Commit 6d2851de authored by Eli Zaretskii's avatar Eli Zaretskii
Browse files

Fix bug #13515 with processing DBCS file names on MS-Windows.

 src/w32.c (max_filename_mbslen): New function.
 (normalize_filename, readdir): Use it to detect locales where ANSI
 encoding of file names uses a double-byte character set (DBCS).
 If a DBCS encoding is used, advance by characters using
 CharNextExA, instead of incrementing a 'char *' pointer.  Use
 _mbslwr instead of _strlwr.
parent 4d4ddaa7
2013-01-23 Eli Zaretskii <eliz@gnu.org>
* w32.c (max_filename_mbslen): New function.
(normalize_filename, readdir): Use it to detect locales where ANSI
encoding of file names uses a double-byte character set (DBCS).
If a DBCS encoding is used, advance by characters using
CharNextExA, instead of incrementing a 'char *' pointer. Use
_mbslwr instead of _strlwr. (Bug#13515)
2013-01-22 Eli Zaretskii <eliz@gnu.org>
 
* w32heap.c (allocate_heap) [!_WIN64]: Decrease the initial
......
......@@ -37,7 +37,7 @@ along with GNU Emacs. If not, see <http://www.gnu.org/licenses/>. */
/* must include CRT headers *before* config.h */
#include <config.h>
#include <mbstring.h> /* for _mbspbrk */
#include <mbstring.h> /* for _mbspbrk and _mbslwr */
#undef access
#undef chdir
......@@ -1304,6 +1304,67 @@ srandom (int seed)
srand (seed);
}
/* Current codepage for encoding file names. */
static int file_name_codepage;
/* Return the maximum length in bytes of a multibyte character
sequence encoded in the current ANSI codepage. This is required to
correctly walk the encoded file names one character at a time. */
static int
max_filename_mbslen (void)
{
/* A simple cache to avoid calling GetCPInfo every time we need to
normalize a file name. The file-name encoding is not supposed to
be changed too frequently, if ever. */
static Lisp_Object last_file_name_encoding;
static int last_max_mbslen;
Lisp_Object current_encoding;
current_encoding = Vfile_name_coding_system;
if (NILP (current_encoding))
current_encoding = Vdefault_file_name_coding_system;
if (!EQ (last_file_name_encoding, current_encoding))
{
CPINFO cp_info;
last_file_name_encoding = current_encoding;
/* Default to the current ANSI codepage. */
file_name_codepage = w32_ansi_code_page;
if (!NILP (current_encoding))
{
char *cpname = SDATA (SYMBOL_NAME (current_encoding));
char *cp = NULL, *end;
int cpnum;
if (strncmp (cpname, "cp", 2) == 0)
cp = cpname + 2;
else if (strncmp (cpname, "windows-", 8) == 0)
cp = cpname + 8;
if (cp)
{
end = cp;
cpnum = strtol (cp, &end, 10);
if (cpnum && *end == '\0' && end - cp >= 2)
file_name_codepage = cpnum;
}
}
if (!file_name_codepage)
file_name_codepage = CP_ACP; /* CP_ACP = 0, but let's not assume that */
if (!GetCPInfo (file_name_codepage, &cp_info))
{
file_name_codepage = CP_ACP;
if (!GetCPInfo (file_name_codepage, &cp_info))
emacs_abort ();
}
last_max_mbslen = cp_info.MaxCharSize;
}
return last_max_mbslen;
}
/* Normalize filename by converting all path separators to
the specified separator. Also conditionally convert upper
......@@ -1313,14 +1374,20 @@ static void
normalize_filename (register char *fp, char path_sep)
{
char sep;
char *elem;
char *elem, *p2;
int dbcs_p = max_filename_mbslen () > 1;
/* Always lower-case drive letters a-z, even if the filesystem
preserves case in filenames.
This is so filenames can be compared by string comparison
functions that are case-sensitive. Even case-preserving filesystems
do not distinguish case in drive letters. */
if (fp[1] == ':' && *fp >= 'A' && *fp <= 'Z')
if (dbcs_p)
p2 = CharNextExA (file_name_codepage, fp, 0);
else
p2 = fp + 1;
if (*p2 == ':' && *fp >= 'A' && *fp <= 'Z')
{
*fp += 'a' - 'A';
fp += 2;
......@@ -1332,7 +1399,10 @@ normalize_filename (register char *fp, char path_sep)
{
if (*fp == '/' || *fp == '\\')
*fp = path_sep;
if (!dbcs_p)
fp++;
else
fp = CharNextExA (file_name_codepage, fp, 0);
}
return;
}
......@@ -1355,13 +1425,20 @@ normalize_filename (register char *fp, char path_sep)
if (elem && elem != fp)
{
*fp = 0; /* temporary end of string */
_strlwr (elem); /* while we convert to lower case */
_mbslwr (elem); /* while we convert to lower case */
}
*fp = sep; /* convert (or restore) path separator */
elem = fp + 1; /* next element starts after separator */
sep = path_sep;
}
} while (*fp++);
if (*fp)
{
if (!dbcs_p)
fp++;
else
fp = CharNextExA (file_name_codepage, fp, 0);
}
} while (*fp);
}
/* Destructively turn backslashes into slashes. */
......@@ -2588,15 +2665,22 @@ readdir (DIR *dirp)
strcpy (dir_static.d_name, dir_find_data.cFileName);
dir_static.d_namlen = strlen (dir_static.d_name);
if (dir_is_fat)
_strlwr (dir_static.d_name);
_mbslwr (dir_static.d_name);
else if (downcase)
{
register char *p;
for (p = dir_static.d_name; *p; p++)
int dbcs_p = max_filename_mbslen () > 1;
for (p = dir_static.d_name; *p; )
{
if (*p >= 'a' && *p <= 'z')
break;
if (dbcs_p)
p = CharNextExA (file_name_codepage, p, 0);
else
p++;
}
if (!*p)
_strlwr (dir_static.d_name);
_mbslwr (dir_static.d_name);
}
return &dir_static;
......
Markdown is supported
0% or .
You are about to add 0 people to the discussion. Proceed with caution.
Finish editing this message first!
Please register or to comment