node_info.node = ctxt->node;
4189 xmlParserAddNodeInfo(ctxt, &node_info);
4190 }
4191 return;
4192 }
4193
4194 /*
4195 * Check for an Empty Element from DTD definition
4196 */
4197 if ((info != NULL) && (info->empty)) {
4198 if ((ctxt->sax != NULL) && (ctxt->sax->endElement != NULL))
4199 ctxt->sax->endElement(ctxt->userData, name);
4200 oldname = docbnamePop(ctxt);
4201#ifdef DEBUG
4202 xmlGenericError(xmlGenericErrorContext,"End of empty tag %s : popping out %s\n", name, oldname);
4203#endif
4204 if (oldname != NULL)
4205 xmlFree(oldname);
4206 return;
4207 }
4208
4209 /*
4210 * Parse the content of the element:
4211 */
4212 currentNode = xmlStrdup(ctxt->name);
4213 depth = ctxt->nameNr;
4214 while (IS_CHAR(CUR)) {
4215 docbParseContent(ctxt);
4216 if (ctxt->nameNr < depth) break;
4217 }
4218
4219 if (!IS_CHAR(CUR)) {
4220 /************
4221 if ((ctxt->sax != NULL) && (ctxt->sax->error != NULL))
4222 ctxt->sax->error(ctxt->userData,
4223 "Premature end of data in tag %s\n", currentNode);
4224 ctxt->wellFormed = 0;
4225 *************/
4226
4227 /*
4228 * end of parsing of this node.
4229 */
4230 nodePop(ctxt);
4231 oldname = docbnamePop(ctxt);
4232#ifdef DEBUG
4233 xmlGenericError(xmlGenericErrorContext,"Premature end of tag %s : popping out %s\n", name, oldname);
4234#endif
4235 if (oldname != NULL)
4236 xmlFree(oldname);
4237 if (currentNode != NULL)
4238 xmlFree(currentNode);
4239 return;
4240 }
4241
4242 /*
4243 * Capture end position and add node
4244 */
4245 if ( currentNode != NULL && ctxt->record_info ) {
4246 node_info.end_pos = ctxt->input->consumed +
4247 (CUR_PTR - ctxt->input->base);
4248 node_info.end_line = ctxt->input->line;
4249 node_info.node = ctxt->node;
4250 xmlParserAddNodeInfo(ctxt, &node_info);
4251 }
4252 if (currentNode != NULL)
4253 xmlFree(currentNode);
4254}
4255
4256/**
4257 * docbParseEntityDecl:
4258 * @ctxt: an SGML parser context
4259 *
4260 * parse <!ENTITY declarations
4261 *
4262 */
4263
4264static void
4265docbParseEntityDecl(xmlParserCtxtPtr ctxt) {
4266 xmlChar *name = NULL;
4267 xmlChar *value = NULL;
4268 xmlChar *URI = NULL, *literal = NULL;
4269 xmlChar *ndata = NULL;
4270 int isParameter = 0;
4271 xmlChar *orig = NULL;
4272
4273 GROW;
4274 if ((RAW == '<') && (NXT(1) == '!') &&
Daniel Veillard61b33d52001-04-24 13:55:12 +0000[diff] [blame]4275 (UPP(2) == 'E') && (UPP(3) == 'N') &&
4276 (UPP(4) == 'T') && (UPP(5) == 'I') &&
4277 (UPP(6) == 'T') && (UPP(7) == 'Y')) {
Daniel Veillardeae522a2001-04-23 13:41:34 +0000[diff] [blame]4278 xmlParserInputPtr input = ctxt->input;
4279 ctxt->instate = XML_PARSER_ENTITY_DECL;
4280 SHRINK;
4281 SKIP(8);
4282 if (!IS_BLANK(CUR)) {
4283 ctxt->errNo = XML_ERR_SPACE_REQUIRED;
4284 if ((ctxt->sax != NULL) && (ctxt->sax->error != NULL))
4285 ctxt->sax->error(ctxt->userData,
4286 "Space required after '<!ENTITY'\n");
4287 ctxt->wellFormed = 0;
4288 ctxt->disableSAX = 1;
4289 }
4290 SKIP_BLANKS;
4291
4292 if (RAW == '%') {
4293 NEXT;
4294 if (!IS_BLANK(CUR)) {
4295 ctxt->errNo = XML_ERR_SPACE_REQUIRED;
4296 if ((ctxt->sax != NULL) && (ctxt->sax->error != NULL))
4297 ctxt->sax->error(ctxt->userData,
4298 "Space required after '%'\n");
4299 ctxt->wellFormed = 0;
4300 ctxt->disableSAX = 1;
4301 }
4302 SKIP_BLANKS;
4303 isParameter = 1;
4304 }
4305
4306 name = xmlParseName(ctxt);
4307 if (name == NULL) {
4308 ctxt->errNo = XML_ERR_NAME_REQUIRED;
4309 if ((ctxt->sax != NULL) && (ctxt->sax->error != NULL))
4310 ctxt->sax->error(ctxt->userData, "sgmlarseEntityDecl: no name\n");
4311 ctxt->wellFormed = 0;
4312 ctxt->disableSAX = 1;
4313 return;
4314 }
4315 if (!IS_BLANK(CUR)) {
4316 ctxt->errNo = XML_ERR_SPACE_REQUIRED;
4317 if ((ctxt->sax != NULL) && (ctxt->sax->error != NULL))
4318 ctxt->sax->error(ctxt->userData,
4319 "Space required after the entity name\n");
4320 ctxt->wellFormed = 0;
4321 ctxt->disableSAX = 1;
4322 }
4323 SKIP_BLANKS;
4324
4325 /*
4326 * handle the various case of definitions...
4327 */
4328 if (isParameter) {
4329 if ((RAW == '"') || (RAW == '\'')) {
4330 value = xmlParseEntityValue(ctxt, &orig);
4331 if (value) {
4332 if ((ctxt->sax != NULL) &&
4333 (!ctxt->disableSAX) && (ctxt->sax->entityDecl != NULL))
4334 ctxt->sax->entityDecl(ctxt->userData, name,
4335 XML_INTERNAL_PARAMETER_ENTITY,
4336 NULL, NULL, value);
4337 }
4338 } else {
4339 URI = xmlParseExternalID(ctxt, &literal, 1);
4340 if ((URI == NULL) && (literal == NULL)) {
4341 ctxt->errNo = XML_ERR_VALUE_REQUIRED;
4342 if ((ctxt->sax != NULL) && (ctxt->sax->error != NULL))
4343 ctxt->sax->error(ctxt->userData,
4344 "Entity value required\n");
4345 ctxt->wellFormed = 0;
4346 ctxt->disableSAX = 1;
4347 }
4348 if (URI) {
4349 xmlURIPtr uri;
4350
4351 uri = xmlParseURI((const char *) URI);
4352 if (uri == NULL) {
4353 ctxt->errNo = XML_ERR_INVALID_URI;
4354 if ((ctxt->sax != NULL) &&
4355 (!ctxt->disableSAX) &&
4356 (ctxt->sax->error != NULL))
4357 ctxt->sax->error(ctxt->userData,
4358 "Invalid URI: %s\n", URI);
4359 ctxt->wellFormed = 0;
4360 } else {
4361 if (uri->fragment != NULL) {
4362 ctxt->errNo = XML_ERR_URI_FRAGMENT;
4363 if ((ctxt->sax != NULL) &&
4364 (!ctxt->disableSAX) &&
4365 (ctxt->sax->error != NULL))
4366 ctxt->sax->error(ctxt->userData,
4367 "Fragment not allowed: %s\n", URI);
4368 ctxt->wellFormed = 0;
4369 } else {
4370 if ((ctxt->sax != NULL) &&
4371 (!ctxt->disableSAX) &&
4372 (ctxt->sax->entityDecl != NULL))
4373 ctxt->sax->entityDecl(ctxt->userData, name,
4374 XML_EXTERNAL_PARAMETER_ENTITY,
4375 literal, URI, NULL);
4376 }
4377 xmlFreeURI(uri);
4378 }
4379 }
4380 }
4381 } else {
4382 if ((RAW == '"') || (RAW == '\'')) {
4383 value = xmlParseEntityValue(ctxt, &orig);
4384 if ((ctxt->sax != NULL) &&
4385 (!ctxt->disableSAX) && (ctxt->sax->entityDecl != NULL))
4386 ctxt->sax->entityDecl(ctxt->userData, name,
4387 XML_INTERNAL_GENERAL_ENTITY,
4388 NULL, NULL, value);
4389 } else {
4390 URI = xmlParseExternalID(ctxt, &literal, 1);
4391 if ((URI == NULL) && (literal == NULL)) {
4392 ctxt->errNo = XML_ERR_VALUE_REQUIRED;
4393 if ((ctxt->sax != NULL) && (ctxt->sax->error != NULL))
4394 ctxt->sax->error(ctxt->userData,
4395 "Entity value required\n");
4396 ctxt->wellFormed = 0;
4397 ctxt->disableSAX = 1;
4398 }
4399 if (URI) {
4400 xmlURIPtr uri;
4401
4402 uri = xmlParseURI((const char *)URI);
4403 if (uri == NULL) {
4404 ctxt->errNo = XML_ERR_INVALID_URI;
4405 if ((ctxt->sax != NULL) &&
4406 (!ctxt->disableSAX) &&
4407 (ctxt->sax->error != NULL))
4408 ctxt->sax->error(ctxt->userData,
4409 "Invalid URI: %s\n", URI);
4410 ctxt->wellFormed = 0;
4411 } else {
4412 if (uri->fragment != NULL) {
4413 ctxt->errNo = XML_ERR_URI_FRAGMENT;
4414 if ((ctxt->sax != NULL) &&
4415 (!ctxt->disableSAX) &&
4416 (ctxt->sax->error != NULL))
4417 ctxt->sax->error(ctxt->userData,
4418 "Fragment not allowed: %s\n", URI);
4419 ctxt->wellFormed = 0;
4420 }
4421 xmlFreeURI(uri);
4422 }
4423 }
4424 if ((RAW != '>') && (!IS_BLANK(CUR))) {
4425 ctxt->errNo = XML_ERR_SPACE_REQUIRED;
4426 if ((ctxt->sax != NULL) && (ctxt->sax->error != NULL))
4427 ctxt->sax->error(ctxt->userData,
4428 "Space required before content model\n");
4429 ctxt->wellFormed = 0;
4430 ctxt->disableSAX = 1;
4431 }
4432 SKIP_BLANKS;
4433
4434 /*
4435 * SGML specific: here we can get the content model
4436 */
4437 if (RAW != '>') {
4438 xmlChar *contmod;
4439
4440 contmod = xmlParseName(ctxt);
4441
4442 if (contmod == NULL) {
4443 ctxt->errNo = XML_ERR_SPACE_REQUIRED;
4444 if ((ctxt->sax != NULL) && (ctxt->sax->error != NULL))
4445 ctxt->sax->error(ctxt->userData,
4446 "Could not parse entity content model\n");
4447 ctxt->wellFormed = 0;
4448 ctxt->disableSAX = 1;
4449 } else {
4450 if (xmlStrEqual(contmod, BAD_CAST"NDATA")) {
4451 if (!IS_BLANK(CUR)) {
4452 ctxt->errNo = XML_ERR_SPACE_REQUIRED;
4453 if ((ctxt->sax != NULL) &&
4454 (ctxt->sax->error != NULL))
4455 ctxt->sax->error(ctxt->userData,
4456 "Space required after 'NDATA'\n");
4457 ctxt->wellFormed = 0;
4458 ctxt->disableSAX = 1;
4459 }
4460 SKIP_BLANKS;
4461 ndata = xmlParseName(ctxt);
4462 if ((ctxt->sax != NULL) && (!ctxt->disableSAX) &&
4463 (ctxt->sax->unparsedEntityDecl != NULL)) {
4464 ctxt->sax->unparsedEntityDecl(ctxt->userData,
4465 name, literal, URI, ndata);
4466 }
4467 } else if (xmlStrEqual(contmod, BAD_CAST"SUBDOC")) {
4468 if ((ctxt->sax != NULL) &&
4469 (ctxt->sax->warning != NULL))
4470 ctxt->sax->warning(ctxt->userData,
4471 "SUBDOC entities are not supported\n");
4472 SKIP_BLANKS;
4473 ndata = xmlParseName(ctxt);
4474 if ((ctxt->sax != NULL) && (!ctxt->disableSAX) &&
4475 (ctxt->sax->unparsedEntityDecl != NULL)) {
4476 ctxt->sax->unparsedEntityDecl(ctxt->userData,
4477 name, literal, URI, ndata);
4478 }
4479 } else if (xmlStrEqual(contmod, BAD_CAST"CDATA")) {
4480 if ((ctxt->sax != NULL) &&
4481 (ctxt->sax->warning != NULL))
4482 ctxt->sax->warning(ctxt->userData,
4483 "CDATA entities are not supported\n");
4484 SKIP_BLANKS;
4485 ndata = xmlParseName(ctxt);
4486 if ((ctxt->sax != NULL) && (!ctxt->disableSAX) &&
4487 (ctxt->sax->unparsedEntityDecl != NULL)) {
4488 ctxt->sax->unparsedEntityDecl(ctxt->userData,
4489 name, literal, URI, ndata);
4490 }
4491 }
4492 xmlFree(contmod);
4493 }
4494 } else {
4495 if ((ctxt->sax != NULL) &&
4496 (!ctxt->disableSAX) && (ctxt->sax->entityDecl != NULL))
4497 ctxt->sax->entityDecl(ctxt->userData, name,
4498 XML_EXTERNAL_GENERAL_PARSED_ENTITY,
4499 literal, URI, NULL);
4500 }
4501 }
4502 }
4503 SKIP_BLANKS;
4504 if (RAW != '>') {
4505 ctxt->errNo = XML_ERR_ENTITY_NOT_FINISHED;
4506 if ((ctxt->sax != NULL) && (ctxt->sax->error != NULL))
4507 ctxt->sax->error(ctxt->userData,
4508 "docbParseEntityDecl: entity %s not terminated\n", name);
4509 ctxt->wellFormed = 0;
4510 ctxt->disableSAX = 1;
4511 } else {
4512 if (input != ctxt->input) {
4513 ctxt->errNo = XML_ERR_ENTITY_BOUNDARY;
4514 if ((ctxt->sax != NULL) && (ctxt->sax->error != NULL))
4515 ctxt->sax->error(ctxt->userData,
4516"Entity declaration doesn't start and stop in the same entity\n");
4517 ctxt->wellFormed = 0;
4518 ctxt->disableSAX = 1;
4519 }
4520 NEXT;
4521 }
4522 if (orig != NULL) {
4523 /*
4524 * Ugly mechanism to save the raw entity value.
4525 */
4526 xmlEntityPtr cur = NULL;
4527
4528 if (isParameter) {
4529 if ((ctxt->sax != NULL) &&
4530 (ctxt->sax->getParameterEntity != NULL))
4531 cur = ctxt->sax->getParameterEntity(ctxt->userData, name);
4532 } else {
4533 if ((ctxt->sax != NULL) &&
4534 (ctxt->sax->getEntity != NULL))
4535 cur = ctxt->sax->getEntity(ctxt->userData, name);
4536 }
4537 if (cur != NULL) {
4538 if (cur->orig != NULL)
4539 xmlFree(orig);
4540 else
4541 cur->orig = orig;
4542 } else
4543 xmlFree(orig);
4544 }
4545 if (name != NULL) xmlFree(name);
4546 if (value != NULL) xmlFree(value);
4547 if (URI != NULL) xmlFree(URI);
4548 if (literal != NULL) xmlFree(literal);
4549 if (ndata != NULL) xmlFree(ndata);
4550 }
4551}
4552
4553/**
4554 * docbParseMarkupDecl:
4555 * @ctxt: an SGML parser context
4556 *
4557 * parse Markup declarations
4558 *
4559 * [29] markupdecl ::= elementdecl | AttlistDecl | EntityDecl |
4560 * NotationDecl | PI | Comment
4561 */
4562static void
4563docbParseMarkupDecl(xmlParserCtxtPtr ctxt) {
4564 GROW;
4565 xmlParseElementDecl(ctxt);
4566 xmlParseAttributeListDecl(ctxt);
4567 docbParseEntityDecl(ctxt);
4568 xmlParseNotationDecl(ctxt);
4569 xmlParsePI(ctxt);
4570 xmlParseComment(ctxt);
4571 /*
4572 * This is only for internal subset. On external entities,
4573 * the replacement is done before parsing stage
4574 */
4575 if ((ctxt->external == 0) && (ctxt->inputNr == 1))
4576 xmlParsePEReference(ctxt);
4577 ctxt->instate = XML_PARSER_DTD;
4578}
4579
4580/**
4581 * docbParseInternalsubset:
4582 * @ctxt: an SGML parser context
4583 *
4584 * parse the internal subset declaration
4585 *
4586 * [28 end] ('[' (markupdecl | PEReference | S)* ']' S?)? '>'
4587 */
4588
4589static void
4590docbParseInternalSubset(xmlParserCtxtPtr ctxt) {
4591 /*
4592 * Is there any DTD definition ?
4593 */
4594 if (RAW == '[') {
4595 ctxt->instate = XML_PARSER_DTD;
4596 NEXT;
4597 /*
4598 * Parse the succession of Markup declarations and
4599 * PEReferences.
4600 * Subsequence (markupdecl | PEReference | S)*
4601 */
4602 while (RAW != ']') {
4603 const xmlChar *check = CUR_PTR;
4604 int cons = ctxt->input->consumed;
4605
4606 SKIP_BLANKS;
4607 docbParseMarkupDecl(ctxt);
4608 xmlParsePEReference(ctxt);
4609
4610 /*
4611 * Pop-up of finished entities.
4612 */
4613 while ((RAW == 0) && (ctxt->inputNr > 1))
4614 xmlPopInput(ctxt);
4615
4616 if ((CUR_PTR == check) && (cons == ctxt->input->consumed)) {
4617 ctxt->errNo = XML_ERR_INTERNAL_ERROR;
4618 if ((ctxt->sax != NULL) && (ctxt->sax->error != NULL))
4619 ctxt->sax->error(ctxt->userData,
4620 "docbParseInternalSubset: error detected in Markup declaration\n");
4621 ctxt->wellFormed = 0;
4622 ctxt->disableSAX = 1;
4623 break;
4624 }
4625 }
4626 if (RAW == ']') {
4627 NEXT;
4628 SKIP_BLANKS;
4629 }
4630 }
4631
4632 /*
4633 * We should be at the end of the DOCTYPE declaration.
4634 */
4635 if (RAW != '>') {
4636 ctxt->errNo = XML_ERR_DOCTYPE_NOT_FINISHED;
4637 if ((ctxt->sax != NULL) && (ctxt->sax->error != NULL))
4638 ctxt->sax->error(ctxt->userData, "DOCTYPE unproperly terminated\n");
4639 ctxt->wellFormed = 0;
4640 ctxt->disableSAX = 1;
4641 }
4642 NEXT;
4643}
4644
4645/**
4646 * docbParseMisc:
4647 * @ctxt: an XML parser context
4648 *
4649 * parse an XML Misc* optionnal field.
4650 *
4651 * [27] Misc ::= Comment | PI | S
4652 */
4653
4654static void
4655docbParseMisc(xmlParserCtxtPtr ctxt) {
4656 while (((RAW == '<') && (NXT(1) == '?')) ||
4657 ((RAW == '<') && (NXT(1) == '!') &&
4658 (NXT(2) == '-') && (NXT(3) == '-')) ||
4659 IS_BLANK(CUR)) {
4660 if ((RAW == '<') && (NXT(1) == '?')) {
4661 xmlParsePI(ctxt); /* TODO: SGML PIs differs */
4662 } else if (IS_BLANK(CUR)) {
4663 NEXT;
4664 } else
4665 xmlParseComment(ctxt);
4666 }
4667}
4668
4669/**
4670 * docbParseDocument :
4671 * @ctxt: an SGML parser context
4672 *
4673 * parse an SGML document (and build a tree if using the standard SAX
4674 * interface).
4675 *
4676 * Returns 0, -1 in case of error. the parser context is augmented
4677 * as a result of the parsing.
4678 */
4679
4680int
4681docbParseDocument(docbParserCtxtPtr ctxt) {
4682 xmlChar start[4];
4683 xmlCharEncoding enc;
4684 xmlDtdPtr dtd;
4685
4686 docbDefaultSAXHandlerInit();
4687 ctxt->html = 2;
4688
4689 GROW;
4690 /*
4691 * SAX: beginning of the document processing.
4692 */
4693 if ((ctxt->sax) && (ctxt->sax->setDocumentLocator))
4694 ctxt->sax->setDocumentLocator(ctxt->userData, &xmlDefaultSAXLocator);
4695
4696 /*
4697 * Get the 4 first bytes and decode the charset
4698 * if enc != XML_CHAR_ENCODING_NONE
4699 * plug some encoding conversion routines.
4700 */
4701 start[0] = RAW;
4702 start[1] = NXT(1);
4703 start[2] = NXT(2);
4704 start[3] = NXT(3);
4705 enc = xmlDetectCharEncoding(start, 4);
4706 if (enc != XML_CHAR_ENCODING_NONE) {
4707 xmlSwitchEncoding(ctxt, enc);
4708 }
4709
4710 /*
4711 * Wipe out everything which is before the first '<'
4712 */
4713 SKIP_BLANKS;
4714 if (CUR == 0) {
4715 if ((ctxt->sax != NULL) && (ctxt->sax->error != NULL))
4716 ctxt->sax->error(ctxt->userData, "Document is empty\n");
4717 ctxt->wellFormed = 0;
4718 }
4719
4720 if ((ctxt->sax) && (ctxt->sax->startDocument) && (!ctxt->disableSAX))
4721 ctxt->sax->startDocument(ctxt->userData);
4722
4723
4724 /*
4725 * The Misc part of the Prolog
4726 */
4727 GROW;
4728 docbParseMisc(ctxt);
4729
4730 /*
4731 * Then possibly doc type declaration(s) and more Misc
4732 * (doctypedecl Misc*)?
4733 */
4734 GROW;
4735 if ((RAW == '<') && (NXT(1) == '!') &&
Daniel Veillard61b33d52001-04-24 13:55:12 +0000[diff] [blame]4736 (UPP(2) == 'D') && (UPP(3) == 'O') &&
4737 (UPP(4) == 'C') && (UPP(5) == 'T') &&
4738 (UPP(6) == 'Y') && (UPP(7) == 'P') &&
4739 (UPP(8) == 'E')) {
Daniel Veillardeae522a2001-04-23 13:41:34 +0000[diff] [blame]4740
4741 ctxt->inSubset = 1;
4742 docbParseDocTypeDecl(ctxt);
4743 if (RAW == '[') {
4744 ctxt->instate = XML_PARSER_DTD;
4745 docbParseInternalSubset(ctxt);
4746 }
4747
4748 /*
4749 * Create and update the external subset.
4750 */
4751 ctxt->inSubset = 2;
4752 if ((ctxt->sax != NULL) && (ctxt->sax->internalSubset != NULL) &&
4753 (!ctxt->disableSAX))
4754 ctxt->sax->internalSubset(ctxt->userData, ctxt->intSubName,
4755 ctxt->extSubSystem, ctxt->extSubURI);
4756 ctxt->inSubset = 0;
4757
4758
4759 ctxt->instate = XML_PARSER_PROLOG;
4760 docbParseMisc(ctxt);
4761 }
4762
4763 /*
4764 * Time to start parsing the tree itself
4765 */
4766 docbParseContent(ctxt);
4767
4768 /*
4769 * autoclose
4770 */
4771 if (CUR == 0)
4772 docbAutoClose(ctxt, NULL);
4773
4774
4775 /*
4776 * SAX: end of the document processing.
4777 */
4778 if ((ctxt->sax) && (ctxt->sax->endDocument != NULL))
4779 ctxt->sax->endDocument(ctxt->userData);
4780
4781 if (ctxt->myDoc != NULL) {
4782 dtd = ctxt->myDoc->intSubset;
4783 if (dtd == NULL)
4784 ctxt->myDoc->intSubset =
4785 xmlCreateIntSubset(ctxt->myDoc, BAD_CAST "SGML",
4786 BAD_CAST "-//W3C//DTD SGML 4.0 Transitional//EN",
4787 BAD_CAST "http://www.w3.org/TR/REC-docbook/loose.dtd");
4788 }
4789 if (! ctxt->wellFormed) return(-1);
4790 return(0);
4791}
4792
4793
4794/************************************************************************
4795 * *
4796 * Parser contexts handling *
4797 * *
4798 ************************************************************************/
4799
4800/**
Daniel Veillard1034da22001-04-25 19:06:28 +0000[diff] [blame^]4801 * docbInitParserCtxt:
Daniel Veillardeae522a2001-04-23 13:41:34 +0000[diff] [blame]4802 * @ctxt: an SGML parser context
4803 *
4804 * Initialize a parser context
4805 */
4806
4807static void
4808docbInitParserCtxt(docbParserCtxtPtr ctxt)
4809{
4810 docbSAXHandler *sax;
4811
4812 if (ctxt == NULL) return;
4813 memset(ctxt, 0, sizeof(docbParserCtxt));
4814
4815 sax = (docbSAXHandler *) xmlMalloc(sizeof(docbSAXHandler));
4816 if (sax == NULL) {
4817 xmlGenericError(xmlGenericErrorContext,
4818 "docbInitParserCtxt: out of memory\n");
4819 }
4820 memset(sax, 0, sizeof(docbSAXHandler));
4821
4822 /* Allocate the Input stack */
4823 ctxt->inputTab = (docbParserInputPtr *)
4824 xmlMalloc(5 * sizeof(docbParserInputPtr));
4825 if (ctxt->inputTab == NULL) {
4826 xmlGenericError(xmlGenericErrorContext,
4827 "docbInitParserCtxt: out of memory\n");
4828 }
4829 ctxt->inputNr = 0;
4830 ctxt->inputMax = 5;
4831 ctxt->input = NULL;
4832 ctxt->version = NULL;
4833 ctxt->encoding = NULL;
4834 ctxt->standalone = -1;
4835 ctxt->instate = XML_PARSER_START;
4836
4837 /* Allocate the Node stack */
4838 ctxt->nodeTab = (docbNodePtr *) xmlMalloc(10 * sizeof(docbNodePtr));
4839 ctxt->nodeNr = 0;
4840 ctxt->nodeMax = 10;
4841 ctxt->node = NULL;
4842
4843 /* Allocate the Name stack */
4844 ctxt->nameTab = (xmlChar **) xmlMalloc(10 * sizeof(xmlChar *));
4845 ctxt->nameNr = 0;
4846 ctxt->nameMax = 10;
4847 ctxt->name = NULL;
4848
4849 if (sax == NULL) ctxt->sax = &docbDefaultSAXHandler;
4850 else {
4851 ctxt->sax = sax;
4852 memcpy(sax, &docbDefaultSAXHandler, sizeof(docbSAXHandler));
4853 }
4854 ctxt->userData = ctxt;
4855 ctxt->myDoc = NULL;
4856 ctxt->wellFormed = 1;
Daniel Veillard61b33d52001-04-24 13:55:12 +0000[diff] [blame]4857 ctxt->replaceEntities = xmlSubstituteEntitiesDefaultValue;
Daniel Veillardeae522a2001-04-23 13:41:34 +0000[diff] [blame]4858 ctxt->html = 2;
4859 ctxt->record_info = 0;
4860 ctxt->validate = 0;
4861 ctxt->nbChars = 0;
4862 ctxt->checkIndex = 0;
4863 xmlInitNodeInfoSeq(&ctxt->node_seq);
4864}
4865
4866/**
4867 * docbFreeParserCtxt:
4868 * @ctxt: an SGML parser context
4869 *
4870 * Free all the memory used by a parser context. However the parsed
4871 * document in ctxt->myDoc is not freed.
4872 */
4873
4874void
4875docbFreeParserCtxt(docbParserCtxtPtr ctxt)
4876{
4877 xmlFreeParserCtxt(ctxt);
4878}
4879
4880/**
4881 * docbCreateDocParserCtxt :
4882 * @cur: a pointer to an array of xmlChar
Daniel Veillard1034da22001-04-25 19:06:28 +0000[diff] [blame^]4883 * @encoding: the SGML document encoding, or NULL
Daniel Veillardeae522a2001-04-23 13:41:34 +0000[diff] [blame]4884 *
4885 * Create a parser context for an SGML document.
4886 *
4887 * Returns the new parser context or NULL
4888 */
4889static docbParserCtxtPtr
Daniel Veillard1034da22001-04-25 19:06:28 +0000[diff] [blame^]4890docbCreateDocParserCtxt(xmlChar *cur, const char *encoding ATTRIBUTE_UNUSED) {
Daniel Veillardeae522a2001-04-23 13:41:34 +0000[diff] [blame]4891 docbParserCtxtPtr ctxt;
4892 docbParserInputPtr input;
4893 /* sgmlCharEncoding enc; */
4894
4895 ctxt = (docbParserCtxtPtr) xmlMalloc(sizeof(docbParserCtxt));
4896 if (ctxt == NULL) {
4897 perror("malloc");
4898 return(NULL);
4899 }
4900 docbInitParserCtxt(ctxt);
4901 input = (docbParserInputPtr) xmlMalloc(sizeof(docbParserInput));
4902 if (input == NULL) {
4903 perror("malloc");
4904 xmlFree(ctxt);
4905 return(NULL);
4906 }
4907 memset(input, 0, sizeof(docbParserInput));
4908
4909 input->line = 1;
4910 input->col = 1;
4911 input->base = cur;
4912 input->cur = cur;
4913
4914 inputPush(ctxt, input);
4915 return(ctxt);
4916}
4917
4918/************************************************************************
4919 * *
4920 * Progressive parsing interfaces *
4921 * *
4922 ************************************************************************/
4923
4924/**
4925 * docbParseLookupSequence:
4926 * @ctxt: an SGML parser context
4927 * @first: the first char to lookup
4928 * @next: the next char to lookup or zero
4929 * @third: the next char to lookup or zero
4930 *
4931 * Try to find if a sequence (first, next, third) or just (first next) or
4932 * (first) is available in the input stream.
4933 * This function has a side effect of (possibly) incrementing ctxt->checkIndex
4934 * to avoid rescanning sequences of bytes, it DOES change the state of the
4935 * parser, do not use liberally.
4936 * This is basically similar to xmlParseLookupSequence()
4937 *
4938 * Returns the index to the current parsing point if the full sequence
4939 * is available, -1 otherwise.
4940 */
4941static int
4942docbParseLookupSequence(docbParserCtxtPtr ctxt, xmlChar first,
4943 xmlChar next, xmlChar third) {
4944 int base, len;
4945 docbParserInputPtr in;
4946 const xmlChar *buf;
4947
4948 in = ctxt->input;
4949 if (in == NULL) return(-1);
4950 base = in->cur - in->base;
4951 if (base < 0) return(-1);
4952 if (ctxt->checkIndex > base)
4953 base = ctxt->checkIndex;
4954 if (in->buf == NULL) {
4955 buf = in->base;
4956 len = in->length;
4957 } else {
4958 buf = in->buf->buffer->content;
4959 len = in->buf->buffer->use;
4960 }
4961 /* take into account the sequence length */
4962 if (third) len -= 2;
4963 else if (next) len --;
4964 for (;base < len;base++) {
4965 if (buf[base] == first) {
4966 if (third != 0) {
4967 if ((buf[base + 1] != next) ||
4968 (buf[base + 2] != third)) continue;
4969 } else if (next != 0) {
4970 if (buf[base + 1] != next) continue;
4971 }
4972 ctxt->checkIndex = 0;
4973#ifdef DEBUG_PUSH
4974 if (next == 0)
4975 xmlGenericError(xmlGenericErrorContext,
4976 "HPP: lookup '%c' found at %d\n",
4977 first, base);
4978 else if (third == 0)
4979 xmlGenericError(xmlGenericErrorContext,
4980 "HPP: lookup '%c%c' found at %d\n",
4981 first, next, base);
4982 else
4983 xmlGenericError(xmlGenericErrorContext,
4984 "HPP: lookup '%c%c%c' found at %d\n",
4985 first, next, third, base);
4986#endif
4987 return(base - (in->cur - in->base));
4988 }
4989 }
4990 ctxt->checkIndex = base;
4991#ifdef DEBUG_PUSH
4992 if (next == 0)
4993 xmlGenericError(xmlGenericErrorContext,
4994 "HPP: lookup '%c' failed\n", first);
4995 else if (third == 0)
4996 xmlGenericError(xmlGenericErrorContext,
4997 "HPP: lookup '%c%c' failed\n", first, next);
4998 else
4999 xmlGenericError(xmlGenericErrorContext,
5000 "HPP: lookup '%c%c%c' failed\n", first, next, third);
5001#endif
5002 return(-1);
5003}
5004
5005/**
5006 * docbParseTryOrFinish:
5007 * @ctxt: an SGML parser context
5008 * @terminate: last chunk indicator
5009 *
5010 * Try to progress on parsing
5011 *
5012 * Returns zero if no parsing was possible
5013 */
5014static int
5015docbParseTryOrFinish(docbParserCtxtPtr ctxt, int terminate) {
5016 int ret = 0;
5017 docbParserInputPtr in;
5018 int avail = 0;
5019 xmlChar cur, next;
5020
5021#ifdef DEBUG_PUSH
5022 switch (ctxt->instate) {
5023 case XML_PARSER_EOF:
5024 xmlGenericError(xmlGenericErrorContext,
5025 "HPP: try EOF\n"); break;
5026 case XML_PARSER_START:
5027 xmlGenericError(xmlGenericErrorContext,
5028 "HPP: try START\n"); break;
5029 case XML_PARSER_MISC:
5030 xmlGenericError(xmlGenericErrorContext,
5031 "HPP: try MISC\n");break;
5032 case XML_PARSER_COMMENT:
5033 xmlGenericError(xmlGenericErrorContext,
5034 "HPP: try COMMENT\n");break;
5035 case XML_PARSER_PROLOG:
5036 xmlGenericError(xmlGenericErrorContext,
5037 "HPP: try PROLOG\n");break;
5038 case XML_PARSER_START_TAG:
5039 xmlGenericError(xmlGenericErrorContext,
5040 "HPP: try START_TAG\n");break;
5041 case XML_PARSER_CONTENT:
5042 xmlGenericError(xmlGenericErrorContext,
5043 "HPP: try CONTENT\n");break;
5044 case XML_PARSER_CDATA_SECTION:
5045 xmlGenericError(xmlGenericErrorContext,
5046 "HPP: try CDATA_SECTION\n");break;
5047 case XML_PARSER_END_TAG:
5048 xmlGenericError(xmlGenericErrorContext,
5049 "HPP: try END_TAG\n");break;
5050 case XML_PARSER_ENTITY_DECL:
5051 xmlGenericError(xmlGenericErrorContext,
5052 "HPP: try ENTITY_DECL\n");break;
5053 case XML_PARSER_ENTITY_VALUE:
5054 xmlGenericError(xmlGenericErrorContext,
5055 "HPP: try ENTITY_VALUE\n");break;
5056 case XML_PARSER_ATTRIBUTE_VALUE:
5057 xmlGenericError(xmlGenericErrorContext,
5058 "HPP: try ATTRIBUTE_VALUE\n");break;
5059 case XML_PARSER_DTD:
5060 xmlGenericError(xmlGenericErrorContext,
5061 "HPP: try DTD\n");break;
5062 case XML_PARSER_EPILOG:
5063 xmlGenericError(xmlGenericErrorContext,
5064 "HPP: try EPILOG\n");break;
5065 case XML_PARSER_PI:
5066 xmlGenericError(xmlGenericErrorContext,
5067 "HPP: try PI\n");break;
5068 }
5069#endif
5070
5071 while (1) {
5072
5073 in = ctxt->input;
5074 if (in == NULL) break;
5075 if (in->buf == NULL)
5076 avail = in->length - (in->cur - in->base);
5077 else
5078 avail = in->buf->buffer->use - (in->cur - in->base);
5079 if ((avail == 0) && (terminate)) {
5080 docbAutoClose(ctxt, NULL);
5081 if ((ctxt->nameNr == 0) && (ctxt->instate != XML_PARSER_EOF)) {
5082 /*
5083 * SAX: end of the document processing.
5084 */
5085 ctxt->instate = XML_PARSER_EOF;
5086 if ((ctxt->sax) && (ctxt->sax->endDocument != NULL))
5087 ctxt->sax->endDocument(ctxt->userData);
5088 }
5089 }
5090 if (avail < 1)
5091 goto done;
5092 switch (ctxt->instate) {
5093 case XML_PARSER_EOF:
5094 /*
5095 * Document parsing is done !
5096 */
5097 goto done;
5098 case XML_PARSER_START:
5099 /*
5100 * Very first chars read from the document flow.
5101 */
5102 cur = in->cur[0];
5103 if (IS_BLANK(cur)) {
5104 SKIP_BLANKS;
5105 if (in->buf == NULL)
5106 avail = in->length - (in->cur - in->base);
5107 else
5108 avail = in->buf->buffer->use - (in->cur - in->base);
5109 }
5110 if ((ctxt->sax) && (ctxt->sax->setDocumentLocator))
5111 ctxt->sax->setDocumentLocator(ctxt->userData,
5112 &xmlDefaultSAXLocator);
5113 if ((ctxt->sax) && (ctxt->sax->startDocument) &&
5114 (!ctxt->disableSAX))
5115 ctxt->sax->startDocument(ctxt->userData);
5116
5117 cur = in->cur[0];
5118 next = in->cur[1];
5119 if ((cur == '<') && (next == '!') &&
5120 (UPP(2) == 'D') && (UPP(3) == 'O') &&
5121 (UPP(4) == 'C') && (UPP(5) == 'T') &&
5122 (UPP(6) == 'Y') && (UPP(7) == 'P') &&
5123 (UPP(8) == 'E')) {
5124 if ((!terminate) &&
5125 (docbParseLookupSequence(ctxt, '>', 0, 0) < 0))
5126 goto done;
5127#ifdef DEBUG_PUSH
5128 xmlGenericError(xmlGenericErrorContext,
5129 "HPP: Parsing internal subset\n");
5130#endif
5131 docbParseDocTypeDecl(ctxt);
5132 ctxt->instate = XML_PARSER_PROLOG;
5133#ifdef DEBUG_PUSH
5134 xmlGenericError(xmlGenericErrorContext,
5135 "HPP: entering PROLOG\n");
5136#endif
5137 } else {
5138 ctxt->instate = XML_PARSER_MISC;
5139 }
5140#ifdef DEBUG_PUSH
5141 xmlGenericError(xmlGenericErrorContext,
5142 "HPP: entering MISC\n");
5143#endif
5144 break;
5145 case XML_PARSER_MISC:
5146 SKIP_BLANKS;
5147 if (in->buf == NULL)
5148 avail = in->length - (in->cur - in->base);
5149 else
5150 avail = in->buf->buffer->use - (in->cur - in->base);
5151 if (avail < 2)
5152 goto done;
5153 cur = in->cur[0];
5154 next = in->cur[1];
5155 if ((cur == '<') && (next == '!') &&
5156 (in->cur[2] == '-') && (in->cur[3] == '-')) {
5157 if ((!terminate) &&
5158 (docbParseLookupSequence(ctxt, '-', '-', '>') < 0))
5159 goto done;
5160#ifdef DEBUG_PUSH
5161 xmlGenericError(xmlGenericErrorContext,
5162 "HPP: Parsing Comment\n");
5163#endif
5164 docbParseComment(ctxt);
5165 ctxt->instate = XML_PARSER_MISC;
5166 } else if ((cur == '<') && (next == '!') &&
5167 (UPP(2) == 'D') && (UPP(3) == 'O') &&
5168 (UPP(4) == 'C') && (UPP(5) == 'T') &&
5169 (UPP(6) == 'Y') && (UPP(7) == 'P') &&
5170 (UPP(8) == 'E')) {
5171 if ((!terminate) &&
5172 (docbParseLookupSequence(ctxt, '>', 0, 0) < 0))
5173 goto done;
5174#ifdef DEBUG_PUSH
5175 xmlGenericError(xmlGenericErrorContext,
5176 "HPP: Parsing internal subset\n");
5177#endif
5178 docbParseDocTypeDecl(ctxt);
5179 ctxt->instate = XML_PARSER_PROLOG;
5180#ifdef DEBUG_PUSH
5181 xmlGenericError(xmlGenericErrorContext,
5182 "HPP: entering PROLOG\n");
5183#endif
5184 } else if ((cur == '<') && (next == '!') &&
5185 (avail < 9)) {
5186 goto done;
5187 } else {
5188 ctxt->instate = XML_PARSER_START_TAG;
5189#ifdef DEBUG_PUSH
5190 xmlGenericError(xmlGenericErrorContext,
5191 "HPP: entering START_TAG\n");
5192#endif
5193 }
5194 break;
5195 case XML_PARSER_PROLOG:
5196 SKIP_BLANKS;
5197 if (in->buf == NULL)
5198 avail = in->length - (in->cur - in->base);
5199 else
5200 avail = in->buf->buffer->use - (in->cur - in->base);
5201 if (avail < 2)
5202 goto done;
5203 cur = in->cur[0];
5204 next = in->cur[1];
5205 if ((cur == '<') && (next == '!') &&
5206 (in->cur[2] == '-') && (in->cur[3] == '-')) {
5207 if ((!terminate) &&
5208 (docbParseLookupSequence(ctxt, '-', '-', '>') < 0))
5209 goto done;
5210#ifdef DEBUG_PUSH
5211 xmlGenericError(xmlGenericErrorContext,
5212 "HPP: Parsing Comment\n");
5213#endif
5214 docbParseComment(ctxt);
5215 ctxt->instate = XML_PARSER_PROLOG;
5216 } else if ((cur == '<') && (next == '!') &&
5217 (avail < 4)) {
5218 goto done;
5219 } else {
5220 ctxt->instate = XML_PARSER_START_TAG;
5221#ifdef DEBUG_PUSH
5222 xmlGenericError(xmlGenericErrorContext,
5223 "HPP: entering START_TAG\n");
5224#endif
5225 }
5226 break;
5227 case XML_PARSER_EPILOG:
5228 if (in->buf == NULL)
5229 avail = in->length - (in->cur - in->base);
5230 else
5231 avail = in->buf->buffer->use - (in->cur - in->base);
5232 if (avail < 1)
5233 goto done;
5234 cur = in->cur[0];
5235 if (IS_BLANK(cur)) {
5236 docbParseCharData(ctxt);
5237 goto done;
5238 }
5239 if (avail < 2)
5240 goto done;
5241 next = in->cur[1];
5242 if ((cur == '<') && (next == '!') &&
5243 (in->cur[2] == '-') && (in->cur[3] == '-')) {
5244 if ((!terminate) &&
5245 (docbParseLookupSequence(ctxt, '-', '-', '>') < 0))
5246 goto done;
5247#ifdef DEBUG_PUSH
5248 xmlGenericError(xmlGenericErrorContext,
5249 "HPP: Parsing Comment\n");
5250#endif
5251 docbParseComment(ctxt);
5252 ctxt->instate = XML_PARSER_EPILOG;
5253 } else if ((cur == '<') && (next == '!') &&
5254 (avail < 4)) {
5255 goto done;
5256 } else {
5257 ctxt->errNo = XML_ERR_DOCUMENT_END;
5258 if ((ctxt->sax != NULL) && (ctxt->sax->error != NULL))
5259 ctxt->sax->error(ctxt->userData,
5260 "Extra content at the end of the document\n");
5261 ctxt->wellFormed = 0;
5262 ctxt->instate = XML_PARSER_EOF;
5263#ifdef DEBUG_PUSH
5264 xmlGenericError(xmlGenericErrorContext,
5265 "HPP: entering EOF\n");
5266#endif
5267 if ((ctxt->sax) && (ctxt->sax->endDocument != NULL))
5268 ctxt->sax->endDocument(ctxt->userData);
5269 goto done;
5270 }
5271 break;
5272 case XML_PARSER_START_TAG: {
5273 xmlChar *name, *oldname;
5274 int depth = ctxt->nameNr;
5275 docbElemDescPtr info;
5276
5277 if (avail < 2)
5278 goto done;
5279 cur = in->cur[0];
5280 if (cur != '<') {
5281 ctxt->instate = XML_PARSER_CONTENT;
5282#ifdef DEBUG_PUSH
5283 xmlGenericError(xmlGenericErrorContext,
5284 "HPP: entering CONTENT\n");
5285#endif
5286 break;
5287 }
5288 if ((!terminate) &&
5289 (docbParseLookupSequence(ctxt, '>', 0, 0) < 0))
5290 goto done;
5291
5292 oldname = xmlStrdup(ctxt->name);
5293 docbParseStartTag(ctxt);
5294 name = ctxt->name;
5295#ifdef DEBUG
5296 if (oldname == NULL)
5297 xmlGenericError(xmlGenericErrorContext,
5298 "Start of element %s\n", name);
5299 else if (name == NULL)
5300 xmlGenericError(xmlGenericErrorContext,
5301 "Start of element failed, was %s\n",
5302 oldname);
5303 else
5304 xmlGenericError(xmlGenericErrorContext,
5305 "Start of element %s, was %s\n",
5306 name, oldname);
5307#endif
5308 if (((depth == ctxt->nameNr) &&
5309 (xmlStrEqual(oldname, ctxt->name))) ||
5310 (name == NULL)) {
5311 if (CUR == '>')
5312 NEXT;
5313 if (oldname != NULL)
5314 xmlFree(oldname);
5315 break;
5316 }
5317 if (oldname != NULL)
5318 xmlFree(oldname);
5319
5320 /*
5321 * Lookup the info for that element.
5322 */
5323 info = docbTagLookup(name);
5324 if (info == NULL) {
5325 if ((ctxt->sax != NULL) && (ctxt->sax->error != NULL))
5326 ctxt->sax->error(ctxt->userData, "Tag %s unknown\n",
5327 name);
5328 ctxt->wellFormed = 0;
5329 } else if (info->depr) {
5330 /***************************
5331 if ((ctxt->sax != NULL) && (ctxt->sax->warning != NULL))
5332 ctxt->sax->warning(ctxt->userData,
5333 "Tag %s is deprecated\n",
5334 name);
5335 ***************************/
5336 }
5337
5338 /*
5339 * Check for an Empty Element labelled the XML/SGML way
5340 */
5341 if ((CUR == '/') && (NXT(1) == '>')) {
5342 SKIP(2);
5343 if ((ctxt->sax != NULL) && (ctxt->sax->endElement != NULL))
5344 ctxt->sax->endElement(ctxt->userData, name);
5345 oldname = docbnamePop(ctxt);
5346#ifdef DEBUG
5347 xmlGenericError(xmlGenericErrorContext,"End of tag the XML way: popping out %s\n",
5348 oldname);
5349#endif
5350 if (oldname != NULL)
5351 xmlFree(oldname);
5352 ctxt->instate = XML_PARSER_CONTENT;
5353#ifdef DEBUG_PUSH
5354 xmlGenericError(xmlGenericErrorContext,
5355 "HPP: entering CONTENT\n");
5356#endif
5357 break;
5358 }
5359
5360 if (CUR == '>') {
5361 NEXT;
5362 } else {
5363 if ((ctxt->sax != NULL) && (ctxt->sax->error != NULL))
5364 ctxt->sax->error(ctxt->userData,
5365 "Couldn't find end of Start Tag %s\n",
5366 name);
5367 ctxt->wellFormed = 0;
5368
5369 /*
5370 * end of parsing of this node.
5371 */
5372 if (xmlStrEqual(name, ctxt->name)) {
5373 nodePop(ctxt);
5374 oldname = docbnamePop(ctxt);
5375#ifdef DEBUG
5376 xmlGenericError(xmlGenericErrorContext,
5377 "End of start tag problem: popping out %s\n", oldname);
5378#endif
5379 if (oldname != NULL)
5380 xmlFree(oldname);
5381 }
5382
5383 ctxt->instate = XML_PARSER_CONTENT;
5384#ifdef DEBUG_PUSH
5385 xmlGenericError(xmlGenericErrorContext,
5386 "HPP: entering CONTENT\n");
5387#endif
5388 break;
5389 }
5390
5391 /*
5392 * Check for an Empty Element from DTD definition
5393 */
5394 if ((info != NULL) && (info->empty)) {
5395 if ((ctxt->sax != NULL) && (ctxt->sax->endElement != NULL))
5396 ctxt->sax->endElement(ctxt->userData, name);
5397 oldname = docbnamePop(ctxt);
5398#ifdef DEBUG
5399 xmlGenericError(xmlGenericErrorContext,"End of empty tag %s : popping out %s\n", name, oldname);
5400#endif
5401 if (oldname != NULL)
5402 xmlFree(oldname);
5403 }
5404 ctxt->instate = XML_PARSER_CONTENT;
5405#ifdef DEBUG_PUSH
5406 xmlGenericError(xmlGenericErrorContext,
5407 "HPP: entering CONTENT\n");
5408#endif
5409 break;
5410 }
5411 case XML_PARSER_CONTENT: {
5412 long cons;
5413 /*
5414 * Handle preparsed entities and charRef
5415 */
5416 if (ctxt->token != 0) {
5417 xmlChar chr[2] = { 0 , 0 } ;
5418
5419 chr[0] = (xmlChar) ctxt->token;
5420 docbCheckParagraph(ctxt);
5421 if ((ctxt->sax != NULL) && (ctxt->sax->characters != NULL))
5422 ctxt->sax->characters(ctxt->userData, chr, 1);
5423 ctxt->token = 0;
5424 ctxt->checkIndex = 0;
5425 }
5426 if ((avail == 1) && (terminate)) {
5427 cur = in->cur[0];
5428 if ((cur != '<') && (cur != '&')) {
5429 if (ctxt->sax != NULL) {
5430 if (IS_BLANK(cur)) {
5431 if (ctxt->sax->ignorableWhitespace != NULL)
5432 ctxt->sax->ignorableWhitespace(
5433 ctxt->userData, &cur, 1);
5434 } else {
5435 docbCheckParagraph(ctxt);
5436 if (ctxt->sax->characters != NULL)
5437 ctxt->sax->characters(
5438 ctxt->userData, &cur, 1);
5439 }
5440 }
5441 ctxt->token = 0;
5442 ctxt->checkIndex = 0;
5443 NEXT;
5444 }
5445 break;
5446 }
5447 if (avail < 2)
5448 goto done;
5449 cur = in->cur[0];
5450 next = in->cur[1];
5451 cons = ctxt->nbChars;
5452 /*
5453 * Sometimes DOCTYPE arrives in the middle of the document
5454 */
5455 if ((cur == '<') && (next == '!') &&
5456 (UPP(2) == 'D') && (UPP(3) == 'O') &&
5457 (UPP(4) == 'C') && (UPP(5) == 'T') &&
5458 (UPP(6) == 'Y') && (UPP(7) == 'P') &&
5459 (UPP(8) == 'E')) {
5460 if ((!terminate) &&
5461 (docbParseLookupSequence(ctxt, '>', 0, 0) < 0))
5462 goto done;
5463 if ((ctxt->sax != NULL) && (ctxt->sax->error != NULL))
5464 ctxt->sax->error(ctxt->userData,
5465 "Misplaced DOCTYPE declaration\n");
5466 ctxt->wellFormed = 0;
5467 docbParseDocTypeDecl(ctxt);
5468 } else if ((cur == '<') && (next == '!') &&
5469 (in->cur[2] == '-') && (in->cur[3] == '-')) {
5470 if ((!terminate) &&
5471 (docbParseLookupSequence(ctxt, '-', '-', '>') < 0))
5472 goto done;
5473#ifdef DEBUG_PUSH
5474 xmlGenericError(xmlGenericErrorContext,
5475 "HPP: Parsing Comment\n");
5476#endif
5477 docbParseComment(ctxt);
5478 ctxt->instate = XML_PARSER_CONTENT;
5479 } else if ((cur == '<') && (next == '!') && (avail < 4)) {
5480 goto done;
5481 } else if ((cur == '<') && (next == '/')) {
5482 ctxt->instate = XML_PARSER_END_TAG;
5483 ctxt->checkIndex = 0;
5484#ifdef DEBUG_PUSH
5485 xmlGenericError(xmlGenericErrorContext,
5486 "HPP: entering END_TAG\n");
5487#endif
5488 break;
5489 } else if (cur == '<') {
5490 ctxt->instate = XML_PARSER_START_TAG;
5491 ctxt->checkIndex = 0;
5492#ifdef DEBUG_PUSH
5493 xmlGenericError(xmlGenericErrorContext,
5494 "HPP: entering START_TAG\n");
5495#endif
5496 break;
5497 } else if (cur == '&') {
5498 if ((!terminate) &&
5499 (docbParseLookupSequence(ctxt, ';', 0, 0) < 0))
5500 goto done;
5501#ifdef DEBUG_PUSH
5502 xmlGenericError(xmlGenericErrorContext,
5503 "HPP: Parsing Reference\n");
5504#endif
5505 /* TODO: check generation of subtrees if noent !!! */
5506 docbParseReference(ctxt);
5507 } else {
5508 /* TODO Avoid the extra copy, handle directly !!!!!! */
5509 /*
5510 * Goal of the following test is :
5511 * - minimize calls to the SAX 'character' callback
5512 * when they are mergeable
5513 */
5514 if ((ctxt->inputNr == 1) &&
5515 (avail < DOCB_PARSER_BIG_BUFFER_SIZE)) {
5516 if ((!terminate) &&
5517 (docbParseLookupSequence(ctxt, '<', 0, 0) < 0))
5518 goto done;
5519 }
5520 ctxt->checkIndex = 0;
5521#ifdef DEBUG_PUSH
5522 xmlGenericError(xmlGenericErrorContext,
5523 "HPP: Parsing char data\n");
5524#endif
5525 docbParseCharData(ctxt);
5526 }
5527 if (cons == ctxt->nbChars) {
5528 if (ctxt->node != NULL) {
5529 if ((ctxt->sax != NULL) && (ctxt->sax->error != NULL))
5530 ctxt->sax->error(ctxt->userData,
5531 "detected an error in element content\n");
5532 ctxt->wellFormed = 0;
5533 NEXT;
5534 }
5535 break;
5536 }
5537
5538 break;
5539 }
5540 case XML_PARSER_END_TAG:
5541 if (avail < 2)
5542 goto done;
5543 if ((!terminate) &&
5544 (docbParseLookupSequence(ctxt, '>', 0, 0) < 0))
5545 goto done;
5546 docbParseEndTag(ctxt);
5547 if (ctxt->nameNr == 0) {
5548 ctxt->instate = XML_PARSER_EPILOG;
5549 } else {
5550 ctxt->instate = XML_PARSER_CONTENT;
5551 }
5552 ctxt->checkIndex = 0;
5553#ifdef DEBUG_PUSH
5554 xmlGenericError(xmlGenericErrorContext,
5555 "HPP: entering CONTENT\n");
5556#endif
5557 break;
5558 case XML_PARSER_CDATA_SECTION:
5559 xmlGenericError(xmlGenericErrorContext,
5560 "HPP: internal error, state == CDATA\n");
5561 ctxt->instate = XML_PARSER_CONTENT;
5562 ctxt->checkIndex = 0;
5563#ifdef DEBUG_PUSH
5564 xmlGenericError(xmlGenericErrorContext,
5565 "HPP: entering CONTENT\n");
5566#endif
5567 break;
5568 case XML_PARSER_DTD:
5569 xmlGenericError(xmlGenericErrorContext,
5570 "HPP: internal error, state == DTD\n");
5571 ctxt->instate = XML_PARSER_CONTENT;
5572 ctxt->checkIndex = 0;
5573#ifdef DEBUG_PUSH
5574 xmlGenericError(xmlGenericErrorContext,
5575 "HPP: entering CONTENT\n");
5576#endif
5577 break;
5578 case XML_PARSER_COMMENT:
5579 xmlGenericError(xmlGenericErrorContext,
5580 "HPP: internal error, state == COMMENT\n");
5581 ctxt->instate = XML_PARSER_CONTENT;
5582 ctxt->checkIndex = 0;
5583#ifdef DEBUG_PUSH
5584 xmlGenericError(xmlGenericErrorContext,
5585 "HPP: entering CONTENT\n");
5586#endif
5587 break;
5588 case XML_PARSER_PI:
5589 xmlGenericError(xmlGenericErrorContext,
5590 "HPP: internal error, state == PI\n");
5591 ctxt->instate = XML_PARSER_CONTENT;
5592 ctxt->checkIndex = 0;
5593#ifdef DEBUG_PUSH
5594 xmlGenericError(xmlGenericErrorContext,
5595 "HPP: entering CONTENT\n");
5596#endif
5597 break;
5598 case XML_PARSER_ENTITY_DECL:
5599 xmlGenericError(xmlGenericErrorContext,
5600 "HPP: internal error, state == ENTITY_DECL\n");
5601 ctxt->instate = XML_PARSER_CONTENT;
5602 ctxt->checkIndex = 0;
5603#ifdef DEBUG_PUSH
5604 xmlGenericError(xmlGenericErrorContext,
5605 "HPP: entering CONTENT\n");
5606#endif
5607 break;
5608 case XML_PARSER_ENTITY_VALUE:
5609 xmlGenericError(xmlGenericErrorContext,
5610 "HPP: internal error, state == ENTITY_VALUE\n");
5611 ctxt->instate = XML_PARSER_CONTENT;
5612 ctxt->checkIndex = 0;
5613#ifdef DEBUG_PUSH
5614 xmlGenericError(xmlGenericErrorContext,
5615 "HPP: entering DTD\n");
5616#endif
5617 break;
5618 case XML_PARSER_ATTRIBUTE_VALUE:
5619 xmlGenericError(xmlGenericErrorContext,
5620 "HPP: internal error, state == ATTRIBUTE_VALUE\n");
5621 ctxt->instate = XML_PARSER_START_TAG;
5622 ctxt->checkIndex = 0;
5623#ifdef DEBUG_PUSH
5624 xmlGenericError(xmlGenericErrorContext,
5625 "HPP: entering START_TAG\n");
5626#endif
5627 break;
5628 case XML_PARSER_SYSTEM_LITERAL:
5629 xmlGenericError(xmlGenericErrorContext,
5630 "HPP: internal error, state == XML_PARSER_SYSTEM_LITERAL\n");
5631 ctxt->instate = XML_PARSER_CONTENT;
5632 ctxt->checkIndex = 0;
5633#ifdef DEBUG_PUSH
5634 xmlGenericError(xmlGenericErrorContext,
5635 "HPP: entering CONTENT\n");
5636#endif
5637 break;
5638
5639 case XML_PARSER_IGNORE:
5640 xmlGenericError(xmlGenericErrorContext,
5641 "HPP: internal error, state == XML_PARSER_IGNORE\n");
5642 ctxt->instate = XML_PARSER_CONTENT;
5643 ctxt->checkIndex = 0;
5644#ifdef DEBUG_PUSH
5645 xmlGenericError(xmlGenericErrorContext,
5646 "HPP: entering CONTENT\n");
5647#endif
5648 break;
5649 }
5650 }
5651done:
5652 if ((avail == 0) && (terminate)) {
5653 docbAutoClose(ctxt, NULL);
5654 if ((ctxt->nameNr == 0) && (ctxt->instate != XML_PARSER_EOF)) {
5655 /*
5656 * SAX: end of the document processing.
5657 */
5658 ctxt->instate = XML_PARSER_EOF;
5659 if ((ctxt->sax) && (ctxt->sax->endDocument != NULL))
5660 ctxt->sax->endDocument(ctxt->userData);
5661 }
5662 }
5663 if ((ctxt->myDoc != NULL) &&
5664 ((terminate) || (ctxt->instate == XML_PARSER_EOF) ||
5665 (ctxt->instate == XML_PARSER_EPILOG))) {
5666 xmlDtdPtr dtd;
5667 dtd = ctxt->myDoc->intSubset;
5668 if (dtd == NULL)
5669 ctxt->myDoc->intSubset =
5670 xmlCreateIntSubset(ctxt->myDoc, BAD_CAST "SGML",
5671 BAD_CAST "-//W3C//DTD SGML 4.0 Transitional//EN",
5672 BAD_CAST "http://www.w3.org/TR/REC-docbook/loose.dtd");
5673 }
5674#ifdef DEBUG_PUSH
5675 xmlGenericError(xmlGenericErrorContext, "HPP: done %d\n", ret);
5676#endif
5677 return(ret);
5678}
5679
5680/**
5681 * docbParseChunk:
5682 * @ctxt: an XML parser context
5683 * @chunk: an char array
5684 * @size: the size in byte of the chunk
5685 * @terminate: last chunk indicator
5686 *
5687 * Parse a Chunk of memory
5688 *
5689 * Returns zero if no error, the xmlParserErrors otherwise.
5690 */
5691int
5692docbParseChunk(docbParserCtxtPtr ctxt, const char *chunk, int size,
5693 int terminate) {
5694 if ((size > 0) && (chunk != NULL) && (ctxt->input != NULL) &&
5695 (ctxt->input->buf != NULL) && (ctxt->instate != XML_PARSER_EOF)) {
5696 int base = ctxt->input->base - ctxt->input->buf->buffer->content;
5697 int cur = ctxt->input->cur - ctxt->input->base;
5698
5699 xmlParserInputBufferPush(ctxt->input->buf, size, chunk);
5700 ctxt->input->base = ctxt->input->buf->buffer->content + base;
5701 ctxt->input->cur = ctxt->input->base + cur;
5702#ifdef DEBUG_PUSH
5703 xmlGenericError(xmlGenericErrorContext, "HPP: pushed %d\n", size);
5704#endif
5705
5706 if ((terminate) || (ctxt->input->buf->buffer->use > 80))
5707 docbParseTryOrFinish(ctxt, terminate);
5708 } else if (ctxt->instate != XML_PARSER_EOF) {
5709 xmlParserInputBufferPush(ctxt->input->buf, 0, "");
5710 docbParseTryOrFinish(ctxt, terminate);
5711 }
5712 if (terminate) {
5713 if ((ctxt->instate != XML_PARSER_EOF) &&
5714 (ctxt->instate != XML_PARSER_EPILOG) &&
5715 (ctxt->instate != XML_PARSER_MISC)) {
5716 ctxt->errNo = XML_ERR_DOCUMENT_END;
5717 if ((ctxt->sax != NULL) && (ctxt->sax->error != NULL))
5718 ctxt->sax->error(ctxt->userData,
5719 "Extra content at the end of the document\n");
5720 ctxt->wellFormed = 0;
5721 }
5722 if (ctxt->instate != XML_PARSER_EOF) {
5723 if ((ctxt->sax) && (ctxt->sax->endDocument != NULL))
5724 ctxt->sax->endDocument(ctxt->userData);
5725 }
5726 ctxt->instate = XML_PARSER_EOF;
5727 }
5728 return((xmlParserErrors) ctxt->errNo);
5729}
5730
5731/************************************************************************
5732 * *
5733 * User entry points *
5734 * *
5735 ************************************************************************/
5736
5737/**
5738 * docbCreatePushParserCtxt :
5739 * @sax: a SAX handler
5740 * @user_data: The user data returned on SAX callbacks
5741 * @chunk: a pointer to an array of chars
5742 * @size: number of chars in the array
5743 * @filename: an optional file name or URI
5744 * @enc: an optional encoding
5745 *
5746 * Create a parser context for using the DocBook SGML parser in push mode
5747 * To allow content encoding detection, @size should be >= 4
5748 * The value of @filename is used for fetching external entities
5749 * and error/warning reports.
5750 *
5751 * Returns the new parser context or NULL
5752 */
5753docbParserCtxtPtr
5754docbCreatePushParserCtxt(docbSAXHandlerPtr sax, void *user_data,
5755 const char *chunk, int size, const char *filename,
5756 xmlCharEncoding enc) {
5757 docbParserCtxtPtr ctxt;
5758 docbParserInputPtr inputStream;
5759 xmlParserInputBufferPtr buf;
5760
5761 buf = xmlAllocParserInputBuffer(enc);
5762 if (buf == NULL) return(NULL);
5763
5764 ctxt = (docbParserCtxtPtr) xmlMalloc(sizeof(docbParserCtxt));
5765 if (ctxt == NULL) {
5766 xmlFree(buf);
5767 return(NULL);
5768 }
5769 memset(ctxt, 0, sizeof(docbParserCtxt));
5770 docbInitParserCtxt(ctxt);
5771 if (sax != NULL) {
5772 if (ctxt->sax != &docbDefaultSAXHandler)
5773 xmlFree(ctxt->sax);
5774 ctxt->sax = (docbSAXHandlerPtr) xmlMalloc(sizeof(docbSAXHandler));
5775 if (ctxt->sax == NULL) {
5776 xmlFree(buf);
5777 xmlFree(ctxt);
5778 return(NULL);
5779 }
5780 memcpy(ctxt->sax, sax, sizeof(docbSAXHandler));
5781 if (user_data != NULL)
5782 ctxt->userData = user_data;
5783 }
5784 if (filename == NULL) {
5785 ctxt->directory = NULL;
5786 } else {
5787 ctxt->directory = xmlParserGetDirectory(filename);
5788 }
5789
5790 inputStream = docbNewInputStream(ctxt);
5791 if (inputStream == NULL) {
5792 xmlFreeParserCtxt(ctxt);
5793 return(NULL);
5794 }
5795
5796 if (filename == NULL)
5797 inputStream->filename = NULL;
5798 else
5799 inputStream->filename = xmlMemStrdup(filename);
5800 inputStream->buf = buf;
5801 inputStream->base = inputStream->buf->buffer->content;
5802 inputStream->cur = inputStream->buf->buffer->content;
5803
5804 inputPush(ctxt, inputStream);
5805
5806 if ((size > 0) && (chunk != NULL) && (ctxt->input != NULL) &&
5807 (ctxt->input->buf != NULL)) {
5808 xmlParserInputBufferPush(ctxt->input->buf, size, chunk);
5809#ifdef DEBUG_PUSH
5810 xmlGenericError(xmlGenericErrorContext, "HPP: pushed %d\n", size);
5811#endif
5812 }
5813
5814 return(ctxt);
5815}
5816
5817/**
5818 * docbSAXParseDoc :
5819 * @cur: a pointer to an array of xmlChar
5820 * @encoding: a free form C string describing the SGML document encoding, or NULL
5821 * @sax: the SAX handler block
5822 * @userData: if using SAX, this pointer will be provided on callbacks.
5823 *
5824 * parse an SGML in-memory document and build a tree.
5825 * It use the given SAX function block to handle the parsing callback.
5826 * If sax is NULL, fallback to the default DOM tree building routines.
5827 *
5828 * Returns the resulting document tree
5829 */
5830
5831docbDocPtr
5832docbSAXParseDoc(xmlChar *cur, const char *encoding, docbSAXHandlerPtr sax, void *userData) {
5833 docbDocPtr ret;
5834 docbParserCtxtPtr ctxt;
5835
5836 if (cur == NULL) return(NULL);
5837
5838
5839 ctxt = docbCreateDocParserCtxt(cur, encoding);
5840 if (ctxt == NULL) return(NULL);
5841 if (sax != NULL) {
5842 ctxt->sax = sax;
5843 ctxt->userData = userData;
5844 }
5845
5846 docbParseDocument(ctxt);
5847 ret = ctxt->myDoc;
5848 if (sax != NULL) {
5849 ctxt->sax = NULL;
5850 ctxt->userData = NULL;
5851 }
5852 docbFreeParserCtxt(ctxt);
5853
5854 return(ret);
5855}
5856
5857/**
5858 * docbParseDoc :
5859 * @cur: a pointer to an array of xmlChar
5860 * @encoding: a free form C string describing the SGML document encoding, or NULL
5861 *
5862 * parse an SGML in-memory document and build a tree.
5863 *
5864 * Returns the resulting document tree
5865 */
5866
5867docbDocPtr
5868docbParseDoc(xmlChar *cur, const char *encoding) {
5869 return(docbSAXParseDoc(cur, encoding, NULL, NULL));
5870}
5871
5872
5873/**
5874 * docbCreateFileParserCtxt :
5875 * @filename: the filename
Daniel Veillard1034da22001-04-25 19:06:28 +0000[diff] [blame^]5876 * @encoding: the SGML document encoding, or NULL
Daniel Veillardeae522a2001-04-23 13:41:34 +0000[diff] [blame]5877 *
5878 * Create a parser context for a file content.
5879 * Automatic support for ZLIB/Compress compressed document is provided
5880 * by default if found at compile-time.
5881 *
5882 * Returns the new parser context or NULL
5883 */
5884docbParserCtxtPtr
Daniel Veillard1034da22001-04-25 19:06:28 +0000[diff] [blame^]5885docbCreateFileParserCtxt(const char *filename,
5886 const char *encoding ATTRIBUTE_UNUSED)
Daniel Veillardeae522a2001-04-23 13:41:34 +0000[diff] [blame]5887{
5888 docbParserCtxtPtr ctxt;
5889 docbParserInputPtr inputStream;
5890 xmlParserInputBufferPtr buf;
5891 /* sgmlCharEncoding enc; */
5892
5893 buf = xmlParserInputBufferCreateFilename(filename, XML_CHAR_ENCODING_NONE);
5894 if (buf == NULL) return(NULL);
5895
5896 ctxt = (docbParserCtxtPtr) xmlMalloc(sizeof(docbParserCtxt));
5897 if (ctxt == NULL) {
5898 perror("malloc");
5899 return(NULL);
5900 }
5901 memset(ctxt, 0, sizeof(docbParserCtxt));
5902 docbInitParserCtxt(ctxt);
5903 inputStream = (docbParserInputPtr) xmlMalloc(sizeof(docbParserInput));
5904 if (inputStream == NULL) {
5905 perror("malloc");
5906 xmlFree(ctxt);
5907 return(NULL);
5908 }
5909 memset(inputStream, 0, sizeof(docbParserInput));
5910
5911 inputStream->filename = xmlMemStrdup(filename);
5912 inputStream->line = 1;
5913 inputStream->col = 1;
5914 inputStream->buf = buf;
5915 inputStream->directory = NULL;
5916
5917 inputStream->base = inputStream->buf->buffer->content;
5918 inputStream->cur = inputStream->buf->buffer->content;
5919 inputStream->free = NULL;
5920
5921 inputPush(ctxt, inputStream);
5922 return(ctxt);
5923}
5924
5925/**
5926 * docbSAXParseFile :
5927 * @filename: the filename
5928 * @encoding: a free form C string describing the SGML document encoding, or NULL
5929 * @sax: the SAX handler block
5930 * @userData: if using SAX, this pointer will be provided on callbacks.
5931 *
5932 * parse an SGML file and build a tree. Automatic support for ZLIB/Compress
5933 * compressed document is provided by default if found at compile-time.
5934 * It use the given SAX function block to handle the parsing callback.
5935 * If sax is NULL, fallback to the default DOM tree building routines.
5936 *
5937 * Returns the resulting document tree
5938 */
5939
5940docbDocPtr
5941docbSAXParseFile(const char *filename, const char *encoding, docbSAXHandlerPtr sax,
5942 void *userData) {
5943 docbDocPtr ret;
5944 docbParserCtxtPtr ctxt;
5945 docbSAXHandlerPtr oldsax = NULL;
5946
5947 ctxt = docbCreateFileParserCtxt(filename, encoding);
5948 if (ctxt == NULL) return(NULL);
5949 if (sax != NULL) {
5950 oldsax = ctxt->sax;
5951 ctxt->sax = sax;
5952 ctxt->userData = userData;
5953 }
5954
5955 docbParseDocument(ctxt);
5956
5957 ret = ctxt->myDoc;
5958 if (sax != NULL) {
5959 ctxt->sax = oldsax;
5960 ctxt->userData = NULL;
5961 }
5962 docbFreeParserCtxt(ctxt);
5963
5964 return(ret);
5965}
5966
5967/**
5968 * docbParseFile :
5969 * @filename: the filename
5970 * @encoding: a free form C string describing document encoding, or NULL
5971 *
5972 * parse a Docbook SGML file and build a tree. Automatic support for
5973 * ZLIB/Compress compressed document is provided by default if found
5974 * at compile-time.
5975 *
5976 * Returns the resulting document tree
5977 */
5978
5979docbDocPtr
5980docbParseFile(const char *filename, const char *encoding) {
5981 return(docbSAXParseFile(filename, encoding, NULL, NULL));
5982}
5983
5984#endif /* LIBXML_DOCB_ENABLED */