summaryrefslogtreecommitdiffstats
path: root/fs/befs
diff options
context:
space:
mode:
authorAlan Stern <stern@rowland.harvard.edu>2009-04-30 16:08:18 +0200
committerGreg Kroah-Hartman <gregkh@suse.de>2009-06-16 06:44:43 +0200
commit74675a58507e769beee7d949dbed788af3c4139d (patch)
treed4ae3cc06dbfadecf1eaf6ed0aef249fc87b07e6 /fs/befs
parentusb: return device strings in UTF-8 (diff)
downloadlinux-74675a58507e769beee7d949dbed788af3c4139d.tar.xz
linux-74675a58507e769beee7d949dbed788af3c4139d.zip
NLS: update handling of Unicode
This patch (as1239) updates the kernel's treatment of Unicode. The character-set conversion routines are well behind the current state of the Unicode specification: They don't recognize the existence of code points beyond plane 0 or of surrogate pairs in the UTF-16 encoding. The old wchar_t 16-bit type is retained because it's still used in lots of places. This shouldn't cause any new problems; if a conversion now results in an invalid 16-bit code then before it must have yielded an undefined code. Difficult-to-read names like "utf_mbstowcs" are replaced with more transparent names like "utf8s_to_utf16s" and the ordering of the parameters is rationalized (buffer lengths come immediate after the pointers they refer to, and the inputs precede the outputs). Fortunately the low-level conversion routines are used in only a few places; the interfaces to the higher-level uni2char and char2uni methods have been left unchanged. Signed-off-by: Alan Stern <stern@rowland.harvard.edu> Acked-by: Clemens Ladisch <clemens@ladisch.de> Signed-off-by: Greg Kroah-Hartman <gregkh@suse.de>
Diffstat (limited to 'fs/befs')
-rw-r--r--fs/befs/linuxvfs.c20
1 files changed, 9 insertions, 11 deletions
diff --git a/fs/befs/linuxvfs.c b/fs/befs/linuxvfs.c
index 9367b6297d84..89cd2deeb4af 100644
--- a/fs/befs/linuxvfs.c
+++ b/fs/befs/linuxvfs.c
@@ -513,7 +513,7 @@ befs_utf2nls(struct super_block *sb, const char *in,
{
struct nls_table *nls = BEFS_SB(sb)->nls;
int i, o;
- wchar_t uni;
+ unicode_t uni;
int unilen, utflen;
char *result;
/* The utf8->nls conversion won't make the final nls string bigger
@@ -539,16 +539,16 @@ befs_utf2nls(struct super_block *sb, const char *in,
for (i = o = 0; i < in_len; i += utflen, o += unilen) {
/* convert from UTF-8 to Unicode */
- utflen = utf8_mbtowc(&uni, &in[i], in_len - i);
- if (utflen < 0) {
+ utflen = utf8_to_utf32(&in[i], in_len - i, &uni);
+ if (utflen < 0)
goto conv_err;
- }
/* convert from Unicode to nls */
+ if (uni > MAX_WCHAR_T)
+ goto conv_err;
unilen = nls->uni2char(uni, &result[o], in_len - o);
- if (unilen < 0) {
+ if (unilen < 0)
goto conv_err;
- }
}
result[o] = '\0';
*out_len = o;
@@ -619,15 +619,13 @@ befs_nls2utf(struct super_block *sb, const char *in,
/* convert from nls to unicode */
unilen = nls->char2uni(&in[i], in_len - i, &uni);
- if (unilen < 0) {
+ if (unilen < 0)
goto conv_err;
- }
/* convert from unicode to UTF-8 */
- utflen = utf8_wctomb(&result[o], uni, 3);
- if (utflen <= 0) {
+ utflen = utf32_to_utf8(uni, &result[o], 3);
+ if (utflen <= 0)
goto conv_err;
- }
}
result[o] = '\0';