third_party/WebKit/Source/core/html/parser/BackgroundHTMLParser.h

   1 /*
   2  * Copyright (C) 2013 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 GOOGLE 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 GOOGLE 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 BackgroundHTMLParser_h
  27 #define BackgroundHTMLParser_h
  28
  29 #include "core/dom/DocumentEncodingData.h"
  30 #include "core/html/parser/BackgroundHTMLInputStream.h"
  31 #include "core/html/parser/CompactHTMLToken.h"
  32 #include "core/html/parser/HTMLParserOptions.h"
  33 #include "core/html/parser/HTMLPreloadScanner.h"
  34 #include "core/html/parser/HTMLSourceTracker.h"
  35 #include "core/html/parser/HTMLTreeBuilderSimulator.h"
  36 #include "core/html/parser/TextResourceDecoder.h"
  37 #include "core/html/parser/XSSAuditorDelegate.h"
  38 #include "wtf/PassOwnPtr.h"
  39 #include "wtf/WeakPtr.h"
  40
  41 namespace blink {
  42
  43 class HTMLDocumentParser;
  44 class XSSAuditor;
  45 class WebScheduler;
  46
  47 class BackgroundHTMLParser {
  48     WTF_MAKE_FAST_ALLOCATED(BackgroundHTMLParser);
  49     WTF_MAKE_NONCOPYABLE(BackgroundHTMLParser);
  50 public:
  51     struct Configuration {
  52         WTF_MAKE_FAST_ALLOCATED(Configuration);
  53     public:
  54         Configuration();
  55         HTMLParserOptions options;
  56         WeakPtr<HTMLDocumentParser> parser;
  57         OwnPtr<XSSAuditor> xssAuditor;
  58         OwnPtr<TokenPreloadScanner> preloadScanner;
  59         OwnPtr<TextResourceDecoder> decoder;
  60         // outstandingTokenLimit must be greater than or equal to
  61         // pendingTokenLimit
  62         size_t outstandingTokenLimit;
  63         size_t pendingTokenLimit;
  64     };
  65
  66     static void start(PassRefPtr<WeakReference<BackgroundHTMLParser>>, PassOwnPtr<Configuration>, WebScheduler*);
  67
  68     struct Checkpoint {
  69         WTF_MAKE_FAST_ALLOCATED(CheckPoint);
  70     public:
  71         WeakPtr<HTMLDocumentParser> parser;
  72         OwnPtr<HTMLToken> token;
  73         OwnPtr<HTMLTokenizer> tokenizer;
  74         HTMLTreeBuilderSimulator::State treeBuilderState;
  75         HTMLInputCheckpoint inputCheckpoint;
  76         TokenPreloadScannerCheckpoint preloadScannerCheckpoint;
  77         String unparsedInput;
  78     };
  79
  80     void appendRawBytesFromParserThread(const char* data, int dataLength);
  81
  82     void appendRawBytesFromMainThread(PassOwnPtr<Vector<char>>);
  83     void setDecoder(PassOwnPtr<TextResourceDecoder>);
  84     void flush();
  85     void resumeFrom(PassOwnPtr<Checkpoint>);
  86     void startedChunkWithCheckpoint(HTMLInputCheckpoint);
  87     void finish();
  88     void stop();
  89
  90     void forcePlaintextForTextDocument();
  91
  92 private:
  93     BackgroundHTMLParser(PassRefPtr<WeakReference<BackgroundHTMLParser>>, PassOwnPtr<Configuration>, WebScheduler*);
  94     ~BackgroundHTMLParser();
  95
  96     void appendDecodedBytes(const String&);
  97     void markEndOfFile();
  98     void pumpTokenizer();
  99     void sendTokensToMainThread();
 100     void updateDocument(const String& decodedData);
 101
 102     WeakPtrFactory<BackgroundHTMLParser> m_weakFactory;
 103     BackgroundHTMLInputStream m_input;
 104     HTMLSourceTracker m_sourceTracker;
 105     OwnPtr<HTMLToken> m_token;
 106     OwnPtr<HTMLTokenizer> m_tokenizer;
 107     HTMLTreeBuilderSimulator m_treeBuilderSimulator;
 108     HTMLParserOptions m_options;
 109     const size_t m_outstandingTokenLimit;
 110     WeakPtr<HTMLDocumentParser> m_parser;
 111
 112     OwnPtr<CompactHTMLTokenStream> m_pendingTokens;
 113     const size_t m_pendingTokenLimit;
 114     PreloadRequestStream m_pendingPreloads;
 115     XSSInfoStream m_pendingXSSInfos;
 116
 117     OwnPtr<XSSAuditor> m_xssAuditor;
 118     OwnPtr<TokenPreloadScanner> m_preloadScanner;
 119     OwnPtr<TextResourceDecoder> m_decoder;
 120     DocumentEncodingData m_lastSeenEncodingData;
 121     WebScheduler* m_scheduler; // NOT OWNED, scheduler will outlive BackgroundHTMLParser
 122
 123     bool m_startingScript;
 124 };
 125
 126 }
 127
 128 #endif