" + "", "http://www.yahoo.com"); parser.registerScanners(); Node linkNodes[] = parser.extractAllNodesThatAre(LinkTag.class); assertEquals("number of links", 2, linkNodes.length); LinkTag linkTag = (LinkTag) linkNodes[0]; assertStringEquals( "Link", "http://www.yahoo.com/s/8741", linkTag.getLink()); // Verify the link data assertStringEquals("Link Text", "", linkTag.getLinkText()); // Verify the reconstruction html assertStringEquals( "toHTML", "", linkTag.toHtml()); } /** * Test case based on a report by Raghavender Srimantula, of the parser giving out of memory exceptions. Found to occur * on the following piece of html *

     * This is test
     * 
     * 

*/ public void testErroneousLinkBugFromYahoo() throws ParserException { createParser( "" + "" + "This is a test\n" + "" + "Yahoo! Movies" + "", "http://www.yahoo.com"); parser.registerScanners(); parseAndAssertNodeCount(2); // The first node should be a Tag assertTrue( "First node should be a HTMLLinkTag", node[0] instanceof LinkTag); // The second node should be a HTMLStringNode assertTrue( "Second node should be a HTMLLinkTag", node[1] instanceof LinkTag); LinkTag linkTag = (LinkTag) node[0]; assertEquals("Link", "http://www.yahoo.com/s/8741", linkTag.getLink()); // Verify the link data assertEquals("Link Text", "This is a test\r\n", linkTag.getLinkText()); // Verify the reconstruction html assertStringEquals( "toHTML()", "This is a test\r\n", linkTag.toHtml()); } public void testEvaluate() { LinkScanner scanner = new LinkScanner("-l"); boolean retVal = scanner.evaluate(" a href ", null); assertEquals( "Evaluation of the Link tag", new Boolean(true), new Boolean(retVal)); } /** * This is the reproduction of a bug which causes a null pointer exception */ public void testExtractLinkInvertedCommasBug() throws ParserException { String tagContents = "a href=r/anorth/top.html"; Tag tag = new Tag(new TagData(0, 0, tagContents, "")); String url = "c:\\cvs\\html\\binaries\\yahoo.htm"; LinkScanner scanner = new LinkScanner("-l"); assertEquals( "Extracted Link", "r/anorth/top.html", scanner.extractLink(tag, url)); } /** * This is the reproduction of a bug which produces multiple text copies. */ public void testExtractLinkInvertedCommasBug2() throws ParserException { createParser("Vancouver schools plan 'Great Northern Way'"); parser.addScanner(new LinkScanner("-l")); parseAndAssertNodeCount(1); assertTrue("The node should be a link tag", node[0] instanceof LinkTag); LinkTag linkTag = (LinkTag) node[0]; assertStringEquals( "Extracted Text", "Vancouver schools plan 'Great Northern Way'", linkTag.getLinkText()); } /** * Bug pointed out by Sam Joseph (sam@neurogrid.net) * Links with spaces in them will get their spaces absorbed */ public void testLinkSpacesBug() throws ParserException { createParser("Click Here"); parser.addScanner(new LinkScanner("-l")); parseAndAssertNodeCount(1); assertTrue("The node should be a link tag", node[0] instanceof LinkTag); LinkTag linkTag = (LinkTag) node[0]; assertEquals( "Link URL of link tag", "http://www.kizna.com/servlets/SomeServlet?name=Sam Joseph", linkTag.getLink()); assertEquals( "Link Text of link tag", "Click Here", linkTag.getLinkText()); } /** * Bug reported by Raj Sharma,5-Apr-2002, upon parsing * http://www.samachar.com, the entire page could not be picked up. * The problem was occurring after parsing a particular link * after which the parsing would not proceed. This link was spread over three lines. * The bug has been reproduced and fixed. */ public void testMultipleLineBug() throws ParserException { createParser( "

Tech Samachar: Journalism 3.0 by Rajesh Jain"); Parser.setLineSeparator("\r\n"); parser.addScanner(new LinkScanner("-l")); parseAndAssertNodeCount(8); assertTrue( "Seventh node should be a link tag", node[6] instanceof LinkTag); LinkTag linkTag = (LinkTag) node[6]; String exp = new String("http://ads.samachar.com/bin/redirect/tech.txt?http://www.samachar.com/technical.html"); //assertEquals("Length of link tag",exp.length(), linkTag.getLink().length()); assertStringEquals("Link URL of link tag", exp, linkTag.getLink()); assertEquals( "Link Text of link tag", " Journalism 3.0", linkTag.getLinkText()); assertTrue( "Eight node should be a string node", node[7] instanceof StringNode); StringNode stringNode = (StringNode) node[7]; assertEquals( "String node contents", " by Rajesh Jain", stringNode.getText()); } public void testRelativeLinkScan() throws ParserException { createParser( " Hello World", "http://www.yahoo.com"); // Register the image scanner parser.addScanner(new LinkScanner("-l")); parseAndAssertNodeCount(1); assertTrue( "Node identified should be HTMLLinkTag", node[0] instanceof LinkTag); LinkTag linkTag = (LinkTag) node[0]; assertEquals( "Expected Link", "http://www.yahoo.com/mytest.html", linkTag.getLink()); } public void testRelativeLinkScan2() throws ParserException { createParser( " Hello World", "http://www.yahoo.com"); // Register the image scanner parser.addScanner(new LinkScanner("-l")); parseAndAssertNodeCount(1); assertTrue( "Node identified should be HTMLLinkTag", node[0] instanceof LinkTag); LinkTag linkTag = (LinkTag) node[0]; assertStringEquals( "Expected Link", "http://www.yahoo.com/abc/def/mytest.html", linkTag.getLink()); } public void testRelativeLinkScan3() throws ParserException { createParser( " Hello World", "http://www.yahoo.com/ghi"); // Register the image scanner parser.addScanner(new LinkScanner("-l")); parseAndAssertNodeCount(1); assertTrue( "Node identified should be HTMLLinkTag", node[0] instanceof LinkTag); LinkTag linkTag = (LinkTag) node[0]; assertStringEquals( "Expected Link", "http://www.yahoo.com/abc/def/mytest.html", linkTag.getLink()); } /** * Test scan with data which is of diff nodes type */ public void testScan() throws ParserException { createParser( "Hello World", "http://www.yahoo.com"); // Register the image scanner LinkScanner linkScanner = new LinkScanner("-l"); parser.addScanner(linkScanner); parser.addScanner(linkScanner.createImageScanner("-i")); parseAndAssertNodeCount(1); assertTrue("Node should be a link node", node[0] instanceof LinkTag); LinkTag linkTag = (LinkTag) node[0]; // Get the link data and cross-check Node[] dataNode = new Node[10]; int i = 0; for (SimpleNodeIterator e = linkTag.children(); e.hasMoreNodes();) { dataNode[i++] = (Node) e.nextNode(); } assertEquals("Number of data nodes", new Integer(2), new Integer(i)); assertTrue( "First data node should be an Image Node", dataNode[0] instanceof ImageTag); assertTrue( "Second data node shouls be a String Node", dataNode[1] instanceof StringNode); // Check the contents of each data node ImageTag imageTag = (ImageTag) dataNode[0]; assertEquals( "Image URL", "http://www.yahoo.com/abcd.jpg", imageTag.getImageURL()); StringNode stringNode = (StringNode) dataNode[1]; assertEquals("String Contents", "Hello World", stringNode.getText()); } public void testReplaceFaultyTagWithEndTag() throws ParserException { String currentLine = "

Site Comments?
Mail Us

"; Tag tag = new Tag(new TagData(85, 87, "a", currentLine)); LinkScanner linkScanner = new LinkScanner(); String newLine = linkScanner.replaceFaultyTagWithEndTag(tag, currentLine); assertEquals( "Expected replacement", "

Site Comments?
Mail Us

", newLine); } public void testInsertEndTagBeforeTag() throws ParserException { String currentLine = "Yahoo! Movies"; Tag tag = new Tag(new TagData(0, 14, "a href=s/7509", currentLine)); LinkScanner linkScanner = new LinkScanner(); String newLine = linkScanner.insertEndTagBeforeNode(tag, currentLine); assertEquals( "Expected insertion", "Yahoo! Movies", newLine); } /** * A bug in the freshmeat page - really bad html * tag - <A>Revision<\a> * Reported by Mazlan Mat */ public void testFreshMeatBug() throws ParserException { createParser("Revision", "http://www.yahoo.com"); // Register the image scanner parser.addScanner(new LinkScanner("-l")); parseAndAssertNodeCount(3); assertTrue("Node 0 should be a tag", node[0] instanceof Tag); Tag tag = (Tag) node[0]; assertEquals("Tag Contents", "a", tag.getText()); assertTrue( "Node 1 should be a string node", node[1] instanceof StringNode); StringNode stringNode = (StringNode) node[1]; assertEquals("StringNode Contents", "Revision", stringNode.getText()); assertTrue("Node 2 should be a string node", node[2] instanceof EndTag); EndTag endTag = (EndTag) node[2]; assertEquals("End Tag Contents", "a", endTag.getText()); } /** * Test suggested by Cedric Rosa * A really bad link tag sends parser into infinite loop */ public void testBrokenLink() throws ParserException { createParser( "" + "
\n" + "", "http://www.yahoo.com"); // Register the image scanner parser.addScanner(new LinkScanner("-l")); parseAndAssertNodeCount(1); assertTrue("Node 0 should be a link tag", node[0] instanceof LinkTag); LinkTag linkTag = (LinkTag) node[0]; assertNotNull(linkTag.toString()); } public void testLinkDataContents() throws ParserException { createParser( "", "http://transfer.go.com"); // Register the image scanner LinkScanner linkScanner = new LinkScanner("-l"); parser.addScanner(linkScanner); parser.addScanner(linkScanner.createImageScanner("-i")); parseAndAssertNodeCount(1); assertTrue("Node 0 should be a link tag", node[0] instanceof LinkTag); LinkTag linkTag = (LinkTag) node[0]; assertEquals( "Link URL", "http://transfer.go.com/cgi/atransfer.pl?goto=http://www.signs.movies.com&name=114332&srvc=nws&context=283&guid=4AD5723D-C802-4310-A388-0B24E1A79689", linkTag.getLink()); assertEquals("Link Text", "", linkTag.getLinkText()); Node[] containedNodes = new Node[10]; int i = 0; for (SimpleNodeIterator e = linkTag.children(); e.hasMoreNodes();) { containedNodes[i++] = e.nextNode(); } assertEquals("There should be 5 contained nodes in the link tag", 5, i); assertTrue( "First contained node should be an image tag", containedNodes[0] instanceof ImageTag); ImageTag imageTag = (ImageTag) containedNodes[0]; assertEquals( "Image Location", "http://ad.abcnews.com/ad/sponsors/buena_vista_pictures/bvpi-ban0003.gif", imageTag.getImageURL()); assertEquals("Image Height", "60", imageTag.getAttribute("HEIGHT")); assertEquals("Image Width", "468", imageTag.getAttribute("WIDTH")); assertEquals("Image Border", "0", imageTag.getAttribute("BORDER")); assertEquals( "Image Alt", "See Signs in Theaters 8-2 - Starring Mel Gibson", imageTag.getAttribute("ALT")); assertTrue( "Second contained node should be Tag", containedNodes[1] instanceof Tag); Tag tag1 = (Tag) containedNodes[1]; assertEquals( "Tag Contents", "font face=\"verdana,arial,helvetica\" SIZE=\"1\"", tag1.getText()); assertTrue( "Third contained node should be Tag", containedNodes[2] instanceof Tag); Tag tag2 = (Tag) containedNodes[2]; assertEquals("Tag Contents", "b", tag2.getText()); assertTrue( "Fourth contained node should be HTMLEndTag", containedNodes[3] instanceof EndTag); EndTag endTag1 = (EndTag) containedNodes[3]; assertEquals("Fourth Tag contents", "b", endTag1.getText()); assertTrue( "Fifth contained node should be HTMLEndTag", containedNodes[4] instanceof EndTag); EndTag endTag2 = (EndTag) containedNodes[4]; assertEquals("Fifth Tag contents", "font", endTag2.getText()); } public void testBaseRefLink() throws ParserException { createParser( "\n" + "\n" + "\n" + "\n" + "Home\n" + "...\n" + "", "http://transfer.go.com"); // Register the image scanner parser.registerScanners(); parseAndAssertNodeCount(7); assertTrue("Node 4 should be a link tag", node[4] instanceof LinkTag); LinkTag linkTag = (LinkTag) node[4]; assertEquals( "Resolved Link", "http://www.abc.com/home.cfm", linkTag.getLink()); assertEquals("Resolved Link Text", "Home", linkTag.getLinkText()); } /** * This is a reproduction of bug 617228, reported by * Stephen J. Harrington. When faced with a link like : * <A * HREF="/cgi-bin/view_search?query_text=postdate>20020701&txt_clr=White&bg_clr=Red&url=http://loc * al * host/Testing/Report * 1.html">20020702 Report 1</A> * * parser is unable to handle the link correctly due to the greater than * symbol being confused to be the end of the tag. */ public void testQueryLink() throws ParserException { createParser( "20020701&txt_clr=White&bg_clr=Red&url=http://localhost/Testing/Report1.html\">20020702 Report 1", "http://transfer.go.com"); // Register the image scanner parser.registerScanners(); parseAndAssertNodeCount(1); assertTrue("Node 1 should be a link tag", node[0] instanceof LinkTag); LinkTag linkTag = (LinkTag) node[0]; assertStringEquals( "Resolved Link", "http://transfer.go.com/cgi-bin/view_search?query_text=postdate>20020701&txt_clr=White&bg_clr=Red&url=http://localhost/Testing/Report1.html", linkTag.getLink()); assertEquals( "Resolved Link Text", "20020702 Report 1", linkTag.getLinkText()); } public void testNotMailtoLink() throws ParserException { createParser( "not@for.real", "http://www.cj.com/"); parser.addScanner(new LinkScanner("-l")); parseAndAssertNodeCount(1); assertTrue("Node should be a HTMLLinkTag", node[0] instanceof LinkTag); LinkTag linkTag = (LinkTag) node[0]; assertEquals( "Link Plain Text", "not@for.real", linkTag.toPlainTextString()); assertTrue("Link is not a mail link", !linkTag.isMailLink()); } public void testMailtoLink() throws ParserException { createParser( "this@is.real", "http://www.cj.com/"); parser.addScanner(new LinkScanner("-l")); parseAndAssertNodeCount(1); assertTrue("Node should be a HTMLLinkTag", node[0] instanceof LinkTag); LinkTag linkTag = (LinkTag) node[0]; assertEquals( "Link Plain Text", "this@is.real", linkTag.toPlainTextString()); assertTrue("Link is a mail link", linkTag.isMailLink()); } public void testJavascriptLink() throws ParserException { createParser( "say hello", "http://www.cj.com/"); parser.addScanner(new LinkScanner("-l")); parseAndAssertNodeCount(1); assertTrue("Node should be a HTMLLinkTag", node[0] instanceof LinkTag); LinkTag linkTag = (LinkTag) node[0]; assertEquals( "Link Plain Text", "say hello", linkTag.toPlainTextString()); assertTrue("Link is a Javascript command", linkTag.isJavascriptLink()); } public void testNotJavascriptLink() throws ParserException { createParser( "say hello", "http://www.cj.com/"); parser.addScanner(new LinkScanner("-l")); parseAndAssertNodeCount(1); assertTrue("Node should be a HTMLLinkTag", node[0] instanceof LinkTag); LinkTag linkTag = (LinkTag) node[0]; assertEquals( "Link Plain Text", "say hello", linkTag.toPlainTextString()); assertTrue( "Link is not a Javascript command", !linkTag.isJavascriptLink()); } public void testFTPLink() throws ParserException { createParser( "my ftp", "http://www.cj.com/"); parser.addScanner(new LinkScanner("-l")); parseAndAssertNodeCount(1); assertTrue("Node should be a HTMLLinkTag", node[0] instanceof LinkTag); LinkTag linkTag = (LinkTag) node[0]; assertEquals("Link Plain Text", "my ftp", linkTag.toPlainTextString()); assertTrue("Link is a FTP site", linkTag.isFTPLink()); } public void testNotFTPLink() throws ParserException { createParser("my ftp", "http://www.cj.com/"); parser.addScanner(new LinkScanner("-l")); parseAndAssertNodeCount(1); assertTrue("Node should be a HTMLLinkTag", node[0] instanceof LinkTag); LinkTag linkTag = (LinkTag) node[0]; assertEquals("Link Plain Text", "my ftp", linkTag.toPlainTextString()); assertTrue("Link is not a FTP site", !linkTag.isFTPLink()); } public void testRelativeLinkNotHTMLBug() throws ParserException { createParser( "New Page", "http://www.mysite.com/books/some.asp"); parser.addScanner(new LinkScanner("-l")); parseAndAssertNodeCount(1); assertTrue("Node should be a HTMLLinkTag", node[0] instanceof LinkTag); LinkTag linkTag = (LinkTag) node[0]; assertEquals( "Link", "http://www.mysite.com/books/newpage.html", linkTag.getLink()); } public void testBadImageInLinkBug() throws ParserException { createParser( "", "http://www.fedpage.com/Event.asp?EventID=1272"); parser.registerScanners(); parseAndAssertNodeCount(1); assertTrue("Node should be a HTMLLinkTag", node[0] instanceof LinkTag); LinkTag linkTag = (LinkTag) node[0]; // Get the image tag from the link Node insideNodes[] = new Node[10]; int j = 0; for (SimpleNodeIterator e = linkTag.children(); e.hasMoreNodes();) { insideNodes[j++] = (Node) e.nextNode(); } assertEquals("Number of contained internal nodes", 1, j); assertTrue(insideNodes[0] instanceof ImageTag); ImageTag imageTag = (ImageTag) insideNodes[0]; assertEquals( "Image Tag Location", "http://www.fedpage.com/images\\register.gif", imageTag.getImageURL()); } /** * This is an attempt to reproduce bug 677874 * reported by James Moliere. A link tag of the form * * Shoe bomber handed life sentence * * is not parsed correctly. The second '=' sign in the link causes * the parser to treat it as a seperate attribute */ public void testLinkContainsEqualTo() throws Exception { createParser( "Shoe bomber handed life sentence"); parser.registerScanners(); parseAndAssertNodeCount(1); assertType("node type", LinkTag.class, node[0]); LinkTag linkTag = (LinkTag) node[0]; assertStringEquals( "link text", "Shoe bomber handed life sentence", linkTag.getLinkText()); assertStringEquals( "link url", "/news/866201.asp?0sl=-32", linkTag.getLink()); } /** * Bug report by Cory Seefurth * @throws Exception */ public void _testLinkWithJSP() throws Exception { createParser( "/literature/index.htm\">Literature"); parser.registerScanners(); parseAndAssertNodeCount(1); assertType("should be link tag", LinkTag.class, node[0]); LinkTag linkTag = (LinkTag) node[0]; assertStringEquals( "expected link", "<%=Application(\"sURL\")%>/literature/index.htm", linkTag.getLink()); } public void testLinkScannerFilter() throws Exception { LinkScanner linkScanner = new LinkScanner(LinkTag.LINK_TAG_FILTER); assertEquals( "linkscanner filter", LinkTag.LINK_TAG_FILTER, linkScanner.getFilter()); } public void testTagSymbolsInLinkText() throws Exception { createParser( "<< An Empire Reborn: Chapter 2 <<"); parser.registerScanners(); parseAndAssertNodeCount(1); assertType("node", LinkTag.class, node[0]); LinkTag linkTag = (LinkTag) node[0]; assertEquals( "link text", "<< An Empire Reborn: Chapter 2 <<", linkTag.getLinkText()); } }

What this is This file is included in the DevDaily.com "Java Source Code Warehouse" project. The intent of this project is to help you "Learn Java by Example" TM. Other links  The search page  Other source code files at this package level  Click here to learn more about this project The source code // $Header: /home/cvs/jakarta-jmeter/src/htmlparser/org/htmlparser/tests/scannersTests/LinkScannerTest.java,v 1.2 2004/02/11 02:16:58 woolfel Exp $ /* * ==================================================================== * Copyright 2002-2004 The Apache Software Foundation. * * Licensed under the Apache License, Version 2.0 (the "License"); * you may not use this file except in compliance with the License. * You may obtain a copy of the License at * * http://www.apache.org/licenses/LICENSE-2.0 * * Unless required by applicable law or agreed to in writing, software * distributed under the License is distributed on an "AS IS" BASIS, * WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied. * See the License for the specific language governing permissions and * limitations under the License. * */ // The developers of JMeter and Apache are greatful to the developers // of HTMLParser for giving Apache Software Foundation a non-exclusive // license. The performance benefits of HTMLParser are clear and the // users of JMeter will benefit from the hard work the HTMLParser // team. For detailed information about HTMLParser, the project is // hosted on sourceforge at http://htmlparser.sourceforge.net/. // // HTMLParser was originally created by Somik Raha in 2000. Since then // a healthy community of users has formed and helped refine the // design so that it is able to tackle the difficult task of parsing // dirty HTML. Derrick Oswald is the current lead developer and was kind // enough to assist JMeter. package org.htmlparser.tests.scannersTests; import org.htmlparser.Node; import org.htmlparser.Parser; import org.htmlparser.StringNode; import org.htmlparser.scanners.LinkScanner; import org.htmlparser.tags.EndTag; import org.htmlparser.tags.ImageTag; import org.htmlparser.tags.LinkTag; import org.htmlparser.tags.Tag; import org.htmlparser.tags.data.TagData; import org.htmlparser.tests.ParserTestCase; import org.htmlparser.util.ParserException; import org.htmlparser.util.SimpleNodeIterator; public class LinkScannerTest extends ParserTestCase { public LinkScannerTest(String name) { super(name); } public void testAccessKey() throws ParserException { createParser("Click Here"); parser.addScanner(new LinkScanner("-l")); parseAndAssertNodeCount(1); assertTrue("The node should be a link tag", node[0] instanceof LinkTag); LinkTag linkTag = (LinkTag) node[0]; assertEquals( "Link URL of link tag", "http://www.kizna.com/servlets/SomeServlet?name=Sam Joseph", linkTag.getLink()); assertEquals( "Link Text of link tag", "Click Here", linkTag.getLinkText()); assertEquals("Access key", "1", linkTag.getAccessKey()); } public void testErroneousLinkBug() throws ParserException { createParser( " Site Comments? " + "" + "Mail Us" + "" + " "); parser.registerScanners(); parseAndAssertNodeCount(6); // The first node should be a Tag assertTrue("First node should be a Tag", node[0] instanceof Tag); // The second node should be a HTMLStringNode assertTrue( "Second node should be a HTMLStringNode", node[1] instanceof StringNode); StringNode stringNode = (StringNode) node[1]; assertEquals( "Text of the StringNode", "Site Comments?", stringNode.getText()); assertTrue("Third node should be a tag", node[2] instanceof Tag); } /** * Test case based on a report by Raghavender Srimantula, of the parser giving out of memory exceptions. Found to occur * on the following piece of html * *

* * */ public void testErroneousLinkBugFromYahoo2() throws ParserException { createParser( "

" + "" + "" + "

\n" + "Yahoo! Movies" + "

... this post is sponsored by my books ...
#1 New Release!	FP Best Seller

 

new blog posts