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 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#include "config.h"
32#include "public/web/WebPageSerializer.h"
33
34#include "core/testing/URLTestHelpers.h"
35#include "public/platform/Platform.h"
36#include "public/platform/WebString.h"
37#include "public/platform/WebURL.h"
38#include "public/platform/WebURLRequest.h"
39#include "public/platform/WebURLResponse.h"
40#include "public/platform/WebUnitTestSupport.h"
41#include "public/web/WebDocument.h"
42#include "public/web/WebFrame.h"
43#include "public/web/WebView.h"
44#include "web/tests/FrameTestHelpers.h"
45
46#include <gtest/gtest.h>
47
48using namespace blink;
49using blink::Document;
50using blink::URLTestHelpers::toKURL;
51
52namespace {
53
54class WebPageSerializerTest : public testing::Test {
55public:
56    WebPageSerializerTest() : m_supportedSchemes(static_cast<size_t>(3))
57    {
58        m_supportedSchemes[0] = "http";
59        m_supportedSchemes[1] = "https";
60        m_supportedSchemes[2] = "file";
61    }
62
63protected:
64    virtual void SetUp()
65    {
66        m_helper.initialize();
67    }
68
69    virtual void TearDown()
70    {
71        Platform::current()->unitTestSupport()->unregisterAllMockedURLs();
72    }
73
74    void registerMockedURLLoad(const std::string& url, const WebString& fileName)
75    {
76        URLTestHelpers::registerMockedURLLoad(toKURL(url), fileName, WebString::fromUTF8("pageserialization/"), WebString::fromUTF8("text/html"));
77    }
78
79    void loadURLInTopFrame(const WebURL& url)
80    {
81        FrameTestHelpers::loadFrame(m_helper.webView()->mainFrame(), url.string().utf8());
82    }
83
84    static bool webVectorContains(const WebVector<WebURL>& vector, const char* url)
85    {
86        return vector.contains(WebURL(toKURL(std::string(url))));
87    }
88
89    // Useful for debugging.
90    static void printWebURLs(const WebVector<WebURL>& urls)
91    {
92        for (size_t i = 0; i < urls.size(); i++)
93            printf("%s\n", urls[i].spec().data());
94    }
95
96    WebView* webView() const { return m_helper.webView(); }
97
98    WebVector<WebCString> m_supportedSchemes;
99
100private:
101    FrameTestHelpers::WebViewHelper m_helper;
102};
103
104TEST_F(WebPageSerializerTest, HTMLNodes)
105{
106    // Register the mocked frame and load it.
107    WebURL topFrameURL = toKURL("http://www.test.com");
108    registerMockedURLLoad("http://www.test.com", WebString::fromUTF8("simple_page.html"));
109    registerMockedURLLoad("http://www.example.com/beautifull.css", WebString::fromUTF8("beautifull.css"));
110    loadURLInTopFrame(topFrameURL);
111
112    // Retrieve all resources.
113    WebVector<WebURL> frames;
114    WebVector<WebURL> resources;
115    ASSERT_TRUE(WebPageSerializer::retrieveAllResources(
116        webView(), m_supportedSchemes, &resources, &frames));
117
118    // Tests that all resources from the frame have been retrieved.
119    EXPECT_EQ(1U, frames.size()); // There should be no duplicates.
120    EXPECT_TRUE(webVectorContains(frames, "http://www.test.com"));
121
122    EXPECT_EQ(14U, resources.size()); // There should be no duplicates.
123    EXPECT_TRUE(webVectorContains(resources, "http://www.example.com/beautifull.css"));
124    EXPECT_TRUE(webVectorContains(resources, "http://www.test.com/awesome.js"));
125    EXPECT_TRUE(webVectorContains(resources, "http://www.test.com/bodyBackground.jpg"));
126    EXPECT_TRUE(webVectorContains(resources, "http://www.test.com/awesome.png"));
127    EXPECT_TRUE(webVectorContains(resources, "http://www.test.com/imageButton.png"));
128    EXPECT_TRUE(webVectorContains(resources, "http://www.test.com/tableBackground.png"));
129    EXPECT_TRUE(webVectorContains(resources, "http://www.test.com/trBackground.png"));
130    EXPECT_TRUE(webVectorContains(resources, "http://www.test.com/tdBackground.png"));
131    EXPECT_TRUE(webVectorContains(resources, "http://www.evene.fr/citations/auteur.php?ida=46"));
132    EXPECT_TRUE(webVectorContains(resources, "http://www.brainyquote.com/quotes/authors/c/charles_darwin.html"));
133    EXPECT_TRUE(webVectorContains(resources, "http://www.test.com/why_deleted.html"));
134    EXPECT_TRUE(webVectorContains(resources, "http://www.test.com/why_inserted.html"));
135    EXPECT_TRUE(webVectorContains(resources, "https://www.secure.com/https.gif"));
136    EXPECT_TRUE(webVectorContains(resources, "file://c/my_folder/file.gif"));
137}
138
139TEST_F(WebPageSerializerTest, MultipleFrames)
140{
141    // Register the mocked frames.
142    WebURL topFrameURL = toKURL("http://www.test.com");
143    registerMockedURLLoad("http://www.test.com", WebString::fromUTF8("top_frame.html"));
144    registerMockedURLLoad("http://www.test.com/simple_iframe.html",
145                          WebString::fromUTF8("simple_iframe.html"));
146    registerMockedURLLoad("http://www.test.com/object_iframe.html",
147                          WebString::fromUTF8("object_iframe.html"));
148    registerMockedURLLoad("http://www.test.com/embed_iframe.html",
149                          WebString::fromUTF8("embed_iframe.html"));
150    // If we don't register a mocked resource for awesome.png, it causes the
151    // document loader of the iframe that has it as its src to assert on close,
152    // not sure why.
153    registerMockedURLLoad("http://www.test.com/awesome.png",
154                          WebString::fromUTF8("awesome.png"));
155
156    loadURLInTopFrame(topFrameURL);
157
158    // Retrieve all resources.
159    WebVector<WebURL> frames;
160    WebVector<WebURL> resources;
161    ASSERT_TRUE(WebPageSerializer::retrieveAllResources(
162        webView(), m_supportedSchemes, &resources, &frames));
163
164    // Tests that all resources from the frame have been retrieved.
165    EXPECT_EQ(4U, frames.size()); // There should be no duplicates.
166    EXPECT_TRUE(webVectorContains(frames, "http://www.test.com"));
167    EXPECT_TRUE(webVectorContains(frames, "http://www.test.com/simple_iframe.html"));
168    EXPECT_TRUE(webVectorContains(frames, "http://www.test.com/object_iframe.html"));
169    EXPECT_TRUE(webVectorContains(frames, "http://www.test.com/embed_iframe.html"));
170
171    EXPECT_EQ(5U, resources.size()); // There should be no duplicates.
172    EXPECT_TRUE(webVectorContains(resources, "http://www.test.com/awesome.png"));
173    EXPECT_TRUE(webVectorContains(resources, "http://www.test.com/innerFrame.png"));
174    EXPECT_TRUE(webVectorContains(resources, "http://www.test.com/flash.swf"));
175    // FIXME: for some reason the following resources is missing on one of the bot
176    //        causing the test to fail. Probably a plugin issue.
177    // EXPECT_TRUE(webVectorContains(resources, "http://www.test.com/music.mid"));
178    EXPECT_TRUE(webVectorContains(resources, "http://www.test.com/object.png"));
179    EXPECT_TRUE(webVectorContains(resources, "http://www.test.com/embed.png"));
180}
181
182}
183