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 /* This code is copied from the linux kernel. We have a userspace 17 * version here to such that hashes will match that implementation. 18 */ 19 20 #ifndef UTF8NORM_H 21 #define UTF8NORM_H 22 23 #include <stdint.h> 24 #include <unistd.h> 25 #include <string.h> 26 27 /* Encoding a unicode version number as a single unsigned int. */ 28 #define UNICODE_MAJ_SHIFT (16) 29 #define UNICODE_MIN_SHIFT (8) 30 31 #define UNICODE_AGE(MAJ, MIN, REV) \ 32 (((unsigned int)(MAJ) << UNICODE_MAJ_SHIFT) | \ 33 ((unsigned int)(MIN) << UNICODE_MIN_SHIFT) | \ 34 ((unsigned int)(REV))) 35 36 /* Highest unicode version supported by the data tables. */ 37 extern int utf8version_is_supported(uint8_t maj, uint8_t min, uint8_t rev); 38 extern int utf8version_latest(void); 39 40 /* 41 * Look for the correct const struct utf8data for a unicode version. 42 * Returns NULL if the version requested is too new. 43 * 44 * Two normalization forms are supported: nfdi and nfdicf. 45 * 46 * nfdi: 47 * - Apply unicode normalization form NFD. 48 * - Remove any Default_Ignorable_Code_Point. 49 * 50 * nfdicf: 51 * - Apply unicode normalization form NFD. 52 * - Remove any Default_Ignorable_Code_Point. 53 * - Apply a full casefold (C + F). 54 */ 55 extern const struct utf8data *utf8nfdi(unsigned int maxage); 56 extern const struct utf8data *utf8nfdicf(unsigned int maxage); 57 58 /* 59 * Determine the maximum age of any unicode character in the string. 60 * Returns 0 if only unassigned code points are present. 61 * Returns -1 if the input is not valid UTF-8. 62 */ 63 extern int utf8agemax(const struct utf8data *data, const char *s); 64 extern int utf8nagemax(const struct utf8data *data, const char *s, size_t len); 65 66 /* 67 * Determine the minimum age of any unicode character in the string. 68 * Returns 0 if any unassigned code points are present. 69 * Returns -1 if the input is not valid UTF-8. 70 */ 71 extern int utf8agemin(const struct utf8data *data, const char *s); 72 extern int utf8nagemin(const struct utf8data *data, const char *s, size_t len); 73 74 /* 75 * Determine the length of the normalized from of the string, 76 * excluding any terminating NULL byte. 77 * Returns 0 if only ignorable code points are present. 78 * Returns -1 if the input is not valid UTF-8. 79 */ 80 extern ssize_t utf8len(const struct utf8data *data, const char *s); 81 extern ssize_t utf8nlen(const struct utf8data *data, const char *s, size_t len); 82 83 /* Needed in struct utf8cursor below. */ 84 #define UTF8HANGULLEAF (12) 85 86 /* 87 * Cursor structure used by the normalizer. 88 */ 89 struct utf8cursor { 90 const struct utf8data *data; 91 const char *s; 92 const char *p; 93 const char *ss; 94 const char *sp; 95 unsigned int len; 96 unsigned int slen; 97 short int ccc; 98 short int nccc; 99 unsigned char hangul[UTF8HANGULLEAF]; 100 }; 101 102 /* 103 * Initialize a utf8cursor to normalize a string. 104 * Returns 0 on success. 105 * Returns -1 on failure. 106 */ 107 extern int utf8cursor(struct utf8cursor *u8c, const struct utf8data *data, 108 const char *s); 109 extern int utf8ncursor(struct utf8cursor *u8c, const struct utf8data *data, 110 const char *s, size_t len); 111 112 /* 113 * Get the next byte in the normalization. 114 * Returns a value > 0 && < 256 on success. 115 * Returns 0 when the end of the normalization is reached. 116 * Returns -1 if the string being normalized is not valid UTF-8. 117 */ 118 extern int utf8byte(struct utf8cursor *u8c); 119 120 #endif /* UTF8NORM_H */ 121