/src/systemd/src/basic/utf8.h
Line | Count | Source (jump to first uncovered line) |
1 | | /* SPDX-License-Identifier: LGPL-2.1-or-later */ |
2 | | #pragma once |
3 | | |
4 | | #include <stdbool.h> |
5 | | #include <stddef.h> |
6 | | #include <stdint.h> |
7 | | #include <uchar.h> |
8 | | |
9 | | #include "macro.h" |
10 | | #include "missing_type.h" |
11 | | |
12 | | #define UTF8_REPLACEMENT_CHARACTER "\xef\xbf\xbd" |
13 | | #define UTF8_BYTE_ORDER_MARK "\xef\xbb\xbf" |
14 | | |
15 | | bool unichar_is_valid(char32_t c); |
16 | | |
17 | | char *utf8_is_valid_n(const char *str, size_t len_bytes) _pure_; |
18 | 0 | static inline char *utf8_is_valid(const char *s) { |
19 | 0 | return utf8_is_valid_n(s, SIZE_MAX); |
20 | 0 | } |
21 | | char *ascii_is_valid(const char *s) _pure_; |
22 | | char *ascii_is_valid_n(const char *str, size_t len); |
23 | | |
24 | | int utf8_to_ascii(const char *str, char replacement_char, char **ret); |
25 | | |
26 | | bool utf8_is_printable_newline(const char* str, size_t length, bool allow_newline) _pure_; |
27 | | #define utf8_is_printable(str, length) utf8_is_printable_newline(str, length, true) |
28 | | |
29 | | char *utf8_escape_invalid(const char *s); |
30 | | char *utf8_escape_non_printable_full(const char *str, size_t console_width, bool force_ellipsis); |
31 | 0 | static inline char *utf8_escape_non_printable(const char *str) { |
32 | 0 | return utf8_escape_non_printable_full(str, SIZE_MAX, false); |
33 | 0 | } |
34 | | |
35 | | size_t utf8_encode_unichar(char *out_utf8, char32_t g); |
36 | | size_t utf16_encode_unichar(char16_t *out, char32_t c); |
37 | | |
38 | | char *utf16_to_utf8(const char16_t *s, size_t length /* bytes! */); |
39 | | char16_t *utf8_to_utf16(const char *s, size_t length); |
40 | | |
41 | | size_t char16_strlen(const char16_t *s); /* returns the number of 16bit words in the string (not bytes!) */ |
42 | | |
43 | | int utf8_encoded_valid_unichar(const char *str, size_t length); |
44 | | int utf8_encoded_to_unichar(const char *str, char32_t *ret_unichar); |
45 | | |
46 | 0 | static inline bool utf16_is_surrogate(char16_t c) { |
47 | 0 | return c >= 0xd800U && c <= 0xdfffU; |
48 | 0 | } |
49 | | |
50 | 0 | static inline bool utf16_is_trailing_surrogate(char16_t c) { |
51 | 0 | return c >= 0xdc00U && c <= 0xdfffU; |
52 | 0 | } |
53 | | |
54 | 0 | static inline char32_t utf16_surrogate_pair_to_unichar(char16_t lead, char16_t trail) { |
55 | 0 | return ((((char32_t) lead - 0xd800U) << 10) + ((char32_t) trail - 0xdc00U) + 0x10000U); |
56 | 0 | } |
57 | | |
58 | | size_t utf8_n_codepoints(const char *str); |
59 | | size_t utf8_console_width(const char *str); |