Gitiles
Code Review Sign In
gerrit-public.fairphone.software / fp2-dev / platform / external / libxml2 / cbaf399537a1fb69ef97b079e4cb553869aaa4d9 / . / DOCBparser.c
blob: bcfeb3d50fc7b048e9e05bdb307cf2a9b72c7ee5 [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 *
Daniel Veillarde95e2392001-06-06 10:46:28 +0000[diff] [blame]4 * This is extremely hackish. It also adds one extension
5 * <?sgml-declaration encoding="ISO-8859-1"?>
6 * allowing to store the encoding of the document within the instance.
7 *
Daniel Veillardeae522a2001-04-23 13:41:34 +0000[diff] [blame]8 * See Copyright for the status of this software.
9 *
Daniel Veillardc5d64342001-06-24 12:13:24 +0000[diff] [blame]10 * daniel@veillard.com
Daniel Veillardeae522a2001-04-23 13:41:34 +0000[diff] [blame]11 */
12
13#include "libxml.h"
14#ifdef LIBXML_DOCB_ENABLED
15
16#include <string.h>
17#ifdef HAVE_CTYPE_H
18#include <ctype.h>
19#endif
20#ifdef HAVE_STDLIB_H
21#include <stdlib.h>
22#endif
23#ifdef HAVE_SYS_STAT_H
24#include <sys/stat.h>
25#endif
26#ifdef HAVE_FCNTL_H
27#include <fcntl.h>
28#endif
29#ifdef HAVE_UNISTD_H
30#include <unistd.h>
31#endif
32#ifdef HAVE_ZLIB_H
33#include <zlib.h>
34#endif
35
36#include <libxml/xmlmemory.h>
37#include <libxml/tree.h>
38#include <libxml/SAX.h>
39#include <libxml/parser.h>
40#include <libxml/parserInternals.h>
41#include <libxml/xmlerror.h>
42#include <libxml/DOCBparser.h>
43#include <libxml/entities.h>
44#include <libxml/encoding.h>
45#include <libxml/valid.h>
46#include <libxml/xmlIO.h>
47#include <libxml/uri.h>
Daniel Veillard3c01b1d2001-10-17 15:58:35 +0000[diff] [blame]48#include <libxml/globals.h>
Daniel Veillardeae522a2001-04-23 13:41:34 +0000[diff] [blame]49
50/*
Daniel Veillard89cad532001-10-22 09:46:13 +0000[diff] [blame]51 * DocBook XML current versions
52 */
53
54#define XML_DOCBOOK_XML_PUBLIC (const xmlChar *) \
55 "-//OASIS//DTD DocBook XML V4.1.2//EN"
56#define XML_DOCBOOK_XML_SYSTEM (const xmlChar *) \
57 "http://www.oasis-open.org/docbook/xml/4.1.2/docbookx.dtd"
58
59/*
Daniel Veillardeae522a2001-04-23 13:41:34 +0000[diff] [blame]60 * Internal description of an SGML entity
61 */
62typedef struct _docbEntityDesc docbEntityDesc;
63typedef docbEntityDesc *docbEntityDescPtr;
64struct _docbEntityDesc {
65 int value; /* the UNICODE value for the character */
66 const char *name; /* The entity name */
67 const char *desc; /* the description */
68};
69
70#if 0
71docbElemDescPtr docbTagLookup (const xmlChar *tag);
72docbEntityDescPtr docbEntityLookup(const xmlChar *name);
73docbEntityDescPtr docbEntityValueLookup(int value);
74
75int docbIsAutoClosed(docbDocPtr doc,
76 docbNodePtr elem);
77int docbAutoCloseTag(docbDocPtr doc,
78 const xmlChar *name,
79 docbNodePtr elem);
80
81#endif
Daniel Veillard61b33d52001-04-24 13:55:12 +0000[diff] [blame]82static int docbParseCharRef(docbParserCtxtPtr ctxt);
83static xmlEntityPtr docbParseEntityRef(docbParserCtxtPtr ctxt,
Daniel Veillardeae522a2001-04-23 13:41:34 +0000[diff] [blame]84 xmlChar **str);
Daniel Veillard61b33d52001-04-24 13:55:12 +0000[diff] [blame]85static void docbParseElement(docbParserCtxtPtr ctxt);
Daniel Veillard1034da22001-04-25 19:06:28 +0000[diff] [blame]86static void docbParseContent(docbParserCtxtPtr ctxt);
Daniel Veillardeae522a2001-04-23 13:41:34 +0000[diff] [blame]87
88/*
89 * Internal description of an SGML element
90 */
91typedef struct _docbElemDesc docbElemDesc;
92typedef docbElemDesc *docbElemDescPtr;
93struct _docbElemDesc {
94 const char *name; /* The tag name */
95 int startTag; /* Whether the start tag can be implied */
96 int endTag; /* Whether the end tag can be implied */
97 int empty; /* Is this an empty element ? */
98 int depr; /* Is this a deprecated element ? */
99 int dtd; /* 1: only in Loose DTD, 2: only Frameset one */
100 const char *desc; /* the description */
101};
102
103
104#define DOCB_MAX_NAMELEN 1000
105#define DOCB_PARSER_BIG_BUFFER_SIZE 1000
106#define DOCB_PARSER_BUFFER_SIZE 100
107
108/* #define DEBUG */
109/* #define DEBUG_PUSH */
110
111/************************************************************************
112 * *
113 * Parser stacks related functions and macros *
114 * *
115 ************************************************************************/
116
117/*
118 * Generic function for accessing stacks in the Parser Context
119 */
120
121#define PUSH_AND_POP(scope, type, name) \
122scope int docb##name##Push(docbParserCtxtPtr ctxt, type value) { \
123 if (ctxt->name##Nr >= ctxt->name##Max) { \
124 ctxt->name##Max *= 2; \
125 ctxt->name##Tab = (type *) xmlRealloc(ctxt->name##Tab, \
126 ctxt->name##Max * sizeof(ctxt->name##Tab[0])); \
127 if (ctxt->name##Tab == NULL) { \
128 xmlGenericError(xmlGenericErrorContext, "realloc failed !\n"); \
129 return(0); \
130 } \
131 } \
132 ctxt->name##Tab[ctxt->name##Nr] = value; \
133 ctxt->name = value; \
134 return(ctxt->name##Nr++); \
135} \
136scope type docb##name##Pop(docbParserCtxtPtr ctxt) { \
137 type ret; \
138 if (ctxt->name##Nr < 0) return(0); \
139 ctxt->name##Nr--; \
140 if (ctxt->name##Nr < 0) return(0); \
141 if (ctxt->name##Nr > 0) \
142 ctxt->name = ctxt->name##Tab[ctxt->name##Nr - 1]; \
143 else \
144 ctxt->name = NULL; \
145 ret = ctxt->name##Tab[ctxt->name##Nr]; \
146 ctxt->name##Tab[ctxt->name##Nr] = 0; \
147 return(ret); \
148} \
149
150/* PUSH_AND_POP(static, xmlNodePtr, node) */
151PUSH_AND_POP(static, xmlChar*, name)
152
153/*
154 * Macros for accessing the content. Those should be used only by the parser,
155 * and not exported.
156 *
157 * Dirty macros, i.e. one need to make assumption on the context to use them
158 *
159 * CUR_PTR return the current pointer to the xmlChar to be parsed.
160 * CUR returns the current xmlChar value, i.e. a 8 bit value if compiled
161 * in ISO-Latin or UTF-8, and the current 16 bit value if compiled
162 * in UNICODE mode. This should be used internally by the parser
163 * only to compare to ASCII values otherwise it would break when
164 * running with UTF-8 encoding.
165 * NXT(n) returns the n'th next xmlChar. Same as CUR is should be used only
166 * to compare on ASCII based substring.
167 * UPP(n) returns the n'th next xmlChar converted to uppercase. Same as CUR
168 * it should be used only to compare on ASCII based substring.
169 * SKIP(n) Skip n xmlChar, and must also be used only to skip ASCII defined
170 * strings within the parser.
171 *
172 * Clean macros, not dependent of an ASCII context, expect UTF-8 encoding
173 *
174 * CURRENT Returns the current char value, with the full decoding of
175 * UTF-8 if we are using this mode. It returns an int.
176 * NEXT Skip to the next character, this does the proper decoding
177 * in UTF-8 mode. It also pop-up unfinished entities on the fly.
178 * COPY(to) copy one char to *to, increment CUR_PTR and to accordingly
179 */
180
181#define UPPER (toupper(*ctxt->input->cur))
182
183#define SKIP(val) ctxt->nbChars += (val),ctxt->input->cur += (val)
184
185#define NXT(val) ctxt->input->cur[(val)]
186
187#define UPP(val) (toupper(ctxt->input->cur[(val)]))
188
189#define CUR_PTR ctxt->input->cur
190
191#define SHRINK xmlParserInputShrink(ctxt->input)
192
193#define GROW xmlParserInputGrow(ctxt->input, INPUT_CHUNK)
194
195#define CURRENT ((int) (*ctxt->input->cur))
196
197#define SKIP_BLANKS docbSkipBlankChars(ctxt)
198
199/* Imported from XML */
200
201/* #define CUR (ctxt->token ? ctxt->token : (int) (*ctxt->input->cur)) */
202#define CUR ((int) (*ctxt->input->cur))
203#define NEXT xmlNextChar(ctxt),ctxt->nbChars++
204
205#define RAW (ctxt->token ? -1 : (*ctxt->input->cur))
206#define NXT(val) ctxt->input->cur[(val)]
207#define CUR_PTR ctxt->input->cur
208
209
210#define NEXTL(l) do { \
211 if (*(ctxt->input->cur) == '\n') { \
212 ctxt->input->line++; ctxt->input->col = 1; \
213 } else ctxt->input->col++; \
214 ctxt->token = 0; ctxt->input->cur += l; ctxt->nbChars++; \
215 } while (0)
216
217/************
218 \
219 if (*ctxt->input->cur == '%') xmlParserHandlePEReference(ctxt); \
220 if (*ctxt->input->cur == '&') xmlParserHandleReference(ctxt);
221 ************/
222
223#define CUR_CHAR(l) docbCurrentChar(ctxt, &l)
224#define CUR_SCHAR(s, l) xmlStringCurrentChar(ctxt, s, &l)
225
226#define COPY_BUF(l,b,i,v) \
227 if (l == 1) b[i++] = (xmlChar) v; \
228 else i += xmlCopyChar(l,&b[i],v)
229
230/**
231 * docbCurrentChar:
232 * @ctxt: the DocBook SGML parser context
233 * @len: pointer to the length of the char read
234 *
Daniel Veillardcbaf3992001-12-31 16:16:02 +0000[diff] [blame^]235 * The current char value, if using UTF-8 this may actually span multiple
Daniel Veillardeae522a2001-04-23 13:41:34 +0000[diff] [blame]236 * bytes in the input buffer. Implement the end of line normalization:
237 * 2.11 End-of-Line Handling
238 * If the encoding is unspecified, in the case we find an ISO-Latin-1
239 * char, then the encoding converter is plugged in automatically.
240 *
Daniel Veillard60087f32001-10-10 09:45:09 +0000[diff] [blame]241 * Returns the current char value and its length
Daniel Veillardeae522a2001-04-23 13:41:34 +0000[diff] [blame]242 */
243
244static int
245docbCurrentChar(xmlParserCtxtPtr ctxt, int *len) {
246 if (ctxt->instate == XML_PARSER_EOF)
247 return(0);
248
249 if (ctxt->token != 0) {
250 *len = 0;
251 return(ctxt->token);
252 }
253 if (ctxt->charset == XML_CHAR_ENCODING_UTF8) {
254 /*
255 * We are supposed to handle UTF8, check it's valid
256 * From rfc2044: encoding of the Unicode values on UTF-8:
257 *
258 * UCS-4 range (hex.) UTF-8 octet sequence (binary)
259 * 0000 0000-0000 007F 0xxxxxxx
260 * 0000 0080-0000 07FF 110xxxxx 10xxxxxx
261 * 0000 0800-0000 FFFF 1110xxxx 10xxxxxx 10xxxxxx
262 *
263 * Check for the 0x110000 limit too
264 */
265 const unsigned char *cur = ctxt->input->cur;
266 unsigned char c;
267 unsigned int val;
268
269 c = *cur;
270 if (c & 0x80) {
271 if (cur[1] == 0)
272 xmlParserInputGrow(ctxt->input, INPUT_CHUNK);
273 if ((cur[1] & 0xc0) != 0x80)
274 goto encoding_error;
275 if ((c & 0xe0) == 0xe0) {
276
277 if (cur[2] == 0)
278 xmlParserInputGrow(ctxt->input, INPUT_CHUNK);
279 if ((cur[2] & 0xc0) != 0x80)
280 goto encoding_error;
281 if ((c & 0xf0) == 0xf0) {
282 if (cur[3] == 0)
283 xmlParserInputGrow(ctxt->input, INPUT_CHUNK);
284 if (((c & 0xf8) != 0xf0) ||
285 ((cur[3] & 0xc0) != 0x80))
286 goto encoding_error;
287 /* 4-byte code */
288 *len = 4;
289 val = (cur[0] & 0x7) << 18;
290 val |= (cur[1] & 0x3f) << 12;
291 val |= (cur[2] & 0x3f) << 6;
292 val |= cur[3] & 0x3f;
293 } else {
294 /* 3-byte code */
295 *len = 3;
296 val = (cur[0] & 0xf) << 12;
297 val |= (cur[1] & 0x3f) << 6;
298 val |= cur[2] & 0x3f;
299 }
300 } else {
301 /* 2-byte code */
302 *len = 2;
303 val = (cur[0] & 0x1f) << 6;
304 val |= cur[1] & 0x3f;
305 }
306 if (!IS_CHAR(val)) {
307 ctxt->errNo = XML_ERR_INVALID_ENCODING;
308 if ((ctxt->sax != NULL) &&
309 (ctxt->sax->error != NULL))
310 ctxt->sax->error(ctxt->userData,
311 "Char 0x%X out of allowed range\n", val);
312 ctxt->wellFormed = 0;
313 ctxt->disableSAX = 1;
314 }
315 return(val);
316 } else {
317 /* 1-byte code */
318 *len = 1;
319 return((int) *ctxt->input->cur);
320 }
321 }
322 /*
Daniel Veillard60087f32001-10-10 09:45:09 +0000[diff] [blame]323 * Assume it's a fixed length encoding (1) with
Daniel Veillardcbaf3992001-12-31 16:16:02 +0000[diff] [blame^]324 * a compatible encoding for the ASCII set, since
Daniel Veillardeae522a2001-04-23 13:41:34 +0000[diff] [blame]325 * XML constructs only use < 128 chars
326 */
327 *len = 1;
328 if ((int) *ctxt->input->cur < 0x80)
329 return((int) *ctxt->input->cur);
330
331 /*
332 * Humm this is bad, do an automatic flow conversion
333 */
334 xmlSwitchEncoding(ctxt, XML_CHAR_ENCODING_8859_1);
335 ctxt->charset = XML_CHAR_ENCODING_UTF8;
336 return(xmlCurrentChar(ctxt, len));
337
338encoding_error:
339 /*
340 * If we detect an UTF8 error that probably mean that the
341 * input encoding didn't get properly advertized in the
342 * declaration header. Report the error and switch the encoding
343 * to ISO-Latin-1 (if you don't like this policy, just declare the
344 * encoding !)
345 */
346 ctxt->errNo = XML_ERR_INVALID_ENCODING;
347 if ((ctxt->sax != NULL) && (ctxt->sax->error != NULL)) {
348 ctxt->sax->error(ctxt->userData,
349 "Input is not proper UTF-8, indicate encoding !\n");
350 ctxt->sax->error(ctxt->userData, "Bytes: 0x%02X 0x%02X 0x%02X 0x%02X\n",
351 ctxt->input->cur[0], ctxt->input->cur[1],
352 ctxt->input->cur[2], ctxt->input->cur[3]);
353 }
354
355 ctxt->charset = XML_CHAR_ENCODING_8859_1;
356 *len = 1;
357 return((int) *ctxt->input->cur);
358}
359
360#if 0
361/**
362 * sgmlNextChar:
363 * @ctxt: the DocBook SGML parser context
364 *
365 * Skip to the next char input char.
366 */
367
368static void
369sgmlNextChar(docbParserCtxtPtr ctxt) {
370 if (ctxt->instate == XML_PARSER_EOF)
371 return;
372 if ((*ctxt->input->cur == 0) &&
373 (xmlParserInputGrow(ctxt->input, INPUT_CHUNK) <= 0)) {
374 xmlPopInput(ctxt);
375 } else {
376 if (*(ctxt->input->cur) == '\n') {
377 ctxt->input->line++; ctxt->input->col = 1;
378 } else ctxt->input->col++;
379 ctxt->input->cur++;
380 ctxt->nbChars++;
381 if (*ctxt->input->cur == 0)
382 xmlParserInputGrow(ctxt->input, INPUT_CHUNK);
383 }
384}
385#endif
386
387/**
388 * docbSkipBlankChars:
389 * @ctxt: the DocBook SGML parser context
390 *
391 * skip all blanks character found at that point in the input streams.
392 *
393 * Returns the number of space chars skipped
394 */
395
396static int
397docbSkipBlankChars(xmlParserCtxtPtr ctxt) {
398 int res = 0;
399
400 while (IS_BLANK(*(ctxt->input->cur))) {
401 if ((*ctxt->input->cur == 0) &&
402 (xmlParserInputGrow(ctxt->input, INPUT_CHUNK) <= 0)) {
403 xmlPopInput(ctxt);
404 } else {
405 if (*(ctxt->input->cur) == '\n') {
406 ctxt->input->line++; ctxt->input->col = 1;
407 } else ctxt->input->col++;
408 ctxt->input->cur++;
409 ctxt->nbChars++;
410 if (*ctxt->input->cur == 0)
411 xmlParserInputGrow(ctxt->input, INPUT_CHUNK);
412 }
413 res++;
414 }
415 return(res);
416}
417
418
419
420/************************************************************************
421 * *
422 * The list of SGML elements and their properties *
423 * *
424 ************************************************************************/
425
426/*
427 * Start Tag: 1 means the start tag can be ommited
428 * End Tag: 1 means the end tag can be ommited
429 * 2 means it's forbidden (empty elements)
430 * Depr: this element is deprecated
431 * DTD: 1 means that this element is valid only in the Loose DTD
432 * 2 means that this element is valid only in the Frameset DTD
433 *
434 * Name,Start Tag,End Tag, Empty, Depr., DTD, Description
435 */
436static docbElemDesc
437docbookElementTable[] = {
438{ "abbrev", 0, 0, 0, 3, 0, "" }, /* word */
439{ "abstract", 0, 0, 0, 9, 0, "" }, /* title */
440{ "accel", 0, 0, 0, 7, 0, "" }, /* smallcptr */
441{ "ackno", 0, 0, 0, 4, 0, "" }, /* docinfo */
442{ "acronym", 0, 0, 0, 3, 0, "" }, /* word */
443{ "action", 0, 0, 0, 7, 0, "" }, /* smallcptr */
444{ "address", 0, 0, 0, 1, 0, "" },
445{ "affiliation",0, 0, 0, 9, 0, "" }, /* shortaffil */
446{ "alt", 0, 0, 0, 1, 0, "" },
447{ "anchor", 0, 2, 1, 0, 0, "" },
448{ "answer", 0, 0, 0, 9, 0, "" }, /* label */
449{ "appendix", 0, 0, 0, 9, 0, "" }, /* appendixinfo */
450{ "appendixinfo",0, 0, 0, 9, 0, "" }, /* graphic */
451{ "application",0, 0, 0, 2, 0, "" }, /* para */
452{ "area", 0, 2, 1, 0, 0, "" },
453{ "areaset", 0, 0, 0, 9, 0, "" }, /* area */
454{ "areaspec", 0, 0, 0, 9, 0, "" }, /* area */
455{ "arg", 0, 0, 0, 1, 0, "" },
Daniel Veillard4ec0b0f2001-04-25 15:53:40 +0000[diff] [blame]456{ "artheader", 0, 0, 0, 9, 0, "" },
Daniel Veillardeae522a2001-04-23 13:41:34 +0000[diff] [blame]457{ "article", 0, 0, 0, 9, 0, "" }, /* div.title.content */
458{ "articleinfo",0, 0, 0, 9, 0, "" }, /* graphic */
459{ "artpagenums",0, 0, 0, 4, 0, "" }, /* docinfo */
460{ "attribution",0, 0, 0, 2, 0, "" }, /* para */
461{ "audiodata", 0, 2, 1, 0, 0, "" },
462{ "audioobject",0, 0, 0, 9, 0, "" }, /* objectinfo */
463{ "authorblurb",0, 0, 0, 9, 0, "" }, /* title */
464{ "authorgroup",0, 0, 0, 9, 0, "" }, /* author */
465{ "authorinitials",0, 0, 0, 4, 0, "" }, /* docinfo */
466{ "author", 0, 0, 0, 9, 0, "" }, /* person.ident.mix */
467{ "beginpage", 0, 2, 1, 0, 0, "" },
468{ "bibliodiv", 0, 0, 0, 9, 0, "" }, /* sect.title.content */
469{ "biblioentry",0, 0, 0, 9, 0, "" }, /* articleinfo */
470{ "bibliography",0, 0, 0, 9, 0, "" }, /* bibliographyinfo */
471{ "bibliographyinfo",0, 0, 0, 9, 0, "" }, /* graphic */
472{ "bibliomisc", 0, 0, 0, 2, 0, "" }, /* para */
473{ "bibliomixed",0, 0, 0, 1, 0, "" }, /* %bibliocomponent.mix, bibliomset) */
474{ "bibliomset", 0, 0, 0, 1, 0, "" }, /* %bibliocomponent.mix; | bibliomset) */
475{ "biblioset", 0, 0, 0, 9, 0, "" }, /* bibliocomponent.mix */
476{ "blockquote", 0, 0, 0, 9, 0, "" }, /* title */
477{ "book", 0, 0, 0, 9, 0, "" }, /* div.title.content */
478{ "bookinfo", 0, 0, 0, 9, 0, "" }, /* graphic */
479{ "bridgehead", 0, 0, 0, 8, 0, "" }, /* title */
480{ "callout", 0, 0, 0, 9, 0, "" }, /* component.mix */
481{ "calloutlist",0, 0, 0, 9, 0, "" }, /* formalobject.title.content */
482{ "caption", 0, 0, 0, 9, 0, "" }, /* textobject.mix */
483{ "caution", 0, 0, 0, 9, 0, "" }, /* title */
484{ "chapter", 0, 0, 0, 9, 0, "" }, /* chapterinfo */
485{ "chapterinfo",0, 0, 0, 9, 0, "" }, /* graphic */
486{ "citation", 0, 0, 0, 2, 0, "" }, /* para */
487{ "citerefentry",0, 0, 0, 9, 0, "" }, /* refentrytitle */
488{ "citetitle", 0, 0, 0, 2, 0, "" }, /* para */
489{ "city", 0, 0, 0, 4, 0, "" }, /* docinfo */
490{ "classname", 0, 0, 0, 7, 0, "" }, /* smallcptr */
491{ "classsynopsisinfo",0,0, 0, 9, 0, "" }, /* cptr */
492{ "classsynopsis",0, 0, 0, 9, 0, "" }, /* ooclass */
493{ "cmdsynopsis",0, 0, 0, 9, 0, "" }, /* command */
494{ "co", 0, 2, 1, 0, 0, "" },
495{ "collab", 0, 0, 0, 9, 0, "" }, /* collabname */
496{ "collabname", 0, 0, 0, 4, 0, "" }, /* docinfo */
497{ "colophon", 0, 0, 0, 9, 0, "" }, /* sect.title.content */
498{ "colspec", 0, 2, 1, 0, 0, "" },
499{ "colspec", 0, 2, 1, 0, 0, "" },
500{ "command", 0, 0, 0, 9, 0, "" }, /* cptr */
501{ "computeroutput",0, 0, 0, 9, 0, "" }, /* cptr */
502{ "confdates", 0, 0, 0, 4, 0, "" }, /* docinfo */
503{ "confgroup", 0, 0, 0, 9, 0, "" }, /* confdates */
504{ "confnum", 0, 0, 0, 4, 0, "" }, /* docinfo */
505{ "confsponsor",0, 0, 0, 4, 0, "" }, /* docinfo */
506{ "conftitle", 0, 0, 0, 4, 0, "" }, /* docinfo */
507{ "constant", 0, 0, 0, 7, 0, "" }, /* smallcptr */
508{ "constructorsynopsis",0,0, 0, 9, 0, "" }, /* modifier */
509{ "contractnum",0, 0, 0, 4, 0, "" }, /* docinfo */
510{ "contractsponsor",0, 0, 0, 4, 0, "" }, /* docinfo */
511{ "contrib", 0, 0, 0, 4, 0, "" }, /* docinfo */
512{ "copyright", 0, 0, 0, 9, 0, "" }, /* year */
513{ "corpauthor", 0, 0, 0, 4, 0, "" }, /* docinfo */
514{ "corpname", 0, 0, 0, 4, 0, "" }, /* docinfo */
515{ "country", 0, 0, 0, 4, 0, "" }, /* docinfo */
516{ "database", 0, 0, 0, 7, 0, "" }, /* smallcptr */
517{ "date", 0, 0, 0, 4, 0, "" }, /* docinfo */
518{ "dedication", 0, 0, 0, 9, 0, "" }, /* sect.title.content */
519{ "destructorsynopsis",0,0, 0, 9, 0, "" }, /* modifier */
Daniel Veillardc057c5d2001-05-02 12:41:24 +0000[diff] [blame]520{ "docinfo", 0, 0, 0, 9, 0, "" },
Daniel Veillardeae522a2001-04-23 13:41:34 +0000[diff] [blame]521{ "edition", 0, 0, 0, 4, 0, "" }, /* docinfo */
522{ "editor", 0, 0, 0, 9, 0, "" }, /* person.ident.mix */
523{ "email", 0, 0, 0, 4, 0, "" }, /* docinfo */
524{ "emphasis", 0, 0, 0, 2, 0, "" }, /* para */
525{ "entry", 0, 0, 0, 9, 0, "" }, /* tbl.entry.mdl */
526{ "entrytbl", 0, 0, 0, 9, 0, "" }, /* tbl.entrytbl.mdl */
527{ "envar", 0, 0, 0, 7, 0, "" }, /* smallcptr */
528{ "epigraph", 0, 0, 0, 9, 0, "" }, /* attribution */
529{ "equation", 0, 0, 0, 9, 0, "" }, /* formalobject.title.content */
530{ "errorcode", 0, 0, 0, 7, 0, "" }, /* smallcptr */
531{ "errorname", 0, 0, 0, 7, 0, "" }, /* smallcptr */
532{ "errortype", 0, 0, 0, 7, 0, "" }, /* smallcptr */
533{ "example", 0, 0, 0, 9, 0, "" }, /* formalobject.title.content */
534{ "exceptionname",0, 0, 0, 7, 0, "" }, /* smallcptr */
535{ "fax", 0, 0, 0, 4, 0, "" }, /* docinfo */
536{ "fieldsynopsis", 0, 0, 0, 9, 0, "" }, /* modifier */
537{ "figure", 0, 0, 0, 9, 0, "" }, /* formalobject.title.content */
538{ "filename", 0, 0, 0, 7, 0, "" }, /* smallcptr */
539{ "firstname", 0, 0, 0, 4, 0, "" }, /* docinfo */
540{ "firstterm", 0, 0, 0, 3, 0, "" }, /* word */
541{ "footnote", 0, 0, 0, 9, 0, "" }, /* footnote.mix */
542{ "footnoteref",0, 2, 1, 0, 0, "" },
543{ "foreignphrase",0, 0, 0, 2, 0, "" }, /* para */
544{ "formalpara", 0, 0, 0, 9, 0, "" }, /* title */
545{ "funcdef", 0, 0, 0, 1, 0, "" },
546{ "funcparams", 0, 0, 0, 9, 0, "" }, /* cptr */
547{ "funcprototype",0, 0, 0, 9, 0, "" }, /* funcdef */
548{ "funcsynopsis",0, 0, 0, 9, 0, "" }, /* funcsynopsisinfo */
549{ "funcsynopsisinfo", 0, 0, 0, 9, 0, "" }, /* cptr */
550{ "function", 0, 0, 0, 9, 0, "" }, /* cptr */
551{ "glossary", 0, 0, 0, 9, 0, "" }, /* glossaryinfo */
552{ "glossaryinfo",0, 0, 0, 9, 0, "" }, /* graphic */
553{ "glossdef", 0, 0, 0, 9, 0, "" }, /* glossdef.mix */
554{ "glossdiv", 0, 0, 0, 9, 0, "" }, /* sect.title.content */
555{ "glossentry", 0, 0, 0, 9, 0, "" }, /* glossterm */
556{ "glosslist", 0, 0, 0, 9, 0, "" }, /* glossentry */
Daniel Veillardc057c5d2001-05-02 12:41:24 +0000[diff] [blame]557{ "glossseealso",0, 0, 1, 2, 0, "" }, /* para */
558{ "glosssee", 0, 0, 1, 2, 0, "" }, /* para */
Daniel Veillardeae522a2001-04-23 13:41:34 +0000[diff] [blame]559{ "glossterm", 0, 0, 0, 2, 0, "" }, /* para */
Daniel Veillard4ec0b0f2001-04-25 15:53:40 +0000[diff] [blame]560{ "graphic", 0, 0, 0, 9, 0, "" },
Daniel Veillardeae522a2001-04-23 13:41:34 +0000[diff] [blame]561{ "graphicco", 0, 0, 0, 9, 0, "" }, /* areaspec */
562{ "group", 0, 0, 0, 9, 0, "" }, /* arg */
563{ "guibutton", 0, 0, 0, 7, 0, "" }, /* smallcptr */
564{ "guiicon", 0, 0, 0, 7, 0, "" }, /* smallcptr */
565{ "guilabel", 0, 0, 0, 7, 0, "" }, /* smallcptr */
566{ "guimenuitem",0, 0, 0, 7, 0, "" }, /* smallcptr */
567{ "guimenu", 0, 0, 0, 7, 0, "" }, /* smallcptr */
568{ "guisubmenu", 0, 0, 0, 7, 0, "" }, /* smallcptr */
569{ "hardware", 0, 0, 0, 7, 0, "" }, /* smallcptr */
570{ "highlights", 0, 0, 0, 9, 0, "" }, /* highlights.mix */
571{ "holder", 0, 0, 0, 4, 0, "" }, /* docinfo */
572{ "honorific", 0, 0, 0, 4, 0, "" }, /* docinfo */
573{ "imagedata", 0, 2, 1, 0, 0, "" },
574{ "imageobjectco",0, 0, 0, 9, 0, "" }, /* areaspec */
575{ "imageobject",0, 0, 0, 9, 0, "" }, /* objectinfo */
576{ "important", 0, 0, 0, 9, 0, "" }, /* title */
577{ "indexdiv", 0, 0, 0, 9, 0, "" }, /* sect.title.content */
578{ "indexentry", 0, 0, 0, 9, 0, "" }, /* primaryie */
579{ "index", 0, 0, 0, 9, 0, "" }, /* indexinfo */
580{ "indexinfo", 0, 0, 0, 9, 0, "" }, /* graphic */
581{ "indexterm", 0, 0, 0, 9, 0, "" }, /* primary */
582{ "informalequation",0, 0, 0, 9, 0, "" }, /* equation.content */
583{ "informalexample",0, 0, 0, 9, 0, "" }, /* example.mix */
584{ "informalfigure",0, 0, 0, 9, 0, "" }, /* figure.mix */
585{ "informaltable",0, 0, 0, 9, 0, "" }, /* graphic */
586{ "initializer",0, 0, 0, 7, 0, "" }, /* smallcptr */
587{ "inlineequation",0, 0, 0, 9, 0, "" }, /* inlineequation.content */
Daniel Veillard02f077a2001-04-26 10:59:11 +0000[diff] [blame]588{ "inlinegraphic",0, 0, 0, 9, 0, "" },
Daniel Veillardeae522a2001-04-23 13:41:34 +0000[diff] [blame]589{ "inlinemediaobject",0,0, 0, 9, 0, "" }, /* objectinfo */
590{ "interfacename",0, 0, 0, 7, 0, "" }, /* smallcptr */
591{ "interface", 0, 0, 0, 7, 0, "" }, /* smallcptr */
592{ "invpartnumber",0, 0, 0, 4, 0, "" }, /* docinfo */
593{ "isbn", 0, 0, 0, 4, 0, "" }, /* docinfo */
594{ "issn", 0, 0, 0, 4, 0, "" }, /* docinfo */
595{ "issuenum", 0, 0, 0, 4, 0, "" }, /* docinfo */
596{ "itemizedlist",0, 0, 0, 9, 0, "" }, /* formalobject.title.content */
597{ "itermset", 0, 0, 0, 9, 0, "" }, /* indexterm */
598{ "jobtitle", 0, 0, 0, 4, 0, "" }, /* docinfo */
599{ "keycap", 0, 0, 0, 7, 0, "" }, /* smallcptr */
600{ "keycode", 0, 0, 0, 7, 0, "" }, /* smallcptr */
601{ "keycombo", 0, 0, 0, 9, 0, "" }, /* keycap */
602{ "keysym", 0, 0, 0, 7, 0, "" }, /* smallcptr */
603{ "keyword", 0, 0, 0, 1, 0, "" },
604{ "keywordset", 0, 0, 0, 9, 0, "" }, /* keyword */
605{ "label", 0, 0, 0, 3, 0, "" }, /* word */
606{ "legalnotice",0, 0, 0, 9, 0, "" }, /* title */
607{ "lineage", 0, 0, 0, 4, 0, "" }, /* docinfo */
608{ "lineannotation",0, 0, 0, 2, 0, "" }, /* para */
609{ "link", 0, 0, 0, 2, 0, "" }, /* para */
610{ "listitem", 0, 0, 0, 9, 0, "" }, /* component.mix */
611{ "literal", 0, 0, 0, 9, 0, "" }, /* cptr */
612{ "literallayout",0, 0, 0, 2, 0, "" }, /* para */
613{ "lot", 0, 0, 0, 9, 0, "" }, /* bookcomponent.title.content */
614{ "lotentry", 0, 0, 0, 2, 0, "" }, /* para */
615{ "manvolnum", 0, 0, 0, 3, 0, "" }, /* word */
616{ "markup", 0, 0, 0, 7, 0, "" }, /* smallcptr */
617{ "medialabel", 0, 0, 0, 7, 0, "" }, /* smallcptr */
618{ "mediaobjectco",0, 0, 0, 9, 0, "" }, /* objectinfo */
619{ "mediaobject",0, 0, 0, 9, 0, "" }, /* objectinfo */
620{ "member", 0, 0, 0, 2, 0, "" }, /* para */
621{ "menuchoice", 0, 0, 0, 9, 0, "" }, /* shortcut */
622{ "methodname", 0, 0, 0, 7, 0, "" }, /* smallcptr */
623{ "methodparam",0, 0, 0, 9, 0, "" }, /* modifier */
624{ "methodsynopsis",0, 0, 0, 9, 0, "" }, /* modifier */
625{ "modespec", 0, 0, 0, 4, 0, "" }, /* docinfo */
626{ "modifier", 0, 0, 0, 7, 0, "" }, /* smallcptr */
627{ "mousebutton",0, 0, 0, 7, 0, "" }, /* smallcptr */
628{ "msgaud", 0, 0, 0, 2, 0, "" }, /* para */
629{ "msgentry", 0, 0, 0, 9, 0, "" }, /* msg */
630{ "msgexplan", 0, 0, 0, 9, 0, "" }, /* title */
631{ "msginfo", 0, 0, 0, 9, 0, "" }, /* msglevel */
632{ "msglevel", 0, 0, 0, 7, 0, "" }, /* smallcptr */
633{ "msgmain", 0, 0, 0, 9, 0, "" }, /* title */
634{ "msgorig", 0, 0, 0, 7, 0, "" }, /* smallcptr */
635{ "msgrel", 0, 0, 0, 9, 0, "" }, /* title */
636{ "msgset", 0, 0, 0, 9, 0, "" }, /* formalobject.title.content */
637{ "msgsub", 0, 0, 0, 9, 0, "" }, /* title */
638{ "msgtext", 0, 0, 0, 9, 0, "" }, /* component.mix */
639{ "msg", 0, 0, 0, 9, 0, "" }, /* title */
640{ "note", 0, 0, 0, 9, 0, "" }, /* title */
641{ "objectinfo", 0, 0, 0, 9, 0, "" }, /* graphic */
642{ "olink", 0, 0, 0, 2, 0, "" }, /* para */
643{ "ooclass", 0, 0, 0, 9, 0, "" }, /* modifier */
644{ "ooexception",0, 0, 0, 9, 0, "" }, /* modifier */
645{ "oointerface",0, 0, 0, 9, 0, "" }, /* modifier */
646{ "optional", 0, 0, 0, 9, 0, "" }, /* cptr */
647{ "option", 0, 0, 0, 7, 0, "" }, /* smallcptr */
648{ "orderedlist",0, 0, 0, 9, 0, "" }, /* formalobject.title.content */
649{ "orgdiv", 0, 0, 0, 4, 0, "" }, /* docinfo */
650{ "orgname", 0, 0, 0, 4, 0, "" }, /* docinfo */
651{ "otheraddr", 0, 0, 0, 4, 0, "" }, /* docinfo */
652{ "othercredit",0, 0, 0, 9, 0, "" }, /* person.ident.mix */
653{ "othername", 0, 0, 0, 4, 0, "" }, /* docinfo */
654{ "pagenums", 0, 0, 0, 4, 0, "" }, /* docinfo */
655{ "paramdef", 0, 0, 0, 1, 0, "" },
656{ "parameter", 0, 0, 0, 7, 0, "" }, /* smallcptr */
657{ "para", 0, 0, 0, 2, 0, "" }, /* para */
658{ "partinfo", 0, 0, 0, 9, 0, "" }, /* graphic */
659{ "partintro", 0, 0, 0, 9, 0, "" }, /* div.title.content */
660{ "part", 0, 0, 0, 9, 0, "" }, /* partinfo */
661{ "phone", 0, 0, 0, 4, 0, "" }, /* docinfo */
662{ "phrase", 0, 0, 0, 2, 0, "" }, /* para */
663{ "pob", 0, 0, 0, 4, 0, "" }, /* docinfo */
664{ "postcode", 0, 0, 0, 4, 0, "" }, /* docinfo */
665{ "prefaceinfo",0, 0, 0, 9, 0, "" }, /* graphic */
666{ "preface", 0, 0, 0, 9, 0, "" }, /* prefaceinfo */
667{ "primaryie", 0, 0, 0, 4, 0, "" }, /* ndxterm */
Daniel Veillardc057c5d2001-05-02 12:41:24 +0000[diff] [blame]668{ "primary", 0, 0, 0, 9, 0, "" }, /* ndxterm */
Daniel Veillardeae522a2001-04-23 13:41:34 +0000[diff] [blame]669{ "printhistory",0, 0, 0, 9, 0, "" }, /* para.class */
670{ "procedure", 0, 0, 0, 9, 0, "" }, /* formalobject.title.content */
671{ "productname",0, 0, 0, 2, 0, "" }, /* para */
672{ "productnumber",0, 0, 0, 4, 0, "" }, /* docinfo */
673{ "programlistingco",0, 0, 0, 9, 0, "" }, /* areaspec */
674{ "programlisting",0, 0, 0, 2, 0, "" }, /* para */
675{ "prompt", 0, 0, 0, 7, 0, "" }, /* smallcptr */
676{ "property", 0, 0, 0, 7, 0, "" }, /* smallcptr */
677{ "pubdate", 0, 0, 0, 4, 0, "" }, /* docinfo */
678{ "publishername",0, 0, 0, 4, 0, "" }, /* docinfo */
679{ "publisher", 0, 0, 0, 9, 0, "" }, /* publishername */
680{ "pubsnumber", 0, 0, 0, 4, 0, "" }, /* docinfo */
681{ "qandadiv", 0, 0, 0, 9, 0, "" }, /* formalobject.title.content */
682{ "qandaentry", 0, 0, 0, 9, 0, "" }, /* revhistory */
683{ "qandaset", 0, 0, 0, 9, 0, "" }, /* formalobject.title.content */
684{ "question", 0, 0, 0, 9, 0, "" }, /* label */
685{ "quote", 0, 0, 0, 2, 0, "" }, /* para */
686{ "refclass", 0, 0, 0, 9, 0, "" }, /* refclass.char.mix */
687{ "refdescriptor",0, 0, 0, 9, 0, "" }, /* refname.char.mix */
688{ "refentryinfo",0, 0, 0, 9, 0, "" }, /* graphic */
689{ "refentry", 0, 0, 0, 9, 0, "" }, /* ndxterm.class */
690{ "refentrytitle",0, 0, 0, 2, 0, "" }, /* para */
691{ "referenceinfo",0, 0, 0, 9, 0, "" }, /* graphic */
692{ "reference", 0, 0, 0, 9, 0, "" }, /* referenceinfo */
693{ "refmeta", 0, 0, 0, 9, 0, "" }, /* ndxterm.class */
694{ "refmiscinfo",0, 0, 0, 4, 0, "" }, /* docinfo */
695{ "refnamediv", 0, 0, 0, 9, 0, "" }, /* refdescriptor */
696{ "refname", 0, 0, 0, 9, 0, "" }, /* refname.char.mix */
697{ "refpurpose", 0, 0, 0, 9, 0, "" }, /* refinline.char.mix */
698{ "refsect1info",0, 0, 0, 9, 0, "" }, /* graphic */
699{ "refsect1", 0, 0, 0, 9, 0, "" }, /* refsect */
700{ "refsect2info",0, 0, 0, 9, 0, "" }, /* graphic */
701{ "refsect2", 0, 0, 0, 9, 0, "" }, /* refsect */
702{ "refsect3info",0, 0, 0, 9, 0, "" }, /* graphic */
703{ "refsect3", 0, 0, 0, 9, 0, "" }, /* refsect */
704{ "refsynopsisdivinfo",0,0, 0, 9, 0, "" }, /* graphic */
705{ "refsynopsisdiv",0, 0, 0, 9, 0, "" }, /* refsynopsisdivinfo */
706{ "releaseinfo",0, 0, 0, 4, 0, "" }, /* docinfo */
707{ "remark", 0, 0, 0, 2, 0, "" }, /* para */
708{ "replaceable",0, 0, 0, 1, 0, "" },
709{ "returnvalue",0, 0, 0, 7, 0, "" }, /* smallcptr */
710{ "revdescription",0, 0, 0, 9, 0, "" }, /* revdescription.mix */
711{ "revhistory", 0, 0, 0, 9, 0, "" }, /* revision */
712{ "revision", 0, 0, 0, 9, 0, "" }, /* revnumber */
713{ "revnumber", 0, 0, 0, 4, 0, "" }, /* docinfo */
714{ "revremark", 0, 0, 0, 4, 0, "" }, /* docinfo */
715{ "row", 0, 0, 0, 9, 0, "" }, /* tbl.row.mdl */
716{ "row", 0, 0, 0, 9, 0, "" }, /* tbl.row.mdl */
717{ "sbr", 0, 2, 1, 0, 0, "" },
718{ "screenco", 0, 0, 0, 9, 0, "" }, /* areaspec */
719{ "screeninfo", 0, 0, 0, 2, 0, "" }, /* para */
720{ "screen", 0, 0, 0, 2, 0, "" }, /* para */
721{ "screenshot", 0, 0, 0, 9, 0, "" }, /* screeninfo */
722{ "secondaryie",0, 0, 0, 4, 0, "" }, /* ndxterm */
723{ "secondary", 0, 0, 0, 4, 0, "" }, /* ndxterm */
724{ "sect1info", 0, 0, 0, 9, 0, "" }, /* graphic */
725{ "sect1", 0, 0, 0, 9, 0, "" }, /* sect */
726{ "sect2info", 0, 0, 0, 9, 0, "" }, /* graphic */
727{ "sect2", 0, 0, 0, 9, 0, "" }, /* sect */
728{ "sect3info", 0, 0, 0, 9, 0, "" }, /* graphic */
729{ "sect3", 0, 0, 0, 9, 0, "" }, /* sect */
730{ "sect4info", 0, 0, 0, 9, 0, "" }, /* graphic */
731{ "sect4", 0, 0, 0, 9, 0, "" }, /* sect */
732{ "sect5info", 0, 0, 0, 9, 0, "" }, /* graphic */
733{ "sect5", 0, 0, 0, 9, 0, "" }, /* sect */
734{ "sectioninfo",0, 0, 0, 9, 0, "" }, /* graphic */
735{ "section", 0, 0, 0, 9, 0, "" }, /* sectioninfo */
736{ "seealsoie", 0, 0, 0, 4, 0, "" }, /* ndxterm */
737{ "seealso", 0, 0, 0, 4, 0, "" }, /* ndxterm */
738{ "seeie", 0, 0, 0, 4, 0, "" }, /* ndxterm */
739{ "see", 0, 0, 0, 4, 0, "" }, /* ndxterm */
740{ "seglistitem",0, 0, 0, 9, 0, "" }, /* seg */
741{ "segmentedlist",0, 0, 0, 9, 0, "" }, /* formalobject.title.content */
742{ "seg", 0, 0, 0, 2, 0, "" }, /* para */
743{ "segtitle", 0, 0, 0, 8, 0, "" }, /* title */
744{ "seriesvolnums", 0, 0, 0, 4, 0, "" }, /* docinfo */
745{ "set", 0, 0, 0, 9, 0, "" }, /* div.title.content */
746{ "setindexinfo",0, 0, 0, 9, 0, "" }, /* graphic */
747{ "setindex", 0, 0, 0, 9, 0, "" }, /* setindexinfo */
748{ "setinfo", 0, 0, 0, 9, 0, "" }, /* graphic */
749{ "sgmltag", 0, 0, 0, 7, 0, "" }, /* smallcptr */
750{ "shortaffil", 0, 0, 0, 4, 0, "" }, /* docinfo */
751{ "shortcut", 0, 0, 0, 9, 0, "" }, /* keycap */
752{ "sidebarinfo",0, 0, 0, 9, 0, "" }, /* graphic */
753{ "sidebar", 0, 0, 0, 9, 0, "" }, /* sidebarinfo */
754{ "simpara", 0, 0, 0, 2, 0, "" }, /* para */
755{ "simplelist", 0, 0, 0, 9, 0, "" }, /* member */
756{ "simplemsgentry", 0, 0, 0, 9, 0, "" }, /* msgtext */
757{ "simplesect", 0, 0, 0, 9, 0, "" }, /* sect.title.content */
758{ "spanspec", 0, 2, 1, 0, 0, "" },
759{ "state", 0, 0, 0, 4, 0, "" }, /* docinfo */
760{ "step", 0, 0, 0, 9, 0, "" }, /* title */
761{ "street", 0, 0, 0, 4, 0, "" }, /* docinfo */
762{ "structfield",0, 0, 0, 7, 0, "" }, /* smallcptr */
763{ "structname", 0, 0, 0, 7, 0, "" }, /* smallcptr */
764{ "subjectset", 0, 0, 0, 9, 0, "" }, /* subject */
765{ "subject", 0, 0, 0, 9, 0, "" }, /* subjectterm */
766{ "subjectterm",0, 0, 0, 1, 0, "" },
767{ "subscript", 0, 0, 0, 1, 0, "" },
768{ "substeps", 0, 0, 0, 9, 0, "" }, /* step */
769{ "subtitle", 0, 0, 0, 8, 0, "" }, /* title */
770{ "superscript", 0, 0, 0, 1, 0, "" },
771{ "surname", 0, 0, 0, 4, 0, "" }, /* docinfo */
772{ "symbol", 0, 0, 0, 7, 0, "" }, /* smallcptr */
773{ "synopfragment", 0, 0, 0, 9, 0, "" }, /* arg */
774{ "synopfragmentref", 0, 0, 0, 1, 0, "" },
775{ "synopsis", 0, 0, 0, 2, 0, "" }, /* para */
776{ "systemitem", 0, 0, 0, 7, 0, "" }, /* smallcptr */
777{ "table", 0, 0, 0, 9, 0, "" }, /* tbl.table.mdl */
778/* { "%tbl.table.name;", 0, 0, 0, 9, 0, "" },*/ /* tbl.table.mdl */
779{ "tbody", 0, 0, 0, 9, 0, "" }, /* row */
780{ "tbody", 0, 0, 0, 9, 0, "" }, /* row */
781{ "term", 0, 0, 0, 2, 0, "" }, /* para */
782{ "tertiaryie", 0, 0, 0, 4, 0, "" }, /* ndxterm */
783{ "tertiary ", 0, 0, 0, 4, 0, "" }, /* ndxterm */
784{ "textobject", 0, 0, 0, 9, 0, "" }, /* objectinfo */
785{ "tfoot", 0, 0, 0, 9, 0, "" }, /* tbl.hdft.mdl */
786{ "tgroup", 0, 0, 0, 9, 0, "" }, /* tbl.tgroup.mdl */
787{ "tgroup", 0, 0, 0, 9, 0, "" }, /* tbl.tgroup.mdl */
788{ "thead", 0, 0, 0, 9, 0, "" }, /* row */
789{ "thead", 0, 0, 0, 9, 0, "" }, /* tbl.hdft.mdl */
790{ "tip", 0, 0, 0, 9, 0, "" }, /* title */
791{ "titleabbrev",0, 0, 0, 8, 0, "" }, /* title */
792{ "title", 0, 0, 0, 8, 0, "" }, /* title */
793{ "tocback", 0, 0, 0, 2, 0, "" }, /* para */
794{ "toc", 0, 0, 0, 9, 0, "" }, /* bookcomponent.title.content */
795{ "tocchap", 0, 0, 0, 9, 0, "" }, /* tocentry */
796{ "tocentry", 0, 0, 0, 2, 0, "" }, /* para */
797{ "tocfront", 0, 0, 0, 2, 0, "" }, /* para */
798{ "toclevel1", 0, 0, 0, 9, 0, "" }, /* tocentry */
799{ "toclevel2", 0, 0, 0, 9, 0, "" }, /* tocentry */
800{ "toclevel3", 0, 0, 0, 9, 0, "" }, /* tocentry */
801{ "toclevel4", 0, 0, 0, 9, 0, "" }, /* tocentry */
802{ "toclevel5", 0, 0, 0, 9, 0, "" }, /* tocentry */
803{ "tocpart", 0, 0, 0, 9, 0, "" }, /* tocentry */
804{ "token", 0, 0, 0, 7, 0, "" }, /* smallcptr */
805{ "trademark", 0, 0, 0, 1, 0, "" },
806{ "type", 0, 0, 0, 7, 0, "" }, /* smallcptr */
807{ "ulink", 0, 0, 0, 2, 0, "" }, /* para */
808{ "userinput", 0, 0, 0, 9, 0, "" }, /* cptr */
809{ "varargs", 0, 2, 1, 0, 0, "" },
810{ "variablelist",0, 0, 0, 9, 0, "" }, /* formalobject.title.content */
811{ "varlistentry",0, 0, 0, 9, 0, "" }, /* term */
812{ "varname", 0, 0, 0, 7, 0, "" }, /* smallcptr */
813{ "videodata", 0, 2, 1, 0, 0, "" },
814{ "videoobject",0, 0, 0, 9, 0, "" }, /* objectinfo */
815{ "void", 0, 2, 1, 0, 0, "" },
816{ "volumenum", 0, 0, 0, 4, 0, "" }, /* docinfo */
817{ "warning", 0, 0, 0, 9, 0, "" }, /* title */
818{ "wordasword", 0, 0, 0, 3, 0, "" }, /* word */
819{ "xref", 0, 2, 1, 0, 0, "" },
820{ "year", 0, 0, 0, 4, 0, "" }, /* docinfo */
821};
822
823#if 0
824/*
825 * start tags that imply the end of a current element
826 * any tag of each line implies the end of the current element if the type of
827 * that element is in the same line
828 */
829static const char *docbEquEnd[] = {
830"dt", "dd", "li", "option", NULL,
831"h1", "h2", "h3", "h4", "h5", "h6", NULL,
832"ol", "menu", "dir", "address", "pre", "listing", "xmp", NULL,
833NULL
834};
835#endif
836
837/*
Daniel Veillardcbaf3992001-12-31 16:16:02 +0000[diff] [blame^]838 * according the SGML DTD, HR should be added to the 2nd line above, as it
Daniel Veillardeae522a2001-04-23 13:41:34 +0000[diff] [blame]839 * is not allowed within a H1, H2, H3, etc. But we should tolerate that case
840 * because many documents contain rules in headings...
841 */
842
843/*
844 * start tags that imply the end of current element
845 */
846static const char *docbStartClose[] = {
847NULL
848};
849
850/*
851 * The list of SGML elements which are supposed not to have
852 * CDATA content and where a p element will be implied
853 *
Daniel Veillardcbaf3992001-12-31 16:16:02 +0000[diff] [blame^]854 * TODO: extend that list by reading the SGML SGML DTD on
Daniel Veillardeae522a2001-04-23 13:41:34 +0000[diff] [blame]855 * implied paragraph
856 */
857static char *docbNoContentElements[] = {
858 NULL
859};
860
861
862static const char** docbStartCloseIndex[100];
863static int docbStartCloseIndexinitialized = 0;
864
865/************************************************************************
866 * *
867 * functions to handle SGML specific data *
868 * *
869 ************************************************************************/
870
871/**
872 * docbInitAutoClose:
873 *
874 * Initialize the docbStartCloseIndex for fast lookup of closing tags names.
875 *
876 */
877static void
878docbInitAutoClose(void) {
879 int indx, i = 0;
880
881 if (docbStartCloseIndexinitialized) return;
882
883 for (indx = 0;indx < 100;indx ++) docbStartCloseIndex[indx] = NULL;
884 indx = 0;
885 while ((docbStartClose[i] != NULL) && (indx < 100 - 1)) {
886 docbStartCloseIndex[indx++] = &docbStartClose[i];
887 while (docbStartClose[i] != NULL) i++;
888 i++;
889 }
890}
891
892/**
893 * docbTagLookup:
894 * @tag: The tag name
895 *
896 * Lookup the SGML tag in the ElementTable
897 *
898 * Returns the related docbElemDescPtr or NULL if not found.
899 */
900static docbElemDescPtr
901docbTagLookup(const xmlChar *tag) {
902 unsigned int i;
903
904 for (i = 0; i < (sizeof(docbookElementTable) /
905 sizeof(docbookElementTable[0]));i++) {
906 if (xmlStrEqual(tag, BAD_CAST docbookElementTable[i].name))
907 return(&docbookElementTable[i]);
908 }
909 return(NULL);
910}
911
912/**
913 * docbCheckAutoClose:
914 * @newtag: The new tag name
915 * @oldtag: The old tag name
916 *
Daniel Veillardcbaf3992001-12-31 16:16:02 +0000[diff] [blame^]917 * Checks whether the new tag is one of the registered valid tags for
918 * closing old.
Daniel Veillardeae522a2001-04-23 13:41:34 +0000[diff] [blame]919 * Initialize the docbStartCloseIndex for fast lookup of closing tags names.
920 *
921 * Returns 0 if no, 1 if yes.
922 */
923static int
924docbCheckAutoClose(const xmlChar *newtag, const xmlChar *oldtag) {
925 int i, indx;
926 const char **closed = NULL;
927
928 if (docbStartCloseIndexinitialized == 0) docbInitAutoClose();
929
930 /* inefficient, but not a big deal */
931 for (indx = 0; indx < 100;indx++) {
932 closed = docbStartCloseIndex[indx];
933 if (closed == NULL) return(0);
934 if (xmlStrEqual(BAD_CAST *closed, newtag)) break;
935 }
936
937 i = closed - docbStartClose;
938 i++;
939 while (docbStartClose[i] != NULL) {
940 if (xmlStrEqual(BAD_CAST docbStartClose[i], oldtag)) {
941 return(1);
942 }
943 i++;
944 }
945 return(0);
946}
947
948/**
949 * docbAutoCloseOnClose:
950 * @ctxt: an SGML parser context
951 * @newtag: The new tag name
952 *
Daniel Veillardcbaf3992001-12-31 16:16:02 +0000[diff] [blame^]953 * The DocBook DTD allows an ending tag to implicitly close other tags.
Daniel Veillardeae522a2001-04-23 13:41:34 +0000[diff] [blame]954 */
955static void
956docbAutoCloseOnClose(docbParserCtxtPtr ctxt, const xmlChar *newtag) {
957 docbElemDescPtr info;
958 xmlChar *oldname;
959 int i;
960
961 if ((newtag[0] == '/') && (newtag[1] == 0))
962 return;
963
964#ifdef DEBUG
965 xmlGenericError(xmlGenericErrorContext,"Close of %s stack: %d elements\n", newtag, ctxt->nameNr);
966 for (i = 0;i < ctxt->nameNr;i++)
967 xmlGenericError(xmlGenericErrorContext,"%d : %s\n", i, ctxt->nameTab[i]);
968#endif
969
970 for (i = (ctxt->nameNr - 1);i >= 0;i--) {
971 if (xmlStrEqual(newtag, ctxt->nameTab[i])) break;
972 }
973 if (i < 0) return;
974
975 while (!xmlStrEqual(newtag, ctxt->name)) {
976 info = docbTagLookup(ctxt->name);
977 if ((info == NULL) || (info->endTag == 1)) {
978#ifdef DEBUG
979 xmlGenericError(xmlGenericErrorContext,"docbAutoCloseOnClose: %s closes %s\n", newtag, ctxt->name);
980#endif
981 } else {
982 if ((ctxt->sax != NULL) && (ctxt->sax->error != NULL))
983 ctxt->sax->error(ctxt->userData,
984 "Opening and ending tag mismatch: %s and %s\n",
985 newtag, ctxt->name);
986 ctxt->wellFormed = 0;
987 }
988 if ((ctxt->sax != NULL) && (ctxt->sax->endElement != NULL))
989 ctxt->sax->endElement(ctxt->userData, ctxt->name);
990 oldname = docbnamePop(ctxt);
991 if (oldname != NULL) {
992#ifdef DEBUG
993 xmlGenericError(xmlGenericErrorContext,"docbAutoCloseOnClose: popped %s\n", oldname);
994#endif
995 xmlFree(oldname);
996 }
997 }
998}
999
1000/**
1001 * docbAutoClose:
1002 * @ctxt: an SGML parser context
1003 * @newtag: The new tag name or NULL
1004 *
Daniel Veillardcbaf3992001-12-31 16:16:02 +0000[diff] [blame^]1005 * The DocBook DTD allows a tag to implicitly close other tags.
Daniel Veillardeae522a2001-04-23 13:41:34 +0000[diff] [blame]1006 * The list is kept in docbStartClose array. This function is
1007 * called when a new tag has been detected and generates the
1008 * appropriates closes if possible/needed.
1009 * If newtag is NULL this mean we are at the end of the resource
1010 * and we should check
1011 */
1012static void
1013docbAutoClose(docbParserCtxtPtr ctxt, const xmlChar *newtag) {
1014 xmlChar *oldname;
1015 while ((newtag != NULL) && (ctxt->name != NULL) &&
1016 (docbCheckAutoClose(newtag, ctxt->name))) {
1017#ifdef DEBUG
1018 xmlGenericError(xmlGenericErrorContext,"docbAutoClose: %s closes %s\n", newtag, ctxt->name);
1019#endif
1020 if ((ctxt->sax != NULL) && (ctxt->sax->endElement != NULL))
1021 ctxt->sax->endElement(ctxt->userData, ctxt->name);
1022 oldname = docbnamePop(ctxt);
1023 if (oldname != NULL) {
1024#ifdef DEBUG
1025 xmlGenericError(xmlGenericErrorContext,"docbAutoClose: popped %s\n", oldname);
1026#endif
1027 xmlFree(oldname);
1028 }
1029 }
1030}
1031
1032/**
1033 * docbAutoCloseTag:
1034 * @doc: the SGML document
1035 * @name: The tag name
1036 * @elem: the SGML element
1037 *
Daniel Veillardcbaf3992001-12-31 16:16:02 +0000[diff] [blame^]1038 * The DocBook DTD allows a tag to implicitly close other tags.
Daniel Veillardeae522a2001-04-23 13:41:34 +0000[diff] [blame]1039 * The list is kept in docbStartClose array. This function checks
1040 * if the element or one of it's children would autoclose the
1041 * given tag.
1042 *
1043 * Returns 1 if autoclose, 0 otherwise
1044 */
1045static int
1046docbAutoCloseTag(docbDocPtr doc, const xmlChar *name, docbNodePtr elem) {
1047 docbNodePtr child;
1048
1049 if (elem == NULL) return(1);
1050 if (xmlStrEqual(name, elem->name)) return(0);
1051 if (docbCheckAutoClose(elem->name, name)) return(1);
1052 child = elem->children;
1053 while (child != NULL) {
1054 if (docbAutoCloseTag(doc, name, child)) return(1);
1055 child = child->next;
1056 }
1057 return(0);
1058}
1059
1060#if 0
1061/**
1062 * docbIsAutoClosed:
1063 * @doc: the SGML document
1064 * @elem: the SGML element
1065 *
1066 * The list is kept in docbStartClose array. This function checks
1067 * if a tag is autoclosed by one of it's child
1068 *
1069 * Returns 1 if autoclosed, 0 otherwise
1070 */
1071static int
1072docbIsAutoClosed(docbDocPtr doc, docbNodePtr elem) {
1073 docbNodePtr child;
1074
1075 if (elem == NULL) return(1);
1076 child = elem->children;
1077 while (child != NULL) {
1078 if (docbAutoCloseTag(doc, elem->name, child)) return(1);
1079 child = child->next;
1080 }
1081 return(0);
1082}
1083#endif
1084
1085/**
1086 * docbCheckParagraph
1087 * @ctxt: an SGML parser context
1088 *
1089 * Check whether a p element need to be implied before inserting
1090 * characters in the current element.
1091 *
1092 * Returns 1 if a paragraph has been inserted, 0 if not and -1
1093 * in case of error.
1094 */
1095
1096static int
1097docbCheckParagraph(docbParserCtxtPtr ctxt) {
1098 const xmlChar *tag;
1099 int i;
1100
1101 if (ctxt == NULL)
1102 return(-1);
1103 tag = ctxt->name;
1104 if (tag == NULL) {
1105 docbAutoClose(ctxt, BAD_CAST"p");
1106 docbnamePush(ctxt, xmlStrdup(BAD_CAST"p"));
1107 if ((ctxt->sax != NULL) && (ctxt->sax->startElement != NULL))
1108 ctxt->sax->startElement(ctxt->userData, BAD_CAST"p", NULL);
1109 return(1);
1110 }
1111 for (i = 0; docbNoContentElements[i] != NULL; i++) {
1112 if (xmlStrEqual(tag, BAD_CAST docbNoContentElements[i])) {
1113#ifdef DEBUG
1114 xmlGenericError(xmlGenericErrorContext,"Implied element paragraph\n");
1115#endif
1116 docbAutoClose(ctxt, BAD_CAST"p");
1117 docbnamePush(ctxt, xmlStrdup(BAD_CAST"p"));
1118 if ((ctxt->sax != NULL) && (ctxt->sax->startElement != NULL))
1119 ctxt->sax->startElement(ctxt->userData, BAD_CAST"p", NULL);
1120 return(1);
1121 }
1122 }
1123 return(0);
1124}
1125
1126/************************************************************************
1127 * *
1128 * The list of SGML predefined entities *
1129 * *
1130 ************************************************************************/
1131
1132
1133static docbEntityDesc
1134docbookEntitiesTable[] = {
1135/*
1136 * the 4 absolute ones, plus apostrophe.
1137 */
1138{ 0x0026, "amp", "AMPERSAND" },
1139{ 0x003C, "lt", "LESS-THAN SIGN" },
1140
1141/*
1142 * Converted with VI macros from docbook ent files
1143 */
1144{ 0x0021, "excl", "EXCLAMATION MARK" },
1145{ 0x0022, "quot", "QUOTATION MARK" },
1146{ 0x0023, "num", "NUMBER SIGN" },
1147{ 0x0024, "dollar", "DOLLAR SIGN" },
1148{ 0x0025, "percnt", "PERCENT SIGN" },
1149{ 0x0027, "apos", "APOSTROPHE" },
1150{ 0x0028, "lpar", "LEFT PARENTHESIS" },
1151{ 0x0029, "rpar", "RIGHT PARENTHESIS" },
1152{ 0x002A, "ast", "ASTERISK OPERATOR" },
1153{ 0x002B, "plus", "PLUS SIGN" },
1154{ 0x002C, "comma", "COMMA" },
1155{ 0x002D, "hyphen", "HYPHEN-MINUS" },
1156{ 0x002E, "period", "FULL STOP" },
1157{ 0x002F, "sol", "SOLIDUS" },
1158{ 0x003A, "colon", "COLON" },
1159{ 0x003B, "semi", "SEMICOLON" },
1160{ 0x003D, "equals", "EQUALS SIGN" },
1161{ 0x003E, "gt", "GREATER-THAN SIGN" },
1162{ 0x003F, "quest", "QUESTION MARK" },
1163{ 0x0040, "commat", "COMMERCIAL AT" },
1164{ 0x005B, "lsqb", "LEFT SQUARE BRACKET" },
1165{ 0x005C, "bsol", "REVERSE SOLIDUS" },
1166{ 0x005D, "rsqb", "RIGHT SQUARE BRACKET" },
1167{ 0x005E, "circ", "RING OPERATOR" },
1168{ 0x005F, "lowbar", "LOW LINE" },
1169{ 0x0060, "grave", "GRAVE ACCENT" },
1170{ 0x007B, "lcub", "LEFT CURLY BRACKET" },
1171{ 0x007C, "verbar", "VERTICAL LINE" },
1172{ 0x007D, "rcub", "RIGHT CURLY BRACKET" },
1173{ 0x00A0, "nbsp", "NO-BREAK SPACE" },
1174{ 0x00A1, "iexcl", "INVERTED EXCLAMATION MARK" },
1175{ 0x00A2, "cent", "CENT SIGN" },
1176{ 0x00A3, "pound", "POUND SIGN" },
1177{ 0x00A4, "curren", "CURRENCY SIGN" },
1178{ 0x00A5, "yen", "YEN SIGN" },
1179{ 0x00A6, "brvbar", "BROKEN BAR" },
1180{ 0x00A7, "sect", "SECTION SIGN" },
1181{ 0x00A8, "die", "" },
1182{ 0x00A8, "Dot", "" },
1183{ 0x00A8, "uml", "" },
1184{ 0x00A9, "copy", "COPYRIGHT SIGN" },
1185{ 0x00AA, "ordf", "FEMININE ORDINAL INDICATOR" },
1186{ 0x00AB, "laquo", "LEFT-POINTING DOUBLE ANGLE QUOTATION MARK" },
1187{ 0x00AC, "not", "NOT SIGN" },
1188{ 0x00AD, "shy", "SOFT HYPHEN" },
1189{ 0x00AE, "reg", "REG TRADE MARK SIGN" },
1190{ 0x00AF, "macr", "MACRON" },
1191{ 0x00B0, "deg", "DEGREE SIGN" },
1192{ 0x00B1, "plusmn", "PLUS-MINUS SIGN" },
1193{ 0x00B2, "sup2", "SUPERSCRIPT TWO" },
1194{ 0x00B3, "sup3", "SUPERSCRIPT THREE" },
1195{ 0x00B4, "acute", "ACUTE ACCENT" },
1196{ 0x00B5, "micro", "MICRO SIGN" },
1197{ 0x00B6, "para", "PILCROW SIGN" },
1198{ 0x00B7, "middot", "MIDDLE DOT" },
1199{ 0x00B8, "cedil", "CEDILLA" },
1200{ 0x00B9, "sup1", "SUPERSCRIPT ONE" },
1201{ 0x00BA, "ordm", "MASCULINE ORDINAL INDICATOR" },
1202{ 0x00BB, "raquo", "RIGHT-POINTING DOUBLE ANGLE QUOTATION MARK" },
1203{ 0x00BC, "frac14", "VULGAR FRACTION ONE QUARTER" },
1204{ 0x00BD, "frac12", "VULGAR FRACTION ONE HALF" },
1205{ 0x00BD, "half", "VULGAR FRACTION ONE HALF" },
1206{ 0x00BE, "frac34", "VULGAR FRACTION THREE QUARTERS" },
1207{ 0x00BF, "iquest", "INVERTED QUESTION MARK" },
1208{ 0x00C0, "Agrave", "LATIN CAPITAL LETTER A WITH GRAVE" },
1209{ 0x00C1, "Aacute", "LATIN CAPITAL LETTER A WITH ACUTE" },
1210{ 0x00C2, "Acirc", "LATIN CAPITAL LETTER A WITH CIRCUMFLEX" },
1211{ 0x00C3, "Atilde", "LATIN CAPITAL LETTER A WITH TILDE" },
1212{ 0x00C4, "Auml", "LATIN CAPITAL LETTER A WITH DIAERESIS" },
1213{ 0x00C5, "Aring", "LATIN CAPITAL LETTER A WITH RING ABOVE" },
1214{ 0x00C6, "AElig", "LATIN CAPITAL LETTER AE" },
1215{ 0x00C7, "Ccedil", "LATIN CAPITAL LETTER C WITH CEDILLA" },
1216{ 0x00C8, "Egrave", "LATIN CAPITAL LETTER E WITH GRAVE" },
1217{ 0x00C9, "Eacute", "LATIN CAPITAL LETTER E WITH ACUTE" },
1218{ 0x00CA, "Ecirc", "LATIN CAPITAL LETTER E WITH CIRCUMFLEX" },
1219{ 0x00CB, "Euml", "LATIN CAPITAL LETTER E WITH DIAERESIS" },
1220{ 0x00CC, "Igrave", "LATIN CAPITAL LETTER I WITH GRAVE" },
1221{ 0x00CD, "Iacute", "LATIN CAPITAL LETTER I WITH ACUTE" },
1222{ 0x00CE, "Icirc", "LATIN CAPITAL LETTER I WITH CIRCUMFLEX" },
1223{ 0x00CF, "Iuml", "LATIN CAPITAL LETTER I WITH DIAERESIS" },
1224{ 0x00D0, "ETH", "LATIN CAPITAL LETTER ETH" },
1225{ 0x00D1, "Ntilde", "LATIN CAPITAL LETTER N WITH TILDE" },
1226{ 0x00D2, "Ograve", "LATIN CAPITAL LETTER O WITH GRAVE" },
1227{ 0x00D3, "Oacute", "LATIN CAPITAL LETTER O WITH ACUTE" },
1228{ 0x00D4, "Ocirc", "LATIN CAPITAL LETTER O WITH CIRCUMFLEX" },
1229{ 0x00D5, "Otilde", "LATIN CAPITAL LETTER O WITH TILDE" },
1230{ 0x00D6, "Ouml", "LATIN CAPITAL LETTER O WITH DIAERESIS" },
1231{ 0x00D7, "times", "MULTIPLICATION SIGN" },
1232{ 0x00D8, "Oslash", "LATIN CAPITAL LETTER O WITH STROKE" },
1233{ 0x00D9, "Ugrave", "LATIN CAPITAL LETTER U WITH GRAVE" },
1234{ 0x00DA, "Uacute", "LATIN CAPITAL LETTER U WITH ACUTE" },
1235{ 0x00DB, "Ucirc", "LATIN CAPITAL LETTER U WITH CIRCUMFLEX" },
1236{ 0x00DC, "Uuml", "LATIN CAPITAL LETTER U WITH DIAERESIS" },
1237{ 0x00DD, "Yacute", "LATIN CAPITAL LETTER Y WITH ACUTE" },
1238{ 0x00DE, "THORN", "LATIN CAPITAL LETTER THORN" },
1239{ 0x00DF, "szlig", "LATIN SMALL LETTER SHARP S" },
1240{ 0x00E0, "agrave", "LATIN SMALL LETTER A WITH GRAVE" },
1241{ 0x00E1, "aacute", "LATIN SMALL LETTER A WITH ACUTE" },
1242{ 0x00E2, "acirc", "LATIN SMALL LETTER A WITH CIRCUMFLEX" },
1243{ 0x00E3, "atilde", "LATIN SMALL LETTER A WITH TILDE" },
1244{ 0x00E4, "auml", "LATIN SMALL LETTER A WITH DIAERESIS" },
1245{ 0x00E5, "aring", "LATIN SMALL LETTER A WITH RING ABOVE" },
1246{ 0x00E6, "aelig", "LATIN SMALL LETTER AE" },
1247{ 0x00E7, "ccedil", "LATIN SMALL LETTER C WITH CEDILLA" },
1248{ 0x00E8, "egrave", "LATIN SMALL LETTER E WITH GRAVE" },
1249{ 0x00E9, "eacute", "LATIN SMALL LETTER E WITH ACUTE" },
1250{ 0x00EA, "ecirc", "LATIN SMALL LETTER E WITH CIRCUMFLEX" },
1251{ 0x00EB, "euml", "LATIN SMALL LETTER E WITH DIAERESIS" },
1252{ 0x00EC, "igrave", "LATIN SMALL LETTER I WITH GRAVE" },
1253{ 0x00ED, "iacute", "LATIN SMALL LETTER I WITH ACUTE" },
1254{ 0x00EE, "icirc", "LATIN SMALL LETTER I WITH CIRCUMFLEX" },
1255{ 0x00EF, "iuml", "LATIN SMALL LETTER I WITH DIAERESIS" },
1256{ 0x00F0, "eth", "LATIN SMALL LETTER ETH" },
1257{ 0x00F1, "ntilde", "LATIN SMALL LETTER N WITH TILDE" },
1258{ 0x00F2, "ograve", "LATIN SMALL LETTER O WITH GRAVE" },
1259{ 0x00F3, "oacute", "LATIN SMALL LETTER O WITH ACUTE" },
1260{ 0x00F4, "ocirc", "LATIN SMALL LETTER O WITH CIRCUMFLEX" },
1261{ 0x00F5, "otilde", "LATIN SMALL LETTER O WITH TILDE" },
1262{ 0x00F6, "ouml", "LATIN SMALL LETTER O WITH DIAERESIS" },
1263{ 0x00F7, "divide", "DIVISION SIGN" },
1264{ 0x00F8, "oslash", "CIRCLED DIVISION SLASH" },
1265{ 0x00F9, "ugrave", "LATIN SMALL LETTER U WITH GRAVE" },
1266{ 0x00FA, "uacute", "LATIN SMALL LETTER U WITH ACUTE" },
1267{ 0x00FB, "ucirc", "LATIN SMALL LETTER U WITH CIRCUMFLEX" },
1268{ 0x00FC, "uuml", "LATIN SMALL LETTER U WITH DIAERESIS" },
1269{ 0x00FD, "yacute", "LATIN SMALL LETTER Y WITH ACUTE" },
1270{ 0x00FE, "thorn", "LATIN SMALL LETTER THORN" },
1271{ 0x00FF, "yuml", "LATIN SMALL LETTER Y WITH DIAERESIS" },
1272{ 0x0100, "Amacr", "LATIN CAPITAL LETTER A WITH MACRON" },
1273{ 0x0101, "amacr", "LATIN SMALL LETTER A WITH MACRON" },
1274{ 0x0102, "Abreve", "LATIN CAPITAL LETTER A WITH BREVE" },
1275{ 0x0103, "abreve", "LATIN SMALL LETTER A WITH BREVE" },
1276{ 0x0104, "Aogon", "LATIN CAPITAL LETTER A WITH OGONEK" },
1277{ 0x0105, "aogon", "LATIN SMALL LETTER A WITH OGONEK" },
1278{ 0x0106, "Cacute", "LATIN CAPITAL LETTER C WITH ACUTE" },
1279{ 0x0107, "cacute", "LATIN SMALL LETTER C WITH ACUTE" },
1280{ 0x0108, "Ccirc", "LATIN CAPITAL LETTER C WITH CIRCUMFLEX" },
1281{ 0x0109, "ccirc", "LATIN SMALL LETTER C WITH CIRCUMFLEX" },
1282{ 0x010A, "Cdot", "LATIN CAPITAL LETTER C WITH DOT ABOVE" },
1283{ 0x010B, "cdot", "DOT OPERATOR" },
1284{ 0x010C, "Ccaron", "LATIN CAPITAL LETTER C WITH CARON" },
1285{ 0x010D, "ccaron", "LATIN SMALL LETTER C WITH CARON" },
1286{ 0x010E, "Dcaron", "LATIN CAPITAL LETTER D WITH CARON" },
1287{ 0x010F, "dcaron", "LATIN SMALL LETTER D WITH CARON" },
1288{ 0x0110, "Dstrok", "LATIN CAPITAL LETTER D WITH STROKE" },
1289{ 0x0111, "dstrok", "LATIN SMALL LETTER D WITH STROKE" },
1290{ 0x0112, "Emacr", "LATIN CAPITAL LETTER E WITH MACRON" },
1291{ 0x0113, "emacr", "LATIN SMALL LETTER E WITH MACRON" },
1292{ 0x0116, "Edot", "LATIN CAPITAL LETTER E WITH DOT ABOVE" },
1293{ 0x0117, "edot", "LATIN SMALL LETTER E WITH DOT ABOVE" },
1294{ 0x0118, "Eogon", "LATIN CAPITAL LETTER E WITH OGONEK" },
1295{ 0x0119, "eogon", "LATIN SMALL LETTER E WITH OGONEK" },
1296{ 0x011A, "Ecaron", "LATIN CAPITAL LETTER E WITH CARON" },
1297{ 0x011B, "ecaron", "LATIN SMALL LETTER E WITH CARON" },
1298{ 0x011C, "Gcirc", "LATIN CAPITAL LETTER G WITH CIRCUMFLEX" },
1299{ 0x011D, "gcirc", "LATIN SMALL LETTER G WITH CIRCUMFLEX" },
1300{ 0x011E, "Gbreve", "LATIN CAPITAL LETTER G WITH BREVE" },
1301{ 0x011F, "gbreve", "LATIN SMALL LETTER G WITH BREVE" },
1302{ 0x0120, "Gdot", "LATIN CAPITAL LETTER G WITH DOT ABOVE" },
1303{ 0x0121, "gdot", "LATIN SMALL LETTER G WITH DOT ABOVE" },
1304{ 0x0122, "Gcedil", "LATIN CAPITAL LETTER G WITH CEDILLA" },
1305{ 0x0124, "Hcirc", "LATIN CAPITAL LETTER H WITH CIRCUMFLEX" },
1306{ 0x0125, "hcirc", "LATIN SMALL LETTER H WITH CIRCUMFLEX" },
1307{ 0x0126, "Hstrok", "LATIN CAPITAL LETTER H WITH STROKE" },
1308{ 0x0127, "hstrok", "LATIN SMALL LETTER H WITH STROKE" },
1309{ 0x0128, "Itilde", "LATIN CAPITAL LETTER I WITH TILDE" },
1310{ 0x0129, "itilde", "LATIN SMALL LETTER I WITH TILDE" },
1311{ 0x012A, "Imacr", "LATIN CAPITAL LETTER I WITH MACRON" },
1312{ 0x012B, "imacr", "LATIN SMALL LETTER I WITH MACRON" },
1313{ 0x012E, "Iogon", "LATIN CAPITAL LETTER I WITH OGONEK" },
1314{ 0x012F, "iogon", "LATIN SMALL LETTER I WITH OGONEK" },
1315{ 0x0130, "Idot", "LATIN CAPITAL LETTER I WITH DOT ABOVE" },
1316{ 0x0131, "inodot", "LATIN SMALL LETTER DOTLESS I" },
1317{ 0x0131, "inodot", "LATIN SMALL LETTER DOTLESS I" },
1318{ 0x0132, "IJlig", "LATIN CAPITAL LIGATURE IJ" },
1319{ 0x0133, "ijlig", "LATIN SMALL LIGATURE IJ" },
1320{ 0x0134, "Jcirc", "LATIN CAPITAL LETTER J WITH CIRCUMFLEX" },
1321{ 0x0135, "jcirc", "LATIN SMALL LETTER J WITH CIRCUMFLEX" },
1322{ 0x0136, "Kcedil", "LATIN CAPITAL LETTER K WITH CEDILLA" },
1323{ 0x0137, "kcedil", "LATIN SMALL LETTER K WITH CEDILLA" },
1324{ 0x0138, "kgreen", "LATIN SMALL LETTER KRA" },
1325{ 0x0139, "Lacute", "LATIN CAPITAL LETTER L WITH ACUTE" },
1326{ 0x013A, "lacute", "LATIN SMALL LETTER L WITH ACUTE" },
1327{ 0x013B, "Lcedil", "LATIN CAPITAL LETTER L WITH CEDILLA" },
1328{ 0x013C, "lcedil", "LATIN SMALL LETTER L WITH CEDILLA" },
1329{ 0x013D, "Lcaron", "LATIN CAPITAL LETTER L WITH CARON" },
1330{ 0x013E, "lcaron", "LATIN SMALL LETTER L WITH CARON" },
1331{ 0x013F, "Lmidot", "LATIN CAPITAL LETTER L WITH MIDDLE DOT" },
1332{ 0x0140, "lmidot", "LATIN SMALL LETTER L WITH MIDDLE DOT" },
1333{ 0x0141, "Lstrok", "LATIN CAPITAL LETTER L WITH STROKE" },
1334{ 0x0142, "lstrok", "LATIN SMALL LETTER L WITH STROKE" },
1335{ 0x0143, "Nacute", "LATIN CAPITAL LETTER N WITH ACUTE" },
1336{ 0x0144, "nacute", "LATIN SMALL LETTER N WITH ACUTE" },
1337{ 0x0145, "Ncedil", "LATIN CAPITAL LETTER N WITH CEDILLA" },
1338{ 0x0146, "ncedil", "LATIN SMALL LETTER N WITH CEDILLA" },
1339{ 0x0147, "Ncaron", "LATIN CAPITAL LETTER N WITH CARON" },
1340{ 0x0148, "ncaron", "LATIN SMALL LETTER N WITH CARON" },
1341{ 0x0149, "napos", "LATIN SMALL LETTER N PRECEDED BY APOSTROPHE" },
1342{ 0x014A, "ENG", "LATIN CAPITAL LETTER ENG" },
1343{ 0x014B, "eng", "LATIN SMALL LETTER ENG" },
1344{ 0x014C, "Omacr", "LATIN CAPITAL LETTER O WITH MACRON" },
1345{ 0x014D, "omacr", "LATIN SMALL LETTER O WITH MACRON" },
1346{ 0x0150, "Odblac", "LATIN CAPITAL LETTER O WITH DOUBLE ACUTE" },
1347{ 0x0151, "odblac", "LATIN SMALL LETTER O WITH DOUBLE ACUTE" },
1348{ 0x0152, "OElig", "LATIN CAPITAL LIGATURE OE" },
1349{ 0x0153, "oelig", "LATIN SMALL LIGATURE OE" },
1350{ 0x0154, "Racute", "LATIN CAPITAL LETTER R WITH ACUTE" },
1351{ 0x0155, "racute", "LATIN SMALL LETTER R WITH ACUTE" },
1352{ 0x0156, "Rcedil", "LATIN CAPITAL LETTER R WITH CEDILLA" },
1353{ 0x0157, "rcedil", "LATIN SMALL LETTER R WITH CEDILLA" },
1354{ 0x0158, "Rcaron", "LATIN CAPITAL LETTER R WITH CARON" },
1355{ 0x0159, "rcaron", "LATIN SMALL LETTER R WITH CARON" },
1356{ 0x015A, "Sacute", "LATIN CAPITAL LETTER S WITH ACUTE" },
1357{ 0x015B, "sacute", "LATIN SMALL LETTER S WITH ACUTE" },
1358{ 0x015C, "Scirc", "LATIN CAPITAL LETTER S WITH CIRCUMFLEX" },
1359{ 0x015D, "scirc", "LATIN SMALL LETTER S WITH CIRCUMFLEX" },
1360{ 0x015E, "Scedil", "LATIN CAPITAL LETTER S WITH CEDILLA" },
1361{ 0x015F, "scedil", "LATIN SMALL LETTER S WITH CEDILLA" },
1362{ 0x0160, "Scaron", "LATIN CAPITAL LETTER S WITH CARON" },
1363{ 0x0161, "scaron", "LATIN SMALL LETTER S WITH CARON" },
1364{ 0x0162, "Tcedil", "LATIN CAPITAL LETTER T WITH CEDILLA" },
1365{ 0x0163, "tcedil", "LATIN SMALL LETTER T WITH CEDILLA" },
1366{ 0x0164, "Tcaron", "LATIN CAPITAL LETTER T WITH CARON" },
1367{ 0x0165, "tcaron", "LATIN SMALL LETTER T WITH CARON" },
1368{ 0x0166, "Tstrok", "LATIN CAPITAL LETTER T WITH STROKE" },
1369{ 0x0167, "tstrok", "LATIN SMALL LETTER T WITH STROKE" },
1370{ 0x0168, "Utilde", "LATIN CAPITAL LETTER U WITH TILDE" },
1371{ 0x0169, "utilde", "LATIN SMALL LETTER U WITH TILDE" },
1372{ 0x016A, "Umacr", "LATIN CAPITAL LETTER U WITH MACRON" },
1373{ 0x016B, "umacr", "LATIN SMALL LETTER U WITH MACRON" },
1374{ 0x016C, "Ubreve", "LATIN CAPITAL LETTER U WITH BREVE" },
1375{ 0x016D, "ubreve", "LATIN SMALL LETTER U WITH BREVE" },
1376{ 0x016E, "Uring", "LATIN CAPITAL LETTER U WITH RING ABOVE" },
1377{ 0x016F, "uring", "LATIN SMALL LETTER U WITH RING ABOVE" },
1378{ 0x0170, "Udblac", "LATIN CAPITAL LETTER U WITH DOUBLE ACUTE" },
1379{ 0x0171, "udblac", "LATIN SMALL LETTER U WITH DOUBLE ACUTE" },
1380{ 0x0172, "Uogon", "LATIN CAPITAL LETTER U WITH OGONEK" },
1381{ 0x0173, "uogon", "LATIN SMALL LETTER U WITH OGONEK" },
1382{ 0x0174, "Wcirc", "LATIN CAPITAL LETTER W WITH CIRCUMFLEX" },
1383{ 0x0175, "wcirc", "LATIN SMALL LETTER W WITH CIRCUMFLEX" },
1384{ 0x0176, "Ycirc", "LATIN CAPITAL LETTER Y WITH CIRCUMFLEX" },
1385{ 0x0177, "ycirc", "LATIN SMALL LETTER Y WITH CIRCUMFLEX" },
1386{ 0x0178, "Yuml", "LATIN CAPITAL LETTER Y WITH DIAERESIS" },
1387{ 0x0179, "Zacute", "LATIN CAPITAL LETTER Z WITH ACUTE" },
1388{ 0x017A, "zacute", "LATIN SMALL LETTER Z WITH ACUTE" },
1389{ 0x017B, "Zdot", "LATIN CAPITAL LETTER Z WITH DOT ABOVE" },
1390{ 0x017C, "zdot", "LATIN SMALL LETTER Z WITH DOT ABOVE" },
1391{ 0x017D, "Zcaron", "LATIN CAPITAL LETTER Z WITH CARON" },
1392{ 0x017E, "zcaron", "LATIN SMALL LETTER Z WITH CARON" },
1393{ 0x0192, "fnof", "LATIN SMALL LETTER F WITH HOOK" },
1394{ 0x01F5, "gacute", "LATIN SMALL LETTER G WITH ACUTE" },
1395{ 0x02C7, "caron", "CARON" },
1396{ 0x02D8, "breve", "BREVE" },
1397{ 0x02D9, "dot", "DOT ABOVE" },
1398{ 0x02DA, "ring", "RING ABOVE" },
1399{ 0x02DB, "ogon", "OGONEK" },
1400{ 0x02DC, "tilde", "TILDE" },
1401{ 0x02DD, "dblac", "DOUBLE ACUTE ACCENT" },
1402{ 0x0386, "Aacgr", "GREEK CAPITAL LETTER ALPHA WITH TONOS" },
1403{ 0x0388, "Eacgr", "GREEK CAPITAL LETTER EPSILON WITH TONOS" },
1404{ 0x0389, "EEacgr", "GREEK CAPITAL LETTER ETA WITH TONOS" },
1405{ 0x038A, "Iacgr", "GREEK CAPITAL LETTER IOTA WITH TONOS" },
1406{ 0x038C, "Oacgr", "GREEK CAPITAL LETTER OMICRON WITH TONOS" },
1407{ 0x038E, "Uacgr", "GREEK CAPITAL LETTER UPSILON WITH TONOS" },
1408{ 0x038F, "OHacgr", "GREEK CAPITAL LETTER OMEGA WITH TONOS" },
1409{ 0x0390, "idiagr", "GREEK SMALL LETTER IOTA WITH DIALYTIKA AND TONOS" },
1410{ 0x0391, "Agr", "GREEK CAPITAL LETTER ALPHA" },
1411{ 0x0392, "Bgr", "GREEK CAPITAL LETTER BETA" },
1412{ 0x0393, "b.Gamma", "GREEK CAPITAL LETTER GAMMA" },
1413{ 0x0393, "Gamma", "GREEK CAPITAL LETTER GAMMA" },
1414{ 0x0393, "Ggr", "GREEK CAPITAL LETTER GAMMA" },
1415{ 0x0394, "b.Delta", "GREEK CAPITAL LETTER DELTA" },
1416{ 0x0394, "Delta", "GREEK CAPITAL LETTER DELTA" },
1417{ 0x0394, "Dgr", "GREEK CAPITAL LETTER DELTA" },
1418{ 0x0395, "Egr", "GREEK CAPITAL LETTER EPSILON" },
1419{ 0x0396, "Zgr", "GREEK CAPITAL LETTER ZETA" },
1420{ 0x0397, "EEgr", "GREEK CAPITAL LETTER ETA" },
1421{ 0x0398, "b.Theta", "GREEK CAPITAL LETTER THETA" },
1422{ 0x0398, "Theta", "GREEK CAPITAL LETTER THETA" },
1423{ 0x0398, "THgr", "GREEK CAPITAL LETTER THETA" },
1424{ 0x0399, "Igr", "GREEK CAPITAL LETTER IOTA" },
1425{ 0x039A, "Kgr", "GREEK CAPITAL LETTER KAPPA" },
1426{ 0x039B, "b.Lambda", "GREEK CAPITAL LETTER LAMDA" },
1427{ 0x039B, "Lambda", "GREEK CAPITAL LETTER LAMDA" },
1428{ 0x039B, "Lgr", "GREEK CAPITAL LETTER LAMDA" },
1429{ 0x039C, "Mgr", "GREEK CAPITAL LETTER MU" },
1430{ 0x039D, "Ngr", "GREEK CAPITAL LETTER NU" },
1431{ 0x039E, "b.Xi", "GREEK CAPITAL LETTER XI" },
1432{ 0x039E, "Xgr", "GREEK CAPITAL LETTER XI" },
1433{ 0x039E, "Xi", "GREEK CAPITAL LETTER XI" },
1434{ 0x039F, "Ogr", "GREEK CAPITAL LETTER OMICRON" },
1435{ 0x03A0, "b.Pi", "GREEK CAPITAL LETTER PI" },
1436{ 0x03A0, "Pgr", "GREEK CAPITAL LETTER PI" },
1437{ 0x03A0, "Pi", "GREEK CAPITAL LETTER PI" },
1438{ 0x03A1, "Rgr", "GREEK CAPITAL LETTER RHO" },
1439{ 0x03A3, "b.Sigma", "GREEK CAPITAL LETTER SIGMA" },
1440{ 0x03A3, "Sgr", "GREEK CAPITAL LETTER SIGMA" },
1441{ 0x03A3, "Sigma", "GREEK CAPITAL LETTER SIGMA" },
1442{ 0x03A4, "Tgr", "GREEK CAPITAL LETTER TAU" },
1443{ 0x03A5, "Ugr", "" },
1444{ 0x03A6, "b.Phi", "GREEK CAPITAL LETTER PHI" },
1445{ 0x03A6, "PHgr", "GREEK CAPITAL LETTER PHI" },
1446{ 0x03A6, "Phi", "GREEK CAPITAL LETTER PHI" },
1447{ 0x03A7, "KHgr", "GREEK CAPITAL LETTER CHI" },
1448{ 0x03A8, "b.Psi", "GREEK CAPITAL LETTER PSI" },
1449{ 0x03A8, "PSgr", "GREEK CAPITAL LETTER PSI" },
1450{ 0x03A8, "Psi", "GREEK CAPITAL LETTER PSI" },
1451{ 0x03A9, "b.Omega", "GREEK CAPITAL LETTER OMEGA" },
1452{ 0x03A9, "OHgr", "GREEK CAPITAL LETTER OMEGA" },
1453{ 0x03A9, "Omega", "GREEK CAPITAL LETTER OMEGA" },
1454{ 0x03AA, "Idigr", "GREEK CAPITAL LETTER IOTA WITH DIALYTIKA" },
1455{ 0x03AB, "Udigr", "GREEK CAPITAL LETTER UPSILON WITH DIALYTIKA" },
1456{ 0x03AC, "aacgr", "GREEK SMALL LETTER ALPHA WITH TONOS" },
1457{ 0x03AD, "eacgr", "GREEK SMALL LETTER EPSILON WITH TONOS" },
1458{ 0x03AE, "eeacgr", "GREEK SMALL LETTER ETA WITH TONOS" },
1459{ 0x03AF, "iacgr", "GREEK SMALL LETTER IOTA WITH TONOS" },
1460{ 0x03B0, "udiagr", "GREEK SMALL LETTER UPSILON WITH DIALYTIKA AND TONOS" },
1461{ 0x03B1, "agr", "" },
1462{ 0x03B1, "alpha", "" },
1463{ 0x03B1, "b.alpha", "" },
1464{ 0x03B2, "b.beta", "GREEK SMALL LETTER BETA" },
1465{ 0x03B2, "beta", "GREEK SMALL LETTER BETA" },
1466{ 0x03B2, "bgr", "GREEK SMALL LETTER BETA" },
1467{ 0x03B3, "b.gamma", "GREEK SMALL LETTER GAMMA" },
1468{ 0x03B3, "gamma", "GREEK SMALL LETTER GAMMA" },
1469{ 0x03B3, "ggr", "GREEK SMALL LETTER GAMMA" },
1470{ 0x03B4, "b.delta", "GREEK SMALL LETTER DELTA" },
1471{ 0x03B4, "delta", "GREEK SMALL LETTER DELTA" },
1472{ 0x03B4, "dgr", "GREEK SMALL LETTER DELTA" },
1473{ 0x03B5, "b.epsi", "" },
1474{ 0x03B5, "b.epsis", "" },
1475{ 0x03B5, "b.epsiv", "" },
1476{ 0x03B5, "egr", "" },
1477{ 0x03B5, "epsiv", "" },
1478{ 0x03B6, "b.zeta", "GREEK SMALL LETTER ZETA" },
1479{ 0x03B6, "zeta", "GREEK SMALL LETTER ZETA" },
1480{ 0x03B6, "zgr", "GREEK SMALL LETTER ZETA" },
1481{ 0x03B7, "b.eta", "GREEK SMALL LETTER ETA" },
1482{ 0x03B7, "eegr", "GREEK SMALL LETTER ETA" },
1483{ 0x03B7, "eta", "GREEK SMALL LETTER ETA" },
1484{ 0x03B8, "b.thetas", "" },
1485{ 0x03B8, "thetas", "" },
1486{ 0x03B8, "thgr", "" },
1487{ 0x03B9, "b.iota", "GREEK SMALL LETTER IOTA" },
1488{ 0x03B9, "igr", "GREEK SMALL LETTER IOTA" },
1489{ 0x03B9, "iota", "GREEK SMALL LETTER IOTA" },
1490{ 0x03BA, "b.kappa", "GREEK SMALL LETTER KAPPA" },
1491{ 0x03BA, "kappa", "GREEK SMALL LETTER KAPPA" },
1492{ 0x03BA, "kgr", "GREEK SMALL LETTER KAPPA" },
1493{ 0x03BB, "b.lambda", "GREEK SMALL LETTER LAMDA" },
1494{ 0x03BB, "lambda", "GREEK SMALL LETTER LAMDA" },
1495{ 0x03BB, "lgr", "GREEK SMALL LETTER LAMDA" },
1496{ 0x03BC, "b.mu", "GREEK SMALL LETTER MU" },
1497{ 0x03BC, "mgr", "GREEK SMALL LETTER MU" },
1498{ 0x03BC, "mu", "GREEK SMALL LETTER MU" },
1499{ 0x03BD, "b.nu", "GREEK SMALL LETTER NU" },
1500{ 0x03BD, "ngr", "GREEK SMALL LETTER NU" },
1501{ 0x03BD, "nu", "GREEK SMALL LETTER NU" },
1502{ 0x03BE, "b.xi", "GREEK SMALL LETTER XI" },
1503{ 0x03BE, "xgr", "GREEK SMALL LETTER XI" },
1504{ 0x03BE, "xi", "GREEK SMALL LETTER XI" },
1505{ 0x03BF, "ogr", "GREEK SMALL LETTER OMICRON" },
1506{ 0x03C0, "b.pi", "GREEK SMALL LETTER PI" },
1507{ 0x03C0, "pgr", "GREEK SMALL LETTER PI" },
1508{ 0x03C0, "pi", "GREEK SMALL LETTER PI" },
1509{ 0x03C1, "b.rho", "GREEK SMALL LETTER RHO" },
1510{ 0x03C1, "rgr", "GREEK SMALL LETTER RHO" },
1511{ 0x03C1, "rho", "GREEK SMALL LETTER RHO" },
1512{ 0x03C2, "b.sigmav", "" },
1513{ 0x03C2, "sfgr", "" },
1514{ 0x03C2, "sigmav", "" },
1515{ 0x03C3, "b.sigma", "GREEK SMALL LETTER SIGMA" },
1516{ 0x03C3, "sgr", "GREEK SMALL LETTER SIGMA" },
1517{ 0x03C3, "sigma", "GREEK SMALL LETTER SIGMA" },
1518{ 0x03C4, "b.tau", "GREEK SMALL LETTER TAU" },
1519{ 0x03C4, "tau", "GREEK SMALL LETTER TAU" },
1520{ 0x03C4, "tgr", "GREEK SMALL LETTER TAU" },
1521{ 0x03C5, "b.upsi", "GREEK SMALL LETTER UPSILON" },
1522{ 0x03C5, "ugr", "GREEK SMALL LETTER UPSILON" },
1523{ 0x03C5, "upsi", "GREEK SMALL LETTER UPSILON" },
1524{ 0x03C6, "b.phis", "GREEK SMALL LETTER PHI" },
1525{ 0x03C6, "phgr", "GREEK SMALL LETTER PHI" },
1526{ 0x03C6, "phis", "GREEK SMALL LETTER PHI" },
1527{ 0x03C7, "b.chi", "GREEK SMALL LETTER CHI" },
1528{ 0x03C7, "chi", "GREEK SMALL LETTER CHI" },
1529{ 0x03C7, "khgr", "GREEK SMALL LETTER CHI" },
1530{ 0x03C8, "b.psi", "GREEK SMALL LETTER PSI" },
1531{ 0x03C8, "psgr", "GREEK SMALL LETTER PSI" },
1532{ 0x03C8, "psi", "GREEK SMALL LETTER PSI" },
1533{ 0x03C9, "b.omega", "GREEK SMALL LETTER OMEGA" },
1534{ 0x03C9, "ohgr", "GREEK SMALL LETTER OMEGA" },
1535{ 0x03C9, "omega", "GREEK SMALL LETTER OMEGA" },
1536{ 0x03CA, "idigr", "GREEK SMALL LETTER IOTA WITH DIALYTIKA" },
1537{ 0x03CB, "udigr", "GREEK SMALL LETTER UPSILON WITH DIALYTIKA" },
1538{ 0x03CC, "oacgr", "GREEK SMALL LETTER OMICRON WITH TONOS" },
1539{ 0x03CD, "uacgr", "GREEK SMALL LETTER UPSILON WITH TONOS" },
1540{ 0x03CE, "ohacgr", "GREEK SMALL LETTER OMEGA WITH TONOS" },
1541{ 0x03D1, "b.thetav", "" },
1542{ 0x03D1, "thetav", "" },
1543{ 0x03D2, "b.Upsi", "" },
1544{ 0x03D2, "Upsi", "" },
1545{ 0x03D5, "b.phiv", "GREEK PHI SYMBOL" },
1546{ 0x03D5, "phiv", "GREEK PHI SYMBOL" },
1547{ 0x03D6, "b.piv", "GREEK PI SYMBOL" },
1548{ 0x03D6, "piv", "GREEK PI SYMBOL" },
1549{ 0x03DC, "b.gammad", "GREEK LETTER DIGAMMA" },
1550{ 0x03DC, "gammad", "GREEK LETTER DIGAMMA" },
1551{ 0x03F0, "b.kappav", "GREEK KAPPA SYMBOL" },
1552{ 0x03F0, "kappav", "GREEK KAPPA SYMBOL" },
1553{ 0x03F1, "b.rhov", "GREEK RHO SYMBOL" },
1554{ 0x03F1, "rhov", "GREEK RHO SYMBOL" },
1555{ 0x0401, "IOcy", "CYRILLIC CAPITAL LETTER IO" },
1556{ 0x0402, "DJcy", "CYRILLIC CAPITAL LETTER DJE" },
1557{ 0x0403, "GJcy", "CYRILLIC CAPITAL LETTER GJE" },
1558{ 0x0404, "Jukcy", "CYRILLIC CAPITAL LETTER UKRAINIAN IE" },
1559{ 0x0405, "DScy", "CYRILLIC CAPITAL LETTER DZE" },
1560{ 0x0406, "Iukcy", "CYRILLIC CAPITAL LETTER BYELORUSSIAN-UKRAINIAN I" },
1561{ 0x0407, "YIcy", "CYRILLIC CAPITAL LETTER YI" },
1562{ 0x0408, "Jsercy", "CYRILLIC CAPITAL LETTER JE" },
1563{ 0x0409, "LJcy", "CYRILLIC CAPITAL LETTER LJE" },
1564{ 0x040A, "NJcy", "CYRILLIC CAPITAL LETTER NJE" },
1565{ 0x040B, "TSHcy", "CYRILLIC CAPITAL LETTER TSHE" },
1566{ 0x040C, "KJcy", "CYRILLIC CAPITAL LETTER KJE" },
1567{ 0x040E, "Ubrcy", "CYRILLIC CAPITAL LETTER SHORT U" },
1568{ 0x040F, "DZcy", "CYRILLIC CAPITAL LETTER DZHE" },
1569{ 0x0410, "Acy", "CYRILLIC CAPITAL LETTER A" },
1570{ 0x0411, "Bcy", "CYRILLIC CAPITAL LETTER BE" },
1571{ 0x0412, "Vcy", "CYRILLIC CAPITAL LETTER VE" },
1572{ 0x0413, "Gcy", "CYRILLIC CAPITAL LETTER GHE" },
1573{ 0x0414, "Dcy", "CYRILLIC CAPITAL LETTER DE" },
1574{ 0x0415, "IEcy", "CYRILLIC CAPITAL LETTER IE" },
1575{ 0x0416, "ZHcy", "CYRILLIC CAPITAL LETTER ZHE" },
1576{ 0x0417, "Zcy", "CYRILLIC CAPITAL LETTER ZE" },
1577{ 0x0418, "Icy", "CYRILLIC CAPITAL LETTER I" },
1578{ 0x0419, "Jcy", "CYRILLIC CAPITAL LETTER SHORT I" },
1579{ 0x041A, "Kcy", "CYRILLIC CAPITAL LETTER KA" },
1580{ 0x041B, "Lcy", "CYRILLIC CAPITAL LETTER EL" },
1581{ 0x041C, "Mcy", "CYRILLIC CAPITAL LETTER EM" },
1582{ 0x041D, "Ncy", "CYRILLIC CAPITAL LETTER EN" },
1583{ 0x041E, "Ocy", "CYRILLIC CAPITAL LETTER O" },
1584{ 0x041F, "Pcy", "CYRILLIC CAPITAL LETTER PE" },
1585{ 0x0420, "Rcy", "CYRILLIC CAPITAL LETTER ER" },
1586{ 0x0421, "Scy", "CYRILLIC CAPITAL LETTER ES" },
1587{ 0x0422, "Tcy", "CYRILLIC CAPITAL LETTER TE" },
1588{ 0x0423, "Ucy", "CYRILLIC CAPITAL LETTER U" },
1589{ 0x0424, "Fcy", "CYRILLIC CAPITAL LETTER EF" },
1590{ 0x0425, "KHcy", "CYRILLIC CAPITAL LETTER HA" },
1591{ 0x0426, "TScy", "CYRILLIC CAPITAL LETTER TSE" },
1592{ 0x0427, "CHcy", "CYRILLIC CAPITAL LETTER CHE" },
1593{ 0x0428, "SHcy", "CYRILLIC CAPITAL LETTER SHA" },
1594{ 0x0429, "SHCHcy", "CYRILLIC CAPITAL LETTER SHCHA" },
1595{ 0x042A, "HARDcy", "CYRILLIC CAPITAL LETTER HARD SIGN" },
1596{ 0x042B, "Ycy", "CYRILLIC CAPITAL LETTER YERU" },
1597{ 0x042C, "SOFTcy", "CYRILLIC CAPITAL LETTER SOFT SIGN" },
1598{ 0x042D, "Ecy", "CYRILLIC CAPITAL LETTER E" },
1599{ 0x042E, "YUcy", "CYRILLIC CAPITAL LETTER YU" },
1600{ 0x042F, "YAcy", "CYRILLIC CAPITAL LETTER YA" },
1601{ 0x0430, "acy", "CYRILLIC SMALL LETTER A" },
1602{ 0x0431, "bcy", "CYRILLIC SMALL LETTER BE" },
1603{ 0x0432, "vcy", "CYRILLIC SMALL LETTER VE" },
1604{ 0x0433, "gcy", "CYRILLIC SMALL LETTER GHE" },
1605{ 0x0434, "dcy", "CYRILLIC SMALL LETTER DE" },
1606{ 0x0435, "iecy", "CYRILLIC SMALL LETTER IE" },
1607{ 0x0436, "zhcy", "CYRILLIC SMALL LETTER ZHE" },
1608{ 0x0437, "zcy", "CYRILLIC SMALL LETTER ZE" },
1609{ 0x0438, "icy", "CYRILLIC SMALL LETTER I" },
1610{ 0x0439, "jcy", "CYRILLIC SMALL LETTER SHORT I" },
1611{ 0x043A, "kcy", "CYRILLIC SMALL LETTER KA" },
1612{ 0x043B, "lcy", "CYRILLIC SMALL LETTER EL" },
1613{ 0x043C, "mcy", "CYRILLIC SMALL LETTER EM" },
1614{ 0x043D, "ncy", "CYRILLIC SMALL LETTER EN" },
1615{ 0x043E, "ocy", "CYRILLIC SMALL LETTER O" },
1616{ 0x043F, "pcy", "CYRILLIC SMALL LETTER PE" },
1617{ 0x0440, "rcy", "CYRILLIC SMALL LETTER ER" },
1618{ 0x0441, "scy", "CYRILLIC SMALL LETTER ES" },
1619{ 0x0442, "tcy", "CYRILLIC SMALL LETTER TE" },
1620{ 0x0443, "ucy", "CYRILLIC SMALL LETTER U" },
1621{ 0x0444, "fcy", "CYRILLIC SMALL LETTER EF" },
1622{ 0x0445, "khcy", "CYRILLIC SMALL LETTER HA" },
1623{ 0x0446, "tscy", "CYRILLIC SMALL LETTER TSE" },
1624{ 0x0447, "chcy", "CYRILLIC SMALL LETTER CHE" },
1625{ 0x0448, "shcy", "CYRILLIC SMALL LETTER SHA" },
1626{ 0x0449, "shchcy", "CYRILLIC SMALL LETTER SHCHA" },
1627{ 0x044A, "hardcy", "CYRILLIC SMALL LETTER HARD SIGN" },
1628{ 0x044B, "ycy", "CYRILLIC SMALL LETTER YERU" },
1629{ 0x044C, "softcy", "CYRILLIC SMALL LETTER SOFT SIGN" },
1630{ 0x044D, "ecy", "CYRILLIC SMALL LETTER E" },
1631{ 0x044E, "yucy", "CYRILLIC SMALL LETTER YU" },
1632{ 0x044F, "yacy", "CYRILLIC SMALL LETTER YA" },
1633{ 0x0451, "iocy", "CYRILLIC SMALL LETTER IO" },
1634{ 0x0452, "djcy", "CYRILLIC SMALL LETTER DJE" },
1635{ 0x0453, "gjcy", "CYRILLIC SMALL LETTER GJE" },
1636{ 0x0454, "jukcy", "CYRILLIC SMALL LETTER UKRAINIAN IE" },
1637{ 0x0455, "dscy", "CYRILLIC SMALL LETTER DZE" },
1638{ 0x0456, "iukcy", "CYRILLIC SMALL LETTER BYELORUSSIAN-UKRAINIAN I" },
1639{ 0x0457, "yicy", "CYRILLIC SMALL LETTER YI" },
1640{ 0x0458, "jsercy", "CYRILLIC SMALL LETTER JE" },
1641{ 0x0459, "ljcy", "CYRILLIC SMALL LETTER LJE" },
1642{ 0x045A, "njcy", "CYRILLIC SMALL LETTER NJE" },
1643{ 0x045B, "tshcy", "CYRILLIC SMALL LETTER TSHE" },
1644{ 0x045C, "kjcy", "CYRILLIC SMALL LETTER KJE" },
1645{ 0x045E, "ubrcy", "CYRILLIC SMALL LETTER SHORT U" },
1646{ 0x045F, "dzcy", "CYRILLIC SMALL LETTER DZHE" },
1647{ 0x2002, "ensp", "EN SPACE" },
1648{ 0x2003, "emsp", "EM SPACE" },
1649{ 0x2004, "emsp13", "THREE-PER-EM SPACE" },
1650{ 0x2005, "emsp14", "FOUR-PER-EM SPACE" },
1651{ 0x2007, "numsp", "FIGURE SPACE" },
1652{ 0x2008, "puncsp", "PUNCTUATION SPACE" },
1653{ 0x2009, "thinsp", "THIN SPACE" },
1654{ 0x200A, "hairsp", "HAIR SPACE" },
1655{ 0x2010, "dash", "HYPHEN" },
1656{ 0x2013, "ndash", "EN DASH" },
1657{ 0x2014, "mdash", "EM DASH" },
1658{ 0x2015, "horbar", "HORIZONTAL BAR" },
1659{ 0x2016, "Verbar", "DOUBLE VERTICAL LINE" },
1660{ 0x2018, "lsquo", "" },
1661{ 0x2018, "rsquor", "" },
1662{ 0x2019, "rsquo", "RIGHT SINGLE QUOTATION MARK" },
1663{ 0x201A, "lsquor", "SINGLE LOW-9 QUOTATION MARK" },
1664{ 0x201C, "ldquo", "" },
1665{ 0x201C, "rdquor", "" },
1666{ 0x201D, "rdquo", "RIGHT DOUBLE QUOTATION MARK" },
1667{ 0x201E, "ldquor", "DOUBLE LOW-9 QUOTATION MARK" },
1668{ 0x2020, "dagger", "DAGGER" },
1669{ 0x2021, "Dagger", "DOUBLE DAGGER" },
1670{ 0x2022, "bull", "BULLET" },
1671{ 0x2025, "nldr", "TWO DOT LEADER" },
1672{ 0x2026, "hellip", "HORIZONTAL ELLIPSIS" },
1673{ 0x2026, "mldr", "HORIZONTAL ELLIPSIS" },
1674{ 0x2030, "permil", "PER MILLE SIGN" },
1675{ 0x2032, "prime", "PRIME" },
1676{ 0x2032, "vprime", "PRIME" },
1677{ 0x2033, "Prime", "DOUBLE PRIME" },
1678{ 0x2034, "tprime", "TRIPLE PRIME" },
1679{ 0x2035, "bprime", "REVERSED PRIME" },
1680{ 0x2041, "caret", "CARET" },
1681{ 0x2043, "hybull", "HYPHEN BULLET" },
1682{ 0x20DB, "tdot", "COMBINING THREE DOTS ABOVE" },
1683{ 0x20DC, "DotDot", "COMBINING FOUR DOTS ABOVE" },
1684{ 0x2105, "incare", "CARE OF" },
1685{ 0x210B, "hamilt", "SCRIPT CAPITAL H" },
1686{ 0x210F, "planck", "PLANCK CONSTANT OVER TWO PI" },
1687{ 0x2111, "image", "BLACK-LETTER CAPITAL I" },
1688{ 0x2112, "lagran", "SCRIPT CAPITAL L" },
1689{ 0x2113, "ell", "SCRIPT SMALL L" },
1690{ 0x2116, "numero", "NUMERO SIGN" },
1691{ 0x2117, "copysr", "SOUND RECORDING COPYRIGHT" },
1692{ 0x2118, "weierp", "SCRIPT CAPITAL P" },
1693{ 0x211C, "real", "BLACK-LETTER CAPITAL R" },
1694{ 0x211E, "rx", "PRESCRIPTION TAKE" },
1695{ 0x2122, "trade", "TRADE MARK SIGN" },
1696{ 0x2126, "ohm", "OHM SIGN" },
1697{ 0x212B, "angst", "ANGSTROM SIGN" },
1698{ 0x212C, "bernou", "SCRIPT CAPITAL B" },
1699{ 0x2133, "phmmat", "SCRIPT CAPITAL M" },
1700{ 0x2134, "order", "SCRIPT SMALL O" },
1701{ 0x2135, "aleph", "ALEF SYMBOL" },
1702{ 0x2136, "beth", "BET SYMBOL" },
1703{ 0x2137, "gimel", "GIMEL SYMBOL" },
1704{ 0x2138, "daleth", "DALET SYMBOL" },
1705{ 0x2153, "frac13", "VULGAR FRACTION ONE THIRD" },
1706{ 0x2154, "frac23", "VULGAR FRACTION TWO THIRDS" },
1707{ 0x2155, "frac15", "VULGAR FRACTION ONE FIFTH" },
1708{ 0x2156, "frac25", "VULGAR FRACTION TWO FIFTHS" },
1709{ 0x2157, "frac35", "VULGAR FRACTION THREE FIFTHS" },
1710{ 0x2158, "frac45", "VULGAR FRACTION FOUR FIFTHS" },
1711{ 0x2159, "frac16", "VULGAR FRACTION ONE SIXTH" },
1712{ 0x215A, "frac56", "VULGAR FRACTION FIVE SIXTHS" },
1713{ 0x215B, "frac18", "" },
1714{ 0x215C, "frac38", "" },
1715{ 0x215D, "frac58", "" },
1716{ 0x215E, "frac78", "" },
1717{ 0x2190, "larr", "LEFTWARDS DOUBLE ARROW" },
1718{ 0x2191, "uarr", "UPWARDS ARROW" },
1719{ 0x2192, "rarr", "RIGHTWARDS DOUBLE ARROW" },
1720{ 0x2193, "darr", "DOWNWARDS ARROW" },
1721{ 0x2194, "harr", "LEFT RIGHT ARROW" },
1722{ 0x2194, "xhArr", "LEFT RIGHT ARROW" },
1723{ 0x2194, "xharr", "LEFT RIGHT ARROW" },
1724{ 0x2195, "varr", "UP DOWN ARROW" },
1725{ 0x2196, "nwarr", "NORTH WEST ARROW" },
1726{ 0x2197, "nearr", "NORTH EAST ARROW" },
1727{ 0x2198, "drarr", "SOUTH EAST ARROW" },
1728{ 0x2199, "dlarr", "SOUTH WEST ARROW" },
1729{ 0x219A, "nlarr", "LEFTWARDS ARROW WITH STROKE" },
1730{ 0x219B, "nrarr", "RIGHTWARDS ARROW WITH STROKE" },
1731{ 0x219D, "rarrw", "RIGHTWARDS SQUIGGLE ARROW" },
1732{ 0x219E, "Larr", "LEFTWARDS TWO HEADED ARROW" },
1733{ 0x21A0, "Rarr", "RIGHTWARDS TWO HEADED ARROW" },
1734{ 0x21A2, "larrtl", "LEFTWARDS ARROW WITH TAIL" },
1735{ 0x21A3, "rarrtl", "RIGHTWARDS ARROW WITH TAIL" },
1736{ 0x21A6, "map", "RIGHTWARDS ARROW FROM BAR" },
1737{ 0x21A9, "larrhk", "LEFTWARDS ARROW WITH HOOK" },
1738{ 0x21AA, "rarrhk", "RIGHTWARDS ARROW WITH HOOK" },
1739{ 0x21AB, "larrlp", "LEFTWARDS ARROW WITH LOOP" },
1740{ 0x21AC, "rarrlp", "RIGHTWARDS ARROW WITH LOOP" },
1741{ 0x21AD, "harrw", "LEFT RIGHT WAVE ARROW" },
1742{ 0x21AE, "nharr", "LEFT RIGHT ARROW WITH STROKE" },
1743{ 0x21B0, "lsh", "UPWARDS ARROW WITH TIP LEFTWARDS" },
1744{ 0x21B1, "rsh", "UPWARDS ARROW WITH TIP RIGHTWARDS" },
1745{ 0x21B6, "cularr", "ANTICLOCKWISE TOP SEMICIRCLE ARROW" },
1746{ 0x21B7, "curarr", "CLOCKWISE TOP SEMICIRCLE ARROW" },
1747{ 0x21BA, "olarr", "ANTICLOCKWISE OPEN CIRCLE ARROW" },
1748{ 0x21BB, "orarr", "CLOCKWISE OPEN CIRCLE ARROW" },
1749{ 0x21BC, "lharu", "LEFTWARDS HARPOON WITH BARB UPWARDS" },
1750{ 0x21BD, "lhard", "LEFTWARDS HARPOON WITH BARB DOWNWARDS" },
1751{ 0x21BE, "uharr", "UPWARDS HARPOON WITH BARB RIGHTWARDS" },
1752{ 0x21BF, "uharl", "UPWARDS HARPOON WITH BARB LEFTWARDS" },
1753{ 0x21C0, "rharu", "RIGHTWARDS HARPOON WITH BARB UPWARDS" },
1754{ 0x21C1, "rhard", "RIGHTWARDS HARPOON WITH BARB DOWNWARDS" },
1755{ 0x21C2, "dharr", "DOWNWARDS HARPOON WITH BARB RIGHTWARDS" },
1756{ 0x21C3, "dharl", "DOWNWARDS HARPOON WITH BARB LEFTWARDS" },
1757{ 0x21C4, "rlarr2", "RIGHTWARDS ARROW OVER LEFTWARDS ARROW" },
1758{ 0x21C6, "lrarr2", "LEFTWARDS ARROW OVER RIGHTWARDS ARROW" },
1759{ 0x21C7, "larr2", "LEFTWARDS PAIRED ARROWS" },
1760{ 0x21C8, "uarr2", "UPWARDS PAIRED ARROWS" },
1761{ 0x21C9, "rarr2", "RIGHTWARDS PAIRED ARROWS" },
1762{ 0x21CA, "darr2", "DOWNWARDS PAIRED ARROWS" },
1763{ 0x21CB, "lrhar2", "LEFTWARDS HARPOON OVER RIGHTWARDS HARPOON" },
1764{ 0x21CC, "rlhar2", "RIGHTWARDS HARPOON OVER LEFTWARDS HARPOON" },
1765{ 0x21CD, "nlArr", "LEFTWARDS DOUBLE ARROW WITH STROKE" },
1766{ 0x21CE, "nhArr", "LEFT RIGHT DOUBLE ARROW WITH STROKE" },
1767{ 0x21CF, "nrArr", "RIGHTWARDS DOUBLE ARROW WITH STROKE" },
1768{ 0x21D0, "lArr", "LEFTWARDS ARROW" },
1769{ 0x21D0, "xlArr", "LEFTWARDS DOUBLE ARROW" },
1770{ 0x21D1, "uArr", "UPWARDS DOUBLE ARROW" },
1771{ 0x21D2, "rArr", "RIGHTWARDS ARROW" },
1772{ 0x21D2, "xrArr", "RIGHTWARDS DOUBLE ARROW" },
1773{ 0x21D3, "dArr", "DOWNWARDS DOUBLE ARROW" },
1774{ 0x21D4, "hArr", "" },
1775{ 0x21D4, "iff", "LEFT RIGHT DOUBLE ARROW" },
1776{ 0x21D5, "vArr", "UP DOWN DOUBLE ARROW" },
1777{ 0x21DA, "lAarr", "LEFTWARDS TRIPLE ARROW" },
1778{ 0x21DB, "rAarr", "RIGHTWARDS TRIPLE ARROW" },
1779{ 0x2200, "forall", "" },
1780{ 0x2201, "comp", "COMPLEMENT" },
1781{ 0x2202, "part", "" },
1782{ 0x2203, "exist", "" },
1783{ 0x2204, "nexist", "THERE DOES NOT EXIST" },
1784{ 0x2205, "empty", "" },
1785{ 0x2207, "nabla", "NABLA" },
1786{ 0x2209, "notin", "" },
1787{ 0x220A, "epsi", "" },
1788{ 0x220A, "epsis", "" },
1789{ 0x220A, "isin", "" },
1790{ 0x220D, "bepsi", "SMALL CONTAINS AS MEMBER" },
1791{ 0x220D, "ni", "" },
1792{ 0x220F, "prod", "N-ARY PRODUCT" },
1793{ 0x2210, "amalg", "N-ARY COPRODUCT" },
1794{ 0x2210, "coprod", "N-ARY COPRODUCT" },
1795{ 0x2210, "samalg", "" },
1796{ 0x2211, "sum", "N-ARY SUMMATION" },
1797{ 0x2212, "minus", "MINUS SIGN" },
1798{ 0x2213, "mnplus", "" },
1799{ 0x2214, "plusdo", "DOT PLUS" },
1800{ 0x2216, "setmn", "SET MINUS" },
1801{ 0x2216, "ssetmn", "SET MINUS" },
1802{ 0x2217, "lowast", "ASTERISK OPERATOR" },
1803{ 0x2218, "compfn", "RING OPERATOR" },
1804{ 0x221A, "radic", "" },
1805{ 0x221D, "prop", "" },
1806{ 0x221D, "vprop", "" },
1807{ 0x221E, "infin", "" },
1808{ 0x221F, "ang90", "RIGHT ANGLE" },
1809{ 0x2220, "ang", "ANGLE" },
1810{ 0x2221, "angmsd", "MEASURED ANGLE" },
1811{ 0x2222, "angsph", "" },
1812{ 0x2223, "mid", "" },
1813{ 0x2224, "nmid", "DOES NOT DIVIDE" },
1814{ 0x2225, "par", "PARALLEL TO" },
1815{ 0x2225, "spar", "PARALLEL TO" },
1816{ 0x2226, "npar", "NOT PARALLEL TO" },
1817{ 0x2226, "nspar", "NOT PARALLEL TO" },
1818{ 0x2227, "and", "" },
1819{ 0x2228, "or", "" },
1820{ 0x2229, "cap", "" },
1821{ 0x222A, "cup", "" },
1822{ 0x222B, "int", "" },
1823{ 0x222E, "conint", "" },
1824{ 0x2234, "there4", "" },
1825{ 0x2235, "becaus", "BECAUSE" },
1826{ 0x223C, "sim", "" },
1827{ 0x223C, "thksim", "TILDE OPERATOR" },
1828{ 0x223D, "bsim", "" },
1829{ 0x2240, "wreath", "WREATH PRODUCT" },
1830{ 0x2241, "nsim", "" },
1831{ 0x2243, "sime", "" },
1832{ 0x2244, "nsime", "" },
1833{ 0x2245, "cong", "" },
1834{ 0x2247, "ncong", "NEITHER APPROXIMATELY NOR ACTUALLY EQUAL TO" },
1835{ 0x2248, "ap", "" },
1836{ 0x2248, "thkap", "ALMOST EQUAL TO" },
1837{ 0x2249, "nap", "NOT ALMOST EQUAL TO" },
1838{ 0x224A, "ape", "" },
1839{ 0x224C, "bcong", "ALL EQUAL TO" },
1840{ 0x224D, "asymp", "EQUIVALENT TO" },
1841{ 0x224E, "bump", "" },
1842{ 0x224F, "bumpe", "" },
1843{ 0x2250, "esdot", "" },
1844{ 0x2251, "eDot", "" },
1845{ 0x2252, "efDot", "" },
1846{ 0x2253, "erDot", "" },
1847{ 0x2254, "colone", "" },
1848{ 0x2255, "ecolon", "" },
1849{ 0x2256, "ecir", "" },
1850{ 0x2257, "cire", "" },
1851{ 0x2259, "wedgeq", "ESTIMATES" },
1852{ 0x225C, "trie", "" },
1853{ 0x2260, "ne", "" },
1854{ 0x2261, "equiv", "" },
1855{ 0x2262, "nequiv", "NOT IDENTICAL TO" },
1856{ 0x2264, "le", "" },
1857{ 0x2264, "les", "LESS-THAN OR EQUAL TO" },
1858{ 0x2265, "ge", "GREATER-THAN OR EQUAL TO" },
1859{ 0x2265, "ges", "GREATER-THAN OR EQUAL TO" },
1860{ 0x2266, "lE", "" },
1861{ 0x2267, "gE", "" },
1862{ 0x2268, "lnE", "" },
1863{ 0x2268, "lne", "" },
1864{ 0x2268, "lvnE", "LESS-THAN BUT NOT EQUAL TO" },
1865{ 0x2269, "gnE", "" },
1866{ 0x2269, "gne", "" },
1867{ 0x2269, "gvnE", "GREATER-THAN BUT NOT EQUAL TO" },
1868{ 0x226A, "Lt", "MUCH LESS-THAN" },
1869{ 0x226B, "Gt", "MUCH GREATER-THAN" },
1870{ 0x226C, "twixt", "BETWEEN" },
1871{ 0x226E, "nlt", "NOT LESS-THAN" },
1872{ 0x226F, "ngt", "NOT GREATER-THAN" },
1873{ 0x2270, "nlE", "" },
1874{ 0x2270, "nle", "NEITHER LESS-THAN NOR EQUAL TO" },
1875{ 0x2270, "nles", "" },
1876{ 0x2271, "ngE", "" },
1877{ 0x2271, "nge", "NEITHER GREATER-THAN NOR EQUAL TO" },
1878{ 0x2271, "nges", "" },
1879{ 0x2272, "lap", "LESS-THAN OR EQUIVALENT TO" },
1880{ 0x2272, "lsim", "LESS-THAN OR EQUIVALENT TO" },
1881{ 0x2273, "gap", "GREATER-THAN OR EQUIVALENT TO" },
1882{ 0x2273, "gsim", "GREATER-THAN OR EQUIVALENT TO" },
1883{ 0x2276, "lg", "LESS-THAN OR GREATER-THAN" },
1884{ 0x2277, "gl", "" },
1885{ 0x227A, "pr", "" },
1886{ 0x227B, "sc", "" },
1887{ 0x227C, "cupre", "" },
1888{ 0x227C, "pre", "" },
1889{ 0x227D, "sccue", "" },
1890{ 0x227D, "sce", "" },
1891{ 0x227E, "prap", "" },
1892{ 0x227E, "prsim", "" },
1893{ 0x227F, "scap", "" },
1894{ 0x227F, "scsim", "" },
1895{ 0x2280, "npr", "DOES NOT PRECEDE" },
1896{ 0x2281, "nsc", "DOES NOT SUCCEED" },
1897{ 0x2282, "sub", "" },
1898{ 0x2283, "sup", "" },
1899{ 0x2284, "nsub", "NOT A SUBSET OF" },
1900{ 0x2285, "nsup", "NOT A SUPERSET OF" },
1901{ 0x2286, "subE", "" },
1902{ 0x2286, "sube", "" },
1903{ 0x2287, "supE", "" },
1904{ 0x2287, "supe", "" },
1905{ 0x2288, "nsubE", "" },
1906{ 0x2288, "nsube", "" },
1907{ 0x2289, "nsupE", "" },
1908{ 0x2289, "nsupe", "" },
1909{ 0x228A, "subne", "" },
1910{ 0x228A, "subnE", "SUBSET OF WITH NOT EQUAL TO" },
1911{ 0x228A, "vsubne", "SUBSET OF WITH NOT EQUAL TO" },
1912{ 0x228B, "supnE", "" },
1913{ 0x228B, "supne", "" },
1914{ 0x228B, "vsupnE", "SUPERSET OF WITH NOT EQUAL TO" },
1915{ 0x228B, "vsupne", "SUPERSET OF WITH NOT EQUAL TO" },
1916{ 0x228E, "uplus", "MULTISET UNION" },
1917{ 0x228F, "sqsub", "" },
1918{ 0x2290, "sqsup", "" },
1919{ 0x2291, "sqsube", "" },
1920{ 0x2292, "sqsupe", "" },
1921{ 0x2293, "sqcap", "SQUARE CAP" },
1922{ 0x2294, "sqcup", "SQUARE CUP" },
1923{ 0x2295, "oplus", "CIRCLED PLUS" },
1924{ 0x2296, "ominus", "CIRCLED MINUS" },
1925{ 0x2297, "otimes", "CIRCLED TIMES" },
1926{ 0x2298, "osol", "CIRCLED DIVISION SLASH" },
1927{ 0x2299, "odot", "CIRCLED DOT OPERATOR" },
1928{ 0x229A, "ocir", "CIRCLED RING OPERATOR" },
1929{ 0x229B, "oast", "CIRCLED ASTERISK OPERATOR" },
1930{ 0x229D, "odash", "CIRCLED DASH" },
1931{ 0x229E, "plusb", "SQUARED PLUS" },
1932{ 0x229F, "minusb", "SQUARED MINUS" },
1933{ 0x22A0, "timesb", "SQUARED TIMES" },
1934{ 0x22A1, "sdotb", "SQUARED DOT OPERATOR" },
1935{ 0x22A2, "vdash", "" },
1936{ 0x22A3, "dashv", "" },
1937{ 0x22A4, "top", "DOWN TACK" },
1938{ 0x22A5, "bottom", "" },
1939{ 0x22A5, "perp", "" },
1940{ 0x22A7, "models", "MODELS" },
1941{ 0x22A8, "vDash", "" },
1942{ 0x22A9, "Vdash", "" },
1943{ 0x22AA, "Vvdash", "" },
1944{ 0x22AC, "nvdash", "DOES NOT PROVE" },
1945{ 0x22AD, "nvDash", "NOT TRUE" },
1946{ 0x22AE, "nVdash", "DOES NOT FORCE" },
1947{ 0x22AF, "nVDash", "NEGATED DOUBLE VERTICAL BAR DOUBLE RIGHT TURNSTILE" },
1948{ 0x22B2, "vltri", "" },
1949{ 0x22B3, "vrtri", "" },
1950{ 0x22B4, "ltrie", "" },
1951{ 0x22B5, "rtrie", "" },
1952{ 0x22B8, "mumap", "MULTIMAP" },
1953{ 0x22BA, "intcal", "INTERCALATE" },
1954{ 0x22BB, "veebar", "" },
1955{ 0x22BC, "barwed", "NAND" },
1956{ 0x22C4, "diam", "DIAMOND OPERATOR" },
1957{ 0x22C5, "sdot", "DOT OPERATOR" },
1958{ 0x22C6, "sstarf", "STAR OPERATOR" },
1959{ 0x22C6, "star", "STAR OPERATOR" },
1960{ 0x22C7, "divonx", "DIVISION TIMES" },
1961{ 0x22C8, "bowtie", "" },
1962{ 0x22C9, "ltimes", "LEFT NORMAL FACTOR SEMIDIRECT PRODUCT" },
1963{ 0x22CA, "rtimes", "RIGHT NORMAL FACTOR SEMIDIRECT PRODUCT" },
1964{ 0x22CB, "lthree", "LEFT SEMIDIRECT PRODUCT" },
1965{ 0x22CC, "rthree", "RIGHT SEMIDIRECT PRODUCT" },
1966{ 0x22CD, "bsime", "" },
1967{ 0x22CE, "cuvee", "CURLY LOGICAL OR" },
1968{ 0x22CF, "cuwed", "CURLY LOGICAL AND" },
1969{ 0x22D0, "Sub", "" },
1970{ 0x22D1, "Sup", "" },
1971{ 0x22D2, "Cap", "DOUBLE INTERSECTION" },
1972{ 0x22D3, "Cup", "DOUBLE UNION" },
1973{ 0x22D4, "fork", "" },
1974{ 0x22D6, "ldot", "" },
1975{ 0x22D7, "gsdot", "" },
1976{ 0x22D8, "Ll", "" },
1977{ 0x22D9, "Gg", "VERY MUCH GREATER-THAN" },
1978{ 0x22DA, "lEg", "" },
1979{ 0x22DA, "leg", "" },
1980{ 0x22DB, "gEl", "" },
1981{ 0x22DB, "gel", "" },
1982{ 0x22DC, "els", "" },
1983{ 0x22DD, "egs", "" },
1984{ 0x22DE, "cuepr", "" },
1985{ 0x22DF, "cuesc", "" },
1986{ 0x22E0, "npre", "DOES NOT PRECEDE OR EQUAL" },
1987{ 0x22E1, "nsce", "DOES NOT SUCCEED OR EQUAL" },
1988{ 0x22E6, "lnsim", "" },
1989{ 0x22E7, "gnsim", "GREATER-THAN BUT NOT EQUIVALENT TO" },
1990{ 0x22E8, "prnap", "" },
1991{ 0x22E8, "prnsim", "" },
1992{ 0x22E9, "scnap", "" },
1993{ 0x22E9, "scnsim", "" },
1994{ 0x22EA, "nltri", "NOT NORMAL SUBGROUP OF" },
1995{ 0x22EB, "nrtri", "DOES NOT CONTAIN AS NORMAL SUBGROUP" },
1996{ 0x22EC, "nltrie", "NOT NORMAL SUBGROUP OF OR EQUAL TO" },
1997{ 0x22ED, "nrtrie", "DOES NOT CONTAIN AS NORMAL SUBGROUP OR EQUAL" },
1998{ 0x22EE, "vellip", "" },
1999{ 0x2306, "Barwed", "PERSPECTIVE" },
2000{ 0x2308, "lceil", "LEFT CEILING" },
2001{ 0x2309, "rceil", "RIGHT CEILING" },
2002{ 0x230A, "lfloor", "LEFT FLOOR" },
2003{ 0x230B, "rfloor", "RIGHT FLOOR" },
2004{ 0x230C, "drcrop", "BOTTOM RIGHT CROP" },
2005{ 0x230D, "dlcrop", "BOTTOM LEFT CROP" },
2006{ 0x230E, "urcrop", "TOP RIGHT CROP" },
2007{ 0x230F, "ulcrop", "TOP LEFT CROP" },
2008{ 0x2315, "telrec", "TELEPHONE RECORDER" },
2009{ 0x2316, "target", "POSITION INDICATOR" },
2010{ 0x231C, "ulcorn", "TOP LEFT CORNER" },
2011{ 0x231D, "urcorn", "TOP RIGHT CORNER" },
2012{ 0x231E, "dlcorn", "BOTTOM LEFT CORNER" },
2013{ 0x231F, "drcorn", "BOTTOM RIGHT CORNER" },
2014{ 0x2322, "frown", "" },
2015{ 0x2322, "sfrown", "FROWN" },
2016{ 0x2323, "smile", "" },
2017{ 0x2323, "ssmile", "SMILE" },
2018{ 0x2423, "blank", "OPEN BOX" },
2019{ 0x24C8, "oS", "CIRCLED LATIN CAPITAL LETTER S" },
2020{ 0x2500, "boxh", "BOX DRAWINGS LIGHT HORIZONTAL" },
2021{ 0x2502, "boxv", "BOX DRAWINGS LIGHT VERTICAL" },
2022{ 0x250C, "boxdr", "BOX DRAWINGS LIGHT DOWN AND RIGHT" },
2023{ 0x2510, "boxdl", "BOX DRAWINGS LIGHT DOWN AND LEFT" },
2024{ 0x2514, "boxur", "BOX DRAWINGS LIGHT UP AND RIGHT" },
2025{ 0x2518, "boxul", "BOX DRAWINGS LIGHT UP AND LEFT" },
2026{ 0x251C, "boxvr", "BOX DRAWINGS LIGHT VERTICAL AND RIGHT" },
2027{ 0x2524, "boxvl", "BOX DRAWINGS LIGHT VERTICAL AND LEFT" },
2028{ 0x252C, "boxhd", "BOX DRAWINGS LIGHT DOWN AND HORIZONTAL" },
2029{ 0x2534, "boxhu", "BOX DRAWINGS LIGHT UP AND HORIZONTAL" },
2030{ 0x253C, "boxvh", "BOX DRAWINGS LIGHT VERTICAL AND HORIZONTAL" },
2031{ 0x2550, "boxH", "BOX DRAWINGS DOUBLE HORIZONTAL" },
2032{ 0x2551, "boxV", "BOX DRAWINGS DOUBLE VERTICAL" },
2033{ 0x2552, "boxDR", "BOX DRAWINGS DOWN SINGLE AND RIGHT DOUBLE" },
2034{ 0x2553, "boxDr", "BOX DRAWINGS DOWN DOUBLE AND RIGHT SINGLE" },
2035{ 0x2554, "boxdR", "BOX DRAWINGS DOUBLE DOWN AND RIGHT" },
2036{ 0x2555, "boxDL", "BOX DRAWINGS DOWN SINGLE AND LEFT DOUBLE" },
2037{ 0x2556, "boxdL", "BOX DRAWINGS DOWN DOUBLE AND LEFT SINGLE" },
2038{ 0x2557, "boxDl", "BOX DRAWINGS DOUBLE DOWN AND LEFT" },
2039{ 0x2558, "boxUR", "BOX DRAWINGS UP SINGLE AND RIGHT DOUBLE" },
2040{ 0x2559, "boxuR", "BOX DRAWINGS UP DOUBLE AND RIGHT SINGLE" },
2041{ 0x255A, "boxUr", "BOX DRAWINGS DOUBLE UP AND RIGHT" },
2042{ 0x255B, "boxUL", "BOX DRAWINGS UP SINGLE AND LEFT DOUBLE" },
2043{ 0x255C, "boxUl", "BOX DRAWINGS UP DOUBLE AND LEFT SINGLE" },
2044{ 0x255D, "boxuL", "BOX DRAWINGS DOUBLE UP AND LEFT" },
2045{ 0x255E, "boxvR", "BOX DRAWINGS VERTICAL SINGLE AND RIGHT DOUBLE" },
2046{ 0x255F, "boxVR", "BOX DRAWINGS VERTICAL DOUBLE AND RIGHT SINGLE" },
2047{ 0x2560, "boxVr", "BOX DRAWINGS DOUBLE VERTICAL AND RIGHT" },
2048{ 0x2561, "boxvL", "BOX DRAWINGS VERTICAL SINGLE AND LEFT DOUBLE" },
2049{ 0x2562, "boxVL", "BOX DRAWINGS VERTICAL DOUBLE AND LEFT SINGLE" },
2050{ 0x2563, "boxVl", "BOX DRAWINGS DOUBLE VERTICAL AND LEFT" },
2051{ 0x2564, "boxhD", "BOX DRAWINGS DOWN SINGLE AND HORIZONTAL DOUBLE" },
2052{ 0x2565, "boxHD", "BOX DRAWINGS DOWN DOUBLE AND HORIZONTAL SINGLE" },
2053{ 0x2566, "boxHd", "BOX DRAWINGS DOUBLE DOWN AND HORIZONTAL" },
2054{ 0x2567, "boxhU", "BOX DRAWINGS UP SINGLE AND HORIZONTAL DOUBLE" },
2055{ 0x2568, "boxHU", "BOX DRAWINGS UP DOUBLE AND HORIZONTAL SINGLE" },
2056{ 0x2569, "boxHu", "BOX DRAWINGS DOUBLE UP AND HORIZONTAL" },
2057{ 0x256A, "boxvH", "BOX DRAWINGS VERTICAL SINGLE AND HORIZONTAL DOUBLE" },
2058{ 0x256B, "boxVH", "BOX DRAWINGS VERTICAL DOUBLE AND HORIZONTAL SINGLE" },
2059{ 0x256C, "boxVh", "BOX DRAWINGS DOUBLE VERTICAL AND HORIZONTAL" },
2060{ 0x2580, "uhblk", "UPPER HALF BLOCK" },
2061{ 0x2584, "lhblk", "LOWER HALF BLOCK" },
2062{ 0x2588, "block", "FULL BLOCK" },
2063{ 0x2591, "blk14", "LIGHT SHADE" },
2064{ 0x2592, "blk12", "MEDIUM SHADE" },
2065{ 0x2593, "blk34", "DARK SHADE" },
2066{ 0x25A1, "square", "WHITE SQUARE" },
2067{ 0x25A1, "squ", "WHITE SQUARE" },
2068{ 0x25AA, "squf", "" },
2069{ 0x25AD, "rect", "WHITE RECTANGLE" },
2070{ 0x25AE, "marker", "BLACK VERTICAL RECTANGLE" },
2071{ 0x25B3, "xutri", "WHITE UP-POINTING TRIANGLE" },
2072{ 0x25B4, "utrif", "BLACK UP-POINTING TRIANGLE" },
2073{ 0x25B5, "utri", "WHITE UP-POINTING TRIANGLE" },
2074{ 0x25B8, "rtrif", "BLACK RIGHT-POINTING TRIANGLE" },
2075{ 0x25B9, "rtri", "WHITE RIGHT-POINTING TRIANGLE" },
2076{ 0x25BD, "xdtri", "WHITE DOWN-POINTING TRIANGLE" },
2077{ 0x25BE, "dtrif", "BLACK DOWN-POINTING TRIANGLE" },
2078{ 0x25BF, "dtri", "WHITE DOWN-POINTING TRIANGLE" },
2079{ 0x25C2, "ltrif", "BLACK LEFT-POINTING TRIANGLE" },
2080{ 0x25C3, "ltri", "WHITE LEFT-POINTING TRIANGLE" },
2081{ 0x25CA, "loz", "LOZENGE" },
2082{ 0x25CB, "cir", "WHITE CIRCLE" },
2083{ 0x25CB, "xcirc", "WHITE CIRCLE" },
2084{ 0x2605, "starf", "BLACK STAR" },
2085{ 0x260E, "phone", "TELEPHONE SIGN" },
2086{ 0x2640, "female", "" },
2087{ 0x2642, "male", "MALE SIGN" },
2088{ 0x2660, "spades", "BLACK SPADE SUIT" },
2089{ 0x2663, "clubs", "BLACK CLUB SUIT" },
2090{ 0x2665, "hearts", "BLACK HEART SUIT" },
2091{ 0x2666, "diams", "BLACK DIAMOND SUIT" },
2092{ 0x2669, "sung", "" },
2093{ 0x266D, "flat", "MUSIC FLAT SIGN" },
2094{ 0x266E, "natur", "MUSIC NATURAL SIGN" },
2095{ 0x266F, "sharp", "MUSIC SHARP SIGN" },
2096{ 0x2713, "check", "CHECK MARK" },
2097{ 0x2717, "cross", "BALLOT X" },
2098{ 0x2720, "malt", "MALTESE CROSS" },
2099{ 0x2726, "lozf", "" },
2100{ 0x2736, "sext", "SIX POINTED BLACK STAR" },
2101{ 0x3008, "lang", "" },
2102{ 0x3009, "rang", "" },
2103{ 0xE291, "rpargt", "" },
2104{ 0xE2A2, "lnap", "" },
2105{ 0xE2AA, "nsmid", "" },
2106{ 0xE2B3, "prnE", "" },
2107{ 0xE2B5, "scnE", "" },
2108{ 0xE2B8, "vsubnE", "" },
2109{ 0xE301, "smid", "" },
2110{ 0xE411, "gnap", "" },
2111{ 0xFB00, "fflig", "" },
2112{ 0xFB01, "filig", "" },
2113{ 0xFB02, "fllig", "" },
2114{ 0xFB03, "ffilig", "" },
2115{ 0xFB04, "ffllig", "" },
2116{ 0xFE68, "sbsol", "SMALL REVERSE SOLIDUS" },
2117};
2118
2119/************************************************************************
2120 * *
2121 * Commodity functions to handle entities *
2122 * *
2123 ************************************************************************/
2124
2125/*
2126 * Macro used to grow the current buffer.
2127 */
2128#define growBuffer(buffer) { \
2129 buffer##_size *= 2; \
2130 buffer = (xmlChar *) xmlRealloc(buffer, buffer##_size * sizeof(xmlChar)); \
2131 if (buffer == NULL) { \
2132 perror("realloc failed"); \
2133 return(NULL); \
2134 } \
2135}
2136
2137/**
2138 * docbEntityLookup:
2139 * @name: the entity name
2140 *
2141 * Lookup the given entity in EntitiesTable
2142 *
2143 * TODO: the linear scan is really ugly, an hash table is really needed.
2144 *
2145 * Returns the associated docbEntityDescPtr if found, NULL otherwise.
2146 */
2147static docbEntityDescPtr
2148docbEntityLookup(const xmlChar *name) {
2149 unsigned int i;
2150
2151 for (i = 0;i < (sizeof(docbookEntitiesTable)/
2152 sizeof(docbookEntitiesTable[0]));i++) {
2153 if (xmlStrEqual(name, BAD_CAST docbookEntitiesTable[i].name)) {
2154#ifdef DEBUG
2155 xmlGenericError(xmlGenericErrorContext,"Found entity %s\n", name);
2156#endif
2157 return(&docbookEntitiesTable[i]);
2158 }
2159 }
2160 return(NULL);
2161}
2162
2163/**
2164 * docbEntityValueLookup:
2165 * @value: the entity's unicode value
2166 *
2167 * Lookup the given entity in EntitiesTable
2168 *
2169 * TODO: the linear scan is really ugly, an hash table is really needed.
2170 *
2171 * Returns the associated docbEntityDescPtr if found, NULL otherwise.
2172 */
2173static docbEntityDescPtr
2174docbEntityValueLookup(int value) {
2175 unsigned int i;
2176#ifdef DEBUG
2177 int lv = 0;
2178#endif
2179
2180 for (i = 0;i < (sizeof(docbookEntitiesTable)/
2181 sizeof(docbookEntitiesTable[0]));i++) {
2182 if (docbookEntitiesTable[i].value >= value) {
2183 if (docbookEntitiesTable[i].value > value)
2184 break;
2185#ifdef DEBUG
2186 xmlGenericError(xmlGenericErrorContext,"Found entity %s\n", docbookEntitiesTable[i].name);
2187#endif
2188 return(&docbookEntitiesTable[i]);
2189 }
2190#ifdef DEBUG
2191 if (lv > docbookEntitiesTable[i].value) {
2192 xmlGenericError(xmlGenericErrorContext,
2193 "docbookEntitiesTable[] is not sorted (%d > %d)!\n",
2194 lv, docbookEntitiesTable[i].value);
2195 }
2196 lv = docbookEntitiesTable[i].value;
2197#endif
2198 }
2199 return(NULL);
2200}
2201
2202#if 0
2203/**
2204 * UTF8ToSgml:
2205 * @out: a pointer to an array of bytes to store the result
2206 * @outlen: the length of @out
2207 * @in: a pointer to an array of UTF-8 chars
2208 * @inlen: the length of @in
2209 *
2210 * Take a block of UTF-8 chars in and try to convert it to an ASCII
2211 * plus SGML entities block of chars out.
2212 *
2213 * Returns 0 if success, -2 if the transcoding fails, or -1 otherwise
2214 * The value of @inlen after return is the number of octets consumed
Daniel Veillardcbaf3992001-12-31 16:16:02 +0000[diff] [blame^]2215 * as the return value is positive, else unpredictable.
Daniel Veillardeae522a2001-04-23 13:41:34 +0000[diff] [blame]2216 * The value of @outlen after return is the number of octets consumed.
2217 */
2218int
2219UTF8ToSgml(unsigned char* out, int *outlen,
2220 const unsigned char* in, int *inlen) {
2221 const unsigned char* processed = in;
2222 const unsigned char* outend;
2223 const unsigned char* outstart = out;
2224 const unsigned char* instart = in;
2225 const unsigned char* inend;
2226 unsigned int c, d;
2227 int trailing;
2228
2229 if (in == NULL) {
2230 /*
2231 * initialization nothing to do
2232 */
2233 *outlen = 0;
2234 *inlen = 0;
2235 return(0);
2236 }
2237 inend = in + (*inlen);
2238 outend = out + (*outlen);
2239 while (in < inend) {
2240 d = *in++;
2241 if (d < 0x80) { c= d; trailing= 0; }
2242 else if (d < 0xC0) {
2243 /* trailing byte in leading position */
2244 *outlen = out - outstart;
2245 *inlen = processed - instart;
2246 return(-2);
2247 } else if (d < 0xE0) { c= d & 0x1F; trailing= 1; }
2248 else if (d < 0xF0) { c= d & 0x0F; trailing= 2; }
2249 else if (d < 0xF8) { c= d & 0x07; trailing= 3; }
2250 else {
2251 /* no chance for this in Ascii */
2252 *outlen = out - outstart;
2253 *inlen = processed - instart;
2254 return(-2);
2255 }
2256
2257 if (inend - in < trailing) {
2258 break;
2259 }
2260
2261 for ( ; trailing; trailing--) {
2262 if ((in >= inend) || (((d= *in++) & 0xC0) != 0x80))
2263 break;
2264 c <<= 6;
2265 c |= d & 0x3F;
2266 }
2267
2268 /* assertion: c is a single UTF-4 value */
2269 if (c < 0x80) {
2270 if (out + 1 >= outend)
2271 break;
2272 *out++ = c;
2273 } else {
2274 int len;
2275 docbEntityDescPtr ent;
2276
2277 /*
2278 * Try to lookup a predefined SGML entity for it
2279 */
2280
2281 ent = docbEntityValueLookup(c);
2282 if (ent == NULL) {
2283 /* no chance for this in Ascii */
2284 *outlen = out - outstart;
2285 *inlen = processed - instart;
2286 return(-2);
2287 }
2288 len = strlen(ent->name);
2289 if (out + 2 + len >= outend)
2290 break;
2291 *out++ = '&';
2292 memcpy(out, ent->name, len);
2293 out += len;
2294 *out++ = ';';
2295 }
2296 processed = in;
2297 }
2298 *outlen = out - outstart;
2299 *inlen = processed - instart;
2300 return(0);
2301}
2302#endif
2303
2304/**
2305 * docbEncodeEntities:
2306 * @out: a pointer to an array of bytes to store the result
2307 * @outlen: the length of @out
2308 * @in: a pointer to an array of UTF-8 chars
2309 * @inlen: the length of @in
2310 * @quoteChar: the quote character to escape (' or ") or zero.
2311 *
2312 * Take a block of UTF-8 chars in and try to convert it to an ASCII
2313 * plus SGML entities block of chars out.
2314 *
2315 * Returns 0 if success, -2 if the transcoding fails, or -1 otherwise
2316 * The value of @inlen after return is the number of octets consumed
Daniel Veillardcbaf3992001-12-31 16:16:02 +0000[diff] [blame^]2317 * as the return value is positive, else unpredictable.
Daniel Veillardeae522a2001-04-23 13:41:34 +0000[diff] [blame]2318 * The value of @outlen after return is the number of octets consumed.
2319 */
2320int
2321docbEncodeEntities(unsigned char* out, int *outlen,
2322 const unsigned char* in, int *inlen, int quoteChar) {
2323 const unsigned char* processed = in;
2324 const unsigned char* outend = out + (*outlen);
2325 const unsigned char* outstart = out;
2326 const unsigned char* instart = in;
2327 const unsigned char* inend = in + (*inlen);
2328 unsigned int c, d;
2329 int trailing;
2330
2331 while (in < inend) {
2332 d = *in++;
2333 if (d < 0x80) { c= d; trailing= 0; }
2334 else if (d < 0xC0) {
2335 /* trailing byte in leading position */
2336 *outlen = out - outstart;
2337 *inlen = processed - instart;
2338 return(-2);
2339 } else if (d < 0xE0) { c= d & 0x1F; trailing= 1; }
2340 else if (d < 0xF0) { c= d & 0x0F; trailing= 2; }
2341 else if (d < 0xF8) { c= d & 0x07; trailing= 3; }
2342 else {
2343 /* no chance for this in Ascii */
2344 *outlen = out - outstart;
2345 *inlen = processed - instart;
2346 return(-2);
2347 }
2348
2349 if (inend - in < trailing)
2350 break;
2351
2352 while (trailing--) {
2353 if (((d= *in++) & 0xC0) != 0x80) {
2354 *outlen = out - outstart;
2355 *inlen = processed - instart;
2356 return(-2);
2357 }
2358 c <<= 6;
2359 c |= d & 0x3F;
2360 }
2361
2362 /* assertion: c is a single UTF-4 value */
2363 if (c < 0x80 && c != (unsigned int) quoteChar && c != '&' && c != '<' && c != '>') {
2364 if (out >= outend)
2365 break;
2366 *out++ = c;
2367 } else {
2368 docbEntityDescPtr ent;
2369 const char *cp;
2370 char nbuf[16];
2371 int len;
2372
2373 /*
2374 * Try to lookup a predefined SGML entity for it
2375 */
2376 ent = docbEntityValueLookup(c);
2377 if (ent == NULL) {
2378 sprintf(nbuf, "#%u", c);
2379 cp = nbuf;
2380 }
2381 else
2382 cp = ent->name;
2383 len = strlen(cp);
2384 if (out + 2 + len > outend)
2385 break;
2386 *out++ = '&';
2387 memcpy(out, cp, len);
2388 out += len;
2389 *out++ = ';';
2390 }
2391 processed = in;
2392 }
2393 *outlen = out - outstart;
2394 *inlen = processed - instart;
2395 return(0);
2396}
2397
2398
2399/************************************************************************
2400 * *
2401 * Commodity functions to handle streams *
2402 * *
2403 ************************************************************************/
2404
2405/**
2406 * docbNewInputStream:
2407 * @ctxt: an SGML parser context
2408 *
2409 * Create a new input stream structure
2410 * Returns the new input stream or NULL
2411 */
2412static docbParserInputPtr
2413docbNewInputStream(docbParserCtxtPtr ctxt) {
2414 docbParserInputPtr input;
2415
2416 input = (xmlParserInputPtr) xmlMalloc(sizeof(docbParserInput));
2417 if (input == NULL) {
2418 ctxt->errNo = XML_ERR_NO_MEMORY;
2419 if ((ctxt->sax != NULL) && (ctxt->sax->error != NULL))
2420 ctxt->sax->error(ctxt->userData,
2421 "malloc: couldn't allocate a new input stream\n");
2422 return(NULL);
2423 }
2424 memset(input, 0, sizeof(docbParserInput));
2425 input->filename = NULL;
2426 input->directory = NULL;
2427 input->base = NULL;
2428 input->cur = NULL;
2429 input->buf = NULL;
2430 input->line = 1;
2431 input->col = 1;
2432 input->buf = NULL;
2433 input->free = NULL;
2434 input->version = NULL;
2435 input->consumed = 0;
2436 input->length = 0;
2437 return(input);
2438}
2439
2440
2441/************************************************************************
2442 * *
2443 * Commodity functions, cleanup needed ? *
2444 * *
2445 ************************************************************************/
2446
2447/**
2448 * areBlanks:
2449 * @ctxt: an SGML parser context
2450 * @str: a xmlChar *
2451 * @len: the size of @str
2452 *
2453 * Is this a sequence of blank chars that one can ignore ?
2454 *
2455 * Returns 1 if ignorable 0 otherwise.
2456 */
2457
2458static int areBlanks(docbParserCtxtPtr ctxt, const xmlChar *str, int len) {
2459 int i;
2460 xmlNodePtr lastChild;
2461
2462 for (i = 0;i < len;i++)
2463 if (!(IS_BLANK(str[i]))) return(0);
2464
2465 if (CUR == 0) return(1);
2466 if (CUR != '<') return(0);
2467 if (ctxt->name == NULL)
2468 return(1);
2469 if (ctxt->node == NULL) return(0);
2470 lastChild = xmlGetLastChild(ctxt->node);
2471 if (lastChild == NULL) {
Daniel Veillard7db37732001-07-12 01:20:08 +0000[diff] [blame]2472 if ((ctxt->node->type != XML_ELEMENT_NODE) &&
2473 (ctxt->node->content != NULL)) return(0);
Daniel Veillardeae522a2001-04-23 13:41:34 +0000[diff] [blame]2474 } else if (xmlNodeIsText(lastChild))
2475 return(0);
2476 return(1);
2477}
2478
2479/************************************************************************
Daniel Veillard61b33d52001-04-24 13:55:12 +0000[diff] [blame]2480 * *
2481 * External entities support *
2482 * *
2483 ************************************************************************/
2484
2485/**
2486 * docbParseCtxtExternalEntity:
2487 * @ctx: the existing parsing context
2488 * @URL: the URL for the entity to load
2489 * @ID: the System ID for the entity to load
2490 * @list: the return value for the set of parsed nodes
2491 *
2492 * Parse an external general entity within an existing parsing context
2493 *
2494 * Returns 0 if the entity is well formed, -1 in case of args problem and
2495 * the parser error code otherwise
2496 */
2497
2498static int
2499docbParseCtxtExternalEntity(xmlParserCtxtPtr ctx, const xmlChar *URL,
2500 const xmlChar *ID, xmlNodePtr *list) {
2501 xmlParserCtxtPtr ctxt;
2502 xmlDocPtr newDoc;
2503 xmlSAXHandlerPtr oldsax = NULL;
2504 int ret = 0;
2505
2506 if (ctx->depth > 40) {
2507 return(XML_ERR_ENTITY_LOOP);
2508 }
2509
2510 if (list != NULL)
2511 *list = NULL;
2512 if ((URL == NULL) && (ID == NULL))
2513 return(-1);
2514 if (ctx->myDoc == NULL) /* @@ relax but check for dereferences */
2515 return(-1);
2516
2517
2518 ctxt = xmlCreateEntityParserCtxt(URL, ID, ctx->myDoc->URL);
2519 if (ctxt == NULL) return(-1);
2520 ctxt->userData = ctxt;
2521 oldsax = ctxt->sax;
2522 ctxt->sax = ctx->sax;
2523 newDoc = xmlNewDoc(BAD_CAST "1.0");
2524 if (newDoc == NULL) {
2525 xmlFreeParserCtxt(ctxt);
2526 return(-1);
2527 }
2528 if (ctx->myDoc != NULL) {
2529 newDoc->intSubset = ctx->myDoc->intSubset;
2530 newDoc->extSubset = ctx->myDoc->extSubset;
2531 }
2532 if (ctx->myDoc->URL != NULL) {
2533 newDoc->URL = xmlStrdup(ctx->myDoc->URL);
2534 }
2535 newDoc->children = xmlNewDocNode(newDoc, NULL, BAD_CAST "pseudoroot", NULL);
2536 if (newDoc->children == NULL) {
2537 ctxt->sax = oldsax;
2538 xmlFreeParserCtxt(ctxt);
2539 newDoc->intSubset = NULL;
2540 newDoc->extSubset = NULL;
2541 xmlFreeDoc(newDoc);
2542 return(-1);
2543 }
2544 nodePush(ctxt, newDoc->children);
2545 if (ctx->myDoc == NULL) {
2546 ctxt->myDoc = newDoc;
2547 } else {
2548 ctxt->myDoc = ctx->myDoc;
2549 newDoc->children->doc = ctx->myDoc;
2550 }
2551
2552 /*
2553 * Parse a possible text declaration first
2554 */
2555 GROW;
2556 if ((RAW == '<') && (NXT(1) == '?') &&
2557 (NXT(2) == 'x') && (NXT(3) == 'm') &&
2558 (NXT(4) == 'l') && (IS_BLANK(NXT(5)))) {
2559 xmlParseTextDecl(ctxt);
2560 }
2561
2562 /*
2563 * Doing validity checking on chunk doesn't make sense
2564 */
2565 ctxt->instate = XML_PARSER_CONTENT;
2566 ctxt->validate = ctx->validate;
2567 ctxt->loadsubset = ctx->loadsubset;
2568 ctxt->depth = ctx->depth + 1;
2569 ctxt->replaceEntities = ctx->replaceEntities;
2570 if (ctxt->validate) {
2571 ctxt->vctxt.error = ctx->vctxt.error;
2572 ctxt->vctxt.warning = ctx->vctxt.warning;
2573 /* Allocate the Node stack */
2574 ctxt->vctxt.nodeTab = (xmlNodePtr *) xmlMalloc(4 * sizeof(xmlNodePtr));
2575 if (ctxt->vctxt.nodeTab == NULL) {
2576 xmlGenericError(xmlGenericErrorContext,
2577 "docbParseCtxtExternalEntity: out of memory\n");
2578 ctxt->validate = 0;
2579 ctxt->vctxt.error = NULL;
2580 ctxt->vctxt.warning = NULL;
2581 } else {
2582 ctxt->vctxt.nodeNr = 0;
2583 ctxt->vctxt.nodeMax = 4;
2584 ctxt->vctxt.node = NULL;
2585 }
2586 } else {
2587 ctxt->vctxt.error = NULL;
2588 ctxt->vctxt.warning = NULL;
2589 }
2590
2591 docbParseContent(ctxt);
2592
2593 if ((RAW == '<') && (NXT(1) == '/')) {
2594 ctxt->errNo = XML_ERR_NOT_WELL_BALANCED;
2595 if ((ctxt->sax != NULL) && (ctxt->sax->error != NULL))
2596 ctxt->sax->error(ctxt->userData,
2597 "chunk is not well balanced\n");
2598 ctxt->wellFormed = 0;
2599 ctxt->disableSAX = 1;
2600 } else if (RAW != 0) {
2601 ctxt->errNo = XML_ERR_EXTRA_CONTENT;
2602 if ((ctxt->sax != NULL) && (ctxt->sax->error != NULL))
2603 ctxt->sax->error(ctxt->userData,
2604 "extra content at the end of well balanced chunk\n");
2605 ctxt->wellFormed = 0;
2606 ctxt->disableSAX = 1;
2607 }
2608 if (ctxt->node != newDoc->children) {
2609 ctxt->errNo = XML_ERR_NOT_WELL_BALANCED;
2610 if ((ctxt->sax != NULL) && (ctxt->sax->error != NULL))
2611 ctxt->sax->error(ctxt->userData,
2612 "chunk is not well balanced\n");
2613 ctxt->wellFormed = 0;
2614 ctxt->disableSAX = 1;
2615 }
2616
2617 if (!ctxt->wellFormed) {
2618 if (ctxt->errNo == 0)
2619 ret = 1;
2620 else
2621 ret = ctxt->errNo;
2622 } else {
2623 if (list != NULL) {
2624 xmlNodePtr cur;
2625
2626 /*
2627 * Return the newly created nodeset after unlinking it from
2628 * they pseudo parent.
2629 */
2630 cur = newDoc->children->children;
2631 *list = cur;
2632 while (cur != NULL) {
2633 cur->parent = NULL;
2634 cur = cur->next;
2635 }
2636 newDoc->children->children = NULL;
2637 }
2638 ret = 0;
2639 }
2640 ctxt->sax = oldsax;
2641 xmlFreeParserCtxt(ctxt);
2642 newDoc->intSubset = NULL;
2643 newDoc->extSubset = NULL;
2644 xmlFreeDoc(newDoc);
2645
2646 return(ret);
2647}
2648
2649/************************************************************************
2650 * *
2651 * The parser itself *
2652 * *
Daniel Veillardeae522a2001-04-23 13:41:34 +0000[diff] [blame]2653 ************************************************************************/
2654
2655/**
2656 * docbParseSGMLName:
2657 * @ctxt: an SGML parser context
2658 *
2659 * parse an SGML tag or attribute name, note that we convert it to lowercase
2660 * since SGML names are not case-sensitive.
2661 *
2662 * Returns the Tag Name parsed or NULL
2663 */
2664
2665static xmlChar *
2666docbParseSGMLName(docbParserCtxtPtr ctxt) {
2667 xmlChar *ret = NULL;
2668 int i = 0;
2669 xmlChar loc[DOCB_PARSER_BUFFER_SIZE];
2670
2671 if (!IS_LETTER(CUR) && (CUR != '_') &&
2672 (CUR != ':')) return(NULL);
2673
2674 while ((i < DOCB_PARSER_BUFFER_SIZE) &&
2675 ((IS_LETTER(CUR)) || (IS_DIGIT(CUR)) ||
2676 (CUR == ':') || (CUR == '_'))) {
2677 if ((CUR >= 'A') && (CUR <= 'Z')) loc[i] = CUR + 0x20;
2678 else loc[i] = CUR;
2679 i++;
2680
2681 NEXT;
2682 }
2683
2684 ret = xmlStrndup(loc, i);
2685
2686 return(ret);
2687}
2688
2689/**
2690 * docbParseName:
2691 * @ctxt: an SGML parser context
2692 *
Daniel Veillardcbaf3992001-12-31 16:16:02 +0000[diff] [blame^]2693 * parse an SGML name, this routine is case sensitive.
Daniel Veillardeae522a2001-04-23 13:41:34 +0000[diff] [blame]2694 *
2695 * Returns the Name parsed or NULL
2696 */
2697
2698static xmlChar *
2699docbParseName(docbParserCtxtPtr ctxt) {
2700 xmlChar buf[DOCB_MAX_NAMELEN];
2701 int len = 0;
2702
2703 GROW;
2704 if (!IS_LETTER(CUR) && (CUR != '_')) {
2705 return(NULL);
2706 }
2707
2708 while ((IS_LETTER(CUR)) || (IS_DIGIT(CUR)) ||
2709 (CUR == '.') || (CUR == '-') ||
2710 (CUR == '_') || (CUR == ':') ||
2711 (IS_COMBINING(CUR)) ||
2712 (IS_EXTENDER(CUR))) {
2713 buf[len++] = CUR;
2714 NEXT;
2715 if (len >= DOCB_MAX_NAMELEN) {
2716 xmlGenericError(xmlGenericErrorContext,
2717 "docbParseName: reached DOCB_MAX_NAMELEN limit\n");
2718 while ((IS_LETTER(CUR)) || (IS_DIGIT(CUR)) ||
2719 (CUR == '.') || (CUR == '-') ||
2720 (CUR == '_') || (CUR == ':') ||
2721 (IS_COMBINING(CUR)) ||
2722 (IS_EXTENDER(CUR)))
2723 NEXT;
2724 break;
2725 }
2726 }
2727 return(xmlStrndup(buf, len));
2728}
2729
2730/**
2731 * docbParseSGMLAttribute:
2732 * @ctxt: an SGML parser context
2733 * @stop: a char stop value
2734 *
2735 * parse an SGML attribute value till the stop (quote), if
2736 * stop is 0 then it stops at the first space
2737 *
2738 * Returns the attribute parsed or NULL
2739 */
2740
2741static xmlChar *
2742docbParseSGMLAttribute(docbParserCtxtPtr ctxt, const xmlChar stop) {
2743 xmlChar *buffer = NULL;
2744 int buffer_size = 0;
2745 xmlChar *out = NULL;
2746 xmlChar *name = NULL;
2747
2748 xmlChar *cur = NULL;
Daniel Veillard61b33d52001-04-24 13:55:12 +0000[diff] [blame]2749 xmlEntityPtr xent;
Daniel Veillardeae522a2001-04-23 13:41:34 +0000[diff] [blame]2750 docbEntityDescPtr ent;
2751
2752 /*
2753 * allocate a translation buffer.
2754 */
2755 buffer_size = DOCB_PARSER_BIG_BUFFER_SIZE;
2756 buffer = (xmlChar *) xmlMalloc(buffer_size * sizeof(xmlChar));
2757 if (buffer == NULL) {
2758 perror("docbParseSGMLAttribute: malloc failed");
2759 return(NULL);
2760 }
2761 out = buffer;
2762
2763 /*
2764 * Ok loop until we reach one of the ending chars
2765 */
2766 while ((CUR != 0) && (CUR != stop) && (CUR != '>')) {
2767 if ((stop == 0) && (IS_BLANK(CUR))) break;
2768 if (CUR == '&') {
2769 if (NXT(1) == '#') {
2770 unsigned int c;
2771 int bits;
2772
2773 c = docbParseCharRef(ctxt);
2774 if (c < 0x80)
2775 { *out++ = c; bits= -6; }
2776 else if (c < 0x800)
2777 { *out++ =((c >> 6) & 0x1F) | 0xC0; bits= 0; }
2778 else if (c < 0x10000)
2779 { *out++ =((c >> 12) & 0x0F) | 0xE0; bits= 6; }
2780 else
2781 { *out++ =((c >> 18) & 0x07) | 0xF0; bits= 12; }
2782
2783 for ( ; bits >= 0; bits-= 6) {
2784 *out++ = ((c >> bits) & 0x3F) | 0x80;
2785 }
2786 } else {
Daniel Veillardc057c5d2001-05-02 12:41:24 +0000[diff] [blame]2787 xent = docbParseEntityRef(ctxt, &name);
Daniel Veillardeae522a2001-04-23 13:41:34 +0000[diff] [blame]2788 if (name == NULL) {
2789 *out++ = '&';
2790 if (out - buffer > buffer_size - 100) {
2791 int indx = out - buffer;
2792
2793 growBuffer(buffer);
2794 out = &buffer[indx];
2795 }
Daniel Veillardeae522a2001-04-23 13:41:34 +0000[diff] [blame]2796 *out++ = '&';
Daniel Veillardeae522a2001-04-23 13:41:34 +0000[diff] [blame]2797 } else {
Daniel Veillardc057c5d2001-05-02 12:41:24 +0000[diff] [blame]2798 ent = docbEntityLookup(name);
2799 if (ent == NULL) {
2800 *out++ = '&';
2801 cur = name;
2802 while (*cur != 0) {
2803 if (out - buffer > buffer_size - 100) {
2804 int indx = out - buffer;
Daniel Veillardeae522a2001-04-23 13:41:34 +0000[diff] [blame]2805
Daniel Veillardc057c5d2001-05-02 12:41:24 +0000[diff] [blame]2806 growBuffer(buffer);
2807 out = &buffer[indx];
2808 }
2809 *out++ = *cur++;
2810 }
2811 xmlFree(name);
2812 } else {
2813 unsigned int c;
2814 int bits;
Daniel Veillardeae522a2001-04-23 13:41:34 +0000[diff] [blame]2815
Daniel Veillardc057c5d2001-05-02 12:41:24 +0000[diff] [blame]2816 if (out - buffer > buffer_size - 100) {
2817 int indx = out - buffer;
2818
2819 growBuffer(buffer);
2820 out = &buffer[indx];
2821 }
2822 c = (xmlChar)ent->value;
2823 if (c < 0x80)
2824 { *out++ = c; bits= -6; }
2825 else if (c < 0x800)
2826 { *out++ =((c >> 6) & 0x1F) | 0xC0; bits= 0; }
2827 else if (c < 0x10000)
2828 { *out++ =((c >> 12) & 0x0F) | 0xE0; bits= 6; }
2829 else
2830 { *out++ =((c >> 18) & 0x07) | 0xF0; bits= 12; }
2831
2832 for ( ; bits >= 0; bits-= 6) {
2833 *out++ = ((c >> bits) & 0x3F) | 0x80;
2834 }
2835 xmlFree(name);
2836 }
2837 }
Daniel Veillardeae522a2001-04-23 13:41:34 +0000[diff] [blame]2838 }
2839 } else {
2840 unsigned int c;
2841 int bits;
2842
2843 if (out - buffer > buffer_size - 100) {
2844 int indx = out - buffer;
2845
2846 growBuffer(buffer);
2847 out = &buffer[indx];
2848 }
2849 c = CUR;
2850 if (c < 0x80)
2851 { *out++ = c; bits= -6; }
2852 else if (c < 0x800)
2853 { *out++ =((c >> 6) & 0x1F) | 0xC0; bits= 0; }
2854 else if (c < 0x10000)
2855 { *out++ =((c >> 12) & 0x0F) | 0xE0; bits= 6; }
2856 else
2857 { *out++ =((c >> 18) & 0x07) | 0xF0; bits= 12; }
2858
2859 for ( ; bits >= 0; bits-= 6) {
2860 *out++ = ((c >> bits) & 0x3F) | 0x80;
2861 }
2862 NEXT;
2863 }
2864 }
2865 *out++ = 0;
2866 return(buffer);
2867}
2868
2869
2870/**
2871 * docbParseEntityRef:
2872 * @ctxt: an SGML parser context
2873 * @str: location to store the entity name
2874 *
2875 * parse an SGML ENTITY references
2876 *
2877 * [68] EntityRef ::= '&' Name ';'
2878 *
Daniel Veillard61b33d52001-04-24 13:55:12 +0000[diff] [blame]2879 * Returns the associated xmlEntityPtr if found, or NULL otherwise,
Daniel Veillardeae522a2001-04-23 13:41:34 +0000[diff] [blame]2880 * if non-NULL *str will have to be freed by the caller.
2881 */
Daniel Veillard61b33d52001-04-24 13:55:12 +0000[diff] [blame]2882static xmlEntityPtr
Daniel Veillardeae522a2001-04-23 13:41:34 +0000[diff] [blame]2883docbParseEntityRef(docbParserCtxtPtr ctxt, xmlChar **str) {
2884 xmlChar *name;
Daniel Veillard61b33d52001-04-24 13:55:12 +0000[diff] [blame]2885 xmlEntityPtr ent = NULL;
Daniel Veillardeae522a2001-04-23 13:41:34 +0000[diff] [blame]2886 *str = NULL;
2887
2888 if (CUR == '&') {
2889 NEXT;
2890 name = docbParseName(ctxt);
Daniel Veillard61b33d52001-04-24 13:55:12 +0000[diff] [blame]2891 if (name == NULL) {
2892 if ((ctxt->sax != NULL) && (ctxt->sax->error != NULL))
2893 ctxt->sax->error(ctxt->userData,
2894 "docbParseEntityRef: no name\n");
2895 ctxt->wellFormed = 0;
2896 } else {
Daniel Veillardeae522a2001-04-23 13:41:34 +0000[diff] [blame]2897 GROW;
Daniel Veillard61b33d52001-04-24 13:55:12 +0000[diff] [blame]2898 if (CUR == ';') {
2899 *str = name;
Daniel Veillardeae522a2001-04-23 13:41:34 +0000[diff] [blame]2900
Daniel Veillard61b33d52001-04-24 13:55:12 +0000[diff] [blame]2901 /*
2902 * Ask first SAX for entity resolution, otherwise try the
2903 * predefined set.
2904 */
2905 if (ctxt->sax != NULL) {
2906 if (ctxt->sax->getEntity != NULL)
2907 ent = ctxt->sax->getEntity(ctxt->userData, name);
2908 if (ent == NULL)
2909 ent = xmlGetPredefinedEntity(name);
2910 }
2911 NEXT;
2912 } else {
2913 if ((ctxt->sax != NULL) && (ctxt->sax->error != NULL))
2914 ctxt->sax->error(ctxt->userData,
Daniel Veillardeae522a2001-04-23 13:41:34 +0000[diff] [blame]2915 "docbParseEntityRef: expecting ';'\n");
Daniel Veillard61b33d52001-04-24 13:55:12 +0000[diff] [blame]2916 *str = name;
2917 }
2918 }
Daniel Veillardeae522a2001-04-23 13:41:34 +0000[diff] [blame]2919 }
2920 return(ent);
2921}
2922
2923/**
2924 * docbParseAttValue:
2925 * @ctxt: an SGML parser context
2926 *
2927 * parse a value for an attribute
2928 * Note: the parser won't do substitution of entities here, this
2929 * will be handled later in xmlStringGetNodeList, unless it was
2930 * asked for ctxt->replaceEntities != 0
2931 *
2932 * Returns the AttValue parsed or NULL.
2933 */
2934
2935static xmlChar *
2936docbParseAttValue(docbParserCtxtPtr ctxt) {
2937 xmlChar *ret = NULL;
2938
2939 if (CUR == '"') {
2940 NEXT;
2941 ret = docbParseSGMLAttribute(ctxt, '"');
2942 if (CUR != '"') {
2943 if ((ctxt->sax != NULL) && (ctxt->sax->error != NULL))
2944 ctxt->sax->error(ctxt->userData, "AttValue: ' expected\n");
2945 ctxt->wellFormed = 0;
2946 } else
2947 NEXT;
2948 } else if (CUR == '\'') {
2949 NEXT;
2950 ret = docbParseSGMLAttribute(ctxt, '\'');
2951 if (CUR != '\'') {
2952 if ((ctxt->sax != NULL) && (ctxt->sax->error != NULL))
2953 ctxt->sax->error(ctxt->userData, "AttValue: ' expected\n");
2954 ctxt->wellFormed = 0;
2955 } else
2956 NEXT;
2957 } else {
2958 /*
2959 * That's an SGMLism, the attribute value may not be quoted
2960 */
2961 ret = docbParseSGMLAttribute(ctxt, 0);
2962 if (ret == NULL) {
2963 if ((ctxt->sax != NULL) && (ctxt->sax->error != NULL))
2964 ctxt->sax->error(ctxt->userData, "AttValue: no value found\n");
2965 ctxt->wellFormed = 0;
2966 }
2967 }
2968 return(ret);
2969}
2970
2971/**
2972 * docbParseSystemLiteral:
2973 * @ctxt: an SGML parser context
2974 *
2975 * parse an SGML Literal
2976 *
2977 * [11] SystemLiteral ::= ('"' [^"]* '"') | ("'" [^']* "'")
2978 *
2979 * Returns the SystemLiteral parsed or NULL
2980 */
2981
2982static xmlChar *
2983docbParseSystemLiteral(docbParserCtxtPtr ctxt) {
2984 const xmlChar *q;
2985 xmlChar *ret = NULL;
2986
2987 if (CUR == '"') {
2988 NEXT;
2989 q = CUR_PTR;
2990 while ((IS_CHAR(CUR)) && (CUR != '"'))
2991 NEXT;
2992 if (!IS_CHAR(CUR)) {
2993 if ((ctxt->sax != NULL) && (ctxt->sax->error != NULL))
2994 ctxt->sax->error(ctxt->userData, "Unfinished SystemLiteral\n");
2995 ctxt->wellFormed = 0;
2996 } else {
2997 ret = xmlStrndup(q, CUR_PTR - q);
2998 NEXT;
2999 }
3000 } else if (CUR == '\'') {
3001 NEXT;
3002 q = CUR_PTR;
3003 while ((IS_CHAR(CUR)) && (CUR != '\''))
3004 NEXT;
3005 if (!IS_CHAR(CUR)) {
3006 if ((ctxt->sax != NULL) && (ctxt->sax->error != NULL))
3007 ctxt->sax->error(ctxt->userData, "Unfinished SystemLiteral\n");
3008 ctxt->wellFormed = 0;
3009 } else {
3010 ret = xmlStrndup(q, CUR_PTR - q);
3011 NEXT;
3012 }
3013 } else {
3014 if ((ctxt->sax != NULL) && (ctxt->sax->error != NULL))
3015 ctxt->sax->error(ctxt->userData,
3016 "SystemLiteral \" or ' expected\n");
3017 ctxt->wellFormed = 0;
3018 }
3019
3020 return(ret);
3021}
3022
3023/**
3024 * docbParsePubidLiteral:
3025 * @ctxt: an SGML parser context
3026 *
3027 * parse an SGML public literal
3028 *
3029 * [12] PubidLiteral ::= '"' PubidChar* '"' | "'" (PubidChar - "'")* "'"
3030 *
3031 * Returns the PubidLiteral parsed or NULL.
3032 */
3033
3034static xmlChar *
3035docbParsePubidLiteral(docbParserCtxtPtr ctxt) {
3036 const xmlChar *q;
3037 xmlChar *ret = NULL;
3038 /*
3039 * Name ::= (Letter | '_') (NameChar)*
3040 */
3041 if (CUR == '"') {
3042 NEXT;
3043 q = CUR_PTR;
3044 while (IS_PUBIDCHAR(CUR)) NEXT;
3045 if (CUR != '"') {
3046 if ((ctxt->sax != NULL) && (ctxt->sax->error != NULL))
3047 ctxt->sax->error(ctxt->userData, "Unfinished PubidLiteral\n");
3048 ctxt->wellFormed = 0;
3049 } else {
3050 ret = xmlStrndup(q, CUR_PTR - q);
3051 NEXT;
3052 }
3053 } else if (CUR == '\'') {
3054 NEXT;
3055 q = CUR_PTR;
3056 while ((IS_LETTER(CUR)) && (CUR != '\''))
3057 NEXT;
3058 if (!IS_LETTER(CUR)) {
3059 if ((ctxt->sax != NULL) && (ctxt->sax->error != NULL))
3060 ctxt->sax->error(ctxt->userData, "Unfinished PubidLiteral\n");
3061 ctxt->wellFormed = 0;
3062 } else {
3063 ret = xmlStrndup(q, CUR_PTR - q);
3064 NEXT;
3065 }
3066 } else {
3067 if ((ctxt->sax != NULL) && (ctxt->sax->error != NULL))
3068 ctxt->sax->error(ctxt->userData, "SystemLiteral \" or ' expected\n");
3069 ctxt->wellFormed = 0;
3070 }
3071
3072 return(ret);
3073}
3074
3075/**
3076 * docbParseCharData:
3077 * @ctxt: an SGML parser context
3078 * @cdata: int indicating whether we are within a CDATA section
3079 *
3080 * parse a CharData section.
3081 * if we are within a CDATA section ']]>' marks an end of section.
3082 *
3083 * [14] CharData ::= [^<&]* - ([^<&]* ']]>' [^<&]*)
3084 */
3085
3086static void
3087docbParseCharData(docbParserCtxtPtr ctxt) {
3088 xmlChar buf[DOCB_PARSER_BIG_BUFFER_SIZE + 5];
3089 int nbchar = 0;
3090 int cur, l;
3091
3092 SHRINK;
3093 cur = CUR_CHAR(l);
3094 while (((cur != '<') || (ctxt->token == '<')) &&
3095 ((cur != '&') || (ctxt->token == '&')) &&
3096 (IS_CHAR(cur))) {
3097 COPY_BUF(l,buf,nbchar,cur);
3098 if (nbchar >= DOCB_PARSER_BIG_BUFFER_SIZE) {
3099 /*
3100 * Ok the segment is to be consumed as chars.
3101 */
3102 if ((ctxt->sax != NULL) && (!ctxt->disableSAX)) {
3103 if (areBlanks(ctxt, buf, nbchar)) {
3104 if (ctxt->sax->ignorableWhitespace != NULL)
3105 ctxt->sax->ignorableWhitespace(ctxt->userData,
3106 buf, nbchar);
3107 } else {
3108 docbCheckParagraph(ctxt);
3109 if (ctxt->sax->characters != NULL)
3110 ctxt->sax->characters(ctxt->userData, buf, nbchar);
3111 }
3112 }
3113 nbchar = 0;
3114 }
3115 NEXTL(l);
3116 cur = CUR_CHAR(l);
3117 }
3118 if (nbchar != 0) {
3119 /*
3120 * Ok the segment is to be consumed as chars.
3121 */
3122 if ((ctxt->sax != NULL) && (!ctxt->disableSAX)) {
3123 if (areBlanks(ctxt, buf, nbchar)) {
3124 if (ctxt->sax->ignorableWhitespace != NULL)
3125 ctxt->sax->ignorableWhitespace(ctxt->userData, buf, nbchar);
3126 } else {
3127 docbCheckParagraph(ctxt);
3128 if (ctxt->sax->characters != NULL)
3129 ctxt->sax->characters(ctxt->userData, buf, nbchar);
3130 }
3131 }
3132 }
3133}
3134
3135/**
3136 * docbParseExternalID:
3137 * @ctxt: an SGML parser context
3138 * @publicID: a xmlChar** receiving PubidLiteral
3139 *
3140 * Parse an External ID or a Public ID
3141 *
3142 * Returns the function returns SystemLiteral and in the second
3143 * case publicID receives PubidLiteral,
3144 * it is possible to return NULL and have publicID set.
3145 */
3146
3147static xmlChar *
3148docbParseExternalID(docbParserCtxtPtr ctxt, xmlChar **publicID) {
3149 xmlChar *URI = NULL;
3150
3151 if ((UPPER == 'S') && (UPP(1) == 'Y') &&
3152 (UPP(2) == 'S') && (UPP(3) == 'T') &&
3153 (UPP(4) == 'E') && (UPP(5) == 'M')) {
3154 SKIP(6);
3155 if (!IS_BLANK(CUR)) {
3156 if ((ctxt->sax != NULL) && (ctxt->sax->error != NULL))
3157 ctxt->sax->error(ctxt->userData,
3158 "Space required after 'SYSTEM'\n");
3159 ctxt->wellFormed = 0;
3160 }
3161 SKIP_BLANKS;
3162 URI = docbParseSystemLiteral(ctxt);
3163 if (URI == NULL) {
3164 if ((ctxt->sax != NULL) && (ctxt->sax->error != NULL))
3165 ctxt->sax->error(ctxt->userData,
3166 "docbParseExternalID: SYSTEM, no URI\n");
3167 ctxt->wellFormed = 0;
3168 }
3169 } else if ((UPPER == 'P') && (UPP(1) == 'U') &&
3170 (UPP(2) == 'B') && (UPP(3) == 'L') &&
3171 (UPP(4) == 'I') && (UPP(5) == 'C')) {
3172 SKIP(6);
3173 if (!IS_BLANK(CUR)) {
3174 if ((ctxt->sax != NULL) && (ctxt->sax->error != NULL))
3175 ctxt->sax->error(ctxt->userData,
3176 "Space required after 'PUBLIC'\n");
3177 ctxt->wellFormed = 0;
3178 }
3179 SKIP_BLANKS;
3180 *publicID = docbParsePubidLiteral(ctxt);
3181 if (*publicID == NULL) {
3182 if ((ctxt->sax != NULL) && (ctxt->sax->error != NULL))
3183 ctxt->sax->error(ctxt->userData,
3184 "docbParseExternalID: PUBLIC, no Public Identifier\n");
3185 ctxt->wellFormed = 0;
3186 }
3187 SKIP_BLANKS;
3188 if ((CUR == '"') || (CUR == '\'')) {
3189 URI = docbParseSystemLiteral(ctxt);
3190 }
3191 }
3192 return(URI);
3193}
3194
3195/**
Daniel Veillarde95e2392001-06-06 10:46:28 +0000[diff] [blame]3196 * docbParsePI:
3197 * @ctxt: an XML parser context
3198 *
3199 * parse an XML Processing Instruction.
3200 *
3201 * [16] PI ::= '<?' PITarget (S (Char* - (Char* '?>' Char*)))? '?>'
3202 *
3203 * The processing is transfered to SAX once parsed.
3204 */
3205
3206static void
3207docbParsePI(xmlParserCtxtPtr ctxt) {
3208 xmlChar *buf = NULL;
3209 int len = 0;
3210 int size = DOCB_PARSER_BUFFER_SIZE;
3211 int cur, l;
3212 xmlChar *target;
3213 xmlParserInputState state;
3214 int count = 0;
3215
3216 if ((RAW == '<') && (NXT(1) == '?')) {
3217 xmlParserInputPtr input = ctxt->input;
3218 state = ctxt->instate;
3219 ctxt->instate = XML_PARSER_PI;
3220 /*
3221 * this is a Processing Instruction.
3222 */
3223 SKIP(2);
3224 SHRINK;
3225
3226 /*
3227 * Parse the target name and check for special support like
3228 * namespace.
3229 */
3230 target = xmlParseName(ctxt);
3231 if (target != NULL) {
3232 xmlChar *encoding = NULL;
3233
3234 if ((RAW == '?') && (NXT(1) == '>')) {
3235 if (input != ctxt->input) {
3236 ctxt->errNo = XML_ERR_ENTITY_BOUNDARY;
3237 if ((ctxt->sax != NULL) && (ctxt->sax->error != NULL))
3238 ctxt->sax->error(ctxt->userData,
3239 "PI declaration doesn't start and stop in the same entity\n");
3240 ctxt->wellFormed = 0;
3241 ctxt->disableSAX = 1;
3242 }
3243 SKIP(2);
3244
3245 /*
3246 * SAX: PI detected.
3247 */
3248 if ((ctxt->sax) && (!ctxt->disableSAX) &&
3249 (ctxt->sax->processingInstruction != NULL))
3250 ctxt->sax->processingInstruction(ctxt->userData,
3251 target, NULL);
3252 ctxt->instate = state;
3253 xmlFree(target);
3254 return;
3255 }
3256 if (xmlStrEqual(target, BAD_CAST "sgml-declaration")) {
3257
3258 encoding = xmlParseEncodingDecl(ctxt);
3259 if (encoding == NULL) {
3260 xmlGenericError(xmlGenericErrorContext,
3261 "sgml-declaration: failed to find/handle encoding\n");
3262#ifdef DEBUG
3263 } else {
3264 xmlGenericError(xmlGenericErrorContext,
3265 "switched to encoding %s\n", encoding);
3266#endif
3267 }
3268
3269 }
3270 buf = (xmlChar *) xmlMalloc(size * sizeof(xmlChar));
3271 if (buf == NULL) {
3272 xmlGenericError(xmlGenericErrorContext,
3273 "malloc of %d byte failed\n", size);
3274 ctxt->instate = state;
3275 return;
3276 }
3277 cur = CUR;
3278 if (encoding != NULL) {
3279 len = snprintf((char *) buf, size - 1,
3280 " encoding = \"%s\"", encoding);
3281 if (len < 0)
3282 len = size;
3283 } else {
3284 if (!IS_BLANK(cur)) {
3285 ctxt->errNo = XML_ERR_SPACE_REQUIRED;
3286 if ((ctxt->sax != NULL) && (ctxt->sax->error != NULL))
3287 ctxt->sax->error(ctxt->userData,
3288 "docbParsePI: PI %s space expected\n", target);
3289 ctxt->wellFormed = 0;
3290 ctxt->disableSAX = 1;
3291 }
3292 SKIP_BLANKS;
3293 }
3294 cur = CUR_CHAR(l);
3295 while (IS_CHAR(cur) && /* checked */
3296 ((cur != '?') || (NXT(1) != '>'))) {
3297 if (len + 5 >= size) {
3298 size *= 2;
3299 buf = (xmlChar *) xmlRealloc(buf, size * sizeof(xmlChar));
3300 if (buf == NULL) {
3301 xmlGenericError(xmlGenericErrorContext,
3302 "realloc of %d byte failed\n", size);
3303 ctxt->instate = state;
3304 return;
3305 }
3306 }
3307 count++;
3308 if (count > 50) {
3309 GROW;
3310 count = 0;
3311 }
3312 COPY_BUF(l,buf,len,cur);
3313 NEXTL(l);
3314 cur = CUR_CHAR(l);
3315 if (cur == 0) {
3316 SHRINK;
3317 GROW;
3318 cur = CUR_CHAR(l);
3319 }
3320 }
3321 buf[len] = 0;
3322 if (cur != '?') {
3323 ctxt->errNo = XML_ERR_PI_NOT_FINISHED;
3324 if ((ctxt->sax != NULL) && (ctxt->sax->error != NULL))
3325 ctxt->sax->error(ctxt->userData,
3326 "docbParsePI: PI %s never end ...\n", target);
3327 ctxt->wellFormed = 0;
3328 ctxt->disableSAX = 1;
3329 } else {
3330 if (input != ctxt->input) {
3331 ctxt->errNo = XML_ERR_ENTITY_BOUNDARY;
3332 if ((ctxt->sax != NULL) && (ctxt->sax->error != NULL))
3333 ctxt->sax->error(ctxt->userData,
3334 "PI declaration doesn't start and stop in the same entity\n");
3335 ctxt->wellFormed = 0;
3336 ctxt->disableSAX = 1;
3337 }
3338 SKIP(2);
3339
3340 /*
3341 * SAX: PI detected.
3342 */
3343 if ((ctxt->sax) && (!ctxt->disableSAX) &&
3344 (ctxt->sax->processingInstruction != NULL))
3345 ctxt->sax->processingInstruction(ctxt->userData,
3346 target, buf);
3347 }
3348 xmlFree(buf);
3349 xmlFree(target);
3350 } else {
3351 ctxt->errNo = XML_ERR_PI_NOT_STARTED;
3352 if ((ctxt->sax != NULL) && (ctxt->sax->error != NULL))
3353 ctxt->sax->error(ctxt->userData,
3354 "docbParsePI : no target name\n");
3355 ctxt->wellFormed = 0;
3356 ctxt->disableSAX = 1;
3357 }
3358 ctxt->instate = state;
3359 }
3360}
3361
3362/**
Daniel Veillardeae522a2001-04-23 13:41:34 +0000[diff] [blame]3363 * docbParseComment:
3364 * @ctxt: an SGML parser context
3365 *
3366 * Parse an XML (SGML) comment <!-- .... -->
3367 *
3368 * [15] Comment ::= '<!--' ((Char - '-') | ('-' (Char - '-')))* '-->'
3369 */
3370static void
3371docbParseComment(docbParserCtxtPtr ctxt) {
3372 xmlChar *buf = NULL;
3373 int len;
3374 int size = DOCB_PARSER_BUFFER_SIZE;
3375 int q, ql;
3376 int r, rl;
3377 int cur, l;
3378 xmlParserInputState state;
3379
3380 /*
3381 * Check that there is a comment right here.
3382 */
3383 if ((RAW != '<') || (NXT(1) != '!') ||
3384 (NXT(2) != '-') || (NXT(3) != '-')) return;
3385
3386 state = ctxt->instate;
3387 ctxt->instate = XML_PARSER_COMMENT;
3388 SHRINK;
3389 SKIP(4);
3390 buf = (xmlChar *) xmlMalloc(size * sizeof(xmlChar));
3391 if (buf == NULL) {
3392 xmlGenericError(xmlGenericErrorContext,
3393 "malloc of %d byte failed\n", size);
3394 ctxt->instate = state;
3395 return;
3396 }
3397 q = CUR_CHAR(ql);
3398 NEXTL(ql);
3399 r = CUR_CHAR(rl);
3400 NEXTL(rl);
3401 cur = CUR_CHAR(l);
3402 len = 0;
3403 while (IS_CHAR(cur) &&
3404 ((cur != '>') ||
3405 (r != '-') || (q != '-'))) {
3406 if (len + 5 >= size) {
3407 size *= 2;
3408 buf = (xmlChar *) xmlRealloc(buf, size * sizeof(xmlChar));
3409 if (buf == NULL) {
3410 xmlGenericError(xmlGenericErrorContext,
3411 "realloc of %d byte failed\n", size);
3412 ctxt->instate = state;
3413 return;
3414 }
3415 }
3416 COPY_BUF(ql,buf,len,q);
3417 q = r;
3418 ql = rl;
3419 r = cur;
3420 rl = l;
3421 NEXTL(l);
3422 cur = CUR_CHAR(l);
3423 if (cur == 0) {
3424 SHRINK;
3425 GROW;
3426 cur = CUR_CHAR(l);
3427 }
3428 }
3429 buf[len] = 0;
3430 if (!IS_CHAR(cur)) {
3431 ctxt->errNo = XML_ERR_COMMENT_NOT_FINISHED;
3432 if ((ctxt->sax != NULL) && (ctxt->sax->error != NULL))
3433 ctxt->sax->error(ctxt->userData,
3434 "Comment not terminated \n<!--%.50s\n", buf);
3435 ctxt->wellFormed = 0;
3436 xmlFree(buf);
3437 } else {
3438 NEXT;
3439 if ((ctxt->sax != NULL) && (ctxt->sax->comment != NULL) &&
3440 (!ctxt->disableSAX))
3441 ctxt->sax->comment(ctxt->userData, buf);
3442 xmlFree(buf);
3443 }
3444 ctxt->instate = state;
3445}
3446
3447/**
3448 * docbParseCharRef:
3449 * @ctxt: an SGML parser context
3450 *
3451 * parse Reference declarations
3452 *
3453 * [66] CharRef ::= '&#' [0-9]+ ';' |
3454 * '&#x' [0-9a-fA-F]+ ';'
3455 *
3456 * Returns the value parsed (as an int)
3457 */
3458static int
3459docbParseCharRef(docbParserCtxtPtr ctxt) {
3460 int val = 0;
3461
3462 if ((CUR == '&') && (NXT(1) == '#') &&
3463 (NXT(2) == 'x')) {
3464 SKIP(3);
3465 while (CUR != ';') {
3466 if ((CUR >= '0') && (CUR <= '9'))
3467 val = val * 16 + (CUR - '0');
3468 else if ((CUR >= 'a') && (CUR <= 'f'))
3469 val = val * 16 + (CUR - 'a') + 10;
3470 else if ((CUR >= 'A') && (CUR <= 'F'))
3471 val = val * 16 + (CUR - 'A') + 10;
3472 else {
3473 if ((ctxt->sax != NULL) && (ctxt->sax->error != NULL))
3474 ctxt->sax->error(ctxt->userData,
3475 "docbParseCharRef: invalid hexadecimal value\n");
3476 ctxt->wellFormed = 0;
3477 val = 0;
3478 break;
3479 }
3480 NEXT;
3481 }
3482 if (CUR == ';')
3483 NEXT;
3484 } else if ((CUR == '&') && (NXT(1) == '#')) {
3485 SKIP(2);
3486 while (CUR != ';') {
3487 if ((CUR >= '0') && (CUR <= '9'))
3488 val = val * 10 + (CUR - '0');
3489 else {
3490 if ((ctxt->sax != NULL) && (ctxt->sax->error != NULL))
3491 ctxt->sax->error(ctxt->userData,
3492 "docbParseCharRef: invalid decimal value\n");
3493 ctxt->wellFormed = 0;
3494 val = 0;
3495 break;
3496 }
3497 NEXT;
3498 }
3499 if (CUR == ';')
3500 NEXT;
3501 } else {
3502 if ((ctxt->sax != NULL) && (ctxt->sax->error != NULL))
3503 ctxt->sax->error(ctxt->userData, "docbParseCharRef: invalid value\n");
3504 ctxt->wellFormed = 0;
3505 }
3506 /*
3507 * Check the value IS_CHAR ...
3508 */
3509 if (IS_CHAR(val)) {
3510 return(val);
3511 } else {
3512 if ((ctxt->sax != NULL) && (ctxt->sax->error != NULL))
3513 ctxt->sax->error(ctxt->userData, "docbParseCharRef: invalid xmlChar value %d\n",
3514 val);
3515 ctxt->wellFormed = 0;
3516 }
3517 return(0);
3518}
3519
3520
3521/**
3522 * docbParseDocTypeDecl :
3523 * @ctxt: an SGML parser context
3524 *
3525 * parse a DOCTYPE declaration
3526 *
3527 * [28] doctypedecl ::= '<!DOCTYPE' S Name (S ExternalID)? S?
3528 * ('[' (markupdecl | PEReference | S)* ']' S?)? '>'
3529 */
3530
3531static void
3532docbParseDocTypeDecl(docbParserCtxtPtr ctxt) {
3533 xmlChar *name;
3534 xmlChar *ExternalID = NULL;
3535 xmlChar *URI = NULL;
3536
3537 /*
3538 * We know that '<!DOCTYPE' has been detected.
3539 */
3540 SKIP(9);
3541
3542 SKIP_BLANKS;
3543
3544 /*
3545 * Parse the DOCTYPE name.
3546 */
3547 name = docbParseName(ctxt);
3548 if (name == NULL) {
3549 if ((ctxt->sax != NULL) && (ctxt->sax->error != NULL))
3550 ctxt->sax->error(ctxt->userData, "docbParseDocTypeDecl : no DOCTYPE name !\n");
3551 ctxt->wellFormed = 0;
3552 }
3553 /*
3554 * Check that upper(name) == "SGML" !!!!!!!!!!!!!
3555 */
3556
3557 SKIP_BLANKS;
3558
3559 /*
3560 * Check for SystemID and ExternalID
3561 */
3562 URI = docbParseExternalID(ctxt, &ExternalID);
3563 SKIP_BLANKS;
3564
3565 /*
3566 * Create or update the document accordingly to the DOCTYPE
Daniel Veillard89cad532001-10-22 09:46:13 +0000[diff] [blame]3567 * But use the predefined PUBLIC and SYSTEM ID of DocBook XML
Daniel Veillardeae522a2001-04-23 13:41:34 +0000[diff] [blame]3568 */
3569 if ((ctxt->sax != NULL) && (ctxt->sax->internalSubset != NULL) &&
3570 (!ctxt->disableSAX))
Daniel Veillard89cad532001-10-22 09:46:13 +0000[diff] [blame]3571 ctxt->sax->internalSubset(ctxt->userData, name,
3572 XML_DOCBOOK_XML_PUBLIC,
3573 XML_DOCBOOK_XML_SYSTEM);
Daniel Veillardeae522a2001-04-23 13:41:34 +0000[diff] [blame]3574
Daniel Veillard89cad532001-10-22 09:46:13 +0000[diff] [blame]3575 if (RAW != '>') {
3576 if ((ctxt->sax != NULL) && (ctxt->sax->error != NULL))
3577 ctxt->sax->error(ctxt->userData,
3578 "docbParseDocTypeDecl : internal subset not handled\n");
3579 } else {
3580 NEXT;
Daniel Veillardeae522a2001-04-23 13:41:34 +0000[diff] [blame]3581 }
Daniel Veillardeae522a2001-04-23 13:41:34 +0000[diff] [blame]3582
3583 /*
3584 * Cleanup, since we don't use all those identifiers
3585 */
3586 if (URI != NULL) xmlFree(URI);
3587 if (ExternalID != NULL) xmlFree(ExternalID);
3588 if (name != NULL) xmlFree(name);
3589}
3590
3591/**
3592 * docbParseAttribute:
3593 * @ctxt: an SGML parser context
3594 * @value: a xmlChar ** used to store the value of the attribute
3595 *
3596 * parse an attribute
3597 *
3598 * [41] Attribute ::= Name Eq AttValue
3599 *
3600 * [25] Eq ::= S? '=' S?
3601 *
3602 * With namespace:
3603 *
3604 * [NS 11] Attribute ::= QName Eq AttValue
3605 *
3606 * Also the case QName == xmlns:??? is handled independently as a namespace
3607 * definition.
3608 *
3609 * Returns the attribute name, and the value in *value.
3610 */
3611
3612static xmlChar *
3613docbParseAttribute(docbParserCtxtPtr ctxt, xmlChar **value) {
3614 xmlChar *name, *val = NULL;
3615
3616 *value = NULL;
3617 name = docbParseName(ctxt);
3618 if (name == NULL) {
3619 if ((ctxt->sax != NULL) && (ctxt->sax->error != NULL))
3620 ctxt->sax->error(ctxt->userData, "error parsing attribute name\n");
3621 ctxt->wellFormed = 0;
3622 return(NULL);
3623 }
3624
3625 /*
3626 * read the value
3627 */
3628 SKIP_BLANKS;
3629 if (CUR == '=') {
3630 NEXT;
3631 SKIP_BLANKS;
3632 val = docbParseAttValue(ctxt);
3633 /******
3634 } else {
3635 * TODO : some attribute must have values, some may not
3636 if ((ctxt->sax != NULL) && (ctxt->sax->error != NULL))
3637 ctxt->sax->warning(ctxt->userData,
3638 "No value for attribute %s\n", name); */
3639 }
3640
3641 *value = val;
3642 return(name);
3643}
3644
3645/**
3646 * docbCheckEncoding:
3647 * @ctxt: an SGML parser context
3648 * @attvalue: the attribute value
3649 *
3650 * Checks an http-equiv attribute from a Meta tag to detect
3651 * the encoding
3652 * If a new encoding is detected the parser is switched to decode
3653 * it and pass UTF8
3654 */
3655static void
3656docbCheckEncoding(docbParserCtxtPtr ctxt, const xmlChar *attvalue) {
3657 const xmlChar *encoding;
3658
3659 if ((ctxt == NULL) || (attvalue == NULL))
3660 return;
3661
3662 encoding = xmlStrstr(attvalue, BAD_CAST"charset=");
3663 if (encoding == NULL)
3664 encoding = xmlStrstr(attvalue, BAD_CAST"Charset=");
3665 if (encoding == NULL)
3666 encoding = xmlStrstr(attvalue, BAD_CAST"CHARSET=");
3667 if (encoding != NULL) {
3668 encoding += 8;
3669 } else {
3670 encoding = xmlStrstr(attvalue, BAD_CAST"charset =");
3671 if (encoding == NULL)
3672 encoding = xmlStrstr(attvalue, BAD_CAST"Charset =");
3673 if (encoding == NULL)
3674 encoding = xmlStrstr(attvalue, BAD_CAST"CHARSET =");
3675 if (encoding != NULL)
3676 encoding += 9;
3677 }
3678 /*
3679 * Restricted from 2.3.5 */
3680 if (encoding != NULL) {
3681 xmlCharEncoding enc;
3682
3683 if (ctxt->input->encoding != NULL)
3684 xmlFree((xmlChar *) ctxt->input->encoding);
3685 ctxt->input->encoding = encoding;
3686
3687 enc = xmlParseCharEncoding((const char *) encoding);
3688 if (enc == XML_CHAR_ENCODING_8859_1) {
3689 ctxt->charset = XML_CHAR_ENCODING_8859_1;
3690 } else if (enc != XML_CHAR_ENCODING_UTF8) {
3691 if ((ctxt->sax != NULL) && (ctxt->sax->error != NULL))
3692 ctxt->sax->error(ctxt->userData,
3693 "Unsupported encoding %s\n", encoding);
3694 /* xmlFree(encoding); */
3695 ctxt->wellFormed = 0;
3696 ctxt->disableSAX = 1;
3697 ctxt->errNo = XML_ERR_UNSUPPORTED_ENCODING;
3698 }
3699 }
3700}
3701
3702/**
3703 * docbCheckMeta:
3704 * @ctxt: an SGML parser context
3705 * @atts: the attributes values
3706 *
3707 * Checks an attributes from a Meta tag
3708 */
3709static void
3710docbCheckMeta(docbParserCtxtPtr ctxt, const xmlChar **atts) {
3711 int i;
3712 const xmlChar *att, *value;
3713 int http = 0;
3714 const xmlChar *content = NULL;
3715
3716 if ((ctxt == NULL) || (atts == NULL))
3717 return;
3718
3719 i = 0;
3720 att = atts[i++];
3721 while (att != NULL) {
3722 value = atts[i++];
3723 if ((value != NULL) &&
3724 ((xmlStrEqual(att, BAD_CAST"http-equiv")) ||
3725 (xmlStrEqual(att, BAD_CAST"Http-Equiv")) ||
3726 (xmlStrEqual(att, BAD_CAST"HTTP-EQUIV"))) &&
3727 ((xmlStrEqual(value, BAD_CAST"Content-Type")) ||
3728 (xmlStrEqual(value, BAD_CAST"content-type")) ||
3729 (xmlStrEqual(value, BAD_CAST"CONTENT-TYPE"))))
3730 http = 1;
3731 else if ((value != NULL) &&
3732 ((xmlStrEqual(att, BAD_CAST"content")) ||
3733 (xmlStrEqual(att, BAD_CAST"Content")) ||
3734 (xmlStrEqual(att, BAD_CAST"CONTENT"))))
3735 content = value;
3736 att = atts[i++];
3737 }
3738 if ((http) && (content != NULL))
3739 docbCheckEncoding(ctxt, content);
3740
3741}
3742
3743/**
3744 * docbParseStartTag:
3745 * @ctxt: an SGML parser context
3746 *
3747 * parse a start of tag either for rule element or
3748 * EmptyElement. In both case we don't parse the tag closing chars.
3749 *
3750 * [40] STag ::= '<' Name (S Attribute)* S? '>'
3751 *
3752 * [44] EmptyElemTag ::= '<' Name (S Attribute)* S? '/>'
3753 *
3754 * With namespace:
3755 *
3756 * [NS 8] STag ::= '<' QName (S Attribute)* S? '>'
3757 *
3758 * [NS 10] EmptyElement ::= '<' QName (S Attribute)* S? '/>'
3759 *
3760 */
3761
3762static void
3763docbParseStartTag(docbParserCtxtPtr ctxt) {
3764 xmlChar *name;
3765 xmlChar *attname;
3766 xmlChar *attvalue;
3767 const xmlChar **atts = NULL;
3768 int nbatts = 0;
3769 int maxatts = 0;
3770 int meta = 0;
3771 int i;
3772
3773 if (CUR != '<') return;
3774 NEXT;
3775
3776 GROW;
3777 name = docbParseSGMLName(ctxt);
3778 if (name == NULL) {
3779 if ((ctxt->sax != NULL) && (ctxt->sax->error != NULL))
3780 ctxt->sax->error(ctxt->userData,
3781 "docbParseStartTag: invalid element name\n");
3782 ctxt->wellFormed = 0;
3783 return;
3784 }
3785 if (xmlStrEqual(name, BAD_CAST"meta"))
3786 meta = 1;
3787
3788 /*
3789 * Check for auto-closure of SGML elements.
3790 */
3791 docbAutoClose(ctxt, name);
3792
3793 /*
3794 * Now parse the attributes, it ends up with the ending
3795 *
3796 * (S Attribute)* S?
3797 */
3798 SKIP_BLANKS;
3799 while ((IS_CHAR(CUR)) &&
3800 (CUR != '>') &&
3801 ((CUR != '/') || (NXT(1) != '>'))) {
3802 long cons = ctxt->nbChars;
3803
3804 GROW;
3805 attname = docbParseAttribute(ctxt, &attvalue);
3806 if (attname != NULL) {
3807
3808 /*
3809 * Well formedness requires at most one declaration of an attribute
3810 */
3811 for (i = 0; i < nbatts;i += 2) {
3812 if (xmlStrEqual(atts[i], attname)) {
3813 if ((ctxt->sax != NULL) && (ctxt->sax->error != NULL))
3814 ctxt->sax->error(ctxt->userData,
3815 "Attribute %s redefined\n",
3816 attname);
3817 ctxt->wellFormed = 0;
3818 xmlFree(attname);
3819 if (attvalue != NULL)
3820 xmlFree(attvalue);
3821 goto failed;
3822 }
3823 }
3824
3825 /*
3826 * Add the pair to atts
3827 */
3828 if (atts == NULL) {
3829 maxatts = 10;
3830 atts = (const xmlChar **) xmlMalloc(maxatts * sizeof(xmlChar *));
3831 if (atts == NULL) {
3832 xmlGenericError(xmlGenericErrorContext,
3833 "malloc of %ld byte failed\n",
3834 maxatts * (long)sizeof(xmlChar *));
3835 if (name != NULL) xmlFree(name);
3836 return;
3837 }
3838 } else if (nbatts + 4 > maxatts) {
3839 maxatts *= 2;
Daniel Veillard50f34372001-08-03 12:06:36 +0000[diff] [blame]3840 atts = (const xmlChar **) xmlRealloc((void *)atts, maxatts * sizeof(xmlChar *));
Daniel Veillardeae522a2001-04-23 13:41:34 +0000[diff] [blame]3841 if (atts == NULL) {
3842 xmlGenericError(xmlGenericErrorContext,
3843 "realloc of %ld byte failed\n",
3844 maxatts * (long)sizeof(xmlChar *));
3845 if (name != NULL) xmlFree(name);
3846 return;
3847 }
3848 }
3849 atts[nbatts++] = attname;
3850 atts[nbatts++] = attvalue;
3851 atts[nbatts] = NULL;
3852 atts[nbatts + 1] = NULL;
3853 }
3854
3855failed:
3856 SKIP_BLANKS;
3857 if (cons == ctxt->nbChars) {
3858 if ((ctxt->sax != NULL) && (ctxt->sax->error != NULL))
3859 ctxt->sax->error(ctxt->userData,
3860 "docbParseStartTag: problem parsing attributes\n");
3861 ctxt->wellFormed = 0;
3862 break;
3863 }
3864 }
3865
3866 /*
3867 * Handle specific association to the META tag
3868 */
3869 if (meta)
3870 docbCheckMeta(ctxt, atts);
3871
3872 /*
3873 * SAX: Start of Element !
3874 */
3875 docbnamePush(ctxt, xmlStrdup(name));
3876#ifdef DEBUG
3877 xmlGenericError(xmlGenericErrorContext,"Start of element %s: pushed %s\n", name, ctxt->name);
3878#endif
3879 if ((ctxt->sax != NULL) && (ctxt->sax->startElement != NULL))
3880 ctxt->sax->startElement(ctxt->userData, name, atts);
3881
3882 if (atts != NULL) {
3883 for (i = 0;i < nbatts;i++) {
3884 if (atts[i] != NULL)
3885 xmlFree((xmlChar *) atts[i]);
3886 }
3887 xmlFree((void *) atts);
3888 }
3889 if (name != NULL) xmlFree(name);
3890}
3891
3892/**
3893 * docbParseEndTag:
3894 * @ctxt: an SGML parser context
3895 *
3896 * parse an end of tag
3897 *
3898 * [42] ETag ::= '</' Name S? '>'
3899 *
3900 * With namespace
3901 *
3902 * [NS 9] ETag ::= '</' QName S? '>'
3903 */
3904
3905static void
3906docbParseEndTag(docbParserCtxtPtr ctxt) {
3907 xmlChar *name;
3908 xmlChar *oldname;
3909 int i;
3910
3911 if ((CUR != '<') || (NXT(1) != '/')) {
3912 if ((ctxt->sax != NULL) && (ctxt->sax->error != NULL))
3913 ctxt->sax->error(ctxt->userData, "docbParseEndTag: '</' not found\n");
3914 ctxt->wellFormed = 0;
3915 return;
3916 }
3917 SKIP(2);
3918
3919 name = docbParseSGMLName(ctxt);
3920 if (name == NULL) {
3921 if (CUR == '>') {
3922 NEXT;
3923 oldname = docbnamePop(ctxt);
3924 if (oldname != NULL) {
3925 if ((ctxt->sax != NULL) && (ctxt->sax->endElement != NULL))
3926 ctxt->sax->endElement(ctxt->userData, name);
3927#ifdef DEBUG
3928 xmlGenericError(xmlGenericErrorContext,"End of tag </>: popping out %s\n", oldname);
3929#endif
3930 xmlFree(oldname);
3931#ifdef DEBUG
3932 } else {
3933 xmlGenericError(xmlGenericErrorContext,"End of tag </>: stack empty !!!\n");
3934#endif
3935 }
3936 return;
3937 } else
3938 return;
3939 }
3940
3941 /*
3942 * We should definitely be at the ending "S? '>'" part
3943 */
3944 SKIP_BLANKS;
3945 if ((!IS_CHAR(CUR)) || (CUR != '>')) {
3946 if ((ctxt->sax != NULL) && (ctxt->sax->error != NULL))
3947 ctxt->sax->error(ctxt->userData, "End tag : expected '>'\n");
3948 ctxt->wellFormed = 0;
3949 } else
3950 NEXT;
3951
3952 /*
3953 * If the name read is not one of the element in the parsing stack
3954 * then return, it's just an error.
3955 */
3956 for (i = (ctxt->nameNr - 1);i >= 0;i--) {
3957 if (xmlStrEqual(name, ctxt->nameTab[i])) break;
3958 }
3959 if (i < 0) {
3960 if ((ctxt->sax != NULL) && (ctxt->sax->error != NULL))
3961 ctxt->sax->error(ctxt->userData,
3962 "Unexpected end tag : %s\n", name);
3963 xmlFree(name);
3964 ctxt->wellFormed = 0;
3965 return;
3966 }
3967
3968
3969 /*
3970 * Check for auto-closure of SGML elements.
3971 */
3972
3973 docbAutoCloseOnClose(ctxt, name);
3974
3975 /*
3976 * Well formedness constraints, opening and closing must match.
3977 * With the exception that the autoclose may have popped stuff out
3978 * of the stack.
3979 */
3980 if (((name[0] != '/') || (name[1] != 0)) &&
3981 (!xmlStrEqual(name, ctxt->name))) {
3982#ifdef DEBUG
3983 xmlGenericError(xmlGenericErrorContext,"End of tag %s: expecting %s\n", name, ctxt->name);
3984#endif
3985 if ((ctxt->name != NULL) &&
3986 (!xmlStrEqual(ctxt->name, name))) {
3987 if ((ctxt->sax != NULL) && (ctxt->sax->error != NULL))
3988 ctxt->sax->error(ctxt->userData,
3989 "Opening and ending tag mismatch: %s and %s\n",
3990 name, ctxt->name);
3991 ctxt->wellFormed = 0;
3992 }
3993 }
3994
3995 /*
3996 * SAX: End of Tag
3997 */
3998 oldname = ctxt->name;
3999 if (((name[0] == '/') && (name[1] == 0)) ||
4000 ((oldname != NULL) && (xmlStrEqual(oldname, name)))) {
4001 if ((ctxt->sax != NULL) && (ctxt->sax->endElement != NULL))
4002 ctxt->sax->endElement(ctxt->userData, name);
4003 oldname = docbnamePop(ctxt);
4004 if (oldname != NULL) {
4005#ifdef DEBUG
4006 xmlGenericError(xmlGenericErrorContext,"End of tag %s: popping out %s\n", name, oldname);
4007#endif
4008 xmlFree(oldname);
4009#ifdef DEBUG
4010 } else {
4011 xmlGenericError(xmlGenericErrorContext,"End of tag %s: stack empty !!!\n", name);
4012#endif
4013 }
4014 }
4015
4016 if (name != NULL)
4017 xmlFree(name);
4018
4019 return;
4020}
4021
4022
4023/**
4024 * docbParseReference:
4025 * @ctxt: an SGML parser context
4026 *
4027 * parse and handle entity references in content,
4028 * this will end-up in a call to character() since this is either a
4029 * CharRef, or a predefined entity.
4030 */
4031static void
4032docbParseReference(docbParserCtxtPtr ctxt) {
4033 docbEntityDescPtr ent;
Daniel Veillard61b33d52001-04-24 13:55:12 +0000[diff] [blame]4034 xmlEntityPtr xent;
Daniel Veillardeae522a2001-04-23 13:41:34 +0000[diff] [blame]4035 xmlChar out[6];
4036 xmlChar *name;
4037 if (CUR != '&') return;
4038
4039 if (NXT(1) == '#') {
4040 unsigned int c;
4041 int bits, i = 0;
4042
4043 c = docbParseCharRef(ctxt);
4044 if (c < 0x80) { out[i++]= c; bits= -6; }
4045 else if (c < 0x800) { out[i++]=((c >> 6) & 0x1F) | 0xC0; bits= 0; }
4046 else if (c < 0x10000) { out[i++]=((c >> 12) & 0x0F) | 0xE0; bits= 6; }
4047 else { out[i++]=((c >> 18) & 0x07) | 0xF0; bits= 12; }
4048
4049 for ( ; bits >= 0; bits-= 6) {
4050 out[i++]= ((c >> bits) & 0x3F) | 0x80;
4051 }
4052 out[i] = 0;
4053
4054 docbCheckParagraph(ctxt);
4055 if ((ctxt->sax != NULL) && (ctxt->sax->characters != NULL))
4056 ctxt->sax->characters(ctxt->userData, out, i);
4057 } else {
Daniel Veillard61b33d52001-04-24 13:55:12 +0000[diff] [blame]4058 /*
4059 * Lookup the entity in the table.
4060 */
4061 xent = docbParseEntityRef(ctxt, &name);
4062 if (xent != NULL) {
Daniel Veillard1034da22001-04-25 19:06:28 +0000[diff] [blame]4063 if (((ctxt->replaceEntities) || (ctxt->loadsubset)) &&
4064 ((xent->children == NULL) &&
4065 (xent->etype == XML_EXTERNAL_GENERAL_PARSED_ENTITY))) {
Daniel Veillard61b33d52001-04-24 13:55:12 +0000[diff] [blame]4066 /*
4067 * we really need to fetch and parse the external entity
4068 */
4069 int parse;
4070 xmlNodePtr children = NULL;
4071
4072 parse = docbParseCtxtExternalEntity(ctxt,
4073 xent->SystemID, xent->ExternalID, &children);
4074 xmlAddChildList((xmlNodePtr) xent, children);
Daniel Veillard1034da22001-04-25 19:06:28 +0000[diff] [blame]4075 }
4076 if (ctxt->replaceEntities) {
Daniel Veillard61b33d52001-04-24 13:55:12 +0000[diff] [blame]4077 if ((ctxt->node != NULL) && (xent->children != NULL)) {
4078 /*
4079 * Seems we are generating the DOM content, do
4080 * a simple tree copy
4081 */
4082 xmlNodePtr new;
4083 new = xmlCopyNodeList(xent->children);
4084
4085 xmlAddChildList(ctxt->node, new);
4086 /*
4087 * This is to avoid a nasty side effect, see
4088 * characters() in SAX.c
4089 */
4090 ctxt->nodemem = 0;
4091 ctxt->nodelen = 0;
4092 }
Daniel Veillard1034da22001-04-25 19:06:28 +0000[diff] [blame]4093 } else {
4094 if ((ctxt->sax != NULL) && (ctxt->sax->reference != NULL) &&
4095 (ctxt->replaceEntities == 0) && (!ctxt->disableSAX)) {
4096 /*
4097 * Create a node.
4098 */
4099 ctxt->sax->reference(ctxt->userData, xent->name);
4100 }
Daniel Veillard61b33d52001-04-24 13:55:12 +0000[diff] [blame]4101 }
4102 } else if (name != NULL) {
4103 ent = docbEntityLookup(name);
4104 if ((ent == NULL) || (ent->value <= 0)) {
4105 docbCheckParagraph(ctxt);
4106 if ((ctxt->sax != NULL) && (ctxt->sax->characters != NULL)) {
4107 ctxt->sax->characters(ctxt->userData, BAD_CAST "&", 1);
4108 ctxt->sax->characters(ctxt->userData, name, xmlStrlen(name));
4109 /* ctxt->sax->characters(ctxt->userData, BAD_CAST ";", 1); */
4110 }
4111 } else {
4112 unsigned int c;
4113 int bits, i = 0;
4114
4115 c = ent->value;
4116 if (c < 0x80)
4117 { out[i++]= c; bits= -6; }
4118 else if (c < 0x800)
4119 { out[i++]=((c >> 6) & 0x1F) | 0xC0; bits= 0; }
4120 else if (c < 0x10000)
4121 { out[i++]=((c >> 12) & 0x0F) | 0xE0; bits= 6; }
4122 else
4123 { out[i++]=((c >> 18) & 0x07) | 0xF0; bits= 12; }
4124
4125 for ( ; bits >= 0; bits-= 6) {
4126 out[i++]= ((c >> bits) & 0x3F) | 0x80;
4127 }
4128 out[i] = 0;
4129
4130 docbCheckParagraph(ctxt);
4131 if ((ctxt->sax != NULL) && (ctxt->sax->characters != NULL))
4132 ctxt->sax->characters(ctxt->userData, out, i);
4133 }
4134 } else {
Daniel Veillardeae522a2001-04-23 13:41:34 +0000[diff] [blame]4135 docbCheckParagraph(ctxt);
4136 if ((ctxt->sax != NULL) && (ctxt->sax->characters != NULL))
4137 ctxt->sax->characters(ctxt->userData, BAD_CAST "&", 1);
4138 return;
4139 }
Daniel Veillard61b33d52001-04-24 13:55:12 +0000[diff] [blame]4140 if (name != NULL)
4141 xmlFree(name);
Daniel Veillardeae522a2001-04-23 13:41:34 +0000[diff] [blame]4142 }
4143}
4144
4145/**
4146 * docbParseContent:
4147 * @ctxt: an SGML parser context
4148 * @name: the node name
4149 *
4150 * Parse a content: comment, sub-element, reference or text.
4151 *
4152 */
Daniel Veillardeae522a2001-04-23 13:41:34 +0000[diff] [blame]4153static void
Daniel Veillard84666b32001-06-11 17:31:08 +0000[diff] [blame]4154docbParseContent(docbParserCtxtPtr ctxt)
4155{
Daniel Veillardeae522a2001-04-23 13:41:34 +0000[diff] [blame]4156 xmlChar *currentNode;
4157 int depth;
4158
4159 currentNode = xmlStrdup(ctxt->name);
4160 depth = ctxt->nameNr;
4161 while (1) {
Daniel Veillard84666b32001-06-11 17:31:08 +0000[diff] [blame]4162 long cons = ctxt->nbChars;
Daniel Veillardeae522a2001-04-23 13:41:34 +0000[diff] [blame]4163
4164 GROW;
Daniel Veillard84666b32001-06-11 17:31:08 +0000[diff] [blame]4165 /*
4166 * Our tag or one of it's parent or children is ending.
4167 */
Daniel Veillardeae522a2001-04-23 13:41:34 +0000[diff] [blame]4168 if ((CUR == '<') && (NXT(1) == '/')) {
Daniel Veillard84666b32001-06-11 17:31:08 +0000[diff] [blame]4169 docbParseEndTag(ctxt);
4170 if (currentNode != NULL)
4171 xmlFree(currentNode);
4172 return;
Daniel Veillardeae522a2001-04-23 13:41:34 +0000[diff] [blame]4173 }
4174
Daniel Veillard84666b32001-06-11 17:31:08 +0000[diff] [blame]4175 /*
4176 * Has this node been popped out during parsing of
4177 * the next element
4178 */
Daniel Veillardeae522a2001-04-23 13:41:34 +0000[diff] [blame]4179 if ((!xmlStrEqual(currentNode, ctxt->name)) &&
Daniel Veillard84666b32001-06-11 17:31:08 +0000[diff] [blame]4180 (depth >= ctxt->nameNr)) {
4181 if (currentNode != NULL)
4182 xmlFree(currentNode);
4183 return;
4184 }
Daniel Veillardeae522a2001-04-23 13:41:34 +0000[diff] [blame]4185
Daniel Veillard84666b32001-06-11 17:31:08 +0000[diff] [blame]4186 /*
4187 * Sometimes DOCTYPE arrives in the middle of the document
4188 */
4189 if ((CUR == '<') && (NXT(1) == '!') &&
4190 (UPP(2) == 'D') && (UPP(3) == 'O') &&
4191 (UPP(4) == 'C') && (UPP(5) == 'T') &&
4192 (UPP(6) == 'Y') && (UPP(7) == 'P') && (UPP(8) == 'E')) {
4193 if ((ctxt->sax != NULL) && (ctxt->sax->error != NULL))
4194 ctxt->sax->error(ctxt->userData,
4195 "Misplaced DOCTYPE declaration\n");
4196 ctxt->wellFormed = 0;
4197 docbParseDocTypeDecl(ctxt);
4198 }
Daniel Veillardeae522a2001-04-23 13:41:34 +0000[diff] [blame]4199
Daniel Veillard84666b32001-06-11 17:31:08 +0000[diff] [blame]4200 /*
4201 * First case : a comment
4202 */
4203 if ((CUR == '<') && (NXT(1) == '!') &&
4204 (NXT(2) == '-') && (NXT(3) == '-')) {
4205 docbParseComment(ctxt);
4206 }
4207
4208 /*
4209 * Second case : a PI
4210 */
4211 else if ((RAW == '<') && (NXT(1) == '?')) {
4212 docbParsePI(ctxt);
4213 }
Daniel Veillardeae522a2001-04-23 13:41:34 +0000[diff] [blame]4214
Daniel Veillard84666b32001-06-11 17:31:08 +0000[diff] [blame]4215 /*
4216 * Third case : a sub-element.
4217 */
4218 else if (CUR == '<') {
4219 docbParseElement(ctxt);
4220 }
Daniel Veillardeae522a2001-04-23 13:41:34 +0000[diff] [blame]4221
Daniel Veillard84666b32001-06-11 17:31:08 +0000[diff] [blame]4222 /*
4223 * Fourth case : a reference. If if has not been resolved,
4224 * parsing returns it's Name, create the node
4225 */
4226 else if (CUR == '&') {
4227 docbParseReference(ctxt);
4228 }
Daniel Veillardeae522a2001-04-23 13:41:34 +0000[diff] [blame]4229
Daniel Veillard84666b32001-06-11 17:31:08 +0000[diff] [blame]4230 /*
4231 * Fifth : end of the resource
4232 */
4233 else if (CUR == 0) {
4234 docbAutoClose(ctxt, NULL);
4235 if (ctxt->nameNr == 0)
4236 break;
4237 }
Daniel Veillardeae522a2001-04-23 13:41:34 +0000[diff] [blame]4238
Daniel Veillard84666b32001-06-11 17:31:08 +0000[diff] [blame]4239 /*
4240 * Last case, text. Note that References are handled directly.
4241 */
4242 else {
4243 docbParseCharData(ctxt);
4244 }
Daniel Veillardeae522a2001-04-23 13:41:34 +0000[diff] [blame]4245
Daniel Veillard84666b32001-06-11 17:31:08 +0000[diff] [blame]4246 if (cons == ctxt->nbChars) {
4247 if (ctxt->node != NULL) {
4248 if ((ctxt->sax != NULL) && (ctxt->sax->error != NULL))
4249 ctxt->sax->error(ctxt->userData,
4250 "detected an error in element content\n");
4251 ctxt->wellFormed = 0;
4252 }
4253 break;
4254 }
Daniel Veillardeae522a2001-04-23 13:41:34 +0000[diff] [blame]4255
4256 GROW;
4257 }
Daniel Veillard84666b32001-06-11 17:31:08 +0000[diff] [blame]4258 if (currentNode != NULL)
4259 xmlFree(currentNode);
Daniel Veillardeae522a2001-04-23 13:41:34 +0000[diff] [blame]4260}
4261
4262/**
4263 * docbParseElement:
4264 * @ctxt: an SGML parser context
4265 *
4266 * parse an SGML element, this is highly recursive
4267 *
4268 * [39] element ::= EmptyElemTag | STag content ETag
4269 *
4270 * [41] Attribute ::= Name Eq AttValue
4271 */
4272
4273static void
4274docbParseElement(docbParserCtxtPtr ctxt) {
4275 xmlChar *name;
4276 xmlChar *currentNode = NULL;
4277 docbElemDescPtr info;
4278 docbParserNodeInfo node_info;
4279 xmlChar *oldname;
4280 int depth = ctxt->nameNr;
4281
4282 /* Capture start position */
4283 if (ctxt->record_info) {
4284 node_info.begin_pos = ctxt->input->consumed +
4285 (CUR_PTR - ctxt->input->base);
4286 node_info.begin_line = ctxt->input->line;
4287 }
4288
4289 oldname = xmlStrdup(ctxt->name);
4290 docbParseStartTag(ctxt);
4291 name = ctxt->name;
4292#ifdef DEBUG
4293 if (oldname == NULL)
4294 xmlGenericError(xmlGenericErrorContext,
4295 "Start of element %s\n", name);
4296 else if (name == NULL)
4297 xmlGenericError(xmlGenericErrorContext,
4298 "Start of element failed, was %s\n", oldname);
4299 else
4300 xmlGenericError(xmlGenericErrorContext,
4301 "Start of element %s, was %s\n", name, oldname);
4302#endif
4303 if (((depth == ctxt->nameNr) && (xmlStrEqual(oldname, ctxt->name))) ||
4304 (name == NULL)) {
4305 if (CUR == '>')
4306 NEXT;
4307 if (oldname != NULL)
4308 xmlFree(oldname);
4309 return;
4310 }
4311 if (oldname != NULL)
4312 xmlFree(oldname);
4313
4314 /*
4315 * Lookup the info for that element.
4316 */
4317 info = docbTagLookup(name);
4318 if (info == NULL) {
4319 if ((ctxt->sax != NULL) && (ctxt->sax->error != NULL))
4320 ctxt->sax->error(ctxt->userData, "Tag %s unknown\n",
4321 name);
4322 ctxt->wellFormed = 0;
4323 } else if (info->depr) {
4324/***************************
4325 if ((ctxt->sax != NULL) && (ctxt->sax->warning != NULL))
4326 ctxt->sax->warning(ctxt->userData, "Tag %s is deprecated\n",
4327 name);
4328 ***************************/
4329 }
4330
4331 /*
Daniel Veillardcbaf3992001-12-31 16:16:02 +0000[diff] [blame^]4332 * Check for an Empty Element labeled the XML/SGML way
Daniel Veillardeae522a2001-04-23 13:41:34 +0000[diff] [blame]4333 */
4334 if ((CUR == '/') && (NXT(1) == '>')) {
4335 SKIP(2);
4336 if ((ctxt->sax != NULL) && (ctxt->sax->endElement != NULL))
4337 ctxt->sax->endElement(ctxt->userData, name);
4338 oldname = docbnamePop(ctxt);
4339#ifdef DEBUG
4340 xmlGenericError(xmlGenericErrorContext,"End of tag the XML way: popping out %s\n", oldname);
4341#endif
4342 if (oldname != NULL)
4343 xmlFree(oldname);
4344 return;
4345 }
4346
4347 if (CUR == '>') {
4348 NEXT;
4349 } else {
4350 if ((ctxt->sax != NULL) && (ctxt->sax->error != NULL))
4351 ctxt->sax->error(ctxt->userData,
4352 "Couldn't find end of Start Tag %s\n",
4353 name);
4354 ctxt->wellFormed = 0;
4355
4356 /*
4357 * end of parsing of this node.
4358 */
4359 if (xmlStrEqual(name, ctxt->name)) {
4360 nodePop(ctxt);
4361 oldname = docbnamePop(ctxt);
4362#ifdef DEBUG
4363 xmlGenericError(xmlGenericErrorContext,"End of start tag problem: popping out %s\n", oldname);
4364#endif
4365 if (oldname != NULL)
4366 xmlFree(oldname);
4367 }
4368
4369 /*
4370 * Capture end position and add node
4371 */
4372 if ( currentNode != NULL && ctxt->record_info ) {
4373 node_info.end_pos = ctxt->input->consumed +
4374 (CUR_PTR - ctxt->input->base);
4375 node_info.end_line = ctxt->input->line;
4376 node_info.node = ctxt->node;
4377 xmlParserAddNodeInfo(ctxt, &node_info);
4378 }
4379 return;
4380 }
4381
4382 /*
4383 * Check for an Empty Element from DTD definition
4384 */
4385 if ((info != NULL) && (info->empty)) {
4386 if ((ctxt->sax != NULL) && (ctxt->sax->endElement != NULL))
4387 ctxt->sax->endElement(ctxt->userData, name);
4388 oldname = docbnamePop(ctxt);
4389#ifdef DEBUG
4390 xmlGenericError(xmlGenericErrorContext,"End of empty tag %s : popping out %s\n", name, oldname);
4391#endif
4392 if (oldname != NULL)
4393 xmlFree(oldname);
4394 return;
4395 }
4396
4397 /*
4398 * Parse the content of the element:
4399 */
4400 currentNode = xmlStrdup(ctxt->name);
4401 depth = ctxt->nameNr;
4402 while (IS_CHAR(CUR)) {
4403 docbParseContent(ctxt);
4404 if (ctxt->nameNr < depth) break;
4405 }
4406
4407 if (!IS_CHAR(CUR)) {
4408 /************
4409 if ((ctxt->sax != NULL) && (ctxt->sax->error != NULL))
4410 ctxt->sax->error(ctxt->userData,
4411 "Premature end of data in tag %s\n", currentNode);
4412 ctxt->wellFormed = 0;
4413 *************/
4414
4415 /*
4416 * end of parsing of this node.
4417 */
4418 nodePop(ctxt);
4419 oldname = docbnamePop(ctxt);
4420#ifdef DEBUG
4421 xmlGenericError(xmlGenericErrorContext,"Premature end of tag %s : popping out %s\n", name, oldname);
4422#endif
4423 if (oldname != NULL)
4424 xmlFree(oldname);
4425 if (currentNode != NULL)
4426 xmlFree(currentNode);
4427 return;
4428 }
4429
4430 /*
4431 * Capture end position and add node
4432 */
4433 if ( currentNode != NULL && ctxt->record_info ) {
4434 node_info.end_pos = ctxt->input->consumed +
4435 (CUR_PTR - ctxt->input->base);
4436 node_info.end_line = ctxt->input->line;
4437 node_info.node = ctxt->node;
4438 xmlParserAddNodeInfo(ctxt, &node_info);
4439 }
4440 if (currentNode != NULL)
4441 xmlFree(currentNode);
4442}
4443
4444/**
4445 * docbParseEntityDecl:
4446 * @ctxt: an SGML parser context
4447 *
4448 * parse <!ENTITY declarations
4449 *
4450 */
4451
4452static void
4453docbParseEntityDecl(xmlParserCtxtPtr ctxt) {
4454 xmlChar *name = NULL;
4455 xmlChar *value = NULL;
4456 xmlChar *URI = NULL, *literal = NULL;
4457 xmlChar *ndata = NULL;
4458 int isParameter = 0;
4459 xmlChar *orig = NULL;
4460
4461 GROW;
4462 if ((RAW == '<') && (NXT(1) == '!') &&
Daniel Veillard61b33d52001-04-24 13:55:12 +0000[diff] [blame]4463 (UPP(2) == 'E') && (UPP(3) == 'N') &&
4464 (UPP(4) == 'T') && (UPP(5) == 'I') &&
4465 (UPP(6) == 'T') && (UPP(7) == 'Y')) {
Daniel Veillardeae522a2001-04-23 13:41:34 +0000[diff] [blame]4466 xmlParserInputPtr input = ctxt->input;
4467 ctxt->instate = XML_PARSER_ENTITY_DECL;
4468 SHRINK;
4469 SKIP(8);
4470 if (!IS_BLANK(CUR)) {
4471 ctxt->errNo = XML_ERR_SPACE_REQUIRED;
4472 if ((ctxt->sax != NULL) && (ctxt->sax->error != NULL))
4473 ctxt->sax->error(ctxt->userData,
4474 "Space required after '<!ENTITY'\n");
4475 ctxt->wellFormed = 0;
4476 ctxt->disableSAX = 1;
4477 }
4478 SKIP_BLANKS;
4479
4480 if (RAW == '%') {
4481 NEXT;
4482 if (!IS_BLANK(CUR)) {
4483 ctxt->errNo = XML_ERR_SPACE_REQUIRED;
4484 if ((ctxt->sax != NULL) && (ctxt->sax->error != NULL))
4485 ctxt->sax->error(ctxt->userData,
4486 "Space required after '%'\n");
4487 ctxt->wellFormed = 0;
4488 ctxt->disableSAX = 1;
4489 }
4490 SKIP_BLANKS;
4491 isParameter = 1;
4492 }
4493
4494 name = xmlParseName(ctxt);
4495 if (name == NULL) {
4496 ctxt->errNo = XML_ERR_NAME_REQUIRED;
4497 if ((ctxt->sax != NULL) && (ctxt->sax->error != NULL))
4498 ctxt->sax->error(ctxt->userData, "sgmlarseEntityDecl: no name\n");
4499 ctxt->wellFormed = 0;
4500 ctxt->disableSAX = 1;
4501 return;
4502 }
4503 if (!IS_BLANK(CUR)) {
4504 ctxt->errNo = XML_ERR_SPACE_REQUIRED;
4505 if ((ctxt->sax != NULL) && (ctxt->sax->error != NULL))
4506 ctxt->sax->error(ctxt->userData,
4507 "Space required after the entity name\n");
4508 ctxt->wellFormed = 0;
4509 ctxt->disableSAX = 1;
4510 }
4511 SKIP_BLANKS;
4512
4513 /*
4514 * handle the various case of definitions...
4515 */
4516 if (isParameter) {
4517 if ((RAW == '"') || (RAW == '\'')) {
4518 value = xmlParseEntityValue(ctxt, &orig);
4519 if (value) {
4520 if ((ctxt->sax != NULL) &&
4521 (!ctxt->disableSAX) && (ctxt->sax->entityDecl != NULL))
4522 ctxt->sax->entityDecl(ctxt->userData, name,
4523 XML_INTERNAL_PARAMETER_ENTITY,
4524 NULL, NULL, value);
4525 }
4526 } else {
4527 URI = xmlParseExternalID(ctxt, &literal, 1);
4528 if ((URI == NULL) && (literal == NULL)) {
4529 ctxt->errNo = XML_ERR_VALUE_REQUIRED;
4530 if ((ctxt->sax != NULL) && (ctxt->sax->error != NULL))
4531 ctxt->sax->error(ctxt->userData,
4532 "Entity value required\n");
4533 ctxt->wellFormed = 0;
4534 ctxt->disableSAX = 1;
4535 }
4536 if (URI) {
4537 xmlURIPtr uri;
4538
4539 uri = xmlParseURI((const char *) URI);
4540 if (uri == NULL) {
4541 ctxt->errNo = XML_ERR_INVALID_URI;
4542 if ((ctxt->sax != NULL) &&
4543 (!ctxt->disableSAX) &&
4544 (ctxt->sax->error != NULL))
4545 ctxt->sax->error(ctxt->userData,
4546 "Invalid URI: %s\n", URI);
4547 ctxt->wellFormed = 0;
4548 } else {
4549 if (uri->fragment != NULL) {
4550 ctxt->errNo = XML_ERR_URI_FRAGMENT;
4551 if ((ctxt->sax != NULL) &&
4552 (!ctxt->disableSAX) &&
4553 (ctxt->sax->error != NULL))
4554 ctxt->sax->error(ctxt->userData,
4555 "Fragment not allowed: %s\n", URI);
4556 ctxt->wellFormed = 0;
4557 } else {
4558 if ((ctxt->sax != NULL) &&
4559 (!ctxt->disableSAX) &&
4560 (ctxt->sax->entityDecl != NULL))
4561 ctxt->sax->entityDecl(ctxt->userData, name,
4562 XML_EXTERNAL_PARAMETER_ENTITY,
4563 literal, URI, NULL);
4564 }
4565 xmlFreeURI(uri);
4566 }
4567 }
4568 }
4569 } else {
4570 if ((RAW == '"') || (RAW == '\'')) {
4571 value = xmlParseEntityValue(ctxt, &orig);
4572 if ((ctxt->sax != NULL) &&
4573 (!ctxt->disableSAX) && (ctxt->sax->entityDecl != NULL))
4574 ctxt->sax->entityDecl(ctxt->userData, name,
4575 XML_INTERNAL_GENERAL_ENTITY,
4576 NULL, NULL, value);
4577 } else {
4578 URI = xmlParseExternalID(ctxt, &literal, 1);
4579 if ((URI == NULL) && (literal == NULL)) {
4580 ctxt->errNo = XML_ERR_VALUE_REQUIRED;
4581 if ((ctxt->sax != NULL) && (ctxt->sax->error != NULL))
4582 ctxt->sax->error(ctxt->userData,
4583 "Entity value required\n");
4584 ctxt->wellFormed = 0;
4585 ctxt->disableSAX = 1;
4586 }
4587 if (URI) {
4588 xmlURIPtr uri;
4589
4590 uri = xmlParseURI((const char *)URI);
4591 if (uri == NULL) {
4592 ctxt->errNo = XML_ERR_INVALID_URI;
4593 if ((ctxt->sax != NULL) &&
4594 (!ctxt->disableSAX) &&
4595 (ctxt->sax->error != NULL))
4596 ctxt->sax->error(ctxt->userData,
4597 "Invalid URI: %s\n", URI);
4598 ctxt->wellFormed = 0;
4599 } else {
4600 if (uri->fragment != NULL) {
4601 ctxt->errNo = XML_ERR_URI_FRAGMENT;
4602 if ((ctxt->sax != NULL) &&
4603 (!ctxt->disableSAX) &&
4604 (ctxt->sax->error != NULL))
4605 ctxt->sax->error(ctxt->userData,
4606 "Fragment not allowed: %s\n", URI);
4607 ctxt->wellFormed = 0;
4608 }
4609 xmlFreeURI(uri);
4610 }
4611 }
4612 if ((RAW != '>') && (!IS_BLANK(CUR))) {
4613 ctxt->errNo = XML_ERR_SPACE_REQUIRED;
4614 if ((ctxt->sax != NULL) && (ctxt->sax->error != NULL))
4615 ctxt->sax->error(ctxt->userData,
4616 "Space required before content model\n");
4617 ctxt->wellFormed = 0;
4618 ctxt->disableSAX = 1;
4619 }
4620 SKIP_BLANKS;
4621
4622 /*
4623 * SGML specific: here we can get the content model
4624 */
4625 if (RAW != '>') {
4626 xmlChar *contmod;
4627
4628 contmod = xmlParseName(ctxt);
4629
4630 if (contmod == NULL) {
4631 ctxt->errNo = XML_ERR_SPACE_REQUIRED;
4632 if ((ctxt->sax != NULL) && (ctxt->sax->error != NULL))
4633 ctxt->sax->error(ctxt->userData,
4634 "Could not parse entity content model\n");
4635 ctxt->wellFormed = 0;
4636 ctxt->disableSAX = 1;
4637 } else {
4638 if (xmlStrEqual(contmod, BAD_CAST"NDATA")) {
4639 if (!IS_BLANK(CUR)) {
4640 ctxt->errNo = XML_ERR_SPACE_REQUIRED;
4641 if ((ctxt->sax != NULL) &&
4642 (ctxt->sax->error != NULL))
4643 ctxt->sax->error(ctxt->userData,
4644 "Space required after 'NDATA'\n");
4645 ctxt->wellFormed = 0;
4646 ctxt->disableSAX = 1;
4647 }
4648 SKIP_BLANKS;
4649 ndata = xmlParseName(ctxt);
4650 if ((ctxt->sax != NULL) && (!ctxt->disableSAX) &&
4651 (ctxt->sax->unparsedEntityDecl != NULL)) {
4652 ctxt->sax->unparsedEntityDecl(ctxt->userData,
4653 name, literal, URI, ndata);
4654 }
4655 } else if (xmlStrEqual(contmod, BAD_CAST"SUBDOC")) {
4656 if ((ctxt->sax != NULL) &&
4657 (ctxt->sax->warning != NULL))
4658 ctxt->sax->warning(ctxt->userData,
4659 "SUBDOC entities are not supported\n");
4660 SKIP_BLANKS;
4661 ndata = xmlParseName(ctxt);
4662 if ((ctxt->sax != NULL) && (!ctxt->disableSAX) &&
4663 (ctxt->sax->unparsedEntityDecl != NULL)) {
4664 ctxt->sax->unparsedEntityDecl(ctxt->userData,
4665 name, literal, URI, ndata);
4666 }
4667 } else if (xmlStrEqual(contmod, BAD_CAST"CDATA")) {
4668 if ((ctxt->sax != NULL) &&
4669 (ctxt->sax->warning != NULL))
4670 ctxt->sax->warning(ctxt->userData,
4671 "CDATA entities are not supported\n");
4672 SKIP_BLANKS;
4673 ndata = xmlParseName(ctxt);
4674 if ((ctxt->sax != NULL) && (!ctxt->disableSAX) &&
4675 (ctxt->sax->unparsedEntityDecl != NULL)) {
4676 ctxt->sax->unparsedEntityDecl(ctxt->userData,
4677 name, literal, URI, ndata);
4678 }
4679 }
4680 xmlFree(contmod);
4681 }
4682 } else {
4683 if ((ctxt->sax != NULL) &&
4684 (!ctxt->disableSAX) && (ctxt->sax->entityDecl != NULL))
4685 ctxt->sax->entityDecl(ctxt->userData, name,
4686 XML_EXTERNAL_GENERAL_PARSED_ENTITY,
4687 literal, URI, NULL);
4688 }
4689 }
4690 }
4691 SKIP_BLANKS;
4692 if (RAW != '>') {
4693 ctxt->errNo = XML_ERR_ENTITY_NOT_FINISHED;
4694 if ((ctxt->sax != NULL) && (ctxt->sax->error != NULL))
4695 ctxt->sax->error(ctxt->userData,
4696 "docbParseEntityDecl: entity %s not terminated\n", name);
4697 ctxt->wellFormed = 0;
4698 ctxt->disableSAX = 1;
4699 } else {
4700 if (input != ctxt->input) {
4701 ctxt->errNo = XML_ERR_ENTITY_BOUNDARY;
4702 if ((ctxt->sax != NULL) && (ctxt->sax->error != NULL))
4703 ctxt->sax->error(ctxt->userData,
4704"Entity declaration doesn't start and stop in the same entity\n");
4705 ctxt->wellFormed = 0;
4706 ctxt->disableSAX = 1;
4707 }
4708 NEXT;
4709 }
4710 if (orig != NULL) {
4711 /*
4712 * Ugly mechanism to save the raw entity value.
4713 */
4714 xmlEntityPtr cur = NULL;
4715
4716 if (isParameter) {
4717 if ((ctxt->sax != NULL) &&
4718 (ctxt->sax->getParameterEntity != NULL))
4719 cur = ctxt->sax->getParameterEntity(ctxt->userData, name);
4720 } else {
4721 if ((ctxt->sax != NULL) &&
4722 (ctxt->sax->getEntity != NULL))
4723 cur = ctxt->sax->getEntity(ctxt->userData, name);
4724 }
4725 if (cur != NULL) {
4726 if (cur->orig != NULL)
4727 xmlFree(orig);
4728 else
4729 cur->orig = orig;
4730 } else
4731 xmlFree(orig);
4732 }
4733 if (name != NULL) xmlFree(name);
4734 if (value != NULL) xmlFree(value);
4735 if (URI != NULL) xmlFree(URI);
4736 if (literal != NULL) xmlFree(literal);
4737 if (ndata != NULL) xmlFree(ndata);
4738 }
4739}
4740
4741/**
4742 * docbParseMarkupDecl:
4743 * @ctxt: an SGML parser context
4744 *
4745 * parse Markup declarations
4746 *
4747 * [29] markupdecl ::= elementdecl | AttlistDecl | EntityDecl |
4748 * NotationDecl | PI | Comment
4749 */
4750static void
4751docbParseMarkupDecl(xmlParserCtxtPtr ctxt) {
4752 GROW;
4753 xmlParseElementDecl(ctxt);
4754 xmlParseAttributeListDecl(ctxt);
4755 docbParseEntityDecl(ctxt);
4756 xmlParseNotationDecl(ctxt);
Daniel Veillarde95e2392001-06-06 10:46:28 +0000[diff] [blame]4757 docbParsePI(ctxt);
Daniel Veillardeae522a2001-04-23 13:41:34 +0000[diff] [blame]4758 xmlParseComment(ctxt);
4759 /*
4760 * This is only for internal subset. On external entities,
4761 * the replacement is done before parsing stage
4762 */
4763 if ((ctxt->external == 0) && (ctxt->inputNr == 1))
4764 xmlParsePEReference(ctxt);
4765 ctxt->instate = XML_PARSER_DTD;
4766}
4767
4768/**
Daniel Veillardcbaf3992001-12-31 16:16:02 +0000[diff] [blame^]4769 * docbParseInternalSubset:
Daniel Veillardeae522a2001-04-23 13:41:34 +0000[diff] [blame]4770 * @ctxt: an SGML parser context
4771 *
4772 * parse the internal subset declaration
4773 *
4774 * [28 end] ('[' (markupdecl | PEReference | S)* ']' S?)? '>'
4775 */
4776
4777static void
4778docbParseInternalSubset(xmlParserCtxtPtr ctxt) {
4779 /*
4780 * Is there any DTD definition ?
4781 */
4782 if (RAW == '[') {
4783 ctxt->instate = XML_PARSER_DTD;
4784 NEXT;
4785 /*
4786 * Parse the succession of Markup declarations and
4787 * PEReferences.
4788 * Subsequence (markupdecl | PEReference | S)*
4789 */
4790 while (RAW != ']') {
4791 const xmlChar *check = CUR_PTR;
4792 int cons = ctxt->input->consumed;
4793
4794 SKIP_BLANKS;
4795 docbParseMarkupDecl(ctxt);
4796 xmlParsePEReference(ctxt);
4797
4798 /*
4799 * Pop-up of finished entities.
4800 */
4801 while ((RAW == 0) && (ctxt->inputNr > 1))
4802 xmlPopInput(ctxt);
4803
4804 if ((CUR_PTR == check) && (cons == ctxt->input->consumed)) {
4805 ctxt->errNo = XML_ERR_INTERNAL_ERROR;
4806 if ((ctxt->sax != NULL) && (ctxt->sax->error != NULL))
4807 ctxt->sax->error(ctxt->userData,
4808 "docbParseInternalSubset: error detected in Markup declaration\n");
4809 ctxt->wellFormed = 0;
4810 ctxt->disableSAX = 1;
4811 break;
4812 }
4813 }
4814 if (RAW == ']') {
4815 NEXT;
4816 SKIP_BLANKS;
4817 }
4818 }
4819
4820 /*
4821 * We should be at the end of the DOCTYPE declaration.
4822 */
4823 if (RAW != '>') {
4824 ctxt->errNo = XML_ERR_DOCTYPE_NOT_FINISHED;
4825 if ((ctxt->sax != NULL) && (ctxt->sax->error != NULL))
Daniel Veillardf6ed8bc2001-10-02 09:22:47 +0000[diff] [blame]4826 ctxt->sax->error(ctxt->userData, "DOCTYPE improperly terminated\n");
Daniel Veillardeae522a2001-04-23 13:41:34 +0000[diff] [blame]4827 ctxt->wellFormed = 0;
4828 ctxt->disableSAX = 1;
4829 }
4830 NEXT;
4831}
4832
4833/**
4834 * docbParseMisc:
4835 * @ctxt: an XML parser context
4836 *
Daniel Veillardcbaf3992001-12-31 16:16:02 +0000[diff] [blame^]4837 * parse an XML Misc* optional field.
Daniel Veillardeae522a2001-04-23 13:41:34 +0000[diff] [blame]4838 *
4839 * [27] Misc ::= Comment | PI | S
4840 */
4841
4842static void
4843docbParseMisc(xmlParserCtxtPtr ctxt) {
4844 while (((RAW == '<') && (NXT(1) == '?')) ||
4845 ((RAW == '<') && (NXT(1) == '!') &&
4846 (NXT(2) == '-') && (NXT(3) == '-')) ||
4847 IS_BLANK(CUR)) {
4848 if ((RAW == '<') && (NXT(1) == '?')) {
Daniel Veillard84666b32001-06-11 17:31:08 +0000[diff] [blame]4849 docbParsePI(ctxt);
4850 } else if (IS_BLANK(CUR)) {
4851 NEXT;
4852 } else
4853 xmlParseComment(ctxt);
Daniel Veillardeae522a2001-04-23 13:41:34 +0000[diff] [blame]4854 }
4855}
4856
4857/**
4858 * docbParseDocument :
4859 * @ctxt: an SGML parser context
4860 *
4861 * parse an SGML document (and build a tree if using the standard SAX
4862 * interface).
4863 *
4864 * Returns 0, -1 in case of error. the parser context is augmented
4865 * as a result of the parsing.
4866 */
4867
4868int
4869docbParseDocument(docbParserCtxtPtr ctxt) {
4870 xmlChar start[4];
4871 xmlCharEncoding enc;
4872 xmlDtdPtr dtd;
4873
4874 docbDefaultSAXHandlerInit();
4875 ctxt->html = 2;
4876
4877 GROW;
4878 /*
4879 * SAX: beginning of the document processing.
4880 */
4881 if ((ctxt->sax) && (ctxt->sax->setDocumentLocator))
4882 ctxt->sax->setDocumentLocator(ctxt->userData, &xmlDefaultSAXLocator);
4883
4884 /*
4885 * Get the 4 first bytes and decode the charset
4886 * if enc != XML_CHAR_ENCODING_NONE
4887 * plug some encoding conversion routines.
4888 */
4889 start[0] = RAW;
4890 start[1] = NXT(1);
4891 start[2] = NXT(2);
4892 start[3] = NXT(3);
4893 enc = xmlDetectCharEncoding(start, 4);
4894 if (enc != XML_CHAR_ENCODING_NONE) {
4895 xmlSwitchEncoding(ctxt, enc);
4896 }
4897
4898 /*
4899 * Wipe out everything which is before the first '<'
4900 */
4901 SKIP_BLANKS;
4902 if (CUR == 0) {
4903 if ((ctxt->sax != NULL) && (ctxt->sax->error != NULL))
4904 ctxt->sax->error(ctxt->userData, "Document is empty\n");
4905 ctxt->wellFormed = 0;
4906 }
4907
4908 if ((ctxt->sax) && (ctxt->sax->startDocument) && (!ctxt->disableSAX))
4909 ctxt->sax->startDocument(ctxt->userData);
4910
4911
4912 /*
4913 * The Misc part of the Prolog
4914 */
4915 GROW;
4916 docbParseMisc(ctxt);
4917
4918 /*
4919 * Then possibly doc type declaration(s) and more Misc
4920 * (doctypedecl Misc*)?
4921 */
4922 GROW;
4923 if ((RAW == '<') && (NXT(1) == '!') &&
Daniel Veillard61b33d52001-04-24 13:55:12 +0000[diff] [blame]4924 (UPP(2) == 'D') && (UPP(3) == 'O') &&
4925 (UPP(4) == 'C') && (UPP(5) == 'T') &&
4926 (UPP(6) == 'Y') && (UPP(7) == 'P') &&
4927 (UPP(8) == 'E')) {
Daniel Veillardeae522a2001-04-23 13:41:34 +0000[diff] [blame]4928
4929 ctxt->inSubset = 1;
4930 docbParseDocTypeDecl(ctxt);
4931 if (RAW == '[') {
4932 ctxt->instate = XML_PARSER_DTD;
4933 docbParseInternalSubset(ctxt);
4934 }
4935
4936 /*
4937 * Create and update the external subset.
4938 */
4939 ctxt->inSubset = 2;
4940 if ((ctxt->sax != NULL) && (ctxt->sax->internalSubset != NULL) &&
4941 (!ctxt->disableSAX))
4942 ctxt->sax->internalSubset(ctxt->userData, ctxt->intSubName,
4943 ctxt->extSubSystem, ctxt->extSubURI);
4944 ctxt->inSubset = 0;
4945
4946
4947 ctxt->instate = XML_PARSER_PROLOG;
4948 docbParseMisc(ctxt);
4949 }
4950
4951 /*
4952 * Time to start parsing the tree itself
4953 */
4954 docbParseContent(ctxt);
4955
4956 /*
4957 * autoclose
4958 */
4959 if (CUR == 0)
4960 docbAutoClose(ctxt, NULL);
4961
4962
4963 /*
4964 * SAX: end of the document processing.
4965 */
4966 if ((ctxt->sax) && (ctxt->sax->endDocument != NULL))
4967 ctxt->sax->endDocument(ctxt->userData);
4968
4969 if (ctxt->myDoc != NULL) {
4970 dtd = ctxt->myDoc->intSubset;
Daniel Veillarde95e2392001-06-06 10:46:28 +0000[diff] [blame]4971 ctxt->myDoc->standalone = -1;
Daniel Veillardeae522a2001-04-23 13:41:34 +0000[diff] [blame]4972 if (dtd == NULL)
4973 ctxt->myDoc->intSubset =
4974 xmlCreateIntSubset(ctxt->myDoc, BAD_CAST "SGML",
4975 BAD_CAST "-//W3C//DTD SGML 4.0 Transitional//EN",
4976 BAD_CAST "http://www.w3.org/TR/REC-docbook/loose.dtd");
4977 }
4978 if (! ctxt->wellFormed) return(-1);
4979 return(0);
4980}
4981
4982
4983/************************************************************************
4984 * *
4985 * Parser contexts handling *
4986 * *
4987 ************************************************************************/
4988
4989/**
Daniel Veillard1034da22001-04-25 19:06:28 +0000[diff] [blame]4990 * docbInitParserCtxt:
Daniel Veillardeae522a2001-04-23 13:41:34 +0000[diff] [blame]4991 * @ctxt: an SGML parser context
4992 *
4993 * Initialize a parser context
4994 */
4995
4996static void
4997docbInitParserCtxt(docbParserCtxtPtr ctxt)
4998{
4999 docbSAXHandler *sax;
5000
5001 if (ctxt == NULL) return;
5002 memset(ctxt, 0, sizeof(docbParserCtxt));
5003
5004 sax = (docbSAXHandler *) xmlMalloc(sizeof(docbSAXHandler));
5005 if (sax == NULL) {
5006 xmlGenericError(xmlGenericErrorContext,
5007 "docbInitParserCtxt: out of memory\n");
5008 }
5009 memset(sax, 0, sizeof(docbSAXHandler));
5010
5011 /* Allocate the Input stack */
5012 ctxt->inputTab = (docbParserInputPtr *)
5013 xmlMalloc(5 * sizeof(docbParserInputPtr));
5014 if (ctxt->inputTab == NULL) {
5015 xmlGenericError(xmlGenericErrorContext,
5016 "docbInitParserCtxt: out of memory\n");
5017 }
5018 ctxt->inputNr = 0;
5019 ctxt->inputMax = 5;
5020 ctxt->input = NULL;
5021 ctxt->version = NULL;
5022 ctxt->encoding = NULL;
5023 ctxt->standalone = -1;
5024 ctxt->instate = XML_PARSER_START;
5025
5026 /* Allocate the Node stack */
5027 ctxt->nodeTab = (docbNodePtr *) xmlMalloc(10 * sizeof(docbNodePtr));
5028 ctxt->nodeNr = 0;
5029 ctxt->nodeMax = 10;
5030 ctxt->node = NULL;
5031
5032 /* Allocate the Name stack */
5033 ctxt->nameTab = (xmlChar **) xmlMalloc(10 * sizeof(xmlChar *));
5034 ctxt->nameNr = 0;
5035 ctxt->nameMax = 10;
5036 ctxt->name = NULL;
5037
5038 if (sax == NULL) ctxt->sax = &docbDefaultSAXHandler;
5039 else {
5040 ctxt->sax = sax;
5041 memcpy(sax, &docbDefaultSAXHandler, sizeof(docbSAXHandler));
5042 }
5043 ctxt->userData = ctxt;
5044 ctxt->myDoc = NULL;
5045 ctxt->wellFormed = 1;
Daniel Veillard635ef722001-10-29 11:48:19 +0000[diff] [blame]5046 ctxt->linenumbers = xmlLineNumbersDefaultValue;
Daniel Veillard61b33d52001-04-24 13:55:12 +0000[diff] [blame]5047 ctxt->replaceEntities = xmlSubstituteEntitiesDefaultValue;
Daniel Veillardeae522a2001-04-23 13:41:34 +0000[diff] [blame]5048 ctxt->html = 2;
5049 ctxt->record_info = 0;
5050 ctxt->validate = 0;
5051 ctxt->nbChars = 0;
5052 ctxt->checkIndex = 0;
5053 xmlInitNodeInfoSeq(&ctxt->node_seq);
5054}
5055
5056/**
5057 * docbFreeParserCtxt:
5058 * @ctxt: an SGML parser context
5059 *
5060 * Free all the memory used by a parser context. However the parsed
5061 * document in ctxt->myDoc is not freed.
5062 */
5063
5064void
5065docbFreeParserCtxt(docbParserCtxtPtr ctxt)
5066{
5067 xmlFreeParserCtxt(ctxt);
5068}
5069
5070/**
5071 * docbCreateDocParserCtxt :
5072 * @cur: a pointer to an array of xmlChar
Daniel Veillard1034da22001-04-25 19:06:28 +0000[diff] [blame]5073 * @encoding: the SGML document encoding, or NULL
Daniel Veillardeae522a2001-04-23 13:41:34 +0000[diff] [blame]5074 *
5075 * Create a parser context for an SGML document.
5076 *
5077 * Returns the new parser context or NULL
5078 */
5079static docbParserCtxtPtr
Daniel Veillard1034da22001-04-25 19:06:28 +0000[diff] [blame]5080docbCreateDocParserCtxt(xmlChar *cur, const char *encoding ATTRIBUTE_UNUSED) {
Daniel Veillardeae522a2001-04-23 13:41:34 +0000[diff] [blame]5081 docbParserCtxtPtr ctxt;
5082 docbParserInputPtr input;
5083 /* sgmlCharEncoding enc; */
5084
5085 ctxt = (docbParserCtxtPtr) xmlMalloc(sizeof(docbParserCtxt));
5086 if (ctxt == NULL) {
5087 perror("malloc");
5088 return(NULL);
5089 }
5090 docbInitParserCtxt(ctxt);
5091 input = (docbParserInputPtr) xmlMalloc(sizeof(docbParserInput));
5092 if (input == NULL) {
5093 perror("malloc");
5094 xmlFree(ctxt);
5095 return(NULL);
5096 }
5097 memset(input, 0, sizeof(docbParserInput));
5098
5099 input->line = 1;
5100 input->col = 1;
5101 input->base = cur;
5102 input->cur = cur;
5103
5104 inputPush(ctxt, input);
5105 return(ctxt);
5106}
5107
5108/************************************************************************
5109 * *
5110 * Progressive parsing interfaces *
5111 * *
5112 ************************************************************************/
5113
5114/**
5115 * docbParseLookupSequence:
5116 * @ctxt: an SGML parser context
5117 * @first: the first char to lookup
5118 * @next: the next char to lookup or zero
5119 * @third: the next char to lookup or zero
5120 *
5121 * Try to find if a sequence (first, next, third) or just (first next) or
5122 * (first) is available in the input stream.
5123 * This function has a side effect of (possibly) incrementing ctxt->checkIndex
5124 * to avoid rescanning sequences of bytes, it DOES change the state of the
5125 * parser, do not use liberally.
5126 * This is basically similar to xmlParseLookupSequence()
5127 *
5128 * Returns the index to the current parsing point if the full sequence
5129 * is available, -1 otherwise.
5130 */
5131static int
5132docbParseLookupSequence(docbParserCtxtPtr ctxt, xmlChar first,
5133 xmlChar next, xmlChar third) {
5134 int base, len;
5135 docbParserInputPtr in;
5136 const xmlChar *buf;
5137
5138 in = ctxt->input;
5139 if (in == NULL) return(-1);
5140 base = in->cur - in->base;
5141 if (base < 0) return(-1);
5142 if (ctxt->checkIndex > base)
5143 base = ctxt->checkIndex;
5144 if (in->buf == NULL) {
5145 buf = in->base;
5146 len = in->length;
5147 } else {
5148 buf = in->buf->buffer->content;
5149 len = in->buf->buffer->use;
5150 }
5151 /* take into account the sequence length */
5152 if (third) len -= 2;
5153 else if (next) len --;
5154 for (;base < len;base++) {
5155 if (buf[base] == first) {
5156 if (third != 0) {
5157 if ((buf[base + 1] != next) ||
5158 (buf[base + 2] != third)) continue;
5159 } else if (next != 0) {
5160 if (buf[base + 1] != next) continue;
5161 }
5162 ctxt->checkIndex = 0;
5163#ifdef DEBUG_PUSH
5164 if (next == 0)
5165 xmlGenericError(xmlGenericErrorContext,
5166 "HPP: lookup '%c' found at %d\n",
5167 first, base);
5168 else if (third == 0)
5169 xmlGenericError(xmlGenericErrorContext,
5170 "HPP: lookup '%c%c' found at %d\n",
5171 first, next, base);
5172 else
5173 xmlGenericError(xmlGenericErrorContext,
5174 "HPP: lookup '%c%c%c' found at %d\n",
5175 first, next, third, base);
5176#endif
5177 return(base - (in->cur - in->base));
5178 }
5179 }
5180 ctxt->checkIndex = base;
5181#ifdef DEBUG_PUSH
5182 if (next == 0)
5183 xmlGenericError(xmlGenericErrorContext,
5184 "HPP: lookup '%c' failed\n", first);
5185 else if (third == 0)
5186 xmlGenericError(xmlGenericErrorContext,
5187 "HPP: lookup '%c%c' failed\n", first, next);
5188 else
5189 xmlGenericError(xmlGenericErrorContext,
5190 "HPP: lookup '%c%c%c' failed\n", first, next, third);
5191#endif
5192 return(-1);
5193}
5194
5195/**
5196 * docbParseTryOrFinish:
5197 * @ctxt: an SGML parser context
5198 * @terminate: last chunk indicator
5199 *
5200 * Try to progress on parsing
5201 *
5202 * Returns zero if no parsing was possible
5203 */
5204static int
5205docbParseTryOrFinish(docbParserCtxtPtr ctxt, int terminate) {
5206 int ret = 0;
5207 docbParserInputPtr in;
5208 int avail = 0;
5209 xmlChar cur, next;
5210
5211#ifdef DEBUG_PUSH
5212 switch (ctxt->instate) {
5213 case XML_PARSER_EOF:
5214 xmlGenericError(xmlGenericErrorContext,
5215 "HPP: try EOF\n"); break;
5216 case XML_PARSER_START:
5217 xmlGenericError(xmlGenericErrorContext,
5218 "HPP: try START\n"); break;
5219 case XML_PARSER_MISC:
5220 xmlGenericError(xmlGenericErrorContext,
5221 "HPP: try MISC\n");break;
5222 case XML_PARSER_COMMENT:
5223 xmlGenericError(xmlGenericErrorContext,
5224 "HPP: try COMMENT\n");break;
5225 case XML_PARSER_PROLOG:
5226 xmlGenericError(xmlGenericErrorContext,
5227 "HPP: try PROLOG\n");break;
5228 case XML_PARSER_START_TAG:
5229 xmlGenericError(xmlGenericErrorContext,
5230 "HPP: try START_TAG\n");break;
5231 case XML_PARSER_CONTENT:
5232 xmlGenericError(xmlGenericErrorContext,
5233 "HPP: try CONTENT\n");break;
5234 case XML_PARSER_CDATA_SECTION:
5235 xmlGenericError(xmlGenericErrorContext,
5236 "HPP: try CDATA_SECTION\n");break;
5237 case XML_PARSER_END_TAG:
5238 xmlGenericError(xmlGenericErrorContext,
5239 "HPP: try END_TAG\n");break;
5240 case XML_PARSER_ENTITY_DECL:
5241 xmlGenericError(xmlGenericErrorContext,
5242 "HPP: try ENTITY_DECL\n");break;
5243 case XML_PARSER_ENTITY_VALUE:
5244 xmlGenericError(xmlGenericErrorContext,
5245 "HPP: try ENTITY_VALUE\n");break;
5246 case XML_PARSER_ATTRIBUTE_VALUE:
5247 xmlGenericError(xmlGenericErrorContext,
5248 "HPP: try ATTRIBUTE_VALUE\n");break;
5249 case XML_PARSER_DTD:
5250 xmlGenericError(xmlGenericErrorContext,
5251 "HPP: try DTD\n");break;
5252 case XML_PARSER_EPILOG:
5253 xmlGenericError(xmlGenericErrorContext,
5254 "HPP: try EPILOG\n");break;
5255 case XML_PARSER_PI:
5256 xmlGenericError(xmlGenericErrorContext,
5257 "HPP: try PI\n");break;
5258 }
5259#endif
5260
5261 while (1) {
5262
5263 in = ctxt->input;
5264 if (in == NULL) break;
5265 if (in->buf == NULL)
5266 avail = in->length - (in->cur - in->base);
5267 else
5268 avail = in->buf->buffer->use - (in->cur - in->base);
5269 if ((avail == 0) && (terminate)) {
5270 docbAutoClose(ctxt, NULL);
5271 if ((ctxt->nameNr == 0) && (ctxt->instate != XML_PARSER_EOF)) {
5272 /*
5273 * SAX: end of the document processing.
5274 */
5275 ctxt->instate = XML_PARSER_EOF;
5276 if ((ctxt->sax) && (ctxt->sax->endDocument != NULL))
5277 ctxt->sax->endDocument(ctxt->userData);
5278 }
5279 }
5280 if (avail < 1)
5281 goto done;
5282 switch (ctxt->instate) {
5283 case XML_PARSER_EOF:
5284 /*
5285 * Document parsing is done !
5286 */
5287 goto done;
5288 case XML_PARSER_START:
5289 /*
5290 * Very first chars read from the document flow.
5291 */
5292 cur = in->cur[0];
5293 if (IS_BLANK(cur)) {
5294 SKIP_BLANKS;
5295 if (in->buf == NULL)
5296 avail = in->length - (in->cur - in->base);
5297 else
5298 avail = in->buf->buffer->use - (in->cur - in->base);
5299 }
5300 if ((ctxt->sax) && (ctxt->sax->setDocumentLocator))
5301 ctxt->sax->setDocumentLocator(ctxt->userData,
5302 &xmlDefaultSAXLocator);
5303 if ((ctxt->sax) && (ctxt->sax->startDocument) &&
5304 (!ctxt->disableSAX))
5305 ctxt->sax->startDocument(ctxt->userData);
5306
5307 cur = in->cur[0];
5308 next = in->cur[1];
5309 if ((cur == '<') && (next == '!') &&
5310 (UPP(2) == 'D') && (UPP(3) == 'O') &&
5311 (UPP(4) == 'C') && (UPP(5) == 'T') &&
5312 (UPP(6) == 'Y') && (UPP(7) == 'P') &&
5313 (UPP(8) == 'E')) {
5314 if ((!terminate) &&
5315 (docbParseLookupSequence(ctxt, '>', 0, 0) < 0))
5316 goto done;
5317#ifdef DEBUG_PUSH
5318 xmlGenericError(xmlGenericErrorContext,
5319 "HPP: Parsing internal subset\n");
5320#endif
5321 docbParseDocTypeDecl(ctxt);
5322 ctxt->instate = XML_PARSER_PROLOG;
5323#ifdef DEBUG_PUSH
5324 xmlGenericError(xmlGenericErrorContext,
5325 "HPP: entering PROLOG\n");
5326#endif
5327 } else {
5328 ctxt->instate = XML_PARSER_MISC;
5329 }
5330#ifdef DEBUG_PUSH
5331 xmlGenericError(xmlGenericErrorContext,
5332 "HPP: entering MISC\n");
5333#endif
5334 break;
5335 case XML_PARSER_MISC:
5336 SKIP_BLANKS;
5337 if (in->buf == NULL)
5338 avail = in->length - (in->cur - in->base);
5339 else
5340 avail = in->buf->buffer->use - (in->cur - in->base);
5341 if (avail < 2)
5342 goto done;
5343 cur = in->cur[0];
5344 next = in->cur[1];
5345 if ((cur == '<') && (next == '!') &&
5346 (in->cur[2] == '-') && (in->cur[3] == '-')) {
5347 if ((!terminate) &&
5348 (docbParseLookupSequence(ctxt, '-', '-', '>') < 0))
5349 goto done;
5350#ifdef DEBUG_PUSH
5351 xmlGenericError(xmlGenericErrorContext,
5352 "HPP: Parsing Comment\n");
5353#endif
5354 docbParseComment(ctxt);
5355 ctxt->instate = XML_PARSER_MISC;
5356 } else if ((cur == '<') && (next == '!') &&
5357 (UPP(2) == 'D') && (UPP(3) == 'O') &&
5358 (UPP(4) == 'C') && (UPP(5) == 'T') &&
5359 (UPP(6) == 'Y') && (UPP(7) == 'P') &&
5360 (UPP(8) == 'E')) {
5361 if ((!terminate) &&
5362 (docbParseLookupSequence(ctxt, '>', 0, 0) < 0))
5363 goto done;
5364#ifdef DEBUG_PUSH
5365 xmlGenericError(xmlGenericErrorContext,
5366 "HPP: Parsing internal subset\n");
5367#endif
5368 docbParseDocTypeDecl(ctxt);
5369 ctxt->instate = XML_PARSER_PROLOG;
5370#ifdef DEBUG_PUSH
5371 xmlGenericError(xmlGenericErrorContext,
5372 "HPP: entering PROLOG\n");
5373#endif
5374 } else if ((cur == '<') && (next == '!') &&
5375 (avail < 9)) {
5376 goto done;
5377 } else {
5378 ctxt->instate = XML_PARSER_START_TAG;
5379#ifdef DEBUG_PUSH
5380 xmlGenericError(xmlGenericErrorContext,
5381 "HPP: entering START_TAG\n");
5382#endif
5383 }
5384 break;
5385 case XML_PARSER_PROLOG:
5386 SKIP_BLANKS;
5387 if (in->buf == NULL)
5388 avail = in->length - (in->cur - in->base);
5389 else
5390 avail = in->buf->buffer->use - (in->cur - in->base);
5391 if (avail < 2)
5392 goto done;
5393 cur = in->cur[0];
5394 next = in->cur[1];
5395 if ((cur == '<') && (next == '!') &&
5396 (in->cur[2] == '-') && (in->cur[3] == '-')) {
5397 if ((!terminate) &&
5398 (docbParseLookupSequence(ctxt, '-', '-', '>') < 0))
5399 goto done;
5400#ifdef DEBUG_PUSH
5401 xmlGenericError(xmlGenericErrorContext,
5402 "HPP: Parsing Comment\n");
5403#endif
5404 docbParseComment(ctxt);
5405 ctxt->instate = XML_PARSER_PROLOG;
5406 } else if ((cur == '<') && (next == '!') &&
5407 (avail < 4)) {
5408 goto done;
5409 } else {
5410 ctxt->instate = XML_PARSER_START_TAG;
5411#ifdef DEBUG_PUSH
5412 xmlGenericError(xmlGenericErrorContext,
5413 "HPP: entering START_TAG\n");
5414#endif
5415 }
5416 break;
5417 case XML_PARSER_EPILOG:
5418 if (in->buf == NULL)
5419 avail = in->length - (in->cur - in->base);
5420 else
5421 avail = in->buf->buffer->use - (in->cur - in->base);
5422 if (avail < 1)
5423 goto done;
5424 cur = in->cur[0];
5425 if (IS_BLANK(cur)) {
5426 docbParseCharData(ctxt);
5427 goto done;
5428 }
5429 if (avail < 2)
5430 goto done;
5431 next = in->cur[1];
5432 if ((cur == '<') && (next == '!') &&
5433 (in->cur[2] == '-') && (in->cur[3] == '-')) {
5434 if ((!terminate) &&
5435 (docbParseLookupSequence(ctxt, '-', '-', '>') < 0))
5436 goto done;
5437#ifdef DEBUG_PUSH
5438 xmlGenericError(xmlGenericErrorContext,
5439 "HPP: Parsing Comment\n");
5440#endif
5441 docbParseComment(ctxt);
5442 ctxt->instate = XML_PARSER_EPILOG;
5443 } else if ((cur == '<') && (next == '!') &&
5444 (avail < 4)) {
5445 goto done;
5446 } else {
5447 ctxt->errNo = XML_ERR_DOCUMENT_END;
5448 if ((ctxt->sax != NULL) && (ctxt->sax->error != NULL))
5449 ctxt->sax->error(ctxt->userData,
5450 "Extra content at the end of the document\n");
5451 ctxt->wellFormed = 0;
5452 ctxt->instate = XML_PARSER_EOF;
5453#ifdef DEBUG_PUSH
5454 xmlGenericError(xmlGenericErrorContext,
5455 "HPP: entering EOF\n");
5456#endif
5457 if ((ctxt->sax) && (ctxt->sax->endDocument != NULL))
5458 ctxt->sax->endDocument(ctxt->userData);
5459 goto done;
5460 }
5461 break;
5462 case XML_PARSER_START_TAG: {
5463 xmlChar *name, *oldname;
5464 int depth = ctxt->nameNr;
5465 docbElemDescPtr info;
5466
5467 if (avail < 2)
5468 goto done;
5469 cur = in->cur[0];
5470 if (cur != '<') {
5471 ctxt->instate = XML_PARSER_CONTENT;
5472#ifdef DEBUG_PUSH
5473 xmlGenericError(xmlGenericErrorContext,
5474 "HPP: entering CONTENT\n");
5475#endif
5476 break;
5477 }
5478 if ((!terminate) &&
5479 (docbParseLookupSequence(ctxt, '>', 0, 0) < 0))
5480 goto done;
5481
5482 oldname = xmlStrdup(ctxt->name);
5483 docbParseStartTag(ctxt);
5484 name = ctxt->name;
5485#ifdef DEBUG
5486 if (oldname == NULL)
5487 xmlGenericError(xmlGenericErrorContext,
5488 "Start of element %s\n", name);
5489 else if (name == NULL)
5490 xmlGenericError(xmlGenericErrorContext,
5491 "Start of element failed, was %s\n",
5492 oldname);
5493 else
5494 xmlGenericError(xmlGenericErrorContext,
5495 "Start of element %s, was %s\n",
5496 name, oldname);
5497#endif
5498 if (((depth == ctxt->nameNr) &&
5499 (xmlStrEqual(oldname, ctxt->name))) ||
5500 (name == NULL)) {
5501 if (CUR == '>')
5502 NEXT;
5503 if (oldname != NULL)
5504 xmlFree(oldname);
5505 break;
5506 }
5507 if (oldname != NULL)
5508 xmlFree(oldname);
5509
5510 /*
5511 * Lookup the info for that element.
5512 */
5513 info = docbTagLookup(name);
5514 if (info == NULL) {
5515 if ((ctxt->sax != NULL) && (ctxt->sax->error != NULL))
5516 ctxt->sax->error(ctxt->userData, "Tag %s unknown\n",
5517 name);
5518 ctxt->wellFormed = 0;
5519 } else if (info->depr) {
5520 /***************************
5521 if ((ctxt->sax != NULL) && (ctxt->sax->warning != NULL))
5522 ctxt->sax->warning(ctxt->userData,
5523 "Tag %s is deprecated\n",
5524 name);
5525 ***************************/
5526 }
5527
5528 /*
Daniel Veillardcbaf3992001-12-31 16:16:02 +0000[diff] [blame^]5529 * Check for an Empty Element labeled the XML/SGML way
Daniel Veillardeae522a2001-04-23 13:41:34 +0000[diff] [blame]5530 */
5531 if ((CUR == '/') && (NXT(1) == '>')) {
5532 SKIP(2);
5533 if ((ctxt->sax != NULL) && (ctxt->sax->endElement != NULL))
5534 ctxt->sax->endElement(ctxt->userData, name);
5535 oldname = docbnamePop(ctxt);
5536#ifdef DEBUG
5537 xmlGenericError(xmlGenericErrorContext,"End of tag the XML way: popping out %s\n",
5538 oldname);
5539#endif
5540 if (oldname != NULL)
5541 xmlFree(oldname);
5542 ctxt->instate = XML_PARSER_CONTENT;
5543#ifdef DEBUG_PUSH
5544 xmlGenericError(xmlGenericErrorContext,
5545 "HPP: entering CONTENT\n");
5546#endif
5547 break;
5548 }
5549
5550 if (CUR == '>') {
5551 NEXT;
5552 } else {
5553 if ((ctxt->sax != NULL) && (ctxt->sax->error != NULL))
5554 ctxt->sax->error(ctxt->userData,
5555 "Couldn't find end of Start Tag %s\n",
5556 name);
5557 ctxt->wellFormed = 0;
5558
5559 /*
5560 * end of parsing of this node.
5561 */
5562 if (xmlStrEqual(name, ctxt->name)) {
5563 nodePop(ctxt);
5564 oldname = docbnamePop(ctxt);
5565#ifdef DEBUG
5566 xmlGenericError(xmlGenericErrorContext,
5567 "End of start tag problem: popping out %s\n", oldname);
5568#endif
5569 if (oldname != NULL)
5570 xmlFree(oldname);
5571 }
5572
5573 ctxt->instate = XML_PARSER_CONTENT;
5574#ifdef DEBUG_PUSH
5575 xmlGenericError(xmlGenericErrorContext,
5576 "HPP: entering CONTENT\n");
5577#endif
5578 break;
5579 }
5580
5581 /*
5582 * Check for an Empty Element from DTD definition
5583 */
5584 if ((info != NULL) && (info->empty)) {
5585 if ((ctxt->sax != NULL) && (ctxt->sax->endElement != NULL))
5586 ctxt->sax->endElement(ctxt->userData, name);
5587 oldname = docbnamePop(ctxt);
5588#ifdef DEBUG
5589 xmlGenericError(xmlGenericErrorContext,"End of empty tag %s : popping out %s\n", name, oldname);
5590#endif
5591 if (oldname != NULL)
5592 xmlFree(oldname);
5593 }
5594 ctxt->instate = XML_PARSER_CONTENT;
5595#ifdef DEBUG_PUSH
5596 xmlGenericError(xmlGenericErrorContext,
5597 "HPP: entering CONTENT\n");
5598#endif
5599 break;
5600 }
5601 case XML_PARSER_CONTENT: {
5602 long cons;
5603 /*
5604 * Handle preparsed entities and charRef
5605 */
5606 if (ctxt->token != 0) {
5607 xmlChar chr[2] = { 0 , 0 } ;
5608
5609 chr[0] = (xmlChar) ctxt->token;
5610 docbCheckParagraph(ctxt);
5611 if ((ctxt->sax != NULL) && (ctxt->sax->characters != NULL))
5612 ctxt->sax->characters(ctxt->userData, chr, 1);
5613 ctxt->token = 0;
5614 ctxt->checkIndex = 0;
5615 }
5616 if ((avail == 1) && (terminate)) {
5617 cur = in->cur[0];
5618 if ((cur != '<') && (cur != '&')) {
5619 if (ctxt->sax != NULL) {
5620 if (IS_BLANK(cur)) {
5621 if (ctxt->sax->ignorableWhitespace != NULL)
5622 ctxt->sax->ignorableWhitespace(
5623 ctxt->userData, &cur, 1);
5624 } else {
5625 docbCheckParagraph(ctxt);
5626 if (ctxt->sax->characters != NULL)
5627 ctxt->sax->characters(
5628 ctxt->userData, &cur, 1);
5629 }
5630 }
5631 ctxt->token = 0;
5632 ctxt->checkIndex = 0;
5633 NEXT;
5634 }
5635 break;
5636 }
5637 if (avail < 2)
5638 goto done;
5639 cur = in->cur[0];
5640 next = in->cur[1];
5641 cons = ctxt->nbChars;
5642 /*
5643 * Sometimes DOCTYPE arrives in the middle of the document
5644 */
5645 if ((cur == '<') && (next == '!') &&
5646 (UPP(2) == 'D') && (UPP(3) == 'O') &&
5647 (UPP(4) == 'C') && (UPP(5) == 'T') &&
5648 (UPP(6) == 'Y') && (UPP(7) == 'P') &&
5649 (UPP(8) == 'E')) {
5650 if ((!terminate) &&
5651 (docbParseLookupSequence(ctxt, '>', 0, 0) < 0))
5652 goto done;
5653 if ((ctxt->sax != NULL) && (ctxt->sax->error != NULL))
5654 ctxt->sax->error(ctxt->userData,
5655 "Misplaced DOCTYPE declaration\n");
5656 ctxt->wellFormed = 0;
5657 docbParseDocTypeDecl(ctxt);
5658 } else if ((cur == '<') && (next == '!') &&
5659 (in->cur[2] == '-') && (in->cur[3] == '-')) {
5660 if ((!terminate) &&
5661 (docbParseLookupSequence(ctxt, '-', '-', '>') < 0))
5662 goto done;
5663#ifdef DEBUG_PUSH
5664 xmlGenericError(xmlGenericErrorContext,
5665 "HPP: Parsing Comment\n");
5666#endif
5667 docbParseComment(ctxt);
5668 ctxt->instate = XML_PARSER_CONTENT;
5669 } else if ((cur == '<') && (next == '!') && (avail < 4)) {
5670 goto done;
5671 } else if ((cur == '<') && (next == '/')) {
5672 ctxt->instate = XML_PARSER_END_TAG;
5673 ctxt->checkIndex = 0;
5674#ifdef DEBUG_PUSH
5675 xmlGenericError(xmlGenericErrorContext,
5676 "HPP: entering END_TAG\n");
5677#endif
5678 break;
5679 } else if (cur == '<') {
5680 ctxt->instate = XML_PARSER_START_TAG;
5681 ctxt->checkIndex = 0;
5682#ifdef DEBUG_PUSH
5683 xmlGenericError(xmlGenericErrorContext,
5684 "HPP: entering START_TAG\n");
5685#endif
5686 break;
5687 } else if (cur == '&') {
5688 if ((!terminate) &&
5689 (docbParseLookupSequence(ctxt, ';', 0, 0) < 0))
5690 goto done;
5691#ifdef DEBUG_PUSH
5692 xmlGenericError(xmlGenericErrorContext,
5693 "HPP: Parsing Reference\n");
5694#endif
5695 /* TODO: check generation of subtrees if noent !!! */
5696 docbParseReference(ctxt);
5697 } else {
5698 /* TODO Avoid the extra copy, handle directly !!!!!! */
5699 /*
5700 * Goal of the following test is :
5701 * - minimize calls to the SAX 'character' callback
5702 * when they are mergeable
5703 */
5704 if ((ctxt->inputNr == 1) &&
5705 (avail < DOCB_PARSER_BIG_BUFFER_SIZE)) {
5706 if ((!terminate) &&
5707 (docbParseLookupSequence(ctxt, '<', 0, 0) < 0))
5708 goto done;
5709 }
5710 ctxt->checkIndex = 0;
5711#ifdef DEBUG_PUSH
5712 xmlGenericError(xmlGenericErrorContext,
5713 "HPP: Parsing char data\n");
5714#endif
5715 docbParseCharData(ctxt);
5716 }
5717 if (cons == ctxt->nbChars) {
5718 if (ctxt->node != NULL) {
5719 if ((ctxt->sax != NULL) && (ctxt->sax->error != NULL))
5720 ctxt->sax->error(ctxt->userData,
5721 "detected an error in element content\n");
5722 ctxt->wellFormed = 0;
5723 NEXT;
5724 }
5725 break;
5726 }
5727
5728 break;
5729 }
5730 case XML_PARSER_END_TAG:
5731 if (avail < 2)
5732 goto done;
5733 if ((!terminate) &&
5734 (docbParseLookupSequence(ctxt, '>', 0, 0) < 0))
5735 goto done;
5736 docbParseEndTag(ctxt);
5737 if (ctxt->nameNr == 0) {
5738 ctxt->instate = XML_PARSER_EPILOG;
5739 } else {
5740 ctxt->instate = XML_PARSER_CONTENT;
5741 }
5742 ctxt->checkIndex = 0;
5743#ifdef DEBUG_PUSH
5744 xmlGenericError(xmlGenericErrorContext,
5745 "HPP: entering CONTENT\n");
5746#endif
5747 break;
5748 case XML_PARSER_CDATA_SECTION:
5749 xmlGenericError(xmlGenericErrorContext,
5750 "HPP: internal error, state == CDATA\n");
5751 ctxt->instate = XML_PARSER_CONTENT;
5752 ctxt->checkIndex = 0;
5753#ifdef DEBUG_PUSH
5754 xmlGenericError(xmlGenericErrorContext,
5755 "HPP: entering CONTENT\n");
5756#endif
5757 break;
5758 case XML_PARSER_DTD:
5759 xmlGenericError(xmlGenericErrorContext,
5760 "HPP: internal error, state == DTD\n");
5761 ctxt->instate = XML_PARSER_CONTENT;
5762 ctxt->checkIndex = 0;
5763#ifdef DEBUG_PUSH
5764 xmlGenericError(xmlGenericErrorContext,
5765 "HPP: entering CONTENT\n");
5766#endif
5767 break;
5768 case XML_PARSER_COMMENT:
5769 xmlGenericError(xmlGenericErrorContext,
5770 "HPP: internal error, state == COMMENT\n");
5771 ctxt->instate = XML_PARSER_CONTENT;
5772 ctxt->checkIndex = 0;
5773#ifdef DEBUG_PUSH
5774 xmlGenericError(xmlGenericErrorContext,
5775 "HPP: entering CONTENT\n");
5776#endif
5777 break;
5778 case XML_PARSER_PI:
5779 xmlGenericError(xmlGenericErrorContext,
5780 "HPP: internal error, state == PI\n");
5781 ctxt->instate = XML_PARSER_CONTENT;
5782 ctxt->checkIndex = 0;
5783#ifdef DEBUG_PUSH
5784 xmlGenericError(xmlGenericErrorContext,
5785 "HPP: entering CONTENT\n");
5786#endif
5787 break;
5788 case XML_PARSER_ENTITY_DECL:
5789 xmlGenericError(xmlGenericErrorContext,
5790 "HPP: internal error, state == ENTITY_DECL\n");
5791 ctxt->instate = XML_PARSER_CONTENT;
5792 ctxt->checkIndex = 0;
5793#ifdef DEBUG_PUSH
5794 xmlGenericError(xmlGenericErrorContext,
5795 "HPP: entering CONTENT\n");
5796#endif
5797 break;
5798 case XML_PARSER_ENTITY_VALUE:
5799 xmlGenericError(xmlGenericErrorContext,
5800 "HPP: internal error, state == ENTITY_VALUE\n");
5801 ctxt->instate = XML_PARSER_CONTENT;
5802 ctxt->checkIndex = 0;
5803#ifdef DEBUG_PUSH
5804 xmlGenericError(xmlGenericErrorContext,
5805 "HPP: entering DTD\n");
5806#endif
5807 break;
5808 case XML_PARSER_ATTRIBUTE_VALUE:
5809 xmlGenericError(xmlGenericErrorContext,
5810 "HPP: internal error, state == ATTRIBUTE_VALUE\n");
5811 ctxt->instate = XML_PARSER_START_TAG;
5812 ctxt->checkIndex = 0;
5813#ifdef DEBUG_PUSH
5814 xmlGenericError(xmlGenericErrorContext,
5815 "HPP: entering START_TAG\n");
5816#endif
5817 break;
5818 case XML_PARSER_SYSTEM_LITERAL:
5819 xmlGenericError(xmlGenericErrorContext,
5820 "HPP: internal error, state == XML_PARSER_SYSTEM_LITERAL\n");
5821 ctxt->instate = XML_PARSER_CONTENT;
5822 ctxt->checkIndex = 0;
5823#ifdef DEBUG_PUSH
5824 xmlGenericError(xmlGenericErrorContext,
5825 "HPP: entering CONTENT\n");
5826#endif
5827 break;
5828
5829 case XML_PARSER_IGNORE:
5830 xmlGenericError(xmlGenericErrorContext,
5831 "HPP: internal error, state == XML_PARSER_IGNORE\n");
5832 ctxt->instate = XML_PARSER_CONTENT;
5833 ctxt->checkIndex = 0;
5834#ifdef DEBUG_PUSH
5835 xmlGenericError(xmlGenericErrorContext,
5836 "HPP: entering CONTENT\n");
5837#endif
5838 break;
5839 }
5840 }
5841done:
5842 if ((avail == 0) && (terminate)) {
5843 docbAutoClose(ctxt, NULL);
5844 if ((ctxt->nameNr == 0) && (ctxt->instate != XML_PARSER_EOF)) {
5845 /*
5846 * SAX: end of the document processing.
5847 */
5848 ctxt->instate = XML_PARSER_EOF;
5849 if ((ctxt->sax) && (ctxt->sax->endDocument != NULL))
5850 ctxt->sax->endDocument(ctxt->userData);
5851 }
5852 }
5853 if ((ctxt->myDoc != NULL) &&
5854 ((terminate) || (ctxt->instate == XML_PARSER_EOF) ||
5855 (ctxt->instate == XML_PARSER_EPILOG))) {
5856 xmlDtdPtr dtd;
5857 dtd = ctxt->myDoc->intSubset;
5858 if (dtd == NULL)
5859 ctxt->myDoc->intSubset =
5860 xmlCreateIntSubset(ctxt->myDoc, BAD_CAST "SGML",
5861 BAD_CAST "-//W3C//DTD SGML 4.0 Transitional//EN",
5862 BAD_CAST "http://www.w3.org/TR/REC-docbook/loose.dtd");
5863 }
5864#ifdef DEBUG_PUSH
5865 xmlGenericError(xmlGenericErrorContext, "HPP: done %d\n", ret);
5866#endif
5867 return(ret);
5868}
5869
5870/**
5871 * docbParseChunk:
5872 * @ctxt: an XML parser context
5873 * @chunk: an char array
5874 * @size: the size in byte of the chunk
5875 * @terminate: last chunk indicator
5876 *
5877 * Parse a Chunk of memory
5878 *
5879 * Returns zero if no error, the xmlParserErrors otherwise.
5880 */
5881int
5882docbParseChunk(docbParserCtxtPtr ctxt, const char *chunk, int size,
5883 int terminate) {
5884 if ((size > 0) && (chunk != NULL) && (ctxt->input != NULL) &&
5885 (ctxt->input->buf != NULL) && (ctxt->instate != XML_PARSER_EOF)) {
5886 int base = ctxt->input->base - ctxt->input->buf->buffer->content;
5887 int cur = ctxt->input->cur - ctxt->input->base;
5888
5889 xmlParserInputBufferPush(ctxt->input->buf, size, chunk);
5890 ctxt->input->base = ctxt->input->buf->buffer->content + base;
5891 ctxt->input->cur = ctxt->input->base + cur;
5892#ifdef DEBUG_PUSH
5893 xmlGenericError(xmlGenericErrorContext, "HPP: pushed %d\n", size);
5894#endif
5895
5896 if ((terminate) || (ctxt->input->buf->buffer->use > 80))
5897 docbParseTryOrFinish(ctxt, terminate);
5898 } else if (ctxt->instate != XML_PARSER_EOF) {
5899 xmlParserInputBufferPush(ctxt->input->buf, 0, "");
5900 docbParseTryOrFinish(ctxt, terminate);
5901 }
5902 if (terminate) {
5903 if ((ctxt->instate != XML_PARSER_EOF) &&
5904 (ctxt->instate != XML_PARSER_EPILOG) &&
5905 (ctxt->instate != XML_PARSER_MISC)) {
5906 ctxt->errNo = XML_ERR_DOCUMENT_END;
5907 if ((ctxt->sax != NULL) && (ctxt->sax->error != NULL))
5908 ctxt->sax->error(ctxt->userData,
5909 "Extra content at the end of the document\n");
5910 ctxt->wellFormed = 0;
5911 }
5912 if (ctxt->instate != XML_PARSER_EOF) {
5913 if ((ctxt->sax) && (ctxt->sax->endDocument != NULL))
5914 ctxt->sax->endDocument(ctxt->userData);
5915 }
5916 ctxt->instate = XML_PARSER_EOF;
5917 }
5918 return((xmlParserErrors) ctxt->errNo);
5919}
5920
5921/************************************************************************
5922 * *
5923 * User entry points *
5924 * *
5925 ************************************************************************/
5926
5927/**
5928 * docbCreatePushParserCtxt :
5929 * @sax: a SAX handler
5930 * @user_data: The user data returned on SAX callbacks
5931 * @chunk: a pointer to an array of chars
5932 * @size: number of chars in the array
5933 * @filename: an optional file name or URI
5934 * @enc: an optional encoding
5935 *
5936 * Create a parser context for using the DocBook SGML parser in push mode
5937 * To allow content encoding detection, @size should be >= 4
5938 * The value of @filename is used for fetching external entities
5939 * and error/warning reports.
5940 *
5941 * Returns the new parser context or NULL
5942 */
5943docbParserCtxtPtr
5944docbCreatePushParserCtxt(docbSAXHandlerPtr sax, void *user_data,
5945 const char *chunk, int size, const char *filename,
5946 xmlCharEncoding enc) {
5947 docbParserCtxtPtr ctxt;
5948 docbParserInputPtr inputStream;
5949 xmlParserInputBufferPtr buf;
5950
5951 buf = xmlAllocParserInputBuffer(enc);
5952 if (buf == NULL) return(NULL);
5953
5954 ctxt = (docbParserCtxtPtr) xmlMalloc(sizeof(docbParserCtxt));
5955 if (ctxt == NULL) {
5956 xmlFree(buf);
5957 return(NULL);
5958 }
5959 memset(ctxt, 0, sizeof(docbParserCtxt));
5960 docbInitParserCtxt(ctxt);
5961 if (sax != NULL) {
5962 if (ctxt->sax != &docbDefaultSAXHandler)
5963 xmlFree(ctxt->sax);
5964 ctxt->sax = (docbSAXHandlerPtr) xmlMalloc(sizeof(docbSAXHandler));
5965 if (ctxt->sax == NULL) {
5966 xmlFree(buf);
5967 xmlFree(ctxt);
5968 return(NULL);
5969 }
5970 memcpy(ctxt->sax, sax, sizeof(docbSAXHandler));
5971 if (user_data != NULL)
5972 ctxt->userData = user_data;
5973 }
5974 if (filename == NULL) {
5975 ctxt->directory = NULL;
5976 } else {
5977 ctxt->directory = xmlParserGetDirectory(filename);
5978 }
5979
5980 inputStream = docbNewInputStream(ctxt);
5981 if (inputStream == NULL) {
5982 xmlFreeParserCtxt(ctxt);
5983 return(NULL);
5984 }
5985
5986 if (filename == NULL)
5987 inputStream->filename = NULL;
5988 else
5989 inputStream->filename = xmlMemStrdup(filename);
5990 inputStream->buf = buf;
5991 inputStream->base = inputStream->buf->buffer->content;
5992 inputStream->cur = inputStream->buf->buffer->content;
5993
5994 inputPush(ctxt, inputStream);
5995
5996 if ((size > 0) && (chunk != NULL) && (ctxt->input != NULL) &&
5997 (ctxt->input->buf != NULL)) {
5998 xmlParserInputBufferPush(ctxt->input->buf, size, chunk);
5999#ifdef DEBUG_PUSH
6000 xmlGenericError(xmlGenericErrorContext, "HPP: pushed %d\n", size);
6001#endif
6002 }
6003
6004 return(ctxt);
6005}
6006
6007/**
6008 * docbSAXParseDoc :
6009 * @cur: a pointer to an array of xmlChar
6010 * @encoding: a free form C string describing the SGML document encoding, or NULL
6011 * @sax: the SAX handler block
6012 * @userData: if using SAX, this pointer will be provided on callbacks.
6013 *
6014 * parse an SGML in-memory document and build a tree.
6015 * It use the given SAX function block to handle the parsing callback.
6016 * If sax is NULL, fallback to the default DOM tree building routines.
6017 *
6018 * Returns the resulting document tree
6019 */
6020
6021docbDocPtr
6022docbSAXParseDoc(xmlChar *cur, const char *encoding, docbSAXHandlerPtr sax, void *userData) {
6023 docbDocPtr ret;
6024 docbParserCtxtPtr ctxt;
6025
6026 if (cur == NULL) return(NULL);
6027
6028
6029 ctxt = docbCreateDocParserCtxt(cur, encoding);
6030 if (ctxt == NULL) return(NULL);
6031 if (sax != NULL) {
6032 ctxt->sax = sax;
6033 ctxt->userData = userData;
6034 }
6035
6036 docbParseDocument(ctxt);
6037 ret = ctxt->myDoc;
6038 if (sax != NULL) {
6039 ctxt->sax = NULL;
6040 ctxt->userData = NULL;
6041 }
6042 docbFreeParserCtxt(ctxt);
6043
6044 return(ret);
6045}
6046
6047/**
6048 * docbParseDoc :
6049 * @cur: a pointer to an array of xmlChar
6050 * @encoding: a free form C string describing the SGML document encoding, or NULL
6051 *
6052 * parse an SGML in-memory document and build a tree.
6053 *
6054 * Returns the resulting document tree
6055 */
6056
6057docbDocPtr
6058docbParseDoc(xmlChar *cur, const char *encoding) {
6059 return(docbSAXParseDoc(cur, encoding, NULL, NULL));
6060}
6061
6062
6063/**
6064 * docbCreateFileParserCtxt :
6065 * @filename: the filename
Daniel Veillard1034da22001-04-25 19:06:28 +0000[diff] [blame]6066 * @encoding: the SGML document encoding, or NULL
Daniel Veillardeae522a2001-04-23 13:41:34 +0000[diff] [blame]6067 *
6068 * Create a parser context for a file content.
6069 * Automatic support for ZLIB/Compress compressed document is provided
6070 * by default if found at compile-time.
6071 *
6072 * Returns the new parser context or NULL
6073 */
6074docbParserCtxtPtr
Daniel Veillard1034da22001-04-25 19:06:28 +0000[diff] [blame]6075docbCreateFileParserCtxt(const char *filename,
6076 const char *encoding ATTRIBUTE_UNUSED)
Daniel Veillardeae522a2001-04-23 13:41:34 +0000[diff] [blame]6077{
6078 docbParserCtxtPtr ctxt;
6079 docbParserInputPtr inputStream;
6080 xmlParserInputBufferPtr buf;
6081 /* sgmlCharEncoding enc; */
6082
6083 buf = xmlParserInputBufferCreateFilename(filename, XML_CHAR_ENCODING_NONE);
6084 if (buf == NULL) return(NULL);
6085
6086 ctxt = (docbParserCtxtPtr) xmlMalloc(sizeof(docbParserCtxt));
6087 if (ctxt == NULL) {
6088 perror("malloc");
6089 return(NULL);
6090 }
6091 memset(ctxt, 0, sizeof(docbParserCtxt));
6092 docbInitParserCtxt(ctxt);
6093 inputStream = (docbParserInputPtr) xmlMalloc(sizeof(docbParserInput));
6094 if (inputStream == NULL) {
6095 perror("malloc");
6096 xmlFree(ctxt);
6097 return(NULL);
6098 }
6099 memset(inputStream, 0, sizeof(docbParserInput));
6100
6101 inputStream->filename = xmlMemStrdup(filename);
6102 inputStream->line = 1;
6103 inputStream->col = 1;
6104 inputStream->buf = buf;
6105 inputStream->directory = NULL;
6106
6107 inputStream->base = inputStream->buf->buffer->content;
6108 inputStream->cur = inputStream->buf->buffer->content;
6109 inputStream->free = NULL;
6110
6111 inputPush(ctxt, inputStream);
6112 return(ctxt);
6113}
6114
6115/**
6116 * docbSAXParseFile :
6117 * @filename: the filename
6118 * @encoding: a free form C string describing the SGML document encoding, or NULL
6119 * @sax: the SAX handler block
6120 * @userData: if using SAX, this pointer will be provided on callbacks.
6121 *
6122 * parse an SGML file and build a tree. Automatic support for ZLIB/Compress
6123 * compressed document is provided by default if found at compile-time.
6124 * It use the given SAX function block to handle the parsing callback.
6125 * If sax is NULL, fallback to the default DOM tree building routines.
6126 *
6127 * Returns the resulting document tree
6128 */
6129
6130docbDocPtr
6131docbSAXParseFile(const char *filename, const char *encoding, docbSAXHandlerPtr sax,
6132 void *userData) {
6133 docbDocPtr ret;
6134 docbParserCtxtPtr ctxt;
6135 docbSAXHandlerPtr oldsax = NULL;
6136
6137 ctxt = docbCreateFileParserCtxt(filename, encoding);
6138 if (ctxt == NULL) return(NULL);
6139 if (sax != NULL) {
6140 oldsax = ctxt->sax;
6141 ctxt->sax = sax;
6142 ctxt->userData = userData;
6143 }
6144
6145 docbParseDocument(ctxt);
6146
6147 ret = ctxt->myDoc;
6148 if (sax != NULL) {
6149 ctxt->sax = oldsax;
6150 ctxt->userData = NULL;
6151 }
6152 docbFreeParserCtxt(ctxt);
6153
6154 return(ret);
6155}
6156
6157/**
6158 * docbParseFile :
6159 * @filename: the filename
6160 * @encoding: a free form C string describing document encoding, or NULL
6161 *
6162 * parse a Docbook SGML file and build a tree. Automatic support for
6163 * ZLIB/Compress compressed document is provided by default if found
6164 * at compile-time.
6165 *
6166 * Returns the resulting document tree
6167 */
6168
6169docbDocPtr
6170docbParseFile(const char *filename, const char *encoding) {
6171 return(docbSAXParseFile(filename, encoding, NULL, NULL));
6172}
6173
6174#endif /* LIBXML_DOCB_ENABLED */