third_party/WebKit/public/web/WebPageSerializer.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 WebPageSerializer_h
  32 #define WebPageSerializer_h
  33
  34 #include "../platform/WebCString.h"
  35 #include "../platform/WebCommon.h"
  36 #include "../platform/WebURL.h"
  37 #include "WebFrame.h"
  38
  39 namespace blink {
  40
  41 class WebPageSerializerClient;
  42 class WebString;
  43 class WebView;
  44 template <typename T> class WebVector;
  45
  46 // Get html data by serializing all frames of current page with lists
  47 // which contain all resource links that have local copy.
  48 class WebPageSerializer {
  49 public:
  50     struct Resource {
  51         WebURL url;
  52         WebCString mimeType;
  53         WebCString data;
  54     };
  55
  56     // Serializes all the frames from the WebView, retrieves the page's
  57     // resources (such as images and CSS) and adds them to the passed vector.
  58     // The first resource in that vector is the top frame contents.
  59     // Note that this also strips-out any script tag or link to JavaScript.
  60     BLINK_EXPORT static void serialize(WebView*, WebVector<Resource>*);
  61
  62     // Serializes the WebView contents to a MHTML representation.
  63     BLINK_EXPORT static WebCString serializeToMHTML(WebView*);
  64
  65     // Similar to serializeToMHTML but uses binary encoding for the MHTML parts.
  66     // This results in a smaller MHTML file but it might not be supported by other browsers.
  67     BLINK_EXPORT static WebCString serializeToMHTMLUsingBinaryEncoding(WebView*);
  68
  69     // IMPORTANT:
  70     // The API below is an older implementation of a pageserialization that
  71     // will be removed soon.
  72
  73
  74     // This function will find out all frames and serialize them to HTML data.
  75     // We have a data buffer to temporary saving generated html data. We will
  76     // sequentially call WebPageSeriazlierClient once the data buffer is full.
  77     //
  78     // Return false means no available frame has been serialized, otherwise
  79     // return true.
  80     //
  81     // The parameter frame specifies which frame need to be serialized.
  82     // The parameter recursive specifies whether we need to
  83     // serialize all sub frames of the specified frame or not.
  84     // The parameter client specifies the pointer of interface
  85     // WebPageSerializerClient providing a sink interface to receive the
  86     // individual chunks of data to be saved.
  87     // The parameter links contain original URLs of all saved links.
  88     // The parameter localPaths contain corresponding local file paths of all
  89     // saved links, which matched with vector:links one by one.
  90     // The parameter localDirectoryName is relative path of directory which
  91     // contain all saved auxiliary files included all sub frames and resources.
  92     BLINK_EXPORT static bool serialize(
  93         WebLocalFrame*,
  94         bool recursive,
  95         WebPageSerializerClient*,
  96         const WebVector<WebURL>& links,
  97         const WebVector<WebString>& localPaths,
  98         const WebString& localDirectoryName);
  99
 100     // Retrieve all the resource for the passed view, including the main frame
 101     // and sub-frames. Returns true if all resources were retrieved
 102     // successfully.
 103     BLINK_EXPORT static bool retrieveAllResources(WebView*,
 104                                                    const WebVector<WebCString>& supportedSchemes,
 105                                                    WebVector<WebURL>* resources,
 106                                                    WebVector<WebURL>* frames);
 107
 108     // FIXME: The following are here for unit testing purposes. Consider
 109     // changing the unit tests instead.
 110
 111     // Generate the META for charset declaration.
 112     BLINK_EXPORT static WebString generateMetaCharsetDeclaration(const WebString& charset);
 113     // Generate the MOTW declaration.
 114     BLINK_EXPORT static WebString generateMarkOfTheWebDeclaration(const WebURL&);
 115     // Generate the default base tag declaration.
 116     BLINK_EXPORT static WebString generateBaseTagDeclaration(const WebString& baseTarget);
 117 };
 118
 119 } // namespace blink
 120
 121 #endif