projects / linux.git / blame
| Commit | Line | Data |
|---|---|---|
| 9f806850 | 1 | /* SPDX-License-Identifier: GPL-2.0-only */ |
| 44594c2f OW |
2 | /* |
| 3 | * Copyright (c) 2014 SGI. | |
| 4 | * All rights reserved. | |
| 44594c2f OW |
5 | */ |
| 6 | ||
| 7 | #ifndef UTF8NORM_H | |
| 8 | #define UTF8NORM_H | |
| 9 | ||
| 10 | #include <linux/types.h> | |
| 11 | #include <linux/export.h> | |
| 12 | #include <linux/string.h> | |
| 13 | #include <linux/module.h> | |
| 49bd03cc | 14 | #include <linux/unicode.h> |
| 44594c2f | 15 | |
| 2b3d0478 | 16 | int utf8version_is_supported(const struct unicode_map *um, unsigned int version); |
| 44594c2f | 17 | |
| 44594c2f OW |
18 | /* |
| 19 | * Determine the length of the normalized from of the string, | |
| 20 | * excluding any terminating NULL byte. | |
| 21 | * Returns 0 if only ignorable code points are present. | |
| 22 | * Returns -1 if the input is not valid UTF-8. | |
| 23 | */ | |
| 6ca99ce7 CH |
24 | ssize_t utf8nlen(const struct unicode_map *um, enum utf8_normalization n, |
| 25 | const char *s, size_t len); | |
| 44594c2f | 26 | |
| a8384c68 OW |
27 | /* Needed in struct utf8cursor below. */ |
| 28 | #define UTF8HANGULLEAF (12) | |
| 29 | ||
| 44594c2f OW |
30 | /* |
| 31 | * Cursor structure used by the normalizer. | |
| 32 | */ | |
| 33 | struct utf8cursor { | |
| 6ca99ce7 CH |
34 | const struct unicode_map *um; |
| 35 | enum utf8_normalization n; | |
| 44594c2f OW |
36 | const char *s; |
| 37 | const char *p; | |
| 38 | const char *ss; | |
| 39 | const char *sp; | |
| 40 | unsigned int len; | |
| 41 | unsigned int slen; | |
| 42 | short int ccc; | |
| 43 | short int nccc; | |
| a8384c68 | 44 | unsigned char hangul[UTF8HANGULLEAF]; |
| 44594c2f OW |
45 | }; |
| 46 | ||
| 47 | /* | |
| 48 | * Initialize a utf8cursor to normalize a string. | |
| 49 | * Returns 0 on success. | |
| 50 | * Returns -1 on failure. | |
| 51 | */ | |
| 6ca99ce7 CH |
52 | int utf8ncursor(struct utf8cursor *u8c, const struct unicode_map *um, |
| 53 | enum utf8_normalization n, const char *s, size_t len); | |
| 44594c2f OW |
54 | |
| 55 | /* | |
| 56 | * Get the next byte in the normalization. | |
| 57 | * Returns a value > 0 && < 256 on success. | |
| 58 | * Returns 0 when the end of the normalization is reached. | |
| 59 | * Returns -1 if the string being normalized is not valid UTF-8. | |
| 60 | */ | |
| 61 | extern int utf8byte(struct utf8cursor *u8c); | |
| 62 | ||
| 2b3d0478 CH |
63 | struct utf8data { |
| 64 | unsigned int maxage; | |
| 65 | unsigned int offset; | |
| 66 | }; | |
| 67 | ||
| 68 | struct utf8data_table { | |
| 69 | const unsigned int *utf8agetab; | |
| 70 | int utf8agetab_size; | |
| 71 | ||
| 72 | const struct utf8data *utf8nfdicfdata; | |
| 73 | int utf8nfdicfdata_size; | |
| 74 | ||
| 75 | const struct utf8data *utf8nfdidata; | |
| 76 | int utf8nfdidata_size; | |
| 77 | ||
| 78 | const unsigned char *utf8data; | |
| 79 | }; | |
| 80 | ||
| 81 | extern struct utf8data_table utf8_data_table; | |
| 82 | ||
| 44594c2f | 83 | #endif /* UTF8NORM_H */ |