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
|
/*
* Copyright (C) 2010 Google, 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,
* 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 "HTMLViewSourceParser.h"
#include "HTMLNames.h"
#include "HTMLTreeBuilder.h"
#include "HTMLViewSourceDocument.h"
namespace WebCore {
HTMLViewSourceParser::HTMLViewSourceParser(HTMLViewSourceDocument* document)
: DecodedDataDocumentParser(document)
, m_tokenizer(HTMLTokenizer::create())
{
}
HTMLViewSourceParser::~HTMLViewSourceParser()
{
}
void HTMLViewSourceParser::insert(const SegmentedString&)
{
ASSERT_NOT_REACHED();
}
void HTMLViewSourceParser::pumpTokenizer()
{
while (m_tokenizer->nextToken(m_input.current(), m_token)) {
m_token.end(m_input.current().numberOfCharactersConsumed());
document()->addSource(sourceForToken(), m_token);
updateTokenizerState();
m_token.clear(m_input.current().numberOfCharactersConsumed());
}
}
void HTMLViewSourceParser::append(const SegmentedString& input)
{
m_input.appendToEnd(input);
m_source.append(input);
pumpTokenizer();
}
String HTMLViewSourceParser::sourceForToken()
{
if (m_token.type() == HTMLToken::EndOfFile)
return String();
ASSERT(m_source.numberOfCharactersConsumed() == m_token.startIndex());
UChar* data = 0;
int length = m_token.endIndex() - m_token.startIndex();
String source = String::createUninitialized(length, data);
for (int i = 0; i < length; ++i) {
data[i] = *m_source;
m_source.advance();
}
return source;
}
void HTMLViewSourceParser::updateTokenizerState()
{
// FIXME: The tokenizer should do this work for us.
if (m_token.type() != HTMLToken::StartTag)
return;
AtomicString tagName(m_token.name().data(), m_token.name().size());
m_tokenizer->setState(HTMLTreeBuilder::adjustedLexerState(m_tokenizer->state(), tagName, document()->frame()));
if (tagName == HTMLNames::scriptTag) {
// The tree builder handles scriptTag separately from the other tokenizer
// state adjustments, so we need to handle it separately too.
ASSERT(m_tokenizer->state() == HTMLTokenizer::DataState);
m_tokenizer->setState(HTMLTokenizer::ScriptDataState);
}
}
void HTMLViewSourceParser::finish()
{
if (!m_input.haveSeenEndOfFile())
m_input.markEndOfFile();
pumpTokenizer();
document()->finishedParsing();
}
bool HTMLViewSourceParser::finishWasCalled()
{
return m_input.haveSeenEndOfFile();
}
}
|
