Blame view
include/charset.h
7.17 KB
f739fcd83 SPDX: Convert a f... |
1 |
/* SPDX-License-Identifier: GPL-2.0+ */ |
78178bb0c lib: add some utf... |
2 3 4 5 |
/* * charset conversion utils * * Copyright (c) 2017 Rob Clark |
78178bb0c lib: add some utf... |
6 7 8 9 |
*/ #ifndef __CHARSET_H_ #define __CHARSET_H_ |
d8c28232c lib: charset: uti... |
10 |
#include <linux/kernel.h> |
f58c5ecb8 efi_loader: new f... |
11 |
#include <linux/types.h> |
984f251fe efi_loader: MAX_U... |
12 |
#define MAX_UTF8_PER_UTF16 3 |
78178bb0c lib: add some utf... |
13 14 |
/** |
35cbb796a efi_loader: suppo... |
15 16 17 18 19 20 21 22 |
* console_read_unicode() - read Unicode code point from console * * @code: pointer to store Unicode code point * Return: 0 = success */ int console_read_unicode(s32 *code); /** |
d8c28232c lib: charset: uti... |
23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 |
* utf8_get() - get next UTF-8 code point from buffer * * @src: pointer to current byte, updated to point to next byte * Return: code point, or 0 for end of string, or -1 if no legal * code point is found. In case of an error src points to * the incorrect byte. */ s32 utf8_get(const char **src); /** * utf8_put() - write UTF-8 code point to buffer * * @code: code point * @dst: pointer to destination buffer, updated to next position * Return: -1 if the input parameters are invalid */ int utf8_put(s32 code, char **dst); /** * utf8_utf16_strnlen() - length of a truncated utf-8 string after conversion * to utf-16 * * @src: utf-8 string * @count: maximum number of code points to convert |
8a4c443c0 lib: charset: cor... |
47 |
* Return: length in u16 after conversion to utf-16 without the |
d8c28232c lib: charset: uti... |
48 |
* trailing \0. If an invalid UTF-8 sequence is hit one |
8a4c443c0 lib: charset: cor... |
49 |
* u16 will be reserved for a replacement character. |
d8c28232c lib: charset: uti... |
50 51 52 53 54 55 56 |
*/ size_t utf8_utf16_strnlen(const char *src, size_t count); /** * utf8_utf16_strlen() - length of a utf-8 string after conversion to utf-16 * * @src: utf-8 string |
8a4c443c0 lib: charset: cor... |
57 58 59 |
* Return: length in u16 after conversion to utf-16 without the * trailing \0. If an invalid UTF-8 sequence is hit one * u16 will be reserved for a replacement character. |
d8c28232c lib: charset: uti... |
60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 |
*/ #define utf8_utf16_strlen(a) utf8_utf16_strnlen((a), SIZE_MAX) /** * utf8_utf16_strncpy() - copy utf-8 string to utf-16 string * * @dst: destination buffer * @src: source buffer * @count: maximum number of code points to copy * Return: -1 if the input parameters are invalid */ int utf8_utf16_strncpy(u16 **dst, const char *src, size_t count); /** * utf8_utf16_strcpy() - copy utf-8 string to utf-16 string * * @dst: destination buffer * @src: source buffer * Return: -1 if the input parameters are invalid */ #define utf8_utf16_strcpy(d, s) utf8_utf16_strncpy((d), (s), SIZE_MAX) /** * utf16_get() - get next UTF-16 code point from buffer * * @src: pointer to current word, updated to point to next word * Return: code point, or 0 for end of string, or -1 if no legal * code point is found. In case of an error src points to * the incorrect word. */ s32 utf16_get(const u16 **src); /** * utf16_put() - write UTF-16 code point to buffer * * @code: code point * @dst: pointer to destination buffer, updated to next position * Return: -1 if the input parameters are invalid */ int utf16_put(s32 code, u16 **dst); /** * utf16_strnlen() - length of a truncated utf-16 string * * @src: utf-16 string * @count: maximum number of code points to convert * Return: length in code points. If an invalid UTF-16 sequence is * hit one position will be reserved for a replacement * character. */ size_t utf16_strnlen(const u16 *src, size_t count); /** * utf16_utf8_strnlen() - length of a truncated utf-16 string after conversion * to utf-8 * * @src: utf-16 string * @count: maximum number of code points to convert * Return: length in bytes after conversion to utf-8 without the * trailing \0. If an invalid UTF-16 sequence is hit one * byte will be reserved for a replacement character. */ size_t utf16_utf8_strnlen(const u16 *src, size_t count); /** * utf16_utf8_strlen() - length of a utf-16 string after conversion to utf-8 * * @src: utf-16 string * Return: length in bytes after conversion to utf-8 without the |
8a4c443c0 lib: charset: cor... |
129 130 |
* trailing \0. If an invalid UTF-16 sequence is hit one * byte will be reserved for a replacement character. |
d8c28232c lib: charset: uti... |
131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 |
*/ #define utf16_utf8_strlen(a) utf16_utf8_strnlen((a), SIZE_MAX) /** * utf16_utf8_strncpy() - copy utf-16 string to utf-8 string * * @dst: destination buffer * @src: source buffer * @count: maximum number of code points to copy * Return: -1 if the input parameters are invalid */ int utf16_utf8_strncpy(char **dst, const u16 *src, size_t count); /** * utf16_utf8_strcpy() - copy utf-16 string to utf-8 string * * @dst: destination buffer * @src: source buffer * Return: -1 if the input parameters are invalid */ #define utf16_utf8_strcpy(d, s) utf16_utf8_strncpy((d), (s), SIZE_MAX) /** |
b5130a812 lib: charset: upp... |
154 155 156 157 158 159 160 161 162 163 164 165 166 167 |
* utf_to_lower() - convert a Unicode letter to lower case * * @code: letter to convert * Return: lower case letter or unchanged letter */ s32 utf_to_lower(const s32 code); /** * utf_to_upper() - convert a Unicode letter to upper case * * @code: letter to convert * Return: upper case letter or unchanged letter */ s32 utf_to_upper(const s32 code); |
f8062c963 lib: charset: add... |
168 169 170 171 172 173 174 175 176 177 178 179 180 181 |
/* * u16_strncmp() - compare two u16 string * * @s1: first string to compare * @s2: second string to compare * @n: maximum number of u16 to compare * Return: 0 if the first n u16 are the same in s1 and s2 * < 0 if the first different u16 in s1 is less than the * corresponding u16 in s2 * > 0 if the first different u16 in s1 is greater than the * corresponding u16 in s2 */ int u16_strncmp(const u16 *s1, const u16 *s2, size_t n); #define u16_strcmp(s1, s2) u16_strncmp((s1), (s2), SIZE_MAX) |
b5130a812 lib: charset: upp... |
182 |
/** |
1dde0d57a efi_loader: renam... |
183 |
* u16_strlen - count non-zero words |
78178bb0c lib: add some utf... |
184 |
* |
1dde0d57a efi_loader: renam... |
185 186 |
* This function matches wsclen() if the -fshort-wchar compiler flag is set. * In the EFI context we explicitly need a function handling u16 strings. |
78178bb0c lib: add some utf... |
187 |
* |
1dde0d57a efi_loader: renam... |
188 189 190 |
* @in: null terminated u16 string * ReturnValue: number of non-zero words. * This is not the number of utf-16 letters! |
78178bb0c lib: add some utf... |
191 |
*/ |
317068b8b efi_loader: suppo... |
192 |
size_t u16_strlen(const void *in); |
78178bb0c lib: add some utf... |
193 194 |
/** |
1dde0d57a efi_loader: renam... |
195 |
* u16_strlen - count non-zero words |
78178bb0c lib: add some utf... |
196 |
* |
1dde0d57a efi_loader: renam... |
197 198 |
* This function matches wscnlen_s() if the -fshort-wchar compiler flag is set. * In the EFI context we explicitly need a function handling u16 strings. |
78178bb0c lib: add some utf... |
199 |
* |
1dde0d57a efi_loader: renam... |
200 201 202 203 |
* @in: null terminated u16 string * @count: maximum number of words to count * ReturnValue: number of non-zero words. * This is not the number of utf-16 letters! |
78178bb0c lib: add some utf... |
204 |
*/ |
1dde0d57a efi_loader: renam... |
205 |
size_t u16_strnlen(const u16 *in, size_t count); |
78178bb0c lib: add some utf... |
206 207 |
/** |
2a3537ae2 lib: add u16_strc... |
208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 |
* u16_strcpy() - copy u16 string * * Copy u16 string pointed to by src, including terminating null word, to * the buffer pointed to by dest. * * @dest: destination buffer * @src: source buffer (null terminated) * Return: 'dest' address */ u16 *u16_strcpy(u16 *dest, const u16 *src); /** * u16_strdup() - duplicate u16 string * * Copy u16 string pointed to by src, including terminating null word, to a * newly allocated buffer. * * @src: source buffer (null terminated) * Return: allocated new buffer on success, NULL on failure */ |
317068b8b efi_loader: suppo... |
228 |
u16 *u16_strdup(const void *src); |
2a3537ae2 lib: add u16_strc... |
229 230 |
/** |
78178bb0c lib: add some utf... |
231 232 233 234 235 |
* utf16_to_utf8() - Convert an utf16 string to utf8 * * Converts 'size' characters of the utf16 string 'src' to utf8 * written to the 'dest' buffer. * |
984f251fe efi_loader: MAX_U... |
236 |
* NOTE that a single utf16 character can generate up to 3 utf8 |
78178bb0c lib: add some utf... |
237 238 239 240 241 242 243 244 245 246 |
* characters. See MAX_UTF8_PER_UTF16. * * @dest the destination buffer to write the utf8 characters * @src the source utf16 string * @size the number of utf16 characters to convert * @return the pointer to the first unwritten byte in 'dest' */ uint8_t *utf16_to_utf8(uint8_t *dest, const uint16_t *src, size_t size); #endif /* __CHARSET_H_ */ |