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
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
|
%% options
copyright owner = Dirk Krause
copyright year = 2015-xxxx
license = bsd
%% header
/** @file
String recoding from ASCII to UTF-8.
CRT on Windows: Not used.
*/
#ifndef DK4CONF_H_INCLUDED
#include "dk4conf.h"
#endif
#ifndef DK4TYPES_H_INCLUDED
#include "dk4types.h"
#endif
#ifndef DK4ERROR_H_INCLUDED
#include "dk4error.h"
#endif
#ifdef __cplusplus
extern "C" {
#endif
/** Recode string from ASCII to UTF-8.
@param dstb Destination buffer.
@param szdstb Size of destination buffer (number of bytes).
@param src Source string to convert.
@param erp Error report, may be NULL.
@return 1 on success, 0 on error.
Error codes:
- DK4_E_INVALID_ARGUMENTS<br>
if src or dstb is NULL or szdstb is 0,
- DK4_E_BUFFER_TOO_SMALL<br>
if dstb is too small,
- DK4_E_SYNTAX<br>
with the number of successfully recoded characters in nelem if a
non-recodable character was found.
*/
int
dk4recode_ascii_to_utf8(
char *dstb, size_t szdstb, const char *src, dk4_er_t *erp
);
/** Calculate required buffer size (including final 0x00 byte)
for ASCII to UTF-8 conversion.
@param src ASCII encoded string.
@param erp Error report, may be NULL.
@return Positive value on success, 0 on error.
Error codes:
- DK4_E_INVALID_ARGUMENTS<br>
if src is NULL,
- DK4_E_SYNTAX<br>
if there are encoding errors,
- DK4_E_MATH_OVERFLOW<br>
if a numeric overflow occured in size calculation.
*/
size_t
dk4recode_size_ascii_to_utf8(const char *src, dk4_er_t *erp);
#ifdef __cplusplus
}
#endif
%% module
#include "dk4rec03.h"
#include "dk4mem.h"
#include "dk4utf8.h"
size_t
dk4recode_size_ascii_to_utf8(const char *src, dk4_er_t *erp)
{
dk4_er_t er; /* Internal error report */
unsigned char buf[8]; /* current character UTF-8 encoded */
size_t sz; /* Size of current UTF-8 encoded character */
size_t rdb = 0; /* Number of bytes read from input */
size_t back = 0; /* Function result */
unsigned char uc; /* Currenct character */
if (NULL != src) {
dk4error_init(&er);
while ('\0' != *src) {
uc = (unsigned char)(*(src++));
rdb++;
sz = sizeof(buf);
if (0 != dk4utf8_encode(buf, &sz, (dk4_c32_t)uc, &er)) {
if ((SIZE_MAX - sz) < back) {
dk4error_set_simple_error_code(erp, DK4_E_MATH_OVERFLOW);
}
back += sz;
} else {
dk4error_set_elsize_nelem(&er, DK4_E_SYNTAX, 1, rdb);
}
}
if (SIZE_MAX == back) {
dk4error_set_simple_error_code(erp, DK4_E_MATH_OVERFLOW);
}
back++;
if (DK4_E_NONE != er.ec) {
dk4error_copy(erp, &er);
back = 0;
}
} else {
dk4error_set_simple_error_code(erp, DK4_E_INVALID_ARGUMENTS);
}
return back;
}
int
dk4recode_ascii_to_utf8(
char *dstb, size_t szdstb, const char *src, dk4_er_t *erp
)
{
unsigned char buf[8];
size_t sz;
size_t rdb = 0;
size_t used = 0;
int back = 0;
unsigned char uc = '\0';
if ((NULL != dstb) && (NULL != src) && (0 < szdstb)) {
back = 1;
while(('\0' != *src) && (1 == back) && (used < szdstb)) {
uc = (unsigned char)(*(src++));
sz = sizeof(buf);
if (0 != dk4utf8_encode(buf, &sz, (dk4_c32_t)uc, erp)) {
if ((szdstb - used) > sz) {
DK4_MEMCPY(&(dstb[used]),buf,sz);
used += sz;
} else {
back = 0;
dk4error_set_simple_error_code(erp, DK4_E_BUFFER_TOO_SMALL);
}
} else {
back = 0;
dk4error_set_elsize_nelem(erp, DK4_E_SYNTAX, 1, rdb);
}
if (0 != back) { rdb++; }
}
if (used < szdstb) {
dstb[used] = '\0';
} else {
dstb[szdstb - 1] = '\0';
back = 0;
dk4error_set_simple_error_code(erp, DK4_E_BUFFER_TOO_SMALL);
}
} else {
dk4error_set_simple_error_code(erp, DK4_E_INVALID_ARGUMENTS);
}
return back;
}
|