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#ifndef HTMLDocumentParser_h
27#define HTMLDocumentParser_h
28
29#include "CachedResourceClient.h"
30#include "FragmentScriptingPermission.h"
31#include "HTMLInputStream.h"
32#include "HTMLScriptRunnerHost.h"
33#include "HTMLSourceTracker.h"
34#include "HTMLToken.h"
35#include "ScriptableDocumentParser.h"
36#include "SegmentedString.h"
37#include "Timer.h"
38#include "XSSFilter.h"
39#include <wtf/OwnPtr.h>
40
41namespace WebCore {
42
43class Document;
44class DocumentFragment;
45class HTMLDocument;
46class HTMLParserScheduler;
47class HTMLTokenizer;
48class HTMLScriptRunner;
49class HTMLTreeBuilder;
50class HTMLPreloadScanner;
51class ScriptController;
52class ScriptSourceCode;
53
54class PumpSession;
55
56class HTMLDocumentParser :  public ScriptableDocumentParser, HTMLScriptRunnerHost, CachedResourceClient {
57    WTF_MAKE_FAST_ALLOCATED;
58public:
59    static PassRefPtr<HTMLDocumentParser> create(HTMLDocument* document, bool reportErrors)
60    {
61        return adoptRef(new HTMLDocumentParser(document, reportErrors));
62    }
63    static PassRefPtr<HTMLDocumentParser> create(DocumentFragment* fragment, Element* contextElement, FragmentScriptingPermission permission)
64    {
65        return adoptRef(new HTMLDocumentParser(fragment, contextElement, permission));
66    }
67
68    virtual ~HTMLDocumentParser();
69
70    // Exposed for HTMLParserScheduler
71    void resumeParsingAfterYield();
72
73    static void parseDocumentFragment(const String&, DocumentFragment*, Element* contextElement, FragmentScriptingPermission = FragmentScriptingAllowed);
74
75    static bool usePreHTML5ParserQuirks(Document*);
76
77    HTMLTokenizer* tokenizer() const { return m_tokenizer.get(); }
78    String sourceForToken(const HTMLToken&);
79
80    virtual TextPosition0 textPosition() const;
81    virtual int lineNumber() const;
82
83    virtual void suspendScheduledTasks();
84    virtual void resumeScheduledTasks();
85
86protected:
87    virtual void insert(const SegmentedString&);
88    virtual void append(const SegmentedString&);
89    virtual void finish();
90
91    HTMLDocumentParser(HTMLDocument*, bool reportErrors);
92    HTMLDocumentParser(DocumentFragment*, Element* contextElement, FragmentScriptingPermission);
93
94    HTMLTreeBuilder* treeBuilder() const { return m_treeBuilder.get(); }
95
96private:
97    // DocumentParser
98    virtual void detach();
99    virtual bool hasInsertionPoint();
100    virtual bool finishWasCalled();
101    virtual bool processingData() const;
102    virtual void prepareToStopParsing();
103    virtual void stopParsing();
104    virtual bool isWaitingForScripts() const;
105    virtual bool isExecutingScript() const;
106    virtual void executeScriptsWaitingForStylesheets();
107
108    // HTMLScriptRunnerHost
109    virtual void watchForLoad(CachedResource*);
110    virtual void stopWatchingForLoad(CachedResource*);
111    virtual HTMLInputStream& inputStream() { return m_input; }
112    virtual bool hasPreloadScanner() const { return m_preloadScanner.get(); }
113    virtual void appendCurrentInputStreamToPreloadScannerAndScan();
114
115    // CachedResourceClient
116    virtual void notifyFinished(CachedResource*);
117
118    enum SynchronousMode {
119        AllowYield,
120        ForceSynchronous,
121    };
122    bool canTakeNextToken(SynchronousMode, PumpSession&);
123    void pumpTokenizer(SynchronousMode);
124    void pumpTokenizerIfPossible(SynchronousMode);
125
126    bool runScriptsForPausedTreeBuilder();
127    void resumeParsingAfterScriptExecution();
128
129    void begin();
130    void attemptToEnd();
131    void endIfDelayed();
132    void attemptToRunDeferredScriptsAndEnd();
133    void end();
134
135    bool isParsingFragment() const;
136    bool isScheduledForResume() const;
137    bool inScriptExecution() const;
138    bool inPumpSession() const { return m_pumpSessionNestingLevel > 0; }
139    bool shouldDelayEnd() const { return inPumpSession() || isWaitingForScripts() || inScriptExecution() || isScheduledForResume(); }
140
141    ScriptController* script() const;
142
143    HTMLInputStream m_input;
144
145    // We hold m_token here because it might be partially complete.
146    HTMLToken m_token;
147
148    OwnPtr<HTMLTokenizer> m_tokenizer;
149    OwnPtr<HTMLScriptRunner> m_scriptRunner;
150    OwnPtr<HTMLTreeBuilder> m_treeBuilder;
151    OwnPtr<HTMLPreloadScanner> m_preloadScanner;
152    OwnPtr<HTMLParserScheduler> m_parserScheduler;
153    HTMLSourceTracker m_sourceTracker;
154    XSSFilter m_xssFilter;
155
156    bool m_endWasDelayed;
157    unsigned m_pumpSessionNestingLevel;
158};
159
160}
161
162#endif
163