Update of /cvsroot/htmlparser/htmlparser/src/org/htmlparser/tests/lexerTests
In directory sc8-pr-cvs1:/tmp/cvs-serv28098/src/org/htmlparser/tests/lexerTests
Modified Files:
AttributeTests.java KitTest.java LexerTests.java
PageTests.java SourceTests.java StreamTests.java
Log Message:
Index: AttributeTests.java
===================================================================
RCS file: /cvsroot/htmlparser/htmlparser/src/org/htmlparser/tests/lexerTests/AttributeTests.java,v
retrieving revision 1.10
retrieving revision 1.11
diff -C2 -d -r1.10 -r1.11
*** AttributeTests.java 2 Jan 2004 16:24:55 -0000 1.10
--- AttributeTests.java 14 Jan 2004 02:53:47 -0000 1.11
***************
*** 29,36 ****
import java.util.Hashtable;
import java.util.Vector;
- import junit.framework.TestSuite;
import org.htmlparser.Node;
- import org.htmlparser.Parser;
import org.htmlparser.PrototypicalNodeFactory;
import org.htmlparser.lexer.nodes.Attribute;
--- 29,34 ----
Index: KitTest.java
===================================================================
RCS file: /cvsroot/htmlparser/htmlparser/src/org/htmlparser/tests/lexerTests/KitTest.java,v
retrieving revision 1.5
retrieving revision 1.6
diff -C2 -d -r1.5 -r1.6
*** KitTest.java 20 Oct 2003 01:28:03 -0000 1.5
--- KitTest.java 14 Jan 2004 02:53:47 -0000 1.6
***************
*** 31,38 ****
import java.util.Vector;
import javax.swing.text.BadLocationException;
- import javax.swing.text.Document;
- import javax.swing.text.EditorKit;
import javax.swing.text.Element;
- import javax.swing.text.ElementIterator;
import javax.swing.text.MutableAttributeSet;
import javax.swing.text.html.HTML;
--- 31,35 ----
***************
*** 43,47 ****
import org.htmlparser.lexer.Cursor;
import org.htmlparser.lexer.Lexer;
- import org.htmlparser.lexer.Page;
import org.htmlparser.AbstractNode;
import org.htmlparser.lexer.nodes.Attribute;
--- 40,43 ----
***************
*** 608,611 ****
--- 604,610 ----
*
* $Log$
+ * Revision 1.6 2004/01/14 02:53:47 derrickoswald
+ * *** empty log message ***
+ *
* Revision 1.5 2003/10/20 01:28:03 derrickoswald
* Removed lexer level AbstractNode.
Index: LexerTests.java
===================================================================
RCS file: /cvsroot/htmlparser/htmlparser/src/org/htmlparser/tests/lexerTests/LexerTests.java,v
retrieving revision 1.16
retrieving revision 1.17
diff -C2 -d -r1.16 -r1.17
*** LexerTests.java 10 Jan 2004 15:23:33 -0000 1.16
--- LexerTests.java 14 Jan 2004 02:53:47 -0000 1.17
***************
*** 27,39 ****
package org.htmlparser.tests.lexerTests;
- import java.io.BufferedReader;
- import java.io.ByteArrayInputStream;
import java.io.IOException;
- import java.io.InputStream;
- import java.io.InputStreamReader;
- import java.io.StringReader;
- import java.io.UnsupportedEncodingException;
import java.net.URL;
- import java.net.URLConnection;
import java.util.HashSet;
--- 27,32 ----
***************
*** 41,48 ****
import org.htmlparser.Parser;
import org.htmlparser.lexer.Lexer;
- import org.htmlparser.lexer.Page;
- import org.htmlparser.lexer.PageIndex;
- import org.htmlparser.lexer.Source;
- import org.htmlparser.lexer.Stream;
import org.htmlparser.lexer.nodes.RemarkNode;
import org.htmlparser.lexer.nodes.StringNode;
--- 34,37 ----
***************
*** 52,56 ****
import org.htmlparser.util.NodeIterator;
import org.htmlparser.util.NodeList;
- import org.htmlparser.util.EncodingChangeException;
import org.htmlparser.util.ParserException;
--- 41,44 ----
***************
*** 621,629 ****
* causes spurious tags.
* The root cause is characters bracketed by [esc]$B and [esc](J (contrary
! * to what is indicated in the j_s_nightingale analysis of the problem) that
* sometimes have an angle bracket (< or 0x3c) embedded in them. These
* are taken to be tags by the parser, instead of being considered strings.
* <p>
! * The URL http://www.009.com/ has an ISO-8859-1 encoding (the default), but
* Japanese characters intermixed on the page with English, using the JIS
* encoding. We detect failure by looking for weird tag names which were
--- 609,617 ----
* causes spurious tags.
* The root cause is characters bracketed by [esc]$B and [esc](J (contrary
! * to what is indicated in then j_s_nightingale analysis of the problem) that
* sometimes have an angle bracket (< or 0x3c) embedded in them. These
* are taken to be tags by the parser, instead of being considered strings.
* <p>
! * The URL refrenced has an ISO-8859-1 encoding (the default), but
* Japanese characters intermixed on the page with English, using the JIS
* encoding. We detect failure by looking for weird tag names which were
***************
*** 667,671 ****
NodeIterator iterator;
! parser = new Parser ("http://htmlparser.sourceforge.net/test/www_009_com.html");
iterator = parser.elements ();
while (iterator.hasMoreNodes ())
--- 655,659 ----
NodeIterator iterator;
! parser = new Parser ("http://www.009.com/");
iterator = parser.elements ();
while (iterator.hasMoreNodes ())
***************
*** 746,784 ****
}
- /**
- * See bug #874175 StringBean doesn't handle charset change well
- * Force an encoding change exception, reset and re-read.
- */
- public void testEncodingChange ()
- throws
- ParserException
- {
- NodeIterator iterator;
- Node node;
- boolean success;
-
- parser = new Parser ("http://htmlparser.sourceforge.net/test/www_china-pub_com.html");
- success = false;
- try
- {
- for (iterator = parser.elements (); iterator.hasMoreNodes (); )
- node = iterator.nextNode ();
- }
- catch (EncodingChangeException ece)
- {
- success = true;
- try
- {
- parser.reset ();
- for (iterator = parser.elements (); iterator.hasMoreNodes (); )
- node = iterator.nextNode ();
- }
- catch (ParserException pe)
- {
- success = false;
- }
- }
- assertTrue ("encoding change failed", success);
- }
}
--- 734,737 ----
Index: PageTests.java
===================================================================
RCS file: /cvsroot/htmlparser/htmlparser/src/org/htmlparser/tests/lexerTests/PageTests.java,v
retrieving revision 1.15
retrieving revision 1.16
diff -C2 -d -r1.15 -r1.16
*** PageTests.java 2 Jan 2004 16:24:56 -0000 1.15
--- PageTests.java 14 Jan 2004 02:53:47 -0000 1.16
***************
*** 28,32 ****
import java.io.IOException;
- import java.io.UnsupportedEncodingException;
import java.net.URL;
import java.net.URLConnection;
--- 28,31 ----
Index: SourceTests.java
===================================================================
RCS file: /cvsroot/htmlparser/htmlparser/src/org/htmlparser/tests/lexerTests/SourceTests.java,v
retrieving revision 1.15
retrieving revision 1.16
diff -C2 -d -r1.15 -r1.16
*** SourceTests.java 2 Jan 2004 16:24:56 -0000 1.15
--- SourceTests.java 14 Jan 2004 02:53:47 -0000 1.16
***************
*** 30,40 ****
import java.io.ByteArrayInputStream;
import java.io.IOException;
- import java.io.InputStream;
import java.io.InputStreamReader;
import java.net.MalformedURLException;
import java.net.URL;
import java.net.URLConnection;
- import java.util.ArrayList;
- import java.util.Random;
import org.htmlparser.lexer.Stream;
--- 30,37 ----
Index: StreamTests.java
===================================================================
RCS file: /cvsroot/htmlparser/htmlparser/src/org/htmlparser/tests/lexerTests/StreamTests.java,v
retrieving revision 1.15
retrieving revision 1.16
diff -C2 -d -r1.15 -r1.16
*** StreamTests.java 2 Jan 2004 16:24:56 -0000 1.15
--- StreamTests.java 14 Jan 2004 02:53:47 -0000 1.16
***************
*** 30,39 ****
import java.io.ByteArrayInputStream;
import java.io.IOException;
- import java.io.InputStream;
import java.net.MalformedURLException;
import java.net.URL;
import java.net.URLConnection;
import java.util.ArrayList;
- import java.util.Random;
import org.htmlparser.lexer.Stream;
--- 30,37 ----
|
