mirror of
https://github.com/edk2-porting/linux-next.git
synced 2024-12-21 11:44:01 +08:00
74675a5850
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>
107 lines
2.9 KiB
C
107 lines
2.9 KiB
C
#ifndef _LINUX_NLS_H
|
|
#define _LINUX_NLS_H
|
|
|
|
#include <linux/init.h>
|
|
|
|
/* 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* wchar_t values is now outdated.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;
|
|
const char *alias;
|
|
int (*uni2char) (wchar_t uni, unsigned char *out, int boundlen);
|
|
int (*char2uni) (const unsigned char *rawstring, int boundlen,
|
|
wchar_t *uni);
|
|
const unsigned char *charset2lower;
|
|
const unsigned char *charset2upper;
|
|
struct module *owner;
|
|
struct nls_table *next;
|
|
};
|
|
|
|
/* 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 *);
|
|
extern struct nls_table *load_nls(char *);
|
|
extern void unload_nls(struct nls_table *);
|
|
extern struct nls_table *load_nls_default(void);
|
|
|
|
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)
|
|
{
|
|
unsigned char nc = t->charset2lower[c];
|
|
|
|
return nc ? nc : c;
|
|
}
|
|
|
|
static inline unsigned char nls_toupper(struct nls_table *t, unsigned char c)
|
|
{
|
|
unsigned char nc = t->charset2upper[c];
|
|
|
|
return nc ? nc : c;
|
|
}
|
|
|
|
static inline int nls_strnicmp(struct nls_table *t, const unsigned char *s1,
|
|
const unsigned char *s2, int len)
|
|
{
|
|
while (len--) {
|
|
if (nls_tolower(t, *s1++) != nls_tolower(t, *s2++))
|
|
return 1;
|
|
}
|
|
|
|
return 0;
|
|
}
|
|
|
|
/*
|
|
* nls_nullsize - return length of null character for codepage
|
|
* @codepage - codepage for which to return length of NULL terminator
|
|
*
|
|
* Since we can't guarantee that the null terminator will be a particular
|
|
* length, we have to check against the codepage. If there's a problem
|
|
* determining it, assume a single-byte NULL terminator.
|
|
*/
|
|
static inline int
|
|
nls_nullsize(const struct nls_table *codepage)
|
|
{
|
|
int charlen;
|
|
char tmp[NLS_MAX_CHARSET_SIZE];
|
|
|
|
charlen = codepage->uni2char(0, tmp, NLS_MAX_CHARSET_SIZE);
|
|
|
|
return charlen > 0 ? charlen : 1;
|
|
}
|
|
|
|
#define MODULE_ALIAS_NLS(name) MODULE_ALIAS("nls_" __stringify(name))
|
|
|
|
#endif /* _LINUX_NLS_H */
|
|
|