HTMLViewSourceParser.cpp revision cad810f21b803229eb11403f9209855525a25d57 
1/*
2 * Copyright (C) 2010 Google, Inc. All Rights Reserved.
3 *
4 * Redistribution and use in source and binary forms, with or without
5 * modification, are permitted provided that the following conditions
6 * are met:
7 * 1. Redistributions of source code must retain the above copyright
8 *    notice, this list of conditions and the following disclaimer.
9 * 2. Redistributions in binary form must reproduce the above copyright
10 *    notice, this list of conditions and the following disclaimer in the
11 *    documentation and/or other materials provided with the distribution.
12 *
13 * THIS SOFTWARE IS PROVIDED BY APPLE INC. ``AS IS'' AND ANY
14 * EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE
15 * IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR
16 * PURPOSE ARE DISCLAIMED.  IN NO EVENT SHALL APPLE INC. OR
17 * CONTRIBUTORS BE LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL,
18 * EXEMPLARY, OR CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT LIMITED TO,
19 * PROCUREMENT OF SUBSTITUTE GOODS OR SERVICES; LOSS OF USE, DATA, OR
20 * PROFITS; OR BUSINESS INTERRUPTION) HOWEVER CAUSED AND ON ANY THEORY
21 * OF LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY, OR TORT
22 * (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE
23 * OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE.
24 */
25
26#include "config.h"
27#include "HTMLViewSourceParser.h"
28
29#include "HTMLDocumentParser.h"
30#include "HTMLNames.h"
31#include "HTMLViewSourceDocument.h"
32
33namespace WebCore {
34
35HTMLViewSourceParser::HTMLViewSourceParser(HTMLViewSourceDocument* document)
36    : DecodedDataDocumentParser(document)
37    , m_tokenizer(HTMLTokenizer::create(HTMLDocumentParser::usePreHTML5ParserQuirks(document)))
38{
39}
40
41HTMLViewSourceParser::~HTMLViewSourceParser()
42{
43}
44
45void HTMLViewSourceParser::insert(const SegmentedString&)
46{
47    ASSERT_NOT_REACHED();
48}
49
50void HTMLViewSourceParser::pumpTokenizer()
51{
52    while (m_tokenizer->nextToken(m_input.current(), m_token)) {
53        m_token.end(m_input.current().numberOfCharactersConsumed());
54        document()->addSource(sourceForToken(), m_token);
55        updateTokenizerState();
56        m_token.clear(m_input.current().numberOfCharactersConsumed());
57    }
58}
59
60void HTMLViewSourceParser::append(const SegmentedString& input)
61{
62    m_input.appendToEnd(input);
63    m_source.append(input);
64    pumpTokenizer();
65}
66
67String HTMLViewSourceParser::sourceForToken()
68{
69    if (m_token.type() == HTMLToken::EndOfFile)
70        return String();
71
72    ASSERT(m_source.numberOfCharactersConsumed() == m_token.startIndex());
73    UChar* data = 0;
74    int length = m_token.endIndex() - m_token.startIndex();
75    String source = String::createUninitialized(length, data);
76    for (int i = 0; i < length; ++i) {
77        data[i] = *m_source;
78        m_source.advance();
79    }
80    return source;
81}
82
83void HTMLViewSourceParser::updateTokenizerState()
84{
85    // FIXME: The tokenizer should do this work for us.
86    if (m_token.type() != HTMLToken::StartTag)
87        return;
88
89    AtomicString tagName(m_token.name().data(), m_token.name().size());
90    m_tokenizer->updateStateFor(tagName, document()->frame());
91}
92
93void HTMLViewSourceParser::finish()
94{
95    if (!m_input.haveSeenEndOfFile())
96        m_input.markEndOfFile();
97    pumpTokenizer();
98    document()->finishedParsing();
99}
100
101bool HTMLViewSourceParser::finishWasCalled()
102{
103    return m_input.haveSeenEndOfFile();
104}
105
106}
107