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
240
241
242
243
244
245
246
247
248
249
250
251
252
253
254
255
256
257
258
259
260
261
262
263
264
265
266
267
268
269
270
271
272
273
274
275
276
277
278
279
280
281
282
283
284
285
286
287
288
289
290
291
292
293
294
295
296
297
298
299
300
301
302
303
304
305
306
307
|
// std::codecvt implementation details, GNU version -*- C++ -*-
// Copyright (C) 2002-2023 Free Software Foundation, Inc.
//
// This file is part of the GNU ISO C++ Library. This library is free
// software; you can redistribute it and/or modify it under the
// terms of the GNU General Public License as published by the
// Free Software Foundation; either version 3, or (at your option)
// any later version.
// This library is distributed in the hope that it will be useful,
// but WITHOUT ANY WARRANTY; without even the implied warranty of
// MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
// GNU General Public License for more details.
// Under Section 7 of GPL version 3, you are granted additional
// permissions described in the GCC Runtime Library Exception, version
// 3.1, as published by the Free Software Foundation.
// You should have received a copy of the GNU General Public License and
// a copy of the GCC Runtime Library Exception along with this program;
// see the files COPYING3 and COPYING.RUNTIME respectively. If not, see
// <http://www.gnu.org/licenses/>.
//
// ISO C++ 14882: 22.2.1.5 - Template class codecvt
//
// Written by Benjamin Kosnik <bkoz@redhat.com>
#include <locale>
#include <cstdlib> // For MB_CUR_MAX
#include <climits> // For MB_LEN_MAX
#include <bits/c++locale_internal.h>
namespace std _GLIBCXX_VISIBILITY(default)
{
_GLIBCXX_BEGIN_NAMESPACE_VERSION
// Specializations.
#ifdef _GLIBCXX_USE_WCHAR_T
codecvt_base::result
codecvt<wchar_t, char, mbstate_t>::
do_out(state_type& __state, const intern_type* __from,
const intern_type* __from_end, const intern_type*& __from_next,
extern_type* __to, extern_type* __to_end,
extern_type*& __to_next) const
{
result __ret = ok;
state_type __tmp_state(__state);
#if __GLIBC__ > 2 || (__GLIBC__ == 2 && __GLIBC_MINOR__ > 2)
__c_locale __old = __uselocale(_M_c_locale_codecvt);
#endif
// wcsnrtombs is *very* fast but stops if encounters NUL characters:
// in case we fall back to wcrtomb and then continue, in a loop.
// NB: wcsnrtombs is a GNU extension
for (__from_next = __from, __to_next = __to;
__from_next < __from_end && __to_next < __to_end
&& __ret == ok;)
{
const intern_type* __from_chunk_end = wmemchr(__from_next, L'\0',
__from_end - __from_next);
if (!__from_chunk_end)
__from_chunk_end = __from_end;
__from = __from_next;
const size_t __conv = wcsnrtombs(__to_next, &__from_next,
__from_chunk_end - __from_next,
__to_end - __to_next, &__state);
if (__conv == static_cast<size_t>(-1))
{
// In case of error, in order to stop at the exact place we
// have to start again from the beginning with a series of
// wcrtomb.
for (; __from < __from_next; ++__from)
__to_next += wcrtomb(__to_next, *__from, &__tmp_state);
__state = __tmp_state;
__ret = error;
}
else if (__from_next && __from_next < __from_chunk_end)
{
__to_next += __conv;
__ret = partial;
}
else
{
__from_next = __from_chunk_end;
__to_next += __conv;
}
if (__from_next < __from_end && __ret == ok)
{
extern_type __buf[MB_LEN_MAX];
__tmp_state = __state;
const size_t __conv2 = wcrtomb(__buf, *__from_next, &__tmp_state);
if (__conv2 > static_cast<size_t>(__to_end - __to_next))
__ret = partial;
else
{
memcpy(__to_next, __buf, __conv2);
__state = __tmp_state;
__to_next += __conv2;
++__from_next;
}
}
}
#if __GLIBC__ > 2 || (__GLIBC__ == 2 && __GLIBC_MINOR__ > 2)
__uselocale(__old);
#endif
return __ret;
}
codecvt_base::result
codecvt<wchar_t, char, mbstate_t>::
do_in(state_type& __state, const extern_type* __from,
const extern_type* __from_end, const extern_type*& __from_next,
intern_type* __to, intern_type* __to_end,
intern_type*& __to_next) const
{
result __ret = ok;
state_type __tmp_state(__state);
#if __GLIBC__ > 2 || (__GLIBC__ == 2 && __GLIBC_MINOR__ > 2)
__c_locale __old = __uselocale(_M_c_locale_codecvt);
#endif
// mbsnrtowcs is *very* fast but stops if encounters NUL characters:
// in case we store a L'\0' and then continue, in a loop.
// NB: mbsnrtowcs is a GNU extension
for (__from_next = __from, __to_next = __to;
__from_next < __from_end && __to_next < __to_end
&& __ret == ok;)
{
const extern_type* __from_chunk_end;
__from_chunk_end = static_cast<const extern_type*>(memchr(__from_next, '\0',
__from_end
- __from_next));
if (!__from_chunk_end)
__from_chunk_end = __from_end;
__from = __from_next;
size_t __conv = mbsnrtowcs(__to_next, &__from_next,
__from_chunk_end - __from_next,
__to_end - __to_next, &__state);
if (__conv == static_cast<size_t>(-1))
{
// In case of error, in order to stop at the exact place we
// have to start again from the beginning with a series of
// mbrtowc.
for (;; ++__to_next, __from += __conv)
{
__conv = mbrtowc(__to_next, __from, __from_end - __from,
&__tmp_state);
if (__conv == static_cast<size_t>(-1)
|| __conv == static_cast<size_t>(-2))
break;
}
__from_next = __from;
__state = __tmp_state;
__ret = error;
}
else if (__from_next && __from_next < __from_chunk_end)
{
// It is unclear what to return in this case (see DR 382).
__to_next += __conv;
__ret = partial;
}
else
{
__from_next = __from_chunk_end;
__to_next += __conv;
}
if (__from_next < __from_end && __ret == ok)
{
if (__to_next < __to_end)
{
// XXX Probably wrong for stateful encodings
__tmp_state = __state;
++__from_next;
*__to_next++ = L'\0';
}
else
__ret = partial;
}
}
#if __GLIBC__ > 2 || (__GLIBC__ == 2 && __GLIBC_MINOR__ > 2)
__uselocale(__old);
#endif
return __ret;
}
int
codecvt<wchar_t, char, mbstate_t>::
do_encoding() const throw()
{
// XXX This implementation assumes that the encoding is
// stateless and is either single-byte or variable-width.
int __ret = 0;
#if __GLIBC__ > 2 || (__GLIBC__ == 2 && __GLIBC_MINOR__ > 2)
__c_locale __old = __uselocale(_M_c_locale_codecvt);
#endif
if (MB_CUR_MAX == 1)
__ret = 1;
#if __GLIBC__ > 2 || (__GLIBC__ == 2 && __GLIBC_MINOR__ > 2)
__uselocale(__old);
#endif
return __ret;
}
int
codecvt<wchar_t, char, mbstate_t>::
do_max_length() const throw()
{
#if __GLIBC__ > 2 || (__GLIBC__ == 2 && __GLIBC_MINOR__ > 2)
__c_locale __old = __uselocale(_M_c_locale_codecvt);
#endif
// XXX Probably wrong for stateful encodings.
int __ret = MB_CUR_MAX;
#if __GLIBC__ > 2 || (__GLIBC__ == 2 && __GLIBC_MINOR__ > 2)
__uselocale(__old);
#endif
return __ret;
}
int
codecvt<wchar_t, char, mbstate_t>::
do_length(state_type& __state, const extern_type* __from,
const extern_type* __end, size_t __max) const
{
int __ret = 0;
state_type __tmp_state(__state);
#if __GLIBC__ > 2 || (__GLIBC__ == 2 && __GLIBC_MINOR__ > 2)
__c_locale __old = __uselocale(_M_c_locale_codecvt);
#endif
// mbsnrtowcs is *very* fast but stops if encounters NUL characters:
// in case we advance past it and then continue, in a loop.
// NB: mbsnrtowcs is a GNU extension
// A dummy internal buffer is needed in order for mbsnrtocws to consider
// its fourth parameter (it wouldn't with NULL as first parameter).
wchar_t* __to = static_cast<wchar_t*>(__builtin_alloca(sizeof(wchar_t)
* __max));
while (__from < __end && __max)
{
const extern_type* __from_chunk_end;
__from_chunk_end = static_cast<const extern_type*>(memchr(__from, '\0',
__end
- __from));
if (!__from_chunk_end)
__from_chunk_end = __end;
const extern_type* __tmp_from = __from;
size_t __conv = mbsnrtowcs(__to, &__from,
__from_chunk_end - __from,
__max, &__state);
if (__conv == static_cast<size_t>(-1))
{
// In case of error, in order to stop at the exact place we
// have to start again from the beginning with a series of
// mbrtowc.
for (__from = __tmp_from;; __from += __conv)
{
__conv = mbrtowc(0, __from, __end - __from,
&__tmp_state);
if (__conv == static_cast<size_t>(-1)
|| __conv == static_cast<size_t>(-2))
break;
}
__state = __tmp_state;
__ret += __from - __tmp_from;
break;
}
if (!__from)
__from = __from_chunk_end;
__ret += __from - __tmp_from;
__max -= __conv;
if (__from < __end && __max)
{
// XXX Probably wrong for stateful encodings
__tmp_state = __state;
++__from;
++__ret;
--__max;
}
}
#if __GLIBC__ > 2 || (__GLIBC__ == 2 && __GLIBC_MINOR__ > 2)
__uselocale(__old);
#endif
return __ret;
}
#endif
_GLIBCXX_END_NAMESPACE_VERSION
} // namespace
|
