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
|
/*
* Copyright (C) 2016 Apple Inc. 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 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,
* 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 "TextDecoder.h"
#include "ExceptionCode.h"
#include "HTMLParserIdioms.h"
namespace WebCore {
ExceptionOr<Ref<TextDecoder>> TextDecoder::create(const String& label, Options options)
{
String strippedLabel = stripLeadingAndTrailingHTMLSpaces(label);
const UChar nullCharacter = '\0';
if (strippedLabel.contains(nullCharacter))
return Exception { RangeError };
auto decoder = adoptRef(*new TextDecoder(strippedLabel.utf8().data(), options));
if (!decoder->m_textEncoding.isValid() || !strcmp(decoder->m_textEncoding.name(), "replacement"))
return Exception { RangeError };
return WTFMove(decoder);
}
TextDecoder::TextDecoder(const char* label, Options options)
: m_textEncoding(label)
, m_options(options)
{
}
void TextDecoder::ignoreBOMIfNecessary(const uint8_t*& data, size_t& length)
{
const uint8_t utf8BOMBytes[3] = {0xEF, 0xBB, 0xBF};
const uint8_t utf16BEBOMBytes[2] = {0xFE, 0xFF};
const uint8_t utf16LEBOMBytes[2] = {0xFF, 0xFE};
if (m_textEncoding == UTF8Encoding()
&& length >= sizeof(utf8BOMBytes)
&& data[0] == utf8BOMBytes[0]
&& data[1] == utf8BOMBytes[1]
&& data[2] == utf8BOMBytes[2]) {
data += sizeof(utf8BOMBytes);
length -= sizeof(utf8BOMBytes);
} else if (m_textEncoding == UTF16BigEndianEncoding()
&& length >= sizeof(utf16BEBOMBytes)
&& data[0] == utf16BEBOMBytes[0]
&& data[1] == utf16BEBOMBytes[1]) {
data += sizeof(utf16BEBOMBytes);
length -= sizeof(utf16BEBOMBytes);
} else if (m_textEncoding == UTF16LittleEndianEncoding()
&& length >= sizeof(utf16LEBOMBytes)
&& data[0] == utf16LEBOMBytes[0]
&& data[1] == utf16LEBOMBytes[1]) {
data += sizeof(utf16LEBOMBytes);
length -= sizeof(utf16LEBOMBytes);
}
}
String TextDecoder::prependBOMIfNecessary(const String& decoded)
{
if (m_hasDecoded || !m_options.ignoreBOM)
return decoded;
const UChar utf16BEBOM[2] = {0xFEFF, '\0'};
// FIXME: Make TextCodec::decode take a flag for prepending BOM so we don't need to do this extra allocation and copy.
return makeString(utf16BEBOM, decoded);
}
static size_t codeUnitByteSize(const TextEncoding& encoding)
{
if (encoding.isByteBasedEncoding())
return 1;
if (encoding == UTF32BigEndianEncoding() || encoding == UTF32LittleEndianEncoding())
return 4;
return 2;
}
ExceptionOr<String> TextDecoder::decode(std::optional<BufferSource::VariantType> input, DecodeOptions options)
{
std::optional<BufferSource> inputBuffer;
const uint8_t* data = nullptr;
size_t length = 0;
if (input) {
inputBuffer = BufferSource(WTFMove(input.value()));
data = inputBuffer->data();
length = inputBuffer->length();
}
ignoreBOMIfNecessary(data, length);
if (m_buffer.size()) {
m_buffer.append(data, length);
data = m_buffer.data();
length = m_buffer.size();
}
const bool stopOnError = true;
bool sawError = false;
if (length % codeUnitByteSize(m_textEncoding))
sawError = true;
const char* charData = reinterpret_cast<const char*>(data);
String result;
if (!sawError)
result = prependBOMIfNecessary(m_textEncoding.decode(charData, length, stopOnError, sawError));
if (sawError) {
if (options.stream) {
result = String();
if (!m_buffer.size())
m_buffer.append(data, length);
} else {
if (m_options.fatal)
return Exception { TypeError };
result = prependBOMIfNecessary(m_textEncoding.decode(charData, length));
}
} else
m_buffer.clear();
m_hasDecoded = true;
return WTFMove(result);
}
String TextDecoder::encoding() const
{
return String(m_textEncoding.name()).convertToASCIILowercase();
}
}
|
