summaryrefslogtreecommitdiff
path: root/iconv
diff options
context:
space:
mode:
authorUlrich Drepper <drepper@redhat.com>2002-06-28 21:23:06 +0000
committerUlrich Drepper <drepper@redhat.com>2002-06-28 21:23:06 +0000
commite438a4684563c16b6d8bfb8e4066d277133e1912 (patch)
tree2b719edc95cbbb5a2f33f5588bb52a04daa9e717 /iconv
parent8dae594a51bdac0e5a045196b1af25e8974812a8 (diff)
Update.
2002-05-26 Bruno Haible <bruno@clisp.org> * iconv/loop.c (STANDARD_FROM_LOOP_ERR_HANDLER): New macro. (STANDARD_TO_LOOP_ERR_HANDLER): Renamed from STANDARD_ERR_HANDLER. All callers changed. * iconv/gconv_simple.c (ascii_internal_loop): For error handling use STANDARD_FROM_LOOP_ERR_HANDLER. (utf8_internal_loop): Likewise. (ucs2_internal_loop): Likewise. (internal_ucs2_loop): Perform error handling like in STANDARD_FROM_LOOP_ERR_HANDLER. * iconvdata/unicode.c (BODY for TO_LOOP): Perform error handling like in STANDARD_FROM_LOOP_ERR_HANDLER. (BODY for FROM_LOOP): Use STANDARD_FROM_LOOP_ERR_HANDLER for error handling. * iconvdata/utf-16.c (BODY for TO_LOOP): Perform error handling like in STANDARD_FROM_LOOP_ERR_HANDLER. (BODY for FROM_LOOP): Use STANDARD_FROM_LOOP_ERR_HANDLER for error handling. * iconvdata/utf-32.c (BODY for TO_LOOP): Perform error handling like in STANDARD_FROM_LOOP_ERR_HANDLER. (BODY for FROM_LOOP): Use STANDARD_FROM_LOOP_ERR_HANDLER for error handling. * iconvdata/big5.c (BODY for FROM_LOOP): For error handling use STANDARD_FROM_LOOP_ERR_HANDLER. * iconvdata/iso-2022-jp.c (BODY for FROM_LOOP): Likewise. * iconvdata/8bit-gap.c (BODY for FROM_LOOP): Likewise. * iconvdata/8bit-generic.c (BODY for FROM_LOOP): Likewise. * iconvdata/ansi_x3.110.c (BODY for FROM_LOOP): Likewise. * iconvdata/armscii-8.c (BODY for FROM_LOOP): Likewise. * iconvdata/cp1255.c (BODY for FROM_LOOP): Likewise. * iconvdata/cp1258.c (BODY for FROM_LOOP): Likewise. * iconvdata/euc-cn.c (BODY for FROM_LOOP): Likewise. * iconvdata/euc-jisx0213.c (BODY for FROM_LOOP): Likewise. * iconvdata/euc-jp.c (BODY for FROM_LOOP): Likewise. * iconvdata/euc-kr.c (BODY for FROM_LOOP): Likewise. * iconvdata/euc-tw.c (BODY for FROM_LOOP): Likewise. * iconvdata/big5hkscs.c (BODY for FROM_LOOP): Likewise. * iconvdata/gb18030.c (BODY for FROM_LOOP): Likewise. * iconvdata/gbk.c (BODY for FROM_LOOP): Likewise. * iconvdata/iso-2022-cn-ext.c (BODY for FROM_LOOP): Likewise. * iconvdata/iso-2022-cn.c (BODY for FROM_LOOP): Likewise. * iconvdata/iso-2022-jp-3.c (BODY for FROM_LOOP): Likewise. * iconvdata/iso-2022-kr.c (BODY for FROM_LOOP): Likewise. * iconvdata/iso646.c (BODY for FROM_LOOP): Likewise. * iconvdata/iso_6937-2.c (BODY for FROM_LOOP): Likewise. * iconvdata/iso_6937.c (BODY for FROM_LOOP): Likewise. * iconvdata/johab.c (BODY for FROM_LOOP): Likewise. * iconvdata/shift_jisx0213.c (BODY for FROM_LOOP): Likewise. * iconvdata/sjis.c (BODY for FROM_LOOP): Likewise. * iconvdata/t.61.c (BODY for FROM_LOOP): Likewise. * iconvdata/uhc.c (BODY for FROM_LOOP): Likewise. * iconvdata/utf-7.c (BODY for FROM_LOOP): Likewise. * iconvdata/gbbig5.c (BODY for FROM_LOOP): Likewise. When ignoring an error, still set result = __GCONV_ILLEGAL_INPUT. (BODY for TO_LOOP): Likewise. * iconvdata/ibm930.c (BODY for FROM_LOOP): For error handling use STANDARD_FROM_LOOP_ERR_HANDLER. (BODY for TO_LOOP): Here use STANDARD_TO_LOOP_ERR_HANDLER. * iconvdata/ibm932.c: Include <dlfcn.h> and <stdint.h>. (BODY for FROM_LOOP): Use STANDARD_FROM_LOOP_ERR_HANDLER for error handling. (BODY for TO_LOOP): Here use STANDARD_TO_LOOP_ERR_HANDLER. * iconvdata/ibm933.c (BODY for FROM_LOOP): For error handling use STANDARD_FROM_LOOP_ERR_HANDLER. (BODY for TO_LOOP): Here use STANDARD_TO_LOOP_ERR_HANDLER. * iconvdata/ibm935.c (BODY for FROM_LOOP): For error handling use STANDARD_FROM_LOOP_ERR_HANDLER. (BODY for TO_LOOP): Here use STANDARD_TO_LOOP_ERR_HANDLER. * iconvdata/ibm937.c (BODY for FROM_LOOP): For error handling use STANDARD_FROM_LOOP_ERR_HANDLER. (BODY for TO_LOOP): Here use STANDARD_TO_LOOP_ERR_HANDLER. * iconvdata/ibm939.c (BODY for FROM_LOOP): For error handling use STANDARD_FROM_LOOP_ERR_HANDLER. (BODY for TO_LOOP): Here use STANDARD_TO_LOOP_ERR_HANDLER. * iconvdata/ibm943.c: Include <dlfcn.h> and <stdint.h>. (BODY for FROM_LOOP): Use STANDARD_FROM_LOOP_ERR_HANDLER for error handling. (BODY for TO_LOOP): Here use STANDARD_TO_LOOP_ERR_HANDLER. * iconvdata/gbgbk.c (BODY for FROM_LOOP): Update. * iconvdata/iso8859-1.c (BODY for TO_LOOP): Update. * iconvdata/tcvn5712-1.c (BODY for TO_LOOP): Update. 2002-06-28 Kaz Kojima <kkojima@rr.iij4u.or.jp> * sysdeps/sh/dl-machine.h (elf_machine_load_address): Use local labels in assembler instructions.
Diffstat (limited to 'iconv')
-rw-r--r--iconv/gconv_simple.c76
-rw-r--r--iconv/loop.c33
2 files changed, 44 insertions, 65 deletions
diff --git a/iconv/gconv_simple.c b/iconv/gconv_simple.c
index b4dcf93c32..fbdac832e0 100644
--- a/iconv/gconv_simple.c
+++ b/iconv/gconv_simple.c
@@ -770,15 +770,7 @@ ucs4le_internal_loop_single (struct __gconv_step *step,
this is not an error because of the lack of possibilities to \
represent the result. This is a genuine bug in the input since \
ASCII does not allow such values. */ \
- if (! ignore_errors_p ()) \
- { \
- /* This is no correct ANSI_X3.4-1968 character. */ \
- result = __GCONV_ILLEGAL_INPUT; \
- break; \
- } \
- \
- ++*irreversible; \
- ++inptr; \
+ STANDARD_FROM_LOOP_ERR_HANDLER (1); \
} \
else \
/* It's an one byte sequence. */ \
@@ -808,7 +800,7 @@ ucs4le_internal_loop_single (struct __gconv_step *step,
if (__builtin_expect (*((const uint32_t *) inptr) > 0x7f, 0)) \
{ \
UNICODE_TAG_HANDLER (*((const uint32_t *) inptr), 4); \
- STANDARD_ERR_HANDLER (4); \
+ STANDARD_TO_LOOP_ERR_HANDLER (4); \
} \
else \
/* It's an one byte sequence. */ \
@@ -872,7 +864,7 @@ ucs4le_internal_loop_single (struct __gconv_step *step,
} \
else \
{ \
- STANDARD_ERR_HANDLER (4); \
+ STANDARD_TO_LOOP_ERR_HANDLER (4); \
} \
\
inptr += 4; \
@@ -951,24 +943,16 @@ ucs4le_internal_loop_single (struct __gconv_step *step,
{ \
int skipped; \
\
- if (! ignore_errors_p ()) \
- { \
- /* This is an illegal encoding. */ \
- result = __GCONV_ILLEGAL_INPUT; \
- break; \
- } \
- \
/* Search the end of this ill-formed UTF-8 character. This \
is the next byte with (x & 0xc0) != 0x80. */ \
- skipped = 0; \
- do \
- { \
- ++inptr; \
- ++skipped; \
- } \
- while (inptr < inend && (*inptr & 0xc0) == 0x80 && skipped < 5); \
+ skipped = 0; \
+ do \
+ ++skipped; \
+ while (inptr + skipped < inend \
+ && (*(inptr + skipped) & 0xc0) == 0x80 \
+ && skipped < 5); \
\
- continue; \
+ STANDARD_FROM_LOOP_ERR_HANDLER (skipped); \
} \
\
if (__builtin_expect (inptr + cnt > inend, 0)) \
@@ -985,16 +969,7 @@ ucs4le_internal_loop_single (struct __gconv_step *step,
break; \
} \
\
- if (ignore_errors_p ()) \
- { \
- /* Ignore it. */ \
- inptr += i; \
- ++*irreversible; \
- continue; \
- } \
- \
- result = __GCONV_ILLEGAL_INPUT; \
- break; \
+ STANDARD_FROM_LOOP_ERR_HANDLER (i); \
} \
\
/* Read the possible remaining bytes. */ \
@@ -1016,15 +991,7 @@ ucs4le_internal_loop_single (struct __gconv_step *step,
if (i < cnt || (cnt > 2 && (ch >> (5 * cnt - 4)) == 0)) \
{ \
/* This is an illegal encoding. */ \
- if (ignore_errors_p ()) \
- { \
- inptr += i; \
- ++*irreversible; \
- continue; \
- } \
- \
- result = __GCONV_ILLEGAL_INPUT; \
- break; \
+ STANDARD_FROM_LOOP_ERR_HANDLER (i); \
} \
\
inptr += cnt; \
@@ -1164,14 +1131,7 @@ ucs4le_internal_loop_single (struct __gconv_step *step,
{ \
/* Surrogate characters in UCS-2 input are not valid. Reject \
them. (Catching this here is not security relevant.) */ \
- if (! ignore_errors_p ()) \
- { \
- result = __GCONV_ILLEGAL_INPUT; \
- break; \
- } \
- inptr += 2; \
- ++*irreversible; \
- continue; \
+ STANDARD_FROM_LOOP_ERR_HANDLER (2); \
} \
\
*((uint32_t *) outptr)++ = u1; \
@@ -1203,7 +1163,7 @@ ucs4le_internal_loop_single (struct __gconv_step *step,
if (__builtin_expect (val >= 0x10000, 0)) \
{ \
UNICODE_TAG_HANDLER (val, 4); \
- STANDARD_ERR_HANDLER (4); \
+ STANDARD_TO_LOOP_ERR_HANDLER (4); \
} \
else if (__builtin_expect (val >= 0xd800 && val < 0xe000, 0)) \
{ \
@@ -1213,11 +1173,9 @@ ucs4le_internal_loop_single (struct __gconv_step *step,
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 ()) \
- { \
- result = __GCONV_ILLEGAL_INPUT; \
- break; \
- } \
+ break; \
inptr += 4; \
++*irreversible; \
continue; \
@@ -1293,7 +1251,7 @@ ucs4le_internal_loop_single (struct __gconv_step *step,
if (__builtin_expect (val >= 0x10000, 0)) \
{ \
UNICODE_TAG_HANDLER (val, 4); \
- STANDARD_ERR_HANDLER (4); \
+ STANDARD_TO_LOOP_ERR_HANDLER (4); \
} \
else if (__builtin_expect (val >= 0xd800 && val < 0xe000, 0)) \
{ \
diff --git a/iconv/loop.c b/iconv/loop.c
index 0b1bce75c0..2fb73da7ea 100644
--- a/iconv/loop.c
+++ b/iconv/loop.c
@@ -178,10 +178,29 @@
(irreversible != NULL && (flags & __GCONV_IGNORE_ERRORS))
-/* Error handling with transliteration/transcription function use and
- ignoring of errors. Note that we cannot use the do while (0) trick
- since `break' and `continue' must reach certain points. */
-#define STANDARD_ERR_HANDLER(Incr) \
+/* Error handling for the FROM_LOOP direction, with ignoring of errors.
+ Note that we cannot use the do while (0) trick since `break' and
+ `continue' must reach certain points. */
+#define STANDARD_FROM_LOOP_ERR_HANDLER(Incr) \
+ { \
+ result = __GCONV_ILLEGAL_INPUT; \
+ \
+ if (! ignore_errors_p ()) \
+ break; \
+ \
+ /* We ignore the invalid input byte sequence. */ \
+ inptr += (Incr); \
+ ++*irreversible; \
+ /* But we keep result == __GCONV_ILLEGAL_INPUT, because of the constraint \
+ that "iconv -c" must give the same exitcode as "iconv". */ \
+ continue; \
+ }
+
+/* Error handling for the TO_LOOP direction, with use of transliteration/
+ transcription functions and ignoring of errors. Note that we cannot use
+ the do while (0) trick since `break' and `continue' must reach certain
+ points. */
+#define STANDARD_TO_LOOP_ERR_HANDLER(Incr) \
{ \
struct __gconv_trans_data *trans; \
\
@@ -212,14 +231,16 @@
/* When we come here it means we ignore the character. */ \
++*irreversible; \
inptr += Incr; \
+ /* But we keep result == __GCONV_ILLEGAL_INPUT, because of the constraint \
+ that "iconv -c" must give the same exitcode as "iconv". */ \
continue; \
}
/* Handling of Unicode 3.1 TAG characters. Unicode recommends
"If language codes are not relevant to the particular processing
- operation, then they should be ignored."
- This macro is usually called right before STANDARD_ERR_HANDLER (Incr). */
+ operation, then they should be ignored." This macro is usually
+ called right before STANDARD_TO_LOOP_ERR_HANDLER (Incr). */
#define UNICODE_TAG_HANDLER(Character, Incr) \
{ \
/* TAG characters are those in the range U+E0000..U+E007F. */ \