Gitiles
Code Review Sign In
gerrit-public.fairphone.software / platform / external / libxml2 / 4ec0b0f4c33bbf0917cccb1c3583122c16b95287 / . / DOCBparser.c
blob: c199b4c384333f80f58af5213d2232f2a5b484ac [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 Veillardeae522a2001-04-23 13:41:34 +0000[diff] [blame]72
73/*
74 * Internal description of an SGML element
75 */
76typedef struct _docbElemDesc docbElemDesc;
77typedef docbElemDesc *docbElemDescPtr;
78struct _docbElemDesc {
79 const char *name; /* The tag name */
80 int startTag; /* Whether the start tag can be implied */
81 int endTag; /* Whether the end tag can be implied */
82 int empty; /* Is this an empty element ? */
83 int depr; /* Is this a deprecated element ? */
84 int dtd; /* 1: only in Loose DTD, 2: only Frameset one */
85 const char *desc; /* the description */
86};
87
88
89#define DOCB_MAX_NAMELEN 1000
90#define DOCB_PARSER_BIG_BUFFER_SIZE 1000
91#define DOCB_PARSER_BUFFER_SIZE 100
92
93/* #define DEBUG */
94/* #define DEBUG_PUSH */
95
96/************************************************************************
97 * *
98 * Parser stacks related functions and macros *
99 * *
100 ************************************************************************/
101
102/*
103 * Generic function for accessing stacks in the Parser Context
104 */
105
106#define PUSH_AND_POP(scope, type, name) \
107scope int docb##name##Push(docbParserCtxtPtr ctxt, type value) { \
108 if (ctxt->name##Nr >= ctxt->name##Max) { \
109 ctxt->name##Max *= 2; \
110 ctxt->name##Tab = (type *) xmlRealloc(ctxt->name##Tab, \
111 ctxt->name##Max * sizeof(ctxt->name##Tab[0])); \
112 if (ctxt->name##Tab == NULL) { \
113 xmlGenericError(xmlGenericErrorContext, "realloc failed !\n"); \
114 return(0); \
115 } \
116 } \
117 ctxt->name##Tab[ctxt->name##Nr] = value; \
118 ctxt->name = value; \
119 return(ctxt->name##Nr++); \
120} \
121scope type docb##name##Pop(docbParserCtxtPtr ctxt) { \
122 type ret; \
123 if (ctxt->name##Nr < 0) return(0); \
124 ctxt->name##Nr--; \
125 if (ctxt->name##Nr < 0) return(0); \
126 if (ctxt->name##Nr > 0) \
127 ctxt->name = ctxt->name##Tab[ctxt->name##Nr - 1]; \
128 else \
129 ctxt->name = NULL; \
130 ret = ctxt->name##Tab[ctxt->name##Nr]; \
131 ctxt->name##Tab[ctxt->name##Nr] = 0; \
132 return(ret); \
133} \
134
135/* PUSH_AND_POP(static, xmlNodePtr, node) */
136PUSH_AND_POP(static, xmlChar*, name)
137
138/*
139 * Macros for accessing the content. Those should be used only by the parser,
140 * and not exported.
141 *
142 * Dirty macros, i.e. one need to make assumption on the context to use them
143 *
144 * CUR_PTR return the current pointer to the xmlChar to be parsed.
145 * CUR returns the current xmlChar value, i.e. a 8 bit value if compiled
146 * in ISO-Latin or UTF-8, and the current 16 bit value if compiled
147 * in UNICODE mode. This should be used internally by the parser
148 * only to compare to ASCII values otherwise it would break when
149 * running with UTF-8 encoding.
150 * NXT(n) returns the n'th next xmlChar. Same as CUR is should be used only
151 * to compare on ASCII based substring.
152 * UPP(n) returns the n'th next xmlChar converted to uppercase. Same as CUR
153 * it should be used only to compare on ASCII based substring.
154 * SKIP(n) Skip n xmlChar, and must also be used only to skip ASCII defined
155 * strings within the parser.
156 *
157 * Clean macros, not dependent of an ASCII context, expect UTF-8 encoding
158 *
159 * CURRENT Returns the current char value, with the full decoding of
160 * UTF-8 if we are using this mode. It returns an int.
161 * NEXT Skip to the next character, this does the proper decoding
162 * in UTF-8 mode. It also pop-up unfinished entities on the fly.
163 * COPY(to) copy one char to *to, increment CUR_PTR and to accordingly
164 */
165
166#define UPPER (toupper(*ctxt->input->cur))
167
168#define SKIP(val) ctxt->nbChars += (val),ctxt->input->cur += (val)
169
170#define NXT(val) ctxt->input->cur[(val)]
171
172#define UPP(val) (toupper(ctxt->input->cur[(val)]))
173
174#define CUR_PTR ctxt->input->cur
175
176#define SHRINK xmlParserInputShrink(ctxt->input)
177
178#define GROW xmlParserInputGrow(ctxt->input, INPUT_CHUNK)
179
180#define CURRENT ((int) (*ctxt->input->cur))
181
182#define SKIP_BLANKS docbSkipBlankChars(ctxt)
183
184/* Imported from XML */
185
186/* #define CUR (ctxt->token ? ctxt->token : (int) (*ctxt->input->cur)) */
187#define CUR ((int) (*ctxt->input->cur))
188#define NEXT xmlNextChar(ctxt),ctxt->nbChars++
189
190#define RAW (ctxt->token ? -1 : (*ctxt->input->cur))
191#define NXT(val) ctxt->input->cur[(val)]
192#define CUR_PTR ctxt->input->cur
193
194
195#define NEXTL(l) do { \
196 if (*(ctxt->input->cur) == '\n') { \
197 ctxt->input->line++; ctxt->input->col = 1; \
198 } else ctxt->input->col++; \
199 ctxt->token = 0; ctxt->input->cur += l; ctxt->nbChars++; \
200 } while (0)
201
202/************
203 \
204 if (*ctxt->input->cur == '%') xmlParserHandlePEReference(ctxt); \
205 if (*ctxt->input->cur == '&') xmlParserHandleReference(ctxt);
206 ************/
207
208#define CUR_CHAR(l) docbCurrentChar(ctxt, &l)
209#define CUR_SCHAR(s, l) xmlStringCurrentChar(ctxt, s, &l)
210
211#define COPY_BUF(l,b,i,v) \
212 if (l == 1) b[i++] = (xmlChar) v; \
213 else i += xmlCopyChar(l,&b[i],v)
214
215/**
216 * docbCurrentChar:
217 * @ctxt: the DocBook SGML parser context
218 * @len: pointer to the length of the char read
219 *
220 * The current char value, if using UTF-8 this may actaully span multiple
221 * bytes in the input buffer. Implement the end of line normalization:
222 * 2.11 End-of-Line Handling
223 * If the encoding is unspecified, in the case we find an ISO-Latin-1
224 * char, then the encoding converter is plugged in automatically.
225 *
226 * Returns the current char value and its lenght
227 */
228
229static int
230docbCurrentChar(xmlParserCtxtPtr ctxt, int *len) {
231 if (ctxt->instate == XML_PARSER_EOF)
232 return(0);
233
234 if (ctxt->token != 0) {
235 *len = 0;
236 return(ctxt->token);
237 }
238 if (ctxt->charset == XML_CHAR_ENCODING_UTF8) {
239 /*
240 * We are supposed to handle UTF8, check it's valid
241 * From rfc2044: encoding of the Unicode values on UTF-8:
242 *
243 * UCS-4 range (hex.) UTF-8 octet sequence (binary)
244 * 0000 0000-0000 007F 0xxxxxxx
245 * 0000 0080-0000 07FF 110xxxxx 10xxxxxx
246 * 0000 0800-0000 FFFF 1110xxxx 10xxxxxx 10xxxxxx
247 *
248 * Check for the 0x110000 limit too
249 */
250 const unsigned char *cur = ctxt->input->cur;
251 unsigned char c;
252 unsigned int val;
253
254 c = *cur;
255 if (c & 0x80) {
256 if (cur[1] == 0)
257 xmlParserInputGrow(ctxt->input, INPUT_CHUNK);
258 if ((cur[1] & 0xc0) != 0x80)
259 goto encoding_error;
260 if ((c & 0xe0) == 0xe0) {
261
262 if (cur[2] == 0)
263 xmlParserInputGrow(ctxt->input, INPUT_CHUNK);
264 if ((cur[2] & 0xc0) != 0x80)
265 goto encoding_error;
266 if ((c & 0xf0) == 0xf0) {
267 if (cur[3] == 0)
268 xmlParserInputGrow(ctxt->input, INPUT_CHUNK);
269 if (((c & 0xf8) != 0xf0) ||
270 ((cur[3] & 0xc0) != 0x80))
271 goto encoding_error;
272 /* 4-byte code */
273 *len = 4;
274 val = (cur[0] & 0x7) << 18;
275 val |= (cur[1] & 0x3f) << 12;
276 val |= (cur[2] & 0x3f) << 6;
277 val |= cur[3] & 0x3f;
278 } else {
279 /* 3-byte code */
280 *len = 3;
281 val = (cur[0] & 0xf) << 12;
282 val |= (cur[1] & 0x3f) << 6;
283 val |= cur[2] & 0x3f;
284 }
285 } else {
286 /* 2-byte code */
287 *len = 2;
288 val = (cur[0] & 0x1f) << 6;
289 val |= cur[1] & 0x3f;
290 }
291 if (!IS_CHAR(val)) {
292 ctxt->errNo = XML_ERR_INVALID_ENCODING;
293 if ((ctxt->sax != NULL) &&
294 (ctxt->sax->error != NULL))
295 ctxt->sax->error(ctxt->userData,
296 "Char 0x%X out of allowed range\n", val);
297 ctxt->wellFormed = 0;
298 ctxt->disableSAX = 1;
299 }
300 return(val);
301 } else {
302 /* 1-byte code */
303 *len = 1;
304 return((int) *ctxt->input->cur);
305 }
306 }
307 /*
308 * Assume it's a fixed lenght encoding (1) with
309 * a compatibke encoding for the ASCII set, since
310 * XML constructs only use < 128 chars
311 */
312 *len = 1;
313 if ((int) *ctxt->input->cur < 0x80)
314 return((int) *ctxt->input->cur);
315
316 /*
317 * Humm this is bad, do an automatic flow conversion
318 */
319 xmlSwitchEncoding(ctxt, XML_CHAR_ENCODING_8859_1);
320 ctxt->charset = XML_CHAR_ENCODING_UTF8;
321 return(xmlCurrentChar(ctxt, len));
322
323encoding_error:
324 /*
325 * If we detect an UTF8 error that probably mean that the
326 * input encoding didn't get properly advertized in the
327 * declaration header. Report the error and switch the encoding
328 * to ISO-Latin-1 (if you don't like this policy, just declare the
329 * encoding !)
330 */
331 ctxt->errNo = XML_ERR_INVALID_ENCODING;
332 if ((ctxt->sax != NULL) && (ctxt->sax->error != NULL)) {
333 ctxt->sax->error(ctxt->userData,
334 "Input is not proper UTF-8, indicate encoding !\n");
335 ctxt->sax->error(ctxt->userData, "Bytes: 0x%02X 0x%02X 0x%02X 0x%02X\n",
336 ctxt->input->cur[0], ctxt->input->cur[1],
337 ctxt->input->cur[2], ctxt->input->cur[3]);
338 }
339
340 ctxt->charset = XML_CHAR_ENCODING_8859_1;
341 *len = 1;
342 return((int) *ctxt->input->cur);
343}
344
345#if 0
346/**
347 * sgmlNextChar:
348 * @ctxt: the DocBook SGML parser context
349 *
350 * Skip to the next char input char.
351 */
352
353static void
354sgmlNextChar(docbParserCtxtPtr ctxt) {
355 if (ctxt->instate == XML_PARSER_EOF)
356 return;
357 if ((*ctxt->input->cur == 0) &&
358 (xmlParserInputGrow(ctxt->input, INPUT_CHUNK) <= 0)) {
359 xmlPopInput(ctxt);
360 } else {
361 if (*(ctxt->input->cur) == '\n') {
362 ctxt->input->line++; ctxt->input->col = 1;
363 } else ctxt->input->col++;
364 ctxt->input->cur++;
365 ctxt->nbChars++;
366 if (*ctxt->input->cur == 0)
367 xmlParserInputGrow(ctxt->input, INPUT_CHUNK);
368 }
369}
370#endif
371
372/**
373 * docbSkipBlankChars:
374 * @ctxt: the DocBook SGML parser context
375 *
376 * skip all blanks character found at that point in the input streams.
377 *
378 * Returns the number of space chars skipped
379 */
380
381static int
382docbSkipBlankChars(xmlParserCtxtPtr ctxt) {
383 int res = 0;
384
385 while (IS_BLANK(*(ctxt->input->cur))) {
386 if ((*ctxt->input->cur == 0) &&
387 (xmlParserInputGrow(ctxt->input, INPUT_CHUNK) <= 0)) {
388 xmlPopInput(ctxt);
389 } else {
390 if (*(ctxt->input->cur) == '\n') {
391 ctxt->input->line++; ctxt->input->col = 1;
392 } else ctxt->input->col++;
393 ctxt->input->cur++;
394 ctxt->nbChars++;
395 if (*ctxt->input->cur == 0)
396 xmlParserInputGrow(ctxt->input, INPUT_CHUNK);
397 }
398 res++;
399 }
400 return(res);
401}
402
403
404
405/************************************************************************
406 * *
407 * The list of SGML elements and their properties *
408 * *
409 ************************************************************************/
410
411/*
412 * Start Tag: 1 means the start tag can be ommited
413 * End Tag: 1 means the end tag can be ommited
414 * 2 means it's forbidden (empty elements)
415 * Depr: this element is deprecated
416 * DTD: 1 means that this element is valid only in the Loose DTD
417 * 2 means that this element is valid only in the Frameset DTD
418 *
419 * Name,Start Tag,End Tag, Empty, Depr., DTD, Description
420 */
421static docbElemDesc
422docbookElementTable[] = {
423{ "abbrev", 0, 0, 0, 3, 0, "" }, /* word */
424{ "abstract", 0, 0, 0, 9, 0, "" }, /* title */
425{ "accel", 0, 0, 0, 7, 0, "" }, /* smallcptr */
426{ "ackno", 0, 0, 0, 4, 0, "" }, /* docinfo */
427{ "acronym", 0, 0, 0, 3, 0, "" }, /* word */
428{ "action", 0, 0, 0, 7, 0, "" }, /* smallcptr */
429{ "address", 0, 0, 0, 1, 0, "" },
430{ "affiliation",0, 0, 0, 9, 0, "" }, /* shortaffil */
431{ "alt", 0, 0, 0, 1, 0, "" },
432{ "anchor", 0, 2, 1, 0, 0, "" },
433{ "answer", 0, 0, 0, 9, 0, "" }, /* label */
434{ "appendix", 0, 0, 0, 9, 0, "" }, /* appendixinfo */
435{ "appendixinfo",0, 0, 0, 9, 0, "" }, /* graphic */
436{ "application",0, 0, 0, 2, 0, "" }, /* para */
437{ "area", 0, 2, 1, 0, 0, "" },
438{ "areaset", 0, 0, 0, 9, 0, "" }, /* area */
439{ "areaspec", 0, 0, 0, 9, 0, "" }, /* area */
440{ "arg", 0, 0, 0, 1, 0, "" },
Daniel Veillard4ec0b0f2001-04-25 15:53:40 +0000[diff] [blame^]441{ "artheader", 0, 0, 0, 9, 0, "" },
Daniel Veillardeae522a2001-04-23 13:41:34 +0000[diff] [blame]442{ "article", 0, 0, 0, 9, 0, "" }, /* div.title.content */
443{ "articleinfo",0, 0, 0, 9, 0, "" }, /* graphic */
444{ "artpagenums",0, 0, 0, 4, 0, "" }, /* docinfo */
445{ "attribution",0, 0, 0, 2, 0, "" }, /* para */
446{ "audiodata", 0, 2, 1, 0, 0, "" },
447{ "audioobject",0, 0, 0, 9, 0, "" }, /* objectinfo */
448{ "authorblurb",0, 0, 0, 9, 0, "" }, /* title */
449{ "authorgroup",0, 0, 0, 9, 0, "" }, /* author */
450{ "authorinitials",0, 0, 0, 4, 0, "" }, /* docinfo */
451{ "author", 0, 0, 0, 9, 0, "" }, /* person.ident.mix */
452{ "beginpage", 0, 2, 1, 0, 0, "" },
453{ "bibliodiv", 0, 0, 0, 9, 0, "" }, /* sect.title.content */
454{ "biblioentry",0, 0, 0, 9, 0, "" }, /* articleinfo */
455{ "bibliography",0, 0, 0, 9, 0, "" }, /* bibliographyinfo */
456{ "bibliographyinfo",0, 0, 0, 9, 0, "" }, /* graphic */
457{ "bibliomisc", 0, 0, 0, 2, 0, "" }, /* para */
458{ "bibliomixed",0, 0, 0, 1, 0, "" }, /* %bibliocomponent.mix, bibliomset) */
459{ "bibliomset", 0, 0, 0, 1, 0, "" }, /* %bibliocomponent.mix; | bibliomset) */
460{ "biblioset", 0, 0, 0, 9, 0, "" }, /* bibliocomponent.mix */
461{ "blockquote", 0, 0, 0, 9, 0, "" }, /* title */
462{ "book", 0, 0, 0, 9, 0, "" }, /* div.title.content */
463{ "bookinfo", 0, 0, 0, 9, 0, "" }, /* graphic */
464{ "bridgehead", 0, 0, 0, 8, 0, "" }, /* title */
465{ "callout", 0, 0, 0, 9, 0, "" }, /* component.mix */
466{ "calloutlist",0, 0, 0, 9, 0, "" }, /* formalobject.title.content */
467{ "caption", 0, 0, 0, 9, 0, "" }, /* textobject.mix */
468{ "caution", 0, 0, 0, 9, 0, "" }, /* title */
469{ "chapter", 0, 0, 0, 9, 0, "" }, /* chapterinfo */
470{ "chapterinfo",0, 0, 0, 9, 0, "" }, /* graphic */
471{ "citation", 0, 0, 0, 2, 0, "" }, /* para */
472{ "citerefentry",0, 0, 0, 9, 0, "" }, /* refentrytitle */
473{ "citetitle", 0, 0, 0, 2, 0, "" }, /* para */
474{ "city", 0, 0, 0, 4, 0, "" }, /* docinfo */
475{ "classname", 0, 0, 0, 7, 0, "" }, /* smallcptr */
476{ "classsynopsisinfo",0,0, 0, 9, 0, "" }, /* cptr */
477{ "classsynopsis",0, 0, 0, 9, 0, "" }, /* ooclass */
478{ "cmdsynopsis",0, 0, 0, 9, 0, "" }, /* command */
479{ "co", 0, 2, 1, 0, 0, "" },
480{ "collab", 0, 0, 0, 9, 0, "" }, /* collabname */
481{ "collabname", 0, 0, 0, 4, 0, "" }, /* docinfo */
482{ "colophon", 0, 0, 0, 9, 0, "" }, /* sect.title.content */
483{ "colspec", 0, 2, 1, 0, 0, "" },
484{ "colspec", 0, 2, 1, 0, 0, "" },
485{ "command", 0, 0, 0, 9, 0, "" }, /* cptr */
486{ "computeroutput",0, 0, 0, 9, 0, "" }, /* cptr */
487{ "confdates", 0, 0, 0, 4, 0, "" }, /* docinfo */
488{ "confgroup", 0, 0, 0, 9, 0, "" }, /* confdates */
489{ "confnum", 0, 0, 0, 4, 0, "" }, /* docinfo */
490{ "confsponsor",0, 0, 0, 4, 0, "" }, /* docinfo */
491{ "conftitle", 0, 0, 0, 4, 0, "" }, /* docinfo */
492{ "constant", 0, 0, 0, 7, 0, "" }, /* smallcptr */
493{ "constructorsynopsis",0,0, 0, 9, 0, "" }, /* modifier */
494{ "contractnum",0, 0, 0, 4, 0, "" }, /* docinfo */
495{ "contractsponsor",0, 0, 0, 4, 0, "" }, /* docinfo */
496{ "contrib", 0, 0, 0, 4, 0, "" }, /* docinfo */
497{ "copyright", 0, 0, 0, 9, 0, "" }, /* year */
498{ "corpauthor", 0, 0, 0, 4, 0, "" }, /* docinfo */
499{ "corpname", 0, 0, 0, 4, 0, "" }, /* docinfo */
500{ "country", 0, 0, 0, 4, 0, "" }, /* docinfo */
501{ "database", 0, 0, 0, 7, 0, "" }, /* smallcptr */
502{ "date", 0, 0, 0, 4, 0, "" }, /* docinfo */
503{ "dedication", 0, 0, 0, 9, 0, "" }, /* sect.title.content */
504{ "destructorsynopsis",0,0, 0, 9, 0, "" }, /* modifier */
505{ "edition", 0, 0, 0, 4, 0, "" }, /* docinfo */
506{ "editor", 0, 0, 0, 9, 0, "" }, /* person.ident.mix */
507{ "email", 0, 0, 0, 4, 0, "" }, /* docinfo */
508{ "emphasis", 0, 0, 0, 2, 0, "" }, /* para */
509{ "entry", 0, 0, 0, 9, 0, "" }, /* tbl.entry.mdl */
510{ "entrytbl", 0, 0, 0, 9, 0, "" }, /* tbl.entrytbl.mdl */
511{ "envar", 0, 0, 0, 7, 0, "" }, /* smallcptr */
512{ "epigraph", 0, 0, 0, 9, 0, "" }, /* attribution */
513{ "equation", 0, 0, 0, 9, 0, "" }, /* formalobject.title.content */
514{ "errorcode", 0, 0, 0, 7, 0, "" }, /* smallcptr */
515{ "errorname", 0, 0, 0, 7, 0, "" }, /* smallcptr */
516{ "errortype", 0, 0, 0, 7, 0, "" }, /* smallcptr */
517{ "example", 0, 0, 0, 9, 0, "" }, /* formalobject.title.content */
518{ "exceptionname",0, 0, 0, 7, 0, "" }, /* smallcptr */
519{ "fax", 0, 0, 0, 4, 0, "" }, /* docinfo */
520{ "fieldsynopsis", 0, 0, 0, 9, 0, "" }, /* modifier */
521{ "figure", 0, 0, 0, 9, 0, "" }, /* formalobject.title.content */
522{ "filename", 0, 0, 0, 7, 0, "" }, /* smallcptr */
523{ "firstname", 0, 0, 0, 4, 0, "" }, /* docinfo */
524{ "firstterm", 0, 0, 0, 3, 0, "" }, /* word */
525{ "footnote", 0, 0, 0, 9, 0, "" }, /* footnote.mix */
526{ "footnoteref",0, 2, 1, 0, 0, "" },
527{ "foreignphrase",0, 0, 0, 2, 0, "" }, /* para */
528{ "formalpara", 0, 0, 0, 9, 0, "" }, /* title */
529{ "funcdef", 0, 0, 0, 1, 0, "" },
530{ "funcparams", 0, 0, 0, 9, 0, "" }, /* cptr */
531{ "funcprototype",0, 0, 0, 9, 0, "" }, /* funcdef */
532{ "funcsynopsis",0, 0, 0, 9, 0, "" }, /* funcsynopsisinfo */
533{ "funcsynopsisinfo", 0, 0, 0, 9, 0, "" }, /* cptr */
534{ "function", 0, 0, 0, 9, 0, "" }, /* cptr */
535{ "glossary", 0, 0, 0, 9, 0, "" }, /* glossaryinfo */
536{ "glossaryinfo",0, 0, 0, 9, 0, "" }, /* graphic */
537{ "glossdef", 0, 0, 0, 9, 0, "" }, /* glossdef.mix */
538{ "glossdiv", 0, 0, 0, 9, 0, "" }, /* sect.title.content */
539{ "glossentry", 0, 0, 0, 9, 0, "" }, /* glossterm */
540{ "glosslist", 0, 0, 0, 9, 0, "" }, /* glossentry */
541{ "glossseealso",0, 0, 0, 2, 0, "" }, /* para */
542{ "glosssee", 0, 0, 0, 2, 0, "" }, /* para */
543{ "glossterm", 0, 0, 0, 2, 0, "" }, /* para */
Daniel Veillard4ec0b0f2001-04-25 15:53:40 +0000[diff] [blame^]544{ "graphic", 0, 0, 0, 9, 0, "" },
Daniel Veillardeae522a2001-04-23 13:41:34 +0000[diff] [blame]545{ "graphicco", 0, 0, 0, 9, 0, "" }, /* areaspec */
546{ "group", 0, 0, 0, 9, 0, "" }, /* arg */
547{ "guibutton", 0, 0, 0, 7, 0, "" }, /* smallcptr */
548{ "guiicon", 0, 0, 0, 7, 0, "" }, /* smallcptr */
549{ "guilabel", 0, 0, 0, 7, 0, "" }, /* smallcptr */
550{ "guimenuitem",0, 0, 0, 7, 0, "" }, /* smallcptr */
551{ "guimenu", 0, 0, 0, 7, 0, "" }, /* smallcptr */
552{ "guisubmenu", 0, 0, 0, 7, 0, "" }, /* smallcptr */
553{ "hardware", 0, 0, 0, 7, 0, "" }, /* smallcptr */
554{ "highlights", 0, 0, 0, 9, 0, "" }, /* highlights.mix */
555{ "holder", 0, 0, 0, 4, 0, "" }, /* docinfo */
556{ "honorific", 0, 0, 0, 4, 0, "" }, /* docinfo */
557{ "imagedata", 0, 2, 1, 0, 0, "" },
558{ "imageobjectco",0, 0, 0, 9, 0, "" }, /* areaspec */
559{ "imageobject",0, 0, 0, 9, 0, "" }, /* objectinfo */
560{ "important", 0, 0, 0, 9, 0, "" }, /* title */
561{ "indexdiv", 0, 0, 0, 9, 0, "" }, /* sect.title.content */
562{ "indexentry", 0, 0, 0, 9, 0, "" }, /* primaryie */
563{ "index", 0, 0, 0, 9, 0, "" }, /* indexinfo */
564{ "indexinfo", 0, 0, 0, 9, 0, "" }, /* graphic */
565{ "indexterm", 0, 0, 0, 9, 0, "" }, /* primary */
566{ "informalequation",0, 0, 0, 9, 0, "" }, /* equation.content */
567{ "informalexample",0, 0, 0, 9, 0, "" }, /* example.mix */
568{ "informalfigure",0, 0, 0, 9, 0, "" }, /* figure.mix */
569{ "informaltable",0, 0, 0, 9, 0, "" }, /* graphic */
570{ "initializer",0, 0, 0, 7, 0, "" }, /* smallcptr */
571{ "inlineequation",0, 0, 0, 9, 0, "" }, /* inlineequation.content */
572{ "inlinegraphic",0, 2, 1, 0, 0, "" },
573{ "inlinemediaobject",0,0, 0, 9, 0, "" }, /* objectinfo */
574{ "interfacename",0, 0, 0, 7, 0, "" }, /* smallcptr */
575{ "interface", 0, 0, 0, 7, 0, "" }, /* smallcptr */
576{ "invpartnumber",0, 0, 0, 4, 0, "" }, /* docinfo */
577{ "isbn", 0, 0, 0, 4, 0, "" }, /* docinfo */
578{ "issn", 0, 0, 0, 4, 0, "" }, /* docinfo */
579{ "issuenum", 0, 0, 0, 4, 0, "" }, /* docinfo */
580{ "itemizedlist",0, 0, 0, 9, 0, "" }, /* formalobject.title.content */
581{ "itermset", 0, 0, 0, 9, 0, "" }, /* indexterm */
582{ "jobtitle", 0, 0, 0, 4, 0, "" }, /* docinfo */
583{ "keycap", 0, 0, 0, 7, 0, "" }, /* smallcptr */
584{ "keycode", 0, 0, 0, 7, 0, "" }, /* smallcptr */
585{ "keycombo", 0, 0, 0, 9, 0, "" }, /* keycap */
586{ "keysym", 0, 0, 0, 7, 0, "" }, /* smallcptr */
587{ "keyword", 0, 0, 0, 1, 0, "" },
588{ "keywordset", 0, 0, 0, 9, 0, "" }, /* keyword */
589{ "label", 0, 0, 0, 3, 0, "" }, /* word */
590{ "legalnotice",0, 0, 0, 9, 0, "" }, /* title */
591{ "lineage", 0, 0, 0, 4, 0, "" }, /* docinfo */
592{ "lineannotation",0, 0, 0, 2, 0, "" }, /* para */
593{ "link", 0, 0, 0, 2, 0, "" }, /* para */
594{ "listitem", 0, 0, 0, 9, 0, "" }, /* component.mix */
595{ "literal", 0, 0, 0, 9, 0, "" }, /* cptr */
596{ "literallayout",0, 0, 0, 2, 0, "" }, /* para */
597{ "lot", 0, 0, 0, 9, 0, "" }, /* bookcomponent.title.content */
598{ "lotentry", 0, 0, 0, 2, 0, "" }, /* para */
599{ "manvolnum", 0, 0, 0, 3, 0, "" }, /* word */
600{ "markup", 0, 0, 0, 7, 0, "" }, /* smallcptr */
601{ "medialabel", 0, 0, 0, 7, 0, "" }, /* smallcptr */
602{ "mediaobjectco",0, 0, 0, 9, 0, "" }, /* objectinfo */
603{ "mediaobject",0, 0, 0, 9, 0, "" }, /* objectinfo */
604{ "member", 0, 0, 0, 2, 0, "" }, /* para */
605{ "menuchoice", 0, 0, 0, 9, 0, "" }, /* shortcut */
606{ "methodname", 0, 0, 0, 7, 0, "" }, /* smallcptr */
607{ "methodparam",0, 0, 0, 9, 0, "" }, /* modifier */
608{ "methodsynopsis",0, 0, 0, 9, 0, "" }, /* modifier */
609{ "modespec", 0, 0, 0, 4, 0, "" }, /* docinfo */
610{ "modifier", 0, 0, 0, 7, 0, "" }, /* smallcptr */
611{ "mousebutton",0, 0, 0, 7, 0, "" }, /* smallcptr */
612{ "msgaud", 0, 0, 0, 2, 0, "" }, /* para */
613{ "msgentry", 0, 0, 0, 9, 0, "" }, /* msg */
614{ "msgexplan", 0, 0, 0, 9, 0, "" }, /* title */
615{ "msginfo", 0, 0, 0, 9, 0, "" }, /* msglevel */
616{ "msglevel", 0, 0, 0, 7, 0, "" }, /* smallcptr */
617{ "msgmain", 0, 0, 0, 9, 0, "" }, /* title */
618{ "msgorig", 0, 0, 0, 7, 0, "" }, /* smallcptr */
619{ "msgrel", 0, 0, 0, 9, 0, "" }, /* title */
620{ "msgset", 0, 0, 0, 9, 0, "" }, /* formalobject.title.content */
621{ "msgsub", 0, 0, 0, 9, 0, "" }, /* title */
622{ "msgtext", 0, 0, 0, 9, 0, "" }, /* component.mix */
623{ "msg", 0, 0, 0, 9, 0, "" }, /* title */
624{ "note", 0, 0, 0, 9, 0, "" }, /* title */
625{ "objectinfo", 0, 0, 0, 9, 0, "" }, /* graphic */
626{ "olink", 0, 0, 0, 2, 0, "" }, /* para */
627{ "ooclass", 0, 0, 0, 9, 0, "" }, /* modifier */
628{ "ooexception",0, 0, 0, 9, 0, "" }, /* modifier */
629{ "oointerface",0, 0, 0, 9, 0, "" }, /* modifier */
630{ "optional", 0, 0, 0, 9, 0, "" }, /* cptr */
631{ "option", 0, 0, 0, 7, 0, "" }, /* smallcptr */
632{ "orderedlist",0, 0, 0, 9, 0, "" }, /* formalobject.title.content */
633{ "orgdiv", 0, 0, 0, 4, 0, "" }, /* docinfo */
634{ "orgname", 0, 0, 0, 4, 0, "" }, /* docinfo */
635{ "otheraddr", 0, 0, 0, 4, 0, "" }, /* docinfo */
636{ "othercredit",0, 0, 0, 9, 0, "" }, /* person.ident.mix */
637{ "othername", 0, 0, 0, 4, 0, "" }, /* docinfo */
638{ "pagenums", 0, 0, 0, 4, 0, "" }, /* docinfo */
639{ "paramdef", 0, 0, 0, 1, 0, "" },
640{ "parameter", 0, 0, 0, 7, 0, "" }, /* smallcptr */
641{ "para", 0, 0, 0, 2, 0, "" }, /* para */
642{ "partinfo", 0, 0, 0, 9, 0, "" }, /* graphic */
643{ "partintro", 0, 0, 0, 9, 0, "" }, /* div.title.content */
644{ "part", 0, 0, 0, 9, 0, "" }, /* partinfo */
645{ "phone", 0, 0, 0, 4, 0, "" }, /* docinfo */
646{ "phrase", 0, 0, 0, 2, 0, "" }, /* para */
647{ "pob", 0, 0, 0, 4, 0, "" }, /* docinfo */
648{ "postcode", 0, 0, 0, 4, 0, "" }, /* docinfo */
649{ "prefaceinfo",0, 0, 0, 9, 0, "" }, /* graphic */
650{ "preface", 0, 0, 0, 9, 0, "" }, /* prefaceinfo */
651{ "primaryie", 0, 0, 0, 4, 0, "" }, /* ndxterm */
652{ "primary ", 0, 0, 0, 4, 0, "" }, /* ndxterm */
653{ "printhistory",0, 0, 0, 9, 0, "" }, /* para.class */
654{ "procedure", 0, 0, 0, 9, 0, "" }, /* formalobject.title.content */
655{ "productname",0, 0, 0, 2, 0, "" }, /* para */
656{ "productnumber",0, 0, 0, 4, 0, "" }, /* docinfo */
657{ "programlistingco",0, 0, 0, 9, 0, "" }, /* areaspec */
658{ "programlisting",0, 0, 0, 2, 0, "" }, /* para */
659{ "prompt", 0, 0, 0, 7, 0, "" }, /* smallcptr */
660{ "property", 0, 0, 0, 7, 0, "" }, /* smallcptr */
661{ "pubdate", 0, 0, 0, 4, 0, "" }, /* docinfo */
662{ "publishername",0, 0, 0, 4, 0, "" }, /* docinfo */
663{ "publisher", 0, 0, 0, 9, 0, "" }, /* publishername */
664{ "pubsnumber", 0, 0, 0, 4, 0, "" }, /* docinfo */
665{ "qandadiv", 0, 0, 0, 9, 0, "" }, /* formalobject.title.content */
666{ "qandaentry", 0, 0, 0, 9, 0, "" }, /* revhistory */
667{ "qandaset", 0, 0, 0, 9, 0, "" }, /* formalobject.title.content */
668{ "question", 0, 0, 0, 9, 0, "" }, /* label */
669{ "quote", 0, 0, 0, 2, 0, "" }, /* para */
670{ "refclass", 0, 0, 0, 9, 0, "" }, /* refclass.char.mix */
671{ "refdescriptor",0, 0, 0, 9, 0, "" }, /* refname.char.mix */
672{ "refentryinfo",0, 0, 0, 9, 0, "" }, /* graphic */
673{ "refentry", 0, 0, 0, 9, 0, "" }, /* ndxterm.class */
674{ "refentrytitle",0, 0, 0, 2, 0, "" }, /* para */
675{ "referenceinfo",0, 0, 0, 9, 0, "" }, /* graphic */
676{ "reference", 0, 0, 0, 9, 0, "" }, /* referenceinfo */
677{ "refmeta", 0, 0, 0, 9, 0, "" }, /* ndxterm.class */
678{ "refmiscinfo",0, 0, 0, 4, 0, "" }, /* docinfo */
679{ "refnamediv", 0, 0, 0, 9, 0, "" }, /* refdescriptor */
680{ "refname", 0, 0, 0, 9, 0, "" }, /* refname.char.mix */
681{ "refpurpose", 0, 0, 0, 9, 0, "" }, /* refinline.char.mix */
682{ "refsect1info",0, 0, 0, 9, 0, "" }, /* graphic */
683{ "refsect1", 0, 0, 0, 9, 0, "" }, /* refsect */
684{ "refsect2info",0, 0, 0, 9, 0, "" }, /* graphic */
685{ "refsect2", 0, 0, 0, 9, 0, "" }, /* refsect */
686{ "refsect3info",0, 0, 0, 9, 0, "" }, /* graphic */
687{ "refsect3", 0, 0, 0, 9, 0, "" }, /* refsect */
688{ "refsynopsisdivinfo",0,0, 0, 9, 0, "" }, /* graphic */
689{ "refsynopsisdiv",0, 0, 0, 9, 0, "" }, /* refsynopsisdivinfo */
690{ "releaseinfo",0, 0, 0, 4, 0, "" }, /* docinfo */
691{ "remark", 0, 0, 0, 2, 0, "" }, /* para */
692{ "replaceable",0, 0, 0, 1, 0, "" },
693{ "returnvalue",0, 0, 0, 7, 0, "" }, /* smallcptr */
694{ "revdescription",0, 0, 0, 9, 0, "" }, /* revdescription.mix */
695{ "revhistory", 0, 0, 0, 9, 0, "" }, /* revision */
696{ "revision", 0, 0, 0, 9, 0, "" }, /* revnumber */
697{ "revnumber", 0, 0, 0, 4, 0, "" }, /* docinfo */
698{ "revremark", 0, 0, 0, 4, 0, "" }, /* docinfo */
699{ "row", 0, 0, 0, 9, 0, "" }, /* tbl.row.mdl */
700{ "row", 0, 0, 0, 9, 0, "" }, /* tbl.row.mdl */
701{ "sbr", 0, 2, 1, 0, 0, "" },
702{ "screenco", 0, 0, 0, 9, 0, "" }, /* areaspec */
703{ "screeninfo", 0, 0, 0, 2, 0, "" }, /* para */
704{ "screen", 0, 0, 0, 2, 0, "" }, /* para */
705{ "screenshot", 0, 0, 0, 9, 0, "" }, /* screeninfo */
706{ "secondaryie",0, 0, 0, 4, 0, "" }, /* ndxterm */
707{ "secondary", 0, 0, 0, 4, 0, "" }, /* ndxterm */
708{ "sect1info", 0, 0, 0, 9, 0, "" }, /* graphic */
709{ "sect1", 0, 0, 0, 9, 0, "" }, /* sect */
710{ "sect2info", 0, 0, 0, 9, 0, "" }, /* graphic */
711{ "sect2", 0, 0, 0, 9, 0, "" }, /* sect */
712{ "sect3info", 0, 0, 0, 9, 0, "" }, /* graphic */
713{ "sect3", 0, 0, 0, 9, 0, "" }, /* sect */
714{ "sect4info", 0, 0, 0, 9, 0, "" }, /* graphic */
715{ "sect4", 0, 0, 0, 9, 0, "" }, /* sect */
716{ "sect5info", 0, 0, 0, 9, 0, "" }, /* graphic */
717{ "sect5", 0, 0, 0, 9, 0, "" }, /* sect */
718{ "sectioninfo",0, 0, 0, 9, 0, "" }, /* graphic */
719{ "section", 0, 0, 0, 9, 0, "" }, /* sectioninfo */
720{ "seealsoie", 0, 0, 0, 4, 0, "" }, /* ndxterm */
721{ "seealso", 0, 0, 0, 4, 0, "" }, /* ndxterm */
722{ "seeie", 0, 0, 0, 4, 0, "" }, /* ndxterm */
723{ "see", 0, 0, 0, 4, 0, "" }, /* ndxterm */
724{ "seglistitem",0, 0, 0, 9, 0, "" }, /* seg */
725{ "segmentedlist",0, 0, 0, 9, 0, "" }, /* formalobject.title.content */
726{ "seg", 0, 0, 0, 2, 0, "" }, /* para */
727{ "segtitle", 0, 0, 0, 8, 0, "" }, /* title */
728{ "seriesvolnums", 0, 0, 0, 4, 0, "" }, /* docinfo */
729{ "set", 0, 0, 0, 9, 0, "" }, /* div.title.content */
730{ "setindexinfo",0, 0, 0, 9, 0, "" }, /* graphic */
731{ "setindex", 0, 0, 0, 9, 0, "" }, /* setindexinfo */
732{ "setinfo", 0, 0, 0, 9, 0, "" }, /* graphic */
733{ "sgmltag", 0, 0, 0, 7, 0, "" }, /* smallcptr */
734{ "shortaffil", 0, 0, 0, 4, 0, "" }, /* docinfo */
735{ "shortcut", 0, 0, 0, 9, 0, "" }, /* keycap */
736{ "sidebarinfo",0, 0, 0, 9, 0, "" }, /* graphic */
737{ "sidebar", 0, 0, 0, 9, 0, "" }, /* sidebarinfo */
738{ "simpara", 0, 0, 0, 2, 0, "" }, /* para */
739{ "simplelist", 0, 0, 0, 9, 0, "" }, /* member */
740{ "simplemsgentry", 0, 0, 0, 9, 0, "" }, /* msgtext */
741{ "simplesect", 0, 0, 0, 9, 0, "" }, /* sect.title.content */
742{ "spanspec", 0, 2, 1, 0, 0, "" },
743{ "state", 0, 0, 0, 4, 0, "" }, /* docinfo */
744{ "step", 0, 0, 0, 9, 0, "" }, /* title */
745{ "street", 0, 0, 0, 4, 0, "" }, /* docinfo */
746{ "structfield",0, 0, 0, 7, 0, "" }, /* smallcptr */
747{ "structname", 0, 0, 0, 7, 0, "" }, /* smallcptr */
748{ "subjectset", 0, 0, 0, 9, 0, "" }, /* subject */
749{ "subject", 0, 0, 0, 9, 0, "" }, /* subjectterm */
750{ "subjectterm",0, 0, 0, 1, 0, "" },
751{ "subscript", 0, 0, 0, 1, 0, "" },
752{ "substeps", 0, 0, 0, 9, 0, "" }, /* step */
753{ "subtitle", 0, 0, 0, 8, 0, "" }, /* title */
754{ "superscript", 0, 0, 0, 1, 0, "" },
755{ "surname", 0, 0, 0, 4, 0, "" }, /* docinfo */
756{ "symbol", 0, 0, 0, 7, 0, "" }, /* smallcptr */
757{ "synopfragment", 0, 0, 0, 9, 0, "" }, /* arg */
758{ "synopfragmentref", 0, 0, 0, 1, 0, "" },
759{ "synopsis", 0, 0, 0, 2, 0, "" }, /* para */
760{ "systemitem", 0, 0, 0, 7, 0, "" }, /* smallcptr */
761{ "table", 0, 0, 0, 9, 0, "" }, /* tbl.table.mdl */
762/* { "%tbl.table.name;", 0, 0, 0, 9, 0, "" },*/ /* tbl.table.mdl */
763{ "tbody", 0, 0, 0, 9, 0, "" }, /* row */
764{ "tbody", 0, 0, 0, 9, 0, "" }, /* row */
765{ "term", 0, 0, 0, 2, 0, "" }, /* para */
766{ "tertiaryie", 0, 0, 0, 4, 0, "" }, /* ndxterm */
767{ "tertiary ", 0, 0, 0, 4, 0, "" }, /* ndxterm */
768{ "textobject", 0, 0, 0, 9, 0, "" }, /* objectinfo */
769{ "tfoot", 0, 0, 0, 9, 0, "" }, /* tbl.hdft.mdl */
770{ "tgroup", 0, 0, 0, 9, 0, "" }, /* tbl.tgroup.mdl */
771{ "tgroup", 0, 0, 0, 9, 0, "" }, /* tbl.tgroup.mdl */
772{ "thead", 0, 0, 0, 9, 0, "" }, /* row */
773{ "thead", 0, 0, 0, 9, 0, "" }, /* tbl.hdft.mdl */
774{ "tip", 0, 0, 0, 9, 0, "" }, /* title */
775{ "titleabbrev",0, 0, 0, 8, 0, "" }, /* title */
776{ "title", 0, 0, 0, 8, 0, "" }, /* title */
777{ "tocback", 0, 0, 0, 2, 0, "" }, /* para */
778{ "toc", 0, 0, 0, 9, 0, "" }, /* bookcomponent.title.content */
779{ "tocchap", 0, 0, 0, 9, 0, "" }, /* tocentry */
780{ "tocentry", 0, 0, 0, 2, 0, "" }, /* para */
781{ "tocfront", 0, 0, 0, 2, 0, "" }, /* para */
782{ "toclevel1", 0, 0, 0, 9, 0, "" }, /* tocentry */
783{ "toclevel2", 0, 0, 0, 9, 0, "" }, /* tocentry */
784{ "toclevel3", 0, 0, 0, 9, 0, "" }, /* tocentry */
785{ "toclevel4", 0, 0, 0, 9, 0, "" }, /* tocentry */
786{ "toclevel5", 0, 0, 0, 9, 0, "" }, /* tocentry */
787{ "tocpart", 0, 0, 0, 9, 0, "" }, /* tocentry */
788{ "token", 0, 0, 0, 7, 0, "" }, /* smallcptr */
789{ "trademark", 0, 0, 0, 1, 0, "" },
790{ "type", 0, 0, 0, 7, 0, "" }, /* smallcptr */
791{ "ulink", 0, 0, 0, 2, 0, "" }, /* para */
792{ "userinput", 0, 0, 0, 9, 0, "" }, /* cptr */
793{ "varargs", 0, 2, 1, 0, 0, "" },
794{ "variablelist",0, 0, 0, 9, 0, "" }, /* formalobject.title.content */
795{ "varlistentry",0, 0, 0, 9, 0, "" }, /* term */
796{ "varname", 0, 0, 0, 7, 0, "" }, /* smallcptr */
797{ "videodata", 0, 2, 1, 0, 0, "" },
798{ "videoobject",0, 0, 0, 9, 0, "" }, /* objectinfo */
799{ "void", 0, 2, 1, 0, 0, "" },
800{ "volumenum", 0, 0, 0, 4, 0, "" }, /* docinfo */
801{ "warning", 0, 0, 0, 9, 0, "" }, /* title */
802{ "wordasword", 0, 0, 0, 3, 0, "" }, /* word */
803{ "xref", 0, 2, 1, 0, 0, "" },
804{ "year", 0, 0, 0, 4, 0, "" }, /* docinfo */
805};
806
807#if 0
808/*
809 * start tags that imply the end of a current element
810 * any tag of each line implies the end of the current element if the type of
811 * that element is in the same line
812 */
813static const char *docbEquEnd[] = {
814"dt", "dd", "li", "option", NULL,
815"h1", "h2", "h3", "h4", "h5", "h6", NULL,
816"ol", "menu", "dir", "address", "pre", "listing", "xmp", NULL,
817NULL
818};
819#endif
820
821/*
822 * acording the SGML DTD, HR should be added to the 2nd line above, as it
823 * is not allowed within a H1, H2, H3, etc. But we should tolerate that case
824 * because many documents contain rules in headings...
825 */
826
827/*
828 * start tags that imply the end of current element
829 */
830static const char *docbStartClose[] = {
831NULL
832};
833
834/*
835 * The list of SGML elements which are supposed not to have
836 * CDATA content and where a p element will be implied
837 *
838 * TODO: extend that list by reading the SGML SGML DtD on
839 * implied paragraph
840 */
841static char *docbNoContentElements[] = {
842 NULL
843};
844
845
846static const char** docbStartCloseIndex[100];
847static int docbStartCloseIndexinitialized = 0;
848
849/************************************************************************
850 * *
851 * functions to handle SGML specific data *
852 * *
853 ************************************************************************/
854
855/**
856 * docbInitAutoClose:
857 *
858 * Initialize the docbStartCloseIndex for fast lookup of closing tags names.
859 *
860 */
861static void
862docbInitAutoClose(void) {
863 int indx, i = 0;
864
865 if (docbStartCloseIndexinitialized) return;
866
867 for (indx = 0;indx < 100;indx ++) docbStartCloseIndex[indx] = NULL;
868 indx = 0;
869 while ((docbStartClose[i] != NULL) && (indx < 100 - 1)) {
870 docbStartCloseIndex[indx++] = &docbStartClose[i];
871 while (docbStartClose[i] != NULL) i++;
872 i++;
873 }
874}
875
876/**
877 * docbTagLookup:
878 * @tag: The tag name
879 *
880 * Lookup the SGML tag in the ElementTable
881 *
882 * Returns the related docbElemDescPtr or NULL if not found.
883 */
884static docbElemDescPtr
885docbTagLookup(const xmlChar *tag) {
886 unsigned int i;
887
888 for (i = 0; i < (sizeof(docbookElementTable) /
889 sizeof(docbookElementTable[0]));i++) {
890 if (xmlStrEqual(tag, BAD_CAST docbookElementTable[i].name))
891 return(&docbookElementTable[i]);
892 }
893 return(NULL);
894}
895
896/**
897 * docbCheckAutoClose:
898 * @newtag: The new tag name
899 * @oldtag: The old tag name
900 *
901 * Checks wether the new tag is one of the registered valid tags for closing old.
902 * Initialize the docbStartCloseIndex for fast lookup of closing tags names.
903 *
904 * Returns 0 if no, 1 if yes.
905 */
906static int
907docbCheckAutoClose(const xmlChar *newtag, const xmlChar *oldtag) {
908 int i, indx;
909 const char **closed = NULL;
910
911 if (docbStartCloseIndexinitialized == 0) docbInitAutoClose();
912
913 /* inefficient, but not a big deal */
914 for (indx = 0; indx < 100;indx++) {
915 closed = docbStartCloseIndex[indx];
916 if (closed == NULL) return(0);
917 if (xmlStrEqual(BAD_CAST *closed, newtag)) break;
918 }
919
920 i = closed - docbStartClose;
921 i++;
922 while (docbStartClose[i] != NULL) {
923 if (xmlStrEqual(BAD_CAST docbStartClose[i], oldtag)) {
924 return(1);
925 }
926 i++;
927 }
928 return(0);
929}
930
931/**
932 * docbAutoCloseOnClose:
933 * @ctxt: an SGML parser context
934 * @newtag: The new tag name
935 *
936 * The HTmL DtD allows an ending tag to implicitely close other tags.
937 */
938static void
939docbAutoCloseOnClose(docbParserCtxtPtr ctxt, const xmlChar *newtag) {
940 docbElemDescPtr info;
941 xmlChar *oldname;
942 int i;
943
944 if ((newtag[0] == '/') && (newtag[1] == 0))
945 return;
946
947#ifdef DEBUG
948 xmlGenericError(xmlGenericErrorContext,"Close of %s stack: %d elements\n", newtag, ctxt->nameNr);
949 for (i = 0;i < ctxt->nameNr;i++)
950 xmlGenericError(xmlGenericErrorContext,"%d : %s\n", i, ctxt->nameTab[i]);
951#endif
952
953 for (i = (ctxt->nameNr - 1);i >= 0;i--) {
954 if (xmlStrEqual(newtag, ctxt->nameTab[i])) break;
955 }
956 if (i < 0) return;
957
958 while (!xmlStrEqual(newtag, ctxt->name)) {
959 info = docbTagLookup(ctxt->name);
960 if ((info == NULL) || (info->endTag == 1)) {
961#ifdef DEBUG
962 xmlGenericError(xmlGenericErrorContext,"docbAutoCloseOnClose: %s closes %s\n", newtag, ctxt->name);
963#endif
964 } else {
965 if ((ctxt->sax != NULL) && (ctxt->sax->error != NULL))
966 ctxt->sax->error(ctxt->userData,
967 "Opening and ending tag mismatch: %s and %s\n",
968 newtag, ctxt->name);
969 ctxt->wellFormed = 0;
970 }
971 if ((ctxt->sax != NULL) && (ctxt->sax->endElement != NULL))
972 ctxt->sax->endElement(ctxt->userData, ctxt->name);
973 oldname = docbnamePop(ctxt);
974 if (oldname != NULL) {
975#ifdef DEBUG
976 xmlGenericError(xmlGenericErrorContext,"docbAutoCloseOnClose: popped %s\n", oldname);
977#endif
978 xmlFree(oldname);
979 }
980 }
981}
982
983/**
984 * docbAutoClose:
985 * @ctxt: an SGML parser context
986 * @newtag: The new tag name or NULL
987 *
988 * The HTmL DtD allows a tag to implicitely close other tags.
989 * The list is kept in docbStartClose array. This function is
990 * called when a new tag has been detected and generates the
991 * appropriates closes if possible/needed.
992 * If newtag is NULL this mean we are at the end of the resource
993 * and we should check
994 */
995static void
996docbAutoClose(docbParserCtxtPtr ctxt, const xmlChar *newtag) {
997 xmlChar *oldname;
998 while ((newtag != NULL) && (ctxt->name != NULL) &&
999 (docbCheckAutoClose(newtag, ctxt->name))) {
1000#ifdef DEBUG
1001 xmlGenericError(xmlGenericErrorContext,"docbAutoClose: %s closes %s\n", newtag, ctxt->name);
1002#endif
1003 if ((ctxt->sax != NULL) && (ctxt->sax->endElement != NULL))
1004 ctxt->sax->endElement(ctxt->userData, ctxt->name);
1005 oldname = docbnamePop(ctxt);
1006 if (oldname != NULL) {
1007#ifdef DEBUG
1008 xmlGenericError(xmlGenericErrorContext,"docbAutoClose: popped %s\n", oldname);
1009#endif
1010 xmlFree(oldname);
1011 }
1012 }
1013}
1014
1015/**
1016 * docbAutoCloseTag:
1017 * @doc: the SGML document
1018 * @name: The tag name
1019 * @elem: the SGML element
1020 *
1021 * The HTmL DtD allows a tag to implicitely close other tags.
1022 * The list is kept in docbStartClose array. This function checks
1023 * if the element or one of it's children would autoclose the
1024 * given tag.
1025 *
1026 * Returns 1 if autoclose, 0 otherwise
1027 */
1028static int
1029docbAutoCloseTag(docbDocPtr doc, const xmlChar *name, docbNodePtr elem) {
1030 docbNodePtr child;
1031
1032 if (elem == NULL) return(1);
1033 if (xmlStrEqual(name, elem->name)) return(0);
1034 if (docbCheckAutoClose(elem->name, name)) return(1);
1035 child = elem->children;
1036 while (child != NULL) {
1037 if (docbAutoCloseTag(doc, name, child)) return(1);
1038 child = child->next;
1039 }
1040 return(0);
1041}
1042
1043#if 0
1044/**
1045 * docbIsAutoClosed:
1046 * @doc: the SGML document
1047 * @elem: the SGML element
1048 *
1049 * The list is kept in docbStartClose array. This function checks
1050 * if a tag is autoclosed by one of it's child
1051 *
1052 * Returns 1 if autoclosed, 0 otherwise
1053 */
1054static int
1055docbIsAutoClosed(docbDocPtr doc, docbNodePtr elem) {
1056 docbNodePtr child;
1057
1058 if (elem == NULL) return(1);
1059 child = elem->children;
1060 while (child != NULL) {
1061 if (docbAutoCloseTag(doc, elem->name, child)) return(1);
1062 child = child->next;
1063 }
1064 return(0);
1065}
1066#endif
1067
1068/**
1069 * docbCheckParagraph
1070 * @ctxt: an SGML parser context
1071 *
1072 * Check whether a p element need to be implied before inserting
1073 * characters in the current element.
1074 *
1075 * Returns 1 if a paragraph has been inserted, 0 if not and -1
1076 * in case of error.
1077 */
1078
1079static int
1080docbCheckParagraph(docbParserCtxtPtr ctxt) {
1081 const xmlChar *tag;
1082 int i;
1083
1084 if (ctxt == NULL)
1085 return(-1);
1086 tag = ctxt->name;
1087 if (tag == NULL) {
1088 docbAutoClose(ctxt, BAD_CAST"p");
1089 docbnamePush(ctxt, xmlStrdup(BAD_CAST"p"));
1090 if ((ctxt->sax != NULL) && (ctxt->sax->startElement != NULL))
1091 ctxt->sax->startElement(ctxt->userData, BAD_CAST"p", NULL);
1092 return(1);
1093 }
1094 for (i = 0; docbNoContentElements[i] != NULL; i++) {
1095 if (xmlStrEqual(tag, BAD_CAST docbNoContentElements[i])) {
1096#ifdef DEBUG
1097 xmlGenericError(xmlGenericErrorContext,"Implied element paragraph\n");
1098#endif
1099 docbAutoClose(ctxt, BAD_CAST"p");
1100 docbnamePush(ctxt, xmlStrdup(BAD_CAST"p"));
1101 if ((ctxt->sax != NULL) && (ctxt->sax->startElement != NULL))
1102 ctxt->sax->startElement(ctxt->userData, BAD_CAST"p", NULL);
1103 return(1);
1104 }
1105 }
1106 return(0);
1107}
1108
1109/************************************************************************
1110 * *
1111 * The list of SGML predefined entities *
1112 * *
1113 ************************************************************************/
1114
1115
1116static docbEntityDesc
1117docbookEntitiesTable[] = {
1118/*
1119 * the 4 absolute ones, plus apostrophe.
1120 */
1121{ 0x0026, "amp", "AMPERSAND" },
1122{ 0x003C, "lt", "LESS-THAN SIGN" },
1123
1124/*
1125 * Converted with VI macros from docbook ent files
1126 */
1127{ 0x0021, "excl", "EXCLAMATION MARK" },
1128{ 0x0022, "quot", "QUOTATION MARK" },
1129{ 0x0023, "num", "NUMBER SIGN" },
1130{ 0x0024, "dollar", "DOLLAR SIGN" },
1131{ 0x0025, "percnt", "PERCENT SIGN" },
1132{ 0x0027, "apos", "APOSTROPHE" },
1133{ 0x0028, "lpar", "LEFT PARENTHESIS" },
1134{ 0x0029, "rpar", "RIGHT PARENTHESIS" },
1135{ 0x002A, "ast", "ASTERISK OPERATOR" },
1136{ 0x002B, "plus", "PLUS SIGN" },
1137{ 0x002C, "comma", "COMMA" },
1138{ 0x002D, "hyphen", "HYPHEN-MINUS" },
1139{ 0x002E, "period", "FULL STOP" },
1140{ 0x002F, "sol", "SOLIDUS" },
1141{ 0x003A, "colon", "COLON" },
1142{ 0x003B, "semi", "SEMICOLON" },
1143{ 0x003D, "equals", "EQUALS SIGN" },
1144{ 0x003E, "gt", "GREATER-THAN SIGN" },
1145{ 0x003F, "quest", "QUESTION MARK" },
1146{ 0x0040, "commat", "COMMERCIAL AT" },
1147{ 0x005B, "lsqb", "LEFT SQUARE BRACKET" },
1148{ 0x005C, "bsol", "REVERSE SOLIDUS" },
1149{ 0x005D, "rsqb", "RIGHT SQUARE BRACKET" },
1150{ 0x005E, "circ", "RING OPERATOR" },
1151{ 0x005F, "lowbar", "LOW LINE" },
1152{ 0x0060, "grave", "GRAVE ACCENT" },
1153{ 0x007B, "lcub", "LEFT CURLY BRACKET" },
1154{ 0x007C, "verbar", "VERTICAL LINE" },
1155{ 0x007D, "rcub", "RIGHT CURLY BRACKET" },
1156{ 0x00A0, "nbsp", "NO-BREAK SPACE" },
1157{ 0x00A1, "iexcl", "INVERTED EXCLAMATION MARK" },
1158{ 0x00A2, "cent", "CENT SIGN" },
1159{ 0x00A3, "pound", "POUND SIGN" },
1160{ 0x00A4, "curren", "CURRENCY SIGN" },
1161{ 0x00A5, "yen", "YEN SIGN" },
1162{ 0x00A6, "brvbar", "BROKEN BAR" },
1163{ 0x00A7, "sect", "SECTION SIGN" },
1164{ 0x00A8, "die", "" },
1165{ 0x00A8, "Dot", "" },
1166{ 0x00A8, "uml", "" },
1167{ 0x00A9, "copy", "COPYRIGHT SIGN" },
1168{ 0x00AA, "ordf", "FEMININE ORDINAL INDICATOR" },
1169{ 0x00AB, "laquo", "LEFT-POINTING DOUBLE ANGLE QUOTATION MARK" },
1170{ 0x00AC, "not", "NOT SIGN" },
1171{ 0x00AD, "shy", "SOFT HYPHEN" },
1172{ 0x00AE, "reg", "REG TRADE MARK SIGN" },
1173{ 0x00AF, "macr", "MACRON" },
1174{ 0x00B0, "deg", "DEGREE SIGN" },
1175{ 0x00B1, "plusmn", "PLUS-MINUS SIGN" },
1176{ 0x00B2, "sup2", "SUPERSCRIPT TWO" },
1177{ 0x00B3, "sup3", "SUPERSCRIPT THREE" },
1178{ 0x00B4, "acute", "ACUTE ACCENT" },
1179{ 0x00B5, "micro", "MICRO SIGN" },
1180{ 0x00B6, "para", "PILCROW SIGN" },
1181{ 0x00B7, "middot", "MIDDLE DOT" },
1182{ 0x00B8, "cedil", "CEDILLA" },
1183{ 0x00B9, "sup1", "SUPERSCRIPT ONE" },
1184{ 0x00BA, "ordm", "MASCULINE ORDINAL INDICATOR" },
1185{ 0x00BB, "raquo", "RIGHT-POINTING DOUBLE ANGLE QUOTATION MARK" },
1186{ 0x00BC, "frac14", "VULGAR FRACTION ONE QUARTER" },
1187{ 0x00BD, "frac12", "VULGAR FRACTION ONE HALF" },
1188{ 0x00BD, "half", "VULGAR FRACTION ONE HALF" },
1189{ 0x00BE, "frac34", "VULGAR FRACTION THREE QUARTERS" },
1190{ 0x00BF, "iquest", "INVERTED QUESTION MARK" },
1191{ 0x00C0, "Agrave", "LATIN CAPITAL LETTER A WITH GRAVE" },
1192{ 0x00C1, "Aacute", "LATIN CAPITAL LETTER A WITH ACUTE" },
1193{ 0x00C2, "Acirc", "LATIN CAPITAL LETTER A WITH CIRCUMFLEX" },
1194{ 0x00C3, "Atilde", "LATIN CAPITAL LETTER A WITH TILDE" },
1195{ 0x00C4, "Auml", "LATIN CAPITAL LETTER A WITH DIAERESIS" },
1196{ 0x00C5, "Aring", "LATIN CAPITAL LETTER A WITH RING ABOVE" },
1197{ 0x00C6, "AElig", "LATIN CAPITAL LETTER AE" },
1198{ 0x00C7, "Ccedil", "LATIN CAPITAL LETTER C WITH CEDILLA" },
1199{ 0x00C8, "Egrave", "LATIN CAPITAL LETTER E WITH GRAVE" },
1200{ 0x00C9, "Eacute", "LATIN CAPITAL LETTER E WITH ACUTE" },
1201{ 0x00CA, "Ecirc", "LATIN CAPITAL LETTER E WITH CIRCUMFLEX" },
1202{ 0x00CB, "Euml", "LATIN CAPITAL LETTER E WITH DIAERESIS" },
1203{ 0x00CC, "Igrave", "LATIN CAPITAL LETTER I WITH GRAVE" },
1204{ 0x00CD, "Iacute", "LATIN CAPITAL LETTER I WITH ACUTE" },
1205{ 0x00CE, "Icirc", "LATIN CAPITAL LETTER I WITH CIRCUMFLEX" },
1206{ 0x00CF, "Iuml", "LATIN CAPITAL LETTER I WITH DIAERESIS" },
1207{ 0x00D0, "ETH", "LATIN CAPITAL LETTER ETH" },
1208{ 0x00D1, "Ntilde", "LATIN CAPITAL LETTER N WITH TILDE" },
1209{ 0x00D2, "Ograve", "LATIN CAPITAL LETTER O WITH GRAVE" },
1210{ 0x00D3, "Oacute", "LATIN CAPITAL LETTER O WITH ACUTE" },
1211{ 0x00D4, "Ocirc", "LATIN CAPITAL LETTER O WITH CIRCUMFLEX" },
1212{ 0x00D5, "Otilde", "LATIN CAPITAL LETTER O WITH TILDE" },
1213{ 0x00D6, "Ouml", "LATIN CAPITAL LETTER O WITH DIAERESIS" },
1214{ 0x00D7, "times", "MULTIPLICATION SIGN" },
1215{ 0x00D8, "Oslash", "LATIN CAPITAL LETTER O WITH STROKE" },
1216{ 0x00D9, "Ugrave", "LATIN CAPITAL LETTER U WITH GRAVE" },
1217{ 0x00DA, "Uacute", "LATIN CAPITAL LETTER U WITH ACUTE" },
1218{ 0x00DB, "Ucirc", "LATIN CAPITAL LETTER U WITH CIRCUMFLEX" },
1219{ 0x00DC, "Uuml", "LATIN CAPITAL LETTER U WITH DIAERESIS" },
1220{ 0x00DD, "Yacute", "LATIN CAPITAL LETTER Y WITH ACUTE" },
1221{ 0x00DE, "THORN", "LATIN CAPITAL LETTER THORN" },
1222{ 0x00DF, "szlig", "LATIN SMALL LETTER SHARP S" },
1223{ 0x00E0, "agrave", "LATIN SMALL LETTER A WITH GRAVE" },
1224{ 0x00E1, "aacute", "LATIN SMALL LETTER A WITH ACUTE" },
1225{ 0x00E2, "acirc", "LATIN SMALL LETTER A WITH CIRCUMFLEX" },
1226{ 0x00E3, "atilde", "LATIN SMALL LETTER A WITH TILDE" },
1227{ 0x00E4, "auml", "LATIN SMALL LETTER A WITH DIAERESIS" },
1228{ 0x00E5, "aring", "LATIN SMALL LETTER A WITH RING ABOVE" },
1229{ 0x00E6, "aelig", "LATIN SMALL LETTER AE" },
1230{ 0x00E7, "ccedil", "LATIN SMALL LETTER C WITH CEDILLA" },
1231{ 0x00E8, "egrave", "LATIN SMALL LETTER E WITH GRAVE" },
1232{ 0x00E9, "eacute", "LATIN SMALL LETTER E WITH ACUTE" },
1233{ 0x00EA, "ecirc", "LATIN SMALL LETTER E WITH CIRCUMFLEX" },
1234{ 0x00EB, "euml", "LATIN SMALL LETTER E WITH DIAERESIS" },
1235{ 0x00EC, "igrave", "LATIN SMALL LETTER I WITH GRAVE" },
1236{ 0x00ED, "iacute", "LATIN SMALL LETTER I WITH ACUTE" },
1237{ 0x00EE, "icirc", "LATIN SMALL LETTER I WITH CIRCUMFLEX" },
1238{ 0x00EF, "iuml", "LATIN SMALL LETTER I WITH DIAERESIS" },
1239{ 0x00F0, "eth", "LATIN SMALL LETTER ETH" },
1240{ 0x00F1, "ntilde", "LATIN SMALL LETTER N WITH TILDE" },
1241{ 0x00F2, "ograve", "LATIN SMALL LETTER O WITH GRAVE" },
1242{ 0x00F3, "oacute", "LATIN SMALL LETTER O WITH ACUTE" },
1243{ 0x00F4, "ocirc", "LATIN SMALL LETTER O WITH CIRCUMFLEX" },
1244{ 0x00F5, "otilde", "LATIN SMALL LETTER O WITH TILDE" },
1245{ 0x00F6, "ouml", "LATIN SMALL LETTER O WITH DIAERESIS" },
1246{ 0x00F7, "divide", "DIVISION SIGN" },
1247{ 0x00F8, "oslash", "CIRCLED DIVISION SLASH" },
1248{ 0x00F9, "ugrave", "LATIN SMALL LETTER U WITH GRAVE" },
1249{ 0x00FA, "uacute", "LATIN SMALL LETTER U WITH ACUTE" },
1250{ 0x00FB, "ucirc", "LATIN SMALL LETTER U WITH CIRCUMFLEX" },
1251{ 0x00FC, "uuml", "LATIN SMALL LETTER U WITH DIAERESIS" },
1252{ 0x00FD, "yacute", "LATIN SMALL LETTER Y WITH ACUTE" },
1253{ 0x00FE, "thorn", "LATIN SMALL LETTER THORN" },
1254{ 0x00FF, "yuml", "LATIN SMALL LETTER Y WITH DIAERESIS" },
1255{ 0x0100, "Amacr", "LATIN CAPITAL LETTER A WITH MACRON" },
1256{ 0x0101, "amacr", "LATIN SMALL LETTER A WITH MACRON" },
1257{ 0x0102, "Abreve", "LATIN CAPITAL LETTER A WITH BREVE" },
1258{ 0x0103, "abreve", "LATIN SMALL LETTER A WITH BREVE" },
1259{ 0x0104, "Aogon", "LATIN CAPITAL LETTER A WITH OGONEK" },
1260{ 0x0105, "aogon", "LATIN SMALL LETTER A WITH OGONEK" },
1261{ 0x0106, "Cacute", "LATIN CAPITAL LETTER C WITH ACUTE" },
1262{ 0x0107, "cacute", "LATIN SMALL LETTER C WITH ACUTE" },
1263{ 0x0108, "Ccirc", "LATIN CAPITAL LETTER C WITH CIRCUMFLEX" },
1264{ 0x0109, "ccirc", "LATIN SMALL LETTER C WITH CIRCUMFLEX" },
1265{ 0x010A, "Cdot", "LATIN CAPITAL LETTER C WITH DOT ABOVE" },
1266{ 0x010B, "cdot", "DOT OPERATOR" },
1267{ 0x010C, "Ccaron", "LATIN CAPITAL LETTER C WITH CARON" },
1268{ 0x010D, "ccaron", "LATIN SMALL LETTER C WITH CARON" },
1269{ 0x010E, "Dcaron", "LATIN CAPITAL LETTER D WITH CARON" },
1270{ 0x010F, "dcaron", "LATIN SMALL LETTER D WITH CARON" },
1271{ 0x0110, "Dstrok", "LATIN CAPITAL LETTER D WITH STROKE" },
1272{ 0x0111, "dstrok", "LATIN SMALL LETTER D WITH STROKE" },
1273{ 0x0112, "Emacr", "LATIN CAPITAL LETTER E WITH MACRON" },
1274{ 0x0113, "emacr", "LATIN SMALL LETTER E WITH MACRON" },
1275{ 0x0116, "Edot", "LATIN CAPITAL LETTER E WITH DOT ABOVE" },
1276{ 0x0117, "edot", "LATIN SMALL LETTER E WITH DOT ABOVE" },
1277{ 0x0118, "Eogon", "LATIN CAPITAL LETTER E WITH OGONEK" },
1278{ 0x0119, "eogon", "LATIN SMALL LETTER E WITH OGONEK" },
1279{ 0x011A, "Ecaron", "LATIN CAPITAL LETTER E WITH CARON" },
1280{ 0x011B, "ecaron", "LATIN SMALL LETTER E WITH CARON" },
1281{ 0x011C, "Gcirc", "LATIN CAPITAL LETTER G WITH CIRCUMFLEX" },
1282{ 0x011D, "gcirc", "LATIN SMALL LETTER G WITH CIRCUMFLEX" },
1283{ 0x011E, "Gbreve", "LATIN CAPITAL LETTER G WITH BREVE" },
1284{ 0x011F, "gbreve", "LATIN SMALL LETTER G WITH BREVE" },
1285{ 0x0120, "Gdot", "LATIN CAPITAL LETTER G WITH DOT ABOVE" },
1286{ 0x0121, "gdot", "LATIN SMALL LETTER G WITH DOT ABOVE" },
1287{ 0x0122, "Gcedil", "LATIN CAPITAL LETTER G WITH CEDILLA" },
1288{ 0x0124, "Hcirc", "LATIN CAPITAL LETTER H WITH CIRCUMFLEX" },
1289{ 0x0125, "hcirc", "LATIN SMALL LETTER H WITH CIRCUMFLEX" },
1290{ 0x0126, "Hstrok", "LATIN CAPITAL LETTER H WITH STROKE" },
1291{ 0x0127, "hstrok", "LATIN SMALL LETTER H WITH STROKE" },
1292{ 0x0128, "Itilde", "LATIN CAPITAL LETTER I WITH TILDE" },
1293{ 0x0129, "itilde", "LATIN SMALL LETTER I WITH TILDE" },
1294{ 0x012A, "Imacr", "LATIN CAPITAL LETTER I WITH MACRON" },
1295{ 0x012B, "imacr", "LATIN SMALL LETTER I WITH MACRON" },
1296{ 0x012E, "Iogon", "LATIN CAPITAL LETTER I WITH OGONEK" },
1297{ 0x012F, "iogon", "LATIN SMALL LETTER I WITH OGONEK" },
1298{ 0x0130, "Idot", "LATIN CAPITAL LETTER I WITH DOT ABOVE" },
1299{ 0x0131, "inodot", "LATIN SMALL LETTER DOTLESS I" },
1300{ 0x0131, "inodot", "LATIN SMALL LETTER DOTLESS I" },
1301{ 0x0132, "IJlig", "LATIN CAPITAL LIGATURE IJ" },
1302{ 0x0133, "ijlig", "LATIN SMALL LIGATURE IJ" },
1303{ 0x0134, "Jcirc", "LATIN CAPITAL LETTER J WITH CIRCUMFLEX" },
1304{ 0x0135, "jcirc", "LATIN SMALL LETTER J WITH CIRCUMFLEX" },
1305{ 0x0136, "Kcedil", "LATIN CAPITAL LETTER K WITH CEDILLA" },
1306{ 0x0137, "kcedil", "LATIN SMALL LETTER K WITH CEDILLA" },
1307{ 0x0138, "kgreen", "LATIN SMALL LETTER KRA" },
1308{ 0x0139, "Lacute", "LATIN CAPITAL LETTER L WITH ACUTE" },
1309{ 0x013A, "lacute", "LATIN SMALL LETTER L WITH ACUTE" },
1310{ 0x013B, "Lcedil", "LATIN CAPITAL LETTER L WITH CEDILLA" },
1311{ 0x013C, "lcedil", "LATIN SMALL LETTER L WITH CEDILLA" },
1312{ 0x013D, "Lcaron", "LATIN CAPITAL LETTER L WITH CARON" },
1313{ 0x013E, "lcaron", "LATIN SMALL LETTER L WITH CARON" },
1314{ 0x013F, "Lmidot", "LATIN CAPITAL LETTER L WITH MIDDLE DOT" },
1315{ 0x0140, "lmidot", "LATIN SMALL LETTER L WITH MIDDLE DOT" },
1316{ 0x0141, "Lstrok", "LATIN CAPITAL LETTER L WITH STROKE" },
1317{ 0x0142, "lstrok", "LATIN SMALL LETTER L WITH STROKE" },
1318{ 0x0143, "Nacute", "LATIN CAPITAL LETTER N WITH ACUTE" },
1319{ 0x0144, "nacute", "LATIN SMALL LETTER N WITH ACUTE" },
1320{ 0x0145, "Ncedil", "LATIN CAPITAL LETTER N WITH CEDILLA" },
1321{ 0x0146, "ncedil", "LATIN SMALL LETTER N WITH CEDILLA" },
1322{ 0x0147, "Ncaron", "LATIN CAPITAL LETTER N WITH CARON" },
1323{ 0x0148, "ncaron", "LATIN SMALL LETTER N WITH CARON" },
1324{ 0x0149, "napos", "LATIN SMALL LETTER N PRECEDED BY APOSTROPHE" },
1325{ 0x014A, "ENG", "LATIN CAPITAL LETTER ENG" },
1326{ 0x014B, "eng", "LATIN SMALL LETTER ENG" },
1327{ 0x014C, "Omacr", "LATIN CAPITAL LETTER O WITH MACRON" },
1328{ 0x014D, "omacr", "LATIN SMALL LETTER O WITH MACRON" },
1329{ 0x0150, "Odblac", "LATIN CAPITAL LETTER O WITH DOUBLE ACUTE" },
1330{ 0x0151, "odblac", "LATIN SMALL LETTER O WITH DOUBLE ACUTE" },
1331{ 0x0152, "OElig", "LATIN CAPITAL LIGATURE OE" },
1332{ 0x0153, "oelig", "LATIN SMALL LIGATURE OE" },
1333{ 0x0154, "Racute", "LATIN CAPITAL LETTER R WITH ACUTE" },
1334{ 0x0155, "racute", "LATIN SMALL LETTER R WITH ACUTE" },
1335{ 0x0156, "Rcedil", "LATIN CAPITAL LETTER R WITH CEDILLA" },
1336{ 0x0157, "rcedil", "LATIN SMALL LETTER R WITH CEDILLA" },
1337{ 0x0158, "Rcaron", "LATIN CAPITAL LETTER R WITH CARON" },
1338{ 0x0159, "rcaron", "LATIN SMALL LETTER R WITH CARON" },
1339{ 0x015A, "Sacute", "LATIN CAPITAL LETTER S WITH ACUTE" },
1340{ 0x015B, "sacute", "LATIN SMALL LETTER S WITH ACUTE" },
1341{ 0x015C, "Scirc", "LATIN CAPITAL LETTER S WITH CIRCUMFLEX" },
1342{ 0x015D, "scirc", "LATIN SMALL LETTER S WITH CIRCUMFLEX" },
1343{ 0x015E, "Scedil", "LATIN CAPITAL LETTER S WITH CEDILLA" },
1344{ 0x015F, "scedil", "LATIN SMALL LETTER S WITH CEDILLA" },
1345{ 0x0160, "Scaron", "LATIN CAPITAL LETTER S WITH CARON" },
1346{ 0x0161, "scaron", "LATIN SMALL LETTER S WITH CARON" },
1347{ 0x0162, "Tcedil", "LATIN CAPITAL LETTER T WITH CEDILLA" },
1348{ 0x0163, "tcedil", "LATIN SMALL LETTER T WITH CEDILLA" },
1349{ 0x0164, "Tcaron", "LATIN CAPITAL LETTER T WITH CARON" },
1350{ 0x0165, "tcaron", "LATIN SMALL LETTER T WITH CARON" },
1351{ 0x0166, "Tstrok", "LATIN CAPITAL LETTER T WITH STROKE" },
1352{ 0x0167, "tstrok", "LATIN SMALL LETTER T WITH STROKE" },
1353{ 0x0168, "Utilde", "LATIN CAPITAL LETTER U WITH TILDE" },
1354{ 0x0169, "utilde", "LATIN SMALL LETTER U WITH TILDE" },
1355{ 0x016A, "Umacr", "LATIN CAPITAL LETTER U WITH MACRON" },
1356{ 0x016B, "umacr", "LATIN SMALL LETTER U WITH MACRON" },
1357{ 0x016C, "Ubreve", "LATIN CAPITAL LETTER U WITH BREVE" },
1358{ 0x016D, "ubreve", "LATIN SMALL LETTER U WITH BREVE" },
1359{ 0x016E, "Uring", "LATIN CAPITAL LETTER U WITH RING ABOVE" },
1360{ 0x016F, "uring", "LATIN SMALL LETTER U WITH RING ABOVE" },
1361{ 0x0170, "Udblac", "LATIN CAPITAL LETTER U WITH DOUBLE ACUTE" },
1362{ 0x0171, "udblac", "LATIN SMALL LETTER U WITH DOUBLE ACUTE" },
1363{ 0x0172, "Uogon", "LATIN CAPITAL LETTER U WITH OGONEK" },
1364{ 0x0173, "uogon", "LATIN SMALL LETTER U WITH OGONEK" },
1365{ 0x0174, "Wcirc", "LATIN CAPITAL LETTER W WITH CIRCUMFLEX" },
1366{ 0x0175, "wcirc", "LATIN SMALL LETTER W WITH CIRCUMFLEX" },
1367{ 0x0176, "Ycirc", "LATIN CAPITAL LETTER Y WITH CIRCUMFLEX" },
1368{ 0x0177, "ycirc", "LATIN SMALL LETTER Y WITH CIRCUMFLEX" },
1369{ 0x0178, "Yuml", "LATIN CAPITAL LETTER Y WITH DIAERESIS" },
1370{ 0x0179, "Zacute", "LATIN CAPITAL LETTER Z WITH ACUTE" },
1371{ 0x017A, "zacute", "LATIN SMALL LETTER Z WITH ACUTE" },
1372{ 0x017B, "Zdot", "LATIN CAPITAL LETTER Z WITH DOT ABOVE" },
1373{ 0x017C, "zdot", "LATIN SMALL LETTER Z WITH DOT ABOVE" },
1374{ 0x017D, "Zcaron", "LATIN CAPITAL LETTER Z WITH CARON" },
1375{ 0x017E, "zcaron", "LATIN SMALL LETTER Z WITH CARON" },
1376{ 0x0192, "fnof", "LATIN SMALL LETTER F WITH HOOK" },
1377{ 0x01F5, "gacute", "LATIN SMALL LETTER G WITH ACUTE" },
1378{ 0x02C7, "caron", "CARON" },
1379{ 0x02D8, "breve", "BREVE" },
1380{ 0x02D9, "dot", "DOT ABOVE" },
1381{ 0x02DA, "ring", "RING ABOVE" },
1382{ 0x02DB, "ogon", "OGONEK" },
1383{ 0x02DC, "tilde", "TILDE" },
1384{ 0x02DD, "dblac", "DOUBLE ACUTE ACCENT" },
1385{ 0x0386, "Aacgr", "GREEK CAPITAL LETTER ALPHA WITH TONOS" },
1386{ 0x0388, "Eacgr", "GREEK CAPITAL LETTER EPSILON WITH TONOS" },
1387{ 0x0389, "EEacgr", "GREEK CAPITAL LETTER ETA WITH TONOS" },
1388{ 0x038A, "Iacgr", "GREEK CAPITAL LETTER IOTA WITH TONOS" },
1389{ 0x038C, "Oacgr", "GREEK CAPITAL LETTER OMICRON WITH TONOS" },
1390{ 0x038E, "Uacgr", "GREEK CAPITAL LETTER UPSILON WITH TONOS" },
1391{ 0x038F, "OHacgr", "GREEK CAPITAL LETTER OMEGA WITH TONOS" },
1392{ 0x0390, "idiagr", "GREEK SMALL LETTER IOTA WITH DIALYTIKA AND TONOS" },
1393{ 0x0391, "Agr", "GREEK CAPITAL LETTER ALPHA" },
1394{ 0x0392, "Bgr", "GREEK CAPITAL LETTER BETA" },
1395{ 0x0393, "b.Gamma", "GREEK CAPITAL LETTER GAMMA" },
1396{ 0x0393, "Gamma", "GREEK CAPITAL LETTER GAMMA" },
1397{ 0x0393, "Ggr", "GREEK CAPITAL LETTER GAMMA" },
1398{ 0x0394, "b.Delta", "GREEK CAPITAL LETTER DELTA" },
1399{ 0x0394, "Delta", "GREEK CAPITAL LETTER DELTA" },
1400{ 0x0394, "Dgr", "GREEK CAPITAL LETTER DELTA" },
1401{ 0x0395, "Egr", "GREEK CAPITAL LETTER EPSILON" },
1402{ 0x0396, "Zgr", "GREEK CAPITAL LETTER ZETA" },
1403{ 0x0397, "EEgr", "GREEK CAPITAL LETTER ETA" },
1404{ 0x0398, "b.Theta", "GREEK CAPITAL LETTER THETA" },
1405{ 0x0398, "Theta", "GREEK CAPITAL LETTER THETA" },
1406{ 0x0398, "THgr", "GREEK CAPITAL LETTER THETA" },
1407{ 0x0399, "Igr", "GREEK CAPITAL LETTER IOTA" },
1408{ 0x039A, "Kgr", "GREEK CAPITAL LETTER KAPPA" },
1409{ 0x039B, "b.Lambda", "GREEK CAPITAL LETTER LAMDA" },
1410{ 0x039B, "Lambda", "GREEK CAPITAL LETTER LAMDA" },
1411{ 0x039B, "Lgr", "GREEK CAPITAL LETTER LAMDA" },
1412{ 0x039C, "Mgr", "GREEK CAPITAL LETTER MU" },
1413{ 0x039D, "Ngr", "GREEK CAPITAL LETTER NU" },
1414{ 0x039E, "b.Xi", "GREEK CAPITAL LETTER XI" },
1415{ 0x039E, "Xgr", "GREEK CAPITAL LETTER XI" },
1416{ 0x039E, "Xi", "GREEK CAPITAL LETTER XI" },
1417{ 0x039F, "Ogr", "GREEK CAPITAL LETTER OMICRON" },
1418{ 0x03A0, "b.Pi", "GREEK CAPITAL LETTER PI" },
1419{ 0x03A0, "Pgr", "GREEK CAPITAL LETTER PI" },
1420{ 0x03A0, "Pi", "GREEK CAPITAL LETTER PI" },
1421{ 0x03A1, "Rgr", "GREEK CAPITAL LETTER RHO" },
1422{ 0x03A3, "b.Sigma", "GREEK CAPITAL LETTER SIGMA" },
1423{ 0x03A3, "Sgr", "GREEK CAPITAL LETTER SIGMA" },
1424{ 0x03A3, "Sigma", "GREEK CAPITAL LETTER SIGMA" },
1425{ 0x03A4, "Tgr", "GREEK CAPITAL LETTER TAU" },
1426{ 0x03A5, "Ugr", "" },
1427{ 0x03A6, "b.Phi", "GREEK CAPITAL LETTER PHI" },
1428{ 0x03A6, "PHgr", "GREEK CAPITAL LETTER PHI" },
1429{ 0x03A6, "Phi", "GREEK CAPITAL LETTER PHI" },
1430{ 0x03A7, "KHgr", "GREEK CAPITAL LETTER CHI" },
1431{ 0x03A8, "b.Psi", "GREEK CAPITAL LETTER PSI" },
1432{ 0x03A8, "PSgr", "GREEK CAPITAL LETTER PSI" },
1433{ 0x03A8, "Psi", "GREEK CAPITAL LETTER PSI" },
1434{ 0x03A9, "b.Omega", "GREEK CAPITAL LETTER OMEGA" },
1435{ 0x03A9, "OHgr", "GREEK CAPITAL LETTER OMEGA" },
1436{ 0x03A9, "Omega", "GREEK CAPITAL LETTER OMEGA" },
1437{ 0x03AA, "Idigr", "GREEK CAPITAL LETTER IOTA WITH DIALYTIKA" },
1438{ 0x03AB, "Udigr", "GREEK CAPITAL LETTER UPSILON WITH DIALYTIKA" },
1439{ 0x03AC, "aacgr", "GREEK SMALL LETTER ALPHA WITH TONOS" },
1440{ 0x03AD, "eacgr", "GREEK SMALL LETTER EPSILON WITH TONOS" },
1441{ 0x03AE, "eeacgr", "GREEK SMALL LETTER ETA WITH TONOS" },
1442{ 0x03AF, "iacgr", "GREEK SMALL LETTER IOTA WITH TONOS" },
1443{ 0x03B0, "udiagr", "GREEK SMALL LETTER UPSILON WITH DIALYTIKA AND TONOS" },
1444{ 0x03B1, "agr", "" },
1445{ 0x03B1, "alpha", "" },
1446{ 0x03B1, "b.alpha", "" },
1447{ 0x03B2, "b.beta", "GREEK SMALL LETTER BETA" },
1448{ 0x03B2, "beta", "GREEK SMALL LETTER BETA" },
1449{ 0x03B2, "bgr", "GREEK SMALL LETTER BETA" },
1450{ 0x03B3, "b.gamma", "GREEK SMALL LETTER GAMMA" },
1451{ 0x03B3, "gamma", "GREEK SMALL LETTER GAMMA" },
1452{ 0x03B3, "ggr", "GREEK SMALL LETTER GAMMA" },
1453{ 0x03B4, "b.delta", "GREEK SMALL LETTER DELTA" },
1454{ 0x03B4, "delta", "GREEK SMALL LETTER DELTA" },
1455{ 0x03B4, "dgr", "GREEK SMALL LETTER DELTA" },
1456{ 0x03B5, "b.epsi", "" },
1457{ 0x03B5, "b.epsis", "" },
1458{ 0x03B5, "b.epsiv", "" },
1459{ 0x03B5, "egr", "" },
1460{ 0x03B5, "epsiv", "" },
1461{ 0x03B6, "b.zeta", "GREEK SMALL LETTER ZETA" },
1462{ 0x03B6, "zeta", "GREEK SMALL LETTER ZETA" },
1463{ 0x03B6, "zgr", "GREEK SMALL LETTER ZETA" },
1464{ 0x03B7, "b.eta", "GREEK SMALL LETTER ETA" },
1465{ 0x03B7, "eegr", "GREEK SMALL LETTER ETA" },
1466{ 0x03B7, "eta", "GREEK SMALL LETTER ETA" },
1467{ 0x03B8, "b.thetas", "" },
1468{ 0x03B8, "thetas", "" },
1469{ 0x03B8, "thgr", "" },
1470{ 0x03B9, "b.iota", "GREEK SMALL LETTER IOTA" },
1471{ 0x03B9, "igr", "GREEK SMALL LETTER IOTA" },
1472{ 0x03B9, "iota", "GREEK SMALL LETTER IOTA" },
1473{ 0x03BA, "b.kappa", "GREEK SMALL LETTER KAPPA" },
1474{ 0x03BA, "kappa", "GREEK SMALL LETTER KAPPA" },
1475{ 0x03BA, "kgr", "GREEK SMALL LETTER KAPPA" },
1476{ 0x03BB, "b.lambda", "GREEK SMALL LETTER LAMDA" },
1477{ 0x03BB, "lambda", "GREEK SMALL LETTER LAMDA" },
1478{ 0x03BB, "lgr", "GREEK SMALL LETTER LAMDA" },
1479{ 0x03BC, "b.mu", "GREEK SMALL LETTER MU" },
1480{ 0x03BC, "mgr", "GREEK SMALL LETTER MU" },
1481{ 0x03BC, "mu", "GREEK SMALL LETTER MU" },
1482{ 0x03BD, "b.nu", "GREEK SMALL LETTER NU" },
1483{ 0x03BD, "ngr", "GREEK SMALL LETTER NU" },
1484{ 0x03BD, "nu", "GREEK SMALL LETTER NU" },
1485{ 0x03BE, "b.xi", "GREEK SMALL LETTER XI" },
1486{ 0x03BE, "xgr", "GREEK SMALL LETTER XI" },
1487{ 0x03BE, "xi", "GREEK SMALL LETTER XI" },
1488{ 0x03BF, "ogr", "GREEK SMALL LETTER OMICRON" },
1489{ 0x03C0, "b.pi", "GREEK SMALL LETTER PI" },
1490{ 0x03C0, "pgr", "GREEK SMALL LETTER PI" },
1491{ 0x03C0, "pi", "GREEK SMALL LETTER PI" },
1492{ 0x03C1, "b.rho", "GREEK SMALL LETTER RHO" },
1493{ 0x03C1, "rgr", "GREEK SMALL LETTER RHO" },
1494{ 0x03C1, "rho", "GREEK SMALL LETTER RHO" },
1495{ 0x03C2, "b.sigmav", "" },
1496{ 0x03C2, "sfgr", "" },
1497{ 0x03C2, "sigmav", "" },
1498{ 0x03C3, "b.sigma", "GREEK SMALL LETTER SIGMA" },
1499{ 0x03C3, "sgr", "GREEK SMALL LETTER SIGMA" },
1500{ 0x03C3, "sigma", "GREEK SMALL LETTER SIGMA" },
1501{ 0x03C4, "b.tau", "GREEK SMALL LETTER TAU" },
1502{ 0x03C4, "tau", "GREEK SMALL LETTER TAU" },
1503{ 0x03C4, "tgr", "GREEK SMALL LETTER TAU" },
1504{ 0x03C5, "b.upsi", "GREEK SMALL LETTER UPSILON" },
1505{ 0x03C5, "ugr", "GREEK SMALL LETTER UPSILON" },
1506{ 0x03C5, "upsi", "GREEK SMALL LETTER UPSILON" },
1507{ 0x03C6, "b.phis", "GREEK SMALL LETTER PHI" },
1508{ 0x03C6, "phgr", "GREEK SMALL LETTER PHI" },
1509{ 0x03C6, "phis", "GREEK SMALL LETTER PHI" },
1510{ 0x03C7, "b.chi", "GREEK SMALL LETTER CHI" },
1511{ 0x03C7, "chi", "GREEK SMALL LETTER CHI" },
1512{ 0x03C7, "khgr", "GREEK SMALL LETTER CHI" },
1513{ 0x03C8, "b.psi", "GREEK SMALL LETTER PSI" },
1514{ 0x03C8, "psgr", "GREEK SMALL LETTER PSI" },
1515{ 0x03C8, "psi", "GREEK SMALL LETTER PSI" },
1516{ 0x03C9, "b.omega", "GREEK SMALL LETTER OMEGA" },
1517{ 0x03C9, "ohgr", "GREEK SMALL LETTER OMEGA" },
1518{ 0x03C9, "omega", "GREEK SMALL LETTER OMEGA" },
1519{ 0x03CA, "idigr", "GREEK SMALL LETTER IOTA WITH DIALYTIKA" },
1520{ 0x03CB, "udigr", "GREEK SMALL LETTER UPSILON WITH DIALYTIKA" },
1521{ 0x03CC, "oacgr", "GREEK SMALL LETTER OMICRON WITH TONOS" },
1522{ 0x03CD, "uacgr", "GREEK SMALL LETTER UPSILON WITH TONOS" },
1523{ 0x03CE, "ohacgr", "GREEK SMALL LETTER OMEGA WITH TONOS" },
1524{ 0x03D1, "b.thetav", "" },
1525{ 0x03D1, "thetav", "" },
1526{ 0x03D2, "b.Upsi", "" },
1527{ 0x03D2, "Upsi", "" },
1528{ 0x03D5, "b.phiv", "GREEK PHI SYMBOL" },
1529{ 0x03D5, "phiv", "GREEK PHI SYMBOL" },
1530{ 0x03D6, "b.piv", "GREEK PI SYMBOL" },
1531{ 0x03D6, "piv", "GREEK PI SYMBOL" },
1532{ 0x03DC, "b.gammad", "GREEK LETTER DIGAMMA" },
1533{ 0x03DC, "gammad", "GREEK LETTER DIGAMMA" },
1534{ 0x03F0, "b.kappav", "GREEK KAPPA SYMBOL" },
1535{ 0x03F0, "kappav", "GREEK KAPPA SYMBOL" },
1536{ 0x03F1, "b.rhov", "GREEK RHO SYMBOL" },
1537{ 0x03F1, "rhov", "GREEK RHO SYMBOL" },
1538{ 0x0401, "IOcy", "CYRILLIC CAPITAL LETTER IO" },
1539{ 0x0402, "DJcy", "CYRILLIC CAPITAL LETTER DJE" },
1540{ 0x0403, "GJcy", "CYRILLIC CAPITAL LETTER GJE" },
1541{ 0x0404, "Jukcy", "CYRILLIC CAPITAL LETTER UKRAINIAN IE" },
1542{ 0x0405, "DScy", "CYRILLIC CAPITAL LETTER DZE" },
1543{ 0x0406, "Iukcy", "CYRILLIC CAPITAL LETTER BYELORUSSIAN-UKRAINIAN I" },
1544{ 0x0407, "YIcy", "CYRILLIC CAPITAL LETTER YI" },
1545{ 0x0408, "Jsercy", "CYRILLIC CAPITAL LETTER JE" },
1546{ 0x0409, "LJcy", "CYRILLIC CAPITAL LETTER LJE" },
1547{ 0x040A, "NJcy", "CYRILLIC CAPITAL LETTER NJE" },
1548{ 0x040B, "TSHcy", "CYRILLIC CAPITAL LETTER TSHE" },
1549{ 0x040C, "KJcy", "CYRILLIC CAPITAL LETTER KJE" },
1550{ 0x040E, "Ubrcy", "CYRILLIC CAPITAL LETTER SHORT U" },
1551{ 0x040F, "DZcy", "CYRILLIC CAPITAL LETTER DZHE" },
1552{ 0x0410, "Acy", "CYRILLIC CAPITAL LETTER A" },
1553{ 0x0411, "Bcy", "CYRILLIC CAPITAL LETTER BE" },
1554{ 0x0412, "Vcy", "CYRILLIC CAPITAL LETTER VE" },
1555{ 0x0413, "Gcy", "CYRILLIC CAPITAL LETTER GHE" },
1556{ 0x0414, "Dcy", "CYRILLIC CAPITAL LETTER DE" },
1557{ 0x0415, "IEcy", "CYRILLIC CAPITAL LETTER IE" },
1558{ 0x0416, "ZHcy", "CYRILLIC CAPITAL LETTER ZHE" },
1559{ 0x0417, "Zcy", "CYRILLIC CAPITAL LETTER ZE" },
1560{ 0x0418, "Icy", "CYRILLIC CAPITAL LETTER I" },
1561{ 0x0419, "Jcy", "CYRILLIC CAPITAL LETTER SHORT I" },
1562{ 0x041A, "Kcy", "CYRILLIC CAPITAL LETTER KA" },
1563{ 0x041B, "Lcy", "CYRILLIC CAPITAL LETTER EL" },
1564{ 0x041C, "Mcy", "CYRILLIC CAPITAL LETTER EM" },
1565{ 0x041D, "Ncy", "CYRILLIC CAPITAL LETTER EN" },
1566{ 0x041E, "Ocy", "CYRILLIC CAPITAL LETTER O" },
1567{ 0x041F, "Pcy", "CYRILLIC CAPITAL LETTER PE" },
1568{ 0x0420, "Rcy", "CYRILLIC CAPITAL LETTER ER" },
1569{ 0x0421, "Scy", "CYRILLIC CAPITAL LETTER ES" },
1570{ 0x0422, "Tcy", "CYRILLIC CAPITAL LETTER TE" },
1571{ 0x0423, "Ucy", "CYRILLIC CAPITAL LETTER U" },
1572{ 0x0424, "Fcy", "CYRILLIC CAPITAL LETTER EF" },
1573{ 0x0425, "KHcy", "CYRILLIC CAPITAL LETTER HA" },
1574{ 0x0426, "TScy", "CYRILLIC CAPITAL LETTER TSE" },
1575{ 0x0427, "CHcy", "CYRILLIC CAPITAL LETTER CHE" },
1576{ 0x0428, "SHcy", "CYRILLIC CAPITAL LETTER SHA" },
1577{ 0x0429, "SHCHcy", "CYRILLIC CAPITAL LETTER SHCHA" },
1578{ 0x042A, "HARDcy", "CYRILLIC CAPITAL LETTER HARD SIGN" },
1579{ 0x042B, "Ycy", "CYRILLIC CAPITAL LETTER YERU" },
1580{ 0x042C, "SOFTcy", "CYRILLIC CAPITAL LETTER SOFT SIGN" },
1581{ 0x042D, "Ecy", "CYRILLIC CAPITAL LETTER E" },
1582{ 0x042E, "YUcy", "CYRILLIC CAPITAL LETTER YU" },
1583{ 0x042F, "YAcy", "CYRILLIC CAPITAL LETTER YA" },
1584{ 0x0430, "acy", "CYRILLIC SMALL LETTER A" },
1585{ 0x0431, "bcy", "CYRILLIC SMALL LETTER BE" },
1586{ 0x0432, "vcy", "CYRILLIC SMALL LETTER VE" },
1587{ 0x0433, "gcy", "CYRILLIC SMALL LETTER GHE" },
1588{ 0x0434, "dcy", "CYRILLIC SMALL LETTER DE" },
1589{ 0x0435, "iecy", "CYRILLIC SMALL LETTER IE" },
1590{ 0x0436, "zhcy", "CYRILLIC SMALL LETTER ZHE" },
1591{ 0x0437, "zcy", "CYRILLIC SMALL LETTER ZE" },
1592{ 0x0438, "icy", "CYRILLIC SMALL LETTER I" },
1593{ 0x0439, "jcy", "CYRILLIC SMALL LETTER SHORT I" },
1594{ 0x043A, "kcy", "CYRILLIC SMALL LETTER KA" },
1595{ 0x043B, "lcy", "CYRILLIC SMALL LETTER EL" },
1596{ 0x043C, "mcy", "CYRILLIC SMALL LETTER EM" },
1597{ 0x043D, "ncy", "CYRILLIC SMALL LETTER EN" },
1598{ 0x043E, "ocy", "CYRILLIC SMALL LETTER O" },
1599{ 0x043F, "pcy", "CYRILLIC SMALL LETTER PE" },
1600{ 0x0440, "rcy", "CYRILLIC SMALL LETTER ER" },
1601{ 0x0441, "scy", "CYRILLIC SMALL LETTER ES" },
1602{ 0x0442, "tcy", "CYRILLIC SMALL LETTER TE" },
1603{ 0x0443, "ucy", "CYRILLIC SMALL LETTER U" },
1604{ 0x0444, "fcy", "CYRILLIC SMALL LETTER EF" },
1605{ 0x0445, "khcy", "CYRILLIC SMALL LETTER HA" },
1606{ 0x0446, "tscy", "CYRILLIC SMALL LETTER TSE" },
1607{ 0x0447, "chcy", "CYRILLIC SMALL LETTER CHE" },
1608{ 0x0448, "shcy", "CYRILLIC SMALL LETTER SHA" },
1609{ 0x0449, "shchcy", "CYRILLIC SMALL LETTER SHCHA" },
1610{ 0x044A, "hardcy", "CYRILLIC SMALL LETTER HARD SIGN" },
1611{ 0x044B, "ycy", "CYRILLIC SMALL LETTER YERU" },
1612{ 0x044C, "softcy", "CYRILLIC SMALL LETTER SOFT SIGN" },
1613{ 0x044D, "ecy", "CYRILLIC SMALL LETTER E" },
1614{ 0x044E, "yucy", "CYRILLIC SMALL LETTER YU" },
1615{ 0x044F, "yacy", "CYRILLIC SMALL LETTER YA" },
1616{ 0x0451, "iocy", "CYRILLIC SMALL LETTER IO" },
1617{ 0x0452, "djcy", "CYRILLIC SMALL LETTER DJE" },
1618{ 0x0453, "gjcy", "CYRILLIC SMALL LETTER GJE" },
1619{ 0x0454, "jukcy", "CYRILLIC SMALL LETTER UKRAINIAN IE" },
1620{ 0x0455, "dscy", "CYRILLIC SMALL LETTER DZE" },
1621{ 0x0456, "iukcy", "CYRILLIC SMALL LETTER BYELORUSSIAN-UKRAINIAN I" },
1622{ 0x0457, "yicy", "CYRILLIC SMALL LETTER YI" },
1623{ 0x0458, "jsercy", "CYRILLIC SMALL LETTER JE" },
1624{ 0x0459, "ljcy", "CYRILLIC SMALL LETTER LJE" },
1625{ 0x045A, "njcy", "CYRILLIC SMALL LETTER NJE" },
1626{ 0x045B, "tshcy", "CYRILLIC SMALL LETTER TSHE" },
1627{ 0x045C, "kjcy", "CYRILLIC SMALL LETTER KJE" },
1628{ 0x045E, "ubrcy", "CYRILLIC SMALL LETTER SHORT U" },
1629{ 0x045F, "dzcy", "CYRILLIC SMALL LETTER DZHE" },
1630{ 0x2002, "ensp", "EN SPACE" },
1631{ 0x2003, "emsp", "EM SPACE" },
1632{ 0x2004, "emsp13", "THREE-PER-EM SPACE" },
1633{ 0x2005, "emsp14", "FOUR-PER-EM SPACE" },
1634{ 0x2007, "numsp", "FIGURE SPACE" },
1635{ 0x2008, "puncsp", "PUNCTUATION SPACE" },
1636{ 0x2009, "thinsp", "THIN SPACE" },
1637{ 0x200A, "hairsp", "HAIR SPACE" },
1638{ 0x2010, "dash", "HYPHEN" },
1639{ 0x2013, "ndash", "EN DASH" },
1640{ 0x2014, "mdash", "EM DASH" },
1641{ 0x2015, "horbar", "HORIZONTAL BAR" },
1642{ 0x2016, "Verbar", "DOUBLE VERTICAL LINE" },
1643{ 0x2018, "lsquo", "" },
1644{ 0x2018, "rsquor", "" },
1645{ 0x2019, "rsquo", "RIGHT SINGLE QUOTATION MARK" },
1646{ 0x201A, "lsquor", "SINGLE LOW-9 QUOTATION MARK" },
1647{ 0x201C, "ldquo", "" },
1648{ 0x201C, "rdquor", "" },
1649{ 0x201D, "rdquo", "RIGHT DOUBLE QUOTATION MARK" },
1650{ 0x201E, "ldquor", "DOUBLE LOW-9 QUOTATION MARK" },
1651{ 0x2020, "dagger", "DAGGER" },
1652{ 0x2021, "Dagger", "DOUBLE DAGGER" },
1653{ 0x2022, "bull", "BULLET" },
1654{ 0x2025, "nldr", "TWO DOT LEADER" },
1655{ 0x2026, "hellip", "HORIZONTAL ELLIPSIS" },
1656{ 0x2026, "mldr", "HORIZONTAL ELLIPSIS" },
1657{ 0x2030, "permil", "PER MILLE SIGN" },
1658{ 0x2032, "prime", "PRIME" },
1659{ 0x2032, "vprime", "PRIME" },
1660{ 0x2033, "Prime", "DOUBLE PRIME" },
1661{ 0x2034, "tprime", "TRIPLE PRIME" },
1662{ 0x2035, "bprime", "REVERSED PRIME" },
1663{ 0x2041, "caret", "CARET" },
1664{ 0x2043, "hybull", "HYPHEN BULLET" },
1665{ 0x20DB, "tdot", "COMBINING THREE DOTS ABOVE" },
1666{ 0x20DC, "DotDot", "COMBINING FOUR DOTS ABOVE" },
1667{ 0x2105, "incare", "CARE OF" },
1668{ 0x210B, "hamilt", "SCRIPT CAPITAL H" },
1669{ 0x210F, "planck", "PLANCK CONSTANT OVER TWO PI" },
1670{ 0x2111, "image", "BLACK-LETTER CAPITAL I" },
1671{ 0x2112, "lagran", "SCRIPT CAPITAL L" },
1672{ 0x2113, "ell", "SCRIPT SMALL L" },
1673{ 0x2116, "numero", "NUMERO SIGN" },
1674{ 0x2117, "copysr", "SOUND RECORDING COPYRIGHT" },
1675{ 0x2118, "weierp", "SCRIPT CAPITAL P" },
1676{ 0x211C, "real", "BLACK-LETTER CAPITAL R" },
1677{ 0x211E, "rx", "PRESCRIPTION TAKE" },
1678{ 0x2122, "trade", "TRADE MARK SIGN" },
1679{ 0x2126, "ohm", "OHM SIGN" },
1680{ 0x212B, "angst", "ANGSTROM SIGN" },
1681{ 0x212C, "bernou", "SCRIPT CAPITAL B" },
1682{ 0x2133, "phmmat", "SCRIPT CAPITAL M" },
1683{ 0x2134, "order", "SCRIPT SMALL O" },
1684{ 0x2135, "aleph", "ALEF SYMBOL" },
1685{ 0x2136, "beth", "BET SYMBOL" },
1686{ 0x2137, "gimel", "GIMEL SYMBOL" },
1687{ 0x2138, "daleth", "DALET SYMBOL" },
1688{ 0x2153, "frac13", "VULGAR FRACTION ONE THIRD" },
1689{ 0x2154, "frac23", "VULGAR FRACTION TWO THIRDS" },
1690{ 0x2155, "frac15", "VULGAR FRACTION ONE FIFTH" },
1691{ 0x2156, "frac25", "VULGAR FRACTION TWO FIFTHS" },
1692{ 0x2157, "frac35", "VULGAR FRACTION THREE FIFTHS" },
1693{ 0x2158, "frac45", "VULGAR FRACTION FOUR FIFTHS" },
1694{ 0x2159, "frac16", "VULGAR FRACTION ONE SIXTH" },
1695{ 0x215A, "frac56", "VULGAR FRACTION FIVE SIXTHS" },
1696{ 0x215B, "frac18", "" },
1697{ 0x215C, "frac38", "" },
1698{ 0x215D, "frac58", "" },
1699{ 0x215E, "frac78", "" },
1700{ 0x2190, "larr", "LEFTWARDS DOUBLE ARROW" },
1701{ 0x2191, "uarr", "UPWARDS ARROW" },
1702{ 0x2192, "rarr", "RIGHTWARDS DOUBLE ARROW" },
1703{ 0x2193, "darr", "DOWNWARDS ARROW" },
1704{ 0x2194, "harr", "LEFT RIGHT ARROW" },
1705{ 0x2194, "xhArr", "LEFT RIGHT ARROW" },
1706{ 0x2194, "xharr", "LEFT RIGHT ARROW" },
1707{ 0x2195, "varr", "UP DOWN ARROW" },
1708{ 0x2196, "nwarr", "NORTH WEST ARROW" },
1709{ 0x2197, "nearr", "NORTH EAST ARROW" },
1710{ 0x2198, "drarr", "SOUTH EAST ARROW" },
1711{ 0x2199, "dlarr", "SOUTH WEST ARROW" },
1712{ 0x219A, "nlarr", "LEFTWARDS ARROW WITH STROKE" },
1713{ 0x219B, "nrarr", "RIGHTWARDS ARROW WITH STROKE" },
1714{ 0x219D, "rarrw", "RIGHTWARDS SQUIGGLE ARROW" },
1715{ 0x219E, "Larr", "LEFTWARDS TWO HEADED ARROW" },
1716{ 0x21A0, "Rarr", "RIGHTWARDS TWO HEADED ARROW" },
1717{ 0x21A2, "larrtl", "LEFTWARDS ARROW WITH TAIL" },
1718{ 0x21A3, "rarrtl", "RIGHTWARDS ARROW WITH TAIL" },
1719{ 0x21A6, "map", "RIGHTWARDS ARROW FROM BAR" },
1720{ 0x21A9, "larrhk", "LEFTWARDS ARROW WITH HOOK" },
1721{ 0x21AA, "rarrhk", "RIGHTWARDS ARROW WITH HOOK" },
1722{ 0x21AB, "larrlp", "LEFTWARDS ARROW WITH LOOP" },
1723{ 0x21AC, "rarrlp", "RIGHTWARDS ARROW WITH LOOP" },
1724{ 0x21AD, "harrw", "LEFT RIGHT WAVE ARROW" },
1725{ 0x21AE, "nharr", "LEFT RIGHT ARROW WITH STROKE" },
1726{ 0x21B0, "lsh", "UPWARDS ARROW WITH TIP LEFTWARDS" },
1727{ 0x21B1, "rsh", "UPWARDS ARROW WITH TIP RIGHTWARDS" },
1728{ 0x21B6, "cularr", "ANTICLOCKWISE TOP SEMICIRCLE ARROW" },
1729{ 0x21B7, "curarr", "CLOCKWISE TOP SEMICIRCLE ARROW" },
1730{ 0x21BA, "olarr", "ANTICLOCKWISE OPEN CIRCLE ARROW" },
1731{ 0x21BB, "orarr", "CLOCKWISE OPEN CIRCLE ARROW" },
1732{ 0x21BC, "lharu", "LEFTWARDS HARPOON WITH BARB UPWARDS" },
1733{ 0x21BD, "lhard", "LEFTWARDS HARPOON WITH BARB DOWNWARDS" },
1734{ 0x21BE, "uharr", "UPWARDS HARPOON WITH BARB RIGHTWARDS" },
1735{ 0x21BF, "uharl", "UPWARDS HARPOON WITH BARB LEFTWARDS" },
1736{ 0x21C0, "rharu", "RIGHTWARDS HARPOON WITH BARB UPWARDS" },
1737{ 0x21C1, "rhard", "RIGHTWARDS HARPOON WITH BARB DOWNWARDS" },
1738{ 0x21C2, "dharr", "DOWNWARDS HARPOON WITH BARB RIGHTWARDS" },
1739{ 0x21C3, "dharl", "DOWNWARDS HARPOON WITH BARB LEFTWARDS" },
1740{ 0x21C4, "rlarr2", "RIGHTWARDS ARROW OVER LEFTWARDS ARROW" },
1741{ 0x21C6, "lrarr2", "LEFTWARDS ARROW OVER RIGHTWARDS ARROW" },
1742{ 0x21C7, "larr2", "LEFTWARDS PAIRED ARROWS" },
1743{ 0x21C8, "uarr2", "UPWARDS PAIRED ARROWS" },
1744{ 0x21C9, "rarr2", "RIGHTWARDS PAIRED ARROWS" },
1745{ 0x21CA, "darr2", "DOWNWARDS PAIRED ARROWS" },
1746{ 0x21CB, "lrhar2", "LEFTWARDS HARPOON OVER RIGHTWARDS HARPOON" },
1747{ 0x21CC, "rlhar2", "RIGHTWARDS HARPOON OVER LEFTWARDS HARPOON" },
1748{ 0x21CD, "nlArr", "LEFTWARDS DOUBLE ARROW WITH STROKE" },
1749{ 0x21CE, "nhArr", "LEFT RIGHT DOUBLE ARROW WITH STROKE" },
1750{ 0x21CF, "nrArr", "RIGHTWARDS DOUBLE ARROW WITH STROKE" },
1751{ 0x21D0, "lArr", "LEFTWARDS ARROW" },
1752{ 0x21D0, "xlArr", "LEFTWARDS DOUBLE ARROW" },
1753{ 0x21D1, "uArr", "UPWARDS DOUBLE ARROW" },
1754{ 0x21D2, "rArr", "RIGHTWARDS ARROW" },
1755{ 0x21D2, "xrArr", "RIGHTWARDS DOUBLE ARROW" },
1756{ 0x21D3, "dArr", "DOWNWARDS DOUBLE ARROW" },
1757{ 0x21D4, "hArr", "" },
1758{ 0x21D4, "iff", "LEFT RIGHT DOUBLE ARROW" },
1759{ 0x21D5, "vArr", "UP DOWN DOUBLE ARROW" },
1760{ 0x21DA, "lAarr", "LEFTWARDS TRIPLE ARROW" },
1761{ 0x21DB, "rAarr", "RIGHTWARDS TRIPLE ARROW" },
1762{ 0x2200, "forall", "" },
1763{ 0x2201, "comp", "COMPLEMENT" },
1764{ 0x2202, "part", "" },
1765{ 0x2203, "exist", "" },
1766{ 0x2204, "nexist", "THERE DOES NOT EXIST" },
1767{ 0x2205, "empty", "" },
1768{ 0x2207, "nabla", "NABLA" },
1769{ 0x2209, "notin", "" },
1770{ 0x220A, "epsi", "" },
1771{ 0x220A, "epsis", "" },
1772{ 0x220A, "isin", "" },
1773{ 0x220D, "bepsi", "SMALL CONTAINS AS MEMBER" },
1774{ 0x220D, "ni", "" },
1775{ 0x220F, "prod", "N-ARY PRODUCT" },
1776{ 0x2210, "amalg", "N-ARY COPRODUCT" },
1777{ 0x2210, "coprod", "N-ARY COPRODUCT" },
1778{ 0x2210, "samalg", "" },
1779{ 0x2211, "sum", "N-ARY SUMMATION" },
1780{ 0x2212, "minus", "MINUS SIGN" },
1781{ 0x2213, "mnplus", "" },
1782{ 0x2214, "plusdo", "DOT PLUS" },
1783{ 0x2216, "setmn", "SET MINUS" },
1784{ 0x2216, "ssetmn", "SET MINUS" },
1785{ 0x2217, "lowast", "ASTERISK OPERATOR" },
1786{ 0x2218, "compfn", "RING OPERATOR" },
1787{ 0x221A, "radic", "" },
1788{ 0x221D, "prop", "" },
1789{ 0x221D, "vprop", "" },
1790{ 0x221E, "infin", "" },
1791{ 0x221F, "ang90", "RIGHT ANGLE" },
1792{ 0x2220, "ang", "ANGLE" },
1793{ 0x2221, "angmsd", "MEASURED ANGLE" },
1794{ 0x2222, "angsph", "" },
1795{ 0x2223, "mid", "" },
1796{ 0x2224, "nmid", "DOES NOT DIVIDE" },
1797{ 0x2225, "par", "PARALLEL TO" },
1798{ 0x2225, "spar", "PARALLEL TO" },
1799{ 0x2226, "npar", "NOT PARALLEL TO" },
1800{ 0x2226, "nspar", "NOT PARALLEL TO" },
1801{ 0x2227, "and", "" },
1802{ 0x2228, "or", "" },
1803{ 0x2229, "cap", "" },
1804{ 0x222A, "cup", "" },
1805{ 0x222B, "int", "" },
1806{ 0x222E, "conint", "" },
1807{ 0x2234, "there4", "" },
1808{ 0x2235, "becaus", "BECAUSE" },
1809{ 0x223C, "sim", "" },
1810{ 0x223C, "thksim", "TILDE OPERATOR" },
1811{ 0x223D, "bsim", "" },
1812{ 0x2240, "wreath", "WREATH PRODUCT" },
1813{ 0x2241, "nsim", "" },
1814{ 0x2243, "sime", "" },
1815{ 0x2244, "nsime", "" },
1816{ 0x2245, "cong", "" },
1817{ 0x2247, "ncong", "NEITHER APPROXIMATELY NOR ACTUALLY EQUAL TO" },
1818{ 0x2248, "ap", "" },
1819{ 0x2248, "thkap", "ALMOST EQUAL TO" },
1820{ 0x2249, "nap", "NOT ALMOST EQUAL TO" },
1821{ 0x224A, "ape", "" },
1822{ 0x224C, "bcong", "ALL EQUAL TO" },
1823{ 0x224D, "asymp", "EQUIVALENT TO" },
1824{ 0x224E, "bump", "" },
1825{ 0x224F, "bumpe", "" },
1826{ 0x2250, "esdot", "" },
1827{ 0x2251, "eDot", "" },
1828{ 0x2252, "efDot", "" },
1829{ 0x2253, "erDot", "" },
1830{ 0x2254, "colone", "" },
1831{ 0x2255, "ecolon", "" },
1832{ 0x2256, "ecir", "" },
1833{ 0x2257, "cire", "" },
1834{ 0x2259, "wedgeq", "ESTIMATES" },
1835{ 0x225C, "trie", "" },
1836{ 0x2260, "ne", "" },
1837{ 0x2261, "equiv", "" },
1838{ 0x2262, "nequiv", "NOT IDENTICAL TO" },
1839{ 0x2264, "le", "" },
1840{ 0x2264, "les", "LESS-THAN OR EQUAL TO" },
1841{ 0x2265, "ge", "GREATER-THAN OR EQUAL TO" },
1842{ 0x2265, "ges", "GREATER-THAN OR EQUAL TO" },
1843{ 0x2266, "lE", "" },
1844{ 0x2267, "gE", "" },
1845{ 0x2268, "lnE", "" },
1846{ 0x2268, "lne", "" },
1847{ 0x2268, "lvnE", "LESS-THAN BUT NOT EQUAL TO" },
1848{ 0x2269, "gnE", "" },
1849{ 0x2269, "gne", "" },
1850{ 0x2269, "gvnE", "GREATER-THAN BUT NOT EQUAL TO" },
1851{ 0x226A, "Lt", "MUCH LESS-THAN" },
1852{ 0x226B, "Gt", "MUCH GREATER-THAN" },
1853{ 0x226C, "twixt", "BETWEEN" },
1854{ 0x226E, "nlt", "NOT LESS-THAN" },
1855{ 0x226F, "ngt", "NOT GREATER-THAN" },
1856{ 0x2270, "nlE", "" },
1857{ 0x2270, "nle", "NEITHER LESS-THAN NOR EQUAL TO" },
1858{ 0x2270, "nles", "" },
1859{ 0x2271, "ngE", "" },
1860{ 0x2271, "nge", "NEITHER GREATER-THAN NOR EQUAL TO" },
1861{ 0x2271, "nges", "" },
1862{ 0x2272, "lap", "LESS-THAN OR EQUIVALENT TO" },
1863{ 0x2272, "lsim", "LESS-THAN OR EQUIVALENT TO" },
1864{ 0x2273, "gap", "GREATER-THAN OR EQUIVALENT TO" },
1865{ 0x2273, "gsim", "GREATER-THAN OR EQUIVALENT TO" },
1866{ 0x2276, "lg", "LESS-THAN OR GREATER-THAN" },
1867{ 0x2277, "gl", "" },
1868{ 0x227A, "pr", "" },
1869{ 0x227B, "sc", "" },
1870{ 0x227C, "cupre", "" },
1871{ 0x227C, "pre", "" },
1872{ 0x227D, "sccue", "" },
1873{ 0x227D, "sce", "" },
1874{ 0x227E, "prap", "" },
1875{ 0x227E, "prsim", "" },
1876{ 0x227F, "scap", "" },
1877{ 0x227F, "scsim", "" },
1878{ 0x2280, "npr", "DOES NOT PRECEDE" },
1879{ 0x2281, "nsc", "DOES NOT SUCCEED" },
1880{ 0x2282, "sub", "" },
1881{ 0x2283, "sup", "" },
1882{ 0x2284, "nsub", "NOT A SUBSET OF" },
1883{ 0x2285, "nsup", "NOT A SUPERSET OF" },
1884{ 0x2286, "subE", "" },
1885{ 0x2286, "sube", "" },
1886{ 0x2287, "supE", "" },
1887{ 0x2287, "supe", "" },
1888{ 0x2288, "nsubE", "" },
1889{ 0x2288, "nsube", "" },
1890{ 0x2289, "nsupE", "" },
1891{ 0x2289, "nsupe", "" },
1892{ 0x228A, "subne", "" },
1893{ 0x228A, "subnE", "SUBSET OF WITH NOT EQUAL TO" },
1894{ 0x228A, "vsubne", "SUBSET OF WITH NOT EQUAL TO" },
1895{ 0x228B, "supnE", "" },
1896{ 0x228B, "supne", "" },
1897{ 0x228B, "vsupnE", "SUPERSET OF WITH NOT EQUAL TO" },
1898{ 0x228B, "vsupne", "SUPERSET OF WITH NOT EQUAL TO" },
1899{ 0x228E, "uplus", "MULTISET UNION" },
1900{ 0x228F, "sqsub", "" },
1901{ 0x2290, "sqsup", "" },
1902{ 0x2291, "sqsube", "" },
1903{ 0x2292, "sqsupe", "" },
1904{ 0x2293, "sqcap", "SQUARE CAP" },
1905{ 0x2294, "sqcup", "SQUARE CUP" },
1906{ 0x2295, "oplus", "CIRCLED PLUS" },
1907{ 0x2296, "ominus", "CIRCLED MINUS" },
1908{ 0x2297, "otimes", "CIRCLED TIMES" },
1909{ 0x2298, "osol", "CIRCLED DIVISION SLASH" },
1910{ 0x2299, "odot", "CIRCLED DOT OPERATOR" },
1911{ 0x229A, "ocir", "CIRCLED RING OPERATOR" },
1912{ 0x229B, "oast", "CIRCLED ASTERISK OPERATOR" },
1913{ 0x229D, "odash", "CIRCLED DASH" },
1914{ 0x229E, "plusb", "SQUARED PLUS" },
1915{ 0x229F, "minusb", "SQUARED MINUS" },
1916{ 0x22A0, "timesb", "SQUARED TIMES" },
1917{ 0x22A1, "sdotb", "SQUARED DOT OPERATOR" },
1918{ 0x22A2, "vdash", "" },
1919{ 0x22A3, "dashv", "" },
1920{ 0x22A4, "top", "DOWN TACK" },
1921{ 0x22A5, "bottom", "" },
1922{ 0x22A5, "perp", "" },
1923{ 0x22A7, "models", "MODELS" },
1924{ 0x22A8, "vDash", "" },
1925{ 0x22A9, "Vdash", "" },
1926{ 0x22AA, "Vvdash", "" },
1927{ 0x22AC, "nvdash", "DOES NOT PROVE" },
1928{ 0x22AD, "nvDash", "NOT TRUE" },
1929{ 0x22AE, "nVdash", "DOES NOT FORCE" },
1930{ 0x22AF, "nVDash", "NEGATED DOUBLE VERTICAL BAR DOUBLE RIGHT TURNSTILE" },
1931{ 0x22B2, "vltri", "" },
1932{ 0x22B3, "vrtri", "" },
1933{ 0x22B4, "ltrie", "" },
1934{ 0x22B5, "rtrie", "" },
1935{ 0x22B8, "mumap", "MULTIMAP" },
1936{ 0x22BA, "intcal", "INTERCALATE" },
1937{ 0x22BB, "veebar", "" },
1938{ 0x22BC, "barwed", "NAND" },
1939{ 0x22C4, "diam", "DIAMOND OPERATOR" },
1940{ 0x22C5, "sdot", "DOT OPERATOR" },
1941{ 0x22C6, "sstarf", "STAR OPERATOR" },
1942{ 0x22C6, "star", "STAR OPERATOR" },
1943{ 0x22C7, "divonx", "DIVISION TIMES" },
1944{ 0x22C8, "bowtie", "" },
1945{ 0x22C9, "ltimes", "LEFT NORMAL FACTOR SEMIDIRECT PRODUCT" },
1946{ 0x22CA, "rtimes", "RIGHT NORMAL FACTOR SEMIDIRECT PRODUCT" },
1947{ 0x22CB, "lthree", "LEFT SEMIDIRECT PRODUCT" },
1948{ 0x22CC, "rthree", "RIGHT SEMIDIRECT PRODUCT" },
1949{ 0x22CD, "bsime", "" },
1950{ 0x22CE, "cuvee", "CURLY LOGICAL OR" },
1951{ 0x22CF, "cuwed", "CURLY LOGICAL AND" },
1952{ 0x22D0, "Sub", "" },
1953{ 0x22D1, "Sup", "" },
1954{ 0x22D2, "Cap", "DOUBLE INTERSECTION" },
1955{ 0x22D3, "Cup", "DOUBLE UNION" },
1956{ 0x22D4, "fork", "" },
1957{ 0x22D6, "ldot", "" },
1958{ 0x22D7, "gsdot", "" },
1959{ 0x22D8, "Ll", "" },
1960{ 0x22D9, "Gg", "VERY MUCH GREATER-THAN" },
1961{ 0x22DA, "lEg", "" },
1962{ 0x22DA, "leg", "" },
1963{ 0x22DB, "gEl", "" },
1964{ 0x22DB, "gel", "" },
1965{ 0x22DC, "els", "" },
1966{ 0x22DD, "egs", "" },
1967{ 0x22DE, "cuepr", "" },
1968{ 0x22DF, "cuesc", "" },
1969{ 0x22E0, "npre", "DOES NOT PRECEDE OR EQUAL" },
1970{ 0x22E1, "nsce", "DOES NOT SUCCEED OR EQUAL" },
1971{ 0x22E6, "lnsim", "" },
1972{ 0x22E7, "gnsim", "GREATER-THAN BUT NOT EQUIVALENT TO" },
1973{ 0x22E8, "prnap", "" },
1974{ 0x22E8, "prnsim", "" },
1975{ 0x22E9, "scnap", "" },
1976{ 0x22E9, "scnsim", "" },
1977{ 0x22EA, "nltri", "NOT NORMAL SUBGROUP OF" },
1978{ 0x22EB, "nrtri", "DOES NOT CONTAIN AS NORMAL SUBGROUP" },
1979{ 0x22EC, "nltrie", "NOT NORMAL SUBGROUP OF OR EQUAL TO" },
1980{ 0x22ED, "nrtrie", "DOES NOT CONTAIN AS NORMAL SUBGROUP OR EQUAL" },
1981{ 0x22EE, "vellip", "" },
1982{ 0x2306, "Barwed", "PERSPECTIVE" },
1983{ 0x2308, "lceil", "LEFT CEILING" },
1984{ 0x2309, "rceil", "RIGHT CEILING" },
1985{ 0x230A, "lfloor", "LEFT FLOOR" },
1986{ 0x230B, "rfloor", "RIGHT FLOOR" },
1987{ 0x230C, "drcrop", "BOTTOM RIGHT CROP" },
1988{ 0x230D, "dlcrop", "BOTTOM LEFT CROP" },
1989{ 0x230E, "urcrop", "TOP RIGHT CROP" },
1990{ 0x230F, "ulcrop", "TOP LEFT CROP" },
1991{ 0x2315, "telrec", "TELEPHONE RECORDER" },
1992{ 0x2316, "target", "POSITION INDICATOR" },
1993{ 0x231C, "ulcorn", "TOP LEFT CORNER" },
1994{ 0x231D, "urcorn", "TOP RIGHT CORNER" },
1995{ 0x231E, "dlcorn", "BOTTOM LEFT CORNER" },
1996{ 0x231F, "drcorn", "BOTTOM RIGHT CORNER" },
1997{ 0x2322, "frown", "" },
1998{ 0x2322, "sfrown", "FROWN" },
1999{ 0x2323, "smile", "" },
2000{ 0x2323, "ssmile", "SMILE" },
2001{ 0x2423, "blank", "OPEN BOX" },
2002{ 0x24C8, "oS", "CIRCLED LATIN CAPITAL LETTER S" },
2003{ 0x2500, "boxh", "BOX DRAWINGS LIGHT HORIZONTAL" },
2004{ 0x2502, "boxv", "BOX DRAWINGS LIGHT VERTICAL" },
2005{ 0x250C, "boxdr", "BOX DRAWINGS LIGHT DOWN AND RIGHT" },
2006{ 0x2510, "boxdl", "BOX DRAWINGS LIGHT DOWN AND LEFT" },
2007{ 0x2514, "boxur", "BOX DRAWINGS LIGHT UP AND RIGHT" },
2008{ 0x2518, "boxul", "BOX DRAWINGS LIGHT UP AND LEFT" },
2009{ 0x251C, "boxvr", "BOX DRAWINGS LIGHT VERTICAL AND RIGHT" },
2010{ 0x2524, "boxvl", "BOX DRAWINGS LIGHT VERTICAL AND LEFT" },
2011{ 0x252C, "boxhd", "BOX DRAWINGS LIGHT DOWN AND HORIZONTAL" },
2012{ 0x2534, "boxhu", "BOX DRAWINGS LIGHT UP AND HORIZONTAL" },
2013{ 0x253C, "boxvh", "BOX DRAWINGS LIGHT VERTICAL AND HORIZONTAL" },
2014{ 0x2550, "boxH", "BOX DRAWINGS DOUBLE HORIZONTAL" },
2015{ 0x2551, "boxV", "BOX DRAWINGS DOUBLE VERTICAL" },
2016{ 0x2552, "boxDR", "BOX DRAWINGS DOWN SINGLE AND RIGHT DOUBLE" },
2017{ 0x2553, "boxDr", "BOX DRAWINGS DOWN DOUBLE AND RIGHT SINGLE" },
2018{ 0x2554, "boxdR", "BOX DRAWINGS DOUBLE DOWN AND RIGHT" },
2019{ 0x2555, "boxDL", "BOX DRAWINGS DOWN SINGLE AND LEFT DOUBLE" },
2020{ 0x2556, "boxdL", "BOX DRAWINGS DOWN DOUBLE AND LEFT SINGLE" },
2021{ 0x2557, "boxDl", "BOX DRAWINGS DOUBLE DOWN AND LEFT" },
2022{ 0x2558, "boxUR", "BOX DRAWINGS UP SINGLE AND RIGHT DOUBLE" },
2023{ 0x2559, "boxuR", "BOX DRAWINGS UP DOUBLE AND RIGHT SINGLE" },
2024{ 0x255A, "boxUr", "BOX DRAWINGS DOUBLE UP AND RIGHT" },
2025{ 0x255B, "boxUL", "BOX DRAWINGS UP SINGLE AND LEFT DOUBLE" },
2026{ 0x255C, "boxUl", "BOX DRAWINGS UP DOUBLE AND LEFT SINGLE" },
2027{ 0x255D, "boxuL", "BOX DRAWINGS DOUBLE UP AND LEFT" },
2028{ 0x255E, "boxvR", "BOX DRAWINGS VERTICAL SINGLE AND RIGHT DOUBLE" },
2029{ 0x255F, "boxVR", "BOX DRAWINGS VERTICAL DOUBLE AND RIGHT SINGLE" },
2030{ 0x2560, "boxVr", "BOX DRAWINGS DOUBLE VERTICAL AND RIGHT" },
2031{ 0x2561, "boxvL", "BOX DRAWINGS VERTICAL SINGLE AND LEFT DOUBLE" },
2032{ 0x2562, "boxVL", "BOX DRAWINGS VERTICAL DOUBLE AND LEFT SINGLE" },
2033{ 0x2563, "boxVl", "BOX DRAWINGS DOUBLE VERTICAL AND LEFT" },
2034{ 0x2564, "boxhD", "BOX DRAWINGS DOWN SINGLE AND HORIZONTAL DOUBLE" },
2035{ 0x2565, "boxHD", "BOX DRAWINGS DOWN DOUBLE AND HORIZONTAL SINGLE" },
2036{ 0x2566, "boxHd", "BOX DRAWINGS DOUBLE DOWN AND HORIZONTAL" },
2037{ 0x2567, "boxhU", "BOX DRAWINGS UP SINGLE AND HORIZONTAL DOUBLE" },
2038{ 0x2568, "boxHU", "BOX DRAWINGS UP DOUBLE AND HORIZONTAL SINGLE" },
2039{ 0x2569, "boxHu", "BOX DRAWINGS DOUBLE UP AND HORIZONTAL" },
2040{ 0x256A, "boxvH", "BOX DRAWINGS VERTICAL SINGLE AND HORIZONTAL DOUBLE" },
2041{ 0x256B, "boxVH", "BOX DRAWINGS VERTICAL DOUBLE AND HORIZONTAL SINGLE" },
2042{ 0x256C, "boxVh", "BOX DRAWINGS DOUBLE VERTICAL AND HORIZONTAL" },
2043{ 0x2580, "uhblk", "UPPER HALF BLOCK" },
2044{ 0x2584, "lhblk", "LOWER HALF BLOCK" },
2045{ 0x2588, "block", "FULL BLOCK" },
2046{ 0x2591, "blk14", "LIGHT SHADE" },
2047{ 0x2592, "blk12", "MEDIUM SHADE" },
2048{ 0x2593, "blk34", "DARK SHADE" },
2049{ 0x25A1, "square", "WHITE SQUARE" },
2050{ 0x25A1, "squ", "WHITE SQUARE" },
2051{ 0x25AA, "squf", "" },
2052{ 0x25AD, "rect", "WHITE RECTANGLE" },
2053{ 0x25AE, "marker", "BLACK VERTICAL RECTANGLE" },
2054{ 0x25B3, "xutri", "WHITE UP-POINTING TRIANGLE" },
2055{ 0x25B4, "utrif", "BLACK UP-POINTING TRIANGLE" },
2056{ 0x25B5, "utri", "WHITE UP-POINTING TRIANGLE" },
2057{ 0x25B8, "rtrif", "BLACK RIGHT-POINTING TRIANGLE" },
2058{ 0x25B9, "rtri", "WHITE RIGHT-POINTING TRIANGLE" },
2059{ 0x25BD, "xdtri", "WHITE DOWN-POINTING TRIANGLE" },
2060{ 0x25BE, "dtrif", "BLACK DOWN-POINTING TRIANGLE" },
2061{ 0x25BF, "dtri", "WHITE DOWN-POINTING TRIANGLE" },
2062{ 0x25C2, "ltrif", "BLACK LEFT-POINTING TRIANGLE" },
2063{ 0x25C3, "ltri", "WHITE LEFT-POINTING TRIANGLE" },
2064{ 0x25CA, "loz", "LOZENGE" },
2065{ 0x25CB, "cir", "WHITE CIRCLE" },
2066{ 0x25CB, "xcirc", "WHITE CIRCLE" },
2067{ 0x2605, "starf", "BLACK STAR" },
2068{ 0x260E, "phone", "TELEPHONE SIGN" },
2069{ 0x2640, "female", "" },
2070{ 0x2642, "male", "MALE SIGN" },
2071{ 0x2660, "spades", "BLACK SPADE SUIT" },
2072{ 0x2663, "clubs", "BLACK CLUB SUIT" },
2073{ 0x2665, "hearts", "BLACK HEART SUIT" },
2074{ 0x2666, "diams", "BLACK DIAMOND SUIT" },
2075{ 0x2669, "sung", "" },
2076{ 0x266D, "flat", "MUSIC FLAT SIGN" },
2077{ 0x266E, "natur", "MUSIC NATURAL SIGN" },
2078{ 0x266F, "sharp", "MUSIC SHARP SIGN" },
2079{ 0x2713, "check", "CHECK MARK" },
2080{ 0x2717, "cross", "BALLOT X" },
2081{ 0x2720, "malt", "MALTESE CROSS" },
2082{ 0x2726, "lozf", "" },
2083{ 0x2736, "sext", "SIX POINTED BLACK STAR" },
2084{ 0x3008, "lang", "" },
2085{ 0x3009, "rang", "" },
2086{ 0xE291, "rpargt", "" },
2087{ 0xE2A2, "lnap", "" },
2088{ 0xE2AA, "nsmid", "" },
2089{ 0xE2B3, "prnE", "" },
2090{ 0xE2B5, "scnE", "" },
2091{ 0xE2B8, "vsubnE", "" },
2092{ 0xE301, "smid", "" },
2093{ 0xE411, "gnap", "" },
2094{ 0xFB00, "fflig", "" },
2095{ 0xFB01, "filig", "" },
2096{ 0xFB02, "fllig", "" },
2097{ 0xFB03, "ffilig", "" },
2098{ 0xFB04, "ffllig", "" },
2099{ 0xFE68, "sbsol", "SMALL REVERSE SOLIDUS" },
2100};
2101
2102/************************************************************************
2103 * *
2104 * Commodity functions to handle entities *
2105 * *
2106 ************************************************************************/
2107
2108/*
2109 * Macro used to grow the current buffer.
2110 */
2111#define growBuffer(buffer) { \
2112 buffer##_size *= 2; \
2113 buffer = (xmlChar *) xmlRealloc(buffer, buffer##_size * sizeof(xmlChar)); \
2114 if (buffer == NULL) { \
2115 perror("realloc failed"); \
2116 return(NULL); \
2117 } \
2118}
2119
2120/**
2121 * docbEntityLookup:
2122 * @name: the entity name
2123 *
2124 * Lookup the given entity in EntitiesTable
2125 *
2126 * TODO: the linear scan is really ugly, an hash table is really needed.
2127 *
2128 * Returns the associated docbEntityDescPtr if found, NULL otherwise.
2129 */
2130static docbEntityDescPtr
2131docbEntityLookup(const xmlChar *name) {
2132 unsigned int i;
2133
2134 for (i = 0;i < (sizeof(docbookEntitiesTable)/
2135 sizeof(docbookEntitiesTable[0]));i++) {
2136 if (xmlStrEqual(name, BAD_CAST docbookEntitiesTable[i].name)) {
2137#ifdef DEBUG
2138 xmlGenericError(xmlGenericErrorContext,"Found entity %s\n", name);
2139#endif
2140 return(&docbookEntitiesTable[i]);
2141 }
2142 }
2143 return(NULL);
2144}
2145
2146/**
2147 * docbEntityValueLookup:
2148 * @value: the entity's unicode value
2149 *
2150 * Lookup the given entity in EntitiesTable
2151 *
2152 * TODO: the linear scan is really ugly, an hash table is really needed.
2153 *
2154 * Returns the associated docbEntityDescPtr if found, NULL otherwise.
2155 */
2156static docbEntityDescPtr
2157docbEntityValueLookup(int value) {
2158 unsigned int i;
2159#ifdef DEBUG
2160 int lv = 0;
2161#endif
2162
2163 for (i = 0;i < (sizeof(docbookEntitiesTable)/
2164 sizeof(docbookEntitiesTable[0]));i++) {
2165 if (docbookEntitiesTable[i].value >= value) {
2166 if (docbookEntitiesTable[i].value > value)
2167 break;
2168#ifdef DEBUG
2169 xmlGenericError(xmlGenericErrorContext,"Found entity %s\n", docbookEntitiesTable[i].name);
2170#endif
2171 return(&docbookEntitiesTable[i]);
2172 }
2173#ifdef DEBUG
2174 if (lv > docbookEntitiesTable[i].value) {
2175 xmlGenericError(xmlGenericErrorContext,
2176 "docbookEntitiesTable[] is not sorted (%d > %d)!\n",
2177 lv, docbookEntitiesTable[i].value);
2178 }
2179 lv = docbookEntitiesTable[i].value;
2180#endif
2181 }
2182 return(NULL);
2183}
2184
2185#if 0
2186/**
2187 * UTF8ToSgml:
2188 * @out: a pointer to an array of bytes to store the result
2189 * @outlen: the length of @out
2190 * @in: a pointer to an array of UTF-8 chars
2191 * @inlen: the length of @in
2192 *
2193 * Take a block of UTF-8 chars in and try to convert it to an ASCII
2194 * plus SGML entities block of chars out.
2195 *
2196 * Returns 0 if success, -2 if the transcoding fails, or -1 otherwise
2197 * The value of @inlen after return is the number of octets consumed
2198 * as the return value is positive, else unpredictiable.
2199 * The value of @outlen after return is the number of octets consumed.
2200 */
2201int
2202UTF8ToSgml(unsigned char* out, int *outlen,
2203 const unsigned char* in, int *inlen) {
2204 const unsigned char* processed = in;
2205 const unsigned char* outend;
2206 const unsigned char* outstart = out;
2207 const unsigned char* instart = in;
2208 const unsigned char* inend;
2209 unsigned int c, d;
2210 int trailing;
2211
2212 if (in == NULL) {
2213 /*
2214 * initialization nothing to do
2215 */
2216 *outlen = 0;
2217 *inlen = 0;
2218 return(0);
2219 }
2220 inend = in + (*inlen);
2221 outend = out + (*outlen);
2222 while (in < inend) {
2223 d = *in++;
2224 if (d < 0x80) { c= d; trailing= 0; }
2225 else if (d < 0xC0) {
2226 /* trailing byte in leading position */
2227 *outlen = out - outstart;
2228 *inlen = processed - instart;
2229 return(-2);
2230 } else if (d < 0xE0) { c= d & 0x1F; trailing= 1; }
2231 else if (d < 0xF0) { c= d & 0x0F; trailing= 2; }
2232 else if (d < 0xF8) { c= d & 0x07; trailing= 3; }
2233 else {
2234 /* no chance for this in Ascii */
2235 *outlen = out - outstart;
2236 *inlen = processed - instart;
2237 return(-2);
2238 }
2239
2240 if (inend - in < trailing) {
2241 break;
2242 }
2243
2244 for ( ; trailing; trailing--) {
2245 if ((in >= inend) || (((d= *in++) & 0xC0) != 0x80))
2246 break;
2247 c <<= 6;
2248 c |= d & 0x3F;
2249 }
2250
2251 /* assertion: c is a single UTF-4 value */
2252 if (c < 0x80) {
2253 if (out + 1 >= outend)
2254 break;
2255 *out++ = c;
2256 } else {
2257 int len;
2258 docbEntityDescPtr ent;
2259
2260 /*
2261 * Try to lookup a predefined SGML entity for it
2262 */
2263
2264 ent = docbEntityValueLookup(c);
2265 if (ent == NULL) {
2266 /* no chance for this in Ascii */
2267 *outlen = out - outstart;
2268 *inlen = processed - instart;
2269 return(-2);
2270 }
2271 len = strlen(ent->name);
2272 if (out + 2 + len >= outend)
2273 break;
2274 *out++ = '&';
2275 memcpy(out, ent->name, len);
2276 out += len;
2277 *out++ = ';';
2278 }
2279 processed = in;
2280 }
2281 *outlen = out - outstart;
2282 *inlen = processed - instart;
2283 return(0);
2284}
2285#endif
2286
2287/**
2288 * docbEncodeEntities:
2289 * @out: a pointer to an array of bytes to store the result
2290 * @outlen: the length of @out
2291 * @in: a pointer to an array of UTF-8 chars
2292 * @inlen: the length of @in
2293 * @quoteChar: the quote character to escape (' or ") or zero.
2294 *
2295 * Take a block of UTF-8 chars in and try to convert it to an ASCII
2296 * plus SGML entities block of chars out.
2297 *
2298 * Returns 0 if success, -2 if the transcoding fails, or -1 otherwise
2299 * The value of @inlen after return is the number of octets consumed
2300 * as the return value is positive, else unpredictiable.
2301 * The value of @outlen after return is the number of octets consumed.
2302 */
2303int
2304docbEncodeEntities(unsigned char* out, int *outlen,
2305 const unsigned char* in, int *inlen, int quoteChar) {
2306 const unsigned char* processed = in;
2307 const unsigned char* outend = out + (*outlen);
2308 const unsigned char* outstart = out;
2309 const unsigned char* instart = in;
2310 const unsigned char* inend = in + (*inlen);
2311 unsigned int c, d;
2312 int trailing;
2313
2314 while (in < inend) {
2315 d = *in++;
2316 if (d < 0x80) { c= d; trailing= 0; }
2317 else if (d < 0xC0) {
2318 /* trailing byte in leading position */
2319 *outlen = out - outstart;
2320 *inlen = processed - instart;
2321 return(-2);
2322 } else if (d < 0xE0) { c= d & 0x1F; trailing= 1; }
2323 else if (d < 0xF0) { c= d & 0x0F; trailing= 2; }
2324 else if (d < 0xF8) { c= d & 0x07; trailing= 3; }
2325 else {
2326 /* no chance for this in Ascii */
2327 *outlen = out - outstart;
2328 *inlen = processed - instart;
2329 return(-2);
2330 }
2331
2332 if (inend - in < trailing)
2333 break;
2334
2335 while (trailing--) {
2336 if (((d= *in++) & 0xC0) != 0x80) {
2337 *outlen = out - outstart;
2338 *inlen = processed - instart;
2339 return(-2);
2340 }
2341 c <<= 6;
2342 c |= d & 0x3F;
2343 }
2344
2345 /* assertion: c is a single UTF-4 value */
2346 if (c < 0x80 && c != (unsigned int) quoteChar && c != '&' && c != '<' && c != '>') {
2347 if (out >= outend)
2348 break;
2349 *out++ = c;
2350 } else {
2351 docbEntityDescPtr ent;
2352 const char *cp;
2353 char nbuf[16];
2354 int len;
2355
2356 /*
2357 * Try to lookup a predefined SGML entity for it
2358 */
2359 ent = docbEntityValueLookup(c);
2360 if (ent == NULL) {
2361 sprintf(nbuf, "#%u", c);
2362 cp = nbuf;
2363 }
2364 else
2365 cp = ent->name;
2366 len = strlen(cp);
2367 if (out + 2 + len > outend)
2368 break;
2369 *out++ = '&';
2370 memcpy(out, cp, len);
2371 out += len;
2372 *out++ = ';';
2373 }
2374 processed = in;
2375 }
2376 *outlen = out - outstart;
2377 *inlen = processed - instart;
2378 return(0);
2379}
2380
2381
2382/************************************************************************
2383 * *
2384 * Commodity functions to handle streams *
2385 * *
2386 ************************************************************************/
2387
2388/**
2389 * docbNewInputStream:
2390 * @ctxt: an SGML parser context
2391 *
2392 * Create a new input stream structure
2393 * Returns the new input stream or NULL
2394 */
2395static docbParserInputPtr
2396docbNewInputStream(docbParserCtxtPtr ctxt) {
2397 docbParserInputPtr input;
2398
2399 input = (xmlParserInputPtr) xmlMalloc(sizeof(docbParserInput));
2400 if (input == NULL) {
2401 ctxt->errNo = XML_ERR_NO_MEMORY;
2402 if ((ctxt->sax != NULL) && (ctxt->sax->error != NULL))
2403 ctxt->sax->error(ctxt->userData,
2404 "malloc: couldn't allocate a new input stream\n");
2405 return(NULL);
2406 }
2407 memset(input, 0, sizeof(docbParserInput));
2408 input->filename = NULL;
2409 input->directory = NULL;
2410 input->base = NULL;
2411 input->cur = NULL;
2412 input->buf = NULL;
2413 input->line = 1;
2414 input->col = 1;
2415 input->buf = NULL;
2416 input->free = NULL;
2417 input->version = NULL;
2418 input->consumed = 0;
2419 input->length = 0;
2420 return(input);
2421}
2422
2423
2424/************************************************************************
2425 * *
2426 * Commodity functions, cleanup needed ? *
2427 * *
2428 ************************************************************************/
2429
2430/**
2431 * areBlanks:
2432 * @ctxt: an SGML parser context
2433 * @str: a xmlChar *
2434 * @len: the size of @str
2435 *
2436 * Is this a sequence of blank chars that one can ignore ?
2437 *
2438 * Returns 1 if ignorable 0 otherwise.
2439 */
2440
2441static int areBlanks(docbParserCtxtPtr ctxt, const xmlChar *str, int len) {
2442 int i;
2443 xmlNodePtr lastChild;
2444
2445 for (i = 0;i < len;i++)
2446 if (!(IS_BLANK(str[i]))) return(0);
2447
2448 if (CUR == 0) return(1);
2449 if (CUR != '<') return(0);
2450 if (ctxt->name == NULL)
2451 return(1);
2452 if (ctxt->node == NULL) return(0);
2453 lastChild = xmlGetLastChild(ctxt->node);
2454 if (lastChild == NULL) {
2455 if (ctxt->node->content != NULL) return(0);
2456 } else if (xmlNodeIsText(lastChild))
2457 return(0);
2458 return(1);
2459}
2460
2461/************************************************************************
Daniel Veillard61b33d52001-04-24 13:55:12 +0000[diff] [blame]2462 * *
2463 * External entities support *
2464 * *
2465 ************************************************************************/
2466
2467/**
2468 * docbParseCtxtExternalEntity:
2469 * @ctx: the existing parsing context
2470 * @URL: the URL for the entity to load
2471 * @ID: the System ID for the entity to load
2472 * @list: the return value for the set of parsed nodes
2473 *
2474 * Parse an external general entity within an existing parsing context
2475 *
2476 * Returns 0 if the entity is well formed, -1 in case of args problem and
2477 * the parser error code otherwise
2478 */
2479
2480static int
2481docbParseCtxtExternalEntity(xmlParserCtxtPtr ctx, const xmlChar *URL,
2482 const xmlChar *ID, xmlNodePtr *list) {
2483 xmlParserCtxtPtr ctxt;
2484 xmlDocPtr newDoc;
2485 xmlSAXHandlerPtr oldsax = NULL;
2486 int ret = 0;
2487
2488 if (ctx->depth > 40) {
2489 return(XML_ERR_ENTITY_LOOP);
2490 }
2491
2492 if (list != NULL)
2493 *list = NULL;
2494 if ((URL == NULL) && (ID == NULL))
2495 return(-1);
2496 if (ctx->myDoc == NULL) /* @@ relax but check for dereferences */
2497 return(-1);
2498
2499
2500 ctxt = xmlCreateEntityParserCtxt(URL, ID, ctx->myDoc->URL);
2501 if (ctxt == NULL) return(-1);
2502 ctxt->userData = ctxt;
2503 oldsax = ctxt->sax;
2504 ctxt->sax = ctx->sax;
2505 newDoc = xmlNewDoc(BAD_CAST "1.0");
2506 if (newDoc == NULL) {
2507 xmlFreeParserCtxt(ctxt);
2508 return(-1);
2509 }
2510 if (ctx->myDoc != NULL) {
2511 newDoc->intSubset = ctx->myDoc->intSubset;
2512 newDoc->extSubset = ctx->myDoc->extSubset;
2513 }
2514 if (ctx->myDoc->URL != NULL) {
2515 newDoc->URL = xmlStrdup(ctx->myDoc->URL);
2516 }
2517 newDoc->children = xmlNewDocNode(newDoc, NULL, BAD_CAST "pseudoroot", NULL);
2518 if (newDoc->children == NULL) {
2519 ctxt->sax = oldsax;
2520 xmlFreeParserCtxt(ctxt);
2521 newDoc->intSubset = NULL;
2522 newDoc->extSubset = NULL;
2523 xmlFreeDoc(newDoc);
2524 return(-1);
2525 }
2526 nodePush(ctxt, newDoc->children);
2527 if (ctx->myDoc == NULL) {
2528 ctxt->myDoc = newDoc;
2529 } else {
2530 ctxt->myDoc = ctx->myDoc;
2531 newDoc->children->doc = ctx->myDoc;
2532 }
2533
2534 /*
2535 * Parse a possible text declaration first
2536 */
2537 GROW;
2538 if ((RAW == '<') && (NXT(1) == '?') &&
2539 (NXT(2) == 'x') && (NXT(3) == 'm') &&
2540 (NXT(4) == 'l') && (IS_BLANK(NXT(5)))) {
2541 xmlParseTextDecl(ctxt);
2542 }
2543
2544 /*
2545 * Doing validity checking on chunk doesn't make sense
2546 */
2547 ctxt->instate = XML_PARSER_CONTENT;
2548 ctxt->validate = ctx->validate;
2549 ctxt->loadsubset = ctx->loadsubset;
2550 ctxt->depth = ctx->depth + 1;
2551 ctxt->replaceEntities = ctx->replaceEntities;
2552 if (ctxt->validate) {
2553 ctxt->vctxt.error = ctx->vctxt.error;
2554 ctxt->vctxt.warning = ctx->vctxt.warning;
2555 /* Allocate the Node stack */
2556 ctxt->vctxt.nodeTab = (xmlNodePtr *) xmlMalloc(4 * sizeof(xmlNodePtr));
2557 if (ctxt->vctxt.nodeTab == NULL) {
2558 xmlGenericError(xmlGenericErrorContext,
2559 "docbParseCtxtExternalEntity: out of memory\n");
2560 ctxt->validate = 0;
2561 ctxt->vctxt.error = NULL;
2562 ctxt->vctxt.warning = NULL;
2563 } else {
2564 ctxt->vctxt.nodeNr = 0;
2565 ctxt->vctxt.nodeMax = 4;
2566 ctxt->vctxt.node = NULL;
2567 }
2568 } else {
2569 ctxt->vctxt.error = NULL;
2570 ctxt->vctxt.warning = NULL;
2571 }
2572
2573 docbParseContent(ctxt);
2574
2575 if ((RAW == '<') && (NXT(1) == '/')) {
2576 ctxt->errNo = XML_ERR_NOT_WELL_BALANCED;
2577 if ((ctxt->sax != NULL) && (ctxt->sax->error != NULL))
2578 ctxt->sax->error(ctxt->userData,
2579 "chunk is not well balanced\n");
2580 ctxt->wellFormed = 0;
2581 ctxt->disableSAX = 1;
2582 } else if (RAW != 0) {
2583 ctxt->errNo = XML_ERR_EXTRA_CONTENT;
2584 if ((ctxt->sax != NULL) && (ctxt->sax->error != NULL))
2585 ctxt->sax->error(ctxt->userData,
2586 "extra content at the end of well balanced chunk\n");
2587 ctxt->wellFormed = 0;
2588 ctxt->disableSAX = 1;
2589 }
2590 if (ctxt->node != newDoc->children) {
2591 ctxt->errNo = XML_ERR_NOT_WELL_BALANCED;
2592 if ((ctxt->sax != NULL) && (ctxt->sax->error != NULL))
2593 ctxt->sax->error(ctxt->userData,
2594 "chunk is not well balanced\n");
2595 ctxt->wellFormed = 0;
2596 ctxt->disableSAX = 1;
2597 }
2598
2599 if (!ctxt->wellFormed) {
2600 if (ctxt->errNo == 0)
2601 ret = 1;
2602 else
2603 ret = ctxt->errNo;
2604 } else {
2605 if (list != NULL) {
2606 xmlNodePtr cur;
2607
2608 /*
2609 * Return the newly created nodeset after unlinking it from
2610 * they pseudo parent.
2611 */
2612 cur = newDoc->children->children;
2613 *list = cur;
2614 while (cur != NULL) {
2615 cur->parent = NULL;
2616 cur = cur->next;
2617 }
2618 newDoc->children->children = NULL;
2619 }
2620 ret = 0;
2621 }
2622 ctxt->sax = oldsax;
2623 xmlFreeParserCtxt(ctxt);
2624 newDoc->intSubset = NULL;
2625 newDoc->extSubset = NULL;
2626 xmlFreeDoc(newDoc);
2627
2628 return(ret);
2629}
2630
2631/************************************************************************
2632 * *
2633 * The parser itself *
2634 * *
Daniel Veillardeae522a2001-04-23 13:41:34 +0000[diff] [blame]2635 ************************************************************************/
2636
2637/**
2638 * docbParseSGMLName:
2639 * @ctxt: an SGML parser context
2640 *
2641 * parse an SGML tag or attribute name, note that we convert it to lowercase
2642 * since SGML names are not case-sensitive.
2643 *
2644 * Returns the Tag Name parsed or NULL
2645 */
2646
2647static xmlChar *
2648docbParseSGMLName(docbParserCtxtPtr ctxt) {
2649 xmlChar *ret = NULL;
2650 int i = 0;
2651 xmlChar loc[DOCB_PARSER_BUFFER_SIZE];
2652
2653 if (!IS_LETTER(CUR) && (CUR != '_') &&
2654 (CUR != ':')) return(NULL);
2655
2656 while ((i < DOCB_PARSER_BUFFER_SIZE) &&
2657 ((IS_LETTER(CUR)) || (IS_DIGIT(CUR)) ||
2658 (CUR == ':') || (CUR == '_'))) {
2659 if ((CUR >= 'A') && (CUR <= 'Z')) loc[i] = CUR + 0x20;
2660 else loc[i] = CUR;
2661 i++;
2662
2663 NEXT;
2664 }
2665
2666 ret = xmlStrndup(loc, i);
2667
2668 return(ret);
2669}
2670
2671/**
2672 * docbParseName:
2673 * @ctxt: an SGML parser context
2674 *
2675 * parse an SGML name, this routine is case sensistive.
2676 *
2677 * Returns the Name parsed or NULL
2678 */
2679
2680static xmlChar *
2681docbParseName(docbParserCtxtPtr ctxt) {
2682 xmlChar buf[DOCB_MAX_NAMELEN];
2683 int len = 0;
2684
2685 GROW;
2686 if (!IS_LETTER(CUR) && (CUR != '_')) {
2687 return(NULL);
2688 }
2689
2690 while ((IS_LETTER(CUR)) || (IS_DIGIT(CUR)) ||
2691 (CUR == '.') || (CUR == '-') ||
2692 (CUR == '_') || (CUR == ':') ||
2693 (IS_COMBINING(CUR)) ||
2694 (IS_EXTENDER(CUR))) {
2695 buf[len++] = CUR;
2696 NEXT;
2697 if (len >= DOCB_MAX_NAMELEN) {
2698 xmlGenericError(xmlGenericErrorContext,
2699 "docbParseName: reached DOCB_MAX_NAMELEN limit\n");
2700 while ((IS_LETTER(CUR)) || (IS_DIGIT(CUR)) ||
2701 (CUR == '.') || (CUR == '-') ||
2702 (CUR == '_') || (CUR == ':') ||
2703 (IS_COMBINING(CUR)) ||
2704 (IS_EXTENDER(CUR)))
2705 NEXT;
2706 break;
2707 }
2708 }
2709 return(xmlStrndup(buf, len));
2710}
2711
2712/**
2713 * docbParseSGMLAttribute:
2714 * @ctxt: an SGML parser context
2715 * @stop: a char stop value
2716 *
2717 * parse an SGML attribute value till the stop (quote), if
2718 * stop is 0 then it stops at the first space
2719 *
2720 * Returns the attribute parsed or NULL
2721 */
2722
2723static xmlChar *
2724docbParseSGMLAttribute(docbParserCtxtPtr ctxt, const xmlChar stop) {
2725 xmlChar *buffer = NULL;
2726 int buffer_size = 0;
2727 xmlChar *out = NULL;
2728 xmlChar *name = NULL;
2729
2730 xmlChar *cur = NULL;
Daniel Veillard61b33d52001-04-24 13:55:12 +0000[diff] [blame]2731 xmlEntityPtr xent;
Daniel Veillardeae522a2001-04-23 13:41:34 +0000[diff] [blame]2732 docbEntityDescPtr ent;
2733
2734 /*
2735 * allocate a translation buffer.
2736 */
2737 buffer_size = DOCB_PARSER_BIG_BUFFER_SIZE;
2738 buffer = (xmlChar *) xmlMalloc(buffer_size * sizeof(xmlChar));
2739 if (buffer == NULL) {
2740 perror("docbParseSGMLAttribute: malloc failed");
2741 return(NULL);
2742 }
2743 out = buffer;
2744
2745 /*
2746 * Ok loop until we reach one of the ending chars
2747 */
2748 while ((CUR != 0) && (CUR != stop) && (CUR != '>')) {
2749 if ((stop == 0) && (IS_BLANK(CUR))) break;
2750 if (CUR == '&') {
2751 if (NXT(1) == '#') {
2752 unsigned int c;
2753 int bits;
2754
2755 c = docbParseCharRef(ctxt);
2756 if (c < 0x80)
2757 { *out++ = c; bits= -6; }
2758 else if (c < 0x800)
2759 { *out++ =((c >> 6) & 0x1F) | 0xC0; bits= 0; }
2760 else if (c < 0x10000)
2761 { *out++ =((c >> 12) & 0x0F) | 0xE0; bits= 6; }
2762 else
2763 { *out++ =((c >> 18) & 0x07) | 0xF0; bits= 12; }
2764
2765 for ( ; bits >= 0; bits-= 6) {
2766 *out++ = ((c >> bits) & 0x3F) | 0x80;
2767 }
2768 } else {
2769 ent = docbParseEntityRef(ctxt, &name);
2770 if (name == NULL) {
2771 *out++ = '&';
2772 if (out - buffer > buffer_size - 100) {
2773 int indx = out - buffer;
2774
2775 growBuffer(buffer);
2776 out = &buffer[indx];
2777 }
2778 } else if (ent == NULL) {
2779 *out++ = '&';
2780 cur = name;
2781 while (*cur != 0) {
2782 if (out - buffer > buffer_size - 100) {
2783 int indx = out - buffer;
2784
2785 growBuffer(buffer);
2786 out = &buffer[indx];
2787 }
2788 *out++ = *cur++;
2789 }
2790 xmlFree(name);
2791 } else {
2792 unsigned int c;
2793 int bits;
2794
2795 if (out - buffer > buffer_size - 100) {
2796 int indx = out - buffer;
2797
2798 growBuffer(buffer);
2799 out = &buffer[indx];
2800 }
2801 c = (xmlChar)ent->value;
2802 if (c < 0x80)
2803 { *out++ = c; bits= -6; }
2804 else if (c < 0x800)
2805 { *out++ =((c >> 6) & 0x1F) | 0xC0; bits= 0; }
2806 else if (c < 0x10000)
2807 { *out++ =((c >> 12) & 0x0F) | 0xE0; bits= 6; }
2808 else
2809 { *out++ =((c >> 18) & 0x07) | 0xF0; bits= 12; }
2810
2811 for ( ; bits >= 0; bits-= 6) {
2812 *out++ = ((c >> bits) & 0x3F) | 0x80;
2813 }
2814 xmlFree(name);
2815 }
2816 }
2817 } else {
2818 unsigned int c;
2819 int bits;
2820
2821 if (out - buffer > buffer_size - 100) {
2822 int indx = out - buffer;
2823
2824 growBuffer(buffer);
2825 out = &buffer[indx];
2826 }
2827 c = CUR;
2828 if (c < 0x80)
2829 { *out++ = c; bits= -6; }
2830 else if (c < 0x800)
2831 { *out++ =((c >> 6) & 0x1F) | 0xC0; bits= 0; }
2832 else if (c < 0x10000)
2833 { *out++ =((c >> 12) & 0x0F) | 0xE0; bits= 6; }
2834 else
2835 { *out++ =((c >> 18) & 0x07) | 0xF0; bits= 12; }
2836
2837 for ( ; bits >= 0; bits-= 6) {
2838 *out++ = ((c >> bits) & 0x3F) | 0x80;
2839 }
2840 NEXT;
2841 }
2842 }
2843 *out++ = 0;
2844 return(buffer);
2845}
2846
2847
2848/**
2849 * docbParseEntityRef:
2850 * @ctxt: an SGML parser context
2851 * @str: location to store the entity name
2852 *
2853 * parse an SGML ENTITY references
2854 *
2855 * [68] EntityRef ::= '&' Name ';'
2856 *
Daniel Veillard61b33d52001-04-24 13:55:12 +0000[diff] [blame]2857 * Returns the associated xmlEntityPtr if found, or NULL otherwise,
Daniel Veillardeae522a2001-04-23 13:41:34 +0000[diff] [blame]2858 * if non-NULL *str will have to be freed by the caller.
2859 */
Daniel Veillard61b33d52001-04-24 13:55:12 +0000[diff] [blame]2860static xmlEntityPtr
Daniel Veillardeae522a2001-04-23 13:41:34 +0000[diff] [blame]2861docbParseEntityRef(docbParserCtxtPtr ctxt, xmlChar **str) {
2862 xmlChar *name;
Daniel Veillard61b33d52001-04-24 13:55:12 +0000[diff] [blame]2863 xmlEntityPtr ent = NULL;
Daniel Veillardeae522a2001-04-23 13:41:34 +0000[diff] [blame]2864 *str = NULL;
2865
2866 if (CUR == '&') {
2867 NEXT;
2868 name = docbParseName(ctxt);
Daniel Veillard61b33d52001-04-24 13:55:12 +0000[diff] [blame]2869 if (name == NULL) {
2870 if ((ctxt->sax != NULL) && (ctxt->sax->error != NULL))
2871 ctxt->sax->error(ctxt->userData,
2872 "docbParseEntityRef: no name\n");
2873 ctxt->wellFormed = 0;
2874 } else {
Daniel Veillardeae522a2001-04-23 13:41:34 +0000[diff] [blame]2875 GROW;
Daniel Veillard61b33d52001-04-24 13:55:12 +0000[diff] [blame]2876 if (CUR == ';') {
2877 *str = name;
Daniel Veillardeae522a2001-04-23 13:41:34 +0000[diff] [blame]2878
Daniel Veillard61b33d52001-04-24 13:55:12 +0000[diff] [blame]2879 /*
2880 * Ask first SAX for entity resolution, otherwise try the
2881 * predefined set.
2882 */
2883 if (ctxt->sax != NULL) {
2884 if (ctxt->sax->getEntity != NULL)
2885 ent = ctxt->sax->getEntity(ctxt->userData, name);
2886 if (ent == NULL)
2887 ent = xmlGetPredefinedEntity(name);
2888 }
2889 NEXT;
2890 } else {
2891 if ((ctxt->sax != NULL) && (ctxt->sax->error != NULL))
2892 ctxt->sax->error(ctxt->userData,
Daniel Veillardeae522a2001-04-23 13:41:34 +0000[diff] [blame]2893 "docbParseEntityRef: expecting ';'\n");
Daniel Veillard61b33d52001-04-24 13:55:12 +0000[diff] [blame]2894 *str = name;
2895 }
2896 }
Daniel Veillardeae522a2001-04-23 13:41:34 +0000[diff] [blame]2897 }
2898 return(ent);
2899}
2900
2901/**
2902 * docbParseAttValue:
2903 * @ctxt: an SGML parser context
2904 *
2905 * parse a value for an attribute
2906 * Note: the parser won't do substitution of entities here, this
2907 * will be handled later in xmlStringGetNodeList, unless it was
2908 * asked for ctxt->replaceEntities != 0
2909 *
2910 * Returns the AttValue parsed or NULL.
2911 */
2912
2913static xmlChar *
2914docbParseAttValue(docbParserCtxtPtr ctxt) {
2915 xmlChar *ret = NULL;
2916
2917 if (CUR == '"') {
2918 NEXT;
2919 ret = docbParseSGMLAttribute(ctxt, '"');
2920 if (CUR != '"') {
2921 if ((ctxt->sax != NULL) && (ctxt->sax->error != NULL))
2922 ctxt->sax->error(ctxt->userData, "AttValue: ' expected\n");
2923 ctxt->wellFormed = 0;
2924 } else
2925 NEXT;
2926 } else if (CUR == '\'') {
2927 NEXT;
2928 ret = docbParseSGMLAttribute(ctxt, '\'');
2929 if (CUR != '\'') {
2930 if ((ctxt->sax != NULL) && (ctxt->sax->error != NULL))
2931 ctxt->sax->error(ctxt->userData, "AttValue: ' expected\n");
2932 ctxt->wellFormed = 0;
2933 } else
2934 NEXT;
2935 } else {
2936 /*
2937 * That's an SGMLism, the attribute value may not be quoted
2938 */
2939 ret = docbParseSGMLAttribute(ctxt, 0);
2940 if (ret == NULL) {
2941 if ((ctxt->sax != NULL) && (ctxt->sax->error != NULL))
2942 ctxt->sax->error(ctxt->userData, "AttValue: no value found\n");
2943 ctxt->wellFormed = 0;
2944 }
2945 }
2946 return(ret);
2947}
2948
2949/**
2950 * docbParseSystemLiteral:
2951 * @ctxt: an SGML parser context
2952 *
2953 * parse an SGML Literal
2954 *
2955 * [11] SystemLiteral ::= ('"' [^"]* '"') | ("'" [^']* "'")
2956 *
2957 * Returns the SystemLiteral parsed or NULL
2958 */
2959
2960static xmlChar *
2961docbParseSystemLiteral(docbParserCtxtPtr ctxt) {
2962 const xmlChar *q;
2963 xmlChar *ret = NULL;
2964
2965 if (CUR == '"') {
2966 NEXT;
2967 q = CUR_PTR;
2968 while ((IS_CHAR(CUR)) && (CUR != '"'))
2969 NEXT;
2970 if (!IS_CHAR(CUR)) {
2971 if ((ctxt->sax != NULL) && (ctxt->sax->error != NULL))
2972 ctxt->sax->error(ctxt->userData, "Unfinished SystemLiteral\n");
2973 ctxt->wellFormed = 0;
2974 } else {
2975 ret = xmlStrndup(q, CUR_PTR - q);
2976 NEXT;
2977 }
2978 } else if (CUR == '\'') {
2979 NEXT;
2980 q = CUR_PTR;
2981 while ((IS_CHAR(CUR)) && (CUR != '\''))
2982 NEXT;
2983 if (!IS_CHAR(CUR)) {
2984 if ((ctxt->sax != NULL) && (ctxt->sax->error != NULL))
2985 ctxt->sax->error(ctxt->userData, "Unfinished SystemLiteral\n");
2986 ctxt->wellFormed = 0;
2987 } else {
2988 ret = xmlStrndup(q, CUR_PTR - q);
2989 NEXT;
2990 }
2991 } else {
2992 if ((ctxt->sax != NULL) && (ctxt->sax->error != NULL))
2993 ctxt->sax->error(ctxt->userData,
2994 "SystemLiteral \" or ' expected\n");
2995 ctxt->wellFormed = 0;
2996 }
2997
2998 return(ret);
2999}
3000
3001/**
3002 * docbParsePubidLiteral:
3003 * @ctxt: an SGML parser context
3004 *
3005 * parse an SGML public literal
3006 *
3007 * [12] PubidLiteral ::= '"' PubidChar* '"' | "'" (PubidChar - "'")* "'"
3008 *
3009 * Returns the PubidLiteral parsed or NULL.
3010 */
3011
3012static xmlChar *
3013docbParsePubidLiteral(docbParserCtxtPtr ctxt) {
3014 const xmlChar *q;
3015 xmlChar *ret = NULL;
3016 /*
3017 * Name ::= (Letter | '_') (NameChar)*
3018 */
3019 if (CUR == '"') {
3020 NEXT;
3021 q = CUR_PTR;
3022 while (IS_PUBIDCHAR(CUR)) NEXT;
3023 if (CUR != '"') {
3024 if ((ctxt->sax != NULL) && (ctxt->sax->error != NULL))
3025 ctxt->sax->error(ctxt->userData, "Unfinished PubidLiteral\n");
3026 ctxt->wellFormed = 0;
3027 } else {
3028 ret = xmlStrndup(q, CUR_PTR - q);
3029 NEXT;
3030 }
3031 } else if (CUR == '\'') {
3032 NEXT;
3033 q = CUR_PTR;
3034 while ((IS_LETTER(CUR)) && (CUR != '\''))
3035 NEXT;
3036 if (!IS_LETTER(CUR)) {
3037 if ((ctxt->sax != NULL) && (ctxt->sax->error != NULL))
3038 ctxt->sax->error(ctxt->userData, "Unfinished PubidLiteral\n");
3039 ctxt->wellFormed = 0;
3040 } else {
3041 ret = xmlStrndup(q, CUR_PTR - q);
3042 NEXT;
3043 }
3044 } else {
3045 if ((ctxt->sax != NULL) && (ctxt->sax->error != NULL))
3046 ctxt->sax->error(ctxt->userData, "SystemLiteral \" or ' expected\n");
3047 ctxt->wellFormed = 0;
3048 }
3049
3050 return(ret);
3051}
3052
3053/**
3054 * docbParseCharData:
3055 * @ctxt: an SGML parser context
3056 * @cdata: int indicating whether we are within a CDATA section
3057 *
3058 * parse a CharData section.
3059 * if we are within a CDATA section ']]>' marks an end of section.
3060 *
3061 * [14] CharData ::= [^<&]* - ([^<&]* ']]>' [^<&]*)
3062 */
3063
3064static void
3065docbParseCharData(docbParserCtxtPtr ctxt) {
3066 xmlChar buf[DOCB_PARSER_BIG_BUFFER_SIZE + 5];
3067 int nbchar = 0;
3068 int cur, l;
3069
3070 SHRINK;
3071 cur = CUR_CHAR(l);
3072 while (((cur != '<') || (ctxt->token == '<')) &&
3073 ((cur != '&') || (ctxt->token == '&')) &&
3074 (IS_CHAR(cur))) {
3075 COPY_BUF(l,buf,nbchar,cur);
3076 if (nbchar >= DOCB_PARSER_BIG_BUFFER_SIZE) {
3077 /*
3078 * Ok the segment is to be consumed as chars.
3079 */
3080 if ((ctxt->sax != NULL) && (!ctxt->disableSAX)) {
3081 if (areBlanks(ctxt, buf, nbchar)) {
3082 if (ctxt->sax->ignorableWhitespace != NULL)
3083 ctxt->sax->ignorableWhitespace(ctxt->userData,
3084 buf, nbchar);
3085 } else {
3086 docbCheckParagraph(ctxt);
3087 if (ctxt->sax->characters != NULL)
3088 ctxt->sax->characters(ctxt->userData, buf, nbchar);
3089 }
3090 }
3091 nbchar = 0;
3092 }
3093 NEXTL(l);
3094 cur = CUR_CHAR(l);
3095 }
3096 if (nbchar != 0) {
3097 /*
3098 * Ok the segment is to be consumed as chars.
3099 */
3100 if ((ctxt->sax != NULL) && (!ctxt->disableSAX)) {
3101 if (areBlanks(ctxt, buf, nbchar)) {
3102 if (ctxt->sax->ignorableWhitespace != NULL)
3103 ctxt->sax->ignorableWhitespace(ctxt->userData, buf, nbchar);
3104 } else {
3105 docbCheckParagraph(ctxt);
3106 if (ctxt->sax->characters != NULL)
3107 ctxt->sax->characters(ctxt->userData, buf, nbchar);
3108 }
3109 }
3110 }
3111}
3112
3113/**
3114 * docbParseExternalID:
3115 * @ctxt: an SGML parser context
3116 * @publicID: a xmlChar** receiving PubidLiteral
3117 *
3118 * Parse an External ID or a Public ID
3119 *
3120 * Returns the function returns SystemLiteral and in the second
3121 * case publicID receives PubidLiteral,
3122 * it is possible to return NULL and have publicID set.
3123 */
3124
3125static xmlChar *
3126docbParseExternalID(docbParserCtxtPtr ctxt, xmlChar **publicID) {
3127 xmlChar *URI = NULL;
3128
3129 if ((UPPER == 'S') && (UPP(1) == 'Y') &&
3130 (UPP(2) == 'S') && (UPP(3) == 'T') &&
3131 (UPP(4) == 'E') && (UPP(5) == 'M')) {
3132 SKIP(6);
3133 if (!IS_BLANK(CUR)) {
3134 if ((ctxt->sax != NULL) && (ctxt->sax->error != NULL))
3135 ctxt->sax->error(ctxt->userData,
3136 "Space required after 'SYSTEM'\n");
3137 ctxt->wellFormed = 0;
3138 }
3139 SKIP_BLANKS;
3140 URI = docbParseSystemLiteral(ctxt);
3141 if (URI == NULL) {
3142 if ((ctxt->sax != NULL) && (ctxt->sax->error != NULL))
3143 ctxt->sax->error(ctxt->userData,
3144 "docbParseExternalID: SYSTEM, no URI\n");
3145 ctxt->wellFormed = 0;
3146 }
3147 } else if ((UPPER == 'P') && (UPP(1) == 'U') &&
3148 (UPP(2) == 'B') && (UPP(3) == 'L') &&
3149 (UPP(4) == 'I') && (UPP(5) == 'C')) {
3150 SKIP(6);
3151 if (!IS_BLANK(CUR)) {
3152 if ((ctxt->sax != NULL) && (ctxt->sax->error != NULL))
3153 ctxt->sax->error(ctxt->userData,
3154 "Space required after 'PUBLIC'\n");
3155 ctxt->wellFormed = 0;
3156 }
3157 SKIP_BLANKS;
3158 *publicID = docbParsePubidLiteral(ctxt);
3159 if (*publicID == NULL) {
3160 if ((ctxt->sax != NULL) && (ctxt->sax->error != NULL))
3161 ctxt->sax->error(ctxt->userData,
3162 "docbParseExternalID: PUBLIC, no Public Identifier\n");
3163 ctxt->wellFormed = 0;
3164 }
3165 SKIP_BLANKS;
3166 if ((CUR == '"') || (CUR == '\'')) {
3167 URI = docbParseSystemLiteral(ctxt);
3168 }
3169 }
3170 return(URI);
3171}
3172
3173/**
3174 * docbParseComment:
3175 * @ctxt: an SGML parser context
3176 *
3177 * Parse an XML (SGML) comment <!-- .... -->
3178 *
3179 * [15] Comment ::= '<!--' ((Char - '-') | ('-' (Char - '-')))* '-->'
3180 */
3181static void
3182docbParseComment(docbParserCtxtPtr ctxt) {
3183 xmlChar *buf = NULL;
3184 int len;
3185 int size = DOCB_PARSER_BUFFER_SIZE;
3186 int q, ql;
3187 int r, rl;
3188 int cur, l;
3189 xmlParserInputState state;
3190
3191 /*
3192 * Check that there is a comment right here.
3193 */
3194 if ((RAW != '<') || (NXT(1) != '!') ||
3195 (NXT(2) != '-') || (NXT(3) != '-')) return;
3196
3197 state = ctxt->instate;
3198 ctxt->instate = XML_PARSER_COMMENT;
3199 SHRINK;
3200 SKIP(4);
3201 buf = (xmlChar *) xmlMalloc(size * sizeof(xmlChar));
3202 if (buf == NULL) {
3203 xmlGenericError(xmlGenericErrorContext,
3204 "malloc of %d byte failed\n", size);
3205 ctxt->instate = state;
3206 return;
3207 }
3208 q = CUR_CHAR(ql);
3209 NEXTL(ql);
3210 r = CUR_CHAR(rl);
3211 NEXTL(rl);
3212 cur = CUR_CHAR(l);
3213 len = 0;
3214 while (IS_CHAR(cur) &&
3215 ((cur != '>') ||
3216 (r != '-') || (q != '-'))) {
3217 if (len + 5 >= size) {
3218 size *= 2;
3219 buf = (xmlChar *) xmlRealloc(buf, size * sizeof(xmlChar));
3220 if (buf == NULL) {
3221 xmlGenericError(xmlGenericErrorContext,
3222 "realloc of %d byte failed\n", size);
3223 ctxt->instate = state;
3224 return;
3225 }
3226 }
3227 COPY_BUF(ql,buf,len,q);
3228 q = r;
3229 ql = rl;
3230 r = cur;
3231 rl = l;
3232 NEXTL(l);
3233 cur = CUR_CHAR(l);
3234 if (cur == 0) {
3235 SHRINK;
3236 GROW;
3237 cur = CUR_CHAR(l);
3238 }
3239 }
3240 buf[len] = 0;
3241 if (!IS_CHAR(cur)) {
3242 ctxt->errNo = XML_ERR_COMMENT_NOT_FINISHED;
3243 if ((ctxt->sax != NULL) && (ctxt->sax->error != NULL))
3244 ctxt->sax->error(ctxt->userData,
3245 "Comment not terminated \n<!--%.50s\n", buf);
3246 ctxt->wellFormed = 0;
3247 xmlFree(buf);
3248 } else {
3249 NEXT;
3250 if ((ctxt->sax != NULL) && (ctxt->sax->comment != NULL) &&
3251 (!ctxt->disableSAX))
3252 ctxt->sax->comment(ctxt->userData, buf);
3253 xmlFree(buf);
3254 }
3255 ctxt->instate = state;
3256}
3257
3258/**
3259 * docbParseCharRef:
3260 * @ctxt: an SGML parser context
3261 *
3262 * parse Reference declarations
3263 *
3264 * [66] CharRef ::= '&#' [0-9]+ ';' |
3265 * '&#x' [0-9a-fA-F]+ ';'
3266 *
3267 * Returns the value parsed (as an int)
3268 */
3269static int
3270docbParseCharRef(docbParserCtxtPtr ctxt) {
3271 int val = 0;
3272
3273 if ((CUR == '&') && (NXT(1) == '#') &&
3274 (NXT(2) == 'x')) {
3275 SKIP(3);
3276 while (CUR != ';') {
3277 if ((CUR >= '0') && (CUR <= '9'))
3278 val = val * 16 + (CUR - '0');
3279 else if ((CUR >= 'a') && (CUR <= 'f'))
3280 val = val * 16 + (CUR - 'a') + 10;
3281 else if ((CUR >= 'A') && (CUR <= 'F'))
3282 val = val * 16 + (CUR - 'A') + 10;
3283 else {
3284 if ((ctxt->sax != NULL) && (ctxt->sax->error != NULL))
3285 ctxt->sax->error(ctxt->userData,
3286 "docbParseCharRef: invalid hexadecimal value\n");
3287 ctxt->wellFormed = 0;
3288 val = 0;
3289 break;
3290 }
3291 NEXT;
3292 }
3293 if (CUR == ';')
3294 NEXT;
3295 } else if ((CUR == '&') && (NXT(1) == '#')) {
3296 SKIP(2);
3297 while (CUR != ';') {
3298 if ((CUR >= '0') && (CUR <= '9'))
3299 val = val * 10 + (CUR - '0');
3300 else {
3301 if ((ctxt->sax != NULL) && (ctxt->sax->error != NULL))
3302 ctxt->sax->error(ctxt->userData,
3303 "docbParseCharRef: invalid decimal value\n");
3304 ctxt->wellFormed = 0;
3305 val = 0;
3306 break;
3307 }
3308 NEXT;
3309 }
3310 if (CUR == ';')
3311 NEXT;
3312 } else {
3313 if ((ctxt->sax != NULL) && (ctxt->sax->error != NULL))
3314 ctxt->sax->error(ctxt->userData, "docbParseCharRef: invalid value\n");
3315 ctxt->wellFormed = 0;
3316 }
3317 /*
3318 * Check the value IS_CHAR ...
3319 */
3320 if (IS_CHAR(val)) {
3321 return(val);
3322 } else {
3323 if ((ctxt->sax != NULL) && (ctxt->sax->error != NULL))
3324 ctxt->sax->error(ctxt->userData, "docbParseCharRef: invalid xmlChar value %d\n",
3325 val);
3326 ctxt->wellFormed = 0;
3327 }
3328 return(0);
3329}
3330
3331
3332/**
3333 * docbParseDocTypeDecl :
3334 * @ctxt: an SGML parser context
3335 *
3336 * parse a DOCTYPE declaration
3337 *
3338 * [28] doctypedecl ::= '<!DOCTYPE' S Name (S ExternalID)? S?
3339 * ('[' (markupdecl | PEReference | S)* ']' S?)? '>'
3340 */
3341
3342static void
3343docbParseDocTypeDecl(docbParserCtxtPtr ctxt) {
3344 xmlChar *name;
3345 xmlChar *ExternalID = NULL;
3346 xmlChar *URI = NULL;
3347
3348 /*
3349 * We know that '<!DOCTYPE' has been detected.
3350 */
3351 SKIP(9);
3352
3353 SKIP_BLANKS;
3354
3355 /*
3356 * Parse the DOCTYPE name.
3357 */
3358 name = docbParseName(ctxt);
3359 if (name == NULL) {
3360 if ((ctxt->sax != NULL) && (ctxt->sax->error != NULL))
3361 ctxt->sax->error(ctxt->userData, "docbParseDocTypeDecl : no DOCTYPE name !\n");
3362 ctxt->wellFormed = 0;
3363 }
3364 /*
3365 * Check that upper(name) == "SGML" !!!!!!!!!!!!!
3366 */
3367
3368 SKIP_BLANKS;
3369
3370 /*
3371 * Check for SystemID and ExternalID
3372 */
3373 URI = docbParseExternalID(ctxt, &ExternalID);
3374 SKIP_BLANKS;
3375
3376 /*
3377 * Create or update the document accordingly to the DOCTYPE
3378 */
3379 if ((ctxt->sax != NULL) && (ctxt->sax->internalSubset != NULL) &&
3380 (!ctxt->disableSAX))
3381 ctxt->sax->internalSubset(ctxt->userData, name, ExternalID, URI);
3382
3383 /*
3384 * Is there any internal subset declarations ?
3385 * they are handled separately in docbParseInternalSubset()
3386 */
Daniel Veillard61b33d52001-04-24 13:55:12 +0000[diff] [blame]3387 if (RAW != '[') {
Daniel Veillardeae522a2001-04-23 13:41:34 +0000[diff] [blame]3388 return;
3389
Daniel Veillard61b33d52001-04-24 13:55:12 +0000[diff] [blame]3390 /*
3391 * We should be at the end of the DOCTYPE declaration.
3392 */
3393 if (CUR != '>') {
3394 if ((ctxt->sax != NULL) && (ctxt->sax->error != NULL))
3395 ctxt->sax->error(ctxt->userData,
3396 "DOCTYPE unproperly terminated\n");
3397 ctxt->wellFormed = 0;
3398 /* We shouldn't try to resynchronize ... */
3399 }
3400 NEXT;
Daniel Veillardeae522a2001-04-23 13:41:34 +0000[diff] [blame]3401 }
Daniel Veillardeae522a2001-04-23 13:41:34 +0000[diff] [blame]3402
3403 /*
3404 * Cleanup, since we don't use all those identifiers
3405 */
3406 if (URI != NULL) xmlFree(URI);
3407 if (ExternalID != NULL) xmlFree(ExternalID);
3408 if (name != NULL) xmlFree(name);
3409}
3410
3411/**
3412 * docbParseAttribute:
3413 * @ctxt: an SGML parser context
3414 * @value: a xmlChar ** used to store the value of the attribute
3415 *
3416 * parse an attribute
3417 *
3418 * [41] Attribute ::= Name Eq AttValue
3419 *
3420 * [25] Eq ::= S? '=' S?
3421 *
3422 * With namespace:
3423 *
3424 * [NS 11] Attribute ::= QName Eq AttValue
3425 *
3426 * Also the case QName == xmlns:??? is handled independently as a namespace
3427 * definition.
3428 *
3429 * Returns the attribute name, and the value in *value.
3430 */
3431
3432static xmlChar *
3433docbParseAttribute(docbParserCtxtPtr ctxt, xmlChar **value) {
3434 xmlChar *name, *val = NULL;
3435
3436 *value = NULL;
3437 name = docbParseName(ctxt);
3438 if (name == NULL) {
3439 if ((ctxt->sax != NULL) && (ctxt->sax->error != NULL))
3440 ctxt->sax->error(ctxt->userData, "error parsing attribute name\n");
3441 ctxt->wellFormed = 0;
3442 return(NULL);
3443 }
3444
3445 /*
3446 * read the value
3447 */
3448 SKIP_BLANKS;
3449 if (CUR == '=') {
3450 NEXT;
3451 SKIP_BLANKS;
3452 val = docbParseAttValue(ctxt);
3453 /******
3454 } else {
3455 * TODO : some attribute must have values, some may not
3456 if ((ctxt->sax != NULL) && (ctxt->sax->error != NULL))
3457 ctxt->sax->warning(ctxt->userData,
3458 "No value for attribute %s\n", name); */
3459 }
3460
3461 *value = val;
3462 return(name);
3463}
3464
3465/**
3466 * docbCheckEncoding:
3467 * @ctxt: an SGML parser context
3468 * @attvalue: the attribute value
3469 *
3470 * Checks an http-equiv attribute from a Meta tag to detect
3471 * the encoding
3472 * If a new encoding is detected the parser is switched to decode
3473 * it and pass UTF8
3474 */
3475static void
3476docbCheckEncoding(docbParserCtxtPtr ctxt, const xmlChar *attvalue) {
3477 const xmlChar *encoding;
3478
3479 if ((ctxt == NULL) || (attvalue == NULL))
3480 return;
3481
3482 encoding = xmlStrstr(attvalue, BAD_CAST"charset=");
3483 if (encoding == NULL)
3484 encoding = xmlStrstr(attvalue, BAD_CAST"Charset=");
3485 if (encoding == NULL)
3486 encoding = xmlStrstr(attvalue, BAD_CAST"CHARSET=");
3487 if (encoding != NULL) {
3488 encoding += 8;
3489 } else {
3490 encoding = xmlStrstr(attvalue, BAD_CAST"charset =");
3491 if (encoding == NULL)
3492 encoding = xmlStrstr(attvalue, BAD_CAST"Charset =");
3493 if (encoding == NULL)
3494 encoding = xmlStrstr(attvalue, BAD_CAST"CHARSET =");
3495 if (encoding != NULL)
3496 encoding += 9;
3497 }
3498 /*
3499 * Restricted from 2.3.5 */
3500 if (encoding != NULL) {
3501 xmlCharEncoding enc;
3502
3503 if (ctxt->input->encoding != NULL)
3504 xmlFree((xmlChar *) ctxt->input->encoding);
3505 ctxt->input->encoding = encoding;
3506
3507 enc = xmlParseCharEncoding((const char *) encoding);
3508 if (enc == XML_CHAR_ENCODING_8859_1) {
3509 ctxt->charset = XML_CHAR_ENCODING_8859_1;
3510 } else if (enc != XML_CHAR_ENCODING_UTF8) {
3511 if ((ctxt->sax != NULL) && (ctxt->sax->error != NULL))
3512 ctxt->sax->error(ctxt->userData,
3513 "Unsupported encoding %s\n", encoding);
3514 /* xmlFree(encoding); */
3515 ctxt->wellFormed = 0;
3516 ctxt->disableSAX = 1;
3517 ctxt->errNo = XML_ERR_UNSUPPORTED_ENCODING;
3518 }
3519 }
3520}
3521
3522/**
3523 * docbCheckMeta:
3524 * @ctxt: an SGML parser context
3525 * @atts: the attributes values
3526 *
3527 * Checks an attributes from a Meta tag
3528 */
3529static void
3530docbCheckMeta(docbParserCtxtPtr ctxt, const xmlChar **atts) {
3531 int i;
3532 const xmlChar *att, *value;
3533 int http = 0;
3534 const xmlChar *content = NULL;
3535
3536 if ((ctxt == NULL) || (atts == NULL))
3537 return;
3538
3539 i = 0;
3540 att = atts[i++];
3541 while (att != NULL) {
3542 value = atts[i++];
3543 if ((value != NULL) &&
3544 ((xmlStrEqual(att, BAD_CAST"http-equiv")) ||
3545 (xmlStrEqual(att, BAD_CAST"Http-Equiv")) ||
3546 (xmlStrEqual(att, BAD_CAST"HTTP-EQUIV"))) &&
3547 ((xmlStrEqual(value, BAD_CAST"Content-Type")) ||
3548 (xmlStrEqual(value, BAD_CAST"content-type")) ||
3549 (xmlStrEqual(value, BAD_CAST"CONTENT-TYPE"))))
3550 http = 1;
3551 else if ((value != NULL) &&
3552 ((xmlStrEqual(att, BAD_CAST"content")) ||
3553 (xmlStrEqual(att, BAD_CAST"Content")) ||
3554 (xmlStrEqual(att, BAD_CAST"CONTENT"))))
3555 content = value;
3556 att = atts[i++];
3557 }
3558 if ((http) && (content != NULL))
3559 docbCheckEncoding(ctxt, content);
3560
3561}
3562
3563/**
3564 * docbParseStartTag:
3565 * @ctxt: an SGML parser context
3566 *
3567 * parse a start of tag either for rule element or
3568 * EmptyElement. In both case we don't parse the tag closing chars.
3569 *
3570 * [40] STag ::= '<' Name (S Attribute)* S? '>'
3571 *
3572 * [44] EmptyElemTag ::= '<' Name (S Attribute)* S? '/>'
3573 *
3574 * With namespace:
3575 *
3576 * [NS 8] STag ::= '<' QName (S Attribute)* S? '>'
3577 *
3578 * [NS 10] EmptyElement ::= '<' QName (S Attribute)* S? '/>'
3579 *
3580 */
3581
3582static void
3583docbParseStartTag(docbParserCtxtPtr ctxt) {
3584 xmlChar *name;
3585 xmlChar *attname;
3586 xmlChar *attvalue;
3587 const xmlChar **atts = NULL;
3588 int nbatts = 0;
3589 int maxatts = 0;
3590 int meta = 0;
3591 int i;
3592
3593 if (CUR != '<') return;
3594 NEXT;
3595
3596 GROW;
3597 name = docbParseSGMLName(ctxt);
3598 if (name == NULL) {
3599 if ((ctxt->sax != NULL) && (ctxt->sax->error != NULL))
3600 ctxt->sax->error(ctxt->userData,
3601 "docbParseStartTag: invalid element name\n");
3602 ctxt->wellFormed = 0;
3603 return;
3604 }
3605 if (xmlStrEqual(name, BAD_CAST"meta"))
3606 meta = 1;
3607
3608 /*
3609 * Check for auto-closure of SGML elements.
3610 */
3611 docbAutoClose(ctxt, name);
3612
3613 /*
3614 * Now parse the attributes, it ends up with the ending
3615 *
3616 * (S Attribute)* S?
3617 */
3618 SKIP_BLANKS;
3619 while ((IS_CHAR(CUR)) &&
3620 (CUR != '>') &&
3621 ((CUR != '/') || (NXT(1) != '>'))) {
3622 long cons = ctxt->nbChars;
3623
3624 GROW;
3625 attname = docbParseAttribute(ctxt, &attvalue);
3626 if (attname != NULL) {
3627
3628 /*
3629 * Well formedness requires at most one declaration of an attribute
3630 */
3631 for (i = 0; i < nbatts;i += 2) {
3632 if (xmlStrEqual(atts[i], attname)) {
3633 if ((ctxt->sax != NULL) && (ctxt->sax->error != NULL))
3634 ctxt->sax->error(ctxt->userData,
3635 "Attribute %s redefined\n",
3636 attname);
3637 ctxt->wellFormed = 0;
3638 xmlFree(attname);
3639 if (attvalue != NULL)
3640 xmlFree(attvalue);
3641 goto failed;
3642 }
3643 }
3644
3645 /*
3646 * Add the pair to atts
3647 */
3648 if (atts == NULL) {
3649 maxatts = 10;
3650 atts = (const xmlChar **) xmlMalloc(maxatts * sizeof(xmlChar *));
3651 if (atts == NULL) {
3652 xmlGenericError(xmlGenericErrorContext,
3653 "malloc of %ld byte failed\n",
3654 maxatts * (long)sizeof(xmlChar *));
3655 if (name != NULL) xmlFree(name);
3656 return;
3657 }
3658 } else if (nbatts + 4 > maxatts) {
3659 maxatts *= 2;
3660 atts = (const xmlChar **) xmlRealloc(atts, maxatts * sizeof(xmlChar *));
3661 if (atts == NULL) {
3662 xmlGenericError(xmlGenericErrorContext,
3663 "realloc of %ld byte failed\n",
3664 maxatts * (long)sizeof(xmlChar *));
3665 if (name != NULL) xmlFree(name);
3666 return;
3667 }
3668 }
3669 atts[nbatts++] = attname;
3670 atts[nbatts++] = attvalue;
3671 atts[nbatts] = NULL;
3672 atts[nbatts + 1] = NULL;
3673 }
3674
3675failed:
3676 SKIP_BLANKS;
3677 if (cons == ctxt->nbChars) {
3678 if ((ctxt->sax != NULL) && (ctxt->sax->error != NULL))
3679 ctxt->sax->error(ctxt->userData,
3680 "docbParseStartTag: problem parsing attributes\n");
3681 ctxt->wellFormed = 0;
3682 break;
3683 }
3684 }
3685
3686 /*
3687 * Handle specific association to the META tag
3688 */
3689 if (meta)
3690 docbCheckMeta(ctxt, atts);
3691
3692 /*
3693 * SAX: Start of Element !
3694 */
3695 docbnamePush(ctxt, xmlStrdup(name));
3696#ifdef DEBUG
3697 xmlGenericError(xmlGenericErrorContext,"Start of element %s: pushed %s\n", name, ctxt->name);
3698#endif
3699 if ((ctxt->sax != NULL) && (ctxt->sax->startElement != NULL))
3700 ctxt->sax->startElement(ctxt->userData, name, atts);
3701
3702 if (atts != NULL) {
3703 for (i = 0;i < nbatts;i++) {
3704 if (atts[i] != NULL)
3705 xmlFree((xmlChar *) atts[i]);
3706 }
3707 xmlFree((void *) atts);
3708 }
3709 if (name != NULL) xmlFree(name);
3710}
3711
3712/**
3713 * docbParseEndTag:
3714 * @ctxt: an SGML parser context
3715 *
3716 * parse an end of tag
3717 *
3718 * [42] ETag ::= '</' Name S? '>'
3719 *
3720 * With namespace
3721 *
3722 * [NS 9] ETag ::= '</' QName S? '>'
3723 */
3724
3725static void
3726docbParseEndTag(docbParserCtxtPtr ctxt) {
3727 xmlChar *name;
3728 xmlChar *oldname;
3729 int i;
3730
3731 if ((CUR != '<') || (NXT(1) != '/')) {
3732 if ((ctxt->sax != NULL) && (ctxt->sax->error != NULL))
3733 ctxt->sax->error(ctxt->userData, "docbParseEndTag: '</' not found\n");
3734 ctxt->wellFormed = 0;
3735 return;
3736 }
3737 SKIP(2);
3738
3739 name = docbParseSGMLName(ctxt);
3740 if (name == NULL) {
3741 if (CUR == '>') {
3742 NEXT;
3743 oldname = docbnamePop(ctxt);
3744 if (oldname != NULL) {
3745 if ((ctxt->sax != NULL) && (ctxt->sax->endElement != NULL))
3746 ctxt->sax->endElement(ctxt->userData, name);
3747#ifdef DEBUG
3748 xmlGenericError(xmlGenericErrorContext,"End of tag </>: popping out %s\n", oldname);
3749#endif
3750 xmlFree(oldname);
3751#ifdef DEBUG
3752 } else {
3753 xmlGenericError(xmlGenericErrorContext,"End of tag </>: stack empty !!!\n");
3754#endif
3755 }
3756 return;
3757 } else
3758 return;
3759 }
3760
3761 /*
3762 * We should definitely be at the ending "S? '>'" part
3763 */
3764 SKIP_BLANKS;
3765 if ((!IS_CHAR(CUR)) || (CUR != '>')) {
3766 if ((ctxt->sax != NULL) && (ctxt->sax->error != NULL))
3767 ctxt->sax->error(ctxt->userData, "End tag : expected '>'\n");
3768 ctxt->wellFormed = 0;
3769 } else
3770 NEXT;
3771
3772 /*
3773 * If the name read is not one of the element in the parsing stack
3774 * then return, it's just an error.
3775 */
3776 for (i = (ctxt->nameNr - 1);i >= 0;i--) {
3777 if (xmlStrEqual(name, ctxt->nameTab[i])) break;
3778 }
3779 if (i < 0) {
3780 if ((ctxt->sax != NULL) && (ctxt->sax->error != NULL))
3781 ctxt->sax->error(ctxt->userData,
3782 "Unexpected end tag : %s\n", name);
3783 xmlFree(name);
3784 ctxt->wellFormed = 0;
3785 return;
3786 }
3787
3788
3789 /*
3790 * Check for auto-closure of SGML elements.
3791 */
3792
3793 docbAutoCloseOnClose(ctxt, name);
3794
3795 /*
3796 * Well formedness constraints, opening and closing must match.
3797 * With the exception that the autoclose may have popped stuff out
3798 * of the stack.
3799 */
3800 if (((name[0] != '/') || (name[1] != 0)) &&
3801 (!xmlStrEqual(name, ctxt->name))) {
3802#ifdef DEBUG
3803 xmlGenericError(xmlGenericErrorContext,"End of tag %s: expecting %s\n", name, ctxt->name);
3804#endif
3805 if ((ctxt->name != NULL) &&
3806 (!xmlStrEqual(ctxt->name, name))) {
3807 if ((ctxt->sax != NULL) && (ctxt->sax->error != NULL))
3808 ctxt->sax->error(ctxt->userData,
3809 "Opening and ending tag mismatch: %s and %s\n",
3810 name, ctxt->name);
3811 ctxt->wellFormed = 0;
3812 }
3813 }
3814
3815 /*
3816 * SAX: End of Tag
3817 */
3818 oldname = ctxt->name;
3819 if (((name[0] == '/') && (name[1] == 0)) ||
3820 ((oldname != NULL) && (xmlStrEqual(oldname, name)))) {
3821 if ((ctxt->sax != NULL) && (ctxt->sax->endElement != NULL))
3822 ctxt->sax->endElement(ctxt->userData, name);
3823 oldname = docbnamePop(ctxt);
3824 if (oldname != NULL) {
3825#ifdef DEBUG
3826 xmlGenericError(xmlGenericErrorContext,"End of tag %s: popping out %s\n", name, oldname);
3827#endif
3828 xmlFree(oldname);
3829#ifdef DEBUG
3830 } else {
3831 xmlGenericError(xmlGenericErrorContext,"End of tag %s: stack empty !!!\n", name);
3832#endif
3833 }
3834 }
3835
3836 if (name != NULL)
3837 xmlFree(name);
3838
3839 return;
3840}
3841
3842
3843/**
3844 * docbParseReference:
3845 * @ctxt: an SGML parser context
3846 *
3847 * parse and handle entity references in content,
3848 * this will end-up in a call to character() since this is either a
3849 * CharRef, or a predefined entity.
3850 */
3851static void
3852docbParseReference(docbParserCtxtPtr ctxt) {
3853 docbEntityDescPtr ent;
Daniel Veillard61b33d52001-04-24 13:55:12 +0000[diff] [blame]3854 xmlEntityPtr xent;
Daniel Veillardeae522a2001-04-23 13:41:34 +0000[diff] [blame]3855 xmlChar out[6];
3856 xmlChar *name;
3857 if (CUR != '&') return;
3858
3859 if (NXT(1) == '#') {
3860 unsigned int c;
3861 int bits, i = 0;
3862
3863 c = docbParseCharRef(ctxt);
3864 if (c < 0x80) { out[i++]= c; bits= -6; }
3865 else if (c < 0x800) { out[i++]=((c >> 6) & 0x1F) | 0xC0; bits= 0; }
3866 else if (c < 0x10000) { out[i++]=((c >> 12) & 0x0F) | 0xE0; bits= 6; }
3867 else { out[i++]=((c >> 18) & 0x07) | 0xF0; bits= 12; }
3868
3869 for ( ; bits >= 0; bits-= 6) {
3870 out[i++]= ((c >> bits) & 0x3F) | 0x80;
3871 }
3872 out[i] = 0;
3873
3874 docbCheckParagraph(ctxt);
3875 if ((ctxt->sax != NULL) && (ctxt->sax->characters != NULL))
3876 ctxt->sax->characters(ctxt->userData, out, i);
3877 } else {
Daniel Veillard61b33d52001-04-24 13:55:12 +0000[diff] [blame]3878 /*
3879 * Lookup the entity in the table.
3880 */
3881 xent = docbParseEntityRef(ctxt, &name);
3882 if (xent != NULL) {
3883 if ((ctxt->sax != NULL) && (ctxt->sax->reference != NULL) &&
3884 (ctxt->replaceEntities == 0) && (!ctxt->disableSAX)) {
3885 /*
3886 * Create a node.
3887 */
3888 ctxt->sax->reference(ctxt->userData, xent->name);
3889 return;
3890 } else if (ctxt->replaceEntities) {
3891 if ((xent->children == NULL) &&
3892 (xent->etype == XML_EXTERNAL_GENERAL_PARSED_ENTITY)) {
3893 /*
3894 * we really need to fetch and parse the external entity
3895 */
3896 int parse;
3897 xmlNodePtr children = NULL;
3898
3899 parse = docbParseCtxtExternalEntity(ctxt,
3900 xent->SystemID, xent->ExternalID, &children);
3901 xmlAddChildList((xmlNodePtr) xent, children);
3902 }
3903 if ((ctxt->node != NULL) && (xent->children != NULL)) {
3904 /*
3905 * Seems we are generating the DOM content, do
3906 * a simple tree copy
3907 */
3908 xmlNodePtr new;
3909 new = xmlCopyNodeList(xent->children);
3910
3911 xmlAddChildList(ctxt->node, new);
3912 /*
3913 * This is to avoid a nasty side effect, see
3914 * characters() in SAX.c
3915 */
3916 ctxt->nodemem = 0;
3917 ctxt->nodelen = 0;
3918 }
3919 }
3920 } else if (name != NULL) {
3921 ent = docbEntityLookup(name);
3922 if ((ent == NULL) || (ent->value <= 0)) {
3923 docbCheckParagraph(ctxt);
3924 if ((ctxt->sax != NULL) && (ctxt->sax->characters != NULL)) {
3925 ctxt->sax->characters(ctxt->userData, BAD_CAST "&", 1);
3926 ctxt->sax->characters(ctxt->userData, name, xmlStrlen(name));
3927 /* ctxt->sax->characters(ctxt->userData, BAD_CAST ";", 1); */
3928 }
3929 } else {
3930 unsigned int c;
3931 int bits, i = 0;
3932
3933 c = ent->value;
3934 if (c < 0x80)
3935 { out[i++]= c; bits= -6; }
3936 else if (c < 0x800)
3937 { out[i++]=((c >> 6) & 0x1F) | 0xC0; bits= 0; }
3938 else if (c < 0x10000)
3939 { out[i++]=((c >> 12) & 0x0F) | 0xE0; bits= 6; }
3940 else
3941 { out[i++]=((c >> 18) & 0x07) | 0xF0; bits= 12; }
3942
3943 for ( ; bits >= 0; bits-= 6) {
3944 out[i++]= ((c >> bits) & 0x3F) | 0x80;
3945 }
3946 out[i] = 0;
3947
3948 docbCheckParagraph(ctxt);
3949 if ((ctxt->sax != NULL) && (ctxt->sax->characters != NULL))
3950 ctxt->sax->characters(ctxt->userData, out, i);
3951 }
3952 } else {
Daniel Veillardeae522a2001-04-23 13:41:34 +0000[diff] [blame]3953 docbCheckParagraph(ctxt);
3954 if ((ctxt->sax != NULL) && (ctxt->sax->characters != NULL))
3955 ctxt->sax->characters(ctxt->userData, BAD_CAST "&", 1);
3956 return;
3957 }
Daniel Veillard61b33d52001-04-24 13:55:12 +0000[diff] [blame]3958 if (name != NULL)
3959 xmlFree(name);
Daniel Veillardeae522a2001-04-23 13:41:34 +0000[diff] [blame]3960 }
3961}
3962
3963/**
3964 * docbParseContent:
3965 * @ctxt: an SGML parser context
3966 * @name: the node name
3967 *
3968 * Parse a content: comment, sub-element, reference or text.
3969 *
3970 */
3971
3972static void
3973docbParseContent(docbParserCtxtPtr ctxt) {
3974 xmlChar *currentNode;
3975 int depth;
3976
3977 currentNode = xmlStrdup(ctxt->name);
3978 depth = ctxt->nameNr;
3979 while (1) {
3980 long cons = ctxt->nbChars;
3981
3982 GROW;
3983 /*
3984 * Our tag or one of it's parent or children is ending.
3985 */
3986 if ((CUR == '<') && (NXT(1) == '/')) {
3987 docbParseEndTag(ctxt);
3988 if (currentNode != NULL) xmlFree(currentNode);
3989 return;
3990 }
3991
3992 /*
3993 * Has this node been popped out during parsing of
3994 * the next element
3995 */
3996 if ((!xmlStrEqual(currentNode, ctxt->name)) &&
3997 (depth >= ctxt->nameNr)) {
3998 if (currentNode != NULL) xmlFree(currentNode);
3999 return;
4000 }
4001
4002 /*
4003 * Sometimes DOCTYPE arrives in the middle of the document
4004 */
4005 if ((CUR == '<') && (NXT(1) == '!') &&
4006 (UPP(2) == 'D') && (UPP(3) == 'O') &&
4007 (UPP(4) == 'C') && (UPP(5) == 'T') &&
4008 (UPP(6) == 'Y') && (UPP(7) == 'P') &&
4009 (UPP(8) == 'E')) {
4010 if ((ctxt->sax != NULL) && (ctxt->sax->error != NULL))
4011 ctxt->sax->error(ctxt->userData,
4012 "Misplaced DOCTYPE declaration\n");
4013 ctxt->wellFormed = 0;
4014 docbParseDocTypeDecl(ctxt);
4015 }
4016
4017 /*
4018 * First case : a comment
4019 */
4020 if ((CUR == '<') && (NXT(1) == '!') &&
4021 (NXT(2) == '-') && (NXT(3) == '-')) {
4022 docbParseComment(ctxt);
4023 }
4024
4025 /*
4026 * Second case : a sub-element.
4027 */
4028 else if (CUR == '<') {
4029 docbParseElement(ctxt);
4030 }
4031
4032 /*
4033 * Third case : a reference. If if has not been resolved,
4034 * parsing returns it's Name, create the node
4035 */
4036 else if (CUR == '&') {
4037 docbParseReference(ctxt);
4038 }
4039
4040 /*
4041 * Fourth : end of the resource
4042 */
4043 else if (CUR == 0) {
4044 docbAutoClose(ctxt, NULL);
Daniel Veillard61b33d52001-04-24 13:55:12 +0000[diff] [blame]4045 if (ctxt->nameNr == 0)
4046 break;
Daniel Veillardeae522a2001-04-23 13:41:34 +0000[diff] [blame]4047 }
4048
4049 /*
4050 * Last case, text. Note that References are handled directly.
4051 */
4052 else {
4053 docbParseCharData(ctxt);
4054 }
4055
4056 if (cons == ctxt->nbChars) {
4057 if (ctxt->node != NULL) {
4058 if ((ctxt->sax != NULL) && (ctxt->sax->error != NULL))
4059 ctxt->sax->error(ctxt->userData,
4060 "detected an error in element content\n");
4061 ctxt->wellFormed = 0;
4062 }
Daniel Veillard61b33d52001-04-24 13:55:12 +0000[diff] [blame]4063 break;
Daniel Veillardeae522a2001-04-23 13:41:34 +0000[diff] [blame]4064 }
4065
4066 GROW;
4067 }
4068 if (currentNode != NULL) xmlFree(currentNode);
4069}
4070
4071/**
4072 * docbParseElement:
4073 * @ctxt: an SGML parser context
4074 *
4075 * parse an SGML element, this is highly recursive
4076 *
4077 * [39] element ::= EmptyElemTag | STag content ETag
4078 *
4079 * [41] Attribute ::= Name Eq AttValue
4080 */
4081
4082static void
4083docbParseElement(docbParserCtxtPtr ctxt) {
4084 xmlChar *name;
4085 xmlChar *currentNode = NULL;
4086 docbElemDescPtr info;
4087 docbParserNodeInfo node_info;
4088 xmlChar *oldname;
4089 int depth = ctxt->nameNr;
4090
4091 /* Capture start position */
4092 if (ctxt->record_info) {
4093 node_info.begin_pos = ctxt->input->consumed +
4094 (CUR_PTR - ctxt->input->base);
4095 node_info.begin_line = ctxt->input->line;
4096 }
4097
4098 oldname = xmlStrdup(ctxt->name);
4099 docbParseStartTag(ctxt);
4100 name = ctxt->name;
4101#ifdef DEBUG
4102 if (oldname == NULL)
4103 xmlGenericError(xmlGenericErrorContext,
4104 "Start of element %s\n", name);
4105 else if (name == NULL)
4106 xmlGenericError(xmlGenericErrorContext,
4107 "Start of element failed, was %s\n", oldname);
4108 else
4109 xmlGenericError(xmlGenericErrorContext,
4110 "Start of element %s, was %s\n", name, oldname);
4111#endif
4112 if (((depth == ctxt->nameNr) && (xmlStrEqual(oldname, ctxt->name))) ||
4113 (name == NULL)) {
4114 if (CUR == '>')
4115 NEXT;
4116 if (oldname != NULL)
4117 xmlFree(oldname);
4118 return;
4119 }
4120 if (oldname != NULL)
4121 xmlFree(oldname);
4122
4123 /*
4124 * Lookup the info for that element.
4125 */
4126 info = docbTagLookup(name);
4127 if (info == NULL) {
4128 if ((ctxt->sax != NULL) && (ctxt->sax->error != NULL))
4129 ctxt->sax->error(ctxt->userData, "Tag %s unknown\n",
4130 name);
4131 ctxt->wellFormed = 0;
4132 } else if (info->depr) {
4133/***************************
4134 if ((ctxt->sax != NULL) && (ctxt->sax->warning != NULL))
4135 ctxt->sax->warning(ctxt->userData, "Tag %s is deprecated\n",
4136 name);
4137 ***************************/
4138 }
4139
4140 /*
4141 * Check for an Empty Element labelled the XML/SGML way
4142 */
4143 if ((CUR == '/') && (NXT(1) == '>')) {
4144 SKIP(2);
4145 if ((ctxt->sax != NULL) && (ctxt->sax->endElement != NULL))
4146 ctxt->sax->endElement(ctxt->userData, name);
4147 oldname = docbnamePop(ctxt);
4148#ifdef DEBUG
4149 xmlGenericError(xmlGenericErrorContext,"End of tag the XML way: popping out %s\n", oldname);
4150#endif
4151 if (oldname != NULL)
4152 xmlFree(oldname);
4153 return;
4154 }
4155
4156 if (CUR == '>') {
4157 NEXT;
4158 } else {
4159 if ((ctxt->sax != NULL) && (ctxt->sax->error != NULL))
4160 ctxt->sax->error(ctxt->userData,
4161 "Couldn't find end of Start Tag %s\n",
4162 name);
4163 ctxt->wellFormed = 0;
4164
4165 /*
4166 * end of parsing of this node.
4167 */
4168 if (xmlStrEqual(name, ctxt->name)) {
4169 nodePop(ctxt);
4170 oldname = docbnamePop(ctxt);
4171#ifdef DEBUG
4172 xmlGenericError(xmlGenericErrorContext,"End of start tag problem: popping out %s\n", oldname);
4173#endif
4174 if (oldname != NULL)
4175 xmlFree(oldname);
4176 }
4177
4178 /*
4179 * Capture end position and add node
4180 */
4181 if ( currentNode != NULL && ctxt->record_info ) {
4182 node_info.end_pos = ctxt->input->consumed +
4183 (CUR_PTR - ctxt->input->base);
4184 node_info.end_line = ctxt->input->line;
4185 node_info.node = ctxt->node;
4186 xmlParserAddNodeInfo(ctxt, &node_info);
4187 }
4188 return;
4189 }
4190
4191 /*
4192 * Check for an Empty Element from DTD definition
4193 */
4194 if ((info != NULL) && (info->empty)) {
4195 if ((ctxt->sax != NULL) && (ctxt->sax->endElement != NULL))
4196 ctxt->sax->endElement(ctxt->userData, name);
4197 oldname = docbnamePop(ctxt);
4198#ifdef DEBUG
4199 xmlGenericError(xmlGenericErrorContext,"End of empty tag %s : popping out %s\n", name, oldname);
4200#endif
4201 if (oldname != NULL)
4202 xmlFree(oldname);
4203 return;
4204 }
4205
4206 /*
4207 * Parse the content of the element:
4208 */
4209 currentNode = xmlStrdup(ctxt->name);
4210 depth = ctxt->nameNr;
4211 while (IS_CHAR(CUR)) {
4212 docbParseContent(ctxt);
4213 if (ctxt->nameNr < depth) break;
4214 }
4215
4216 if (!IS_CHAR(CUR)) {
4217 /************
4218 if ((ctxt->sax != NULL) && (ctxt->sax->error != NULL))
4219 ctxt->sax->error(ctxt->userData,
4220 "Premature end of data in tag %s\n", currentNode);
4221 ctxt->wellFormed = 0;
4222 *************/
4223
4224 /*
4225 * end of parsing of this node.
4226 */
4227 nodePop(ctxt);
4228 oldname = docbnamePop(ctxt);
4229#ifdef DEBUG
4230 xmlGenericError(xmlGenericErrorContext,"Premature end of tag %s : popping out %s\n", name, oldname);
4231#endif
4232 if (oldname != NULL)
4233 xmlFree(oldname);
4234 if (currentNode != NULL)
4235 xmlFree(currentNode);
4236 return;
4237 }
4238
4239 /*
4240 * Capture end position and add node
4241 */
4242 if ( currentNode != NULL && ctxt->record_info ) {
4243 node_info.end_pos = ctxt->input->consumed +
4244 (CUR_PTR - ctxt->input->base);
4245 node_info.end_line = ctxt->input->line;
4246 node_info.node = ctxt->node;
4247 xmlParserAddNodeInfo(ctxt, &node_info);
4248 }
4249 if (currentNode != NULL)
4250 xmlFree(currentNode);
4251}
4252
4253/**
4254 * docbParseEntityDecl:
4255 * @ctxt: an SGML parser context
4256 *
4257 * parse <!ENTITY declarations
4258 *
4259 */
4260
4261static void
4262docbParseEntityDecl(xmlParserCtxtPtr ctxt) {
4263 xmlChar *name = NULL;
4264 xmlChar *value = NULL;
4265 xmlChar *URI = NULL, *literal = NULL;
4266 xmlChar *ndata = NULL;
4267 int isParameter = 0;
4268 xmlChar *orig = NULL;
4269
4270 GROW;
4271 if ((RAW == '<') && (NXT(1) == '!') &&
Daniel Veillard61b33d52001-04-24 13:55:12 +0000[diff] [blame]4272 (UPP(2) == 'E') && (UPP(3) == 'N') &&
4273 (UPP(4) == 'T') && (UPP(5) == 'I') &&
4274 (UPP(6) == 'T') && (UPP(7) == 'Y')) {
Daniel Veillardeae522a2001-04-23 13:41:34 +0000[diff] [blame]4275 xmlParserInputPtr input = ctxt->input;
4276 ctxt->instate = XML_PARSER_ENTITY_DECL;
4277 SHRINK;
4278 SKIP(8);
4279 if (!IS_BLANK(CUR)) {
4280 ctxt->errNo = XML_ERR_SPACE_REQUIRED;
4281 if ((ctxt->sax != NULL) && (ctxt->sax->error != NULL))
4282 ctxt->sax->error(ctxt->userData,
4283 "Space required after '<!ENTITY'\n");
4284 ctxt->wellFormed = 0;
4285 ctxt->disableSAX = 1;
4286 }
4287 SKIP_BLANKS;
4288
4289 if (RAW == '%') {
4290 NEXT;
4291 if (!IS_BLANK(CUR)) {
4292 ctxt->errNo = XML_ERR_SPACE_REQUIRED;
4293 if ((ctxt->sax != NULL) && (ctxt->sax->error != NULL))
4294 ctxt->sax->error(ctxt->userData,
4295 "Space required after '%'\n");
4296 ctxt->wellFormed = 0;
4297 ctxt->disableSAX = 1;
4298 }
4299 SKIP_BLANKS;
4300 isParameter = 1;
4301 }
4302
4303 name = xmlParseName(ctxt);
4304 if (name == NULL) {
4305 ctxt->errNo = XML_ERR_NAME_REQUIRED;
4306 if ((ctxt->sax != NULL) && (ctxt->sax->error != NULL))
4307 ctxt->sax->error(ctxt->userData, "sgmlarseEntityDecl: no name\n");
4308 ctxt->wellFormed = 0;
4309 ctxt->disableSAX = 1;
4310 return;
4311 }
4312 if (!IS_BLANK(CUR)) {
4313 ctxt->errNo = XML_ERR_SPACE_REQUIRED;
4314 if ((ctxt->sax != NULL) && (ctxt->sax->error != NULL))
4315 ctxt->sax->error(ctxt->userData,
4316 "Space required after the entity name\n");
4317 ctxt->wellFormed = 0;
4318 ctxt->disableSAX = 1;
4319 }
4320 SKIP_BLANKS;
4321
4322 /*
4323 * handle the various case of definitions...
4324 */
4325 if (isParameter) {
4326 if ((RAW == '"') || (RAW == '\'')) {
4327 value = xmlParseEntityValue(ctxt, &orig);
4328 if (value) {
4329 if ((ctxt->sax != NULL) &&
4330 (!ctxt->disableSAX) && (ctxt->sax->entityDecl != NULL))
4331 ctxt->sax->entityDecl(ctxt->userData, name,
4332 XML_INTERNAL_PARAMETER_ENTITY,
4333 NULL, NULL, value);
4334 }
4335 } else {
4336 URI = xmlParseExternalID(ctxt, &literal, 1);
4337 if ((URI == NULL) && (literal == NULL)) {
4338 ctxt->errNo = XML_ERR_VALUE_REQUIRED;
4339 if ((ctxt->sax != NULL) && (ctxt->sax->error != NULL))
4340 ctxt->sax->error(ctxt->userData,
4341 "Entity value required\n");
4342 ctxt->wellFormed = 0;
4343 ctxt->disableSAX = 1;
4344 }
4345 if (URI) {
4346 xmlURIPtr uri;
4347
4348 uri = xmlParseURI((const char *) URI);
4349 if (uri == NULL) {
4350 ctxt->errNo = XML_ERR_INVALID_URI;
4351 if ((ctxt->sax != NULL) &&
4352 (!ctxt->disableSAX) &&
4353 (ctxt->sax->error != NULL))
4354 ctxt->sax->error(ctxt->userData,
4355 "Invalid URI: %s\n", URI);
4356 ctxt->wellFormed = 0;
4357 } else {
4358 if (uri->fragment != NULL) {
4359 ctxt->errNo = XML_ERR_URI_FRAGMENT;
4360 if ((ctxt->sax != NULL) &&
4361 (!ctxt->disableSAX) &&
4362 (ctxt->sax->error != NULL))
4363 ctxt->sax->error(ctxt->userData,
4364 "Fragment not allowed: %s\n", URI);
4365 ctxt->wellFormed = 0;
4366 } else {
4367 if ((ctxt->sax != NULL) &&
4368 (!ctxt->disableSAX) &&
4369 (ctxt->sax->entityDecl != NULL))
4370 ctxt->sax->entityDecl(ctxt->userData, name,
4371 XML_EXTERNAL_PARAMETER_ENTITY,
4372 literal, URI, NULL);
4373 }
4374 xmlFreeURI(uri);
4375 }
4376 }
4377 }
4378 } else {
4379 if ((RAW == '"') || (RAW == '\'')) {
4380 value = xmlParseEntityValue(ctxt, &orig);
4381 if ((ctxt->sax != NULL) &&
4382 (!ctxt->disableSAX) && (ctxt->sax->entityDecl != NULL))
4383 ctxt->sax->entityDecl(ctxt->userData, name,
4384 XML_INTERNAL_GENERAL_ENTITY,
4385 NULL, NULL, value);
4386 } else {
4387 URI = xmlParseExternalID(ctxt, &literal, 1);
4388 if ((URI == NULL) && (literal == NULL)) {
4389 ctxt->errNo = XML_ERR_VALUE_REQUIRED;
4390 if ((ctxt->sax != NULL) && (ctxt->sax->error != NULL))
4391 ctxt->sax->error(ctxt->userData,
4392 "Entity value required\n");
4393 ctxt->wellFormed = 0;
4394 ctxt->disableSAX = 1;
4395 }
4396 if (URI) {
4397 xmlURIPtr uri;
4398
4399 uri = xmlParseURI((const char *)URI);
4400 if (uri == NULL) {
4401 ctxt->errNo = XML_ERR_INVALID_URI;
4402 if ((ctxt->sax != NULL) &&
4403 (!ctxt->disableSAX) &&
4404 (ctxt->sax->error != NULL))
4405 ctxt->sax->error(ctxt->userData,
4406 "Invalid URI: %s\n", URI);
4407 ctxt->wellFormed = 0;
4408 } else {
4409 if (uri->fragment != NULL) {
4410 ctxt->errNo = XML_ERR_URI_FRAGMENT;
4411 if ((ctxt->sax != NULL) &&
4412 (!ctxt->disableSAX) &&
4413 (ctxt->sax->error != NULL))
4414 ctxt->sax->error(ctxt->userData,
4415 "Fragment not allowed: %s\n", URI);
4416 ctxt->wellFormed = 0;
4417 }
4418 xmlFreeURI(uri);
4419 }
4420 }
4421 if ((RAW != '>') && (!IS_BLANK(CUR))) {
4422 ctxt->errNo = XML_ERR_SPACE_REQUIRED;
4423 if ((ctxt->sax != NULL) && (ctxt->sax->error != NULL))
4424 ctxt->sax->error(ctxt->userData,
4425 "Space required before content model\n");
4426 ctxt->wellFormed = 0;
4427 ctxt->disableSAX = 1;
4428 }
4429 SKIP_BLANKS;
4430
4431 /*
4432 * SGML specific: here we can get the content model
4433 */
4434 if (RAW != '>') {
4435 xmlChar *contmod;
4436
4437 contmod = xmlParseName(ctxt);
4438
4439 if (contmod == NULL) {
4440 ctxt->errNo = XML_ERR_SPACE_REQUIRED;
4441 if ((ctxt->sax != NULL) && (ctxt->sax->error != NULL))
4442 ctxt->sax->error(ctxt->userData,
4443 "Could not parse entity content model\n");
4444 ctxt->wellFormed = 0;
4445 ctxt->disableSAX = 1;
4446 } else {
4447 if (xmlStrEqual(contmod, BAD_CAST"NDATA")) {
4448 if (!IS_BLANK(CUR)) {
4449 ctxt->errNo = XML_ERR_SPACE_REQUIRED;
4450 if ((ctxt->sax != NULL) &&
4451 (ctxt->sax->error != NULL))
4452 ctxt->sax->error(ctxt->userData,
4453 "Space required after 'NDATA'\n");
4454 ctxt->wellFormed = 0;
4455 ctxt->disableSAX = 1;
4456 }
4457 SKIP_BLANKS;
4458 ndata = xmlParseName(ctxt);
4459 if ((ctxt->sax != NULL) && (!ctxt->disableSAX) &&
4460 (ctxt->sax->unparsedEntityDecl != NULL)) {
4461 ctxt->sax->unparsedEntityDecl(ctxt->userData,
4462 name, literal, URI, ndata);
4463 }
4464 } else if (xmlStrEqual(contmod, BAD_CAST"SUBDOC")) {
4465 if ((ctxt->sax != NULL) &&
4466 (ctxt->sax->warning != NULL))
4467 ctxt->sax->warning(ctxt->userData,
4468 "SUBDOC entities are not supported\n");
4469 SKIP_BLANKS;
4470 ndata = xmlParseName(ctxt);
4471 if ((ctxt->sax != NULL) && (!ctxt->disableSAX) &&
4472 (ctxt->sax->unparsedEntityDecl != NULL)) {
4473 ctxt->sax->unparsedEntityDecl(ctxt->userData,
4474 name, literal, URI, ndata);
4475 }
4476 } else if (xmlStrEqual(contmod, BAD_CAST"CDATA")) {
4477 if ((ctxt->sax != NULL) &&
4478 (ctxt->sax->warning != NULL))
4479 ctxt->sax->warning(ctxt->userData,
4480 "CDATA entities are not supported\n");
4481 SKIP_BLANKS;
4482 ndata = xmlParseName(ctxt);
4483 if ((ctxt->sax != NULL) && (!ctxt->disableSAX) &&
4484 (ctxt->sax->unparsedEntityDecl != NULL)) {
4485 ctxt->sax->unparsedEntityDecl(ctxt->userData,
4486 name, literal, URI, ndata);
4487 }
4488 }
4489 xmlFree(contmod);
4490 }
4491 } else {
4492 if ((ctxt->sax != NULL) &&
4493 (!ctxt->disableSAX) && (ctxt->sax->entityDecl != NULL))
4494 ctxt->sax->entityDecl(ctxt->userData, name,
4495 XML_EXTERNAL_GENERAL_PARSED_ENTITY,
4496 literal, URI, NULL);
4497 }
4498 }
4499 }
4500 SKIP_BLANKS;
4501 if (RAW != '>') {
4502 ctxt->errNo = XML_ERR_ENTITY_NOT_FINISHED;
4503 if ((ctxt->sax != NULL) && (ctxt->sax->error != NULL))
4504 ctxt->sax->error(ctxt->userData,
4505 "docbParseEntityDecl: entity %s not terminated\n", name);
4506 ctxt->wellFormed = 0;
4507 ctxt->disableSAX = 1;
4508 } else {
4509 if (input != ctxt->input) {
4510 ctxt->errNo = XML_ERR_ENTITY_BOUNDARY;
4511 if ((ctxt->sax != NULL) && (ctxt->sax->error != NULL))
4512 ctxt->sax->error(ctxt->userData,
4513"Entity declaration doesn't start and stop in the same entity\n");
4514 ctxt->wellFormed = 0;
4515 ctxt->disableSAX = 1;
4516 }
4517 NEXT;
4518 }
4519 if (orig != NULL) {
4520 /*
4521 * Ugly mechanism to save the raw entity value.
4522 */
4523 xmlEntityPtr cur = NULL;
4524
4525 if (isParameter) {
4526 if ((ctxt->sax != NULL) &&
4527 (ctxt->sax->getParameterEntity != NULL))
4528 cur = ctxt->sax->getParameterEntity(ctxt->userData, name);
4529 } else {
4530 if ((ctxt->sax != NULL) &&
4531 (ctxt->sax->getEntity != NULL))
4532 cur = ctxt->sax->getEntity(ctxt->userData, name);
4533 }
4534 if (cur != NULL) {
4535 if (cur->orig != NULL)
4536 xmlFree(orig);
4537 else
4538 cur->orig = orig;
4539 } else
4540 xmlFree(orig);
4541 }
4542 if (name != NULL) xmlFree(name);
4543 if (value != NULL) xmlFree(value);
4544 if (URI != NULL) xmlFree(URI);
4545 if (literal != NULL) xmlFree(literal);
4546 if (ndata != NULL) xmlFree(ndata);
4547 }
4548}
4549
4550/**
4551 * docbParseMarkupDecl:
4552 * @ctxt: an SGML parser context
4553 *
4554 * parse Markup declarations
4555 *
4556 * [29] markupdecl ::= elementdecl | AttlistDecl | EntityDecl |
4557 * NotationDecl | PI | Comment
4558 */
4559static void
4560docbParseMarkupDecl(xmlParserCtxtPtr ctxt) {
4561 GROW;
4562 xmlParseElementDecl(ctxt);
4563 xmlParseAttributeListDecl(ctxt);
4564 docbParseEntityDecl(ctxt);
4565 xmlParseNotationDecl(ctxt);
4566 xmlParsePI(ctxt);
4567 xmlParseComment(ctxt);
4568 /*
4569 * This is only for internal subset. On external entities,
4570 * the replacement is done before parsing stage
4571 */
4572 if ((ctxt->external == 0) && (ctxt->inputNr == 1))
4573 xmlParsePEReference(ctxt);
4574 ctxt->instate = XML_PARSER_DTD;
4575}
4576
4577/**
4578 * docbParseInternalsubset:
4579 * @ctxt: an SGML parser context
4580 *
4581 * parse the internal subset declaration
4582 *
4583 * [28 end] ('[' (markupdecl | PEReference | S)* ']' S?)? '>'
4584 */
4585
4586static void
4587docbParseInternalSubset(xmlParserCtxtPtr ctxt) {
4588 /*
4589 * Is there any DTD definition ?
4590 */
4591 if (RAW == '[') {
4592 ctxt->instate = XML_PARSER_DTD;
4593 NEXT;
4594 /*
4595 * Parse the succession of Markup declarations and
4596 * PEReferences.
4597 * Subsequence (markupdecl | PEReference | S)*
4598 */
4599 while (RAW != ']') {
4600 const xmlChar *check = CUR_PTR;
4601 int cons = ctxt->input->consumed;
4602
4603 SKIP_BLANKS;
4604 docbParseMarkupDecl(ctxt);
4605 xmlParsePEReference(ctxt);
4606
4607 /*
4608 * Pop-up of finished entities.
4609 */
4610 while ((RAW == 0) && (ctxt->inputNr > 1))
4611 xmlPopInput(ctxt);
4612
4613 if ((CUR_PTR == check) && (cons == ctxt->input->consumed)) {
4614 ctxt->errNo = XML_ERR_INTERNAL_ERROR;
4615 if ((ctxt->sax != NULL) && (ctxt->sax->error != NULL))
4616 ctxt->sax->error(ctxt->userData,
4617 "docbParseInternalSubset: error detected in Markup declaration\n");
4618 ctxt->wellFormed = 0;
4619 ctxt->disableSAX = 1;
4620 break;
4621 }
4622 }
4623 if (RAW == ']') {
4624 NEXT;
4625 SKIP_BLANKS;
4626 }
4627 }
4628
4629 /*
4630 * We should be at the end of the DOCTYPE declaration.
4631 */
4632 if (RAW != '>') {
4633 ctxt->errNo = XML_ERR_DOCTYPE_NOT_FINISHED;
4634 if ((ctxt->sax != NULL) && (ctxt->sax->error != NULL))
4635 ctxt->sax->error(ctxt->userData, "DOCTYPE unproperly terminated\n");
4636 ctxt->wellFormed = 0;
4637 ctxt->disableSAX = 1;
4638 }
4639 NEXT;
4640}
4641
4642/**
4643 * docbParseMisc:
4644 * @ctxt: an XML parser context
4645 *
4646 * parse an XML Misc* optionnal field.
4647 *
4648 * [27] Misc ::= Comment | PI | S
4649 */
4650
4651static void
4652docbParseMisc(xmlParserCtxtPtr ctxt) {
4653 while (((RAW == '<') && (NXT(1) == '?')) ||
4654 ((RAW == '<') && (NXT(1) == '!') &&
4655 (NXT(2) == '-') && (NXT(3) == '-')) ||
4656 IS_BLANK(CUR)) {
4657 if ((RAW == '<') && (NXT(1) == '?')) {
4658 xmlParsePI(ctxt); /* TODO: SGML PIs differs */
4659 } else if (IS_BLANK(CUR)) {
4660 NEXT;
4661 } else
4662 xmlParseComment(ctxt);
4663 }
4664}
4665
4666/**
4667 * docbParseDocument :
4668 * @ctxt: an SGML parser context
4669 *
4670 * parse an SGML document (and build a tree if using the standard SAX
4671 * interface).
4672 *
4673 * Returns 0, -1 in case of error. the parser context is augmented
4674 * as a result of the parsing.
4675 */
4676
4677int
4678docbParseDocument(docbParserCtxtPtr ctxt) {
4679 xmlChar start[4];
4680 xmlCharEncoding enc;
4681 xmlDtdPtr dtd;
4682
4683 docbDefaultSAXHandlerInit();
4684 ctxt->html = 2;
4685
4686 GROW;
4687 /*
4688 * SAX: beginning of the document processing.
4689 */
4690 if ((ctxt->sax) && (ctxt->sax->setDocumentLocator))
4691 ctxt->sax->setDocumentLocator(ctxt->userData, &xmlDefaultSAXLocator);
4692
4693 /*
4694 * Get the 4 first bytes and decode the charset
4695 * if enc != XML_CHAR_ENCODING_NONE
4696 * plug some encoding conversion routines.
4697 */
4698 start[0] = RAW;
4699 start[1] = NXT(1);
4700 start[2] = NXT(2);
4701 start[3] = NXT(3);
4702 enc = xmlDetectCharEncoding(start, 4);
4703 if (enc != XML_CHAR_ENCODING_NONE) {
4704 xmlSwitchEncoding(ctxt, enc);
4705 }
4706
4707 /*
4708 * Wipe out everything which is before the first '<'
4709 */
4710 SKIP_BLANKS;
4711 if (CUR == 0) {
4712 if ((ctxt->sax != NULL) && (ctxt->sax->error != NULL))
4713 ctxt->sax->error(ctxt->userData, "Document is empty\n");
4714 ctxt->wellFormed = 0;
4715 }
4716
4717 if ((ctxt->sax) && (ctxt->sax->startDocument) && (!ctxt->disableSAX))
4718 ctxt->sax->startDocument(ctxt->userData);
4719
4720
4721 /*
4722 * The Misc part of the Prolog
4723 */
4724 GROW;
4725 docbParseMisc(ctxt);
4726
4727 /*
4728 * Then possibly doc type declaration(s) and more Misc
4729 * (doctypedecl Misc*)?
4730 */
4731 GROW;
4732 if ((RAW == '<') && (NXT(1) == '!') &&
Daniel Veillard61b33d52001-04-24 13:55:12 +0000[diff] [blame]4733 (UPP(2) == 'D') && (UPP(3) == 'O') &&
4734 (UPP(4) == 'C') && (UPP(5) == 'T') &&
4735 (UPP(6) == 'Y') && (UPP(7) == 'P') &&
4736 (UPP(8) == 'E')) {
Daniel Veillardeae522a2001-04-23 13:41:34 +0000[diff] [blame]4737
4738 ctxt->inSubset = 1;
4739 docbParseDocTypeDecl(ctxt);
4740 if (RAW == '[') {
4741 ctxt->instate = XML_PARSER_DTD;
4742 docbParseInternalSubset(ctxt);
4743 }
4744
4745 /*
4746 * Create and update the external subset.
4747 */
4748 ctxt->inSubset = 2;
4749 if ((ctxt->sax != NULL) && (ctxt->sax->internalSubset != NULL) &&
4750 (!ctxt->disableSAX))
4751 ctxt->sax->internalSubset(ctxt->userData, ctxt->intSubName,
4752 ctxt->extSubSystem, ctxt->extSubURI);
4753 ctxt->inSubset = 0;
4754
4755
4756 ctxt->instate = XML_PARSER_PROLOG;
4757 docbParseMisc(ctxt);
4758 }
4759
4760 /*
4761 * Time to start parsing the tree itself
4762 */
4763 docbParseContent(ctxt);
4764
4765 /*
4766 * autoclose
4767 */
4768 if (CUR == 0)
4769 docbAutoClose(ctxt, NULL);
4770
4771
4772 /*
4773 * SAX: end of the document processing.
4774 */
4775 if ((ctxt->sax) && (ctxt->sax->endDocument != NULL))
4776 ctxt->sax->endDocument(ctxt->userData);
4777
4778 if (ctxt->myDoc != NULL) {
4779 dtd = ctxt->myDoc->intSubset;
4780 if (dtd == NULL)
4781 ctxt->myDoc->intSubset =
4782 xmlCreateIntSubset(ctxt->myDoc, BAD_CAST "SGML",
4783 BAD_CAST "-//W3C//DTD SGML 4.0 Transitional//EN",
4784 BAD_CAST "http://www.w3.org/TR/REC-docbook/loose.dtd");
4785 }
4786 if (! ctxt->wellFormed) return(-1);
4787 return(0);
4788}
4789
4790
4791/************************************************************************
4792 * *
4793 * Parser contexts handling *
4794 * *
4795 ************************************************************************/
4796
4797/**
4798 * xmlInitParserCtxt:
4799 * @ctxt: an SGML parser context
4800 *
4801 * Initialize a parser context
4802 */
4803
4804static void
4805docbInitParserCtxt(docbParserCtxtPtr ctxt)
4806{
4807 docbSAXHandler *sax;
4808
4809 if (ctxt == NULL) return;
4810 memset(ctxt, 0, sizeof(docbParserCtxt));
4811
4812 sax = (docbSAXHandler *) xmlMalloc(sizeof(docbSAXHandler));
4813 if (sax == NULL) {
4814 xmlGenericError(xmlGenericErrorContext,
4815 "docbInitParserCtxt: out of memory\n");
4816 }
4817 memset(sax, 0, sizeof(docbSAXHandler));
4818
4819 /* Allocate the Input stack */
4820 ctxt->inputTab = (docbParserInputPtr *)
4821 xmlMalloc(5 * sizeof(docbParserInputPtr));
4822 if (ctxt->inputTab == NULL) {
4823 xmlGenericError(xmlGenericErrorContext,
4824 "docbInitParserCtxt: out of memory\n");
4825 }
4826 ctxt->inputNr = 0;
4827 ctxt->inputMax = 5;
4828 ctxt->input = NULL;
4829 ctxt->version = NULL;
4830 ctxt->encoding = NULL;
4831 ctxt->standalone = -1;
4832 ctxt->instate = XML_PARSER_START;
4833
4834 /* Allocate the Node stack */
4835 ctxt->nodeTab = (docbNodePtr *) xmlMalloc(10 * sizeof(docbNodePtr));
4836 ctxt->nodeNr = 0;
4837 ctxt->nodeMax = 10;
4838 ctxt->node = NULL;
4839
4840 /* Allocate the Name stack */
4841 ctxt->nameTab = (xmlChar **) xmlMalloc(10 * sizeof(xmlChar *));
4842 ctxt->nameNr = 0;
4843 ctxt->nameMax = 10;
4844 ctxt->name = NULL;
4845
4846 if (sax == NULL) ctxt->sax = &docbDefaultSAXHandler;
4847 else {
4848 ctxt->sax = sax;
4849 memcpy(sax, &docbDefaultSAXHandler, sizeof(docbSAXHandler));
4850 }
4851 ctxt->userData = ctxt;
4852 ctxt->myDoc = NULL;
4853 ctxt->wellFormed = 1;
Daniel Veillard61b33d52001-04-24 13:55:12 +0000[diff] [blame]4854 ctxt->replaceEntities = xmlSubstituteEntitiesDefaultValue;
Daniel Veillardeae522a2001-04-23 13:41:34 +0000[diff] [blame]4855 ctxt->html = 2;
4856 ctxt->record_info = 0;
4857 ctxt->validate = 0;
4858 ctxt->nbChars = 0;
4859 ctxt->checkIndex = 0;
4860 xmlInitNodeInfoSeq(&ctxt->node_seq);
4861}
4862
4863/**
4864 * docbFreeParserCtxt:
4865 * @ctxt: an SGML parser context
4866 *
4867 * Free all the memory used by a parser context. However the parsed
4868 * document in ctxt->myDoc is not freed.
4869 */
4870
4871void
4872docbFreeParserCtxt(docbParserCtxtPtr ctxt)
4873{
4874 xmlFreeParserCtxt(ctxt);
4875}
4876
4877/**
4878 * docbCreateDocParserCtxt :
4879 * @cur: a pointer to an array of xmlChar
4880 * @encoding: a free form C string describing the SGML document encoding, or NULL
4881 *
4882 * Create a parser context for an SGML document.
4883 *
4884 * Returns the new parser context or NULL
4885 */
4886static docbParserCtxtPtr
4887docbCreateDocParserCtxt(xmlChar *cur, const char *encoding) {
4888 docbParserCtxtPtr ctxt;
4889 docbParserInputPtr input;
4890 /* sgmlCharEncoding enc; */
4891
4892 ctxt = (docbParserCtxtPtr) xmlMalloc(sizeof(docbParserCtxt));
4893 if (ctxt == NULL) {
4894 perror("malloc");
4895 return(NULL);
4896 }
4897 docbInitParserCtxt(ctxt);
4898 input = (docbParserInputPtr) xmlMalloc(sizeof(docbParserInput));
4899 if (input == NULL) {
4900 perror("malloc");
4901 xmlFree(ctxt);
4902 return(NULL);
4903 }
4904 memset(input, 0, sizeof(docbParserInput));
4905
4906 input->line = 1;
4907 input->col = 1;
4908 input->base = cur;
4909 input->cur = cur;
4910
4911 inputPush(ctxt, input);
4912 return(ctxt);
4913}
4914
4915/************************************************************************
4916 * *
4917 * Progressive parsing interfaces *
4918 * *
4919 ************************************************************************/
4920
4921/**
4922 * docbParseLookupSequence:
4923 * @ctxt: an SGML parser context
4924 * @first: the first char to lookup
4925 * @next: the next char to lookup or zero
4926 * @third: the next char to lookup or zero
4927 *
4928 * Try to find if a sequence (first, next, third) or just (first next) or
4929 * (first) is available in the input stream.
4930 * This function has a side effect of (possibly) incrementing ctxt->checkIndex
4931 * to avoid rescanning sequences of bytes, it DOES change the state of the
4932 * parser, do not use liberally.
4933 * This is basically similar to xmlParseLookupSequence()
4934 *
4935 * Returns the index to the current parsing point if the full sequence
4936 * is available, -1 otherwise.
4937 */
4938static int
4939docbParseLookupSequence(docbParserCtxtPtr ctxt, xmlChar first,
4940 xmlChar next, xmlChar third) {
4941 int base, len;
4942 docbParserInputPtr in;
4943 const xmlChar *buf;
4944
4945 in = ctxt->input;
4946 if (in == NULL) return(-1);
4947 base = in->cur - in->base;
4948 if (base < 0) return(-1);
4949 if (ctxt->checkIndex > base)
4950 base = ctxt->checkIndex;
4951 if (in->buf == NULL) {
4952 buf = in->base;
4953 len = in->length;
4954 } else {
4955 buf = in->buf->buffer->content;
4956 len = in->buf->buffer->use;
4957 }
4958 /* take into account the sequence length */
4959 if (third) len -= 2;
4960 else if (next) len --;
4961 for (;base < len;base++) {
4962 if (buf[base] == first) {
4963 if (third != 0) {
4964 if ((buf[base + 1] != next) ||
4965 (buf[base + 2] != third)) continue;
4966 } else if (next != 0) {
4967 if (buf[base + 1] != next) continue;
4968 }
4969 ctxt->checkIndex = 0;
4970#ifdef DEBUG_PUSH
4971 if (next == 0)
4972 xmlGenericError(xmlGenericErrorContext,
4973 "HPP: lookup '%c' found at %d\n",
4974 first, base);
4975 else if (third == 0)
4976 xmlGenericError(xmlGenericErrorContext,
4977 "HPP: lookup '%c%c' found at %d\n",
4978 first, next, base);
4979 else
4980 xmlGenericError(xmlGenericErrorContext,
4981 "HPP: lookup '%c%c%c' found at %d\n",
4982 first, next, third, base);
4983#endif
4984 return(base - (in->cur - in->base));
4985 }
4986 }
4987 ctxt->checkIndex = base;
4988#ifdef DEBUG_PUSH
4989 if (next == 0)
4990 xmlGenericError(xmlGenericErrorContext,
4991 "HPP: lookup '%c' failed\n", first);
4992 else if (third == 0)
4993 xmlGenericError(xmlGenericErrorContext,
4994 "HPP: lookup '%c%c' failed\n", first, next);
4995 else
4996 xmlGenericError(xmlGenericErrorContext,
4997 "HPP: lookup '%c%c%c' failed\n", first, next, third);
4998#endif
4999 return(-1);
5000}
5001
5002/**
5003 * docbParseTryOrFinish:
5004 * @ctxt: an SGML parser context
5005 * @terminate: last chunk indicator
5006 *
5007 * Try to progress on parsing
5008 *
5009 * Returns zero if no parsing was possible
5010 */
5011static int
5012docbParseTryOrFinish(docbParserCtxtPtr ctxt, int terminate) {
5013 int ret = 0;
5014 docbParserInputPtr in;
5015 int avail = 0;
5016 xmlChar cur, next;
5017
5018#ifdef DEBUG_PUSH
5019 switch (ctxt->instate) {
5020 case XML_PARSER_EOF:
5021 xmlGenericError(xmlGenericErrorContext,
5022 "HPP: try EOF\n"); break;
5023 case XML_PARSER_START:
5024 xmlGenericError(xmlGenericErrorContext,
5025 "HPP: try START\n"); break;
5026 case XML_PARSER_MISC:
5027 xmlGenericError(xmlGenericErrorContext,
5028 "HPP: try MISC\n");break;
5029 case XML_PARSER_COMMENT:
5030 xmlGenericError(xmlGenericErrorContext,
5031 "HPP: try COMMENT\n");break;
5032 case XML_PARSER_PROLOG:
5033 xmlGenericError(xmlGenericErrorContext,
5034 "HPP: try PROLOG\n");break;
5035 case XML_PARSER_START_TAG:
5036 xmlGenericError(xmlGenericErrorContext,
5037 "HPP: try START_TAG\n");break;
5038 case XML_PARSER_CONTENT:
5039 xmlGenericError(xmlGenericErrorContext,
5040 "HPP: try CONTENT\n");break;
5041 case XML_PARSER_CDATA_SECTION:
5042 xmlGenericError(xmlGenericErrorContext,
5043 "HPP: try CDATA_SECTION\n");break;
5044 case XML_PARSER_END_TAG:
5045 xmlGenericError(xmlGenericErrorContext,
5046 "HPP: try END_TAG\n");break;
5047 case XML_PARSER_ENTITY_DECL:
5048 xmlGenericError(xmlGenericErrorContext,
5049 "HPP: try ENTITY_DECL\n");break;
5050 case XML_PARSER_ENTITY_VALUE:
5051 xmlGenericError(xmlGenericErrorContext,
5052 "HPP: try ENTITY_VALUE\n");break;
5053 case XML_PARSER_ATTRIBUTE_VALUE:
5054 xmlGenericError(xmlGenericErrorContext,
5055 "HPP: try ATTRIBUTE_VALUE\n");break;
5056 case XML_PARSER_DTD:
5057 xmlGenericError(xmlGenericErrorContext,
5058 "HPP: try DTD\n");break;
5059 case XML_PARSER_EPILOG:
5060 xmlGenericError(xmlGenericErrorContext,
5061 "HPP: try EPILOG\n");break;
5062 case XML_PARSER_PI:
5063 xmlGenericError(xmlGenericErrorContext,
5064 "HPP: try PI\n");break;
5065 }
5066#endif
5067
5068 while (1) {
5069
5070 in = ctxt->input;
5071 if (in == NULL) break;
5072 if (in->buf == NULL)
5073 avail = in->length - (in->cur - in->base);
5074 else
5075 avail = in->buf->buffer->use - (in->cur - in->base);
5076 if ((avail == 0) && (terminate)) {
5077 docbAutoClose(ctxt, NULL);
5078 if ((ctxt->nameNr == 0) && (ctxt->instate != XML_PARSER_EOF)) {
5079 /*
5080 * SAX: end of the document processing.
5081 */
5082 ctxt->instate = XML_PARSER_EOF;
5083 if ((ctxt->sax) && (ctxt->sax->endDocument != NULL))
5084 ctxt->sax->endDocument(ctxt->userData);
5085 }
5086 }
5087 if (avail < 1)
5088 goto done;
5089 switch (ctxt->instate) {
5090 case XML_PARSER_EOF:
5091 /*
5092 * Document parsing is done !
5093 */
5094 goto done;
5095 case XML_PARSER_START:
5096 /*
5097 * Very first chars read from the document flow.
5098 */
5099 cur = in->cur[0];
5100 if (IS_BLANK(cur)) {
5101 SKIP_BLANKS;
5102 if (in->buf == NULL)
5103 avail = in->length - (in->cur - in->base);
5104 else
5105 avail = in->buf->buffer->use - (in->cur - in->base);
5106 }
5107 if ((ctxt->sax) && (ctxt->sax->setDocumentLocator))
5108 ctxt->sax->setDocumentLocator(ctxt->userData,
5109 &xmlDefaultSAXLocator);
5110 if ((ctxt->sax) && (ctxt->sax->startDocument) &&
5111 (!ctxt->disableSAX))
5112 ctxt->sax->startDocument(ctxt->userData);
5113
5114 cur = in->cur[0];
5115 next = in->cur[1];
5116 if ((cur == '<') && (next == '!') &&
5117 (UPP(2) == 'D') && (UPP(3) == 'O') &&
5118 (UPP(4) == 'C') && (UPP(5) == 'T') &&
5119 (UPP(6) == 'Y') && (UPP(7) == 'P') &&
5120 (UPP(8) == 'E')) {
5121 if ((!terminate) &&
5122 (docbParseLookupSequence(ctxt, '>', 0, 0) < 0))
5123 goto done;
5124#ifdef DEBUG_PUSH
5125 xmlGenericError(xmlGenericErrorContext,
5126 "HPP: Parsing internal subset\n");
5127#endif
5128 docbParseDocTypeDecl(ctxt);
5129 ctxt->instate = XML_PARSER_PROLOG;
5130#ifdef DEBUG_PUSH
5131 xmlGenericError(xmlGenericErrorContext,
5132 "HPP: entering PROLOG\n");
5133#endif
5134 } else {
5135 ctxt->instate = XML_PARSER_MISC;
5136 }
5137#ifdef DEBUG_PUSH
5138 xmlGenericError(xmlGenericErrorContext,
5139 "HPP: entering MISC\n");
5140#endif
5141 break;
5142 case XML_PARSER_MISC:
5143 SKIP_BLANKS;
5144 if (in->buf == NULL)
5145 avail = in->length - (in->cur - in->base);
5146 else
5147 avail = in->buf->buffer->use - (in->cur - in->base);
5148 if (avail < 2)
5149 goto done;
5150 cur = in->cur[0];
5151 next = in->cur[1];
5152 if ((cur == '<') && (next == '!') &&
5153 (in->cur[2] == '-') && (in->cur[3] == '-')) {
5154 if ((!terminate) &&
5155 (docbParseLookupSequence(ctxt, '-', '-', '>') < 0))
5156 goto done;
5157#ifdef DEBUG_PUSH
5158 xmlGenericError(xmlGenericErrorContext,
5159 "HPP: Parsing Comment\n");
5160#endif
5161 docbParseComment(ctxt);
5162 ctxt->instate = XML_PARSER_MISC;
5163 } else if ((cur == '<') && (next == '!') &&
5164 (UPP(2) == 'D') && (UPP(3) == 'O') &&
5165 (UPP(4) == 'C') && (UPP(5) == 'T') &&
5166 (UPP(6) == 'Y') && (UPP(7) == 'P') &&
5167 (UPP(8) == 'E')) {
5168 if ((!terminate) &&
5169 (docbParseLookupSequence(ctxt, '>', 0, 0) < 0))
5170 goto done;
5171#ifdef DEBUG_PUSH
5172 xmlGenericError(xmlGenericErrorContext,
5173 "HPP: Parsing internal subset\n");
5174#endif
5175 docbParseDocTypeDecl(ctxt);
5176 ctxt->instate = XML_PARSER_PROLOG;
5177#ifdef DEBUG_PUSH
5178 xmlGenericError(xmlGenericErrorContext,
5179 "HPP: entering PROLOG\n");
5180#endif
5181 } else if ((cur == '<') && (next == '!') &&
5182 (avail < 9)) {
5183 goto done;
5184 } else {
5185 ctxt->instate = XML_PARSER_START_TAG;
5186#ifdef DEBUG_PUSH
5187 xmlGenericError(xmlGenericErrorContext,
5188 "HPP: entering START_TAG\n");
5189#endif
5190 }
5191 break;
5192 case XML_PARSER_PROLOG:
5193 SKIP_BLANKS;
5194 if (in->buf == NULL)
5195 avail = in->length - (in->cur - in->base);
5196 else
5197 avail = in->buf->buffer->use - (in->cur - in->base);
5198 if (avail < 2)
5199 goto done;
5200 cur = in->cur[0];
5201 next = in->cur[1];
5202 if ((cur == '<') && (next == '!') &&
5203 (in->cur[2] == '-') && (in->cur[3] == '-')) {
5204 if ((!terminate) &&
5205 (docbParseLookupSequence(ctxt, '-', '-', '>') < 0))
5206 goto done;
5207#ifdef DEBUG_PUSH
5208 xmlGenericError(xmlGenericErrorContext,
5209 "HPP: Parsing Comment\n");
5210#endif
5211 docbParseComment(ctxt);
5212 ctxt->instate = XML_PARSER_PROLOG;
5213 } else if ((cur == '<') && (next == '!') &&
5214 (avail < 4)) {
5215 goto done;
5216 } else {
5217 ctxt->instate = XML_PARSER_START_TAG;
5218#ifdef DEBUG_PUSH
5219 xmlGenericError(xmlGenericErrorContext,
5220 "HPP: entering START_TAG\n");
5221#endif
5222 }
5223 break;
5224 case XML_PARSER_EPILOG:
5225 if (in->buf == NULL)
5226 avail = in->length - (in->cur - in->base);
5227 else
5228 avail = in->buf->buffer->use - (in->cur - in->base);
5229 if (avail < 1)
5230 goto done;
5231 cur = in->cur[0];
5232 if (IS_BLANK(cur)) {
5233 docbParseCharData(ctxt);
5234 goto done;
5235 }
5236 if (avail < 2)
5237 goto done;
5238 next = in->cur[1];
5239 if ((cur == '<') && (next == '!') &&
5240 (in->cur[2] == '-') && (in->cur[3] == '-')) {
5241 if ((!terminate) &&
5242 (docbParseLookupSequence(ctxt, '-', '-', '>') < 0))
5243 goto done;
5244#ifdef DEBUG_PUSH
5245 xmlGenericError(xmlGenericErrorContext,
5246 "HPP: Parsing Comment\n");
5247#endif
5248 docbParseComment(ctxt);
5249 ctxt->instate = XML_PARSER_EPILOG;
5250 } else if ((cur == '<') && (next == '!') &&
5251 (avail < 4)) {
5252 goto done;
5253 } else {
5254 ctxt->errNo = XML_ERR_DOCUMENT_END;
5255 if ((ctxt->sax != NULL) && (ctxt->sax->error != NULL))
5256 ctxt->sax->error(ctxt->userData,
5257 "Extra content at the end of the document\n");
5258 ctxt->wellFormed = 0;
5259 ctxt->instate = XML_PARSER_EOF;
5260#ifdef DEBUG_PUSH
5261 xmlGenericError(xmlGenericErrorContext,
5262 "HPP: entering EOF\n");
5263#endif
5264 if ((ctxt->sax) && (ctxt->sax->endDocument != NULL))
5265 ctxt->sax->endDocument(ctxt->userData);
5266 goto done;
5267 }
5268 break;
5269 case XML_PARSER_START_TAG: {
5270 xmlChar *name, *oldname;
5271 int depth = ctxt->nameNr;
5272 docbElemDescPtr info;
5273
5274 if (avail < 2)
5275 goto done;
5276 cur = in->cur[0];
5277 if (cur != '<') {
5278 ctxt->instate = XML_PARSER_CONTENT;
5279#ifdef DEBUG_PUSH
5280 xmlGenericError(xmlGenericErrorContext,
5281 "HPP: entering CONTENT\n");
5282#endif
5283 break;
5284 }
5285 if ((!terminate) &&
5286 (docbParseLookupSequence(ctxt, '>', 0, 0) < 0))
5287 goto done;
5288
5289 oldname = xmlStrdup(ctxt->name);
5290 docbParseStartTag(ctxt);
5291 name = ctxt->name;
5292#ifdef DEBUG
5293 if (oldname == NULL)
5294 xmlGenericError(xmlGenericErrorContext,
5295 "Start of element %s\n", name);
5296 else if (name == NULL)
5297 xmlGenericError(xmlGenericErrorContext,
5298 "Start of element failed, was %s\n",
5299 oldname);
5300 else
5301 xmlGenericError(xmlGenericErrorContext,
5302 "Start of element %s, was %s\n",
5303 name, oldname);
5304#endif
5305 if (((depth == ctxt->nameNr) &&
5306 (xmlStrEqual(oldname, ctxt->name))) ||
5307 (name == NULL)) {
5308 if (CUR == '>')
5309 NEXT;
5310 if (oldname != NULL)
5311 xmlFree(oldname);
5312 break;
5313 }
5314 if (oldname != NULL)
5315 xmlFree(oldname);
5316
5317 /*
5318 * Lookup the info for that element.
5319 */
5320 info = docbTagLookup(name);
5321 if (info == NULL) {
5322 if ((ctxt->sax != NULL) && (ctxt->sax->error != NULL))
5323 ctxt->sax->error(ctxt->userData, "Tag %s unknown\n",
5324 name);
5325 ctxt->wellFormed = 0;
5326 } else if (info->depr) {
5327 /***************************
5328 if ((ctxt->sax != NULL) && (ctxt->sax->warning != NULL))
5329 ctxt->sax->warning(ctxt->userData,
5330 "Tag %s is deprecated\n",
5331 name);
5332 ***************************/
5333 }
5334
5335 /*
5336 * Check for an Empty Element labelled the XML/SGML way
5337 */
5338 if ((CUR == '/') && (NXT(1) == '>')) {
5339 SKIP(2);
5340 if ((ctxt->sax != NULL) && (ctxt->sax->endElement != NULL))
5341 ctxt->sax->endElement(ctxt->userData, name);
5342 oldname = docbnamePop(ctxt);
5343#ifdef DEBUG
5344 xmlGenericError(xmlGenericErrorContext,"End of tag the XML way: popping out %s\n",
5345 oldname);
5346#endif
5347 if (oldname != NULL)
5348 xmlFree(oldname);
5349 ctxt->instate = XML_PARSER_CONTENT;
5350#ifdef DEBUG_PUSH
5351 xmlGenericError(xmlGenericErrorContext,
5352 "HPP: entering CONTENT\n");
5353#endif
5354 break;
5355 }
5356
5357 if (CUR == '>') {
5358 NEXT;
5359 } else {
5360 if ((ctxt->sax != NULL) && (ctxt->sax->error != NULL))
5361 ctxt->sax->error(ctxt->userData,
5362 "Couldn't find end of Start Tag %s\n",
5363 name);
5364 ctxt->wellFormed = 0;
5365
5366 /*
5367 * end of parsing of this node.
5368 */
5369 if (xmlStrEqual(name, ctxt->name)) {
5370 nodePop(ctxt);
5371 oldname = docbnamePop(ctxt);
5372#ifdef DEBUG
5373 xmlGenericError(xmlGenericErrorContext,
5374 "End of start tag problem: popping out %s\n", oldname);
5375#endif
5376 if (oldname != NULL)
5377 xmlFree(oldname);
5378 }
5379
5380 ctxt->instate = XML_PARSER_CONTENT;
5381#ifdef DEBUG_PUSH
5382 xmlGenericError(xmlGenericErrorContext,
5383 "HPP: entering CONTENT\n");
5384#endif
5385 break;
5386 }
5387
5388 /*
5389 * Check for an Empty Element from DTD definition
5390 */
5391 if ((info != NULL) && (info->empty)) {
5392 if ((ctxt->sax != NULL) && (ctxt->sax->endElement != NULL))
5393 ctxt->sax->endElement(ctxt->userData, name);
5394 oldname = docbnamePop(ctxt);
5395#ifdef DEBUG
5396 xmlGenericError(xmlGenericErrorContext,"End of empty tag %s : popping out %s\n", name, oldname);
5397#endif
5398 if (oldname != NULL)
5399 xmlFree(oldname);
5400 }
5401 ctxt->instate = XML_PARSER_CONTENT;
5402#ifdef DEBUG_PUSH
5403 xmlGenericError(xmlGenericErrorContext,
5404 "HPP: entering CONTENT\n");
5405#endif
5406 break;
5407 }
5408 case XML_PARSER_CONTENT: {
5409 long cons;
5410 /*
5411 * Handle preparsed entities and charRef
5412 */
5413 if (ctxt->token != 0) {
5414 xmlChar chr[2] = { 0 , 0 } ;
5415
5416 chr[0] = (xmlChar) ctxt->token;
5417 docbCheckParagraph(ctxt);
5418 if ((ctxt->sax != NULL) && (ctxt->sax->characters != NULL))
5419 ctxt->sax->characters(ctxt->userData, chr, 1);
5420 ctxt->token = 0;
5421 ctxt->checkIndex = 0;
5422 }
5423 if ((avail == 1) && (terminate)) {
5424 cur = in->cur[0];
5425 if ((cur != '<') && (cur != '&')) {
5426 if (ctxt->sax != NULL) {
5427 if (IS_BLANK(cur)) {
5428 if (ctxt->sax->ignorableWhitespace != NULL)
5429 ctxt->sax->ignorableWhitespace(
5430 ctxt->userData, &cur, 1);
5431 } else {
5432 docbCheckParagraph(ctxt);
5433 if (ctxt->sax->characters != NULL)
5434 ctxt->sax->characters(
5435 ctxt->userData, &cur, 1);
5436 }
5437 }
5438 ctxt->token = 0;
5439 ctxt->checkIndex = 0;
5440 NEXT;
5441 }
5442 break;
5443 }
5444 if (avail < 2)
5445 goto done;
5446 cur = in->cur[0];
5447 next = in->cur[1];
5448 cons = ctxt->nbChars;
5449 /*
5450 * Sometimes DOCTYPE arrives in the middle of the document
5451 */
5452 if ((cur == '<') && (next == '!') &&
5453 (UPP(2) == 'D') && (UPP(3) == 'O') &&
5454 (UPP(4) == 'C') && (UPP(5) == 'T') &&
5455 (UPP(6) == 'Y') && (UPP(7) == 'P') &&
5456 (UPP(8) == 'E')) {
5457 if ((!terminate) &&
5458 (docbParseLookupSequence(ctxt, '>', 0, 0) < 0))
5459 goto done;
5460 if ((ctxt->sax != NULL) && (ctxt->sax->error != NULL))
5461 ctxt->sax->error(ctxt->userData,
5462 "Misplaced DOCTYPE declaration\n");
5463 ctxt->wellFormed = 0;
5464 docbParseDocTypeDecl(ctxt);
5465 } else if ((cur == '<') && (next == '!') &&
5466 (in->cur[2] == '-') && (in->cur[3] == '-')) {
5467 if ((!terminate) &&
5468 (docbParseLookupSequence(ctxt, '-', '-', '>') < 0))
5469 goto done;
5470#ifdef DEBUG_PUSH
5471 xmlGenericError(xmlGenericErrorContext,
5472 "HPP: Parsing Comment\n");
5473#endif
5474 docbParseComment(ctxt);
5475 ctxt->instate = XML_PARSER_CONTENT;
5476 } else if ((cur == '<') && (next == '!') && (avail < 4)) {
5477 goto done;
5478 } else if ((cur == '<') && (next == '/')) {
5479 ctxt->instate = XML_PARSER_END_TAG;
5480 ctxt->checkIndex = 0;
5481#ifdef DEBUG_PUSH
5482 xmlGenericError(xmlGenericErrorContext,
5483 "HPP: entering END_TAG\n");
5484#endif
5485 break;
5486 } else if (cur == '<') {
5487 ctxt->instate = XML_PARSER_START_TAG;
5488 ctxt->checkIndex = 0;
5489#ifdef DEBUG_PUSH
5490 xmlGenericError(xmlGenericErrorContext,
5491 "HPP: entering START_TAG\n");
5492#endif
5493 break;
5494 } else if (cur == '&') {
5495 if ((!terminate) &&
5496 (docbParseLookupSequence(ctxt, ';', 0, 0) < 0))
5497 goto done;
5498#ifdef DEBUG_PUSH
5499 xmlGenericError(xmlGenericErrorContext,
5500 "HPP: Parsing Reference\n");
5501#endif
5502 /* TODO: check generation of subtrees if noent !!! */
5503 docbParseReference(ctxt);
5504 } else {
5505 /* TODO Avoid the extra copy, handle directly !!!!!! */
5506 /*
5507 * Goal of the following test is :
5508 * - minimize calls to the SAX 'character' callback
5509 * when they are mergeable
5510 */
5511 if ((ctxt->inputNr == 1) &&
5512 (avail < DOCB_PARSER_BIG_BUFFER_SIZE)) {
5513 if ((!terminate) &&
5514 (docbParseLookupSequence(ctxt, '<', 0, 0) < 0))
5515 goto done;
5516 }
5517 ctxt->checkIndex = 0;
5518#ifdef DEBUG_PUSH
5519 xmlGenericError(xmlGenericErrorContext,
5520 "HPP: Parsing char data\n");
5521#endif
5522 docbParseCharData(ctxt);
5523 }
5524 if (cons == ctxt->nbChars) {
5525 if (ctxt->node != NULL) {
5526 if ((ctxt->sax != NULL) && (ctxt->sax->error != NULL))
5527 ctxt->sax->error(ctxt->userData,
5528 "detected an error in element content\n");
5529 ctxt->wellFormed = 0;
5530 NEXT;
5531 }
5532 break;
5533 }
5534
5535 break;
5536 }
5537 case XML_PARSER_END_TAG:
5538 if (avail < 2)
5539 goto done;
5540 if ((!terminate) &&
5541 (docbParseLookupSequence(ctxt, '>', 0, 0) < 0))
5542 goto done;
5543 docbParseEndTag(ctxt);
5544 if (ctxt->nameNr == 0) {
5545 ctxt->instate = XML_PARSER_EPILOG;
5546 } else {
5547 ctxt->instate = XML_PARSER_CONTENT;
5548 }
5549 ctxt->checkIndex = 0;
5550#ifdef DEBUG_PUSH
5551 xmlGenericError(xmlGenericErrorContext,
5552 "HPP: entering CONTENT\n");
5553#endif
5554 break;
5555 case XML_PARSER_CDATA_SECTION:
5556 xmlGenericError(xmlGenericErrorContext,
5557 "HPP: internal error, state == CDATA\n");
5558 ctxt->instate = XML_PARSER_CONTENT;
5559 ctxt->checkIndex = 0;
5560#ifdef DEBUG_PUSH
5561 xmlGenericError(xmlGenericErrorContext,
5562 "HPP: entering CONTENT\n");
5563#endif
5564 break;
5565 case XML_PARSER_DTD:
5566 xmlGenericError(xmlGenericErrorContext,
5567 "HPP: internal error, state == DTD\n");
5568 ctxt->instate = XML_PARSER_CONTENT;
5569 ctxt->checkIndex = 0;
5570#ifdef DEBUG_PUSH
5571 xmlGenericError(xmlGenericErrorContext,
5572 "HPP: entering CONTENT\n");
5573#endif
5574 break;
5575 case XML_PARSER_COMMENT:
5576 xmlGenericError(xmlGenericErrorContext,
5577 "HPP: internal error, state == COMMENT\n");
5578 ctxt->instate = XML_PARSER_CONTENT;
5579 ctxt->checkIndex = 0;
5580#ifdef DEBUG_PUSH
5581 xmlGenericError(xmlGenericErrorContext,
5582 "HPP: entering CONTENT\n");
5583#endif
5584 break;
5585 case XML_PARSER_PI:
5586 xmlGenericError(xmlGenericErrorContext,
5587 "HPP: internal error, state == PI\n");
5588 ctxt->instate = XML_PARSER_CONTENT;
5589 ctxt->checkIndex = 0;
5590#ifdef DEBUG_PUSH
5591 xmlGenericError(xmlGenericErrorContext,
5592 "HPP: entering CONTENT\n");
5593#endif
5594 break;
5595 case XML_PARSER_ENTITY_DECL:
5596 xmlGenericError(xmlGenericErrorContext,
5597 "HPP: internal error, state == ENTITY_DECL\n");
5598 ctxt->instate = XML_PARSER_CONTENT;
5599 ctxt->checkIndex = 0;
5600#ifdef DEBUG_PUSH
5601 xmlGenericError(xmlGenericErrorContext,
5602 "HPP: entering CONTENT\n");
5603#endif
5604 break;
5605 case XML_PARSER_ENTITY_VALUE:
5606 xmlGenericError(xmlGenericErrorContext,
5607 "HPP: internal error, state == ENTITY_VALUE\n");
5608 ctxt->instate = XML_PARSER_CONTENT;
5609 ctxt->checkIndex = 0;
5610#ifdef DEBUG_PUSH
5611 xmlGenericError(xmlGenericErrorContext,
5612 "HPP: entering DTD\n");
5613#endif
5614 break;
5615 case XML_PARSER_ATTRIBUTE_VALUE:
5616 xmlGenericError(xmlGenericErrorContext,
5617 "HPP: internal error, state == ATTRIBUTE_VALUE\n");
5618 ctxt->instate = XML_PARSER_START_TAG;
5619 ctxt->checkIndex = 0;
5620#ifdef DEBUG_PUSH
5621 xmlGenericError(xmlGenericErrorContext,
5622 "HPP: entering START_TAG\n");
5623#endif
5624 break;
5625 case XML_PARSER_SYSTEM_LITERAL:
5626 xmlGenericError(xmlGenericErrorContext,
5627 "HPP: internal error, state == XML_PARSER_SYSTEM_LITERAL\n");
5628 ctxt->instate = XML_PARSER_CONTENT;
5629 ctxt->checkIndex = 0;
5630#ifdef DEBUG_PUSH
5631 xmlGenericError(xmlGenericErrorContext,
5632 "HPP: entering CONTENT\n");
5633#endif
5634 break;
5635
5636 case XML_PARSER_IGNORE:
5637 xmlGenericError(xmlGenericErrorContext,
5638 "HPP: internal error, state == XML_PARSER_IGNORE\n");
5639 ctxt->instate = XML_PARSER_CONTENT;
5640 ctxt->checkIndex = 0;
5641#ifdef DEBUG_PUSH
5642 xmlGenericError(xmlGenericErrorContext,
5643 "HPP: entering CONTENT\n");
5644#endif
5645 break;
5646 }
5647 }
5648done:
5649 if ((avail == 0) && (terminate)) {
5650 docbAutoClose(ctxt, NULL);
5651 if ((ctxt->nameNr == 0) && (ctxt->instate != XML_PARSER_EOF)) {
5652 /*
5653 * SAX: end of the document processing.
5654 */
5655 ctxt->instate = XML_PARSER_EOF;
5656 if ((ctxt->sax) && (ctxt->sax->endDocument != NULL))
5657 ctxt->sax->endDocument(ctxt->userData);
5658 }
5659 }
5660 if ((ctxt->myDoc != NULL) &&
5661 ((terminate) || (ctxt->instate == XML_PARSER_EOF) ||
5662 (ctxt->instate == XML_PARSER_EPILOG))) {
5663 xmlDtdPtr dtd;
5664 dtd = ctxt->myDoc->intSubset;
5665 if (dtd == NULL)
5666 ctxt->myDoc->intSubset =
5667 xmlCreateIntSubset(ctxt->myDoc, BAD_CAST "SGML",
5668 BAD_CAST "-//W3C//DTD SGML 4.0 Transitional//EN",
5669 BAD_CAST "http://www.w3.org/TR/REC-docbook/loose.dtd");
5670 }
5671#ifdef DEBUG_PUSH
5672 xmlGenericError(xmlGenericErrorContext, "HPP: done %d\n", ret);
5673#endif
5674 return(ret);
5675}
5676
5677/**
5678 * docbParseChunk:
5679 * @ctxt: an XML parser context
5680 * @chunk: an char array
5681 * @size: the size in byte of the chunk
5682 * @terminate: last chunk indicator
5683 *
5684 * Parse a Chunk of memory
5685 *
5686 * Returns zero if no error, the xmlParserErrors otherwise.
5687 */
5688int
5689docbParseChunk(docbParserCtxtPtr ctxt, const char *chunk, int size,
5690 int terminate) {
5691 if ((size > 0) && (chunk != NULL) && (ctxt->input != NULL) &&
5692 (ctxt->input->buf != NULL) && (ctxt->instate != XML_PARSER_EOF)) {
5693 int base = ctxt->input->base - ctxt->input->buf->buffer->content;
5694 int cur = ctxt->input->cur - ctxt->input->base;
5695
5696 xmlParserInputBufferPush(ctxt->input->buf, size, chunk);
5697 ctxt->input->base = ctxt->input->buf->buffer->content + base;
5698 ctxt->input->cur = ctxt->input->base + cur;
5699#ifdef DEBUG_PUSH
5700 xmlGenericError(xmlGenericErrorContext, "HPP: pushed %d\n", size);
5701#endif
5702
5703 if ((terminate) || (ctxt->input->buf->buffer->use > 80))
5704 docbParseTryOrFinish(ctxt, terminate);
5705 } else if (ctxt->instate != XML_PARSER_EOF) {
5706 xmlParserInputBufferPush(ctxt->input->buf, 0, "");
5707 docbParseTryOrFinish(ctxt, terminate);
5708 }
5709 if (terminate) {
5710 if ((ctxt->instate != XML_PARSER_EOF) &&
5711 (ctxt->instate != XML_PARSER_EPILOG) &&
5712 (ctxt->instate != XML_PARSER_MISC)) {
5713 ctxt->errNo = XML_ERR_DOCUMENT_END;
5714 if ((ctxt->sax != NULL) && (ctxt->sax->error != NULL))
5715 ctxt->sax->error(ctxt->userData,
5716 "Extra content at the end of the document\n");
5717 ctxt->wellFormed = 0;
5718 }
5719 if (ctxt->instate != XML_PARSER_EOF) {
5720 if ((ctxt->sax) && (ctxt->sax->endDocument != NULL))
5721 ctxt->sax->endDocument(ctxt->userData);
5722 }
5723 ctxt->instate = XML_PARSER_EOF;
5724 }
5725 return((xmlParserErrors) ctxt->errNo);
5726}
5727
5728/************************************************************************
5729 * *
5730 * User entry points *
5731 * *
5732 ************************************************************************/
5733
5734/**
5735 * docbCreatePushParserCtxt :
5736 * @sax: a SAX handler
5737 * @user_data: The user data returned on SAX callbacks
5738 * @chunk: a pointer to an array of chars
5739 * @size: number of chars in the array
5740 * @filename: an optional file name or URI
5741 * @enc: an optional encoding
5742 *
5743 * Create a parser context for using the DocBook SGML parser in push mode
5744 * To allow content encoding detection, @size should be >= 4
5745 * The value of @filename is used for fetching external entities
5746 * and error/warning reports.
5747 *
5748 * Returns the new parser context or NULL
5749 */
5750docbParserCtxtPtr
5751docbCreatePushParserCtxt(docbSAXHandlerPtr sax, void *user_data,
5752 const char *chunk, int size, const char *filename,
5753 xmlCharEncoding enc) {
5754 docbParserCtxtPtr ctxt;
5755 docbParserInputPtr inputStream;
5756 xmlParserInputBufferPtr buf;
5757
5758 buf = xmlAllocParserInputBuffer(enc);
5759 if (buf == NULL) return(NULL);
5760
5761 ctxt = (docbParserCtxtPtr) xmlMalloc(sizeof(docbParserCtxt));
5762 if (ctxt == NULL) {
5763 xmlFree(buf);
5764 return(NULL);
5765 }
5766 memset(ctxt, 0, sizeof(docbParserCtxt));
5767 docbInitParserCtxt(ctxt);
5768 if (sax != NULL) {
5769 if (ctxt->sax != &docbDefaultSAXHandler)
5770 xmlFree(ctxt->sax);
5771 ctxt->sax = (docbSAXHandlerPtr) xmlMalloc(sizeof(docbSAXHandler));
5772 if (ctxt->sax == NULL) {
5773 xmlFree(buf);
5774 xmlFree(ctxt);
5775 return(NULL);
5776 }
5777 memcpy(ctxt->sax, sax, sizeof(docbSAXHandler));
5778 if (user_data != NULL)
5779 ctxt->userData = user_data;
5780 }
5781 if (filename == NULL) {
5782 ctxt->directory = NULL;
5783 } else {
5784 ctxt->directory = xmlParserGetDirectory(filename);
5785 }
5786
5787 inputStream = docbNewInputStream(ctxt);
5788 if (inputStream == NULL) {
5789 xmlFreeParserCtxt(ctxt);
5790 return(NULL);
5791 }
5792
5793 if (filename == NULL)
5794 inputStream->filename = NULL;
5795 else
5796 inputStream->filename = xmlMemStrdup(filename);
5797 inputStream->buf = buf;
5798 inputStream->base = inputStream->buf->buffer->content;
5799 inputStream->cur = inputStream->buf->buffer->content;
5800
5801 inputPush(ctxt, inputStream);
5802
5803 if ((size > 0) && (chunk != NULL) && (ctxt->input != NULL) &&
5804 (ctxt->input->buf != NULL)) {
5805 xmlParserInputBufferPush(ctxt->input->buf, size, chunk);
5806#ifdef DEBUG_PUSH
5807 xmlGenericError(xmlGenericErrorContext, "HPP: pushed %d\n", size);
5808#endif
5809 }
5810
5811 return(ctxt);
5812}
5813
5814/**
5815 * docbSAXParseDoc :
5816 * @cur: a pointer to an array of xmlChar
5817 * @encoding: a free form C string describing the SGML document encoding, or NULL
5818 * @sax: the SAX handler block
5819 * @userData: if using SAX, this pointer will be provided on callbacks.
5820 *
5821 * parse an SGML in-memory document and build a tree.
5822 * It use the given SAX function block to handle the parsing callback.
5823 * If sax is NULL, fallback to the default DOM tree building routines.
5824 *
5825 * Returns the resulting document tree
5826 */
5827
5828docbDocPtr
5829docbSAXParseDoc(xmlChar *cur, const char *encoding, docbSAXHandlerPtr sax, void *userData) {
5830 docbDocPtr ret;
5831 docbParserCtxtPtr ctxt;
5832
5833 if (cur == NULL) return(NULL);
5834
5835
5836 ctxt = docbCreateDocParserCtxt(cur, encoding);
5837 if (ctxt == NULL) return(NULL);
5838 if (sax != NULL) {
5839 ctxt->sax = sax;
5840 ctxt->userData = userData;
5841 }
5842
5843 docbParseDocument(ctxt);
5844 ret = ctxt->myDoc;
5845 if (sax != NULL) {
5846 ctxt->sax = NULL;
5847 ctxt->userData = NULL;
5848 }
5849 docbFreeParserCtxt(ctxt);
5850
5851 return(ret);
5852}
5853
5854/**
5855 * docbParseDoc :
5856 * @cur: a pointer to an array of xmlChar
5857 * @encoding: a free form C string describing the SGML document encoding, or NULL
5858 *
5859 * parse an SGML in-memory document and build a tree.
5860 *
5861 * Returns the resulting document tree
5862 */
5863
5864docbDocPtr
5865docbParseDoc(xmlChar *cur, const char *encoding) {
5866 return(docbSAXParseDoc(cur, encoding, NULL, NULL));
5867}
5868
5869
5870/**
5871 * docbCreateFileParserCtxt :
5872 * @filename: the filename
5873 * @encoding: a free form C string describing the SGML document encoding, or NULL
5874 *
5875 * Create a parser context for a file content.
5876 * Automatic support for ZLIB/Compress compressed document is provided
5877 * by default if found at compile-time.
5878 *
5879 * Returns the new parser context or NULL
5880 */
5881docbParserCtxtPtr
5882docbCreateFileParserCtxt(const char *filename, const char *encoding)
5883{
5884 docbParserCtxtPtr ctxt;
5885 docbParserInputPtr inputStream;
5886 xmlParserInputBufferPtr buf;
5887 /* sgmlCharEncoding enc; */
5888
5889 buf = xmlParserInputBufferCreateFilename(filename, XML_CHAR_ENCODING_NONE);
5890 if (buf == NULL) return(NULL);
5891
5892 ctxt = (docbParserCtxtPtr) xmlMalloc(sizeof(docbParserCtxt));
5893 if (ctxt == NULL) {
5894 perror("malloc");
5895 return(NULL);
5896 }
5897 memset(ctxt, 0, sizeof(docbParserCtxt));
5898 docbInitParserCtxt(ctxt);
5899 inputStream = (docbParserInputPtr) xmlMalloc(sizeof(docbParserInput));
5900 if (inputStream == NULL) {
5901 perror("malloc");
5902 xmlFree(ctxt);
5903 return(NULL);
5904 }
5905 memset(inputStream, 0, sizeof(docbParserInput));
5906
5907 inputStream->filename = xmlMemStrdup(filename);
5908 inputStream->line = 1;
5909 inputStream->col = 1;
5910 inputStream->buf = buf;
5911 inputStream->directory = NULL;
5912
5913 inputStream->base = inputStream->buf->buffer->content;
5914 inputStream->cur = inputStream->buf->buffer->content;
5915 inputStream->free = NULL;
5916
5917 inputPush(ctxt, inputStream);
5918 return(ctxt);
5919}
5920
5921/**
5922 * docbSAXParseFile :
5923 * @filename: the filename
5924 * @encoding: a free form C string describing the SGML document encoding, or NULL
5925 * @sax: the SAX handler block
5926 * @userData: if using SAX, this pointer will be provided on callbacks.
5927 *
5928 * parse an SGML file and build a tree. Automatic support for ZLIB/Compress
5929 * compressed document is provided by default if found at compile-time.
5930 * It use the given SAX function block to handle the parsing callback.
5931 * If sax is NULL, fallback to the default DOM tree building routines.
5932 *
5933 * Returns the resulting document tree
5934 */
5935
5936docbDocPtr
5937docbSAXParseFile(const char *filename, const char *encoding, docbSAXHandlerPtr sax,
5938 void *userData) {
5939 docbDocPtr ret;
5940 docbParserCtxtPtr ctxt;
5941 docbSAXHandlerPtr oldsax = NULL;
5942
5943 ctxt = docbCreateFileParserCtxt(filename, encoding);
5944 if (ctxt == NULL) return(NULL);
5945 if (sax != NULL) {
5946 oldsax = ctxt->sax;
5947 ctxt->sax = sax;
5948 ctxt->userData = userData;
5949 }
5950
5951 docbParseDocument(ctxt);
5952
5953 ret = ctxt->myDoc;
5954 if (sax != NULL) {
5955 ctxt->sax = oldsax;
5956 ctxt->userData = NULL;
5957 }
5958 docbFreeParserCtxt(ctxt);
5959
5960 return(ret);
5961}
5962
5963/**
5964 * docbParseFile :
5965 * @filename: the filename
5966 * @encoding: a free form C string describing document encoding, or NULL
5967 *
5968 * parse a Docbook SGML file and build a tree. Automatic support for
5969 * ZLIB/Compress compressed document is provided by default if found
5970 * at compile-time.
5971 *
5972 * Returns the resulting document tree
5973 */
5974
5975docbDocPtr
5976docbParseFile(const char *filename, const char *encoding) {
5977 return(docbSAXParseFile(filename, encoding, NULL, NULL));
5978}
5979
5980#endif /* LIBXML_DOCB_ENABLED */