diff options
| author | Ulrich Drepper <drepper@redhat.com> | 2000-01-23 08:11:29 +0000 |
|---|---|---|
| committer | Ulrich Drepper <drepper@redhat.com> | 2000-01-23 08:11:29 +0000 |
| commit | bd32e4a68782e7e6fe5a4f18f2d52ca347591c07 (patch) | |
| tree | cb2ecfd0ce370ce0b957e9e6a811b73d0fa0e5bd /iconv | |
| parent | b8c5ef62427df8a76c4985dfc2101a3986d9842e (diff) | |
Fix two problems in UTF-8 decoder.
Diffstat (limited to 'iconv')
| -rw-r--r-- | iconv/gconv_simple.c | 25 |
1 files changed, 18 insertions, 7 deletions
diff --git a/iconv/gconv_simple.c b/iconv/gconv_simple.c index 3f9df34de2..e56c5e707d 100644 --- a/iconv/gconv_simple.c +++ b/iconv/gconv_simple.c @@ -1,5 +1,5 @@ /* Simple transformations functions. - Copyright (C) 1997, 1998, 1999 Free Software Foundation, Inc. + Copyright (C) 1997, 1998, 1999, 2000 Free Software Foundation, Inc. This file is part of the GNU C Library. Contributed by Ulrich Drepper <drepper@cygnus.com>, 1997. @@ -255,8 +255,11 @@ internal_ucs4_loop (const unsigned char **inptrp, const unsigned char *inend, } \ else \ { \ - if ((ch & 0xe0) == 0xc0) \ + if (ch >= 0xc2 && ch < 0xe0) \ { \ + /* We expect two bytes. The first byte cannot be 0xc0 or 0xc1, \ + otherwise the wide character could have been represented \ + using a single byte. */ \ cnt = 2; \ ch &= 0x1f; \ } \ @@ -304,15 +307,23 @@ internal_ucs4_loop (const unsigned char **inptrp, const unsigned char *inend, uint32_t byte = inptr[i]; \ \ if ((byte & 0xc0) != 0x80) \ - { \ - /* This is an illegal encoding. */ \ - result = __GCONV_ILLEGAL_INPUT; \ - break; \ - } \ + /* This is an illegal encoding. */ \ + break; \ \ ch <<= 6; \ ch |= byte & 0x3f; \ } \ + \ + /* If i < cnt, some trail byte was not >= 0x80, < 0xc0. \ + If cnt > 2 and ch < 2^(5*cnt-4), the wide character ch could \ + have been represented with fewer than cnt bytes. */ \ + if (i < cnt || (cnt > 2 && (ch >> (5 * cnt - 4)) == 0)) \ + { \ + /* This is an illegal encoding. */ \ + result = GCONV_ILLEGAL_INPUT; \ + break; \ + } \ + \ inptr += cnt; \ } \ \ |