Have iconv accept redundant escape sequences in IBM900, IBM903, IBM905,

IBM907, and IBM909.

Patch for bug #17197 changes the encoder to avoid generating redundant
shift sequences.  However, those sequences may already be present in
data encododed by prior versions of the encoder.  This change modifies
the decoder to also avoid rejecting redundant shift sequences.

        [BZ #19432]
        * iconvdata/Makefile: Add bug-iconv11.
        * iconvdata/bug-iconv11.c: New test.
        * iconvdata/ibm930.c: Do not reject redundant shift sequences.
        * iconvdata/ibm933.c: Same.
        * iconvdata/ibm935.c: Same.
        * iconvdata/ibm937.c: Same.
        * iconvdata/ibm939.c: Same.
This commit is contained in:
Martin Sebor 2016-01-15 11:25:13 -07:00
parent f2b3078e6a
commit 692de4b396
8 changed files with 136 additions and 61 deletions

View File

@ -1,3 +1,14 @@
2016-01-15 Martin Sebor <msebor@redhat.com>
[BZ #19432]
* iconvdata/Makefile: Add bug-iconv11.
* iconvdata/bug-iconv11.c: New test.
* iconvdata/ibm930.c: Do not reject redundant shift sequences.
* iconvdata/ibm933.c: Same.
* iconvdata/ibm935.c: Same.
* iconvdata/ibm937.c: Same.
* iconvdata/ibm939.c: Same.
2016-01-15 Martin Sebor <msebor@redhat.com> 2016-01-15 Martin Sebor <msebor@redhat.com>
[BZ #19443] [BZ #19443]

View File

@ -68,7 +68,7 @@ modules.so := $(addsuffix .so, $(modules))
ifeq (yes,$(build-shared)) ifeq (yes,$(build-shared))
tests = bug-iconv1 bug-iconv2 tst-loading tst-e2big tst-iconv4 bug-iconv4 \ tests = bug-iconv1 bug-iconv2 tst-loading tst-e2big tst-iconv4 bug-iconv4 \
tst-iconv6 bug-iconv5 bug-iconv6 tst-iconv7 bug-iconv8 bug-iconv9 \ tst-iconv6 bug-iconv5 bug-iconv6 tst-iconv7 bug-iconv8 bug-iconv9 \
bug-iconv10 bug-iconv10 bug-iconv11
ifeq ($(have-thread-library),yes) ifeq ($(have-thread-library),yes)
tests += bug-iconv3 tests += bug-iconv3
endif endif

114
iconvdata/bug-iconv11.c Normal file
View File

@ -0,0 +1,114 @@
/* bug 19432: iconv rejects redundant escape sequences in IBM903,
IBM905, IBM907, and IBM909
Copyright (C) 2016 Free Software Foundation, Inc.
This file is part of the GNU C Library.
The GNU C Library is free software; you can redistribute it and/or
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
Lesser General Public License for more details.
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 <iconv.h>
#include <stdio.h>
#include <stdlib.h>
#include <string.h>
#include <errno.h>
// The longest test input sequence.
#define MAXINBYTES 8
#define MAXOUTBYTES (MAXINBYTES * MB_LEN_MAX)
/* Verify that a conversion of the INPUT sequence consisting of
INBYTESLEFT bytes in the encoding specified by the codeset
named by FROM_SET is successful.
Return 0 on success, non-zero on iconv() failure. */
static int
test_ibm93x (const char *from_set, const char *input, size_t inbytesleft)
{
const char to_set[] = "UTF-8";
iconv_t cd = iconv_open (to_set, from_set);
if (cd == (iconv_t) -1)
{
printf ("iconv_open(\"%s\", \"%s\"): %s\n",
from_set, to_set, strerror (errno));
return 1;
}
char output [MAXOUTBYTES];
size_t outbytesleft = sizeof output;
char *inbuf = (char*)input;
char *outbuf = output;
printf ("iconv(cd, %p, %zu, %p, %zu)\n",
inbuf, inbytesleft, outbuf, outbytesleft);
errno = 0;
size_t ret = iconv (cd, &inbuf, &inbytesleft, &outbuf, &outbytesleft);
printf (" ==> %td: %s\n"
" inbuf%+td, inbytesleft=%zu, outbuf%+td, outbytesleft=%zu\n",
ret, strerror (errno),
inbuf - input, inbytesleft, outbuf - output, outbytesleft);
// Return 0 on success, non-zero on iconv() failure.
return ret == (size_t)-1 || errno;
}
static int
do_test (void)
{
// State-dependent encodings to exercise.
static const char* const to_code[] = {
"IBM930", "IBM933", "IBM935", "IBM937", "IBM939"
};
static const size_t ncodesets = sizeof to_code / sizeof *to_code;
static const struct {
char txt[MAXINBYTES];
size_t len;
} input[] = {
#define DATA(s) { s, sizeof s - 1 }
/* <SI>: denotes the shift-in 1-byte escape sequence, changing
the encoder from a sigle-byte encoding to multibyte
<SO>: denotes the shift-out 1-byte escape sequence, switching
the encoder from a multibyte to a single-byte state */
DATA ("\x0e"), // <SI> (not redundant)
DATA ("\x0f"), // <S0> (redundant with initial state)
DATA ("\x0e\x0e"), // <SI><SI>
DATA ("\x0e\x0f\x0f"), // <SI><SO><SO>
DATA ("\x0f\x0f"), // <SO><SO>
DATA ("\x0f\x0e\x0e"), // <SO><SI><SI>
DATA ("\x0e\x0f\xc7\x0f"), // <SI><SO><G><SO>
DATA ("\xc7\x0f") // <G><SO> (redundant with initial state)
};
static const size_t ninputs = sizeof input / sizeof *input;
int ret = 0;
size_t i, j;
/* Iterate over the IBM93x codesets above and exercise each with
the input sequences above. */
for (i = 0; i != ncodesets; ++i)
for (j = 0; j != ninputs; ++j)
ret += test_ibm93x (to_code [i], input [i].txt, input [i].len);
return ret;
}
#define TEST_FUNCTION do_test ()
#include "../test-skeleton.c"

View File

@ -110,24 +110,14 @@ enum
\ \
if (__builtin_expect (ch, 0) == SO) \ if (__builtin_expect (ch, 0) == SO) \
{ \ { \
/* Shift OUT, change to DBCS converter. */ \ /* Shift OUT, change to DBCS converter (redundant escape okay). */ \
if (curcs == db) \
{ \
result = __GCONV_ILLEGAL_INPUT; \
break; \
} \
curcs = db; \ curcs = db; \
++inptr; \ ++inptr; \
continue; \ continue; \
} \ } \
else if (__builtin_expect (ch, 0) == SI) \ else if (__builtin_expect (ch, 0) == SI) \
{ \ { \
/* Shift IN, change to SBCS converter */ \ /* Shift IN, change to SBCS converter (redundant escape okay). */ \
if (curcs == sb) \
{ \
result = __GCONV_ILLEGAL_INPUT; \
break; \
} \
curcs = sb; \ curcs = sb; \
++inptr; \ ++inptr; \
continue; \ continue; \

View File

@ -108,24 +108,14 @@ enum
\ \
if (__builtin_expect (ch, 0) == SO) \ if (__builtin_expect (ch, 0) == SO) \
{ \ { \
/* Shift OUT, change to DBCS converter. */ \ /* Shift OUT, change to DBCS converter (redundant escape okay). */ \
if (curcs == db) \
{ \
result = __GCONV_ILLEGAL_INPUT; \
break; \
} \
curcs = db; \ curcs = db; \
++inptr; \ ++inptr; \
continue; \ continue; \
} \ } \
else if (__builtin_expect (ch, 0) == SI) \ else if (__builtin_expect (ch, 0) == SI) \
{ \ { \
/* Shift IN, change to SBCS converter. */ \ /* Shift IN, change to SBCS converter (redundant escape okay). */ \
if (curcs == sb) \
{ \
result = __GCONV_ILLEGAL_INPUT; \
break; \
} \
curcs = sb; \ curcs = sb; \
++inptr; \ ++inptr; \
continue; \ continue; \

View File

@ -109,24 +109,14 @@ enum
\ \
if (__builtin_expect(ch, 0) == SO) \ if (__builtin_expect(ch, 0) == SO) \
{ \ { \
/* Shift OUT, change to DBCS converter. */ \ /* Shift OUT, change to DBCS converter (redundant escape okay). */ \
if (curcs == db) \
{ \
result = __GCONV_ILLEGAL_INPUT; \
break; \
} \
curcs = db; \ curcs = db; \
++inptr; \ ++inptr; \
continue; \ continue; \
} \ } \
else if (__builtin_expect (ch, 0) == SI) \ else if (__builtin_expect (ch, 0) == SI) \
{ \ { \
/* Shift IN, change to SBCS converter. */ \ /* Shift IN, change to SBCS converter (redundant escape okay). */ \
if (curcs == sb) \
{ \
result = __GCONV_ILLEGAL_INPUT; \
break; \
} \
curcs = sb; \ curcs = sb; \
++inptr; \ ++inptr; \
continue; \ continue; \

View File

@ -109,24 +109,14 @@ enum
\ \
if (__builtin_expect (ch, 0) == SO) \ if (__builtin_expect (ch, 0) == SO) \
{ \ { \
/* Shift OUT, change to DBCS converter. */ \ /* Shift OUT, change to DBCS converter (redundant escape okay). */ \
if (curcs == db) \
{ \
result = __GCONV_ILLEGAL_INPUT; \
break; \
} \
curcs = db; \ curcs = db; \
++inptr; \ ++inptr; \
continue; \ continue; \
} \ } \
else if (__builtin_expect (ch, 0) == SI) \ else if (__builtin_expect (ch, 0) == SI) \
{ \ { \
/* Shift IN, change to SBCS converter. */ \ /* Shift IN, change to SBCS converter (redundant escape okay). */ \
if (curcs == sb) \
{ \
result = __GCONV_ILLEGAL_INPUT; \
break; \
} \
curcs = sb; \ curcs = sb; \
++inptr; \ ++inptr; \
continue; \ continue; \

View File

@ -109,24 +109,14 @@ enum
\ \
if (__builtin_expect (ch, 0) == SO) \ if (__builtin_expect (ch, 0) == SO) \
{ \ { \
/* Shift OUT, change to DBCS converter. */ \ /* Shift OUT, change to DBCS converter (redundant escape okay). */ \
if (curcs == db) \
{ \
result = __GCONV_ILLEGAL_INPUT; \
break; \
} \
curcs = db; \ curcs = db; \
++inptr; \ ++inptr; \
continue; \ continue; \
} \ } \
else if (__builtin_expect (ch, 0) == SI) \ else if (__builtin_expect (ch, 0) == SI) \
{ \ { \
/* Shift IN, change to SBCS converter. */ \ /* Shift IN, change to SBCS converter (redundant escape okay). */ \
if (curcs == sb) \
{ \
result = __GCONV_ILLEGAL_INPUT; \
break; \
} \
curcs = sb; \ curcs = sb; \
++inptr; \ ++inptr; \
continue; \ continue; \