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
222
223
224
225
226
227
228
229
230
231
232
233
234
235
236
237
238
239
|
%% options
copyright owner = Dirk Krause
copyright year = 2015-xxxx
SPDX-License-Identifier: BSD-3-Clause
%% header
/** @file
String recoding from UTF-8 to UTF-16.
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-8 to UTF-16.
@param dstb Destination buffer.
@param szdstb Size of destination buffer (number of dk_c16-t).
@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_utf8_to_utf16(
dk4_c16_t *dstb, size_t szdstb, const char *src, dk4_er_t *erp
);
/** Calculate required buffer size (including final 0x0000U word)
to convert from UTF-8 to UTF-16.
@param src UTF-8 encoded source string.
@param erp Error report, may be NULL.
@return Positive required buffer size (number of dk4_c16_t) on success,
0 on error.
Error codes:
- DK4_E_INVALID_ARGUMENTS<br>
if src is NULL,
- DK4_E_MATH_OVERFLOW<br>
if the required size calculation results in mathematical overflow,
- DK4_E_SYNTAX<br>
if there are errors while decoding the source string.
*/
size_t
dk4recode_size_utf8_to_utf16(const char *src, dk4_er_t *erp);
#ifdef __cplusplus
}
#endif
%% module
#include "dk4conf.h"
#include "dk4rec11.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
$!trace-include
size_t
dk4recode_size_utf8_to_utf16(const char *src, dk4_er_t *erp)
{
dk4_er_t er;
dk4_utf8_decoder_t dec;
dk4_c16_t c16[4];
size_t rdb = 0;
size_t back = 0;
size_t sz;
dk4_c32_t c32;
#if DK4_USE_ASSERT
assert(NULL != src);
#endif
if (NULL != src) {
/* Initialize data structures.
*/
dk4error_init(&er);
dk4utf8_init(&dec);
/* Process source string.
*/
while ('\0' != *src) {
rdb++;
switch(dk4utf8_add(&dec, (unsigned char)(*(src++)))) {
case DK4_EDSTM_FINISHED: {
c32 = dk4utf8_get(&dec);
dk4utf8_init(&dec);
sz = DK4_SIZEOF(c16,dk4_c16_t);
if (0 != dk4utf16_encode(c16, &sz, c32, &er)) {
if ((SIZE_MAX - sz) >= back) {
back += sz;
} else {
dk4error_set_simple_error_code(&er, DK4_E_MATH_OVERFLOW);
}
} else {
dk4error_set_elsize_nelem(&er, DK4_E_SYNTAX, 1, rdb);
}
} break;
case DK4_EDSTM_ERROR: {
dk4error_set_elsize_nelem(&er, DK4_E_SYNTAX, 1, rdb);
} break;
}
}
if (0 == dk4utf8_is_empty(&dec)) {
dk4error_set_elsize_nelem(&er, DK4_E_SYNTAX, 1, rdb);
}
/* Add one for the finalizer.
*/
if (SIZE_MAX == back) {
dk4error_set_simple_error_code(&er, DK4_E_MATH_OVERFLOW);
} else {
back++;
}
/* On error return 0 and pass error code.
*/
if (DK4_E_NONE != er.ec) {
back = 0;
dk4error_copy(erp, &er);
}
} else {
dk4error_set_simple_error_code(erp, DK4_E_INVALID_ARGUMENTS);
}
return back;
}
int
dk4recode_utf8_to_utf16(
dk4_c16_t *dstb, size_t szdstb, const char *src, dk4_er_t *erp
)
{
dk4_c16_t buf[8];
dk4_utf8_decoder_t dec;
size_t sz;
size_t used = 0;
size_t rdb = 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;
dk4utf8_init(&dec);
while(('\0' != *src) && (1 == back) && (used < szdstb)) {
switch(dk4utf8_add(&dec, (unsigned char)(*(src++)))) {
case DK4_EDSTM_FINISHED: {
c32 = dk4utf8_get(&dec);
dk4utf8_init(&dec);
sz = DK4_SIZEOF(buf,dk4_c16_t);
if (0 != dk4utf16_encode(buf, &sz, c32, erp)) {
if ((szdstb - used) > sz) {
DK4_MEMCPY(&(dstb[used]),buf,(2 * 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);
}
} break;
case DK4_EDSTM_ERROR: {
back = 0;
dk4error_set_elsize_nelem(erp, DK4_E_SYNTAX, 1, rdb);
} break;
}
if(back) { rdb++; }
}
if (used < szdstb) {
dstb[used] = (dk4_c16_t)0U;
} else {
dstb[szdstb - 1] = (dk4_c16_t)0U;
back = 0;
dk4error_set_simple_error_code(erp, DK4_E_BUFFER_TOO_SMALL);
}
if (0 == dk4utf8_is_empty(&dec)) {
back = 0;
dk4error_set_elsize_nelem(erp, DK4_E_SYNTAX, 1, rdb);
}
} else {
dk4error_set_simple_error_code(erp, DK4_E_INVALID_ARGUMENTS);
}
return back;
}
|