xref: /openbmc/linux/fs/unicode/utf8n.h (revision cb1aaebe)
1 /*
2  * Copyright (c) 2014 SGI.
3  * All rights reserved.
4  *
5  * This program is free software; you can redistribute it and/or
6  * modify it under the terms of the GNU General Public License as
7  * published by the Free Software Foundation.
8  *
9  * This program is distributed in the hope that it would be useful,
10  * but WITHOUT ANY WARRANTY; without even the implied warranty of
11  * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
12  * GNU General Public License for more details.
13  *
14  */
15 
16 #ifndef UTF8NORM_H
17 #define UTF8NORM_H
18 
19 #include <linux/types.h>
20 #include <linux/export.h>
21 #include <linux/string.h>
22 #include <linux/module.h>
23 
24 /* Encoding a unicode version number as a single unsigned int. */
25 #define UNICODE_MAJ_SHIFT		(16)
26 #define UNICODE_MIN_SHIFT		(8)
27 
28 #define UNICODE_AGE(MAJ, MIN, REV)			\
29 	(((unsigned int)(MAJ) << UNICODE_MAJ_SHIFT) |	\
30 	 ((unsigned int)(MIN) << UNICODE_MIN_SHIFT) |	\
31 	 ((unsigned int)(REV)))
32 
33 /* Highest unicode version supported by the data tables. */
34 extern int utf8version_is_supported(u8 maj, u8 min, u8 rev);
35 extern int utf8version_latest(void);
36 
37 /*
38  * Look for the correct const struct utf8data for a unicode version.
39  * Returns NULL if the version requested is too new.
40  *
41  * Two normalization forms are supported: nfdi and nfdicf.
42  *
43  * nfdi:
44  *  - Apply unicode normalization form NFD.
45  *  - Remove any Default_Ignorable_Code_Point.
46  *
47  * nfdicf:
48  *  - Apply unicode normalization form NFD.
49  *  - Remove any Default_Ignorable_Code_Point.
50  *  - Apply a full casefold (C + F).
51  */
52 extern const struct utf8data *utf8nfdi(unsigned int maxage);
53 extern const struct utf8data *utf8nfdicf(unsigned int maxage);
54 
55 /*
56  * Determine the maximum age of any unicode character in the string.
57  * Returns 0 if only unassigned code points are present.
58  * Returns -1 if the input is not valid UTF-8.
59  */
60 extern int utf8agemax(const struct utf8data *data, const char *s);
61 extern int utf8nagemax(const struct utf8data *data, const char *s, size_t len);
62 
63 /*
64  * Determine the minimum age of any unicode character in the string.
65  * Returns 0 if any unassigned code points are present.
66  * Returns -1 if the input is not valid UTF-8.
67  */
68 extern int utf8agemin(const struct utf8data *data, const char *s);
69 extern int utf8nagemin(const struct utf8data *data, const char *s, size_t len);
70 
71 /*
72  * Determine the length of the normalized from of the string,
73  * excluding any terminating NULL byte.
74  * Returns 0 if only ignorable code points are present.
75  * Returns -1 if the input is not valid UTF-8.
76  */
77 extern ssize_t utf8len(const struct utf8data *data, const char *s);
78 extern ssize_t utf8nlen(const struct utf8data *data, const char *s, size_t len);
79 
80 /* Needed in struct utf8cursor below. */
81 #define UTF8HANGULLEAF	(12)
82 
83 /*
84  * Cursor structure used by the normalizer.
85  */
86 struct utf8cursor {
87 	const struct utf8data	*data;
88 	const char	*s;
89 	const char	*p;
90 	const char	*ss;
91 	const char	*sp;
92 	unsigned int	len;
93 	unsigned int	slen;
94 	short int	ccc;
95 	short int	nccc;
96 	unsigned char	hangul[UTF8HANGULLEAF];
97 };
98 
99 /*
100  * Initialize a utf8cursor to normalize a string.
101  * Returns 0 on success.
102  * Returns -1 on failure.
103  */
104 extern int utf8cursor(struct utf8cursor *u8c, const struct utf8data *data,
105 		      const char *s);
106 extern int utf8ncursor(struct utf8cursor *u8c, const struct utf8data *data,
107 		       const char *s, size_t len);
108 
109 /*
110  * Get the next byte in the normalization.
111  * Returns a value > 0 && < 256 on success.
112  * Returns 0 when the end of the normalization is reached.
113  * Returns -1 if the string being normalized is not valid UTF-8.
114  */
115 extern int utf8byte(struct utf8cursor *u8c);
116 
117 #endif /* UTF8NORM_H */
118