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/dom/Document.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 #include "web/tests/URLTestHelpers.h" 46 47 #include <gtest/gtest.h> 48 49 using namespace blink; 50 using WebCore::Document; 51 using blink::URLTestHelpers::toKURL; 52 53 namespace { 54 55 class WebPageSerializerTest : public testing::Test { 56 public: 57 WebPageSerializerTest() : m_supportedSchemes(static_cast<size_t>(3)) 58 { 59 m_supportedSchemes[0] = "http"; 60 m_supportedSchemes[1] = "https"; 61 m_supportedSchemes[2] = "file"; 62 } 63 64 protected: 65 virtual void SetUp() 66 { 67 m_helper.initialize(); 68 } 69 70 virtual void TearDown() 71 { 72 Platform::current()->unitTestSupport()->unregisterAllMockedURLs(); 73 } 74 75 void registerMockedURLLoad(const std::string& url, const WebString& fileName) 76 { 77 URLTestHelpers::registerMockedURLLoad(toKURL(url), fileName, WebString::fromUTF8("pageserialization/"), WebString::fromUTF8("text/html")); 78 } 79 80 void loadURLInTopFrame(const WebURL& url) 81 { 82 FrameTestHelpers::loadFrame(m_helper.webView()->mainFrame(), url.string().utf8()); 83 } 84 85 static bool webVectorContains(const WebVector<WebURL>& vector, const char* url) 86 { 87 return vector.contains(WebURL(toKURL(std::string(url)))); 88 } 89 90 // Useful for debugging. 91 static void printWebURLs(const WebVector<WebURL>& urls) 92 { 93 for (size_t i = 0; i < urls.size(); i++) 94 printf("%s\n", urls[i].spec().data()); 95 } 96 97 WebView* webView() const { return m_helper.webView(); } 98 99 WebVector<WebCString> m_supportedSchemes; 100 101 private: 102 FrameTestHelpers::WebViewHelper m_helper; 103 }; 104 105 TEST_F(WebPageSerializerTest, HTMLNodes) 106 { 107 // Register the mocked frame and load it. 108 WebURL topFrameURL = toKURL("http://www.test.com"); 109 registerMockedURLLoad("http://www.test.com", WebString::fromUTF8("simple_page.html")); 110 registerMockedURLLoad("http://www.example.com/beautifull.css", WebString::fromUTF8("beautifull.css")); 111 loadURLInTopFrame(topFrameURL); 112 113 // Retrieve all resources. 114 WebVector<WebURL> frames; 115 WebVector<WebURL> resources; 116 ASSERT_TRUE(WebPageSerializer::retrieveAllResources( 117 webView(), m_supportedSchemes, &resources, &frames)); 118 119 // Tests that all resources from the frame have been retrieved. 120 EXPECT_EQ(1U, frames.size()); // There should be no duplicates. 121 EXPECT_TRUE(webVectorContains(frames, "http://www.test.com")); 122 123 EXPECT_EQ(14U, resources.size()); // There should be no duplicates. 124 EXPECT_TRUE(webVectorContains(resources, "http://www.example.com/beautifull.css")); 125 EXPECT_TRUE(webVectorContains(resources, "http://www.test.com/awesome.js")); 126 EXPECT_TRUE(webVectorContains(resources, "http://www.test.com/bodyBackground.jpg")); 127 EXPECT_TRUE(webVectorContains(resources, "http://www.test.com/awesome.png")); 128 EXPECT_TRUE(webVectorContains(resources, "http://www.test.com/imageButton.png")); 129 EXPECT_TRUE(webVectorContains(resources, "http://www.test.com/tableBackground.png")); 130 EXPECT_TRUE(webVectorContains(resources, "http://www.test.com/trBackground.png")); 131 EXPECT_TRUE(webVectorContains(resources, "http://www.test.com/tdBackground.png")); 132 EXPECT_TRUE(webVectorContains(resources, "http://www.evene.fr/citations/auteur.php?ida=46")); 133 EXPECT_TRUE(webVectorContains(resources, "http://www.brainyquote.com/quotes/authors/c/charles_darwin.html")); 134 EXPECT_TRUE(webVectorContains(resources, "http://www.test.com/why_deleted.html")); 135 EXPECT_TRUE(webVectorContains(resources, "http://www.test.com/why_inserted.html")); 136 EXPECT_TRUE(webVectorContains(resources, "https://www.secure.com/https.gif")); 137 EXPECT_TRUE(webVectorContains(resources, "file://c/my_folder/file.gif")); 138 } 139 140 TEST_F(WebPageSerializerTest, MultipleFrames) 141 { 142 // Register the mocked frames. 143 WebURL topFrameURL = toKURL("http://www.test.com"); 144 registerMockedURLLoad("http://www.test.com", WebString::fromUTF8("top_frame.html")); 145 registerMockedURLLoad("http://www.test.com/simple_iframe.html", 146 WebString::fromUTF8("simple_iframe.html")); 147 registerMockedURLLoad("http://www.test.com/object_iframe.html", 148 WebString::fromUTF8("object_iframe.html")); 149 registerMockedURLLoad("http://www.test.com/embed_iframe.html", 150 WebString::fromUTF8("embed_iframe.html")); 151 // If we don't register a mocked resource for awesome.png, it causes the 152 // document loader of the iframe that has it as its src to assert on close, 153 // not sure why. 154 registerMockedURLLoad("http://www.test.com/awesome.png", 155 WebString::fromUTF8("awesome.png")); 156 157 loadURLInTopFrame(topFrameURL); 158 159 // Retrieve all resources. 160 WebVector<WebURL> frames; 161 WebVector<WebURL> resources; 162 ASSERT_TRUE(WebPageSerializer::retrieveAllResources( 163 webView(), m_supportedSchemes, &resources, &frames)); 164 165 // Tests that all resources from the frame have been retrieved. 166 EXPECT_EQ(4U, frames.size()); // There should be no duplicates. 167 EXPECT_TRUE(webVectorContains(frames, "http://www.test.com")); 168 EXPECT_TRUE(webVectorContains(frames, "http://www.test.com/simple_iframe.html")); 169 EXPECT_TRUE(webVectorContains(frames, "http://www.test.com/object_iframe.html")); 170 EXPECT_TRUE(webVectorContains(frames, "http://www.test.com/embed_iframe.html")); 171 172 EXPECT_EQ(5U, resources.size()); // There should be no duplicates. 173 EXPECT_TRUE(webVectorContains(resources, "http://www.test.com/awesome.png")); 174 EXPECT_TRUE(webVectorContains(resources, "http://www.test.com/innerFrame.png")); 175 EXPECT_TRUE(webVectorContains(resources, "http://www.test.com/flash.swf")); 176 // FIXME: for some reason the following resources is missing on one of the bot 177 // causing the test to fail. Probably a plugin issue. 178 // EXPECT_TRUE(webVectorContains(resources, "http://www.test.com/music.mid")); 179 EXPECT_TRUE(webVectorContains(resources, "http://www.test.com/object.png")); 180 EXPECT_TRUE(webVectorContains(resources, "http://www.test.com/embed.png")); 181 } 182 183 } 184