DOCBparser.c revision eae522a0d8aa9f830d2e447f29b504030dbb6bbd
1/* 2 * DOCBparser.c : an attempt to parse SGML Docbook documents 3 * 4 * See Copyright for the status of this software. 5 * 6 * Daniel.Veillard@w3.org 7 */ 8 9#include "libxml.h" 10#ifdef LIBXML_DOCB_ENABLED 11 12#include <string.h> 13#ifdef HAVE_CTYPE_H 14#include <ctype.h> 15#endif 16#ifdef HAVE_STDLIB_H 17#include <stdlib.h> 18#endif 19#ifdef HAVE_SYS_STAT_H 20#include <sys/stat.h> 21#endif 22#ifdef HAVE_FCNTL_H 23#include <fcntl.h> 24#endif 25#ifdef HAVE_UNISTD_H 26#include <unistd.h> 27#endif 28#ifdef HAVE_ZLIB_H 29#include <zlib.h> 30#endif 31 32#include <libxml/xmlmemory.h> 33#include <libxml/tree.h> 34#include <libxml/SAX.h> 35#include <libxml/parser.h> 36#include <libxml/parserInternals.h> 37#include <libxml/xmlerror.h> 38#include <libxml/DOCBparser.h> 39#include <libxml/entities.h> 40#include <libxml/encoding.h> 41#include <libxml/valid.h> 42#include <libxml/xmlIO.h> 43#include <libxml/uri.h> 44 45/* 46 * Internal description of an SGML entity 47 */ 48typedef struct _docbEntityDesc docbEntityDesc; 49typedef docbEntityDesc *docbEntityDescPtr; 50struct _docbEntityDesc { 51 int value; /* the UNICODE value for the character */ 52 const char *name; /* The entity name */ 53 const char *desc; /* the description */ 54}; 55 56#if 0 57docbElemDescPtr docbTagLookup (const xmlChar *tag); 58docbEntityDescPtr docbEntityLookup(const xmlChar *name); 59docbEntityDescPtr docbEntityValueLookup(int value); 60 61int docbIsAutoClosed(docbDocPtr doc, 62 docbNodePtr elem); 63int docbAutoCloseTag(docbDocPtr doc, 64 const xmlChar *name, 65 docbNodePtr elem); 66 67#endif 68static int docbParseCharRef(docbParserCtxtPtr ctxt); 69static docbEntityDescPtr docbParseEntityRef(docbParserCtxtPtr ctxt, 70 xmlChar **str); 71static void docbParseElement(docbParserCtxtPtr ctxt); 72 73/* 74 * Internal description of an SGML element 75 */ 76typedef struct _docbElemDesc docbElemDesc; 77typedef docbElemDesc *docbElemDescPtr; 78struct _docbElemDesc { 79 const char *name; /* The tag name */ 80 int startTag; /* Whether the start tag can be implied */ 81 int endTag; /* Whether the end tag can be implied */ 82 int empty; /* Is this an empty element ? */ 83 int depr; /* Is this a deprecated element ? */ 84 int dtd; /* 1: only in Loose DTD, 2: only Frameset one */ 85 const char *desc; /* the description */ 86}; 87 88 89#define DOCB_MAX_NAMELEN 1000 90#define DOCB_PARSER_BIG_BUFFER_SIZE 1000 91#define DOCB_PARSER_BUFFER_SIZE 100 92 93/* #define DEBUG */ 94/* #define DEBUG_PUSH */ 95 96/************************************************************************ 97 * * 98 * Parser stacks related functions and macros * 99 * * 100 ************************************************************************/ 101 102/* 103 * Generic function for accessing stacks in the Parser Context 104 */ 105 106#define PUSH_AND_POP(scope, type, name) \ 107scope int docb##name##Push(docbParserCtxtPtr ctxt, type value) { \ 108 if (ctxt->name##Nr >= ctxt->name##Max) { \ 109 ctxt->name##Max *= 2; \ 110 ctxt->name##Tab = (type *) xmlRealloc(ctxt->name##Tab, \ 111 ctxt->name##Max * sizeof(ctxt->name##Tab[0])); \ 112 if (ctxt->name##Tab == NULL) { \ 113 xmlGenericError(xmlGenericErrorContext, "realloc failed !\n"); \ 114 return(0); \ 115 } \ 116 } \ 117 ctxt->name##Tab[ctxt->name##Nr] = value; \ 118 ctxt->name = value; \ 119 return(ctxt->name##Nr++); \ 120} \ 121scope type docb##name##Pop(docbParserCtxtPtr ctxt) { \ 122 type ret; \ 123 if (ctxt->name##Nr < 0) return(0); \ 124 ctxt->name##Nr--; \ 125 if (ctxt->name##Nr < 0) return(0); \ 126 if (ctxt->name##Nr > 0) \ 127 ctxt->name = ctxt->name##Tab[ctxt->name##Nr - 1]; \ 128 else \ 129 ctxt->name = NULL; \ 130 ret = ctxt->name##Tab[ctxt->name##Nr]; \ 131 ctxt->name##Tab[ctxt->name##Nr] = 0; \ 132 return(ret); \ 133} \ 134 135/* PUSH_AND_POP(static, xmlNodePtr, node) */ 136PUSH_AND_POP(static, xmlChar*, name) 137 138/* 139 * Macros for accessing the content. Those should be used only by the parser, 140 * and not exported. 141 * 142 * Dirty macros, i.e. one need to make assumption on the context to use them 143 * 144 * CUR_PTR return the current pointer to the xmlChar to be parsed. 145 * CUR returns the current xmlChar value, i.e. a 8 bit value if compiled 146 * in ISO-Latin or UTF-8, and the current 16 bit value if compiled 147 * in UNICODE mode. This should be used internally by the parser 148 * only to compare to ASCII values otherwise it would break when 149 * running with UTF-8 encoding. 150 * NXT(n) returns the n'th next xmlChar. Same as CUR is should be used only 151 * to compare on ASCII based substring. 152 * UPP(n) returns the n'th next xmlChar converted to uppercase. Same as CUR 153 * it should be used only to compare on ASCII based substring. 154 * SKIP(n) Skip n xmlChar, and must also be used only to skip ASCII defined 155 * strings within the parser. 156 * 157 * Clean macros, not dependent of an ASCII context, expect UTF-8 encoding 158 * 159 * CURRENT Returns the current char value, with the full decoding of 160 * UTF-8 if we are using this mode. It returns an int. 161 * NEXT Skip to the next character, this does the proper decoding 162 * in UTF-8 mode. It also pop-up unfinished entities on the fly. 163 * COPY(to) copy one char to *to, increment CUR_PTR and to accordingly 164 */ 165 166#define UPPER (toupper(*ctxt->input->cur)) 167 168#define SKIP(val) ctxt->nbChars += (val),ctxt->input->cur += (val) 169 170#define NXT(val) ctxt->input->cur[(val)] 171 172#define UPP(val) (toupper(ctxt->input->cur[(val)])) 173 174#define CUR_PTR ctxt->input->cur 175 176#define SHRINK xmlParserInputShrink(ctxt->input) 177 178#define GROW xmlParserInputGrow(ctxt->input, INPUT_CHUNK) 179 180#define CURRENT ((int) (*ctxt->input->cur)) 181 182#define SKIP_BLANKS docbSkipBlankChars(ctxt) 183 184/* Imported from XML */ 185 186/* #define CUR (ctxt->token ? ctxt->token : (int) (*ctxt->input->cur)) */ 187#define CUR ((int) (*ctxt->input->cur)) 188#define NEXT xmlNextChar(ctxt),ctxt->nbChars++ 189 190#define RAW (ctxt->token ? -1 : (*ctxt->input->cur)) 191#define NXT(val) ctxt->input->cur[(val)] 192#define CUR_PTR ctxt->input->cur 193 194 195#define NEXTL(l) do { \ 196 if (*(ctxt->input->cur) == '\n') { \ 197 ctxt->input->line++; ctxt->input->col = 1; \ 198 } else ctxt->input->col++; \ 199 ctxt->token = 0; ctxt->input->cur += l; ctxt->nbChars++; \ 200 } while (0) 201 202/************ 203 \ 204 if (*ctxt->input->cur == '%') xmlParserHandlePEReference(ctxt); \ 205 if (*ctxt->input->cur == '&') xmlParserHandleReference(ctxt); 206 ************/ 207 208#define CUR_CHAR(l) docbCurrentChar(ctxt, &l) 209#define CUR_SCHAR(s, l) xmlStringCurrentChar(ctxt, s, &l) 210 211#define COPY_BUF(l,b,i,v) \ 212 if (l == 1) b[i++] = (xmlChar) v; \ 213 else i += xmlCopyChar(l,&b[i],v) 214 215/** 216 * docbCurrentChar: 217 * @ctxt: the DocBook SGML parser context 218 * @len: pointer to the length of the char read 219 * 220 * The current char value, if using UTF-8 this may actaully span multiple 221 * bytes in the input buffer. Implement the end of line normalization: 222 * 2.11 End-of-Line Handling 223 * If the encoding is unspecified, in the case we find an ISO-Latin-1 224 * char, then the encoding converter is plugged in automatically. 225 * 226 * Returns the current char value and its lenght 227 */ 228 229static int 230docbCurrentChar(xmlParserCtxtPtr ctxt, int *len) { 231 if (ctxt->instate == XML_PARSER_EOF) 232 return(0); 233 234 if (ctxt->token != 0) { 235 *len = 0; 236 return(ctxt->token); 237 } 238 if (ctxt->charset == XML_CHAR_ENCODING_UTF8) { 239 /* 240 * We are supposed to handle UTF8, check it's valid 241 * From rfc2044: encoding of the Unicode values on UTF-8: 242 * 243 * UCS-4 range (hex.) UTF-8 octet sequence (binary) 244 * 0000 0000-0000 007F 0xxxxxxx 245 * 0000 0080-0000 07FF 110xxxxx 10xxxxxx 246 * 0000 0800-0000 FFFF 1110xxxx 10xxxxxx 10xxxxxx 247 * 248 * Check for the 0x110000 limit too 249 */ 250 const unsigned char *cur = ctxt->input->cur; 251 unsigned char c; 252 unsigned int val; 253 254 c = *cur; 255 if (c & 0x80) { 256 if (cur[1] == 0) 257 xmlParserInputGrow(ctxt->input, INPUT_CHUNK); 258 if ((cur[1] & 0xc0) != 0x80) 259 goto encoding_error; 260 if ((c & 0xe0) == 0xe0) { 261 262 if (cur[2] == 0) 263 xmlParserInputGrow(ctxt->input, INPUT_CHUNK); 264 if ((cur[2] & 0xc0) != 0x80) 265 goto encoding_error; 266 if ((c & 0xf0) == 0xf0) { 267 if (cur[3] == 0) 268 xmlParserInputGrow(ctxt->input, INPUT_CHUNK); 269 if (((c & 0xf8) != 0xf0) || 270 ((cur[3] & 0xc0) != 0x80)) 271 goto encoding_error; 272 /* 4-byte code */ 273 *len = 4; 274 val = (cur[0] & 0x7) << 18; 275 val |= (cur[1] & 0x3f) << 12; 276 val |= (cur[2] & 0x3f) << 6; 277 val |= cur[3] & 0x3f; 278 } else { 279 /* 3-byte code */ 280 *len = 3; 281 val = (cur[0] & 0xf) << 12; 282 val |= (cur[1] & 0x3f) << 6; 283 val |= cur[2] & 0x3f; 284 } 285 } else { 286 /* 2-byte code */ 287 *len = 2; 288 val = (cur[0] & 0x1f) << 6; 289 val |= cur[1] & 0x3f; 290 } 291 if (!IS_CHAR(val)) { 292 ctxt->errNo = XML_ERR_INVALID_ENCODING; 293 if ((ctxt->sax != NULL) && 294 (ctxt->sax->error != NULL)) 295 ctxt->sax->error(ctxt->userData, 296 "Char 0x%X out of allowed range\n", val); 297 ctxt->wellFormed = 0; 298 ctxt->disableSAX = 1; 299 } 300 return(val); 301 } else { 302 /* 1-byte code */ 303 *len = 1; 304 return((int) *ctxt->input->cur); 305 } 306 } 307 /* 308 * Assume it's a fixed lenght encoding (1) with 309 * a compatibke encoding for the ASCII set, since 310 * XML constructs only use < 128 chars 311 */ 312 *len = 1; 313 if ((int) *ctxt->input->cur < 0x80) 314 return((int) *ctxt->input->cur); 315 316 /* 317 * Humm this is bad, do an automatic flow conversion 318 */ 319 xmlSwitchEncoding(ctxt, XML_CHAR_ENCODING_8859_1); 320 ctxt->charset = XML_CHAR_ENCODING_UTF8; 321 return(xmlCurrentChar(ctxt, len)); 322 323encoding_error: 324 /* 325 * If we detect an UTF8 error that probably mean that the 326 * input encoding didn't get properly advertized in the 327 * declaration header. Report the error and switch the encoding 328 * to ISO-Latin-1 (if you don't like this policy, just declare the 329 * encoding !) 330 */ 331 ctxt->errNo = XML_ERR_INVALID_ENCODING; 332 if ((ctxt->sax != NULL) && (ctxt->sax->error != NULL)) { 333 ctxt->sax->error(ctxt->userData, 334 "Input is not proper UTF-8, indicate encoding !\n"); 335 ctxt->sax->error(ctxt->userData, "Bytes: 0x%02X 0x%02X 0x%02X 0x%02X\n", 336 ctxt->input->cur[0], ctxt->input->cur[1], 337 ctxt->input->cur[2], ctxt->input->cur[3]); 338 } 339 340 ctxt->charset = XML_CHAR_ENCODING_8859_1; 341 *len = 1; 342 return((int) *ctxt->input->cur); 343} 344 345#if 0 346/** 347 * sgmlNextChar: 348 * @ctxt: the DocBook SGML parser context 349 * 350 * Skip to the next char input char. 351 */ 352 353static void 354sgmlNextChar(docbParserCtxtPtr ctxt) { 355 if (ctxt->instate == XML_PARSER_EOF) 356 return; 357 if ((*ctxt->input->cur == 0) && 358 (xmlParserInputGrow(ctxt->input, INPUT_CHUNK) <= 0)) { 359 xmlPopInput(ctxt); 360 } else { 361 if (*(ctxt->input->cur) == '\n') { 362 ctxt->input->line++; ctxt->input->col = 1; 363 } else ctxt->input->col++; 364 ctxt->input->cur++; 365 ctxt->nbChars++; 366 if (*ctxt->input->cur == 0) 367 xmlParserInputGrow(ctxt->input, INPUT_CHUNK); 368 } 369} 370#endif 371 372/** 373 * docbSkipBlankChars: 374 * @ctxt: the DocBook SGML parser context 375 * 376 * skip all blanks character found at that point in the input streams. 377 * 378 * Returns the number of space chars skipped 379 */ 380 381static int 382docbSkipBlankChars(xmlParserCtxtPtr ctxt) { 383 int res = 0; 384 385 while (IS_BLANK(*(ctxt->input->cur))) { 386 if ((*ctxt->input->cur == 0) && 387 (xmlParserInputGrow(ctxt->input, INPUT_CHUNK) <= 0)) { 388 xmlPopInput(ctxt); 389 } else { 390 if (*(ctxt->input->cur) == '\n') { 391 ctxt->input->line++; ctxt->input->col = 1; 392 } else ctxt->input->col++; 393 ctxt->input->cur++; 394 ctxt->nbChars++; 395 if (*ctxt->input->cur == 0) 396 xmlParserInputGrow(ctxt->input, INPUT_CHUNK); 397 } 398 res++; 399 } 400 return(res); 401} 402 403 404 405/************************************************************************ 406 * * 407 * The list of SGML elements and their properties * 408 * * 409 ************************************************************************/ 410 411/* 412 * Start Tag: 1 means the start tag can be ommited 413 * End Tag: 1 means the end tag can be ommited 414 * 2 means it's forbidden (empty elements) 415 * Depr: this element is deprecated 416 * DTD: 1 means that this element is valid only in the Loose DTD 417 * 2 means that this element is valid only in the Frameset DTD 418 * 419 * Name,Start Tag,End Tag, Empty, Depr., DTD, Description 420 */ 421static docbElemDesc 422docbookElementTable[] = { 423{ "abbrev", 0, 0, 0, 3, 0, "" }, /* word */ 424{ "abstract", 0, 0, 0, 9, 0, "" }, /* title */ 425{ "accel", 0, 0, 0, 7, 0, "" }, /* smallcptr */ 426{ "ackno", 0, 0, 0, 4, 0, "" }, /* docinfo */ 427{ "acronym", 0, 0, 0, 3, 0, "" }, /* word */ 428{ "action", 0, 0, 0, 7, 0, "" }, /* smallcptr */ 429{ "address", 0, 0, 0, 1, 0, "" }, 430{ "affiliation",0, 0, 0, 9, 0, "" }, /* shortaffil */ 431{ "alt", 0, 0, 0, 1, 0, "" }, 432{ "anchor", 0, 2, 1, 0, 0, "" }, 433{ "answer", 0, 0, 0, 9, 0, "" }, /* label */ 434{ "appendix", 0, 0, 0, 9, 0, "" }, /* appendixinfo */ 435{ "appendixinfo",0, 0, 0, 9, 0, "" }, /* graphic */ 436{ "application",0, 0, 0, 2, 0, "" }, /* para */ 437{ "area", 0, 2, 1, 0, 0, "" }, 438{ "areaset", 0, 0, 0, 9, 0, "" }, /* area */ 439{ "areaspec", 0, 0, 0, 9, 0, "" }, /* area */ 440{ "arg", 0, 0, 0, 1, 0, "" }, 441{ "article", 0, 0, 0, 9, 0, "" }, /* div.title.content */ 442{ "articleinfo",0, 0, 0, 9, 0, "" }, /* graphic */ 443{ "artpagenums",0, 0, 0, 4, 0, "" }, /* docinfo */ 444{ "attribution",0, 0, 0, 2, 0, "" }, /* para */ 445{ "audiodata", 0, 2, 1, 0, 0, "" }, 446{ "audioobject",0, 0, 0, 9, 0, "" }, /* objectinfo */ 447{ "authorblurb",0, 0, 0, 9, 0, "" }, /* title */ 448{ "authorgroup",0, 0, 0, 9, 0, "" }, /* author */ 449{ "authorinitials",0, 0, 0, 4, 0, "" }, /* docinfo */ 450{ "author", 0, 0, 0, 9, 0, "" }, /* person.ident.mix */ 451{ "beginpage", 0, 2, 1, 0, 0, "" }, 452{ "bibliodiv", 0, 0, 0, 9, 0, "" }, /* sect.title.content */ 453{ "biblioentry",0, 0, 0, 9, 0, "" }, /* articleinfo */ 454{ "bibliography",0, 0, 0, 9, 0, "" }, /* bibliographyinfo */ 455{ "bibliographyinfo",0, 0, 0, 9, 0, "" }, /* graphic */ 456{ "bibliomisc", 0, 0, 0, 2, 0, "" }, /* para */ 457{ "bibliomixed",0, 0, 0, 1, 0, "" }, /* %bibliocomponent.mix, bibliomset) */ 458{ "bibliomset", 0, 0, 0, 1, 0, "" }, /* %bibliocomponent.mix; | bibliomset) */ 459{ "biblioset", 0, 0, 0, 9, 0, "" }, /* bibliocomponent.mix */ 460{ "blockquote", 0, 0, 0, 9, 0, "" }, /* title */ 461{ "book", 0, 0, 0, 9, 0, "" }, /* div.title.content */ 462{ "bookinfo", 0, 0, 0, 9, 0, "" }, /* graphic */ 463{ "bridgehead", 0, 0, 0, 8, 0, "" }, /* title */ 464{ "callout", 0, 0, 0, 9, 0, "" }, /* component.mix */ 465{ "calloutlist",0, 0, 0, 9, 0, "" }, /* formalobject.title.content */ 466{ "caption", 0, 0, 0, 9, 0, "" }, /* textobject.mix */ 467{ "caution", 0, 0, 0, 9, 0, "" }, /* title */ 468{ "chapter", 0, 0, 0, 9, 0, "" }, /* chapterinfo */ 469{ "chapterinfo",0, 0, 0, 9, 0, "" }, /* graphic */ 470{ "citation", 0, 0, 0, 2, 0, "" }, /* para */ 471{ "citerefentry",0, 0, 0, 9, 0, "" }, /* refentrytitle */ 472{ "citetitle", 0, 0, 0, 2, 0, "" }, /* para */ 473{ "city", 0, 0, 0, 4, 0, "" }, /* docinfo */ 474{ "classname", 0, 0, 0, 7, 0, "" }, /* smallcptr */ 475{ "classsynopsisinfo",0,0, 0, 9, 0, "" }, /* cptr */ 476{ "classsynopsis",0, 0, 0, 9, 0, "" }, /* ooclass */ 477{ "cmdsynopsis",0, 0, 0, 9, 0, "" }, /* command */ 478{ "co", 0, 2, 1, 0, 0, "" }, 479{ "collab", 0, 0, 0, 9, 0, "" }, /* collabname */ 480{ "collabname", 0, 0, 0, 4, 0, "" }, /* docinfo */ 481{ "colophon", 0, 0, 0, 9, 0, "" }, /* sect.title.content */ 482{ "colspec", 0, 2, 1, 0, 0, "" }, 483{ "colspec", 0, 2, 1, 0, 0, "" }, 484{ "command", 0, 0, 0, 9, 0, "" }, /* cptr */ 485{ "computeroutput",0, 0, 0, 9, 0, "" }, /* cptr */ 486{ "confdates", 0, 0, 0, 4, 0, "" }, /* docinfo */ 487{ "confgroup", 0, 0, 0, 9, 0, "" }, /* confdates */ 488{ "confnum", 0, 0, 0, 4, 0, "" }, /* docinfo */ 489{ "confsponsor",0, 0, 0, 4, 0, "" }, /* docinfo */ 490{ "conftitle", 0, 0, 0, 4, 0, "" }, /* docinfo */ 491{ "constant", 0, 0, 0, 7, 0, "" }, /* smallcptr */ 492{ "constructorsynopsis",0,0, 0, 9, 0, "" }, /* modifier */ 493{ "contractnum",0, 0, 0, 4, 0, "" }, /* docinfo */ 494{ "contractsponsor",0, 0, 0, 4, 0, "" }, /* docinfo */ 495{ "contrib", 0, 0, 0, 4, 0, "" }, /* docinfo */ 496{ "copyright", 0, 0, 0, 9, 0, "" }, /* year */ 497{ "corpauthor", 0, 0, 0, 4, 0, "" }, /* docinfo */ 498{ "corpname", 0, 0, 0, 4, 0, "" }, /* docinfo */ 499{ "country", 0, 0, 0, 4, 0, "" }, /* docinfo */ 500{ "database", 0, 0, 0, 7, 0, "" }, /* smallcptr */ 501{ "date", 0, 0, 0, 4, 0, "" }, /* docinfo */ 502{ "dedication", 0, 0, 0, 9, 0, "" }, /* sect.title.content */ 503{ "destructorsynopsis",0,0, 0, 9, 0, "" }, /* modifier */ 504{ "edition", 0, 0, 0, 4, 0, "" }, /* docinfo */ 505{ "editor", 0, 0, 0, 9, 0, "" }, /* person.ident.mix */ 506{ "email", 0, 0, 0, 4, 0, "" }, /* docinfo */ 507{ "emphasis", 0, 0, 0, 2, 0, "" }, /* para */ 508{ "entry", 0, 0, 0, 9, 0, "" }, /* tbl.entry.mdl */ 509{ "entrytbl", 0, 0, 0, 9, 0, "" }, /* tbl.entrytbl.mdl */ 510{ "envar", 0, 0, 0, 7, 0, "" }, /* smallcptr */ 511{ "epigraph", 0, 0, 0, 9, 0, "" }, /* attribution */ 512{ "equation", 0, 0, 0, 9, 0, "" }, /* formalobject.title.content */ 513{ "errorcode", 0, 0, 0, 7, 0, "" }, /* smallcptr */ 514{ "errorname", 0, 0, 0, 7, 0, "" }, /* smallcptr */ 515{ "errortype", 0, 0, 0, 7, 0, "" }, /* smallcptr */ 516{ "example", 0, 0, 0, 9, 0, "" }, /* formalobject.title.content */ 517{ "exceptionname",0, 0, 0, 7, 0, "" }, /* smallcptr */ 518{ "fax", 0, 0, 0, 4, 0, "" }, /* docinfo */ 519{ "fieldsynopsis", 0, 0, 0, 9, 0, "" }, /* modifier */ 520{ "figure", 0, 0, 0, 9, 0, "" }, /* formalobject.title.content */ 521{ "filename", 0, 0, 0, 7, 0, "" }, /* smallcptr */ 522{ "firstname", 0, 0, 0, 4, 0, "" }, /* docinfo */ 523{ "firstterm", 0, 0, 0, 3, 0, "" }, /* word */ 524{ "footnote", 0, 0, 0, 9, 0, "" }, /* footnote.mix */ 525{ "footnoteref",0, 2, 1, 0, 0, "" }, 526{ "foreignphrase",0, 0, 0, 2, 0, "" }, /* para */ 527{ "formalpara", 0, 0, 0, 9, 0, "" }, /* title */ 528{ "funcdef", 0, 0, 0, 1, 0, "" }, 529{ "funcparams", 0, 0, 0, 9, 0, "" }, /* cptr */ 530{ "funcprototype",0, 0, 0, 9, 0, "" }, /* funcdef */ 531{ "funcsynopsis",0, 0, 0, 9, 0, "" }, /* funcsynopsisinfo */ 532{ "funcsynopsisinfo", 0, 0, 0, 9, 0, "" }, /* cptr */ 533{ "function", 0, 0, 0, 9, 0, "" }, /* cptr */ 534{ "glossary", 0, 0, 0, 9, 0, "" }, /* glossaryinfo */ 535{ "glossaryinfo",0, 0, 0, 9, 0, "" }, /* graphic */ 536{ "glossdef", 0, 0, 0, 9, 0, "" }, /* glossdef.mix */ 537{ "glossdiv", 0, 0, 0, 9, 0, "" }, /* sect.title.content */ 538{ "glossentry", 0, 0, 0, 9, 0, "" }, /* glossterm */ 539{ "glosslist", 0, 0, 0, 9, 0, "" }, /* glossentry */ 540{ "glossseealso",0, 0, 0, 2, 0, "" }, /* para */ 541{ "glosssee", 0, 0, 0, 2, 0, "" }, /* para */ 542{ "glossterm", 0, 0, 0, 2, 0, "" }, /* para */ 543{ "graphic", 0, 2, 1, 0, 0, "" }, 544{ "graphicco", 0, 0, 0, 9, 0, "" }, /* areaspec */ 545{ "group", 0, 0, 0, 9, 0, "" }, /* arg */ 546{ "guibutton", 0, 0, 0, 7, 0, "" }, /* smallcptr */ 547{ "guiicon", 0, 0, 0, 7, 0, "" }, /* smallcptr */ 548{ "guilabel", 0, 0, 0, 7, 0, "" }, /* smallcptr */ 549{ "guimenuitem",0, 0, 0, 7, 0, "" }, /* smallcptr */ 550{ "guimenu", 0, 0, 0, 7, 0, "" }, /* smallcptr */ 551{ "guisubmenu", 0, 0, 0, 7, 0, "" }, /* smallcptr */ 552{ "hardware", 0, 0, 0, 7, 0, "" }, /* smallcptr */ 553{ "highlights", 0, 0, 0, 9, 0, "" }, /* highlights.mix */ 554{ "holder", 0, 0, 0, 4, 0, "" }, /* docinfo */ 555{ "honorific", 0, 0, 0, 4, 0, "" }, /* docinfo */ 556{ "imagedata", 0, 2, 1, 0, 0, "" }, 557{ "imageobjectco",0, 0, 0, 9, 0, "" }, /* areaspec */ 558{ "imageobject",0, 0, 0, 9, 0, "" }, /* objectinfo */ 559{ "important", 0, 0, 0, 9, 0, "" }, /* title */ 560{ "indexdiv", 0, 0, 0, 9, 0, "" }, /* sect.title.content */ 561{ "indexentry", 0, 0, 0, 9, 0, "" }, /* primaryie */ 562{ "index", 0, 0, 0, 9, 0, "" }, /* indexinfo */ 563{ "indexinfo", 0, 0, 0, 9, 0, "" }, /* graphic */ 564{ "indexterm", 0, 0, 0, 9, 0, "" }, /* primary */ 565{ "informalequation",0, 0, 0, 9, 0, "" }, /* equation.content */ 566{ "informalexample",0, 0, 0, 9, 0, "" }, /* example.mix */ 567{ "informalfigure",0, 0, 0, 9, 0, "" }, /* figure.mix */ 568{ "informaltable",0, 0, 0, 9, 0, "" }, /* graphic */ 569{ "initializer",0, 0, 0, 7, 0, "" }, /* smallcptr */ 570{ "inlineequation",0, 0, 0, 9, 0, "" }, /* inlineequation.content */ 571{ "inlinegraphic",0, 2, 1, 0, 0, "" }, 572{ "inlinemediaobject",0,0, 0, 9, 0, "" }, /* objectinfo */ 573{ "interfacename",0, 0, 0, 7, 0, "" }, /* smallcptr */ 574{ "interface", 0, 0, 0, 7, 0, "" }, /* smallcptr */ 575{ "invpartnumber",0, 0, 0, 4, 0, "" }, /* docinfo */ 576{ "isbn", 0, 0, 0, 4, 0, "" }, /* docinfo */ 577{ "issn", 0, 0, 0, 4, 0, "" }, /* docinfo */ 578{ "issuenum", 0, 0, 0, 4, 0, "" }, /* docinfo */ 579{ "itemizedlist",0, 0, 0, 9, 0, "" }, /* formalobject.title.content */ 580{ "itermset", 0, 0, 0, 9, 0, "" }, /* indexterm */ 581{ "jobtitle", 0, 0, 0, 4, 0, "" }, /* docinfo */ 582{ "keycap", 0, 0, 0, 7, 0, "" }, /* smallcptr */ 583{ "keycode", 0, 0, 0, 7, 0, "" }, /* smallcptr */ 584{ "keycombo", 0, 0, 0, 9, 0, "" }, /* keycap */ 585{ "keysym", 0, 0, 0, 7, 0, "" }, /* smallcptr */ 586{ "keyword", 0, 0, 0, 1, 0, "" }, 587{ "keywordset", 0, 0, 0, 9, 0, "" }, /* keyword */ 588{ "label", 0, 0, 0, 3, 0, "" }, /* word */ 589{ "legalnotice",0, 0, 0, 9, 0, "" }, /* title */ 590{ "lineage", 0, 0, 0, 4, 0, "" }, /* docinfo */ 591{ "lineannotation",0, 0, 0, 2, 0, "" }, /* para */ 592{ "link", 0, 0, 0, 2, 0, "" }, /* para */ 593{ "listitem", 0, 0, 0, 9, 0, "" }, /* component.mix */ 594{ "literal", 0, 0, 0, 9, 0, "" }, /* cptr */ 595{ "literallayout",0, 0, 0, 2, 0, "" }, /* para */ 596{ "lot", 0, 0, 0, 9, 0, "" }, /* bookcomponent.title.content */ 597{ "lotentry", 0, 0, 0, 2, 0, "" }, /* para */ 598{ "manvolnum", 0, 0, 0, 3, 0, "" }, /* word */ 599{ "markup", 0, 0, 0, 7, 0, "" }, /* smallcptr */ 600{ "medialabel", 0, 0, 0, 7, 0, "" }, /* smallcptr */ 601{ "mediaobjectco",0, 0, 0, 9, 0, "" }, /* objectinfo */ 602{ "mediaobject",0, 0, 0, 9, 0, "" }, /* objectinfo */ 603{ "member", 0, 0, 0, 2, 0, "" }, /* para */ 604{ "menuchoice", 0, 0, 0, 9, 0, "" }, /* shortcut */ 605{ "methodname", 0, 0, 0, 7, 0, "" }, /* smallcptr */ 606{ "methodparam",0, 0, 0, 9, 0, "" }, /* modifier */ 607{ "methodsynopsis",0, 0, 0, 9, 0, "" }, /* modifier */ 608{ "modespec", 0, 0, 0, 4, 0, "" }, /* docinfo */ 609{ "modifier", 0, 0, 0, 7, 0, "" }, /* smallcptr */ 610{ "mousebutton",0, 0, 0, 7, 0, "" }, /* smallcptr */ 611{ "msgaud", 0, 0, 0, 2, 0, "" }, /* para */ 612{ "msgentry", 0, 0, 0, 9, 0, "" }, /* msg */ 613{ "msgexplan", 0, 0, 0, 9, 0, "" }, /* title */ 614{ "msginfo", 0, 0, 0, 9, 0, "" }, /* msglevel */ 615{ "msglevel", 0, 0, 0, 7, 0, "" }, /* smallcptr */ 616{ "msgmain", 0, 0, 0, 9, 0, "" }, /* title */ 617{ "msgorig", 0, 0, 0, 7, 0, "" }, /* smallcptr */ 618{ "msgrel", 0, 0, 0, 9, 0, "" }, /* title */ 619{ "msgset", 0, 0, 0, 9, 0, "" }, /* formalobject.title.content */ 620{ "msgsub", 0, 0, 0, 9, 0, "" }, /* title */ 621{ "msgtext", 0, 0, 0, 9, 0, "" }, /* component.mix */ 622{ "msg", 0, 0, 0, 9, 0, "" }, /* title */ 623{ "note", 0, 0, 0, 9, 0, "" }, /* title */ 624{ "objectinfo", 0, 0, 0, 9, 0, "" }, /* graphic */ 625{ "olink", 0, 0, 0, 2, 0, "" }, /* para */ 626{ "ooclass", 0, 0, 0, 9, 0, "" }, /* modifier */ 627{ "ooexception",0, 0, 0, 9, 0, "" }, /* modifier */ 628{ "oointerface",0, 0, 0, 9, 0, "" }, /* modifier */ 629{ "optional", 0, 0, 0, 9, 0, "" }, /* cptr */ 630{ "option", 0, 0, 0, 7, 0, "" }, /* smallcptr */ 631{ "orderedlist",0, 0, 0, 9, 0, "" }, /* formalobject.title.content */ 632{ "orgdiv", 0, 0, 0, 4, 0, "" }, /* docinfo */ 633{ "orgname", 0, 0, 0, 4, 0, "" }, /* docinfo */ 634{ "otheraddr", 0, 0, 0, 4, 0, "" }, /* docinfo */ 635{ "othercredit",0, 0, 0, 9, 0, "" }, /* person.ident.mix */ 636{ "othername", 0, 0, 0, 4, 0, "" }, /* docinfo */ 637{ "pagenums", 0, 0, 0, 4, 0, "" }, /* docinfo */ 638{ "paramdef", 0, 0, 0, 1, 0, "" }, 639{ "parameter", 0, 0, 0, 7, 0, "" }, /* smallcptr */ 640{ "para", 0, 0, 0, 2, 0, "" }, /* para */ 641{ "partinfo", 0, 0, 0, 9, 0, "" }, /* graphic */ 642{ "partintro", 0, 0, 0, 9, 0, "" }, /* div.title.content */ 643{ "part", 0, 0, 0, 9, 0, "" }, /* partinfo */ 644{ "phone", 0, 0, 0, 4, 0, "" }, /* docinfo */ 645{ "phrase", 0, 0, 0, 2, 0, "" }, /* para */ 646{ "pob", 0, 0, 0, 4, 0, "" }, /* docinfo */ 647{ "postcode", 0, 0, 0, 4, 0, "" }, /* docinfo */ 648{ "prefaceinfo",0, 0, 0, 9, 0, "" }, /* graphic */ 649{ "preface", 0, 0, 0, 9, 0, "" }, /* prefaceinfo */ 650{ "primaryie", 0, 0, 0, 4, 0, "" }, /* ndxterm */ 651{ "primary ", 0, 0, 0, 4, 0, "" }, /* ndxterm */ 652{ "printhistory",0, 0, 0, 9, 0, "" }, /* para.class */ 653{ "procedure", 0, 0, 0, 9, 0, "" }, /* formalobject.title.content */ 654{ "productname",0, 0, 0, 2, 0, "" }, /* para */ 655{ "productnumber",0, 0, 0, 4, 0, "" }, /* docinfo */ 656{ "programlistingco",0, 0, 0, 9, 0, "" }, /* areaspec */ 657{ "programlisting",0, 0, 0, 2, 0, "" }, /* para */ 658{ "prompt", 0, 0, 0, 7, 0, "" }, /* smallcptr */ 659{ "property", 0, 0, 0, 7, 0, "" }, /* smallcptr */ 660{ "pubdate", 0, 0, 0, 4, 0, "" }, /* docinfo */ 661{ "publishername",0, 0, 0, 4, 0, "" }, /* docinfo */ 662{ "publisher", 0, 0, 0, 9, 0, "" }, /* publishername */ 663{ "pubsnumber", 0, 0, 0, 4, 0, "" }, /* docinfo */ 664{ "qandadiv", 0, 0, 0, 9, 0, "" }, /* formalobject.title.content */ 665{ "qandaentry", 0, 0, 0, 9, 0, "" }, /* revhistory */ 666{ "qandaset", 0, 0, 0, 9, 0, "" }, /* formalobject.title.content */ 667{ "question", 0, 0, 0, 9, 0, "" }, /* label */ 668{ "quote", 0, 0, 0, 2, 0, "" }, /* para */ 669{ "refclass", 0, 0, 0, 9, 0, "" }, /* refclass.char.mix */ 670{ "refdescriptor",0, 0, 0, 9, 0, "" }, /* refname.char.mix */ 671{ "refentryinfo",0, 0, 0, 9, 0, "" }, /* graphic */ 672{ "refentry", 0, 0, 0, 9, 0, "" }, /* ndxterm.class */ 673{ "refentrytitle",0, 0, 0, 2, 0, "" }, /* para */ 674{ "referenceinfo",0, 0, 0, 9, 0, "" }, /* graphic */ 675{ "reference", 0, 0, 0, 9, 0, "" }, /* referenceinfo */ 676{ "refmeta", 0, 0, 0, 9, 0, "" }, /* ndxterm.class */ 677{ "refmiscinfo",0, 0, 0, 4, 0, "" }, /* docinfo */ 678{ "refnamediv", 0, 0, 0, 9, 0, "" }, /* refdescriptor */ 679{ "refname", 0, 0, 0, 9, 0, "" }, /* refname.char.mix */ 680{ "refpurpose", 0, 0, 0, 9, 0, "" }, /* refinline.char.mix */ 681{ "refsect1info",0, 0, 0, 9, 0, "" }, /* graphic */ 682{ "refsect1", 0, 0, 0, 9, 0, "" }, /* refsect */ 683{ "refsect2info",0, 0, 0, 9, 0, "" }, /* graphic */ 684{ "refsect2", 0, 0, 0, 9, 0, "" }, /* refsect */ 685{ "refsect3info",0, 0, 0, 9, 0, "" }, /* graphic */ 686{ "refsect3", 0, 0, 0, 9, 0, "" }, /* refsect */ 687{ "refsynopsisdivinfo",0,0, 0, 9, 0, "" }, /* graphic */ 688{ "refsynopsisdiv",0, 0, 0, 9, 0, "" }, /* refsynopsisdivinfo */ 689{ "releaseinfo",0, 0, 0, 4, 0, "" }, /* docinfo */ 690{ "remark", 0, 0, 0, 2, 0, "" }, /* para */ 691{ "replaceable",0, 0, 0, 1, 0, "" }, 692{ "returnvalue",0, 0, 0, 7, 0, "" }, /* smallcptr */ 693{ "revdescription",0, 0, 0, 9, 0, "" }, /* revdescription.mix */ 694{ "revhistory", 0, 0, 0, 9, 0, "" }, /* revision */ 695{ "revision", 0, 0, 0, 9, 0, "" }, /* revnumber */ 696{ "revnumber", 0, 0, 0, 4, 0, "" }, /* docinfo */ 697{ "revremark", 0, 0, 0, 4, 0, "" }, /* docinfo */ 698{ "row", 0, 0, 0, 9, 0, "" }, /* tbl.row.mdl */ 699{ "row", 0, 0, 0, 9, 0, "" }, /* tbl.row.mdl */ 700{ "sbr", 0, 2, 1, 0, 0, "" }, 701{ "screenco", 0, 0, 0, 9, 0, "" }, /* areaspec */ 702{ "screeninfo", 0, 0, 0, 2, 0, "" }, /* para */ 703{ "screen", 0, 0, 0, 2, 0, "" }, /* para */ 704{ "screenshot", 0, 0, 0, 9, 0, "" }, /* screeninfo */ 705{ "secondaryie",0, 0, 0, 4, 0, "" }, /* ndxterm */ 706{ "secondary", 0, 0, 0, 4, 0, "" }, /* ndxterm */ 707{ "sect1info", 0, 0, 0, 9, 0, "" }, /* graphic */ 708{ "sect1", 0, 0, 0, 9, 0, "" }, /* sect */ 709{ "sect2info", 0, 0, 0, 9, 0, "" }, /* graphic */ 710{ "sect2", 0, 0, 0, 9, 0, "" }, /* sect */ 711{ "sect3info", 0, 0, 0, 9, 0, "" }, /* graphic */ 712{ "sect3", 0, 0, 0, 9, 0, "" }, /* sect */ 713{ "sect4info", 0, 0, 0, 9, 0, "" }, /* graphic */ 714{ "sect4", 0, 0, 0, 9, 0, "" }, /* sect */ 715{ "sect5info", 0, 0, 0, 9, 0, "" }, /* graphic */ 716{ "sect5", 0, 0, 0, 9, 0, "" }, /* sect */ 717{ "sectioninfo",0, 0, 0, 9, 0, "" }, /* graphic */ 718{ "section", 0, 0, 0, 9, 0, "" }, /* sectioninfo */ 719{ "seealsoie", 0, 0, 0, 4, 0, "" }, /* ndxterm */ 720{ "seealso", 0, 0, 0, 4, 0, "" }, /* ndxterm */ 721{ "seeie", 0, 0, 0, 4, 0, "" }, /* ndxterm */ 722{ "see", 0, 0, 0, 4, 0, "" }, /* ndxterm */ 723{ "seglistitem",0, 0, 0, 9, 0, "" }, /* seg */ 724{ "segmentedlist",0, 0, 0, 9, 0, "" }, /* formalobject.title.content */ 725{ "seg", 0, 0, 0, 2, 0, "" }, /* para */ 726{ "segtitle", 0, 0, 0, 8, 0, "" }, /* title */ 727{ "seriesvolnums", 0, 0, 0, 4, 0, "" }, /* docinfo */ 728{ "set", 0, 0, 0, 9, 0, "" }, /* div.title.content */ 729{ "setindexinfo",0, 0, 0, 9, 0, "" }, /* graphic */ 730{ "setindex", 0, 0, 0, 9, 0, "" }, /* setindexinfo */ 731{ "setinfo", 0, 0, 0, 9, 0, "" }, /* graphic */ 732{ "sgmltag", 0, 0, 0, 7, 0, "" }, /* smallcptr */ 733{ "shortaffil", 0, 0, 0, 4, 0, "" }, /* docinfo */ 734{ "shortcut", 0, 0, 0, 9, 0, "" }, /* keycap */ 735{ "sidebarinfo",0, 0, 0, 9, 0, "" }, /* graphic */ 736{ "sidebar", 0, 0, 0, 9, 0, "" }, /* sidebarinfo */ 737{ "simpara", 0, 0, 0, 2, 0, "" }, /* para */ 738{ "simplelist", 0, 0, 0, 9, 0, "" }, /* member */ 739{ "simplemsgentry", 0, 0, 0, 9, 0, "" }, /* msgtext */ 740{ "simplesect", 0, 0, 0, 9, 0, "" }, /* sect.title.content */ 741{ "spanspec", 0, 2, 1, 0, 0, "" }, 742{ "state", 0, 0, 0, 4, 0, "" }, /* docinfo */ 743{ "step", 0, 0, 0, 9, 0, "" }, /* title */ 744{ "street", 0, 0, 0, 4, 0, "" }, /* docinfo */ 745{ "structfield",0, 0, 0, 7, 0, "" }, /* smallcptr */ 746{ "structname", 0, 0, 0, 7, 0, "" }, /* smallcptr */ 747{ "subjectset", 0, 0, 0, 9, 0, "" }, /* subject */ 748{ "subject", 0, 0, 0, 9, 0, "" }, /* subjectterm */ 749{ "subjectterm",0, 0, 0, 1, 0, "" }, 750{ "subscript", 0, 0, 0, 1, 0, "" }, 751{ "substeps", 0, 0, 0, 9, 0, "" }, /* step */ 752{ "subtitle", 0, 0, 0, 8, 0, "" }, /* title */ 753{ "superscript", 0, 0, 0, 1, 0, "" }, 754{ "surname", 0, 0, 0, 4, 0, "" }, /* docinfo */ 755{ "symbol", 0, 0, 0, 7, 0, "" }, /* smallcptr */ 756{ "synopfragment", 0, 0, 0, 9, 0, "" }, /* arg */ 757{ "synopfragmentref", 0, 0, 0, 1, 0, "" }, 758{ "synopsis", 0, 0, 0, 2, 0, "" }, /* para */ 759{ "systemitem", 0, 0, 0, 7, 0, "" }, /* smallcptr */ 760{ "table", 0, 0, 0, 9, 0, "" }, /* tbl.table.mdl */ 761/* { "%tbl.table.name;", 0, 0, 0, 9, 0, "" },*/ /* tbl.table.mdl */ 762{ "tbody", 0, 0, 0, 9, 0, "" }, /* row */ 763{ "tbody", 0, 0, 0, 9, 0, "" }, /* row */ 764{ "term", 0, 0, 0, 2, 0, "" }, /* para */ 765{ "tertiaryie", 0, 0, 0, 4, 0, "" }, /* ndxterm */ 766{ "tertiary ", 0, 0, 0, 4, 0, "" }, /* ndxterm */ 767{ "textobject", 0, 0, 0, 9, 0, "" }, /* objectinfo */ 768{ "tfoot", 0, 0, 0, 9, 0, "" }, /* tbl.hdft.mdl */ 769{ "tgroup", 0, 0, 0, 9, 0, "" }, /* tbl.tgroup.mdl */ 770{ "tgroup", 0, 0, 0, 9, 0, "" }, /* tbl.tgroup.mdl */ 771{ "thead", 0, 0, 0, 9, 0, "" }, /* row */ 772{ "thead", 0, 0, 0, 9, 0, "" }, /* tbl.hdft.mdl */ 773{ "tip", 0, 0, 0, 9, 0, "" }, /* title */ 774{ "titleabbrev",0, 0, 0, 8, 0, "" }, /* title */ 775{ "title", 0, 0, 0, 8, 0, "" }, /* title */ 776{ "tocback", 0, 0, 0, 2, 0, "" }, /* para */ 777{ "toc", 0, 0, 0, 9, 0, "" }, /* bookcomponent.title.content */ 778{ "tocchap", 0, 0, 0, 9, 0, "" }, /* tocentry */ 779{ "tocentry", 0, 0, 0, 2, 0, "" }, /* para */ 780{ "tocfront", 0, 0, 0, 2, 0, "" }, /* para */ 781{ "toclevel1", 0, 0, 0, 9, 0, "" }, /* tocentry */ 782{ "toclevel2", 0, 0, 0, 9, 0, "" }, /* tocentry */ 783{ "toclevel3", 0, 0, 0, 9, 0, "" }, /* tocentry */ 784{ "toclevel4", 0, 0, 0, 9, 0, "" }, /* tocentry */ 785{ "toclevel5", 0, 0, 0, 9, 0, "" }, /* tocentry */ 786{ "tocpart", 0, 0, 0, 9, 0, "" }, /* tocentry */ 787{ "token", 0, 0, 0, 7, 0, "" }, /* smallcptr */ 788{ "trademark", 0, 0, 0, 1, 0, "" }, 789{ "type", 0, 0, 0, 7, 0, "" }, /* smallcptr */ 790{ "ulink", 0, 0, 0, 2, 0, "" }, /* para */ 791{ "userinput", 0, 0, 0, 9, 0, "" }, /* cptr */ 792{ "varargs", 0, 2, 1, 0, 0, "" }, 793{ "variablelist",0, 0, 0, 9, 0, "" }, /* formalobject.title.content */ 794{ "varlistentry",0, 0, 0, 9, 0, "" }, /* term */ 795{ "varname", 0, 0, 0, 7, 0, "" }, /* smallcptr */ 796{ "videodata", 0, 2, 1, 0, 0, "" }, 797{ "videoobject",0, 0, 0, 9, 0, "" }, /* objectinfo */ 798{ "void", 0, 2, 1, 0, 0, "" }, 799{ "volumenum", 0, 0, 0, 4, 0, "" }, /* docinfo */ 800{ "warning", 0, 0, 0, 9, 0, "" }, /* title */ 801{ "wordasword", 0, 0, 0, 3, 0, "" }, /* word */ 802{ "xref", 0, 2, 1, 0, 0, "" }, 803{ "year", 0, 0, 0, 4, 0, "" }, /* docinfo */ 804}; 805 806#if 0 807/* 808 * start tags that imply the end of a current element 809 * any tag of each line implies the end of the current element if the type of 810 * that element is in the same line 811 */ 812static const char *docbEquEnd[] = { 813"dt", "dd", "li", "option", NULL, 814"h1", "h2", "h3", "h4", "h5", "h6", NULL, 815"ol", "menu", "dir", "address", "pre", "listing", "xmp", NULL, 816NULL 817}; 818#endif 819 820/* 821 * acording the SGML DTD, HR should be added to the 2nd line above, as it 822 * is not allowed within a H1, H2, H3, etc. But we should tolerate that case 823 * because many documents contain rules in headings... 824 */ 825 826/* 827 * start tags that imply the end of current element 828 */ 829static const char *docbStartClose[] = { 830NULL 831}; 832 833/* 834 * The list of SGML elements which are supposed not to have 835 * CDATA content and where a p element will be implied 836 * 837 * TODO: extend that list by reading the SGML SGML DtD on 838 * implied paragraph 839 */ 840static char *docbNoContentElements[] = { 841 NULL 842}; 843 844 845static const char** docbStartCloseIndex[100]; 846static int docbStartCloseIndexinitialized = 0; 847 848/************************************************************************ 849 * * 850 * functions to handle SGML specific data * 851 * * 852 ************************************************************************/ 853 854/** 855 * docbInitAutoClose: 856 * 857 * Initialize the docbStartCloseIndex for fast lookup of closing tags names. 858 * 859 */ 860static void 861docbInitAutoClose(void) { 862 int indx, i = 0; 863 864 if (docbStartCloseIndexinitialized) return; 865 866 for (indx = 0;indx < 100;indx ++) docbStartCloseIndex[indx] = NULL; 867 indx = 0; 868 while ((docbStartClose[i] != NULL) && (indx < 100 - 1)) { 869 docbStartCloseIndex[indx++] = &docbStartClose[i]; 870 while (docbStartClose[i] != NULL) i++; 871 i++; 872 } 873} 874 875/** 876 * docbTagLookup: 877 * @tag: The tag name 878 * 879 * Lookup the SGML tag in the ElementTable 880 * 881 * Returns the related docbElemDescPtr or NULL if not found. 882 */ 883static docbElemDescPtr 884docbTagLookup(const xmlChar *tag) { 885 unsigned int i; 886 887 for (i = 0; i < (sizeof(docbookElementTable) / 888 sizeof(docbookElementTable[0]));i++) { 889 if (xmlStrEqual(tag, BAD_CAST docbookElementTable[i].name)) 890 return(&docbookElementTable[i]); 891 } 892 return(NULL); 893} 894 895/** 896 * docbCheckAutoClose: 897 * @newtag: The new tag name 898 * @oldtag: The old tag name 899 * 900 * Checks wether the new tag is one of the registered valid tags for closing old. 901 * Initialize the docbStartCloseIndex for fast lookup of closing tags names. 902 * 903 * Returns 0 if no, 1 if yes. 904 */ 905static int 906docbCheckAutoClose(const xmlChar *newtag, const xmlChar *oldtag) { 907 int i, indx; 908 const char **closed = NULL; 909 910 if (docbStartCloseIndexinitialized == 0) docbInitAutoClose(); 911 912 /* inefficient, but not a big deal */ 913 for (indx = 0; indx < 100;indx++) { 914 closed = docbStartCloseIndex[indx]; 915 if (closed == NULL) return(0); 916 if (xmlStrEqual(BAD_CAST *closed, newtag)) break; 917 } 918 919 i = closed - docbStartClose; 920 i++; 921 while (docbStartClose[i] != NULL) { 922 if (xmlStrEqual(BAD_CAST docbStartClose[i], oldtag)) { 923 return(1); 924 } 925 i++; 926 } 927 return(0); 928} 929 930/** 931 * docbAutoCloseOnClose: 932 * @ctxt: an SGML parser context 933 * @newtag: The new tag name 934 * 935 * The HTmL DtD allows an ending tag to implicitely close other tags. 936 */ 937static void 938docbAutoCloseOnClose(docbParserCtxtPtr ctxt, const xmlChar *newtag) { 939 docbElemDescPtr info; 940 xmlChar *oldname; 941 int i; 942 943 if ((newtag[0] == '/') && (newtag[1] == 0)) 944 return; 945 946#ifdef DEBUG 947 xmlGenericError(xmlGenericErrorContext,"Close of %s stack: %d elements\n", newtag, ctxt->nameNr); 948 for (i = 0;i < ctxt->nameNr;i++) 949 xmlGenericError(xmlGenericErrorContext,"%d : %s\n", i, ctxt->nameTab[i]); 950#endif 951 952 for (i = (ctxt->nameNr - 1);i >= 0;i--) { 953 if (xmlStrEqual(newtag, ctxt->nameTab[i])) break; 954 } 955 if (i < 0) return; 956 957 while (!xmlStrEqual(newtag, ctxt->name)) { 958 info = docbTagLookup(ctxt->name); 959 if ((info == NULL) || (info->endTag == 1)) { 960#ifdef DEBUG 961 xmlGenericError(xmlGenericErrorContext,"docbAutoCloseOnClose: %s closes %s\n", newtag, ctxt->name); 962#endif 963 } else { 964 if ((ctxt->sax != NULL) && (ctxt->sax->error != NULL)) 965 ctxt->sax->error(ctxt->userData, 966 "Opening and ending tag mismatch: %s and %s\n", 967 newtag, ctxt->name); 968 ctxt->wellFormed = 0; 969 } 970 if ((ctxt->sax != NULL) && (ctxt->sax->endElement != NULL)) 971 ctxt->sax->endElement(ctxt->userData, ctxt->name); 972 oldname = docbnamePop(ctxt); 973 if (oldname != NULL) { 974#ifdef DEBUG 975 xmlGenericError(xmlGenericErrorContext,"docbAutoCloseOnClose: popped %s\n", oldname); 976#endif 977 xmlFree(oldname); 978 } 979 } 980} 981 982/** 983 * docbAutoClose: 984 * @ctxt: an SGML parser context 985 * @newtag: The new tag name or NULL 986 * 987 * The HTmL DtD allows a tag to implicitely close other tags. 988 * The list is kept in docbStartClose array. This function is 989 * called when a new tag has been detected and generates the 990 * appropriates closes if possible/needed. 991 * If newtag is NULL this mean we are at the end of the resource 992 * and we should check 993 */ 994static void 995docbAutoClose(docbParserCtxtPtr ctxt, const xmlChar *newtag) { 996 xmlChar *oldname; 997 while ((newtag != NULL) && (ctxt->name != NULL) && 998 (docbCheckAutoClose(newtag, ctxt->name))) { 999#ifdef DEBUG 1000 xmlGenericError(xmlGenericErrorContext,"docbAutoClose: %s closes %s\n", newtag, ctxt->name); 1001#endif 1002 if ((ctxt->sax != NULL) && (ctxt->sax->endElement != NULL)) 1003 ctxt->sax->endElement(ctxt->userData, ctxt->name); 1004 oldname = docbnamePop(ctxt); 1005 if (oldname != NULL) { 1006#ifdef DEBUG 1007 xmlGenericError(xmlGenericErrorContext,"docbAutoClose: popped %s\n", oldname); 1008#endif 1009 xmlFree(oldname); 1010 } 1011 } 1012} 1013 1014/** 1015 * docbAutoCloseTag: 1016 * @doc: the SGML document 1017 * @name: The tag name 1018 * @elem: the SGML element 1019 * 1020 * The HTmL DtD allows a tag to implicitely close other tags. 1021 * The list is kept in docbStartClose array. This function checks 1022 * if the element or one of it's children would autoclose the 1023 * given tag. 1024 * 1025 * Returns 1 if autoclose, 0 otherwise 1026 */ 1027static int 1028docbAutoCloseTag(docbDocPtr doc, const xmlChar *name, docbNodePtr elem) { 1029 docbNodePtr child; 1030 1031 if (elem == NULL) return(1); 1032 if (xmlStrEqual(name, elem->name)) return(0); 1033 if (docbCheckAutoClose(elem->name, name)) return(1); 1034 child = elem->children; 1035 while (child != NULL) { 1036 if (docbAutoCloseTag(doc, name, child)) return(1); 1037 child = child->next; 1038 } 1039 return(0); 1040} 1041 1042#if 0 1043/** 1044 * docbIsAutoClosed: 1045 * @doc: the SGML document 1046 * @elem: the SGML element 1047 * 1048 * The list is kept in docbStartClose array. This function checks 1049 * if a tag is autoclosed by one of it's child 1050 * 1051 * Returns 1 if autoclosed, 0 otherwise 1052 */ 1053static int 1054docbIsAutoClosed(docbDocPtr doc, docbNodePtr elem) { 1055 docbNodePtr child; 1056 1057 if (elem == NULL) return(1); 1058 child = elem->children; 1059 while (child != NULL) { 1060 if (docbAutoCloseTag(doc, elem->name, child)) return(1); 1061 child = child->next; 1062 } 1063 return(0); 1064} 1065#endif 1066 1067/** 1068 * docbCheckParagraph 1069 * @ctxt: an SGML parser context 1070 * 1071 * Check whether a p element need to be implied before inserting 1072 * characters in the current element. 1073 * 1074 * Returns 1 if a paragraph has been inserted, 0 if not and -1 1075 * in case of error. 1076 */ 1077 1078static int 1079docbCheckParagraph(docbParserCtxtPtr ctxt) { 1080 const xmlChar *tag; 1081 int i; 1082 1083 if (ctxt == NULL) 1084 return(-1); 1085 tag = ctxt->name; 1086 if (tag == NULL) { 1087 docbAutoClose(ctxt, BAD_CAST"p"); 1088 docbnamePush(ctxt, xmlStrdup(BAD_CAST"p")); 1089 if ((ctxt->sax != NULL) && (ctxt->sax->startElement != NULL)) 1090 ctxt->sax->startElement(ctxt->userData, BAD_CAST"p", NULL); 1091 return(1); 1092 } 1093 for (i = 0; docbNoContentElements[i] != NULL; i++) { 1094 if (xmlStrEqual(tag, BAD_CAST docbNoContentElements[i])) { 1095#ifdef DEBUG 1096 xmlGenericError(xmlGenericErrorContext,"Implied element paragraph\n"); 1097#endif 1098 docbAutoClose(ctxt, BAD_CAST"p"); 1099 docbnamePush(ctxt, xmlStrdup(BAD_CAST"p")); 1100 if ((ctxt->sax != NULL) && (ctxt->sax->startElement != NULL)) 1101 ctxt->sax->startElement(ctxt->userData, BAD_CAST"p", NULL); 1102 return(1); 1103 } 1104 } 1105 return(0); 1106} 1107 1108/************************************************************************ 1109 * * 1110 * The list of SGML predefined entities * 1111 * * 1112 ************************************************************************/ 1113 1114 1115static docbEntityDesc 1116docbookEntitiesTable[] = { 1117/* 1118 * the 4 absolute ones, plus apostrophe. 1119 */ 1120{ 0x0026, "amp", "AMPERSAND" }, 1121{ 0x003C, "lt", "LESS-THAN SIGN" }, 1122 1123/* 1124 * Converted with VI macros from docbook ent files 1125 */ 1126{ 0x0021, "excl", "EXCLAMATION MARK" }, 1127{ 0x0022, "quot", "QUOTATION MARK" }, 1128{ 0x0023, "num", "NUMBER SIGN" }, 1129{ 0x0024, "dollar", "DOLLAR SIGN" }, 1130{ 0x0025, "percnt", "PERCENT SIGN" }, 1131{ 0x0027, "apos", "APOSTROPHE" }, 1132{ 0x0028, "lpar", "LEFT PARENTHESIS" }, 1133{ 0x0029, "rpar", "RIGHT PARENTHESIS" }, 1134{ 0x002A, "ast", "ASTERISK OPERATOR" }, 1135{ 0x002B, "plus", "PLUS SIGN" }, 1136{ 0x002C, "comma", "COMMA" }, 1137{ 0x002D, "hyphen", "HYPHEN-MINUS" }, 1138{ 0x002E, "period", "FULL STOP" }, 1139{ 0x002F, "sol", "SOLIDUS" }, 1140{ 0x003A, "colon", "COLON" }, 1141{ 0x003B, "semi", "SEMICOLON" }, 1142{ 0x003D, "equals", "EQUALS SIGN" }, 1143{ 0x003E, "gt", "GREATER-THAN SIGN" }, 1144{ 0x003F, "quest", "QUESTION MARK" }, 1145{ 0x0040, "commat", "COMMERCIAL AT" }, 1146{ 0x005B, "lsqb", "LEFT SQUARE BRACKET" }, 1147{ 0x005C, "bsol", "REVERSE SOLIDUS" }, 1148{ 0x005D, "rsqb", "RIGHT SQUARE BRACKET" }, 1149{ 0x005E, "circ", "RING OPERATOR" }, 1150{ 0x005F, "lowbar", "LOW LINE" }, 1151{ 0x0060, "grave", "GRAVE ACCENT" }, 1152{ 0x007B, "lcub", "LEFT CURLY BRACKET" }, 1153{ 0x007C, "verbar", "VERTICAL LINE" }, 1154{ 0x007D, "rcub", "RIGHT CURLY BRACKET" }, 1155{ 0x00A0, "nbsp", "NO-BREAK SPACE" }, 1156{ 0x00A1, "iexcl", "INVERTED EXCLAMATION MARK" }, 1157{ 0x00A2, "cent", "CENT SIGN" }, 1158{ 0x00A3, "pound", "POUND SIGN" }, 1159{ 0x00A4, "curren", "CURRENCY SIGN" }, 1160{ 0x00A5, "yen", "YEN SIGN" }, 1161{ 0x00A6, "brvbar", "BROKEN BAR" }, 1162{ 0x00A7, "sect", "SECTION SIGN" }, 1163{ 0x00A8, "die", "" }, 1164{ 0x00A8, "Dot", "" }, 1165{ 0x00A8, "uml", "" }, 1166{ 0x00A9, "copy", "COPYRIGHT SIGN" }, 1167{ 0x00AA, "ordf", "FEMININE ORDINAL INDICATOR" }, 1168{ 0x00AB, "laquo", "LEFT-POINTING DOUBLE ANGLE QUOTATION MARK" }, 1169{ 0x00AC, "not", "NOT SIGN" }, 1170{ 0x00AD, "shy", "SOFT HYPHEN" }, 1171{ 0x00AE, "reg", "REG TRADE MARK SIGN" }, 1172{ 0x00AF, "macr", "MACRON" }, 1173{ 0x00B0, "deg", "DEGREE SIGN" }, 1174{ 0x00B1, "plusmn", "PLUS-MINUS SIGN" }, 1175{ 0x00B2, "sup2", "SUPERSCRIPT TWO" }, 1176{ 0x00B3, "sup3", "SUPERSCRIPT THREE" }, 1177{ 0x00B4, "acute", "ACUTE ACCENT" }, 1178{ 0x00B5, "micro", "MICRO SIGN" }, 1179{ 0x00B6, "para", "PILCROW SIGN" }, 1180{ 0x00B7, "middot", "MIDDLE DOT" }, 1181{ 0x00B8, "cedil", "CEDILLA" }, 1182{ 0x00B9, "sup1", "SUPERSCRIPT ONE" }, 1183{ 0x00BA, "ordm", "MASCULINE ORDINAL INDICATOR" }, 1184{ 0x00BB, "raquo", "RIGHT-POINTING DOUBLE ANGLE QUOTATION MARK" }, 1185{ 0x00BC, "frac14", "VULGAR FRACTION ONE QUARTER" }, 1186{ 0x00BD, "frac12", "VULGAR FRACTION ONE HALF" }, 1187{ 0x00BD, "half", "VULGAR FRACTION ONE HALF" }, 1188{ 0x00BE, "frac34", "VULGAR FRACTION THREE QUARTERS" }, 1189{ 0x00BF, "iquest", "INVERTED QUESTION MARK" }, 1190{ 0x00C0, "Agrave", "LATIN CAPITAL LETTER A WITH GRAVE" }, 1191{ 0x00C1, "Aacute", "LATIN CAPITAL LETTER A WITH ACUTE" }, 1192{ 0x00C2, "Acirc", "LATIN CAPITAL LETTER A WITH CIRCUMFLEX" }, 1193{ 0x00C3, "Atilde", "LATIN CAPITAL LETTER A WITH TILDE" }, 1194{ 0x00C4, "Auml", "LATIN CAPITAL LETTER A WITH DIAERESIS" }, 1195{ 0x00C5, "Aring", "LATIN CAPITAL LETTER A WITH RING ABOVE" }, 1196{ 0x00C6, "AElig", "LATIN CAPITAL LETTER AE" }, 1197{ 0x00C7, "Ccedil", "LATIN CAPITAL LETTER C WITH CEDILLA" }, 1198{ 0x00C8, "Egrave", "LATIN CAPITAL LETTER E WITH GRAVE" }, 1199{ 0x00C9, "Eacute", "LATIN CAPITAL LETTER E WITH ACUTE" }, 1200{ 0x00CA, "Ecirc", "LATIN CAPITAL LETTER E WITH CIRCUMFLEX" }, 1201{ 0x00CB, "Euml", "LATIN CAPITAL LETTER E WITH DIAERESIS" }, 1202{ 0x00CC, "Igrave", "LATIN CAPITAL LETTER I WITH GRAVE" }, 1203{ 0x00CD, "Iacute", "LATIN CAPITAL LETTER I WITH ACUTE" }, 1204{ 0x00CE, "Icirc", "LATIN CAPITAL LETTER I WITH CIRCUMFLEX" }, 1205{ 0x00CF, "Iuml", "LATIN CAPITAL LETTER I WITH DIAERESIS" }, 1206{ 0x00D0, "ETH", "LATIN CAPITAL LETTER ETH" }, 1207{ 0x00D1, "Ntilde", "LATIN CAPITAL LETTER N WITH TILDE" }, 1208{ 0x00D2, "Ograve", "LATIN CAPITAL LETTER O WITH GRAVE" }, 1209{ 0x00D3, "Oacute", "LATIN CAPITAL LETTER O WITH ACUTE" }, 1210{ 0x00D4, "Ocirc", "LATIN CAPITAL LETTER O WITH CIRCUMFLEX" }, 1211{ 0x00D5, "Otilde", "LATIN CAPITAL LETTER O WITH TILDE" }, 1212{ 0x00D6, "Ouml", "LATIN CAPITAL LETTER O WITH DIAERESIS" }, 1213{ 0x00D7, "times", "MULTIPLICATION SIGN" }, 1214{ 0x00D8, "Oslash", "LATIN CAPITAL LETTER O WITH STROKE" }, 1215{ 0x00D9, "Ugrave", "LATIN CAPITAL LETTER U WITH GRAVE" }, 1216{ 0x00DA, "Uacute", "LATIN CAPITAL LETTER U WITH ACUTE" }, 1217{ 0x00DB, "Ucirc", "LATIN CAPITAL LETTER U WITH CIRCUMFLEX" }, 1218{ 0x00DC, "Uuml", "LATIN CAPITAL LETTER U WITH DIAERESIS" }, 1219{ 0x00DD, "Yacute", "LATIN CAPITAL LETTER Y WITH ACUTE" }, 1220{ 0x00DE, "THORN", "LATIN CAPITAL LETTER THORN" }, 1221{ 0x00DF, "szlig", "LATIN SMALL LETTER SHARP S" }, 1222{ 0x00E0, "agrave", "LATIN SMALL LETTER A WITH GRAVE" }, 1223{ 0x00E1, "aacute", "LATIN SMALL LETTER A WITH ACUTE" }, 1224{ 0x00E2, "acirc", "LATIN SMALL LETTER A WITH CIRCUMFLEX" }, 1225{ 0x00E3, "atilde", "LATIN SMALL LETTER A WITH TILDE" }, 1226{ 0x00E4, "auml", "LATIN SMALL LETTER A WITH DIAERESIS" }, 1227{ 0x00E5, "aring", "LATIN SMALL LETTER A WITH RING ABOVE" }, 1228{ 0x00E6, "aelig", "LATIN SMALL LETTER AE" }, 1229{ 0x00E7, "ccedil", "LATIN SMALL LETTER C WITH CEDILLA" }, 1230{ 0x00E8, "egrave", "LATIN SMALL LETTER E WITH GRAVE" }, 1231{ 0x00E9, "eacute", "LATIN SMALL LETTER E WITH ACUTE" }, 1232{ 0x00EA, "ecirc", "LATIN SMALL LETTER E WITH CIRCUMFLEX" }, 1233{ 0x00EB, "euml", "LATIN SMALL LETTER E WITH DIAERESIS" }, 1234{ 0x00EC, "igrave", "LATIN SMALL LETTER I WITH GRAVE" }, 1235{ 0x00ED, "iacute", "LATIN SMALL LETTER I WITH ACUTE" }, 1236{ 0x00EE, "icirc", "LATIN SMALL LETTER I WITH CIRCUMFLEX" }, 1237{ 0x00EF, "iuml", "LATIN SMALL LETTER I WITH DIAERESIS" }, 1238{ 0x00F0, "eth", "LATIN SMALL LETTER ETH" }, 1239{ 0x00F1, "ntilde", "LATIN SMALL LETTER N WITH TILDE" }, 1240{ 0x00F2, "ograve", "LATIN SMALL LETTER O WITH GRAVE" }, 1241{ 0x00F3, "oacute", "LATIN SMALL LETTER O WITH ACUTE" }, 1242{ 0x00F4, "ocirc", "LATIN SMALL LETTER O WITH CIRCUMFLEX" }, 1243{ 0x00F5, "otilde", "LATIN SMALL LETTER O WITH TILDE" }, 1244{ 0x00F6, "ouml", "LATIN SMALL LETTER O WITH DIAERESIS" }, 1245{ 0x00F7, "divide", "DIVISION SIGN" }, 1246{ 0x00F8, "oslash", "CIRCLED DIVISION SLASH" }, 1247{ 0x00F9, "ugrave", "LATIN SMALL LETTER U WITH GRAVE" }, 1248{ 0x00FA, "uacute", "LATIN SMALL LETTER U WITH ACUTE" }, 1249{ 0x00FB, "ucirc", "LATIN SMALL LETTER U WITH CIRCUMFLEX" }, 1250{ 0x00FC, "uuml", "LATIN SMALL LETTER U WITH DIAERESIS" }, 1251{ 0x00FD, "yacute", "LATIN SMALL LETTER Y WITH ACUTE" }, 1252{ 0x00FE, "thorn", "LATIN SMALL LETTER THORN" }, 1253{ 0x00FF, "yuml", "LATIN SMALL LETTER Y WITH DIAERESIS" }, 1254{ 0x0100, "Amacr", "LATIN CAPITAL LETTER A WITH MACRON" }, 1255{ 0x0101, "amacr", "LATIN SMALL LETTER A WITH MACRON" }, 1256{ 0x0102, "Abreve", "LATIN CAPITAL LETTER A WITH BREVE" }, 1257{ 0x0103, "abreve", "LATIN SMALL LETTER A WITH BREVE" }, 1258{ 0x0104, "Aogon", "LATIN CAPITAL LETTER A WITH OGONEK" }, 1259{ 0x0105, "aogon", "LATIN SMALL LETTER A WITH OGONEK" }, 1260{ 0x0106, "Cacute", "LATIN CAPITAL LETTER C WITH ACUTE" }, 1261{ 0x0107, "cacute", "LATIN SMALL LETTER C WITH ACUTE" }, 1262{ 0x0108, "Ccirc", "LATIN CAPITAL LETTER C WITH CIRCUMFLEX" }, 1263{ 0x0109, "ccirc", "LATIN SMALL LETTER C WITH CIRCUMFLEX" }, 1264{ 0x010A, "Cdot", "LATIN CAPITAL LETTER C WITH DOT ABOVE" }, 1265{ 0x010B, "cdot", "DOT OPERATOR" }, 1266{ 0x010C, "Ccaron", "LATIN CAPITAL LETTER C WITH CARON" }, 1267{ 0x010D, "ccaron", "LATIN SMALL LETTER C WITH CARON" }, 1268{ 0x010E, "Dcaron", "LATIN CAPITAL LETTER D WITH CARON" }, 1269{ 0x010F, "dcaron", "LATIN SMALL LETTER D WITH CARON" }, 1270{ 0x0110, "Dstrok", "LATIN CAPITAL LETTER D WITH STROKE" }, 1271{ 0x0111, "dstrok", "LATIN SMALL LETTER D WITH STROKE" }, 1272{ 0x0112, "Emacr", "LATIN CAPITAL LETTER E WITH MACRON" }, 1273{ 0x0113, "emacr", "LATIN SMALL LETTER E WITH MACRON" }, 1274{ 0x0116, "Edot", "LATIN CAPITAL LETTER E WITH DOT ABOVE" }, 1275{ 0x0117, "edot", "LATIN SMALL LETTER E WITH DOT ABOVE" }, 1276{ 0x0118, "Eogon", "LATIN CAPITAL LETTER E WITH OGONEK" }, 1277{ 0x0119, "eogon", "LATIN SMALL LETTER E WITH OGONEK" }, 1278{ 0x011A, "Ecaron", "LATIN CAPITAL LETTER E WITH CARON" }, 1279{ 0x011B, "ecaron", "LATIN SMALL LETTER E WITH CARON" }, 1280{ 0x011C, "Gcirc", "LATIN CAPITAL LETTER G WITH CIRCUMFLEX" }, 1281{ 0x011D, "gcirc", "LATIN SMALL LETTER G WITH CIRCUMFLEX" }, 1282{ 0x011E, "Gbreve", "LATIN CAPITAL LETTER G WITH BREVE" }, 1283{ 0x011F, "gbreve", "LATIN SMALL LETTER G WITH BREVE" }, 1284{ 0x0120, "Gdot", "LATIN CAPITAL LETTER G WITH DOT ABOVE" }, 1285{ 0x0121, "gdot", "LATIN SMALL LETTER G WITH DOT ABOVE" }, 1286{ 0x0122, "Gcedil", "LATIN CAPITAL LETTER G WITH CEDILLA" }, 1287{ 0x0124, "Hcirc", "LATIN CAPITAL LETTER H WITH CIRCUMFLEX" }, 1288{ 0x0125, "hcirc", "LATIN SMALL LETTER H WITH CIRCUMFLEX" }, 1289{ 0x0126, "Hstrok", "LATIN CAPITAL LETTER H WITH STROKE" }, 1290{ 0x0127, "hstrok", "LATIN SMALL LETTER H WITH STROKE" }, 1291{ 0x0128, "Itilde", "LATIN CAPITAL LETTER I WITH TILDE" }, 1292{ 0x0129, "itilde", "LATIN SMALL LETTER I WITH TILDE" }, 1293{ 0x012A, "Imacr", "LATIN CAPITAL LETTER I WITH MACRON" }, 1294{ 0x012B, "imacr", "LATIN SMALL LETTER I WITH MACRON" }, 1295{ 0x012E, "Iogon", "LATIN CAPITAL LETTER I WITH OGONEK" }, 1296{ 0x012F, "iogon", "LATIN SMALL LETTER I WITH OGONEK" }, 1297{ 0x0130, "Idot", "LATIN CAPITAL LETTER I WITH DOT ABOVE" }, 1298{ 0x0131, "inodot", "LATIN SMALL LETTER DOTLESS I" }, 1299{ 0x0131, "inodot", "LATIN SMALL LETTER DOTLESS I" }, 1300{ 0x0132, "IJlig", "LATIN CAPITAL LIGATURE IJ" }, 1301{ 0x0133, "ijlig", "LATIN SMALL LIGATURE IJ" }, 1302{ 0x0134, "Jcirc", "LATIN CAPITAL LETTER J WITH CIRCUMFLEX" }, 1303{ 0x0135, "jcirc", "LATIN SMALL LETTER J WITH CIRCUMFLEX" }, 1304{ 0x0136, "Kcedil", "LATIN CAPITAL LETTER K WITH CEDILLA" }, 1305{ 0x0137, "kcedil", "LATIN SMALL LETTER K WITH CEDILLA" }, 1306{ 0x0138, "kgreen", "LATIN SMALL LETTER KRA" }, 1307{ 0x0139, "Lacute", "LATIN CAPITAL LETTER L WITH ACUTE" }, 1308{ 0x013A, "lacute", "LATIN SMALL LETTER L WITH ACUTE" }, 1309{ 0x013B, "Lcedil", "LATIN CAPITAL LETTER L WITH CEDILLA" }, 1310{ 0x013C, "lcedil", "LATIN SMALL LETTER L WITH CEDILLA" }, 1311{ 0x013D, "Lcaron", "LATIN CAPITAL LETTER L WITH CARON" }, 1312{ 0x013E, "lcaron", "LATIN SMALL LETTER L WITH CARON" }, 1313{ 0x013F, "Lmidot", "LATIN CAPITAL LETTER L WITH MIDDLE DOT" }, 1314{ 0x0140, "lmidot", "LATIN SMALL LETTER L WITH MIDDLE DOT" }, 1315{ 0x0141, "Lstrok", "LATIN CAPITAL LETTER L WITH STROKE" }, 1316{ 0x0142, "lstrok", "LATIN SMALL LETTER L WITH STROKE" }, 1317{ 0x0143, "Nacute", "LATIN CAPITAL LETTER N WITH ACUTE" }, 1318{ 0x0144, "nacute", "LATIN SMALL LETTER N WITH ACUTE" }, 1319{ 0x0145, "Ncedil", "LATIN CAPITAL LETTER N WITH CEDILLA" }, 1320{ 0x0146, "ncedil", "LATIN SMALL LETTER N WITH CEDILLA" }, 1321{ 0x0147, "Ncaron", "LATIN CAPITAL LETTER N WITH CARON" }, 1322{ 0x0148, "ncaron", "LATIN SMALL LETTER N WITH CARON" }, 1323{ 0x0149, "napos", "LATIN SMALL LETTER N PRECEDED BY APOSTROPHE" }, 1324{ 0x014A, "ENG", "LATIN CAPITAL LETTER ENG" }, 1325{ 0x014B, "eng", "LATIN SMALL LETTER ENG" }, 1326{ 0x014C, "Omacr", "LATIN CAPITAL LETTER O WITH MACRON" }, 1327{ 0x014D, "omacr", "LATIN SMALL LETTER O WITH MACRON" }, 1328{ 0x0150, "Odblac", "LATIN CAPITAL LETTER O WITH DOUBLE ACUTE" }, 1329{ 0x0151, "odblac", "LATIN SMALL LETTER O WITH DOUBLE ACUTE" }, 1330{ 0x0152, "OElig", "LATIN CAPITAL LIGATURE OE" }, 1331{ 0x0153, "oelig", "LATIN SMALL LIGATURE OE" }, 1332{ 0x0154, "Racute", "LATIN CAPITAL LETTER R WITH ACUTE" }, 1333{ 0x0155, "racute", "LATIN SMALL LETTER R WITH ACUTE" }, 1334{ 0x0156, "Rcedil", "LATIN CAPITAL LETTER R WITH CEDILLA" }, 1335{ 0x0157, "rcedil", "LATIN SMALL LETTER R WITH CEDILLA" }, 1336{ 0x0158, "Rcaron", "LATIN CAPITAL LETTER R WITH CARON" }, 1337{ 0x0159, "rcaron", "LATIN SMALL LETTER R WITH CARON" }, 1338{ 0x015A, "Sacute", "LATIN CAPITAL LETTER S WITH ACUTE" }, 1339{ 0x015B, "sacute", "LATIN SMALL LETTER S WITH ACUTE" }, 1340{ 0x015C, "Scirc", "LATIN CAPITAL LETTER S WITH CIRCUMFLEX" }, 1341{ 0x015D, "scirc", "LATIN SMALL LETTER S WITH CIRCUMFLEX" }, 1342{ 0x015E, "Scedil", "LATIN CAPITAL LETTER S WITH CEDILLA" }, 1343{ 0x015F, "scedil", "LATIN SMALL LETTER S WITH CEDILLA" }, 1344{ 0x0160, "Scaron", "LATIN CAPITAL LETTER S WITH CARON" }, 1345{ 0x0161, "scaron", "LATIN SMALL LETTER S WITH CARON" }, 1346{ 0x0162, "Tcedil", "LATIN CAPITAL LETTER T WITH CEDILLA" }, 1347{ 0x0163, "tcedil", "LATIN SMALL LETTER T WITH CEDILLA" }, 1348{ 0x0164, "Tcaron", "LATIN CAPITAL LETTER T WITH CARON" }, 1349{ 0x0165, "tcaron", "LATIN SMALL LETTER T WITH CARON" }, 1350{ 0x0166, "Tstrok", "LATIN CAPITAL LETTER T WITH STROKE" }, 1351{ 0x0167, "tstrok", "LATIN SMALL LETTER T WITH STROKE" }, 1352{ 0x0168, "Utilde", "LATIN CAPITAL LETTER U WITH TILDE" }, 1353{ 0x0169, "utilde", "LATIN SMALL LETTER U WITH TILDE" }, 1354{ 0x016A, "Umacr", "LATIN CAPITAL LETTER U WITH MACRON" }, 1355{ 0x016B, "umacr", "LATIN SMALL LETTER U WITH MACRON" }, 1356{ 0x016C, "Ubreve", "LATIN CAPITAL LETTER U WITH BREVE" }, 1357{ 0x016D, "ubreve", "LATIN SMALL LETTER U WITH BREVE" }, 1358{ 0x016E, "Uring", "LATIN CAPITAL LETTER U WITH RING ABOVE" }, 1359{ 0x016F, "uring", "LATIN SMALL LETTER U WITH RING ABOVE" }, 1360{ 0x0170, "Udblac", "LATIN CAPITAL LETTER U WITH DOUBLE ACUTE" }, 1361{ 0x0171, "udblac", "LATIN SMALL LETTER U WITH DOUBLE ACUTE" }, 1362{ 0x0172, "Uogon", "LATIN CAPITAL LETTER U WITH OGONEK" }, 1363{ 0x0173, "uogon", "LATIN SMALL LETTER U WITH OGONEK" }, 1364{ 0x0174, "Wcirc", "LATIN CAPITAL LETTER W WITH CIRCUMFLEX" }, 1365{ 0x0175, "wcirc", "LATIN SMALL LETTER W WITH CIRCUMFLEX" }, 1366{ 0x0176, "Ycirc", "LATIN CAPITAL LETTER Y WITH CIRCUMFLEX" }, 1367{ 0x0177, "ycirc", "LATIN SMALL LETTER Y WITH CIRCUMFLEX" }, 1368{ 0x0178, "Yuml", "LATIN CAPITAL LETTER Y WITH DIAERESIS" }, 1369{ 0x0179, "Zacute", "LATIN CAPITAL LETTER Z WITH ACUTE" }, 1370{ 0x017A, "zacute", "LATIN SMALL LETTER Z WITH ACUTE" }, 1371{ 0x017B, "Zdot", "LATIN CAPITAL LETTER Z WITH DOT ABOVE" }, 1372{ 0x017C, "zdot", "LATIN SMALL LETTER Z WITH DOT ABOVE" }, 1373{ 0x017D, "Zcaron", "LATIN CAPITAL LETTER Z WITH CARON" }, 1374{ 0x017E, "zcaron", "LATIN SMALL LETTER Z WITH CARON" }, 1375{ 0x0192, "fnof", "LATIN SMALL LETTER F WITH HOOK" }, 1376{ 0x01F5, "gacute", "LATIN SMALL LETTER G WITH ACUTE" }, 1377{ 0x02C7, "caron", "CARON" }, 1378{ 0x02D8, "breve", "BREVE" }, 1379{ 0x02D9, "dot", "DOT ABOVE" }, 1380{ 0x02DA, "ring", "RING ABOVE" }, 1381{ 0x02DB, "ogon", "OGONEK" }, 1382{ 0x02DC, "tilde", "TILDE" }, 1383{ 0x02DD, "dblac", "DOUBLE ACUTE ACCENT" }, 1384{ 0x0386, "Aacgr", "GREEK CAPITAL LETTER ALPHA WITH TONOS" }, 1385{ 0x0388, "Eacgr", "GREEK CAPITAL LETTER EPSILON WITH TONOS" }, 1386{ 0x0389, "EEacgr", "GREEK CAPITAL LETTER ETA WITH TONOS" }, 1387{ 0x038A, "Iacgr", "GREEK CAPITAL LETTER IOTA WITH TONOS" }, 1388{ 0x038C, "Oacgr", "GREEK CAPITAL LETTER OMICRON WITH TONOS" }, 1389{ 0x038E, "Uacgr", "GREEK CAPITAL LETTER UPSILON WITH TONOS" }, 1390{ 0x038F, "OHacgr", "GREEK CAPITAL LETTER OMEGA WITH TONOS" }, 1391{ 0x0390, "idiagr", "GREEK SMALL LETTER IOTA WITH DIALYTIKA AND TONOS" }, 1392{ 0x0391, "Agr", "GREEK CAPITAL LETTER ALPHA" }, 1393{ 0x0392, "Bgr", "GREEK CAPITAL LETTER BETA" }, 1394{ 0x0393, "b.Gamma", "GREEK CAPITAL LETTER GAMMA" }, 1395{ 0x0393, "Gamma", "GREEK CAPITAL LETTER GAMMA" }, 1396{ 0x0393, "Ggr", "GREEK CAPITAL LETTER GAMMA" }, 1397{ 0x0394, "b.Delta", "GREEK CAPITAL LETTER DELTA" }, 1398{ 0x0394, "Delta", "GREEK CAPITAL LETTER DELTA" }, 1399{ 0x0394, "Dgr", "GREEK CAPITAL LETTER DELTA" }, 1400{ 0x0395, "Egr", "GREEK CAPITAL LETTER EPSILON" }, 1401{ 0x0396, "Zgr", "GREEK CAPITAL LETTER ZETA" }, 1402{ 0x0397, "EEgr", "GREEK CAPITAL LETTER ETA" }, 1403{ 0x0398, "b.Theta", "GREEK CAPITAL LETTER THETA" }, 1404{ 0x0398, "Theta", "GREEK CAPITAL LETTER THETA" }, 1405{ 0x0398, "THgr", "GREEK CAPITAL LETTER THETA" }, 1406{ 0x0399, "Igr", "GREEK CAPITAL LETTER IOTA" }, 1407{ 0x039A, "Kgr", "GREEK CAPITAL LETTER KAPPA" }, 1408{ 0x039B, "b.Lambda", "GREEK CAPITAL LETTER LAMDA" }, 1409{ 0x039B, "Lambda", "GREEK CAPITAL LETTER LAMDA" }, 1410{ 0x039B, "Lgr", "GREEK CAPITAL LETTER LAMDA" }, 1411{ 0x039C, "Mgr", "GREEK CAPITAL LETTER MU" }, 1412{ 0x039D, "Ngr", "GREEK CAPITAL LETTER NU" }, 1413{ 0x039E, "b.Xi", "GREEK CAPITAL LETTER XI" }, 1414{ 0x039E, "Xgr", "GREEK CAPITAL LETTER XI" }, 1415{ 0x039E, "Xi", "GREEK CAPITAL LETTER XI" }, 1416{ 0x039F, "Ogr", "GREEK CAPITAL LETTER OMICRON" }, 1417{ 0x03A0, "b.Pi", "GREEK CAPITAL LETTER PI" }, 1418{ 0x03A0, "Pgr", "GREEK CAPITAL LETTER PI" }, 1419{ 0x03A0, "Pi", "GREEK CAPITAL LETTER PI" }, 1420{ 0x03A1, "Rgr", "GREEK CAPITAL LETTER RHO" }, 1421{ 0x03A3, "b.Sigma", "GREEK CAPITAL LETTER SIGMA" }, 1422{ 0x03A3, "Sgr", "GREEK CAPITAL LETTER SIGMA" }, 1423{ 0x03A3, "Sigma", "GREEK CAPITAL LETTER SIGMA" }, 1424{ 0x03A4, "Tgr", "GREEK CAPITAL LETTER TAU" }, 1425{ 0x03A5, "Ugr", "" }, 1426{ 0x03A6, "b.Phi", "GREEK CAPITAL LETTER PHI" }, 1427{ 0x03A6, "PHgr", "GREEK CAPITAL LETTER PHI" }, 1428{ 0x03A6, "Phi", "GREEK CAPITAL LETTER PHI" }, 1429{ 0x03A7, "KHgr", "GREEK CAPITAL LETTER CHI" }, 1430{ 0x03A8, "b.Psi", "GREEK CAPITAL LETTER PSI" }, 1431{ 0x03A8, "PSgr", "GREEK CAPITAL LETTER PSI" }, 1432{ 0x03A8, "Psi", "GREEK CAPITAL LETTER PSI" }, 1433{ 0x03A9, "b.Omega", "GREEK CAPITAL LETTER OMEGA" }, 1434{ 0x03A9, "OHgr", "GREEK CAPITAL LETTER OMEGA" }, 1435{ 0x03A9, "Omega", "GREEK CAPITAL LETTER OMEGA" }, 1436{ 0x03AA, "Idigr", "GREEK CAPITAL LETTER IOTA WITH DIALYTIKA" }, 1437{ 0x03AB, "Udigr", "GREEK CAPITAL LETTER UPSILON WITH DIALYTIKA" }, 1438{ 0x03AC, "aacgr", "GREEK SMALL LETTER ALPHA WITH TONOS" }, 1439{ 0x03AD, "eacgr", "GREEK SMALL LETTER EPSILON WITH TONOS" }, 1440{ 0x03AE, "eeacgr", "GREEK SMALL LETTER ETA WITH TONOS" }, 1441{ 0x03AF, "iacgr", "GREEK SMALL LETTER IOTA WITH TONOS" }, 1442{ 0x03B0, "udiagr", "GREEK SMALL LETTER UPSILON WITH DIALYTIKA AND TONOS" }, 1443{ 0x03B1, "agr", "" }, 1444{ 0x03B1, "alpha", "" }, 1445{ 0x03B1, "b.alpha", "" }, 1446{ 0x03B2, "b.beta", "GREEK SMALL LETTER BETA" }, 1447{ 0x03B2, "beta", "GREEK SMALL LETTER BETA" }, 1448{ 0x03B2, "bgr", "GREEK SMALL LETTER BETA" }, 1449{ 0x03B3, "b.gamma", "GREEK SMALL LETTER GAMMA" }, 1450{ 0x03B3, "gamma", "GREEK SMALL LETTER GAMMA" }, 1451{ 0x03B3, "ggr", "GREEK SMALL LETTER GAMMA" }, 1452{ 0x03B4, "b.delta", "GREEK SMALL LETTER DELTA" }, 1453{ 0x03B4, "delta", "GREEK SMALL LETTER DELTA" }, 1454{ 0x03B4, "dgr", "GREEK SMALL LETTER DELTA" }, 1455{ 0x03B5, "b.epsi", "" }, 1456{ 0x03B5, "b.epsis", "" }, 1457{ 0x03B5, "b.epsiv", "" }, 1458{ 0x03B5, "egr", "" }, 1459{ 0x03B5, "epsiv", "" }, 1460{ 0x03B6, "b.zeta", "GREEK SMALL LETTER ZETA" }, 1461{ 0x03B6, "zeta", "GREEK SMALL LETTER ZETA" }, 1462{ 0x03B6, "zgr", "GREEK SMALL LETTER ZETA" }, 1463{ 0x03B7, "b.eta", "GREEK SMALL LETTER ETA" }, 1464{ 0x03B7, "eegr", "GREEK SMALL LETTER ETA" }, 1465{ 0x03B7, "eta", "GREEK SMALL LETTER ETA" }, 1466{ 0x03B8, "b.thetas", "" }, 1467{ 0x03B8, "thetas", "" }, 1468{ 0x03B8, "thgr", "" }, 1469{ 0x03B9, "b.iota", "GREEK SMALL LETTER IOTA" }, 1470{ 0x03B9, "igr", "GREEK SMALL LETTER IOTA" }, 1471{ 0x03B9, "iota", "GREEK SMALL LETTER IOTA" }, 1472{ 0x03BA, "b.kappa", "GREEK SMALL LETTER KAPPA" }, 1473{ 0x03BA, "kappa", "GREEK SMALL LETTER KAPPA" }, 1474{ 0x03BA, "kgr", "GREEK SMALL LETTER KAPPA" }, 1475{ 0x03BB, "b.lambda", "GREEK SMALL LETTER LAMDA" }, 1476{ 0x03BB, "lambda", "GREEK SMALL LETTER LAMDA" }, 1477{ 0x03BB, "lgr", "GREEK SMALL LETTER LAMDA" }, 1478{ 0x03BC, "b.mu", "GREEK SMALL LETTER MU" }, 1479{ 0x03BC, "mgr", "GREEK SMALL LETTER MU" }, 1480{ 0x03BC, "mu", "GREEK SMALL LETTER MU" }, 1481{ 0x03BD, "b.nu", "GREEK SMALL LETTER NU" }, 1482{ 0x03BD, "ngr", "GREEK SMALL LETTER NU" }, 1483{ 0x03BD, "nu", "GREEK SMALL LETTER NU" }, 1484{ 0x03BE, "b.xi", "GREEK SMALL LETTER XI" }, 1485{ 0x03BE, "xgr", "GREEK SMALL LETTER XI" }, 1486{ 0x03BE, "xi", "GREEK SMALL LETTER XI" }, 1487{ 0x03BF, "ogr", "GREEK SMALL LETTER OMICRON" }, 1488{ 0x03C0, "b.pi", "GREEK SMALL LETTER PI" }, 1489{ 0x03C0, "pgr", "GREEK SMALL LETTER PI" }, 1490{ 0x03C0, "pi", "GREEK SMALL LETTER PI" }, 1491{ 0x03C1, "b.rho", "GREEK SMALL LETTER RHO" }, 1492{ 0x03C1, "rgr", "GREEK SMALL LETTER RHO" }, 1493{ 0x03C1, "rho", "GREEK SMALL LETTER RHO" }, 1494{ 0x03C2, "b.sigmav", "" }, 1495{ 0x03C2, "sfgr", "" }, 1496{ 0x03C2, "sigmav", "" }, 1497{ 0x03C3, "b.sigma", "GREEK SMALL LETTER SIGMA" }, 1498{ 0x03C3, "sgr", "GREEK SMALL LETTER SIGMA" }, 1499{ 0x03C3, "sigma", "GREEK SMALL LETTER SIGMA" }, 1500{ 0x03C4, "b.tau", "GREEK SMALL LETTER TAU" }, 1501{ 0x03C4, "tau", "GREEK SMALL LETTER TAU" }, 1502{ 0x03C4, "tgr", "GREEK SMALL LETTER TAU" }, 1503{ 0x03C5, "b.upsi", "GREEK SMALL LETTER UPSILON" }, 1504{ 0x03C5, "ugr", "GREEK SMALL LETTER UPSILON" }, 1505{ 0x03C5, "upsi", "GREEK SMALL LETTER UPSILON" }, 1506{ 0x03C6, "b.phis", "GREEK SMALL LETTER PHI" }, 1507{ 0x03C6, "phgr", "GREEK SMALL LETTER PHI" }, 1508{ 0x03C6, "phis", "GREEK SMALL LETTER PHI" }, 1509{ 0x03C7, "b.chi", "GREEK SMALL LETTER CHI" }, 1510{ 0x03C7, "chi", "GREEK SMALL LETTER CHI" }, 1511{ 0x03C7, "khgr", "GREEK SMALL LETTER CHI" }, 1512{ 0x03C8, "b.psi", "GREEK SMALL LETTER PSI" }, 1513{ 0x03C8, "psgr", "GREEK SMALL LETTER PSI" }, 1514{ 0x03C8, "psi", "GREEK SMALL LETTER PSI" }, 1515{ 0x03C9, "b.omega", "GREEK SMALL LETTER OMEGA" }, 1516{ 0x03C9, "ohgr", "GREEK SMALL LETTER OMEGA" }, 1517{ 0x03C9, "omega", "GREEK SMALL LETTER OMEGA" }, 1518{ 0x03CA, "idigr", "GREEK SMALL LETTER IOTA WITH DIALYTIKA" }, 1519{ 0x03CB, "udigr", "GREEK SMALL LETTER UPSILON WITH DIALYTIKA" }, 1520{ 0x03CC, "oacgr", "GREEK SMALL LETTER OMICRON WITH TONOS" }, 1521{ 0x03CD, "uacgr", "GREEK SMALL LETTER UPSILON WITH TONOS" }, 1522{ 0x03CE, "ohacgr", "GREEK SMALL LETTER OMEGA WITH TONOS" }, 1523{ 0x03D1, "b.thetav", "" }, 1524{ 0x03D1, "thetav", "" }, 1525{ 0x03D2, "b.Upsi", "" }, 1526{ 0x03D2, "Upsi", "" }, 1527{ 0x03D5, "b.phiv", "GREEK PHI SYMBOL" }, 1528{ 0x03D5, "phiv", "GREEK PHI SYMBOL" }, 1529{ 0x03D6, "b.piv", "GREEK PI SYMBOL" }, 1530{ 0x03D6, "piv", "GREEK PI SYMBOL" }, 1531{ 0x03DC, "b.gammad", "GREEK LETTER DIGAMMA" }, 1532{ 0x03DC, "gammad", "GREEK LETTER DIGAMMA" }, 1533{ 0x03F0, "b.kappav", "GREEK KAPPA SYMBOL" }, 1534{ 0x03F0, "kappav", "GREEK KAPPA SYMBOL" }, 1535{ 0x03F1, "b.rhov", "GREEK RHO SYMBOL" }, 1536{ 0x03F1, "rhov", "GREEK RHO SYMBOL" }, 1537{ 0x0401, "IOcy", "CYRILLIC CAPITAL LETTER IO" }, 1538{ 0x0402, "DJcy", "CYRILLIC CAPITAL LETTER DJE" }, 1539{ 0x0403, "GJcy", "CYRILLIC CAPITAL LETTER GJE" }, 1540{ 0x0404, "Jukcy", "CYRILLIC CAPITAL LETTER UKRAINIAN IE" }, 1541{ 0x0405, "DScy", "CYRILLIC CAPITAL LETTER DZE" }, 1542{ 0x0406, "Iukcy", "CYRILLIC CAPITAL LETTER BYELORUSSIAN-UKRAINIAN I" }, 1543{ 0x0407, "YIcy", "CYRILLIC CAPITAL LETTER YI" }, 1544{ 0x0408, "Jsercy", "CYRILLIC CAPITAL LETTER JE" }, 1545{ 0x0409, "LJcy", "CYRILLIC CAPITAL LETTER LJE" }, 1546{ 0x040A, "NJcy", "CYRILLIC CAPITAL LETTER NJE" }, 1547{ 0x040B, "TSHcy", "CYRILLIC CAPITAL LETTER TSHE" }, 1548{ 0x040C, "KJcy", "CYRILLIC CAPITAL LETTER KJE" }, 1549{ 0x040E, "Ubrcy", "CYRILLIC CAPITAL LETTER SHORT U" }, 1550{ 0x040F, "DZcy", "CYRILLIC CAPITAL LETTER DZHE" }, 1551{ 0x0410, "Acy", "CYRILLIC CAPITAL LETTER A" }, 1552{ 0x0411, "Bcy", "CYRILLIC CAPITAL LETTER BE" }, 1553{ 0x0412, "Vcy", "CYRILLIC CAPITAL LETTER VE" }, 1554{ 0x0413, "Gcy", "CYRILLIC CAPITAL LETTER GHE" }, 1555{ 0x0414, "Dcy", "CYRILLIC CAPITAL LETTER DE" }, 1556{ 0x0415, "IEcy", "CYRILLIC CAPITAL LETTER IE" }, 1557{ 0x0416, "ZHcy", "CYRILLIC CAPITAL LETTER ZHE" }, 1558{ 0x0417, "Zcy", "CYRILLIC CAPITAL LETTER ZE" }, 1559{ 0x0418, "Icy", "CYRILLIC CAPITAL LETTER I" }, 1560{ 0x0419, "Jcy", "CYRILLIC CAPITAL LETTER SHORT I" }, 1561{ 0x041A, "Kcy", "CYRILLIC CAPITAL LETTER KA" }, 1562{ 0x041B, "Lcy", "CYRILLIC CAPITAL LETTER EL" }, 1563{ 0x041C, "Mcy", "CYRILLIC CAPITAL LETTER EM" }, 1564{ 0x041D, "Ncy", "CYRILLIC CAPITAL LETTER EN" }, 1565{ 0x041E, "Ocy", "CYRILLIC CAPITAL LETTER O" }, 1566{ 0x041F, "Pcy", "CYRILLIC CAPITAL LETTER PE" }, 1567{ 0x0420, "Rcy", "CYRILLIC CAPITAL LETTER ER" }, 1568{ 0x0421, "Scy", "CYRILLIC CAPITAL LETTER ES" }, 1569{ 0x0422, "Tcy", "CYRILLIC CAPITAL LETTER TE" }, 1570{ 0x0423, "Ucy", "CYRILLIC CAPITAL LETTER U" }, 1571{ 0x0424, "Fcy", "CYRILLIC CAPITAL LETTER EF" }, 1572{ 0x0425, "KHcy", "CYRILLIC CAPITAL LETTER HA" }, 1573{ 0x0426, "TScy", "CYRILLIC CAPITAL LETTER TSE" }, 1574{ 0x0427, "CHcy", "CYRILLIC CAPITAL LETTER CHE" }, 1575{ 0x0428, "SHcy", "CYRILLIC CAPITAL LETTER SHA" }, 1576{ 0x0429, "SHCHcy", "CYRILLIC CAPITAL LETTER SHCHA" }, 1577{ 0x042A, "HARDcy", "CYRILLIC CAPITAL LETTER HARD SIGN" }, 1578{ 0x042B, "Ycy", "CYRILLIC CAPITAL LETTER YERU" }, 1579{ 0x042C, "SOFTcy", "CYRILLIC CAPITAL LETTER SOFT SIGN" }, 1580{ 0x042D, "Ecy", "CYRILLIC CAPITAL LETTER E" }, 1581{ 0x042E, "YUcy", "CYRILLIC CAPITAL LETTER YU" }, 1582{ 0x042F, "YAcy", "CYRILLIC CAPITAL LETTER YA" }, 1583{ 0x0430, "acy", "CYRILLIC SMALL LETTER A" }, 1584{ 0x0431, "bcy", "CYRILLIC SMALL LETTER BE" }, 1585{ 0x0432, "vcy", "CYRILLIC SMALL LETTER VE" }, 1586{ 0x0433, "gcy", "CYRILLIC SMALL LETTER GHE" }, 1587{ 0x0434, "dcy", "CYRILLIC SMALL LETTER DE" }, 1588{ 0x0435, "iecy", "CYRILLIC SMALL LETTER IE" }, 1589{ 0x0436, "zhcy", "CYRILLIC SMALL LETTER ZHE" }, 1590{ 0x0437, "zcy", "CYRILLIC SMALL LETTER ZE" }, 1591{ 0x0438, "icy", "CYRILLIC SMALL LETTER I" }, 1592{ 0x0439, "jcy", "CYRILLIC SMALL LETTER SHORT I" }, 1593{ 0x043A, "kcy", "CYRILLIC SMALL LETTER KA" }, 1594{ 0x043B, "lcy", "CYRILLIC SMALL LETTER EL" }, 1595{ 0x043C, "mcy", "CYRILLIC SMALL LETTER EM" }, 1596{ 0x043D, "ncy", "CYRILLIC SMALL LETTER EN" }, 1597{ 0x043E, "ocy", "CYRILLIC SMALL LETTER O" }, 1598{ 0x043F, "pcy", "CYRILLIC SMALL LETTER PE" }, 1599{ 0x0440, "rcy", "CYRILLIC SMALL LETTER ER" }, 1600{ 0x0441, "scy", "CYRILLIC SMALL LETTER ES" }, 1601{ 0x0442, "tcy", "CYRILLIC SMALL LETTER TE" }, 1602{ 0x0443, "ucy", "CYRILLIC SMALL LETTER U" }, 1603{ 0x0444, "fcy", "CYRILLIC SMALL LETTER EF" }, 1604{ 0x0445, "khcy", "CYRILLIC SMALL LETTER HA" }, 1605{ 0x0446, "tscy", "CYRILLIC SMALL LETTER TSE" }, 1606{ 0x0447, "chcy", "CYRILLIC SMALL LETTER CHE" }, 1607{ 0x0448, "shcy", "CYRILLIC SMALL LETTER SHA" }, 1608{ 0x0449, "shchcy", "CYRILLIC SMALL LETTER SHCHA" }, 1609{ 0x044A, "hardcy", "CYRILLIC SMALL LETTER HARD SIGN" }, 1610{ 0x044B, "ycy", "CYRILLIC SMALL LETTER YERU" }, 1611{ 0x044C, "softcy", "CYRILLIC SMALL LETTER SOFT SIGN" }, 1612{ 0x044D, "ecy", "CYRILLIC SMALL LETTER E" }, 1613{ 0x044E, "yucy", "CYRILLIC SMALL LETTER YU" }, 1614{ 0x044F, "yacy", "CYRILLIC SMALL LETTER YA" }, 1615{ 0x0451, "iocy", "CYRILLIC SMALL LETTER IO" }, 1616{ 0x0452, "djcy", "CYRILLIC SMALL LETTER DJE" }, 1617{ 0x0453, "gjcy", "CYRILLIC SMALL LETTER GJE" }, 1618{ 0x0454, "jukcy", "CYRILLIC SMALL LETTER UKRAINIAN IE" }, 1619{ 0x0455, "dscy", "CYRILLIC SMALL LETTER DZE" }, 1620{ 0x0456, "iukcy", "CYRILLIC SMALL LETTER BYELORUSSIAN-UKRAINIAN I" }, 1621{ 0x0457, "yicy", "CYRILLIC SMALL LETTER YI" }, 1622{ 0x0458, "jsercy", "CYRILLIC SMALL LETTER JE" }, 1623{ 0x0459, "ljcy", "CYRILLIC SMALL LETTER LJE" }, 1624{ 0x045A, "njcy", "CYRILLIC SMALL LETTER NJE" }, 1625{ 0x045B, "tshcy", "CYRILLIC SMALL LETTER TSHE" }, 1626{ 0x045C, "kjcy", "CYRILLIC SMALL LETTER KJE" }, 1627{ 0x045E, "ubrcy", "CYRILLIC SMALL LETTER SHORT U" }, 1628{ 0x045F, "dzcy", "CYRILLIC SMALL LETTER DZHE" }, 1629{ 0x2002, "ensp", "EN SPACE" }, 1630{ 0x2003, "emsp", "EM SPACE" }, 1631{ 0x2004, "emsp13", "THREE-PER-EM SPACE" }, 1632{ 0x2005, "emsp14", "FOUR-PER-EM SPACE" }, 1633{ 0x2007, "numsp", "FIGURE SPACE" }, 1634{ 0x2008, "puncsp", "PUNCTUATION SPACE" }, 1635{ 0x2009, "thinsp", "THIN SPACE" }, 1636{ 0x200A, "hairsp", "HAIR SPACE" }, 1637{ 0x2010, "dash", "HYPHEN" }, 1638{ 0x2013, "ndash", "EN DASH" }, 1639{ 0x2014, "mdash", "EM DASH" }, 1640{ 0x2015, "horbar", "HORIZONTAL BAR" }, 1641{ 0x2016, "Verbar", "DOUBLE VERTICAL LINE" }, 1642{ 0x2018, "lsquo", "" }, 1643{ 0x2018, "rsquor", "" }, 1644{ 0x2019, "rsquo", "RIGHT SINGLE QUOTATION MARK" }, 1645{ 0x201A, "lsquor", "SINGLE LOW-9 QUOTATION MARK" }, 1646{ 0x201C, "ldquo", "" }, 1647{ 0x201C, "rdquor", "" }, 1648{ 0x201D, "rdquo", "RIGHT DOUBLE QUOTATION MARK" }, 1649{ 0x201E, "ldquor", "DOUBLE LOW-9 QUOTATION MARK" }, 1650{ 0x2020, "dagger", "DAGGER" }, 1651{ 0x2021, "Dagger", "DOUBLE DAGGER" }, 1652{ 0x2022, "bull", "BULLET" }, 1653{ 0x2025, "nldr", "TWO DOT LEADER" }, 1654{ 0x2026, "hellip", "HORIZONTAL ELLIPSIS" }, 1655{ 0x2026, "mldr", "HORIZONTAL ELLIPSIS" }, 1656{ 0x2030, "permil", "PER MILLE SIGN" }, 1657{ 0x2032, "prime", "PRIME" }, 1658{ 0x2032, "vprime", "PRIME" }, 1659{ 0x2033, "Prime", "DOUBLE PRIME" }, 1660{ 0x2034, "tprime", "TRIPLE PRIME" }, 1661{ 0x2035, "bprime", "REVERSED PRIME" }, 1662{ 0x2041, "caret", "CARET" }, 1663{ 0x2043, "hybull", "HYPHEN BULLET" }, 1664{ 0x20DB, "tdot", "COMBINING THREE DOTS ABOVE" }, 1665{ 0x20DC, "DotDot", "COMBINING FOUR DOTS ABOVE" }, 1666{ 0x2105, "incare", "CARE OF" }, 1667{ 0x210B, "hamilt", "SCRIPT CAPITAL H" }, 1668{ 0x210F, "planck", "PLANCK CONSTANT OVER TWO PI" }, 1669{ 0x2111, "image", "BLACK-LETTER CAPITAL I" }, 1670{ 0x2112, "lagran", "SCRIPT CAPITAL L" }, 1671{ 0x2113, "ell", "SCRIPT SMALL L" }, 1672{ 0x2116, "numero", "NUMERO SIGN" }, 1673{ 0x2117, "copysr", "SOUND RECORDING COPYRIGHT" }, 1674{ 0x2118, "weierp", "SCRIPT CAPITAL P" }, 1675{ 0x211C, "real", "BLACK-LETTER CAPITAL R" }, 1676{ 0x211E, "rx", "PRESCRIPTION TAKE" }, 1677{ 0x2122, "trade", "TRADE MARK SIGN" }, 1678{ 0x2126, "ohm", "OHM SIGN" }, 1679{ 0x212B, "angst", "ANGSTROM SIGN" }, 1680{ 0x212C, "bernou", "SCRIPT CAPITAL B" }, 1681{ 0x2133, "phmmat", "SCRIPT CAPITAL M" }, 1682{ 0x2134, "order", "SCRIPT SMALL O" }, 1683{ 0x2135, "aleph", "ALEF SYMBOL" }, 1684{ 0x2136, "beth", "BET SYMBOL" }, 1685{ 0x2137, "gimel", "GIMEL SYMBOL" }, 1686{ 0x2138, "daleth", "DALET SYMBOL" }, 1687{ 0x2153, "frac13", "VULGAR FRACTION ONE THIRD" }, 1688{ 0x2154, "frac23", "VULGAR FRACTION TWO THIRDS" }, 1689{ 0x2155, "frac15", "VULGAR FRACTION ONE FIFTH" }, 1690{ 0x2156, "frac25", "VULGAR FRACTION TWO FIFTHS" }, 1691{ 0x2157, "frac35", "VULGAR FRACTION THREE FIFTHS" }, 1692{ 0x2158, "frac45", "VULGAR FRACTION FOUR FIFTHS" }, 1693{ 0x2159, "frac16", "VULGAR FRACTION ONE SIXTH" }, 1694{ 0x215A, "frac56", "VULGAR FRACTION FIVE SIXTHS" }, 1695{ 0x215B, "frac18", "" }, 1696{ 0x215C, "frac38", "" }, 1697{ 0x215D, "frac58", "" }, 1698{ 0x215E, "frac78", "" }, 1699{ 0x2190, "larr", "LEFTWARDS DOUBLE ARROW" }, 1700{ 0x2191, "uarr", "UPWARDS ARROW" }, 1701{ 0x2192, "rarr", "RIGHTWARDS DOUBLE ARROW" }, 1702{ 0x2193, "darr", "DOWNWARDS ARROW" }, 1703{ 0x2194, "harr", "LEFT RIGHT ARROW" }, 1704{ 0x2194, "xhArr", "LEFT RIGHT ARROW" }, 1705{ 0x2194, "xharr", "LEFT RIGHT ARROW" }, 1706{ 0x2195, "varr", "UP DOWN ARROW" }, 1707{ 0x2196, "nwarr", "NORTH WEST ARROW" }, 1708{ 0x2197, "nearr", "NORTH EAST ARROW" }, 1709{ 0x2198, "drarr", "SOUTH EAST ARROW" }, 1710{ 0x2199, "dlarr", "SOUTH WEST ARROW" }, 1711{ 0x219A, "nlarr", "LEFTWARDS ARROW WITH STROKE" }, 1712{ 0x219B, "nrarr", "RIGHTWARDS ARROW WITH STROKE" }, 1713{ 0x219D, "rarrw", "RIGHTWARDS SQUIGGLE ARROW" }, 1714{ 0x219E, "Larr", "LEFTWARDS TWO HEADED ARROW" }, 1715{ 0x21A0, "Rarr", "RIGHTWARDS TWO HEADED ARROW" }, 1716{ 0x21A2, "larrtl", "LEFTWARDS ARROW WITH TAIL" }, 1717{ 0x21A3, "rarrtl", "RIGHTWARDS ARROW WITH TAIL" }, 1718{ 0x21A6, "map", "RIGHTWARDS ARROW FROM BAR" }, 1719{ 0x21A9, "larrhk", "LEFTWARDS ARROW WITH HOOK" }, 1720{ 0x21AA, "rarrhk", "RIGHTWARDS ARROW WITH HOOK" }, 1721{ 0x21AB, "larrlp", "LEFTWARDS ARROW WITH LOOP" }, 1722{ 0x21AC, "rarrlp", "RIGHTWARDS ARROW WITH LOOP" }, 1723{ 0x21AD, "harrw", "LEFT RIGHT WAVE ARROW" }, 1724{ 0x21AE, "nharr", "LEFT RIGHT ARROW WITH STROKE" }, 1725{ 0x21B0, "lsh", "UPWARDS ARROW WITH TIP LEFTWARDS" }, 1726{ 0x21B1, "rsh", "UPWARDS ARROW WITH TIP RIGHTWARDS" }, 1727{ 0x21B6, "cularr", "ANTICLOCKWISE TOP SEMICIRCLE ARROW" }, 1728{ 0x21B7, "curarr", "CLOCKWISE TOP SEMICIRCLE ARROW" }, 1729{ 0x21BA, "olarr", "ANTICLOCKWISE OPEN CIRCLE ARROW" }, 1730{ 0x21BB, "orarr", "CLOCKWISE OPEN CIRCLE ARROW" }, 1731{ 0x21BC, "lharu", "LEFTWARDS HARPOON WITH BARB UPWARDS" }, 1732{ 0x21BD, "lhard", "LEFTWARDS HARPOON WITH BARB DOWNWARDS" }, 1733{ 0x21BE, "uharr", "UPWARDS HARPOON WITH BARB RIGHTWARDS" }, 1734{ 0x21BF, "uharl", "UPWARDS HARPOON WITH BARB LEFTWARDS" }, 1735{ 0x21C0, "rharu", "RIGHTWARDS HARPOON WITH BARB UPWARDS" }, 1736{ 0x21C1, "rhard", "RIGHTWARDS HARPOON WITH BARB DOWNWARDS" }, 1737{ 0x21C2, "dharr", "DOWNWARDS HARPOON WITH BARB RIGHTWARDS" }, 1738{ 0x21C3, "dharl", "DOWNWARDS HARPOON WITH BARB LEFTWARDS" }, 1739{ 0x21C4, "rlarr2", "RIGHTWARDS ARROW OVER LEFTWARDS ARROW" }, 1740{ 0x21C6, "lrarr2", "LEFTWARDS ARROW OVER RIGHTWARDS ARROW" }, 1741{ 0x21C7, "larr2", "LEFTWARDS PAIRED ARROWS" }, 1742{ 0x21C8, "uarr2", "UPWARDS PAIRED ARROWS" }, 1743{ 0x21C9, "rarr2", "RIGHTWARDS PAIRED ARROWS" }, 1744{ 0x21CA, "darr2", "DOWNWARDS PAIRED ARROWS" }, 1745{ 0x21CB, "lrhar2", "LEFTWARDS HARPOON OVER RIGHTWARDS HARPOON" }, 1746{ 0x21CC, "rlhar2", "RIGHTWARDS HARPOON OVER LEFTWARDS HARPOON" }, 1747{ 0x21CD, "nlArr", "LEFTWARDS DOUBLE ARROW WITH STROKE" }, 1748{ 0x21CE, "nhArr", "LEFT RIGHT DOUBLE ARROW WITH STROKE" }, 1749{ 0x21CF, "nrArr", "RIGHTWARDS DOUBLE ARROW WITH STROKE" }, 1750{ 0x21D0, "lArr", "LEFTWARDS ARROW" }, 1751{ 0x21D0, "xlArr", "LEFTWARDS DOUBLE ARROW" }, 1752{ 0x21D1, "uArr", "UPWARDS DOUBLE ARROW" }, 1753{ 0x21D2, "rArr", "RIGHTWARDS ARROW" }, 1754{ 0x21D2, "xrArr", "RIGHTWARDS DOUBLE ARROW" }, 1755{ 0x21D3, "dArr", "DOWNWARDS DOUBLE ARROW" }, 1756{ 0x21D4, "hArr", "" }, 1757{ 0x21D4, "iff", "LEFT RIGHT DOUBLE ARROW" }, 1758{ 0x21D5, "vArr", "UP DOWN DOUBLE ARROW" }, 1759{ 0x21DA, "lAarr", "LEFTWARDS TRIPLE ARROW" }, 1760{ 0x21DB, "rAarr", "RIGHTWARDS TRIPLE ARROW" }, 1761{ 0x2200, "forall", "" }, 1762{ 0x2201, "comp", "COMPLEMENT" }, 1763{ 0x2202, "part", "" }, 1764{ 0x2203, "exist", "" }, 1765{ 0x2204, "nexist", "THERE DOES NOT EXIST" }, 1766{ 0x2205, "empty", "" }, 1767{ 0x2207, "nabla", "NABLA" }, 1768{ 0x2209, "notin", "" }, 1769{ 0x220A, "epsi", "" }, 1770{ 0x220A, "epsis", "" }, 1771{ 0x220A, "isin", "" }, 1772{ 0x220D, "bepsi", "SMALL CONTAINS AS MEMBER" }, 1773{ 0x220D, "ni", "" }, 1774{ 0x220F, "prod", "N-ARY PRODUCT" }, 1775{ 0x2210, "amalg", "N-ARY COPRODUCT" }, 1776{ 0x2210, "coprod", "N-ARY COPRODUCT" }, 1777{ 0x2210, "samalg", "" }, 1778{ 0x2211, "sum", "N-ARY SUMMATION" }, 1779{ 0x2212, "minus", "MINUS SIGN" }, 1780{ 0x2213, "mnplus", "" }, 1781{ 0x2214, "plusdo", "DOT PLUS" }, 1782{ 0x2216, "setmn", "SET MINUS" }, 1783{ 0x2216, "ssetmn", "SET MINUS" }, 1784{ 0x2217, "lowast", "ASTERISK OPERATOR" }, 1785{ 0x2218, "compfn", "RING OPERATOR" }, 1786{ 0x221A, "radic", "" }, 1787{ 0x221D, "prop", "" }, 1788{ 0x221D, "vprop", "" }, 1789{ 0x221E, "infin", "" }, 1790{ 0x221F, "ang90", "RIGHT ANGLE" }, 1791{ 0x2220, "ang", "ANGLE" }, 1792{ 0x2221, "angmsd", "MEASURED ANGLE" }, 1793{ 0x2222, "angsph", "" }, 1794{ 0x2223, "mid", "" }, 1795{ 0x2224, "nmid", "DOES NOT DIVIDE" }, 1796{ 0x2225, "par", "PARALLEL TO" }, 1797{ 0x2225, "spar", "PARALLEL TO" }, 1798{ 0x2226, "npar", "NOT PARALLEL TO" }, 1799{ 0x2226, "nspar", "NOT PARALLEL TO" }, 1800{ 0x2227, "and", "" }, 1801{ 0x2228, "or", "" }, 1802{ 0x2229, "cap", "" }, 1803{ 0x222A, "cup", "" }, 1804{ 0x222B, "int", "" }, 1805{ 0x222E, "conint", "" }, 1806{ 0x2234, "there4", "" }, 1807{ 0x2235, "becaus", "BECAUSE" }, 1808{ 0x223C, "sim", "" }, 1809{ 0x223C, "thksim", "TILDE OPERATOR" }, 1810{ 0x223D, "bsim", "" }, 1811{ 0x2240, "wreath", "WREATH PRODUCT" }, 1812{ 0x2241, "nsim", "" }, 1813{ 0x2243, "sime", "" }, 1814{ 0x2244, "nsime", "" }, 1815{ 0x2245, "cong", "" }, 1816{ 0x2247, "ncong", "NEITHER APPROXIMATELY NOR ACTUALLY EQUAL TO" }, 1817{ 0x2248, "ap", "" }, 1818{ 0x2248, "thkap", "ALMOST EQUAL TO" }, 1819{ 0x2249, "nap", "NOT ALMOST EQUAL TO" }, 1820{ 0x224A, "ape", "" }, 1821{ 0x224C, "bcong", "ALL EQUAL TO" }, 1822{ 0x224D, "asymp", "EQUIVALENT TO" }, 1823{ 0x224E, "bump", "" }, 1824{ 0x224F, "bumpe", "" }, 1825{ 0x2250, "esdot", "" }, 1826{ 0x2251, "eDot", "" }, 1827{ 0x2252, "efDot", "" }, 1828{ 0x2253, "erDot", "" }, 1829{ 0x2254, "colone", "" }, 1830{ 0x2255, "ecolon", "" }, 1831{ 0x2256, "ecir", "" }, 1832{ 0x2257, "cire", "" }, 1833{ 0x2259, "wedgeq", "ESTIMATES" }, 1834{ 0x225C, "trie", "" }, 1835{ 0x2260, "ne", "" }, 1836{ 0x2261, "equiv", "" }, 1837{ 0x2262, "nequiv", "NOT IDENTICAL TO" }, 1838{ 0x2264, "le", "" }, 1839{ 0x2264, "les", "LESS-THAN OR EQUAL TO" }, 1840{ 0x2265, "ge", "GREATER-THAN OR EQUAL TO" }, 1841{ 0x2265, "ges", "GREATER-THAN OR EQUAL TO" }, 1842{ 0x2266, "lE", "" }, 1843{ 0x2267, "gE", "" }, 1844{ 0x2268, "lnE", "" }, 1845{ 0x2268, "lne", "" }, 1846{ 0x2268, "lvnE", "LESS-THAN BUT NOT EQUAL TO" }, 1847{ 0x2269, "gnE", "" }, 1848{ 0x2269, "gne", "" }, 1849{ 0x2269, "gvnE", "GREATER-THAN BUT NOT EQUAL TO" }, 1850{ 0x226A, "Lt", "MUCH LESS-THAN" }, 1851{ 0x226B, "Gt", "MUCH GREATER-THAN" }, 1852{ 0x226C, "twixt", "BETWEEN" }, 1853{ 0x226E, "nlt", "NOT LESS-THAN" }, 1854{ 0x226F, "ngt", "NOT GREATER-THAN" }, 1855{ 0x2270, "nlE", "" }, 1856{ 0x2270, "nle", "NEITHER LESS-THAN NOR EQUAL TO" }, 1857{ 0x2270, "nles", "" }, 1858{ 0x2271, "ngE", "" }, 1859{ 0x2271, "nge", "NEITHER GREATER-THAN NOR EQUAL TO" }, 1860{ 0x2271, "nges", "" }, 1861{ 0x2272, "lap", "LESS-THAN OR EQUIVALENT TO" }, 1862{ 0x2272, "lsim", "LESS-THAN OR EQUIVALENT TO" }, 1863{ 0x2273, "gap", "GREATER-THAN OR EQUIVALENT TO" }, 1864{ 0x2273, "gsim", "GREATER-THAN OR EQUIVALENT TO" }, 1865{ 0x2276, "lg", "LESS-THAN OR GREATER-THAN" }, 1866{ 0x2277, "gl", "" }, 1867{ 0x227A, "pr", "" }, 1868{ 0x227B, "sc", "" }, 1869{ 0x227C, "cupre", "" }, 1870{ 0x227C, "pre", "" }, 1871{ 0x227D, "sccue", "" }, 1872{ 0x227D, "sce", "" }, 1873{ 0x227E, "prap", "" }, 1874{ 0x227E, "prsim", "" }, 1875{ 0x227F, "scap", "" }, 1876{ 0x227F, "scsim", "" }, 1877{ 0x2280, "npr", "DOES NOT PRECEDE" }, 1878{ 0x2281, "nsc", "DOES NOT SUCCEED" }, 1879{ 0x2282, "sub", "" }, 1880{ 0x2283, "sup", "" }, 1881{ 0x2284, "nsub", "NOT A SUBSET OF" }, 1882{ 0x2285, "nsup", "NOT A SUPERSET OF" }, 1883{ 0x2286, "subE", "" }, 1884{ 0x2286, "sube", "" }, 1885{ 0x2287, "supE", "" }, 1886{ 0x2287, "supe", "" }, 1887{ 0x2288, "nsubE", "" }, 1888{ 0x2288, "nsube", "" }, 1889{ 0x2289, "nsupE", "" }, 1890{ 0x2289, "nsupe", "" }, 1891{ 0x228A, "subne", "" }, 1892{ 0x228A, "subnE", "SUBSET OF WITH NOT EQUAL TO" }, 1893{ 0x228A, "vsubne", "SUBSET OF WITH NOT EQUAL TO" }, 1894{ 0x228B, "supnE", "" }, 1895{ 0x228B, "supne", "" }, 1896{ 0x228B, "vsupnE", "SUPERSET OF WITH NOT EQUAL TO" }, 1897{ 0x228B, "vsupne", "SUPERSET OF WITH NOT EQUAL TO" }, 1898{ 0x228E, "uplus", "MULTISET UNION" }, 1899{ 0x228F, "sqsub", "" }, 1900{ 0x2290, "sqsup", "" }, 1901{ 0x2291, "sqsube", "" }, 1902{ 0x2292, "sqsupe", "" }, 1903{ 0x2293, "sqcap", "SQUARE CAP" }, 1904{ 0x2294, "sqcup", "SQUARE CUP" }, 1905{ 0x2295, "oplus", "CIRCLED PLUS" }, 1906{ 0x2296, "ominus", "CIRCLED MINUS" }, 1907{ 0x2297, "otimes", "CIRCLED TIMES" }, 1908{ 0x2298, "osol", "CIRCLED DIVISION SLASH" }, 1909{ 0x2299, "odot", "CIRCLED DOT OPERATOR" }, 1910{ 0x229A, "ocir", "CIRCLED RING OPERATOR" }, 1911{ 0x229B, "oast", "CIRCLED ASTERISK OPERATOR" }, 1912{ 0x229D, "odash", "CIRCLED DASH" }, 1913{ 0x229E, "plusb", "SQUARED PLUS" }, 1914{ 0x229F, "minusb", "SQUARED MINUS" }, 1915{ 0x22A0, "timesb", "SQUARED TIMES" }, 1916{ 0x22A1, "sdotb", "SQUARED DOT OPERATOR" }, 1917{ 0x22A2, "vdash", "" }, 1918{ 0x22A3, "dashv", "" }, 1919{ 0x22A4, "top", "DOWN TACK" }, 1920{ 0x22A5, "bottom", "" }, 1921{ 0x22A5, "perp", "" }, 1922{ 0x22A7, "models", "MODELS" }, 1923{ 0x22A8, "vDash", "" }, 1924{ 0x22A9, "Vdash", "" }, 1925{ 0x22AA, "Vvdash", "" }, 1926{ 0x22AC, "nvdash", "DOES NOT PROVE" }, 1927{ 0x22AD, "nvDash", "NOT TRUE" }, 1928{ 0x22AE, "nVdash", "DOES NOT FORCE" }, 1929{ 0x22AF, "nVDash", "NEGATED DOUBLE VERTICAL BAR DOUBLE RIGHT TURNSTILE" }, 1930{ 0x22B2, "vltri", "" }, 1931{ 0x22B3, "vrtri", "" }, 1932{ 0x22B4, "ltrie", "" }, 1933{ 0x22B5, "rtrie", "" }, 1934{ 0x22B8, "mumap", "MULTIMAP" }, 1935{ 0x22BA, "intcal", "INTERCALATE" }, 1936{ 0x22BB, "veebar", "" }, 1937{ 0x22BC, "barwed", "NAND" }, 1938{ 0x22C4, "diam", "DIAMOND OPERATOR" }, 1939{ 0x22C5, "sdot", "DOT OPERATOR" }, 1940{ 0x22C6, "sstarf", "STAR OPERATOR" }, 1941{ 0x22C6, "star", "STAR OPERATOR" }, 1942{ 0x22C7, "divonx", "DIVISION TIMES" }, 1943{ 0x22C8, "bowtie", "" }, 1944{ 0x22C9, "ltimes", "LEFT NORMAL FACTOR SEMIDIRECT PRODUCT" }, 1945{ 0x22CA, "rtimes", "RIGHT NORMAL FACTOR SEMIDIRECT PRODUCT" }, 1946{ 0x22CB, "lthree", "LEFT SEMIDIRECT PRODUCT" }, 1947{ 0x22CC, "rthree", "RIGHT SEMIDIRECT PRODUCT" }, 1948{ 0x22CD, "bsime", "" }, 1949{ 0x22CE, "cuvee", "CURLY LOGICAL OR" }, 1950{ 0x22CF, "cuwed", "CURLY LOGICAL AND" }, 1951{ 0x22D0, "Sub", "" }, 1952{ 0x22D1, "Sup", "" }, 1953{ 0x22D2, "Cap", "DOUBLE INTERSECTION" }, 1954{ 0x22D3, "Cup", "DOUBLE UNION" }, 1955{ 0x22D4, "fork", "" }, 1956{ 0x22D6, "ldot", "" }, 1957{ 0x22D7, "gsdot", "" }, 1958{ 0x22D8, "Ll", "" }, 1959{ 0x22D9, "Gg", "VERY MUCH GREATER-THAN" }, 1960{ 0x22DA, "lEg", "" }, 1961{ 0x22DA, "leg", "" }, 1962{ 0x22DB, "gEl", "" }, 1963{ 0x22DB, "gel", "" }, 1964{ 0x22DC, "els", "" }, 1965{ 0x22DD, "egs", "" }, 1966{ 0x22DE, "cuepr", "" }, 1967{ 0x22DF, "cuesc", "" }, 1968{ 0x22E0, "npre", "DOES NOT PRECEDE OR EQUAL" }, 1969{ 0x22E1, "nsce", "DOES NOT SUCCEED OR EQUAL" }, 1970{ 0x22E6, "lnsim", "" }, 1971{ 0x22E7, "gnsim", "GREATER-THAN BUT NOT EQUIVALENT TO" }, 1972{ 0x22E8, "prnap", "" }, 1973{ 0x22E8, "prnsim", "" }, 1974{ 0x22E9, "scnap", "" }, 1975{ 0x22E9, "scnsim", "" }, 1976{ 0x22EA, "nltri", "NOT NORMAL SUBGROUP OF" }, 1977{ 0x22EB, "nrtri", "DOES NOT CONTAIN AS NORMAL SUBGROUP" }, 1978{ 0x22EC, "nltrie", "NOT NORMAL SUBGROUP OF OR EQUAL TO" }, 1979{ 0x22ED, "nrtrie", "DOES NOT CONTAIN AS NORMAL SUBGROUP OR EQUAL" }, 1980{ 0x22EE, "vellip", "" }, 1981{ 0x2306, "Barwed", "PERSPECTIVE" }, 1982{ 0x2308, "lceil", "LEFT CEILING" }, 1983{ 0x2309, "rceil", "RIGHT CEILING" }, 1984{ 0x230A, "lfloor", "LEFT FLOOR" }, 1985{ 0x230B, "rfloor", "RIGHT FLOOR" }, 1986{ 0x230C, "drcrop", "BOTTOM RIGHT CROP" }, 1987{ 0x230D, "dlcrop", "BOTTOM LEFT CROP" }, 1988{ 0x230E, "urcrop", "TOP RIGHT CROP" }, 1989{ 0x230F, "ulcrop", "TOP LEFT CROP" }, 1990{ 0x2315, "telrec", "TELEPHONE RECORDER" }, 1991{ 0x2316, "target", "POSITION INDICATOR" }, 1992{ 0x231C, "ulcorn", "TOP LEFT CORNER" }, 1993{ 0x231D, "urcorn", "TOP RIGHT CORNER" }, 1994{ 0x231E, "dlcorn", "BOTTOM LEFT CORNER" }, 1995{ 0x231F, "drcorn", "BOTTOM RIGHT CORNER" }, 1996{ 0x2322, "frown", "" }, 1997{ 0x2322, "sfrown", "FROWN" }, 1998{ 0x2323, "smile", "" }, 1999{ 0x2323, "ssmile", "SMILE" }, 2000{ 0x2423, "blank", "OPEN BOX" }, 2001{ 0x24C8, "oS", "CIRCLED LATIN CAPITAL LETTER S" }, 2002{ 0x2500, "boxh", "BOX DRAWINGS LIGHT HORIZONTAL" }, 2003{ 0x2502, "boxv", "BOX DRAWINGS LIGHT VERTICAL" }, 2004{ 0x250C, "boxdr", "BOX DRAWINGS LIGHT DOWN AND RIGHT" }, 2005{ 0x2510, "boxdl", "BOX DRAWINGS LIGHT DOWN AND LEFT" }, 2006{ 0x2514, "boxur", "BOX DRAWINGS LIGHT UP AND RIGHT" }, 2007{ 0x2518, "boxul", "BOX DRAWINGS LIGHT UP AND LEFT" }, 2008{ 0x251C, "boxvr", "BOX DRAWINGS LIGHT VERTICAL AND RIGHT" }, 2009{ 0x2524, "boxvl", "BOX DRAWINGS LIGHT VERTICAL AND LEFT" }, 2010{ 0x252C, "boxhd", "BOX DRAWINGS LIGHT DOWN AND HORIZONTAL" }, 2011{ 0x2534, "boxhu", "BOX DRAWINGS LIGHT UP AND HORIZONTAL" }, 2012{ 0x253C, "boxvh", "BOX DRAWINGS LIGHT VERTICAL AND HORIZONTAL" }, 2013{ 0x2550, "boxH", "BOX DRAWINGS DOUBLE HORIZONTAL" }, 2014{ 0x2551, "boxV", "BOX DRAWINGS DOUBLE VERTICAL" }, 2015{ 0x2552, "boxDR", "BOX DRAWINGS DOWN SINGLE AND RIGHT DOUBLE" }, 2016{ 0x2553, "boxDr", "BOX DRAWINGS DOWN DOUBLE AND RIGHT SINGLE" }, 2017{ 0x2554, "boxdR", "BOX DRAWINGS DOUBLE DOWN AND RIGHT" }, 2018{ 0x2555, "boxDL", "BOX DRAWINGS DOWN SINGLE AND LEFT DOUBLE" }, 2019{ 0x2556, "boxdL", "BOX DRAWINGS DOWN DOUBLE AND LEFT SINGLE" }, 2020{ 0x2557, "boxDl", "BOX DRAWINGS DOUBLE DOWN AND LEFT" }, 2021{ 0x2558, "boxUR", "BOX DRAWINGS UP SINGLE AND RIGHT DOUBLE" }, 2022{ 0x2559, "boxuR", "BOX DRAWINGS UP DOUBLE AND RIGHT SINGLE" }, 2023{ 0x255A, "boxUr", "BOX DRAWINGS DOUBLE UP AND RIGHT" }, 2024{ 0x255B, "boxUL", "BOX DRAWINGS UP SINGLE AND LEFT DOUBLE" }, 2025{ 0x255C, "boxUl", "BOX DRAWINGS UP DOUBLE AND LEFT SINGLE" }, 2026{ 0x255D, "boxuL", "BOX DRAWINGS DOUBLE UP AND LEFT" }, 2027{ 0x255E, "boxvR", "BOX DRAWINGS VERTICAL SINGLE AND RIGHT DOUBLE" }, 2028{ 0x255F, "boxVR", "BOX DRAWINGS VERTICAL DOUBLE AND RIGHT SINGLE" }, 2029{ 0x2560, "boxVr", "BOX DRAWINGS DOUBLE VERTICAL AND RIGHT" }, 2030{ 0x2561, "boxvL", "BOX DRAWINGS VERTICAL SINGLE AND LEFT DOUBLE" }, 2031{ 0x2562, "boxVL", "BOX DRAWINGS VERTICAL DOUBLE AND LEFT SINGLE" }, 2032{ 0x2563, "boxVl", "BOX DRAWINGS DOUBLE VERTICAL AND LEFT" }, 2033{ 0x2564, "boxhD", "BOX DRAWINGS DOWN SINGLE AND HORIZONTAL DOUBLE" }, 2034{ 0x2565, "boxHD", "BOX DRAWINGS DOWN DOUBLE AND HORIZONTAL SINGLE" }, 2035{ 0x2566, "boxHd", "BOX DRAWINGS DOUBLE DOWN AND HORIZONTAL" }, 2036{ 0x2567, "boxhU", "BOX DRAWINGS UP SINGLE AND HORIZONTAL DOUBLE" }, 2037{ 0x2568, "boxHU", "BOX DRAWINGS UP DOUBLE AND HORIZONTAL SINGLE" }, 2038{ 0x2569, "boxHu", "BOX DRAWINGS DOUBLE UP AND HORIZONTAL" }, 2039{ 0x256A, "boxvH", "BOX DRAWINGS VERTICAL SINGLE AND HORIZONTAL DOUBLE" }, 2040{ 0x256B, "boxVH", "BOX DRAWINGS VERTICAL DOUBLE AND HORIZONTAL SINGLE" }, 2041{ 0x256C, "boxVh", "BOX DRAWINGS DOUBLE VERTICAL AND HORIZONTAL" }, 2042{ 0x2580, "uhblk", "UPPER HALF BLOCK" }, 2043{ 0x2584, "lhblk", "LOWER HALF BLOCK" }, 2044{ 0x2588, "block", "FULL BLOCK" }, 2045{ 0x2591, "blk14", "LIGHT SHADE" }, 2046{ 0x2592, "blk12", "MEDIUM SHADE" }, 2047{ 0x2593, "blk34", "DARK SHADE" }, 2048{ 0x25A1, "square", "WHITE SQUARE" }, 2049{ 0x25A1, "squ", "WHITE SQUARE" }, 2050{ 0x25AA, "squf", "" }, 2051{ 0x25AD, "rect", "WHITE RECTANGLE" }, 2052{ 0x25AE, "marker", "BLACK VERTICAL RECTANGLE" }, 2053{ 0x25B3, "xutri", "WHITE UP-POINTING TRIANGLE" }, 2054{ 0x25B4, "utrif", "BLACK UP-POINTING TRIANGLE" }, 2055{ 0x25B5, "utri", "WHITE UP-POINTING TRIANGLE" }, 2056{ 0x25B8, "rtrif", "BLACK RIGHT-POINTING TRIANGLE" }, 2057{ 0x25B9, "rtri", "WHITE RIGHT-POINTING TRIANGLE" }, 2058{ 0x25BD, "xdtri", "WHITE DOWN-POINTING TRIANGLE" }, 2059{ 0x25BE, "dtrif", "BLACK DOWN-POINTING TRIANGLE" }, 2060{ 0x25BF, "dtri", "WHITE DOWN-POINTING TRIANGLE" }, 2061{ 0x25C2, "ltrif", "BLACK LEFT-POINTING TRIANGLE" }, 2062{ 0x25C3, "ltri", "WHITE LEFT-POINTING TRIANGLE" }, 2063{ 0x25CA, "loz", "LOZENGE" }, 2064{ 0x25CB, "cir", "WHITE CIRCLE" }, 2065{ 0x25CB, "xcirc", "WHITE CIRCLE" }, 2066{ 0x2605, "starf", "BLACK STAR" }, 2067{ 0x260E, "phone", "TELEPHONE SIGN" }, 2068{ 0x2640, "female", "" }, 2069{ 0x2642, "male", "MALE SIGN" }, 2070{ 0x2660, "spades", "BLACK SPADE SUIT" }, 2071{ 0x2663, "clubs", "BLACK CLUB SUIT" }, 2072{ 0x2665, "hearts", "BLACK HEART SUIT" }, 2073{ 0x2666, "diams", "BLACK DIAMOND SUIT" }, 2074{ 0x2669, "sung", "" }, 2075{ 0x266D, "flat", "MUSIC FLAT SIGN" }, 2076{ 0x266E, "natur", "MUSIC NATURAL SIGN" }, 2077{ 0x266F, "sharp", "MUSIC SHARP SIGN" }, 2078{ 0x2713, "check", "CHECK MARK" }, 2079{ 0x2717, "cross", "BALLOT X" }, 2080{ 0x2720, "malt", "MALTESE CROSS" }, 2081{ 0x2726, "lozf", "" }, 2082{ 0x2736, "sext", "SIX POINTED BLACK STAR" }, 2083{ 0x3008, "lang", "" }, 2084{ 0x3009, "rang", "" }, 2085{ 0xE291, "rpargt", "" }, 2086{ 0xE2A2, "lnap", "" }, 2087{ 0xE2AA, "nsmid", "" }, 2088{ 0xE2B3, "prnE", "" }, 2089{ 0xE2B5, "scnE", "" }, 2090{ 0xE2B8, "vsubnE", "" }, 2091{ 0xE301, "smid", "" }, 2092{ 0xE411, "gnap", "" }, 2093{ 0xFB00, "fflig", "" }, 2094{ 0xFB01, "filig", "" }, 2095{ 0xFB02, "fllig", "" }, 2096{ 0xFB03, "ffilig", "" }, 2097{ 0xFB04, "ffllig", "" }, 2098{ 0xFE68, "sbsol", "SMALL REVERSE SOLIDUS" }, 2099}; 2100 2101/************************************************************************ 2102 * * 2103 * Commodity functions to handle entities * 2104 * * 2105 ************************************************************************/ 2106 2107/* 2108 * Macro used to grow the current buffer. 2109 */ 2110#define growBuffer(buffer) { \ 2111 buffer##_size *= 2; \ 2112 buffer = (xmlChar *) xmlRealloc(buffer, buffer##_size * sizeof(xmlChar)); \ 2113 if (buffer == NULL) { \ 2114 perror("realloc failed"); \ 2115 return(NULL); \ 2116 } \ 2117} 2118 2119/** 2120 * docbEntityLookup: 2121 * @name: the entity name 2122 * 2123 * Lookup the given entity in EntitiesTable 2124 * 2125 * TODO: the linear scan is really ugly, an hash table is really needed. 2126 * 2127 * Returns the associated docbEntityDescPtr if found, NULL otherwise. 2128 */ 2129static docbEntityDescPtr 2130docbEntityLookup(const xmlChar *name) { 2131 unsigned int i; 2132 2133 for (i = 0;i < (sizeof(docbookEntitiesTable)/ 2134 sizeof(docbookEntitiesTable[0]));i++) { 2135 if (xmlStrEqual(name, BAD_CAST docbookEntitiesTable[i].name)) { 2136#ifdef DEBUG 2137 xmlGenericError(xmlGenericErrorContext,"Found entity %s\n", name); 2138#endif 2139 return(&docbookEntitiesTable[i]); 2140 } 2141 } 2142 return(NULL); 2143} 2144 2145/** 2146 * docbEntityValueLookup: 2147 * @value: the entity's unicode value 2148 * 2149 * Lookup the given entity in EntitiesTable 2150 * 2151 * TODO: the linear scan is really ugly, an hash table is really needed. 2152 * 2153 * Returns the associated docbEntityDescPtr if found, NULL otherwise. 2154 */ 2155static docbEntityDescPtr 2156docbEntityValueLookup(int value) { 2157 unsigned int i; 2158#ifdef DEBUG 2159 int lv = 0; 2160#endif 2161 2162 for (i = 0;i < (sizeof(docbookEntitiesTable)/ 2163 sizeof(docbookEntitiesTable[0]));i++) { 2164 if (docbookEntitiesTable[i].value >= value) { 2165 if (docbookEntitiesTable[i].value > value) 2166 break; 2167#ifdef DEBUG 2168 xmlGenericError(xmlGenericErrorContext,"Found entity %s\n", docbookEntitiesTable[i].name); 2169#endif 2170 return(&docbookEntitiesTable[i]); 2171 } 2172#ifdef DEBUG 2173 if (lv > docbookEntitiesTable[i].value) { 2174 xmlGenericError(xmlGenericErrorContext, 2175 "docbookEntitiesTable[] is not sorted (%d > %d)!\n", 2176 lv, docbookEntitiesTable[i].value); 2177 } 2178 lv = docbookEntitiesTable[i].value; 2179#endif 2180 } 2181 return(NULL); 2182} 2183 2184#if 0 2185/** 2186 * UTF8ToSgml: 2187 * @out: a pointer to an array of bytes to store the result 2188 * @outlen: the length of @out 2189 * @in: a pointer to an array of UTF-8 chars 2190 * @inlen: the length of @in 2191 * 2192 * Take a block of UTF-8 chars in and try to convert it to an ASCII 2193 * plus SGML entities block of chars out. 2194 * 2195 * Returns 0 if success, -2 if the transcoding fails, or -1 otherwise 2196 * The value of @inlen after return is the number of octets consumed 2197 * as the return value is positive, else unpredictiable. 2198 * The value of @outlen after return is the number of octets consumed. 2199 */ 2200int 2201UTF8ToSgml(unsigned char* out, int *outlen, 2202 const unsigned char* in, int *inlen) { 2203 const unsigned char* processed = in; 2204 const unsigned char* outend; 2205 const unsigned char* outstart = out; 2206 const unsigned char* instart = in; 2207 const unsigned char* inend; 2208 unsigned int c, d; 2209 int trailing; 2210 2211 if (in == NULL) { 2212 /* 2213 * initialization nothing to do 2214 */ 2215 *outlen = 0; 2216 *inlen = 0; 2217 return(0); 2218 } 2219 inend = in + (*inlen); 2220 outend = out + (*outlen); 2221 while (in < inend) { 2222 d = *in++; 2223 if (d < 0x80) { c= d; trailing= 0; } 2224 else if (d < 0xC0) { 2225 /* trailing byte in leading position */ 2226 *outlen = out - outstart; 2227 *inlen = processed - instart; 2228 return(-2); 2229 } else if (d < 0xE0) { c= d & 0x1F; trailing= 1; } 2230 else if (d < 0xF0) { c= d & 0x0F; trailing= 2; } 2231 else if (d < 0xF8) { c= d & 0x07; trailing= 3; } 2232 else { 2233 /* no chance for this in Ascii */ 2234 *outlen = out - outstart; 2235 *inlen = processed - instart; 2236 return(-2); 2237 } 2238 2239 if (inend - in < trailing) { 2240 break; 2241 } 2242 2243 for ( ; trailing; trailing--) { 2244 if ((in >= inend) || (((d= *in++) & 0xC0) != 0x80)) 2245 break; 2246 c <<= 6; 2247 c |= d & 0x3F; 2248 } 2249 2250 /* assertion: c is a single UTF-4 value */ 2251 if (c < 0x80) { 2252 if (out + 1 >= outend) 2253 break; 2254 *out++ = c; 2255 } else { 2256 int len; 2257 docbEntityDescPtr ent; 2258 2259 /* 2260 * Try to lookup a predefined SGML entity for it 2261 */ 2262 2263 ent = docbEntityValueLookup(c); 2264 if (ent == NULL) { 2265 /* no chance for this in Ascii */ 2266 *outlen = out - outstart; 2267 *inlen = processed - instart; 2268 return(-2); 2269 } 2270 len = strlen(ent->name); 2271 if (out + 2 + len >= outend) 2272 break; 2273 *out++ = '&'; 2274 memcpy(out, ent->name, len); 2275 out += len; 2276 *out++ = ';'; 2277 } 2278 processed = in; 2279 } 2280 *outlen = out - outstart; 2281 *inlen = processed - instart; 2282 return(0); 2283} 2284#endif 2285 2286/** 2287 * docbEncodeEntities: 2288 * @out: a pointer to an array of bytes to store the result 2289 * @outlen: the length of @out 2290 * @in: a pointer to an array of UTF-8 chars 2291 * @inlen: the length of @in 2292 * @quoteChar: the quote character to escape (' or ") or zero. 2293 * 2294 * Take a block of UTF-8 chars in and try to convert it to an ASCII 2295 * plus SGML entities block of chars out. 2296 * 2297 * Returns 0 if success, -2 if the transcoding fails, or -1 otherwise 2298 * The value of @inlen after return is the number of octets consumed 2299 * as the return value is positive, else unpredictiable. 2300 * The value of @outlen after return is the number of octets consumed. 2301 */ 2302int 2303docbEncodeEntities(unsigned char* out, int *outlen, 2304 const unsigned char* in, int *inlen, int quoteChar) { 2305 const unsigned char* processed = in; 2306 const unsigned char* outend = out + (*outlen); 2307 const unsigned char* outstart = out; 2308 const unsigned char* instart = in; 2309 const unsigned char* inend = in + (*inlen); 2310 unsigned int c, d; 2311 int trailing; 2312 2313 while (in < inend) { 2314 d = *in++; 2315 if (d < 0x80) { c= d; trailing= 0; } 2316 else if (d < 0xC0) { 2317 /* trailing byte in leading position */ 2318 *outlen = out - outstart; 2319 *inlen = processed - instart; 2320 return(-2); 2321 } else if (d < 0xE0) { c= d & 0x1F; trailing= 1; } 2322 else if (d < 0xF0) { c= d & 0x0F; trailing= 2; } 2323 else if (d < 0xF8) { c= d & 0x07; trailing= 3; } 2324 else { 2325 /* no chance for this in Ascii */ 2326 *outlen = out - outstart; 2327 *inlen = processed - instart; 2328 return(-2); 2329 } 2330 2331 if (inend - in < trailing) 2332 break; 2333 2334 while (trailing--) { 2335 if (((d= *in++) & 0xC0) != 0x80) { 2336 *outlen = out - outstart; 2337 *inlen = processed - instart; 2338 return(-2); 2339 } 2340 c <<= 6; 2341 c |= d & 0x3F; 2342 } 2343 2344 /* assertion: c is a single UTF-4 value */ 2345 if (c < 0x80 && c != (unsigned int) quoteChar && c != '&' && c != '<' && c != '>') { 2346 if (out >= outend) 2347 break; 2348 *out++ = c; 2349 } else { 2350 docbEntityDescPtr ent; 2351 const char *cp; 2352 char nbuf[16]; 2353 int len; 2354 2355 /* 2356 * Try to lookup a predefined SGML entity for it 2357 */ 2358 ent = docbEntityValueLookup(c); 2359 if (ent == NULL) { 2360 sprintf(nbuf, "#%u", c); 2361 cp = nbuf; 2362 } 2363 else 2364 cp = ent->name; 2365 len = strlen(cp); 2366 if (out + 2 + len > outend) 2367 break; 2368 *out++ = '&'; 2369 memcpy(out, cp, len); 2370 out += len; 2371 *out++ = ';'; 2372 } 2373 processed = in; 2374 } 2375 *outlen = out - outstart; 2376 *inlen = processed - instart; 2377 return(0); 2378} 2379 2380 2381/************************************************************************ 2382 * * 2383 * Commodity functions to handle streams * 2384 * * 2385 ************************************************************************/ 2386 2387/** 2388 * docbNewInputStream: 2389 * @ctxt: an SGML parser context 2390 * 2391 * Create a new input stream structure 2392 * Returns the new input stream or NULL 2393 */ 2394static docbParserInputPtr 2395docbNewInputStream(docbParserCtxtPtr ctxt) { 2396 docbParserInputPtr input; 2397 2398 input = (xmlParserInputPtr) xmlMalloc(sizeof(docbParserInput)); 2399 if (input == NULL) { 2400 ctxt->errNo = XML_ERR_NO_MEMORY; 2401 if ((ctxt->sax != NULL) && (ctxt->sax->error != NULL)) 2402 ctxt->sax->error(ctxt->userData, 2403 "malloc: couldn't allocate a new input stream\n"); 2404 return(NULL); 2405 } 2406 memset(input, 0, sizeof(docbParserInput)); 2407 input->filename = NULL; 2408 input->directory = NULL; 2409 input->base = NULL; 2410 input->cur = NULL; 2411 input->buf = NULL; 2412 input->line = 1; 2413 input->col = 1; 2414 input->buf = NULL; 2415 input->free = NULL; 2416 input->version = NULL; 2417 input->consumed = 0; 2418 input->length = 0; 2419 return(input); 2420} 2421 2422 2423/************************************************************************ 2424 * * 2425 * Commodity functions, cleanup needed ? * 2426 * * 2427 ************************************************************************/ 2428 2429/** 2430 * areBlanks: 2431 * @ctxt: an SGML parser context 2432 * @str: a xmlChar * 2433 * @len: the size of @str 2434 * 2435 * Is this a sequence of blank chars that one can ignore ? 2436 * 2437 * Returns 1 if ignorable 0 otherwise. 2438 */ 2439 2440static int areBlanks(docbParserCtxtPtr ctxt, const xmlChar *str, int len) { 2441 int i; 2442 xmlNodePtr lastChild; 2443 2444 for (i = 0;i < len;i++) 2445 if (!(IS_BLANK(str[i]))) return(0); 2446 2447 if (CUR == 0) return(1); 2448 if (CUR != '<') return(0); 2449 if (ctxt->name == NULL) 2450 return(1); 2451 if (ctxt->node == NULL) return(0); 2452 lastChild = xmlGetLastChild(ctxt->node); 2453 if (lastChild == NULL) { 2454 if (ctxt->node->content != NULL) return(0); 2455 } else if (xmlNodeIsText(lastChild)) 2456 return(0); 2457 return(1); 2458} 2459 2460/************************************************************************ 2461 * * 2462 * The parser itself * 2463 * * 2464 ************************************************************************/ 2465 2466/** 2467 * docbParseSGMLName: 2468 * @ctxt: an SGML parser context 2469 * 2470 * parse an SGML tag or attribute name, note that we convert it to lowercase 2471 * since SGML names are not case-sensitive. 2472 * 2473 * Returns the Tag Name parsed or NULL 2474 */ 2475 2476static xmlChar * 2477docbParseSGMLName(docbParserCtxtPtr ctxt) { 2478 xmlChar *ret = NULL; 2479 int i = 0; 2480 xmlChar loc[DOCB_PARSER_BUFFER_SIZE]; 2481 2482 if (!IS_LETTER(CUR) && (CUR != '_') && 2483 (CUR != ':')) return(NULL); 2484 2485 while ((i < DOCB_PARSER_BUFFER_SIZE) && 2486 ((IS_LETTER(CUR)) || (IS_DIGIT(CUR)) || 2487 (CUR == ':') || (CUR == '_'))) { 2488 if ((CUR >= 'A') && (CUR <= 'Z')) loc[i] = CUR + 0x20; 2489 else loc[i] = CUR; 2490 i++; 2491 2492 NEXT; 2493 } 2494 2495 ret = xmlStrndup(loc, i); 2496 2497 return(ret); 2498} 2499 2500/** 2501 * docbParseName: 2502 * @ctxt: an SGML parser context 2503 * 2504 * parse an SGML name, this routine is case sensistive. 2505 * 2506 * Returns the Name parsed or NULL 2507 */ 2508 2509static xmlChar * 2510docbParseName(docbParserCtxtPtr ctxt) { 2511 xmlChar buf[DOCB_MAX_NAMELEN]; 2512 int len = 0; 2513 2514 GROW; 2515 if (!IS_LETTER(CUR) && (CUR != '_')) { 2516 return(NULL); 2517 } 2518 2519 while ((IS_LETTER(CUR)) || (IS_DIGIT(CUR)) || 2520 (CUR == '.') || (CUR == '-') || 2521 (CUR == '_') || (CUR == ':') || 2522 (IS_COMBINING(CUR)) || 2523 (IS_EXTENDER(CUR))) { 2524 buf[len++] = CUR; 2525 NEXT; 2526 if (len >= DOCB_MAX_NAMELEN) { 2527 xmlGenericError(xmlGenericErrorContext, 2528 "docbParseName: reached DOCB_MAX_NAMELEN limit\n"); 2529 while ((IS_LETTER(CUR)) || (IS_DIGIT(CUR)) || 2530 (CUR == '.') || (CUR == '-') || 2531 (CUR == '_') || (CUR == ':') || 2532 (IS_COMBINING(CUR)) || 2533 (IS_EXTENDER(CUR))) 2534 NEXT; 2535 break; 2536 } 2537 } 2538 return(xmlStrndup(buf, len)); 2539} 2540 2541/** 2542 * docbParseSGMLAttribute: 2543 * @ctxt: an SGML parser context 2544 * @stop: a char stop value 2545 * 2546 * parse an SGML attribute value till the stop (quote), if 2547 * stop is 0 then it stops at the first space 2548 * 2549 * Returns the attribute parsed or NULL 2550 */ 2551 2552static xmlChar * 2553docbParseSGMLAttribute(docbParserCtxtPtr ctxt, const xmlChar stop) { 2554 xmlChar *buffer = NULL; 2555 int buffer_size = 0; 2556 xmlChar *out = NULL; 2557 xmlChar *name = NULL; 2558 2559 xmlChar *cur = NULL; 2560 docbEntityDescPtr ent; 2561 2562 /* 2563 * allocate a translation buffer. 2564 */ 2565 buffer_size = DOCB_PARSER_BIG_BUFFER_SIZE; 2566 buffer = (xmlChar *) xmlMalloc(buffer_size * sizeof(xmlChar)); 2567 if (buffer == NULL) { 2568 perror("docbParseSGMLAttribute: malloc failed"); 2569 return(NULL); 2570 } 2571 out = buffer; 2572 2573 /* 2574 * Ok loop until we reach one of the ending chars 2575 */ 2576 while ((CUR != 0) && (CUR != stop) && (CUR != '>')) { 2577 if ((stop == 0) && (IS_BLANK(CUR))) break; 2578 if (CUR == '&') { 2579 if (NXT(1) == '#') { 2580 unsigned int c; 2581 int bits; 2582 2583 c = docbParseCharRef(ctxt); 2584 if (c < 0x80) 2585 { *out++ = c; bits= -6; } 2586 else if (c < 0x800) 2587 { *out++ =((c >> 6) & 0x1F) | 0xC0; bits= 0; } 2588 else if (c < 0x10000) 2589 { *out++ =((c >> 12) & 0x0F) | 0xE0; bits= 6; } 2590 else 2591 { *out++ =((c >> 18) & 0x07) | 0xF0; bits= 12; } 2592 2593 for ( ; bits >= 0; bits-= 6) { 2594 *out++ = ((c >> bits) & 0x3F) | 0x80; 2595 } 2596 } else { 2597 ent = docbParseEntityRef(ctxt, &name); 2598 if (name == NULL) { 2599 *out++ = '&'; 2600 if (out - buffer > buffer_size - 100) { 2601 int indx = out - buffer; 2602 2603 growBuffer(buffer); 2604 out = &buffer[indx]; 2605 } 2606 } else if (ent == NULL) { 2607 *out++ = '&'; 2608 cur = name; 2609 while (*cur != 0) { 2610 if (out - buffer > buffer_size - 100) { 2611 int indx = out - buffer; 2612 2613 growBuffer(buffer); 2614 out = &buffer[indx]; 2615 } 2616 *out++ = *cur++; 2617 } 2618 xmlFree(name); 2619 } else { 2620 unsigned int c; 2621 int bits; 2622 2623 if (out - buffer > buffer_size - 100) { 2624 int indx = out - buffer; 2625 2626 growBuffer(buffer); 2627 out = &buffer[indx]; 2628 } 2629 c = (xmlChar)ent->value; 2630 if (c < 0x80) 2631 { *out++ = c; bits= -6; } 2632 else if (c < 0x800) 2633 { *out++ =((c >> 6) & 0x1F) | 0xC0; bits= 0; } 2634 else if (c < 0x10000) 2635 { *out++ =((c >> 12) & 0x0F) | 0xE0; bits= 6; } 2636 else 2637 { *out++ =((c >> 18) & 0x07) | 0xF0; bits= 12; } 2638 2639 for ( ; bits >= 0; bits-= 6) { 2640 *out++ = ((c >> bits) & 0x3F) | 0x80; 2641 } 2642 xmlFree(name); 2643 } 2644 } 2645 } else { 2646 unsigned int c; 2647 int bits; 2648 2649 if (out - buffer > buffer_size - 100) { 2650 int indx = out - buffer; 2651 2652 growBuffer(buffer); 2653 out = &buffer[indx]; 2654 } 2655 c = CUR; 2656 if (c < 0x80) 2657 { *out++ = c; bits= -6; } 2658 else if (c < 0x800) 2659 { *out++ =((c >> 6) & 0x1F) | 0xC0; bits= 0; } 2660 else if (c < 0x10000) 2661 { *out++ =((c >> 12) & 0x0F) | 0xE0; bits= 6; } 2662 else 2663 { *out++ =((c >> 18) & 0x07) | 0xF0; bits= 12; } 2664 2665 for ( ; bits >= 0; bits-= 6) { 2666 *out++ = ((c >> bits) & 0x3F) | 0x80; 2667 } 2668 NEXT; 2669 } 2670 } 2671 *out++ = 0; 2672 return(buffer); 2673} 2674 2675 2676/** 2677 * docbParseEntityRef: 2678 * @ctxt: an SGML parser context 2679 * @str: location to store the entity name 2680 * 2681 * parse an SGML ENTITY references 2682 * 2683 * [68] EntityRef ::= '&' Name ';' 2684 * 2685 * Returns the associated docbEntityDescPtr if found, or NULL otherwise, 2686 * if non-NULL *str will have to be freed by the caller. 2687 */ 2688static docbEntityDescPtr 2689docbParseEntityRef(docbParserCtxtPtr ctxt, xmlChar **str) { 2690 xmlChar *name; 2691 docbEntityDescPtr ent = NULL; 2692 *str = NULL; 2693 2694 if (CUR == '&') { 2695 NEXT; 2696 name = docbParseName(ctxt); 2697 if (name == NULL) { 2698 if ((ctxt->sax != NULL) && (ctxt->sax->error != NULL)) 2699 ctxt->sax->error(ctxt->userData, "docbParseEntityRef: no name\n"); 2700 ctxt->wellFormed = 0; 2701 } else { 2702 GROW; 2703 if (CUR == ';') { 2704 *str = name; 2705 2706 /* 2707 * Lookup the entity in the table. 2708 */ 2709 ent = docbEntityLookup(name); 2710 if (ent != NULL) /* OK that's ugly !!! */ 2711 NEXT; 2712 } else { 2713 if ((ctxt->sax != NULL) && (ctxt->sax->error != NULL)) 2714 ctxt->sax->error(ctxt->userData, 2715 "docbParseEntityRef: expecting ';'\n"); 2716 *str = name; 2717 } 2718 } 2719 } 2720 return(ent); 2721} 2722 2723/** 2724 * docbParseAttValue: 2725 * @ctxt: an SGML parser context 2726 * 2727 * parse a value for an attribute 2728 * Note: the parser won't do substitution of entities here, this 2729 * will be handled later in xmlStringGetNodeList, unless it was 2730 * asked for ctxt->replaceEntities != 0 2731 * 2732 * Returns the AttValue parsed or NULL. 2733 */ 2734 2735static xmlChar * 2736docbParseAttValue(docbParserCtxtPtr ctxt) { 2737 xmlChar *ret = NULL; 2738 2739 if (CUR == '"') { 2740 NEXT; 2741 ret = docbParseSGMLAttribute(ctxt, '"'); 2742 if (CUR != '"') { 2743 if ((ctxt->sax != NULL) && (ctxt->sax->error != NULL)) 2744 ctxt->sax->error(ctxt->userData, "AttValue: ' expected\n"); 2745 ctxt->wellFormed = 0; 2746 } else 2747 NEXT; 2748 } else if (CUR == '\'') { 2749 NEXT; 2750 ret = docbParseSGMLAttribute(ctxt, '\''); 2751 if (CUR != '\'') { 2752 if ((ctxt->sax != NULL) && (ctxt->sax->error != NULL)) 2753 ctxt->sax->error(ctxt->userData, "AttValue: ' expected\n"); 2754 ctxt->wellFormed = 0; 2755 } else 2756 NEXT; 2757 } else { 2758 /* 2759 * That's an SGMLism, the attribute value may not be quoted 2760 */ 2761 ret = docbParseSGMLAttribute(ctxt, 0); 2762 if (ret == NULL) { 2763 if ((ctxt->sax != NULL) && (ctxt->sax->error != NULL)) 2764 ctxt->sax->error(ctxt->userData, "AttValue: no value found\n"); 2765 ctxt->wellFormed = 0; 2766 } 2767 } 2768 return(ret); 2769} 2770 2771/** 2772 * docbParseSystemLiteral: 2773 * @ctxt: an SGML parser context 2774 * 2775 * parse an SGML Literal 2776 * 2777 * [11] SystemLiteral ::= ('"' [^"]* '"') | ("'" [^']* "'") 2778 * 2779 * Returns the SystemLiteral parsed or NULL 2780 */ 2781 2782static xmlChar * 2783docbParseSystemLiteral(docbParserCtxtPtr ctxt) { 2784 const xmlChar *q; 2785 xmlChar *ret = NULL; 2786 2787 if (CUR == '"') { 2788 NEXT; 2789 q = CUR_PTR; 2790 while ((IS_CHAR(CUR)) && (CUR != '"')) 2791 NEXT; 2792 if (!IS_CHAR(CUR)) { 2793 if ((ctxt->sax != NULL) && (ctxt->sax->error != NULL)) 2794 ctxt->sax->error(ctxt->userData, "Unfinished SystemLiteral\n"); 2795 ctxt->wellFormed = 0; 2796 } else { 2797 ret = xmlStrndup(q, CUR_PTR - q); 2798 NEXT; 2799 } 2800 } else if (CUR == '\'') { 2801 NEXT; 2802 q = CUR_PTR; 2803 while ((IS_CHAR(CUR)) && (CUR != '\'')) 2804 NEXT; 2805 if (!IS_CHAR(CUR)) { 2806 if ((ctxt->sax != NULL) && (ctxt->sax->error != NULL)) 2807 ctxt->sax->error(ctxt->userData, "Unfinished SystemLiteral\n"); 2808 ctxt->wellFormed = 0; 2809 } else { 2810 ret = xmlStrndup(q, CUR_PTR - q); 2811 NEXT; 2812 } 2813 } else { 2814 if ((ctxt->sax != NULL) && (ctxt->sax->error != NULL)) 2815 ctxt->sax->error(ctxt->userData, 2816 "SystemLiteral \" or ' expected\n"); 2817 ctxt->wellFormed = 0; 2818 } 2819 2820 return(ret); 2821} 2822 2823/** 2824 * docbParsePubidLiteral: 2825 * @ctxt: an SGML parser context 2826 * 2827 * parse an SGML public literal 2828 * 2829 * [12] PubidLiteral ::= '"' PubidChar* '"' | "'" (PubidChar - "'")* "'" 2830 * 2831 * Returns the PubidLiteral parsed or NULL. 2832 */ 2833 2834static xmlChar * 2835docbParsePubidLiteral(docbParserCtxtPtr ctxt) { 2836 const xmlChar *q; 2837 xmlChar *ret = NULL; 2838 /* 2839 * Name ::= (Letter | '_') (NameChar)* 2840 */ 2841 if (CUR == '"') { 2842 NEXT; 2843 q = CUR_PTR; 2844 while (IS_PUBIDCHAR(CUR)) NEXT; 2845 if (CUR != '"') { 2846 if ((ctxt->sax != NULL) && (ctxt->sax->error != NULL)) 2847 ctxt->sax->error(ctxt->userData, "Unfinished PubidLiteral\n"); 2848 ctxt->wellFormed = 0; 2849 } else { 2850 ret = xmlStrndup(q, CUR_PTR - q); 2851 NEXT; 2852 } 2853 } else if (CUR == '\'') { 2854 NEXT; 2855 q = CUR_PTR; 2856 while ((IS_LETTER(CUR)) && (CUR != '\'')) 2857 NEXT; 2858 if (!IS_LETTER(CUR)) { 2859 if ((ctxt->sax != NULL) && (ctxt->sax->error != NULL)) 2860 ctxt->sax->error(ctxt->userData, "Unfinished PubidLiteral\n"); 2861 ctxt->wellFormed = 0; 2862 } else { 2863 ret = xmlStrndup(q, CUR_PTR - q); 2864 NEXT; 2865 } 2866 } else { 2867 if ((ctxt->sax != NULL) && (ctxt->sax->error != NULL)) 2868 ctxt->sax->error(ctxt->userData, "SystemLiteral \" or ' expected\n"); 2869 ctxt->wellFormed = 0; 2870 } 2871 2872 return(ret); 2873} 2874 2875/** 2876 * docbParseCharData: 2877 * @ctxt: an SGML parser context 2878 * @cdata: int indicating whether we are within a CDATA section 2879 * 2880 * parse a CharData section. 2881 * if we are within a CDATA section ']]>' marks an end of section. 2882 * 2883 * [14] CharData ::= [^<&]* - ([^<&]* ']]>' [^<&]*) 2884 */ 2885 2886static void 2887docbParseCharData(docbParserCtxtPtr ctxt) { 2888 xmlChar buf[DOCB_PARSER_BIG_BUFFER_SIZE + 5]; 2889 int nbchar = 0; 2890 int cur, l; 2891 2892 SHRINK; 2893 cur = CUR_CHAR(l); 2894 while (((cur != '<') || (ctxt->token == '<')) && 2895 ((cur != '&') || (ctxt->token == '&')) && 2896 (IS_CHAR(cur))) { 2897 COPY_BUF(l,buf,nbchar,cur); 2898 if (nbchar >= DOCB_PARSER_BIG_BUFFER_SIZE) { 2899 /* 2900 * Ok the segment is to be consumed as chars. 2901 */ 2902 if ((ctxt->sax != NULL) && (!ctxt->disableSAX)) { 2903 if (areBlanks(ctxt, buf, nbchar)) { 2904 if (ctxt->sax->ignorableWhitespace != NULL) 2905 ctxt->sax->ignorableWhitespace(ctxt->userData, 2906 buf, nbchar); 2907 } else { 2908 docbCheckParagraph(ctxt); 2909 if (ctxt->sax->characters != NULL) 2910 ctxt->sax->characters(ctxt->userData, buf, nbchar); 2911 } 2912 } 2913 nbchar = 0; 2914 } 2915 NEXTL(l); 2916 cur = CUR_CHAR(l); 2917 } 2918 if (nbchar != 0) { 2919 /* 2920 * Ok the segment is to be consumed as chars. 2921 */ 2922 if ((ctxt->sax != NULL) && (!ctxt->disableSAX)) { 2923 if (areBlanks(ctxt, buf, nbchar)) { 2924 if (ctxt->sax->ignorableWhitespace != NULL) 2925 ctxt->sax->ignorableWhitespace(ctxt->userData, buf, nbchar); 2926 } else { 2927 docbCheckParagraph(ctxt); 2928 if (ctxt->sax->characters != NULL) 2929 ctxt->sax->characters(ctxt->userData, buf, nbchar); 2930 } 2931 } 2932 } 2933} 2934 2935/** 2936 * docbParseExternalID: 2937 * @ctxt: an SGML parser context 2938 * @publicID: a xmlChar** receiving PubidLiteral 2939 * 2940 * Parse an External ID or a Public ID 2941 * 2942 * Returns the function returns SystemLiteral and in the second 2943 * case publicID receives PubidLiteral, 2944 * it is possible to return NULL and have publicID set. 2945 */ 2946 2947static xmlChar * 2948docbParseExternalID(docbParserCtxtPtr ctxt, xmlChar **publicID) { 2949 xmlChar *URI = NULL; 2950 2951 if ((UPPER == 'S') && (UPP(1) == 'Y') && 2952 (UPP(2) == 'S') && (UPP(3) == 'T') && 2953 (UPP(4) == 'E') && (UPP(5) == 'M')) { 2954 SKIP(6); 2955 if (!IS_BLANK(CUR)) { 2956 if ((ctxt->sax != NULL) && (ctxt->sax->error != NULL)) 2957 ctxt->sax->error(ctxt->userData, 2958 "Space required after 'SYSTEM'\n"); 2959 ctxt->wellFormed = 0; 2960 } 2961 SKIP_BLANKS; 2962 URI = docbParseSystemLiteral(ctxt); 2963 if (URI == NULL) { 2964 if ((ctxt->sax != NULL) && (ctxt->sax->error != NULL)) 2965 ctxt->sax->error(ctxt->userData, 2966 "docbParseExternalID: SYSTEM, no URI\n"); 2967 ctxt->wellFormed = 0; 2968 } 2969 } else if ((UPPER == 'P') && (UPP(1) == 'U') && 2970 (UPP(2) == 'B') && (UPP(3) == 'L') && 2971 (UPP(4) == 'I') && (UPP(5) == 'C')) { 2972 SKIP(6); 2973 if (!IS_BLANK(CUR)) { 2974 if ((ctxt->sax != NULL) && (ctxt->sax->error != NULL)) 2975 ctxt->sax->error(ctxt->userData, 2976 "Space required after 'PUBLIC'\n"); 2977 ctxt->wellFormed = 0; 2978 } 2979 SKIP_BLANKS; 2980 *publicID = docbParsePubidLiteral(ctxt); 2981 if (*publicID == NULL) { 2982 if ((ctxt->sax != NULL) && (ctxt->sax->error != NULL)) 2983 ctxt->sax->error(ctxt->userData, 2984 "docbParseExternalID: PUBLIC, no Public Identifier\n"); 2985 ctxt->wellFormed = 0; 2986 } 2987 SKIP_BLANKS; 2988 if ((CUR == '"') || (CUR == '\'')) { 2989 URI = docbParseSystemLiteral(ctxt); 2990 } 2991 } 2992 return(URI); 2993} 2994 2995/** 2996 * docbParseComment: 2997 * @ctxt: an SGML parser context 2998 * 2999 * Parse an XML (SGML) comment <!-- .... --> 3000 * 3001 * [15] Comment ::= '<!--' ((Char - '-') | ('-' (Char - '-')))* '-->' 3002 */ 3003static void 3004docbParseComment(docbParserCtxtPtr ctxt) { 3005 xmlChar *buf = NULL; 3006 int len; 3007 int size = DOCB_PARSER_BUFFER_SIZE; 3008 int q, ql; 3009 int r, rl; 3010 int cur, l; 3011 xmlParserInputState state; 3012 3013 /* 3014 * Check that there is a comment right here. 3015 */ 3016 if ((RAW != '<') || (NXT(1) != '!') || 3017 (NXT(2) != '-') || (NXT(3) != '-')) return; 3018 3019 state = ctxt->instate; 3020 ctxt->instate = XML_PARSER_COMMENT; 3021 SHRINK; 3022 SKIP(4); 3023 buf = (xmlChar *) xmlMalloc(size * sizeof(xmlChar)); 3024 if (buf == NULL) { 3025 xmlGenericError(xmlGenericErrorContext, 3026 "malloc of %d byte failed\n", size); 3027 ctxt->instate = state; 3028 return; 3029 } 3030 q = CUR_CHAR(ql); 3031 NEXTL(ql); 3032 r = CUR_CHAR(rl); 3033 NEXTL(rl); 3034 cur = CUR_CHAR(l); 3035 len = 0; 3036 while (IS_CHAR(cur) && 3037 ((cur != '>') || 3038 (r != '-') || (q != '-'))) { 3039 if (len + 5 >= size) { 3040 size *= 2; 3041 buf = (xmlChar *) xmlRealloc(buf, size * sizeof(xmlChar)); 3042 if (buf == NULL) { 3043 xmlGenericError(xmlGenericErrorContext, 3044 "realloc of %d byte failed\n", size); 3045 ctxt->instate = state; 3046 return; 3047 } 3048 } 3049 COPY_BUF(ql,buf,len,q); 3050 q = r; 3051 ql = rl; 3052 r = cur; 3053 rl = l; 3054 NEXTL(l); 3055 cur = CUR_CHAR(l); 3056 if (cur == 0) { 3057 SHRINK; 3058 GROW; 3059 cur = CUR_CHAR(l); 3060 } 3061 } 3062 buf[len] = 0; 3063 if (!IS_CHAR(cur)) { 3064 ctxt->errNo = XML_ERR_COMMENT_NOT_FINISHED; 3065 if ((ctxt->sax != NULL) && (ctxt->sax->error != NULL)) 3066 ctxt->sax->error(ctxt->userData, 3067 "Comment not terminated \n<!--%.50s\n", buf); 3068 ctxt->wellFormed = 0; 3069 xmlFree(buf); 3070 } else { 3071 NEXT; 3072 if ((ctxt->sax != NULL) && (ctxt->sax->comment != NULL) && 3073 (!ctxt->disableSAX)) 3074 ctxt->sax->comment(ctxt->userData, buf); 3075 xmlFree(buf); 3076 } 3077 ctxt->instate = state; 3078} 3079 3080/** 3081 * docbParseCharRef: 3082 * @ctxt: an SGML parser context 3083 * 3084 * parse Reference declarations 3085 * 3086 * [66] CharRef ::= '&#' [0-9]+ ';' | 3087 * '&#x' [0-9a-fA-F]+ ';' 3088 * 3089 * Returns the value parsed (as an int) 3090 */ 3091static int 3092docbParseCharRef(docbParserCtxtPtr ctxt) { 3093 int val = 0; 3094 3095 if ((CUR == '&') && (NXT(1) == '#') && 3096 (NXT(2) == 'x')) { 3097 SKIP(3); 3098 while (CUR != ';') { 3099 if ((CUR >= '0') && (CUR <= '9')) 3100 val = val * 16 + (CUR - '0'); 3101 else if ((CUR >= 'a') && (CUR <= 'f')) 3102 val = val * 16 + (CUR - 'a') + 10; 3103 else if ((CUR >= 'A') && (CUR <= 'F')) 3104 val = val * 16 + (CUR - 'A') + 10; 3105 else { 3106 if ((ctxt->sax != NULL) && (ctxt->sax->error != NULL)) 3107 ctxt->sax->error(ctxt->userData, 3108 "docbParseCharRef: invalid hexadecimal value\n"); 3109 ctxt->wellFormed = 0; 3110 val = 0; 3111 break; 3112 } 3113 NEXT; 3114 } 3115 if (CUR == ';') 3116 NEXT; 3117 } else if ((CUR == '&') && (NXT(1) == '#')) { 3118 SKIP(2); 3119 while (CUR != ';') { 3120 if ((CUR >= '0') && (CUR <= '9')) 3121 val = val * 10 + (CUR - '0'); 3122 else { 3123 if ((ctxt->sax != NULL) && (ctxt->sax->error != NULL)) 3124 ctxt->sax->error(ctxt->userData, 3125 "docbParseCharRef: invalid decimal value\n"); 3126 ctxt->wellFormed = 0; 3127 val = 0; 3128 break; 3129 } 3130 NEXT; 3131 } 3132 if (CUR == ';') 3133 NEXT; 3134 } else { 3135 if ((ctxt->sax != NULL) && (ctxt->sax->error != NULL)) 3136 ctxt->sax->error(ctxt->userData, "docbParseCharRef: invalid value\n"); 3137 ctxt->wellFormed = 0; 3138 } 3139 /* 3140 * Check the value IS_CHAR ... 3141 */ 3142 if (IS_CHAR(val)) { 3143 return(val); 3144 } else { 3145 if ((ctxt->sax != NULL) && (ctxt->sax->error != NULL)) 3146 ctxt->sax->error(ctxt->userData, "docbParseCharRef: invalid xmlChar value %d\n", 3147 val); 3148 ctxt->wellFormed = 0; 3149 } 3150 return(0); 3151} 3152 3153 3154/** 3155 * docbParseDocTypeDecl : 3156 * @ctxt: an SGML parser context 3157 * 3158 * parse a DOCTYPE declaration 3159 * 3160 * [28] doctypedecl ::= '<!DOCTYPE' S Name (S ExternalID)? S? 3161 * ('[' (markupdecl | PEReference | S)* ']' S?)? '>' 3162 */ 3163 3164static void 3165docbParseDocTypeDecl(docbParserCtxtPtr ctxt) { 3166 xmlChar *name; 3167 xmlChar *ExternalID = NULL; 3168 xmlChar *URI = NULL; 3169 3170 /* 3171 * We know that '<!DOCTYPE' has been detected. 3172 */ 3173 SKIP(9); 3174 3175 SKIP_BLANKS; 3176 3177 /* 3178 * Parse the DOCTYPE name. 3179 */ 3180 name = docbParseName(ctxt); 3181 if (name == NULL) { 3182 if ((ctxt->sax != NULL) && (ctxt->sax->error != NULL)) 3183 ctxt->sax->error(ctxt->userData, "docbParseDocTypeDecl : no DOCTYPE name !\n"); 3184 ctxt->wellFormed = 0; 3185 } 3186 /* 3187 * Check that upper(name) == "SGML" !!!!!!!!!!!!! 3188 */ 3189 3190 SKIP_BLANKS; 3191 3192 /* 3193 * Check for SystemID and ExternalID 3194 */ 3195 URI = docbParseExternalID(ctxt, &ExternalID); 3196 SKIP_BLANKS; 3197 3198 /* 3199 * Create or update the document accordingly to the DOCTYPE 3200 */ 3201 if ((ctxt->sax != NULL) && (ctxt->sax->internalSubset != NULL) && 3202 (!ctxt->disableSAX)) 3203 ctxt->sax->internalSubset(ctxt->userData, name, ExternalID, URI); 3204 3205 /* 3206 * Is there any internal subset declarations ? 3207 * they are handled separately in docbParseInternalSubset() 3208 */ 3209 if (RAW == '[') 3210 return; 3211 3212 3213 /* 3214 * We should be at the end of the DOCTYPE declaration. 3215 */ 3216 if (CUR != '>') { 3217 if ((ctxt->sax != NULL) && (ctxt->sax->error != NULL)) 3218 ctxt->sax->error(ctxt->userData, "DOCTYPE unproperly terminated\n"); 3219 ctxt->wellFormed = 0; 3220 /* We shouldn't try to resynchronize ... */ 3221 } 3222 NEXT; 3223 3224 /* 3225 * Cleanup, since we don't use all those identifiers 3226 */ 3227 if (URI != NULL) xmlFree(URI); 3228 if (ExternalID != NULL) xmlFree(ExternalID); 3229 if (name != NULL) xmlFree(name); 3230} 3231 3232/** 3233 * docbParseAttribute: 3234 * @ctxt: an SGML parser context 3235 * @value: a xmlChar ** used to store the value of the attribute 3236 * 3237 * parse an attribute 3238 * 3239 * [41] Attribute ::= Name Eq AttValue 3240 * 3241 * [25] Eq ::= S? '=' S? 3242 * 3243 * With namespace: 3244 * 3245 * [NS 11] Attribute ::= QName Eq AttValue 3246 * 3247 * Also the case QName == xmlns:??? is handled independently as a namespace 3248 * definition. 3249 * 3250 * Returns the attribute name, and the value in *value. 3251 */ 3252 3253static xmlChar * 3254docbParseAttribute(docbParserCtxtPtr ctxt, xmlChar **value) { 3255 xmlChar *name, *val = NULL; 3256 3257 *value = NULL; 3258 name = docbParseName(ctxt); 3259 if (name == NULL) { 3260 if ((ctxt->sax != NULL) && (ctxt->sax->error != NULL)) 3261 ctxt->sax->error(ctxt->userData, "error parsing attribute name\n"); 3262 ctxt->wellFormed = 0; 3263 return(NULL); 3264 } 3265 3266 /* 3267 * read the value 3268 */ 3269 SKIP_BLANKS; 3270 if (CUR == '=') { 3271 NEXT; 3272 SKIP_BLANKS; 3273 val = docbParseAttValue(ctxt); 3274 /****** 3275 } else { 3276 * TODO : some attribute must have values, some may not 3277 if ((ctxt->sax != NULL) && (ctxt->sax->error != NULL)) 3278 ctxt->sax->warning(ctxt->userData, 3279 "No value for attribute %s\n", name); */ 3280 } 3281 3282 *value = val; 3283 return(name); 3284} 3285 3286/** 3287 * docbCheckEncoding: 3288 * @ctxt: an SGML parser context 3289 * @attvalue: the attribute value 3290 * 3291 * Checks an http-equiv attribute from a Meta tag to detect 3292 * the encoding 3293 * If a new encoding is detected the parser is switched to decode 3294 * it and pass UTF8 3295 */ 3296static void 3297docbCheckEncoding(docbParserCtxtPtr ctxt, const xmlChar *attvalue) { 3298 const xmlChar *encoding; 3299 3300 if ((ctxt == NULL) || (attvalue == NULL)) 3301 return; 3302 3303 encoding = xmlStrstr(attvalue, BAD_CAST"charset="); 3304 if (encoding == NULL) 3305 encoding = xmlStrstr(attvalue, BAD_CAST"Charset="); 3306 if (encoding == NULL) 3307 encoding = xmlStrstr(attvalue, BAD_CAST"CHARSET="); 3308 if (encoding != NULL) { 3309 encoding += 8; 3310 } else { 3311 encoding = xmlStrstr(attvalue, BAD_CAST"charset ="); 3312 if (encoding == NULL) 3313 encoding = xmlStrstr(attvalue, BAD_CAST"Charset ="); 3314 if (encoding == NULL) 3315 encoding = xmlStrstr(attvalue, BAD_CAST"CHARSET ="); 3316 if (encoding != NULL) 3317 encoding += 9; 3318 } 3319 /* 3320 * Restricted from 2.3.5 */ 3321 if (encoding != NULL) { 3322 xmlCharEncoding enc; 3323 3324 if (ctxt->input->encoding != NULL) 3325 xmlFree((xmlChar *) ctxt->input->encoding); 3326 ctxt->input->encoding = encoding; 3327 3328 enc = xmlParseCharEncoding((const char *) encoding); 3329 if (enc == XML_CHAR_ENCODING_8859_1) { 3330 ctxt->charset = XML_CHAR_ENCODING_8859_1; 3331 } else if (enc != XML_CHAR_ENCODING_UTF8) { 3332 if ((ctxt->sax != NULL) && (ctxt->sax->error != NULL)) 3333 ctxt->sax->error(ctxt->userData, 3334 "Unsupported encoding %s\n", encoding); 3335 /* xmlFree(encoding); */ 3336 ctxt->wellFormed = 0; 3337 ctxt->disableSAX = 1; 3338 ctxt->errNo = XML_ERR_UNSUPPORTED_ENCODING; 3339 } 3340 } 3341} 3342 3343/** 3344 * docbCheckMeta: 3345 * @ctxt: an SGML parser context 3346 * @atts: the attributes values 3347 * 3348 * Checks an attributes from a Meta tag 3349 */ 3350static void 3351docbCheckMeta(docbParserCtxtPtr ctxt, const xmlChar **atts) { 3352 int i; 3353 const xmlChar *att, *value; 3354 int http = 0; 3355 const xmlChar *content = NULL; 3356 3357 if ((ctxt == NULL) || (atts == NULL)) 3358 return; 3359 3360 i = 0; 3361 att = atts[i++]; 3362 while (att != NULL) { 3363 value = atts[i++]; 3364 if ((value != NULL) && 3365 ((xmlStrEqual(att, BAD_CAST"http-equiv")) || 3366 (xmlStrEqual(att, BAD_CAST"Http-Equiv")) || 3367 (xmlStrEqual(att, BAD_CAST"HTTP-EQUIV"))) && 3368 ((xmlStrEqual(value, BAD_CAST"Content-Type")) || 3369 (xmlStrEqual(value, BAD_CAST"content-type")) || 3370 (xmlStrEqual(value, BAD_CAST"CONTENT-TYPE")))) 3371 http = 1; 3372 else if ((value != NULL) && 3373 ((xmlStrEqual(att, BAD_CAST"content")) || 3374 (xmlStrEqual(att, BAD_CAST"Content")) || 3375 (xmlStrEqual(att, BAD_CAST"CONTENT")))) 3376 content = value; 3377 att = atts[i++]; 3378 } 3379 if ((http) && (content != NULL)) 3380 docbCheckEncoding(ctxt, content); 3381 3382} 3383 3384/** 3385 * docbParseStartTag: 3386 * @ctxt: an SGML parser context 3387 * 3388 * parse a start of tag either for rule element or 3389 * EmptyElement. In both case we don't parse the tag closing chars. 3390 * 3391 * [40] STag ::= '<' Name (S Attribute)* S? '>' 3392 * 3393 * [44] EmptyElemTag ::= '<' Name (S Attribute)* S? '/>' 3394 * 3395 * With namespace: 3396 * 3397 * [NS 8] STag ::= '<' QName (S Attribute)* S? '>' 3398 * 3399 * [NS 10] EmptyElement ::= '<' QName (S Attribute)* S? '/>' 3400 * 3401 */ 3402 3403static void 3404docbParseStartTag(docbParserCtxtPtr ctxt) { 3405 xmlChar *name; 3406 xmlChar *attname; 3407 xmlChar *attvalue; 3408 const xmlChar **atts = NULL; 3409 int nbatts = 0; 3410 int maxatts = 0; 3411 int meta = 0; 3412 int i; 3413 3414 if (CUR != '<') return; 3415 NEXT; 3416 3417 GROW; 3418 name = docbParseSGMLName(ctxt); 3419 if (name == NULL) { 3420 if ((ctxt->sax != NULL) && (ctxt->sax->error != NULL)) 3421 ctxt->sax->error(ctxt->userData, 3422 "docbParseStartTag: invalid element name\n"); 3423 ctxt->wellFormed = 0; 3424 return; 3425 } 3426 if (xmlStrEqual(name, BAD_CAST"meta")) 3427 meta = 1; 3428 3429 /* 3430 * Check for auto-closure of SGML elements. 3431 */ 3432 docbAutoClose(ctxt, name); 3433 3434 /* 3435 * Now parse the attributes, it ends up with the ending 3436 * 3437 * (S Attribute)* S? 3438 */ 3439 SKIP_BLANKS; 3440 while ((IS_CHAR(CUR)) && 3441 (CUR != '>') && 3442 ((CUR != '/') || (NXT(1) != '>'))) { 3443 long cons = ctxt->nbChars; 3444 3445 GROW; 3446 attname = docbParseAttribute(ctxt, &attvalue); 3447 if (attname != NULL) { 3448 3449 /* 3450 * Well formedness requires at most one declaration of an attribute 3451 */ 3452 for (i = 0; i < nbatts;i += 2) { 3453 if (xmlStrEqual(atts[i], attname)) { 3454 if ((ctxt->sax != NULL) && (ctxt->sax->error != NULL)) 3455 ctxt->sax->error(ctxt->userData, 3456 "Attribute %s redefined\n", 3457 attname); 3458 ctxt->wellFormed = 0; 3459 xmlFree(attname); 3460 if (attvalue != NULL) 3461 xmlFree(attvalue); 3462 goto failed; 3463 } 3464 } 3465 3466 /* 3467 * Add the pair to atts 3468 */ 3469 if (atts == NULL) { 3470 maxatts = 10; 3471 atts = (const xmlChar **) xmlMalloc(maxatts * sizeof(xmlChar *)); 3472 if (atts == NULL) { 3473 xmlGenericError(xmlGenericErrorContext, 3474 "malloc of %ld byte failed\n", 3475 maxatts * (long)sizeof(xmlChar *)); 3476 if (name != NULL) xmlFree(name); 3477 return; 3478 } 3479 } else if (nbatts + 4 > maxatts) { 3480 maxatts *= 2; 3481 atts = (const xmlChar **) xmlRealloc(atts, maxatts * sizeof(xmlChar *)); 3482 if (atts == NULL) { 3483 xmlGenericError(xmlGenericErrorContext, 3484 "realloc of %ld byte failed\n", 3485 maxatts * (long)sizeof(xmlChar *)); 3486 if (name != NULL) xmlFree(name); 3487 return; 3488 } 3489 } 3490 atts[nbatts++] = attname; 3491 atts[nbatts++] = attvalue; 3492 atts[nbatts] = NULL; 3493 atts[nbatts + 1] = NULL; 3494 } 3495 3496failed: 3497 SKIP_BLANKS; 3498 if (cons == ctxt->nbChars) { 3499 if ((ctxt->sax != NULL) && (ctxt->sax->error != NULL)) 3500 ctxt->sax->error(ctxt->userData, 3501 "docbParseStartTag: problem parsing attributes\n"); 3502 ctxt->wellFormed = 0; 3503 break; 3504 } 3505 } 3506 3507 /* 3508 * Handle specific association to the META tag 3509 */ 3510 if (meta) 3511 docbCheckMeta(ctxt, atts); 3512 3513 /* 3514 * SAX: Start of Element ! 3515 */ 3516 docbnamePush(ctxt, xmlStrdup(name)); 3517#ifdef DEBUG 3518 xmlGenericError(xmlGenericErrorContext,"Start of element %s: pushed %s\n", name, ctxt->name); 3519#endif 3520 if ((ctxt->sax != NULL) && (ctxt->sax->startElement != NULL)) 3521 ctxt->sax->startElement(ctxt->userData, name, atts); 3522 3523 if (atts != NULL) { 3524 for (i = 0;i < nbatts;i++) { 3525 if (atts[i] != NULL) 3526 xmlFree((xmlChar *) atts[i]); 3527 } 3528 xmlFree((void *) atts); 3529 } 3530 if (name != NULL) xmlFree(name); 3531} 3532 3533/** 3534 * docbParseEndTag: 3535 * @ctxt: an SGML parser context 3536 * 3537 * parse an end of tag 3538 * 3539 * [42] ETag ::= '</' Name S? '>' 3540 * 3541 * With namespace 3542 * 3543 * [NS 9] ETag ::= '</' QName S? '>' 3544 */ 3545 3546static void 3547docbParseEndTag(docbParserCtxtPtr ctxt) { 3548 xmlChar *name; 3549 xmlChar *oldname; 3550 int i; 3551 3552 if ((CUR != '<') || (NXT(1) != '/')) { 3553 if ((ctxt->sax != NULL) && (ctxt->sax->error != NULL)) 3554 ctxt->sax->error(ctxt->userData, "docbParseEndTag: '</' not found\n"); 3555 ctxt->wellFormed = 0; 3556 return; 3557 } 3558 SKIP(2); 3559 3560 name = docbParseSGMLName(ctxt); 3561 if (name == NULL) { 3562 if (CUR == '>') { 3563 NEXT; 3564 oldname = docbnamePop(ctxt); 3565 if (oldname != NULL) { 3566 if ((ctxt->sax != NULL) && (ctxt->sax->endElement != NULL)) 3567 ctxt->sax->endElement(ctxt->userData, name); 3568#ifdef DEBUG 3569 xmlGenericError(xmlGenericErrorContext,"End of tag </>: popping out %s\n", oldname); 3570#endif 3571 xmlFree(oldname); 3572#ifdef DEBUG 3573 } else { 3574 xmlGenericError(xmlGenericErrorContext,"End of tag </>: stack empty !!!\n"); 3575#endif 3576 } 3577 return; 3578 } else 3579 return; 3580 } 3581 3582 /* 3583 * We should definitely be at the ending "S? '>'" part 3584 */ 3585 SKIP_BLANKS; 3586 if ((!IS_CHAR(CUR)) || (CUR != '>')) { 3587 if ((ctxt->sax != NULL) && (ctxt->sax->error != NULL)) 3588 ctxt->sax->error(ctxt->userData, "End tag : expected '>'\n"); 3589 ctxt->wellFormed = 0; 3590 } else 3591 NEXT; 3592 3593 /* 3594 * If the name read is not one of the element in the parsing stack 3595 * then return, it's just an error. 3596 */ 3597 for (i = (ctxt->nameNr - 1);i >= 0;i--) { 3598 if (xmlStrEqual(name, ctxt->nameTab[i])) break; 3599 } 3600 if (i < 0) { 3601 if ((ctxt->sax != NULL) && (ctxt->sax->error != NULL)) 3602 ctxt->sax->error(ctxt->userData, 3603 "Unexpected end tag : %s\n", name); 3604 xmlFree(name); 3605 ctxt->wellFormed = 0; 3606 return; 3607 } 3608 3609 3610 /* 3611 * Check for auto-closure of SGML elements. 3612 */ 3613 3614 docbAutoCloseOnClose(ctxt, name); 3615 3616 /* 3617 * Well formedness constraints, opening and closing must match. 3618 * With the exception that the autoclose may have popped stuff out 3619 * of the stack. 3620 */ 3621 if (((name[0] != '/') || (name[1] != 0)) && 3622 (!xmlStrEqual(name, ctxt->name))) { 3623#ifdef DEBUG 3624 xmlGenericError(xmlGenericErrorContext,"End of tag %s: expecting %s\n", name, ctxt->name); 3625#endif 3626 if ((ctxt->name != NULL) && 3627 (!xmlStrEqual(ctxt->name, name))) { 3628 if ((ctxt->sax != NULL) && (ctxt->sax->error != NULL)) 3629 ctxt->sax->error(ctxt->userData, 3630 "Opening and ending tag mismatch: %s and %s\n", 3631 name, ctxt->name); 3632 ctxt->wellFormed = 0; 3633 } 3634 } 3635 3636 /* 3637 * SAX: End of Tag 3638 */ 3639 oldname = ctxt->name; 3640 if (((name[0] == '/') && (name[1] == 0)) || 3641 ((oldname != NULL) && (xmlStrEqual(oldname, name)))) { 3642 if ((ctxt->sax != NULL) && (ctxt->sax->endElement != NULL)) 3643 ctxt->sax->endElement(ctxt->userData, name); 3644 oldname = docbnamePop(ctxt); 3645 if (oldname != NULL) { 3646#ifdef DEBUG 3647 xmlGenericError(xmlGenericErrorContext,"End of tag %s: popping out %s\n", name, oldname); 3648#endif 3649 xmlFree(oldname); 3650#ifdef DEBUG 3651 } else { 3652 xmlGenericError(xmlGenericErrorContext,"End of tag %s: stack empty !!!\n", name); 3653#endif 3654 } 3655 } 3656 3657 if (name != NULL) 3658 xmlFree(name); 3659 3660 return; 3661} 3662 3663 3664/** 3665 * docbParseReference: 3666 * @ctxt: an SGML parser context 3667 * 3668 * parse and handle entity references in content, 3669 * this will end-up in a call to character() since this is either a 3670 * CharRef, or a predefined entity. 3671 */ 3672static void 3673docbParseReference(docbParserCtxtPtr ctxt) { 3674 docbEntityDescPtr ent; 3675 xmlChar out[6]; 3676 xmlChar *name; 3677 if (CUR != '&') return; 3678 3679 if (NXT(1) == '#') { 3680 unsigned int c; 3681 int bits, i = 0; 3682 3683 c = docbParseCharRef(ctxt); 3684 if (c < 0x80) { out[i++]= c; bits= -6; } 3685 else if (c < 0x800) { out[i++]=((c >> 6) & 0x1F) | 0xC0; bits= 0; } 3686 else if (c < 0x10000) { out[i++]=((c >> 12) & 0x0F) | 0xE0; bits= 6; } 3687 else { out[i++]=((c >> 18) & 0x07) | 0xF0; bits= 12; } 3688 3689 for ( ; bits >= 0; bits-= 6) { 3690 out[i++]= ((c >> bits) & 0x3F) | 0x80; 3691 } 3692 out[i] = 0; 3693 3694 docbCheckParagraph(ctxt); 3695 if ((ctxt->sax != NULL) && (ctxt->sax->characters != NULL)) 3696 ctxt->sax->characters(ctxt->userData, out, i); 3697 } else { 3698 ent = docbParseEntityRef(ctxt, &name); 3699 if (name == NULL) { 3700 docbCheckParagraph(ctxt); 3701 if ((ctxt->sax != NULL) && (ctxt->sax->characters != NULL)) 3702 ctxt->sax->characters(ctxt->userData, BAD_CAST "&", 1); 3703 return; 3704 } 3705 if ((ent == NULL) || (ent->value <= 0)) { 3706 docbCheckParagraph(ctxt); 3707 if ((ctxt->sax != NULL) && (ctxt->sax->characters != NULL)) { 3708 ctxt->sax->characters(ctxt->userData, BAD_CAST "&", 1); 3709 ctxt->sax->characters(ctxt->userData, name, xmlStrlen(name)); 3710 /* ctxt->sax->characters(ctxt->userData, BAD_CAST ";", 1); */ 3711 } 3712 } else { 3713 unsigned int c; 3714 int bits, i = 0; 3715 3716 c = ent->value; 3717 if (c < 0x80) 3718 { out[i++]= c; bits= -6; } 3719 else if (c < 0x800) 3720 { out[i++]=((c >> 6) & 0x1F) | 0xC0; bits= 0; } 3721 else if (c < 0x10000) 3722 { out[i++]=((c >> 12) & 0x0F) | 0xE0; bits= 6; } 3723 else 3724 { out[i++]=((c >> 18) & 0x07) | 0xF0; bits= 12; } 3725 3726 for ( ; bits >= 0; bits-= 6) { 3727 out[i++]= ((c >> bits) & 0x3F) | 0x80; 3728 } 3729 out[i] = 0; 3730 3731 docbCheckParagraph(ctxt); 3732 if ((ctxt->sax != NULL) && (ctxt->sax->characters != NULL)) 3733 ctxt->sax->characters(ctxt->userData, out, i); 3734 } 3735 xmlFree(name); 3736 } 3737} 3738 3739/** 3740 * docbParseContent: 3741 * @ctxt: an SGML parser context 3742 * @name: the node name 3743 * 3744 * Parse a content: comment, sub-element, reference or text. 3745 * 3746 */ 3747 3748static void 3749docbParseContent(docbParserCtxtPtr ctxt) { 3750 xmlChar *currentNode; 3751 int depth; 3752 3753 currentNode = xmlStrdup(ctxt->name); 3754 depth = ctxt->nameNr; 3755 while (1) { 3756 long cons = ctxt->nbChars; 3757 3758 GROW; 3759 /* 3760 * Our tag or one of it's parent or children is ending. 3761 */ 3762 if ((CUR == '<') && (NXT(1) == '/')) { 3763 docbParseEndTag(ctxt); 3764 if (currentNode != NULL) xmlFree(currentNode); 3765 return; 3766 } 3767 3768 /* 3769 * Has this node been popped out during parsing of 3770 * the next element 3771 */ 3772 if ((!xmlStrEqual(currentNode, ctxt->name)) && 3773 (depth >= ctxt->nameNr)) { 3774 if (currentNode != NULL) xmlFree(currentNode); 3775 return; 3776 } 3777 3778 /* 3779 * Sometimes DOCTYPE arrives in the middle of the document 3780 */ 3781 if ((CUR == '<') && (NXT(1) == '!') && 3782 (UPP(2) == 'D') && (UPP(3) == 'O') && 3783 (UPP(4) == 'C') && (UPP(5) == 'T') && 3784 (UPP(6) == 'Y') && (UPP(7) == 'P') && 3785 (UPP(8) == 'E')) { 3786 if ((ctxt->sax != NULL) && (ctxt->sax->error != NULL)) 3787 ctxt->sax->error(ctxt->userData, 3788 "Misplaced DOCTYPE declaration\n"); 3789 ctxt->wellFormed = 0; 3790 docbParseDocTypeDecl(ctxt); 3791 } 3792 3793 /* 3794 * First case : a comment 3795 */ 3796 if ((CUR == '<') && (NXT(1) == '!') && 3797 (NXT(2) == '-') && (NXT(3) == '-')) { 3798 docbParseComment(ctxt); 3799 } 3800 3801 /* 3802 * Second case : a sub-element. 3803 */ 3804 else if (CUR == '<') { 3805 docbParseElement(ctxt); 3806 } 3807 3808 /* 3809 * Third case : a reference. If if has not been resolved, 3810 * parsing returns it's Name, create the node 3811 */ 3812 else if (CUR == '&') { 3813 docbParseReference(ctxt); 3814 } 3815 3816 /* 3817 * Fourth : end of the resource 3818 */ 3819 else if (CUR == 0) { 3820 docbAutoClose(ctxt, NULL); 3821 } 3822 3823 /* 3824 * Last case, text. Note that References are handled directly. 3825 */ 3826 else { 3827 docbParseCharData(ctxt); 3828 } 3829 3830 if (cons == ctxt->nbChars) { 3831 if (ctxt->node != NULL) { 3832 if ((ctxt->sax != NULL) && (ctxt->sax->error != NULL)) 3833 ctxt->sax->error(ctxt->userData, 3834 "detected an error in element content\n"); 3835 ctxt->wellFormed = 0; 3836 } 3837 break; 3838 } 3839 3840 GROW; 3841 } 3842 if (currentNode != NULL) xmlFree(currentNode); 3843} 3844 3845/** 3846 * docbParseElement: 3847 * @ctxt: an SGML parser context 3848 * 3849 * parse an SGML element, this is highly recursive 3850 * 3851 * [39] element ::= EmptyElemTag | STag content ETag 3852 * 3853 * [41] Attribute ::= Name Eq AttValue 3854 */ 3855 3856static void 3857docbParseElement(docbParserCtxtPtr ctxt) { 3858 xmlChar *name; 3859 xmlChar *currentNode = NULL; 3860 docbElemDescPtr info; 3861 docbParserNodeInfo node_info; 3862 xmlChar *oldname; 3863 int depth = ctxt->nameNr; 3864 3865 /* Capture start position */ 3866 if (ctxt->record_info) { 3867 node_info.begin_pos = ctxt->input->consumed + 3868 (CUR_PTR - ctxt->input->base); 3869 node_info.begin_line = ctxt->input->line; 3870 } 3871 3872 oldname = xmlStrdup(ctxt->name); 3873 docbParseStartTag(ctxt); 3874 name = ctxt->name; 3875#ifdef DEBUG 3876 if (oldname == NULL) 3877 xmlGenericError(xmlGenericErrorContext, 3878 "Start of element %s\n", name); 3879 else if (name == NULL) 3880 xmlGenericError(xmlGenericErrorContext, 3881 "Start of element failed, was %s\n", oldname); 3882 else 3883 xmlGenericError(xmlGenericErrorContext, 3884 "Start of element %s, was %s\n", name, oldname); 3885#endif 3886 if (((depth == ctxt->nameNr) && (xmlStrEqual(oldname, ctxt->name))) || 3887 (name == NULL)) { 3888 if (CUR == '>') 3889 NEXT; 3890 if (oldname != NULL) 3891 xmlFree(oldname); 3892 return; 3893 } 3894 if (oldname != NULL) 3895 xmlFree(oldname); 3896 3897 /* 3898 * Lookup the info for that element. 3899 */ 3900 info = docbTagLookup(name); 3901 if (info == NULL) { 3902 if ((ctxt->sax != NULL) && (ctxt->sax->error != NULL)) 3903 ctxt->sax->error(ctxt->userData, "Tag %s unknown\n", 3904 name); 3905 ctxt->wellFormed = 0; 3906 } else if (info->depr) { 3907/*************************** 3908 if ((ctxt->sax != NULL) && (ctxt->sax->warning != NULL)) 3909 ctxt->sax->warning(ctxt->userData, "Tag %s is deprecated\n", 3910 name); 3911 ***************************/ 3912 } 3913 3914 /* 3915 * Check for an Empty Element labelled the XML/SGML way 3916 */ 3917 if ((CUR == '/') && (NXT(1) == '>')) { 3918 SKIP(2); 3919 if ((ctxt->sax != NULL) && (ctxt->sax->endElement != NULL)) 3920 ctxt->sax->endElement(ctxt->userData, name); 3921 oldname = docbnamePop(ctxt); 3922#ifdef DEBUG 3923 xmlGenericError(xmlGenericErrorContext,"End of tag the XML way: popping out %s\n", oldname); 3924#endif 3925 if (oldname != NULL) 3926 xmlFree(oldname); 3927 return; 3928 } 3929 3930 if (CUR == '>') { 3931 NEXT; 3932 } else { 3933 if ((ctxt->sax != NULL) && (ctxt->sax->error != NULL)) 3934 ctxt->sax->error(ctxt->userData, 3935 "Couldn't find end of Start Tag %s\n", 3936 name); 3937 ctxt->wellFormed = 0; 3938 3939 /* 3940 * end of parsing of this node. 3941 */ 3942 if (xmlStrEqual(name, ctxt->name)) { 3943 nodePop(ctxt); 3944 oldname = docbnamePop(ctxt); 3945#ifdef DEBUG 3946 xmlGenericError(xmlGenericErrorContext,"End of start tag problem: popping out %s\n", oldname); 3947#endif 3948 if (oldname != NULL) 3949 xmlFree(oldname); 3950 } 3951 3952 /* 3953 * Capture end position and add node 3954 */ 3955 if ( currentNode != NULL && ctxt->record_info ) { 3956 node_info.end_pos = ctxt->input->consumed + 3957 (CUR_PTR - ctxt->input->base); 3958 node_info.end_line = ctxt->input->line; 3959 node_info.node = ctxt->node; 3960 xmlParserAddNodeInfo(ctxt, &node_info); 3961 } 3962 return; 3963 } 3964 3965 /* 3966 * Check for an Empty Element from DTD definition 3967 */ 3968 if ((info != NULL) && (info->empty)) { 3969 if ((ctxt->sax != NULL) && (ctxt->sax->endElement != NULL)) 3970 ctxt->sax->endElement(ctxt->userData, name); 3971 oldname = docbnamePop(ctxt); 3972#ifdef DEBUG 3973 xmlGenericError(xmlGenericErrorContext,"End of empty tag %s : popping out %s\n", name, oldname); 3974#endif 3975 if (oldname != NULL) 3976 xmlFree(oldname); 3977 return; 3978 } 3979 3980 /* 3981 * Parse the content of the element: 3982 */ 3983 currentNode = xmlStrdup(ctxt->name); 3984 depth = ctxt->nameNr; 3985 while (IS_CHAR(CUR)) { 3986 docbParseContent(ctxt); 3987 if (ctxt->nameNr < depth) break; 3988 } 3989 3990 if (!IS_CHAR(CUR)) { 3991 /************ 3992 if ((ctxt->sax != NULL) && (ctxt->sax->error != NULL)) 3993 ctxt->sax->error(ctxt->userData, 3994 "Premature end of data in tag %s\n", currentNode); 3995 ctxt->wellFormed = 0; 3996 *************/ 3997 3998 /* 3999 * end of parsing of this node. 4000 */ 4001 nodePop(ctxt); 4002 oldname = docbnamePop(ctxt); 4003#ifdef DEBUG 4004 xmlGenericError(xmlGenericErrorContext,"Premature end of tag %s : popping out %s\n", name, oldname); 4005#endif 4006 if (oldname != NULL) 4007 xmlFree(oldname); 4008 if (currentNode != NULL) 4009 xmlFree(currentNode); 4010 return; 4011 } 4012 4013 /* 4014 * Capture end position and add node 4015 */ 4016 if ( currentNode != NULL && ctxt->record_info ) { 4017 node_info.end_pos = ctxt->input->consumed + 4018 (CUR_PTR - ctxt->input->base); 4019 node_info.end_line = ctxt->input->line; 4020 node_info.node = ctxt->node; 4021 xmlParserAddNodeInfo(ctxt, &node_info); 4022 } 4023 if (currentNode != NULL) 4024 xmlFree(currentNode); 4025} 4026 4027/** 4028 * docbParseEntityDecl: 4029 * @ctxt: an SGML parser context 4030 * 4031 * parse <!ENTITY declarations 4032 * 4033 */ 4034 4035static void 4036docbParseEntityDecl(xmlParserCtxtPtr ctxt) { 4037 xmlChar *name = NULL; 4038 xmlChar *value = NULL; 4039 xmlChar *URI = NULL, *literal = NULL; 4040 xmlChar *ndata = NULL; 4041 int isParameter = 0; 4042 xmlChar *orig = NULL; 4043 4044 GROW; 4045 if ((RAW == '<') && (NXT(1) == '!') && 4046 (NXT(2) == 'E') && (NXT(3) == 'N') && 4047 (NXT(4) == 'T') && (NXT(5) == 'I') && 4048 (NXT(6) == 'T') && (NXT(7) == 'Y')) { 4049 xmlParserInputPtr input = ctxt->input; 4050 ctxt->instate = XML_PARSER_ENTITY_DECL; 4051 SHRINK; 4052 SKIP(8); 4053 if (!IS_BLANK(CUR)) { 4054 ctxt->errNo = XML_ERR_SPACE_REQUIRED; 4055 if ((ctxt->sax != NULL) && (ctxt->sax->error != NULL)) 4056 ctxt->sax->error(ctxt->userData, 4057 "Space required after '<!ENTITY'\n"); 4058 ctxt->wellFormed = 0; 4059 ctxt->disableSAX = 1; 4060 } 4061 SKIP_BLANKS; 4062 4063 if (RAW == '%') { 4064 NEXT; 4065 if (!IS_BLANK(CUR)) { 4066 ctxt->errNo = XML_ERR_SPACE_REQUIRED; 4067 if ((ctxt->sax != NULL) && (ctxt->sax->error != NULL)) 4068 ctxt->sax->error(ctxt->userData, 4069 "Space required after '%'\n"); 4070 ctxt->wellFormed = 0; 4071 ctxt->disableSAX = 1; 4072 } 4073 SKIP_BLANKS; 4074 isParameter = 1; 4075 } 4076 4077 name = xmlParseName(ctxt); 4078 if (name == NULL) { 4079 ctxt->errNo = XML_ERR_NAME_REQUIRED; 4080 if ((ctxt->sax != NULL) && (ctxt->sax->error != NULL)) 4081 ctxt->sax->error(ctxt->userData, "sgmlarseEntityDecl: no name\n"); 4082 ctxt->wellFormed = 0; 4083 ctxt->disableSAX = 1; 4084 return; 4085 } 4086 if (!IS_BLANK(CUR)) { 4087 ctxt->errNo = XML_ERR_SPACE_REQUIRED; 4088 if ((ctxt->sax != NULL) && (ctxt->sax->error != NULL)) 4089 ctxt->sax->error(ctxt->userData, 4090 "Space required after the entity name\n"); 4091 ctxt->wellFormed = 0; 4092 ctxt->disableSAX = 1; 4093 } 4094 SKIP_BLANKS; 4095 4096 /* 4097 * handle the various case of definitions... 4098 */ 4099 if (isParameter) { 4100 if ((RAW == '"') || (RAW == '\'')) { 4101 value = xmlParseEntityValue(ctxt, &orig); 4102 if (value) { 4103 if ((ctxt->sax != NULL) && 4104 (!ctxt->disableSAX) && (ctxt->sax->entityDecl != NULL)) 4105 ctxt->sax->entityDecl(ctxt->userData, name, 4106 XML_INTERNAL_PARAMETER_ENTITY, 4107 NULL, NULL, value); 4108 } 4109 } else { 4110 URI = xmlParseExternalID(ctxt, &literal, 1); 4111 if ((URI == NULL) && (literal == NULL)) { 4112 ctxt->errNo = XML_ERR_VALUE_REQUIRED; 4113 if ((ctxt->sax != NULL) && (ctxt->sax->error != NULL)) 4114 ctxt->sax->error(ctxt->userData, 4115 "Entity value required\n"); 4116 ctxt->wellFormed = 0; 4117 ctxt->disableSAX = 1; 4118 } 4119 if (URI) { 4120 xmlURIPtr uri; 4121 4122 uri = xmlParseURI((const char *) URI); 4123 if (uri == NULL) { 4124 ctxt->errNo = XML_ERR_INVALID_URI; 4125 if ((ctxt->sax != NULL) && 4126 (!ctxt->disableSAX) && 4127 (ctxt->sax->error != NULL)) 4128 ctxt->sax->error(ctxt->userData, 4129 "Invalid URI: %s\n", URI); 4130 ctxt->wellFormed = 0; 4131 } else { 4132 if (uri->fragment != NULL) { 4133 ctxt->errNo = XML_ERR_URI_FRAGMENT; 4134 if ((ctxt->sax != NULL) && 4135 (!ctxt->disableSAX) && 4136 (ctxt->sax->error != NULL)) 4137 ctxt->sax->error(ctxt->userData, 4138 "Fragment not allowed: %s\n", URI); 4139 ctxt->wellFormed = 0; 4140 } else { 4141 if ((ctxt->sax != NULL) && 4142 (!ctxt->disableSAX) && 4143 (ctxt->sax->entityDecl != NULL)) 4144 ctxt->sax->entityDecl(ctxt->userData, name, 4145 XML_EXTERNAL_PARAMETER_ENTITY, 4146 literal, URI, NULL); 4147 } 4148 xmlFreeURI(uri); 4149 } 4150 } 4151 } 4152 } else { 4153 if ((RAW == '"') || (RAW == '\'')) { 4154 value = xmlParseEntityValue(ctxt, &orig); 4155 if ((ctxt->sax != NULL) && 4156 (!ctxt->disableSAX) && (ctxt->sax->entityDecl != NULL)) 4157 ctxt->sax->entityDecl(ctxt->userData, name, 4158 XML_INTERNAL_GENERAL_ENTITY, 4159 NULL, NULL, value); 4160 } else { 4161 URI = xmlParseExternalID(ctxt, &literal, 1); 4162 if ((URI == NULL) && (literal == NULL)) { 4163 ctxt->errNo = XML_ERR_VALUE_REQUIRED; 4164 if ((ctxt->sax != NULL) && (ctxt->sax->error != NULL)) 4165 ctxt->sax->error(ctxt->userData, 4166 "Entity value required\n"); 4167 ctxt->wellFormed = 0; 4168 ctxt->disableSAX = 1; 4169 } 4170 if (URI) { 4171 xmlURIPtr uri; 4172 4173 uri = xmlParseURI((const char *)URI); 4174 if (uri == NULL) { 4175 ctxt->errNo = XML_ERR_INVALID_URI; 4176 if ((ctxt->sax != NULL) && 4177 (!ctxt->disableSAX) && 4178 (ctxt->sax->error != NULL)) 4179 ctxt->sax->error(ctxt->userData, 4180 "Invalid URI: %s\n", URI); 4181 ctxt->wellFormed = 0; 4182 } else { 4183 if (uri->fragment != NULL) { 4184 ctxt->errNo = XML_ERR_URI_FRAGMENT; 4185 if ((ctxt->sax != NULL) && 4186 (!ctxt->disableSAX) && 4187 (ctxt->sax->error != NULL)) 4188 ctxt->sax->error(ctxt->userData, 4189 "Fragment not allowed: %s\n", URI); 4190 ctxt->wellFormed = 0; 4191 } 4192 xmlFreeURI(uri); 4193 } 4194 } 4195 if ((RAW != '>') && (!IS_BLANK(CUR))) { 4196 ctxt->errNo = XML_ERR_SPACE_REQUIRED; 4197 if ((ctxt->sax != NULL) && (ctxt->sax->error != NULL)) 4198 ctxt->sax->error(ctxt->userData, 4199 "Space required before content model\n"); 4200 ctxt->wellFormed = 0; 4201 ctxt->disableSAX = 1; 4202 } 4203 SKIP_BLANKS; 4204 4205 /* 4206 * SGML specific: here we can get the content model 4207 */ 4208 if (RAW != '>') { 4209 xmlChar *contmod; 4210 4211 contmod = xmlParseName(ctxt); 4212 4213 if (contmod == NULL) { 4214 ctxt->errNo = XML_ERR_SPACE_REQUIRED; 4215 if ((ctxt->sax != NULL) && (ctxt->sax->error != NULL)) 4216 ctxt->sax->error(ctxt->userData, 4217 "Could not parse entity content model\n"); 4218 ctxt->wellFormed = 0; 4219 ctxt->disableSAX = 1; 4220 } else { 4221 if (xmlStrEqual(contmod, BAD_CAST"NDATA")) { 4222 if (!IS_BLANK(CUR)) { 4223 ctxt->errNo = XML_ERR_SPACE_REQUIRED; 4224 if ((ctxt->sax != NULL) && 4225 (ctxt->sax->error != NULL)) 4226 ctxt->sax->error(ctxt->userData, 4227 "Space required after 'NDATA'\n"); 4228 ctxt->wellFormed = 0; 4229 ctxt->disableSAX = 1; 4230 } 4231 SKIP_BLANKS; 4232 ndata = xmlParseName(ctxt); 4233 if ((ctxt->sax != NULL) && (!ctxt->disableSAX) && 4234 (ctxt->sax->unparsedEntityDecl != NULL)) { 4235 ctxt->sax->unparsedEntityDecl(ctxt->userData, 4236 name, literal, URI, ndata); 4237 } 4238 } else if (xmlStrEqual(contmod, BAD_CAST"SUBDOC")) { 4239 if ((ctxt->sax != NULL) && 4240 (ctxt->sax->warning != NULL)) 4241 ctxt->sax->warning(ctxt->userData, 4242 "SUBDOC entities are not supported\n"); 4243 SKIP_BLANKS; 4244 ndata = xmlParseName(ctxt); 4245 if ((ctxt->sax != NULL) && (!ctxt->disableSAX) && 4246 (ctxt->sax->unparsedEntityDecl != NULL)) { 4247 ctxt->sax->unparsedEntityDecl(ctxt->userData, 4248 name, literal, URI, ndata); 4249 } 4250 } else if (xmlStrEqual(contmod, BAD_CAST"CDATA")) { 4251 if ((ctxt->sax != NULL) && 4252 (ctxt->sax->warning != NULL)) 4253 ctxt->sax->warning(ctxt->userData, 4254 "CDATA entities are not supported\n"); 4255 SKIP_BLANKS; 4256 ndata = xmlParseName(ctxt); 4257 if ((ctxt->sax != NULL) && (!ctxt->disableSAX) && 4258 (ctxt->sax->unparsedEntityDecl != NULL)) { 4259 ctxt->sax->unparsedEntityDecl(ctxt->userData, 4260 name, literal, URI, ndata); 4261 } 4262 } 4263 xmlFree(contmod); 4264 } 4265 } else { 4266 if ((ctxt->sax != NULL) && 4267 (!ctxt->disableSAX) && (ctxt->sax->entityDecl != NULL)) 4268 ctxt->sax->entityDecl(ctxt->userData, name, 4269 XML_EXTERNAL_GENERAL_PARSED_ENTITY, 4270 literal, URI, NULL); 4271 } 4272 } 4273 } 4274 SKIP_BLANKS; 4275 if (RAW != '>') { 4276 ctxt->errNo = XML_ERR_ENTITY_NOT_FINISHED; 4277 if ((ctxt->sax != NULL) && (ctxt->sax->error != NULL)) 4278 ctxt->sax->error(ctxt->userData, 4279 "docbParseEntityDecl: entity %s not terminated\n", name); 4280 ctxt->wellFormed = 0; 4281 ctxt->disableSAX = 1; 4282 } else { 4283 if (input != ctxt->input) { 4284 ctxt->errNo = XML_ERR_ENTITY_BOUNDARY; 4285 if ((ctxt->sax != NULL) && (ctxt->sax->error != NULL)) 4286 ctxt->sax->error(ctxt->userData, 4287"Entity declaration doesn't start and stop in the same entity\n"); 4288 ctxt->wellFormed = 0; 4289 ctxt->disableSAX = 1; 4290 } 4291 NEXT; 4292 } 4293 if (orig != NULL) { 4294 /* 4295 * Ugly mechanism to save the raw entity value. 4296 */ 4297 xmlEntityPtr cur = NULL; 4298 4299 if (isParameter) { 4300 if ((ctxt->sax != NULL) && 4301 (ctxt->sax->getParameterEntity != NULL)) 4302 cur = ctxt->sax->getParameterEntity(ctxt->userData, name); 4303 } else { 4304 if ((ctxt->sax != NULL) && 4305 (ctxt->sax->getEntity != NULL)) 4306 cur = ctxt->sax->getEntity(ctxt->userData, name); 4307 } 4308 if (cur != NULL) { 4309 if (cur->orig != NULL) 4310 xmlFree(orig); 4311 else 4312 cur->orig = orig; 4313 } else 4314 xmlFree(orig); 4315 } 4316 if (name != NULL) xmlFree(name); 4317 if (value != NULL) xmlFree(value); 4318 if (URI != NULL) xmlFree(URI); 4319 if (literal != NULL) xmlFree(literal); 4320 if (ndata != NULL) xmlFree(ndata); 4321 } 4322} 4323 4324/** 4325 * docbParseMarkupDecl: 4326 * @ctxt: an SGML parser context 4327 * 4328 * parse Markup declarations 4329 * 4330 * [29] markupdecl ::= elementdecl | AttlistDecl | EntityDecl | 4331 * NotationDecl | PI | Comment 4332 */ 4333static void 4334docbParseMarkupDecl(xmlParserCtxtPtr ctxt) { 4335 GROW; 4336 xmlParseElementDecl(ctxt); 4337 xmlParseAttributeListDecl(ctxt); 4338 docbParseEntityDecl(ctxt); 4339 xmlParseNotationDecl(ctxt); 4340 xmlParsePI(ctxt); 4341 xmlParseComment(ctxt); 4342 /* 4343 * This is only for internal subset. On external entities, 4344 * the replacement is done before parsing stage 4345 */ 4346 if ((ctxt->external == 0) && (ctxt->inputNr == 1)) 4347 xmlParsePEReference(ctxt); 4348 ctxt->instate = XML_PARSER_DTD; 4349} 4350 4351/** 4352 * docbParseInternalsubset: 4353 * @ctxt: an SGML parser context 4354 * 4355 * parse the internal subset declaration 4356 * 4357 * [28 end] ('[' (markupdecl | PEReference | S)* ']' S?)? '>' 4358 */ 4359 4360static void 4361docbParseInternalSubset(xmlParserCtxtPtr ctxt) { 4362 /* 4363 * Is there any DTD definition ? 4364 */ 4365 if (RAW == '[') { 4366 ctxt->instate = XML_PARSER_DTD; 4367 NEXT; 4368 /* 4369 * Parse the succession of Markup declarations and 4370 * PEReferences. 4371 * Subsequence (markupdecl | PEReference | S)* 4372 */ 4373 while (RAW != ']') { 4374 const xmlChar *check = CUR_PTR; 4375 int cons = ctxt->input->consumed; 4376 4377 SKIP_BLANKS; 4378 docbParseMarkupDecl(ctxt); 4379 xmlParsePEReference(ctxt); 4380 4381 /* 4382 * Pop-up of finished entities. 4383 */ 4384 while ((RAW == 0) && (ctxt->inputNr > 1)) 4385 xmlPopInput(ctxt); 4386 4387 if ((CUR_PTR == check) && (cons == ctxt->input->consumed)) { 4388 ctxt->errNo = XML_ERR_INTERNAL_ERROR; 4389 if ((ctxt->sax != NULL) && (ctxt->sax->error != NULL)) 4390 ctxt->sax->error(ctxt->userData, 4391 "docbParseInternalSubset: error detected in Markup declaration\n"); 4392 ctxt->wellFormed = 0; 4393 ctxt->disableSAX = 1; 4394 break; 4395 } 4396 } 4397 if (RAW == ']') { 4398 NEXT; 4399 SKIP_BLANKS; 4400 } 4401 } 4402 4403 /* 4404 * We should be at the end of the DOCTYPE declaration. 4405 */ 4406 if (RAW != '>') { 4407 ctxt->errNo = XML_ERR_DOCTYPE_NOT_FINISHED; 4408 if ((ctxt->sax != NULL) && (ctxt->sax->error != NULL)) 4409 ctxt->sax->error(ctxt->userData, "DOCTYPE unproperly terminated\n"); 4410 ctxt->wellFormed = 0; 4411 ctxt->disableSAX = 1; 4412 } 4413 NEXT; 4414} 4415 4416/** 4417 * docbParseMisc: 4418 * @ctxt: an XML parser context 4419 * 4420 * parse an XML Misc* optionnal field. 4421 * 4422 * [27] Misc ::= Comment | PI | S 4423 */ 4424 4425static void 4426docbParseMisc(xmlParserCtxtPtr ctxt) { 4427 while (((RAW == '<') && (NXT(1) == '?')) || 4428 ((RAW == '<') && (NXT(1) == '!') && 4429 (NXT(2) == '-') && (NXT(3) == '-')) || 4430 IS_BLANK(CUR)) { 4431 if ((RAW == '<') && (NXT(1) == '?')) { 4432 xmlParsePI(ctxt); /* TODO: SGML PIs differs */ 4433 } else if (IS_BLANK(CUR)) { 4434 NEXT; 4435 } else 4436 xmlParseComment(ctxt); 4437 } 4438} 4439 4440/** 4441 * docbParseDocument : 4442 * @ctxt: an SGML parser context 4443 * 4444 * parse an SGML document (and build a tree if using the standard SAX 4445 * interface). 4446 * 4447 * Returns 0, -1 in case of error. the parser context is augmented 4448 * as a result of the parsing. 4449 */ 4450 4451int 4452docbParseDocument(docbParserCtxtPtr ctxt) { 4453 xmlChar start[4]; 4454 xmlCharEncoding enc; 4455 xmlDtdPtr dtd; 4456 4457 docbDefaultSAXHandlerInit(); 4458 ctxt->html = 2; 4459 4460 GROW; 4461 /* 4462 * SAX: beginning of the document processing. 4463 */ 4464 if ((ctxt->sax) && (ctxt->sax->setDocumentLocator)) 4465 ctxt->sax->setDocumentLocator(ctxt->userData, &xmlDefaultSAXLocator); 4466 4467 /* 4468 * Get the 4 first bytes and decode the charset 4469 * if enc != XML_CHAR_ENCODING_NONE 4470 * plug some encoding conversion routines. 4471 */ 4472 start[0] = RAW; 4473 start[1] = NXT(1); 4474 start[2] = NXT(2); 4475 start[3] = NXT(3); 4476 enc = xmlDetectCharEncoding(start, 4); 4477 if (enc != XML_CHAR_ENCODING_NONE) { 4478 xmlSwitchEncoding(ctxt, enc); 4479 } 4480 4481 /* 4482 * Wipe out everything which is before the first '<' 4483 */ 4484 SKIP_BLANKS; 4485 if (CUR == 0) { 4486 if ((ctxt->sax != NULL) && (ctxt->sax->error != NULL)) 4487 ctxt->sax->error(ctxt->userData, "Document is empty\n"); 4488 ctxt->wellFormed = 0; 4489 } 4490 4491 if ((ctxt->sax) && (ctxt->sax->startDocument) && (!ctxt->disableSAX)) 4492 ctxt->sax->startDocument(ctxt->userData); 4493 4494 4495 /* 4496 * The Misc part of the Prolog 4497 */ 4498 GROW; 4499 docbParseMisc(ctxt); 4500 4501 /* 4502 * Then possibly doc type declaration(s) and more Misc 4503 * (doctypedecl Misc*)? 4504 */ 4505 GROW; 4506 if ((RAW == '<') && (NXT(1) == '!') && 4507 (NXT(2) == 'D') && (NXT(3) == 'O') && 4508 (NXT(4) == 'C') && (NXT(5) == 'T') && 4509 (NXT(6) == 'Y') && (NXT(7) == 'P') && 4510 (NXT(8) == 'E')) { 4511 4512 ctxt->inSubset = 1; 4513 docbParseDocTypeDecl(ctxt); 4514 if (RAW == '[') { 4515 ctxt->instate = XML_PARSER_DTD; 4516 docbParseInternalSubset(ctxt); 4517 } 4518 4519 /* 4520 * Create and update the external subset. 4521 */ 4522 ctxt->inSubset = 2; 4523 if ((ctxt->sax != NULL) && (ctxt->sax->internalSubset != NULL) && 4524 (!ctxt->disableSAX)) 4525 ctxt->sax->internalSubset(ctxt->userData, ctxt->intSubName, 4526 ctxt->extSubSystem, ctxt->extSubURI); 4527 ctxt->inSubset = 0; 4528 4529 4530 ctxt->instate = XML_PARSER_PROLOG; 4531 docbParseMisc(ctxt); 4532 } 4533 4534 /* 4535 * Time to start parsing the tree itself 4536 */ 4537 docbParseContent(ctxt); 4538 4539 /* 4540 * autoclose 4541 */ 4542 if (CUR == 0) 4543 docbAutoClose(ctxt, NULL); 4544 4545 4546 /* 4547 * SAX: end of the document processing. 4548 */ 4549 if ((ctxt->sax) && (ctxt->sax->endDocument != NULL)) 4550 ctxt->sax->endDocument(ctxt->userData); 4551 4552 if (ctxt->myDoc != NULL) { 4553 dtd = ctxt->myDoc->intSubset; 4554 if (dtd == NULL) 4555 ctxt->myDoc->intSubset = 4556 xmlCreateIntSubset(ctxt->myDoc, BAD_CAST "SGML", 4557 BAD_CAST "-//W3C//DTD SGML 4.0 Transitional//EN", 4558 BAD_CAST "http://www.w3.org/TR/REC-docbook/loose.dtd"); 4559 } 4560 if (! ctxt->wellFormed) return(-1); 4561 return(0); 4562} 4563 4564 4565/************************************************************************ 4566 * * 4567 * Parser contexts handling * 4568 * * 4569 ************************************************************************/ 4570 4571/** 4572 * xmlInitParserCtxt: 4573 * @ctxt: an SGML parser context 4574 * 4575 * Initialize a parser context 4576 */ 4577 4578static void 4579docbInitParserCtxt(docbParserCtxtPtr ctxt) 4580{ 4581 docbSAXHandler *sax; 4582 4583 if (ctxt == NULL) return; 4584 memset(ctxt, 0, sizeof(docbParserCtxt)); 4585 4586 sax = (docbSAXHandler *) xmlMalloc(sizeof(docbSAXHandler)); 4587 if (sax == NULL) { 4588 xmlGenericError(xmlGenericErrorContext, 4589 "docbInitParserCtxt: out of memory\n"); 4590 } 4591 memset(sax, 0, sizeof(docbSAXHandler)); 4592 4593 /* Allocate the Input stack */ 4594 ctxt->inputTab = (docbParserInputPtr *) 4595 xmlMalloc(5 * sizeof(docbParserInputPtr)); 4596 if (ctxt->inputTab == NULL) { 4597 xmlGenericError(xmlGenericErrorContext, 4598 "docbInitParserCtxt: out of memory\n"); 4599 } 4600 ctxt->inputNr = 0; 4601 ctxt->inputMax = 5; 4602 ctxt->input = NULL; 4603 ctxt->version = NULL; 4604 ctxt->encoding = NULL; 4605 ctxt->standalone = -1; 4606 ctxt->instate = XML_PARSER_START; 4607 4608 /* Allocate the Node stack */ 4609 ctxt->nodeTab = (docbNodePtr *) xmlMalloc(10 * sizeof(docbNodePtr)); 4610 ctxt->nodeNr = 0; 4611 ctxt->nodeMax = 10; 4612 ctxt->node = NULL; 4613 4614 /* Allocate the Name stack */ 4615 ctxt->nameTab = (xmlChar **) xmlMalloc(10 * sizeof(xmlChar *)); 4616 ctxt->nameNr = 0; 4617 ctxt->nameMax = 10; 4618 ctxt->name = NULL; 4619 4620 if (sax == NULL) ctxt->sax = &docbDefaultSAXHandler; 4621 else { 4622 ctxt->sax = sax; 4623 memcpy(sax, &docbDefaultSAXHandler, sizeof(docbSAXHandler)); 4624 } 4625 ctxt->userData = ctxt; 4626 ctxt->myDoc = NULL; 4627 ctxt->wellFormed = 1; 4628 ctxt->replaceEntities = 0; 4629 ctxt->html = 2; 4630 ctxt->record_info = 0; 4631 ctxt->validate = 0; 4632 ctxt->nbChars = 0; 4633 ctxt->checkIndex = 0; 4634 xmlInitNodeInfoSeq(&ctxt->node_seq); 4635} 4636 4637/** 4638 * docbFreeParserCtxt: 4639 * @ctxt: an SGML parser context 4640 * 4641 * Free all the memory used by a parser context. However the parsed 4642 * document in ctxt->myDoc is not freed. 4643 */ 4644 4645void 4646docbFreeParserCtxt(docbParserCtxtPtr ctxt) 4647{ 4648 xmlFreeParserCtxt(ctxt); 4649} 4650 4651/** 4652 * docbCreateDocParserCtxt : 4653 * @cur: a pointer to an array of xmlChar 4654 * @encoding: a free form C string describing the SGML document encoding, or NULL 4655 * 4656 * Create a parser context for an SGML document. 4657 * 4658 * Returns the new parser context or NULL 4659 */ 4660static docbParserCtxtPtr 4661docbCreateDocParserCtxt(xmlChar *cur, const char *encoding) { 4662 docbParserCtxtPtr ctxt; 4663 docbParserInputPtr input; 4664 /* sgmlCharEncoding enc; */ 4665 4666 ctxt = (docbParserCtxtPtr) xmlMalloc(sizeof(docbParserCtxt)); 4667 if (ctxt == NULL) { 4668 perror("malloc"); 4669 return(NULL); 4670 } 4671 docbInitParserCtxt(ctxt); 4672 input = (docbParserInputPtr) xmlMalloc(sizeof(docbParserInput)); 4673 if (input == NULL) { 4674 perror("malloc"); 4675 xmlFree(ctxt); 4676 return(NULL); 4677 } 4678 memset(input, 0, sizeof(docbParserInput)); 4679 4680 input->line = 1; 4681 input->col = 1; 4682 input->base = cur; 4683 input->cur = cur; 4684 4685 inputPush(ctxt, input); 4686 return(ctxt); 4687} 4688 4689/************************************************************************ 4690 * * 4691 * Progressive parsing interfaces * 4692 * * 4693 ************************************************************************/ 4694 4695/** 4696 * docbParseLookupSequence: 4697 * @ctxt: an SGML parser context 4698 * @first: the first char to lookup 4699 * @next: the next char to lookup or zero 4700 * @third: the next char to lookup or zero 4701 * 4702 * Try to find if a sequence (first, next, third) or just (first next) or 4703 * (first) is available in the input stream. 4704 * This function has a side effect of (possibly) incrementing ctxt->checkIndex 4705 * to avoid rescanning sequences of bytes, it DOES change the state of the 4706 * parser, do not use liberally. 4707 * This is basically similar to xmlParseLookupSequence() 4708 * 4709 * Returns the index to the current parsing point if the full sequence 4710 * is available, -1 otherwise. 4711 */ 4712static int 4713docbParseLookupSequence(docbParserCtxtPtr ctxt, xmlChar first, 4714 xmlChar next, xmlChar third) { 4715 int base, len; 4716 docbParserInputPtr in; 4717 const xmlChar *buf; 4718 4719 in = ctxt->input; 4720 if (in == NULL) return(-1); 4721 base = in->cur - in->base; 4722 if (base < 0) return(-1); 4723 if (ctxt->checkIndex > base) 4724 base = ctxt->checkIndex; 4725 if (in->buf == NULL) { 4726 buf = in->base; 4727 len = in->length; 4728 } else { 4729 buf = in->buf->buffer->content; 4730 len = in->buf->buffer->use; 4731 } 4732 /* take into account the sequence length */ 4733 if (third) len -= 2; 4734 else if (next) len --; 4735 for (;base < len;base++) { 4736 if (buf[base] == first) { 4737 if (third != 0) { 4738 if ((buf[base + 1] != next) || 4739 (buf[base + 2] != third)) continue; 4740 } else if (next != 0) { 4741 if (buf[base + 1] != next) continue; 4742 } 4743 ctxt->checkIndex = 0; 4744#ifdef DEBUG_PUSH 4745 if (next == 0) 4746 xmlGenericError(xmlGenericErrorContext, 4747 "HPP: lookup '%c' found at %d\n", 4748 first, base); 4749 else if (third == 0) 4750 xmlGenericError(xmlGenericErrorContext, 4751 "HPP: lookup '%c%c' found at %d\n", 4752 first, next, base); 4753 else 4754 xmlGenericError(xmlGenericErrorContext, 4755 "HPP: lookup '%c%c%c' found at %d\n", 4756 first, next, third, base); 4757#endif 4758 return(base - (in->cur - in->base)); 4759 } 4760 } 4761 ctxt->checkIndex = base; 4762#ifdef DEBUG_PUSH 4763 if (next == 0) 4764 xmlGenericError(xmlGenericErrorContext, 4765 "HPP: lookup '%c' failed\n", first); 4766 else if (third == 0) 4767 xmlGenericError(xmlGenericErrorContext, 4768 "HPP: lookup '%c%c' failed\n", first, next); 4769 else 4770 xmlGenericError(xmlGenericErrorContext, 4771 "HPP: lookup '%c%c%c' failed\n", first, next, third); 4772#endif 4773 return(-1); 4774} 4775 4776/** 4777 * docbParseTryOrFinish: 4778 * @ctxt: an SGML parser context 4779 * @terminate: last chunk indicator 4780 * 4781 * Try to progress on parsing 4782 * 4783 * Returns zero if no parsing was possible 4784 */ 4785static int 4786docbParseTryOrFinish(docbParserCtxtPtr ctxt, int terminate) { 4787 int ret = 0; 4788 docbParserInputPtr in; 4789 int avail = 0; 4790 xmlChar cur, next; 4791 4792#ifdef DEBUG_PUSH 4793 switch (ctxt->instate) { 4794 case XML_PARSER_EOF: 4795 xmlGenericError(xmlGenericErrorContext, 4796 "HPP: try EOF\n"); break; 4797 case XML_PARSER_START: 4798 xmlGenericError(xmlGenericErrorContext, 4799 "HPP: try START\n"); break; 4800 case XML_PARSER_MISC: 4801 xmlGenericError(xmlGenericErrorContext, 4802 "HPP: try MISC\n");break; 4803 case XML_PARSER_COMMENT: 4804 xmlGenericError(xmlGenericErrorContext, 4805 "HPP: try COMMENT\n");break; 4806 case XML_PARSER_PROLOG: 4807 xmlGenericError(xmlGenericErrorContext, 4808 "HPP: try PROLOG\n");break; 4809 case XML_PARSER_START_TAG: 4810 xmlGenericError(xmlGenericErrorContext, 4811 "HPP: try START_TAG\n");break; 4812 case XML_PARSER_CONTENT: 4813 xmlGenericError(xmlGenericErrorContext, 4814 "HPP: try CONTENT\n");break; 4815 case XML_PARSER_CDATA_SECTION: 4816 xmlGenericError(xmlGenericErrorContext, 4817 "HPP: try CDATA_SECTION\n");break; 4818 case XML_PARSER_END_TAG: 4819 xmlGenericError(xmlGenericErrorContext, 4820 "HPP: try END_TAG\n");break; 4821 case XML_PARSER_ENTITY_DECL: 4822 xmlGenericError(xmlGenericErrorContext, 4823 "HPP: try ENTITY_DECL\n");break; 4824 case XML_PARSER_ENTITY_VALUE: 4825 xmlGenericError(xmlGenericErrorContext, 4826 "HPP: try ENTITY_VALUE\n");break; 4827 case XML_PARSER_ATTRIBUTE_VALUE: 4828 xmlGenericError(xmlGenericErrorContext, 4829 "HPP: try ATTRIBUTE_VALUE\n");break; 4830 case XML_PARSER_DTD: 4831 xmlGenericError(xmlGenericErrorContext, 4832 "HPP: try DTD\n");break; 4833 case XML_PARSER_EPILOG: 4834 xmlGenericError(xmlGenericErrorContext, 4835 "HPP: try EPILOG\n");break; 4836 case XML_PARSER_PI: 4837 xmlGenericError(xmlGenericErrorContext, 4838 "HPP: try PI\n");break; 4839 } 4840#endif 4841 4842 while (1) { 4843 4844 in = ctxt->input; 4845 if (in == NULL) break; 4846 if (in->buf == NULL) 4847 avail = in->length - (in->cur - in->base); 4848 else 4849 avail = in->buf->buffer->use - (in->cur - in->base); 4850 if ((avail == 0) && (terminate)) { 4851 docbAutoClose(ctxt, NULL); 4852 if ((ctxt->nameNr == 0) && (ctxt->instate != XML_PARSER_EOF)) { 4853 /* 4854 * SAX: end of the document processing. 4855 */ 4856 ctxt->instate = XML_PARSER_EOF; 4857 if ((ctxt->sax) && (ctxt->sax->endDocument != NULL)) 4858 ctxt->sax->endDocument(ctxt->userData); 4859 } 4860 } 4861 if (avail < 1) 4862 goto done; 4863 switch (ctxt->instate) { 4864 case XML_PARSER_EOF: 4865 /* 4866 * Document parsing is done ! 4867 */ 4868 goto done; 4869 case XML_PARSER_START: 4870 /* 4871 * Very first chars read from the document flow. 4872 */ 4873 cur = in->cur[0]; 4874 if (IS_BLANK(cur)) { 4875 SKIP_BLANKS; 4876 if (in->buf == NULL) 4877 avail = in->length - (in->cur - in->base); 4878 else 4879 avail = in->buf->buffer->use - (in->cur - in->base); 4880 } 4881 if ((ctxt->sax) && (ctxt->sax->setDocumentLocator)) 4882 ctxt->sax->setDocumentLocator(ctxt->userData, 4883 &xmlDefaultSAXLocator); 4884 if ((ctxt->sax) && (ctxt->sax->startDocument) && 4885 (!ctxt->disableSAX)) 4886 ctxt->sax->startDocument(ctxt->userData); 4887 4888 cur = in->cur[0]; 4889 next = in->cur[1]; 4890 if ((cur == '<') && (next == '!') && 4891 (UPP(2) == 'D') && (UPP(3) == 'O') && 4892 (UPP(4) == 'C') && (UPP(5) == 'T') && 4893 (UPP(6) == 'Y') && (UPP(7) == 'P') && 4894 (UPP(8) == 'E')) { 4895 if ((!terminate) && 4896 (docbParseLookupSequence(ctxt, '>', 0, 0) < 0)) 4897 goto done; 4898#ifdef DEBUG_PUSH 4899 xmlGenericError(xmlGenericErrorContext, 4900 "HPP: Parsing internal subset\n"); 4901#endif 4902 docbParseDocTypeDecl(ctxt); 4903 ctxt->instate = XML_PARSER_PROLOG; 4904#ifdef DEBUG_PUSH 4905 xmlGenericError(xmlGenericErrorContext, 4906 "HPP: entering PROLOG\n"); 4907#endif 4908 } else { 4909 ctxt->instate = XML_PARSER_MISC; 4910 } 4911#ifdef DEBUG_PUSH 4912 xmlGenericError(xmlGenericErrorContext, 4913 "HPP: entering MISC\n"); 4914#endif 4915 break; 4916 case XML_PARSER_MISC: 4917 SKIP_BLANKS; 4918 if (in->buf == NULL) 4919 avail = in->length - (in->cur - in->base); 4920 else 4921 avail = in->buf->buffer->use - (in->cur - in->base); 4922 if (avail < 2) 4923 goto done; 4924 cur = in->cur[0]; 4925 next = in->cur[1]; 4926 if ((cur == '<') && (next == '!') && 4927 (in->cur[2] == '-') && (in->cur[3] == '-')) { 4928 if ((!terminate) && 4929 (docbParseLookupSequence(ctxt, '-', '-', '>') < 0)) 4930 goto done; 4931#ifdef DEBUG_PUSH 4932 xmlGenericError(xmlGenericErrorContext, 4933 "HPP: Parsing Comment\n"); 4934#endif 4935 docbParseComment(ctxt); 4936 ctxt->instate = XML_PARSER_MISC; 4937 } else if ((cur == '<') && (next == '!') && 4938 (UPP(2) == 'D') && (UPP(3) == 'O') && 4939 (UPP(4) == 'C') && (UPP(5) == 'T') && 4940 (UPP(6) == 'Y') && (UPP(7) == 'P') && 4941 (UPP(8) == 'E')) { 4942 if ((!terminate) && 4943 (docbParseLookupSequence(ctxt, '>', 0, 0) < 0)) 4944 goto done; 4945#ifdef DEBUG_PUSH 4946 xmlGenericError(xmlGenericErrorContext, 4947 "HPP: Parsing internal subset\n"); 4948#endif 4949 docbParseDocTypeDecl(ctxt); 4950 ctxt->instate = XML_PARSER_PROLOG; 4951#ifdef DEBUG_PUSH 4952 xmlGenericError(xmlGenericErrorContext, 4953 "HPP: entering PROLOG\n"); 4954#endif 4955 } else if ((cur == '<') && (next == '!') && 4956 (avail < 9)) { 4957 goto done; 4958 } else { 4959 ctxt->instate = XML_PARSER_START_TAG; 4960#ifdef DEBUG_PUSH 4961 xmlGenericError(xmlGenericErrorContext, 4962 "HPP: entering START_TAG\n"); 4963#endif 4964 } 4965 break; 4966 case XML_PARSER_PROLOG: 4967 SKIP_BLANKS; 4968 if (in->buf == NULL) 4969 avail = in->length - (in->cur - in->base); 4970 else 4971 avail = in->buf->buffer->use - (in->cur - in->base); 4972 if (avail < 2) 4973 goto done; 4974 cur = in->cur[0]; 4975 next = in->cur[1]; 4976 if ((cur == '<') && (next == '!') && 4977 (in->cur[2] == '-') && (in->cur[3] == '-')) { 4978 if ((!terminate) && 4979 (docbParseLookupSequence(ctxt, '-', '-', '>') < 0)) 4980 goto done; 4981#ifdef DEBUG_PUSH 4982 xmlGenericError(xmlGenericErrorContext, 4983 "HPP: Parsing Comment\n"); 4984#endif 4985 docbParseComment(ctxt); 4986 ctxt->instate = XML_PARSER_PROLOG; 4987 } else if ((cur == '<') && (next == '!') && 4988 (avail < 4)) { 4989 goto done; 4990 } else { 4991 ctxt->instate = XML_PARSER_START_TAG; 4992#ifdef DEBUG_PUSH 4993 xmlGenericError(xmlGenericErrorContext, 4994 "HPP: entering START_TAG\n"); 4995#endif 4996 } 4997 break; 4998 case XML_PARSER_EPILOG: 4999 if (in->buf == NULL) 5000 avail = in->length - (in->cur - in->base); 5001 else 5002 avail = in->buf->buffer->use - (in->cur - in->base); 5003 if (avail < 1) 5004 goto done; 5005 cur = in->cur[0]; 5006 if (IS_BLANK(cur)) { 5007 docbParseCharData(ctxt); 5008 goto done; 5009 } 5010 if (avail < 2) 5011 goto done; 5012 next = in->cur[1]; 5013 if ((cur == '<') && (next == '!') && 5014 (in->cur[2] == '-') && (in->cur[3] == '-')) { 5015 if ((!terminate) && 5016 (docbParseLookupSequence(ctxt, '-', '-', '>') < 0)) 5017 goto done; 5018#ifdef DEBUG_PUSH 5019 xmlGenericError(xmlGenericErrorContext, 5020 "HPP: Parsing Comment\n"); 5021#endif 5022 docbParseComment(ctxt); 5023 ctxt->instate = XML_PARSER_EPILOG; 5024 } else if ((cur == '<') && (next == '!') && 5025 (avail < 4)) { 5026 goto done; 5027 } else { 5028 ctxt->errNo = XML_ERR_DOCUMENT_END; 5029 if ((ctxt->sax != NULL) && (ctxt->sax->error != NULL)) 5030 ctxt->sax->error(ctxt->userData, 5031 "Extra content at the end of the document\n"); 5032 ctxt->wellFormed = 0; 5033 ctxt->instate = XML_PARSER_EOF; 5034#ifdef DEBUG_PUSH 5035 xmlGenericError(xmlGenericErrorContext, 5036 "HPP: entering EOF\n"); 5037#endif 5038 if ((ctxt->sax) && (ctxt->sax->endDocument != NULL)) 5039 ctxt->sax->endDocument(ctxt->userData); 5040 goto done; 5041 } 5042 break; 5043 case XML_PARSER_START_TAG: { 5044 xmlChar *name, *oldname; 5045 int depth = ctxt->nameNr; 5046 docbElemDescPtr info; 5047 5048 if (avail < 2) 5049 goto done; 5050 cur = in->cur[0]; 5051 if (cur != '<') { 5052 ctxt->instate = XML_PARSER_CONTENT; 5053#ifdef DEBUG_PUSH 5054 xmlGenericError(xmlGenericErrorContext, 5055 "HPP: entering CONTENT\n"); 5056#endif 5057 break; 5058 } 5059 if ((!terminate) && 5060 (docbParseLookupSequence(ctxt, '>', 0, 0) < 0)) 5061 goto done; 5062 5063 oldname = xmlStrdup(ctxt->name); 5064 docbParseStartTag(ctxt); 5065 name = ctxt->name; 5066#ifdef DEBUG 5067 if (oldname == NULL) 5068 xmlGenericError(xmlGenericErrorContext, 5069 "Start of element %s\n", name); 5070 else if (name == NULL) 5071 xmlGenericError(xmlGenericErrorContext, 5072 "Start of element failed, was %s\n", 5073 oldname); 5074 else 5075 xmlGenericError(xmlGenericErrorContext, 5076 "Start of element %s, was %s\n", 5077 name, oldname); 5078#endif 5079 if (((depth == ctxt->nameNr) && 5080 (xmlStrEqual(oldname, ctxt->name))) || 5081 (name == NULL)) { 5082 if (CUR == '>') 5083 NEXT; 5084 if (oldname != NULL) 5085 xmlFree(oldname); 5086 break; 5087 } 5088 if (oldname != NULL) 5089 xmlFree(oldname); 5090 5091 /* 5092 * Lookup the info for that element. 5093 */ 5094 info = docbTagLookup(name); 5095 if (info == NULL) { 5096 if ((ctxt->sax != NULL) && (ctxt->sax->error != NULL)) 5097 ctxt->sax->error(ctxt->userData, "Tag %s unknown\n", 5098 name); 5099 ctxt->wellFormed = 0; 5100 } else if (info->depr) { 5101 /*************************** 5102 if ((ctxt->sax != NULL) && (ctxt->sax->warning != NULL)) 5103 ctxt->sax->warning(ctxt->userData, 5104 "Tag %s is deprecated\n", 5105 name); 5106 ***************************/ 5107 } 5108 5109 /* 5110 * Check for an Empty Element labelled the XML/SGML way 5111 */ 5112 if ((CUR == '/') && (NXT(1) == '>')) { 5113 SKIP(2); 5114 if ((ctxt->sax != NULL) && (ctxt->sax->endElement != NULL)) 5115 ctxt->sax->endElement(ctxt->userData, name); 5116 oldname = docbnamePop(ctxt); 5117#ifdef DEBUG 5118 xmlGenericError(xmlGenericErrorContext,"End of tag the XML way: popping out %s\n", 5119 oldname); 5120#endif 5121 if (oldname != NULL) 5122 xmlFree(oldname); 5123 ctxt->instate = XML_PARSER_CONTENT; 5124#ifdef DEBUG_PUSH 5125 xmlGenericError(xmlGenericErrorContext, 5126 "HPP: entering CONTENT\n"); 5127#endif 5128 break; 5129 } 5130 5131 if (CUR == '>') { 5132 NEXT; 5133 } else { 5134 if ((ctxt->sax != NULL) && (ctxt->sax->error != NULL)) 5135 ctxt->sax->error(ctxt->userData, 5136 "Couldn't find end of Start Tag %s\n", 5137 name); 5138 ctxt->wellFormed = 0; 5139 5140 /* 5141 * end of parsing of this node. 5142 */ 5143 if (xmlStrEqual(name, ctxt->name)) { 5144 nodePop(ctxt); 5145 oldname = docbnamePop(ctxt); 5146#ifdef DEBUG 5147 xmlGenericError(xmlGenericErrorContext, 5148 "End of start tag problem: popping out %s\n", oldname); 5149#endif 5150 if (oldname != NULL) 5151 xmlFree(oldname); 5152 } 5153 5154 ctxt->instate = XML_PARSER_CONTENT; 5155#ifdef DEBUG_PUSH 5156 xmlGenericError(xmlGenericErrorContext, 5157 "HPP: entering CONTENT\n"); 5158#endif 5159 break; 5160 } 5161 5162 /* 5163 * Check for an Empty Element from DTD definition 5164 */ 5165 if ((info != NULL) && (info->empty)) { 5166 if ((ctxt->sax != NULL) && (ctxt->sax->endElement != NULL)) 5167 ctxt->sax->endElement(ctxt->userData, name); 5168 oldname = docbnamePop(ctxt); 5169#ifdef DEBUG 5170 xmlGenericError(xmlGenericErrorContext,"End of empty tag %s : popping out %s\n", name, oldname); 5171#endif 5172 if (oldname != NULL) 5173 xmlFree(oldname); 5174 } 5175 ctxt->instate = XML_PARSER_CONTENT; 5176#ifdef DEBUG_PUSH 5177 xmlGenericError(xmlGenericErrorContext, 5178 "HPP: entering CONTENT\n"); 5179#endif 5180 break; 5181 } 5182 case XML_PARSER_CONTENT: { 5183 long cons; 5184 /* 5185 * Handle preparsed entities and charRef 5186 */ 5187 if (ctxt->token != 0) { 5188 xmlChar chr[2] = { 0 , 0 } ; 5189 5190 chr[0] = (xmlChar) ctxt->token; 5191 docbCheckParagraph(ctxt); 5192 if ((ctxt->sax != NULL) && (ctxt->sax->characters != NULL)) 5193 ctxt->sax->characters(ctxt->userData, chr, 1); 5194 ctxt->token = 0; 5195 ctxt->checkIndex = 0; 5196 } 5197 if ((avail == 1) && (terminate)) { 5198 cur = in->cur[0]; 5199 if ((cur != '<') && (cur != '&')) { 5200 if (ctxt->sax != NULL) { 5201 if (IS_BLANK(cur)) { 5202 if (ctxt->sax->ignorableWhitespace != NULL) 5203 ctxt->sax->ignorableWhitespace( 5204 ctxt->userData, &cur, 1); 5205 } else { 5206 docbCheckParagraph(ctxt); 5207 if (ctxt->sax->characters != NULL) 5208 ctxt->sax->characters( 5209 ctxt->userData, &cur, 1); 5210 } 5211 } 5212 ctxt->token = 0; 5213 ctxt->checkIndex = 0; 5214 NEXT; 5215 } 5216 break; 5217 } 5218 if (avail < 2) 5219 goto done; 5220 cur = in->cur[0]; 5221 next = in->cur[1]; 5222 cons = ctxt->nbChars; 5223 /* 5224 * Sometimes DOCTYPE arrives in the middle of the document 5225 */ 5226 if ((cur == '<') && (next == '!') && 5227 (UPP(2) == 'D') && (UPP(3) == 'O') && 5228 (UPP(4) == 'C') && (UPP(5) == 'T') && 5229 (UPP(6) == 'Y') && (UPP(7) == 'P') && 5230 (UPP(8) == 'E')) { 5231 if ((!terminate) && 5232 (docbParseLookupSequence(ctxt, '>', 0, 0) < 0)) 5233 goto done; 5234 if ((ctxt->sax != NULL) && (ctxt->sax->error != NULL)) 5235 ctxt->sax->error(ctxt->userData, 5236 "Misplaced DOCTYPE declaration\n"); 5237 ctxt->wellFormed = 0; 5238 docbParseDocTypeDecl(ctxt); 5239 } else if ((cur == '<') && (next == '!') && 5240 (in->cur[2] == '-') && (in->cur[3] == '-')) { 5241 if ((!terminate) && 5242 (docbParseLookupSequence(ctxt, '-', '-', '>') < 0)) 5243 goto done; 5244#ifdef DEBUG_PUSH 5245 xmlGenericError(xmlGenericErrorContext, 5246 "HPP: Parsing Comment\n"); 5247#endif 5248 docbParseComment(ctxt); 5249 ctxt->instate = XML_PARSER_CONTENT; 5250 } else if ((cur == '<') && (next == '!') && (avail < 4)) { 5251 goto done; 5252 } else if ((cur == '<') && (next == '/')) { 5253 ctxt->instate = XML_PARSER_END_TAG; 5254 ctxt->checkIndex = 0; 5255#ifdef DEBUG_PUSH 5256 xmlGenericError(xmlGenericErrorContext, 5257 "HPP: entering END_TAG\n"); 5258#endif 5259 break; 5260 } else if (cur == '<') { 5261 ctxt->instate = XML_PARSER_START_TAG; 5262 ctxt->checkIndex = 0; 5263#ifdef DEBUG_PUSH 5264 xmlGenericError(xmlGenericErrorContext, 5265 "HPP: entering START_TAG\n"); 5266#endif 5267 break; 5268 } else if (cur == '&') { 5269 if ((!terminate) && 5270 (docbParseLookupSequence(ctxt, ';', 0, 0) < 0)) 5271 goto done; 5272#ifdef DEBUG_PUSH 5273 xmlGenericError(xmlGenericErrorContext, 5274 "HPP: Parsing Reference\n"); 5275#endif 5276 /* TODO: check generation of subtrees if noent !!! */ 5277 docbParseReference(ctxt); 5278 } else { 5279 /* TODO Avoid the extra copy, handle directly !!!!!! */ 5280 /* 5281 * Goal of the following test is : 5282 * - minimize calls to the SAX 'character' callback 5283 * when they are mergeable 5284 */ 5285 if ((ctxt->inputNr == 1) && 5286 (avail < DOCB_PARSER_BIG_BUFFER_SIZE)) { 5287 if ((!terminate) && 5288 (docbParseLookupSequence(ctxt, '<', 0, 0) < 0)) 5289 goto done; 5290 } 5291 ctxt->checkIndex = 0; 5292#ifdef DEBUG_PUSH 5293 xmlGenericError(xmlGenericErrorContext, 5294 "HPP: Parsing char data\n"); 5295#endif 5296 docbParseCharData(ctxt); 5297 } 5298 if (cons == ctxt->nbChars) { 5299 if (ctxt->node != NULL) { 5300 if ((ctxt->sax != NULL) && (ctxt->sax->error != NULL)) 5301 ctxt->sax->error(ctxt->userData, 5302 "detected an error in element content\n"); 5303 ctxt->wellFormed = 0; 5304 NEXT; 5305 } 5306 break; 5307 } 5308 5309 break; 5310 } 5311 case XML_PARSER_END_TAG: 5312 if (avail < 2) 5313 goto done; 5314 if ((!terminate) && 5315 (docbParseLookupSequence(ctxt, '>', 0, 0) < 0)) 5316 goto done; 5317 docbParseEndTag(ctxt); 5318 if (ctxt->nameNr == 0) { 5319 ctxt->instate = XML_PARSER_EPILOG; 5320 } else { 5321 ctxt->instate = XML_PARSER_CONTENT; 5322 } 5323 ctxt->checkIndex = 0; 5324#ifdef DEBUG_PUSH 5325 xmlGenericError(xmlGenericErrorContext, 5326 "HPP: entering CONTENT\n"); 5327#endif 5328 break; 5329 case XML_PARSER_CDATA_SECTION: 5330 xmlGenericError(xmlGenericErrorContext, 5331 "HPP: internal error, state == CDATA\n"); 5332 ctxt->instate = XML_PARSER_CONTENT; 5333 ctxt->checkIndex = 0; 5334#ifdef DEBUG_PUSH 5335 xmlGenericError(xmlGenericErrorContext, 5336 "HPP: entering CONTENT\n"); 5337#endif 5338 break; 5339 case XML_PARSER_DTD: 5340 xmlGenericError(xmlGenericErrorContext, 5341 "HPP: internal error, state == DTD\n"); 5342 ctxt->instate = XML_PARSER_CONTENT; 5343 ctxt->checkIndex = 0; 5344#ifdef DEBUG_PUSH 5345 xmlGenericError(xmlGenericErrorContext, 5346 "HPP: entering CONTENT\n"); 5347#endif 5348 break; 5349 case XML_PARSER_COMMENT: 5350 xmlGenericError(xmlGenericErrorContext, 5351 "HPP: internal error, state == COMMENT\n"); 5352 ctxt->instate = XML_PARSER_CONTENT; 5353 ctxt->checkIndex = 0; 5354#ifdef DEBUG_PUSH 5355 xmlGenericError(xmlGenericErrorContext, 5356 "HPP: entering CONTENT\n"); 5357#endif 5358 break; 5359 case XML_PARSER_PI: 5360 xmlGenericError(xmlGenericErrorContext, 5361 "HPP: internal error, state == PI\n"); 5362 ctxt->instate = XML_PARSER_CONTENT; 5363 ctxt->checkIndex = 0; 5364#ifdef DEBUG_PUSH 5365 xmlGenericError(xmlGenericErrorContext, 5366 "HPP: entering CONTENT\n"); 5367#endif 5368 break; 5369 case XML_PARSER_ENTITY_DECL: 5370 xmlGenericError(xmlGenericErrorContext, 5371 "HPP: internal error, state == ENTITY_DECL\n"); 5372 ctxt->instate = XML_PARSER_CONTENT; 5373 ctxt->checkIndex = 0; 5374#ifdef DEBUG_PUSH 5375 xmlGenericError(xmlGenericErrorContext, 5376 "HPP: entering CONTENT\n"); 5377#endif 5378 break; 5379 case XML_PARSER_ENTITY_VALUE: 5380 xmlGenericError(xmlGenericErrorContext, 5381 "HPP: internal error, state == ENTITY_VALUE\n"); 5382 ctxt->instate = XML_PARSER_CONTENT; 5383 ctxt->checkIndex = 0; 5384#ifdef DEBUG_PUSH 5385 xmlGenericError(xmlGenericErrorContext, 5386 "HPP: entering DTD\n"); 5387#endif 5388 break; 5389 case XML_PARSER_ATTRIBUTE_VALUE: 5390 xmlGenericError(xmlGenericErrorContext, 5391 "HPP: internal error, state == ATTRIBUTE_VALUE\n"); 5392 ctxt->instate = XML_PARSER_START_TAG; 5393 ctxt->checkIndex = 0; 5394#ifdef DEBUG_PUSH 5395 xmlGenericError(xmlGenericErrorContext, 5396 "HPP: entering START_TAG\n"); 5397#endif 5398 break; 5399 case XML_PARSER_SYSTEM_LITERAL: 5400 xmlGenericError(xmlGenericErrorContext, 5401 "HPP: internal error, state == XML_PARSER_SYSTEM_LITERAL\n"); 5402 ctxt->instate = XML_PARSER_CONTENT; 5403 ctxt->checkIndex = 0; 5404#ifdef DEBUG_PUSH 5405 xmlGenericError(xmlGenericErrorContext, 5406 "HPP: entering CONTENT\n"); 5407#endif 5408 break; 5409 5410 case XML_PARSER_IGNORE: 5411 xmlGenericError(xmlGenericErrorContext, 5412 "HPP: internal error, state == XML_PARSER_IGNORE\n"); 5413 ctxt->instate = XML_PARSER_CONTENT; 5414 ctxt->checkIndex = 0; 5415#ifdef DEBUG_PUSH 5416 xmlGenericError(xmlGenericErrorContext, 5417 "HPP: entering CONTENT\n"); 5418#endif 5419 break; 5420 } 5421 } 5422done: 5423 if ((avail == 0) && (terminate)) { 5424 docbAutoClose(ctxt, NULL); 5425 if ((ctxt->nameNr == 0) && (ctxt->instate != XML_PARSER_EOF)) { 5426 /* 5427 * SAX: end of the document processing. 5428 */ 5429 ctxt->instate = XML_PARSER_EOF; 5430 if ((ctxt->sax) && (ctxt->sax->endDocument != NULL)) 5431 ctxt->sax->endDocument(ctxt->userData); 5432 } 5433 } 5434 if ((ctxt->myDoc != NULL) && 5435 ((terminate) || (ctxt->instate == XML_PARSER_EOF) || 5436 (ctxt->instate == XML_PARSER_EPILOG))) { 5437 xmlDtdPtr dtd; 5438 dtd = ctxt->myDoc->intSubset; 5439 if (dtd == NULL) 5440 ctxt->myDoc->intSubset = 5441 xmlCreateIntSubset(ctxt->myDoc, BAD_CAST "SGML", 5442 BAD_CAST "-//W3C//DTD SGML 4.0 Transitional//EN", 5443 BAD_CAST "http://www.w3.org/TR/REC-docbook/loose.dtd"); 5444 } 5445#ifdef DEBUG_PUSH 5446 xmlGenericError(xmlGenericErrorContext, "HPP: done %d\n", ret); 5447#endif 5448 return(ret); 5449} 5450 5451/** 5452 * docbParseChunk: 5453 * @ctxt: an XML parser context 5454 * @chunk: an char array 5455 * @size: the size in byte of the chunk 5456 * @terminate: last chunk indicator 5457 * 5458 * Parse a Chunk of memory 5459 * 5460 * Returns zero if no error, the xmlParserErrors otherwise. 5461 */ 5462int 5463docbParseChunk(docbParserCtxtPtr ctxt, const char *chunk, int size, 5464 int terminate) { 5465 if ((size > 0) && (chunk != NULL) && (ctxt->input != NULL) && 5466 (ctxt->input->buf != NULL) && (ctxt->instate != XML_PARSER_EOF)) { 5467 int base = ctxt->input->base - ctxt->input->buf->buffer->content; 5468 int cur = ctxt->input->cur - ctxt->input->base; 5469 5470 xmlParserInputBufferPush(ctxt->input->buf, size, chunk); 5471 ctxt->input->base = ctxt->input->buf->buffer->content + base; 5472 ctxt->input->cur = ctxt->input->base + cur; 5473#ifdef DEBUG_PUSH 5474 xmlGenericError(xmlGenericErrorContext, "HPP: pushed %d\n", size); 5475#endif 5476 5477 if ((terminate) || (ctxt->input->buf->buffer->use > 80)) 5478 docbParseTryOrFinish(ctxt, terminate); 5479 } else if (ctxt->instate != XML_PARSER_EOF) { 5480 xmlParserInputBufferPush(ctxt->input->buf, 0, ""); 5481 docbParseTryOrFinish(ctxt, terminate); 5482 } 5483 if (terminate) { 5484 if ((ctxt->instate != XML_PARSER_EOF) && 5485 (ctxt->instate != XML_PARSER_EPILOG) && 5486 (ctxt->instate != XML_PARSER_MISC)) { 5487 ctxt->errNo = XML_ERR_DOCUMENT_END; 5488 if ((ctxt->sax != NULL) && (ctxt->sax->error != NULL)) 5489 ctxt->sax->error(ctxt->userData, 5490 "Extra content at the end of the document\n"); 5491 ctxt->wellFormed = 0; 5492 } 5493 if (ctxt->instate != XML_PARSER_EOF) { 5494 if ((ctxt->sax) && (ctxt->sax->endDocument != NULL)) 5495 ctxt->sax->endDocument(ctxt->userData); 5496 } 5497 ctxt->instate = XML_PARSER_EOF; 5498 } 5499 return((xmlParserErrors) ctxt->errNo); 5500} 5501 5502/************************************************************************ 5503 * * 5504 * User entry points * 5505 * * 5506 ************************************************************************/ 5507 5508/** 5509 * docbCreatePushParserCtxt : 5510 * @sax: a SAX handler 5511 * @user_data: The user data returned on SAX callbacks 5512 * @chunk: a pointer to an array of chars 5513 * @size: number of chars in the array 5514 * @filename: an optional file name or URI 5515 * @enc: an optional encoding 5516 * 5517 * Create a parser context for using the DocBook SGML parser in push mode 5518 * To allow content encoding detection, @size should be >= 4 5519 * The value of @filename is used for fetching external entities 5520 * and error/warning reports. 5521 * 5522 * Returns the new parser context or NULL 5523 */ 5524docbParserCtxtPtr 5525docbCreatePushParserCtxt(docbSAXHandlerPtr sax, void *user_data, 5526 const char *chunk, int size, const char *filename, 5527 xmlCharEncoding enc) { 5528 docbParserCtxtPtr ctxt; 5529 docbParserInputPtr inputStream; 5530 xmlParserInputBufferPtr buf; 5531 5532 buf = xmlAllocParserInputBuffer(enc); 5533 if (buf == NULL) return(NULL); 5534 5535 ctxt = (docbParserCtxtPtr) xmlMalloc(sizeof(docbParserCtxt)); 5536 if (ctxt == NULL) { 5537 xmlFree(buf); 5538 return(NULL); 5539 } 5540 memset(ctxt, 0, sizeof(docbParserCtxt)); 5541 docbInitParserCtxt(ctxt); 5542 if (sax != NULL) { 5543 if (ctxt->sax != &docbDefaultSAXHandler) 5544 xmlFree(ctxt->sax); 5545 ctxt->sax = (docbSAXHandlerPtr) xmlMalloc(sizeof(docbSAXHandler)); 5546 if (ctxt->sax == NULL) { 5547 xmlFree(buf); 5548 xmlFree(ctxt); 5549 return(NULL); 5550 } 5551 memcpy(ctxt->sax, sax, sizeof(docbSAXHandler)); 5552 if (user_data != NULL) 5553 ctxt->userData = user_data; 5554 } 5555 if (filename == NULL) { 5556 ctxt->directory = NULL; 5557 } else { 5558 ctxt->directory = xmlParserGetDirectory(filename); 5559 } 5560 5561 inputStream = docbNewInputStream(ctxt); 5562 if (inputStream == NULL) { 5563 xmlFreeParserCtxt(ctxt); 5564 return(NULL); 5565 } 5566 5567 if (filename == NULL) 5568 inputStream->filename = NULL; 5569 else 5570 inputStream->filename = xmlMemStrdup(filename); 5571 inputStream->buf = buf; 5572 inputStream->base = inputStream->buf->buffer->content; 5573 inputStream->cur = inputStream->buf->buffer->content; 5574 5575 inputPush(ctxt, inputStream); 5576 5577 if ((size > 0) && (chunk != NULL) && (ctxt->input != NULL) && 5578 (ctxt->input->buf != NULL)) { 5579 xmlParserInputBufferPush(ctxt->input->buf, size, chunk); 5580#ifdef DEBUG_PUSH 5581 xmlGenericError(xmlGenericErrorContext, "HPP: pushed %d\n", size); 5582#endif 5583 } 5584 5585 return(ctxt); 5586} 5587 5588/** 5589 * docbSAXParseDoc : 5590 * @cur: a pointer to an array of xmlChar 5591 * @encoding: a free form C string describing the SGML document encoding, or NULL 5592 * @sax: the SAX handler block 5593 * @userData: if using SAX, this pointer will be provided on callbacks. 5594 * 5595 * parse an SGML in-memory document and build a tree. 5596 * It use the given SAX function block to handle the parsing callback. 5597 * If sax is NULL, fallback to the default DOM tree building routines. 5598 * 5599 * Returns the resulting document tree 5600 */ 5601 5602docbDocPtr 5603docbSAXParseDoc(xmlChar *cur, const char *encoding, docbSAXHandlerPtr sax, void *userData) { 5604 docbDocPtr ret; 5605 docbParserCtxtPtr ctxt; 5606 5607 if (cur == NULL) return(NULL); 5608 5609 5610 ctxt = docbCreateDocParserCtxt(cur, encoding); 5611 if (ctxt == NULL) return(NULL); 5612 if (sax != NULL) { 5613 ctxt->sax = sax; 5614 ctxt->userData = userData; 5615 } 5616 5617 docbParseDocument(ctxt); 5618 ret = ctxt->myDoc; 5619 if (sax != NULL) { 5620 ctxt->sax = NULL; 5621 ctxt->userData = NULL; 5622 } 5623 docbFreeParserCtxt(ctxt); 5624 5625 return(ret); 5626} 5627 5628/** 5629 * docbParseDoc : 5630 * @cur: a pointer to an array of xmlChar 5631 * @encoding: a free form C string describing the SGML document encoding, or NULL 5632 * 5633 * parse an SGML in-memory document and build a tree. 5634 * 5635 * Returns the resulting document tree 5636 */ 5637 5638docbDocPtr 5639docbParseDoc(xmlChar *cur, const char *encoding) { 5640 return(docbSAXParseDoc(cur, encoding, NULL, NULL)); 5641} 5642 5643 5644/** 5645 * docbCreateFileParserCtxt : 5646 * @filename: the filename 5647 * @encoding: a free form C string describing the SGML document encoding, or NULL 5648 * 5649 * Create a parser context for a file content. 5650 * Automatic support for ZLIB/Compress compressed document is provided 5651 * by default if found at compile-time. 5652 * 5653 * Returns the new parser context or NULL 5654 */ 5655docbParserCtxtPtr 5656docbCreateFileParserCtxt(const char *filename, const char *encoding) 5657{ 5658 docbParserCtxtPtr ctxt; 5659 docbParserInputPtr inputStream; 5660 xmlParserInputBufferPtr buf; 5661 /* sgmlCharEncoding enc; */ 5662 5663 buf = xmlParserInputBufferCreateFilename(filename, XML_CHAR_ENCODING_NONE); 5664 if (buf == NULL) return(NULL); 5665 5666 ctxt = (docbParserCtxtPtr) xmlMalloc(sizeof(docbParserCtxt)); 5667 if (ctxt == NULL) { 5668 perror("malloc"); 5669 return(NULL); 5670 } 5671 memset(ctxt, 0, sizeof(docbParserCtxt)); 5672 docbInitParserCtxt(ctxt); 5673 inputStream = (docbParserInputPtr) xmlMalloc(sizeof(docbParserInput)); 5674 if (inputStream == NULL) { 5675 perror("malloc"); 5676 xmlFree(ctxt); 5677 return(NULL); 5678 } 5679 memset(inputStream, 0, sizeof(docbParserInput)); 5680 5681 inputStream->filename = xmlMemStrdup(filename); 5682 inputStream->line = 1; 5683 inputStream->col = 1; 5684 inputStream->buf = buf; 5685 inputStream->directory = NULL; 5686 5687 inputStream->base = inputStream->buf->buffer->content; 5688 inputStream->cur = inputStream->buf->buffer->content; 5689 inputStream->free = NULL; 5690 5691 inputPush(ctxt, inputStream); 5692 return(ctxt); 5693} 5694 5695/** 5696 * docbSAXParseFile : 5697 * @filename: the filename 5698 * @encoding: a free form C string describing the SGML document encoding, or NULL 5699 * @sax: the SAX handler block 5700 * @userData: if using SAX, this pointer will be provided on callbacks. 5701 * 5702 * parse an SGML file and build a tree. Automatic support for ZLIB/Compress 5703 * compressed document is provided by default if found at compile-time. 5704 * It use the given SAX function block to handle the parsing callback. 5705 * If sax is NULL, fallback to the default DOM tree building routines. 5706 * 5707 * Returns the resulting document tree 5708 */ 5709 5710docbDocPtr 5711docbSAXParseFile(const char *filename, const char *encoding, docbSAXHandlerPtr sax, 5712 void *userData) { 5713 docbDocPtr ret; 5714 docbParserCtxtPtr ctxt; 5715 docbSAXHandlerPtr oldsax = NULL; 5716 5717 ctxt = docbCreateFileParserCtxt(filename, encoding); 5718 if (ctxt == NULL) return(NULL); 5719 if (sax != NULL) { 5720 oldsax = ctxt->sax; 5721 ctxt->sax = sax; 5722 ctxt->userData = userData; 5723 } 5724 5725 docbParseDocument(ctxt); 5726 5727 ret = ctxt->myDoc; 5728 if (sax != NULL) { 5729 ctxt->sax = oldsax; 5730 ctxt->userData = NULL; 5731 } 5732 docbFreeParserCtxt(ctxt); 5733 5734 return(ret); 5735} 5736 5737/** 5738 * docbParseFile : 5739 * @filename: the filename 5740 * @encoding: a free form C string describing document encoding, or NULL 5741 * 5742 * parse a Docbook SGML file and build a tree. Automatic support for 5743 * ZLIB/Compress compressed document is provided by default if found 5744 * at compile-time. 5745 * 5746 * Returns the resulting document tree 5747 */ 5748 5749docbDocPtr 5750docbParseFile(const char *filename, const char *encoding) { 5751 return(docbSAXParseFile(filename, encoding, NULL, NULL)); 5752} 5753 5754#endif /* LIBXML_DOCB_ENABLED */ 5755