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