1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949 950 951 952 953 954 955 956 957 958 959 960 961 962 963 964 965 966 967 968 969 970 971 972 973 974 975 976 977 978 979 980 981 982 983 984 985 986 987 988 989 990 991 992 993 994 995 996 997 998 999 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
|
/*===========================================================================
* Filename : encoding.c
* About : Character encoding handling
*
* Copyright (C) 2005 Kazuki Ohta <mover AT hct.zaq.ne.jp>
* Copyright (C) 2005 Jun Inoue <jun.lambda AT gmail.com>
* Copyright (C) 2005-2006 YAMAMOTO Kengo <yamaken AT bp.iij4u.or.jp>
* Copyright (c) 2007-2008 SigScheme Project <uim-en AT googlegroups.com>
*
* All rights reserved.
*
* Redistribution and use in source and binary forms, with or without
* modification, are permitted provided that the following conditions
* are met:
*
* 1. Redistributions of source code must retain the above copyright
* notice, this list of conditions and the following disclaimer.
* 2. Redistributions in binary form must reproduce the above copyright
* notice, this list of conditions and the following disclaimer in the
* documentation and/or other materials provided with the distribution.
* 3. Neither the name of authors nor the names of its contributors
* may be used to endorse or promote products derived from this software
* without specific prior written permission.
*
* THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS ``AS
* IS'' AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO,
* THE IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR
* PURPOSE ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT HOLDERS OR
* CONTRIBUTORS BE LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL,
* EXEMPLARY, OR CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT LIMITED TO,
* PROCUREMENT OF SUBSTITUTE GOODS OR SERVICES; LOSS OF USE, DATA, OR PROFITS;
* OR BUSINESS INTERRUPTION) HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY,
* WHETHER IN CONTRACT, STRICT LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR
* OTHERWISE) ARISING IN ANY WAY OUT OF THE USE OF THIS SOFTWARE, EVEN IF
* ADVISED OF THE POSSIBILITY OF SUCH DAMAGE.
===========================================================================*/
/* Acknowledgement: much information was gained from the
* i18n-introduction of the debian project. Many thanks to its
* authors, Tomohiro KUBOTA, et al. */
/*
* This file is intended to be portable. Don't depend on SigScheme and don't
* merge into another file.
*/
#include <config.h>
#include <stdlib.h>
#include <string.h>
#include "scmint.h"
#include "encoding-config.h"
#include "encoding.h"
/*=======================================
File Local Macro Definitions
=======================================*/
/*=======================================
File Local Type Definitions
=======================================*/
typedef unsigned char uchar;
/*=======================================
File Local Functions
=======================================*/
static scm_bool pred_always_true(void) SCM_UNUSED;
static scm_bool pred_always_false(void) SCM_UNUSED;
#if SCM_USE_EUCJP
static const char *eucjp_encoding(void);
static enum ScmCodedCharSet eucjp_ccs(void);
static int eucjp_char_len(scm_ichar_t ch);
static ScmMultibyteCharInfo eucjp_scan_char(ScmMultibyteString mbs);
static scm_ichar_t eucjp_str2int(const uchar *src, size_t len,
ScmMultibyteState state);
static uchar *eucjp_int2str(uchar *dst, scm_ichar_t ch,
ScmMultibyteState state);
#endif
#if SCM_USE_ISO2022KR
static ScmMultibyteCharInfo iso2022kr_scan_char(ScmMultibyteString mbs);
static ScmMultibyteCharInfo iso2022kr_scan_input_char(ScmMultibyteString mbs);
#endif
#if SCM_USE_ISO2022JP
static ScmMultibyteCharInfo iso2022jp_scan_char(ScmMultibyteString mbs);
static ScmMultibyteCharInfo iso2022jp_scan_input_char(ScmMultibyteString mbs);
#endif
#if SCM_USE_SJIS
static const char *sjis_encoding(void);
static enum ScmCodedCharSet sjis_ccs(void);
static int sjis_char_len(scm_ichar_t ch);
static ScmMultibyteCharInfo sjis_scan_char(ScmMultibyteString mbs);
static uchar *sjis_int2str(uchar *dst, scm_ichar_t ch,
ScmMultibyteState state);
#endif
#if (SCM_USE_EUCCN || SCM_USE_EUCKR || SCM_USE_SJIS)
/* generic double-byte char */
static scm_ichar_t dbc_str2int(const uchar *src, size_t len,
ScmMultibyteState state);
#endif
#if (SCM_USE_EUCCN || SCM_USE_EUCKR)
/* shared by EUCCN and EUCKR */
static int euc_char_len(scm_ichar_t ch);
static uchar *euc_int2str(uchar *dst, scm_ichar_t ch, ScmMultibyteState state);
#endif
#if SCM_USE_EUCCN
static const char *euccn_encoding(void);
static enum ScmCodedCharSet euccn_ccs(void);
static ScmMultibyteCharInfo euccn_scan_char(ScmMultibyteString mbs);
#endif
#if SCM_USE_EUCKR
static const char *euckr_encoding(void);
static enum ScmCodedCharSet euckr_ccs(void);
static ScmMultibyteCharInfo euckr_scan_char(ScmMultibyteString mbs);
#endif
#if SCM_USE_UTF8
static const char *utf8_encoding(void);
static enum ScmCodedCharSet utf8_ccs(void);
static int utf8_char_len(scm_ichar_t ch);
static ScmMultibyteCharInfo utf8_scan_char(ScmMultibyteString mbs);
static scm_ichar_t utf8_str2int(const uchar *src, size_t len,
ScmMultibyteState state);
static uchar *utf8_int2str(uchar *dst, scm_ichar_t ch,
ScmMultibyteState state);
#endif
static const char *unibyte_encoding(void);
static enum ScmCodedCharSet unibyte_ccs(void);
static int unibyte_char_len(scm_ichar_t ch);
static ScmMultibyteCharInfo unibyte_scan_char(ScmMultibyteString mbs);
static scm_ichar_t unibyte_str2int(const uchar *src, size_t len,
ScmMultibyteState state);
static uchar *unibyte_int2str(uchar *dst, scm_ichar_t ch,
ScmMultibyteState state);
/*=======================================
Local Variables
=======================================*/
#if SCM_USE_UTF8
static const ScmCharCodecVTbl utf8_codec_vtbl = {
&pred_always_false,
&utf8_encoding,
&utf8_ccs,
&utf8_char_len,
&utf8_scan_char,
(ScmCharCodecMethod_str2int)&utf8_str2int,
(ScmCharCodecMethod_int2str)&utf8_int2str
};
#define utf8_codec (&utf8_codec_vtbl)
#endif
#if SCM_USE_EUCCN
static const ScmCharCodecVTbl euccn_codec_vtbl = {
&pred_always_false,
&euccn_encoding,
&euccn_ccs,
&euc_char_len,
&euccn_scan_char,
(ScmCharCodecMethod_str2int)&dbc_str2int,
(ScmCharCodecMethod_int2str)&euc_int2str
};
#define euccn_codec (&euccn_codec_vtbl)
#endif
#if SCM_USE_EUCJP
static const ScmCharCodecVTbl eucjp_codec_vtbl = {
&pred_always_false,
&eucjp_encoding,
&eucjp_ccs,
&eucjp_char_len,
&eucjp_scan_char,
(ScmCharCodecMethod_str2int)&eucjp_str2int,
(ScmCharCodecMethod_int2str)&eucjp_int2str
};
#define eucjp_codec (&eucjp_codec_vtbl)
#endif
#if SCM_USE_EUCKR
static const ScmCharCodecVTbl euckr_codec_vtbl = {
&pred_always_false,
&euckr_encoding,
&euckr_ccs,
&euc_char_len,
&euckr_scan_char,
(ScmCharCodecMethod_str2int)&dbc_str2int,
(ScmCharCodecMethod_int2str)&euc_int2str
};
#define euckr_codec (&euckr_codec_vtbl)
#endif
#if SCM_USE_SJIS
static const ScmCharCodecVTbl sjis_codec_vtbl = {
&pred_always_false,
&sjis_encoding,
&sjis_ccs,
&sjis_char_len,
&sjis_scan_char,
(ScmCharCodecMethod_str2int)&dbc_str2int,
(ScmCharCodecMethod_int2str)&sjis_int2str
};
#define sjis_codec (&sjis_codec_vtbl)
#endif
static const ScmCharCodecVTbl unibyte_codec_vtbl = {
&pred_always_false,
&unibyte_encoding,
&unibyte_ccs,
&unibyte_char_len,
&unibyte_scan_char,
(ScmCharCodecMethod_str2int)&unibyte_str2int,
(ScmCharCodecMethod_int2str)&unibyte_int2str
};
#define unibyte_codec (&unibyte_codec_vtbl)
static ScmCharCodec *const available_codecs[] = {
#if SCM_USE_UTF8
utf8_codec,
#endif
#if SCM_USE_EUCJP
eucjp_codec,
#endif
#if SCM_USE_EUCCN
euccn_codec,
#endif
#if SCM_USE_EUCKR
euckr_codec,
#endif
#if SCM_USE_SJIS
sjis_codec,
#endif
unibyte_codec,
NULL
};
/*=======================================
Global Variables
=======================================*/
SCM_DEFINE_EXPORTED_VARS(encoding);
/*=======================================
Public API
=======================================*/
SCM_EXPORT void
scm_encoding_init(void)
{
SCM_GLOBAL_VARS_INIT(encoding);
/* To allow re-initialization of the interpreter, this variables must be
* initialized by assignment. Initialized .data section does not work for
* such situation. -- YamaKen 2006-03-31 */
/* temporary solution */
scm_current_char_codec
#if SCM_USE_UTF8_AS_DEFAULT
= utf8_codec;
#elif SCM_USE_EUCJP_AS_DEFAULT
= eucjp_codec;
#elif SCM_USE_EUCCN_AS_DEFAULT
= euccn_codec;
#elif SCM_USE_EUCKR_AS_DEFAULT
= euckr_codec;
#elif SCM_USE_SJIS_AS_DEFAULT
= sjis_codec;
#else
= unibyte_codec;
#endif
}
SCM_EXPORT size_t
scm_mb_strlen(ScmCharCodec *codec, ScmMultibyteString mbs)
{
size_t len;
ScmMultibyteCharInfo c;
SCM_ENCODING_CDBG((SCM_DBG_ENCODING, "mb_strlen: size = ~ZU; str = ~S;",
SCM_MBS_GET_SIZE(mbs), SCM_MBS_GET_STR(mbs)));
for (len = 0; SCM_MBS_GET_SIZE(mbs); len++) {
c = SCM_CHARCODEC_SCAN_CHAR(codec, mbs);
SCM_ENCODING_CDBG((SCM_DBG_ENCODING, "~ZU, ~D;",
SCM_MBCINFO_GET_SIZE(c), c.flag));
SCM_MBS_SKIP_CHAR(mbs, c);
}
SCM_ENCODING_CDBG((SCM_DBG_ENCODING, "len=~ZU\n", len));
return len;
}
/* FIXME: pick a better name. */
SCM_EXPORT size_t
scm_mb_bare_c_strlen(ScmCharCodec *codec, const char *s)
{
ScmMultibyteString mbs;
SCM_MBS_INIT2(mbs, s, strlen(s));
return scm_mb_strlen(codec, mbs);
}
SCM_EXPORT ScmMultibyteString
scm_mb_substring(ScmCharCodec *codec,
ScmMultibyteString mbs, size_t i, size_t len)
{
ScmMultibyteString ret, end;
ScmMultibyteCharInfo c;
ret = mbs;
while (i--) {
c = SCM_CHARCODEC_SCAN_CHAR(codec, ret);
SCM_MBS_SKIP_CHAR(ret, c);
}
end = ret;
while (len--) {
c = SCM_CHARCODEC_SCAN_CHAR(codec, end);
SCM_MBS_SKIP_CHAR(end, c);
}
SCM_MBS_SET_SIZE(ret, SCM_MBS_GET_STR(end) - SCM_MBS_GET_STR(ret));
return ret;
}
/* TODO: support encoding name canonicalization */
SCM_EXPORT ScmCharCodec *
scm_mb_find_codec(const char *encoding)
{
ScmCharCodec *const *codecp;
for (codecp = &available_codecs[0]; *codecp; codecp++) {
if (strcmp(SCM_CHARCODEC_ENCODING(*codecp), encoding) == 0)
return *codecp;
}
return NULL;
}
SCM_EXPORT scm_ichar_t
scm_charcodec_read_char(ScmCharCodec *codec, ScmMultibyteString *mbs,
const char *caller)
{
ScmMultibyteCharInfo mbc;
ScmMultibyteState state;
scm_ichar_t ch;
SCM_ENCODING_ASSERT(SCM_MBS_GET_SIZE(*mbs));
state = SCM_MBS_GET_STATE(*mbs);
mbc = SCM_CHARCODEC_SCAN_CHAR(codec, *mbs);
if (SCM_MBCINFO_ERRORP(mbc) || SCM_MBCINFO_INCOMPLETEP(mbc))
SCM_ENCODING_ERROR("scm_charcodec_read_char: invalid char sequence");
ch = SCM_CHARCODEC_STR2INT(codec,
SCM_MBS_GET_STR(*mbs),
SCM_MBCINFO_GET_SIZE(mbc),
state);
if (ch == SCM_ICHAR_EOF)
SCM_ENCODING_ERROR("scm_charcodec_read_char: invalid char sequence");
SCM_MBS_SKIP_CHAR(*mbs, mbc);
return ch;
}
/*=======================================
Encoding-specific functions
=======================================*/
static scm_bool
pred_always_true(void)
{
return scm_true;
}
static scm_bool
pred_always_false(void)
{
return scm_false;
}
/* Every encoding implements the <encoding name>_scan_char()
* primitive. Its job is to determine the length of the first
* character in the given string. Stateful encodings should save
* their state *at exit*, that is, the state right after reading the
* first character (so don't omit it). */
/* Convenience macros. Start with ENTER and return with RETURN*.
* EXPECT_SIZE() declares the expected length of the character. We'll
* use it to return information on how many octets are missing. It
* also serves as documentation. */
#define ENTER ScmMultibyteCharInfo _ret; SCM_MBCINFO_INIT(_ret)
#define RETURN(n) \
do { \
SCM_MBCINFO_SET_SIZE(_ret, n); \
return _ret; \
} while (/* CONSTCOND */ 0)
#define RETURN_ERROR() \
do { \
SCM_MBCINFO_SET_ERROR(_ret); \
RETURN(1); \
} while (/* CONSTCOND */ 0)
#define RETURN_INCOMPLETE(n) \
do { \
SCM_MBCINFO_SET_INCOMPLETE(_ret); \
RETURN(n); \
} while (/* CONSTCOND */ 0)
#define SAVE_STATE(stat) SCM_MBCINFO_SET_STATE(_ret, (stat))
#define EXPECT_SIZE(size) SCM_EMPTY_EXPR /* Currently ignored. */
/* Encodings based on ISO/IEC 2022. */
/* Control regions. */
#define IN_CL(c) ((uchar)(c) < 0x20)
#define IN_CR(c) (0x80 <= (uchar)(c) && (uchar)(c) <= 0x9F)
/* General purpose regions. */
#define IN_GL94(c) (0x21 <= (uchar)(c) && (uchar)(c) <= 0x7E)
#define IN_GL96(c) (0x20 <= (uchar)(c) && (uchar)(c) <= 0x7F)
#define IN_GR94(c) (0xA1 <= (uchar)(c) && (uchar)(c) <= 0xFE)
#define IN_GR96(c) (0xA0 <= (uchar)(c) /* && (uchar)(c) <= 0xFF */)
#define IS_ASCII(c) ((scm_ichar_t)(c) <= 0x7F)
#define IS_GR_SPC_OR_DEL(c) ((uchar)(c) == 0xA0 || (uchar)(c) == 0xFF)
#define CHAR_BITS 8
#define BYTE_MASK 0xFF
#define IS_1BYTE(e) ((scm_ichar_t)(e) <= 0x7F)
#define IS_2BYTES(e) ((scm_ichar_t)(e) <= 0xFFFF)
#define IS_3BYTES(e) ((scm_ichar_t)(e) <= ((SS3 << CHAR_BITS * 2) | 0xFFFF))
#define ESC 0x1B
#define SO 0x0E
#define SI 0x0F
#define SS2 0x8E
#define SS3 0x8F
#if SCM_USE_EUCJP
static const char *
eucjp_encoding(void)
{
return "EUC-JP";
}
static enum ScmCodedCharSet
eucjp_ccs(void)
{
return SCM_CCS_JIS;
}
/* FIXME: Optimize */
static int
eucjp_char_len(scm_ichar_t ch)
{
uchar *end;
uchar buf[SCM_MB_CHAR_BUF_SIZE];
end = eucjp_int2str(buf, ch, SCM_MB_STATELESS);
return (end) ? end - buf : 0;
}
/* G0 <- (96) ASCII (or was it JIS X 0201 Roman?)
* G1 <- (94x94) JIS X 0208 kanji/kana
* G2 <- (94) JIS X 0201 Katakana ("half-width katakana")
* G3 <- (94x94) JIS X 0212 kanji, or JIS X 0213 kanji plane 2
*
* GL <- G0 (ASCII)
* GR <- G1 (JIS X 0208)
* CL <- JIS X 0211 C0
* CR <- JIS X 0211 C1 */
static ScmMultibyteCharInfo
eucjp_scan_char(ScmMultibyteString mbs)
{
const uchar *str = (const uchar *)SCM_MBS_GET_STR(mbs);
const size_t size = SCM_MBS_GET_SIZE(mbs);
ENTER;
if (!size)
RETURN(0);
if (IN_CL(str[0]) || IN_GL96(str[0]))
RETURN(1);
else if (IN_GR94(str[0]) || (uchar)str[0] == SS2) {
EXPECT_SIZE(2);
if (size < 2) RETURN_INCOMPLETE(1);
#if SCM_STRICT_ENCODING_CHECK
if (!IN_GR96(str[1])) RETURN_ERROR();
#endif
RETURN(2);
} else if ((uchar)str[0] == SS3) {
EXPECT_SIZE(3);
#if SCM_STRICT_ENCODING_CHECK
if (size < 2) RETURN_INCOMPLETE(size);
if (IS_GR_SPC_OR_DEL(str[1]))
RETURN(2);
if (!IN_GR94(str[1])) RETURN_ERROR();
if (size < 3) RETURN_INCOMPLETE(size);
if (!IN_GR94(str[2])) RETURN_ERROR();
RETURN(3);
#else /* not SCM_STRICT_ENCODING_CHECK */
if (size < 3)
RETURN_INCOMPLETE(size);
RETURN(3);
#endif /* not SCM_STRICT_ENCODING_CHECK */
}
RETURN_ERROR();
}
static scm_ichar_t
eucjp_str2int(const uchar *src, size_t len, ScmMultibyteState state)
{
scm_ichar_t ch;
switch (len) {
case 1:
ch = src[0];
break;
case 2:
ch = src[0] << CHAR_BITS;
ch |= src[1];
break;
case 3:
ch = src[0] << CHAR_BITS * 2;
ch |= src[1] << CHAR_BITS;
ch |= src[2];
break;
default:
return SCM_ICHAR_EOF;
}
return ch;
}
/* TODO: migrate to a canonical form shared with ISO-2022 variants that contain
absolute character set identifier instead of raw encoding-dependent
shifts */
static uchar *
eucjp_int2str(uchar *dst, scm_ichar_t ch, ScmMultibyteState state)
{
#if SCM_STRICT_ENCODING_CHECK
uchar seq[3];
#endif
if (IS_1BYTE(ch)) {
*dst++ = ch;
} else if (IS_2BYTES(ch)) {
#if SCM_STRICT_ENCODING_CHECK
seq[0] = ch >> CHAR_BITS;
seq[1] = ch & BYTE_MASK;
if ((!IN_GR94(seq[0]) && seq[0] != SS2)
|| !IN_GR96(seq[1]))
return NULL;
#endif
*dst++ = ch >> CHAR_BITS;
*dst++ = ch & BYTE_MASK;
} else if (IS_3BYTES(ch)) {
#if SCM_STRICT_ENCODING_CHECK
seq[0] = ch >> CHAR_BITS * 2;
seq[1] = (ch >> CHAR_BITS) & BYTE_MASK;
seq[2] = ch & BYTE_MASK;
if (seq[0] != SS3 || !IN_GR94(seq[1]) || !IN_GR94(seq[2]))
return NULL;
#endif
*dst++ = ch >> CHAR_BITS * 2;
*dst++ = (ch >> CHAR_BITS) & BYTE_MASK;
*dst++ = ch & BYTE_MASK;
} else {
return NULL;
}
*dst = '\0';
return dst;
}
#endif /* SCM_USE_EUCJP */
#if (SCM_USE_EUCCN || SCM_USE_EUCKR || SCM_USE_SJIS)
/* generic double-byte char */
static scm_ichar_t
dbc_str2int(const uchar *src, size_t len, ScmMultibyteState state)
{
scm_ichar_t ch;
switch (len) {
case 1:
ch = src[0];
break;
case 2:
ch = src[0] << CHAR_BITS;
ch |= src[1];
break;
default:
return SCM_ICHAR_EOF;
}
return ch;
}
#endif /* (SCM_USE_EUCCN || SCM_USE_EUCKR || SCM_USE_SJIS) */
#if (SCM_USE_EUCCN || SCM_USE_EUCKR)
/* FIXME: Optimize */
static int
euc_char_len(scm_ichar_t ch)
{
uchar *end;
uchar buf[SCM_MB_CHAR_BUF_SIZE];
end = euc_int2str(buf, ch, SCM_MB_STATELESS);
return (end) ? end - buf : 0;
}
static uchar *
euc_int2str(uchar *dst, scm_ichar_t ch, ScmMultibyteState state)
{
#if SCM_STRICT_ENCODING_CHECK
uchar seq[2];
#endif
if (IS_1BYTE(ch)) {
*dst++ = ch;
} else if (IS_2BYTES(ch)) {
#if SCM_STRICT_ENCODING_CHECK
seq[0] = ch >> CHAR_BITS;
seq[1] = ch & BYTE_MASK;
if (!IN_GR94(seq[0]) || !IN_GR96(seq[1]))
return NULL;
#endif
*dst++ = ch >> CHAR_BITS;
*dst++ = ch & BYTE_MASK;
} else {
return NULL;
}
*dst = '\0';
return dst;
}
#endif /* (SCM_USE_EUCCN || SCM_USE_EUCKR) */
#if SCM_USE_EUCCN
static const char *
euccn_encoding(void)
{
return "EUC-CN";
}
static enum ScmCodedCharSet
euccn_ccs(void)
{
return SCM_CCS_UNKNOWN;
}
/* FIXME: NOT TESTED!
*
* G0 <- ASCII (or GB 1988?)
* G1 <- GB2312
*
* GL <- G0 (ASCII)
* GR <- G1 (GB2312) */
static ScmMultibyteCharInfo
euccn_scan_char(ScmMultibyteString mbs)
{
/* TODO: maybe we can make this an alias of eucjp_scan_char()? */
const uchar *str = (const uchar *)SCM_MBS_GET_STR(mbs);
const size_t size = SCM_MBS_GET_SIZE(mbs);
ENTER;
if (!size)
RETURN(0);
if (IS_ASCII(str[0]))
RETURN(1);
if (IN_GR94(str[0])) {
EXPECT_SIZE(2);
if (size < 2)
RETURN_INCOMPLETE(size);
#if SCM_STRICT_ENCODING_CHECK
if (!IN_GR96(str[1]))
RETURN_ERROR();
#endif
RETURN(2);
}
RETURN_ERROR();
}
#endif
#if SCM_USE_EUCKR
static enum ScmCodedCharSet
euckr_ccs(void)
{
return SCM_CCS_UNKNOWN;
}
static const char *
euckr_encoding(void)
{
return "EUC-KR";
}
/* FIXME: NOT TESTED! I'm not sure about this encoding. There's also
* a Microsoft variant called CP949, which is not supported (yet).
* RFC 1557 says KS X 1001 is 94x94.
*
* G0 <- ASCII
* G1 <- KS X 1001 (aka KSC 5601)
*
* GL <- G0
* GR <- G1 */
static ScmMultibyteCharInfo
euckr_scan_char(ScmMultibyteString mbs)
{
const uchar *str = (const uchar *)SCM_MBS_GET_STR(mbs);
const size_t size = SCM_MBS_GET_SIZE(mbs);
ENTER;
if (!size)
RETURN(0);
if (IS_ASCII(str[0]))
RETURN(1);
if (IN_GR94(str[0])) {
EXPECT_SIZE(2);
if (size < 2)
RETURN_INCOMPLETE(size);
#if SCM_STRICT_ENCODING_CHECK
if (!IN_GR96(str[1]))
RETURN_ERROR();
#endif
RETURN(2);
}
RETURN_ERROR();
}
#endif /* SCM_USE_EUCKR */
/*==== Encodings for Unicode ====*/
#define IN_OCT_BMP(u) ((scm_ichar_t)(u) <= 0x7ff)
#define IN_BMP(u) ((scm_ichar_t)(u) <= 0xffff)
#define IN_SMP(u) ((scm_ichar_t)(u) <= 0x10ffff && !IN_BMP(u))
#if SCM_USE_UTF8
/* RFC 3629 */
#define MASK(n) ((LEN_CODE(n) >> 1) | 0x80)
#define LEN_CODE(n) (((1 << (n)) - 1) << (8 - n))
#define IS_LEN(c, n) ((MASK(n) & (c)) == LEN_CODE(n))
#define IS_TRAILING(c) (IS_LEN((c), 1))
#define LEN_CODE_BITS(n) (n + 1)
#define TRAILING_CODE_BITS LEN_CODE_BITS(1)
#define TRAILING_VAL_BITS (CHAR_BITS - TRAILING_CODE_BITS)
#define LEADING_VAL_BITS(n) (CHAR_BITS - LEN_CODE_BITS(n))
#define LEADING_VAL(u, n) ((u) >> TRAILING_VAL_BITS * ((n) - 1))
#define TRAILING_VAL(u, i) (~MASK(1) & ((u) >> TRAILING_VAL_BITS * (i)))
static const char *
utf8_encoding(void)
{
return "UTF-8";
}
static enum ScmCodedCharSet
utf8_ccs(void)
{
return SCM_CCS_UNICODE;
}
/* FIXME: Optimize */
static int
utf8_char_len(scm_ichar_t ch)
{
uchar *end;
uchar buf[SCM_MB_CHAR_BUF_SIZE];
end = utf8_int2str(buf, ch, SCM_MB_STATELESS);
return (end) ? end - buf : 0;
}
static ScmMultibyteCharInfo
utf8_scan_char(ScmMultibyteString mbs)
{
const uchar *str = (const uchar *)SCM_MBS_GET_STR(mbs);
const size_t size = SCM_MBS_GET_SIZE(mbs);
size_t len;
ENTER;
if (!size)
RETURN(0);
if (IS_ASCII(str[0]))
RETURN(1);
if (IS_LEN(str[0], 2)) len = 2;
else if (IS_LEN(str[0], 3)) len = 3;
else if (IS_LEN(str[0], 4)) len = 4;
else RETURN_ERROR();
#if SCM_STRICT_ENCODING_CHECK
{
size_t i;
for (i = 1; i < len; i++) {
if (size <= i)
RETURN_INCOMPLETE(size);
if (!IS_TRAILING(str[i]))
RETURN_ERROR();
}
}
#else /* not SCM_STRICT_ENCODING_CHECK */
if (size < len)
RETURN_INCOMPLETE(size);
#endif /* not SCM_STRICT_ENCODING_CHECK */
RETURN(len);
}
static scm_ichar_t
utf8_str2int(const uchar *src, size_t len, ScmMultibyteState state)
{
scm_ichar_t ch;
switch (len) {
case 1:
ch = src[0];
break;
case 2:
ch = (~MASK(2) & src[0]) << TRAILING_VAL_BITS;
ch |= (~MASK(1) & src[1]);
break;
case 3:
ch = (~MASK(3) & src[0]) << TRAILING_VAL_BITS * 2;
ch |= (~MASK(1) & src[1]) << TRAILING_VAL_BITS;
ch |= (~MASK(1) & src[2]);
break;
case 4:
ch = (~MASK(4) & src[0]) << TRAILING_VAL_BITS * 3;
ch |= (~MASK(1) & src[1]) << TRAILING_VAL_BITS * 2;
ch |= (~MASK(1) & src[2]) << TRAILING_VAL_BITS;
ch |= (~MASK(1) & src[3]);
break;
default:
return SCM_ICHAR_EOF;
}
return ch;
}
static uchar *
utf8_int2str(uchar *dst, scm_ichar_t ch, ScmMultibyteState state)
{
if (IS_ASCII(ch)) {
*dst++ = ch;
} else if (IN_OCT_BMP(ch)) {
*dst++ = LEN_CODE(2) | LEADING_VAL(ch, 2);
*dst++ = LEN_CODE(1) | TRAILING_VAL(ch, 0);
} else if (IN_BMP(ch)) {
*dst++ = LEN_CODE(3) | LEADING_VAL(ch, 3);
*dst++ = LEN_CODE(1) | TRAILING_VAL(ch, 1);
*dst++ = LEN_CODE(1) | TRAILING_VAL(ch, 0);
} else if (IN_SMP(ch)) {
*dst++ = LEN_CODE(4) | LEADING_VAL(ch, 4);
*dst++ = LEN_CODE(1) | TRAILING_VAL(ch, 2);
*dst++ = LEN_CODE(1) | TRAILING_VAL(ch, 1);
*dst++ = LEN_CODE(1) | TRAILING_VAL(ch, 0);
} else {
return NULL;
}
*dst = '\0';
return dst;
}
#undef MASK
#undef LEN_CODE
#undef IS_LEN
#undef IS_TRAILING
#undef LEN_CODE_BITS
#undef TRAILING_CODE_BITS
#undef TRAILING_VAL_BITS
#undef LEADING_VAL_BITS
#undef LEADING_VAL
#undef TRAILING_VAL
#endif /* SCM_USE_UTF8 */
/*==== Other encodings ====*/
#if SCM_USE_SJIS
/* The cwazy Japanese encoding. This function implements the JIS X
* 0213 variant.
*
* 0 .. 0x7F: ASCII
* 0x80: undefined
* 0x81 .. 0x9F: lead byte of 2-byte char
* 0xA0: undefined
* 0xA1 .. 0xDF: JIS X 0201 katakana (1 byte)
* 0xE0 .. 0xEF: lead byte of 2-byte char
* 0xF0 .. 0xFC: lead byte of 2-byte char if JIS X 0213 is used
* 0xFD .. 0xFF: undefined
*
* 0x40 .. 0x7E: trailing byte of 2-byte char
* 0x80 .. 0xFC: trailing byte of 2-byte char
*/
#define IS_KANA(c) (0xA1 <= (uchar)(c) && (uchar)(c) <= 0xDF)
#define IS_LEAD(c) \
(0x81 <= (uchar)(c) \
&& !IS_KANA(c) \
&& (uchar)(c) <= 0xFC \
&& (uchar)(c) != 0xA0)
#define IS_TRAIL(c) (0x40 <= (uchar)(c) && (uchar)(c) <= 0xFC && (c) != 0x7E)
static const char *
sjis_encoding(void)
{
return "Shift_JIS";
}
static enum ScmCodedCharSet
sjis_ccs(void)
{
return SCM_CCS_JIS;
}
/* FIXME: Optimize */
static int
sjis_char_len(scm_ichar_t ch)
{
uchar *end;
uchar buf[SCM_MB_CHAR_BUF_SIZE];
end = sjis_int2str(buf, ch, SCM_MB_STATELESS);
return (end) ? end - buf : 0;
}
static ScmMultibyteCharInfo
sjis_scan_char(ScmMultibyteString mbs)
{
const uchar *str = (const uchar *)SCM_MBS_GET_STR(mbs);
const size_t size = SCM_MBS_GET_SIZE(mbs);
ENTER;
if (!size)
RETURN(0);
if (IS_LEAD(str[0])) {
EXPECT_SIZE(2);
if (size < 2)
RETURN_INCOMPLETE(size);
#if SCM_STRICT_ENCODING_CHECK
if (!IS_TRAIL(str[1]))
RETURN_ERROR();
#endif
RETURN(2);
}
RETURN(1);
}
static uchar *
sjis_int2str(uchar *dst, scm_ichar_t ch, ScmMultibyteState state)
{
uchar high, low;
#if SCM_STRICT_ENCODING_CHECK
if (ch >> CHAR_BITS * 2)
return NULL;
#endif
high = ch >> CHAR_BITS;
low = ch & BYTE_MASK;
if (IS_LEAD(high)) {
#if SCM_STRICT_ENCODING_CHECK
if (!IS_TRAIL(high))
return NULL;
#endif
*dst++ = high;
}
*dst++ = low;
*dst = '\0';
return dst;
}
#undef IS_KANA
#undef IS_LEAD
#undef IS_TRAIL
#endif /* SCM_USE_SJIS */
/* Single-byte encodings. Please add any that you know are missing.
* Sorted alphabetically.
*
* ASCII
* ISO 646
* ISO-8859-*
* VISCII
*/
static const char *
unibyte_encoding(void)
{
/* conventional assumption */
return "ISO-8859-1";
}
static enum ScmCodedCharSet
unibyte_ccs(void)
{
/* conventional assumption */
return SCM_CCS_ISO8859_1;
}
static int
unibyte_char_len(scm_ichar_t ch)
{
return (0 < ch && ch <= 0xff) ? 1 : 0;
}
static ScmMultibyteCharInfo
unibyte_scan_char(ScmMultibyteString mbs)
{
ENTER;
if (SCM_MBS_GET_SIZE(mbs))
RETURN(1);
RETURN(0);
}
static scm_ichar_t
unibyte_str2int(const uchar *src, size_t len, ScmMultibyteState state)
{
#if SCM_STRICT_ENCODING_CHECK
if (len != 1)
return SCM_ICHAR_EOF;
#endif
return src[0];
}
static uchar *
unibyte_int2str(uchar *dst, scm_ichar_t ch, ScmMultibyteState state)
{
#if SCM_STRICT_ENCODING_CHECK
if (ch & ~BYTE_MASK)
return NULL;
#endif
*dst++ = ch;
*dst = '\0';
return dst;
}
|