[Htmlparser-cvs] htmlparser/src/org/htmlparser/tests ParserTest.java,1.51,1.52
Brought to you by:
derrickoswald
Menu
▾
▴
[Htmlparser-cvs] htmlparser/src/org/htmlparser/tests ParserTest.java,1.51,1.52
|
From: <der...@us...> - 2004-01-02 05:01:32
|
Update of /cvsroot/htmlparser/htmlparser/src/org/htmlparser/tests
In directory sc8-pr-cvs1:/tmp/cvs-serv27740
Modified Files:
ParserTest.java
Log Message:
Added testcases but was unable to reproduce the following bugs in the version 1.4 codebase:
839264 toHtml() parse error in Javascripts with "form" keyword
833592 DOCTYPE element is not parsed correctly
826764 ParserException occurs only when using setInputHTML() instea
825820 Words conjoined
825645 <input> not getting parsed inside table
813838 links not parsed correctly
and
#851882 zero length alt tag causes bug in ImageScanner
#832530 empty attribute causes parser to fail
#805598 attribute src in tag img sometimes not correctly parsed
(these 3 are all the same bug, duplicates of the following):
#753012 IMG SRC not parsed v1.3 & v1.4
#755929 Empty string attr. value causes attr parsing to be stopped
#778781 SRC-attribute suppression in IMG-tags
Also reviewed these test cases, again, with none reproducible in 1.4:
#788746 parser crashes on comments like <!-- foobar --!>
#772700 Jsp Tags are not parsed correctly when in quoted attributes.
Index: ParserTest.java
===================================================================
RCS file: /cvsroot/htmlparser/htmlparser/src/org/htmlparser/tests/ParserTest.java,v
retrieving revision 1.51
retrieving revision 1.52
diff -C2 -d -r1.51 -r1.52
*** ParserTest.java 8 Dec 2003 01:31:53 -0000 1.51
--- ParserTest.java 2 Jan 2004 05:01:28 -0000 1.52
***************
*** 29,33 ****
--- 29,36 ----
package org.htmlparser.tests;
+ import java.io.BufferedInputStream;
+ import java.io.DataInputStream;
import java.io.File;
+ import java.io.FileInputStream;
import java.io.FileWriter;
import java.io.PrintWriter;
***************
*** 749,752 ****
--- 752,851 ----
}
assertEquals("Expected nodes",21,i);
+ }
+
+ /**
+ * See bug #826764 ParserException occurs only when using setInputHTML() instea
+ */
+ public void testSetInputHTML () throws Exception
+ {
+ String html;
+ String path;
+ File file;
+ PrintWriter out;
+ Node[] nodes;
+
+ html = "<html></html>";
+ createParser (html);
+ path = System.getProperty ("user.dir");
+ if (!path.endsWith (File.separator))
+ path += File.separator;
+ file = new File (path + "delete_me.html");
+ try
+ {
+ out = new PrintWriter (new FileWriter (file));
+ out.print ("<html>\r\n");
+ out.print ("<head>\r\n");
+ out.print ("<!-- BEGIN TYPE -->\r\n");
+ out.print ("<!-- NAVIGATION -->\r\n");
+ out.print ("<!-- END TYPE -->\r\n");
+ out.print ("<!-- BEGIN TITLE -->\r\n");
+ out.print ("<title>Einstiegsseite</title>\r\n");
+ out.print ("<!-- END TITLE -->\r\n");
+ out.print ("</head>\r\n");
+ out.print ("<body>\r\n");
+ out.print ("<ul>\r\n");
+ out.print ("<li>\r\n");
+ out.print ("<!-- BEGIN ITEM -->\r\n");
+ out.print ("<!-- BEGIN REF -->\r\n");
+ out.print ("<a href=\"kapitel1/index.html\">\r\n");
+ out.print ("<!-- END REF -->\r\n");
+ out.print ("<!-- BEGIN REFTITLE -->\r\n");
+ out.print ("Kapitel 1\r\n");
+ out.print ("<!-- END REFTITLE -->\r\n");
+ out.print ("</a>\r\n");
+ out.print ("<!-- END ITEM -->\r\n");
+ out.print ("</li>\r\n");
+ out.print ("<li>\r\n");
+ out.print ("<!-- BEGIN ITEM -->\r\n");
+ out.print ("<!-- BEGIN REF -->\r\n");
+ out.print ("<a href=\"kapitel2/index.html\">\r\n");
+ out.print ("<!-- END REF -->\r\n");
+ out.print ("<!-- BEGIN REFTITLE -->\r\n");
+ out.print ("Kapitel 2\r\n");
+ out.print ("<!-- END REFTITLE -->\r\n");
+ out.print ("</a>\r\n");
+ out.print ("<!-- END ITEM -->\r\n");
+ out.print ("</li>\r\n");
+ out.print ("<li>\r\n");
+ out.print ("<!-- BEGIN ITEM -->\r\n");
+ out.print ("<!-- BEGIN REF -->\r\n");
+ out.print ("<a href=\"kapitel3/index.html\">\r\n");
+ out.print ("<!-- END REF -->\r\n");
+ out.print ("<!-- BEGIN REFTITLE -->\r\n");
+ out.print ("Kapitel 3\r\n");
+ out.print ("<!-- END REFTITLE -->\r\n");
+ out.print ("</a>\r\n");
+ out.print ("<!-- END ITEM -->\r\n");
+ out.print ("</li>\r\n");
+ out.print ("</ul>\r\n");
+ out.print ("</body>\r\n");
+ out.print ("</html>");
+ out.close ();
+ DataInputStream stream = new DataInputStream (
+ new BufferedInputStream (new FileInputStream (file)));
+ byte[] buffer = new byte[(int)file.length ()];
+ stream.readFully (buffer);
+ html = new String (buffer);
+ try
+ {
+ parser.setInputHTML (html);
+ nodes = parser.extractAllNodesThatAre (LinkTag.class);
+ }
+ catch (ParserException e)
+ {
+ e.printStackTrace ();
+ nodes = new Node[0];
+ }
+ int count = nodes.length;
+ assertTrue ("node count", 3 == nodes.length);
+ }
+ catch (Exception e)
+ {
+ fail (e.toString ());
+ }
+ finally
+ {
+ file.delete ();
+ }
}
}
|
