1
Fork 0
mirror of https://git.savannah.gnu.org/git/guile.git synced 2025-04-30 03:40:34 +02:00

fix bug where scm_from_utf8_stringn would not detect bad utf-8

* libguile/strings.c (scm_from_utf8_stringn):
* libguile/symbols.c (utf8_string_equals_wide_string): The "bad UTF8"
  return from u8_mbtouc is a 0xfffd character, not a negative byte
  length.  Fixes a bug in which invalid UTF-8 would not be caught.

* libguile/bytevectors.c (scm_utf8_to_string): Use scm_from_utf8_stringn
  directly.  Just a little cleanup.

* test-suite/tests/iconv.test ("narrow non-ascii string"): Add test for
  parsing bad utf-8 with substitution.
This commit is contained in:
Andy Wingo 2013-01-15 11:01:10 +01:00
parent b4fa6cc909
commit 8c76a8971b
4 changed files with 13 additions and 8 deletions

View file

@ -1,4 +1,4 @@
/* Copyright (C) 2009, 2010, 2011, 2012 Free Software Foundation, Inc.
/* Copyright (C) 2009, 2010, 2011, 2012, 2013 Free Software Foundation, Inc.
*
* This library is free software; you can redistribute it and/or
* modify it under the terms of the GNU Lesser General Public License
@ -2050,8 +2050,7 @@ SCM_DEFINE (scm_utf8_to_string, "utf8->string",
c_utf_len = SCM_BYTEVECTOR_LENGTH (utf);
c_utf = (char *) SCM_BYTEVECTOR_CONTENTS (utf);
str = scm_from_stringn (c_utf, c_utf_len, "UTF-8",
SCM_FAILED_CONVERSION_ERROR);
str = scm_from_utf8_stringn (c_utf, c_utf_len);
return (str);
}

View file

@ -1,4 +1,4 @@
/* Copyright (C) 1995,1996,1998,2000,2001, 2004, 2006, 2008, 2009, 2010, 2011, 2012 Free Software Foundation, Inc.
/* Copyright (C) 1995,1996,1998,2000,2001, 2004, 2006, 2008, 2009, 2010, 2011, 2012, 2013 Free Software Foundation, Inc.
*
* This library is free software; you can redistribute it and/or
* modify it under the terms of the GNU Lesser General Public License
@ -1526,7 +1526,8 @@ scm_from_stringn (const char *str, size_t len, const char *encoding,
if (encoding == NULL || len == 0)
return scm_from_latin1_stringn (str, len);
else if (strcmp (encoding, "UTF-8") == 0)
else if (strcmp (encoding, "UTF-8") == 0
&& handler == SCM_FAILED_CONVERSION_ERROR)
return scm_from_utf8_stringn (str, len);
u32len = 0;
@ -1639,7 +1640,7 @@ scm_from_utf8_stringn (const char *str, size_t len)
nbytes = u8_mbtouc (&c, ustr + i, len - i);
if (nbytes < 0)
if (c == 0xfffd)
/* Bad UTF-8. */
decoding_error (__func__, errno, str, len);

View file

@ -1,5 +1,5 @@
/* Copyright (C) 1995, 1996, 1997, 1998, 2000, 2001, 2003, 2004,
* 2006, 2009, 2011 Free Software Foundation, Inc.
* 2006, 2009, 2011, 2013 Free Software Foundation, Inc.
*
* This library is free software; you can redistribute it and/or
* modify it under the terms of the GNU Lesser General Public License
@ -167,7 +167,7 @@ utf8_string_equals_wide_string (const scm_t_uint8 *narrow, size_t nlen,
nbytes = u8_mbtouc (&c, narrow + byte_idx, nlen - byte_idx);
if (nbytes == 0)
break;
else if (nbytes < 0)
else if (c == 0xfffd)
/* Bad UTF-8. */
return 0;
else if (c != wide[char_idx])

View file

@ -94,6 +94,11 @@
(pass-if-exception "misparse latin1 as utf8" exception:decoding-error
(bytevector->string (string->bytevector s "latin1") "utf-8"))
(pass-if "misparse latin1 as utf8 with substitutions"
(equal? (bytevector->string (string->bytevector s "latin1")
"utf-8" 'substitute)
"?t?"))
(pass-if-exception "misparse latin1 as ascii" exception:decoding-error
(bytevector->string (string->bytevector s "latin1") "ascii"))))