Home | History | Annotate | Download | only in web 
      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 "WebEntities.h"
     42 #include "WebPageSerializer.h"
     43 #include "WebPageSerializerClient.h"
     44 #include "public/platform/WebString.h"
     45 #include "public/platform/WebURL.h"
     46 
     47 namespace WTF{
     48 class TextEncoding;
     49 }
     50 
     51 namespace WebCore {
     52 class Document;
     53 class Element;
     54 class Node;
     55 }
     56 
     57 namespace WebKit {
     58 class WebFrameImpl;
     59 
     60 // Get html data by serializing all frames of current page with lists
     61 // which contain all resource links that have local copy.
     62 // contain all saved auxiliary files included all sub frames and resources.
     63 // This function will find out all frames and serialize them to HTML data.
     64 // We have a data buffer to temporary saving generated html data. We will
     65 // sequentially call WebViewDelegate::SendSerializedHtmlData once the data
     66 // buffer is full. See comments of WebViewDelegate::SendSerializedHtmlData
     67 // for getting more information.
     68 class WebPageSerializerImpl {
     69 public:
     70     // Do serialization action. Return false means no available frame has been
     71     // serialized, otherwise return true.
     72     bool serialize();
     73 
     74     // The parameter specifies which frame need to be serialized.
     75     // The parameter recursive_serialization specifies whether we need to
     76     // serialize all sub frames of the specified frame or not.
     77     // The parameter delegate specifies the pointer of interface
     78     // DomSerializerDelegate provide sink interface which can receive the
     79     // individual chunks of data to be saved.
     80     // The parameter links contain original URLs of all saved links.
     81     // The parameter local_paths contain corresponding local file paths of all
     82     // saved links, which matched with vector:links one by one.
     83     // The parameter local_directory_name is relative path of directory which
     84     // contain all saved auxiliary files included all sub frames and resources.
     85     WebPageSerializerImpl(WebFrame* frame,
     86                           bool recursive,
     87                           WebPageSerializerClient* client,
     88                           const WebVector<WebURL>& links,
     89                           const WebVector<WebString>& localPaths,
     90                           const WebString& localDirectoryName);
     91 
     92 private:
     93     // Specified frame which need to be serialized;
     94     WebFrameImpl* m_specifiedWebFrameImpl;
     95     // Pointer of WebPageSerializerClient
     96     WebPageSerializerClient* m_client;
     97     // This hash map is used to map resource URL of original link to its local
     98     // file path.
     99     typedef HashMap<WTF::String, WTF::String> LinkLocalPathMap;
    100     // local_links_ include all pair of local resource path and corresponding
    101     // original link.
    102     LinkLocalPathMap m_localLinks;
    103     // Data buffer for saving result of serialized DOM data.
    104     StringBuilder m_dataBuffer;
    105     // Passing true to recursive_serialization_ indicates we will serialize not
    106     // only the specified frame but also all sub-frames in the specific frame.
    107     // Otherwise we only serialize the specified frame excluded all sub-frames.
    108     bool m_recursiveSerialization;
    109     // Flag indicates whether we have collected all frames which need to be
    110     // serialized or not;
    111     bool m_framesCollected;
    112     // Local directory name of all local resource files.
    113     WTF::String m_localDirectoryName;
    114     // Vector for saving all frames which need to be serialized.
    115     Vector<WebFrameImpl*> m_frames;
    116 
    117     // Web entities conversion maps.
    118     WebEntities m_htmlEntities;
    119     WebEntities m_xmlEntities;
    120 
    121     struct SerializeDomParam {
    122         const WebCore::KURL& url;
    123         const WTF::TextEncoding& textEncoding;
    124         WebCore::Document* document;
    125         const WTF::String& directoryName;
    126         bool isHTMLDocument; // document.isHTMLDocument()
    127         bool haveSeenDocType;
    128         bool haveAddedCharsetDeclaration;
    129         // This meta element need to be skipped when serializing DOM.
    130         const WebCore::Element* skipMetaElement;
    131         // Flag indicates we are in script or style tag.
    132         bool isInScriptOrStyleTag;
    133         bool haveAddedXMLProcessingDirective;
    134         // Flag indicates whether we have added additional contents before end tag.
    135         // This flag will be re-assigned in each call of function
    136         // PostActionAfterSerializeOpenTag and it could be changed in function
    137         // PreActionBeforeSerializeEndTag if the function adds new contents into
    138         // serialization stream.
    139         bool haveAddedContentsBeforeEnd;
    140 
    141         SerializeDomParam(const WebCore::KURL&, const WTF::TextEncoding&, WebCore::Document*, const WTF::String& directoryName);
    142     };
    143 
    144     // Collect all target frames which need to be serialized.
    145     void collectTargetFrames();
    146     // Before we begin serializing open tag of a element, we give the target
    147     // element a chance to do some work prior to add some additional data.
    148     WTF::String preActionBeforeSerializeOpenTag(const WebCore::Element* element,
    149                                                     SerializeDomParam* param,
    150                                                     bool* needSkip);
    151     // After we finish serializing open tag of a element, we give the target
    152     // element a chance to do some post work to add some additional data.
    153     WTF::String postActionAfterSerializeOpenTag(const WebCore::Element* element,
    154                                                     SerializeDomParam* param);
    155     // Before we begin serializing end tag of a element, we give the target
    156     // element a chance to do some work prior to add some additional data.
    157     WTF::String preActionBeforeSerializeEndTag(const WebCore::Element* element,
    158                                                    SerializeDomParam* param,
    159                                                    bool* needSkip);
    160     // After we finish serializing end tag of a element, we give the target
    161     // element a chance to do some post work to add some additional data.
    162     WTF::String postActionAfterSerializeEndTag(const WebCore::Element* element,
    163                                                    SerializeDomParam* param);
    164     // Save generated html content to data buffer.
    165     void saveHTMLContentToBuffer(const WTF::String& content,
    166                                  SerializeDomParam* param);
    167 
    168     enum FlushOption {
    169         ForceFlush,
    170         DoNotForceFlush,
    171     };
    172 
    173     // Flushes the content buffer by encoding and sending the content to the
    174     // WebPageSerializerClient. Content is not flushed if the buffer is not full
    175     // unless force is 1.
    176     void encodeAndFlushBuffer(WebPageSerializerClient::PageSerializationStatus status,
    177                               SerializeDomParam* param,
    178                               FlushOption);
    179     // Serialize open tag of an specified element.
    180     void openTagToString(WebCore::Element*,
    181                          SerializeDomParam* param);
    182     // Serialize end tag of an specified element.
    183     void endTagToString(WebCore::Element*,
    184                         SerializeDomParam* param);
    185     // Build content for a specified node
    186     void buildContentForNode(WebCore::Node*,
    187                              SerializeDomParam* param);
    188 };
    189 
    190 } // namespace WebKit
    191 
    192 #endif
    193