File: MarkupTokenizerBase.h

package info (click to toggle)
qtwebkit 2.3.4.dfsg-9.1
  • links: PTS, VCS
  • area: main
  • in suites: stretch
  • size: 290,564 kB
  • ctags: 273,642
  • sloc: cpp: 1,417,509; python: 85,048; ansic: 39,357; perl: 38,862; ruby: 10,313; objc: 9,505; xml: 8,679; asm: 3,864; yacc: 2,458; sh: 1,237; lex: 813; makefile: 592; java: 228; php: 79
file content (207 lines) | stat: -rw-r--r-- 7,785 bytes parent folder | download | duplicates (3)
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
/*
 * Copyright (C) 2008 Apple Inc. All Rights Reserved.
 * Copyright (C) 2009 Torch Mobile, Inc. http://www.torchmobile.com/
 * 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.
 */

#ifndef MarkupTokenizerBase_h
#define MarkupTokenizerBase_h

#include "SegmentedString.h"
#include <wtf/Noncopyable.h>
#include <wtf/PassOwnPtr.h>
#include <wtf/Vector.h>
#include <wtf/text/AtomicString.h>
#include <wtf/text/TextPosition.h>

namespace WebCore {

// Never use this type for a variable, as it contains several non-virtual functions.
template<typename Token, typename State>
class MarkupTokenizerBase {
    WTF_MAKE_NONCOPYABLE(MarkupTokenizerBase);
    WTF_MAKE_FAST_ALLOCATED;
public:
    virtual ~MarkupTokenizerBase() { }

    typename State::State state() const { return m_state; }
    void setState(typename State::State state) { m_state = state; }

    bool forceNullCharacterReplacement() const { return m_forceNullCharacterReplacement; }
    void setForceNullCharacterReplacement(bool value) { m_forceNullCharacterReplacement = value; }

    // This method needs to be defined in a template specialization when subclassing this template
    inline bool shouldSkipNullCharacters() const;

protected:
    // http://www.whatwg.org/specs/web-apps/current-work/#preprocessing-the-input-stream
    class InputStreamPreprocessor {
        WTF_MAKE_NONCOPYABLE(InputStreamPreprocessor);
    public:
        InputStreamPreprocessor(MarkupTokenizerBase<Token, State>* tokenizer)
            : m_tokenizer(tokenizer)
            , m_nextInputCharacter('\0')
            , m_skipNextNewLine(false)
        {
        }

        ALWAYS_INLINE UChar nextInputCharacter() const { return m_nextInputCharacter; }

        // Returns whether we succeeded in peeking at the next character.
        // The only way we can fail to peek is if there are no more
        // characters in |source| (after collapsing \r\n, etc).
        ALWAYS_INLINE bool peek(SegmentedString& source)
        {
        PeekAgain:
            m_nextInputCharacter = source.currentChar();

            // Every branch in this function is expensive, so we have a
            // fast-reject branch for characters that don't require special
            // handling. Please run the parser benchmark whenever you touch
            // this function. It's very hot.
            static const UChar specialCharacterMask = '\n' | '\r' | '\0';
            if (m_nextInputCharacter & ~specialCharacterMask) {
                m_skipNextNewLine = false;
                return true;
            }

            if (m_nextInputCharacter == '\n' && m_skipNextNewLine) {
                m_skipNextNewLine = false;
                source.advancePastNewlineAndUpdateLineNumber();
                if (source.isEmpty())
                    return false;
                m_nextInputCharacter = source.currentChar();
            }
            if (m_nextInputCharacter == '\r') {
                m_nextInputCharacter = '\n';
                m_skipNextNewLine = true;
            } else {
                m_skipNextNewLine = false;
                // FIXME: The spec indicates that the surrogate pair range as well as
                // a number of specific character values are parse errors and should be replaced
                // by the replacement character. We suspect this is a problem with the spec as doing
                // that filtering breaks surrogate pair handling and causes us not to match Minefield.
                if (m_nextInputCharacter == '\0' && !shouldTreatNullAsEndOfFileMarker(source)) {
                    if (m_tokenizer->shouldSkipNullCharacters()) {
                        source.advancePastNonNewline();
                        if (source.isEmpty())
                            return false;
                        goto PeekAgain;
                    }
                    m_nextInputCharacter = 0xFFFD;
                }
            }
            return true;
        }

        // Returns whether there are more characters in |source| after advancing.
        ALWAYS_INLINE bool advance(SegmentedString& source)
        {
            source.advanceAndUpdateLineNumber();
            if (source.isEmpty())
                return false;
            return peek(source);
        }

        static const UChar endOfFileMarker = 0;

    private:
        bool shouldTreatNullAsEndOfFileMarker(SegmentedString& source) const
        {
            return source.isClosed() && source.length() == 1;
        }

        MarkupTokenizerBase<Token, State>* m_tokenizer;

        // http://www.whatwg.org/specs/web-apps/current-work/#next-input-character
        UChar m_nextInputCharacter;
        bool m_skipNextNewLine;
    };

    MarkupTokenizerBase() : m_inputStreamPreprocessor(this) { reset(); }

    inline void bufferCharacter(UChar character)
    {
        ASSERT(character != InputStreamPreprocessor::endOfFileMarker);
        m_token->ensureIsCharacterToken();
        m_token->appendToCharacter(character);
    }

    inline void bufferCodePoint(unsigned);

    // This method can get hidden in subclasses
    inline bool emitAndResumeIn(SegmentedString& source, typename State::State state)
    {
        m_state = state;
        source.advanceAndUpdateLineNumber();
        return true;
    }
    
    // This method can get hidden in subclasses
    inline bool emitAndReconsumeIn(SegmentedString&, typename State::State state)
    {
        m_state = state;
        return true;
    }

    inline bool emitEndOfFile(SegmentedString& source)
    {
        if (haveBufferedCharacterToken())
            return true;
        m_state = State::DataState;
        source.advanceAndUpdateLineNumber();
        m_token->clear();
        m_token->makeEndOfFile();
        return true;
    }

    void reset()
    {
        m_state = State::DataState;
        m_token = 0;
    }

    inline bool haveBufferedCharacterToken()
    {
        return m_token->type() == Token::Type::Character;
    }
    
    typename State::State m_state;

    // m_token is owned by the caller. If nextToken is not on the stack,
    // this member might be pointing to unallocated memory.
    Token* m_token;

    bool m_forceNullCharacterReplacement;

    // http://www.whatwg.org/specs/web-apps/current-work/#additional-allowed-character
    UChar m_additionalAllowedCharacter;

    // http://www.whatwg.org/specs/web-apps/current-work/#preprocessing-the-input-stream
    InputStreamPreprocessor m_inputStreamPreprocessor;
};

}

#endif // MarkupTokenizerBase_h