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
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
199
200
201
202
203
204
205
206
207
208
209
210
211
212
213
214
215
216
217
218
219
220
221
|
%% options
copyright owner = Dirk Krause
copyright year = 2015-xxxx
SPDX-License-Identifier: BSD-3-Clause
%% header
/** @file
String recoding from UTF-16 to UTF-8.
CRT on Windows: Not used.
*/
#ifndef DK4CONF_H_INCLUDED
#if DK4_BUILDING_DKTOOLS4
#include "dk4conf.h"
#else
#include <dktools-4/dk4conf.h>
#endif
#endif
#ifndef DK4TYPES_H_INCLUDED
#if DK4_BUILDING_DKTOOLS4
#include "dk4types.h"
#else
#include <dktools-4/dk4types.h>
#endif
#endif
#ifndef DK4ERROR_H_INCLUDED
#if DK4_BUILDING_DKTOOLS4
#include "dk4error.h"
#else
#include <dktools-4/dk4error.h>
#endif
#endif
#ifdef __cplusplus
extern "C" {
#endif
/** Recode string from UTF-16 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_utf16_to_utf8(
char *dstb, size_t szdstb, const dk4_c16_t *src, dk4_er_t *erp
);
/** Calculate required buffer size (including final 0x00 byte)
for UTF-16 to UTF-8 conversion.
@param src UTF-16 encoded source string.
@param erp Error report, may be NULL.
@return Positive buffer size on success, 0 on error.
Error codes:
- DK4_E_INVALID_ARGUMENTS<br>
if src or dstb is NULL or szdstb is 0,
- DK4_E_SYNTAX<br>
with the number of successfully recoded characters in nelem if a
non-recodable character was found.
*/
size_t
dk4recode_size_utf16_to_utf8(const dk4_c16_t *src, dk4_er_t *erp);
#ifdef __cplusplus
}
#endif
%% module
#include "dk4conf.h"
#include "dk4rec12.h"
#include "dk4mem.h"
#include "dk4utf8.h"
#include "dk4utf16.h"
#if DK4_HAVE_ASSERT_H
#ifndef ASSERT_H_INCLUDED
#include <assert.h>
#define ASSERT_H_INCLUDED 1
#endif
#endif
size_t
dk4recode_size_utf16_to_utf8(const dk4_c16_t *src, dk4_er_t *erp)
{
dk4_er_t er;
unsigned char buf[8];
dk4_utf16_decoder_t dec;
size_t sz;
size_t rd = 0;
size_t back = 0;
dk4_c32_t c32 = dkC32(0);
#if DK4_USE_ASSERT
assert(NULL != src);
#endif
if (NULL != src) {
dk4error_init(&er);
dk4utf16_init(&dec);
while(((dk4_c16_t)0U != *src) && (DK4_E_NONE == er.ec)) {
switch(dk4utf16_add(&dec, *(src++))) {
case DK4_EDSTM_FINISHED: {
c32 = dk4utf16_get(&dec);
dk4utf16_init(&dec);
sz = sizeof(buf);
if (0 != dk4utf8_encode(buf, &sz, c32, &er)) {
if ((SIZE_MAX - sz) >= back) {
back += sz;
rd++;
} else {
dk4error_set_simple_error_code(&er, DK4_E_MATH_OVERFLOW);
}
}
} break;
case DK4_EDSTM_ERROR: {
dk4error_set_elsize_nelem(&er, DK4_E_SYNTAX, 2, rd);
} break;
}
}
if (0 == dk4utf16_is_empty(&dec)) {
dk4error_set_elsize_nelem(&er, DK4_E_SYNTAX, 2, rd);
}
if (SIZE_MAX > back) {
back++;
} else {
dk4error_set_simple_error_code(&er, DK4_E_MATH_OVERFLOW);
}
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_utf16_to_utf8(
char *dstb, size_t szdstb, const dk4_c16_t *src, dk4_er_t *erp
)
{
unsigned char buf[8];
dk4_utf16_decoder_t dec;
size_t sz;
size_t used = 0;
size_t rd = 0;
dk4_c32_t c32 = dkC32(0);
int back = 0;
#if DK4_USE_ASSERT
assert(NULL != dstb);
assert(0 < szdstb);
assert(NULL != src);
#endif
if ((NULL != dstb) && (NULL != src) && (0 < szdstb)) {
back = 1;
dk4utf16_init(&dec);
while(((dk4_c16_t)0U != *src) && (1 == back) && (used < szdstb)) {
switch(dk4utf16_add(&dec, *(src++))) {
case DK4_EDSTM_FINISHED: {
c32 = dk4utf16_get(&dec);
dk4utf16_init(&dec);
sz = sizeof(buf);
if (0 != dk4utf8_encode(buf, &sz, c32, 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, 2, rd);
}
} break;
case DK4_EDSTM_ERROR: {
back = 0;
dk4error_set_elsize_nelem(erp, DK4_E_SYNTAX, 2, rd);
} break;
}
if (0 != back) { rd++; }
}
if (used < szdstb) {
dstb[used] = '\0';
} else {
dstb[szdstb - 1] = '\0';
back = 0;
dk4error_set_simple_error_code(erp, DK4_E_BUFFER_TOO_SMALL);
}
if (0 == dk4utf16_is_empty(&dec)) {
back = 0;
dk4error_set_elsize_nelem(erp, DK4_E_SYNTAX, 2, rd);
}
} else {
dk4error_set_simple_error_code(erp, DK4_E_INVALID_ARGUMENTS);
}
return back;
}
|