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 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 1208
|
/* Character set conversion with error handling.
Copyright (C) 2001-2018 Free Software Foundation, Inc.
Written by Bruno Haible and Simon Josefsson.
This program is free software: you can redistribute it and/or
modify it under the terms of either:
* the GNU Lesser General Public License as published by the Free
Software Foundation; either version 3 of the License, or (at your
option) any later version.
or
* the GNU General Public License as published by the Free
Software Foundation; either version 2 of the License, or (at your
option) any later version.
or both in parallel, as here.
This program is distributed in the hope that it will be useful,
but WITHOUT ANY WARRANTY; without even the implied warranty of
MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
GNU General Public License for more details.
You should have received a copy of the GNU General Public License
along with this program. If not, see <https://www.gnu.org/licenses/>. */
#include <config.h>
/* Specification. */
#include "striconveh.h"
#include <errno.h>
#include <stdbool.h>
#include <stdlib.h>
#include <string.h>
#if HAVE_ICONV
# include <iconv.h>
# include "unistr.h"
#endif
#include "c-strcase.h"
#include "c-strcaseeq.h"
#ifndef SIZE_MAX
# define SIZE_MAX ((size_t) -1)
#endif
#if HAVE_ICONV
/* The caller must provide an iconveh_t, not just an iconv_t, because when a
conversion error occurs, we may have to determine the Unicode representation
of the inconvertible character. */
int
iconveh_open (const char *to_codeset, const char *from_codeset, iconveh_t *cdp)
{
iconv_t cd;
iconv_t cd1;
iconv_t cd2;
/* Avoid glibc-2.1 bug with EUC-KR. */
# if ((__GLIBC__ == 2 && __GLIBC_MINOR__ <= 1) && !defined __UCLIBC__) \
&& !defined _LIBICONV_VERSION
if (c_strcasecmp (from_codeset, "EUC-KR") == 0
|| c_strcasecmp (to_codeset, "EUC-KR") == 0)
{
errno = EINVAL;
return -1;
}
# endif
cd = iconv_open (to_codeset, from_codeset);
if (STRCASEEQ (from_codeset, "UTF-8", 'U','T','F','-','8',0,0,0,0))
cd1 = (iconv_t)(-1);
else
{
cd1 = iconv_open ("UTF-8", from_codeset);
if (cd1 == (iconv_t)(-1))
{
int saved_errno = errno;
if (cd != (iconv_t)(-1))
iconv_close (cdp->cd);
errno = saved_errno;
return -1;
}
}
if (STRCASEEQ (to_codeset, "UTF-8", 'U','T','F','-','8',0,0,0,0)
# if (((__GLIBC__ == 2 && __GLIBC_MINOR__ >= 2) || __GLIBC__ > 2) \
&& !defined __UCLIBC__) \
|| _LIBICONV_VERSION >= 0x0105
|| c_strcasecmp (to_codeset, "UTF-8//TRANSLIT") == 0
# endif
)
cd2 = (iconv_t)(-1);
else
{
cd2 = iconv_open (to_codeset, "UTF-8");
if (cd2 == (iconv_t)(-1))
{
int saved_errno = errno;
if (cd1 != (iconv_t)(-1))
iconv_close (cd1);
if (cd != (iconv_t)(-1))
iconv_close (cd);
errno = saved_errno;
return -1;
}
}
cdp->cd = cd;
cdp->cd1 = cd1;
cdp->cd2 = cd2;
return 0;
}
int
iconveh_close (const iconveh_t *cd)
{
if (cd->cd2 != (iconv_t)(-1) && iconv_close (cd->cd2) < 0)
{
/* Return -1, but preserve the errno from iconv_close. */
int saved_errno = errno;
if (cd->cd1 != (iconv_t)(-1))
iconv_close (cd->cd1);
if (cd->cd != (iconv_t)(-1))
iconv_close (cd->cd);
errno = saved_errno;
return -1;
}
if (cd->cd1 != (iconv_t)(-1) && iconv_close (cd->cd1) < 0)
{
/* Return -1, but preserve the errno from iconv_close. */
int saved_errno = errno;
if (cd->cd != (iconv_t)(-1))
iconv_close (cd->cd);
errno = saved_errno;
return -1;
}
if (cd->cd != (iconv_t)(-1) && iconv_close (cd->cd) < 0)
return -1;
return 0;
}
/* iconv_carefully is like iconv, except that it stops as soon as it encounters
a conversion error, and it returns in *INCREMENTED a boolean telling whether
it has incremented the input pointers past the error location. */
# if !defined _LIBICONV_VERSION && !(defined __GLIBC__ && !defined __UCLIBC__)
/* Irix iconv() inserts a NUL byte if it cannot convert.
NetBSD iconv() inserts a question mark if it cannot convert.
Only GNU libiconv and GNU libc are known to prefer to fail rather
than doing a lossy conversion. */
static size_t
iconv_carefully (iconv_t cd,
const char **inbuf, size_t *inbytesleft,
char **outbuf, size_t *outbytesleft,
bool *incremented)
{
const char *inptr = *inbuf;
const char *inptr_end = inptr + *inbytesleft;
char *outptr = *outbuf;
size_t outsize = *outbytesleft;
const char *inptr_before;
size_t res;
do
{
size_t insize;
inptr_before = inptr;
res = (size_t)(-1);
for (insize = 1; inptr + insize <= inptr_end; insize++)
{
res = iconv (cd,
(ICONV_CONST char **) &inptr, &insize,
&outptr, &outsize);
if (!(res == (size_t)(-1) && errno == EINVAL))
break;
/* iconv can eat up a shift sequence but give EINVAL while attempting
to convert the first character. E.g. libiconv does this. */
if (inptr > inptr_before)
{
res = 0;
break;
}
}
if (res == 0)
{
*outbuf = outptr;
*outbytesleft = outsize;
}
}
while (res == 0 && inptr < inptr_end);
*inbuf = inptr;
*inbytesleft = inptr_end - inptr;
if (res != (size_t)(-1) && res > 0)
{
/* iconv() has already incremented INPTR. We cannot go back to a
previous INPTR, otherwise the state inside CD would become invalid,
if FROM_CODESET is a stateful encoding. So, tell the caller that
*INBUF has already been incremented. */
*incremented = (inptr > inptr_before);
errno = EILSEQ;
return (size_t)(-1);
}
else
{
*incremented = false;
return res;
}
}
# else
# define iconv_carefully(cd, inbuf, inbytesleft, outbuf, outbytesleft, incremented) \
(*(incremented) = false, \
iconv (cd, (ICONV_CONST char **) (inbuf), inbytesleft, outbuf, outbytesleft))
# endif
/* iconv_carefully_1 is like iconv_carefully, except that it stops after
converting one character or one shift sequence. */
static size_t
iconv_carefully_1 (iconv_t cd,
const char **inbuf, size_t *inbytesleft,
char **outbuf, size_t *outbytesleft,
bool *incremented)
{
const char *inptr_before = *inbuf;
const char *inptr = inptr_before;
const char *inptr_end = inptr_before + *inbytesleft;
char *outptr = *outbuf;
size_t outsize = *outbytesleft;
size_t res = (size_t)(-1);
size_t insize;
for (insize = 1; inptr_before + insize <= inptr_end; insize++)
{
inptr = inptr_before;
res = iconv (cd,
(ICONV_CONST char **) &inptr, &insize,
&outptr, &outsize);
if (!(res == (size_t)(-1) && errno == EINVAL))
break;
/* iconv can eat up a shift sequence but give EINVAL while attempting
to convert the first character. E.g. libiconv does this. */
if (inptr > inptr_before)
{
res = 0;
break;
}
}
*inbuf = inptr;
*inbytesleft = inptr_end - inptr;
# if !defined _LIBICONV_VERSION && !(defined __GLIBC__ && !defined __UCLIBC__)
/* Irix iconv() inserts a NUL byte if it cannot convert.
NetBSD iconv() inserts a question mark if it cannot convert.
Only GNU libiconv and GNU libc are known to prefer to fail rather
than doing a lossy conversion. */
if (res != (size_t)(-1) && res > 0)
{
/* iconv() has already incremented INPTR. We cannot go back to a
previous INPTR, otherwise the state inside CD would become invalid,
if FROM_CODESET is a stateful encoding. So, tell the caller that
*INBUF has already been incremented. */
*incremented = (inptr > inptr_before);
errno = EILSEQ;
return (size_t)(-1);
}
# endif
if (res != (size_t)(-1))
{
*outbuf = outptr;
*outbytesleft = outsize;
}
*incremented = false;
return res;
}
/* utf8conv_carefully is like iconv, except that
- it converts from UTF-8 to UTF-8,
- it stops as soon as it encounters a conversion error, and it returns
in *INCREMENTED a boolean telling whether it has incremented the input
pointers past the error location,
- if one_character_only is true, it stops after converting one
character. */
static size_t
utf8conv_carefully (bool one_character_only,
const char **inbuf, size_t *inbytesleft,
char **outbuf, size_t *outbytesleft,
bool *incremented)
{
const char *inptr = *inbuf;
size_t insize = *inbytesleft;
char *outptr = *outbuf;
size_t outsize = *outbytesleft;
size_t res;
res = 0;
do
{
ucs4_t uc;
int n;
int m;
n = u8_mbtoucr (&uc, (const uint8_t *) inptr, insize);
if (n < 0)
{
errno = (n == -2 ? EINVAL : EILSEQ);
n = u8_mbtouc (&uc, (const uint8_t *) inptr, insize);
inptr += n;
insize -= n;
res = (size_t)(-1);
*incremented = true;
break;
}
if (outsize == 0)
{
errno = E2BIG;
res = (size_t)(-1);
*incremented = false;
break;
}
m = u8_uctomb ((uint8_t *) outptr, uc, outsize);
if (m == -2)
{
errno = E2BIG;
res = (size_t)(-1);
*incremented = false;
break;
}
inptr += n;
insize -= n;
if (m == -1)
{
errno = EILSEQ;
res = (size_t)(-1);
*incremented = true;
break;
}
outptr += m;
outsize -= m;
}
while (!one_character_only && insize > 0);
*inbuf = inptr;
*inbytesleft = insize;
*outbuf = outptr;
*outbytesleft = outsize;
return res;
}
static int
mem_cd_iconveh_internal (const char *src, size_t srclen,
iconv_t cd, iconv_t cd1, iconv_t cd2,
enum iconv_ilseq_handler handler,
size_t extra_alloc,
size_t *offsets,
char **resultp, size_t *lengthp)
{
/* When a conversion error occurs, we cannot start using CD1 and CD2 at
this point: FROM_CODESET may be a stateful encoding like ISO-2022-KR.
Instead, we have to start afresh from the beginning of SRC. */
/* Use a temporary buffer, so that for small strings, a single malloc()
call will be sufficient. */
# define tmpbufsize 4096
/* The alignment is needed when converting e.g. to glibc's WCHAR_T or
libiconv's UCS-4-INTERNAL encoding. */
union { unsigned int align; char buf[tmpbufsize]; } tmp;
# define tmpbuf tmp.buf
char *initial_result;
char *result;
size_t allocated;
size_t length;
size_t last_length = (size_t)(-1); /* only needed if offsets != NULL */
if (*resultp != NULL && *lengthp >= sizeof (tmpbuf))
{
initial_result = *resultp;
allocated = *lengthp;
}
else
{
initial_result = tmpbuf;
allocated = sizeof (tmpbuf);
}
result = initial_result;
/* Test whether a direct conversion is possible at all. */
if (cd == (iconv_t)(-1))
goto indirectly;
if (offsets != NULL)
{
size_t i;
for (i = 0; i < srclen; i++)
offsets[i] = (size_t)(-1);
last_length = (size_t)(-1);
}
length = 0;
/* First, try a direct conversion, and see whether a conversion error
occurs at all. */
{
const char *inptr = src;
size_t insize = srclen;
/* Avoid glibc-2.1 bug and Solaris 2.7-2.9 bug. */
# if defined _LIBICONV_VERSION \
|| !(((__GLIBC__ == 2 && __GLIBC_MINOR__ <= 1) && !defined __UCLIBC__) \
|| defined __sun)
/* Set to the initial state. */
iconv (cd, NULL, NULL, NULL, NULL);
# endif
while (insize > 0)
{
char *outptr = result + length;
size_t outsize = allocated - extra_alloc - length;
bool incremented;
size_t res;
bool grow;
if (offsets != NULL)
{
if (length != last_length) /* ensure that offset[] be increasing */
{
offsets[inptr - src] = length;
last_length = length;
}
res = iconv_carefully_1 (cd,
&inptr, &insize,
&outptr, &outsize,
&incremented);
}
else
/* Use iconv_carefully instead of iconv here, because:
- If TO_CODESET is UTF-8, we can do the error handling in this
loop, no need for a second loop,
- With iconv() implementations other than GNU libiconv and GNU
libc, if we use iconv() in a big swoop, checking for an E2BIG
return, we lose the number of irreversible conversions. */
res = iconv_carefully (cd,
&inptr, &insize,
&outptr, &outsize,
&incremented);
length = outptr - result;
grow = (length + extra_alloc > allocated / 2);
if (res == (size_t)(-1))
{
if (errno == E2BIG)
grow = true;
else if (errno == EINVAL)
break;
else if (errno == EILSEQ && handler != iconveh_error)
{
if (cd2 == (iconv_t)(-1))
{
/* TO_CODESET is UTF-8. */
/* Error handling can produce up to 1 byte of output. */
if (length + 1 + extra_alloc > allocated)
{
char *memory;
allocated = 2 * allocated;
if (length + 1 + extra_alloc > allocated)
abort ();
if (result == initial_result)
memory = (char *) malloc (allocated);
else
memory = (char *) realloc (result, allocated);
if (memory == NULL)
{
if (result != initial_result)
free (result);
errno = ENOMEM;
return -1;
}
if (result == initial_result)
memcpy (memory, initial_result, length);
result = memory;
grow = false;
}
/* The input is invalid in FROM_CODESET. Eat up one byte
and emit a question mark. */
if (!incremented)
{
if (insize == 0)
abort ();
inptr++;
insize--;
}
result[length] = '?';
length++;
}
else
goto indirectly;
}
else
{
if (result != initial_result)
{
int saved_errno = errno;
free (result);
errno = saved_errno;
}
return -1;
}
}
if (insize == 0)
break;
if (grow)
{
char *memory;
allocated = 2 * allocated;
if (result == initial_result)
memory = (char *) malloc (allocated);
else
memory = (char *) realloc (result, allocated);
if (memory == NULL)
{
if (result != initial_result)
free (result);
errno = ENOMEM;
return -1;
}
if (result == initial_result)
memcpy (memory, initial_result, length);
result = memory;
}
}
}
/* Now get the conversion state back to the initial state.
But avoid glibc-2.1 bug and Solaris 2.7 bug. */
#if defined _LIBICONV_VERSION \
|| !(((__GLIBC__ == 2 && __GLIBC_MINOR__ <= 1) && !defined __UCLIBC__) \
|| defined __sun)
for (;;)
{
char *outptr = result + length;
size_t outsize = allocated - extra_alloc - length;
size_t res;
res = iconv (cd, NULL, NULL, &outptr, &outsize);
length = outptr - result;
if (res == (size_t)(-1))
{
if (errno == E2BIG)
{
char *memory;
allocated = 2 * allocated;
if (result == initial_result)
memory = (char *) malloc (allocated);
else
memory = (char *) realloc (result, allocated);
if (memory == NULL)
{
if (result != initial_result)
free (result);
errno = ENOMEM;
return -1;
}
if (result == initial_result)
memcpy (memory, initial_result, length);
result = memory;
}
else
{
if (result != initial_result)
{
int saved_errno = errno;
free (result);
errno = saved_errno;
}
return -1;
}
}
else
break;
}
#endif
/* The direct conversion succeeded. */
goto done;
indirectly:
/* The direct conversion failed.
Use a conversion through UTF-8. */
if (offsets != NULL)
{
size_t i;
for (i = 0; i < srclen; i++)
offsets[i] = (size_t)(-1);
last_length = (size_t)(-1);
}
length = 0;
{
const bool slowly = (offsets != NULL || handler == iconveh_error);
# define utf8bufsize 4096 /* may also be smaller or larger than tmpbufsize */
char utf8buf[utf8bufsize + 1];
size_t utf8len = 0;
const char *in1ptr = src;
size_t in1size = srclen;
bool do_final_flush1 = true;
bool do_final_flush2 = true;
/* Avoid glibc-2.1 bug and Solaris 2.7-2.9 bug. */
# if defined _LIBICONV_VERSION \
|| !(((__GLIBC__ == 2 && __GLIBC_MINOR__ <= 1) && !defined __UCLIBC__) \
|| defined __sun)
/* Set to the initial state. */
if (cd1 != (iconv_t)(-1))
iconv (cd1, NULL, NULL, NULL, NULL);
if (cd2 != (iconv_t)(-1))
iconv (cd2, NULL, NULL, NULL, NULL);
# endif
while (in1size > 0 || do_final_flush1 || utf8len > 0 || do_final_flush2)
{
char *out1ptr = utf8buf + utf8len;
size_t out1size = utf8bufsize - utf8len;
bool incremented1;
size_t res1;
int errno1;
/* Conversion step 1: from FROM_CODESET to UTF-8. */
if (in1size > 0)
{
if (offsets != NULL
&& length != last_length) /* ensure that offset[] be increasing */
{
offsets[in1ptr - src] = length;
last_length = length;
}
if (cd1 != (iconv_t)(-1))
{
if (slowly)
res1 = iconv_carefully_1 (cd1,
&in1ptr, &in1size,
&out1ptr, &out1size,
&incremented1);
else
res1 = iconv_carefully (cd1,
&in1ptr, &in1size,
&out1ptr, &out1size,
&incremented1);
}
else
{
/* FROM_CODESET is UTF-8. */
res1 = utf8conv_carefully (slowly,
&in1ptr, &in1size,
&out1ptr, &out1size,
&incremented1);
}
}
else if (do_final_flush1)
{
/* Now get the conversion state of CD1 back to the initial state.
But avoid glibc-2.1 bug and Solaris 2.7 bug. */
# if defined _LIBICONV_VERSION \
|| !(((__GLIBC__ == 2 && __GLIBC_MINOR__ <= 1) && !defined __UCLIBC__) \
|| defined __sun)
if (cd1 != (iconv_t)(-1))
res1 = iconv (cd1, NULL, NULL, &out1ptr, &out1size);
else
# endif
res1 = 0;
do_final_flush1 = false;
incremented1 = true;
}
else
{
res1 = 0;
incremented1 = true;
}
if (res1 == (size_t)(-1)
&& !(errno == E2BIG || errno == EINVAL || errno == EILSEQ))
{
if (result != initial_result)
{
int saved_errno = errno;
free (result);
errno = saved_errno;
}
return -1;
}
if (res1 == (size_t)(-1)
&& errno == EILSEQ && handler != iconveh_error)
{
/* The input is invalid in FROM_CODESET. Eat up one byte and
emit a question mark. Room for the question mark was allocated
at the end of utf8buf. */
if (!incremented1)
{
if (in1size == 0)
abort ();
in1ptr++;
in1size--;
}
*out1ptr++ = '?';
res1 = 0;
}
errno1 = errno;
utf8len = out1ptr - utf8buf;
if (offsets != NULL
|| in1size == 0
|| utf8len > utf8bufsize / 2
|| (res1 == (size_t)(-1) && errno1 == E2BIG))
{
/* Conversion step 2: from UTF-8 to TO_CODESET. */
const char *in2ptr = utf8buf;
size_t in2size = utf8len;
while (in2size > 0
|| (in1size == 0 && !do_final_flush1 && do_final_flush2))
{
char *out2ptr = result + length;
size_t out2size = allocated - extra_alloc - length;
bool incremented2;
size_t res2;
bool grow;
if (in2size > 0)
{
if (cd2 != (iconv_t)(-1))
res2 = iconv_carefully (cd2,
&in2ptr, &in2size,
&out2ptr, &out2size,
&incremented2);
else
/* TO_CODESET is UTF-8. */
res2 = utf8conv_carefully (false,
&in2ptr, &in2size,
&out2ptr, &out2size,
&incremented2);
}
else /* in1size == 0 && !do_final_flush1
&& in2size == 0 && do_final_flush2 */
{
/* Now get the conversion state of CD1 back to the initial
state. But avoid glibc-2.1 bug and Solaris 2.7 bug. */
# if defined _LIBICONV_VERSION \
|| !(((__GLIBC__ == 2 && __GLIBC_MINOR__ <= 1) && !defined __UCLIBC__) \
|| defined __sun)
if (cd2 != (iconv_t)(-1))
res2 = iconv (cd2, NULL, NULL, &out2ptr, &out2size);
else
# endif
res2 = 0;
do_final_flush2 = false;
incremented2 = true;
}
length = out2ptr - result;
grow = (length + extra_alloc > allocated / 2);
if (res2 == (size_t)(-1))
{
if (errno == E2BIG)
grow = true;
else if (errno == EINVAL)
break;
else if (errno == EILSEQ && handler != iconveh_error)
{
/* Error handling can produce up to 10 bytes of ASCII
output. But TO_CODESET may be UCS-2, UTF-16 or
UCS-4, so use CD2 here as well. */
char scratchbuf[10];
size_t scratchlen;
ucs4_t uc;
const char *inptr;
size_t insize;
size_t res;
if (incremented2)
{
if (u8_prev (&uc, (const uint8_t *) in2ptr,
(const uint8_t *) utf8buf)
== NULL)
abort ();
}
else
{
int n;
if (in2size == 0)
abort ();
n = u8_mbtouc_unsafe (&uc, (const uint8_t *) in2ptr,
in2size);
in2ptr += n;
in2size -= n;
}
if (handler == iconveh_escape_sequence)
{
static char hex[16] = "0123456789ABCDEF";
scratchlen = 0;
scratchbuf[scratchlen++] = '\\';
if (uc < 0x10000)
scratchbuf[scratchlen++] = 'u';
else
{
scratchbuf[scratchlen++] = 'U';
scratchbuf[scratchlen++] = hex[(uc>>28) & 15];
scratchbuf[scratchlen++] = hex[(uc>>24) & 15];
scratchbuf[scratchlen++] = hex[(uc>>20) & 15];
scratchbuf[scratchlen++] = hex[(uc>>16) & 15];
}
scratchbuf[scratchlen++] = hex[(uc>>12) & 15];
scratchbuf[scratchlen++] = hex[(uc>>8) & 15];
scratchbuf[scratchlen++] = hex[(uc>>4) & 15];
scratchbuf[scratchlen++] = hex[uc & 15];
}
else
{
scratchbuf[0] = '?';
scratchlen = 1;
}
inptr = scratchbuf;
insize = scratchlen;
if (cd2 != (iconv_t)(-1))
res = iconv (cd2,
(ICONV_CONST char **) &inptr, &insize,
&out2ptr, &out2size);
else
{
/* TO_CODESET is UTF-8. */
if (out2size >= insize)
{
memcpy (out2ptr, inptr, insize);
out2ptr += insize;
out2size -= insize;
inptr += insize;
insize = 0;
res = 0;
}
else
{
errno = E2BIG;
res = (size_t)(-1);
}
}
length = out2ptr - result;
if (res == (size_t)(-1) && errno == E2BIG)
{
char *memory;
allocated = 2 * allocated;
if (length + 1 + extra_alloc > allocated)
abort ();
if (result == initial_result)
memory = (char *) malloc (allocated);
else
memory = (char *) realloc (result, allocated);
if (memory == NULL)
{
if (result != initial_result)
free (result);
errno = ENOMEM;
return -1;
}
if (result == initial_result)
memcpy (memory, initial_result, length);
result = memory;
grow = false;
out2ptr = result + length;
out2size = allocated - extra_alloc - length;
if (cd2 != (iconv_t)(-1))
res = iconv (cd2,
(ICONV_CONST char **) &inptr,
&insize,
&out2ptr, &out2size);
else
{
/* TO_CODESET is UTF-8. */
if (!(out2size >= insize))
abort ();
memcpy (out2ptr, inptr, insize);
out2ptr += insize;
out2size -= insize;
inptr += insize;
insize = 0;
res = 0;
}
length = out2ptr - result;
}
# if !defined _LIBICONV_VERSION && !(defined __GLIBC__ && !defined __UCLIBC__)
/* Irix iconv() inserts a NUL byte if it cannot convert.
NetBSD iconv() inserts a question mark if it cannot
convert.
Only GNU libiconv and GNU libc are known to prefer
to fail rather than doing a lossy conversion. */
if (res != (size_t)(-1) && res > 0)
{
errno = EILSEQ;
res = (size_t)(-1);
}
# endif
if (res == (size_t)(-1))
{
/* Failure converting the ASCII replacement. */
if (result != initial_result)
{
int saved_errno = errno;
free (result);
errno = saved_errno;
}
return -1;
}
}
else
{
if (result != initial_result)
{
int saved_errno = errno;
free (result);
errno = saved_errno;
}
return -1;
}
}
if (!(in2size > 0
|| (in1size == 0 && !do_final_flush1 && do_final_flush2)))
break;
if (grow)
{
char *memory;
allocated = 2 * allocated;
if (result == initial_result)
memory = (char *) malloc (allocated);
else
memory = (char *) realloc (result, allocated);
if (memory == NULL)
{
if (result != initial_result)
free (result);
errno = ENOMEM;
return -1;
}
if (result == initial_result)
memcpy (memory, initial_result, length);
result = memory;
}
}
/* Move the remaining bytes to the beginning of utf8buf. */
if (in2size > 0)
memmove (utf8buf, in2ptr, in2size);
utf8len = in2size;
}
if (res1 == (size_t)(-1))
{
if (errno1 == EINVAL)
in1size = 0;
else if (errno1 == EILSEQ)
{
if (result != initial_result)
free (result);
errno = errno1;
return -1;
}
}
}
# undef utf8bufsize
}
done:
/* Now the final memory allocation. */
if (result == tmpbuf)
{
size_t memsize = length + extra_alloc;
if (*resultp != NULL && *lengthp >= memsize)
result = *resultp;
else
{
char *memory;
memory = (char *) malloc (memsize > 0 ? memsize : 1);
if (memory != NULL)
result = memory;
else
{
errno = ENOMEM;
return -1;
}
}
memcpy (result, tmpbuf, length);
}
else if (result != *resultp && length + extra_alloc < allocated)
{
/* Shrink the allocated memory if possible. */
size_t memsize = length + extra_alloc;
char *memory;
memory = (char *) realloc (result, memsize > 0 ? memsize : 1);
if (memory != NULL)
result = memory;
}
*resultp = result;
*lengthp = length;
return 0;
# undef tmpbuf
# undef tmpbufsize
}
int
mem_cd_iconveh (const char *src, size_t srclen,
const iconveh_t *cd,
enum iconv_ilseq_handler handler,
size_t *offsets,
char **resultp, size_t *lengthp)
{
return mem_cd_iconveh_internal (src, srclen, cd->cd, cd->cd1, cd->cd2,
handler, 0, offsets, resultp, lengthp);
}
char *
str_cd_iconveh (const char *src,
const iconveh_t *cd,
enum iconv_ilseq_handler handler)
{
/* For most encodings, a trailing NUL byte in the input will be converted
to a trailing NUL byte in the output. But not for UTF-7. So that this
function is usable for UTF-7, we have to exclude the NUL byte from the
conversion and add it by hand afterwards. */
char *result = NULL;
size_t length = 0;
int retval = mem_cd_iconveh_internal (src, strlen (src),
cd->cd, cd->cd1, cd->cd2, handler, 1,
NULL, &result, &length);
if (retval < 0)
{
if (result != NULL)
{
int saved_errno = errno;
free (result);
errno = saved_errno;
}
return NULL;
}
/* Add the terminating NUL byte. */
result[length] = '\0';
return result;
}
#endif
int
mem_iconveh (const char *src, size_t srclen,
const char *from_codeset, const char *to_codeset,
enum iconv_ilseq_handler handler,
size_t *offsets,
char **resultp, size_t *lengthp)
{
if (srclen == 0)
{
/* Nothing to convert. */
*lengthp = 0;
return 0;
}
else if (offsets == NULL && c_strcasecmp (from_codeset, to_codeset) == 0)
{
char *result;
if (*resultp != NULL && *lengthp >= srclen)
result = *resultp;
else
{
result = (char *) malloc (srclen);
if (result == NULL)
{
errno = ENOMEM;
return -1;
}
}
memcpy (result, src, srclen);
*resultp = result;
*lengthp = srclen;
return 0;
}
else
{
#if HAVE_ICONV
iconveh_t cd;
char *result;
size_t length;
int retval;
if (iconveh_open (to_codeset, from_codeset, &cd) < 0)
return -1;
result = *resultp;
length = *lengthp;
retval = mem_cd_iconveh (src, srclen, &cd, handler, offsets,
&result, &length);
if (retval < 0)
{
/* Close cd, but preserve the errno from str_cd_iconv. */
int saved_errno = errno;
iconveh_close (&cd);
errno = saved_errno;
}
else
{
if (iconveh_close (&cd) < 0)
{
/* Return -1, but free the allocated memory, and while doing
that, preserve the errno from iconveh_close. */
int saved_errno = errno;
if (result != *resultp && result != NULL)
free (result);
errno = saved_errno;
return -1;
}
*resultp = result;
*lengthp = length;
}
return retval;
#else
/* This is a different error code than if iconv_open existed but didn't
support from_codeset and to_codeset, so that the caller can emit
an error message such as
"iconv() is not supported. Installing GNU libiconv and
then reinstalling this package would fix this." */
errno = ENOSYS;
return -1;
#endif
}
}
char *
str_iconveh (const char *src,
const char *from_codeset, const char *to_codeset,
enum iconv_ilseq_handler handler)
{
if (*src == '\0' || c_strcasecmp (from_codeset, to_codeset) == 0)
{
char *result = strdup (src);
if (result == NULL)
errno = ENOMEM;
return result;
}
else
{
#if HAVE_ICONV
iconveh_t cd;
char *result;
if (iconveh_open (to_codeset, from_codeset, &cd) < 0)
return NULL;
result = str_cd_iconveh (src, &cd, handler);
if (result == NULL)
{
/* Close cd, but preserve the errno from str_cd_iconv. */
int saved_errno = errno;
iconveh_close (&cd);
errno = saved_errno;
}
else
{
if (iconveh_close (&cd) < 0)
{
/* Return NULL, but free the allocated memory, and while doing
that, preserve the errno from iconveh_close. */
int saved_errno = errno;
free (result);
errno = saved_errno;
return NULL;
}
}
return result;
#else
/* This is a different error code than if iconv_open existed but didn't
support from_codeset and to_codeset, so that the caller can emit
an error message such as
"iconv() is not supported. Installing GNU libiconv and
then reinstalling this package would fix this." */
errno = ENOSYS;
return NULL;
#endif
}
}
|