2000-03-21 20:18:34 +00:00
|
|
|
/* Conversion module for Unicode
|
2024-01-01 18:12:26 +00:00
|
|
|
Copyright (C) 1999-2024 Free Software Foundation, Inc.
|
2000-03-21 20:18:34 +00:00
|
|
|
This file is part of the GNU C Library.
|
|
|
|
|
|
|
|
The GNU C Library is free software; you can redistribute it and/or
|
2001-07-06 04:58:11 +00:00
|
|
|
modify it under the terms of the GNU Lesser General Public
|
|
|
|
License as published by the Free Software Foundation; either
|
|
|
|
version 2.1 of the License, or (at your option) any later version.
|
2000-03-21 20:18:34 +00:00
|
|
|
|
|
|
|
The GNU C Library 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
|
2001-07-06 04:58:11 +00:00
|
|
|
Lesser General Public License for more details.
|
2000-03-21 20:18:34 +00:00
|
|
|
|
2001-07-06 04:58:11 +00:00
|
|
|
You should have received a copy of the GNU Lesser General Public
|
2012-02-09 23:18:22 +00:00
|
|
|
License along with the GNU C Library; if not, see
|
Prefer https to http for gnu.org and fsf.org URLs
Also, change sources.redhat.com to sourceware.org.
This patch was automatically generated by running the following shell
script, which uses GNU sed, and which avoids modifying files imported
from upstream:
sed -ri '
s,(http|ftp)(://(.*\.)?(gnu|fsf|sourceware)\.org($|[^.]|\.[^a-z])),https\2,g
s,(http|ftp)(://(.*\.)?)sources\.redhat\.com($|[^.]|\.[^a-z]),https\2sourceware.org\4,g
' \
$(find $(git ls-files) -prune -type f \
! -name '*.po' \
! -name 'ChangeLog*' \
! -path COPYING ! -path COPYING.LIB \
! -path manual/fdl-1.3.texi ! -path manual/lgpl-2.1.texi \
! -path manual/texinfo.tex ! -path scripts/config.guess \
! -path scripts/config.sub ! -path scripts/install-sh \
! -path scripts/mkinstalldirs ! -path scripts/move-if-change \
! -path INSTALL ! -path locale/programs/charmap-kw.h \
! -path po/libc.pot ! -path sysdeps/gnu/errlist.c \
! '(' -name configure \
-execdir test -f configure.ac -o -f configure.in ';' ')' \
! '(' -name preconfigure \
-execdir test -f preconfigure.ac ';' ')' \
-print)
and then by running 'make dist-prepare' to regenerate files built
from the altered files, and then executing the following to cleanup:
chmod a+x sysdeps/unix/sysv/linux/riscv/configure
# Omit irrelevant whitespace and comment-only changes,
# perhaps from a slightly-different Autoconf version.
git checkout -f \
sysdeps/csky/configure \
sysdeps/hppa/configure \
sysdeps/riscv/configure \
sysdeps/unix/sysv/linux/csky/configure
# Omit changes that caused a pre-commit check to fail like this:
# remote: *** error: sysdeps/powerpc/powerpc64/ppc-mcount.S: trailing lines
git checkout -f \
sysdeps/powerpc/powerpc64/ppc-mcount.S \
sysdeps/unix/sysv/linux/s390/s390-64/syscall.S
# Omit change that caused a pre-commit check to fail like this:
# remote: *** error: sysdeps/sparc/sparc64/multiarch/memcpy-ultra3.S: last line does not end in newline
git checkout -f sysdeps/sparc/sparc64/multiarch/memcpy-ultra3.S
2019-09-07 05:40:42 +00:00
|
|
|
<https://www.gnu.org/licenses/>. */
|
2000-03-21 20:18:34 +00:00
|
|
|
|
|
|
|
#include <byteswap.h>
|
2000-06-12 19:47:50 +00:00
|
|
|
#include <dlfcn.h>
|
2000-03-21 20:18:34 +00:00
|
|
|
#include <gconv.h>
|
|
|
|
#include <stddef.h>
|
|
|
|
#include <stdint.h>
|
|
|
|
#include <stdlib.h>
|
|
|
|
#include <string.h>
|
|
|
|
|
|
|
|
/* This is the Byte Order Mark character (BOM). */
|
|
|
|
#define BOM 0xfeff
|
|
|
|
/* And in the other endian format. */
|
|
|
|
#define BOM_OE 0xfffe
|
|
|
|
|
|
|
|
|
|
|
|
/* Definitions used in the body of the `gconv' function. */
|
|
|
|
#define FROM_LOOP from_unicode_loop
|
|
|
|
#define TO_LOOP to_unicode_loop
|
|
|
|
#define DEFINE_INIT 0
|
|
|
|
#define DEFINE_FINI 0
|
|
|
|
#define MIN_NEEDED_FROM 2
|
|
|
|
#define MIN_NEEDED_TO 4
|
2014-05-01 20:42:40 +00:00
|
|
|
#define ONE_DIRECTION 0
|
2000-03-21 20:18:34 +00:00
|
|
|
#define FROM_DIRECTION (dir == from_unicode)
|
|
|
|
#define PREPARE_LOOP \
|
|
|
|
enum direction dir = ((struct unicode_data *) step->__data)->dir; \
|
|
|
|
int swap; \
|
|
|
|
if (FROM_DIRECTION) \
|
|
|
|
{ \
|
|
|
|
if (data->__invocation_counter == 0) \
|
|
|
|
{ \
|
|
|
|
/* We have to find out which byte order the file is encoded in. */ \
|
2000-04-09 17:43:29 +00:00
|
|
|
if (inptr + 2 > inend) \
|
2002-11-20 23:42:04 +00:00
|
|
|
return (inptr == inend \
|
|
|
|
? __GCONV_EMPTY_INPUT : __GCONV_INCOMPLETE_INPUT); \
|
2000-03-21 20:18:34 +00:00
|
|
|
\
|
2023-02-10 17:09:10 +00:00
|
|
|
if (get16 (inptr) == BOM) \
|
2000-03-21 20:18:34 +00:00
|
|
|
/* Simply ignore the BOM character. */ \
|
2001-04-12 20:26:40 +00:00
|
|
|
*inptrp = inptr += 2; \
|
2023-02-10 17:09:10 +00:00
|
|
|
else if (get16 (inptr) == BOM_OE) \
|
2000-03-21 20:18:34 +00:00
|
|
|
{ \
|
2011-12-21 23:45:50 +00:00
|
|
|
data->__flags |= __GCONV_SWAP; \
|
2001-04-12 20:26:40 +00:00
|
|
|
*inptrp = inptr += 2; \
|
2000-03-21 20:18:34 +00:00
|
|
|
} \
|
|
|
|
} \
|
|
|
|
} \
|
|
|
|
else if (!data->__internal_use && data->__invocation_counter == 0) \
|
|
|
|
{ \
|
|
|
|
/* Emit the Byte Order Mark. */ \
|
2014-02-10 13:45:42 +00:00
|
|
|
if (__glibc_unlikely (outbuf + 2 > outend)) \
|
2000-03-21 20:18:34 +00:00
|
|
|
return __GCONV_FULL_OUTPUT; \
|
|
|
|
\
|
2023-02-10 17:09:10 +00:00
|
|
|
put16 (outbuf, BOM); \
|
2000-03-21 20:18:34 +00:00
|
|
|
outbuf += 2; \
|
|
|
|
} \
|
2011-12-21 23:45:50 +00:00
|
|
|
swap = data->__flags & __GCONV_SWAP;
|
2000-06-12 19:47:50 +00:00
|
|
|
#define EXTRA_LOOP_ARGS , swap
|
2000-03-21 20:18:34 +00:00
|
|
|
|
|
|
|
|
|
|
|
/* Direction of the transformation. */
|
|
|
|
enum direction
|
|
|
|
{
|
|
|
|
illegal_dir,
|
|
|
|
to_unicode,
|
|
|
|
from_unicode
|
|
|
|
};
|
|
|
|
|
|
|
|
struct unicode_data
|
|
|
|
{
|
|
|
|
enum direction dir;
|
|
|
|
};
|
|
|
|
|
|
|
|
|
2000-11-28 07:10:56 +00:00
|
|
|
extern int gconv_init (struct __gconv_step *step);
|
2000-03-21 20:18:34 +00:00
|
|
|
int
|
|
|
|
gconv_init (struct __gconv_step *step)
|
|
|
|
{
|
|
|
|
/* Determine which direction. */
|
|
|
|
struct unicode_data *new_data;
|
|
|
|
enum direction dir = illegal_dir;
|
|
|
|
int result;
|
|
|
|
|
2000-08-24 22:55:41 +00:00
|
|
|
if (strcmp (step->__from_name, "UNICODE//") == 0)
|
2000-03-21 20:18:34 +00:00
|
|
|
dir = from_unicode;
|
|
|
|
else
|
|
|
|
dir = to_unicode;
|
|
|
|
|
|
|
|
new_data = (struct unicode_data *) malloc (sizeof (struct unicode_data));
|
|
|
|
|
|
|
|
result = __GCONV_NOMEM;
|
|
|
|
if (new_data != NULL)
|
|
|
|
{
|
|
|
|
new_data->dir = dir;
|
|
|
|
step->__data = new_data;
|
|
|
|
|
|
|
|
if (dir == from_unicode)
|
|
|
|
{
|
|
|
|
step->__min_needed_from = MIN_NEEDED_FROM;
|
|
|
|
step->__max_needed_from = MIN_NEEDED_FROM;
|
|
|
|
step->__min_needed_to = MIN_NEEDED_TO;
|
|
|
|
step->__max_needed_to = MIN_NEEDED_TO;
|
|
|
|
}
|
|
|
|
else
|
|
|
|
{
|
|
|
|
step->__min_needed_from = MIN_NEEDED_TO;
|
|
|
|
step->__max_needed_from = MIN_NEEDED_TO;
|
|
|
|
step->__min_needed_to = MIN_NEEDED_FROM;
|
|
|
|
step->__max_needed_to = MIN_NEEDED_FROM;
|
|
|
|
}
|
|
|
|
|
|
|
|
step->__stateful = 0;
|
|
|
|
|
|
|
|
result = __GCONV_OK;
|
|
|
|
}
|
|
|
|
|
|
|
|
return result;
|
|
|
|
}
|
|
|
|
|
|
|
|
|
2000-11-28 07:10:56 +00:00
|
|
|
extern void gconv_end (struct __gconv_step *data);
|
2000-03-21 20:18:34 +00:00
|
|
|
void
|
|
|
|
gconv_end (struct __gconv_step *data)
|
|
|
|
{
|
|
|
|
free (data->__data);
|
|
|
|
}
|
|
|
|
|
|
|
|
|
|
|
|
/* Convert from the internal (UCS4-like) format to UCS2. */
|
|
|
|
#define MIN_NEEDED_INPUT MIN_NEEDED_TO
|
|
|
|
#define MIN_NEEDED_OUTPUT MIN_NEEDED_FROM
|
|
|
|
#define LOOPFCT TO_LOOP
|
|
|
|
#define BODY \
|
|
|
|
{ \
|
2000-03-28 17:33:37 +00:00
|
|
|
uint32_t c = get32 (inptr); \
|
2000-03-21 20:18:34 +00:00
|
|
|
\
|
2014-02-10 13:45:42 +00:00
|
|
|
if (__glibc_unlikely (c >= 0x10000)) \
|
2000-03-21 20:18:34 +00:00
|
|
|
{ \
|
Update.
2001-06-04 Bruno Haible <haible@clisp.cons.org>
* iconv/loop.c (UNICODE_TAG_HANDLER): New macro.
* iconv/gconv_simple.c (__gconv_transform_internal_ascii): Invoke
UNICODE_TAG_HANDLER.
(__gconv_transform_internal_ucs2): Likewise.
(__gconv_transform_internal_ucs2reverse): Likewise.
* iconvdata/8bit-gap.c (BODY for TO_LOOP): Invoke UNICODE_TAG_HANDLER.
* iconvdata/8bit-generic.c (BODY for TO_LOOP): Likewise.
* iconvdata/ansi_x3.110.c (BODY for TO_LOOP): Likewise.
* iconvdata/big5.c (BODY for TO_LOOP): Likewise.
* iconvdata/big5hkscs.c (BODY for TO_LOOP): Likewise.
* iconvdata/cp1255.c (BODY for TO_LOOP): Likewise.
* iconvdata/cp1258.c (BODY for TO_LOOP): Likewise.
* iconvdata/euc-cn.c (BODY for TO_LOOP): Likewise.
* iconvdata/euc-jp.c (BODY for TO_LOOP): Likewise.
* iconvdata/euc-kr.c (BODY for TO_LOOP): Likewise.
* iconvdata/euc-tw.c (BODY for TO_LOOP): Likewise.
* iconvdata/gbk.c (BODY for TO_LOOP): Likewise.
* iconvdata/ibm930.c (BODY for TO_LOOP): Likewise.
* iconvdata/ibm932.c (BODY for TO_LOOP): Likewise.
* iconvdata/ibm933.c (BODY for TO_LOOP): Likewise.
* iconvdata/ibm935.c (BODY for TO_LOOP): Likewise.
* iconvdata/ibm937.c (BODY for TO_LOOP): Likewise.
* iconvdata/ibm939.c (BODY for TO_LOOP): Likewise.
* iconvdata/ibm943.c (BODY for TO_LOOP): Likewise.
* iconvdata/iso646.c (BODY for TO_LOOP): Likewise.
* iconvdata/iso8859-1.c (BODY for TO_LOOP): Likewise.
* iconvdata/iso_6937.c (BODY for TO_LOOP): Likewise.
* iconvdata/iso_6937-2.c (BODY for TO_LOOP): Likewise.
* iconvdata/iso-2022-cn.c (BODY for TO_LOOP): Likewise.
* iconvdata/iso-2022-cn-ext.c (BODY for TO_LOOP): Likewise.
* iconvdata/iso-2022-kr.c (BODY for TO_LOOP): Likewise.
* iconvdata/johab.c (BODY for TO_LOOP): Likewise.
* iconvdata/sjis.c (BODY for TO_LOOP): Likewise.
* iconvdata/t.61.c (BODY for TO_LOOP): Likewise.
* iconvdata/uhc.c (BODY for TO_LOOP): Likewise.
* iconvdata/unicode.c (BODY for TO_LOOP): Likewise.
* iconvdata/iso-2022-jp.c (TAG_none, TAG_language, TAG_language_j,
TAG_language_ja, TAG_language_k, TAG_language_ko, TAG_language_z,
TAG_language_zh, CURRENT_TAG_MASK): New enum values.
(EMIT_SHIFT_TO_INIT): Don't emit an escape sequence if ASCII_set
is already selected but set2 or tag are set.
(conversion): New enum type.
(cvlist_t): New type.
(CVLIST, CVLIST_FIRST, CVLIST_REST): New macros.
(conversion_lists): New array.
(BODY for TO_LOOP): Keep track of Unicode 3.1 language tag. If "ja",
prefer conversion to Japanese character sets. If "zh", prefer
conversion to GB2312. If "ko", prefer conversion to KSC5601. Small
optimizations.
(INIT_PARAMS): Add tag.
(UPDATE_PARAMS): Add tag.
2001-06-04 Bruno Haible <haible@clisp.cons.org>
* locale/programs/locfile.c (write_locale_data): Before creat(),
unlink the file, to avoid crashing the processes that mmap it. Change
a double slash to a single slash. Free fname in case of error return.
2001-06-02 Jakub Jelinek <jakub@redhat.com>
* sysdeps/i386/fpu/s_frexpl.S (__frexpl): Mostly revert 2000-12-03
changes, do the special handling for denormal numbers, not for
normalized numbers (patch by <trevin@xmission.com>).
* math/test-misc.c (main): Test frexpl with denormal arguments.
2001-06-04 Jakub Jelinek <jakub@redhat.com>
* math/libm-test.inc (llround_test): Add two new llround tests.
* sysdeps/ieee754/ldbl-96/s_llroundl.c (__llroundl): Don't allow
overflow when rounding away from zero.
2001-06-04 Jakub Jelinek <jakub@redhat.com>
* math/Makefile (libm-calls): Add e_log2, w_log2, remove s_log2.
* math/math_private.h (__ieee754_log2, __ieee754_log2f,
__ieee754_log2l): New prototypes.
* sysdeps/generic/w_log2.c: New file.
* sysdeps/generic/w_log2f.c: New file.
* sysdeps/generic/w_log2l.c: New file.
* sysdeps/generic/s_log2l.c: Move...
* sysdeps/generic/e_log2l.c: ...to here. Rename to __ieee754_log2l.
* sysdeps/ieee754/k_standard.c (__kernel_standard): Handle log2(0)
and log2(x < 0).
* sysdeps/i386/fpu/s_log2.S: Move...
* sysdeps/i386/fpu/e_log2.S: ...to here. Rename to __ieee754_log2.
* sysdeps/i386/fpu/s_log2f.S: Move...
* sysdeps/i386/fpu/e_log2f.S: ...to here. Rename to __ieee754_log2f.
* sysdeps/i386/fpu/s_log2l.S: Move...
* sysdeps/i386/fpu/e_log2l.S: ...to here. Rename to __ieee754_log2l.
* sysdeps/m68k/fpu/s_log2.S: Move...
* sysdeps/m68k/fpu/e_log2.S: ...to here. Rename to __ieee754_log2.
* sysdeps/m68k/fpu/s_log2f.S: Move...
* sysdeps/m68k/fpu/e_log2f.S: ...to here. Rename to __ieee754_log2f.
* sysdeps/m68k/fpu/s_log2l.S: Move...
* sysdeps/m68k/fpu/e_log2l.S: ...to here. Rename to __ieee754_log2l.
* sysdeps/ieee754/dbl-64/s_log2.c: Move...
* sysdeps/ieee754/dbl-64/e_log2.c: ...to here. Rename to
__ieee754_log2.
* sysdeps/ieee754/flt-32/s_log2f.c: Move...
* sysdeps/ieee754/flt-32/e_log2f.c: ...to here. Rename to
__ieee754_log2f.
2001-06-04 Jakub Jelinek <jakub@redhat.com>
* sysdeps/generic/w_exp2.c (u_threshold): Lower threshold so that
even arguments which result in denormalized exp2 are accepted.
(__exp2): Arguments equal to u_threshold already result into
underflow.
* sysdeps/generic/w_exp2f.c (u_threshold, __exp2f): Likewise.
* sysdeps/generic/w_exp2l.c (u_threshold, __exp2l): Likewise.
* sysdeps/ieee754/dbl-64/e_exp2.c (__ieee754_exp2): Lomark was too
low, with corrected lowmark use greaterequal, not greater.
* sysdeps/ieee754/flt-32/e_exp2f.c (__ieee754_exp2f): Likewise.
2001-06-04 Jakub Jelinek <jakub@redhat.com>
* math/libm-test.inc (ilogb_test): Test that ilogb(+-Inf) == INT_MAX.
* sysdeps/i386/fpu/s_ilogb.S (__ilogb): Return INT_MAX for +-Inf.
* sysdeps/i386/fpu/s_ilogbf.S (__ilogbf): Likewise.
* sysdeps/i386/fpu/s_ilogbl.S (__ilogbl): Likewise.
* sysdeps/ieee754/dbl-64/s_ilogb.c (__ilogb): Likewise.
* sysdeps/ieee754/flt-32/s_ilogbf.c (__ilogbf): Likewise.
* sysdeps/ieee754/ldbl-128/s_ilogbl.c (__ilogbl): Likewise.
* sysdeps/ieee754/ldbl-96/s_ilogbl.c (__ilogbl): Likewise.
2001-06-04 Jakub Jelinek <jakub@redhat.com>
* sysdeps/generic/w_coshl.c (__coshl): Test if finite argument
gave non-finite result instead of using constant in generic
version.
* sysdeps/generic/w_coshf.c (__coshf): Likewise.
* sysdeps/generic/w_cosh.c (__cosh): Likewise.
* sysdeps/generic/w_exp10.c (o_threshold, u_threshold): Remove.
(__exp10): Test if finite argument gave non-finite result.
* sysdeps/generic/w_exp10f.c (o_threshold, u_threshold, __exp10f):
Likewise.
* sysdeps/generic/w_exp10l.c (o_threshold, u_threshold, __exp10l):
Likewise.
2001-06-04 Jakub Jelinek <jakub@redhat.com>
* sysdeps/ieee754/ldbl-96/e_coshl.c (__ieee754_coshl): Fix
overflow threshold constant (log(LDBL_MAX)+M_LN2l).
2001-05-29 Bruno Haible <haible@clisp.cons.org>
* locale/programs/ld-ctype.c (idx_table): New struct type.
(idx_table_init, idx_table_get, idx_table_add): New functions.
(MAX_CHARNAMES_IDX): Remove macro.
(locale_ctype_t): Change type of charnames_idx field.
(ctype_startup): Change initialization of charnames_idx field.
(find_idx): Use idx_table_get and idx_table_add for speed.
* locale/programs/charmap.c (charmap_new_char): Fix ucs4 value
computation of characters in a range.
2001-05-29 Bruno Haible <haible@clisp.cons.org>
* iconvdata/gb18030.c (__fourbyte_to_ucs1): Add mappings for <U03F4>,
<U03F5>.
(__ucs_to_gb18030_tab1): Likewise.
(BODY for FROM_LOOP): Add mapping for <U00010000>..<U0010FFFF>.
(BODY for TO_LOOP): Likewise.
* iconvdata/tst-table-charmap.sh: Update for charmaps containing
<U00xxxxxx> syntax.
* iconvdata/tst-table-from.c (bmp_only): New variable.
(utf8_decode): If bmp_only, don't return characters outside Unicode
plane 0.
(main): When testing UTF-8 or GB18030, set bmp_only to 1. Don't print
a conversion line if utf8_decode returns NULL.
* iconvdata/tst-table-to.c (main): When testing encodings other than
UTF-8 and GB18030, loop upto U+30000 instead of U+10000. Use UTF-8
instead of UCS-2 as input.
* iconvdata/tst-table.sh: For GB18030, use only the part < 0x10000
of the charmap.
2001-05-29 Bruno Haible <haible@clisp.cons.org>
* iconvdata/cns11643l1.c: Update to Unicode 3.1.
(__cns11643l1_to_ucs4_tab): Regenerated.
(__cns11643l1_from_ucs4_tab12): Regenerated.
* iconvdata/cns11643.c: Update to Unicode 3.1.
(__cns11643l14_to_ucs4_tab): Remove array.
(__cns11643l3_to_ucs4_tab, __cns11643l4_to_ucs4_tab,
__cns11643l5_to_ucs4_tab, __cns11643l6_to_ucs4_tab,
__cns11643l7_to_ucs4_tab, __cns11643l15_to_ucs4_tab): New arrays.
(__cns11643_from_ucs4p0_tab): Renamed from __cns11643_from_ucs4_tab.
(__cns11643_from_ucs4p2_tab): New array.
* iconvdata/cns11643.h (__cns11643l14_to_ucs4_tab): Remove declaration.
(__cns11643l3_to_ucs4_tab, __cns11643l4_to_ucs4_tab,
__cns11643l5_to_ucs4_tab, __cns11643l6_to_ucs4_tab,
__cns11643l7_to_ucs4_tab, __cns11643l15_to_ucs4_tab): New declarations.
(cns11643_to_ucs4): Treat planes 3, 4, 5, 6, 7, 15 instead of 14.
(__cns11643_from_ucs4_tab): Remove declaration.
(__cns11643_from_ucs4p0_tab, __cns11643_from_ucs4p2_tab): New
declarations.
(ucs4_to_cns11643): Update for new arrays. Treat U+3400..U+4DFF and
U+20000..U+2A6D6.
* iconvdata/cns11643l2.h (__cns11643_from_ucs4_tab): Remove
declaration.
(__cns11643_from_ucs4p0_tab): New declaration.
(ucs4_to_cns11643l2): Update for new arrays.
* iconvdata/iso-2022-cn-ext.c (BODY for FROM_LOOP): Handle planes
3 to 7.
(BODY for TO_LOOP): Handle planes 3 to 7, instead of plane 14.
* iconvdata/EUC-TW.irreversible: New file.
* iconvdata/tst-table.sh: Use it.
* iconvdata/Makefile (distribute): Add CP1255.irreversible,
CP1258.irreversible, EUC-TW.irreversible.
2001-05-29 Bruno Haible <haible@clisp.cons.org>
* locale/C-translit.h.in: Add transliterations for new Unicode 3.1
mathematical symbols.
2001-06-06 12:55:46 +00:00
|
|
|
UNICODE_TAG_HANDLER (c, 4); \
|
2002-06-28 21:23:06 +00:00
|
|
|
STANDARD_TO_LOOP_ERR_HANDLER (4); \
|
2000-06-06 03:16:30 +00:00
|
|
|
} \
|
2014-02-10 13:45:42 +00:00
|
|
|
else if (__glibc_unlikely (c >= 0xd800 && c < 0xe000)) \
|
2000-09-18 22:41:47 +00:00
|
|
|
{ \
|
|
|
|
/* Surrogate characters in UCS-4 input are not valid. \
|
|
|
|
We must catch this, because the UCS-2 output might be \
|
|
|
|
interpreted as UTF-16 by other programs. If we let \
|
|
|
|
surrogates pass through, attackers could make a security \
|
|
|
|
hole exploit by synthesizing any desired plane 1-16 \
|
|
|
|
character. */ \
|
2024-09-20 11:10:54 +00:00
|
|
|
result = __gconv_mark_illegal_input (step_data); \
|
2000-09-18 22:41:47 +00:00
|
|
|
if (! ignore_errors_p ()) \
|
2002-06-28 21:23:06 +00:00
|
|
|
break; \
|
2000-09-18 22:41:47 +00:00
|
|
|
inptr += 4; \
|
|
|
|
++*irreversible; \
|
|
|
|
continue; \
|
|
|
|
} \
|
2000-06-06 03:16:30 +00:00
|
|
|
else \
|
|
|
|
{ \
|
|
|
|
put16 (outptr, c); \
|
|
|
|
outptr += 2; \
|
|
|
|
} \
|
2000-03-21 20:18:34 +00:00
|
|
|
\
|
|
|
|
inptr += 4; \
|
|
|
|
}
|
2000-06-12 19:47:50 +00:00
|
|
|
#define LOOP_NEED_FLAGS
|
2000-03-21 20:18:34 +00:00
|
|
|
#define EXTRA_LOOP_DECLS \
|
2000-06-12 19:47:50 +00:00
|
|
|
, int swap
|
2000-03-21 20:18:34 +00:00
|
|
|
#include <iconv/loop.c>
|
|
|
|
|
|
|
|
|
|
|
|
/* Convert from UCS2 to the internal (UCS4-like) format. */
|
|
|
|
#define MIN_NEEDED_INPUT MIN_NEEDED_FROM
|
|
|
|
#define MIN_NEEDED_OUTPUT MIN_NEEDED_TO
|
|
|
|
#define LOOPFCT FROM_LOOP
|
|
|
|
#define BODY \
|
|
|
|
{ \
|
2000-03-28 17:33:37 +00:00
|
|
|
uint16_t u1 = get16 (inptr); \
|
2000-03-21 20:18:34 +00:00
|
|
|
\
|
|
|
|
if (swap) \
|
|
|
|
u1 = bswap_16 (u1); \
|
|
|
|
\
|
2014-02-10 13:45:42 +00:00
|
|
|
if (__glibc_unlikely (u1 >= 0xd800 && u1 < 0xe000)) \
|
2000-09-18 22:41:47 +00:00
|
|
|
{ \
|
|
|
|
/* Surrogate characters in UCS-2 input are not valid. Reject \
|
|
|
|
them. (Catching this here is not security relevant.) */ \
|
2002-06-28 21:23:06 +00:00
|
|
|
STANDARD_FROM_LOOP_ERR_HANDLER (2); \
|
2000-09-18 22:41:47 +00:00
|
|
|
} \
|
|
|
|
\
|
2000-03-28 17:33:37 +00:00
|
|
|
put32 (outptr, u1); \
|
2000-03-21 20:18:34 +00:00
|
|
|
\
|
|
|
|
inptr += 2; \
|
|
|
|
outptr += 4; \
|
|
|
|
}
|
2000-09-18 22:41:47 +00:00
|
|
|
#define LOOP_NEED_FLAGS
|
2000-03-21 20:18:34 +00:00
|
|
|
#define EXTRA_LOOP_DECLS \
|
2000-06-12 19:47:50 +00:00
|
|
|
, int swap
|
2000-03-21 20:18:34 +00:00
|
|
|
#include <iconv/loop.c>
|
|
|
|
|
|
|
|
|
|
|
|
/* Now define the toplevel functions. */
|
|
|
|
#include <iconv/skeleton.c>
|