1/*
2 * Copyright (C) 2011 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 promo te 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 PageSerializer_h
32#define PageSerializer_h
33
34#include "URL.h"
35#include "URLHash.h"
36#include "SharedBuffer.h"
37#include <wtf/HashMap.h>
38#include <wtf/ListHashSet.h>
39#include <wtf/Vector.h>
40
41namespace WebCore {
42
43class CachedImage;
44class CSSStyleSheet;
45class Document;
46class Frame;
47class Page;
48class RenderElement;
49class StyleProperties;
50class StyleRule;
51
52// This class is used to serialize a page contents back to text (typically HTML).
53// It serializes all the page frames and retrieves resources such as images and CSS stylesheets.
54class PageSerializer {
55public:
56    struct Resource {
57        URL url;
58        String mimeType;
59        RefPtr<SharedBuffer> data;
60        Resource();
61        Resource(const URL&, const String& mimeType, PassRefPtr<SharedBuffer> data);
62    };
63
64    explicit PageSerializer(Vector<Resource>*);
65
66    // Initiates the serialization of the frame's page. All serialized content and retrieved
67    // resources are added to the Vector passed to the constructor. The first resource in that
68    // vector is the top frame serialized content.
69    void serialize(Page*);
70
71    URL urlForBlankFrame(Frame*);
72
73private:
74    void serializeFrame(Frame*);
75
76    // Serializes the stylesheet back to text and adds it to the resources if URL is not-empty.
77    // It also adds any resources included in that stylesheet (including any imported stylesheets and their own resources).
78    void serializeCSSStyleSheet(CSSStyleSheet*, const URL&);
79
80    void addImageToResources(CachedImage*, RenderElement*, const URL&);
81    void retrieveResourcesForProperties(const StyleProperties*, Document*);
82    void retrieveResourcesForRule(StyleRule*, Document*);
83
84    Vector<Resource>* m_resources;
85    ListHashSet<URL> m_resourceURLs;
86    HashMap<Frame*, URL> m_blankFrameURLs;
87    unsigned m_blankFrameCounter;
88};
89
90}
91
92#endif
93