third_party/WebKit/Source/web/tests/WebPageSerializerTest.cpp

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