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
|
/* $OpenBSD: citrus_utf8.c,v 1.6 2012/12/05 23:19:59 deraadt Exp $ */
/*-
* Copyright (c) 2002-2004 Tim J. Robbins
* All rights reserved.
*
* Redistribution and use in source and binary forms, with or without
* modification, are permitted provided that the following conditions
* are met:
* 1. Redistributions of source code must retain the above copyright
* notice, this list of conditions and the following disclaimer.
* 2. Redistributions in binary form must reproduce the above copyright
* notice, this list of conditions and the following disclaimer in the
* documentation and/or other materials provided with the distribution.
*
* THIS SOFTWARE IS PROVIDED BY THE AUTHOR AND CONTRIBUTORS ``AS IS'' AND
* ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE
* IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE
* ARE DISCLAIMED. IN NO EVENT SHALL THE AUTHOR OR CONTRIBUTORS BE LIABLE
* FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR CONSEQUENTIAL
* DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS
* OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS INTERRUPTION)
* HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT
* LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY
* OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF
* SUCH DAMAGE.
*/
#include <errno.h>
#include <sys/param.h>
#include <string.h>
#include <wchar.h>
#include <uchar.h>
#include "private/bionic_mbstate.h"
//
// This file is basically OpenBSD's citrus_utf8.c but rewritten to not require a
// 12-byte mbstate_t so we're backwards-compatible with our LP32 ABI where
// mbstate_t was only 4 bytes.
//
// The state is the UTF-8 sequence. We only support <= 4-bytes sequences so LP32
// mbstate_t already has enough space (out of the 4 available bytes we only
// need 3 since we should never need to store the entire sequence in the
// intermediary state).
//
// The C standard leaves the conversion state undefined after a bad conversion.
// To avoid unexpected failures due to the possible use of the internal private
// state we always reset the conversion state when encountering illegal
// sequences.
//
// We also implement the POSIX interface directly rather than being accessed via
// function pointers.
//
int mbsinit(const mbstate_t* ps) {
return ps == nullptr || mbstate_is_initial(ps);
}
size_t mbrtowc(wchar_t* pwc, const char* s, size_t n, mbstate_t* ps) {
static mbstate_t __private_state;
mbstate_t* state = (ps == nullptr) ? &__private_state : ps;
// Our wchar_t is UTF-32.
return mbrtoc32(reinterpret_cast<char32_t*>(pwc), s, n, state);
}
size_t mbsnrtowcs(wchar_t* dst, const char** src, size_t nmc, size_t len, mbstate_t* ps) {
static mbstate_t __private_state;
mbstate_t* state = (ps == nullptr) ? &__private_state : ps;
size_t i, o, r;
// The fast paths in the loops below are not safe if an ASCII
// character appears as anything but the first byte of a
// multibyte sequence. Check now to avoid doing it in the loops.
if (nmc > 0 && mbstate_bytes_so_far(state) > 0 && static_cast<uint8_t>((*src)[0]) < 0x80) {
return mbstate_reset_and_return_illegal(EILSEQ, state);
}
// Measure only?
if (dst == nullptr) {
for (i = o = 0; i < nmc; i += r, o++) {
if (static_cast<uint8_t>((*src)[i]) < 0x80) {
// Fast path for plain ASCII characters.
if ((*src)[i] == '\0') {
return mbstate_reset_and_return(o, state);
}
r = 1;
} else {
r = mbrtowc(nullptr, *src + i, nmc - i, state);
if (r == __MB_ERR_ILLEGAL_SEQUENCE) {
return mbstate_reset_and_return_illegal(EILSEQ, state);
}
if (r == __MB_ERR_INCOMPLETE_SEQUENCE) {
return mbstate_reset_and_return_illegal(EILSEQ, state);
}
if (r == 0) {
return mbstate_reset_and_return(o, state);
}
}
}
return mbstate_reset_and_return(o, state);
}
// Actually convert, updating `dst` and `src`.
for (i = o = 0; i < nmc && o < len; i += r, o++) {
if (static_cast<uint8_t>((*src)[i]) < 0x80) {
// Fast path for plain ASCII characters.
dst[o] = (*src)[i];
r = 1;
if ((*src)[i] == '\0') {
*src = nullptr;
return mbstate_reset_and_return(o, state);
}
} else {
r = mbrtowc(dst + o, *src + i, nmc - i, state);
if (r == __MB_ERR_ILLEGAL_SEQUENCE) {
*src += i;
return mbstate_reset_and_return_illegal(EILSEQ, state);
}
if (r == __MB_ERR_INCOMPLETE_SEQUENCE) {
*src += nmc;
return mbstate_reset_and_return_illegal(EILSEQ, state);
}
if (r == 0) {
*src = nullptr;
return mbstate_reset_and_return(o, state);
}
}
}
*src += i;
return mbstate_reset_and_return(o, state);
}
size_t mbsrtowcs(wchar_t* dst, const char** src, size_t len, mbstate_t* ps) {
return mbsnrtowcs(dst, src, SIZE_MAX, len, ps);
}
size_t wcrtomb(char* s, wchar_t wc, mbstate_t* ps) {
static mbstate_t __private_state;
mbstate_t* state = (ps == nullptr) ? &__private_state : ps;
// Our wchar_t is UTF-32.
return c32rtomb(s, static_cast<char32_t>(wc), state);
}
size_t wcsnrtombs(char* dst, const wchar_t** src, size_t nwc, size_t len, mbstate_t* ps) {
static mbstate_t __private_state;
mbstate_t* state = (ps == nullptr) ? &__private_state : ps;
if (!mbstate_is_initial(state)) {
return mbstate_reset_and_return_illegal(EILSEQ, state);
}
char buf[MB_LEN_MAX];
size_t i, o, r;
if (dst == nullptr) {
for (i = o = 0; i < nwc; i++, o += r) {
wchar_t wc = (*src)[i];
if (static_cast<uint32_t>(wc) < 0x80) {
// Fast path for plain ASCII characters.
if (wc == 0) {
return o;
}
r = 1;
} else {
r = wcrtomb(buf, wc, state);
if (r == __MB_ERR_ILLEGAL_SEQUENCE) {
return r;
}
}
}
return o;
}
for (i = o = 0; i < nwc && o < len; i++, o += r) {
wchar_t wc = (*src)[i];
if (static_cast<uint32_t>(wc) < 0x80) {
// Fast path for plain ASCII characters.
dst[o] = wc;
if (wc == 0) {
*src = nullptr;
return o;
}
r = 1;
} else if (len - o >= sizeof(buf)) {
// Enough space to translate in-place.
r = wcrtomb(dst + o, wc, state);
if (r == __MB_ERR_ILLEGAL_SEQUENCE) {
*src += i;
return r;
}
} else {
// May not be enough space; use temp buffer.
r = wcrtomb(buf, wc, state);
if (r == __MB_ERR_ILLEGAL_SEQUENCE) {
*src += i;
return r;
}
if (r > len - o) {
break;
}
memcpy(dst + o, buf, r);
}
}
*src += i;
return o;
}
size_t wcsrtombs(char* dst, const wchar_t** src, size_t len, mbstate_t* ps) {
return wcsnrtombs(dst, src, SIZE_MAX, len, ps);
}
|
