/* Conversion module for Unicode
- Copyright (C) 1999, 2000 Free Software Foundation, Inc.
+ Copyright (C) 1999-2019 Free Software Foundation, Inc.
This file is part of the GNU C Library.
Contributed by Ulrich Drepper <drepper@cygnus.com>, 1999.
The GNU C Library is free software; you can redistribute it and/or
- modify it under the terms of the GNU Library General Public License as
- published by the Free Software Foundation; either version 2 of the
- License, or (at your option) any later version.
+ 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.
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
- Library General Public License for more details.
+ Lesser General Public License for more details.
- You should have received a copy of the GNU Library General Public
- License along with the GNU C Library; see the file COPYING.LIB. If not,
- write to the Free Software Foundation, Inc., 59 Temple Place - Suite 330,
- Boston, MA 02111-1307, USA. */
+ You should have received a copy of the GNU Lesser General Public
+ License along with the GNU C Library; if not, see
+ <http://www.gnu.org/licenses/>. */
#include <byteswap.h>
+#include <dlfcn.h>
#include <gconv.h>
#include <stddef.h>
#include <stdint.h>
#define DEFINE_FINI 0
#define MIN_NEEDED_FROM 2
#define MIN_NEEDED_TO 4
+#define ONE_DIRECTION 0
#define FROM_DIRECTION (dir == from_unicode)
#define PREPARE_LOOP \
enum direction dir = ((struct unicode_data *) step->__data)->dir; \
{ \
/* We have to find out which byte order the file is encoded in. */ \
if (inptr + 2 > inend) \
- return __GCONV_EMPTY_INPUT; \
+ return (inptr == inend \
+ ? __GCONV_EMPTY_INPUT : __GCONV_INCOMPLETE_INPUT); \
\
if (get16u (inptr) == BOM) \
/* Simply ignore the BOM character. */ \
- inptr += 2; \
+ *inptrp = inptr += 2; \
else if (get16u (inptr) == BOM_OE) \
{ \
- ((struct unicode_data *) step->__data)->swap = 1; \
- inptr += 2; \
+ data->__flags |= __GCONV_SWAP; \
+ *inptrp = inptr += 2; \
} \
} \
} \
else if (!data->__internal_use && data->__invocation_counter == 0) \
{ \
/* Emit the Byte Order Mark. */ \
- if (__builtin_expect (outbuf + 2 > outend, 0)) \
+ if (__glibc_unlikely (outbuf + 2 > outend)) \
return __GCONV_FULL_OUTPUT; \
\
put16u (outbuf, BOM); \
outbuf += 2; \
} \
- swap = ((struct unicode_data *) step->__data)->swap;
-#define EXTRA_LOOP_ARGS , data, swap
+ swap = data->__flags & __GCONV_SWAP;
+#define EXTRA_LOOP_ARGS , swap
/* Direction of the transformation. */
struct unicode_data
{
enum direction dir;
- int swap;
};
+extern int gconv_init (struct __gconv_step *step);
int
gconv_init (struct __gconv_step *step)
{
enum direction dir = illegal_dir;
int result;
- if (__strcasecmp (step->__from_name, "UNICODE") == 0)
+ if (strcmp (step->__from_name, "UNICODE//") == 0)
dir = from_unicode;
else
dir = to_unicode;
if (new_data != NULL)
{
new_data->dir = dir;
- new_data->swap = 0;
step->__data = new_data;
if (dir == from_unicode)
}
+extern void gconv_end (struct __gconv_step *data);
void
gconv_end (struct __gconv_step *data)
{
{ \
uint32_t c = get32 (inptr); \
\
- if (__builtin_expect (c, 0) >= 0x10000) \
+ if (__glibc_unlikely (c >= 0x10000)) \
{ \
+ UNICODE_TAG_HANDLER (c, 4); \
+ STANDARD_TO_LOOP_ERR_HANDLER (4); \
+ } \
+ else if (__glibc_unlikely (c >= 0xd800 && c < 0xe000)) \
+ { \
+ /* 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. */ \
+ result = __GCONV_ILLEGAL_INPUT; \
if (! ignore_errors_p ()) \
- { \
- /* This is an illegal character. */ \
- result = __GCONV_ILLEGAL_INPUT; \
- break; \
- } \
- \
- ++*converted; \
+ break; \
+ inptr += 4; \
+ ++*irreversible; \
+ continue; \
} \
else \
{ \
\
inptr += 4; \
}
+#define LOOP_NEED_FLAGS
#define EXTRA_LOOP_DECLS \
- , struct __gconv_step_data *step_data, int swap
+ , int swap
#include <iconv/loop.c>
if (swap) \
u1 = bswap_16 (u1); \
\
+ if (__glibc_unlikely (u1 >= 0xd800 && u1 < 0xe000)) \
+ { \
+ /* Surrogate characters in UCS-2 input are not valid. Reject \
+ them. (Catching this here is not security relevant.) */ \
+ STANDARD_FROM_LOOP_ERR_HANDLER (2); \
+ } \
+ \
put32 (outptr, u1); \
\
inptr += 2; \
outptr += 4; \
}
+#define LOOP_NEED_FLAGS
#define EXTRA_LOOP_DECLS \
- , struct __gconv_step_data *step_data, int swap
+ , int swap
#include <iconv/loop.c>
projects / thirdparty / glibc.git / blobdiff