84 lines · c
1/* SPDX-License-Identifier: GPL-2.0-only */2/*3 * Copyright (c) 2014 SGI.4 * All rights reserved.5 */6 7#ifndef UTF8NORM_H8#define UTF8NORM_H9 10#include <linux/types.h>11#include <linux/export.h>12#include <linux/string.h>13#include <linux/module.h>14#include <linux/unicode.h>15 16int utf8version_is_supported(const struct unicode_map *um, unsigned int version);17 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 */24ssize_t utf8nlen(const struct unicode_map *um, enum utf8_normalization n,25 const char *s, size_t len);26 27/* Needed in struct utf8cursor below. */28#define UTF8HANGULLEAF (12)29 30/*31 * Cursor structure used by the normalizer.32 */33struct utf8cursor {34 const struct unicode_map *um;35 enum utf8_normalization n;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;44 unsigned char hangul[UTF8HANGULLEAF];45};46 47/*48 * Initialize a utf8cursor to normalize a string.49 * Returns 0 on success.50 * Returns -1 on failure.51 */52int utf8ncursor(struct utf8cursor *u8c, const struct unicode_map *um,53 enum utf8_normalization n, const char *s, size_t len);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 */61extern int utf8byte(struct utf8cursor *u8c);62 63struct utf8data {64 unsigned int maxage;65 unsigned int offset;66};67 68struct 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 81extern struct utf8data_table utf8_data_table;82 83#endif /* UTF8NORM_H */84