encoding.c 64 KB
Newer Older
1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17
/*
 * encoding.c : implements the encoding conversion functions needed for XML
 *
 * Related specs: 
 * rfc2044        (UTF-8 and UTF-16) F. Yergeau Alis Technologies
 * rfc2781        UTF-16, an encoding of ISO 10646, P. Hoffman, F. Yergeau
 * [ISO-10646]    UTF-8 and UTF-16 in Annexes
 * [ISO-8859-1]   ISO Latin-1 characters codes.
 * [UNICODE]      The Unicode Consortium, "The Unicode Standard --
 *                Worldwide Character Encoding -- Version 1.0", Addison-
 *                Wesley, Volume 1, 1991, Volume 2, 1992.  UTF-8 is
 *                described in Unicode Technical Report #4.
 * [US-ASCII]     Coded Character Set--7-bit American Standard Code for
 *                Information Interchange, ANSI X3.4-1986.
 *
 * See Copyright for the status of this software.
 *
18
 * daniel@veillard.com
19 20 21 22 23
 *
 * UTF8 string routines from:
 * "William M. Brack" <wbrack@mmm.com.hk>
 *
 * Original code for IsoLatin1 and UTF-16 by "Martin J. Duerst" <duerst@w3.org>
24 25
 */

26
#define IN_LIBXML
Bjorn Reese's avatar
Bjorn Reese committed
27
#include "libxml.h"
28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46

#include <string.h>

#ifdef HAVE_CTYPE_H
#include <ctype.h>
#endif
#ifdef HAVE_STDLIB_H
#include <stdlib.h>
#endif
#ifdef LIBXML_ICONV_ENABLED
#ifdef HAVE_ERRNO_H
#include <errno.h>
#endif
#endif
#include <libxml/encoding.h>
#include <libxml/xmlmemory.h>
#ifdef LIBXML_HTML_ENABLED
#include <libxml/HTMLparser.h>
#endif
47
#include <libxml/globals.h>
48
#include <libxml/xmlerror.h>
49

50 51
static xmlCharEncodingHandlerPtr xmlUTF16LEHandler = NULL;
static xmlCharEncodingHandlerPtr xmlUTF16BEHandler = NULL;
52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71

typedef struct _xmlCharEncodingAlias xmlCharEncodingAlias;
typedef xmlCharEncodingAlias *xmlCharEncodingAliasPtr;
struct _xmlCharEncodingAlias {
    const char *name;
    const char *alias;
};

static xmlCharEncodingAliasPtr xmlCharEncodingAliases = NULL;
static int xmlCharEncodingAliasesNb = 0;
static int xmlCharEncodingAliasesMax = 0;

#ifdef LIBXML_ICONV_ENABLED
#if 0
#define DEBUG_ENCODING  /* Define this to get encoding traces */
#endif
#endif

static int xmlLittleEndian = 1;

72 73 74 75 76 77 78 79 80 81 82 83 84 85
/************************************************************************
 *									*
 *			Generic UTF8 handling routines			*
 *									*
 * From rfc2044: encoding of the Unicode values on UTF-8:		*
 *									*
 * UCS-4 range (hex.)           UTF-8 octet sequence (binary)		*
 * 0000 0000-0000 007F   0xxxxxxx					*
 * 0000 0080-0000 07FF   110xxxxx 10xxxxxx				*
 * 0000 0800-0000 FFFF   1110xxxx 10xxxxxx 10xxxxxx 			*
 *									*
 * I hope we won't use values > 0xFFFF anytime soon !			*
 *									*
 ************************************************************************/
86

87 88 89 90
/**
 * xmlUTF8Strlen:
 * @utf:  a sequence of UTF-8 encoded bytes
 *
91
 * compute the length of an UTF8 string, it doesn't do a full UTF8
92 93 94 95 96
 * checking of the content of the string.
 *
 * Returns the number of characters in the string or -1 in case of error
 */
int
97
xmlUTF8Strlen(const xmlChar *utf) {
98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127
    int ret = 0;

    if (utf == NULL)
	return(-1);

    while (*utf != 0) {
	if (utf[0] & 0x80) {
	    if ((utf[1] & 0xc0) != 0x80)
		return(-1);
	    if ((utf[0] & 0xe0) == 0xe0) {
		if ((utf[2] & 0xc0) != 0x80)
		    return(-1);
		if ((utf[0] & 0xf0) == 0xf0) {
		    if ((utf[0] & 0xf8) != 0xf0 || (utf[3] & 0xc0) != 0x80)
			return(-1);
		    utf += 4;
		} else {
		    utf += 3;
		}
	    } else {
		utf += 2;
	    }
	} else {
	    utf++;
	}
	ret++;
    }
    return(ret);
}

128 129 130 131 132 133 134 135 136 137
/**
 * xmlGetUTF8Char:
 * @utf:  a sequence of UTF-8 encoded bytes
 * @len:  a pointer to @bytes len
 *
 * Read one UTF8 Char from @utf
 *
 * Returns the char value or -1 in case of error and update @len with the
 *        number of bytes used
 */
138
static int
139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202
xmlGetUTF8Char(const unsigned char *utf, int *len) {
    unsigned int c;

    if (utf == NULL)
	goto error;
    if (len == NULL)
	goto error;
    if (*len < 1)
	goto error;

    c = utf[0];
    if (c & 0x80) {
	if (*len < 2)
	    goto error;
	if ((utf[1] & 0xc0) != 0x80)
	    goto error;
	if ((c & 0xe0) == 0xe0) {
	    if (*len < 3)
		goto error;
	    if ((utf[2] & 0xc0) != 0x80)
		goto error;
	    if ((c & 0xf0) == 0xf0) {
		if (*len < 4)
		    goto error;
		if ((c & 0xf8) != 0xf0 || (utf[3] & 0xc0) != 0x80)
		    goto error;
		*len = 4;
		/* 4-byte code */
		c = (utf[0] & 0x7) << 18;
		c |= (utf[1] & 0x3f) << 12;
		c |= (utf[2] & 0x3f) << 6;
		c |= utf[3] & 0x3f;
	    } else {
	      /* 3-byte code */
		*len = 3;
		c = (utf[0] & 0xf) << 12;
		c |= (utf[1] & 0x3f) << 6;
		c |= utf[2] & 0x3f;
	    }
	} else {
	  /* 2-byte code */
	    *len = 2;
	    c = (utf[0] & 0x1f) << 6;
	    c |= utf[1] & 0x3f;
	}
    } else {
	/* 1-byte code */
	*len = 1;
    }
    return(c);

error:
    *len = 0;
    return(-1);
}

/**
 * xmlCheckUTF8: Check utf-8 string for legality.
 * @utf: Pointer to putative utf-8 encoded string.
 *
 * Checks @utf for being valid utf-8. @utf is assumed to be
 * null-terminated. This function is not super-strict, as it will
 * allow longer utf-8 sequences than necessary. Note that Java is
 * capable of producing these sequences if provoked. Also note, this
203
 * routine checks for the 4-byte maximum size, but does not check for
204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238
 * 0x10ffff maximum value.
 *
 * Return value: true if @utf is valid.
 **/
int
xmlCheckUTF8(const unsigned char *utf)
{
    int ix;
    unsigned char c;

    for (ix = 0; (c = utf[ix]);) {
        if (c & 0x80) {
	    if ((utf[ix + 1] & 0xc0) != 0x80)
	        return(0);
	    if ((c & 0xe0) == 0xe0) {
	        if ((utf[ix + 2] & 0xc0) != 0x80)
		    return(0);
	        if ((c & 0xf0) == 0xf0) {
		    if ((c & 0xf8) != 0xf0 || (utf[ix + 3] & 0xc0) != 0x80)
		        return(0);
		    ix += 4;
		    /* 4-byte code */
	        } else
		  /* 3-byte code */
		    ix += 3;
	    } else
	      /* 2-byte code */
	        ix += 2;
	} else
	    /* 1-byte code */
	    ix++;
      }
      return(1);
}

239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409
/**
 * xmlUTF8Strsize:
 * @utf:  a sequence of UTF-8 encoded bytes
 * @len:  the number of characters in the array
 *
 * storage size of an UTF8 string
 *
 * Returns the storage size of
 * the first 'len' characters of ARRAY
 *
 */

int
xmlUTF8Strsize(const xmlChar *utf, int len) {
    const xmlChar	*ptr=utf;
    xmlChar	ch;

    if (len <= 0)
	return(0);

    while ( len-- > 0) {
	if ( !*ptr )
	    break;
	if ( (ch = *ptr++) & 0x80)
	    while ( (ch<<=1) & 0x80 )
		ptr++;
    }
    return (ptr - utf);
}


/**
 * xmlUTF8Strndup:
 * @utf:  the input UTF8 *
 * @len:  the len of @utf (in chars)
 *
 * a strndup for array of UTF8's
 *
 * Returns a new UTF8 * or NULL
 */
xmlChar *
xmlUTF8Strndup(const xmlChar *utf, int len) {
    xmlChar *ret;
    int i;
    
    if ((utf == NULL) || (len < 0)) return(NULL);
    i = xmlUTF8Strsize(utf, len);
    ret = (xmlChar *) xmlMalloc((i + 1) * sizeof(xmlChar));
    if (ret == NULL) {
        xmlGenericError(xmlGenericErrorContext,
		"malloc of %ld byte failed\n",
	        (len + 1) * (long)sizeof(xmlChar));
        return(NULL);
    }
    memcpy(ret, utf, i * sizeof(xmlChar));
    ret[i] = 0;
    return(ret);
}

/**
 * xmlUTF8Strpos:
 * @utf:  the input UTF8 *
 * @pos:  the position of the desired UTF8 char (in chars)
 *
 * a function to provide the equivalent of fetching a
 * character from a string array
 *
 * Returns a pointer to the UTF8 character or NULL
 */
xmlChar *
xmlUTF8Strpos(const xmlChar *utf, int pos) {
    xmlChar ch;

    if (utf == NULL) return(NULL);
    if ( (pos < 0) || (pos >= xmlUTF8Strlen(utf)) )
	return(NULL);
    while (pos--) {
	if ((ch=*utf++) == 0) return(NULL);
	if ( ch & 0x80 ) {
	    /* if not simple ascii, verify proper format */
	    if ( (ch & 0xc0) != 0xc0 )
		return(NULL);
	    /* then skip over remaining bytes for this char */
	    while ( (ch <<= 1) & 0x80 )
		if ( (*utf++ & 0xc0) != 0x80 )
		    return(NULL);
	}
    }
    return((xmlChar *)utf);
}

/**
 * xmlUTF8Strloc:
 * @utf:  the input UTF8 *
 * @utfchar:  the UTF8 character to be found
 *
 * a function to provide relative location of a UTF8 char
 *
 * Returns the relative character position of the desired char
 * or -1 if not found
 */
int
xmlUTF8Strloc(const xmlChar *utf, const xmlChar *utfchar) {
    int i, size;
    xmlChar ch;

    if (utf==NULL || utfchar==NULL) return -1;
    size = xmlUTF8Strsize(utfchar, 1);
	for(i=0; (ch=*utf) != 0; i++) {
	    if (xmlStrncmp(utf, utfchar, size)==0)
		return(i);
	    utf++;
	    if ( ch & 0x80 ) {
		/* if not simple ascii, verify proper format */
		if ( (ch & 0xc0) != 0xc0 )
		    return(-1);
		/* then skip over remaining bytes for this char */
		while ( (ch <<= 1) & 0x80 )
		    if ( (*utf++ & 0xc0) != 0x80 )
			return(-1);
	    }
	}

    return(-1);
}
/**
 * xmlUTF8Strsub:
 * @utf:  a sequence of UTF-8 encoded bytes
 * @start: relative pos of first char
 * @len:   total number to copy
 *
 * Note:  positions are given in units of UTF-8 chars
 *
 * Returns a pointer to a newly created string
 * or NULL if any problem
 */

xmlChar *
xmlUTF8Strsub(const xmlChar *utf, int start, int len) {
    int	    i;
    xmlChar ch;

    if (utf == NULL) return(NULL);
    if (start < 0) return(NULL);
    if (len < 0) return(NULL);

    /*
     * Skip over any leading chars
     */
    for (i = 0;i < start;i++) {
	if ((ch=*utf++) == 0) return(NULL);
	if ( ch & 0x80 ) {
	    /* if not simple ascii, verify proper format */
	    if ( (ch & 0xc0) != 0xc0 )
		return(NULL);
	    /* then skip over remaining bytes for this char */
	    while ( (ch <<= 1) & 0x80 )
		if ( (*utf++ & 0xc0) != 0x80 )
		    return(NULL);
	}
    }

    return(xmlUTF8Strndup(utf, len));
}

/************************************************************************
 *									*
 *		Conversions To/From UTF8 encoding			*
 *									*
 ************************************************************************/

410 411 412 413 414 415 416 417 418 419 420
/**
 * asciiToUTF8:
 * @out:  a pointer to an array of bytes to store the result
 * @outlen:  the length of @out
 * @in:  a pointer to an array of ASCII chars
 * @inlen:  the length of @in
 *
 * Take a block of ASCII chars in and try to convert it to an UTF-8
 * block of chars out.
 * Returns 0 if success, or -1 otherwise
 * The value of @inlen after return is the number of octets consumed
421
 *     as the return value is positive, else unpredictable.
422 423
 * The value of @outlen after return is the number of ocetes consumed.
 */
424
static int
425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472
asciiToUTF8(unsigned char* out, int *outlen,
              const unsigned char* in, int *inlen) {
    unsigned char* outstart = out;
    const unsigned char* base = in;
    const unsigned char* processed = in;
    unsigned char* outend = out + *outlen;
    const unsigned char* inend;
    unsigned int c;
    int bits;

    inend = in + (*inlen);
    while ((in < inend) && (out - outstart + 5 < *outlen)) {
	c= *in++;

	/* assertion: c is a single UTF-4 value */
        if (out >= outend)
	    break;
        if      (c <    0x80) {  *out++=  c;                bits= -6; }
        else { 
	    *outlen = out - outstart;
	    *inlen = processed - base;
	    return(-1);
	}
 
        for ( ; bits >= 0; bits-= 6) {
            if (out >= outend)
	        break;
            *out++= ((c >> bits) & 0x3F) | 0x80;
        }
	processed = (const unsigned char*) in;
    }
    *outlen = out - outstart;
    *inlen = processed - base;
    return(0);
}

/**
 * UTF8Toascii:
 * @out:  a pointer to an array of bytes to store the result
 * @outlen:  the length of @out
 * @in:  a pointer to an array of UTF-8 chars
 * @inlen:  the length of @in
 *
 * Take a block of UTF-8 chars in and try to convert it to an ASCII
 * block of chars out.
 *
 * Returns 0 if success, -2 if the transcoding fails, or -1 otherwise
 * The value of @inlen after return is the number of octets consumed
473
 *     as the return value is positive, else unpredictable.
474 475
 * The value of @outlen after return is the number of ocetes consumed.
 */
476
static int
477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554
UTF8Toascii(unsigned char* out, int *outlen,
              const unsigned char* in, int *inlen) {
    const unsigned char* processed = in;
    const unsigned char* outend;
    const unsigned char* outstart = out;
    const unsigned char* instart = in;
    const unsigned char* inend;
    unsigned int c, d;
    int trailing;

    if (in == NULL) {
        /*
	 * initialization nothing to do
	 */
	*outlen = 0;
	*inlen = 0;
	return(0);
    }
    inend = in + (*inlen);
    outend = out + (*outlen);
    while (in < inend) {
	d = *in++;
	if      (d < 0x80)  { c= d; trailing= 0; }
	else if (d < 0xC0) {
	    /* trailing byte in leading position */
	    *outlen = out - outstart;
	    *inlen = processed - instart;
	    return(-2);
        } else if (d < 0xE0)  { c= d & 0x1F; trailing= 1; }
        else if (d < 0xF0)  { c= d & 0x0F; trailing= 2; }
        else if (d < 0xF8)  { c= d & 0x07; trailing= 3; }
	else {
	    /* no chance for this in Ascii */
	    *outlen = out - outstart;
	    *inlen = processed - instart;
	    return(-2);
	}

	if (inend - in < trailing) {
	    break;
	} 

	for ( ; trailing; trailing--) {
	    if ((in >= inend) || (((d= *in++) & 0xC0) != 0x80))
		break;
	    c <<= 6;
	    c |= d & 0x3F;
	}

	/* assertion: c is a single UTF-4 value */
	if (c < 0x80) {
	    if (out >= outend)
		break;
	    *out++ = c;
	} else {
	    /* no chance for this in Ascii */
	    *outlen = out - outstart;
	    *inlen = processed - instart;
	    return(-2);
	}
	processed = in;
    }
    *outlen = out - outstart;
    *inlen = processed - instart;
    return(0);
}

/**
 * isolat1ToUTF8:
 * @out:  a pointer to an array of bytes to store the result
 * @outlen:  the length of @out
 * @in:  a pointer to an array of ISO Latin 1 chars
 * @inlen:  the length of @in
 *
 * Take a block of ISO Latin 1 chars in and try to convert it to an UTF-8
 * block of chars out.
 * Returns 0 if success, or -1 otherwise
 * The value of @inlen after return is the number of octets consumed
555
 *     as the return value is positive, else unpredictable.
556 557 558 559 560 561 562 563 564 565 566 567 568
 * The value of @outlen after return is the number of ocetes consumed.
 */
int
isolat1ToUTF8(unsigned char* out, int *outlen,
              const unsigned char* in, int *inlen) {
    unsigned char* outstart = out;
    const unsigned char* base = in;
    const unsigned char* processed = in;
    unsigned char* outend = out + *outlen;
    const unsigned char* inend;
    unsigned int c;

    inend = in + (*inlen);
569 570
    while (in < inend) {
	c = *in++;
571 572 573

        if (out >= outend)
	    break;
574 575 576 577 578 579 580

        if (c < 0x80) {
	    *out++ =  c;
	    processed++;
	    continue;
	} else {
	    *out++= ((c >>  6) & 0x1F) | 0xC0;
581
            if (out >= outend)
582 583 584
		break;
            *out++= (c & 0x3F) | 0x80;
	    processed++;
585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603
        }
    }
    *outlen = out - outstart;
    *inlen = processed - base;
    return(0);
}

/**
 * UTF8Toisolat1:
 * @out:  a pointer to an array of bytes to store the result
 * @outlen:  the length of @out
 * @in:  a pointer to an array of UTF-8 chars
 * @inlen:  the length of @in
 *
 * Take a block of UTF-8 chars in and try to convert it to an ISO Latin 1
 * block of chars out.
 *
 * Returns 0 if success, -2 if the transcoding fails, or -1 otherwise
 * The value of @inlen after return is the number of octets consumed
604
 *     as the return value is positive, else unpredictable.
605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687
 * The value of @outlen after return is the number of ocetes consumed.
 */
int
UTF8Toisolat1(unsigned char* out, int *outlen,
              const unsigned char* in, int *inlen) {
    const unsigned char* processed = in;
    const unsigned char* outend;
    const unsigned char* outstart = out;
    const unsigned char* instart = in;
    const unsigned char* inend;
    unsigned int c, d;
    int trailing;

    if (in == NULL) {
        /*
	 * initialization nothing to do
	 */
	*outlen = 0;
	*inlen = 0;
	return(0);
    }
    inend = in + (*inlen);
    outend = out + (*outlen);
    while (in < inend) {
	d = *in++;
	if      (d < 0x80)  { c= d; trailing= 0; }
	else if (d < 0xC0) {
	    /* trailing byte in leading position */
	    *outlen = out - outstart;
	    *inlen = processed - instart;
	    return(-2);
        } else if (d < 0xE0)  { c= d & 0x1F; trailing= 1; }
        else if (d < 0xF0)  { c= d & 0x0F; trailing= 2; }
        else if (d < 0xF8)  { c= d & 0x07; trailing= 3; }
	else {
	    /* no chance for this in IsoLat1 */
	    *outlen = out - outstart;
	    *inlen = processed - instart;
	    return(-2);
	}

	if (inend - in < trailing) {
	    break;
	} 

	for ( ; trailing; trailing--) {
	    if (in >= inend)
		break;
	    if (((d= *in++) & 0xC0) != 0x80) {
		*outlen = out - outstart;
		*inlen = processed - instart;
		return(-2);
	    }
	    c <<= 6;
	    c |= d & 0x3F;
	}

	/* assertion: c is a single UTF-4 value */
	if (c <= 0xFF) {
	    if (out >= outend)
		break;
	    *out++ = c;
	} else {
	    /* no chance for this in IsoLat1 */
	    *outlen = out - outstart;
	    *inlen = processed - instart;
	    return(-2);
	}
	processed = in;
    }
    *outlen = out - outstart;
    *inlen = processed - instart;
    return(0);
}

/**
 * UTF16LEToUTF8:
 * @out:  a pointer to an array of bytes to store the result
 * @outlen:  the length of @out
 * @inb:  a pointer to an array of UTF-16LE passwd as a byte array
 * @inlenb:  the length of @in in UTF-16LE chars
 *
 * Take a block of UTF-16LE ushorts in and try to convert it to an UTF-8
688
 * block of chars out. This function assume the endian property
689 690 691 692 693 694
 * is the same between the native type of this machine and the
 * inputed one.
 *
 * Returns the number of byte written, or -1 by lack of space, or -2
 *     if the transcoding fails (for *in is not valid utf16 string)
 *     The value of *inlen after return is the number of octets consumed
695
 *     as the return value is positive, else unpredictable.
696
 */
697
static int
698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780
UTF16LEToUTF8(unsigned char* out, int *outlen,
            const unsigned char* inb, int *inlenb)
{
    unsigned char* outstart = out;
    const unsigned char* processed = inb;
    unsigned char* outend = out + *outlen;
    unsigned short* in = (unsigned short*) inb;
    unsigned short* inend;
    unsigned int c, d, inlen;
    unsigned char *tmp;
    int bits;

    if ((*inlenb % 2) == 1)
        (*inlenb)--;
    inlen = *inlenb / 2;
    inend = in + inlen;
    while ((in < inend) && (out - outstart + 5 < *outlen)) {
        if (xmlLittleEndian) {
	    c= *in++;
	} else {
	    tmp = (unsigned char *) in;
	    c = *tmp++;
	    c = c | (((unsigned int)*tmp) << 8);
	    in++;
	}
        if ((c & 0xFC00) == 0xD800) {    /* surrogates */
	    if (in >= inend) {           /* (in > inend) shouldn't happens */
		break;
	    }
	    if (xmlLittleEndian) {
		d = *in++;
	    } else {
		tmp = (unsigned char *) in;
		d = *tmp++;
		d = d | (((unsigned int)*tmp) << 8);
		in++;
	    }
            if ((d & 0xFC00) == 0xDC00) {
                c &= 0x03FF;
                c <<= 10;
                c |= d & 0x03FF;
                c += 0x10000;
            }
            else {
		*outlen = out - outstart;
		*inlenb = processed - inb;
	        return(-2);
	    }
        }

	/* assertion: c is a single UTF-4 value */
        if (out >= outend)
	    break;
        if      (c <    0x80) {  *out++=  c;                bits= -6; }
        else if (c <   0x800) {  *out++= ((c >>  6) & 0x1F) | 0xC0;  bits=  0; }
        else if (c < 0x10000) {  *out++= ((c >> 12) & 0x0F) | 0xE0;  bits=  6; }
        else                  {  *out++= ((c >> 18) & 0x07) | 0xF0;  bits= 12; }
 
        for ( ; bits >= 0; bits-= 6) {
            if (out >= outend)
	        break;
            *out++= ((c >> bits) & 0x3F) | 0x80;
        }
	processed = (const unsigned char*) in;
    }
    *outlen = out - outstart;
    *inlenb = processed - inb;
    return(0);
}

/**
 * UTF8ToUTF16LE:
 * @outb:  a pointer to an array of bytes to store the result
 * @outlen:  the length of @outb
 * @in:  a pointer to an array of UTF-8 chars
 * @inlen:  the length of @in
 *
 * Take a block of UTF-8 chars in and try to convert it to an UTF-16LE
 * block of chars out.
 *
 * Returns the number of byte written, or -1 by lack of space, or -2
 *     if the transcoding failed. 
 */
781
static int
782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894
UTF8ToUTF16LE(unsigned char* outb, int *outlen,
            const unsigned char* in, int *inlen)
{
    unsigned short* out = (unsigned short*) outb;
    const unsigned char* processed = in;
    unsigned short* outstart= out;
    unsigned short* outend;
    const unsigned char* inend= in+*inlen;
    unsigned int c, d;
    int trailing;
    unsigned char *tmp;
    unsigned short tmp1, tmp2;

    if (in == NULL) {
        /*
	 * initialization, add the Byte Order Mark
	 */
        if (*outlen >= 2) {
	    outb[0] = 0xFF;
	    outb[1] = 0xFE;
	    *outlen = 2;
	    *inlen = 0;
#ifdef DEBUG_ENCODING
            xmlGenericError(xmlGenericErrorContext,
		    "Added FFFE Byte Order Mark\n");
#endif
	    return(2);
	}
	*outlen = 0;
	*inlen = 0;
	return(0);
    }
    outend = out + (*outlen / 2);
    while (in < inend) {
      d= *in++;
      if      (d < 0x80)  { c= d; trailing= 0; }
      else if (d < 0xC0) {
          /* trailing byte in leading position */
	  *outlen = (out - outstart) * 2;
	  *inlen = processed - in;
	  return(-2);
      } else if (d < 0xE0)  { c= d & 0x1F; trailing= 1; }
      else if (d < 0xF0)  { c= d & 0x0F; trailing= 2; }
      else if (d < 0xF8)  { c= d & 0x07; trailing= 3; }
      else {
	/* no chance for this in UTF-16 */
	*outlen = (out - outstart) * 2;
	*inlen = processed - in;
	return(-2);
      }

      if (inend - in < trailing) {
          break;
      } 

      for ( ; trailing; trailing--) {
          if ((in >= inend) || (((d= *in++) & 0xC0) != 0x80))
	      break;
          c <<= 6;
          c |= d & 0x3F;
      }

      /* assertion: c is a single UTF-4 value */
        if (c < 0x10000) {
            if (out >= outend)
	        break;
	    if (xmlLittleEndian) {
		*out++ = c;
	    } else {
		tmp = (unsigned char *) out;
		*tmp = c ;
		*(tmp + 1) = c >> 8 ;
		out++;
	    }
        }
        else if (c < 0x110000) {
            if (out+1 >= outend)
	        break;
            c -= 0x10000;
	    if (xmlLittleEndian) {
		*out++ = 0xD800 | (c >> 10);
		*out++ = 0xDC00 | (c & 0x03FF);
	    } else {
		tmp1 = 0xD800 | (c >> 10);
		tmp = (unsigned char *) out;
		*tmp = (unsigned char) tmp1;
		*(tmp + 1) = tmp1 >> 8;
		out++;

		tmp2 = 0xDC00 | (c & 0x03FF);
		tmp = (unsigned char *) out;
		*tmp  = (unsigned char) tmp2;
		*(tmp + 1) = tmp2 >> 8;
		out++;
	    }
        }
        else
	    break;
	processed = in;
    }
    *outlen = (out - outstart) * 2;
    *inlen = processed - in;
    return(0);
}

/**
 * UTF16BEToUTF8:
 * @out:  a pointer to an array of bytes to store the result
 * @outlen:  the length of @out
 * @inb:  a pointer to an array of UTF-16 passwd as a byte array
 * @inlenb:  the length of @in in UTF-16 chars
 *
 * Take a block of UTF-16 ushorts in and try to convert it to an UTF-8
895
 * block of chars out. This function assume the endian property
896 897 898 899 900 901
 * is the same between the native type of this machine and the
 * inputed one.
 *
 * Returns the number of byte written, or -1 by lack of space, or -2
 *     if the transcoding fails (for *in is not valid utf16 string)
 * The value of *inlen after return is the number of octets consumed
902
 *     as the return value is positive, else unpredictable.
903
 */
904
static int
905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949 950 951 952 953 954 955 956 957 958 959 960 961 962 963 964 965 966 967 968 969 970 971 972 973 974 975 976 977 978 979 980 981 982 983 984 985 986 987 988 989 990 991
UTF16BEToUTF8(unsigned char* out, int *outlen,
            const unsigned char* inb, int *inlenb)
{
    unsigned char* outstart = out;
    const unsigned char* processed = inb;
    unsigned char* outend = out + *outlen;
    unsigned short* in = (unsigned short*) inb;
    unsigned short* inend;
    unsigned int c, d, inlen;
    unsigned char *tmp;
    int bits;

    if ((*inlenb % 2) == 1)
        (*inlenb)--;
    inlen = *inlenb / 2;
    inend= in + inlen;
    while (in < inend) {
	if (xmlLittleEndian) {
	    tmp = (unsigned char *) in;
	    c = *tmp++;
	    c = c << 8;
	    c = c | (unsigned int) *tmp;
	    in++;
	} else {
	    c= *in++;
	} 
        if ((c & 0xFC00) == 0xD800) {    /* surrogates */
	    if (in >= inend) {           /* (in > inend) shouldn't happens */
		*outlen = out - outstart;
		*inlenb = processed - inb;
	        return(-2);
	    }
	    if (xmlLittleEndian) {
		tmp = (unsigned char *) in;
		d = *tmp++;
		d = d << 8;
		d = d | (unsigned int) *tmp;
		in++;
	    } else {
		d= *in++;
	    }
            if ((d & 0xFC00) == 0xDC00) {
                c &= 0x03FF;
                c <<= 10;
                c |= d & 0x03FF;
                c += 0x10000;
            }
            else {
		*outlen = out - outstart;
		*inlenb = processed - inb;
	        return(-2);
	    }
        }

	/* assertion: c is a single UTF-4 value */
        if (out >= outend) 
	    break;
        if      (c <    0x80) {  *out++=  c;                bits= -6; }
        else if (c <   0x800) {  *out++= ((c >>  6) & 0x1F) | 0xC0;  bits=  0; }
        else if (c < 0x10000) {  *out++= ((c >> 12) & 0x0F) | 0xE0;  bits=  6; }
        else                  {  *out++= ((c >> 18) & 0x07) | 0xF0;  bits= 12; }
 
        for ( ; bits >= 0; bits-= 6) {
            if (out >= outend) 
	        break;
            *out++= ((c >> bits) & 0x3F) | 0x80;
        }
	processed = (const unsigned char*) in;
    }
    *outlen = out - outstart;
    *inlenb = processed - inb;
    return(0);
}

/**
 * UTF8ToUTF16BE:
 * @outb:  a pointer to an array of bytes to store the result
 * @outlen:  the length of @outb
 * @in:  a pointer to an array of UTF-8 chars
 * @inlen:  the length of @in
 *
 * Take a block of UTF-8 chars in and try to convert it to an UTF-16BE
 * block of chars out.
 *
 * Returns the number of byte written, or -1 by lack of space, or -2
 *     if the transcoding failed. 
 */
992
static int
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
UTF8ToUTF16BE(unsigned char* outb, int *outlen,
            const unsigned char* in, int *inlen)
{
    unsigned short* out = (unsigned short*) outb;
    const unsigned char* processed = in;
    unsigned short* outstart= out;
    unsigned short* outend;
    const unsigned char* inend= in+*inlen;
    unsigned int c, d;
    int trailing;
    unsigned char *tmp;
    unsigned short tmp1, tmp2;

    if (in == NULL) {
        /*
	 * initialization, add the Byte Order Mark
	 */
        if (*outlen >= 2) {
	    outb[0] = 0xFE;
	    outb[1] = 0xFF;
	    *outlen = 2;
	    *inlen = 0;
#ifdef DEBUG_ENCODING
            xmlGenericError(xmlGenericErrorContext,
		    "Added FEFF Byte Order Mark\n");
#endif
	    return(2);
	}
	*outlen = 0;
	*inlen = 0;
	return(0);
    }
    outend = out + (*outlen / 2);
    while (in < inend) {
      d= *in++;
      if      (d < 0x80)  { c= d; trailing= 0; }
      else if (d < 0xC0)  {
          /* trailing byte in leading position */
	  *outlen = out - outstart;
	  *inlen = processed - in;
	  return(-2);
      } else if (d < 0xE0)  { c= d & 0x1F; trailing= 1; }
      else if (d < 0xF0)  { c= d & 0x0F; trailing= 2; }
      else if (d < 0xF8)  { c= d & 0x07; trailing= 3; }
      else {
          /* no chance for this in UTF-16 */
	  *outlen = out - outstart;
	  *inlen = processed - in;
	  return(-2);
      }

      if (inend - in < trailing) {
          break;
      } 

      for ( ; trailing; trailing--) {
          if ((in >= inend) || (((d= *in++) & 0xC0) != 0x80))  break;
          c <<= 6;
          c |= d & 0x3F;
      }

      /* assertion: c is a single UTF-4 value */
        if (c < 0x10000) {
            if (out >= outend)  break;
	    if (xmlLittleEndian) {
		tmp = (unsigned char *) out;
		*tmp = c >> 8;
		*(tmp + 1) = c;
		out++;
	    } else {
		*out++ = c;
	    }
        }
        else if (c < 0x110000) {
            if (out+1 >= outend)  break;
            c -= 0x10000;
	    if (xmlLittleEndian) {
		tmp1 = 0xD800 | (c >> 10);
		tmp = (unsigned char *) out;
		*tmp = tmp1 >> 8;
		*(tmp + 1) = (unsigned char) tmp1;
		out++;

		tmp2 = 0xDC00 | (c & 0x03FF);
		tmp = (unsigned char *) out;
		*tmp = tmp2 >> 8;
		*(tmp + 1) = (unsigned char) tmp2;
		out++;
	    } else {
		*out++ = 0xD800 | (c >> 10);
		*out++ = 0xDC00 | (c & 0x03FF);
	    }
        }
        else
	    break;
	processed = in;
    }
    *outlen = (out - outstart) * 2;
    *inlen = processed - in;
    return(0);
}

1095 1096 1097 1098 1099 1100
/************************************************************************
 *									*
 *		Generic encoding handling routines			*
 *									*
 ************************************************************************/

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
/**
 * xmlDetectCharEncoding:
 * @in:  a pointer to the first bytes of the XML entity, must be at least
 *       4 bytes long.
 * @len:  pointer to the length of the buffer
 *
 * Guess the encoding of the entity using the first bytes of the entity content
 * accordingly of the non-normative appendix F of the XML-1.0 recommendation.
 * 
 * Returns one of the XML_CHAR_ENCODING_... values.
 */
xmlCharEncoding
xmlDetectCharEncoding(const unsigned char* in, int len)
{
    if (len >= 4) {
	if ((in[0] == 0x00) && (in[1] == 0x00) &&
	    (in[2] == 0x00) && (in[3] == 0x3C))
	    return(XML_CHAR_ENCODING_UCS4BE);
	if ((in[0] == 0x3C) && (in[1] == 0x00) &&
	    (in[2] == 0x00) && (in[3] == 0x00))
	    return(XML_CHAR_ENCODING_UCS4LE);
	if ((in[0] == 0x00) && (in[1] == 0x00) &&
	    (in[2] == 0x3C) && (in[3] == 0x00))
	    return(XML_CHAR_ENCODING_UCS4_2143);
	if ((in[0] == 0x00) && (in[1] == 0x3C) &&
	    (in[2] == 0x00) && (in[3] == 0x00))
	    return(XML_CHAR_ENCODING_UCS4_3412);
	if ((in[0] == 0x4C) && (in[1] == 0x6F) &&
	    (in[2] == 0xA7) && (in[3] == 0x94))
	    return(XML_CHAR_ENCODING_EBCDIC);
	if ((in[0] == 0x3C) && (in[1] == 0x3F) &&
	    (in[2] == 0x78) && (in[3] == 0x6D))
	    return(XML_CHAR_ENCODING_UTF8);
    }
1135 1136 1137 1138 1139 1140 1141 1142 1143
    if (len >= 3) {
	/*
	 * Errata on XML-1.0 June 20 2001
	 * We now allow an UTF8 encoded BOM
	 */
	if ((in[0] == 0xEF) && (in[1] == 0xBB) &&
	    (in[2] == 0xBF))
	    return(XML_CHAR_ENCODING_UTF8);
    }
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
    if (len >= 2) {
	if ((in[0] == 0xFE) && (in[1] == 0xFF))
	    return(XML_CHAR_ENCODING_UTF16BE);
	if ((in[0] == 0xFF) && (in[1] == 0xFE))
	    return(XML_CHAR_ENCODING_UTF16LE);
    }
    return(XML_CHAR_ENCODING_NONE);
}

/**
 * xmlCleanupEncodingAliases:
 *
 * Unregisters all aliases
 */
void
xmlCleanupEncodingAliases(void) {
    int i;

    if (xmlCharEncodingAliases == NULL)
	return;

    for (i = 0;i < xmlCharEncodingAliasesNb;i++) {
	if (xmlCharEncodingAliases[i].name != NULL)
	    xmlFree((char *) xmlCharEncodingAliases[i].name);
	if (xmlCharEncodingAliases[i].alias != NULL)
	    xmlFree((char *) xmlCharEncodingAliases[i].alias);
    }
    xmlCharEncodingAliasesNb = 0;
    xmlCharEncodingAliasesMax = 0;
    xmlFree(xmlCharEncodingAliases);
1174
    xmlCharEncodingAliases = NULL;
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 1208 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 1300 1301 1302 1303 1304 1305 1306 1307 1308
}

/**
 * xmlGetEncodingAlias:
 * @alias:  the alias name as parsed, in UTF-8 format (ASCII actually)
 *
 * Lookup an encoding name for the given alias.
 * 
 * Returns NULL if not found the original name otherwise
 */
const char *
xmlGetEncodingAlias(const char *alias) {
    int i;
    char upper[100];

    if (alias == NULL)
	return(NULL);

    if (xmlCharEncodingAliases == NULL)
	return(NULL);

    for (i = 0;i < 99;i++) {
        upper[i] = toupper(alias[i]);
	if (upper[i] == 0) break;
    }
    upper[i] = 0;

    /*
     * Walk down the list looking for a definition of the alias
     */
    for (i = 0;i < xmlCharEncodingAliasesNb;i++) {
	if (!strcmp(xmlCharEncodingAliases[i].alias, upper)) {
	    return(xmlCharEncodingAliases[i].name);
	}
    }
    return(NULL);
}

/**
 * xmlAddEncodingAlias:
 * @name:  the encoding name as parsed, in UTF-8 format (ASCII actually)
 * @alias:  the alias name as parsed, in UTF-8 format (ASCII actually)
 *
 * Registers and alias @alias for an encoding named @name. Existing alias
 * will be overwritten.
 * 
 * Returns 0 in case of success, -1 in case of error
 */
int
xmlAddEncodingAlias(const char *name, const char *alias) {
    int i;
    char upper[100];

    if ((name == NULL) || (alias == NULL))
	return(-1);

    for (i = 0;i < 99;i++) {
        upper[i] = toupper(alias[i]);
	if (upper[i] == 0) break;
    }
    upper[i] = 0;

    if (xmlCharEncodingAliases == NULL) {
	xmlCharEncodingAliasesNb = 0;
	xmlCharEncodingAliasesMax = 20;
	xmlCharEncodingAliases = (xmlCharEncodingAliasPtr) 
	      xmlMalloc(xmlCharEncodingAliasesMax * sizeof(xmlCharEncodingAlias));
	if (xmlCharEncodingAliases == NULL)
	    return(-1);
    } else if (xmlCharEncodingAliasesNb >= xmlCharEncodingAliasesMax) {
	xmlCharEncodingAliasesMax *= 2;
	xmlCharEncodingAliases = (xmlCharEncodingAliasPtr) 
	      xmlRealloc(xmlCharEncodingAliases,
		         xmlCharEncodingAliasesMax * sizeof(xmlCharEncodingAlias));
    }
    /*
     * Walk down the list looking for a definition of the alias
     */
    for (i = 0;i < xmlCharEncodingAliasesNb;i++) {
	if (!strcmp(xmlCharEncodingAliases[i].alias, upper)) {
	    /*
	     * Replace the definition.
	     */
	    xmlFree((char *) xmlCharEncodingAliases[i].name);
	    xmlCharEncodingAliases[i].name = xmlMemStrdup(name);
	    return(0);
	}
    }
    /*
     * Add the definition
     */
    xmlCharEncodingAliases[xmlCharEncodingAliasesNb].name = xmlMemStrdup(name);
    xmlCharEncodingAliases[xmlCharEncodingAliasesNb].alias = xmlMemStrdup(upper);
    xmlCharEncodingAliasesNb++;
    return(0);
}

/**
 * xmlDelEncodingAlias:
 * @alias:  the alias name as parsed, in UTF-8 format (ASCII actually)
 *
 * Unregisters an encoding alias @alias
 * 
 * Returns 0 in case of success, -1 in case of error
 */
int
xmlDelEncodingAlias(const char *alias) {
    int i;

    if (alias == NULL)
	return(-1);

    if (xmlCharEncodingAliases == NULL)
	return(-1);
    /*
     * Walk down the list looking for a definition of the alias
     */
    for (i = 0;i < xmlCharEncodingAliasesNb;i++) {
	if (!strcmp(xmlCharEncodingAliases[i].alias, alias)) {
	    xmlFree((char *) xmlCharEncodingAliases[i].name);
	    xmlFree((char *) xmlCharEncodingAliases[i].alias);
	    xmlCharEncodingAliasesNb--;
	    memmove(&xmlCharEncodingAliases[i], &xmlCharEncodingAliases[i + 1],
		    sizeof(xmlCharEncodingAlias) * (xmlCharEncodingAliasesNb - i));
	    return(0);
	}
    }
    return(-1);
}

/**
 * xmlParseCharEncoding:
 * @name:  the encoding name as parsed, in UTF-8 format (ASCII actually)
 *
1309
 * Compare the string to the known encoding schemes already known. Note
1310 1311 1312 1313 1314 1315 1316 1317 1318 1319 1320 1321 1322 1323 1324 1325 1326 1327 1328 1329 1330 1331 1332 1333 1334 1335 1336 1337 1338 1339 1340 1341 1342 1343 1344 1345 1346 1347 1348 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 1376 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 1422 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
 * that the comparison is case insensitive accordingly to the section
 * [XML] 4.3.3 Character Encoding in Entities.
 * 
 * Returns one of the XML_CHAR_ENCODING_... values or XML_CHAR_ENCODING_NONE
 * if not recognized.
 */
xmlCharEncoding
xmlParseCharEncoding(const char* name)
{
    const char *alias;
    char upper[500];
    int i;

    if (name == NULL)
	return(XML_CHAR_ENCODING_NONE);

    /*
     * Do the alias resolution
     */
    alias = xmlGetEncodingAlias(name);
    if (alias != NULL)
	name = alias;

    for (i = 0;i < 499;i++) {
        upper[i] = toupper(name[i]);
	if (upper[i] == 0) break;
    }
    upper[i] = 0;

    if (!strcmp(upper, "")) return(XML_CHAR_ENCODING_NONE);
    if (!strcmp(upper, "UTF-8")) return(XML_CHAR_ENCODING_UTF8);
    if (!strcmp(upper, "UTF8")) return(XML_CHAR_ENCODING_UTF8);

    /*
     * NOTE: if we were able to parse this, the endianness of UTF16 is
     *       already found and in use
     */
    if (!strcmp(upper, "UTF-16")) return(XML_CHAR_ENCODING_UTF16LE);
    if (!strcmp(upper, "UTF16")) return(XML_CHAR_ENCODING_UTF16LE);
    
    if (!strcmp(upper, "ISO-10646-UCS-2")) return(XML_CHAR_ENCODING_UCS2);
    if (!strcmp(upper, "UCS-2")) return(XML_CHAR_ENCODING_UCS2);
    if (!strcmp(upper, "UCS2")) return(XML_CHAR_ENCODING_UCS2);

    /*
     * NOTE: if we were able to parse this, the endianness of UCS4 is
     *       already found and in use
     */
    if (!strcmp(upper, "ISO-10646-UCS-4")) return(XML_CHAR_ENCODING_UCS4LE);
    if (!strcmp(upper, "UCS-4")) return(XML_CHAR_ENCODING_UCS4LE);
    if (!strcmp(upper, "UCS4")) return(XML_CHAR_ENCODING_UCS4LE);

    
    if (!strcmp(upper,  "ISO-8859-1")) return(XML_CHAR_ENCODING_8859_1);
    if (!strcmp(upper,  "ISO-LATIN-1")) return(XML_CHAR_ENCODING_8859_1);
    if (!strcmp(upper,  "ISO LATIN 1")) return(XML_CHAR_ENCODING_8859_1);

    if (!strcmp(upper,  "ISO-8859-2")) return(XML_CHAR_ENCODING_8859_2);
    if (!strcmp(upper,  "ISO-LATIN-2")) return(XML_CHAR_ENCODING_8859_2);
    if (!strcmp(upper,  "ISO LATIN 2")) return(XML_CHAR_ENCODING_8859_2);

    if (!strcmp(upper,  "ISO-8859-3")) return(XML_CHAR_ENCODING_8859_3);
    if (!strcmp(upper,  "ISO-8859-4")) return(XML_CHAR_ENCODING_8859_4);
    if (!strcmp(upper,  "ISO-8859-5")) return(XML_CHAR_ENCODING_8859_5);
    if (!strcmp(upper,  "ISO-8859-6")) return(XML_CHAR_ENCODING_8859_6);
    if (!strcmp(upper,  "ISO-8859-7")) return(XML_CHAR_ENCODING_8859_7);
    if (!strcmp(upper,  "ISO-8859-8")) return(XML_CHAR_ENCODING_8859_8);
    if (!strcmp(upper,  "ISO-8859-9")) return(XML_CHAR_ENCODING_8859_9);

    if (!strcmp(upper, "ISO-2022-JP")) return(XML_CHAR_ENCODING_2022_JP);
    if (!strcmp(upper, "SHIFT_JIS")) return(XML_CHAR_ENCODING_SHIFT_JIS);
    if (!strcmp(upper, "EUC-JP")) return(XML_CHAR_ENCODING_EUC_JP);

#ifdef DEBUG_ENCODING
    xmlGenericError(xmlGenericErrorContext, "Unknown encoding %s\n", name);
#endif
    return(XML_CHAR_ENCODING_ERROR);
}

/**
 * xmlGetCharEncodingName:
 * @enc:  the encoding
 *
 * The "canonical" name for XML encoding.
 * C.f. http://www.w3.org/TR/REC-xml#charencoding
 * Section 4.3.3  Character Encoding in Entities
 *
 * Returns the canonical name for the given encoding
 */

const char*
xmlGetCharEncodingName(xmlCharEncoding enc) {
    switch (enc) {
        case XML_CHAR_ENCODING_ERROR:
	    return(NULL);
        case XML_CHAR_ENCODING_NONE:
	    return(NULL);
        case XML_CHAR_ENCODING_UTF8:
	    return("UTF-8");
        case XML_CHAR_ENCODING_UTF16LE:
	    return("UTF-16");
        case XML_CHAR_ENCODING_UTF16BE:
	    return("UTF-16");
        case XML_CHAR_ENCODING_EBCDIC:
            return("EBCDIC");
        case XML_CHAR_ENCODING_UCS4LE:
            return("ISO-10646-UCS-4");
        case XML_CHAR_ENCODING_UCS4BE:
            return("ISO-10646-UCS-4");
        case XML_CHAR_ENCODING_UCS4_2143:
            return("ISO-10646-UCS-4");
        case XML_CHAR_ENCODING_UCS4_3412:
            return("ISO-10646-UCS-4");
        case XML_CHAR_ENCODING_UCS2:
            return("ISO-10646-UCS-2");
        case XML_CHAR_ENCODING_8859_1:
	    return("ISO-8859-1");
        case XML_CHAR_ENCODING_8859_2:
	    return("ISO-8859-2");
        case XML_CHAR_ENCODING_8859_3:
	    return("ISO-8859-3");
        case XML_CHAR_ENCODING_8859_4:
	    return("ISO-8859-4");
        case XML_CHAR_ENCODING_8859_5:
	    return("ISO-8859-5");
        case XML_CHAR_ENCODING_8859_6:
	    return("ISO-8859-6");
        case XML_CHAR_ENCODING_8859_7:
	    return("ISO-8859-7");
        case XML_CHAR_ENCODING_8859_8:
	    return("ISO-8859-8");
        case XML_CHAR_ENCODING_8859_9:
	    return("ISO-8859-9");
        case XML_CHAR_ENCODING_2022_JP:
            return("ISO-2022-JP");
        case XML_CHAR_ENCODING_SHIFT_JIS:
            return("Shift-JIS");
        case XML_CHAR_ENCODING_EUC_JP:
            return("EUC-JP");
	case XML_CHAR_ENCODING_ASCII:
	    return(NULL);
    }
    return(NULL);
}

1455 1456 1457 1458 1459 1460
/************************************************************************
 *									*
 *			Char encoding handlers				*
 *									*
 ************************************************************************/

1461 1462 1463 1464 1465 1466 1467 1468 1469 1470 1471 1472 1473 1474 1475 1476 1477 1478 1479 1480 1481 1482

/* the size should be growable, but it's not a big deal ... */
#define MAX_ENCODING_HANDLERS 50
static xmlCharEncodingHandlerPtr *handlers = NULL;
static int nbCharEncodingHandler = 0;

/*
 * The default is UTF-8 for XML, that's also the default used for the
 * parser internals, so the default encoding handler is NULL
 */

static xmlCharEncodingHandlerPtr xmlDefaultCharEncodingHandler = NULL;

/**
 * xmlNewCharEncodingHandler:
 * @name:  the encoding name, in UTF-8 format (ASCII actually)
 * @input:  the xmlCharEncodingInputFunc to read that encoding
 * @output:  the xmlCharEncodingOutputFunc to write that encoding
 *
 * Create and registers an xmlCharEncodingHandler.
 * Returns the xmlCharEncodingHandlerPtr created (or NULL in case of error).
 */
1483
static xmlCharEncodingHandlerPtr
1484 1485 1486 1487 1488 1489 1490 1491 1492 1493 1494 1495 1496 1497 1498 1499 1500 1501 1502 1503 1504 1505 1506 1507 1508 1509 1510 1511 1512 1513 1514 1515 1516 1517 1518 1519 1520 1521 1522 1523 1524 1525 1526 1527 1528 1529 1530 1531 1532 1533 1534 1535 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
xmlNewCharEncodingHandler(const char *name, 
                          xmlCharEncodingInputFunc input,
                          xmlCharEncodingOutputFunc output) {
    xmlCharEncodingHandlerPtr handler;
    const char *alias;
    char upper[500];
    int i;
    char *up = 0;

    /*
     * Do the alias resolution
     */
    alias = xmlGetEncodingAlias(name);
    if (alias != NULL)
	name = alias;

    /*
     * Keep only the uppercase version of the encoding.
     */
    if (name == NULL) {
        xmlGenericError(xmlGenericErrorContext,
		"xmlNewCharEncodingHandler : no name !\n");
	return(NULL);
    }
    for (i = 0;i < 499;i++) {
        upper[i] = toupper(name[i]);
	if (upper[i] == 0) break;
    }
    upper[i] = 0;
    up = xmlMemStrdup(upper);
    if (up == NULL) {
        xmlGenericError(xmlGenericErrorContext,
		"xmlNewCharEncodingHandler : out of memory !\n");
	return(NULL);
    }

    /*
     * allocate and fill-up an handler block.
     */
    handler = (xmlCharEncodingHandlerPtr)
              xmlMalloc(sizeof(xmlCharEncodingHandler));
    if (handler == NULL) {
        xmlGenericError(xmlGenericErrorContext,
		"xmlNewCharEncodingHandler : out of memory !\n");
	return(NULL);
    }
    handler->input = input;
    handler->output = output;
    handler->name = up;

#ifdef LIBXML_ICONV_ENABLED
    handler->iconv_in = NULL;
    handler->iconv_out = NULL;
#endif /* LIBXML_ICONV_ENABLED */

    /*
     * registers and returns the handler.
     */
    xmlRegisterCharEncodingHandler(handler);
#ifdef DEBUG_ENCODING
    xmlGenericError(xmlGenericErrorContext,
	    "Registered encoding handler for %s\n", name);
#endif
    return(handler);
}

/**
 * xmlInitCharEncodingHandlers:
 *
 * Initialize the char encoding support, it registers the default
 * encoding supported.
 * NOTE: while public, this function usually doesn't need to be called
 *       in normal processing.
 */
void
xmlInitCharEncodingHandlers(void) {
    unsigned short int tst = 0x1234;
    unsigned char *ptr = (unsigned char *) &tst; 

    if (handlers != NULL) return;

    handlers = (xmlCharEncodingHandlerPtr *)
        xmlMalloc(MAX_ENCODING_HANDLERS * sizeof(xmlCharEncodingHandlerPtr));

    if (*ptr == 0x12) xmlLittleEndian = 0;
    else if (*ptr == 0x34) xmlLittleEndian = 1;
    else xmlGenericError(xmlGenericErrorContext,
	    "Odd problem at endianness detection\n");

    if (handlers == NULL) {
        xmlGenericError(xmlGenericErrorContext,
		"xmlInitCharEncodingHandlers : out of memory !\n");
	return;
    }
    xmlNewCharEncodingHandler("UTF-8", NULL, NULL);
    xmlUTF16LEHandler = 
          xmlNewCharEncodingHandler("UTF-16LE", UTF16LEToUTF8, UTF8ToUTF16LE);
    xmlUTF16BEHandler = 
          xmlNewCharEncodingHandler("UTF-16BE", UTF16BEToUTF8, UTF8ToUTF16BE);
    xmlNewCharEncodingHandler("ISO-8859-1", isolat1ToUTF8, UTF8Toisolat1);
    xmlNewCharEncodingHandler("ASCII", asciiToUTF8, UTF8Toascii);
1585
    xmlNewCharEncodingHandler("US-ASCII", asciiToUTF8, UTF8Toascii);
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
#ifdef LIBXML_HTML_ENABLED
    xmlNewCharEncodingHandler("HTML", NULL, UTF8ToHtml);
#endif
}

/**
 * xmlCleanupCharEncodingHandlers:
 *
 * Cleanup the memory allocated for the char encoding support, it
 * unregisters all the encoding handlers and the aliases.
 */
void
xmlCleanupCharEncodingHandlers(void) {
    xmlCleanupEncodingAliases();

    if (handlers == NULL) return;

    for (;nbCharEncodingHandler > 0;) {
        nbCharEncodingHandler--;
	if (handlers[nbCharEncodingHandler] != NULL) {
	    if (handlers[nbCharEncodingHandler]->name != NULL)
		xmlFree(handlers[nbCharEncodingHandler]->name);
	    xmlFree(handlers[nbCharEncodingHandler]);
	}
    }
    xmlFree(handlers);
    handlers = NULL;
    nbCharEncodingHandler = 0;
    xmlDefaultCharEncodingHandler = NULL;
}

/**
 * xmlRegisterCharEncodingHandler:
 * @handler:  the xmlCharEncodingHandlerPtr handler block
 *
1621
 * Register the char encoding handler, surprising, isn't it ?
1622 1623 1624 1625 1626 1627 1628 1629 1630 1631 1632 1633 1634 1635 1636 1637 1638 1639 1640 1641 1642 1643 1644 1645
 */
void
xmlRegisterCharEncodingHandler(xmlCharEncodingHandlerPtr handler) {
    if (handlers == NULL) xmlInitCharEncodingHandlers();
    if (handler == NULL) {
        xmlGenericError(xmlGenericErrorContext,
		"xmlRegisterCharEncodingHandler: NULL handler !\n");
	return;
    }

    if (nbCharEncodingHandler >= MAX_ENCODING_HANDLERS) {
        xmlGenericError(xmlGenericErrorContext, 
	"xmlRegisterCharEncodingHandler: Too many handler registered\n");
        xmlGenericError(xmlGenericErrorContext,
		"\tincrease MAX_ENCODING_HANDLERS : %s\n", __FILE__);
	return;
    }
    handlers[nbCharEncodingHandler++] = handler;
}

/**
 * xmlGetCharEncodingHandler:
 * @enc:  an xmlCharEncoding value.
 *
1646
 * Search in the registered set the handler able to read/write that encoding.
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 1699 1700 1701 1702 1703 1704 1705 1706 1707 1708 1709 1710 1711 1712 1713 1714 1715 1716 1717 1718 1719 1720 1721 1722 1723 1724 1725 1726 1727 1728 1729 1730 1731 1732 1733 1734 1735 1736 1737 1738 1739 1740 1741 1742 1743 1744 1745 1746 1747 1748 1749 1750 1751 1752 1753 1754 1755 1756 1757 1758 1759 1760 1761 1762 1763 1764 1765 1766 1767 1768 1769 1770 1771 1772
 *
 * Returns the handler or NULL if not found
 */
xmlCharEncodingHandlerPtr
xmlGetCharEncodingHandler(xmlCharEncoding enc) {
    xmlCharEncodingHandlerPtr handler;

    if (handlers == NULL) xmlInitCharEncodingHandlers();
    switch (enc) {
        case XML_CHAR_ENCODING_ERROR:
	    return(NULL);
        case XML_CHAR_ENCODING_NONE:
	    return(NULL);
        case XML_CHAR_ENCODING_UTF8:
	    return(NULL);
        case XML_CHAR_ENCODING_UTF16LE:
	    return(xmlUTF16LEHandler);
        case XML_CHAR_ENCODING_UTF16BE:
	    return(xmlUTF16BEHandler);
        case XML_CHAR_ENCODING_EBCDIC:
            handler = xmlFindCharEncodingHandler("EBCDIC");
            if (handler != NULL) return(handler);
            handler = xmlFindCharEncodingHandler("ebcdic");
            if (handler != NULL) return(handler);
	    break;
        case XML_CHAR_ENCODING_UCS4BE:
            handler = xmlFindCharEncodingHandler("ISO-10646-UCS-4");
            if (handler != NULL) return(handler);
            handler = xmlFindCharEncodingHandler("UCS-4");
            if (handler != NULL) return(handler);
            handler = xmlFindCharEncodingHandler("UCS4");
            if (handler != NULL) return(handler);
	    break;
        case XML_CHAR_ENCODING_UCS4LE:
            handler = xmlFindCharEncodingHandler("ISO-10646-UCS-4");
            if (handler != NULL) return(handler);
            handler = xmlFindCharEncodingHandler("UCS-4");
            if (handler != NULL) return(handler);
            handler = xmlFindCharEncodingHandler("UCS4");
            if (handler != NULL) return(handler);
	    break;
        case XML_CHAR_ENCODING_UCS4_2143:
	    break;
        case XML_CHAR_ENCODING_UCS4_3412:
	    break;
        case XML_CHAR_ENCODING_UCS2:
            handler = xmlFindCharEncodingHandler("ISO-10646-UCS-2");
            if (handler != NULL) return(handler);
            handler = xmlFindCharEncodingHandler("UCS-2");
            if (handler != NULL) return(handler);
            handler = xmlFindCharEncodingHandler("UCS2");
            if (handler != NULL) return(handler);
	    break;

	    /*
	     * We used to keep ISO Latin encodings native in the
	     * generated data. This led to so many problems that
	     * this has been removed. One can still change this
	     * back by registering no-ops encoders for those
	     */
        case XML_CHAR_ENCODING_8859_1:
	    handler = xmlFindCharEncodingHandler("ISO-8859-1");
	    if (handler != NULL) return(handler);
	    break;
        case XML_CHAR_ENCODING_8859_2:
	    handler = xmlFindCharEncodingHandler("ISO-8859-2");
	    if (handler != NULL) return(handler);
	    break;
        case XML_CHAR_ENCODING_8859_3:
	    handler = xmlFindCharEncodingHandler("ISO-8859-3");
	    if (handler != NULL) return(handler);
	    break;
        case XML_CHAR_ENCODING_8859_4:
	    handler = xmlFindCharEncodingHandler("ISO-8859-4");
	    if (handler != NULL) return(handler);
	    break;
        case XML_CHAR_ENCODING_8859_5:
	    handler = xmlFindCharEncodingHandler("ISO-8859-5");
	    if (handler != NULL) return(handler);
	    break;
        case XML_CHAR_ENCODING_8859_6:
	    handler = xmlFindCharEncodingHandler("ISO-8859-6");
	    if (handler != NULL) return(handler);
	    break;
        case XML_CHAR_ENCODING_8859_7:
	    handler = xmlFindCharEncodingHandler("ISO-8859-7");
	    if (handler != NULL) return(handler);
	    break;
        case XML_CHAR_ENCODING_8859_8:
	    handler = xmlFindCharEncodingHandler("ISO-8859-8");
	    if (handler != NULL) return(handler);
	    break;
        case XML_CHAR_ENCODING_8859_9:
	    handler = xmlFindCharEncodingHandler("ISO-8859-9");
	    if (handler != NULL) return(handler);
	    break;


        case XML_CHAR_ENCODING_2022_JP:
            handler = xmlFindCharEncodingHandler("ISO-2022-JP");
            if (handler != NULL) return(handler);
	    break;
        case XML_CHAR_ENCODING_SHIFT_JIS:
            handler = xmlFindCharEncodingHandler("SHIFT-JIS");
            if (handler != NULL) return(handler);
            handler = xmlFindCharEncodingHandler("SHIFT_JIS");
            if (handler != NULL) return(handler);
            handler = xmlFindCharEncodingHandler("Shift_JIS");
            if (handler != NULL) return(handler);
	    break;
        case XML_CHAR_ENCODING_EUC_JP:
            handler = xmlFindCharEncodingHandler("EUC-JP");
            if (handler != NULL) return(handler);
	    break;
	default: 
	    break;
    }
    
#ifdef DEBUG_ENCODING
    xmlGenericError(xmlGenericErrorContext,
	    "No handler found for encoding %d\n", enc);
#endif
    return(NULL);
}

/**
1773 1774
 * xmlFindCharEncodingHandler:
 * @name:  a string describing the char encoding.
1775
 *
1776
 * Search in the registered set the handler able to read/write that encoding.
1777 1778 1779 1780 1781 1782 1783 1784 1785 1786 1787 1788 1789 1790 1791 1792 1793 1794 1795 1796 1797 1798 1799 1800 1801 1802 1803 1804 1805 1806 1807 1808 1809 1810 1811 1812 1813 1814 1815 1816 1817 1818 1819 1820 1821 1822 1823 1824 1825 1826 1827 1828 1829 1830 1831 1832 1833 1834 1835 1836 1837 1838 1839 1840 1841 1842 1843 1844 1845 1846 1847 1848 1849 1850 1851 1852 1853 1854 1855 1856 1857 1858 1859 1860 1861 1862 1863 1864 1865 1866 1867 1868 1869
 *
 * Returns the handler or NULL if not found
 */
xmlCharEncodingHandlerPtr
xmlFindCharEncodingHandler(const char *name) {
    const char *nalias;
    const char *norig;
    xmlCharEncoding alias;
#ifdef LIBXML_ICONV_ENABLED
    xmlCharEncodingHandlerPtr enc;
    iconv_t icv_in, icv_out;
#endif /* LIBXML_ICONV_ENABLED */
    char upper[100];
    int i;

    if (handlers == NULL) xmlInitCharEncodingHandlers();
    if (name == NULL) return(xmlDefaultCharEncodingHandler);
    if (name[0] == 0) return(xmlDefaultCharEncodingHandler);

    /*
     * Do the alias resolution
     */
    norig = name;
    nalias = xmlGetEncodingAlias(name);
    if (nalias != NULL)
	name = nalias;

    /*
     * Check first for directly registered encoding names
     */
    for (i = 0;i < 99;i++) {
        upper[i] = toupper(name[i]);
	if (upper[i] == 0) break;
    }
    upper[i] = 0;

    for (i = 0;i < nbCharEncodingHandler; i++)
        if (!strcmp(upper, handlers[i]->name)) {
#ifdef DEBUG_ENCODING
            xmlGenericError(xmlGenericErrorContext,
		    "Found registered handler for encoding %s\n", name);
#endif
	    return(handlers[i]);
	}

#ifdef LIBXML_ICONV_ENABLED
    /* check whether iconv can handle this */
    icv_in = iconv_open("UTF-8", name);
    icv_out = iconv_open(name, "UTF-8");
    if ((icv_in != (iconv_t) -1) && (icv_out != (iconv_t) -1)) {
	    enc = (xmlCharEncodingHandlerPtr)
	          xmlMalloc(sizeof(xmlCharEncodingHandler));
	    if (enc == NULL) {
	        iconv_close(icv_in);
	        iconv_close(icv_out);
		return(NULL);
	    }
	    enc->name = xmlMemStrdup(name);
	    enc->input = NULL;
	    enc->output = NULL;
	    enc->iconv_in = icv_in;
	    enc->iconv_out = icv_out;
#ifdef DEBUG_ENCODING
            xmlGenericError(xmlGenericErrorContext,
		    "Found iconv handler for encoding %s\n", name);
#endif
	    return enc;
    } else