1/* SPDX-License-Identifier: GPL-2.0-only */ 2/* 3 * Copyright (c) 2014 SGI. 4 * All rights reserved. 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. */ 25extern int utf8version_is_supported(u8 maj, u8 min, u8 rev); 26extern int utf8version_latest(void); 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 */ 43extern const struct utf8data *utf8nfdi(unsigned int maxage); 44extern 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 */ 51extern int utf8agemax(const struct utf8data *data, const char *s); 52extern 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 */ 59extern int utf8agemin(const struct utf8data *data, const char *s); 60extern 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 */ 68extern ssize_t utf8len(const struct utf8data *data, const char *s); 69extern ssize_t utf8nlen(const struct utf8data *data, const char *s, size_t len); 70 71/* Needed in struct utf8cursor below. */ 72#define UTF8HANGULLEAF (12) 73 74/* 75 * Cursor structure used by the normalizer. 76 */ 77struct 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; 87 unsigned char hangul[UTF8HANGULLEAF]; 88}; 89 90/* 91 * Initialize a utf8cursor to normalize a string. 92 * Returns 0 on success. 93 * Returns -1 on failure. 94 */ 95extern int utf8cursor(struct utf8cursor *u8c, const struct utf8data *data, 96 const char *s); 97extern 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 */ 106extern int utf8byte(struct utf8cursor *u8c); 107 108#endif /* UTF8NORM_H */ 109