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