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
|
/*
* Copyright (C) 2007-2019 Apple Inc. All rights reserved.
* Copyright (C) 2010 Patrick Gansterer <paroga@paroga.com>
*
* 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 APPLE INC. ``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 APPLE INC. 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 "config.h"
#include <wtf/unicode/UTF8Conversion.h>
#include <wtf/ASCIICType.h>
#include <wtf/text/StringHasher.h>
#include <wtf/unicode/CharacterNames.h>
namespace WTF {
namespace Unicode {
bool convertLatin1ToUTF8(const LChar** sourceStart, const LChar* sourceEnd, char** targetStart, char* targetEnd)
{
const LChar* source;
char* target = *targetStart;
int i = 0;
for (source = *sourceStart; source < sourceEnd; ++source) {
UBool sawError = false;
// Work around bug in either Windows compiler or old version of ICU, where passing a uint8_t to
// U8_APPEND warns, by converting from uint8_t to a wider type.
UChar32 character = *source;
U8_APPEND(reinterpret_cast<uint8_t*>(target), i, targetEnd - *targetStart, character, sawError);
if (sawError)
return false;
}
*sourceStart = source;
*targetStart = target + i;
return true;
}
ConversionResult convertUTF16ToUTF8(const UChar** sourceStart, const UChar* sourceEnd, char** targetStart, char* targetEnd, bool strict)
{
ConversionResult result = ConversionOK;
const UChar* source = *sourceStart;
char* target = *targetStart;
UBool sawError = false;
int i = 0;
while (source < sourceEnd) {
UChar32 ch;
int j = 0;
U16_NEXT(source, j, sourceEnd - source, ch);
if (U_IS_SURROGATE(ch)) {
if (source + j == sourceEnd && U_IS_SURROGATE_LEAD(ch)) {
result = SourceExhausted;
break;
}
if (strict) {
result = SourceIllegal;
break;
}
ch = replacementCharacter;
}
U8_APPEND(reinterpret_cast<uint8_t*>(target), i, targetEnd - target, ch, sawError);
if (sawError) {
result = TargetExhausted;
break;
}
source += j;
}
*sourceStart = source;
*targetStart = target + i;
return result;
}
template<bool replaceInvalidSequences>
bool convertUTF8ToUTF16Impl(const char* source, const char* sourceEnd, UChar** targetStart, UChar* targetEnd, bool* sourceAllASCII)
{
RELEASE_ASSERT(sourceEnd - source <= std::numeric_limits<int>::max());
UBool error = false;
UChar* target = *targetStart;
RELEASE_ASSERT(targetEnd - target <= std::numeric_limits<int>::max());
UChar32 orAllData = 0;
int targetOffset = 0;
for (int sourceOffset = 0; sourceOffset < sourceEnd - source; ) {
UChar32 character;
if constexpr (replaceInvalidSequences) {
U8_NEXT_OR_FFFD(reinterpret_cast<const uint8_t*>(source), sourceOffset, sourceEnd - source, character);
} else {
U8_NEXT(reinterpret_cast<const uint8_t*>(source), sourceOffset, sourceEnd - source, character);
}
if (character < 0)
return false;
U16_APPEND(target, targetOffset, targetEnd - target, character, error);
if (error)
return false;
orAllData |= character;
}
RELEASE_ASSERT(target + targetOffset <= targetEnd);
*targetStart = target + targetOffset;
if (sourceAllASCII)
*sourceAllASCII = isASCII(orAllData);
return true;
}
bool convertUTF8ToUTF16(const char* source, const char* sourceEnd, UChar** targetStart, UChar* targetEnd, bool* sourceAllASCII)
{
return convertUTF8ToUTF16Impl<false>(source, sourceEnd, targetStart, targetEnd, sourceAllASCII);
}
bool convertUTF8ToUTF16ReplacingInvalidSequences(const char* source, const char* sourceEnd, UChar** targetStart, UChar* targetEnd, bool* sourceAllASCII)
{
return convertUTF8ToUTF16Impl<true>(source, sourceEnd, targetStart, targetEnd, sourceAllASCII);
}
unsigned calculateStringHashAndLengthFromUTF8MaskingTop8Bits(const char* data, const char* dataEnd, unsigned& dataLength, unsigned& utf16Length)
{
StringHasher stringHasher;
utf16Length = 0;
int inputOffset = 0;
int inputLength = dataEnd - data;
while (inputOffset < inputLength) {
UChar32 character;
U8_NEXT(reinterpret_cast<const uint8_t*>(data), inputOffset, inputLength, character);
if (character < 0)
return 0;
if (U_IS_BMP(character)) {
ASSERT(!U_IS_SURROGATE(character));
stringHasher.addCharacter(character);
utf16Length++;
} else {
ASSERT(U_IS_SUPPLEMENTARY(character));
stringHasher.addCharacters(U16_LEAD(character), U16_TRAIL(character));
utf16Length += 2;
}
}
dataLength = inputOffset;
return stringHasher.hashWithTop8BitsMasked();
}
bool equalUTF16WithUTF8(const UChar* a, const char* b, const char* bEnd)
{
while (b < bEnd) {
int offset = 0;
UChar32 character;
U8_NEXT(reinterpret_cast<const uint8_t*>(b), offset, bEnd - b, character);
if (character < 0)
return false;
b += offset;
if (U_IS_BMP(character)) {
ASSERT(!U_IS_SURROGATE(character));
if (*a++ != character)
return false;
} else {
ASSERT(U_IS_SUPPLEMENTARY(character));
if (*a++ != U16_LEAD(character))
return false;
if (*a++ != U16_TRAIL(character))
return false;
}
}
return true;
}
bool equalLatin1WithUTF8(const LChar* a, const char* b, const char* bEnd)
{
while (b < bEnd) {
if (isASCII(*a) || isASCII(*b)) {
if (*a++ != *b++)
return false;
continue;
}
if (b + 1 == bEnd)
return false;
if ((b[0] & 0xE0) != 0xC0 || (b[1] & 0xC0) != 0x80)
return false;
LChar character = ((b[0] & 0x1F) << 6) | (b[1] & 0x3F);
b += 2;
if (*a++ != character)
return false;
}
return true;
}
} // namespace Unicode
} // namespace WTF
|
