third_party/WebKit/Source/web/WebPageSerializerImpl.h

   1 /*
   2  * Copyright (C) 2009 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 are
   6  * met:
   7  *
   8  *     * Redistributions of source code must retain the above copyright
   9  * notice, this list of conditions and the following disclaimer.
  10  *     * Redistributions in binary form must reproduce the above
  11  * copyright notice, this list of conditions and the following disclaimer
  12  * in the documentation and/or other materials provided with the
  13  * distribution.
  14  *     * Neither the name of Google Inc. nor the names of its
  15  * contributors may be used to endorse or promote products derived from
  16  * this software without specific prior written permission.
  17  *
  18  * THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS
  19  * "AS IS" AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT
  20  * LIMITED TO, THE IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR
  21  * A PARTICULAR PURPOSE ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT
  22  * OWNER OR CONTRIBUTORS BE LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL,
  23  * SPECIAL, EXEMPLARY, OR CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT
  24  * LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS OR SERVICES; LOSS OF USE,
  25  * DATA, OR PROFITS; OR BUSINESS INTERRUPTION) HOWEVER CAUSED AND ON ANY
  26  * THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY, OR TORT
  27  * (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE
  28  * OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE.
  29  */
  30
  31 #ifndef WebPageSerializerImpl_h
  32 #define WebPageSerializerImpl_h
  33
  34 #include "wtf/Forward.h"
  35 #include "wtf/HashMap.h"
  36 #include "wtf/Vector.h"
  37 #include "wtf/text/StringBuilder.h"
  38 #include "wtf/text/StringHash.h"
  39 #include "wtf/text/WTFString.h"
  40
  41 #include "public/platform/WebString.h"
  42 #include "public/platform/WebURL.h"
  43 #include "public/web/WebPageSerializer.h"
  44 #include "public/web/WebPageSerializerClient.h"
  45 #include "web/WebEntities.h"
  46
  47 namespace WTF {
  48 class TextEncoding;
  49 }
  50
  51 namespace blink {
  52
  53 class Document;
  54 class Element;
  55 class Node;
  56 class WebLocalFrameImpl;
  57
  58 // Get html data by serializing all frames of current page with lists
  59 // which contain all resource links that have local copy.
  60 // contain all saved auxiliary files included all sub frames and resources.
  61 // This function will find out all frames and serialize them to HTML data.
  62 // We have a data buffer to temporary saving generated html data. We will
  63 // sequentially call WebViewDelegate::SendSerializedHtmlData once the data
  64 // buffer is full. See comments of WebViewDelegate::SendSerializedHtmlData
  65 // for getting more information.
  66 class WebPageSerializerImpl {
  67     STACK_ALLOCATED();
  68 public:
  69     // Do serialization action. Return false means no available frame has been
  70     // serialized, otherwise return true.
  71     bool serialize();
  72
  73     // The parameter specifies which frame need to be serialized.
  74     // The parameter recursive_serialization specifies whether we need to
  75     // serialize all sub frames of the specified frame or not.
  76     // The parameter delegate specifies the pointer of interface
  77     // DomSerializerDelegate provide sink interface which can receive the
  78     // individual chunks of data to be saved.
  79     // The parameter links contain original URLs of all saved links.
  80     // The parameter local_paths contain corresponding local file paths of all
  81     // saved links, which matched with vector:links one by one.
  82     // The parameter local_directory_name is relative path of directory which
  83     // contain all saved auxiliary files included all sub frames and resources.
  84     WebPageSerializerImpl(WebFrame* frame,
  85                           bool recursive,
  86                           WebPageSerializerClient* client,
  87                           const WebVector<WebURL>& links,
  88                           const WebVector<WebString>& localPaths,
  89                           const WebString& localDirectoryName);
  90
  91 private:
  92     // Specified frame which need to be serialized;
  93     RawPtrWillBeMember<WebLocalFrameImpl> m_specifiedWebLocalFrameImpl;
  94     // Pointer of WebPageSerializerClient
  95     WebPageSerializerClient* m_client;
  96     // This hash map is used to map resource URL of original link to its local
  97     // file path.
  98     typedef HashMap<WTF::String, WTF::String> LinkLocalPathMap;
  99     // local_links_ include all pair of local resource path and corresponding
 100     // original link.
 101     LinkLocalPathMap m_localLinks;
 102     // Data buffer for saving result of serialized DOM data.
 103     StringBuilder m_dataBuffer;
 104     // Passing true to recursive_serialization_ indicates we will serialize not
 105     // only the specified frame but also all sub-frames in the specific frame.
 106     // Otherwise we only serialize the specified frame excluded all sub-frames.
 107     bool m_recursiveSerialization;
 108     // Flag indicates whether we have collected all frames which need to be
 109     // serialized or not;
 110     bool m_framesCollected;
 111     // Local directory name of all local resource files.
 112     WTF::String m_localDirectoryName;
 113     // Vector for saving all frames which need to be serialized.
 114     WillBeHeapVector<RawPtrWillBeMember<WebLocalFrameImpl>> m_frames;
 115
 116     // Web entities conversion maps.
 117     WebEntities m_htmlEntities;
 118     WebEntities m_xmlEntities;
 119
 120     class SerializeDomParam {
 121         STACK_ALLOCATED();
 122     public:
 123         SerializeDomParam(const KURL&, const WTF::TextEncoding&, Document*, const WTF::String& directoryName);
 124
 125         const KURL& url;
 126         const WTF::TextEncoding& textEncoding;
 127         RawPtrWillBeMember<Document> document;
 128         const WTF::String& directoryName;
 129         bool isHTMLDocument; // document.isHTMLDocument()
 130         bool haveSeenDocType;
 131         bool haveAddedCharsetDeclaration;
 132         // This meta element need to be skipped when serializing DOM.
 133         RawPtrWillBeMember<const Element> skipMetaElement;
 134         // Flag indicates we are in script or style tag.
 135         bool isInScriptOrStyleTag;
 136         bool haveAddedXMLProcessingDirective;
 137         // Flag indicates whether we have added additional contents before end tag.
 138         // This flag will be re-assigned in each call of function
 139         // PostActionAfterSerializeOpenTag and it could be changed in function
 140         // PreActionBeforeSerializeEndTag if the function adds new contents into
 141         // serialization stream.
 142         bool haveAddedContentsBeforeEnd;
 143     };
 144
 145     // Collect all target frames which need to be serialized.
 146     void collectTargetFrames();
 147     // Before we begin serializing open tag of a element, we give the target
 148     // element a chance to do some work prior to add some additional data.
 149     WTF::String preActionBeforeSerializeOpenTag(const Element*,
 150                                                     SerializeDomParam* param,
 151                                                     bool* needSkip);
 152     // After we finish serializing open tag of a element, we give the target
 153     // element a chance to do some post work to add some additional data.
 154     WTF::String postActionAfterSerializeOpenTag(const Element*,
 155                                                     SerializeDomParam* param);
 156     // Before we begin serializing end tag of a element, we give the target
 157     // element a chance to do some work prior to add some additional data.
 158     WTF::String preActionBeforeSerializeEndTag(const Element*,
 159                                                    SerializeDomParam* param,
 160                                                    bool* needSkip);
 161     // After we finish serializing end tag of a element, we give the target
 162     // element a chance to do some post work to add some additional data.
 163     WTF::String postActionAfterSerializeEndTag(const Element*,
 164                                                    SerializeDomParam* param);
 165     // Save generated html content to data buffer.
 166     void saveHTMLContentToBuffer(const WTF::String& content,
 167                                  SerializeDomParam* param);
 168
 169     enum FlushOption {
 170         ForceFlush,
 171         DoNotForceFlush,
 172     };
 173
 174     // Flushes the content buffer by encoding and sending the content to the
 175     // WebPageSerializerClient. Content is not flushed if the buffer is not full
 176     // unless force is 1.
 177     void encodeAndFlushBuffer(WebPageSerializerClient::PageSerializationStatus status,
 178                               SerializeDomParam* param,
 179                               FlushOption);
 180     // Serialize open tag of an specified element.
 181     void openTagToString(Element*,
 182                          SerializeDomParam* param);
 183     // Serialize end tag of an specified element.
 184     void endTagToString(Element*,
 185                         SerializeDomParam* param);
 186     // Build content for a specified node
 187     void buildContentForNode(Node*,
 188                              SerializeDomParam* param);
 189 };
 190
 191 } // namespace blink
 192
 193 #endif