Thread: [Htmlparser-cvs] htmlparser/src/org/htmlparser/tests/scannersTests LabelScannerTest.java,1.17,1.18
Brought to you by:
derrickoswald
From: <der...@us...> - 2003-05-10 01:22:28
|
Update of /cvsroot/htmlparser/htmlparser/src/org/htmlparser/tests/scannersTests In directory sc8-pr-cvs1:/tmp/cvs-serv13750/org/htmlparser/tests/scannersTests Modified Files: LabelScannerTest.java Log Message: For Dhaval: New Test case. I added the LabelScanner to the parser and parsed. Strangely instead of returning node count as 13(number of LABEL tags) I get 17. Also when I see output of every node (using toHtml()), uptil "Microsoft Passport" everything is correct and I am getting LABEL tags as well. But the next node that I get is a String node with value as #alue="AOL"># (without the hash) and that entire tag got messed up. Any ideas. I have attached test file for that purpose. U'll also have to use the new LabelScanner.java file. Its quite strange. Index: LabelScannerTest.java =================================================================== RCS file: /cvsroot/htmlparser/htmlparser/src/org/htmlparser/tests/scannersTests/LabelScannerTest.java,v retrieving revision 1.17 retrieving revision 1.18 diff -C2 -d -r1.17 -r1.18 *** LabelScannerTest.java 10 May 2003 01:14:59 -0000 1.17 --- LabelScannerTest.java 10 May 2003 01:22:24 -0000 1.18 *************** *** 117,121 **** public void testNestedLabels() throws ParserException { ! createParser("<label>John Doe<label>Jane Doe</label>"); parser.registerScanners(); LabelScanner labelScanner = new LabelScanner("-l"); --- 117,121 ---- public void testNestedLabels() throws ParserException { ! createParser("<label id=\"attr1\"><label>Jane Doe"); parser.registerScanners(); LabelScanner labelScanner = new LabelScanner("-l"); *************** *** 126,130 **** LabelTag labelTag = (LabelTag) node[0]; ! assertStringEquals("Label","<LABEL>John Doe</LABEL>",labelTag.toHtml()); labelTag = (LabelTag) node[1]; assertStringEquals("Label","<LABEL>Jane Doe</LABEL>",labelTag.toHtml()); --- 126,130 ---- LabelTag labelTag = (LabelTag) node[0]; ! assertStringEquals("Label","<LABEL ID=\"attr1\" ></LABEL>",labelTag.toHtml()); labelTag = (LabelTag) node[1]; assertStringEquals("Label","<LABEL>Jane Doe</LABEL>",labelTag.toHtml()); *************** *** 132,135 **** --- 132,193 ---- assertNull("ID",attr.get("id")); } + + public void testNestedLabels2() throws ParserException { + String testHTML = new String( + "<LABEL value=\"Google Search\">Google</LABEL>" + + "<LABEL value=\"AltaVista Search\">AltaVista" + + "<LABEL value=\"Lycos Search\"></LABEL>" + + "<LABEL>Yahoo!</LABEL>" + + "<LABEL>\nHotmail</LABEL>" + + "<LABEL value=\"ICQ Messenger\">" + + "<LABEL>Mailcity\n</LABEL>"+ + "<LABEL>\nIndiatimes\n</LABEL>"+ + "<LABEL>\nRediff\n</LABEL>\n"+ + "<LABEL>Cricinfo" + + "<LABEL value=\"Microsoft Passport\">" + + "<LABEL value=\"AOL\"><SPAN>AOL</SPAN></LABEL>" + + "<LABEL value=\"Time Warner\">Time <B>Warner <SPAN>AOL </SPAN>Inc.</B>" + ); + createParser(testHTML); + //parser.registerScanners(); + LabelScanner labelScanner = new LabelScanner("-l"); + parser.addScanner(labelScanner); + parseAndAssertNodeCount(13); + + for(int j=0;j<nodeCount;j++) + { + //assertTrue("Node " + j + " should be Label Tag",node[j] instanceof LabelTag); + System.out.println(node[j].getClass().getName()); + System.out.println(node[j].toHtml()); + } + + LabelTag LabelTag; + LabelTag = (LabelTag) node[0]; + assertStringEquals("HTML String","<LABEL VALUE=\"Google Search\">Google</LABEL>",LabelTag.toHtml()); + LabelTag = (LabelTag) node[1]; + assertStringEquals("HTML String","<LABEL VALUE=\"AltaVista Search\">AltaVista</LABEL>",LabelTag.toHtml()); + LabelTag = (LabelTag) node[2]; + assertStringEquals("HTML String","<LABEL VALUE=\"Lycos Search\"></LABEL>",LabelTag.toHtml()); + LabelTag = (LabelTag) node[3]; + assertStringEquals("HTML String","<LABEL>Yahoo!</LABEL>",LabelTag.toHtml()); + LabelTag = (LabelTag) node[4]; + assertStringEquals("HTML String","<LABEL>\r\nHotmail</LABEL>",LabelTag.toHtml()); + LabelTag = (LabelTag) node[5]; + assertStringEquals("HTML String","<LABEL VALUE=\"ICQ Messenger\"></LABEL>",LabelTag.toHtml()); + LabelTag = (LabelTag) node[6]; + assertStringEquals("HTML String","<LABEL>Mailcity\r\n</LABEL>",LabelTag.toHtml()); + LabelTag = (LabelTag) node[7]; + assertStringEquals("HTML String","<LABEL>\r\nIndiatimes\r\n</LABEL>",LabelTag.toHtml()); + LabelTag = (LabelTag) node[8]; + assertStringEquals("HTML String","<LABEL>\r\nRediff\r\n</LABEL>",LabelTag.toHtml()); + LabelTag = (LabelTag) node[9]; + assertStringEquals("HTML String","<LABEL>Cricinfo</LABEL>",LabelTag.toHtml()); + LabelTag = (LabelTag) node[10]; + assertStringEquals("HTML String","<LABEL VALUE=\"Microsoft Passport\"></LABEL>",LabelTag.toHtml()); + LabelTag = (LabelTag) node[11]; + assertStringEquals("HTML String","<LABEL VALUE=\"AOL\"><SPAN>AOL</SPAN></LABEL>",LabelTag.toHtml()); + LabelTag = (LabelTag) node[12]; + assertStringEquals("HTML String","<LABEL value=\"Time Warner\">Time <B>Warner <SPAN>AOL </SPAN>Inc.</B>",LabelTag.toHtml()); + } public static TestSuite suite() { |