diff options
author | Alan Stern <stern@rowland.harvard.edu> | 2009-04-30 10:08:18 -0400 |
---|---|---|
committer | Greg Kroah-Hartman <gregkh@suse.de> | 2009-06-16 00:44:43 -0400 |
commit | 74675a58507e769beee7d949dbed788af3c4139d (patch) | |
tree | d4ae3cc06dbfadecf1eaf6ed0aef249fc87b07e6 /fs/ncpfs/ncplib_kernel.c | |
parent | a853a3d4eb2edb066248a39f0634f6f5858816a0 (diff) |
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/ncpfs/ncplib_kernel.c')
-rw-r--r-- | fs/ncpfs/ncplib_kernel.c | 8 |
1 files changed, 5 insertions, 3 deletions
diff --git a/fs/ncpfs/ncplib_kernel.c b/fs/ncpfs/ncplib_kernel.c index 97645f112114..0ec6237a5970 100644 --- a/fs/ncpfs/ncplib_kernel.c +++ b/fs/ncpfs/ncplib_kernel.c | |||
@@ -1113,11 +1113,13 @@ ncp__io2vol(struct ncp_server *server, unsigned char *vname, unsigned int *vlen, | |||
1113 | 1113 | ||
1114 | if (NCP_IS_FLAG(server, NCP_FLAG_UTF8)) { | 1114 | if (NCP_IS_FLAG(server, NCP_FLAG_UTF8)) { |
1115 | int k; | 1115 | int k; |
1116 | unicode_t u; | ||
1116 | 1117 | ||
1117 | k = utf8_mbtowc(&ec, iname, iname_end - iname); | 1118 | k = utf8_to_utf32(iname, iname_end - iname, &u); |
1118 | if (k < 0) | 1119 | if (k < 0 || u > MAX_WCHAR_T) |
1119 | return -EINVAL; | 1120 | return -EINVAL; |
1120 | iname += k; | 1121 | iname += k; |
1122 | ec = u; | ||
1121 | } else { | 1123 | } else { |
1122 | if (*iname == NCP_ESC) { | 1124 | if (*iname == NCP_ESC) { |
1123 | int k; | 1125 | int k; |
@@ -1214,7 +1216,7 @@ ncp__vol2io(struct ncp_server *server, unsigned char *iname, unsigned int *ilen, | |||
1214 | if (NCP_IS_FLAG(server, NCP_FLAG_UTF8)) { | 1216 | if (NCP_IS_FLAG(server, NCP_FLAG_UTF8)) { |
1215 | int k; | 1217 | int k; |
1216 | 1218 | ||
1217 | k = utf8_wctomb(iname, ec, iname_end - iname); | 1219 | k = utf32_to_utf8(ec, iname, iname_end - iname); |
1218 | if (k < 0) { | 1220 | if (k < 0) { |
1219 | err = -ENAMETOOLONG; | 1221 | err = -ENAMETOOLONG; |
1220 | goto quit; | 1222 | goto quit; |