mirror of
https://git.kernel.org/pub/scm/linux/kernel/git/stable/linux.git
synced 2024-08-26 19:00:25 +00:00
![Thomas Gleixner](/assets/img/avatar_default.png)
Based on 2 normalized pattern(s): this program is free software you can redistribute it and or modify it under the terms of the gnu general public license 2 as published by the free software foundation this program is distributed in the hope that it will be useful but without any warranty without even the implied warranty of merchantability or fitness for a particular purpose see the gnu general public license for more details this program is free software you can redistribute it and or modify it under the terms of the gnu general public license as published by the free software foundation this program is distributed in the hope that it [would] be useful but without any warranty without even the implied warranty of merchantability or fitness for a particular purpose see the gnu general public license for more details extracted by the scancode license scanner the SPDX license identifier GPL-2.0-only has been chosen to replace the boilerplate/reference in 9 file(s). Signed-off-by: Thomas Gleixner <tglx@linutronix.de> Reviewed-by: Allison Randal <allison@lohutok.net> Reviewed-by: Alexios Zavras <alexios.zavras@intel.com> Cc: linux-spdx@vger.kernel.org Link: https://lkml.kernel.org/r/20190529141901.804956444@linutronix.de Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
108 lines
3.2 KiB
C
108 lines
3.2 KiB
C
/* SPDX-License-Identifier: GPL-2.0-only */
|
|
/*
|
|
* Copyright (c) 2014 SGI.
|
|
* All rights reserved.
|
|
*/
|
|
|
|
#ifndef UTF8NORM_H
|
|
#define UTF8NORM_H
|
|
|
|
#include <linux/types.h>
|
|
#include <linux/export.h>
|
|
#include <linux/string.h>
|
|
#include <linux/module.h>
|
|
|
|
/* Encoding a unicode version number as a single unsigned int. */
|
|
#define UNICODE_MAJ_SHIFT (16)
|
|
#define UNICODE_MIN_SHIFT (8)
|
|
|
|
#define UNICODE_AGE(MAJ, MIN, REV) \
|
|
(((unsigned int)(MAJ) << UNICODE_MAJ_SHIFT) | \
|
|
((unsigned int)(MIN) << UNICODE_MIN_SHIFT) | \
|
|
((unsigned int)(REV)))
|
|
|
|
/* Highest unicode version supported by the data tables. */
|
|
extern int utf8version_is_supported(u8 maj, u8 min, u8 rev);
|
|
extern int utf8version_latest(void);
|
|
|
|
/*
|
|
* Look for the correct const struct utf8data for a unicode version.
|
|
* Returns NULL if the version requested is too new.
|
|
*
|
|
* Two normalization forms are supported: nfdi and nfdicf.
|
|
*
|
|
* nfdi:
|
|
* - Apply unicode normalization form NFD.
|
|
* - Remove any Default_Ignorable_Code_Point.
|
|
*
|
|
* nfdicf:
|
|
* - Apply unicode normalization form NFD.
|
|
* - Remove any Default_Ignorable_Code_Point.
|
|
* - Apply a full casefold (C + F).
|
|
*/
|
|
extern const struct utf8data *utf8nfdi(unsigned int maxage);
|
|
extern const struct utf8data *utf8nfdicf(unsigned int maxage);
|
|
|
|
/*
|
|
* Determine the maximum age of any unicode character in the string.
|
|
* Returns 0 if only unassigned code points are present.
|
|
* Returns -1 if the input is not valid UTF-8.
|
|
*/
|
|
extern int utf8agemax(const struct utf8data *data, const char *s);
|
|
extern int utf8nagemax(const struct utf8data *data, const char *s, size_t len);
|
|
|
|
/*
|
|
* Determine the minimum age of any unicode character in the string.
|
|
* Returns 0 if any unassigned code points are present.
|
|
* Returns -1 if the input is not valid UTF-8.
|
|
*/
|
|
extern int utf8agemin(const struct utf8data *data, const char *s);
|
|
extern int utf8nagemin(const struct utf8data *data, const char *s, size_t len);
|
|
|
|
/*
|
|
* Determine the length of the normalized from of the string,
|
|
* excluding any terminating NULL byte.
|
|
* Returns 0 if only ignorable code points are present.
|
|
* Returns -1 if the input is not valid UTF-8.
|
|
*/
|
|
extern ssize_t utf8len(const struct utf8data *data, const char *s);
|
|
extern ssize_t utf8nlen(const struct utf8data *data, const char *s, size_t len);
|
|
|
|
/* Needed in struct utf8cursor below. */
|
|
#define UTF8HANGULLEAF (12)
|
|
|
|
/*
|
|
* Cursor structure used by the normalizer.
|
|
*/
|
|
struct utf8cursor {
|
|
const struct utf8data *data;
|
|
const char *s;
|
|
const char *p;
|
|
const char *ss;
|
|
const char *sp;
|
|
unsigned int len;
|
|
unsigned int slen;
|
|
short int ccc;
|
|
short int nccc;
|
|
unsigned char hangul[UTF8HANGULLEAF];
|
|
};
|
|
|
|
/*
|
|
* Initialize a utf8cursor to normalize a string.
|
|
* Returns 0 on success.
|
|
* Returns -1 on failure.
|
|
*/
|
|
extern int utf8cursor(struct utf8cursor *u8c, const struct utf8data *data,
|
|
const char *s);
|
|
extern int utf8ncursor(struct utf8cursor *u8c, const struct utf8data *data,
|
|
const char *s, size_t len);
|
|
|
|
/*
|
|
* Get the next byte in the normalization.
|
|
* Returns a value > 0 && < 256 on success.
|
|
* Returns 0 when the end of the normalization is reached.
|
|
* Returns -1 if the string being normalized is not valid UTF-8.
|
|
*/
|
|
extern int utf8byte(struct utf8cursor *u8c);
|
|
|
|
#endif /* UTF8NORM_H */
|