parser.c 283 KB
Newer Older
1 2 3 4 5 6 7 8 9 10 11 12 13 14
/*
 * parser.c : an XML 1.0 parser, namespaces and validity support are mostly
 *            implemented on top of the SAX interfaces
 *
 * References:
 *   The XML specification:
 *     http://www.w3.org/TR/REC-xml
 *   Original 1.0 version:
 *     http://www.w3.org/TR/1998/REC-xml-19980210
 *   XML second edition working draft
 *     http://www.w3.org/TR/2000/WD-xml-2e-20000814
 *
 * Okay this is a big file, the parser core is around 7000 lines, then it
 * is followed by the progressive parser top routines, then the various
15
 * high level APIs to call the parser and a few miscellaneous functions.
16 17 18 19 20 21 22 23 24
 * A number of helper functions and deprecated ones have been moved to
 * parserInternals.c to reduce this file size.
 * As much as possible the functions are associated with their relative
 * production in the XML specification. A few productions defining the
 * different ranges of character are actually implanted either in 
 * parserInternals.h or parserInternals.c
 * The DOM tree build is realized from the default SAX callbacks in
 * the module SAX.c.
 * The routines doing the validation checks are in valid.c and called either
25
 * from the SAX callbacks or as standalone functions using a preparsed
26 27 28 29
 * document.
 *
 * See Copyright for the status of this software.
 *
30
 * daniel@veillard.com
31 32
 */

Bjorn Reese's avatar
Bjorn Reese committed
33 34
#include "libxml.h"

35
#if defined(WIN32) && !defined (__CYGWIN__)
36 37 38 39 40 41 42 43
#define XML_DIR_SEP '\\'
#else
#define XML_DIR_SEP '/'
#endif

#include <stdlib.h>
#include <string.h>
#include <libxml/xmlmemory.h>
44 45
#include <libxml/threads.h>
#include <libxml/globals.h>
46 47 48 49 50 51 52 53 54
#include <libxml/tree.h>
#include <libxml/parser.h>
#include <libxml/parserInternals.h>
#include <libxml/valid.h>
#include <libxml/entities.h>
#include <libxml/xmlerror.h>
#include <libxml/encoding.h>
#include <libxml/xmlIO.h>
#include <libxml/uri.h>
55 56 57
#ifdef LIBXML_CATALOG_ENABLED
#include <libxml/catalog.h>
#endif
58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78

#ifdef HAVE_CTYPE_H
#include <ctype.h>
#endif
#ifdef HAVE_STDLIB_H
#include <stdlib.h>
#endif
#ifdef HAVE_SYS_STAT_H
#include <sys/stat.h>
#endif
#ifdef HAVE_FCNTL_H
#include <fcntl.h>
#endif
#ifdef HAVE_UNISTD_H
#include <unistd.h>
#endif
#ifdef HAVE_ZLIB_H
#include <zlib.h>
#endif


79
#define XML_PARSER_BIG_BUFFER_SIZE 300
80 81
#define XML_PARSER_BUFFER_SIZE 100

82 83
#define SAX_COMPAT_MODE BAD_CAST "SAX compatibility mode document"

84 85 86 87
/*
 * List of XML prefixed PI allowed by W3C specs
 */

88
static const char *xmlW3CPIs[] = {
89 90 91 92 93 94 95 96
    "xml-stylesheet",
    NULL
};

/* DEPR void xmlParserHandleReference(xmlParserCtxtPtr ctxt); */
xmlEntityPtr xmlParseStringPEReference(xmlParserCtxtPtr ctxt,
                                       const xmlChar **str);

97
static int
98 99
xmlParseExternalEntityPrivate(xmlDocPtr doc, xmlParserCtxtPtr oldctxt,
	              xmlSAXHandlerPtr sax,
100
		      void *user_data, int depth, const xmlChar *URL,
101
		      const xmlChar *ID, xmlNodePtr *list);
102

103 104 105 106
static void
xmlAddEntityReference(xmlEntityPtr ent, xmlNodePtr firstNode,
                      xmlNodePtr lastNode);

107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148
/************************************************************************
 *									*
 * 		Parser stacks related functions and macros		*
 *									*
 ************************************************************************/

xmlEntityPtr xmlParseStringEntityRef(xmlParserCtxtPtr ctxt,
                                     const xmlChar ** str);

/*
 * Generic function for accessing stacks in the Parser Context
 */

#define PUSH_AND_POP(scope, type, name)					\
scope int name##Push(xmlParserCtxtPtr ctxt, type value) {		\
    if (ctxt->name##Nr >= ctxt->name##Max) {				\
	ctxt->name##Max *= 2;						\
        ctxt->name##Tab = (type *) xmlRealloc(ctxt->name##Tab,		\
	             ctxt->name##Max * sizeof(ctxt->name##Tab[0]));	\
        if (ctxt->name##Tab == NULL) {					\
	    xmlGenericError(xmlGenericErrorContext,			\
		    "realloc failed !\n");				\
	    return(0);							\
	}								\
    }									\
    ctxt->name##Tab[ctxt->name##Nr] = value;				\
    ctxt->name = value;							\
    return(ctxt->name##Nr++);						\
}									\
scope type name##Pop(xmlParserCtxtPtr ctxt) {				\
    type ret;								\
    if (ctxt->name##Nr <= 0) return(0);					\
    ctxt->name##Nr--;							\
    if (ctxt->name##Nr > 0)						\
	ctxt->name = ctxt->name##Tab[ctxt->name##Nr - 1];		\
    else								\
        ctxt->name = NULL;						\
    ret = ctxt->name##Tab[ctxt->name##Nr];				\
    ctxt->name##Tab[ctxt->name##Nr] = 0;				\
    return(ret);							\
}									\

149 150 151 152 153 154 155 156 157 158 159
/**
 * inputPop:
 * @ctxt: an XML parser context
 *
 * Pops the top parser input from the input stack
 *
 * Returns the input just removed
 */
/**
 * inputPush:
 * @ctxt:  an XML parser context
160
 * @value:  the parser input
161 162
 *
 * Pushes a new parser input on top of the input stack
163 164
 *
 * Returns 0 in case of error, the index in the stack otherwise
165 166 167 168 169 170 171 172 173 174 175 176
 */
/**
 * namePop:
 * @ctxt: an XML parser context
 *
 * Pops the top element name from the name stack
 *
 * Returns the name just removed
 */
/**
 * namePush:
 * @ctxt:  an XML parser context
177
 * @value:  the element name
178 179
 *
 * Pushes a new element name on top of the name stack
180 181
 *
 * Returns 0 in case of error, the index in the stack otherwise
182 183 184 185 186 187 188 189 190 191 192 193
 */
/**
 * nodePop:
 * @ctxt: an XML parser context
 *
 * Pops the top element node from the node stack
 *
 * Returns the node just removed
 */
/**
 * nodePush:
 * @ctxt:  an XML parser context
194
 * @value:  the element node
195 196
 *
 * Pushes a new element node on top of the node stack
197 198
 *
 * Returns 0 in case of error, the index in the stack otherwise
199
 */
200 201 202 203 204 205 206
/*
 * Those macros actually generate the functions
 */
PUSH_AND_POP(extern, xmlParserInputPtr, input)
PUSH_AND_POP(extern, xmlNodePtr, node)
PUSH_AND_POP(extern, xmlChar*, name)

207
static int spacePush(xmlParserCtxtPtr ctxt, int val) {
208 209 210 211 212 213 214 215 216 217 218 219 220 221 222
    if (ctxt->spaceNr >= ctxt->spaceMax) {
	ctxt->spaceMax *= 2;
        ctxt->spaceTab = (int *) xmlRealloc(ctxt->spaceTab,
	             ctxt->spaceMax * sizeof(ctxt->spaceTab[0]));
        if (ctxt->spaceTab == NULL) {
	    xmlGenericError(xmlGenericErrorContext,
		    "realloc failed !\n");
	    return(0);
	}
    }
    ctxt->spaceTab[ctxt->spaceNr] = val;
    ctxt->space = &ctxt->spaceTab[ctxt->spaceNr];
    return(ctxt->spaceNr++);
}

223
static int spacePop(xmlParserCtxtPtr ctxt) {
224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260
    int ret;
    if (ctxt->spaceNr <= 0) return(0);
    ctxt->spaceNr--;
    if (ctxt->spaceNr > 0)
	ctxt->space = &ctxt->spaceTab[ctxt->spaceNr - 1];
    else
        ctxt->space = NULL;
    ret = ctxt->spaceTab[ctxt->spaceNr];
    ctxt->spaceTab[ctxt->spaceNr] = -1;
    return(ret);
}

/*
 * Macros for accessing the content. Those should be used only by the parser,
 * and not exported.
 *
 * Dirty macros, i.e. one often need to make assumption on the context to
 * use them
 *
 *   CUR_PTR return the current pointer to the xmlChar to be parsed.
 *           To be used with extreme caution since operations consuming
 *           characters may move the input buffer to a different location !
 *   CUR     returns the current xmlChar value, i.e. a 8 bit value if compiled
 *           This should be used internally by the parser
 *           only to compare to ASCII values otherwise it would break when
 *           running with UTF-8 encoding.
 *   RAW     same as CUR but in the input buffer, bypass any token
 *           extraction that may have been done
 *   NXT(n)  returns the n'th next xmlChar. Same as CUR is should be used only
 *           to compare on ASCII based substring.
 *   SKIP(n) Skip n xmlChar, and must also be used only to skip ASCII defined
 *           strings within the parser.
 *
 * Clean macros, not dependent of an ASCII context, expect UTF-8 encoding
 *
 *   NEXT    Skip to the next character, this does the proper decoding
 *           in UTF-8 mode. It also pop-up unfinished entities on the fly.
261
 *   NEXTL(l) Skip l xmlChar in the input buffer
262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282
 *   CUR_CHAR(l) returns the current unicode character (int), set l
 *           to the number of xmlChars used for the encoding [0-5].
 *   CUR_SCHAR  same but operate on a string instead of the context
 *   COPY_BUF  copy the current unicode char to the target buffer, increment
 *            the index
 *   GROW, SHRINK  handling of input buffers
 */

#define RAW (ctxt->token ? -1 : (*ctxt->input->cur))
#define CUR (ctxt->token ? ctxt->token : (*ctxt->input->cur))
#define NXT(val) ctxt->input->cur[(val)]
#define CUR_PTR ctxt->input->cur

#define SKIP(val) do {							\
    ctxt->nbChars += (val),ctxt->input->cur += (val);			\
    if (*ctxt->input->cur == '%') xmlParserHandlePEReference(ctxt);	\
    if ((*ctxt->input->cur == 0) &&					\
        (xmlParserInputGrow(ctxt->input, INPUT_CHUNK) <= 0))		\
	    xmlPopInput(ctxt);						\
  } while (0)

283
#define SHRINK if (ctxt->input->cur - ctxt->input->base > INPUT_CHUNK) {\
284 285 286 287
    xmlParserInputShrink(ctxt->input);					\
    if ((*ctxt->input->cur == 0) &&					\
        (xmlParserInputGrow(ctxt->input, INPUT_CHUNK) <= 0))		\
	    xmlPopInput(ctxt);						\
288
  }
289

290
#define GROW if (ctxt->input->end - ctxt->input->cur < INPUT_CHUNK) {	\
291 292 293 294
    xmlParserInputGrow(ctxt->input, INPUT_CHUNK);			\
    if ((*ctxt->input->cur == 0) &&					\
        (xmlParserInputGrow(ctxt->input, INPUT_CHUNK) <= 0))		\
	    xmlPopInput(ctxt);						\
295
  }
296 297 298 299 300

#define SKIP_BLANKS xmlSkipBlankChars(ctxt)

#define NEXT xmlNextChar(ctxt)

301 302 303 304 305 306 307
#define NEXT1 {								\
	ctxt->input->cur++;						\
	ctxt->nbChars++;						\
	if (*ctxt->input->cur == 0)					\
	    xmlParserInputGrow(ctxt->input, INPUT_CHUNK);		\
    }

308 309 310 311 312 313 314 315 316 317 318 319 320
#define NEXTL(l) do {							\
    if (*(ctxt->input->cur) == '\n') {					\
	ctxt->input->line++; ctxt->input->col = 1;			\
    } else ctxt->input->col++;						\
    ctxt->token = 0; ctxt->input->cur += l;				\
    if (*ctxt->input->cur == '%') xmlParserHandlePEReference(ctxt);	\
  } while (0)

#define CUR_CHAR(l) xmlCurrentChar(ctxt, &l)
#define CUR_SCHAR(s, l) xmlStringCurrentChar(ctxt, s, &l)

#define COPY_BUF(l,b,i,v)						\
    if (l == 1) b[i++] = (xmlChar) v;					\
321
    else i += xmlCopyCharMultiByte(&b[i],v)
322 323 324 325 326 327 328 329 330 331 332 333 334

/**
 * xmlSkipBlankChars:
 * @ctxt:  the XML parser context
 *
 * skip all blanks character found at that point in the input streams.
 * It pops up finished entities in the process if allowable at that point.
 *
 * Returns the number of space chars skipped
 */

int
xmlSkipBlankChars(xmlParserCtxtPtr ctxt) {
335
    int res = 0;
336

337 338 339 340 341 342
    if (ctxt->token != 0) {
	if (!IS_BLANK(ctxt->token))
	    return(0);
	ctxt->token = 0;
	res++;
    }
343 344 345 346
    /*
     * It's Okay to use CUR/NEXT here since all the blanks are on
     * the ASCII range.
     */
347 348 349 350 351 352 353 354 355 356 357
    if ((ctxt->inputNr == 1) && (ctxt->instate != XML_PARSER_DTD)) {
	const xmlChar *cur;
	/*
	 * if we are in the document content, go really fast
	 */
	cur = ctxt->input->cur;
	while (IS_BLANK(*cur)) {
	    if (*cur == '\n') {
		ctxt->input->line++; ctxt->input->col = 1;
	    }
	    cur++;
358
	    res++;
359 360 361 362 363
	    if (*cur == 0) {
		ctxt->input->cur = cur;
		xmlParserInputGrow(ctxt->input, INPUT_CHUNK);
		cur = ctxt->input->cur;
	    }
364
	}
365 366 367 368
	ctxt->input->cur = cur;
    } else {
	int cur;
	do {
369
	    cur = CUR;
370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385
	    while (IS_BLANK(cur)) { /* CHECKED tstblanks.xml */
		NEXT;
		cur = CUR;
		res++;
	    }
	    while ((cur == 0) && (ctxt->inputNr > 1) &&
		   (ctxt->instate != XML_PARSER_COMMENT)) {
		xmlPopInput(ctxt);
		cur = CUR;
	    }
	    /*
	     * Need to handle support of entities branching here
	     */
	    if (*ctxt->input->cur == '%') xmlParserHandlePEReference(ctxt);
	} while (IS_BLANK(cur)); /* CHECKED tstblanks.xml */
    }
386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457
    return(res);
}

/************************************************************************
 *									*
 *		Commodity functions to handle entities			*
 *									*
 ************************************************************************/

/**
 * xmlPopInput:
 * @ctxt:  an XML parser context
 *
 * xmlPopInput: the current input pointed by ctxt->input came to an end
 *          pop it and return the next char.
 *
 * Returns the current xmlChar in the parser context
 */
xmlChar
xmlPopInput(xmlParserCtxtPtr ctxt) {
    if (ctxt->inputNr == 1) return(0); /* End of main Input */
    if (xmlParserDebugEntities)
	xmlGenericError(xmlGenericErrorContext,
		"Popping input %d\n", ctxt->inputNr);
    xmlFreeInputStream(inputPop(ctxt));
    if ((*ctxt->input->cur == 0) &&
        (xmlParserInputGrow(ctxt->input, INPUT_CHUNK) <= 0))
	    return(xmlPopInput(ctxt));
    return(CUR);
}

/**
 * xmlPushInput:
 * @ctxt:  an XML parser context
 * @input:  an XML parser input fragment (entity, XML fragment ...).
 *
 * xmlPushInput: switch to a new input stream which is stacked on top
 *               of the previous one(s).
 */
void
xmlPushInput(xmlParserCtxtPtr ctxt, xmlParserInputPtr input) {
    if (input == NULL) return;

    if (xmlParserDebugEntities) {
	if ((ctxt->input != NULL) && (ctxt->input->filename))
	    xmlGenericError(xmlGenericErrorContext,
		    "%s(%d): ", ctxt->input->filename,
		    ctxt->input->line);
	xmlGenericError(xmlGenericErrorContext,
		"Pushing input %d : %.30s\n", ctxt->inputNr+1, input->cur);
    }
    inputPush(ctxt, input);
    GROW;
}

/**
 * xmlParseCharRef:
 * @ctxt:  an XML parser context
 *
 * parse Reference declarations
 *
 * [66] CharRef ::= '&#' [0-9]+ ';' |
 *                  '&#x' [0-9a-fA-F]+ ';'
 *
 * [ WFC: Legal Character ]
 * Characters referred to using character references must match the
 * production for Char. 
 *
 * Returns the value parsed (as an int), 0 in case of error
 */
int
xmlParseCharRef(xmlParserCtxtPtr ctxt) {
458
    unsigned int val = 0;
459 460 461 462 463 464 465 466 467 468 469 470 471 472 473
    int count = 0;

    if (ctxt->token != 0) {
	val = ctxt->token;
        ctxt->token = 0;
        return(val);
    }
    /*
     * Using RAW/CUR/NEXT is okay since we are working on ASCII range here
     */
    if ((RAW == '&') && (NXT(1) == '#') &&
        (NXT(2) == 'x')) {
	SKIP(3);
	GROW;
	while (RAW != ';') { /* loop blocked by count */
474 475 476 477 478
	    if (count++ > 20) {
		count = 0;
		GROW;
	    }
	    if ((RAW >= '0') && (RAW <= '9')) 
479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505
	        val = val * 16 + (CUR - '0');
	    else if ((RAW >= 'a') && (RAW <= 'f') && (count < 20))
	        val = val * 16 + (CUR - 'a') + 10;
	    else if ((RAW >= 'A') && (RAW <= 'F') && (count < 20))
	        val = val * 16 + (CUR - 'A') + 10;
	    else {
		ctxt->errNo = XML_ERR_INVALID_HEX_CHARREF;
	        if ((ctxt->sax != NULL) && (ctxt->sax->error != NULL))
		    ctxt->sax->error(ctxt->userData, 
		         "xmlParseCharRef: invalid hexadecimal value\n");
		ctxt->wellFormed = 0;
		ctxt->disableSAX = 1;
		val = 0;
		break;
	    }
	    NEXT;
	    count++;
	}
	if (RAW == ';') {
	    /* on purpose to avoid reentrancy problems with NEXT and SKIP */
	    ctxt->nbChars ++;
	    ctxt->input->cur++;
	}
    } else if  ((RAW == '&') && (NXT(1) == '#')) {
	SKIP(2);
	GROW;
	while (RAW != ';') { /* loop blocked by count */
506 507 508 509 510
	    if (count++ > 20) {
		count = 0;
		GROW;
	    }
	    if ((RAW >= '0') && (RAW <= '9')) 
511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548
	        val = val * 10 + (CUR - '0');
	    else {
		ctxt->errNo = XML_ERR_INVALID_DEC_CHARREF;
	        if ((ctxt->sax != NULL) && (ctxt->sax->error != NULL))
		    ctxt->sax->error(ctxt->userData, 
		         "xmlParseCharRef: invalid decimal value\n");
		ctxt->wellFormed = 0;
		ctxt->disableSAX = 1;
		val = 0;
		break;
	    }
	    NEXT;
	    count++;
	}
	if (RAW == ';') {
	    /* on purpose to avoid reentrancy problems with NEXT and SKIP */
	    ctxt->nbChars ++;
	    ctxt->input->cur++;
	}
    } else {
	ctxt->errNo = XML_ERR_INVALID_CHARREF;
	if ((ctxt->sax != NULL) && (ctxt->sax->error != NULL))
	    ctxt->sax->error(ctxt->userData,
	       "xmlParseCharRef: invalid value\n");
	ctxt->wellFormed = 0;
	ctxt->disableSAX = 1;
    }

    /*
     * [ WFC: Legal Character ]
     * Characters referred to using character references must match the
     * production for Char. 
     */
    if (IS_CHAR(val)) {
        return(val);
    } else {
	ctxt->errNo = XML_ERR_INVALID_CHAR;
	if ((ctxt->sax != NULL) && (ctxt->sax->error != NULL))
549 550
	    ctxt->sax->error(ctxt->userData,
                             "xmlParseCharRef: invalid xmlChar value %d\n",
551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575
	                     val);
	ctxt->wellFormed = 0;
	ctxt->disableSAX = 1;
    }
    return(0);
}

/**
 * xmlParseStringCharRef:
 * @ctxt:  an XML parser context
 * @str:  a pointer to an index in the string
 *
 * parse Reference declarations, variant parsing from a string rather
 * than an an input flow.
 *
 * [66] CharRef ::= '&#' [0-9]+ ';' |
 *                  '&#x' [0-9a-fA-F]+ ';'
 *
 * [ WFC: Legal Character ]
 * Characters referred to using character references must match the
 * production for Char. 
 *
 * Returns the value parsed (as an int), 0 in case of error, str will be
 *         updated to the current value of the index
 */
576
static int
577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634
xmlParseStringCharRef(xmlParserCtxtPtr ctxt, const xmlChar **str) {
    const xmlChar *ptr;
    xmlChar cur;
    int val = 0;

    if ((str == NULL) || (*str == NULL)) return(0);
    ptr = *str;
    cur = *ptr;
    if ((cur == '&') && (ptr[1] == '#') && (ptr[2] == 'x')) {
	ptr += 3;
	cur = *ptr;
	while (cur != ';') { /* Non input consuming loop */
	    if ((cur >= '0') && (cur <= '9')) 
	        val = val * 16 + (cur - '0');
	    else if ((cur >= 'a') && (cur <= 'f'))
	        val = val * 16 + (cur - 'a') + 10;
	    else if ((cur >= 'A') && (cur <= 'F'))
	        val = val * 16 + (cur - 'A') + 10;
	    else {
		ctxt->errNo = XML_ERR_INVALID_HEX_CHARREF;
	        if ((ctxt->sax != NULL) && (ctxt->sax->error != NULL))
		    ctxt->sax->error(ctxt->userData, 
		         "xmlParseStringCharRef: invalid hexadecimal value\n");
		ctxt->wellFormed = 0;
		ctxt->disableSAX = 1;
		val = 0;
		break;
	    }
	    ptr++;
	    cur = *ptr;
	}
	if (cur == ';')
	    ptr++;
    } else if  ((cur == '&') && (ptr[1] == '#')){
	ptr += 2;
	cur = *ptr;
	while (cur != ';') { /* Non input consuming loops */
	    if ((cur >= '0') && (cur <= '9')) 
	        val = val * 10 + (cur - '0');
	    else {
		ctxt->errNo = XML_ERR_INVALID_DEC_CHARREF;
	        if ((ctxt->sax != NULL) && (ctxt->sax->error != NULL))
		    ctxt->sax->error(ctxt->userData, 
		         "xmlParseStringCharRef: invalid decimal value\n");
		ctxt->wellFormed = 0;
		ctxt->disableSAX = 1;
		val = 0;
		break;
	    }
	    ptr++;
	    cur = *ptr;
	}
	if (cur == ';')
	    ptr++;
    } else {
	ctxt->errNo = XML_ERR_INVALID_CHARREF;
	if ((ctxt->sax != NULL) && (ctxt->sax->error != NULL))
	    ctxt->sax->error(ctxt->userData,
635
	       "xmlParseStringCharRef: invalid value\n");
636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652
	ctxt->wellFormed = 0;
	ctxt->disableSAX = 1;
	return(0);
    }
    *str = ptr;

    /*
     * [ WFC: Legal Character ]
     * Characters referred to using character references must match the
     * production for Char. 
     */
    if (IS_CHAR(val)) {
        return(val);
    } else {
	ctxt->errNo = XML_ERR_INVALID_CHAR;
	if ((ctxt->sax != NULL) && (ctxt->sax->error != NULL))
	    ctxt->sax->error(ctxt->userData,
653
		             "xmlParseStringCharRef: invalid xmlChar value %d\n", val);
654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689
	ctxt->wellFormed = 0;
	ctxt->disableSAX = 1;
    }
    return(0);
}

/**
 * xmlParserHandlePEReference:
 * @ctxt:  the parser context
 * 
 * [69] PEReference ::= '%' Name ';'
 *
 * [ WFC: No Recursion ]
 * A parsed entity must not contain a recursive
 * reference to itself, either directly or indirectly. 
 *
 * [ WFC: Entity Declared ]
 * In a document without any DTD, a document with only an internal DTD
 * subset which contains no parameter entity references, or a document
 * with "standalone='yes'", ...  ... The declaration of a parameter
 * entity must precede any reference to it...
 *
 * [ VC: Entity Declared ]
 * In a document with an external subset or external parameter entities
 * with "standalone='no'", ...  ... The declaration of a parameter entity
 * must precede any reference to it...
 *
 * [ WFC: In DTD ]
 * Parameter-entity references may only appear in the DTD.
 * NOTE: misleading but this is handled.
 *
 * A PEReference may have been detected in the current input stream
 * the handling is done accordingly to 
 *      http://www.w3.org/TR/REC-xml#entproc
 * i.e. 
 *   - Included in literal in entity values
690
 *   - Included as Parameter Entity reference within DTDs
691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731
 */
void
xmlParserHandlePEReference(xmlParserCtxtPtr ctxt) {
    xmlChar *name;
    xmlEntityPtr entity = NULL;
    xmlParserInputPtr input;

    if (ctxt->token != 0) {
        return;
    }	
    if (RAW != '%') return;
    switch(ctxt->instate) {
	case XML_PARSER_CDATA_SECTION:
	    return;
        case XML_PARSER_COMMENT:
	    return;
	case XML_PARSER_START_TAG:
	    return;
	case XML_PARSER_END_TAG:
	    return;
        case XML_PARSER_EOF:
	    ctxt->errNo = XML_ERR_PEREF_AT_EOF;
	    if ((ctxt->sax != NULL) && (ctxt->sax->error != NULL))
	        ctxt->sax->error(ctxt->userData, "PEReference at EOF\n");
	    ctxt->wellFormed = 0;
	    ctxt->disableSAX = 1;
	    return;
        case XML_PARSER_PROLOG:
	case XML_PARSER_START:
	case XML_PARSER_MISC:
	    ctxt->errNo = XML_ERR_PEREF_IN_PROLOG;
	    if ((ctxt->sax != NULL) && (ctxt->sax->error != NULL))
	        ctxt->sax->error(ctxt->userData, "PEReference in prolog!\n");
	    ctxt->wellFormed = 0;
	    ctxt->disableSAX = 1;
	    return;
	case XML_PARSER_ENTITY_DECL:
        case XML_PARSER_CONTENT:
        case XML_PARSER_ATTRIBUTE_VALUE:
        case XML_PARSER_PI:
	case XML_PARSER_SYSTEM_LITERAL:
732
	case XML_PARSER_PUBLIC_LITERAL:
733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769
	    /* we just ignore it there */
	    return;
        case XML_PARSER_EPILOG:
	    ctxt->errNo = XML_ERR_PEREF_IN_EPILOG;
	    if ((ctxt->sax != NULL) && (ctxt->sax->error != NULL))
	        ctxt->sax->error(ctxt->userData, "PEReference in epilog!\n");
	    ctxt->wellFormed = 0;
	    ctxt->disableSAX = 1;
	    return;
	case XML_PARSER_ENTITY_VALUE:
	    /*
	     * NOTE: in the case of entity values, we don't do the
	     *       substitution here since we need the literal
	     *       entity value to be able to save the internal
	     *       subset of the document.
	     *       This will be handled by xmlStringDecodeEntities
	     */
	    return;
        case XML_PARSER_DTD:
	    /*
	     * [WFC: Well-Formedness Constraint: PEs in Internal Subset]
	     * In the internal DTD subset, parameter-entity references
	     * can occur only where markup declarations can occur, not
	     * within markup declarations.
	     * In that case this is handled in xmlParseMarkupDecl
	     */
	    if ((ctxt->external == 0) && (ctxt->inputNr == 1))
		return;
            break;
        case XML_PARSER_IGNORE:
            return;
    }

    NEXT;
    name = xmlParseName(ctxt);
    if (xmlParserDebugEntities)
	xmlGenericError(xmlGenericErrorContext,
770
		"PEReference: %s\n", name);
771 772 773
    if (name == NULL) {
        ctxt->errNo = XML_ERR_PEREF_NO_NAME;
	if ((ctxt->sax != NULL) && (ctxt->sax->error != NULL))
774
	    ctxt->sax->error(ctxt->userData, "xmlParserHandlePEReference: no name\n");
775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820
	ctxt->wellFormed = 0;
	ctxt->disableSAX = 1;
    } else {
	if (RAW == ';') {
	    NEXT;
	    if ((ctxt->sax != NULL) && (ctxt->sax->getParameterEntity != NULL))
		entity = ctxt->sax->getParameterEntity(ctxt->userData, name);
	    if (entity == NULL) {
	        
		/*
		 * [ WFC: Entity Declared ]
		 * In a document without any DTD, a document with only an
		 * internal DTD subset which contains no parameter entity
		 * references, or a document with "standalone='yes'", ...
		 * ... The declaration of a parameter entity must precede
		 * any reference to it...
		 */
		if ((ctxt->standalone == 1) ||
		    ((ctxt->hasExternalSubset == 0) &&
		     (ctxt->hasPErefs == 0))) {
		    if ((ctxt->sax != NULL) && (ctxt->sax->error != NULL))
			ctxt->sax->error(ctxt->userData,
			 "PEReference: %%%s; not found\n", name);
		    ctxt->wellFormed = 0;
		    ctxt->disableSAX = 1;
	        } else {
		    /*
		     * [ VC: Entity Declared ]
		     * In a document with an external subset or external
		     * parameter entities with "standalone='no'", ...
		     * ... The declaration of a parameter entity must precede
		     * any reference to it...
		     */
		    if ((!ctxt->disableSAX) &&
			(ctxt->validate) && (ctxt->vctxt.error != NULL)) {
			ctxt->vctxt.error(ctxt->vctxt.userData,
			     "PEReference: %%%s; not found\n", name);
		    } else if ((!ctxt->disableSAX) &&
			(ctxt->sax != NULL) && (ctxt->sax->warning != NULL))
			ctxt->sax->warning(ctxt->userData,
			 "PEReference: %%%s; not found\n", name);
		    ctxt->valid = 0;
		}
	    } else {
	        if ((entity->etype == XML_INTERNAL_PARAMETER_ENTITY) ||
		    (entity->etype == XML_EXTERNAL_PARAMETER_ENTITY)) {
821 822 823
		    xmlChar start[4];
		    xmlCharEncoding enc;

824 825 826
		    /*
		     * handle the extra spaces added before and after
		     * c.f. http://www.w3.org/TR/REC-xml#as-PE
827
		     * this is done independently.
828 829 830
		     */
		    input = xmlNewEntityInputStream(ctxt, entity);
		    xmlPushInput(ctxt, input);
831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846

		    /* 
		     * Get the 4 first bytes and decode the charset
		     * if enc != XML_CHAR_ENCODING_NONE
		     * plug some encoding conversion routines.
		     */
		    GROW
		    start[0] = RAW;
		    start[1] = NXT(1);
		    start[2] = NXT(2);
		    start[3] = NXT(3);
		    enc = xmlDetectCharEncoding(start, 4);
		    if (enc != XML_CHAR_ENCODING_NONE) {
			xmlSwitchEncoding(ctxt, enc);
		    }

847 848 849 850 851 852 853 854 855 856 857
		    if ((entity->etype == XML_EXTERNAL_PARAMETER_ENTITY) &&
			(RAW == '<') && (NXT(1) == '?') &&
			(NXT(2) == 'x') && (NXT(3) == 'm') &&
			(NXT(4) == 'l') && (IS_BLANK(NXT(5)))) {
			xmlParseTextDecl(ctxt);
		    }
		    if (ctxt->token == 0)
			ctxt->token = ' ';
		} else {
		    if ((ctxt->sax != NULL) && (ctxt->sax->error != NULL))
			ctxt->sax->error(ctxt->userData,
858
			 "xmlParserHandlePEReference: %s is not a parameter entity\n",
859 860 861 862 863 864 865 866 867
			                 name);
		    ctxt->wellFormed = 0;
		    ctxt->disableSAX = 1;
		}
	    }
	} else {
	    ctxt->errNo = XML_ERR_PEREF_SEMICOL_MISSING;
	    if ((ctxt->sax != NULL) && (ctxt->sax->error != NULL))
		ctxt->sax->error(ctxt->userData,
868
				 "xmlParserHandlePEReference: expecting ';'\n");
869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897
	    ctxt->wellFormed = 0;
	    ctxt->disableSAX = 1;
	}
	xmlFree(name);
    }
}

/*
 * Macro used to grow the current buffer.
 */
#define growBuffer(buffer) {						\
    buffer##_size *= 2;							\
    buffer = (xmlChar *)						\
    		xmlRealloc(buffer, buffer##_size * sizeof(xmlChar));	\
    if (buffer == NULL) {						\
	perror("realloc failed");					\
	return(NULL);							\
    }									\
}

/**
 * xmlStringDecodeEntities:
 * @ctxt:  the parser context
 * @str:  the input string
 * @what:  combination of XML_SUBSTITUTE_REF and XML_SUBSTITUTE_PEREF
 * @end:  an end marker xmlChar, 0 if none
 * @end2:  an end marker xmlChar, 0 if none
 * @end3:  an end marker xmlChar, 0 if none
 * 
898
 * Takes a entity string content and process to do the adequate substitutions.
899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936
 *
 * [67] Reference ::= EntityRef | CharRef
 *
 * [69] PEReference ::= '%' Name ';'
 *
 * Returns A newly allocated string with the substitution done. The caller
 *      must deallocate it !
 */
xmlChar *
xmlStringDecodeEntities(xmlParserCtxtPtr ctxt, const xmlChar *str, int what,
		        xmlChar end, xmlChar  end2, xmlChar end3) {
    xmlChar *buffer = NULL;
    int buffer_size = 0;

    xmlChar *current = NULL;
    xmlEntityPtr ent;
    int c,l;
    int nbchars = 0;

    if (str == NULL)
	return(NULL);

    if (ctxt->depth > 40) {
	ctxt->errNo = XML_ERR_ENTITY_LOOP;
	if ((ctxt->sax != NULL) && (ctxt->sax->error != NULL))
	    ctxt->sax->error(ctxt->userData,
		"Detected entity reference loop\n");
	ctxt->wellFormed = 0;
	ctxt->disableSAX = 1;
	return(NULL);
    }

    /*
     * allocate a translation buffer.
     */
    buffer_size = XML_PARSER_BIG_BUFFER_SIZE;
    buffer = (xmlChar *) xmlMalloc(buffer_size * sizeof(xmlChar));
    if (buffer == NULL) {
937
	perror("xmlStringDecodeEntities: malloc failed");
938 939 940 941
	return(NULL);
    }

    /*
942
     * OK loop until we reach one of the ending char or a size limit.
943 944 945 946 947 948 949 950 951 952 953 954 955 956 957 958 959 960 961 962 963 964 965 966 967 968 969 970 971 972 973 974 975 976 977 978 979 980 981 982 983 984 985 986 987 988 989 990 991 992 993 994 995 996 997 998 999 1000 1001 1002 1003 1004 1005 1006 1007 1008 1009 1010 1011 1012 1013 1014 1015 1016 1017 1018 1019 1020 1021 1022 1023 1024 1025 1026 1027 1028 1029 1030 1031 1032 1033 1034 1035 1036 1037 1038 1039 1040 1041 1042 1043 1044 1045 1046 1047 1048 1049 1050 1051 1052 1053 1054 1055 1056 1057 1058 1059 1060 1061 1062 1063 1064 1065 1066 1067 1068 1069 1070 1071 1072 1073 1074 1075 1076 1077 1078 1079 1080 1081 1082 1083 1084 1085 1086 1087 1088 1089 1090 1091 1092 1093 1094 1095 1096 1097 1098 1099 1100 1101 1102 1103 1104 1105 1106 1107 1108 1109 1110 1111 1112 1113 1114 1115 1116 1117 1118 1119 1120 1121 1122 1123 1124 1125 1126 1127 1128 1129 1130 1131 1132 1133 1134 1135 1136 1137 1138 1139 1140 1141 1142 1143 1144 1145 1146 1147 1148 1149 1150 1151 1152 1153 1154 1155 1156 1157 1158 1159 1160 1161 1162 1163 1164 1165 1166 1167 1168 1169 1170 1171 1172 1173 1174 1175 1176 1177 1178 1179 1180 1181 1182 1183 1184 1185 1186 1187 1188 1189 1190 1191 1192 1193 1194 1195 1196 1197 1198 1199 1200 1201 1202 1203 1204 1205 1206 1207
     * we are operating on already parsed values.
     */
    c = CUR_SCHAR(str, l);
    while ((c != 0) && (c != end) && /* non input consuming loop */
	   (c != end2) && (c != end3)) {

	if (c == 0) break;
        if ((c == '&') && (str[1] == '#')) {
	    int val = xmlParseStringCharRef(ctxt, &str);
	    if (val != 0) {
		COPY_BUF(0,buffer,nbchars,val);
	    }
	} else if ((c == '&') && (what & XML_SUBSTITUTE_REF)) {
	    if (xmlParserDebugEntities)
		xmlGenericError(xmlGenericErrorContext,
			"String decoding Entity Reference: %.30s\n",
			str);
	    ent = xmlParseStringEntityRef(ctxt, &str);
	    if ((ent != NULL) &&
		(ent->etype == XML_INTERNAL_PREDEFINED_ENTITY)) {
		if (ent->content != NULL) {
		    COPY_BUF(0,buffer,nbchars,ent->content[0]);
		} else {
		    if ((ctxt->sax != NULL) && (ctxt->sax->error != NULL))
			ctxt->sax->error(ctxt->userData,
			    "internal error entity has no content\n");
		}
	    } else if ((ent != NULL) && (ent->content != NULL)) {
		xmlChar *rep;

		ctxt->depth++;
		rep = xmlStringDecodeEntities(ctxt, ent->content, what,
			                      0, 0, 0);
		ctxt->depth--;
		if (rep != NULL) {
		    current = rep;
		    while (*current != 0) { /* non input consuming loop */
			buffer[nbchars++] = *current++;
			if (nbchars >
		            buffer_size - XML_PARSER_BUFFER_SIZE) {
			    growBuffer(buffer);
			}
		    }
		    xmlFree(rep);
		}
	    } else if (ent != NULL) {
		int i = xmlStrlen(ent->name);
		const xmlChar *cur = ent->name;

		buffer[nbchars++] = '&';
		if (nbchars > buffer_size - i - XML_PARSER_BUFFER_SIZE) {
		    growBuffer(buffer);
		}
		for (;i > 0;i--)
		    buffer[nbchars++] = *cur++;
		buffer[nbchars++] = ';';
	    }
	} else if (c == '%' && (what & XML_SUBSTITUTE_PEREF)) {
	    if (xmlParserDebugEntities)
		xmlGenericError(xmlGenericErrorContext,
			"String decoding PE Reference: %.30s\n", str);
	    ent = xmlParseStringPEReference(ctxt, &str);
	    if (ent != NULL) {
		xmlChar *rep;

		ctxt->depth++;
		rep = xmlStringDecodeEntities(ctxt, ent->content, what,
			                      0, 0, 0);
		ctxt->depth--;
		if (rep != NULL) {
		    current = rep;
		    while (*current != 0) { /* non input consuming loop */
			buffer[nbchars++] = *current++;
			if (nbchars >
		            buffer_size - XML_PARSER_BUFFER_SIZE) {
			    growBuffer(buffer);
			}
		    }
		    xmlFree(rep);
		}
	    }
	} else {
	    COPY_BUF(l,buffer,nbchars,c);
	    str += l;
	    if (nbchars > buffer_size - XML_PARSER_BUFFER_SIZE) {
	      growBuffer(buffer);
	    }
	}
	c = CUR_SCHAR(str, l);
    }
    buffer[nbchars++] = 0;
    return(buffer);
}


/************************************************************************
 *									*
 *		Commodity functions to handle xmlChars			*
 *									*
 ************************************************************************/

/**
 * xmlStrndup:
 * @cur:  the input xmlChar *
 * @len:  the len of @cur
 *
 * a strndup for array of xmlChar's
 *
 * Returns a new xmlChar * or NULL
 */
xmlChar *
xmlStrndup(const xmlChar *cur, int len) {
    xmlChar *ret;
    
    if ((cur == NULL) || (len < 0)) return(NULL);
    ret = (xmlChar *) xmlMalloc((len + 1) * sizeof(xmlChar));
    if (ret == NULL) {
        xmlGenericError(xmlGenericErrorContext,
		"malloc of %ld byte failed\n",
	        (len + 1) * (long)sizeof(xmlChar));
        return(NULL);
    }
    memcpy(ret, cur, len * sizeof(xmlChar));
    ret[len] = 0;
    return(ret);
}

/**
 * xmlStrdup:
 * @cur:  the input xmlChar *
 *
 * a strdup for array of xmlChar's. Since they are supposed to be
 * encoded in UTF-8 or an encoding with 8bit based chars, we assume
 * a termination mark of '0'.
 *
 * Returns a new xmlChar * or NULL
 */
xmlChar *
xmlStrdup(const xmlChar *cur) {
    const xmlChar *p = cur;

    if (cur == NULL) return(NULL);
    while (*p != 0) p++; /* non input consuming */
    return(xmlStrndup(cur, p - cur));
}

/**
 * xmlCharStrndup:
 * @cur:  the input char *
 * @len:  the len of @cur
 *
 * a strndup for char's to xmlChar's
 *
 * Returns a new xmlChar * or NULL
 */

xmlChar *
xmlCharStrndup(const char *cur, int len) {
    int i;
    xmlChar *ret;
    
    if ((cur == NULL) || (len < 0)) return(NULL);
    ret = (xmlChar *) xmlMalloc((len + 1) * sizeof(xmlChar));
    if (ret == NULL) {
        xmlGenericError(xmlGenericErrorContext, "malloc of %ld byte failed\n",
	        (len + 1) * (long)sizeof(xmlChar));
        return(NULL);
    }
    for (i = 0;i < len;i++)
        ret[i] = (xmlChar) cur[i];
    ret[len] = 0;
    return(ret);
}

/**
 * xmlCharStrdup:
 * @cur:  the input char *
 * @len:  the len of @cur
 *
 * a strdup for char's to xmlChar's
 *
 * Returns a new xmlChar * or NULL
 */

xmlChar *
xmlCharStrdup(const char *cur) {
    const char *p = cur;

    if (cur == NULL) return(NULL);
    while (*p != '\0') p++; /* non input consuming */
    return(xmlCharStrndup(cur, p - cur));
}

/**
 * xmlStrcmp:
 * @str1:  the first xmlChar *
 * @str2:  the second xmlChar *
 *
 * a strcmp for xmlChar's
 *
 * Returns the integer result of the comparison
 */

int
xmlStrcmp(const xmlChar *str1, const xmlChar *str2) {
    register int tmp;

    if (str1 == str2) return(0);
    if (str1 == NULL) return(-1);
    if (str2 == NULL) return(1);
    do {
        tmp = *str1++ - *str2;
	if (tmp != 0) return(tmp);
    } while (*str2++ != 0);
    return 0;
}

/**
 * xmlStrEqual:
 * @str1:  the first xmlChar *
 * @str2:  the second xmlChar *
 *
 * Check if both string are equal of have same content
 * Should be a bit more readable and faster than xmlStrEqual()
 *
 * Returns 1 if they are equal, 0 if they are different
 */

int
xmlStrEqual(const xmlChar *str1, const xmlChar *str2) {
    if (str1 == str2) return(1);
    if (str1 == NULL) return(0);
    if (str2 == NULL) return(0);
    do {
	if (*str1++ != *str2) return(0);
    } while (*str2++);
    return(1);
}

/**
 * xmlStrncmp:
 * @str1:  the first xmlChar *
 * @str2:  the second xmlChar *
 * @len:  the max comparison length
 *
 * a strncmp for xmlChar's
 *
 * Returns the integer result of the comparison
 */

int
xmlStrncmp(const xmlChar *str1, const xmlChar *str2, int len) {
    register int tmp;

    if (len <= 0) return(0);
    if (str1 == str2) return(0);
    if (str1 == NULL) return(-1);
    if (str2 == NULL) return(1);
    do {
        tmp = *str1++ - *str2;
	if (tmp != 0 || --len == 0) return(tmp);
    } while (*str2++ != 0);
    return 0;
}

1208
static const xmlChar casemap[256] = {
1209 1210 1211 1212 1213 1214 1215 1216 1217 1218 1219 1220 1221 1222 1223 1224 1225 1226 1227 1228 1229 1230 1231 1232 1233 1234 1235 1236 1237 1238 1239 1240 1241 1242 1243 1244 1245 1246 1247 1248 1249 1250 1251 1252 1253 1254 1255 1256 1257 1258 1259 1260 1261 1262 1263 1264 1265 1266 1267 1268 1269 1270 1271 1272 1273 1274 1275 1276 1277 1278 1279 1280 1281 1282 1283 1284 1285 1286 1287 1288 1289 1290 1291 1292 1293 1294 1295 1296 1297 1298 1299
    0x00,0x01,0x02,0x03,0x04,0x05,0x06,0x07,
    0x08,0x09,0x0A,0x0B,0x0C,0x0D,0x0E,0x0F,
    0x10,0x11,0x12,0x13,0x14,0x15,0x16,0x17,
    0x18,0x19,0x1A,0x1B,0x1C,0x1D,0x1E,0x1F,
    0x20,0x21,0x22,0x23,0x24,0x25,0x26,0x27,
    0x28,0x29,0x2A,0x2B,0x2C,0x2D,0x2E,0x2F,
    0x30,0x31,0x32,0x33,0x34,0x35,0x36,0x37,
    0x38,0x39,0x3A,0x3B,0x3C,0x3D,0x3E,0x3F,
    0x40,0x61,0x62,0x63,0x64,0x65,0x66,0x67,
    0x68,0x69,0x6A,0x6B,0x6C,0x6D,0x6E,0x6F,
    0x70,0x71,0x72,0x73,0x74,0x75,0x76,0x77,
    0x78,0x79,0x7A,0x7B,0x5C,0x5D,0x5E,0x5F,
    0x60,0x61,0x62,0x63,0x64,0x65,0x66,0x67,
    0x68,0x69,0x6A,0x6B,0x6C,0x6D,0x6E,0x6F,
    0x70,0x71,0x72,0x73,0x74,0x75,0x76,0x77,
    0x78,0x79,0x7A,0x7B,0x7C,0x7D,0x7E,0x7F,
    0x80,0x81,0x82,0x83,0x84,0x85,0x86,0x87,
    0x88,0x89,0x8A,0x8B,0x8C,0x8D,0x8E,0x8F,
    0x90,0x91,0x92,0x93,0x94,0x95,0x96,0x97,
    0x98,0x99,0x9A,0x9B,0x9C,0x9D,0x9E,0x9F,
    0xA0,0xA1,0xA2,0xA3,0xA4,0xA5,0xA6,0xA7,
    0xA8,0xA9,0xAA,0xAB,0xAC,0xAD,0xAE,0xAF,
    0xB0,0xB1,0xB2,0xB3,0xB4,0xB5,0xB6,0xB7,
    0xB8,0xB9,0xBA,0xBB,0xBC,0xBD,0xBE,0xBF,
    0xC0,0xC1,0xC2,0xC3,0xC4,0xC5,0xC6,0xC7,
    0xC8,0xC9,0xCA,0xCB,0xCC,0xCD,0xCE,0xCF,
    0xD0,0xD1,0xD2,0xD3,0xD4,0xD5,0xD6,0xD7,
    0xD8,0xD9,0xDA,0xDB,0xDC,0xDD,0xDE,0xDF,
    0xE0,0xE1,0xE2,0xE3,0xE4,0xE5,0xE6,0xE7,
    0xE8,0xE9,0xEA,0xEB,0xEC,0xED,0xEE,0xEF,
    0xF0,0xF1,0xF2,0xF3,0xF4,0xF5,0xF6,0xF7,
    0xF8,0xF9,0xFA,0xFB,0xFC,0xFD,0xFE,0xFF
};

/**
 * xmlStrcasecmp:
 * @str1:  the first xmlChar *
 * @str2:  the second xmlChar *
 *
 * a strcasecmp for xmlChar's
 *
 * Returns the integer result of the comparison
 */

int
xmlStrcasecmp(const xmlChar *str1, const xmlChar *str2) {
    register int tmp;

    if (str1 == str2) return(0);
    if (str1 == NULL) return(-1);
    if (str2 == NULL) return(1);
    do {
	tmp = casemap[*str1++] - casemap[*str2];
	if (tmp != 0) return(tmp);
    } while (*str2++ != 0);
    return 0;
}

/**
 * xmlStrncasecmp:
 * @str1:  the first xmlChar *
 * @str2:  the second xmlChar *
 * @len:  the max comparison length
 *
 * a strncasecmp for xmlChar's
 *
 * Returns the integer result of the comparison
 */

int
xmlStrncasecmp(const xmlChar *str1, const xmlChar *str2, int len) {
    register int tmp;

    if (len <= 0) return(0);
    if (str1 == str2) return(0);
    if (str1 == NULL) return(-1);
    if (str2 == NULL) return(1);
    do {
	tmp = casemap[*str1++] - casemap[*str2];
	if (tmp != 0 || --len == 0) return(tmp);
    } while (*str2++ != 0);
    return 0;
}

/**
 * xmlStrchr:
 * @str:  the xmlChar * array
 * @val:  the xmlChar to search
 *
 * a strchr for xmlChar's
 *
1300
 * Returns the xmlChar * for the first occurrence or NULL.
1301 1302 1303 1304 1305 1306 1307 1308 1309 1310 1311 1312 1313 1314 1315 1316 1317 1318 1319
 */

const xmlChar *
xmlStrchr(const xmlChar *str, xmlChar val) {
    if (str == NULL) return(NULL);
    while (*str != 0) { /* non input consuming */
        if (*str == val) return((xmlChar *) str);
	str++;
    }
    return(NULL);
}

/**
 * xmlStrstr:
 * @str:  the xmlChar * array (haystack)
 * @val:  the xmlChar to search (needle)
 *
 * a strstr for xmlChar's
 *
1320
 * Returns the xmlChar * for the first occurrence or NULL.
1321 1322 1323
 */

const xmlChar *
1324
xmlStrstr(const xmlChar *str, const xmlChar *val) {
1325 1326 1327 1328 1329 1330 1331 1332 1333 1334 1335 1336 1337 1338 1339 1340 1341 1342 1343 1344 1345 1346 1347
    int n;
    
    if (str == NULL) return(NULL);
    if (val == NULL) return(NULL);
    n = xmlStrlen(val);

    if (n == 0) return(str);
    while (*str != 0) { /* non input consuming */
        if (*str == *val) {
	    if (!xmlStrncmp(str, val, n)) return((const xmlChar *) str);
	}
	str++;
    }
    return(NULL);
}

/**
 * xmlStrcasestr:
 * @str:  the xmlChar * array (haystack)
 * @val:  the xmlChar to search (needle)
 *
 * a case-ignoring strstr for xmlChar's
 *
1348
 * Returns the xmlChar * for the first occurrence or NULL.
1349 1350 1351 1352 1353 1354 1355 1356 1357 1358 1359 1360 1361 1362 1363 1364 1365 1366 1367 1368 1369 1370 1371 1372 1373 1374 1375
 */

const xmlChar *
xmlStrcasestr(const xmlChar *str, xmlChar *val) {
    int n;
    
    if (str == NULL) return(NULL);
    if (val == NULL) return(NULL);
    n = xmlStrlen(val);

    if (n == 0) return(str);
    while (*str != 0) { /* non input consuming */
	if (casemap[*str] == casemap[*val])
	    if (!xmlStrncasecmp(str, val, n)) return(str);
	str++;
    }
    return(NULL);
}

/**
 * xmlStrsub:
 * @str:  the xmlChar * array (haystack)
 * @start:  the index of the first char (zero based)
 * @len:  the length of the substring
 *
 * Extract a substring of a given string
 *
1376
 * Returns the xmlChar * for the first occurrence or NULL.
1377 1378 1379 1380 1381 1382 1383 1384 1385 1386 1387 1388 1389 1390 1391 1392 1393 1394 1395 1396 1397 1398 1399 1400 1401 1402 1403 1404 1405 1406 1407 1408 1409 1410 1411 1412 1413 1414 1415 1416 1417 1418 1419 1420 1421
 */

xmlChar *
xmlStrsub(const xmlChar *str, int start, int len) {
    int i;
    
    if (str == NULL) return(NULL);
    if (start < 0) return(NULL);
    if (len < 0) return(NULL);

    for (i = 0;i < start;i++) {
        if (*str == 0) return(NULL);
	str++;
    }
    if (*str == 0) return(NULL);
    return(xmlStrndup(str, len));
}

/**
 * xmlStrlen:
 * @str:  the xmlChar * array
 *
 * length of a xmlChar's string
 *
 * Returns the number of xmlChar contained in the ARRAY.
 */

int
xmlStrlen(const xmlChar *str) {
    int len = 0;

    if (str == NULL) return(0);
    while (*str != 0) { /* non input consuming */
	str++;
	len++;
    }
    return(len);
}

/**
 * xmlStrncat:
 * @cur:  the original xmlChar * array
 * @add:  the xmlChar * array added
 * @len:  the length of @add
 *
1422
 * a strncat for array of xmlChar's, it will extend @cur with the len
1423 1424 1425 1426 1427 1428 1429 1430 1431 1432 1433 1434 1435 1436 1437 1438 1439 1440 1441 1442 1443 1444 1445 1446 1447 1448 1449 1450 1451 1452 1453 1454 1455 1456 1457 1458 1459 1460 1461 1462 1463 1464 1465 1466 1467 1468 1469 1470 1471 1472 1473 1474 1475 1476 1477 1478 1479 1480 1481 1482 1483 1484 1485 1486 1487 1488 1489 1490 1491 1492 1493 1494 1495
 * first bytes of @add.
 *
 * Returns a new xmlChar *, the original @cur is reallocated if needed
 * and should not be freed
 */

xmlChar *
xmlStrncat(xmlChar *cur, const xmlChar *add, int len) {
    int size;
    xmlChar *ret;

    if ((add == NULL) || (len == 0))
        return(cur);
    if (cur == NULL)
        return(xmlStrndup(add, len));

    size = xmlStrlen(cur);
    ret = (xmlChar *) xmlRealloc(cur, (size + len + 1) * sizeof(xmlChar));
    if (ret == NULL) {
        xmlGenericError(xmlGenericErrorContext,
		"xmlStrncat: realloc of %ld byte failed\n",
	        (size + len + 1) * (long)sizeof(xmlChar));
        return(cur);
    }
    memcpy(&ret[size], add, len * sizeof(xmlChar));
    ret[size + len] = 0;
    return(ret);
}

/**
 * xmlStrcat:
 * @cur:  the original xmlChar * array
 * @add:  the xmlChar * array added
 *
 * a strcat for array of xmlChar's. Since they are supposed to be
 * encoded in UTF-8 or an encoding with 8bit based chars, we assume
 * a termination mark of '0'.
 *
 * Returns a new xmlChar * containing the concatenated string.
 */
xmlChar *
xmlStrcat(xmlChar *cur, const xmlChar *add) {
    const xmlChar *p = add;

    if (add == NULL) return(cur);
    if (cur == NULL) 
        return(xmlStrdup(add));

    while (*p != 0) p++; /* non input consuming */
    return(xmlStrncat(cur, add, p - add));
}

/************************************************************************
 *									*
 *		Commodity functions, cleanup needed ?			*
 *									*
 ************************************************************************/

/**
 * areBlanks:
 * @ctxt:  an XML parser context
 * @str:  a xmlChar *
 * @len:  the size of @str
 *
 * Is this a sequence of blank chars that one can ignore ?
 *
 * Returns 1 if ignorable 0 otherwise.
 */

static int areBlanks(xmlParserCtxtPtr ctxt, const xmlChar *str, int len) {
    int i, ret;
    xmlNodePtr lastChild;

1496 1497 1498 1499 1500
    /*
     * Don't spend time trying to differentiate them, the same callback is
     * used !
     */
    if (ctxt->sax->ignorableWhitespace == ctxt->sax->characters)
1501 1502
	return(0);

1503 1504 1505 1506 1507 1508 1509 1510 1511 1512 1513 1514 1515
    /*
     * Check for xml:space value.
     */
    if (*(ctxt->space) == 1)
	return(0);

    /*
     * Check that the string is made of blanks
     */
    for (i = 0;i < len;i++)
        if (!(IS_BLANK(str[i]))) return(0);

    /*
1516
     * Look if the element is mixed content in the DTD if available
1517
     */
1518
    if (ctxt->node == NULL) return(0);
1519 1520 1521 1522 1523 1524 1525 1526 1527 1528 1529 1530 1531 1532 1533
    if (ctxt->myDoc != NULL) {
	ret = xmlIsMixedElement(ctxt->myDoc, ctxt->node->name);
        if (ret == 0) return(1);
        if (ret == 1) return(0);
    }

    /*
     * Otherwise, heuristic :-\
     */
    if (RAW != '<') return(0);
    if ((ctxt->node->children == NULL) &&
	(RAW == '<') && (NXT(1) == '/')) return(0);

    lastChild = xmlGetLastChild(ctxt->node);
    if (lastChild == NULL) {
1534 1535
        if ((ctxt->node->type != XML_ELEMENT_NODE) &&
            (ctxt->node->content != NULL)) return(0);
1536 1537 1538 1539 1540 1541 1542 1543 1544 1545 1546 1547 1548 1549 1550 1551 1552 1553 1554 1555 1556 1557 1558 1559 1560 1561 1562 1563 1564 1565 1566 1567 1568 1569 1570 1571 1572 1573 1574 1575 1576 1577 1578 1579 1580 1581 1582 1583 1584 1585 1586 1587 1588 1589 1590 1591 1592 1593 1594 1595 1596 1597 1598 1599 1600 1601 1602 1603 1604 1605 1606 1607 1608 1609 1610 1611 1612 1613 1614 1615 1616 1617 1618 1619 1620 1621 1622 1623 1624 1625 1626 1627 1628 1629 1630 1631 1632 1633 1634 1635 1636 1637 1638 1639 1640 1641 1642 1643 1644 1645 1646 1647 1648 1649 1650 1651 1652 1653 1654 1655 1656 1657 1658 1659 1660 1661 1662 1663 1664 1665 1666 1667 1668 1669 1670 1671 1672 1673 1674 1675 1676 1677 1678 1679 1680 1681 1682 1683 1684 1685 1686 1687 1688 1689 1690 1691 1692 1693 1694 1695 1696 1697 1698
    } else if (xmlNodeIsText(lastChild))
        return(0);
    else if ((ctxt->node->children != NULL) &&
             (xmlNodeIsText(ctxt->node->children)))
        return(0);
    return(1);
}

/************************************************************************
 *									*
 *		Extra stuff for namespace support			*
 *	Relates to http://www.w3.org/TR/WD-xml-names			*
 *									*
 ************************************************************************/

/**
 * xmlSplitQName:
 * @ctxt:  an XML parser context
 * @name:  an XML parser context
 * @prefix:  a xmlChar ** 
 *
 * parse an UTF8 encoded XML qualified name string
 *
 * [NS 5] QName ::= (Prefix ':')? LocalPart
 *
 * [NS 6] Prefix ::= NCName
 *
 * [NS 7] LocalPart ::= NCName
 *
 * Returns the local part, and prefix is updated
 *   to get the Prefix if any.
 */

xmlChar *
xmlSplitQName(xmlParserCtxtPtr ctxt, const xmlChar *name, xmlChar **prefix) {
    xmlChar buf[XML_MAX_NAMELEN + 5];
    xmlChar *buffer = NULL;
    int len = 0;
    int max = XML_MAX_NAMELEN;
    xmlChar *ret = NULL;
    const xmlChar *cur = name;
    int c;

    *prefix = NULL;

#ifndef XML_XML_NAMESPACE
    /* xml: prefix is not really a namespace */
    if ((cur[0] == 'x') && (cur[1] == 'm') &&
        (cur[2] == 'l') && (cur[3] == ':'))
	return(xmlStrdup(name));
#endif

    /* nasty but valid */
    if (cur[0] == ':')
	return(xmlStrdup(name));

    c = *cur++;
    while ((c != 0) && (c != ':') && (len < max)) { /* tested bigname.xml */
	buf[len++] = c;
	c = *cur++;
    }
    if (len >= max) {
	/*
	 * Okay someone managed to make a huge name, so he's ready to pay
	 * for the processing speed.
	 */
	max = len * 2;
	
	buffer = (xmlChar *) xmlMalloc(max * sizeof(xmlChar));
	if (buffer == NULL) {
	    if ((ctxt->sax != NULL) && (ctxt->sax->error != NULL))
		ctxt->sax->error(ctxt->userData,
				 "xmlSplitQName: out of memory\n");
	    return(NULL);
	}
	memcpy(buffer, buf, len);
	while ((c != 0) && (c != ':')) { /* tested bigname.xml */
	    if (len + 10 > max) {
		max *= 2;
		buffer = (xmlChar *) xmlRealloc(buffer,
						max * sizeof(xmlChar));
		if (buffer == NULL) {
		    if ((ctxt->sax != NULL) && (ctxt->sax->error != NULL))
			ctxt->sax->error(ctxt->userData,
					 "xmlSplitQName: out of memory\n");
		    return(NULL);
		}
	    }
	    buffer[len++] = c;
	    c = *cur++;
	}
	buffer[len] = 0;
    }
    
    if (buffer == NULL)
	ret = xmlStrndup(buf, len);
    else {
	ret = buffer;
	buffer = NULL;
	max = XML_MAX_NAMELEN;
    }


    if (c == ':') {
	c = *cur++;
	if (c == 0) return(ret);
        *prefix = ret;
	len = 0;

	while ((c != 0) && (len < max)) { /* tested bigname2.xml */
	    buf[len++] = c;
	    c = *cur++;
	}
	if (len >= max) {
	    /*
	     * Okay someone managed to make a huge name, so he's ready to pay
	     * for the processing speed.
	     */
	    max = len * 2;
	    
	    buffer = (xmlChar *) xmlMalloc(max * sizeof(xmlChar));
	    if (buffer == NULL) {
		if ((ctxt->sax != NULL) && (ctxt->sax->error != NULL))
		    ctxt->sax->error(ctxt->userData,
				     "xmlSplitQName: out of memory\n");
		return(NULL);
	    }
	    memcpy(buffer, buf, len);
	    while (c != 0) { /* tested bigname2.xml */
		if (len + 10 > max) {
		    max *= 2;
		    buffer = (xmlChar *) xmlRealloc(buffer,
						    max * sizeof(xmlChar));
		    if (buffer == NULL) {
			if ((ctxt->sax != NULL) && (ctxt->sax->error != NULL))
			    ctxt->sax->error(ctxt->userData,
					     "xmlSplitQName: out of memory\n");
			return(NULL);
		    }
		}
		buffer[len++] = c;
		c = *cur++;
	    }
	    buffer[len] = 0;
	}
	
	if (buffer == NULL)
	    ret = xmlStrndup(buf, len);
	else {
	    ret = buffer;
	}
    }

    return(ret);
}

/************************************************************************
 *									*
 *			The parser itself				*
 *	Relates to http://www.w3.org/TR/REC-xml				*
 *									*
 ************************************************************************/

1699
static xmlChar * xmlParseNameComplex(xmlParserCtxtPtr ctxt);
1700 1701 1702 1703 1704 1705 1706 1707 1708 1709 1710 1711 1712 1713 1714 1715 1716 1717
/**
 * xmlParseName:
 * @ctxt:  an XML parser context
 *
 * parse an XML name.
 *
 * [4] NameChar ::= Letter | Digit | '.' | '-' | '_' | ':' |
 *                  CombiningChar | Extender
 *
 * [5] Name ::= (Letter | '_' | ':') (NameChar)*
 *
 * [6] Names ::= Name (S Name)*
 *
 * Returns the Name parsed or NULL
 */

xmlChar *
xmlParseName(xmlParserCtxtPtr ctxt) {