NLS: improve UTF8 -> UTF16 string conversion routine
The utf8s_to_utf16s conversion routine needs to be improved. Unlike
its utf16s_to_utf8s sibling, it doesn't accept arguments specifying
the maximum length of the output buffer or the endianness of its
16-bit output.
This patch (as1501) adds the two missing arguments, and adjusts the
only two places in the kernel where the function is called. A
follow-on patch will add a third caller that does utilize the new
capabilities.
The two conversion routines are still annoyingly inconsistent in the
way they handle invalid byte combinations. But that's a subject for a
different patch.
Signed-off-by: Alan Stern <stern@rowland.harvard.edu>
CC: Clemens Ladisch <clemens@ladisch.de>
Signed-off-by: Greg Kroah-Hartman <gregkh@suse.de>
diff --git a/fs/nls/nls_base.c b/fs/nls/nls_base.c
index 44a88a9..0eb059e 100644
--- a/fs/nls/nls_base.c
+++ b/fs/nls/nls_base.c
@@ -114,34 +114,57 @@
}
EXPORT_SYMBOL(utf32_to_utf8);
-int utf8s_to_utf16s(const u8 *s, int len, wchar_t *pwcs)
+static inline void put_utf16(wchar_t *s, unsigned c, enum utf16_endian endian)
+{
+ switch (endian) {
+ default:
+ *s = (wchar_t) c;
+ break;
+ case UTF16_LITTLE_ENDIAN:
+ *s = __cpu_to_le16(c);
+ break;
+ case UTF16_BIG_ENDIAN:
+ *s = __cpu_to_be16(c);
+ break;
+ }
+}
+
+int utf8s_to_utf16s(const u8 *s, int len, enum utf16_endian endian,
+ wchar_t *pwcs, int maxlen)
{
u16 *op;
int size;
unicode_t u;
op = pwcs;
- while (*s && len > 0) {
+ while (len > 0 && maxlen > 0 && *s) {
if (*s & 0x80) {
size = utf8_to_utf32(s, len, &u);
if (size < 0)
return -EINVAL;
-
- if (u >= PLANE_SIZE) {
- u -= PLANE_SIZE;
- *op++ = (wchar_t) (SURROGATE_PAIR |
- ((u >> 10) & SURROGATE_BITS));
- *op++ = (wchar_t) (SURROGATE_PAIR |
- SURROGATE_LOW |
- (u & SURROGATE_BITS));
- } else {
- *op++ = (wchar_t) u;
- }
s += size;
len -= size;
+
+ if (u >= PLANE_SIZE) {
+ if (maxlen < 2)
+ break;
+ u -= PLANE_SIZE;
+ put_utf16(op++, SURROGATE_PAIR |
+ ((u >> 10) & SURROGATE_BITS),
+ endian);
+ put_utf16(op++, SURROGATE_PAIR |
+ SURROGATE_LOW |
+ (u & SURROGATE_BITS),
+ endian);
+ maxlen -= 2;
+ } else {
+ put_utf16(op++, u, endian);
+ maxlen--;
+ }
} else {
- *op++ = *s++;
+ put_utf16(op++, *s++, endian);
len--;
+ maxlen--;
}
}
return op - pwcs;