htmlparser-cvs — syncmail email notification of CVS commits

[Htmlparser-cvs] htmlparser/src/org/htmlparser/parserHelper AttributeParser.java,1.30,1.31 CompositeTagScannerHelper.java,1.40,1.41 ParserHelper.java,1.10,1.11 ScriptScannerHelper.java,1.5,1.6 StringParser.java,1.33,1.34 TagParser.java,1.36,1.37

[<der...@us...>]

Update of /cvsroot/htmlparser/htmlparser/src/org/htmlparser/parserHelper
In directory sc8-pr-cvs1:/tmp/cvs-serv26018/htmlparser/src/org/htmlparser/parserHelper

Modified Files:
	AttributeParser.java CompositeTagScannerHelper.java 
	ParserHelper.java ScriptScannerHelper.java StringParser.java 
	TagParser.java 
Log Message:
Update version headers to 1.4-20030727 and update changelog.



Index: AttributeParser.java
===================================================================
RCS file: /cvsroot/htmlparser/htmlparser/src/org/htmlparser/parserHelper/AttributeParser.java,v
retrieving revision 1.30
retrieving revision 1.31
diff -C2 -d -r1.30 -r1.31
*** AttributeParser.java	13 Jul 2003 12:15:04 -0000	1.30
--- AttributeParser.java	27 Jul 2003 19:19:17 -0000	1.31
***************
*** 1,3 ****
! // HTMLParser Library v1_4_20030713 - A java-based parser for HTML
  // Copyright (C) Dec 31, 2000 Somik Raha
  //
--- 1,3 ----
! // HTMLParser Library v1_4_20030727 - A java-based parser for HTML
  // Copyright (C) Dec 31, 2000 Somik Raha
  //

Index: CompositeTagScannerHelper.java
===================================================================
RCS file: /cvsroot/htmlparser/htmlparser/src/org/htmlparser/parserHelper/CompositeTagScannerHelper.java,v
retrieving revision 1.40
retrieving revision 1.41
diff -C2 -d -r1.40 -r1.41
*** CompositeTagScannerHelper.java	13 Jul 2003 12:15:04 -0000	1.40
--- CompositeTagScannerHelper.java	27 Jul 2003 19:19:17 -0000	1.41
***************
*** 1,3 ****
! // HTMLParser Library v1_4_20030713 - A java-based parser for HTML
  // Copyright (C) Dec 31, 2000 Somik Raha
  // 
--- 1,3 ----
! // HTMLParser Library v1_4_20030727 - A java-based parser for HTML
  // Copyright (C) Dec 31, 2000 Somik Raha
  // 

Index: ParserHelper.java
===================================================================
RCS file: /cvsroot/htmlparser/htmlparser/src/org/htmlparser/parserHelper/ParserHelper.java,v
retrieving revision 1.10
retrieving revision 1.11
diff -C2 -d -r1.10 -r1.11
*** ParserHelper.java	13 Jul 2003 12:15:04 -0000	1.10
--- ParserHelper.java	27 Jul 2003 19:19:17 -0000	1.11
***************
*** 1,3 ****
! // HTMLParser Library v1_4_20030713 - A java-based parser for HTML
  // Copyright (C) Dec 31, 2000 Somik Raha
  //
--- 1,3 ----
! // HTMLParser Library v1_4_20030727 - A java-based parser for HTML
  // Copyright (C) Dec 31, 2000 Somik Raha
  //

Index: ScriptScannerHelper.java
===================================================================
RCS file: /cvsroot/htmlparser/htmlparser/src/org/htmlparser/parserHelper/ScriptScannerHelper.java,v
retrieving revision 1.5
retrieving revision 1.6
diff -C2 -d -r1.5 -r1.6
*** ScriptScannerHelper.java	13 Jul 2003 12:15:04 -0000	1.5
--- ScriptScannerHelper.java	27 Jul 2003 19:19:17 -0000	1.6
***************
*** 1,3 ****
! //HTMLParser Library v1_4_20030713 - A java-based parser for HTML
  //Copyright (C) Dec 31, 2000 Somik Raha
  //
--- 1,3 ----
! //HTMLParser Library v1_4_20030727 - A java-based parser for HTML
  //Copyright (C) Dec 31, 2000 Somik Raha
  //

Index: StringParser.java
===================================================================
RCS file: /cvsroot/htmlparser/htmlparser/src/org/htmlparser/parserHelper/StringParser.java,v
retrieving revision 1.33
retrieving revision 1.34
diff -C2 -d -r1.33 -r1.34
*** StringParser.java	13 Jul 2003 12:15:04 -0000	1.33
--- StringParser.java	27 Jul 2003 19:19:17 -0000	1.34
***************
*** 1,3 ****
! // HTMLParser Library v1_4_20030713 - A java-based parser for HTML
  // Copyright (C) Dec 31, 2000 Somik Raha
  //
--- 1,3 ----
! // HTMLParser Library v1_4_20030727 - A java-based parser for HTML
  // Copyright (C) Dec 31, 2000 Somik Raha
  //

Index: TagParser.java
===================================================================
RCS file: /cvsroot/htmlparser/htmlparser/src/org/htmlparser/parserHelper/TagParser.java,v
retrieving revision 1.36
retrieving revision 1.37
diff -C2 -d -r1.36 -r1.37
*** TagParser.java	13 Jul 2003 12:15:05 -0000	1.36
--- TagParser.java	27 Jul 2003 19:19:17 -0000	1.37
***************
*** 1,3 ****
! // HTMLParser Library v1_4_20030713 - A java-based parser for HTML
  // Copyright (C) Dec 31, 2000 Somik Raha
  //
--- 1,3 ----
! // HTMLParser Library v1_4_20030727 - A java-based parser for HTML
  // Copyright (C) Dec 31, 2000 Somik Raha
  //

[Htmlparser-cvs] htmlparser/src/org/htmlparser/lexer Page.java,1.1,1.2 Source.java,1.1,1.2 Stream.java,1.1,1.2

[<der...@us...>]

Update of /cvsroot/htmlparser/htmlparser/src/org/htmlparser/lexer
In directory sc8-pr-cvs1:/tmp/cvs-serv26018/htmlparser/src/org/htmlparser/lexer

Modified Files:
	Page.java Source.java Stream.java 
Log Message:
Update version headers to 1.4-20030727 and update changelog.



Index: Page.java
===================================================================
RCS file: /cvsroot/htmlparser/htmlparser/src/org/htmlparser/lexer/Page.java,v
retrieving revision 1.1
retrieving revision 1.2
diff -C2 -d -r1.1 -r1.2
*** Page.java	17 Jul 2003 01:42:13 -0000	1.1
--- Page.java	27 Jul 2003 19:19:17 -0000	1.2
***************
*** 1,3 ****
! // HTMLParser Library v1_4_20030525 - A java-based parser for HTML
  // Copyright (C) Dec 31, 2000 Somik Raha
  //
--- 1,3 ----
! // HTMLParser Library v1_4_20030727 - A java-based parser for HTML
  // Copyright (C) Dec 31, 2000 Somik Raha
  //

Index: Source.java
===================================================================
RCS file: /cvsroot/htmlparser/htmlparser/src/org/htmlparser/lexer/Source.java,v
retrieving revision 1.1
retrieving revision 1.2
diff -C2 -d -r1.1 -r1.2
*** Source.java	17 Jul 2003 01:42:13 -0000	1.1
--- Source.java	27 Jul 2003 19:19:17 -0000	1.2
***************
*** 1,3 ****
! // HTMLParser Library v1_4_20030525 - A java-based parser for HTML
  // Copyright (C) Dec 31, 2000 Somik Raha
  //
--- 1,3 ----
! // HTMLParser Library v1_4_20030727 - A java-based parser for HTML
  // Copyright (C) Dec 31, 2000 Somik Raha
  //

Index: Stream.java
===================================================================
RCS file: /cvsroot/htmlparser/htmlparser/src/org/htmlparser/lexer/Stream.java,v
retrieving revision 1.1
retrieving revision 1.2
diff -C2 -d -r1.1 -r1.2
*** Stream.java	17 Jul 2003 01:42:13 -0000	1.1
--- Stream.java	27 Jul 2003 19:19:17 -0000	1.2
***************
*** 1,3 ****
! // HTMLParser Library v1_4_20030525 - A java-based parser for HTML
  // Copyright (C) Dec 31, 2000 Somik Raha
  //
--- 1,3 ----
! // HTMLParser Library v1_4_20030727 - A java-based parser for HTML
  // Copyright (C) Dec 31, 2000 Somik Raha
  //

[Htmlparser-cvs] htmlparser/docs changes.txt,1.185,1.186 release.txt,1.45,1.46

[<der...@us...>]

Update of /cvsroot/htmlparser/htmlparser/docs
In directory sc8-pr-cvs1:/tmp/cvs-serv26018/htmlparser/docs

Modified Files:
	changes.txt release.txt 
Log Message:
Update version headers to 1.4-20030727 and update changelog.



Index: changes.txt
===================================================================
RCS file: /cvsroot/htmlparser/htmlparser/docs/changes.txt,v
retrieving revision 1.185
retrieving revision 1.186
diff -C2 -d -r1.185 -r1.186
*** changes.txt	13 Jul 2003 12:15:02 -0000	1.185
--- changes.txt	27 Jul 2003 19:19:16 -0000	1.186
***************
*** 13,16 ****
--- 13,102 ----
  *******************************************************************************
  
+ Integration Build 1.4 - 20030727
+ --------------------------------
+ 
+ 2003-07-22 20:12  derrickoswald
+ 
+ 	* build.xml:
+ 
+ 	Use junit.jar and commons-logging.jar now found in lib/.
+ 	
+ 2003-07-16 22:14  jkerievsky
+ 
+ 	* src/org/htmlparser/tests/utilTests/BeanTest.java:
+ 
+ 	updated last test in StringBean, and disabled the test, as is doesn't pass right now
+ 	
+ 2003-07-16 21:49  derrickoswald
+ 
+ 	* lib/: commons-logging.jar, junit.jar:
+ 
+ 	Add needed libraries.
+ 	
+ 2003-07-16 21:42  derrickoswald
+ 
+ 	* src/org/htmlparser/: lexer/Page.java, lexer/Source.java,
+ 	lexer/Stream.java, tests/lexerTests/AllTests.java,
+ 	tests/lexerTests/PageTests.java, tests/lexerTests/SourceTests.java,
+ 	tests/lexerTests/StreamTests.java:
+ 
+ 	Initial drop of new io subsystem.
+ 	
+ 2003-07-16 20:56  derrickoswald
+ 
+ 	* src/org/htmlparser/tests/utilTests/BeanTest.java:
+ 
+ 	More tests.
+ 	testOutputWithPreAndScriptTags is now correct, I think.
+ 	The overarching goal of StringBean is to return the text, and only the text, that a user would see in a browser. When I open this html in Netscape I see nothing:
+ 	
+ 	<body><pre>
+ 	<script language=\"javascript\">
+ 	if(navigator.appName.indexOf(\"Netscape\") != -1)
+ 	 document.write ('xxx');
+ 	else
+ 	 document.write ('yyy');
+ 	</script>
+ 	</pre></body>
+ 	
+ 	That's what StringBean says too.
+ 	
+ 	Although this points out a flaw in the specification (such as it is, see the StringBean javadoc):
+ 	
+ 	 * Text within <SCRIPT></SCRIPT> tags is removed.
+ 	 * The text within <PRE></PRE> tags is not altered.
+ 	
+ 	So what happens when there's both?
+ 	The 'not altered' means, not collapsed, not that the HTML is returned literally.
+ 	To test this out, see how Netscape handles:
+ 	
+ 	<body><pre>
+ 	<b>Hello
+ 	World</b>
+ 	</pre></body>
+ 	
+ 	For me it shows:
+ 	
+ 	Hello
+ 	World
+ 	
+ 	which means it consumes (and honours) the bold tags even though it is within <pre></pre>
+ 	So the StringBean <pre> handling is correct, or so it seems.
+ 	
+ 	I guess that most questions can be answered by submitting it to a browser.
+ 	
+ 2003-07-16 16:05  jkerievsky
+ 
+ 	* src/org/htmlparser/tests/utilTests/BeanTest.java:
+ 
+ 	added some more BeanTests, including one that is Xed out, as I think it may uncover a bug
+ 	
+ 2003-07-15 20:17  derrickoswald
+ 
+ 	* src/org/htmlparser/tests/utilTests/: AllTests.java,
+ 	BeanTest.java:
+ 
+ 	Add some StringBean tests for Joshua.
+ 	
  Integration Build 1.4 - 20030713
  --------------------------------

Index: release.txt
===================================================================
RCS file: /cvsroot/htmlparser/htmlparser/docs/release.txt,v
retrieving revision 1.45
retrieving revision 1.46
diff -C2 -d -r1.45 -r1.46
*** release.txt	13 Jul 2003 12:15:03 -0000	1.45
--- release.txt	27 Jul 2003 19:19:16 -0000	1.46
***************
*** 1,3 ****
! HTMLParser Version 1.4 (Integration Build Jul 13, 2003)
  *********************************************
  
--- 1,3 ----
! HTMLParser Version 1.4 (Integration Build Jul 27, 2003)
  *********************************************
  

[Htmlparser-cvs] htmlparser build.xml,1.38,1.39

[<der...@us...>]

Update of /cvsroot/htmlparser/htmlparser
In directory sc8-pr-cvs1:/tmp/cvs-serv26018/htmlparser

Modified Files:
	build.xml 
Log Message:
Update version headers to 1.4-20030727 and update changelog.



Index: build.xml
===================================================================
RCS file: /cvsroot/htmlparser/htmlparser/build.xml,v
retrieving revision 1.38
retrieving revision 1.39
diff -C2 -d -r1.38 -r1.39
*** build.xml	23 Jul 2003 00:12:05 -0000	1.38
--- build.xml	27 Jul 2003 19:19:16 -0000	1.39
***************
*** 1,2 ****
--- 1,73 ----
+ <!--
+ Build Procedure
+ - cd htmlparser
+ - 'ant jar' generates new htmlparser.jar in htmlparser/release/htmlparser1_4/lib
+ 
+ Release Procedure
+ - cd htmlparser
+ - set environment variables CVSROOT and CVS_RSH (see changeLog task)
+ - 'ant changeLog' generates htmlparser/ChangeLog
+ - edit the ChangeLog to exclude changes already incorporated and the previous 
+   release's "update of version headers" drop - the CVS date spec is only accurate
+   to the day since it comes from the version coded in the Parser.java file,
+   that's why this step can't be automated
+ - incorporate changes from ChangeLog into htmlparser/docs/changes under
+   a heading like "Integration Build 1.4 - 20030713"
+ - 'ant jar' generates new htmlparser.jar in htmlparser/release/htmlparser1_4/lib
+ - 'ant test' compiles and runs the unit tests
+ - 'rm /home/derrick/htmlparser/htmlparser_cvs/htmlparser/docs/docs/*'
+   and 'rm /home/derrick/htmlparser/htmlparser_cvs/htmlparser/docs/docs/images/*'
+   deletes local Wiki pages, of course any one else would have to adjust this and
+   also the hard-coded path in WikiCapturer
+ - 'javac -classpath release/htmlparser1_4/lib/htmlparser.jar ../WikiCapturer/src/org/htmlparser/wikicapturer/CaptureWiki.java ../WikiCapturer/src/org/htmlparser/wikicapturer/PhpWikiVisitor.java'
+   and 'java -classpath release/htmlparser1_4/lib/htmlparser.jar:../WikiCapturer/src org.htmlparser.wikicapturer.CaptureWiki'
+   fetches current Wiki pages
+ - perform a CVS update on htmlparser/docs/docs to identify new and changed files
+   and commit them - that's why this step can't be automated
+ - 'ant' updates the version headers, creates the jar file and doc files and zips
+   everything into a file htmlparser/distribution/htmlparser1_4_20030727.zip
+ - commit docs/changes, docs/docs, docs/docs/images and src/* using a reason of
+   the form:
+ Update version headers to 1.4-20030727 and update changelog.
+ 
+ Sourceforge File Release Procedure
+ - upload the zip file to the sourceforge site
+ $ ftp upload.sourceforge.net
+ Name: anonymous
+ Password: you...@us...
+ ftp> cd incoming
+ ftp> bin
+ ftp> put htmlparser1_4_20030727.zip
+ ftp> bye
+ - add a release to the 'Integation Builds' package
+ Admin-File Releases-Add Release, use a name of the form '1_4_20030727'
+ - Step 1, 'Paste The Notes' (using numeric character references and
+   character entity references because this is displayed as HTML) with a
+   format like :
+ Integration build.
+ Failing Unit Tests:
+ Open Bugs:
+ Pending Bugs:
+ - use the 'Upload Change Log:' field to specify the ChamgeLog file you edited
+ - Step 2, check the checkbox of the htmlparser1_4_20030727.zip file from the
+   list of files in the uploads section
+ - Submit/Refresh
+ - Step 3, mark the zip file Processor-Independent, and give it a .zip type
+ - Update/Refresh
+ - Step 4, check the 'I'm sure' checkbox
+ - Send Notice
+ - go back to Admin-File Releases-Edit Release, choose the previous release
+   and mark it as hidden
+ - Submit/Refresh
+ 
+ Submit News
+ - from the project summary screen, select 'Submit News' and title it like:
+ HTML Parser Integration Release 1.4-20030727 
+ - type in a summary of the changes made
+ - SUBMIT
+ - delete the previous release news item using Admin-Publicity-Administrate project news
+ - choose the old news item, change the Status to 'Delete'
+ - SUBMIT
+ -->
  <project name="HTMLParser" default="htmlparser" basedir=".">
  
***************
*** 126,130 ****
  
      <!-- Compile the java code in ${src} -->
!     <javac srcdir="${src}" includes="org/htmlparser/**" excludes="org/htmlparser/tests/**,org/htmlparser/util/Generate.java" debug="on" classpath=".:${commons-logging.jar}" />
    </target>
  
--- 197,201 ----
  
      <!-- Compile the java code in ${src} -->
!     <javac srcdir="${src}" includes="org/htmlparser/**" excludes="org/htmlparser/tests/**,org/htmlparser/util/Generate.java,org/htmlparser/lexer" debug="on" classpath="src:${commons-logging.jar}" />
    </target>
  
***************
*** 171,174 ****
--- 242,246 ----
      <javac srcdir="${src}" includes="org/htmlparser/tests/**" debug="on">
        <classpath>
+         <pathelement location="src"/>
          <pathelement location="${junit.jar}"/>
          <pathelement location="${commons-logging.jar}"/>
***************
*** 210,213 ****
--- 282,286 ----
      <javadoc packagenames="org.htmlparser.*"
             sourcepath="${src}"
+            classpath="src:${commons-logging.jar}"
             defaultexcludes="yes"
             excludepackagenames="org.htmlparser.tests.*"

[Htmlparser-cvs] htmlparser/docs/docs FirstName.html,NONE,1.1 LastName.html,NONE,1.1

[<der...@us...>]

Update of /cvsroot/htmlparser/htmlparser/docs/docs
In directory sc8-pr-cvs1:/tmp/cvs-serv25057/htmlparser/docs/docs

Added Files:
	FirstName.html LastName.html 
Log Message:
update Wiki image



--- NEW FILE: FirstName.html ---
<html><head><title>First Name</title></head><body><DIV CLASS="wikitext">
<P>Describe <A CLASS="wiki" HREF="FirstName.html">FirstName</A> here.</P></DIV><DIV ID="actionbar" CLASS="toolbar"><HR NOSHADE="noshade" CLASS="printer"/><P CLASS="editdate">Last edited on Thursday, July 17, 2003  4:35:59 am.</P><HR NOSHADE="noshade" CLASS="toolbar"/></body></html>
--- NEW FILE: LastName.html ---
<html><head><title>Last Name</title></head><body><DIV CLASS="wikitext">
<P>Describe <A CLASS="wiki" HREF="LastName.html">LastName</A> here.fdsadfsafdsaf</P></DIV><DIV ID="actionbar" CLASS="toolbar"><HR NOSHADE="noshade" CLASS="printer"/><P CLASS="editdate">Last edited on Thursday, July 17, 2003  4:38:05 am.</P><HR NOSHADE="noshade" CLASS="toolbar"/></body></html>

[Htmlparser-cvs] htmlparser/docs/docs ParsingXml.html,1.1,1.2

[<der...@us...>]

Update of /cvsroot/htmlparser/htmlparser/docs/docs
In directory sc8-pr-cvs1:/tmp/cvs-serv25041/htmlparser/docs/docs

Modified Files:
	ParsingXml.html 
Log Message:
update Wiki image



Index: ParsingXml.html
===================================================================
RCS file: /cvsroot/htmlparser/htmlparser/docs/docs/ParsingXml.html,v
retrieving revision 1.1
retrieving revision 1.2
diff -C2 -d -r1.1 -r1.2
*** ParsingXml.html	13 Jul 2003 11:40:59 -0000	1.1
--- ParsingXml.html	27 Jul 2003 13:20:27 -0000	1.2
***************
*** 5,10 ****
  <P>&lt;Reviewer&gt;</P>
  <P>&lt;PeopleID&gt;9&lt;/PeopleID&gt;</P>
! <P>&lt;<SPAN CLASS="wikiunknown"><U>FirstName</U></SPAN>&gt;Niall&lt;/<SPAN CLASS="wikiunknown"><U>FirstName</U></SPAN>&gt;</P>
! <P>&lt;<SPAN CLASS="wikiunknown"><U>LastName</U></SPAN>&gt;Adams&lt;/<SPAN CLASS="wikiunknown"><U>LastName</U></SPAN>&gt;</P>
  <P>&lt;<SPAN CLASS="wikiunknown"><U>FullName</U></SPAN>&gt;Niall Adams&lt;/<SPAN CLASS="wikiunknown"><U>FullName</U></SPAN>&gt;</P>
  <P>&lt;Organization&gt;Imperial College&lt;/Organization&gt;</P>
--- 5,10 ----
  <P>&lt;Reviewer&gt;</P>
  <P>&lt;PeopleID&gt;9&lt;/PeopleID&gt;</P>
! <P>&lt;<A CLASS="wiki" HREF="FirstName.html">FirstName</A>&gt;Niall&lt;/<A CLASS="wiki" HREF="FirstName.html">FirstName</A>&gt;</P>
[...1663 lines suppressed...]
  <P>&lt;PeopleID&gt;117&lt;/PeopleID&gt;</P>
! <P>&lt;<A CLASS="wiki" HREF="FirstName.html">FirstName</A>&gt;Ruben&lt;/<A CLASS="wiki" HREF="FirstName.html">FirstName</A>&gt;</P>
! <P>&lt;<A CLASS="wiki" HREF="LastName.html">LastName</A>&gt;Zamar&lt;/<A CLASS="wiki" HREF="LastName.html">LastName</A>&gt;</P>
  <P>&lt;<SPAN CLASS="wikiunknown"><U>FullName</U></SPAN>&gt;Ruben Zamar&lt;/<SPAN CLASS="wikiunknown"><U>FullName</U></SPAN>&gt;</P>
  <P>&lt;Organization&gt;University of British Columbia&lt;/Organization&gt;</P>
***************
*** 1797,1802 ****
  <P>&lt;Reviewer&gt;</P>
  <P>&lt;PeopleID&gt;118&lt;/PeopleID&gt;</P>
! <P>&lt;<SPAN CLASS="wikiunknown"><U>FirstName</U></SPAN>&gt;Zijian&lt;/<SPAN CLASS="wikiunknown"><U>FirstName</U></SPAN>&gt;</P>
! <P>&lt;<SPAN CLASS="wikiunknown"><U>LastName</U></SPAN>&gt;Zheng&lt;/<SPAN CLASS="wikiunknown"><U>LastName</U></SPAN>&gt;</P>
  <P>&lt;<SPAN CLASS="wikiunknown"><U>FullName</U></SPAN>&gt;Zijian Zheng&lt;/<SPAN CLASS="wikiunknown"><U>FullName</U></SPAN>&gt;</P>
  <P>&lt;Organization&gt;IDS Software Systems&lt;/Organization&gt;</P>
--- 1797,1802 ----
  <P>&lt;Reviewer&gt;</P>
  <P>&lt;PeopleID&gt;118&lt;/PeopleID&gt;</P>
! <P>&lt;<A CLASS="wiki" HREF="FirstName.html">FirstName</A>&gt;Zijian&lt;/<A CLASS="wiki" HREF="FirstName.html">FirstName</A>&gt;</P>
! <P>&lt;<A CLASS="wiki" HREF="LastName.html">LastName</A>&gt;Zheng&lt;/<A CLASS="wiki" HREF="LastName.html">LastName</A>&gt;</P>
  <P>&lt;<SPAN CLASS="wikiunknown"><U>FullName</U></SPAN>&gt;Zijian Zheng&lt;/<SPAN CLASS="wikiunknown"><U>FullName</U></SPAN>&gt;</P>
  <P>&lt;Organization&gt;IDS Software Systems&lt;/Organization&gt;</P>

[Htmlparser-cvs] htmlparser build.xml,1.37,1.38

[<der...@us...>]

Update of /cvsroot/htmlparser/htmlparser
In directory sc8-pr-cvs1:/tmp/cvs-serv12744/htmlparser

Modified Files:
	build.xml 
Log Message:
Use junit.jar and commons-logging.jar now found in lib/.



Index: build.xml
===================================================================
RCS file: /cvsroot/htmlparser/htmlparser/build.xml,v
retrieving revision 1.37
retrieving revision 1.38
diff -C2 -d -r1.37 -r1.38
*** build.xml	1 Jun 2003 20:50:06 -0000	1.37
--- build.xml	23 Jul 2003 00:12:05 -0000	1.38
***************
*** 17,22 ****
    <property name="releaseDir" value="release"/>
    <property name="finalLoc" value="distribution"/>
!   <!-- location of junit.jar if there is no link to it in $JAVA_HOME/jre/lib/ext -->
!   <property name="junit.jar" value="../nonexistant_directory/junit.jar"/>
  
    <target name="init" description="initialize version properties">
--- 17,22 ----
    <property name="releaseDir" value="release"/>
    <property name="finalLoc" value="distribution"/>
!   <property name="junit.jar" value="lib/junit.jar"/>
!   <property name="commons-logging.jar" value="lib/commons-logging.jar"/>
  
    <target name="init" description="initialize version properties">
***************
*** 126,130 ****
  
      <!-- Compile the java code in ${src} -->
!     <javac srcdir="${src}" includes="org/htmlparser/**" excludes="org/htmlparser/tests/**,org/htmlparser/util/Generate.java" debug="on" />
    </target>
  
--- 126,130 ----
  
      <!-- Compile the java code in ${src} -->
!     <javac srcdir="${src}" includes="org/htmlparser/**" excludes="org/htmlparser/tests/**,org/htmlparser/util/Generate.java" debug="on" classpath=".:${commons-logging.jar}" />
    </target>
  
***************
*** 172,175 ****
--- 172,176 ----
        <classpath>
          <pathelement location="${junit.jar}"/>
+         <pathelement location="${commons-logging.jar}"/>
        </classpath>
      </javac>
***************
*** 179,182 ****
--- 180,184 ----
          <pathelement location="${src}"/>
          <pathelement location="${junit.jar}"/>
+         <pathelement location="${commons-logging.jar}"/>
        </classpath>
        <arg value="-text"/>

[Htmlparser-cvs] htmlparser/src/org/htmlparser/tests/utilTests BeanTest.java,1.32,1.33

[<jke...@us...>]

Update of /cvsroot/htmlparser/htmlparser/src/org/htmlparser/tests/utilTests
In directory sc8-pr-cvs1:/tmp/cvs-serv4164/src/org/htmlparser/tests/utilTests

Modified Files:
	BeanTest.java 
Log Message:
updated last test in StringBean, and disabled the test, as is doesn't pass right now

Index: BeanTest.java
===================================================================
RCS file: /cvsroot/htmlparser/htmlparser/src/org/htmlparser/tests/utilTests/BeanTest.java,v
retrieving revision 1.32
retrieving revision 1.33
diff -C2 -d -r1.32 -r1.33
*** BeanTest.java	17 Jul 2003 00:56:47 -0000	1.32
--- BeanTest.java	17 Jul 2003 02:14:07 -0000	1.33
***************
*** 465,469 ****
  	 * Test output with pre and script tags
  	 */
! 	public void testOutputWithPreAndScriptTags() {
  		StringBean sb;
  		sb = new StringBean ();
--- 465,469 ----
  	 * Test output with pre and script tags
  	 */
! 	public void xtestOutputWithPreAndScriptTags() {
  		StringBean sb;
  		sb = new StringBean ();
***************
*** 477,481 ****
  		+ "</script>\r\n";
  		
! 		check (sb, "<body><pre>"+sampleScript+"</pre></body>", "");
  	}
      
--- 477,481 ----
  		+ "</script>\r\n";
  		
! 		check (sb, "<body><pre>"+sampleScript+"</pre></body>", sampleScript);
  	}
      

[Htmlparser-cvs] htmlparser/lib junit.jar,NONE,1.1

[<der...@us...>]

Update of /cvsroot/htmlparser/htmlparser/lib
In directory sc8-pr-cvs1:/tmp/cvs-serv344/htmlparser/lib

Added Files:
	junit.jar 
Log Message:
Add needed libraries.



--- NEW FILE: junit.jar ---
(This appears to be a binary file; contents omitted.)

[Htmlparser-cvs] htmlparser/lib commons-logging.jar,NONE,1.1

[<der...@us...>]

Update of /cvsroot/htmlparser/htmlparser/lib
In directory sc8-pr-cvs1:/tmp/cvs-serv328/htmlparser/lib

Added Files:
	commons-logging.jar 
Log Message:
Add needed libraries.



--- NEW FILE: commons-logging.jar ---
(This appears to be a binary file; contents omitted.)

[Htmlparser-cvs] htmlparser/lib - New directory

[<der...@us...>]

Update of /cvsroot/htmlparser/htmlparser/lib
In directory sc8-pr-cvs1:/tmp/cvs-serv32602/lib

Log Message:
Directory /cvsroot/htmlparser/htmlparser/lib added to the repository

[Htmlparser-cvs] htmlparser/src/org/htmlparser/tests/lexerTests AllTests.java,NONE,1.1 PageTests.java,NONE,1.1 SourceTests.java,NONE,1.1 StreamTests.java,NONE,1.1

[<der...@us...>]

Update of /cvsroot/htmlparser/htmlparser/src/org/htmlparser/tests/lexerTests
In directory sc8-pr-cvs1:/tmp/cvs-serv31631/org/htmlparser/tests/lexerTests

Added Files:
	AllTests.java PageTests.java SourceTests.java StreamTests.java 
Log Message:
Initial drop of new io subsystem.



--- NEW FILE: AllTests.java ---
// HTMLParser Library v1_4_20030525 - A java-based parser for HTML
// Copyright (C) Dec 31, 2000 Somik Raha
//
// 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
//
// For any questions or suggestions, you can write to me at :
// Email :so...@in...
// 
// Postal Address : 
// Somik Raha
// Extreme Programmer & Coach
// Industrial Logic Corporation
// 2583 Cedar Street, Berkeley, 
// CA 94708, USA
// Website : http://www.industriallogic.com

package org.htmlparser.tests.lexerTests;

import junit.framework.TestCase;
import junit.framework.TestSuite;

public class AllTests extends TestCase 
{
	public AllTests (String name)
    {
		super (name);
	}

	public static TestSuite suite ()
    {
		TestSuite suite = new TestSuite ("Lexer Tests");
		suite.addTestSuite (StreamTests.class);
		suite.addTestSuite (SourceTests.class);
		suite.addTestSuite (PageTests.class);
		return suite; 
	}

    /**
     * Mainline for all suites of tests.
     * @param args Command line arguments. The following options
     * are understood:
     * <pre>
     * -text  -- use junit.textui.TestRunner
     * -awt   -- use junit.awtui.TestRunner
     * -swing -- use junit.swingui.TestRunner (default)
     * </pre>
     * All other options are passed on to the junit framework.
     */
    public static void main(String[] args)
    {
        String runner;
        int i;
        String arguments[];
        Class cls;

        runner = null;
        for (i = 0; (i < args.length) && (null == runner); i++)
        {
            if (args[i].equalsIgnoreCase ("-text"))
                runner = "junit.textui.TestRunner";
            else if (args[i].equalsIgnoreCase ("-awt"))
                runner = "junit.awtui.TestRunner";
            else if (args[i].equalsIgnoreCase ("-swing"))
                runner = "junit.swingui.TestRunner";
        }
        if (null != runner)
        {
            // remove it from the arguments
            arguments = new String[args.length - 1];
            System.arraycopy (args, 0, arguments, 0, i - 1);
            System.arraycopy (args, i, arguments, i - 1, args.length - i);
            args = arguments;
        }
        else
            runner = "junit.swingui.TestRunner";

        /*
         * from http://www.mail-archive.com/commons-user%40jakarta.apache.org/msg02958.html
         *
         * The problem is within the UI test runners of JUnit. They bring 
         * with them a custom classloader, which causes the 
         * LogConfigurationException. Unfortunately Log4j doesn't work 
         * either.
         * 
         * Solution: Disable "Reload classes every run" or start JUnit with 
         * command line option -noloading before the name of the Testsuite.
         */

        // append the test class
        arguments = new String[args.length + 2];
        System.arraycopy (args, 0, arguments, 0, args.length);
        arguments[arguments.length - 2] = "-noloading";
        arguments[arguments.length - 1] = "org.htmlparser.tests.lexerTests.AllTests";

        // invoke main() of the test runner
        try
        {
            cls = Class.forName (runner);
            java.lang.reflect.Method method = cls.getDeclaredMethod (
                "main", new Class[] { String[].class });
            method.invoke (
                null,
                new Object[] { arguments });
        }
        catch (Throwable t)
        {
            System.err.println (
                "cannot run unit test ("
                + t.getMessage ()
                + ")");
        }
    }
}

--- NEW FILE: PageTests.java ---
// HTMLParser Library v1_4_20030525 - A java-based parser for HTML
// Copyright (C) Dec 31, 2000 Somik Raha
//
// 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
//
// For any questions or suggestions, you can write to me at :
// Email :so...@in...
// 
// Postal Address : 
// Somik Raha
// Extreme Programmer & Coach
// Industrial Logic Corporation
// 2583 Cedar Street, Berkeley, 
// CA 94708, USA
// Website : http://www.industriallogic.com

package org.htmlparser.tests.lexerTests;

import java.io.IOException;
import java.io.UnsupportedEncodingException;
import java.net.URL;
import java.net.URLConnection;

import junit.framework.TestCase;

import org.htmlparser.lexer.Page;

public class PageTests extends TestCase
{
    /**
     * The default charset.
     * This should be <code>ISO-8859-1</code>,
     * see RFC 2616 (http://www.ietf.org/rfc/rfc2616.txt?number=2616) section 3.7.1
     * Another alias is "8859_1".
     */
    public static final String DEFAULT_CHARSET = "ISO-8859-1";

    /**
     * Test the third level page class.
     */
	public PageTests (String name)
    {
		super (name);
	}

    /**
     * Test initialization with a null value.
     */
	public void testNull ()
        throws
            IOException,
            UnsupportedEncodingException
    {
        Page page;

        try
        {
            page = new Page (null);
            assertTrue ("null value in constructor", false);
        }
        catch (IllegalArgumentException iae)
        {
            // expected outcome
        }
    }

    /**
     * Test initialization with a real value.
     */
	public void testURLConnection ()
        throws
            IOException,
            UnsupportedEncodingException
    {
        String link;
        URL url;
        Page page;

        link = "http://www.ibm.com/jp/";
        url = new URL (link);
        page = new Page (url.openConnection ());
    }
}
--- NEW FILE: SourceTests.java ---
// HTMLParser Library v1_4_20030525 - A java-based parser for HTML
// Copyright (C) Dec 31, 2000 Somik Raha
//
// 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
//
// For any questions or suggestions, you can write to me at :
// Email :so...@in...
// 
// Postal Address : 
// Somik Raha
// Extreme Programmer & Coach
// Industrial Logic Corporation
// 2583 Cedar Street, Berkeley, 
// CA 94708, USA
// Website : http://www.industriallogic.com

package org.htmlparser.tests.lexerTests;

import java.io.BufferedInputStream;
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 junit.framework.TestCase;

import org.htmlparser.lexer.Stream;
import org.htmlparser.lexer.Source;

public class SourceTests extends TestCase
{
    /**
     * The default charset.
     * This should be <code>ISO-8859-1</code>,
     * see RFC 2616 (http://www.ietf.org/rfc/rfc2616.txt?number=2616) section 3.7.1
     * Another alias is "8859_1".
     */
    public static final String DEFAULT_CHARSET = "ISO-8859-1";

    /**
     * Test the first level stream class.
     */
	public SourceTests (String name)
    {
		super (name);
	}

    /**
     * Test initialization with a null value.
     */
	public void testNull () throws IOException
    {
        Source source;
        
        source = new Source (null);
        assertTrue ("erroneous character", -1 == source.read ());
    }

    /**
     * Test initialization with a null charset name.
     */
	public void testEmpty () throws IOException
    {
        Source source;
        
        source = new Source (new Stream (new ByteArrayInputStream (new byte[0])), null);
        assertTrue ("erroneous character", -1 == source.read ());
    }

    /**
     * Test initialization with an input stream having only one byte.
     */
	public void testOneByte () throws IOException
    {
        Source source;
        
        source = new Source (new Stream (new ByteArrayInputStream (new byte[] { (byte)0x42 })), null);
        assertTrue ("erroneous character", 'B' == source.read ());
        assertTrue ("extra character", -1 == source.read ());
    }

    /**
     * Test close.
     */
	public void testClose () throws IOException
    {
        Source source;

        source = new Source (new Stream (new ByteArrayInputStream ("hello word".getBytes ())), null);
        assertTrue ("no character", -1 != source.read ());
        source.close ();
        try
        {
            source.read ();
            fail ("not closed");
        }
        catch (IOException ioe)
        {
            // expected outcome
        }
   }

    /**
     * Test reset.
     */
	public void testReset () throws IOException
    {
        String reference;
        Source source;
        StringBuffer buffer;
        int c;
        
        reference = "Now is the time for all good men to come to the aid of the party";
        source = new Source (new Stream (new ByteArrayInputStream (reference.getBytes (DEFAULT_CHARSET))), null);
        buffer = new StringBuffer (reference.length ());
        while (-1 != (c = source.read ()))
            buffer.append ((char)c);
        assertTrue ("string incorrect", reference.equals (buffer.toString ()));
        source.reset ();
        buffer.setLength (0);
        while (-1 != (c = source.read ()))
            buffer.append ((char)c);
        assertTrue ("string incorrect", reference.equals (buffer.toString ()));
        source.close ();
    }

    /**
     * Test reset in the middle of reading.
     */
	public void testMidReset () throws IOException
    {
        String reference;
        Source source;
        StringBuffer buffer;
        int c;
        
        reference = "Now is the time for all good men to come to the aid of the party";
        source = new Source (new Stream (new ByteArrayInputStream (reference.getBytes (DEFAULT_CHARSET))), null);
        buffer = new StringBuffer (reference.length ());
        for (int i = 0; i < 25; i++)
            buffer.append ((char)source.read ());
        source.reset ();
        for (int i = 0; i < 25; i++)
            source.read ();
        while (-1 != (c = source.read ()))
            buffer.append ((char)c);
        assertTrue ("string incorrect", reference.equals (buffer.toString ()));
        source.close ();
    }

    /**
     * Test mark/reset in the middle of reading.
     */
	public void testMarkReset () throws IOException
    {
        String reference;
        Source source;
        StringBuffer buffer;
        int c;
        
        reference = "Now is the time for all good men to come to the aid of the party";
        source = new Source (new Stream (new ByteArrayInputStream (reference.getBytes (DEFAULT_CHARSET))), null);
        assertTrue ("not markable", source.markSupported ());
        buffer = new StringBuffer (reference.length ());
        for (int i = 0; i < 25; i++)
            buffer.append ((char)source.read ());
        source.mark (88);
        for (int i = 0; i < 25; i++)
            source.read ();
        source.reset ();
        while (-1 != (c = source.read ()))
            buffer.append ((char)c);
        assertTrue ("string incorrect", reference.equals (buffer.toString ()));
        source.close ();
    }

    /**
     * Test skip.
     */
	public void testSkip () throws IOException
    {
        String part1;
        String part2;
        String part3;
        String reference;
        Source source;
        StringBuffer buffer;
        int c;
       
        part1 = "Now is the time ";
        part2 = "for all good men ";
        part3 = "to come to the aid of the party";
        reference = part1 + part2 + part3;
        source = new Source (new Stream (new ByteArrayInputStream (reference.getBytes (DEFAULT_CHARSET))), null);
        buffer = new StringBuffer (reference.length ());
        for (int i = 0; i < part1.length (); i++)
            buffer.append ((char)source.read ());
        source.skip (part2.length ());
        while (-1 != (c = source.read ()))
            buffer.append ((char)c);
        assertTrue ("string incorrect", (part1 + part3).equals (buffer.toString ()));
        source.close ();
    }

    /**
     * Test multi-byte read.
     */
	public void testMultByte () throws IOException
    {
        String reference;
        Source source;
        char[] buffer;
        
        reference = "Now is the time for all good men to come to the aid of the party";
        source = new Source (new Stream (new ByteArrayInputStream (reference.getBytes (DEFAULT_CHARSET))), null);
        buffer = new char[reference.length ()];
        source.read (buffer, 0, buffer.length);
        assertTrue ("string incorrect", reference.equals (new String (buffer)));
        assertTrue ("extra character", -1 == source.read ());
        source.close ();
    }

    /**
     * Test positioned multi-byte read.
     */
	public void testPositionedMultByte () throws IOException
    {
        String part1;
        String part2;
        String part3;
        String reference;
        Source source;
        char[] buffer;
        int c;
        int length;
       
        part1 = "Now is the time ";
        part2 = "for all good men ";
        part3 = "to come to the aid of the party";
        reference = part1 + part2 + part3;
        source = new Source (new Stream (new ByteArrayInputStream (reference.getBytes (DEFAULT_CHARSET))), null);
        buffer = new char[reference.length ()];
        for (int i = 0; i < part1.length (); i++)
            buffer[i] = (char)source.read ();
        length = source.read (buffer, part1.length (), part2.length ());
        assertTrue ("incorrect length", part2.length () == length);
        length += part1.length ();
        for (int i = 0; i < part3.length (); i++)
            buffer[i + length] = (char)source.read ();
        assertTrue ("string incorrect", reference.equals (new String (buffer)));
        assertTrue ("extra character", -1 == source.read ());
        source.close ();
    }

    /**
     * Test ready.
     */
	public void testReady () throws IOException
    {
        Source source;
        
        source = new Source (new Stream (new ByteArrayInputStream (new byte[] { (byte)0x42, (byte)0x62 })), null);
        assertTrue ("ready?", !source.ready ());
        assertTrue ("erroneous character", 'B' == source.read ());
        assertTrue ("not ready", source.ready ());
        assertTrue ("erroneous character", 'b' == source.read ());
        assertTrue ("ready?", !source.ready ());
        assertTrue ("extra character", -1 == source.read ());
    }

    /**
     * Test that the same characters are returned as with another reader.
     */
    public void testSameChars () throws IOException
    {
        String link;
        ArrayList chars1;
        ArrayList chars2;
        URL url;
        URLConnection connection;
        InputStreamReader in;
        int c;
        Source source;
        int index;

        // pick a big file
        link = "http://sourceforge.net/projects/htmlparser/HTMLParser_Coverage.html";
        chars1 = new ArrayList ();
        chars2 = new ArrayList ();
	    try
	    {
	        url = new URL (link);
            connection = url.openConnection ();
            connection.connect ();
            in = new InputStreamReader (new BufferedInputStream (connection.getInputStream ()), DEFAULT_CHARSET);
            while (-1 != (c = in.read ()))
                chars1.add (new Character ((char)c));
            in.close ();

            connection = url.openConnection ();
            connection.connect ();
            source = new Source (new Stream (connection.getInputStream ()));
            while (-1 != (c = source.read ()))
                chars2.add (new Character ((char)c));
            source.close ();

            index = 0;
            while (index < chars1.size ())
            {
                assertEquals ("characters differ at position " + index, chars1.get (index), chars2.get (index));
                index++;
            }
            assertTrue ("extra characters", index == chars2.size ());
	    }
	    catch (MalformedURLException murle)
        {
            fail ("bad url " + link);
        }
    }
}

--- NEW FILE: StreamTests.java ---
// HTMLParser Library v1_4_20030525 - A java-based parser for HTML
// Copyright (C) Dec 31, 2000 Somik Raha
//
// 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
//
// For any questions or suggestions, you can write to me at :
// Email :so...@in...
// 
// Postal Address : 
// Somik Raha
// Extreme Programmer & Coach
// Industrial Logic Corporation
// 2583 Cedar Street, Berkeley, 
// CA 94708, USA
// Website : http://www.industriallogic.com

package org.htmlparser.tests.lexerTests;

import java.io.BufferedInputStream;
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 junit.framework.TestCase;

import org.htmlparser.lexer.Stream;

public class StreamTests extends TestCase
{
    /**
     * Test the first level stream class.
     */
	public StreamTests (String name)
    {
		super (name);
	}

    /**
     * Test initialization with a null value.
     */
	public void testNull () throws IOException
    {
        Stream stream;
        
        stream = new Stream (null);
        assertTrue ("erroneous character", -1 == stream.read ());
    }

    /**
     * Test initialization with an empty input stream.
     */
	public void testEmpty () throws IOException
    {
        Stream stream;
        
        stream = new Stream (new ByteArrayInputStream (new byte[0]));
        assertTrue ("erroneous character", -1 == stream.read ());
    }

    /**
     * Test initialization with an input stream having only one byte.
     */
	public void testOneByte () throws IOException
    {
        Stream stream;
        
        stream = new Stream (new ByteArrayInputStream (new byte[] { (byte)0x42 }));
        assertTrue ("erroneous character", 0x42 == stream.read ());
        assertTrue ("erroneous character", -1 == stream.read ());
    }

    /**
     * Test that the same bytes are returned as with a naked input stream.
     */
    public void testSameBytes () throws IOException
    {
        String link;
        ArrayList bytes1;
        ArrayList bytes2;
        URL url;
        URLConnection connection;
        BufferedInputStream in;
        int b;
        Stream stream;
        int index;

        // pick a big file
        link = "http://sourceforge.net/projects/htmlparser/HTMLParser_Coverage.html";
        bytes1 = new ArrayList ();
        bytes2 = new ArrayList ();
	    try
	    {
	        url = new URL (link);
            connection = url.openConnection ();
            connection.connect ();
            in = new BufferedInputStream (connection.getInputStream ());
            while (-1 != (b = in.read ()))
                bytes1.add (new Byte ((byte)b));
            in.close ();

            connection = url.openConnection ();
            connection.connect ();
            stream = new Stream (connection.getInputStream ());
            while (-1 != (b = stream.read ()))
                bytes2.add (new Byte ((byte)b));
            stream.close ();

            index = 0;
            while (index < bytes1.size ())
            {
                assertEquals ("bytes differ at position " + index, bytes1.get (index), bytes2.get (index));
                index++;
            }
            assertTrue ("extra bytes", index == bytes2.size ());
	    }
	    catch (MalformedURLException murle)
        {
            fail ("bad url " + link);
        }
    }

    /**
     * Test that threading works and is faster than a naked input stream.
     * This, admittedly contrived, test illustrates the following principles:
     * <li>the underlying network code is already multi-threaded, so there may
     * not be a need to use application level threading in most cases</li>
     * <li>results may vary based on network connection speed, JVM, and
     * especially application usage pattterns</li>
     * <li>issues only show up with large files, in my case greater than
     * about 72,400 bytes, since the underlying network code reads that far
     * into the socket before throttling back and waiting</li>
     * <li>this is only applicable to TCP/IP usage, disk access would not
     * have this problem, since the cost of reading disk is much less than
     * the round-trip cost of a TCP/IP handshake</li>
     * So, what does it do? It sets up to read a URL two ways, once with a
     * naked input stream, and then with the Stream class. In each case, before
     * reading, it delays about 2 seconds (for me anyway) to allow the java.net
     * implementation to read ahead and then throttle back. The threaded Stream
     * though keeps reading while this delay is going on and hence gets a big
     * chunk of the file in memory. This advantage translates to a faster
     * spin through the bytes after the delay. 
     */
    public void testThreaded () throws IOException
    {
        String link;
        URL url;
        URLConnection connection;
        BufferedInputStream in;
        int index;
        long begin;
        double bytes_per_second;
        int delay;
        Stream stream;
        long time1;
        long time2;
        Thread thread;
        long available1;
        long available2;

        // pick a big file
        link = "http://htmlparser.sourceforge.net/javadoc_1_3/index-all.html";
	    try
	    {
	        url = new URL (link);

            // estimate the connection speed
            System.gc ();
            index = 0;
            connection = url.openConnection ();
            connection.connect ();
            in = new BufferedInputStream (connection.getInputStream ());
            begin = System.currentTimeMillis ();
            while (-1 != in.read ())
                index++;
            bytes_per_second = 1000.0 * index / (System.currentTimeMillis () - begin);
            in.close ();

            delay = (int)(1.5 * 1000 * bytes_per_second / 72400); // 72400 is the throttle limit on my machine

            // try the naked input stream
            System.gc ();
            index = 0;
            available1 = 0;
            connection = url.openConnection ();
            connection.connect ();
            in = new BufferedInputStream (connection.getInputStream ());
            try
            {
                Thread.sleep (delay);
            }
            catch (Exception e)
            {
                e.printStackTrace ();
            }
            begin = System.currentTimeMillis ();
            do
            {
                index++;
                if (0 == index % 1000)
                    available1 += in.available ();
            }
            while (-1 != in.read ());
            time1 = System.currentTimeMillis () - begin;
            in.close ();

            // try a threaded stream
            System.gc ();
            index = 0;
            available2 = 0;
            connection = url.openConnection ();
            connection.connect ();
            int length = connection.getContentLength ();
            stream = new Stream (connection.getInputStream (), length);
            thread = new Thread (stream);
            thread.setPriority (Thread.NORM_PRIORITY - 1);
            thread.start ();
            try
            {
                Thread.sleep (delay);
            }
            catch (Exception e)
            {
                e.printStackTrace ();
            }
            begin = System.currentTimeMillis ();
            do
            {
                index++;
                if (0 == index % 1000)
                    available2 += stream.available ();
            }
            while (-1 != stream.read ());
            time2 = System.currentTimeMillis () - begin;

            System.out.println ("fills: " + stream.fills);
            System.out.println ("reallocations: " + stream.reallocations);
            System.out.println ("synchronous: " + stream.synchronous);
            System.out.println ("buffer size: " + stream.mBuffer.length);
            System.out.println ("bytes: " + stream.mLevel);
            stream.close ();

            System.out.println ("time (" + time2 + ") vs. (" + time1 + ") for " + index + " bytes");
            double samples = index / 1000;
            System.out.println ("average available bytes (" + available2/samples + ") vs. (" + available1/samples + ")");

            assertTrue ("slower (" + time2 + ") vs. (" + time1 + ")", time2 < time1);
            assertTrue ("average available bytes not greater (" + available2/samples + ") vs. (" + available1/samples + ")", available2 > available1);
	    }
	    catch (MalformedURLException murle)
        {
            fail ("bad url " + link);
        }
    }

    /**
     * Test that mark and reset work as per the contract.
     */
    public void testMarkReset () throws IOException
    {
        String link;
        ArrayList bytes1;
        ArrayList bytes2;
        URL url;
        URLConnection connection;
        Stream stream;
        int b;
        int index;

        // pick a small file > 2000 bytes
        link = "http://sourceforge.net/projects/htmlparser/overview-summary.html";
        bytes1 = new ArrayList ();
        bytes2 = new ArrayList ();
	    try
	    {
	        url = new URL (link);
            connection = url.openConnection ();
            connection.connect ();
            stream = new Stream (connection.getInputStream ());
            assertTrue ("mark not supported", stream.markSupported ());

            for (int i = 0; i < 1000; i++)
            {
                b = stream.read ();
                bytes1.add (new Byte ((byte)b));
            }
            stream.reset ();
            for (int i = 0; i < 1000; i++)
            {
                b = stream.read ();
                bytes2.add (new Byte ((byte)b));
            }
            
            index = 0;
            while (index < bytes1.size ())
            {
                assertEquals ("bytes differ at position " + index, bytes1.get (index), bytes2.get (index));
                index++;
            }
            
            bytes1.clear ();
            bytes2.clear ();

            stream.mark (1000); // the 1000 is ignored
            for (int i = 0; i < 1000; i++)
            {
                b = stream.read ();
                bytes1.add (new Byte ((byte)b));
            }
            stream.reset ();
            for (int i = 0; i < 1000; i++)
            {
                b = stream.read ();
                bytes2.add (new Byte ((byte)b));
            }
            stream.close ();

            index = 0;
            while (index < bytes1.size ())
            {
                assertEquals ("bytes differ at position " + (index + 1000), bytes1.get (index), bytes2.get (index));
                index++;
            }
	    }
	    catch (MalformedURLException murle)
        {
            fail ("bad url " + link);
        }
    }

    /**
     * Test that mark and reset work as per the contract when threaded.
     */
    public void testMarkResetThreaded () throws IOException
    {
        String link;
        ArrayList bytes1;
        ArrayList bytes2;
        URL url;
        URLConnection connection;
        Stream stream;
        int b;
        int index;

        // pick a small file > 2000 bytes
        link = "http://sourceforge.net/projects/htmlparser/overview-summary.html";
        bytes1 = new ArrayList ();
        bytes2 = new ArrayList ();
	    try
	    {
	        url = new URL (link);
            connection = url.openConnection ();
            connection.connect ();
            stream = new Stream (connection.getInputStream ());
            (new Thread (stream)).start ();
            assertTrue ("mark not supported", stream.markSupported ());

            for (int i = 0; i < 1000; i++)
            {
                b = stream.read ();
                bytes1.add (new Byte ((byte)b));
            }
            stream.reset ();
            for (int i = 0; i < 1000; i++)
            {
                b = stream.read ();
                bytes2.add (new Byte ((byte)b));
            }
            
            index = 0;
            while (index < bytes1.size ())
            {
                assertEquals ("bytes differ at position " + index, bytes1.get (index), bytes2.get (index));
                index++;
            }
            
            bytes1.clear ();
            bytes2.clear ();

            stream.mark (1000); // the 1000 is ignored
            for (int i = 0; i < 1000; i++)
            {
                b = stream.read ();
                bytes1.add (new Byte ((byte)b));
            }
            stream.reset ();
            for (int i = 0; i < 1000; i++)
            {
                b = stream.read ();
                bytes2.add (new Byte ((byte)b));
            }
            stream.close ();

            index = 0;
            while (index < bytes1.size ())
            {
                assertEquals ("bytes differ at position " + (index + 1000), bytes1.get (index), bytes2.get (index));
                index++;
            }
	    }
	    catch (MalformedURLException murle)
        {
            fail ("bad url " + link);
        }
    }

    /**
     * Test close.
     */
	public void testClose () throws IOException
    {
        Stream stream;
        
        stream = new Stream (new ByteArrayInputStream (new byte[] { (byte)0x42, (byte)0x78 }));
        assertTrue ("erroneous character", 0x42 == stream.read ());
        stream.close ();
        assertTrue ("not closed", -1 == stream.read ());
   }
}

[Htmlparser-cvs] htmlparser/src/org/htmlparser/lexer Page.java,NONE,1.1 Source.java,NONE,1.1 Stream.java,NONE,1.1

[<der...@us...>]

Update of /cvsroot/htmlparser/htmlparser/src/org/htmlparser/lexer
In directory sc8-pr-cvs1:/tmp/cvs-serv31631/org/htmlparser/lexer

Added Files:
	Page.java Source.java Stream.java 
Log Message:
Initial drop of new io subsystem.



--- NEW FILE: Page.java ---
// HTMLParser Library v1_4_20030525 - A java-based parser for HTML
// Copyright (C) Dec 31, 2000 Somik Raha
//
// 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
//
// For any questions or suggestions, you can write to me at :
// Email :so...@in...
// 
// Postal Address : 
// Somik Raha
// Extreme Programmer & Coach
// Industrial Logic Corporation
// 2583 Cedar Street, Berkeley, 
// CA 94708, USA
// Website : http://www.industriallogic.com

package org.htmlparser.lexer;

import java.io.IOException;
import java.io.Reader;
import java.io.UnsupportedEncodingException;
import java.lang.reflect.InvocationTargetException;
import java.lang.reflect.Method;
import java.net.URLConnection;

import org.apache.commons.logging.Log;
import org.apache.commons.logging.LogFactory;

/**
 * Represents the contents of an HTML page.
 * Contains a character array of the page downloaded so far,
 * a String with those characters in it,
 * and an index of positions of line separators (actually the first
 * character position on the next line).
 */
public class Page
{
    /**
     * The default charset.
     * This should be <code>ISO-8859-1</code>,
     * see RFC 2616 (http://www.ietf.org/rfc/rfc2616.txt?number=2616) section 3.7.1
     * Another alias is "8859_1".
     */
    public static final String DEFAULT_CHARSET = "ISO-8859-1";

    /**
     * The logging object.
     */
    protected static Log mLog = null;

    /**
     * The source of characters.
     */
    protected Source mSource;

    /**
     * The characters read so far from the source.
     */
    protected char[] mCharacters;
    
    /**
     * The string representation of the source.
     */
    protected String mString;

    /**
     * Character positions of the first character in each line.
     */
    protected int mIndex[];

    /**
     * The index position to be used next.
     */
    protected int mIndexLength;

    /**
     * Messages for page not there (404).
     */
    private String[] mFourOhFour =
    {
        "The web site you seek cannot be located, but countless more exist",
        "You step in the stream, but the water has moved on. This page is not here.",
        "Yesterday the page existed. Today it does not. The internet is like that.",
        "That page was so big. It might have been very useful. But now it is gone.",
        "Three things are certain: death, taxes and broken links. Guess which has occured.",
        "Chaos reigns within. Reflect, repent and enter the correct URL. Order shall return.",
        "Stay the patient course. Of little worth is your ire. The page is not found.",
        "A non-existant URL reduces your expensive computer to a simple stone.",
        "Many people have visited that page. Today, you are not one of the lucky ones.",
        "Cutting the wind with a knife. Bookmarking a URL. Both are ephemeral.",
    };

    /**
     * Construct a page reading from a URL.
     * @param connection A fully conditioned connection. The connect()
     * method will be called so it need not be connected yet.
     * @exception IOException If an i/o exception occurs creating the
     * source.
     * @exception UnsupportedEncodingException if the character set specified in the
     * HTTP header is not supported.
     */
    public Page (URLConnection connection)
        throws
            IOException,
            UnsupportedEncodingException
    {
        if (null == connection)
            throw new IllegalArgumentException ("connection cannot be null");
        connection.connect ();
        mSource = new Source (new Stream (connection.getInputStream ()), getCharacterSet (connection));
        mCharacters = null;
        mString = null;
        mIndex = null;
        mIndexLength = 0;
    }

    /**
     * Try and extract the character set from the HTTP header.
     * @param connection The connection with the charset info.
     * @return The character set name to use for this HTML page.
     */
    protected String getCharacterSet (URLConnection connection)
    {
        final String CONTENT_TYPE_STRING = "Content-Type";

        String string;
        String ret;
        
        ret = DEFAULT_CHARSET;
        string = connection.getHeaderField (CONTENT_TYPE_STRING);
        if (null != string)
            ret = getCharset (string);

        return (ret);
    }

    /**
     * Get a CharacterSet name corresponding to a charset parameter.
     * @param content A text line of the form:
     * <pre>
     * text/html; charset=Shift_JIS
     * </pre>
     * which is applicable both to the HTTP header field Content-Type and
     * the meta tag http-equiv="Content-Type".
     * Note this method also handles non-compliant quoted charset directives such as:
     * <pre>
     * text/html; charset="UTF-8"
     * </pre>
     * and
     * <pre>
     * text/html; charset='UTF-8'
     * </pre>
     * @return The character set name to use when reading the input stream.
     * For JDKs that have the Charset class this is qualified by passing
     * the name to findCharset() to render it into canonical form.
     * If the charset parameter is not found in the given string, the default
     * character set is returned.
     * @see ParserHelper#findCharset
     * @see #DEFAULT_CHARSET
     */
    protected String getCharset (String content)
    {
        final String CHARSET_STRING = "charset";
        int index;
        String ret;

        ret = DEFAULT_CHARSET;
        if (null != content)
        {
			index = content.indexOf (CHARSET_STRING);
            
            if (index != -1)
            {
                content = content.substring (index + CHARSET_STRING.length ()).trim ();
                if (content.startsWith ("="))
                {
                    content = content.substring (1).trim ();
                    index = content.indexOf (";");
                    if (index != -1)
                        content = content.substring (0, index);

					//remove any double quotes from around charset string
                    if (content.startsWith ("\"") && content.endsWith ("\"") && (1 < content.length ()))
                        content = content.substring (1, content.length () - 1);

                    //remove any single quote from around charset string
                    if (content.startsWith ("'") && content.endsWith ("'") && (1 < content.length ()))
                        content = content.substring (1, content.length () - 1);

                    ret = findCharset (content, ret);

                    // Charset names are not case-sensitive;
                    // that is, case is always ignored when comparing charset names.
                    if (!ret.equalsIgnoreCase (content))
					{
                        getLog ().info (
                            "detected charset \""
                            + content
                            + "\", using \""
                            + ret
                            + "\"");
					}
                }
            }
        }

        return (ret);
    }

	/**
	 * Lookup a character set name.
	 * <em>Vacuous for JVM's without <code>java.nio.charset</code>.</em>
	 * This uses reflection so the code will still run under prior JDK's but
	 * in that case the default is always returned.
	 * @param name The name to look up. One of the aliases for a character set.
	 * @param _default The name to return if the lookup fails.
	 */
	public String findCharset (String name, String _default)
	{
		String ret;
        
		try
		{
			Class cls;
			Method method;
			Object object;

            cls = Class.forName ("java.nio.charset.Charset");
			method = cls.getMethod ("forName", new Class[] { String.class });
			object = method.invoke (null, new Object[] { name });
			method = cls.getMethod ("name", new Class[] { });
			object = method.invoke (object, new Object[] { });
			ret = (String)object;
		}
		catch (ClassNotFoundException cnfe)
		{
			// for reflection exceptions, assume the name is correct
			ret = name;
		}
		catch (NoSuchMethodException nsme)
		{
			// for reflection exceptions, assume the name is correct
			ret = name;
		}
		catch (IllegalAccessException ia)
		{
			// for reflection exceptions, assume the name is correct
			ret = name;
		}
		catch (InvocationTargetException ita)
		{
			// java.nio.charset.IllegalCharsetNameException
			// and java.nio.charset.UnsupportedCharsetException
			// return the default
			ret = _default;
            getLog ().debug (
                "unable to determine cannonical charset name for "
                + name
                + " - using "
                + _default,
                ita);
		}
        
		return (ret);
	}

    //
    // Bean patterns
    //

    public Log getLog ()
    {
        if (null == mLog)
            mLog = LogFactory.getLog (this.getClass ());
//        String name = this.getClass ().getName ();
//        java.util.logging.Logger logger = java.util.logging.Logger.getLogger (name);
//        logger.setLevel (java.util.logging.Level.FINEST);
        return (mLog);
    }
}

--- NEW FILE: Source.java ---
// HTMLParser Library v1_4_20030525 - A java-based parser for HTML
// Copyright (C) Dec 31, 2000 Somik Raha
//
// 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
//
// For any questions or suggestions, you can write to me at :
// Email :so...@in...
// 
// Postal Address : 
// Somik Raha
// Extreme Programmer & Coach
// Industrial Logic Corporation
// 2583 Cedar Street, Berkeley, 
// CA 94708, USA
// Website : http://www.industriallogic.com

package org.htmlparser.lexer;

import java.io.IOException;
import java.io.InputStreamReader;
import java.io.Reader;
import java.io.UnsupportedEncodingException;

/**
 * A buffered source of characters.
 * A Source is very similar to a the following construct:
 * <pre>
 * new InputStreamReader (new BufferedInputStream (connection.getInputStream ()), charset)
 * </pre>
 * It differs from the above, in two ways:
 * <li>the fetching of bytes from the connection's input stream may be asynchronous</li>
 * <li>the character set may be changed, which resets the input stream</li>
 * 
 */
public class Source extends Reader
{
    /**
     * An initial buffer size.
     */
    protected static final int BUFFER_SIZE = 4096;

    /**
     * Return value when no more characters are left.
     */
    public static final int EOF = -1;

    /**
     * The stream of bytes.
     */
    protected Stream mStream;

    /**
     * The converter from bytes to characters.
     */
    protected InputStreamReader mReader;

    /**
     * The characters read so far.
     */
    public volatile char[] mBuffer;

    /**
     * The number of valid bytes in the buffer.
     */
    public volatile int mLevel;

    /**
     * The offset of the next byte returned by read().
     */
    protected int mOffset;

    /**
     * The bookmark.
     */
    protected int mMark;

    /**
     * Create a source of characters using the default character set.
     * @param stream The stream of bytes to use.
     */
    public Source (Stream stream)
        throws
            UnsupportedEncodingException
    {
        this (stream, null);
    }

    /**
     * Create a source of characters.
     * @param stream The stream of bytes to use.
     * @param charset The character set used in encoding the stream.
     */
    public Source (Stream stream, String charset)
        throws
            UnsupportedEncodingException
    {
        if (null == stream)
            stream = new Stream (null);
        mStream = stream;
        if (null == charset)
            mReader = new InputStreamReader (stream);
        else
            mReader = new InputStreamReader (stream, charset);
        mBuffer = null;
        mLevel = 0;
        mOffset = 0;
        mMark = -1;
    }

    /**
     * Fetch more characters from the underlying reader.
     * Has no effect if the underlying reader has been drained.
     * @param min The minimum to read.
     * @exception IOException If the underlying reader read() throws one.
     */
    protected void fill (int min)
        throws
            IOException
    {
        char[] buffer;
        int read;

        if (null != mReader) // mReader goes null when it's been sucked dry
        {
            // get some buffer space
            // unknown length... keep doubling
            if (null == mBuffer)
            {
                mBuffer = new char[Math.max (BUFFER_SIZE, min)];
                buffer = mBuffer;
            }
            else
            {
                read = Math.max (BUFFER_SIZE / 2, min);
                if (mBuffer.length - mLevel < read)
                    buffer = new char[Math.max (mBuffer.length * 2, mBuffer.length + min)];
                else
                    buffer = mBuffer;
            }

            // read into the end of the 'new' buffer
            read = mReader.read (buffer, mLevel, buffer.length - mLevel);
            if (-1 == read)
            {
                mReader.close ();
                mReader = null;
            }
            else
            {
                if (mBuffer != buffer)
                {   // copy the bytes previously read
                    System.arraycopy (mBuffer, 0, buffer, 0, mLevel);
                    mBuffer = buffer;
                }
                mLevel += read;
            }
        }
    }

    //
    // Reader overrides
    //

    /**
     * Close the stream.  Once a stream has been closed, further read(),
     * ready(), mark(), or reset() invocations will throw an IOException.
     * Closing a previously-closed stream, however, has no effect.
     * @exception IOException  If an I/O error occurs
     */
    public void close () throws IOException
    {
        mStream = null;
        if (null != mReader)
            mReader.close ();
        mReader = null;
        mBuffer = null;
        mLevel = 0;
        mOffset = 0;
        mMark = -1;
    }
    
    /**
     * Read a single character.
     * This method will block until a character is available,
     * an I/O error occurs, or the end of the stream is reached.
     * @return The character read, as an integer in the range 0 to 65535
     * (<tt>0x00-0xffff</tt>), or -1 if the end of the stream has
     * been reached
     * @exception IOException If an I/O error occurs.
     */
    public int read () throws IOException
    {
        int ret;
        
        if (null == mStream) // mStream goes null on close()
            throw new IOException ("reader is closed");
        if (mLevel - mOffset < 1)
            fill (1);
        if (mOffset >= mLevel)
            ret = EOF;
        else
        {
            ret = mBuffer[mOffset];
            mOffset++;
        }
            
        return (ret);
    }
    
    /**
     * Read characters into a portion of an array.  This method will block
     * until some input is available, an I/O error occurs, or the end of the
     * stream is reached.
     * @param cbuf Destination buffer
     * @param off Offset at which to start storing characters
     * @param len Maximum number of characters to read
     * @return The number of characters read, or -1 if the end of the
     * stream has been reached
     * @exception IOException If an I/O error occurs.
     */
    public int read (char[] cbuf, int off, int len) throws IOException
    {
        int ret;

        if (null == mStream) // mStream goes null on close()
            throw new IOException ("reader is closed");
        if ((null == cbuf) || (0 > off) || (0 > len))
            throw new IOException ("illegal argument read ("
                + ((null == cbuf) ? "null" : "cbuf")
                + ", " + off + ", " + len + ")");
        if (mLevel - mOffset < len)
            fill (len - (mLevel - mOffset)); // minimum to satisfy this request
        if (mOffset >= mLevel)
            ret = EOF;
        else
        {
            ret = Math.min (mLevel - mOffset, len);
            System.arraycopy (mBuffer, mOffset, cbuf, off, ret);
            mOffset += ret;
        }
            
        return (ret);
    }
    
    /**
     * Reset the stream.  If the stream has been marked, then attempt to
     * reposition it at the mark.  If the stream has not been marked, then
     * attempt to reset it in some way appropriate to the particular stream,
     * for example by repositioning it to its starting point.  Not all
     * character-input streams support the reset() operation, and some support
     * reset() without supporting mark().
     * @exception  IOException  If the stream has not been marked,
     * or if the mark has been invalidated,
     * or if the stream does not support reset(),
     * or if some other I/O error occurs
     */
    public void reset () throws IOException
    {
        if (null == mStream) // mStream goes null on close()
            throw new IOException ("reader is closed");
        if (-1 != mMark)
            mOffset = mMark;
        else
            mOffset = 0;
    }
    
    /**
     * Tell whether this stream supports the mark() operation. 
     * @return <code>true</code> if and only if this stream supports the mark operation.
     */
    public boolean markSupported ()
    {
        return (true);
    }
    
    /**
     * Mark the present position in the stream.  Subsequent calls to reset()
     * will attempt to reposition the stream to this point.  Not all
     * character-input streams support the mark() operation.
     * @param  readAheadLimit <em>Not used.</em>
     * @exception IOException <em>Never thrown</em>.
     *
     */
    public void mark (int readAheadLimit) throws IOException
    {
        if (null == mStream) // mStream goes null on close()
            throw new IOException ("reader is closed");
        mMark = mOffset;
    }
    
    /**
     * Tell whether this stream is ready to be read.
     * @return <code>true</code> if the next read() is guaranteed not to block
     * for input, <code>false</code> otherwise.
     * Note that returning false does not guarantee that the next read will block.
     * @exception IOException <em>Never thrown</em>.
     */
    public boolean ready () throws IOException
    {
        if (null == mStream) // mStream goes null on close()
            throw new IOException ("reader is closed");
        return (mOffset < mLevel);
    }
    
    /**
     * Skip characters.
     * This method will block until some characters are available,
     * an I/O error occurs, or the end of the stream is reached.
     * <em>Note: n is treated as an int</em>
     * @param n The number of characters to skip.
     * @return The number of characters actually skipped
     * @exception IllegalArgumentException If <code>n</code> is negative.
     * @exception IOException If an I/O error occurs.
     */
    public long skip (long n) throws IOException
    {
        long ret;

        if (null == mStream) // mStream goes null on close()
            throw new IOException ("reader is closed");
        if (mLevel - mOffset < n)
            fill ((int)(n - (mLevel - mOffset))); // minimum to satisfy this request
        if (mOffset >= mLevel)
            ret = EOF;
        else
        {
            ret = Math.min (mLevel - mOffset, n);
            mOffset += ret;
        }
        
        return (ret);
    }
}

--- NEW FILE: Stream.java ---
// HTMLParser Library v1_4_20030525 - A java-based parser for HTML
// Copyright (C) Dec 31, 2000 Somik Raha
//
// 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
//
// For any questions or suggestions, you can write to me at :
// Email :so...@in...
// 
// Postal Address : 
// Somik Raha
// Extreme Programmer & Coach
// Industrial Logic Corporation
// 2583 Cedar Street, Berkeley, 
// CA 94708, USA
// Website : http://www.industriallogic.com

package org.htmlparser.lexer;

import java.io.IOException;
import java.io.InputStream;
import java.lang.Runnable;

/**
 * Provides for asynchronous fetching from a stream.
 * 
 */
public class Stream extends InputStream implements Runnable
{
    public int fills = 0;
    public int reallocations = 0;
    public int synchronous = 0;

    /**
     * An initial buffer size.
     */
    protected static final int BUFFER_SIZE = 4096;

    /**
     * Return value when no more characters are left.
     */
    protected static final int EOF = -1;

    /**
     * The underlying stream.
     */
    protected volatile InputStream mIn;

    /**
     * The bytes read so far.
     */
    public volatile byte[] mBuffer;

    /**
     * The number of valid bytes in the buffer.
     */
    public volatile int mLevel;

    /**
     * The offset of the next byte returned by read().
     */
    protected int mOffset;

    /**
     * The content length from the HTTP header.
     */
    protected int mContentLength;

    /**
     * The bookmark.
     */
    protected int mMark;

    /**
     * Construct a stream with no assumptions about the number of bytes available.
     * @param in The input stream to use.
     */
    public Stream (InputStream in)
    {
        this (in, 0);
    }

    /**
     * Construct a stream to read the given number of bytes.
     * @param in The input stream to use.
     * @param bytes The maximum number of bytes to read.
     * This should be set to the ContentLength from the HTTP header.
     * A negative or zero value indicates an unknown number of bytes.
     */
    public Stream (InputStream in, int bytes)
    {
        mIn = in;
        mBuffer = null;
        mLevel = 0;
        mOffset = 0;
        mContentLength = bytes < 0 ? 0 : bytes;
        mMark = -1;
    }

    /**
     * Fetch more bytes from the underlying stream.
     * Has no effect if the underlying stream has been drained.
     * @param force If <code>true</code>, an attempt is made to read from the
     * underlying stream, even if bytes are available, If <code>false</code>,
     * a read of the underlying stream will not occur if there are already
     * bytes available.
     * @return <code>true</code> if not at the end of the input stream.
     * @exception IOException If the underlying stream read() or available() throws one.
     */
    protected synchronized boolean fill (boolean force)
        throws
            IOException
    {
        int size;
        byte[] buffer;
        int read;
        boolean ret;

        ret = false;

        if (null != mIn) // mIn goes null when it's been sucked dry
        {
            if (!force)
            {   // check for change of state while waiting on the monitor in a synchronous call
                if (0 != available ())
                    return (true);
                synchronous++;
            }

            // get some buffer space
            if (0 == mContentLength)
            {   // unknown content length... keep doubling
                if (null == mBuffer)
                {
                    mBuffer = new byte[Math.max (BUFFER_SIZE, mIn.available ())];
                    buffer = mBuffer;
                }
                else
                {   
                    if (mBuffer.length - mLevel < BUFFER_SIZE / 2)
                        buffer = new byte[Math.max (mBuffer.length * 2, mBuffer.length + mIn.available ())];
                    else
                        buffer = mBuffer;
                }
                size = buffer.length - mLevel;
            }
            else
            {   // known content length... allocate once
                size = mContentLength - mLevel;
                if (null == mBuffer)
                    mBuffer =  new byte[size];
                buffer = mBuffer;
            }

            // read into the end of the 'new' buffer
            read = mIn.read (buffer, mLevel, size);
            if (-1 == read)
            {
                mIn.close ();
                mIn = null;
            }
            else
            {
                if (mBuffer != buffer)
                {   // copy the bytes previously read
                    System.arraycopy (mBuffer, 0, buffer, 0, mLevel);
                    mBuffer = buffer;
                    reallocations++;
                }
                mLevel += read;
                if ((0 != mContentLength) && (mLevel == mContentLength))
                {
                    mIn.close ();
                    mIn = null;
                }
                ret = true;
                fills++;
            }
        }

        return (ret);
    }

    //
    // Runnable interface
    //

    /**
     * Continually read the underlying stream untill exhausted.
     * @see java.lang.Thread#run()
     */
    public void run ()
    {
        boolean filled;

        do
        {   // keep hammering the socket with no delay, it's metered upstream
            try
            {
                filled = fill (true);
            }
            catch (IOException ioe)
            {
                ioe.printStackTrace ();
                // exit the thread if there is a problem,
                // let the synchronous reader find out about it
                filled = false;
            }
        }
        while (filled);
    }

    //
    // InputStream overrides
    //

    /**
     * Reads the next byte of data from the input stream. The value byte is
     * returned as an <code>int</code> in the range <code>0</code> to
     * <code>255</code>. If no byte is available because the end of the stream
     * has been reached, the value <code>-1</code> is returned. This method
     * blocks until input data is available, the end of the stream is detected,
     * or an exception is thrown.
     * @return  The next byte of data, or <code>-1</code> if the end of the
     * stream is reached.
     * @exception IOException If an I/O error occurs.
     */
    public int read () throws IOException
    {
        int ret;

        // The following is unsynchronized code.
        // Some would argue that unsynchronized access isn't thread safe
        // but I think I can rationalize it in this case...
        // The two volatile members are mLevel and mBuffer (besides mIn).
        // If (mOffset >= mLevel) turns false after the test, fill is
        // superflously called, but it's synchronized and figures it out.
        // (mOffset < mLevel) only goes more true by the operation of the
        // background thread, it increases the value of mLevel
        // and volatile int access is atomic.
        // If mBuffer changes by the operation of the background thread,
        // the array pointed to can only be bigger than the previous buffer,
        // and hence no array bounds exception can be raised.
        if (0 == available ())
            fill (false);
        if (0 != available ())
            ret = mBuffer[mOffset++];
        else
            ret = EOF;
        
        return (ret);
    }
    
    /**
     * Returns the number of bytes that can be read (or skipped over) from
     * this input stream without blocking by the next caller of a method for
     * this input stream.  The next caller might be the same thread or or
     * another thread.
     * @return The number of bytes that can be read from this input stream
     * without blocking.
     * @exception IOException If an I/O error occurs.
     */
    public int available () throws IOException
    {
        return (mLevel - mOffset);
    }
    
    /**
     * Closes this input stream and releases any system resources associated
     * with the stream.
     * @exception IOException If an I/O error occurs.
     */
    public synchronized void close () throws IOException
    {
        if (null != mIn)
        {
            mIn.close ();
            mIn = null;
        }
        mBuffer = null;
        mLevel = 0;
        mOffset = 0;
        mContentLength =0;
        mMark = -1;
    }
    
    /**
     * Repositions this stream to the position at the time the
     * <code>mark</code> method was last called on this input stream.
     *
     * <p> The general contract of <code>reset</code> is:
     *
     * <p><ul>
     *
     * <li> If the method <code>markSupported</code> returns
     * <code>true</code>, then:
     *
     *     <ul><li> If the method <code>mark</code> has not been called since
     *     the stream was created, or the number of bytes read from the stream
     *     since <code>mark</code> was last called is larger than the argument
     *     to <code>mark</code> at that last call, then an
     *     <code>IOException</code> might be thrown.
     *
     *     <li> If such an <code>IOException</code> is not thrown, then the
     *     stream is reset to a state such that all the bytes read since the
     *     most recent call to <code>mark</code> (or since the start of the
     *     file, if <code>mark</code> has not been called) will be resupplied
     *     to subsequent callers of the <code>read</code> method, followed by
     *     any bytes that otherwise would have been the next input data as of
     *     the time of the call to <code>reset</code>. </ul>
     *
     * <li> If the method <code>markSupported</code> returns
     * <code>false</code>, then:
     *
     *     <ul><li> The call to <code>reset</code> may throw an
     *     <code>IOException</code>.
     *
     *     <li> If an <code>IOException</code> is not thrown, then the stream
     *     is reset to a fixed state that depends on the particular type of the
     *     input stream and how it was created. The bytes that will be supplied
     *     to subsequent callers of the <code>read</code> method depend on the
     *     particular type of the input stream. </ul></ul>
     *
     * @exception IOException <em>Never thrown. Just for subclassers.</em>
     * @see java.io.InputStream#mark(int)
     * @see java.io.IOException
     *
     */
    public void reset () throws IOException
    {
        if (-1 != mMark)
            mOffset = mMark;
        else
            mOffset = 0;
    }
    
    /**
     * Tests if this input stream supports the <code>mark</code> and
     * <code>reset</code> methods. Whether or not <code>mark</code> and
     * <code>reset</code> are supported is an invariant property of a
     * particular input stream instance. The <code>markSupported</code> method
     * of <code>InputStream</code> returns <code>false</code>.
     *
     * @return <code>true</code>.
     * @see java.io.InputStream#mark(int)
     * @see java.io.InputStream#reset()
     *
     */
    public boolean markSupported ()
    {
        return (true);
    }
    
    /**
     * Marks the current position in this input stream. A subsequent call to
     * the <code>reset</code> method repositions this stream at the last marked
     * position so that subsequent reads re-read the same bytes.
     *
     * <p> The <code>readlimit</code> arguments tells this input stream to
     * allow that many bytes to be read before the mark position gets
     * invalidated.
     *
     * <p> The general contract of <code>mark</code> is that, if the method
     * <code>markSupported</code> returns <code>true</code>, the stream somehow
     * remembers all the bytes read after the call to <code>mark</code> and
     * stands ready to supply those same bytes again if and whenever the method
     * <code>reset</code> is called.  However, the stream is not required to
     * remember any data at all if more than <code>readlimit</code> bytes are
     * read from the stream before <code>reset</code> is called.
     *
     * @param readlimit <em>Not used.</em>
     * @see java.io.InputStream#reset()
     *
     */
    public void mark (int readlimit)
    {
        mMark = mOffset;
    }
}

[Htmlparser-cvs] htmlparser/src/org/htmlparser/tests/utilTests BeanTest.java,1.31,1.32

[<der...@us...>]

Update of /cvsroot/htmlparser/htmlparser/src/org/htmlparser/tests/utilTests
In directory sc8-pr-cvs1:/tmp/cvs-serv24819/org/htmlparser/tests/utilTests

Modified Files:
	BeanTest.java 
Log Message:
More tests.
testOutputWithPreAndScriptTags is now correct, I think.
The overarching goal of StringBean is to return the text, and only the text, that a user would see in a browser. When I open this html in Netscape I see nothing:

<body><pre>
<script language=\"javascript\">
if(navigator.appName.indexOf(\"Netscape\") != -1)
 document.write ('xxx');
else
 document.write ('yyy');
</script>
</pre></body>

That's what StringBean says too.

Although this points out a flaw in the specification (such as it is, see the StringBean javadoc):

 * Text within <SCRIPT></SCRIPT> tags is removed.
 * The text within <PRE></PRE> tags is not altered.

So what happens when there's both?
The 'not altered' means, not collapsed, not that the HTML is returned literally.
To test this out, see how Netscape handles:

<body><pre>
<b>Hello
World</b>
</pre></body>

For me it shows:

Hello
World

which means it consumes (and honours) the bold tags even though it is within <pre></pre>
So the StringBean <pre> handling is correct, or so it seems.

I guess that most questions can be answered by submitting it to a browser.




Index: BeanTest.java
===================================================================
RCS file: /cvsroot/htmlparser/htmlparser/src/org/htmlparser/tests/utilTests/BeanTest.java,v
retrieving revision 1.31
retrieving revision 1.32
diff -C2 -d -r1.31 -r1.32
*** BeanTest.java	16 Jul 2003 20:05:07 -0000	1.31
--- BeanTest.java	17 Jul 2003 00:56:47 -0000	1.32
***************
*** 405,413 ****
  		check (sb, "<body>"+sampleScript+"</body>", "");
  	}
! 	
  	/**
  	 * Test output with pre and script tags
  	 */
! 	public void xtestOutputWithPreAndScriptTags() {
  		StringBean sb;
  		sb = new StringBean ();
--- 405,469 ----
  		check (sb, "<body>"+sampleScript+"</body>", "");
  	}
! 
!     /*
! 	 * Test output with pre and any tag.
! 	 */
! 	public void testOutputWithPreAndAnyTag()
!     {
!         StringBean sb;
! 
!         sb = new StringBean ();
!         sb.setLinks (false);
!         sb.setReplaceNonBreakingSpaces (true);
!         sb.setCollapse (false);
!         check (sb, "<html><head></head><body><pre><hello></pre></body></html>", "");
!     }
! 
!     /*
! 	 * Test output with pre and any tag and text.
! 	 */
! 	public void testOutputWithPreAndAnyTagPlusText()
!     {
!         StringBean sb;
! 
!         sb = new StringBean ();
!         sb.setLinks (false);
!         sb.setReplaceNonBreakingSpaces (true);
!         sb.setCollapse (false);
!         check (sb, "<html><head></head><body><pre><hello>dogfood</hello></pre></body></html>", "dogfood");
!     }
! 
!     /*
! 	 * Test output with pre and any tag and text.
! 	 */
! 	public void testOutputWithPreAndAnyTagPlusTextWithWhitespace()
!     {
!         StringBean sb;
! 
!         sb = new StringBean ();
!         sb.setLinks (false);
!         sb.setReplaceNonBreakingSpaces (true);
!         sb.setCollapse (true);
!         check (sb, "<html><head></head><body><pre><hello>dog  food</hello></pre></body></html>", "dog  food");
!     }
! 
!     /*
! 	 * Test output without pre and any tag and text.
! 	 */
! 	public void testOutputWithoutPreAndAnyTagPlusTextWithWhitespace()
!     {
!         StringBean sb;
! 
!         sb = new StringBean ();
!         sb.setLinks (false);
!         sb.setReplaceNonBreakingSpaces (true);
!         sb.setCollapse (true);
!         check (sb, "<html><head></head><body><hello>dog  food</hello></body></html>", "dog food");
!     }
! 
  	/**
  	 * Test output with pre and script tags
  	 */
! 	public void testOutputWithPreAndScriptTags() {
  		StringBean sb;
  		sb = new StringBean ();
***************
*** 421,425 ****
  		+ "</script>\r\n";
  		
! 		check (sb, "<body><pre>"+sampleScript+"</pre></body>", sampleScript);
  	}
      
--- 477,481 ----
  		+ "</script>\r\n";
  		
! 		check (sb, "<body><pre>"+sampleScript+"</pre></body>", "");
  	}
      

[Htmlparser-cvs] htmlparser/src/org/htmlparser/tests/utilTests BeanTest.java,1.30,1.31

[<jke...@us...>]

Update of /cvsroot/htmlparser/htmlparser/src/org/htmlparser/tests/utilTests
In directory sc8-pr-cvs1:/tmp/cvs-serv8877/src/org/htmlparser/tests/utilTests

Modified Files:
	BeanTest.java 
Log Message:
added some more BeanTests, including one that is Xed out, as I think it may uncover a bug

Index: BeanTest.java
===================================================================
RCS file: /cvsroot/htmlparser/htmlparser/src/org/htmlparser/tests/utilTests/BeanTest.java,v
retrieving revision 1.30
retrieving revision 1.31
diff -C2 -d -r1.30 -r1.31
*** BeanTest.java	16 Jul 2003 00:17:23 -0000	1.30
--- BeanTest.java	16 Jul 2003 20:05:07 -0000	1.31
***************
*** 377,380 ****
--- 377,427 ----
          check (sb, "<html><head></head><body>\t\t x</body></html>", "x");
      }
+     
+ 	/**
+ 	 * Test text including a "pre" tag
+ 	 */
+ 	public void testOutputWithPreTags() {
+ 		StringBean sb;
+ 		sb = new StringBean ();
+ 		String sampleCode = "public class Product {}";
+ 		check (sb, "<body><pre>"+sampleCode+"</pre></body>", sampleCode);
+ 	}
+     
+ 	/**
+ 	 * Test text including a "script" tag
+ 	 */
+ 	public void testOutputWithScriptTags() {
+ 		StringBean sb;
+ 		sb = new StringBean ();
+ 		
+ 		String sampleScript =
+ 		  "<script language=\"javascript\">\r\n"
+ 		+ "if(navigator.appName.indexOf(\"Netscape\") != -1)\r\n" 
+ 		+ " document.write ('xxx');\r\n" 
+ 		+ "else\r\n"
+ 		+ " document.write ('yyy');\r\n"
+ 		+ "</script>\r\n";
+ 		
+ 		check (sb, "<body>"+sampleScript+"</body>", "");
+ 	}
+ 	
+ 	/**
+ 	 * Test output with pre and script tags
+ 	 */
+ 	public void xtestOutputWithPreAndScriptTags() {
+ 		StringBean sb;
+ 		sb = new StringBean ();
+ 		
+ 		String sampleScript =
+ 		  "<script language=\"javascript\">\r\n"
+ 		+ "if(navigator.appName.indexOf(\"Netscape\") != -1)\r\n" 
+ 		+ " document.write ('xxx');\r\n" 
+ 		+ "else\r\n"
+ 		+ " document.write ('yyy');\r\n"
+ 		+ "</script>\r\n";
+ 		
+ 		check (sb, "<body><pre>"+sampleScript+"</pre></body>", sampleScript);
+ 	}
+     
  }
  

[Htmlparser-cvs] htmlparser/src/org/htmlparser/tests/utilTests AllTests.java,1.39,1.40 BeanTest.java,1.29,1.30

[<der...@us...>]

Update of /cvsroot/htmlparser/htmlparser/src/org/htmlparser/tests/utilTests
In directory sc8-pr-cvs1:/tmp/cvs-serv6564/org/htmlparser/tests/utilTests

Modified Files:
	AllTests.java BeanTest.java 
Log Message:
Add some StringBean tests for Joshua.



Index: AllTests.java
===================================================================
RCS file: /cvsroot/htmlparser/htmlparser/src/org/htmlparser/tests/utilTests/AllTests.java,v
retrieving revision 1.39
retrieving revision 1.40
diff -C2 -d -r1.39 -r1.40
*** AllTests.java	13 Jul 2003 12:15:12 -0000	1.39
--- AllTests.java	16 Jul 2003 00:17:23 -0000	1.40
***************
*** 46,52 ****
  	super(name);
  }
! public static void main(String[] args) {
! 	new junit.awtui.TestRunner().start(new String[] {"org.htmlparser.tests.AllTests"});
! }
  /**
   * Insert the method's description here.
--- 46,113 ----
  	super(name);
  }
! 
!     /**
!      * Mainline for all suites of tests.
!      * @param args Command line arguments. The following options
!      * are understood:
!      * <pre>
!      * -text  -- use junit.textui.TestRunner
!      * -awt   -- use junit.awtui.TestRunner
!      * -swing -- use junit.swingui.TestRunner (default)
!      * </pre>
!      * All other options are passed on to the junit framework.
!      */
! 	public static void main(String[] args)
!     {
!         String runner;
!         int i;
!         String arguments[];
!         Class cls;
! 
!         runner = null;
!         for (i = 0; (i < args.length) && (null == runner); i++)
!         {
!             if (args[i].equalsIgnoreCase ("-text"))
!                 runner = "junit.textui.TestRunner";
!             else if (args[i].equalsIgnoreCase ("-awt"))
!                 runner = "junit.awtui.TestRunner";
!             else if (args[i].equalsIgnoreCase ("-swing"))
!                 runner = "junit.swingui.TestRunner";
!         }
!         if (null != runner)
!         {
!             // remove it from the arguments
!             arguments = new String[args.length - 1];
!             System.arraycopy (args, 0, arguments, 0, i - 1);
!             System.arraycopy (args, i, arguments, i - 1, args.length - i);
!             args = arguments;
!         }
!         else
!             runner = "junit.swingui.TestRunner";
! 
!         // append the test class
!         arguments = new String[args.length + 1];
!         System.arraycopy (args, 0, arguments, 0, args.length);
!         arguments[args.length] = "org.htmlparser.tests.utilTests.AllTests";
! 
!         // invoke main() of the test runner
!         try
!         {
!             cls = Class.forName (runner);
!             java.lang.reflect.Method method = cls.getDeclaredMethod (
!                 "main", new Class[] { String[].class });
!             method.invoke (
!                 null,
!                 new Object[] { arguments });
!         }
!         catch (Throwable t)
!         {
!             System.err.println (
!                 "cannot run unit test ("
!                 + t.getMessage ()
!                 + ")");
!         }
! 	}
! 
  /**
   * Insert the method's description here.

Index: BeanTest.java
===================================================================
RCS file: /cvsroot/htmlparser/htmlparser/src/org/htmlparser/tests/utilTests/BeanTest.java,v
retrieving revision 1.29
retrieving revision 1.30
diff -C2 -d -r1.29 -r1.30
*** BeanTest.java	13 Jul 2003 12:15:12 -0000	1.29
--- BeanTest.java	16 Jul 2003 00:17:23 -0000	1.30
***************
*** 33,39 ****
--- 33,42 ----
  import java.io.ByteArrayInputStream;
  import java.io.ByteArrayOutputStream;
+ import java.io.File;
+ import java.io.FileWriter;
  import java.io.IOException;
  import java.io.ObjectInputStream;
  import java.io.ObjectOutputStream;
+ import java.io.PrintWriter;
  import java.net.URL;
  import java.util.Vector;
***************
*** 89,92 ****
--- 92,129 ----
      }
  
+     /**
+      * Makes sure that the bean returns text when passed the html.
+      */
+     protected void check (StringBean bean, String html, String text)
+     {
+         String path;
+         File file;
+         PrintWriter out;
+         String string;
+         
+         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.println (html);
+             out.close ();
+             bean.setURL (file.getAbsolutePath ());
+             string = bean.getStrings ();
+         }
+         catch (Exception e)
+         {
+             fail (e.toString ());
+             string = null; // never reached
+         }
+         finally
+         {
+             file.delete ();
+         }
+         assertEquals ("stringbean text differs", text, string);
+     }
+ 
      public void testZeroArgConstructor ()
          throws
***************
*** 266,269 ****
--- 303,379 ----
              "Links property change not fired for URL change",
              hit[0].booleanValue ());
+     }
+ 
+     /**
+      * Test no text returns empty string.
+      */
+     public void testCollapsed1 ()
+     {
+         StringBean sb;
+ 
+         sb = new StringBean ();
+         sb.setLinks (false);
+         sb.setReplaceNonBreakingSpaces (true);
+         sb.setCollapse (false);
+         check (sb, "<html><head></head><body></body></html>", "");
+         check (sb, "<html><head></head><body> </body></html>", " ");
+         check (sb, "<html><head></head><body>\t</body></html>", "\t");
+         sb.setCollapse (true);
+         check (sb, "<html><head></head><body></body></html>", "");
+         check (sb, "<html><head></head><body> </body></html>", "");
+         check (sb, "<html><head></head><body>\t</body></html>", "");
+     }
+ 
+     /**
+      * Test multiple whitespace returns empty string.
+      */
+     public void testCollapsed2 ()
+     {
+         StringBean sb;
+ 
+         sb = new StringBean ();
+         sb.setLinks (false);
+         sb.setReplaceNonBreakingSpaces (true);
+         sb.setCollapse (false);
+         check (sb, "<html><head></head><body>  </body></html>", "  ");
+         check (sb, "<html><head></head><body>\t\t</body></html>", "\t\t");
+         check (sb, "<html><head></head><body> \t\t</body></html>", " \t\t");
+         check (sb, "<html><head></head><body>\t \t</body></html>", "\t \t");
+         check (sb, "<html><head></head><body>\t\t </body></html>", "\t\t ");
+         sb.setCollapse (true);
+         check (sb, "<html><head></head><body>  </body></html>", "");
+         check (sb, "<html><head></head><body>\t\t</body></html>", "");
+         check (sb, "<html><head></head><body> \t\t</body></html>", "");
+         check (sb, "<html><head></head><body>\t \t</body></html>", "");
+         check (sb, "<html><head></head><body>\t\t </body></html>", "");
+     }
+ 
+     /**
+      * Test text preceded or followed by whitespace returns just text.
+      */
+     public void testCollapsed3 ()
+     {
+         StringBean sb;
+ 
+         sb = new StringBean ();
+         sb.setLinks (false);
+         sb.setReplaceNonBreakingSpaces (true);
+         sb.setCollapse (false);
+         check (sb, "<html><head></head><body>x  </body></html>", "x  ");
+         check (sb, "<html><head></head><body>x\t\t</body></html>", "x\t\t");
+         check (sb, "<html><head></head><body>x \t\t</body></html>", "x \t\t");
+         check (sb, "<html><head></head><body>x\t \t</body></html>", "x\t \t");
+         check (sb, "<html><head></head><body>x\t\t </body></html>", "x\t\t ");
+         sb.setCollapse (true);
+         check (sb, "<html><head></head><body>x  </body></html>", "x");
+         check (sb, "<html><head></head><body>x\t\t</body></html>", "x");
+         check (sb, "<html><head></head><body>x \t\t</body></html>", "x");
+         check (sb, "<html><head></head><body>x\t \t</body></html>", "x");
+         check (sb, "<html><head></head><body>x\t\t </body></html>", "x");
+         check (sb, "<html><head></head><body>  x</body></html>", "x");
+         check (sb, "<html><head></head><body>\t\tx</body></html>", "x");
+         check (sb, "<html><head></head><body> \t\tx</body></html>", "x");
+         check (sb, "<html><head></head><body>\t \tx</body></html>", "x");
+         check (sb, "<html><head></head><body>\t\t x</body></html>", "x");
      }
  }

[Htmlparser-cvs] htmlparser/src/org/htmlparser/tests/utilTests AllTests.java,1.38,1.39 BeanTest.java,1.28,1.29 CharacterTranslationTest.java,1.24,1.25 HTMLLinkProcessorTest.java,1.37,1.38 HTMLTagParserTest.java,1.37,1.38 package.html,1.8,1.9

[<der...@us...>]

Update of /cvsroot/htmlparser/htmlparser/src/org/htmlparser/tests/utilTests
In directory sc8-pr-cvs1:/tmp/cvs-serv15493/htmlparser/src/org/htmlparser/tests/utilTests

Modified Files:
	AllTests.java BeanTest.java CharacterTranslationTest.java 
	HTMLLinkProcessorTest.java HTMLTagParserTest.java package.html 
Log Message:
Update version headers to 1.4-20030713 and update changelog.



Index: AllTests.java
===================================================================
RCS file: /cvsroot/htmlparser/htmlparser/src/org/htmlparser/tests/utilTests/AllTests.java,v
retrieving revision 1.38
retrieving revision 1.39
diff -C2 -d -r1.38 -r1.39
*** AllTests.java	29 Jun 2003 12:29:33 -0000	1.38
--- AllTests.java	13 Jul 2003 12:15:12 -0000	1.39
***************
*** 1,3 ****
! // HTMLParser Library v1_4_20030629 - A java-based parser for HTML
  // Copyright (C) Dec 31, 2000 Somik Raha
  //
--- 1,3 ----
! // HTMLParser Library v1_4_20030713 - A java-based parser for HTML
  // Copyright (C) Dec 31, 2000 Somik Raha
  //

Index: BeanTest.java
===================================================================
RCS file: /cvsroot/htmlparser/htmlparser/src/org/htmlparser/tests/utilTests/BeanTest.java,v
retrieving revision 1.28
retrieving revision 1.29
diff -C2 -d -r1.28 -r1.29
*** BeanTest.java	29 Jun 2003 12:29:33 -0000	1.28
--- BeanTest.java	13 Jul 2003 12:15:12 -0000	1.29
***************
*** 1,3 ****
! // HTMLParser Library v1_4_20030629 - A java-based parser for HTML
  // Copyright (C) Dec 31, 2000 Somik Raha
  //
--- 1,3 ----
! // HTMLParser Library v1_4_20030713 - A java-based parser for HTML
  // Copyright (C) Dec 31, 2000 Somik Raha
  //

Index: CharacterTranslationTest.java
===================================================================
RCS file: /cvsroot/htmlparser/htmlparser/src/org/htmlparser/tests/utilTests/CharacterTranslationTest.java,v
retrieving revision 1.24
retrieving revision 1.25
diff -C2 -d -r1.24 -r1.25
*** CharacterTranslationTest.java	29 Jun 2003 12:29:33 -0000	1.24
--- CharacterTranslationTest.java	13 Jul 2003 12:15:12 -0000	1.25
***************
*** 1,3 ****
! // HTMLParser Library v1_4_20030629 - A java-based parser for HTML
  // Copyright (C) Dec 31, 2000 Somik Raha
  //
--- 1,3 ----
! // HTMLParser Library v1_4_20030713 - A java-based parser for HTML
  // Copyright (C) Dec 31, 2000 Somik Raha
  //

Index: HTMLLinkProcessorTest.java
===================================================================
RCS file: /cvsroot/htmlparser/htmlparser/src/org/htmlparser/tests/utilTests/HTMLLinkProcessorTest.java,v
retrieving revision 1.37
retrieving revision 1.38
diff -C2 -d -r1.37 -r1.38
*** HTMLLinkProcessorTest.java	29 Jun 2003 12:29:33 -0000	1.37
--- HTMLLinkProcessorTest.java	13 Jul 2003 12:15:12 -0000	1.38
***************
*** 1,3 ****
! // HTMLParser Library v1_4_20030629 - A java-based parser for HTML
  // Copyright (C) Dec 31, 2000 Somik Raha
  //
--- 1,3 ----
! // HTMLParser Library v1_4_20030713 - A java-based parser for HTML
  // Copyright (C) Dec 31, 2000 Somik Raha
  //

Index: HTMLTagParserTest.java
===================================================================
RCS file: /cvsroot/htmlparser/htmlparser/src/org/htmlparser/tests/utilTests/HTMLTagParserTest.java,v
retrieving revision 1.37
retrieving revision 1.38
diff -C2 -d -r1.37 -r1.38
*** HTMLTagParserTest.java	29 Jun 2003 12:29:33 -0000	1.37
--- HTMLTagParserTest.java	13 Jul 2003 12:15:12 -0000	1.38
***************
*** 1,3 ****
! // HTMLParser Library v1_4_20030629 - A java-based parser for HTML
  // Copyright (C) Dec 31, 2000 Somik Raha
  //
--- 1,3 ----
! // HTMLParser Library v1_4_20030713 - A java-based parser for HTML
  // Copyright (C) Dec 31, 2000 Somik Raha
  //

Index: package.html
===================================================================
RCS file: /cvsroot/htmlparser/htmlparser/src/org/htmlparser/tests/utilTests/package.html,v
retrieving revision 1.8
retrieving revision 1.9
diff -C2 -d -r1.8 -r1.9
*** package.html	29 Jun 2003 12:29:33 -0000	1.8
--- package.html	13 Jul 2003 12:15:12 -0000	1.9
***************
*** 6,10 ****
    @(#)package.html	1.60 98/01/27
  
!  HTMLParser Library v1_4_20030629 - A java-based parser for HTML
   Copyright (C) Dec 31, 2000 Somik Raha
  
--- 6,10 ----
    @(#)package.html	1.60 98/01/27
  
!  HTMLParser Library v1_4_20030713 - A java-based parser for HTML
   Copyright (C) Dec 31, 2000 Somik Raha
  

[Htmlparser-cvs] htmlparser/src/org/htmlparser/visitors CompositeTagFindingVisitor.java,1.8,1.9 HtmlPage.java,1.26,1.27 LinkFindingVisitor.java,1.21,1.22 NodeVisitor.java,1.21,1.22 ObjectFindingVisitor.java,1.26,1.27 StringFindingVisitor.java,1.26,1.27 TagFindingVisitor.java,1.27,1.28 TextExtractingVisitor.java,1.25,1.26 UrlModifyingVisitor.java,1.24,1.25 package.html,1.8,1.9

[<der...@us...>]

Update of /cvsroot/htmlparser/htmlparser/src/org/htmlparser/visitors
In directory sc8-pr-cvs1:/tmp/cvs-serv15493/htmlparser/src/org/htmlparser/visitors

Modified Files:
	CompositeTagFindingVisitor.java HtmlPage.java 
	LinkFindingVisitor.java NodeVisitor.java 
	ObjectFindingVisitor.java StringFindingVisitor.java 
	TagFindingVisitor.java TextExtractingVisitor.java 
	UrlModifyingVisitor.java package.html 
Log Message:
Update version headers to 1.4-20030713 and update changelog.



Index: CompositeTagFindingVisitor.java
===================================================================
RCS file: /cvsroot/htmlparser/htmlparser/src/org/htmlparser/visitors/CompositeTagFindingVisitor.java,v
retrieving revision 1.8
retrieving revision 1.9
diff -C2 -d -r1.8 -r1.9
*** CompositeTagFindingVisitor.java	29 Jun 2003 12:29:33 -0000	1.8
--- CompositeTagFindingVisitor.java	13 Jul 2003 12:15:14 -0000	1.9
***************
*** 1,3 ****
! // HTMLParser Library v1_4_20030629 - A java-based parser for HTML
  // Copyright (C) Dec 31, 2000 Somik Raha
  // 
--- 1,3 ----
! // HTMLParser Library v1_4_20030713 - A java-based parser for HTML
  // Copyright (C) Dec 31, 2000 Somik Raha
  // 

Index: HtmlPage.java
===================================================================
RCS file: /cvsroot/htmlparser/htmlparser/src/org/htmlparser/visitors/HtmlPage.java,v
retrieving revision 1.26
retrieving revision 1.27
diff -C2 -d -r1.26 -r1.27
*** HtmlPage.java	29 Jun 2003 12:29:33 -0000	1.26
--- HtmlPage.java	13 Jul 2003 12:15:14 -0000	1.27
***************
*** 1,3 ****
! // HTMLParser Library v1_4_20030629 - A java-based parser for HTML
  // Copyright (C) Dec 31, 2000 Somik Raha
  // 
--- 1,3 ----
! // HTMLParser Library v1_4_20030713 - A java-based parser for HTML
  // Copyright (C) Dec 31, 2000 Somik Raha
  // 

Index: LinkFindingVisitor.java
===================================================================
RCS file: /cvsroot/htmlparser/htmlparser/src/org/htmlparser/visitors/LinkFindingVisitor.java,v
retrieving revision 1.21
retrieving revision 1.22
diff -C2 -d -r1.21 -r1.22
*** LinkFindingVisitor.java	29 Jun 2003 12:29:33 -0000	1.21
--- LinkFindingVisitor.java	13 Jul 2003 12:15:14 -0000	1.22
***************
*** 1,3 ****
! // HTMLParser Library v1_4_20030629 - A java-based parser for HTML
  // Copyright (C) Dec 31, 2000 Somik Raha
  // 
--- 1,3 ----
! // HTMLParser Library v1_4_20030713 - A java-based parser for HTML
  // Copyright (C) Dec 31, 2000 Somik Raha
  // 

Index: NodeVisitor.java
===================================================================
RCS file: /cvsroot/htmlparser/htmlparser/src/org/htmlparser/visitors/NodeVisitor.java,v
retrieving revision 1.21
retrieving revision 1.22
diff -C2 -d -r1.21 -r1.22
*** NodeVisitor.java	29 Jun 2003 12:29:33 -0000	1.21
--- NodeVisitor.java	13 Jul 2003 12:15:14 -0000	1.22
***************
*** 1,3 ****
! // HTMLParser Library v1_4_20030629 - A java-based parser for HTML
  // Copyright (C) Dec 31, 2000 Somik Raha
  // 
--- 1,3 ----
! // HTMLParser Library v1_4_20030713 - A java-based parser for HTML
  // Copyright (C) Dec 31, 2000 Somik Raha
  // 

Index: ObjectFindingVisitor.java
===================================================================
RCS file: /cvsroot/htmlparser/htmlparser/src/org/htmlparser/visitors/ObjectFindingVisitor.java,v
retrieving revision 1.26
retrieving revision 1.27
diff -C2 -d -r1.26 -r1.27
*** ObjectFindingVisitor.java	29 Jun 2003 12:29:33 -0000	1.26
--- ObjectFindingVisitor.java	13 Jul 2003 12:15:14 -0000	1.27
***************
*** 1,3 ****
! // HTMLParser Library v1_4_20030629 - A java-based parser for HTML
  // Copyright (C) Dec 31, 2000 Somik Raha
  // 
--- 1,3 ----
! // HTMLParser Library v1_4_20030713 - A java-based parser for HTML
  // Copyright (C) Dec 31, 2000 Somik Raha
  // 

Index: StringFindingVisitor.java
===================================================================
RCS file: /cvsroot/htmlparser/htmlparser/src/org/htmlparser/visitors/StringFindingVisitor.java,v
retrieving revision 1.26
retrieving revision 1.27
diff -C2 -d -r1.26 -r1.27
*** StringFindingVisitor.java	29 Jun 2003 12:29:33 -0000	1.26
--- StringFindingVisitor.java	13 Jul 2003 12:15:14 -0000	1.27
***************
*** 1,3 ****
! // HTMLParser Library v1_4_20030629 - A java-based parser for HTML
  // Copyright (C) Dec 31, 2000 Somik Raha
  // 
--- 1,3 ----
! // HTMLParser Library v1_4_20030713 - A java-based parser for HTML
  // Copyright (C) Dec 31, 2000 Somik Raha
  // 

Index: TagFindingVisitor.java
===================================================================
RCS file: /cvsroot/htmlparser/htmlparser/src/org/htmlparser/visitors/TagFindingVisitor.java,v
retrieving revision 1.27
retrieving revision 1.28
diff -C2 -d -r1.27 -r1.28
*** TagFindingVisitor.java	29 Jun 2003 12:29:33 -0000	1.27
--- TagFindingVisitor.java	13 Jul 2003 12:15:14 -0000	1.28
***************
*** 1,3 ****
! // HTMLParser Library v1_4_20030629 - A java-based parser for HTML
  // Copyright (C) Dec 31, 2000 Somik Raha
  // 
--- 1,3 ----
! // HTMLParser Library v1_4_20030713 - A java-based parser for HTML
  // Copyright (C) Dec 31, 2000 Somik Raha
  // 

Index: TextExtractingVisitor.java
===================================================================
RCS file: /cvsroot/htmlparser/htmlparser/src/org/htmlparser/visitors/TextExtractingVisitor.java,v
retrieving revision 1.25
retrieving revision 1.26
diff -C2 -d -r1.25 -r1.26
*** TextExtractingVisitor.java	29 Jun 2003 12:29:33 -0000	1.25
--- TextExtractingVisitor.java	13 Jul 2003 12:15:14 -0000	1.26
***************
*** 1,3 ****
! // HTMLParser Library v1_4_20030629 - A java-based parser for HTML
  // Copyright (C) Dec 31, 2000 Somik Raha
  // 
--- 1,3 ----
! // HTMLParser Library v1_4_20030713 - A java-based parser for HTML
  // Copyright (C) Dec 31, 2000 Somik Raha
  // 

Index: UrlModifyingVisitor.java
===================================================================
RCS file: /cvsroot/htmlparser/htmlparser/src/org/htmlparser/visitors/UrlModifyingVisitor.java,v
retrieving revision 1.24
retrieving revision 1.25
diff -C2 -d -r1.24 -r1.25
*** UrlModifyingVisitor.java	29 Jun 2003 12:29:33 -0000	1.24
--- UrlModifyingVisitor.java	13 Jul 2003 12:15:14 -0000	1.25
***************
*** 1,3 ****
! // HTMLParser Library v1_4_20030629 - A java-based parser for HTML
  // Copyright (C) Dec 31, 2000 Somik Raha
  // 
--- 1,3 ----
! // HTMLParser Library v1_4_20030713 - A java-based parser for HTML
  // Copyright (C) Dec 31, 2000 Somik Raha
  // 

Index: package.html
===================================================================
RCS file: /cvsroot/htmlparser/htmlparser/src/org/htmlparser/visitors/package.html,v
retrieving revision 1.8
retrieving revision 1.9
diff -C2 -d -r1.8 -r1.9
*** package.html	29 Jun 2003 12:29:33 -0000	1.8
--- package.html	13 Jul 2003 12:15:14 -0000	1.9
***************
*** 6,10 ****
    @(#)package.html	1.60 98/01/27
  
!  HTMLParser Library v1_4_20030629 - A java-based parser for HTML
   Copyright (C) Dec 31, 2000 Somik Raha
  
--- 6,10 ----
    @(#)package.html	1.60 98/01/27
  
!  HTMLParser Library v1_4_20030713 - A java-based parser for HTML
   Copyright (C) Dec 31, 2000 Somik Raha
  

[Htmlparser-cvs] htmlparser/src/org/htmlparser/util ChainedException.java,1.32,1.33 CommandLine.java,1.31,1.32 DefaultParserFeedback.java,1.19,1.20 FeedbackManager.java,1.33,1.34 Generate.java,1.34,1.35 IteratorImpl.java,1.20,1.21 LinkProcessor.java,1.18,1.19 NodeIterator.java,1.20,1.21 NodeList.java,1.34,1.35 ParserException.java,1.18,1.19 ParserFeedback.java,1.19,1.20 ParserUtils.java,1.21,1.22 PeekingIterator.java,1.8,1.9 SimpleNodeIterator.java,1.22,1.23 Translate.java,1.28,1.29 package.html,1.8,1.9

[<der...@us...>]

Update of /cvsroot/htmlparser/htmlparser/src/org/htmlparser/util
In directory sc8-pr-cvs1:/tmp/cvs-serv15493/htmlparser/src/org/htmlparser/util

Modified Files:
	ChainedException.java CommandLine.java 
	DefaultParserFeedback.java FeedbackManager.java Generate.java 
	IteratorImpl.java LinkProcessor.java NodeIterator.java 
	NodeList.java ParserException.java ParserFeedback.java 
	ParserUtils.java PeekingIterator.java SimpleNodeIterator.java 
	Translate.java package.html 
Log Message:
Update version headers to 1.4-20030713 and update changelog.



Index: ChainedException.java
===================================================================
RCS file: /cvsroot/htmlparser/htmlparser/src/org/htmlparser/util/ChainedException.java,v
retrieving revision 1.32
retrieving revision 1.33
diff -C2 -d -r1.32 -r1.33
*** ChainedException.java	29 Jun 2003 12:29:33 -0000	1.32
--- ChainedException.java	13 Jul 2003 12:15:14 -0000	1.33
***************
*** 1,3 ****
! // HTMLParser Library v1_4_20030629 - A java-based parser for HTML
  // Copyright (C) Dec 31, 2000 Somik Raha
  //
--- 1,3 ----
! // HTMLParser Library v1_4_20030713 - A java-based parser for HTML
  // Copyright (C) Dec 31, 2000 Somik Raha
  //

Index: CommandLine.java
===================================================================
RCS file: /cvsroot/htmlparser/htmlparser/src/org/htmlparser/util/CommandLine.java,v
retrieving revision 1.31
retrieving revision 1.32
diff -C2 -d -r1.31 -r1.32
*** CommandLine.java	29 Jun 2003 12:29:33 -0000	1.31
--- CommandLine.java	13 Jul 2003 12:15:14 -0000	1.32
***************
*** 1,3 ****
! // HTMLParser Library v1_4_20030629 - A java-based parser for HTML
  // Copyright (C) Dec 31, 2000 Somik Raha
  //
--- 1,3 ----
! // HTMLParser Library v1_4_20030713 - A java-based parser for HTML
  // Copyright (C) Dec 31, 2000 Somik Raha
  //

Index: DefaultParserFeedback.java
===================================================================
RCS file: /cvsroot/htmlparser/htmlparser/src/org/htmlparser/util/DefaultParserFeedback.java,v
retrieving revision 1.19
retrieving revision 1.20
diff -C2 -d -r1.19 -r1.20
*** DefaultParserFeedback.java	29 Jun 2003 12:29:33 -0000	1.19
--- DefaultParserFeedback.java	13 Jul 2003 12:15:14 -0000	1.20
***************
*** 1,3 ****
! // HTMLParser Library v1_4_20030629 - A java-based parser for HTML
  // Copyright (C) Dec 31, 2000 Somik Raha
  //
--- 1,3 ----
! // HTMLParser Library v1_4_20030713 - A java-based parser for HTML
  // Copyright (C) Dec 31, 2000 Somik Raha
  //

Index: FeedbackManager.java
===================================================================
RCS file: /cvsroot/htmlparser/htmlparser/src/org/htmlparser/util/FeedbackManager.java,v
retrieving revision 1.33
retrieving revision 1.34
diff -C2 -d -r1.33 -r1.34
*** FeedbackManager.java	29 Jun 2003 12:29:33 -0000	1.33
--- FeedbackManager.java	13 Jul 2003 12:15:14 -0000	1.34
***************
*** 1,3 ****
! // HTMLParser Library v1_4_20030629 - A java-based parser for HTML
  // Copyright (C) Dec 31, 2000 Somik Raha
  //
--- 1,3 ----
! // HTMLParser Library v1_4_20030713 - A java-based parser for HTML
  // Copyright (C) Dec 31, 2000 Somik Raha
  //

Index: Generate.java
===================================================================
RCS file: /cvsroot/htmlparser/htmlparser/src/org/htmlparser/util/Generate.java,v
retrieving revision 1.34
retrieving revision 1.35
diff -C2 -d -r1.34 -r1.35
*** Generate.java	29 Jun 2003 12:29:33 -0000	1.34
--- Generate.java	13 Jul 2003 12:15:14 -0000	1.35
***************
*** 1,3 ****
! // HTMLParser Library v1_4_20030629 - A java-based parser for HTML
  // Copyright (C) Dec 31, 2000 Somik Raha
  //
--- 1,3 ----
! // HTMLParser Library v1_4_20030713 - A java-based parser for HTML
  // Copyright (C) Dec 31, 2000 Somik Raha
  //

Index: IteratorImpl.java
===================================================================
RCS file: /cvsroot/htmlparser/htmlparser/src/org/htmlparser/util/IteratorImpl.java,v
retrieving revision 1.20
retrieving revision 1.21
diff -C2 -d -r1.20 -r1.21
*** IteratorImpl.java	29 Jun 2003 12:29:33 -0000	1.20
--- IteratorImpl.java	13 Jul 2003 12:15:14 -0000	1.21
***************
*** 1,3 ****
! // HTMLParser Library v1_4_20030629 - A java-based parser for HTML
  // Copyright (C) Dec 31, 2000 Somik Raha
  //
--- 1,3 ----
! // HTMLParser Library v1_4_20030713 - A java-based parser for HTML
  // Copyright (C) Dec 31, 2000 Somik Raha
  //

Index: LinkProcessor.java
===================================================================
RCS file: /cvsroot/htmlparser/htmlparser/src/org/htmlparser/util/LinkProcessor.java,v
retrieving revision 1.18
retrieving revision 1.19
diff -C2 -d -r1.18 -r1.19
*** LinkProcessor.java	29 Jun 2003 12:29:33 -0000	1.18
--- LinkProcessor.java	13 Jul 2003 12:15:14 -0000	1.19
***************
*** 1,3 ****
! // HTMLParser Library v1_4_20030629 - A java-based parser for HTML
  // Copyright (C) Dec 31, 2000 Somik Raha
  //
--- 1,3 ----
! // HTMLParser Library v1_4_20030713 - A java-based parser for HTML
  // Copyright (C) Dec 31, 2000 Somik Raha
  //

Index: NodeIterator.java
===================================================================
RCS file: /cvsroot/htmlparser/htmlparser/src/org/htmlparser/util/NodeIterator.java,v
retrieving revision 1.20
retrieving revision 1.21
diff -C2 -d -r1.20 -r1.21
*** NodeIterator.java	29 Jun 2003 12:29:33 -0000	1.20
--- NodeIterator.java	13 Jul 2003 12:15:14 -0000	1.21
***************
*** 1,3 ****
! // HTMLParser Library v1_4_20030629 - A java-based parser for HTML
  // Copyright (C) Dec 31, 2000 Somik Raha
  //
--- 1,3 ----
! // HTMLParser Library v1_4_20030713 - A java-based parser for HTML
  // Copyright (C) Dec 31, 2000 Somik Raha
  //

Index: NodeList.java
===================================================================
RCS file: /cvsroot/htmlparser/htmlparser/src/org/htmlparser/util/NodeList.java,v
retrieving revision 1.34
retrieving revision 1.35
diff -C2 -d -r1.34 -r1.35
*** NodeList.java	12 Jul 2003 00:33:59 -0000	1.34
--- NodeList.java	13 Jul 2003 12:15:14 -0000	1.35
***************
*** 1,3 ****
! // HTMLParser Library v1_4_20030629 - A java-based parser for HTML
  // Copyright (C) Dec 31, 2000 Somik Raha
  //
--- 1,3 ----
! // HTMLParser Library v1_4_20030713 - A java-based parser for HTML
  // Copyright (C) Dec 31, 2000 Somik Raha
  //

Index: ParserException.java
===================================================================
RCS file: /cvsroot/htmlparser/htmlparser/src/org/htmlparser/util/ParserException.java,v
retrieving revision 1.18
retrieving revision 1.19
diff -C2 -d -r1.18 -r1.19
*** ParserException.java	29 Jun 2003 12:29:33 -0000	1.18
--- ParserException.java	13 Jul 2003 12:15:14 -0000	1.19
***************
*** 1,3 ****
! // HTMLParser Library v1_4_20030629 - A java-based parser for HTML
  // Copyright (C) Dec 31, 2000 Somik Raha
  //
--- 1,3 ----
! // HTMLParser Library v1_4_20030713 - A java-based parser for HTML
  // Copyright (C) Dec 31, 2000 Somik Raha
  //

Index: ParserFeedback.java
===================================================================
RCS file: /cvsroot/htmlparser/htmlparser/src/org/htmlparser/util/ParserFeedback.java,v
retrieving revision 1.19
retrieving revision 1.20
diff -C2 -d -r1.19 -r1.20
*** ParserFeedback.java	29 Jun 2003 12:29:33 -0000	1.19
--- ParserFeedback.java	13 Jul 2003 12:15:14 -0000	1.20
***************
*** 1,3 ****
! // HTMLParser Library v1_4_20030629 - A java-based parser for HTML
  // Copyright (C) Dec 31, 2000 Somik Raha
  //
--- 1,3 ----
! // HTMLParser Library v1_4_20030713 - A java-based parser for HTML
  // Copyright (C) Dec 31, 2000 Somik Raha
  //

Index: ParserUtils.java
===================================================================
RCS file: /cvsroot/htmlparser/htmlparser/src/org/htmlparser/util/ParserUtils.java,v
retrieving revision 1.21
retrieving revision 1.22
diff -C2 -d -r1.21 -r1.22
*** ParserUtils.java	29 Jun 2003 12:29:33 -0000	1.21
--- ParserUtils.java	13 Jul 2003 12:15:14 -0000	1.22
***************
*** 1,3 ****
! // HTMLParser Library v1_4_20030629 - A java-based parser for HTML
  // Copyright (C) Dec 31, 2000 Somik Raha
  //
--- 1,3 ----
! // HTMLParser Library v1_4_20030713 - A java-based parser for HTML
  // Copyright (C) Dec 31, 2000 Somik Raha
  //

Index: PeekingIterator.java
===================================================================
RCS file: /cvsroot/htmlparser/htmlparser/src/org/htmlparser/util/PeekingIterator.java,v
retrieving revision 1.8
retrieving revision 1.9
diff -C2 -d -r1.8 -r1.9
*** PeekingIterator.java	29 Jun 2003 12:29:33 -0000	1.8
--- PeekingIterator.java	13 Jul 2003 12:15:14 -0000	1.9
***************
*** 1,3 ****
! // HTMLParser Library v1_4_20030629 - A java-based parser for HTML
  // Copyright (C) Dec 31, 2000 Somik Raha
  //
--- 1,3 ----
! // HTMLParser Library v1_4_20030713 - A java-based parser for HTML
  // Copyright (C) Dec 31, 2000 Somik Raha
  //

Index: SimpleNodeIterator.java
===================================================================
RCS file: /cvsroot/htmlparser/htmlparser/src/org/htmlparser/util/SimpleNodeIterator.java,v
retrieving revision 1.22
retrieving revision 1.23
diff -C2 -d -r1.22 -r1.23
*** SimpleNodeIterator.java	29 Jun 2003 12:29:33 -0000	1.22
--- SimpleNodeIterator.java	13 Jul 2003 12:15:14 -0000	1.23
***************
*** 1,3 ****
! // HTMLParser Library v1_4_20030629 - A java-based parser for HTML
  // Copyright (C) Dec 31, 2000 Somik Raha
  // 
--- 1,3 ----
! // HTMLParser Library v1_4_20030713 - A java-based parser for HTML
  // Copyright (C) Dec 31, 2000 Somik Raha
  // 

Index: Translate.java
===================================================================
RCS file: /cvsroot/htmlparser/htmlparser/src/org/htmlparser/util/Translate.java,v
retrieving revision 1.28
retrieving revision 1.29
diff -C2 -d -r1.28 -r1.29
*** Translate.java	29 Jun 2003 12:29:33 -0000	1.28
--- Translate.java	13 Jul 2003 12:15:14 -0000	1.29
***************
*** 1,3 ****
! // HTMLParser Library v1_4_20030629 - A java-based parser for HTML
  // Copyright (C) Dec 31, 2000 Somik Raha
  //
--- 1,3 ----
! // HTMLParser Library v1_4_20030713 - A java-based parser for HTML
  // Copyright (C) Dec 31, 2000 Somik Raha
  //

Index: package.html
===================================================================
RCS file: /cvsroot/htmlparser/htmlparser/src/org/htmlparser/util/package.html,v
retrieving revision 1.8
retrieving revision 1.9
diff -C2 -d -r1.8 -r1.9
*** package.html	29 Jun 2003 12:29:33 -0000	1.8
--- package.html	13 Jul 2003 12:15:14 -0000	1.9
***************
*** 6,10 ****
    @(#)package.html	1.60 98/01/27
  
!  HTMLParser Library v1_4_20030629 - A java-based parser for HTML
   Copyright (C) Dec 31, 2000 Somik Raha
  
--- 6,10 ----
    @(#)package.html	1.60 98/01/27
  
!  HTMLParser Library v1_4_20030713 - A java-based parser for HTML
   Copyright (C) Dec 31, 2000 Somik Raha
  

[Htmlparser-cvs] htmlparser/src/org/htmlparser/tests/visitorsTests AllTests.java,1.27,1.28

[<der...@us...>]

Update of /cvsroot/htmlparser/htmlparser/src/org/htmlparser/tests/visitorsTests
In directory sc8-pr-cvs1:/tmp/cvs-serv15493/htmlparser/src/org/htmlparser/tests/visitorsTests

Modified Files:
	AllTests.java 
Log Message:
Update version headers to 1.4-20030713 and update changelog.



Index: AllTests.java
===================================================================
RCS file: /cvsroot/htmlparser/htmlparser/src/org/htmlparser/tests/visitorsTests/AllTests.java,v
retrieving revision 1.27
retrieving revision 1.28
diff -C2 -d -r1.27 -r1.28
*** AllTests.java	29 Jun 2003 12:29:33 -0000	1.27
--- AllTests.java	13 Jul 2003 12:15:12 -0000	1.28
***************
*** 1,3 ****
! // HTMLParser Library v1_4_20030629 - A java-based parser for HTML
  // Copyright (C) Dec 31, 2000 Somik Raha
  //
--- 1,3 ----
! // HTMLParser Library v1_4_20030713 - A java-based parser for HTML
  // Copyright (C) Dec 31, 2000 Somik Raha
  //

[Htmlparser-cvs] htmlparser/src/org/htmlparser/tests/tagTests AllTests.java,1.36,1.37 AppletTagTest.java,1.20,1.21 BaseHrefTagTest.java,1.19,1.20 DoctypeTagTest.java,1.20,1.21 EndTagTest.java,1.21,1.22 FormTagTest.java,1.24,1.25 FrameSetTagTest.java,1.20,1.21 FrameTagTest.java,1.20,1.21 ImageTagTest.java,1.23,1.24 InputTagTest.java,1.21,1.22 JspTagTest.java,1.23,1.24 LinkTagTest.java,1.26,1.27 MetaTagTest.java,1.21,1.22 OptionTagTest.java,1.22,1.23 ScriptTagTest.java,1.21,1.22 SelectTagTest.java,1.23,1.24 StyleTagTest.java,1.20,1.21 TagTest.java,1.32,1.33 TextareaTagTest.java,1.21,1.22 TitleTagTest.java,1.20,1.21 package.html,1.8,1.9

[<der...@us...>]

Update of /cvsroot/htmlparser/htmlparser/src/org/htmlparser/tests/tagTests
In directory sc8-pr-cvs1:/tmp/cvs-serv15493/htmlparser/src/org/htmlparser/tests/tagTests

Modified Files:
	AllTests.java AppletTagTest.java BaseHrefTagTest.java 
	DoctypeTagTest.java EndTagTest.java FormTagTest.java 
	FrameSetTagTest.java FrameTagTest.java ImageTagTest.java 
	InputTagTest.java JspTagTest.java LinkTagTest.java 
	MetaTagTest.java OptionTagTest.java ScriptTagTest.java 
	SelectTagTest.java StyleTagTest.java TagTest.java 
	TextareaTagTest.java TitleTagTest.java package.html 
Log Message:
Update version headers to 1.4-20030713 and update changelog.



Index: AllTests.java
===================================================================
RCS file: /cvsroot/htmlparser/htmlparser/src/org/htmlparser/tests/tagTests/AllTests.java,v
retrieving revision 1.36
retrieving revision 1.37
diff -C2 -d -r1.36 -r1.37
*** AllTests.java	29 Jun 2003 12:29:33 -0000	1.36
--- AllTests.java	13 Jul 2003 12:15:11 -0000	1.37
***************
*** 1,3 ****
! // HTMLParser Library v1_4_20030629 - A java-based parser for HTML
  // Copyright (C) Dec 31, 2000 Somik Raha
  //
--- 1,3 ----
! // HTMLParser Library v1_4_20030713 - A java-based parser for HTML
  // Copyright (C) Dec 31, 2000 Somik Raha
  //

Index: AppletTagTest.java
===================================================================
RCS file: /cvsroot/htmlparser/htmlparser/src/org/htmlparser/tests/tagTests/AppletTagTest.java,v
retrieving revision 1.20
retrieving revision 1.21
diff -C2 -d -r1.20 -r1.21
*** AppletTagTest.java	29 Jun 2003 12:29:33 -0000	1.20
--- AppletTagTest.java	13 Jul 2003 12:15:11 -0000	1.21
***************
*** 1,3 ****
! // HTMLParser Library v1_4_20030629 - A java-based parser for HTML
  // Copyright (C) Dec 31, 2000 Somik Raha
  //
--- 1,3 ----
! // HTMLParser Library v1_4_20030713 - A java-based parser for HTML
  // Copyright (C) Dec 31, 2000 Somik Raha
  //

Index: BaseHrefTagTest.java
===================================================================
RCS file: /cvsroot/htmlparser/htmlparser/src/org/htmlparser/tests/tagTests/BaseHrefTagTest.java,v
retrieving revision 1.19
retrieving revision 1.20
diff -C2 -d -r1.19 -r1.20
*** BaseHrefTagTest.java	29 Jun 2003 12:29:33 -0000	1.19
--- BaseHrefTagTest.java	13 Jul 2003 12:15:11 -0000	1.20
***************
*** 1,3 ****
! // HTMLParser Library v1_4_20030629 - A java-based parser for HTML
  // Copyright (C) Dec 31, 2000 Somik Raha
  //
--- 1,3 ----
! // HTMLParser Library v1_4_20030713 - A java-based parser for HTML
  // Copyright (C) Dec 31, 2000 Somik Raha
  //

Index: DoctypeTagTest.java
===================================================================
RCS file: /cvsroot/htmlparser/htmlparser/src/org/htmlparser/tests/tagTests/DoctypeTagTest.java,v
retrieving revision 1.20
retrieving revision 1.21
diff -C2 -d -r1.20 -r1.21
*** DoctypeTagTest.java	29 Jun 2003 12:29:33 -0000	1.20
--- DoctypeTagTest.java	13 Jul 2003 12:15:12 -0000	1.21
***************
*** 1,3 ****
! // HTMLParser Library v1_4_20030629 - A java-based parser for HTML
  // Copyright (C) Dec 31, 2000 Somik Raha
  //
--- 1,3 ----
! // HTMLParser Library v1_4_20030713 - A java-based parser for HTML
  // Copyright (C) Dec 31, 2000 Somik Raha
  //

Index: EndTagTest.java
===================================================================
RCS file: /cvsroot/htmlparser/htmlparser/src/org/htmlparser/tests/tagTests/EndTagTest.java,v
retrieving revision 1.21
retrieving revision 1.22
diff -C2 -d -r1.21 -r1.22
*** EndTagTest.java	29 Jun 2003 12:29:33 -0000	1.21
--- EndTagTest.java	13 Jul 2003 12:15:12 -0000	1.22
***************
*** 1,3 ****
! // HTMLParser Library v1_4_20030629 - A java-based parser for HTML
  // Copyright (C) Dec 31, 2000 Somik Raha
  //
--- 1,3 ----
! // HTMLParser Library v1_4_20030713 - A java-based parser for HTML
  // Copyright (C) Dec 31, 2000 Somik Raha
  //

Index: FormTagTest.java
===================================================================
RCS file: /cvsroot/htmlparser/htmlparser/src/org/htmlparser/tests/tagTests/FormTagTest.java,v
retrieving revision 1.24
retrieving revision 1.25
diff -C2 -d -r1.24 -r1.25
*** FormTagTest.java	29 Jun 2003 12:29:33 -0000	1.24
--- FormTagTest.java	13 Jul 2003 12:15:12 -0000	1.25
***************
*** 1,3 ****
! // HTMLParser Library v1_4_20030629 - A java-based parser for HTML
  // Copyright (C) Dec 31, 2000 Somik Raha
  //
--- 1,3 ----
! // HTMLParser Library v1_4_20030713 - A java-based parser for HTML
  // Copyright (C) Dec 31, 2000 Somik Raha
  //

Index: FrameSetTagTest.java
===================================================================
RCS file: /cvsroot/htmlparser/htmlparser/src/org/htmlparser/tests/tagTests/FrameSetTagTest.java,v
retrieving revision 1.20
retrieving revision 1.21
diff -C2 -d -r1.20 -r1.21
*** FrameSetTagTest.java	29 Jun 2003 12:29:33 -0000	1.20
--- FrameSetTagTest.java	13 Jul 2003 12:15:12 -0000	1.21
***************
*** 1,3 ****
! // HTMLParser Library v1_4_20030629 - A java-based parser for HTML
  // Copyright (C) Dec 31, 2000 Somik Raha
  //
--- 1,3 ----
! // HTMLParser Library v1_4_20030713 - A java-based parser for HTML
  // Copyright (C) Dec 31, 2000 Somik Raha
  //

Index: FrameTagTest.java
===================================================================
RCS file: /cvsroot/htmlparser/htmlparser/src/org/htmlparser/tests/tagTests/FrameTagTest.java,v
retrieving revision 1.20
retrieving revision 1.21
diff -C2 -d -r1.20 -r1.21
*** FrameTagTest.java	29 Jun 2003 12:29:33 -0000	1.20
--- FrameTagTest.java	13 Jul 2003 12:15:12 -0000	1.21
***************
*** 1,3 ****
! // HTMLParser Library v1_4_20030629 - A java-based parser for HTML
  // Copyright (C) Dec 31, 2000 Somik Raha
  //
--- 1,3 ----
! // HTMLParser Library v1_4_20030713 - A java-based parser for HTML
  // Copyright (C) Dec 31, 2000 Somik Raha
  //

Index: ImageTagTest.java
===================================================================
RCS file: /cvsroot/htmlparser/htmlparser/src/org/htmlparser/tests/tagTests/ImageTagTest.java,v
retrieving revision 1.23
retrieving revision 1.24
diff -C2 -d -r1.23 -r1.24
*** ImageTagTest.java	29 Jun 2003 12:29:33 -0000	1.23
--- ImageTagTest.java	13 Jul 2003 12:15:12 -0000	1.24
***************
*** 1,3 ****
! // HTMLParser Library v1_4_20030629 - A java-based parser for HTML
  // Copyright (C) Dec 31, 2000 Somik Raha
  //
--- 1,3 ----
! // HTMLParser Library v1_4_20030713 - A java-based parser for HTML
  // Copyright (C) Dec 31, 2000 Somik Raha
  //

Index: InputTagTest.java
===================================================================
RCS file: /cvsroot/htmlparser/htmlparser/src/org/htmlparser/tests/tagTests/InputTagTest.java,v
retrieving revision 1.21
retrieving revision 1.22
diff -C2 -d -r1.21 -r1.22
*** InputTagTest.java	29 Jun 2003 12:29:33 -0000	1.21
--- InputTagTest.java	13 Jul 2003 12:15:12 -0000	1.22
***************
*** 1,3 ****
! // HTMLParser Library v1_4_20030629 - A java-based parser for HTML
  // Copyright (C) Dec 31, 2000 Somik Raha
  //
--- 1,3 ----
! // HTMLParser Library v1_4_20030713 - A java-based parser for HTML
  // Copyright (C) Dec 31, 2000 Somik Raha
  //

Index: JspTagTest.java
===================================================================
RCS file: /cvsroot/htmlparser/htmlparser/src/org/htmlparser/tests/tagTests/JspTagTest.java,v
retrieving revision 1.23
retrieving revision 1.24
diff -C2 -d -r1.23 -r1.24
*** JspTagTest.java	29 Jun 2003 12:29:33 -0000	1.23
--- JspTagTest.java	13 Jul 2003 12:15:12 -0000	1.24
***************
*** 1,3 ****
! // HTMLParser Library v1_4_20030629 - A java-based parser for HTML
  // Copyright (C) Dec 31, 2000 Somik Raha
  //
--- 1,3 ----
! // HTMLParser Library v1_4_20030713 - A java-based parser for HTML
  // Copyright (C) Dec 31, 2000 Somik Raha
  //

Index: LinkTagTest.java
===================================================================
RCS file: /cvsroot/htmlparser/htmlparser/src/org/htmlparser/tests/tagTests/LinkTagTest.java,v
retrieving revision 1.26
retrieving revision 1.27
diff -C2 -d -r1.26 -r1.27
*** LinkTagTest.java	29 Jun 2003 12:29:33 -0000	1.26
--- LinkTagTest.java	13 Jul 2003 12:15:12 -0000	1.27
***************
*** 1,3 ****
! // HTMLParser Library v1_4_20030629 - A java-based parser for HTML
  // Copyright (C) Dec 31, 2000 Somik Raha
  //
--- 1,3 ----
! // HTMLParser Library v1_4_20030713 - A java-based parser for HTML
  // Copyright (C) Dec 31, 2000 Somik Raha
  //

Index: MetaTagTest.java
===================================================================
RCS file: /cvsroot/htmlparser/htmlparser/src/org/htmlparser/tests/tagTests/MetaTagTest.java,v
retrieving revision 1.21
retrieving revision 1.22
diff -C2 -d -r1.21 -r1.22
*** MetaTagTest.java	29 Jun 2003 12:29:33 -0000	1.21
--- MetaTagTest.java	13 Jul 2003 12:15:12 -0000	1.22
***************
*** 1,3 ****
! // HTMLParser Library v1_4_20030629 - A java-based parser for HTML
  // Copyright (C) Dec 31, 2000 Somik Raha
  //
--- 1,3 ----
! // HTMLParser Library v1_4_20030713 - A java-based parser for HTML
  // Copyright (C) Dec 31, 2000 Somik Raha
  //

Index: OptionTagTest.java
===================================================================
RCS file: /cvsroot/htmlparser/htmlparser/src/org/htmlparser/tests/tagTests/OptionTagTest.java,v
retrieving revision 1.22
retrieving revision 1.23
diff -C2 -d -r1.22 -r1.23
*** OptionTagTest.java	29 Jun 2003 12:29:33 -0000	1.22
--- OptionTagTest.java	13 Jul 2003 12:15:12 -0000	1.23
***************
*** 1,3 ****
! // HTMLParser Library v1_4_20030629 - A java-based parser for HTML
  // Copyright (C) Dec 31, 2000 Somik Raha
  //
--- 1,3 ----
! // HTMLParser Library v1_4_20030713 - A java-based parser for HTML
  // Copyright (C) Dec 31, 2000 Somik Raha
  //

Index: ScriptTagTest.java
===================================================================
RCS file: /cvsroot/htmlparser/htmlparser/src/org/htmlparser/tests/tagTests/ScriptTagTest.java,v
retrieving revision 1.21
retrieving revision 1.22
diff -C2 -d -r1.21 -r1.22
*** ScriptTagTest.java	29 Jun 2003 12:29:33 -0000	1.21
--- ScriptTagTest.java	13 Jul 2003 12:15:12 -0000	1.22
***************
*** 1,3 ****
! // HTMLParser Library v1_4_20030629 - A java-based parser for HTML
  // Copyright (C) Dec 31, 2000 Somik Raha
  //
--- 1,3 ----
! // HTMLParser Library v1_4_20030713 - A java-based parser for HTML
  // Copyright (C) Dec 31, 2000 Somik Raha
  //

Index: SelectTagTest.java
===================================================================
RCS file: /cvsroot/htmlparser/htmlparser/src/org/htmlparser/tests/tagTests/SelectTagTest.java,v
retrieving revision 1.23
retrieving revision 1.24
diff -C2 -d -r1.23 -r1.24
*** SelectTagTest.java	29 Jun 2003 12:29:33 -0000	1.23
--- SelectTagTest.java	13 Jul 2003 12:15:12 -0000	1.24
***************
*** 1,3 ****
! // HTMLParser Library v1_4_20030629 - A java-based parser for HTML
  // Copyright (C) Dec 31, 2000 Somik Raha
  //
--- 1,3 ----
! // HTMLParser Library v1_4_20030713 - A java-based parser for HTML
  // Copyright (C) Dec 31, 2000 Somik Raha
  //

Index: StyleTagTest.java
===================================================================
RCS file: /cvsroot/htmlparser/htmlparser/src/org/htmlparser/tests/tagTests/StyleTagTest.java,v
retrieving revision 1.20
retrieving revision 1.21
diff -C2 -d -r1.20 -r1.21
*** StyleTagTest.java	29 Jun 2003 12:29:33 -0000	1.20
--- StyleTagTest.java	13 Jul 2003 12:15:12 -0000	1.21
***************
*** 1,3 ****
! // HTMLParser Library v1_4_20030629 - A java-based parser for HTML
  // Copyright (C) Dec 31, 2000 Somik Raha
  //
--- 1,3 ----
! // HTMLParser Library v1_4_20030713 - A java-based parser for HTML
  // Copyright (C) Dec 31, 2000 Somik Raha
  //

Index: TagTest.java
===================================================================
RCS file: /cvsroot/htmlparser/htmlparser/src/org/htmlparser/tests/tagTests/TagTest.java,v
retrieving revision 1.32
retrieving revision 1.33
diff -C2 -d -r1.32 -r1.33
*** TagTest.java	29 Jun 2003 12:29:33 -0000	1.32
--- TagTest.java	13 Jul 2003 12:15:12 -0000	1.33
***************
*** 1,3 ****
! // HTMLParser Library v1_4_20030629 - A java-based parser for HTML
  // Copyright (C) Dec 31, 2000 Somik Raha
  //
--- 1,3 ----
! // HTMLParser Library v1_4_20030713 - A java-based parser for HTML
  // Copyright (C) Dec 31, 2000 Somik Raha
  //

Index: TextareaTagTest.java
===================================================================
RCS file: /cvsroot/htmlparser/htmlparser/src/org/htmlparser/tests/tagTests/TextareaTagTest.java,v
retrieving revision 1.21
retrieving revision 1.22
diff -C2 -d -r1.21 -r1.22
*** TextareaTagTest.java	29 Jun 2003 12:29:33 -0000	1.21
--- TextareaTagTest.java	13 Jul 2003 12:15:12 -0000	1.22
***************
*** 1,3 ****
! // HTMLParser Library v1_4_20030629 - A java-based parser for HTML
  // Copyright (C) Dec 31, 2000 Somik Raha
  //
--- 1,3 ----
! // HTMLParser Library v1_4_20030713 - A java-based parser for HTML
  // Copyright (C) Dec 31, 2000 Somik Raha
  //

Index: TitleTagTest.java
===================================================================
RCS file: /cvsroot/htmlparser/htmlparser/src/org/htmlparser/tests/tagTests/TitleTagTest.java,v
retrieving revision 1.20
retrieving revision 1.21
diff -C2 -d -r1.20 -r1.21
*** TitleTagTest.java	29 Jun 2003 12:29:33 -0000	1.20
--- TitleTagTest.java	13 Jul 2003 12:15:12 -0000	1.21
***************
*** 1,3 ****
! // HTMLParser Library v1_4_20030629 - A java-based parser for HTML
  // Copyright (C) Dec 31, 2000 Somik Raha
  //
--- 1,3 ----
! // HTMLParser Library v1_4_20030713 - A java-based parser for HTML
  // Copyright (C) Dec 31, 2000 Somik Raha
  //

Index: package.html
===================================================================
RCS file: /cvsroot/htmlparser/htmlparser/src/org/htmlparser/tests/tagTests/package.html,v
retrieving revision 1.8
retrieving revision 1.9
diff -C2 -d -r1.8 -r1.9
*** package.html	29 Jun 2003 12:29:33 -0000	1.8
--- package.html	13 Jul 2003 12:15:12 -0000	1.9
***************
*** 6,10 ****
    @(#)package.html	1.60 98/01/27
  
!  HTMLParser Library v1_4_20030629 - A java-based parser for HTML
   Copyright (C) Dec 31, 2000 Somik Raha
  
--- 6,10 ----
    @(#)package.html	1.60 98/01/27
  
!  HTMLParser Library v1_4_20030713 - A java-based parser for HTML
   Copyright (C) Dec 31, 2000 Somik Raha
  

[Htmlparser-cvs] htmlparser/src/org/htmlparser/tests/temporaryFailures AttributeParserTest.java,1.3,1.4 TagParserTest.java,1.3,1.4

[<der...@us...>]

Update of /cvsroot/htmlparser/htmlparser/src/org/htmlparser/tests/temporaryFailures
In directory sc8-pr-cvs1:/tmp/cvs-serv15493/htmlparser/src/org/htmlparser/tests/temporaryFailures

Modified Files:
	AttributeParserTest.java TagParserTest.java 
Log Message:
Update version headers to 1.4-20030713 and update changelog.



Index: AttributeParserTest.java
===================================================================
RCS file: /cvsroot/htmlparser/htmlparser/src/org/htmlparser/tests/temporaryFailures/AttributeParserTest.java,v
retrieving revision 1.3
retrieving revision 1.4
diff -C2 -d -r1.3 -r1.4
*** AttributeParserTest.java	29 Jun 2003 12:29:33 -0000	1.3
--- AttributeParserTest.java	13 Jul 2003 12:15:12 -0000	1.4
***************
*** 1,3 ****
! // HTMLParser Library v1_4_20030629 - A java-based parser for HTML
  // Copyright (C) Dec 31, 2000 Somik Raha
  //
--- 1,3 ----
! // HTMLParser Library v1_4_20030713 - A java-based parser for HTML
  // Copyright (C) Dec 31, 2000 Somik Raha
  //

Index: TagParserTest.java
===================================================================
RCS file: /cvsroot/htmlparser/htmlparser/src/org/htmlparser/tests/temporaryFailures/TagParserTest.java,v
retrieving revision 1.3
retrieving revision 1.4
diff -C2 -d -r1.3 -r1.4
*** TagParserTest.java	29 Jun 2003 12:29:33 -0000	1.3
--- TagParserTest.java	13 Jul 2003 12:15:12 -0000	1.4
***************
*** 1,3 ****
! // HTMLParser Library v1_4_20030629 - A java-based parser for HTML
  // Copyright (C) Dec 31, 2000 Somik Raha
  //
--- 1,3 ----
! // HTMLParser Library v1_4_20030713 - A java-based parser for HTML
  // Copyright (C) Dec 31, 2000 Somik Raha
  //

[Htmlparser-cvs] htmlparser/src/org/htmlparser/tests/scannersTests AllTests.java,1.41,1.42 AppletScannerTest.java,1.19,1.20 BaseHREFScannerTest.java,1.19,1.20 DivScannerTest.java,1.25,1.26 FormScannerTest.java,1.25,1.26 FrameScannerTest.java,1.19,1.20 FrameSetScannerTest.java,1.19,1.20 HeadScannerTest.java,1.8,1.9 ImageScannerTest.java,1.22,1.23 InputTagScannerTest.java,1.19,1.20 JspScannerTest.java,1.20,1.21 LabelScannerTest.java,1.27,1.28 LinkScannerTest.java,1.29,1.30 MetaTagScannerTest.java,1.20,1.21 OptionTagScannerTest.java,1.21,1.22 ScriptScannerTest.java,1.30,1.31 SelectTagScannerTest.java,1.21,1.22 SpanScannerTest.java,1.22,1.23 StyleScannerTest.java,1.20,1.21 TableScannerTest.java,1.26,1.27 TagScannerTest.java,1.20,1.21 TextareaTagScannerTest.java,1.19,1.20 TitleScannerTest.java,1.20,1.21 XmlEndTagScanningTest.java,1.22,1.23 package.html,1.8,1.9

[<der...@us...>]

Update of /cvsroot/htmlparser/htmlparser/src/org/htmlparser/tests/scannersTests
In directory sc8-pr-cvs1:/tmp/cvs-serv15493/htmlparser/src/org/htmlparser/tests/scannersTests

Modified Files:
	AllTests.java AppletScannerTest.java BaseHREFScannerTest.java 
	DivScannerTest.java FormScannerTest.java FrameScannerTest.java 
	FrameSetScannerTest.java HeadScannerTest.java 
	ImageScannerTest.java InputTagScannerTest.java 
	JspScannerTest.java LabelScannerTest.java LinkScannerTest.java 
	MetaTagScannerTest.java OptionTagScannerTest.java 
	ScriptScannerTest.java SelectTagScannerTest.java 
	SpanScannerTest.java StyleScannerTest.java 
	TableScannerTest.java TagScannerTest.java 
	TextareaTagScannerTest.java TitleScannerTest.java 
	XmlEndTagScanningTest.java package.html 
Log Message:
Update version headers to 1.4-20030713 and update changelog.



Index: AllTests.java
===================================================================
RCS file: /cvsroot/htmlparser/htmlparser/src/org/htmlparser/tests/scannersTests/AllTests.java,v
retrieving revision 1.41
retrieving revision 1.42
diff -C2 -d -r1.41 -r1.42
*** AllTests.java	29 Jun 2003 12:29:32 -0000	1.41
--- AllTests.java	13 Jul 2003 12:15:11 -0000	1.42
***************
*** 1,3 ****
! // HTMLParser Library v1_4_20030629 - A java-based parser for HTML
  // Copyright (C) Dec 31, 2000 Somik Raha
  //
--- 1,3 ----
! // HTMLParser Library v1_4_20030713 - A java-based parser for HTML
  // Copyright (C) Dec 31, 2000 Somik Raha
  //
***************
*** 19,23 ****
  // Email :so...@ki...
  // 
! // HTMLParser Library v1_4_20030629 - A java-based parser for HTML
  // Copyright (C) Dec 31, 2000 Somik Raha
  //
--- 19,23 ----
  // Email :so...@ki...
  // 
! // HTMLParser Library v1_4_20030713 - A java-based parser for HTML
  // Copyright (C) Dec 31, 2000 Somik Raha
  //

Index: AppletScannerTest.java
===================================================================
RCS file: /cvsroot/htmlparser/htmlparser/src/org/htmlparser/tests/scannersTests/AppletScannerTest.java,v
retrieving revision 1.19
retrieving revision 1.20
diff -C2 -d -r1.19 -r1.20
*** AppletScannerTest.java	29 Jun 2003 12:29:32 -0000	1.19
--- AppletScannerTest.java	13 Jul 2003 12:15:11 -0000	1.20
***************
*** 1,3 ****
! // HTMLParser Library v1_4_20030629 - A java-based parser for HTML
  // Copyright (C) Dec 31, 2000 Somik Raha
  //
--- 1,3 ----
! // HTMLParser Library v1_4_20030713 - A java-based parser for HTML
  // Copyright (C) Dec 31, 2000 Somik Raha
  //

Index: BaseHREFScannerTest.java
===================================================================
RCS file: /cvsroot/htmlparser/htmlparser/src/org/htmlparser/tests/scannersTests/BaseHREFScannerTest.java,v
retrieving revision 1.19
retrieving revision 1.20
diff -C2 -d -r1.19 -r1.20
*** BaseHREFScannerTest.java	29 Jun 2003 12:29:32 -0000	1.19
--- BaseHREFScannerTest.java	13 Jul 2003 12:15:11 -0000	1.20
***************
*** 1,3 ****
! // HTMLParser Library v1_4_20030629 - A java-based parser for HTML
  // Copyright (C) Dec 31, 2000 Somik Raha
  //
--- 1,3 ----
! // HTMLParser Library v1_4_20030713 - A java-based parser for HTML
  // Copyright (C) Dec 31, 2000 Somik Raha
  //

Index: DivScannerTest.java
===================================================================
RCS file: /cvsroot/htmlparser/htmlparser/src/org/htmlparser/tests/scannersTests/DivScannerTest.java,v
retrieving revision 1.25
retrieving revision 1.26
diff -C2 -d -r1.25 -r1.26
*** DivScannerTest.java	29 Jun 2003 12:29:32 -0000	1.25
--- DivScannerTest.java	13 Jul 2003 12:15:11 -0000	1.26
***************
*** 1,3 ****
! // HTMLParser Library v1_4_20030629 - A java-based parser for HTML
  // Copyright (C) Dec 31, 2000 Somik Raha
  // 
--- 1,3 ----
! // HTMLParser Library v1_4_20030713 - A java-based parser for HTML
  // Copyright (C) Dec 31, 2000 Somik Raha
  // 

Index: FormScannerTest.java
===================================================================
RCS file: /cvsroot/htmlparser/htmlparser/src/org/htmlparser/tests/scannersTests/FormScannerTest.java,v
retrieving revision 1.25
retrieving revision 1.26
diff -C2 -d -r1.25 -r1.26
*** FormScannerTest.java	29 Jun 2003 12:29:32 -0000	1.25
--- FormScannerTest.java	13 Jul 2003 12:15:11 -0000	1.26
***************
*** 1,3 ****
! // HTMLParser Library v1_4_20030629 - A java-based parser for HTML
  // Copyright (C) Dec 31, 2000 Somik Raha
  //
--- 1,3 ----
! // HTMLParser Library v1_4_20030713 - A java-based parser for HTML
  // Copyright (C) Dec 31, 2000 Somik Raha
  //

Index: FrameScannerTest.java
===================================================================
RCS file: /cvsroot/htmlparser/htmlparser/src/org/htmlparser/tests/scannersTests/FrameScannerTest.java,v
retrieving revision 1.19
retrieving revision 1.20
diff -C2 -d -r1.19 -r1.20
*** FrameScannerTest.java	29 Jun 2003 12:29:32 -0000	1.19
--- FrameScannerTest.java	13 Jul 2003 12:15:11 -0000	1.20
***************
*** 1,3 ****
! // HTMLParser Library v1_4_20030629 - A java-based parser for HTML
  // Copyright (C) Dec 31, 2000 Somik Raha
  //
--- 1,3 ----
! // HTMLParser Library v1_4_20030713 - A java-based parser for HTML
  // Copyright (C) Dec 31, 2000 Somik Raha
  //

Index: FrameSetScannerTest.java
===================================================================
RCS file: /cvsroot/htmlparser/htmlparser/src/org/htmlparser/tests/scannersTests/FrameSetScannerTest.java,v
retrieving revision 1.19
retrieving revision 1.20
diff -C2 -d -r1.19 -r1.20
*** FrameSetScannerTest.java	29 Jun 2003 12:29:32 -0000	1.19
--- FrameSetScannerTest.java	13 Jul 2003 12:15:11 -0000	1.20
***************
*** 1,3 ****
! // HTMLParser Library v1_4_20030629 - A java-based parser for HTML
  // Copyright (C) Dec 31, 2000 Somik Raha
  //
--- 1,3 ----
! // HTMLParser Library v1_4_20030713 - A java-based parser for HTML
  // Copyright (C) Dec 31, 2000 Somik Raha
  //

Index: HeadScannerTest.java
===================================================================
RCS file: /cvsroot/htmlparser/htmlparser/src/org/htmlparser/tests/scannersTests/HeadScannerTest.java,v
retrieving revision 1.8
retrieving revision 1.9
diff -C2 -d -r1.8 -r1.9
*** HeadScannerTest.java	29 Jun 2003 12:29:32 -0000	1.8
--- HeadScannerTest.java	13 Jul 2003 12:15:11 -0000	1.9
***************
*** 1,3 ****
! // HTMLParser Library v1_4_20030629 - A java-based parser for HTML
  // Copyright (C) Dec 31, 2000 Somik Raha
  // 
--- 1,3 ----
! // HTMLParser Library v1_4_20030713 - A java-based parser for HTML
  // Copyright (C) Dec 31, 2000 Somik Raha
  // 

Index: ImageScannerTest.java
===================================================================
RCS file: /cvsroot/htmlparser/htmlparser/src/org/htmlparser/tests/scannersTests/ImageScannerTest.java,v
retrieving revision 1.22
retrieving revision 1.23
diff -C2 -d -r1.22 -r1.23
*** ImageScannerTest.java	29 Jun 2003 12:29:32 -0000	1.22
--- ImageScannerTest.java	13 Jul 2003 12:15:11 -0000	1.23
***************
*** 1,3 ****
! // HTMLParser Library v1_4_20030629 - A java-based parser for HTML
  // Copyright (C) Dec 31, 2000 Somik Raha
  //
--- 1,3 ----
! // HTMLParser Library v1_4_20030713 - A java-based parser for HTML
  // Copyright (C) Dec 31, 2000 Somik Raha
  //

Index: InputTagScannerTest.java
===================================================================
RCS file: /cvsroot/htmlparser/htmlparser/src/org/htmlparser/tests/scannersTests/InputTagScannerTest.java,v
retrieving revision 1.19
retrieving revision 1.20
diff -C2 -d -r1.19 -r1.20
*** InputTagScannerTest.java	29 Jun 2003 12:29:32 -0000	1.19
--- InputTagScannerTest.java	13 Jul 2003 12:15:11 -0000	1.20
***************
*** 1,3 ****
! // HTMLParser Library v1_4_20030629 - A java-based parser for HTML
  // Copyright (C) Dec 31, 2000 Somik Raha
  //
--- 1,3 ----
! // HTMLParser Library v1_4_20030713 - A java-based parser for HTML
  // Copyright (C) Dec 31, 2000 Somik Raha
  //

Index: JspScannerTest.java
===================================================================
RCS file: /cvsroot/htmlparser/htmlparser/src/org/htmlparser/tests/scannersTests/JspScannerTest.java,v
retrieving revision 1.20
retrieving revision 1.21
diff -C2 -d -r1.20 -r1.21
*** JspScannerTest.java	29 Jun 2003 12:29:32 -0000	1.20
--- JspScannerTest.java	13 Jul 2003 12:15:11 -0000	1.21
***************
*** 1,3 ****
! // HTMLParser Library v1_4_20030629 - A java-based parser for HTML
  // Copyright (C) Dec 31, 2000 Somik Raha
  //
--- 1,3 ----
! // HTMLParser Library v1_4_20030713 - A java-based parser for HTML
  // Copyright (C) Dec 31, 2000 Somik Raha
  //

Index: LabelScannerTest.java
===================================================================
RCS file: /cvsroot/htmlparser/htmlparser/src/org/htmlparser/tests/scannersTests/LabelScannerTest.java,v
retrieving revision 1.27
retrieving revision 1.28
diff -C2 -d -r1.27 -r1.28
*** LabelScannerTest.java	29 Jun 2003 12:29:32 -0000	1.27
--- LabelScannerTest.java	13 Jul 2003 12:15:11 -0000	1.28
***************
*** 1,3 ****
! // HTMLParser Library v1_4_20030629 - A java-based parser for HTML
  // Copyright (C) Dec 31, 2000 Somik Raha
  // 
--- 1,3 ----
! // HTMLParser Library v1_4_20030713 - A java-based parser for HTML
  // Copyright (C) Dec 31, 2000 Somik Raha
  // 

Index: LinkScannerTest.java
===================================================================
RCS file: /cvsroot/htmlparser/htmlparser/src/org/htmlparser/tests/scannersTests/LinkScannerTest.java,v
retrieving revision 1.29
retrieving revision 1.30
diff -C2 -d -r1.29 -r1.30
*** LinkScannerTest.java	29 Jun 2003 12:29:32 -0000	1.29
--- LinkScannerTest.java	13 Jul 2003 12:15:11 -0000	1.30
***************
*** 1,3 ****
! // HTMLParser Library v1_4_20030629 - A java-based parser for HTML
  // Copyright (C) Dec 31, 2000 Somik Raha
  //
--- 1,3 ----
! // HTMLParser Library v1_4_20030713 - A java-based parser for HTML
  // Copyright (C) Dec 31, 2000 Somik Raha
  //

Index: MetaTagScannerTest.java
===================================================================
RCS file: /cvsroot/htmlparser/htmlparser/src/org/htmlparser/tests/scannersTests/MetaTagScannerTest.java,v
retrieving revision 1.20
retrieving revision 1.21
diff -C2 -d -r1.20 -r1.21
*** MetaTagScannerTest.java	29 Jun 2003 12:29:32 -0000	1.20
--- MetaTagScannerTest.java	13 Jul 2003 12:15:11 -0000	1.21
***************
*** 1,3 ****
! // HTMLParser Library v1_4_20030629 - A java-based parser for HTML
  // Copyright (C) Dec 31, 2000 Somik Raha
  //
--- 1,3 ----
! // HTMLParser Library v1_4_20030713 - A java-based parser for HTML
  // Copyright (C) Dec 31, 2000 Somik Raha
  //

Index: OptionTagScannerTest.java
===================================================================
RCS file: /cvsroot/htmlparser/htmlparser/src/org/htmlparser/tests/scannersTests/OptionTagScannerTest.java,v
retrieving revision 1.21
retrieving revision 1.22
diff -C2 -d -r1.21 -r1.22
*** OptionTagScannerTest.java	29 Jun 2003 12:29:32 -0000	1.21
--- OptionTagScannerTest.java	13 Jul 2003 12:15:11 -0000	1.22
***************
*** 1,3 ****
! // HTMLParser Library v1_4_20030629 - A java-based parser for HTML
  // Copyright (C) Dec 31, 2000 Somik Raha
  //
--- 1,3 ----
! // HTMLParser Library v1_4_20030713 - A java-based parser for HTML
  // Copyright (C) Dec 31, 2000 Somik Raha
  //

Index: ScriptScannerTest.java
===================================================================
RCS file: /cvsroot/htmlparser/htmlparser/src/org/htmlparser/tests/scannersTests/ScriptScannerTest.java,v
retrieving revision 1.30
retrieving revision 1.31
diff -C2 -d -r1.30 -r1.31
*** ScriptScannerTest.java	29 Jun 2003 12:29:32 -0000	1.30
--- ScriptScannerTest.java	13 Jul 2003 12:15:11 -0000	1.31
***************
*** 1,3 ****
! // HTMLParser Library v1_4_20030629 - A java-based parser for HTML
  // Copyright (C) Dec 31, 2000 Somik Raha
  //
--- 1,3 ----
! // HTMLParser Library v1_4_20030713 - A java-based parser for HTML
  // Copyright (C) Dec 31, 2000 Somik Raha
  //

Index: SelectTagScannerTest.java
===================================================================
RCS file: /cvsroot/htmlparser/htmlparser/src/org/htmlparser/tests/scannersTests/SelectTagScannerTest.java,v
retrieving revision 1.21
retrieving revision 1.22
diff -C2 -d -r1.21 -r1.22
*** SelectTagScannerTest.java	29 Jun 2003 12:29:32 -0000	1.21
--- SelectTagScannerTest.java	13 Jul 2003 12:15:11 -0000	1.22
***************
*** 1,3 ****
! // HTMLParser Library v1_4_20030629 - A java-based parser for HTML
  // Copyright (C) Dec 31, 2000 Somik Raha
  //
--- 1,3 ----
! // HTMLParser Library v1_4_20030713 - A java-based parser for HTML
  // Copyright (C) Dec 31, 2000 Somik Raha
  //

Index: SpanScannerTest.java
===================================================================
RCS file: /cvsroot/htmlparser/htmlparser/src/org/htmlparser/tests/scannersTests/SpanScannerTest.java,v
retrieving revision 1.22
retrieving revision 1.23
diff -C2 -d -r1.22 -r1.23
*** SpanScannerTest.java	29 Jun 2003 12:29:32 -0000	1.22
--- SpanScannerTest.java	13 Jul 2003 12:15:11 -0000	1.23
***************
*** 1,3 ****
! // HTMLParser Library v1_4_20030629 - A java-based parser for HTML
  // Copyright (C) Dec 31, 2000 Somik Raha
  // 
--- 1,3 ----
! // HTMLParser Library v1_4_20030713 - A java-based parser for HTML
  // Copyright (C) Dec 31, 2000 Somik Raha
  // 

Index: StyleScannerTest.java
===================================================================
RCS file: /cvsroot/htmlparser/htmlparser/src/org/htmlparser/tests/scannersTests/StyleScannerTest.java,v
retrieving revision 1.20
retrieving revision 1.21
diff -C2 -d -r1.20 -r1.21
*** StyleScannerTest.java	29 Jun 2003 12:29:32 -0000	1.20
--- StyleScannerTest.java	13 Jul 2003 12:15:11 -0000	1.21
***************
*** 1,3 ****
! // HTMLParser Library v1_4_20030629 - A java-based parser for HTML
  // Copyright (C) Dec 31, 2000 Somik Raha
  //
--- 1,3 ----
! // HTMLParser Library v1_4_20030713 - A java-based parser for HTML
  // Copyright (C) Dec 31, 2000 Somik Raha
  //

Index: TableScannerTest.java
===================================================================
RCS file: /cvsroot/htmlparser/htmlparser/src/org/htmlparser/tests/scannersTests/TableScannerTest.java,v
retrieving revision 1.26
retrieving revision 1.27
diff -C2 -d -r1.26 -r1.27
*** TableScannerTest.java	29 Jun 2003 12:29:32 -0000	1.26
--- TableScannerTest.java	13 Jul 2003 12:15:11 -0000	1.27
***************
*** 1,3 ****
! // HTMLParser Library v1_4_20030629 - A java-based parser for HTML
  // Copyright (C) Dec 31, 2000 Somik Raha
  // 
--- 1,3 ----
! // HTMLParser Library v1_4_20030713 - A java-based parser for HTML
  // Copyright (C) Dec 31, 2000 Somik Raha
  // 

Index: TagScannerTest.java
===================================================================
RCS file: /cvsroot/htmlparser/htmlparser/src/org/htmlparser/tests/scannersTests/TagScannerTest.java,v
retrieving revision 1.20
retrieving revision 1.21
diff -C2 -d -r1.20 -r1.21
*** TagScannerTest.java	29 Jun 2003 12:29:32 -0000	1.20
--- TagScannerTest.java	13 Jul 2003 12:15:11 -0000	1.21
***************
*** 1,3 ****
! // HTMLParser Library v1_4_20030629 - A java-based parser for HTML
  // Copyright (C) Dec 31, 2000 Somik Raha
  //
--- 1,3 ----
! // HTMLParser Library v1_4_20030713 - A java-based parser for HTML
  // Copyright (C) Dec 31, 2000 Somik Raha
  //

Index: TextareaTagScannerTest.java
===================================================================
RCS file: /cvsroot/htmlparser/htmlparser/src/org/htmlparser/tests/scannersTests/TextareaTagScannerTest.java,v
retrieving revision 1.19
retrieving revision 1.20
diff -C2 -d -r1.19 -r1.20
*** TextareaTagScannerTest.java	29 Jun 2003 12:29:32 -0000	1.19
--- TextareaTagScannerTest.java	13 Jul 2003 12:15:11 -0000	1.20
***************
*** 1,3 ****
! // HTMLParser Library v1_4_20030629 - A java-based parser for HTML
  // Copyright (C) Dec 31, 2000 Somik Raha
  //
--- 1,3 ----
! // HTMLParser Library v1_4_20030713 - A java-based parser for HTML
  // Copyright (C) Dec 31, 2000 Somik Raha
  //

Index: TitleScannerTest.java
===================================================================
RCS file: /cvsroot/htmlparser/htmlparser/src/org/htmlparser/tests/scannersTests/TitleScannerTest.java,v
retrieving revision 1.20
retrieving revision 1.21
diff -C2 -d -r1.20 -r1.21
*** TitleScannerTest.java	29 Jun 2003 12:29:32 -0000	1.20
--- TitleScannerTest.java	13 Jul 2003 12:15:11 -0000	1.21
***************
*** 1,3 ****
! // HTMLParser Library v1_4_20030629 - A java-based parser for HTML
  // Copyright (C) Dec 31, 2000 Somik Raha
  //
--- 1,3 ----
! // HTMLParser Library v1_4_20030713 - A java-based parser for HTML
  // Copyright (C) Dec 31, 2000 Somik Raha
  //

Index: XmlEndTagScanningTest.java
===================================================================
RCS file: /cvsroot/htmlparser/htmlparser/src/org/htmlparser/tests/scannersTests/XmlEndTagScanningTest.java,v
retrieving revision 1.22
retrieving revision 1.23
diff -C2 -d -r1.22 -r1.23
*** XmlEndTagScanningTest.java	29 Jun 2003 12:29:32 -0000	1.22
--- XmlEndTagScanningTest.java	13 Jul 2003 12:15:11 -0000	1.23
***************
*** 1,3 ****
! // HTMLParser Library v1_4_20030629 - A java-based parser for HTML
  // Copyright (C) Dec 31, 2000 Somik Raha
  // 
--- 1,3 ----
! // HTMLParser Library v1_4_20030713 - A java-based parser for HTML
  // Copyright (C) Dec 31, 2000 Somik Raha
  // 

Index: package.html
===================================================================
RCS file: /cvsroot/htmlparser/htmlparser/src/org/htmlparser/tests/scannersTests/package.html,v
retrieving revision 1.8
retrieving revision 1.9
diff -C2 -d -r1.8 -r1.9
*** package.html	29 Jun 2003 12:29:32 -0000	1.8
--- package.html	13 Jul 2003 12:15:11 -0000	1.9
***************
*** 6,10 ****
    @(#)package.html	1.60 98/01/27
  
!  HTMLParser Library v1_4_20030629 - A java-based parser for HTML
   Copyright (C) Dec 31, 2000 Somik Raha
  
--- 6,10 ----
    @(#)package.html	1.60 98/01/27
  
!  HTMLParser Library v1_4_20030713 - A java-based parser for HTML
   Copyright (C) Dec 31, 2000 Somik Raha
  

[Htmlparser-cvs] htmlparser/src/org/htmlparser/tests/parserHelperTests AllTests.java,1.20,1.21 CompositeTagScannerHelperTest.java,1.13,1.14 RemarkNodeParserTest.java,1.28,1.29 StringParserTest.java,1.30,1.31

[<der...@us...>]

Update of /cvsroot/htmlparser/htmlparser/src/org/htmlparser/tests/parserHelperTests
In directory sc8-pr-cvs1:/tmp/cvs-serv15493/htmlparser/src/org/htmlparser/tests/parserHelperTests

Modified Files:
	AllTests.java CompositeTagScannerHelperTest.java 
	RemarkNodeParserTest.java StringParserTest.java 
Log Message:
Update version headers to 1.4-20030713 and update changelog.



Index: AllTests.java
===================================================================
RCS file: /cvsroot/htmlparser/htmlparser/src/org/htmlparser/tests/parserHelperTests/AllTests.java,v
retrieving revision 1.20
retrieving revision 1.21
diff -C2 -d -r1.20 -r1.21
*** AllTests.java	29 Jun 2003 12:29:32 -0000	1.20
--- AllTests.java	13 Jul 2003 12:15:10 -0000	1.21
***************
*** 1,3 ****
! // HTMLParser Library v1_4_20030629 - A java-based parser for HTML
  // Copyright (C) Dec 31, 2000 Somik Raha
  //
--- 1,3 ----
! // HTMLParser Library v1_4_20030713 - A java-based parser for HTML
  // Copyright (C) Dec 31, 2000 Somik Raha
  //

Index: CompositeTagScannerHelperTest.java
===================================================================
RCS file: /cvsroot/htmlparser/htmlparser/src/org/htmlparser/tests/parserHelperTests/CompositeTagScannerHelperTest.java,v
retrieving revision 1.13
retrieving revision 1.14
diff -C2 -d -r1.13 -r1.14
*** CompositeTagScannerHelperTest.java	29 Jun 2003 12:29:32 -0000	1.13
--- CompositeTagScannerHelperTest.java	13 Jul 2003 12:15:10 -0000	1.14
***************
*** 1,3 ****
! // HTMLParser Library v1_4_20030629 - A java-based parser for HTML
  // Copyright (C) Dec 31, 2000 Somik Raha
  // 
--- 1,3 ----
! // HTMLParser Library v1_4_20030713 - A java-based parser for HTML
  // Copyright (C) Dec 31, 2000 Somik Raha
  // 

Index: RemarkNodeParserTest.java
===================================================================
RCS file: /cvsroot/htmlparser/htmlparser/src/org/htmlparser/tests/parserHelperTests/RemarkNodeParserTest.java,v
retrieving revision 1.28
retrieving revision 1.29
diff -C2 -d -r1.28 -r1.29
*** RemarkNodeParserTest.java	29 Jun 2003 12:29:32 -0000	1.28
--- RemarkNodeParserTest.java	13 Jul 2003 12:15:10 -0000	1.29
***************
*** 1,3 ****
! // HTMLParser Library v1_4_20030629 - A java-based parser for HTML
  // Copyright (C) Dec 31, 2000 Somik Raha
  //
--- 1,3 ----
! // HTMLParser Library v1_4_20030713 - A java-based parser for HTML
  // Copyright (C) Dec 31, 2000 Somik Raha
  //

Index: StringParserTest.java
===================================================================
RCS file: /cvsroot/htmlparser/htmlparser/src/org/htmlparser/tests/parserHelperTests/StringParserTest.java,v
retrieving revision 1.30
retrieving revision 1.31
diff -C2 -d -r1.30 -r1.31
*** StringParserTest.java	29 Jun 2003 12:29:32 -0000	1.30
--- StringParserTest.java	13 Jul 2003 12:15:11 -0000	1.31
***************
*** 1,3 ****
! // HTMLParser Library v1_4_20030629 - A java-based parser for HTML
  // Copyright (C) Dec 31, 2000 Somik Raha
  //
--- 1,3 ----
! // HTMLParser Library v1_4_20030713 - A java-based parser for HTML
  // Copyright (C) Dec 31, 2000 Somik Raha
  //

[Htmlparser-cvs] htmlparser/src/org/htmlparser/tests/nodeDecoratorTests AllTests.java,1.3,1.4 DecodingNodeTest.java,1.4,1.5 EscapeCharacterRemovingNodeTest.java,1.4,1.5 NonBreakingSpaceConvertingNodeTest.java,1.3,1.4

[<der...@us...>]

Update of /cvsroot/htmlparser/htmlparser/src/org/htmlparser/tests/nodeDecoratorTests
In directory sc8-pr-cvs1:/tmp/cvs-serv15493/htmlparser/src/org/htmlparser/tests/nodeDecoratorTests

Modified Files:
	AllTests.java DecodingNodeTest.java 
	EscapeCharacterRemovingNodeTest.java 
	NonBreakingSpaceConvertingNodeTest.java 
Log Message:
Update version headers to 1.4-20030713 and update changelog.



Index: AllTests.java
===================================================================
RCS file: /cvsroot/htmlparser/htmlparser/src/org/htmlparser/tests/nodeDecoratorTests/AllTests.java,v
retrieving revision 1.3
retrieving revision 1.4
diff -C2 -d -r1.3 -r1.4
*** AllTests.java	29 Jun 2003 12:29:32 -0000	1.3
--- AllTests.java	13 Jul 2003 12:15:09 -0000	1.4
***************
*** 1,3 ****
! // HTMLParser Library v1_4_20030629 - A java-based parser for HTML
  // Copyright (C) Dec 31, 2000 Somik Raha
  //
--- 1,3 ----
! // HTMLParser Library v1_4_20030713 - A java-based parser for HTML
  // Copyright (C) Dec 31, 2000 Somik Raha
  //

Index: DecodingNodeTest.java
===================================================================
RCS file: /cvsroot/htmlparser/htmlparser/src/org/htmlparser/tests/nodeDecoratorTests/DecodingNodeTest.java,v
retrieving revision 1.4
retrieving revision 1.5
diff -C2 -d -r1.4 -r1.5
*** DecodingNodeTest.java	12 Jul 2003 00:33:59 -0000	1.4
--- DecodingNodeTest.java	13 Jul 2003 12:15:10 -0000	1.5
***************
*** 1,3 ****
! // HTMLParser Library v1_4_20030629 - A java-based parser for HTML
  // Copyright (C) Dec 31, 2000 Somik Raha
  //
--- 1,3 ----
! // HTMLParser Library v1_4_20030713 - A java-based parser for HTML
  // Copyright (C) Dec 31, 2000 Somik Raha
  //

Index: EscapeCharacterRemovingNodeTest.java
===================================================================
RCS file: /cvsroot/htmlparser/htmlparser/src/org/htmlparser/tests/nodeDecoratorTests/EscapeCharacterRemovingNodeTest.java,v
retrieving revision 1.4
retrieving revision 1.5
diff -C2 -d -r1.4 -r1.5
*** EscapeCharacterRemovingNodeTest.java	12 Jul 2003 00:33:59 -0000	1.4
--- EscapeCharacterRemovingNodeTest.java	13 Jul 2003 12:15:10 -0000	1.5
***************
*** 1,3 ****
! // HTMLParser Library v1_4_20030629 - A java-based parser for HTML
  // Copyright (C) Dec 31, 2000 Somik Raha
  //
--- 1,3 ----
! // HTMLParser Library v1_4_20030713 - A java-based parser for HTML
  // Copyright (C) Dec 31, 2000 Somik Raha
  //

Index: NonBreakingSpaceConvertingNodeTest.java
===================================================================
RCS file: /cvsroot/htmlparser/htmlparser/src/org/htmlparser/tests/nodeDecoratorTests/NonBreakingSpaceConvertingNodeTest.java,v
retrieving revision 1.3
retrieving revision 1.4
diff -C2 -d -r1.3 -r1.4
*** NonBreakingSpaceConvertingNodeTest.java	12 Jul 2003 00:33:59 -0000	1.3
--- NonBreakingSpaceConvertingNodeTest.java	13 Jul 2003 12:15:10 -0000	1.4
***************
*** 1,3 ****
! // HTMLParser Library v1_4_20030629 - A java-based parser for HTML
  // Copyright (C) Dec 31, 2000 Somik Raha
  //
--- 1,3 ----
! // HTMLParser Library v1_4_20030713 - A java-based parser for HTML
  // Copyright (C) Dec 31, 2000 Somik Raha
  //