summaryrefslogtreecommitdiffstats
path: root/WebCore/html/HTML5TreeBuilder.cpp
blob: 0153e9451ce8aafb892fc54495550ac08d95e016 (plain)
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
/*
 * 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 GOOGLE 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 GOOGLE 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 "HTML5TreeBuilder.h"

#include "Element.h"
#include "HTML5Lexer.h"
#include "HTML5Token.h"
#include "HTMLDocument.h"
#include "HTMLNames.h"
#include "HTMLParser.h"
#include "HTMLTokenizer.h"
#include "NotImplemented.h"
#include <wtf/UnusedParam.h>

namespace WebCore {

using namespace HTMLNames;

HTML5TreeBuilder::HTML5TreeBuilder(HTML5Lexer* lexer, HTMLDocument* document, bool reportErrors)
    : m_document(document)
    , m_reportErrors(reportErrors)
    , m_isPaused(false)
    , m_lexer(lexer)
    , m_legacyHTMLParser(new HTMLParser(document, reportErrors))
{
}

HTML5TreeBuilder::~HTML5TreeBuilder()
{
}

static void convertToOldStyle(HTML5Token& token, Token& oldStyleToken)
{
    switch (token.type()) {
    case HTML5Token::Uninitialized:
    case HTML5Token::DOCTYPE:
        ASSERT_NOT_REACHED();
        break;
    case HTML5Token::EndOfFile:
        ASSERT_NOT_REACHED();
        notImplemented();
        break;
    case HTML5Token::StartTag:
    case HTML5Token::EndTag: {
        oldStyleToken.beginTag = (token.type() == HTML5Token::StartTag);
        oldStyleToken.selfClosingTag = token.selfClosing();
        oldStyleToken.tagName = token.name();
        HTML5Token::AttributeList& attributes = token.attributes();
        for (HTML5Token::AttributeList::iterator iter = attributes.begin();
             iter != attributes.end(); ++iter) {
            if (!iter->m_name.isEmpty()) {
                String name = String(StringImpl::adopt(iter->m_name));
                String value = String(StringImpl::adopt(iter->m_value));
                RefPtr<Attribute> mappedAttribute = Attribute::createMapped(name, value);
                if (!oldStyleToken.attrs)
                    oldStyleToken.attrs = NamedNodeMap::create();
                oldStyleToken.attrs->insertAttribute(mappedAttribute.release(), false);
            }
        }
        break;
    }
    case HTML5Token::Comment:
        oldStyleToken.tagName = commentAtom;
        oldStyleToken.text = token.takeComment().impl();
        break;
    case HTML5Token::Character:
        oldStyleToken.tagName = textAtom;
        oldStyleToken.text = token.takeCharacters().impl();
        break;
    }
}

void HTML5TreeBuilder::handleScriptStartTag()
{
    notImplemented(); // The HTML frgment case?
    m_lexer->setState(HTML5Lexer::ScriptDataState);
    notImplemented(); // Save insertion mode.
}

void HTML5TreeBuilder::handleScriptEndTag(Element* scriptElement)
{
    ASSERT(!m_scriptToProcess); // Caller never called takeScriptToProcess!
    notImplemented(); // Save insertion mode and insertion point?

    // Pause ourselves so that parsing stops until the script can be processed by the caller.
    m_isPaused = true;
    m_scriptToProcess = scriptElement;
}

PassRefPtr<Element> HTML5TreeBuilder::takeScriptToProcess()
{
    // Unpause ourselves, callers may pause us again when processing the script.
    // The HTML5 spec is written as though scripts are executed inside the tree
    // builder.  We pause the parser to exit the tree builder, and then resume
    // before running scripts.
    m_isPaused = false;
    return m_scriptToProcess.release();
}

PassRefPtr<Node> HTML5TreeBuilder::passTokenToLegacyParser(HTML5Token& token)
{
    if (token.type() == HTML5Token::DOCTYPE) {
        DoctypeToken doctypeToken;
        doctypeToken.m_name.append(token.name().characters(), token.name().length());
        doctypeToken.m_publicID = token.publicIdentifier();
        doctypeToken.m_systemID = token.systemIdentifier();

        m_legacyHTMLParser->parseDoctypeToken(&doctypeToken);
        return 0;
    }

    // For now, we translate into an old-style token for testing.
    Token oldStyleToken;
    convertToOldStyle(token, oldStyleToken);

    RefPtr<Node> result =  m_legacyHTMLParser->parseToken(&oldStyleToken);
    if (token.type() == HTML5Token::StartTag) {
        // This work is supposed to be done by the parser, but
        // when using the old parser for we have to do this manually.
        if (token.name() == scriptTag) {
            handleScriptStartTag();
            m_lastScriptElement = static_pointer_cast<Element>(result);
        } else if (token.name() == textareaTag || token.name() == titleTag)
            m_lexer->setState(HTML5Lexer::RCDATAState);
        else if (token.name() == styleTag || token.name() == iframeTag
                 || token.name() == xmpTag || token.name() == noembedTag) {
            // FIXME: noscript and noframes may conditionally enter this state as well.
            m_lexer->setState(HTML5Lexer::RAWTEXTState);
        } else if (token.name() == plaintextTag)
            m_lexer->setState(HTML5Lexer::PLAINTEXTState);
        else if (token.name() == preTag || token.name() == listingTag)
            m_lexer->skipLeadingNewLineForListing();
    }
    if (token.type() == HTML5Token::EndTag) {
        if (token.name() == scriptTag) {
            if (m_lastScriptElement) {
                handleScriptEndTag(m_lastScriptElement.get());
                m_lastScriptElement = 0;
            }
        }
    }
    return result.release();
}

PassRefPtr<Node> HTML5TreeBuilder::constructTreeFromToken(HTML5Token& token)
{
    // Make MSVC ignore our unreachable code for now.
    if (true)
        return passTokenToLegacyParser(token);

    // HTML5 expects the tokenizer to call the parser every time a character is
    // emitted.  We instead collect characters and call the parser with a batch.
    // In order to make our first-pass parser code simple, processToken matches
    // the spec in only handling one character at a time.
    if (token.type() == HTML5Token::Character) {
        HTML5Token::DataVector characters = token.characters();
        HTML5Token::DataVector::const_iterator itr = characters.begin();
        for (;itr; ++itr)
            processToken(token, *itr);
        return 0; // FIXME: Should we be returning the Text node?
    }
    return processToken(token);
}

PassRefPtr<Node> HTML5TreeBuilder::processToken(HTML5Token& token, UChar currentCharacter)
{
    UNUSED_PARAM(token);
    UNUSED_PARAM(currentCharacter);
    // Implementation coming in the next patch.
    return 0;
}

void HTML5TreeBuilder::finished()
{
    // We should call m_document->finishedParsing() here, except
    // m_legacyHTMLParser->finished() does it for us.
    m_legacyHTMLParser->finished();
}

}