Mercurial > hg > octave-nkf > gnulib-hg
diff lib/unistr/u8-mbtouc-unsafe.c @ 13864:83949b090c98
unistr/u8-mbtouc: Improve handling of ill-formed UTF-8 input.
* lib/unistr/u8-mbtouc.c (u8_mbtouc): For an invalid multibyte
character, return the number of bytes that belong together, not always
1.
* lib/unistr/u8-mbtouc-unsafe.c (u8_mbtouc_unsafe): Likewise.
* lib/unistr/u8-mbtouc-aux.c (u8_mbtouc_aux): Likewise.
* lib/unistr/u8-mbtouc-unsafe-aux.c (u8_mbtouc_unsafe_aux): Likewise.
* lib/unistr/u8-mbsnlen.c (u8_mbsnlen): Use u8_mbtouc to determine the
number of bytes of an invalid character.
* tests/unistr/test-u8-mbtouc.c (test_safe_function): New function.
(main): Invoke it.
* tests/unistr/test-u8-mbtouc.h (test_function): Update two test results.
* tests/unistr/test-u8-mbsnlen.c (main): Test various kinds of
malformed byte sequences.
* modules/unistr/u8-mbtouc (configure.ac): Bump version number.
* modules/unistr/u8-mbtouc-unsafe (configure.ac): Likewise.
* modules/unistr/u8-mbsnlen (configure.ac): Likewise.
Reported by Ben Pfaff and Paolo Bonzini.
| author | Bruno Haible <bruno@clisp.org> |
|---|---|
| date | Sat, 13 Nov 2010 19:43:06 +0100 |
| parents | c2cbabec01dd |
| children | 97fc9a21a8fb |
line wrap: on
line diff
--- a/lib/unistr/u8-mbtouc-unsafe.c +++ b/lib/unistr/u8-mbtouc-unsafe.c @@ -52,13 +52,15 @@ | (unsigned int) (s[1] ^ 0x80); return 2; } +#if CONFIG_UNICODE_SAFETY /* invalid multibyte character */ +#endif } else { /* incomplete multibyte character */ *puc = 0xfffd; - return n; + return 1; } } else if (c < 0xf0) @@ -66,23 +68,39 @@ if (n >= 3) { #if CONFIG_UNICODE_SAFETY - if ((s[1] ^ 0x80) < 0x40 && (s[2] ^ 0x80) < 0x40 - && (c >= 0xe1 || s[1] >= 0xa0) - && (c != 0xed || s[1] < 0xa0)) -#endif + if ((s[1] ^ 0x80) < 0x40) { - *puc = ((unsigned int) (c & 0x0f) << 12) - | ((unsigned int) (s[1] ^ 0x80) << 6) - | (unsigned int) (s[2] ^ 0x80); - return 3; + if ((s[2] ^ 0x80) < 0x40) + { + if ((c >= 0xe1 || s[1] >= 0xa0) + && (c != 0xed || s[1] < 0xa0)) +#endif + { + *puc = ((unsigned int) (c & 0x0f) << 12) + | ((unsigned int) (s[1] ^ 0x80) << 6) + | (unsigned int) (s[2] ^ 0x80); + return 3; + } +#if CONFIG_UNICODE_SAFETY + /* invalid multibyte character */ + *puc = 0xfffd; + return 3; + } + /* invalid multibyte character */ + *puc = 0xfffd; + return 2; } /* invalid multibyte character */ +#endif } else { /* incomplete multibyte character */ *puc = 0xfffd; - return n; + if (n == 1 || (s[1] ^ 0x80) >= 0x40) + return 1; + else + return 2; } } else if (c < 0xf8) @@ -90,28 +108,51 @@ if (n >= 4) { #if CONFIG_UNICODE_SAFETY - if ((s[1] ^ 0x80) < 0x40 && (s[2] ^ 0x80) < 0x40 - && (s[3] ^ 0x80) < 0x40 - && (c >= 0xf1 || s[1] >= 0x90) + if ((s[1] ^ 0x80) < 0x40) + { + if ((s[2] ^ 0x80) < 0x40) + { + if ((s[3] ^ 0x80) < 0x40) + { + if ((c >= 0xf1 || s[1] >= 0x90) #if 1 - && (c < 0xf4 || (c == 0xf4 && s[1] < 0x90)) + && (c < 0xf4 || (c == 0xf4 && s[1] < 0x90)) +#endif + ) #endif - ) -#endif - { - *puc = ((unsigned int) (c & 0x07) << 18) - | ((unsigned int) (s[1] ^ 0x80) << 12) - | ((unsigned int) (s[2] ^ 0x80) << 6) - | (unsigned int) (s[3] ^ 0x80); - return 4; + { + *puc = ((unsigned int) (c & 0x07) << 18) + | ((unsigned int) (s[1] ^ 0x80) << 12) + | ((unsigned int) (s[2] ^ 0x80) << 6) + | (unsigned int) (s[3] ^ 0x80); + return 4; + } +#if CONFIG_UNICODE_SAFETY + /* invalid multibyte character */ + *puc = 0xfffd; + return 4; + } + /* invalid multibyte character */ + *puc = 0xfffd; + return 3; + } + /* invalid multibyte character */ + *puc = 0xfffd; + return 2; } /* invalid multibyte character */ +#endif } else { /* incomplete multibyte character */ *puc = 0xfffd; - return n; + if (n == 1 || (s[1] ^ 0x80) >= 0x40) + return 1; + else if (n == 2 || (s[2] ^ 0x80) >= 0x40) + return 2; + else + return 3; } } #if 0 @@ -120,19 +161,42 @@ if (n >= 5) { #if CONFIG_UNICODE_SAFETY - if ((s[1] ^ 0x80) < 0x40 && (s[2] ^ 0x80) < 0x40 - && (s[3] ^ 0x80) < 0x40 && (s[4] ^ 0x80) < 0x40 - && (c >= 0xf9 || s[1] >= 0x88)) -#endif + if ((s[1] ^ 0x80) < 0x40) { - *puc = ((unsigned int) (c & 0x03) << 24) - | ((unsigned int) (s[1] ^ 0x80) << 18) - | ((unsigned int) (s[2] ^ 0x80) << 12) - | ((unsigned int) (s[3] ^ 0x80) << 6) - | (unsigned int) (s[4] ^ 0x80); - return 5; + if ((s[2] ^ 0x80) < 0x40) + { + if ((s[3] ^ 0x80) < 0x40) + { + if ((s[4] ^ 0x80) < 0x40) + { + if (c >= 0xf9 || s[1] >= 0x88) +#endif + { + *puc = ((unsigned int) (c & 0x03) << 24) + | ((unsigned int) (s[1] ^ 0x80) << 18) + | ((unsigned int) (s[2] ^ 0x80) << 12) + | ((unsigned int) (s[3] ^ 0x80) << 6) + | (unsigned int) (s[4] ^ 0x80); + return 5; + } +#if CONFIG_UNICODE_SAFETY + /* invalid multibyte character */ + *puc = 0xfffd; + return 5; + } + /* invalid multibyte character */ + *puc = 0xfffd; + return 4; + } + /* invalid multibyte character */ + *puc = 0xfffd; + return 3; + } + /* invalid multibyte character */ + return 2; } /* invalid multibyte character */ +#endif } else { @@ -146,21 +210,49 @@ if (n >= 6) { #if CONFIG_UNICODE_SAFETY - if ((s[1] ^ 0x80) < 0x40 && (s[2] ^ 0x80) < 0x40 - && (s[3] ^ 0x80) < 0x40 && (s[4] ^ 0x80) < 0x40 - && (s[5] ^ 0x80) < 0x40 - && (c >= 0xfd || s[1] >= 0x84)) -#endif + if ((s[1] ^ 0x80) < 0x40) { - *puc = ((unsigned int) (c & 0x01) << 30) - | ((unsigned int) (s[1] ^ 0x80) << 24) - | ((unsigned int) (s[2] ^ 0x80) << 18) - | ((unsigned int) (s[3] ^ 0x80) << 12) - | ((unsigned int) (s[4] ^ 0x80) << 6) - | (unsigned int) (s[5] ^ 0x80); - return 6; + if ((s[2] ^ 0x80) < 0x40) + { + if ((s[3] ^ 0x80) < 0x40) + { + if ((s[4] ^ 0x80) < 0x40) + { + if ((s[5] ^ 0x80) < 0x40) + { + if (c >= 0xfd || s[1] >= 0x84) +#endif + { + *puc = ((unsigned int) (c & 0x01) << 30) + | ((unsigned int) (s[1] ^ 0x80) << 24) + | ((unsigned int) (s[2] ^ 0x80) << 18) + | ((unsigned int) (s[3] ^ 0x80) << 12) + | ((unsigned int) (s[4] ^ 0x80) << 6) + | (unsigned int) (s[5] ^ 0x80); + return 6; + } +#if CONFIG_UNICODE_SAFETY + /* invalid multibyte character */ + *puc = 0xfffd; + return 6; + } + /* invalid multibyte character */ + *puc = 0xfffd; + return 5; + } + /* invalid multibyte character */ + *puc = 0xfffd; + return 4; + } + /* invalid multibyte character */ + *puc = 0xfffd; + return 3; + } + /* invalid multibyte character */ + return 2; } /* invalid multibyte character */ +#endif } else {