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>

1 files changed, 3 insertions, 33 deletions

diff --git a/fs/isofs/joliet.c b/fs/isofs/joliet.c
index 92c14b850e9c..a048de81c093 100644
--- a/fs/isofs/joliet.c
+++ b/fs/isofs/joliet.c
@@ -37,37 +37,6 @@ uni16_to_x8(unsigned char *ascii, __be16 *uni, int len, struct nls_table *nls)
         return (op - ascii);
 }
 
-/* Convert big endian wide character string to utf8 */
-static int
-wcsntombs_be(__u8 *s, const __u8 *pwcs, int inlen, int maxlen)
-{
-        const __u8 *ip;
-        __u8 *op;
-        int size;
-        __u16 c;
-
-        op = s;
-        ip = pwcs;
-        while ((*ip || ip[1]) && (maxlen > 0) && (inlen > 0)) {
-                c = (*ip << 8) | ip[1];
-                if (c > 0x7f) {
-                        size = utf8_wctomb(op, c, maxlen);
-                        if (size == -1) {
-                                /* Ignore character and move on */
-                                maxlen--;
-                        } else {
-                                op += size;
-                                maxlen -= size;
-                        }
-                } else {
-                        *op++ = (__u8) c;
-                }
-                ip += 2;
-                inlen--;
-        }
-        return (op - s);
-}
-
 int
 get_joliet_filename(struct iso_directory_record * de, unsigned char *outname, struct inode * inode)
 {
@@ -79,8 +48,9 @@ get_joliet_filename(struct iso_directory_record * de, unsigned char *outname, st
         nls = ISOFS_SB(inode->i_sb)->s_nls_iocharset;
 
         if (utf8) {
-                len = wcsntombs_be(outname, de->name,
-                                de->name_len[0] >> 1, PAGE_SIZE);
+                len = utf16s_to_utf8s((const wchar_t *) de->name,
+                                de->name_len[0] >> 1, UTF16_BIG_ENDIAN,
+                                outname, PAGE_SIZE);
         } else {
                 len = uni16_to_x8(outname, (__be16 *) de->name,
                                 de->name_len[0] >> 1, nls);