Thomas Gleixner | 9f80685 | 2019-05-29 07:18:08 -0700 | [diff] [blame] | 1 | /* SPDX-License-Identifier: GPL-2.0-only */ |
Olaf Weber | 44594c2 | 2019-04-25 13:45:46 -0400 | [diff] [blame] | 2 | /* |
| 3 | * Copyright (c) 2014 SGI. |
| 4 | * All rights reserved. |
Olaf Weber | 44594c2 | 2019-04-25 13:45:46 -0400 | [diff] [blame] | 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> |
| 14 | |
| 15 | /* Encoding a unicode version number as a single unsigned int. */ |
| 16 | #define UNICODE_MAJ_SHIFT (16) |
| 17 | #define UNICODE_MIN_SHIFT (8) |
| 18 | |
| 19 | #define UNICODE_AGE(MAJ, MIN, REV) \ |
| 20 | (((unsigned int)(MAJ) << UNICODE_MAJ_SHIFT) | \ |
| 21 | ((unsigned int)(MIN) << UNICODE_MIN_SHIFT) | \ |
| 22 | ((unsigned int)(REV))) |
| 23 | |
| 24 | /* Highest unicode version supported by the data tables. */ |
| 25 | extern int utf8version_is_supported(u8 maj, u8 min, u8 rev); |
Gabriel Krisman Bertazi | 9d53690 | 2019-04-25 13:51:22 -0400 | [diff] [blame] | 26 | extern int utf8version_latest(void); |
Olaf Weber | 44594c2 | 2019-04-25 13:45:46 -0400 | [diff] [blame] | 27 | |
| 28 | /* |
| 29 | * Look for the correct const struct utf8data for a unicode version. |
| 30 | * Returns NULL if the version requested is too new. |
| 31 | * |
| 32 | * Two normalization forms are supported: nfdi and nfdicf. |
| 33 | * |
| 34 | * nfdi: |
| 35 | * - Apply unicode normalization form NFD. |
| 36 | * - Remove any Default_Ignorable_Code_Point. |
| 37 | * |
| 38 | * nfdicf: |
| 39 | * - Apply unicode normalization form NFD. |
| 40 | * - Remove any Default_Ignorable_Code_Point. |
| 41 | * - Apply a full casefold (C + F). |
| 42 | */ |
| 43 | extern const struct utf8data *utf8nfdi(unsigned int maxage); |
| 44 | extern const struct utf8data *utf8nfdicf(unsigned int maxage); |
| 45 | |
| 46 | /* |
| 47 | * Determine the maximum age of any unicode character in the string. |
| 48 | * Returns 0 if only unassigned code points are present. |
| 49 | * Returns -1 if the input is not valid UTF-8. |
| 50 | */ |
| 51 | extern int utf8agemax(const struct utf8data *data, const char *s); |
| 52 | extern int utf8nagemax(const struct utf8data *data, const char *s, size_t len); |
| 53 | |
| 54 | /* |
| 55 | * Determine the minimum age of any unicode character in the string. |
| 56 | * Returns 0 if any unassigned code points are present. |
| 57 | * Returns -1 if the input is not valid UTF-8. |
| 58 | */ |
| 59 | extern int utf8agemin(const struct utf8data *data, const char *s); |
| 60 | extern int utf8nagemin(const struct utf8data *data, const char *s, size_t len); |
| 61 | |
| 62 | /* |
| 63 | * Determine the length of the normalized from of the string, |
| 64 | * excluding any terminating NULL byte. |
| 65 | * Returns 0 if only ignorable code points are present. |
| 66 | * Returns -1 if the input is not valid UTF-8. |
| 67 | */ |
| 68 | extern ssize_t utf8len(const struct utf8data *data, const char *s); |
| 69 | extern ssize_t utf8nlen(const struct utf8data *data, const char *s, size_t len); |
| 70 | |
Olaf Weber | a8384c6 | 2019-04-25 13:49:18 -0400 | [diff] [blame] | 71 | /* Needed in struct utf8cursor below. */ |
| 72 | #define UTF8HANGULLEAF (12) |
| 73 | |
Olaf Weber | 44594c2 | 2019-04-25 13:45:46 -0400 | [diff] [blame] | 74 | /* |
| 75 | * Cursor structure used by the normalizer. |
| 76 | */ |
| 77 | struct utf8cursor { |
| 78 | const struct utf8data *data; |
| 79 | const char *s; |
| 80 | const char *p; |
| 81 | const char *ss; |
| 82 | const char *sp; |
| 83 | unsigned int len; |
| 84 | unsigned int slen; |
| 85 | short int ccc; |
| 86 | short int nccc; |
Olaf Weber | a8384c6 | 2019-04-25 13:49:18 -0400 | [diff] [blame] | 87 | unsigned char hangul[UTF8HANGULLEAF]; |
Olaf Weber | 44594c2 | 2019-04-25 13:45:46 -0400 | [diff] [blame] | 88 | }; |
| 89 | |
| 90 | /* |
| 91 | * Initialize a utf8cursor to normalize a string. |
| 92 | * Returns 0 on success. |
| 93 | * Returns -1 on failure. |
| 94 | */ |
| 95 | extern int utf8cursor(struct utf8cursor *u8c, const struct utf8data *data, |
| 96 | const char *s); |
| 97 | extern int utf8ncursor(struct utf8cursor *u8c, const struct utf8data *data, |
| 98 | const char *s, size_t len); |
| 99 | |
| 100 | /* |
| 101 | * Get the next byte in the normalization. |
| 102 | * Returns a value > 0 && < 256 on success. |
| 103 | * Returns 0 when the end of the normalization is reached. |
| 104 | * Returns -1 if the string being normalized is not valid UTF-8. |
| 105 | */ |
| 106 | extern int utf8byte(struct utf8cursor *u8c); |
| 107 | |
| 108 | #endif /* UTF8NORM_H */ |