[deliverable/linux.git] / include / linux / nls.h

#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 * wchar_t values is now outdated.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_base.c */
extern int __register_nls(struct nls_table *, struct module *);
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);
#define register_nls(nls) __register_nls((nls), THIS_MODULE)

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,
		enum utf16_endian endian, wchar_t *pwcs, int maxlen);
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 */
Commit	Line	Data
1da177e4 LT	1	#ifndef _LINUX_NLS_H
	2	#define _LINUX_NLS_H
	3
	4	#include <linux/init.h>
	5
74675a58 AS	6	/* Unicode has changed over the years. Unicode code points no longer
	7	* fit into 16 bits; as of Unicode 5 valid code points range from 0
	8	* to 0x10ffff (17 planes, where each plane holds 65536 code points).
	9	*
	10	* The original decision to represent Unicode characters as 16-bit
	11	* wchar_t values is now outdated. But plane 0 still includes the
	12	* most commonly used characters, so we will retain it. The newer
	13	* 32-bit unicode_t type can be used when it is necessary to
	14	* represent the full Unicode character set.
	15	*/
	16
	17	/* Plane-0 Unicode character */
	18	typedef u16 wchar_t;
	19	#define MAX_WCHAR_T 0xffff
	20
	21	/* Arbitrary Unicode character */
	22	typedef u32 unicode_t;
1da177e4 LT	23
1da177e4 LT	24	struct nls_table {
b9ec0339 DV	25	const char *charset;
b9ec0339 DV	26	const char *alias;
1da177e4 LT	27	int (uni2char) (wchar_t uni, unsigned char out, int boundlen);
	28	int (char2uni) (const unsigned char rawstring, int boundlen,
	29	wchar_t *uni);
b9ec0339 DV	30	const unsigned char *charset2lower;
b9ec0339 DV	31	const unsigned char *charset2upper;
1da177e4 LT	32	struct module *owner;
	33	struct nls_table *next;
	34	};
	35
	36	/* this value hold the maximum octet of charset */
	37	#define NLS_MAX_CHARSET_SIZE 6 /* for UTF-8 */
	38
74675a58 AS	39	/* Byte order for UTF-16 strings */
	40	enum utf16_endian {
	41	UTF16_HOST_ENDIAN,
	42	UTF16_LITTLE_ENDIAN,
	43	UTF16_BIG_ENDIAN
	44	};
	45
0720a06a	46	/* nls_base.c */
479e64c2	47	extern int __register_nls(struct nls_table , struct module );
1da177e4 LT	48	extern int unregister_nls(struct nls_table *);
	49	extern struct nls_table load_nls(char );
	50	extern void unload_nls(struct nls_table *);
	51	extern struct nls_table *load_nls_default(void);
479e64c2	52	#define register_nls(nls) __register_nls((nls), THIS_MODULE)
1da177e4	53
74675a58 AS	54	extern int utf8_to_utf32(const u8 s, int len, unicode_t pu);
74675a58 AS	55	extern int utf32_to_utf8(unicode_t u, u8 *s, int maxlen);
0720a06a AS	56	extern int utf8s_to_utf16s(const u8 *s, int len,
0720a06a AS	57	enum utf16_endian endian, wchar_t *pwcs, int maxlen);
74675a58 AS	58	extern int utf16s_to_utf8s(const wchar_t *pwcs, int len,
74675a58 AS	59	enum utf16_endian endian, u8 *s, int maxlen);
1da177e4 LT	60
	61	static inline unsigned char nls_tolower(struct nls_table *t, unsigned char c)
	62	{
	63	unsigned char nc = t->charset2lower[c];
	64
	65	return nc ? nc : c;
	66	}
	67
	68	static inline unsigned char nls_toupper(struct nls_table *t, unsigned char c)
	69	{
	70	unsigned char nc = t->charset2upper[c];
	71
	72	return nc ? nc : c;
	73	}
	74
	75	static inline int nls_strnicmp(struct nls_table t, const unsigned char s1,
	76	const unsigned char *s2, int len)
	77	{
	78	while (len--) {
	79	if (nls_tolower(t, s1++) != nls_tolower(t, s2++))
	80	return 1;
	81	}
	82
	83	return 0;
	84	}
	85
d37dc42a JL	86	/*
	87	* nls_nullsize - return length of null character for codepage
	88	* @codepage - codepage for which to return length of NULL terminator
	89	*
	90	* Since we can't guarantee that the null terminator will be a particular
	91	* length, we have to check against the codepage. If there's a problem
	92	* determining it, assume a single-byte NULL terminator.
	93	*/
	94	static inline int
	95	nls_nullsize(const struct nls_table *codepage)
	96	{
	97	int charlen;
	98	char tmp[NLS_MAX_CHARSET_SIZE];
	99
	100	charlen = codepage->uni2char(0, tmp, NLS_MAX_CHARSET_SIZE);
	101
	102	return charlen > 0 ? charlen : 1;
	103	}
	104
1da177e4 LT	105	#define MODULE_ALIAS_NLS(name) MODULE_ALIAS("nls_" __stringify(name))
	106
	107	#endif /* _LINUX_NLS_H */
	108