📄 tagtest.java
字号:
// HTMLParser Library $Name: v1_6 $ - A java-based parser for HTML// http://sourceforge.org/projects/htmlparser// Copyright (C) 2004 Somik Raha//// Revision Control Information//// $Source: /cvsroot/htmlparser/htmlparser/src/org/htmlparser/tests/tagTests/TagTest.java,v $// $Author: derrickoswald $// $Date: 2004/09/02 02:28:14 $// $Revision: 1.62 $//// This library is free software; you can redistribute it and/or// modify it under the terms of the GNU Lesser General Public// License as published by the Free Software Foundation; either// version 2.1 of the License, or (at your option) any later version.//// This library is distributed in the hope that it will be useful,// but WITHOUT ANY WARRANTY; without even the implied warranty of// MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU// Lesser General Public License for more details.//// You should have received a copy of the GNU Lesser General Public// License along with this library; if not, write to the Free Software// Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA 02111-1307 USA//package org.htmlparser.tests.tagTests;import org.htmlparser.Attribute;import org.htmlparser.Node;import org.htmlparser.PrototypicalNodeFactory;import org.htmlparser.Tag;import org.htmlparser.Text;import org.htmlparser.tags.BodyTag;import org.htmlparser.tags.Div;import org.htmlparser.tags.Html;import org.htmlparser.tags.LinkTag;import org.htmlparser.tests.ParserTestCase;import org.htmlparser.util.NodeIterator;import org.htmlparser.util.ParserException;public class TagTest extends ParserTestCase{ static { System.setProperty ("org.htmlparser.tests.tagTests.TagTest", "TagTest"); } private static final boolean JSP_TESTS_ENABLED = false; public TagTest(String name) { super(name); } /** * The bug being reproduced is this : <BR> * <BODY aLink=#ff0000 bgColor=#ffffff link=#0000cc onload=setfocus() text=#000000 <BR> * vLink=#551a8b> * The above line is incorrectly parsed in that, the BODY tag is not identified. */ public void testBodyTagBug1() throws ParserException { String body = "<BODY aLink=#ff0000 bgColor=#ffffff link=#0000cc " + "onload=setfocus() text=#000000\nvLink=#551a8b>"; createParser(body); parseAndAssertNodeCount(1); // The node should be a body Tag assertTrue("Node should be a BodyTag",node[0] instanceof BodyTag); BodyTag tag = (BodyTag)node[0]; String text = tag.toHtml (); assertEquals("Contents of the tag",body + "</BODY>",text); } /** * The following should be identified as a tag : <BR> * <MYTAG abcd\n"+ * "efgh\n"+ * "ijkl\n"+ * "mnop> * Creation date: (6/17/2001 5:27:42 PM) */ public void testLargeTagBug() throws ParserException { String mytag = "MYTAG abcd\n"+ "efgh\n"+ "ijkl\n"+ "mnop"; createParser( "<" + mytag + ">" ); parseAndAssertNodeCount(1); // The node should be an Tag assertTrue("Node should be a Tag",node[0] instanceof Tag); Tag tag = (Tag)node[0]; assertEquals("Contents of the tag",mytag,tag.getText()); } /** * Bug reported by Gordon Deudney 2002-03-15 * Nested JSP Tags were not working */ public void testNestedTags() throws ParserException { if (JSP_TESTS_ENABLED) { String s = "input type=\"text\" value=\"<%=\"test\"%>\" name=\"text\""; String line = "<"+s+">"; createParser(line); parseAndAssertNodeCount(1); assertTrue("The node found should have been an Tag",node[0] instanceof Tag); Tag tag = (Tag) node[0]; assertEquals("Tag Contents",s,tag.getText()); } } /** * Test parseParameter method * Created by Kaarle Kaila (august 2001) * the tag name is here G */ public void testParseParameter3() throws ParserException { Tag tag; Node node=null; String lin1 = "<DIV class=\"userData\" id=\"oLayout\" name=\"oLayout\"></DIV>"; createParser(lin1); NodeIterator en = parser.elements(); try { if (en.hasMoreNodes()) { node = en.nextNode(); tag = (Tag)node; String classValue= tag.getAttribute ("CLASS"); assertEquals ("The class value should be ","userData",classValue); } } catch (ClassCastException ce) { fail("Bad class element = " + node.getClass().getName()); } } /** * Test parseParameter method * Created by Kaarle Kaila (august 2001) * the tag name is here A (and should be eaten up by linkScanner) */ public void testParseParameterA() throws ParserException { Tag tag; Tag etag; Text snode; Node node=null; String lin1 = "<A href=\"http://www.iki.fi/kaila\" myParameter yourParameter=\"Kaarle Kaaila\">Kaarle's homepage</A><p>Paragraph</p>"; createParser(lin1); NodeIterator en = parser.elements(); String a,href,myValue,nice; try { if (en.hasMoreNodes()) { node = en.nextNode(); tag = (Tag)node; a = ((Attribute)(tag.getAttributesEx ().elementAt (0))).getName (); href = tag.getAttribute ("HREF"); myValue = tag.getAttribute ("MYPARAMETER"); nice = tag.getAttribute ("YOURPARAMETER"); assertEquals ("Link tag (A)","A",a); assertEquals ("href value","http://www.iki.fi/kaila",href); assertEquals ("myparameter value",null,myValue); assertEquals ("yourparameter value","Kaarle Kaaila",nice); } if (!(node instanceof LinkTag)) { // linkscanner has eaten up this piece if ( en.hasMoreNodes()) { node = en.nextNode(); snode = (Text)node; assertEquals("Value of element","Kaarle's homepage",snode.getText()); } if (en.hasMoreNodes()) { node = en.nextNode(); etag = (Tag)node; assertEquals("endtag of link","/A", etag.getText()); } } // testing rest if (en.hasMoreNodes()) { node = en.nextNode(); tag = (Tag)node; assertEquals("following paragraph begins",tag.getText(),"p"); } if (en.hasMoreNodes()) { node = en.nextNode(); snode = (Text)node; assertEquals("paragraph contents","Paragraph",snode.getText()); } if (en.hasMoreNodes()) { node = en.nextNode(); etag = (Tag)node; assertEquals("paragrapg endtag","/p",etag.getText()); } } catch (ClassCastException ce) { fail("Bad class element = " + node.getClass().getName()); } } /** * Test parseParameter method * Created by Kaarle Kaila (august 2001) * the tag name is here G */ public void testParseParameterG() throws ParserException{ Tag tag; Tag etag; Text snode; Node node=null; String lin1 = "<G href=\"http://www.iki.fi/kaila\" myParameter yourParameter=\"Kaila\">Kaarle's homepage</G><p>Paragraph</p>"; createParser(lin1); NodeIterator en = parser.elements(); String a,href,myValue,nice; try { if (en.hasMoreNodes()) { node = en.nextNode(); tag = (Tag)node; a = ((Attribute)(tag.getAttributesEx ().elementAt (0))).getName (); href = tag.getAttribute ("HREF"); myValue = tag.getAttribute ("MYPARAMETER"); nice = tag.getAttribute ("YOURPARAMETER"); assertEquals ("The tagname should be G",a,"G"); assertEquals ("Check the http address",href,"http://www.iki.fi/kaila"); assertEquals ("myValue is not null",myValue,null); assertEquals ("The second parameter value",nice,"Kaila"); } if (en.hasMoreNodes()) { node = en.nextNode(); snode = (Text)node; assertEquals("The text of the element",snode.getText(),"Kaarle's homepage"); } if (en.hasMoreNodes()) { node = en.nextNode(); etag = (Tag)node; assertEquals("Endtag is G","/G", etag.getText()); } // testing rest if (en.hasMoreNodes()) { node = en.nextNode(); tag = (Tag)node; assertEquals("Follow up by p-tag","p", tag.getText()); } if (en.hasMoreNodes()) { node = en.nextNode(); snode = (Text)node; assertEquals("Verify the paragraph text","Paragraph", snode.getText()); } if (en.hasMoreNodes()) { node = en.nextNode(); etag = (Tag)node; assertEquals("Still patragraph endtag","/p", etag.getText()); } } catch (ClassCastException ce) { fail("Bad class element = " + node.getClass().getName()); } } /** * Test parseParameter method * Created by Kaarle Kaila (august 2002) * the tag name is here A (and should be eaten up by linkScanner) * Tests elements where = sign is surrounded by spaces */ public void testParseParameterSpace() throws ParserException{ Tag tag; Tag etag; Text snode; Node node=null; String lin1 = "<A yourParameter = \"Kaarle\">Kaarle's homepage</A>"; createParser(lin1); NodeIterator en = parser.elements(); String a,nice; try { if (en.hasMoreNodes()) { node = en.nextNode(); tag = (Tag)node; a = ((Attribute)(tag.getAttributesEx ().elementAt (0))).getName (); nice = tag.getAttribute ("YOURPARAMETER"); assertEquals ("Link tag (A)",a,"A"); assertEquals ("yourParameter value","Kaarle",nice); } if (!(node instanceof LinkTag)) { // linkscanner has eaten up this piece if ( en.hasMoreNodes()) { node = en.nextNode(); snode = (Text)node; assertEquals("Value of element","Kaarle's homepage",snode.getText()); } if (en.hasMoreNodes()) { node = en.nextNode(); etag = (Tag)node; assertEquals("Still patragraph endtag","/A",etag.getText()); } } // testing rest } catch (ClassCastException ce) { fail("Bad class element = " + node.getClass().getName()); } } /** * Reproduction of a bug reported by Annette Doyle * This is actually a pretty good example of dirty html - we are in a fix * here, bcos the font tag (the first one) has an erroneous inverted comma. In Tag, * we ignore anything in inverted commas, and dont if its outside. This kind of messes * up our parsing almost completely. */ public void testStrictParsing() throws ParserException { String testHTML = "<div align=\"center\">" + "<font face=\"Arial,\"helvetica,\" sans-serif=\"sans-serif\" size=\"2\" color=\"#FFFFFF\">" + "<a href=\"/index.html\" link=\"#000000\" vlink=\"#000000\"><font color=\"#FFFFFF\">Home</font></a>\n"+ "<a href=\"/cia/notices.html\" link=\"#000000\" vlink=\"#000000\"><font color=\"#FFFFFF\">Notices</font></a>\n"+ "<a href=\"/cia/notices.html#priv\" link=\"#000000\" vlink=\"#000000\"><font color=\"#FFFFFF\">Privacy</font></a>\n"+ "<a href=\"/cia/notices.html#sec\" link=\"#000000\" vlink=\"#000000\"><font color=\"#FFFFFF\">Security</font></a>\n"+ "<a href=\"/cia/contact.htm\" link=\"#000000\" vlink=\"#000000\"><font color=\"#FFFFFF\">Contact Us</font></a>\n"+ "<a href=\"/cia/sitemap.html\" link=\"#000000\" vlink=\"#000000\"><font color=\"#FFFFFF\">Site Map</font></a>\n"+ "<a href=\"/cia/siteindex.html\" link=\"#000000\" vlink=\"#000000\"><font color=\"#FFFFFF\">Index</font></a>\n"+ "<a href=\"/search\" link=\"#000000\" vlink=\"#000000\"><font color=\"#FFFFFF\">Search</font></a>\n"+ "</font>" +⌨️ 快捷键说明
复制代码
Ctrl + C
搜索代码
Ctrl + F
全屏模式
F11
切换主题
Ctrl + Shift + D
显示快捷键
?
增大字号
Ctrl + =
减小字号
Ctrl + -