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>
diff --git a/include/linux/nls.h b/include/linux/nls.h
index 52b1a76..d47beef 100644
--- a/include/linux/nls.h
+++ b/include/linux/nls.h
@@ -3,8 +3,23 @@
#include <linux/init.h>
-/* unicode character */
-typedef __u16 wchar_t;
+/* Unicode has changed over the years. Unicode code points no longer
+ * fit into 16 bits; as of Unicode 5 valid code points range from 0
+ * to 0x10ffff (17 planes, where each plane holds 65536 code points).
+ *
+ * The original decision to represent Unicode characters as 16-bit
+ * wchar_t values is now outdated. But plane 0 still includes the
+ * most commonly used characters, so we will retain it. The newer
+ * 32-bit unicode_t type can be used when it is necessary to
+ * represent the full Unicode character set.
+ */
+
+/* Plane-0 Unicode character */
+typedef u16 wchar_t;
+#define MAX_WCHAR_T 0xffff
+
+/* Arbitrary Unicode character */
+typedef u32 unicode_t;
struct nls_table {
const char *charset;
@@ -21,6 +36,13 @@
/* this value hold the maximum octet of charset */
#define NLS_MAX_CHARSET_SIZE 6 /* for UTF-8 */
+/* Byte order for UTF-16 strings */
+enum utf16_endian {
+ UTF16_HOST_ENDIAN,
+ UTF16_LITTLE_ENDIAN,
+ UTF16_BIG_ENDIAN
+};
+
/* nls.c */
extern int register_nls(struct nls_table *);
extern int unregister_nls(struct nls_table *);
@@ -28,10 +50,11 @@
extern void unload_nls(struct nls_table *);
extern struct nls_table *load_nls_default(void);
-extern int utf8_mbtowc(wchar_t *, const __u8 *, int);
-extern int utf8_mbstowcs(wchar_t *, const __u8 *, int);
-extern int utf8_wctomb(__u8 *, wchar_t, int);
-extern int utf8_wcstombs(__u8 *, const wchar_t *, int);
+extern int utf8_to_utf32(const u8 *s, int len, unicode_t *pu);
+extern int utf32_to_utf8(unicode_t u, u8 *s, int maxlen);
+extern int utf8s_to_utf16s(const u8 *s, int len, wchar_t *pwcs);
+extern int utf16s_to_utf8s(const wchar_t *pwcs, int len,
+ enum utf16_endian endian, u8 *s, int maxlen);
static inline unsigned char nls_tolower(struct nls_table *t, unsigned char c)
{