1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
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
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
|
/* MIT License
*
* Copyright (c) 2023 Tyge Løvset
*
* Permission is hereby granted, free of charge, to any person obtaining a copy
* of this software and associated documentation files (the "Software"), to deal
* in the Software without restriction, including without limitation the rights
* to use, copy, modify, merge, publish, distribute, sublicense, and/or sell
* copies of the Software, and to permit persons to whom the Software is
* furnished to do so, subject to the following conditions:
*
* The above copyright notice and this permission notice shall be included in all
* copies or substantial portions of the Software.
*
* THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
* IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
* FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE
* AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
* LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM,
* OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE
* SOFTWARE.
*/
#include "priv/linkage.h"
#ifndef UTF8_H_INCLUDED
#define UTF8_H_INCLUDED
#include "ccommon.h"
#include <ctype.h>
#include "forward.h"
enum {
U8G_Cc, U8G_Lt, U8G_Nd, U8G_Nl,
U8G_Pc, U8G_Pd, U8G_Pf, U8G_Pi,
U8G_Sc, U8G_Zl, U8G_Zp, U8G_Zs,
U8G_Arabic, U8G_Cyrillic,
U8G_Devanagari, U8G_Greek,
U8G_Han, U8G_Latin,
U8G_SIZE
};
// utf8 methods defined in src/utf8code.c:
extern bool utf8_isgroup(int group, uint32_t c);
extern bool utf8_isalpha(uint32_t c);
extern uint32_t utf8_casefold(uint32_t c);
extern uint32_t utf8_tolower(uint32_t c);
extern uint32_t utf8_toupper(uint32_t c);
extern bool utf8_iscased(uint32_t c);
extern bool utf8_isword(uint32_t c);
extern bool utf8_valid_n(const char* s, intptr_t nbytes);
extern int utf8_icmp_ss(csubstr s1, csubstr s2);
extern int utf8_encode(char *out, uint32_t c);
extern uint32_t utf8_peek_off(const char *s, int offset);
STC_INLINE bool utf8_isupper(uint32_t c)
{ return utf8_tolower(c) != c; }
STC_INLINE bool utf8_islower(uint32_t c)
{ return utf8_toupper(c) != c; }
STC_INLINE bool utf8_isalnum(uint32_t c) {
if (c < 128) return isalnum((int)c) != 0;
return utf8_isalpha(c) || utf8_isgroup(U8G_Nd, c);
}
STC_INLINE bool utf8_isblank(uint32_t c) {
if (c < 128) return (c == ' ') | (c == '\t');
return utf8_isgroup(U8G_Zs, c);
}
STC_INLINE bool utf8_isspace(uint32_t c) {
if (c < 128) return isspace((int)c) != 0;
return ((c == 8232) | (c == 8233)) || utf8_isgroup(U8G_Zs, c);
}
/* decode next utf8 codepoint. https://bjoern.hoehrmann.de/utf-8/decoder/dfa */
typedef struct { uint32_t state, codep; } utf8_decode_t;
extern const uint8_t utf8_dtab[]; /* utf8code.c */
STC_INLINE uint32_t utf8_decode(utf8_decode_t* d, const uint32_t byte) {
const uint32_t type = utf8_dtab[byte];
d->codep = d->state ? (byte & 0x3fu) | (d->codep << 6)
: (0xffU >> type) & byte;
return d->state = utf8_dtab[256 + d->state + type];
}
STC_INLINE uint32_t utf8_peek(const char* s) {
utf8_decode_t d = {.state=0};
do { utf8_decode(&d, (uint8_t)*s++); } while (d.state);
return d.codep;
}
/* case-insensitive utf8 string comparison */
STC_INLINE int utf8_icmp(const char* s1, const char* s2) {
return utf8_icmp_ss(c_ss(s1, INTPTR_MAX), c_ss(s2, INTPTR_MAX));
}
STC_INLINE bool utf8_valid(const char* s) {
return utf8_valid_n(s, INTPTR_MAX);
}
/* following functions are independent but assume valid utf8 strings: */
/* number of bytes in the utf8 codepoint from s */
STC_INLINE int utf8_chr_size(const char *s) {
unsigned b = (uint8_t)*s;
if (b < 0x80) return 1;
/*if (b < 0xC2) return 0;*/
if (b < 0xE0) return 2;
if (b < 0xF0) return 3;
/*if (b < 0xF5)*/ return 4;
/*return 0;*/
}
/* number of codepoints in the utf8 string s */
STC_INLINE intptr_t utf8_size(const char *s) {
intptr_t size = 0;
while (*s)
size += (*++s & 0xC0) != 0x80;
return size;
}
STC_INLINE intptr_t utf8_size_n(const char *s, intptr_t nbytes) {
intptr_t size = 0;
while ((nbytes-- != 0) & (*s != 0)) {
size += (*++s & 0xC0) != 0x80;
}
return size;
}
STC_INLINE const char* utf8_at(const char *s, intptr_t index) {
while ((index > 0) & (*s != 0))
index -= (*++s & 0xC0) != 0x80;
return s;
}
STC_INLINE intptr_t utf8_pos(const char* s, intptr_t index)
{ return (intptr_t)(utf8_at(s, index) - s); }
#endif // UTF8_H_INCLUDED
#if defined i_import || (defined i_implement && !defined _i_inc_utf8)
# include "../../src/utf8code.c"
#endif
#ifndef _i_inc_utf8
#undef i_static
#undef i_header
#undef i_implement
#undef i_import
#undef i_opt
#endif
#undef _i_inc_utf8
|
