You are viewing a plain text version of this content. The canonical link for it is here.
Posted to commits@lenya.apache.org by gr...@apache.org on 2005/04/24 07:30:38 UTC

svn commit: r164448 [129/299] - in /lenya/site: ./ 1_2_x/ 1_2_x/components/ 1_2_x/components/accesscontrol/ 1_2_x/components/asset-management/ 1_2_x/components/authoring/ 1_2_x/components/deployment/ 1_2_x/components/editors/ 1_2_x/components/layout/ 1_2_x/components/layout/images/ 1_2_x/components/layout/images/live/ 1_2_x/components/link-management/ 1_2_x/components/metadata/ 1_2_x/components/multilingual/ 1_2_x/components/publication/ 1_2_x/components/repository/ 1_2_x/components/resource-types/ 1_2_x/components/revisioncontrol/ 1_2_x/components/search/ 1_2_x/components/sitemanagement/ 1_2_x/components/tasks/ 1_2_x/components/uri-handling/ 1_2_x/components/uri-handling/images/ 1_2_x/components/uri-handling/images/live/ 1_2_x/components/workflow/ 1_2_x/installation/ 1_2_x/misc/ 1_4/ 1_4/concepts/ 1_4/installation/ 1_4/reference/ 1_4/reference/publication-templating/ 1_4/reference/usecase-framework/ apidocs/ apidocs/1.2/ apidocs/1.2/org/ apidocs/1.2/org/apache/ apidocs/1.2/org/apache/lenya/ apidocs/1.2/org/apache/lenya/ac/ apidocs/1.2/org/apache/lenya/ac/cache/ apidocs/1.2/org/apache/lenya/ac/file/ apidocs/1.2/org/apache/lenya/ac/impl/ apidocs/1.2/org/apache/lenya/ac/ldap/ apidocs/1.2/org/apache/lenya/cms/ apidocs/1.2/org/apache/lenya/cms/ac/ apidocs/1.2/org/apache/lenya/cms/ac/cocoon/ apidocs/1.2/org/apache/lenya/cms/ac/usecase/ apidocs/1.2/org/apache/lenya/cms/ac/workflow/ apidocs/1.2/org/apache/lenya/cms/ant/ apidocs/1.2/org/apache/lenya/cms/authoring/ apidocs/1.2/org/apache/lenya/cms/cocoon/ apidocs/1.2/org/apache/lenya/cms/cocoon/acting/ apidocs/1.2/org/apache/lenya/cms/cocoon/bean/ apidocs/1.2/org/apache/lenya/cms/cocoon/components/ apidocs/1.2/org/apache/lenya/cms/cocoon/components/modules/ apidocs/1.2/org/apache/lenya/cms/cocoon/components/modules/input/ apidocs/1.2/org/apache/lenya/cms/cocoon/flow/ apidocs/1.2/org/apache/lenya/cms/cocoon/generation/ apidocs/1.2/org/apache/lenya/cms/cocoon/scheduler/ apidocs/1.2/org/apache/lenya/cms/cocoon/source/ apidocs/1.2/org/apache/lenya/cms/cocoon/task/ apidocs/1.2/org/apache/lenya/cms/cocoon/transformation/ apidocs/1.2/org/apache/lenya/cms/cocoon/uriparameterizer/ apidocs/1.2/org/apache/lenya/cms/cocoon/workflow/ apidocs/1.2/org/apache/lenya/cms/mail/ apidocs/1.2/org/apache/lenya/cms/publication/ apidocs/1.2/org/apache/lenya/cms/publication/file/ apidocs/1.2/org/apache/lenya/cms/publication/task/ apidocs/1.2/org/apache/lenya/cms/publication/util/ apidocs/1.2/org/apache/lenya/cms/publication/xsp/ apidocs/1.2/org/apache/lenya/cms/publishing/ apidocs/1.2/org/apache/lenya/cms/rc/ apidocs/1.2/org/apache/lenya/cms/scheduler/ apidocs/1.2/org/apache/lenya/cms/scheduler/xml/ apidocs/1.2/org/apache/lenya/cms/task/ apidocs/1.2/org/apache/lenya/cms/workflow/ apidocs/1.2/org/apache/lenya/defaultpub/ apidocs/1.2/org/apache/lenya/defaultpub/cms/ apidocs/1.2/org/apache/lenya/defaultpub/cms/task/ apidocs/1.2/org/apache/lenya/lucene/ apidocs/1.2/org/apache/lenya/lucene/html/ apidocs/1.2/org/apache/lenya/lucene/index/ apidocs/1.2/org/apache/lenya/lucene/parser/ apidocs/1.2/org/apache/lenya/net/ apidocs/1.2/org/apache/lenya/search/ apidocs/1.2/org/apache/lenya/search/crawler/ apidocs/1.2/org/apache/lenya/util/ apidocs/1.2/org/apache/lenya/workflow/ apidocs/1.2/org/apache/lenya/workflow/impl/ apidocs/1.2/org/apache/lenya/xml/ apidocs/1.2/org/apache/lenya/xml/parser/ apidocs/1.2/org/apache/lenya/xml/xpointer/ apidocs/1.2/resources/ apidocs/1.4/ apidocs/1.4/org/ apidocs/1.4/org/apache/ apidocs/1.4/org/apache/lenya/ apidocs/1.4/org/apache/lenya/ac/ apidocs/1.4/org/apache/lenya/ac/cache/ apidocs/1.4/org/apache/lenya/ac/file/ apidocs/1.4/org/apache/lenya/ac/impl/ apidocs/1.4/org/apache/lenya/ac/ldap/ apidocs/1.4/org/apache/lenya/cms/ apidocs/1.4/org/apache/lenya/cms/ac/ apidocs/1.4/org/apache/lenya/cms/ac/cocoon/ apidocs/1.4/org/apache/lenya/cms/ac/usecase/ apidocs/1.4/org/apache/lenya/cms/ac/usecases/ apidocs/1.4/org/apache/lenya/cms/ac/workflow/ apidocs/1.4/org/apache/lenya/cms/ant/ apidocs/1.4/org/apache/lenya/cms/authoring/ apidocs/1.4/org/apache/lenya/cms/cocoon/ apidocs/1.4/org/apache/lenya/cms/cocoon/acting/ apidocs/1.4/org/apache/lenya/cms/cocoon/bean/ apidocs/1.4/org/apache/lenya/cms/cocoon/components/ apidocs/1.4/org/apache/lenya/cms/cocoon/components/modules/ apidocs/1.4/org/apache/lenya/cms/cocoon/components/modules/input/ apidocs/1.4/org/apache/lenya/cms/cocoon/flow/ apidocs/1.4/org/apache/lenya/cms/cocoon/generation/ apidocs/1.4/org/apache/lenya/cms/cocoon/matching/ apidocs/1.4/org/apache/lenya/cms/cocoon/scheduler/ apidocs/1.4/org/apache/lenya/cms/cocoon/source/ apidocs/1.4/org/apache/lenya/cms/cocoon/task/ apidocs/1.4/org/apache/lenya/cms/cocoon/transformation/ apidocs/1.4/org/apache/lenya/cms/cocoon/uriparameterizer/ apidocs/1.4/org/apache/lenya/cms/cocoon/workflow/ apidocs/1.4/org/apache/lenya/cms/mail/ apidocs/1.4/org/apache/lenya/cms/metadata/ apidocs/1.4/org/apache/lenya/cms/metadata/dublincore/ apidocs/1.4/org/apache/lenya/cms/metadata/usecases/ apidocs/1.4/org/apache/lenya/cms/publication/ apidocs/1.4/org/apache/lenya/cms/publication/file/ apidocs/1.4/org/apache/lenya/cms/publication/task/ apidocs/1.4/org/apache/lenya/cms/publication/templating/ apidocs/1.4/org/apache/lenya/cms/publication/util/ apidocs/1.4/org/apache/lenya/cms/publishing/ apidocs/1.4/org/apache/lenya/cms/rc/ apidocs/1.4/org/apache/lenya/cms/scheduler/ apidocs/1.4/org/apache/lenya/cms/scheduler/xml/ apidocs/1.4/org/apache/lenya/cms/search/ apidocs/1.4/org/apache/lenya/cms/search/usecases/ apidocs/1.4/org/apache/lenya/cms/site/ apidocs/1.4/org/apache/lenya/cms/site/topicmap/ apidocs/1.4/org/apache/lenya/cms/site/tree/ apidocs/1.4/org/apache/lenya/cms/site/usecases/ apidocs/1.4/org/apache/lenya/cms/task/ apidocs/1.4/org/apache/lenya/cms/usecase/ apidocs/1.4/org/apache/lenya/cms/workflow/ apidocs/1.4/org/apache/lenya/cms/workflow/usecases/ apidocs/1.4/org/apache/lenya/defaultpub/ apidocs/1.4/org/apache/lenya/defaultpub/cms/ apidocs/1.4/org/apache/lenya/defaultpub/cms/task/ apidocs/1.4/org/apache/lenya/defaultpub/cms/usecases/ apidocs/1.4/org/apache/lenya/lucene/ apidocs/1.4/org/apache/lenya/lucene/html/ apidocs/1.4/org/apache/lenya/lucene/index/ apidocs/1.4/org/apache/lenya/lucene/parser/ apidocs/1.4/org/apache/lenya/net/ apidocs/1.4/org/apache/lenya/search/ apidocs/1.4/org/apache/lenya/search/crawler/ apidocs/1.4/org/apache/lenya/util/ apidocs/1.4/org/apache/lenya/workflow/ apidocs/1.4/org/apache/lenya/workflow/impl/ apidocs/1.4/org/apache/lenya/xml/ apidocs/1.4/org/apache/lenya/xml/parser/ apidocs/1.4/org/apache/lenya/xml/xpointer/ apidocs/1.4/resources/ community/ images/ images/live/ skin/ skin/css/ skin/images/ skin/scripts/

Added: lenya/site/apidocs/1.2/org/apache/lenya/search/crawler/ContentHandler.html
URL: http://svn.apache.org/viewcvs/lenya/site/apidocs/1.2/org/apache/lenya/search/crawler/ContentHandler.html?rev=164448&view=auto
==============================================================================
--- lenya/site/apidocs/1.2/org/apache/lenya/search/crawler/ContentHandler.html (added)
+++ lenya/site/apidocs/1.2/org/apache/lenya/search/crawler/ContentHandler.html Sat Apr 23 22:30:06 2005
@@ -0,0 +1,459 @@
+<!DOCTYPE HTML PUBLIC "-//W3C//DTD HTML 4.01 Transitional//EN" "http://www.w3.org/TR/html4/loose.dtd">
+<!--NewPage-->
+<HTML>
+<HEAD>
+<!-- Generated by javadoc (build 1.4.2_03) on Mon Feb 21 17:32:47 EST 2005 -->
+<TITLE>
+ContentHandler (Apache Lenya API - Version 1.2.2)
+</TITLE>
+
+<META NAME="keywords" CONTENT="org.apache.lenya.search.crawler.ContentHandler interface">
+
+<LINK REL ="stylesheet" TYPE="text/css" HREF="../../../../../javadoc.css" TITLE="Style">
+
+<SCRIPT type="text/javascript">
+function windowTitle()
+{
+    parent.document.title="ContentHandler (Apache Lenya API - Version 1.2.2)";
+}
+</SCRIPT>
+
+</HEAD>
+
+<BODY BGCOLOR="white" onload="windowTitle();">
+
+
+<!-- ========= START OF TOP NAVBAR ======= -->
+<A NAME="navbar_top"><!-- --></A>
+<A HREF="#skip-navbar_top" title="Skip navigation links"></A>
+<TABLE BORDER="0" WIDTH="100%" CELLPADDING="1" CELLSPACING="0" SUMMARY="">
+<TR>
+<TD COLSPAN=3 BGCOLOR="#EEEEFF" CLASS="NavBarCell1">
+<A NAME="navbar_top_firstrow"><!-- --></A>
+<TABLE BORDER="0" CELLPADDING="0" CELLSPACING="3" SUMMARY="">
+  <TR ALIGN="center" VALIGN="top">
+  <TD BGCOLOR="#EEEEFF" CLASS="NavBarCell1">    <A HREF="../../../../../overview-summary.html"><FONT CLASS="NavBarFont1"><B>Overview</B></FONT></A>&nbsp;</TD>
+  <TD BGCOLOR="#EEEEFF" CLASS="NavBarCell1">    <A HREF="package-summary.html"><FONT CLASS="NavBarFont1"><B>Package</B></FONT></A>&nbsp;</TD>
+  <TD BGCOLOR="#FFFFFF" CLASS="NavBarCell1Rev"> &nbsp;<FONT CLASS="NavBarFont1Rev"><B>Class</B></FONT>&nbsp;</TD>
+  <TD BGCOLOR="#EEEEFF" CLASS="NavBarCell1">    <A HREF="package-tree.html"><FONT CLASS="NavBarFont1"><B>Tree</B></FONT></A>&nbsp;</TD>
+  <TD BGCOLOR="#EEEEFF" CLASS="NavBarCell1">    <A HREF="../../../../../deprecated-list.html"><FONT CLASS="NavBarFont1"><B>Deprecated</B></FONT></A>&nbsp;</TD>
+  <TD BGCOLOR="#EEEEFF" CLASS="NavBarCell1">    <A HREF="../../../../../help-doc.html"><FONT CLASS="NavBarFont1"><B>Help</B></FONT></A>&nbsp;</TD>
+  </TR>
+</TABLE>
+</TD>
+<TD ALIGN="right" VALIGN="top" ROWSPAN=3><EM>
+</EM>
+</TD>
+</TR>
+
+<TR>
+<TD BGCOLOR="white" CLASS="NavBarCell2"><FONT SIZE="-2">
+&nbsp;PREV CLASS&nbsp;
+&nbsp;NEXT CLASS</FONT></TD>
+<TD BGCOLOR="white" CLASS="NavBarCell2"><FONT SIZE="-2">
+  <A HREF="../../../../../index.html" target="_top"><B>FRAMES</B></A>  &nbsp;
+&nbsp;<A HREF="ContentHandler.html" target="_top"><B>NO FRAMES</B></A>  &nbsp;
+&nbsp;<SCRIPT type="text/javascript">
+  <!--
+  if(window==top) {
+    document.writeln('<A HREF="../../../../../allclasses-noframe.html"><B>All Classes</B></A>');
+  }
+  //-->
+</SCRIPT>
+<NOSCRIPT>
+  <A HREF="../../../../../allclasses-noframe.html"><B>All Classes</B></A>
+</NOSCRIPT>
+
+</FONT></TD>
+</TR>
+<TR>
+<TD VALIGN="top" CLASS="NavBarCell3"><FONT SIZE="-2">
+  SUMMARY:&nbsp;NESTED&nbsp;|&nbsp;FIELD&nbsp;|&nbsp;CONSTR&nbsp;|&nbsp;<A HREF="#method_summary">METHOD</A></FONT></TD>
+<TD VALIGN="top" CLASS="NavBarCell3"><FONT SIZE="-2">
+DETAIL:&nbsp;FIELD&nbsp;|&nbsp;CONSTR&nbsp;|&nbsp;<A HREF="#method_detail">METHOD</A></FONT></TD>
+</TR>
+</TABLE>
+<A NAME="skip-navbar_top"></A>
+<!-- ========= END OF TOP NAVBAR ========= -->
+
+<HR>
+<!-- ======== START OF CLASS DATA ======== -->
+<H2>
+<FONT SIZE="-1">
+org.apache.lenya.search.crawler</FONT>
+<BR>
+Interface ContentHandler</H2>
+<DL>
+<DT><B>All Known Implementing Classes:</B> <DD><A HREF="../../../../../org/apache/lenya/search/crawler/HTMLHandler.html" title="class in org.apache.lenya.search.crawler">HTMLHandler</A></DD>
+</DL>
+<HR>
+<DL>
+<DT>public interface <B>ContentHandler</B></DL>
+
+<P>
+DOCUMENT ME!
+<P>
+
+<P>
+<HR>
+
+<P>
+<!-- ======== NESTED CLASS SUMMARY ======== -->
+
+
+<!-- =========== FIELD SUMMARY =========== -->
+
+
+<!-- ======== CONSTRUCTOR SUMMARY ======== -->
+
+
+<!-- ========== METHOD SUMMARY =========== -->
+
+<A NAME="method_summary"><!-- --></A>
+<TABLE BORDER="1" WIDTH="100%" CELLPADDING="3" CELLSPACING="0" SUMMARY="">
+<TR BGCOLOR="#CCCCFF" CLASS="TableHeadingColor">
+<TD COLSPAN=2><FONT SIZE="+2">
+<B>Method Summary</B></FONT></TD>
+</TR>
+<TR BGCOLOR="white" CLASS="TableRowColor">
+<TD ALIGN="right" VALIGN="top" WIDTH="1%"><FONT SIZE="-1">
+<CODE>&nbsp;java.lang.String</CODE></FONT></TD>
+<TD><CODE><B><A HREF="../../../../../org/apache/lenya/search/crawler/ContentHandler.html#getAuthor()">getAuthor</A></B>()</CODE>
+
+<BR>
+&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;Return author</TD>
+</TR>
+<TR BGCOLOR="white" CLASS="TableRowColor">
+<TD ALIGN="right" VALIGN="top" WIDTH="1%"><FONT SIZE="-1">
+<CODE>&nbsp;java.lang.String</CODE></FONT></TD>
+<TD><CODE><B><A HREF="../../../../../org/apache/lenya/search/crawler/ContentHandler.html#getCategories()">getCategories</A></B>()</CODE>
+
+<BR>
+&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;Return categories (from META tags)</TD>
+</TR>
+<TR BGCOLOR="white" CLASS="TableRowColor">
+<TD ALIGN="right" VALIGN="top" WIDTH="1%"><FONT SIZE="-1">
+<CODE>&nbsp;java.lang.String</CODE></FONT></TD>
+<TD><CODE><B><A HREF="../../../../../org/apache/lenya/search/crawler/ContentHandler.html#getContents()">getContents</A></B>()</CODE>
+
+<BR>
+&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;Return contents</TD>
+</TR>
+<TR BGCOLOR="white" CLASS="TableRowColor">
+<TD ALIGN="right" VALIGN="top" WIDTH="1%"><FONT SIZE="-1">
+<CODE>&nbsp;java.lang.String</CODE></FONT></TD>
+<TD><CODE><B><A HREF="../../../../../org/apache/lenya/search/crawler/ContentHandler.html#getDescription()">getDescription</A></B>()</CODE>
+
+<BR>
+&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;Return description (from META tags)</TD>
+</TR>
+<TR BGCOLOR="white" CLASS="TableRowColor">
+<TD ALIGN="right" VALIGN="top" WIDTH="1%"><FONT SIZE="-1">
+<CODE>&nbsp;java.lang.String</CODE></FONT></TD>
+<TD><CODE><B><A HREF="../../../../../org/apache/lenya/search/crawler/ContentHandler.html#getHREF()">getHREF</A></B>()</CODE>
+
+<BR>
+&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;Return META HREF</TD>
+</TR>
+<TR BGCOLOR="white" CLASS="TableRowColor">
+<TD ALIGN="right" VALIGN="top" WIDTH="1%"><FONT SIZE="-1">
+<CODE>&nbsp;java.lang.String</CODE></FONT></TD>
+<TD><CODE><B><A HREF="../../../../../org/apache/lenya/search/crawler/ContentHandler.html#getKeywords()">getKeywords</A></B>()</CODE>
+
+<BR>
+&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;Return keywords (from META tags)</TD>
+</TR>
+<TR BGCOLOR="white" CLASS="TableRowColor">
+<TD ALIGN="right" VALIGN="top" WIDTH="1%"><FONT SIZE="-1">
+<CODE>&nbsp;java.util.List</CODE></FONT></TD>
+<TD><CODE><B><A HREF="../../../../../org/apache/lenya/search/crawler/ContentHandler.html#getLinks()">getLinks</A></B>()</CODE>
+
+<BR>
+&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;Return links</TD>
+</TR>
+<TR BGCOLOR="white" CLASS="TableRowColor">
+<TD ALIGN="right" VALIGN="top" WIDTH="1%"><FONT SIZE="-1">
+<CODE>&nbsp;long</CODE></FONT></TD>
+<TD><CODE><B><A HREF="../../../../../org/apache/lenya/search/crawler/ContentHandler.html#getPublished()">getPublished</A></B>()</CODE>
+
+<BR>
+&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;Return published date (from META tag)</TD>
+</TR>
+<TR BGCOLOR="white" CLASS="TableRowColor">
+<TD ALIGN="right" VALIGN="top" WIDTH="1%"><FONT SIZE="-1">
+<CODE>&nbsp;boolean</CODE></FONT></TD>
+<TD><CODE><B><A HREF="../../../../../org/apache/lenya/search/crawler/ContentHandler.html#getRobotFollow()">getRobotFollow</A></B>()</CODE>
+
+<BR>
+&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;Return description (from META tags)</TD>
+</TR>
+<TR BGCOLOR="white" CLASS="TableRowColor">
+<TD ALIGN="right" VALIGN="top" WIDTH="1%"><FONT SIZE="-1">
+<CODE>&nbsp;boolean</CODE></FONT></TD>
+<TD><CODE><B><A HREF="../../../../../org/apache/lenya/search/crawler/ContentHandler.html#getRobotIndex()">getRobotIndex</A></B>()</CODE>
+
+<BR>
+&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;Return description (from META tags)</TD>
+</TR>
+<TR BGCOLOR="white" CLASS="TableRowColor">
+<TD ALIGN="right" VALIGN="top" WIDTH="1%"><FONT SIZE="-1">
+<CODE>&nbsp;java.lang.String</CODE></FONT></TD>
+<TD><CODE><B><A HREF="../../../../../org/apache/lenya/search/crawler/ContentHandler.html#getTitle()">getTitle</A></B>()</CODE>
+
+<BR>
+&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;Return page title</TD>
+</TR>
+<TR BGCOLOR="white" CLASS="TableRowColor">
+<TD ALIGN="right" VALIGN="top" WIDTH="1%"><FONT SIZE="-1">
+<CODE>&nbsp;void</CODE></FONT></TD>
+<TD><CODE><B><A HREF="../../../../../org/apache/lenya/search/crawler/ContentHandler.html#parse(java.io.InputStream)">parse</A></B>(java.io.InputStream&nbsp;in)</CODE>
+
+<BR>
+&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;Parse Content.</TD>
+</TR>
+</TABLE>
+&nbsp;
+<P>
+
+<!-- ============ FIELD DETAIL =========== -->
+
+
+<!-- ========= CONSTRUCTOR DETAIL ======== -->
+
+
+<!-- ============ METHOD DETAIL ========== -->
+
+<A NAME="method_detail"><!-- --></A>
+<TABLE BORDER="1" WIDTH="100%" CELLPADDING="3" CELLSPACING="0" SUMMARY="">
+<TR BGCOLOR="#CCCCFF" CLASS="TableHeadingColor">
+<TD COLSPAN=1><FONT SIZE="+2">
+<B>Method Detail</B></FONT></TD>
+</TR>
+</TABLE>
+
+<A NAME="getAuthor()"><!-- --></A><H3>
+getAuthor</H3>
+<PRE>
+public java.lang.String <B>getAuthor</B>()</PRE>
+<DL>
+<DD>Return author
+<P>
+<DD><DL>
+
+<DT><B>Returns:</B><DD>DOCUMENT ME!</DL>
+</DD>
+</DL>
+<HR>
+
+<A NAME="getCategories()"><!-- --></A><H3>
+getCategories</H3>
+<PRE>
+public java.lang.String <B>getCategories</B>()</PRE>
+<DL>
+<DD>Return categories (from META tags)
+<P>
+<DD><DL>
+
+<DT><B>Returns:</B><DD>DOCUMENT ME!</DL>
+</DD>
+</DL>
+<HR>
+
+<A NAME="getContents()"><!-- --></A><H3>
+getContents</H3>
+<PRE>
+public java.lang.String <B>getContents</B>()</PRE>
+<DL>
+<DD>Return contents
+<P>
+<DD><DL>
+
+<DT><B>Returns:</B><DD>DOCUMENT ME!</DL>
+</DD>
+</DL>
+<HR>
+
+<A NAME="getDescription()"><!-- --></A><H3>
+getDescription</H3>
+<PRE>
+public java.lang.String <B>getDescription</B>()</PRE>
+<DL>
+<DD>Return description (from META tags)
+<P>
+<DD><DL>
+
+<DT><B>Returns:</B><DD>DOCUMENT ME!</DL>
+</DD>
+</DL>
+<HR>
+
+<A NAME="getHREF()"><!-- --></A><H3>
+getHREF</H3>
+<PRE>
+public java.lang.String <B>getHREF</B>()</PRE>
+<DL>
+<DD>Return META HREF
+<P>
+<DD><DL>
+
+<DT><B>Returns:</B><DD>DOCUMENT ME!</DL>
+</DD>
+</DL>
+<HR>
+
+<A NAME="getKeywords()"><!-- --></A><H3>
+getKeywords</H3>
+<PRE>
+public java.lang.String <B>getKeywords</B>()</PRE>
+<DL>
+<DD>Return keywords (from META tags)
+<P>
+<DD><DL>
+
+<DT><B>Returns:</B><DD>DOCUMENT ME!</DL>
+</DD>
+</DL>
+<HR>
+
+<A NAME="getLinks()"><!-- --></A><H3>
+getLinks</H3>
+<PRE>
+public java.util.List <B>getLinks</B>()</PRE>
+<DL>
+<DD>Return links
+<P>
+<DD><DL>
+
+<DT><B>Returns:</B><DD>DOCUMENT ME!</DL>
+</DD>
+</DL>
+<HR>
+
+<A NAME="getPublished()"><!-- --></A><H3>
+getPublished</H3>
+<PRE>
+public long <B>getPublished</B>()</PRE>
+<DL>
+<DD>Return published date (from META tag)
+<P>
+<DD><DL>
+
+<DT><B>Returns:</B><DD>DOCUMENT ME!</DL>
+</DD>
+</DL>
+<HR>
+
+<A NAME="getRobotFollow()"><!-- --></A><H3>
+getRobotFollow</H3>
+<PRE>
+public boolean <B>getRobotFollow</B>()</PRE>
+<DL>
+<DD>Return description (from META tags)
+<P>
+<DD><DL>
+
+<DT><B>Returns:</B><DD>DOCUMENT ME!</DL>
+</DD>
+</DL>
+<HR>
+
+<A NAME="getRobotIndex()"><!-- --></A><H3>
+getRobotIndex</H3>
+<PRE>
+public boolean <B>getRobotIndex</B>()</PRE>
+<DL>
+<DD>Return description (from META tags)
+<P>
+<DD><DL>
+
+<DT><B>Returns:</B><DD>DOCUMENT ME!</DL>
+</DD>
+</DL>
+<HR>
+
+<A NAME="getTitle()"><!-- --></A><H3>
+getTitle</H3>
+<PRE>
+public java.lang.String <B>getTitle</B>()</PRE>
+<DL>
+<DD>Return page title
+<P>
+<DD><DL>
+
+<DT><B>Returns:</B><DD>DOCUMENT ME!</DL>
+</DD>
+</DL>
+<HR>
+
+<A NAME="parse(java.io.InputStream)"><!-- --></A><H3>
+parse</H3>
+<PRE>
+public void <B>parse</B>(java.io.InputStream&nbsp;in)</PRE>
+<DL>
+<DD>Parse Content.
+<P>
+<DD><DL>
+<DT><B>Parameters:</B><DD><CODE>in</CODE> - DOCUMENT ME!</DL>
+</DD>
+</DL>
+<!-- ========= END OF CLASS DATA ========= -->
+<HR>
+
+
+<!-- ======= START OF BOTTOM NAVBAR ====== -->
+<A NAME="navbar_bottom"><!-- --></A>
+<A HREF="#skip-navbar_bottom" title="Skip navigation links"></A>
+<TABLE BORDER="0" WIDTH="100%" CELLPADDING="1" CELLSPACING="0" SUMMARY="">
+<TR>
+<TD COLSPAN=3 BGCOLOR="#EEEEFF" CLASS="NavBarCell1">
+<A NAME="navbar_bottom_firstrow"><!-- --></A>
+<TABLE BORDER="0" CELLPADDING="0" CELLSPACING="3" SUMMARY="">
+  <TR ALIGN="center" VALIGN="top">
+  <TD BGCOLOR="#EEEEFF" CLASS="NavBarCell1">    <A HREF="../../../../../overview-summary.html"><FONT CLASS="NavBarFont1"><B>Overview</B></FONT></A>&nbsp;</TD>
+  <TD BGCOLOR="#EEEEFF" CLASS="NavBarCell1">    <A HREF="package-summary.html"><FONT CLASS="NavBarFont1"><B>Package</B></FONT></A>&nbsp;</TD>
+  <TD BGCOLOR="#FFFFFF" CLASS="NavBarCell1Rev"> &nbsp;<FONT CLASS="NavBarFont1Rev"><B>Class</B></FONT>&nbsp;</TD>
+  <TD BGCOLOR="#EEEEFF" CLASS="NavBarCell1">    <A HREF="package-tree.html"><FONT CLASS="NavBarFont1"><B>Tree</B></FONT></A>&nbsp;</TD>
+  <TD BGCOLOR="#EEEEFF" CLASS="NavBarCell1">    <A HREF="../../../../../deprecated-list.html"><FONT CLASS="NavBarFont1"><B>Deprecated</B></FONT></A>&nbsp;</TD>
+  <TD BGCOLOR="#EEEEFF" CLASS="NavBarCell1">    <A HREF="../../../../../help-doc.html"><FONT CLASS="NavBarFont1"><B>Help</B></FONT></A>&nbsp;</TD>
+  </TR>
+</TABLE>
+</TD>
+<TD ALIGN="right" VALIGN="top" ROWSPAN=3><EM>
+</EM>
+</TD>
+</TR>
+
+<TR>
+<TD BGCOLOR="white" CLASS="NavBarCell2"><FONT SIZE="-2">
+&nbsp;PREV CLASS&nbsp;
+&nbsp;NEXT CLASS</FONT></TD>
+<TD BGCOLOR="white" CLASS="NavBarCell2"><FONT SIZE="-2">
+  <A HREF="../../../../../index.html" target="_top"><B>FRAMES</B></A>  &nbsp;
+&nbsp;<A HREF="ContentHandler.html" target="_top"><B>NO FRAMES</B></A>  &nbsp;
+&nbsp;<SCRIPT type="text/javascript">
+  <!--
+  if(window==top) {
+    document.writeln('<A HREF="../../../../../allclasses-noframe.html"><B>All Classes</B></A>');
+  }
+  //-->
+</SCRIPT>
+<NOSCRIPT>
+  <A HREF="../../../../../allclasses-noframe.html"><B>All Classes</B></A>
+</NOSCRIPT>
+
+</FONT></TD>
+</TR>
+<TR>
+<TD VALIGN="top" CLASS="NavBarCell3"><FONT SIZE="-2">
+  SUMMARY:&nbsp;NESTED&nbsp;|&nbsp;FIELD&nbsp;|&nbsp;CONSTR&nbsp;|&nbsp;<A HREF="#method_summary">METHOD</A></FONT></TD>
+<TD VALIGN="top" CLASS="NavBarCell3"><FONT SIZE="-2">
+DETAIL:&nbsp;FIELD&nbsp;|&nbsp;CONSTR&nbsp;|&nbsp;<A HREF="#method_detail">METHOD</A></FONT></TD>
+</TR>
+</TABLE>
+<A NAME="skip-navbar_bottom"></A>
+<!-- ======== END OF BOTTOM NAVBAR ======= -->
+
+<HR>
+Copyright © 1999-2004 Apache Software Foundation. All Rights Reserved.
+</BODY>
+</HTML>

Propchange: lenya/site/apidocs/1.2/org/apache/lenya/search/crawler/ContentHandler.html
------------------------------------------------------------------------------
    svn:eol-style = native

Propchange: lenya/site/apidocs/1.2/org/apache/lenya/search/crawler/ContentHandler.html
------------------------------------------------------------------------------
    svn:mime-type = text/html

Added: lenya/site/apidocs/1.2/org/apache/lenya/search/crawler/CrawlerConfiguration.html
URL: http://svn.apache.org/viewcvs/lenya/site/apidocs/1.2/org/apache/lenya/search/crawler/CrawlerConfiguration.html?rev=164448&view=auto
==============================================================================
--- lenya/site/apidocs/1.2/org/apache/lenya/search/crawler/CrawlerConfiguration.html (added)
+++ lenya/site/apidocs/1.2/org/apache/lenya/search/crawler/CrawlerConfiguration.html Sat Apr 23 22:30:06 2005
@@ -0,0 +1,456 @@
+<!DOCTYPE HTML PUBLIC "-//W3C//DTD HTML 4.01 Transitional//EN" "http://www.w3.org/TR/html4/loose.dtd">
+<!--NewPage-->
+<HTML>
+<HEAD>
+<!-- Generated by javadoc (build 1.4.2_03) on Mon Feb 21 17:32:47 EST 2005 -->
+<TITLE>
+CrawlerConfiguration (Apache Lenya API - Version 1.2.2)
+</TITLE>
+
+<META NAME="keywords" CONTENT="org.apache.lenya.search.crawler.CrawlerConfiguration class">
+
+<LINK REL ="stylesheet" TYPE="text/css" HREF="../../../../../javadoc.css" TITLE="Style">
+
+<SCRIPT type="text/javascript">
+function windowTitle()
+{
+    parent.document.title="CrawlerConfiguration (Apache Lenya API - Version 1.2.2)";
+}
+</SCRIPT>
+
+</HEAD>
+
+<BODY BGCOLOR="white" onload="windowTitle();">
+
+
+<!-- ========= START OF TOP NAVBAR ======= -->
+<A NAME="navbar_top"><!-- --></A>
+<A HREF="#skip-navbar_top" title="Skip navigation links"></A>
+<TABLE BORDER="0" WIDTH="100%" CELLPADDING="1" CELLSPACING="0" SUMMARY="">
+<TR>
+<TD COLSPAN=3 BGCOLOR="#EEEEFF" CLASS="NavBarCell1">
+<A NAME="navbar_top_firstrow"><!-- --></A>
+<TABLE BORDER="0" CELLPADDING="0" CELLSPACING="3" SUMMARY="">
+  <TR ALIGN="center" VALIGN="top">
+  <TD BGCOLOR="#EEEEFF" CLASS="NavBarCell1">    <A HREF="../../../../../overview-summary.html"><FONT CLASS="NavBarFont1"><B>Overview</B></FONT></A>&nbsp;</TD>
+  <TD BGCOLOR="#EEEEFF" CLASS="NavBarCell1">    <A HREF="package-summary.html"><FONT CLASS="NavBarFont1"><B>Package</B></FONT></A>&nbsp;</TD>
+  <TD BGCOLOR="#FFFFFF" CLASS="NavBarCell1Rev"> &nbsp;<FONT CLASS="NavBarFont1Rev"><B>Class</B></FONT>&nbsp;</TD>
+  <TD BGCOLOR="#EEEEFF" CLASS="NavBarCell1">    <A HREF="package-tree.html"><FONT CLASS="NavBarFont1"><B>Tree</B></FONT></A>&nbsp;</TD>
+  <TD BGCOLOR="#EEEEFF" CLASS="NavBarCell1">    <A HREF="../../../../../deprecated-list.html"><FONT CLASS="NavBarFont1"><B>Deprecated</B></FONT></A>&nbsp;</TD>
+  <TD BGCOLOR="#EEEEFF" CLASS="NavBarCell1">    <A HREF="../../../../../help-doc.html"><FONT CLASS="NavBarFont1"><B>Help</B></FONT></A>&nbsp;</TD>
+  </TR>
+</TABLE>
+</TD>
+<TD ALIGN="right" VALIGN="top" ROWSPAN=3><EM>
+</EM>
+</TD>
+</TR>
+
+<TR>
+<TD BGCOLOR="white" CLASS="NavBarCell2"><FONT SIZE="-2">
+&nbsp;PREV CLASS&nbsp;
+&nbsp;<A HREF="../../../../../org/apache/lenya/search/crawler/HTMLHandler.html" title="class in org.apache.lenya.search.crawler"><B>NEXT CLASS</B></A></FONT></TD>
+<TD BGCOLOR="white" CLASS="NavBarCell2"><FONT SIZE="-2">
+  <A HREF="../../../../../index.html" target="_top"><B>FRAMES</B></A>  &nbsp;
+&nbsp;<A HREF="CrawlerConfiguration.html" target="_top"><B>NO FRAMES</B></A>  &nbsp;
+&nbsp;<SCRIPT type="text/javascript">
+  <!--
+  if(window==top) {
+    document.writeln('<A HREF="../../../../../allclasses-noframe.html"><B>All Classes</B></A>');
+  }
+  //-->
+</SCRIPT>
+<NOSCRIPT>
+  <A HREF="../../../../../allclasses-noframe.html"><B>All Classes</B></A>
+</NOSCRIPT>
+
+</FONT></TD>
+</TR>
+<TR>
+<TD VALIGN="top" CLASS="NavBarCell3"><FONT SIZE="-2">
+  SUMMARY:&nbsp;NESTED&nbsp;|&nbsp;FIELD&nbsp;|&nbsp;<A HREF="#constructor_summary">CONSTR</A>&nbsp;|&nbsp;<A HREF="#method_summary">METHOD</A></FONT></TD>
+<TD VALIGN="top" CLASS="NavBarCell3"><FONT SIZE="-2">
+DETAIL:&nbsp;FIELD&nbsp;|&nbsp;<A HREF="#constructor_detail">CONSTR</A>&nbsp;|&nbsp;<A HREF="#method_detail">METHOD</A></FONT></TD>
+</TR>
+</TABLE>
+<A NAME="skip-navbar_top"></A>
+<!-- ========= END OF TOP NAVBAR ========= -->
+
+<HR>
+<!-- ======== START OF CLASS DATA ======== -->
+<H2>
+<FONT SIZE="-1">
+org.apache.lenya.search.crawler</FONT>
+<BR>
+Class CrawlerConfiguration</H2>
+<PRE>
+java.lang.Object
+  <IMG SRC="../../../../../resources/inherit.gif" ALT="extended by"><B>org.apache.lenya.search.crawler.CrawlerConfiguration</B>
+</PRE>
+<HR>
+<DL>
+<DT>public class <B>CrawlerConfiguration</B><DT>extends java.lang.Object</DL>
+
+<P>
+DOCUMENT ME!
+<P>
+
+<P>
+<HR>
+
+<P>
+<!-- ======== NESTED CLASS SUMMARY ======== -->
+
+
+<!-- =========== FIELD SUMMARY =========== -->
+
+
+<!-- ======== CONSTRUCTOR SUMMARY ======== -->
+
+<A NAME="constructor_summary"><!-- --></A>
+<TABLE BORDER="1" WIDTH="100%" CELLPADDING="3" CELLSPACING="0" SUMMARY="">
+<TR BGCOLOR="#CCCCFF" CLASS="TableHeadingColor">
+<TD COLSPAN=2><FONT SIZE="+2">
+<B>Constructor Summary</B></FONT></TD>
+</TR>
+<TR BGCOLOR="white" CLASS="TableRowColor">
+<TD><CODE><B><A HREF="../../../../../org/apache/lenya/search/crawler/CrawlerConfiguration.html#CrawlerConfiguration(java.lang.String)">CrawlerConfiguration</A></B>(java.lang.String&nbsp;configurationFilePath)</CODE>
+
+<BR>
+&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;Creates a new CrawlerConfiguration object.</TD>
+</TR>
+</TABLE>
+&nbsp;
+<!-- ========== METHOD SUMMARY =========== -->
+
+<A NAME="method_summary"><!-- --></A>
+<TABLE BORDER="1" WIDTH="100%" CELLPADDING="3" CELLSPACING="0" SUMMARY="">
+<TR BGCOLOR="#CCCCFF" CLASS="TableHeadingColor">
+<TD COLSPAN=2><FONT SIZE="+2">
+<B>Method Summary</B></FONT></TD>
+</TR>
+<TR BGCOLOR="white" CLASS="TableRowColor">
+<TD ALIGN="right" VALIGN="top" WIDTH="1%"><FONT SIZE="-1">
+<CODE>&nbsp;void</CODE></FONT></TD>
+<TD><CODE><B><A HREF="../../../../../org/apache/lenya/search/crawler/CrawlerConfiguration.html#configure(org.w3c.dom.Element)">configure</A></B>(org.w3c.dom.Element&nbsp;root)</CODE>
+
+<BR>
+&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;Extract parameters from configuration</TD>
+</TR>
+<TR BGCOLOR="white" CLASS="TableRowColor">
+<TD ALIGN="right" VALIGN="top" WIDTH="1%"><FONT SIZE="-1">
+<CODE>&nbsp;java.lang.String</CODE></FONT></TD>
+<TD><CODE><B><A HREF="../../../../../org/apache/lenya/search/crawler/CrawlerConfiguration.html#getBaseURL()">getBaseURL</A></B>()</CODE>
+
+<BR>
+&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;DOCUMENT ME!</TD>
+</TR>
+<TR BGCOLOR="white" CLASS="TableRowColor">
+<TD ALIGN="right" VALIGN="top" WIDTH="1%"><FONT SIZE="-1">
+<CODE>&nbsp;java.lang.String</CODE></FONT></TD>
+<TD><CODE><B><A HREF="../../../../../org/apache/lenya/search/crawler/CrawlerConfiguration.html#getHTDocsDumpDir()">getHTDocsDumpDir</A></B>()</CODE>
+
+<BR>
+&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;Get htdocs-dump-dir/@src</TD>
+</TR>
+<TR BGCOLOR="white" CLASS="TableRowColor">
+<TD ALIGN="right" VALIGN="top" WIDTH="1%"><FONT SIZE="-1">
+<CODE>&nbsp;java.lang.String</CODE></FONT></TD>
+<TD><CODE><B><A HREF="../../../../../org/apache/lenya/search/crawler/CrawlerConfiguration.html#getRobotsDomain()">getRobotsDomain</A></B>()</CODE>
+
+<BR>
+&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;Get robots/@domain</TD>
+</TR>
+<TR BGCOLOR="white" CLASS="TableRowColor">
+<TD ALIGN="right" VALIGN="top" WIDTH="1%"><FONT SIZE="-1">
+<CODE>&nbsp;java.lang.String</CODE></FONT></TD>
+<TD><CODE><B><A HREF="../../../../../org/apache/lenya/search/crawler/CrawlerConfiguration.html#getRobotsFile()">getRobotsFile</A></B>()</CODE>
+
+<BR>
+&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;Get robots/@src</TD>
+</TR>
+<TR BGCOLOR="white" CLASS="TableRowColor">
+<TD ALIGN="right" VALIGN="top" WIDTH="1%"><FONT SIZE="-1">
+<CODE>&nbsp;java.lang.String</CODE></FONT></TD>
+<TD><CODE><B><A HREF="../../../../../org/apache/lenya/search/crawler/CrawlerConfiguration.html#getScopeURL()">getScopeURL</A></B>()</CODE>
+
+<BR>
+&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;DOCUMENT ME!</TD>
+</TR>
+<TR BGCOLOR="white" CLASS="TableRowColor">
+<TD ALIGN="right" VALIGN="top" WIDTH="1%"><FONT SIZE="-1">
+<CODE>&nbsp;java.lang.String</CODE></FONT></TD>
+<TD><CODE><B><A HREF="../../../../../org/apache/lenya/search/crawler/CrawlerConfiguration.html#getURIList()">getURIList</A></B>()</CODE>
+
+<BR>
+&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;DOCUMENT ME!</TD>
+</TR>
+<TR BGCOLOR="white" CLASS="TableRowColor">
+<TD ALIGN="right" VALIGN="top" WIDTH="1%"><FONT SIZE="-1">
+<CODE>&nbsp;java.lang.String</CODE></FONT></TD>
+<TD><CODE><B><A HREF="../../../../../org/apache/lenya/search/crawler/CrawlerConfiguration.html#getUserAgent()">getUserAgent</A></B>()</CODE>
+
+<BR>
+&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;DOCUMENT ME!</TD>
+</TR>
+<TR BGCOLOR="white" CLASS="TableRowColor">
+<TD ALIGN="right" VALIGN="top" WIDTH="1%"><FONT SIZE="-1">
+<CODE>static&nbsp;void</CODE></FONT></TD>
+<TD><CODE><B><A HREF="../../../../../org/apache/lenya/search/crawler/CrawlerConfiguration.html#main(java.lang.String[])">main</A></B>(java.lang.String[]&nbsp;args)</CODE>
+
+<BR>
+&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;DOCUMENT ME!</TD>
+</TR>
+<TR BGCOLOR="white" CLASS="TableRowColor">
+<TD ALIGN="right" VALIGN="top" WIDTH="1%"><FONT SIZE="-1">
+<CODE>&nbsp;java.lang.String</CODE></FONT></TD>
+<TD><CODE><B><A HREF="../../../../../org/apache/lenya/search/crawler/CrawlerConfiguration.html#resolvePath(java.lang.String)">resolvePath</A></B>(java.lang.String&nbsp;path)</CODE>
+
+<BR>
+&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;Resolve path</TD>
+</TR>
+</TABLE>
+&nbsp;<A NAME="methods_inherited_from_class_java.lang.Object"><!-- --></A>
+<TABLE BORDER="1" WIDTH="100%" CELLPADDING="3" CELLSPACING="0" SUMMARY="">
+<TR BGCOLOR="#EEEEFF" CLASS="TableSubHeadingColor">
+<TD><B>Methods inherited from class java.lang.Object</B></TD>
+</TR>
+<TR BGCOLOR="white" CLASS="TableRowColor">
+<TD><CODE>clone, equals, finalize, getClass, hashCode, notify, notifyAll, toString, wait, wait, wait</CODE></TD>
+</TR>
+</TABLE>
+&nbsp;
+<P>
+
+<!-- ============ FIELD DETAIL =========== -->
+
+
+<!-- ========= CONSTRUCTOR DETAIL ======== -->
+
+<A NAME="constructor_detail"><!-- --></A>
+<TABLE BORDER="1" WIDTH="100%" CELLPADDING="3" CELLSPACING="0" SUMMARY="">
+<TR BGCOLOR="#CCCCFF" CLASS="TableHeadingColor">
+<TD COLSPAN=1><FONT SIZE="+2">
+<B>Constructor Detail</B></FONT></TD>
+</TR>
+</TABLE>
+
+<A NAME="CrawlerConfiguration(java.lang.String)"><!-- --></A><H3>
+CrawlerConfiguration</H3>
+<PRE>
+public <B>CrawlerConfiguration</B>(java.lang.String&nbsp;configurationFilePath)</PRE>
+<DL>
+<DD>Creates a new CrawlerConfiguration object.
+<P>
+<DT><B>Parameters:</B><DD><CODE>configurationFilePath</CODE> - DOCUMENT ME!</DL>
+
+<!-- ============ METHOD DETAIL ========== -->
+
+<A NAME="method_detail"><!-- --></A>
+<TABLE BORDER="1" WIDTH="100%" CELLPADDING="3" CELLSPACING="0" SUMMARY="">
+<TR BGCOLOR="#CCCCFF" CLASS="TableHeadingColor">
+<TD COLSPAN=1><FONT SIZE="+2">
+<B>Method Detail</B></FONT></TD>
+</TR>
+</TABLE>
+
+<A NAME="main(java.lang.String[])"><!-- --></A><H3>
+main</H3>
+<PRE>
+public static void <B>main</B>(java.lang.String[]&nbsp;args)</PRE>
+<DL>
+<DD>DOCUMENT ME!
+<P>
+<DD><DL>
+<DT><B>Parameters:</B><DD><CODE>args</CODE> - DOCUMENT ME!</DL>
+</DD>
+</DL>
+<HR>
+
+<A NAME="configure(org.w3c.dom.Element)"><!-- --></A><H3>
+configure</H3>
+<PRE>
+public void <B>configure</B>(org.w3c.dom.Element&nbsp;root)
+               throws java.lang.Exception</PRE>
+<DL>
+<DD>Extract parameters from configuration
+<P>
+<DD><DL>
+
+<DT><B>Throws:</B>
+<DD><CODE>java.lang.Exception</CODE> - DOCUMENT ME!</DL>
+</DD>
+</DL>
+<HR>
+
+<A NAME="getBaseURL()"><!-- --></A><H3>
+getBaseURL</H3>
+<PRE>
+public java.lang.String <B>getBaseURL</B>()</PRE>
+<DL>
+<DD>DOCUMENT ME!
+<P>
+<DD><DL>
+
+<DT><B>Returns:</B><DD>DOCUMENT ME!</DL>
+</DD>
+</DL>
+<HR>
+
+<A NAME="getScopeURL()"><!-- --></A><H3>
+getScopeURL</H3>
+<PRE>
+public java.lang.String <B>getScopeURL</B>()</PRE>
+<DL>
+<DD>DOCUMENT ME!
+<P>
+<DD><DL>
+
+<DT><B>Returns:</B><DD>DOCUMENT ME!</DL>
+</DD>
+</DL>
+<HR>
+
+<A NAME="getUserAgent()"><!-- --></A><H3>
+getUserAgent</H3>
+<PRE>
+public java.lang.String <B>getUserAgent</B>()</PRE>
+<DL>
+<DD>DOCUMENT ME!
+<P>
+<DD><DL>
+
+<DT><B>Returns:</B><DD>DOCUMENT ME!</DL>
+</DD>
+</DL>
+<HR>
+
+<A NAME="getURIList()"><!-- --></A><H3>
+getURIList</H3>
+<PRE>
+public java.lang.String <B>getURIList</B>()</PRE>
+<DL>
+<DD>DOCUMENT ME!
+<P>
+<DD><DL>
+
+<DT><B>Returns:</B><DD>DOCUMENT ME!</DL>
+</DD>
+</DL>
+<HR>
+
+<A NAME="getHTDocsDumpDir()"><!-- --></A><H3>
+getHTDocsDumpDir</H3>
+<PRE>
+public java.lang.String <B>getHTDocsDumpDir</B>()</PRE>
+<DL>
+<DD>Get htdocs-dump-dir/@src
+<P>
+<DD><DL>
+
+<DT><B>Returns:</B><DD>htdocs-dump-dir/@src</DL>
+</DD>
+</DL>
+<HR>
+
+<A NAME="getRobotsFile()"><!-- --></A><H3>
+getRobotsFile</H3>
+<PRE>
+public java.lang.String <B>getRobotsFile</B>()</PRE>
+<DL>
+<DD>Get robots/@src
+<P>
+<DD><DL>
+
+<DT><B>Returns:</B><DD>robots/@src</DL>
+</DD>
+</DL>
+<HR>
+
+<A NAME="getRobotsDomain()"><!-- --></A><H3>
+getRobotsDomain</H3>
+<PRE>
+public java.lang.String <B>getRobotsDomain</B>()</PRE>
+<DL>
+<DD>Get robots/@domain
+<P>
+<DD><DL>
+
+<DT><B>Returns:</B><DD>robots/@domain</DL>
+</DD>
+</DL>
+<HR>
+
+<A NAME="resolvePath(java.lang.String)"><!-- --></A><H3>
+resolvePath</H3>
+<PRE>
+public java.lang.String <B>resolvePath</B>(java.lang.String&nbsp;path)</PRE>
+<DL>
+<DD>Resolve path
+<P>
+<DD><DL>
+<DT><B>Parameters:</B><DD><CODE>path</CODE> - Original path
+<DT><B>Returns:</B><DD>Resolved path</DL>
+</DD>
+</DL>
+<!-- ========= END OF CLASS DATA ========= -->
+<HR>
+
+
+<!-- ======= START OF BOTTOM NAVBAR ====== -->
+<A NAME="navbar_bottom"><!-- --></A>
+<A HREF="#skip-navbar_bottom" title="Skip navigation links"></A>
+<TABLE BORDER="0" WIDTH="100%" CELLPADDING="1" CELLSPACING="0" SUMMARY="">
+<TR>
+<TD COLSPAN=3 BGCOLOR="#EEEEFF" CLASS="NavBarCell1">
+<A NAME="navbar_bottom_firstrow"><!-- --></A>
+<TABLE BORDER="0" CELLPADDING="0" CELLSPACING="3" SUMMARY="">
+  <TR ALIGN="center" VALIGN="top">
+  <TD BGCOLOR="#EEEEFF" CLASS="NavBarCell1">    <A HREF="../../../../../overview-summary.html"><FONT CLASS="NavBarFont1"><B>Overview</B></FONT></A>&nbsp;</TD>
+  <TD BGCOLOR="#EEEEFF" CLASS="NavBarCell1">    <A HREF="package-summary.html"><FONT CLASS="NavBarFont1"><B>Package</B></FONT></A>&nbsp;</TD>
+  <TD BGCOLOR="#FFFFFF" CLASS="NavBarCell1Rev"> &nbsp;<FONT CLASS="NavBarFont1Rev"><B>Class</B></FONT>&nbsp;</TD>
+  <TD BGCOLOR="#EEEEFF" CLASS="NavBarCell1">    <A HREF="package-tree.html"><FONT CLASS="NavBarFont1"><B>Tree</B></FONT></A>&nbsp;</TD>
+  <TD BGCOLOR="#EEEEFF" CLASS="NavBarCell1">    <A HREF="../../../../../deprecated-list.html"><FONT CLASS="NavBarFont1"><B>Deprecated</B></FONT></A>&nbsp;</TD>
+  <TD BGCOLOR="#EEEEFF" CLASS="NavBarCell1">    <A HREF="../../../../../help-doc.html"><FONT CLASS="NavBarFont1"><B>Help</B></FONT></A>&nbsp;</TD>
+  </TR>
+</TABLE>
+</TD>
+<TD ALIGN="right" VALIGN="top" ROWSPAN=3><EM>
+</EM>
+</TD>
+</TR>
+
+<TR>
+<TD BGCOLOR="white" CLASS="NavBarCell2"><FONT SIZE="-2">
+&nbsp;PREV CLASS&nbsp;
+&nbsp;<A HREF="../../../../../org/apache/lenya/search/crawler/HTMLHandler.html" title="class in org.apache.lenya.search.crawler"><B>NEXT CLASS</B></A></FONT></TD>
+<TD BGCOLOR="white" CLASS="NavBarCell2"><FONT SIZE="-2">
+  <A HREF="../../../../../index.html" target="_top"><B>FRAMES</B></A>  &nbsp;
+&nbsp;<A HREF="CrawlerConfiguration.html" target="_top"><B>NO FRAMES</B></A>  &nbsp;
+&nbsp;<SCRIPT type="text/javascript">
+  <!--
+  if(window==top) {
+    document.writeln('<A HREF="../../../../../allclasses-noframe.html"><B>All Classes</B></A>');
+  }
+  //-->
+</SCRIPT>
+<NOSCRIPT>
+  <A HREF="../../../../../allclasses-noframe.html"><B>All Classes</B></A>
+</NOSCRIPT>
+
+</FONT></TD>
+</TR>
+<TR>
+<TD VALIGN="top" CLASS="NavBarCell3"><FONT SIZE="-2">
+  SUMMARY:&nbsp;NESTED&nbsp;|&nbsp;FIELD&nbsp;|&nbsp;<A HREF="#constructor_summary">CONSTR</A>&nbsp;|&nbsp;<A HREF="#method_summary">METHOD</A></FONT></TD>
+<TD VALIGN="top" CLASS="NavBarCell3"><FONT SIZE="-2">
+DETAIL:&nbsp;FIELD&nbsp;|&nbsp;<A HREF="#constructor_detail">CONSTR</A>&nbsp;|&nbsp;<A HREF="#method_detail">METHOD</A></FONT></TD>
+</TR>
+</TABLE>
+<A NAME="skip-navbar_bottom"></A>
+<!-- ======== END OF BOTTOM NAVBAR ======= -->
+
+<HR>
+Copyright © 1999-2004 Apache Software Foundation. All Rights Reserved.
+</BODY>
+</HTML>

Propchange: lenya/site/apidocs/1.2/org/apache/lenya/search/crawler/CrawlerConfiguration.html
------------------------------------------------------------------------------
    svn:eol-style = native

Propchange: lenya/site/apidocs/1.2/org/apache/lenya/search/crawler/CrawlerConfiguration.html
------------------------------------------------------------------------------
    svn:mime-type = text/html

Added: lenya/site/apidocs/1.2/org/apache/lenya/search/crawler/HTMLHandler.html
URL: http://svn.apache.org/viewcvs/lenya/site/apidocs/1.2/org/apache/lenya/search/crawler/HTMLHandler.html?rev=164448&view=auto
==============================================================================
--- lenya/site/apidocs/1.2/org/apache/lenya/search/crawler/HTMLHandler.html (added)
+++ lenya/site/apidocs/1.2/org/apache/lenya/search/crawler/HTMLHandler.html Sat Apr 23 22:30:06 2005
@@ -0,0 +1,719 @@
+<!DOCTYPE HTML PUBLIC "-//W3C//DTD HTML 4.01 Transitional//EN" "http://www.w3.org/TR/html4/loose.dtd">
+<!--NewPage-->
+<HTML>
+<HEAD>
+<!-- Generated by javadoc (build 1.4.2_03) on Mon Feb 21 17:32:47 EST 2005 -->
+<TITLE>
+HTMLHandler (Apache Lenya API - Version 1.2.2)
+</TITLE>
+
+<META NAME="keywords" CONTENT="org.apache.lenya.search.crawler.HTMLHandler class">
+
+<LINK REL ="stylesheet" TYPE="text/css" HREF="../../../../../javadoc.css" TITLE="Style">
+
+<SCRIPT type="text/javascript">
+function windowTitle()
+{
+    parent.document.title="HTMLHandler (Apache Lenya API - Version 1.2.2)";
+}
+</SCRIPT>
+
+</HEAD>
+
+<BODY BGCOLOR="white" onload="windowTitle();">
+
+
+<!-- ========= START OF TOP NAVBAR ======= -->
+<A NAME="navbar_top"><!-- --></A>
+<A HREF="#skip-navbar_top" title="Skip navigation links"></A>
+<TABLE BORDER="0" WIDTH="100%" CELLPADDING="1" CELLSPACING="0" SUMMARY="">
+<TR>
+<TD COLSPAN=3 BGCOLOR="#EEEEFF" CLASS="NavBarCell1">
+<A NAME="navbar_top_firstrow"><!-- --></A>
+<TABLE BORDER="0" CELLPADDING="0" CELLSPACING="3" SUMMARY="">
+  <TR ALIGN="center" VALIGN="top">
+  <TD BGCOLOR="#EEEEFF" CLASS="NavBarCell1">    <A HREF="../../../../../overview-summary.html"><FONT CLASS="NavBarFont1"><B>Overview</B></FONT></A>&nbsp;</TD>
+  <TD BGCOLOR="#EEEEFF" CLASS="NavBarCell1">    <A HREF="package-summary.html"><FONT CLASS="NavBarFont1"><B>Package</B></FONT></A>&nbsp;</TD>
+  <TD BGCOLOR="#FFFFFF" CLASS="NavBarCell1Rev"> &nbsp;<FONT CLASS="NavBarFont1Rev"><B>Class</B></FONT>&nbsp;</TD>
+  <TD BGCOLOR="#EEEEFF" CLASS="NavBarCell1">    <A HREF="package-tree.html"><FONT CLASS="NavBarFont1"><B>Tree</B></FONT></A>&nbsp;</TD>
+  <TD BGCOLOR="#EEEEFF" CLASS="NavBarCell1">    <A HREF="../../../../../deprecated-list.html"><FONT CLASS="NavBarFont1"><B>Deprecated</B></FONT></A>&nbsp;</TD>
+  <TD BGCOLOR="#EEEEFF" CLASS="NavBarCell1">    <A HREF="../../../../../help-doc.html"><FONT CLASS="NavBarFont1"><B>Help</B></FONT></A>&nbsp;</TD>
+  </TR>
+</TABLE>
+</TD>
+<TD ALIGN="right" VALIGN="top" ROWSPAN=3><EM>
+</EM>
+</TD>
+</TR>
+
+<TR>
+<TD BGCOLOR="white" CLASS="NavBarCell2"><FONT SIZE="-2">
+&nbsp;<A HREF="../../../../../org/apache/lenya/search/crawler/CrawlerConfiguration.html" title="class in org.apache.lenya.search.crawler"><B>PREV CLASS</B></A>&nbsp;
+&nbsp;<A HREF="../../../../../org/apache/lenya/search/crawler/IterativeHTMLCrawler.html" title="class in org.apache.lenya.search.crawler"><B>NEXT CLASS</B></A></FONT></TD>
+<TD BGCOLOR="white" CLASS="NavBarCell2"><FONT SIZE="-2">
+  <A HREF="../../../../../index.html" target="_top"><B>FRAMES</B></A>  &nbsp;
+&nbsp;<A HREF="HTMLHandler.html" target="_top"><B>NO FRAMES</B></A>  &nbsp;
+&nbsp;<SCRIPT type="text/javascript">
+  <!--
+  if(window==top) {
+    document.writeln('<A HREF="../../../../../allclasses-noframe.html"><B>All Classes</B></A>');
+  }
+  //-->
+</SCRIPT>
+<NOSCRIPT>
+  <A HREF="../../../../../allclasses-noframe.html"><B>All Classes</B></A>
+</NOSCRIPT>
+
+</FONT></TD>
+</TR>
+<TR>
+<TD VALIGN="top" CLASS="NavBarCell3"><FONT SIZE="-2">
+  SUMMARY:&nbsp;NESTED&nbsp;|&nbsp;<A HREF="#fields_inherited_from_class_javax.swing.text.html.HTMLEditorKit.ParserCallback">FIELD</A>&nbsp;|&nbsp;<A HREF="#constructor_summary">CONSTR</A>&nbsp;|&nbsp;<A HREF="#method_summary">METHOD</A></FONT></TD>
+<TD VALIGN="top" CLASS="NavBarCell3"><FONT SIZE="-2">
+DETAIL:&nbsp;FIELD&nbsp;|&nbsp;<A HREF="#constructor_detail">CONSTR</A>&nbsp;|&nbsp;<A HREF="#method_detail">METHOD</A></FONT></TD>
+</TR>
+</TABLE>
+<A NAME="skip-navbar_top"></A>
+<!-- ========= END OF TOP NAVBAR ========= -->
+
+<HR>
+<!-- ======== START OF CLASS DATA ======== -->
+<H2>
+<FONT SIZE="-1">
+org.apache.lenya.search.crawler</FONT>
+<BR>
+Class HTMLHandler</H2>
+<PRE>
+java.lang.Object
+  <IMG SRC="../../../../../resources/inherit.gif" ALT="extended by">javax.swing.text.html.HTMLEditorKit.ParserCallback
+      <IMG SRC="../../../../../resources/inherit.gif" ALT="extended by"><B>org.apache.lenya.search.crawler.HTMLHandler</B>
+</PRE>
+<DL>
+<DT><B>All Implemented Interfaces:</B> <DD><A HREF="../../../../../org/apache/lenya/search/crawler/ContentHandler.html" title="interface in org.apache.lenya.search.crawler">ContentHandler</A></DD>
+</DL>
+<HR>
+<DL>
+<DT>public final class <B>HTMLHandler</B><DT>extends javax.swing.text.html.HTMLEditorKit.ParserCallback<DT>implements <A HREF="../../../../../org/apache/lenya/search/crawler/ContentHandler.html" title="interface in org.apache.lenya.search.crawler">ContentHandler</A></DL>
+
+<P>
+DOCUMENT ME!
+<P>
+
+<P>
+<HR>
+
+<P>
+<!-- ======== NESTED CLASS SUMMARY ======== -->
+
+
+<!-- =========== FIELD SUMMARY =========== -->
+
+<A NAME="field_summary"><!-- --></A>
+<TABLE BORDER="1" WIDTH="100%" CELLPADDING="3" CELLSPACING="0" SUMMARY="">
+<TR BGCOLOR="#CCCCFF" CLASS="TableHeadingColor">
+<TD COLSPAN=2><FONT SIZE="+2">
+<B>Field Summary</B></FONT></TD>
+</TR>
+</TABLE>
+&nbsp;<A NAME="fields_inherited_from_class_javax.swing.text.html.HTMLEditorKit.ParserCallback"><!-- --></A>
+<TABLE BORDER="1" WIDTH="100%" CELLPADDING="3" CELLSPACING="0" SUMMARY="">
+<TR BGCOLOR="#EEEEFF" CLASS="TableSubHeadingColor">
+<TD><B>Fields inherited from class javax.swing.text.html.HTMLEditorKit.ParserCallback</B></TD>
+</TR>
+<TR BGCOLOR="white" CLASS="TableRowColor">
+<TD><CODE>IMPLIED</CODE></TD>
+</TR>
+</TABLE>
+&nbsp;
+<!-- ======== CONSTRUCTOR SUMMARY ======== -->
+
+<A NAME="constructor_summary"><!-- --></A>
+<TABLE BORDER="1" WIDTH="100%" CELLPADDING="3" CELLSPACING="0" SUMMARY="">
+<TR BGCOLOR="#CCCCFF" CLASS="TableHeadingColor">
+<TD COLSPAN=2><FONT SIZE="+2">
+<B>Constructor Summary</B></FONT></TD>
+</TR>
+<TR BGCOLOR="white" CLASS="TableRowColor">
+<TD><CODE><B><A HREF="../../../../../org/apache/lenya/search/crawler/HTMLHandler.html#HTMLHandler()">HTMLHandler</A></B>()</CODE>
+
+<BR>
+&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;Constructor - initializes variables</TD>
+</TR>
+</TABLE>
+&nbsp;
+<!-- ========== METHOD SUMMARY =========== -->
+
+<A NAME="method_summary"><!-- --></A>
+<TABLE BORDER="1" WIDTH="100%" CELLPADDING="3" CELLSPACING="0" SUMMARY="">
+<TR BGCOLOR="#CCCCFF" CLASS="TableHeadingColor">
+<TD COLSPAN=2><FONT SIZE="+2">
+<B>Method Summary</B></FONT></TD>
+</TR>
+<TR BGCOLOR="white" CLASS="TableRowColor">
+<TD ALIGN="right" VALIGN="top" WIDTH="1%"><FONT SIZE="-1">
+<CODE>&nbsp;java.lang.String</CODE></FONT></TD>
+<TD><CODE><B><A HREF="../../../../../org/apache/lenya/search/crawler/HTMLHandler.html#getAuthor()">getAuthor</A></B>()</CODE>
+
+<BR>
+&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;Parse Content. [24] 320:1</TD>
+</TR>
+<TR BGCOLOR="white" CLASS="TableRowColor">
+<TD ALIGN="right" VALIGN="top" WIDTH="1%"><FONT SIZE="-1">
+<CODE>&nbsp;java.lang.String</CODE></FONT></TD>
+<TD><CODE><B><A HREF="../../../../../org/apache/lenya/search/crawler/HTMLHandler.html#getCategories()">getCategories</A></B>()</CODE>
+
+<BR>
+&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;Return categories (from META tags)</TD>
+</TR>
+<TR BGCOLOR="white" CLASS="TableRowColor">
+<TD ALIGN="right" VALIGN="top" WIDTH="1%"><FONT SIZE="-1">
+<CODE>&nbsp;java.lang.String</CODE></FONT></TD>
+<TD><CODE><B><A HREF="../../../../../org/apache/lenya/search/crawler/HTMLHandler.html#getContents()">getContents</A></B>()</CODE>
+
+<BR>
+&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;Return contents</TD>
+</TR>
+<TR BGCOLOR="white" CLASS="TableRowColor">
+<TD ALIGN="right" VALIGN="top" WIDTH="1%"><FONT SIZE="-1">
+<CODE>&nbsp;java.lang.String</CODE></FONT></TD>
+<TD><CODE><B><A HREF="../../../../../org/apache/lenya/search/crawler/HTMLHandler.html#getDescription()">getDescription</A></B>()</CODE>
+
+<BR>
+&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;Return description (from META tags)</TD>
+</TR>
+<TR BGCOLOR="white" CLASS="TableRowColor">
+<TD ALIGN="right" VALIGN="top" WIDTH="1%"><FONT SIZE="-1">
+<CODE>&nbsp;java.lang.String</CODE></FONT></TD>
+<TD><CODE><B><A HREF="../../../../../org/apache/lenya/search/crawler/HTMLHandler.html#getHREF()">getHREF</A></B>()</CODE>
+
+<BR>
+&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;Return META HREF</TD>
+</TR>
+<TR BGCOLOR="white" CLASS="TableRowColor">
+<TD ALIGN="right" VALIGN="top" WIDTH="1%"><FONT SIZE="-1">
+<CODE>&nbsp;java.lang.String</CODE></FONT></TD>
+<TD><CODE><B><A HREF="../../../../../org/apache/lenya/search/crawler/HTMLHandler.html#getKeywords()">getKeywords</A></B>()</CODE>
+
+<BR>
+&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;Return keywords (from META tags)</TD>
+</TR>
+<TR BGCOLOR="white" CLASS="TableRowColor">
+<TD ALIGN="right" VALIGN="top" WIDTH="1%"><FONT SIZE="-1">
+<CODE>&nbsp;java.util.List</CODE></FONT></TD>
+<TD><CODE><B><A HREF="../../../../../org/apache/lenya/search/crawler/HTMLHandler.html#getLinks()">getLinks</A></B>()</CODE>
+
+<BR>
+&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;Return links</TD>
+</TR>
+<TR BGCOLOR="white" CLASS="TableRowColor">
+<TD ALIGN="right" VALIGN="top" WIDTH="1%"><FONT SIZE="-1">
+<CODE>&nbsp;long</CODE></FONT></TD>
+<TD><CODE><B><A HREF="../../../../../org/apache/lenya/search/crawler/HTMLHandler.html#getPublished()">getPublished</A></B>()</CODE>
+
+<BR>
+&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;Return published date (from META tag)</TD>
+</TR>
+<TR BGCOLOR="white" CLASS="TableRowColor">
+<TD ALIGN="right" VALIGN="top" WIDTH="1%"><FONT SIZE="-1">
+<CODE>&nbsp;boolean</CODE></FONT></TD>
+<TD><CODE><B><A HREF="../../../../../org/apache/lenya/search/crawler/HTMLHandler.html#getRobotFollow()">getRobotFollow</A></B>()</CODE>
+
+<BR>
+&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;Return boolean true if links are to be followed</TD>
+</TR>
+<TR BGCOLOR="white" CLASS="TableRowColor">
+<TD ALIGN="right" VALIGN="top" WIDTH="1%"><FONT SIZE="-1">
+<CODE>&nbsp;boolean</CODE></FONT></TD>
+<TD><CODE><B><A HREF="../../../../../org/apache/lenya/search/crawler/HTMLHandler.html#getRobotIndex()">getRobotIndex</A></B>()</CODE>
+
+<BR>
+&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;Return boolean true if this is to be indexed</TD>
+</TR>
+<TR BGCOLOR="white" CLASS="TableRowColor">
+<TD ALIGN="right" VALIGN="top" WIDTH="1%"><FONT SIZE="-1">
+<CODE>&nbsp;java.lang.String</CODE></FONT></TD>
+<TD><CODE><B><A HREF="../../../../../org/apache/lenya/search/crawler/HTMLHandler.html#getTitle()">getTitle</A></B>()</CODE>
+
+<BR>
+&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;Return page title</TD>
+</TR>
+<TR BGCOLOR="white" CLASS="TableRowColor">
+<TD ALIGN="right" VALIGN="top" WIDTH="1%"><FONT SIZE="-1">
+<CODE>&nbsp;void</CODE></FONT></TD>
+<TD><CODE><B><A HREF="../../../../../org/apache/lenya/search/crawler/HTMLHandler.html#handleAnchor(javax.swing.text.MutableAttributeSet)">handleAnchor</A></B>(javax.swing.text.MutableAttributeSet&nbsp;attribs)</CODE>
+
+<BR>
+&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;Handle Anchor <A HREF="~"></A> tags</TD>
+</TR>
+<TR BGCOLOR="white" CLASS="TableRowColor">
+<TD ALIGN="right" VALIGN="top" WIDTH="1%"><FONT SIZE="-1">
+<CODE>&nbsp;void</CODE></FONT></TD>
+<TD><CODE><B><A HREF="../../../../../org/apache/lenya/search/crawler/HTMLHandler.html#handleEndTag(javax.swing.text.html.HTML.Tag, int)">handleEndTag</A></B>(javax.swing.text.html.HTML.Tag&nbsp;tag,
+             int&nbsp;pos)</CODE>
+
+<BR>
+&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;Closing tag</TD>
+</TR>
+<TR BGCOLOR="white" CLASS="TableRowColor">
+<TD ALIGN="right" VALIGN="top" WIDTH="1%"><FONT SIZE="-1">
+<CODE>&nbsp;void</CODE></FONT></TD>
+<TD><CODE><B><A HREF="../../../../../org/apache/lenya/search/crawler/HTMLHandler.html#handleMeta(javax.swing.text.MutableAttributeSet)">handleMeta</A></B>(javax.swing.text.MutableAttributeSet&nbsp;attribs)</CODE>
+
+<BR>
+&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;Handle META tags</TD>
+</TR>
+<TR BGCOLOR="white" CLASS="TableRowColor">
+<TD ALIGN="right" VALIGN="top" WIDTH="1%"><FONT SIZE="-1">
+<CODE>&nbsp;void</CODE></FONT></TD>
+<TD><CODE><B><A HREF="../../../../../org/apache/lenya/search/crawler/HTMLHandler.html#handleSimpleTag(javax.swing.text.html.HTML.Tag, javax.swing.text.MutableAttributeSet, int)">handleSimpleTag</A></B>(javax.swing.text.html.HTML.Tag&nbsp;tag,
+                javax.swing.text.MutableAttributeSet&nbsp;attribs,
+                int&nbsp;pos)</CODE>
+
+<BR>
+&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;Handle standalone tags</TD>
+</TR>
+<TR BGCOLOR="white" CLASS="TableRowColor">
+<TD ALIGN="right" VALIGN="top" WIDTH="1%"><FONT SIZE="-1">
+<CODE>&nbsp;void</CODE></FONT></TD>
+<TD><CODE><B><A HREF="../../../../../org/apache/lenya/search/crawler/HTMLHandler.html#handleStartTag(javax.swing.text.html.HTML.Tag, javax.swing.text.MutableAttributeSet, int)">handleStartTag</A></B>(javax.swing.text.html.HTML.Tag&nbsp;tag,
+               javax.swing.text.MutableAttributeSet&nbsp;attribs,
+               int&nbsp;pos)</CODE>
+
+<BR>
+&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;Opening tag</TD>
+</TR>
+<TR BGCOLOR="white" CLASS="TableRowColor">
+<TD ALIGN="right" VALIGN="top" WIDTH="1%"><FONT SIZE="-1">
+<CODE>&nbsp;void</CODE></FONT></TD>
+<TD><CODE><B><A HREF="../../../../../org/apache/lenya/search/crawler/HTMLHandler.html#handleText(char[], int)">handleText</A></B>(char[]&nbsp;text,
+           int&nbsp;pos)</CODE>
+
+<BR>
+&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;Handle page text</TD>
+</TR>
+<TR BGCOLOR="white" CLASS="TableRowColor">
+<TD ALIGN="right" VALIGN="top" WIDTH="1%"><FONT SIZE="-1">
+<CODE>&nbsp;void</CODE></FONT></TD>
+<TD><CODE><B><A HREF="../../../../../org/apache/lenya/search/crawler/HTMLHandler.html#parse(java.io.InputStream)">parse</A></B>(java.io.InputStream&nbsp;in)</CODE>
+
+<BR>
+&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;Parse Content.</TD>
+</TR>
+</TABLE>
+&nbsp;<A NAME="methods_inherited_from_class_javax.swing.text.html.HTMLEditorKit.ParserCallback"><!-- --></A>
+<TABLE BORDER="1" WIDTH="100%" CELLPADDING="3" CELLSPACING="0" SUMMARY="">
+<TR BGCOLOR="#EEEEFF" CLASS="TableSubHeadingColor">
+<TD><B>Methods inherited from class javax.swing.text.html.HTMLEditorKit.ParserCallback</B></TD>
+</TR>
+<TR BGCOLOR="white" CLASS="TableRowColor">
+<TD><CODE>flush, handleComment, handleEndOfLineString, handleError</CODE></TD>
+</TR>
+</TABLE>
+&nbsp;<A NAME="methods_inherited_from_class_java.lang.Object"><!-- --></A>
+<TABLE BORDER="1" WIDTH="100%" CELLPADDING="3" CELLSPACING="0" SUMMARY="">
+<TR BGCOLOR="#EEEEFF" CLASS="TableSubHeadingColor">
+<TD><B>Methods inherited from class java.lang.Object</B></TD>
+</TR>
+<TR BGCOLOR="white" CLASS="TableRowColor">
+<TD><CODE>clone, equals, finalize, getClass, hashCode, notify, notifyAll, toString, wait, wait, wait</CODE></TD>
+</TR>
+</TABLE>
+&nbsp;
+<P>
+
+<!-- ============ FIELD DETAIL =========== -->
+
+
+<!-- ========= CONSTRUCTOR DETAIL ======== -->
+
+<A NAME="constructor_detail"><!-- --></A>
+<TABLE BORDER="1" WIDTH="100%" CELLPADDING="3" CELLSPACING="0" SUMMARY="">
+<TR BGCOLOR="#CCCCFF" CLASS="TableHeadingColor">
+<TD COLSPAN=1><FONT SIZE="+2">
+<B>Constructor Detail</B></FONT></TD>
+</TR>
+</TABLE>
+
+<A NAME="HTMLHandler()"><!-- --></A><H3>
+HTMLHandler</H3>
+<PRE>
+public <B>HTMLHandler</B>()</PRE>
+<DL>
+<DD>Constructor - initializes variables
+<P>
+</DL>
+
+<!-- ============ METHOD DETAIL ========== -->
+
+<A NAME="method_detail"><!-- --></A>
+<TABLE BORDER="1" WIDTH="100%" CELLPADDING="3" CELLSPACING="0" SUMMARY="">
+<TR BGCOLOR="#CCCCFF" CLASS="TableHeadingColor">
+<TD COLSPAN=1><FONT SIZE="+2">
+<B>Method Detail</B></FONT></TD>
+</TR>
+</TABLE>
+
+<A NAME="getAuthor()"><!-- --></A><H3>
+getAuthor</H3>
+<PRE>
+public java.lang.String <B>getAuthor</B>()</PRE>
+<DL>
+<DD>Parse Content. [24] 320:1
+<P>
+<DD><DL>
+<DT><B>Specified by:</B><DD><CODE><A HREF="../../../../../org/apache/lenya/search/crawler/ContentHandler.html#getAuthor()">getAuthor</A></CODE> in interface <CODE><A HREF="../../../../../org/apache/lenya/search/crawler/ContentHandler.html" title="interface in org.apache.lenya.search.crawler">ContentHandler</A></CODE></DL>
+</DD>
+<DD><DL>
+
+<DT><B>Returns:</B><DD>DOCUMENT ME!</DL>
+</DD>
+</DL>
+<HR>
+
+<A NAME="getCategories()"><!-- --></A><H3>
+getCategories</H3>
+<PRE>
+public java.lang.String <B>getCategories</B>()</PRE>
+<DL>
+<DD>Return categories (from META tags)
+<P>
+<DD><DL>
+<DT><B>Specified by:</B><DD><CODE><A HREF="../../../../../org/apache/lenya/search/crawler/ContentHandler.html#getCategories()">getCategories</A></CODE> in interface <CODE><A HREF="../../../../../org/apache/lenya/search/crawler/ContentHandler.html" title="interface in org.apache.lenya.search.crawler">ContentHandler</A></CODE></DL>
+</DD>
+<DD><DL>
+
+<DT><B>Returns:</B><DD>DOCUMENT ME!</DL>
+</DD>
+</DL>
+<HR>
+
+<A NAME="getContents()"><!-- --></A><H3>
+getContents</H3>
+<PRE>
+public java.lang.String <B>getContents</B>()</PRE>
+<DL>
+<DD>Return contents
+<P>
+<DD><DL>
+<DT><B>Specified by:</B><DD><CODE><A HREF="../../../../../org/apache/lenya/search/crawler/ContentHandler.html#getContents()">getContents</A></CODE> in interface <CODE><A HREF="../../../../../org/apache/lenya/search/crawler/ContentHandler.html" title="interface in org.apache.lenya.search.crawler">ContentHandler</A></CODE></DL>
+</DD>
+<DD><DL>
+
+<DT><B>Returns:</B><DD>DOCUMENT ME!</DL>
+</DD>
+</DL>
+<HR>
+
+<A NAME="getDescription()"><!-- --></A><H3>
+getDescription</H3>
+<PRE>
+public java.lang.String <B>getDescription</B>()</PRE>
+<DL>
+<DD>Return description (from META tags)
+<P>
+<DD><DL>
+<DT><B>Specified by:</B><DD><CODE><A HREF="../../../../../org/apache/lenya/search/crawler/ContentHandler.html#getDescription()">getDescription</A></CODE> in interface <CODE><A HREF="../../../../../org/apache/lenya/search/crawler/ContentHandler.html" title="interface in org.apache.lenya.search.crawler">ContentHandler</A></CODE></DL>
+</DD>
+<DD><DL>
+
+<DT><B>Returns:</B><DD>DOCUMENT ME!</DL>
+</DD>
+</DL>
+<HR>
+
+<A NAME="getHREF()"><!-- --></A><H3>
+getHREF</H3>
+<PRE>
+public java.lang.String <B>getHREF</B>()</PRE>
+<DL>
+<DD>Return META HREF
+<P>
+<DD><DL>
+<DT><B>Specified by:</B><DD><CODE><A HREF="../../../../../org/apache/lenya/search/crawler/ContentHandler.html#getHREF()">getHREF</A></CODE> in interface <CODE><A HREF="../../../../../org/apache/lenya/search/crawler/ContentHandler.html" title="interface in org.apache.lenya.search.crawler">ContentHandler</A></CODE></DL>
+</DD>
+<DD><DL>
+
+<DT><B>Returns:</B><DD>DOCUMENT ME!</DL>
+</DD>
+</DL>
+<HR>
+
+<A NAME="getKeywords()"><!-- --></A><H3>
+getKeywords</H3>
+<PRE>
+public java.lang.String <B>getKeywords</B>()</PRE>
+<DL>
+<DD>Return keywords (from META tags)
+<P>
+<DD><DL>
+<DT><B>Specified by:</B><DD><CODE><A HREF="../../../../../org/apache/lenya/search/crawler/ContentHandler.html#getKeywords()">getKeywords</A></CODE> in interface <CODE><A HREF="../../../../../org/apache/lenya/search/crawler/ContentHandler.html" title="interface in org.apache.lenya.search.crawler">ContentHandler</A></CODE></DL>
+</DD>
+<DD><DL>
+
+<DT><B>Returns:</B><DD>DOCUMENT ME!</DL>
+</DD>
+</DL>
+<HR>
+
+<A NAME="getLinks()"><!-- --></A><H3>
+getLinks</H3>
+<PRE>
+public java.util.List <B>getLinks</B>()</PRE>
+<DL>
+<DD>Return links
+<P>
+<DD><DL>
+<DT><B>Specified by:</B><DD><CODE><A HREF="../../../../../org/apache/lenya/search/crawler/ContentHandler.html#getLinks()">getLinks</A></CODE> in interface <CODE><A HREF="../../../../../org/apache/lenya/search/crawler/ContentHandler.html" title="interface in org.apache.lenya.search.crawler">ContentHandler</A></CODE></DL>
+</DD>
+<DD><DL>
+
+<DT><B>Returns:</B><DD>DOCUMENT ME!</DL>
+</DD>
+</DL>
+<HR>
+
+<A NAME="getPublished()"><!-- --></A><H3>
+getPublished</H3>
+<PRE>
+public long <B>getPublished</B>()</PRE>
+<DL>
+<DD>Return published date (from META tag)
+<P>
+<DD><DL>
+<DT><B>Specified by:</B><DD><CODE><A HREF="../../../../../org/apache/lenya/search/crawler/ContentHandler.html#getPublished()">getPublished</A></CODE> in interface <CODE><A HREF="../../../../../org/apache/lenya/search/crawler/ContentHandler.html" title="interface in org.apache.lenya.search.crawler">ContentHandler</A></CODE></DL>
+</DD>
+<DD><DL>
+
+<DT><B>Returns:</B><DD>DOCUMENT ME!</DL>
+</DD>
+</DL>
+<HR>
+
+<A NAME="getRobotFollow()"><!-- --></A><H3>
+getRobotFollow</H3>
+<PRE>
+public boolean <B>getRobotFollow</B>()</PRE>
+<DL>
+<DD>Return boolean true if links are to be followed
+<P>
+<DD><DL>
+<DT><B>Specified by:</B><DD><CODE><A HREF="../../../../../org/apache/lenya/search/crawler/ContentHandler.html#getRobotFollow()">getRobotFollow</A></CODE> in interface <CODE><A HREF="../../../../../org/apache/lenya/search/crawler/ContentHandler.html" title="interface in org.apache.lenya.search.crawler">ContentHandler</A></CODE></DL>
+</DD>
+<DD><DL>
+
+<DT><B>Returns:</B><DD>DOCUMENT ME!</DL>
+</DD>
+</DL>
+<HR>
+
+<A NAME="getRobotIndex()"><!-- --></A><H3>
+getRobotIndex</H3>
+<PRE>
+public boolean <B>getRobotIndex</B>()</PRE>
+<DL>
+<DD>Return boolean true if this is to be indexed
+<P>
+<DD><DL>
+<DT><B>Specified by:</B><DD><CODE><A HREF="../../../../../org/apache/lenya/search/crawler/ContentHandler.html#getRobotIndex()">getRobotIndex</A></CODE> in interface <CODE><A HREF="../../../../../org/apache/lenya/search/crawler/ContentHandler.html" title="interface in org.apache.lenya.search.crawler">ContentHandler</A></CODE></DL>
+</DD>
+<DD><DL>
+
+<DT><B>Returns:</B><DD>DOCUMENT ME!</DL>
+</DD>
+</DL>
+<HR>
+
+<A NAME="getTitle()"><!-- --></A><H3>
+getTitle</H3>
+<PRE>
+public java.lang.String <B>getTitle</B>()</PRE>
+<DL>
+<DD>Return page title
+<P>
+<DD><DL>
+<DT><B>Specified by:</B><DD><CODE><A HREF="../../../../../org/apache/lenya/search/crawler/ContentHandler.html#getTitle()">getTitle</A></CODE> in interface <CODE><A HREF="../../../../../org/apache/lenya/search/crawler/ContentHandler.html" title="interface in org.apache.lenya.search.crawler">ContentHandler</A></CODE></DL>
+</DD>
+<DD><DL>
+
+<DT><B>Returns:</B><DD>DOCUMENT ME!</DL>
+</DD>
+</DL>
+<HR>
+
+<A NAME="handleAnchor(javax.swing.text.MutableAttributeSet)"><!-- --></A><H3>
+handleAnchor</H3>
+<PRE>
+public void <B>handleAnchor</B>(javax.swing.text.MutableAttributeSet&nbsp;attribs)</PRE>
+<DL>
+<DD>Handle Anchor <A HREF="~"></A> tags
+<P>
+<DD><DL>
+</DL>
+</DD>
+<DD><DL>
+<DT><B>Parameters:</B><DD><CODE>attribs</CODE> - DOCUMENT ME!</DL>
+</DD>
+</DL>
+<HR>
+
+<A NAME="handleEndTag(javax.swing.text.html.HTML.Tag, int)"><!-- --></A><H3>
+handleEndTag</H3>
+<PRE>
+public void <B>handleEndTag</B>(javax.swing.text.html.HTML.Tag&nbsp;tag,
+                         int&nbsp;pos)</PRE>
+<DL>
+<DD>Closing tag
+<P>
+<DD><DL>
+</DL>
+</DD>
+<DD><DL>
+<DT><B>Parameters:</B><DD><CODE>tag</CODE> - DOCUMENT ME!<DD><CODE>pos</CODE> - DOCUMENT ME!</DL>
+</DD>
+</DL>
+<HR>
+
+<A NAME="handleMeta(javax.swing.text.MutableAttributeSet)"><!-- --></A><H3>
+handleMeta</H3>
+<PRE>
+public void <B>handleMeta</B>(javax.swing.text.MutableAttributeSet&nbsp;attribs)</PRE>
+<DL>
+<DD>Handle META tags
+<P>
+<DD><DL>
+</DL>
+</DD>
+<DD><DL>
+<DT><B>Parameters:</B><DD><CODE>attribs</CODE> - DOCUMENT ME!</DL>
+</DD>
+</DL>
+<HR>
+
+<A NAME="handleSimpleTag(javax.swing.text.html.HTML.Tag, javax.swing.text.MutableAttributeSet, int)"><!-- --></A><H3>
+handleSimpleTag</H3>
+<PRE>
+public void <B>handleSimpleTag</B>(javax.swing.text.html.HTML.Tag&nbsp;tag,
+                            javax.swing.text.MutableAttributeSet&nbsp;attribs,
+                            int&nbsp;pos)</PRE>
+<DL>
+<DD>Handle standalone tags
+<P>
+<DD><DL>
+</DL>
+</DD>
+<DD><DL>
+<DT><B>Parameters:</B><DD><CODE>tag</CODE> - DOCUMENT ME!<DD><CODE>attribs</CODE> - DOCUMENT ME!<DD><CODE>pos</CODE> - DOCUMENT ME!</DL>
+</DD>
+</DL>
+<HR>
+
+<A NAME="handleStartTag(javax.swing.text.html.HTML.Tag, javax.swing.text.MutableAttributeSet, int)"><!-- --></A><H3>
+handleStartTag</H3>
+<PRE>
+public void <B>handleStartTag</B>(javax.swing.text.html.HTML.Tag&nbsp;tag,
+                           javax.swing.text.MutableAttributeSet&nbsp;attribs,
+                           int&nbsp;pos)</PRE>
+<DL>
+<DD>Opening tag
+<P>
+<DD><DL>
+</DL>
+</DD>
+<DD><DL>
+<DT><B>Parameters:</B><DD><CODE>tag</CODE> - DOCUMENT ME!<DD><CODE>attribs</CODE> - DOCUMENT ME!<DD><CODE>pos</CODE> - DOCUMENT ME!</DL>
+</DD>
+</DL>
+<HR>
+
+<A NAME="handleText(char[], int)"><!-- --></A><H3>
+handleText</H3>
+<PRE>
+public void <B>handleText</B>(char[]&nbsp;text,
+                       int&nbsp;pos)</PRE>
+<DL>
+<DD>Handle page text
+<P>
+<DD><DL>
+</DL>
+</DD>
+<DD><DL>
+<DT><B>Parameters:</B><DD><CODE>text</CODE> - DOCUMENT ME!<DD><CODE>pos</CODE> - DOCUMENT ME!</DL>
+</DD>
+</DL>
+<HR>
+
+<A NAME="parse(java.io.InputStream)"><!-- --></A><H3>
+parse</H3>
+<PRE>
+public void <B>parse</B>(java.io.InputStream&nbsp;in)</PRE>
+<DL>
+<DD>Parse Content.
+<P>
+<DD><DL>
+<DT><B>Specified by:</B><DD><CODE><A HREF="../../../../../org/apache/lenya/search/crawler/ContentHandler.html#parse(java.io.InputStream)">parse</A></CODE> in interface <CODE><A HREF="../../../../../org/apache/lenya/search/crawler/ContentHandler.html" title="interface in org.apache.lenya.search.crawler">ContentHandler</A></CODE></DL>
+</DD>
+<DD><DL>
+<DT><B>Parameters:</B><DD><CODE>in</CODE> - DOCUMENT ME!</DL>
+</DD>
+</DL>
+<!-- ========= END OF CLASS DATA ========= -->
+<HR>
+
+
+<!-- ======= START OF BOTTOM NAVBAR ====== -->
+<A NAME="navbar_bottom"><!-- --></A>
+<A HREF="#skip-navbar_bottom" title="Skip navigation links"></A>
+<TABLE BORDER="0" WIDTH="100%" CELLPADDING="1" CELLSPACING="0" SUMMARY="">
+<TR>
+<TD COLSPAN=3 BGCOLOR="#EEEEFF" CLASS="NavBarCell1">
+<A NAME="navbar_bottom_firstrow"><!-- --></A>
+<TABLE BORDER="0" CELLPADDING="0" CELLSPACING="3" SUMMARY="">
+  <TR ALIGN="center" VALIGN="top">
+  <TD BGCOLOR="#EEEEFF" CLASS="NavBarCell1">    <A HREF="../../../../../overview-summary.html"><FONT CLASS="NavBarFont1"><B>Overview</B></FONT></A>&nbsp;</TD>
+  <TD BGCOLOR="#EEEEFF" CLASS="NavBarCell1">    <A HREF="package-summary.html"><FONT CLASS="NavBarFont1"><B>Package</B></FONT></A>&nbsp;</TD>
+  <TD BGCOLOR="#FFFFFF" CLASS="NavBarCell1Rev"> &nbsp;<FONT CLASS="NavBarFont1Rev"><B>Class</B></FONT>&nbsp;</TD>
+  <TD BGCOLOR="#EEEEFF" CLASS="NavBarCell1">    <A HREF="package-tree.html"><FONT CLASS="NavBarFont1"><B>Tree</B></FONT></A>&nbsp;</TD>
+  <TD BGCOLOR="#EEEEFF" CLASS="NavBarCell1">    <A HREF="../../../../../deprecated-list.html"><FONT CLASS="NavBarFont1"><B>Deprecated</B></FONT></A>&nbsp;</TD>
+  <TD BGCOLOR="#EEEEFF" CLASS="NavBarCell1">    <A HREF="../../../../../help-doc.html"><FONT CLASS="NavBarFont1"><B>Help</B></FONT></A>&nbsp;</TD>
+  </TR>
+</TABLE>
+</TD>
+<TD ALIGN="right" VALIGN="top" ROWSPAN=3><EM>
+</EM>
+</TD>
+</TR>
+
+<TR>
+<TD BGCOLOR="white" CLASS="NavBarCell2"><FONT SIZE="-2">
+&nbsp;<A HREF="../../../../../org/apache/lenya/search/crawler/CrawlerConfiguration.html" title="class in org.apache.lenya.search.crawler"><B>PREV CLASS</B></A>&nbsp;
+&nbsp;<A HREF="../../../../../org/apache/lenya/search/crawler/IterativeHTMLCrawler.html" title="class in org.apache.lenya.search.crawler"><B>NEXT CLASS</B></A></FONT></TD>
+<TD BGCOLOR="white" CLASS="NavBarCell2"><FONT SIZE="-2">
+  <A HREF="../../../../../index.html" target="_top"><B>FRAMES</B></A>  &nbsp;
+&nbsp;<A HREF="HTMLHandler.html" target="_top"><B>NO FRAMES</B></A>  &nbsp;
+&nbsp;<SCRIPT type="text/javascript">
+  <!--
+  if(window==top) {
+    document.writeln('<A HREF="../../../../../allclasses-noframe.html"><B>All Classes</B></A>');
+  }
+  //-->
+</SCRIPT>
+<NOSCRIPT>
+  <A HREF="../../../../../allclasses-noframe.html"><B>All Classes</B></A>
+</NOSCRIPT>
+
+</FONT></TD>
+</TR>
+<TR>
+<TD VALIGN="top" CLASS="NavBarCell3"><FONT SIZE="-2">
+  SUMMARY:&nbsp;NESTED&nbsp;|&nbsp;<A HREF="#fields_inherited_from_class_javax.swing.text.html.HTMLEditorKit.ParserCallback">FIELD</A>&nbsp;|&nbsp;<A HREF="#constructor_summary">CONSTR</A>&nbsp;|&nbsp;<A HREF="#method_summary">METHOD</A></FONT></TD>
+<TD VALIGN="top" CLASS="NavBarCell3"><FONT SIZE="-2">
+DETAIL:&nbsp;FIELD&nbsp;|&nbsp;<A HREF="#constructor_detail">CONSTR</A>&nbsp;|&nbsp;<A HREF="#method_detail">METHOD</A></FONT></TD>
+</TR>
+</TABLE>
+<A NAME="skip-navbar_bottom"></A>
+<!-- ======== END OF BOTTOM NAVBAR ======= -->
+
+<HR>
+Copyright © 1999-2004 Apache Software Foundation. All Rights Reserved.
+</BODY>
+</HTML>

Propchange: lenya/site/apidocs/1.2/org/apache/lenya/search/crawler/HTMLHandler.html
------------------------------------------------------------------------------
    svn:eol-style = native

Propchange: lenya/site/apidocs/1.2/org/apache/lenya/search/crawler/HTMLHandler.html
------------------------------------------------------------------------------
    svn:mime-type = text/html

Added: lenya/site/apidocs/1.2/org/apache/lenya/search/crawler/IterativeHTMLCrawler.html
URL: http://svn.apache.org/viewcvs/lenya/site/apidocs/1.2/org/apache/lenya/search/crawler/IterativeHTMLCrawler.html?rev=164448&view=auto
==============================================================================
--- lenya/site/apidocs/1.2/org/apache/lenya/search/crawler/IterativeHTMLCrawler.html (added)
+++ lenya/site/apidocs/1.2/org/apache/lenya/search/crawler/IterativeHTMLCrawler.html Sat Apr 23 22:30:06 2005
@@ -0,0 +1,560 @@
+<!DOCTYPE HTML PUBLIC "-//W3C//DTD HTML 4.01 Transitional//EN" "http://www.w3.org/TR/html4/loose.dtd">
+<!--NewPage-->
+<HTML>
+<HEAD>
+<!-- Generated by javadoc (build 1.4.2_03) on Mon Feb 21 17:32:47 EST 2005 -->
+<TITLE>
+IterativeHTMLCrawler (Apache Lenya API - Version 1.2.2)
+</TITLE>
+
+<META NAME="keywords" CONTENT="org.apache.lenya.search.crawler.IterativeHTMLCrawler class">
+
+<LINK REL ="stylesheet" TYPE="text/css" HREF="../../../../../javadoc.css" TITLE="Style">
+
+<SCRIPT type="text/javascript">
+function windowTitle()
+{
+    parent.document.title="IterativeHTMLCrawler (Apache Lenya API - Version 1.2.2)";
+}
+</SCRIPT>
+
+</HEAD>
+
+<BODY BGCOLOR="white" onload="windowTitle();">
+
+
+<!-- ========= START OF TOP NAVBAR ======= -->
+<A NAME="navbar_top"><!-- --></A>
+<A HREF="#skip-navbar_top" title="Skip navigation links"></A>
+<TABLE BORDER="0" WIDTH="100%" CELLPADDING="1" CELLSPACING="0" SUMMARY="">
+<TR>
+<TD COLSPAN=3 BGCOLOR="#EEEEFF" CLASS="NavBarCell1">
+<A NAME="navbar_top_firstrow"><!-- --></A>
+<TABLE BORDER="0" CELLPADDING="0" CELLSPACING="3" SUMMARY="">
+  <TR ALIGN="center" VALIGN="top">
+  <TD BGCOLOR="#EEEEFF" CLASS="NavBarCell1">    <A HREF="../../../../../overview-summary.html"><FONT CLASS="NavBarFont1"><B>Overview</B></FONT></A>&nbsp;</TD>
+  <TD BGCOLOR="#EEEEFF" CLASS="NavBarCell1">    <A HREF="package-summary.html"><FONT CLASS="NavBarFont1"><B>Package</B></FONT></A>&nbsp;</TD>
+  <TD BGCOLOR="#FFFFFF" CLASS="NavBarCell1Rev"> &nbsp;<FONT CLASS="NavBarFont1Rev"><B>Class</B></FONT>&nbsp;</TD>
+  <TD BGCOLOR="#EEEEFF" CLASS="NavBarCell1">    <A HREF="package-tree.html"><FONT CLASS="NavBarFont1"><B>Tree</B></FONT></A>&nbsp;</TD>
+  <TD BGCOLOR="#EEEEFF" CLASS="NavBarCell1">    <A HREF="../../../../../deprecated-list.html"><FONT CLASS="NavBarFont1"><B>Deprecated</B></FONT></A>&nbsp;</TD>
+  <TD BGCOLOR="#EEEEFF" CLASS="NavBarCell1">    <A HREF="../../../../../help-doc.html"><FONT CLASS="NavBarFont1"><B>Help</B></FONT></A>&nbsp;</TD>
+  </TR>
+</TABLE>
+</TD>
+<TD ALIGN="right" VALIGN="top" ROWSPAN=3><EM>
+</EM>
+</TD>
+</TR>
+
+<TR>
+<TD BGCOLOR="white" CLASS="NavBarCell2"><FONT SIZE="-2">
+&nbsp;<A HREF="../../../../../org/apache/lenya/search/crawler/HTMLHandler.html" title="class in org.apache.lenya.search.crawler"><B>PREV CLASS</B></A>&nbsp;
+&nbsp;NEXT CLASS</FONT></TD>
+<TD BGCOLOR="white" CLASS="NavBarCell2"><FONT SIZE="-2">
+  <A HREF="../../../../../index.html" target="_top"><B>FRAMES</B></A>  &nbsp;
+&nbsp;<A HREF="IterativeHTMLCrawler.html" target="_top"><B>NO FRAMES</B></A>  &nbsp;
+&nbsp;<SCRIPT type="text/javascript">
+  <!--
+  if(window==top) {
+    document.writeln('<A HREF="../../../../../allclasses-noframe.html"><B>All Classes</B></A>');
+  }
+  //-->
+</SCRIPT>
+<NOSCRIPT>
+  <A HREF="../../../../../allclasses-noframe.html"><B>All Classes</B></A>
+</NOSCRIPT>
+
+</FONT></TD>
+</TR>
+<TR>
+<TD VALIGN="top" CLASS="NavBarCell3"><FONT SIZE="-2">
+  SUMMARY:&nbsp;NESTED&nbsp;|&nbsp;FIELD&nbsp;|&nbsp;<A HREF="#constructor_summary">CONSTR</A>&nbsp;|&nbsp;<A HREF="#method_summary">METHOD</A></FONT></TD>
+<TD VALIGN="top" CLASS="NavBarCell3"><FONT SIZE="-2">
+DETAIL:&nbsp;FIELD&nbsp;|&nbsp;<A HREF="#constructor_detail">CONSTR</A>&nbsp;|&nbsp;<A HREF="#method_detail">METHOD</A></FONT></TD>
+</TR>
+</TABLE>
+<A NAME="skip-navbar_top"></A>
+<!-- ========= END OF TOP NAVBAR ========= -->
+
+<HR>
+<!-- ======== START OF CLASS DATA ======== -->
+<H2>
+<FONT SIZE="-1">
+org.apache.lenya.search.crawler</FONT>
+<BR>
+Class IterativeHTMLCrawler</H2>
+<PRE>
+java.lang.Object
+  <IMG SRC="../../../../../resources/inherit.gif" ALT="extended by"><B>org.apache.lenya.search.crawler.IterativeHTMLCrawler</B>
+</PRE>
+<HR>
+<DL>
+<DT>public class <B>IterativeHTMLCrawler</B><DT>extends java.lang.Object</DL>
+
+<P>
+Crawl iteratively
+<P>
+
+<P>
+<HR>
+
+<P>
+<!-- ======== NESTED CLASS SUMMARY ======== -->
+
+
+<!-- =========== FIELD SUMMARY =========== -->
+
+
+<!-- ======== CONSTRUCTOR SUMMARY ======== -->
+
+<A NAME="constructor_summary"><!-- --></A>
+<TABLE BORDER="1" WIDTH="100%" CELLPADDING="3" CELLSPACING="0" SUMMARY="">
+<TR BGCOLOR="#CCCCFF" CLASS="TableHeadingColor">
+<TD COLSPAN=2><FONT SIZE="+2">
+<B>Constructor Summary</B></FONT></TD>
+</TR>
+<TR BGCOLOR="white" CLASS="TableRowColor">
+<TD><CODE><B><A HREF="../../../../../org/apache/lenya/search/crawler/IterativeHTMLCrawler.html#IterativeHTMLCrawler(java.io.File)">IterativeHTMLCrawler</A></B>(java.io.File&nbsp;config)</CODE>
+
+<BR>
+&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;Creates a new IterativeHTMLCrawler object.</TD>
+</TR>
+<TR BGCOLOR="white" CLASS="TableRowColor">
+<TD><CODE><B><A HREF="../../../../../org/apache/lenya/search/crawler/IterativeHTMLCrawler.html#IterativeHTMLCrawler(java.lang.String, java.lang.String, java.lang.String)">IterativeHTMLCrawler</A></B>(java.lang.String&nbsp;url_list_file,
+                     java.lang.String&nbsp;html_dump_directory,
+                     java.lang.String&nbsp;userAgent)</CODE>
+
+<BR>
+&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;Creates a new IterativeHTMLCrawler object.</TD>
+</TR>
+</TABLE>
+&nbsp;
+<!-- ========== METHOD SUMMARY =========== -->
+
+<A NAME="method_summary"><!-- --></A>
+<TABLE BORDER="1" WIDTH="100%" CELLPADDING="3" CELLSPACING="0" SUMMARY="">
+<TR BGCOLOR="#CCCCFF" CLASS="TableHeadingColor">
+<TD COLSPAN=2><FONT SIZE="+2">
+<B>Method Summary</B></FONT></TD>
+</TR>
+<TR BGCOLOR="white" CLASS="TableRowColor">
+<TD ALIGN="right" VALIGN="top" WIDTH="1%"><FONT SIZE="-1">
+<CODE>&nbsp;java.net.URL</CODE></FONT></TD>
+<TD><CODE><B><A HREF="../../../../../org/apache/lenya/search/crawler/IterativeHTMLCrawler.html#addURL(java.lang.String, java.lang.String)">addURL</A></B>(java.lang.String&nbsp;urlCandidate,
+       java.lang.String&nbsp;currentURLPath)</CODE>
+
+<BR>
+&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;Add URLs to crawl</TD>
+</TR>
+<TR BGCOLOR="white" CLASS="TableRowColor">
+<TD ALIGN="right" VALIGN="top" WIDTH="1%"><FONT SIZE="-1">
+<CODE>&nbsp;java.net.URL</CODE></FONT></TD>
+<TD><CODE><B><A HREF="../../../../../org/apache/lenya/search/crawler/IterativeHTMLCrawler.html#completeURL(java.net.URL, java.lang.String)">completeURL</A></B>(java.net.URL&nbsp;parent,
+            java.lang.String&nbsp;child)</CODE>
+
+<BR>
+&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;DOCUMENT ME!</TD>
+</TR>
+<TR BGCOLOR="white" CLASS="TableRowColor">
+<TD ALIGN="right" VALIGN="top" WIDTH="1%"><FONT SIZE="-1">
+<CODE>&nbsp;void</CODE></FONT></TD>
+<TD><CODE><B><A HREF="../../../../../org/apache/lenya/search/crawler/IterativeHTMLCrawler.html#crawl(java.net.URL, java.lang.String)">crawl</A></B>(java.net.URL&nbsp;start,
+      java.lang.String&nbsp;scope)</CODE>
+
+<BR>
+&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;Crawl</TD>
+</TR>
+<TR BGCOLOR="white" CLASS="TableRowColor">
+<TD ALIGN="right" VALIGN="top" WIDTH="1%"><FONT SIZE="-1">
+<CODE>&nbsp;void</CODE></FONT></TD>
+<TD><CODE><B><A HREF="../../../../../org/apache/lenya/search/crawler/IterativeHTMLCrawler.html#dumpHTDoc(java.net.URL)">dumpHTDoc</A></B>(java.net.URL&nbsp;url)</CODE>
+
+<BR>
+&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;DOCUMENT ME!</TD>
+</TR>
+<TR BGCOLOR="white" CLASS="TableRowColor">
+<TD ALIGN="right" VALIGN="top" WIDTH="1%"><FONT SIZE="-1">
+<CODE>&nbsp;boolean</CODE></FONT></TD>
+<TD><CODE><B><A HREF="../../../../../org/apache/lenya/search/crawler/IterativeHTMLCrawler.html#filterURL(java.lang.String, java.lang.String, java.util.TreeSet)">filterURL</A></B>(java.lang.String&nbsp;url,
+          java.lang.String&nbsp;currentURLPath,
+          java.util.TreeSet&nbsp;links)</CODE>
+
+<BR>
+&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;DOCUMENT ME!</TD>
+</TR>
+<TR BGCOLOR="white" CLASS="TableRowColor">
+<TD ALIGN="right" VALIGN="top" WIDTH="1%"><FONT SIZE="-1">
+<CODE>&nbsp;java.lang.String</CODE></FONT></TD>
+<TD><CODE><B><A HREF="../../../../../org/apache/lenya/search/crawler/IterativeHTMLCrawler.html#getExtension(java.io.File)">getExtension</A></B>(java.io.File&nbsp;file)</CODE>
+
+<BR>
+&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;DOCUMENT ME!</TD>
+</TR>
+<TR BGCOLOR="white" CLASS="TableRowColor">
+<TD ALIGN="right" VALIGN="top" WIDTH="1%"><FONT SIZE="-1">
+<CODE>&nbsp;java.lang.String</CODE></FONT></TD>
+<TD><CODE><B><A HREF="../../../../../org/apache/lenya/search/crawler/IterativeHTMLCrawler.html#getExtension(java.net.URL)">getExtension</A></B>(java.net.URL&nbsp;url)</CODE>
+
+<BR>
+&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;DOCUMENT ME!</TD>
+</TR>
+<TR BGCOLOR="white" CLASS="TableRowColor">
+<TD ALIGN="right" VALIGN="top" WIDTH="1%"><FONT SIZE="-1">
+<CODE>static&nbsp;java.util.List</CODE></FONT></TD>
+<TD><CODE><B><A HREF="../../../../../org/apache/lenya/search/crawler/IterativeHTMLCrawler.html#handleHTML(java.net.HttpURLConnection)">handleHTML</A></B>(java.net.HttpURLConnection&nbsp;httpCon)</CODE>
+
+<BR>
+&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;DOCUMENT ME!</TD>
+</TR>
+<TR BGCOLOR="white" CLASS="TableRowColor">
+<TD ALIGN="right" VALIGN="top" WIDTH="1%"><FONT SIZE="-1">
+<CODE>&nbsp;void</CODE></FONT></TD>
+<TD><CODE><B><A HREF="../../../../../org/apache/lenya/search/crawler/IterativeHTMLCrawler.html#handlePDF(java.net.HttpURLConnection)">handlePDF</A></B>(java.net.HttpURLConnection&nbsp;httpCon)</CODE>
+
+<BR>
+&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;Parse PDF for links</TD>
+</TR>
+<TR BGCOLOR="white" CLASS="TableRowColor">
+<TD ALIGN="right" VALIGN="top" WIDTH="1%"><FONT SIZE="-1">
+<CODE>&nbsp;boolean</CODE></FONT></TD>
+<TD><CODE><B><A HREF="../../../../../org/apache/lenya/search/crawler/IterativeHTMLCrawler.html#inScope(java.lang.String)">inScope</A></B>(java.lang.String&nbsp;url)</CODE>
+
+<BR>
+&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;DOCUMENT ME!</TD>
+</TR>
+<TR BGCOLOR="white" CLASS="TableRowColor">
+<TD ALIGN="right" VALIGN="top" WIDTH="1%"><FONT SIZE="-1">
+<CODE>static&nbsp;void</CODE></FONT></TD>
+<TD><CODE><B><A HREF="../../../../../org/apache/lenya/search/crawler/IterativeHTMLCrawler.html#main(java.lang.String[])">main</A></B>(java.lang.String[]&nbsp;args)</CODE>
+
+<BR>
+&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;Command line interface</TD>
+</TR>
+<TR BGCOLOR="white" CLASS="TableRowColor">
+<TD ALIGN="right" VALIGN="top" WIDTH="1%"><FONT SIZE="-1">
+<CODE>&nbsp;java.lang.String</CODE></FONT></TD>
+<TD><CODE><B><A HREF="../../../../../org/apache/lenya/search/crawler/IterativeHTMLCrawler.html#parseHREF(java.lang.String, java.lang.String, java.lang.String)">parseHREF</A></B>(java.lang.String&nbsp;url,
+          java.lang.String&nbsp;urlLowCase,
+          java.lang.String&nbsp;currentURLPath)</CODE>
+
+<BR>
+&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;Parse URL and complete if necessary</TD>
+</TR>
+<TR BGCOLOR="white" CLASS="TableRowColor">
+<TD ALIGN="right" VALIGN="top" WIDTH="1%"><FONT SIZE="-1">
+<CODE>&nbsp;java.util.List</CODE></FONT></TD>
+<TD><CODE><B><A HREF="../../../../../org/apache/lenya/search/crawler/IterativeHTMLCrawler.html#parsePage(java.lang.String)">parsePage</A></B>(java.lang.String&nbsp;urlString)</CODE>
+
+<BR>
+&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;DOCUMENT ME!</TD>
+</TR>
+</TABLE>
+&nbsp;<A NAME="methods_inherited_from_class_java.lang.Object"><!-- --></A>
+<TABLE BORDER="1" WIDTH="100%" CELLPADDING="3" CELLSPACING="0" SUMMARY="">
+<TR BGCOLOR="#EEEEFF" CLASS="TableSubHeadingColor">
+<TD><B>Methods inherited from class java.lang.Object</B></TD>
+</TR>
+<TR BGCOLOR="white" CLASS="TableRowColor">
+<TD><CODE>clone, equals, finalize, getClass, hashCode, notify, notifyAll, toString, wait, wait, wait</CODE></TD>
+</TR>
+</TABLE>
+&nbsp;
+<P>
+
+<!-- ============ FIELD DETAIL =========== -->
+
+
+<!-- ========= CONSTRUCTOR DETAIL ======== -->
+
+<A NAME="constructor_detail"><!-- --></A>
+<TABLE BORDER="1" WIDTH="100%" CELLPADDING="3" CELLSPACING="0" SUMMARY="">
+<TR BGCOLOR="#CCCCFF" CLASS="TableHeadingColor">
+<TD COLSPAN=1><FONT SIZE="+2">
+<B>Constructor Detail</B></FONT></TD>
+</TR>
+</TABLE>
+
+<A NAME="IterativeHTMLCrawler(java.lang.String, java.lang.String, java.lang.String)"><!-- --></A><H3>
+IterativeHTMLCrawler</H3>
+<PRE>
+public <B>IterativeHTMLCrawler</B>(java.lang.String&nbsp;url_list_file,
+                            java.lang.String&nbsp;html_dump_directory,
+                            java.lang.String&nbsp;userAgent)</PRE>
+<DL>
+<DD>Creates a new IterativeHTMLCrawler object.
+<P>
+<DT><B>Parameters:</B><DD><CODE>url_list_file</CODE> - File where all dumped files will be listed<DD><CODE>html_dump_directory</CODE> - Directory where htdocs should be dumped<DD><CODE>userAgent</CODE> - User-agent for robots.txt</DL>
+<HR>
+
+<A NAME="IterativeHTMLCrawler(java.io.File)"><!-- --></A><H3>
+IterativeHTMLCrawler</H3>
+<PRE>
+public <B>IterativeHTMLCrawler</B>(java.io.File&nbsp;config)</PRE>
+<DL>
+<DD>Creates a new IterativeHTMLCrawler object.
+<P>
+<DT><B>Parameters:</B><DD><CODE>config</CODE> - Configuration File</DL>
+
+<!-- ============ METHOD DETAIL ========== -->
+
+<A NAME="method_detail"><!-- --></A>
+<TABLE BORDER="1" WIDTH="100%" CELLPADDING="3" CELLSPACING="0" SUMMARY="">
+<TR BGCOLOR="#CCCCFF" CLASS="TableHeadingColor">
+<TD COLSPAN=1><FONT SIZE="+2">
+<B>Method Detail</B></FONT></TD>
+</TR>
+</TABLE>
+
+<A NAME="main(java.lang.String[])"><!-- --></A><H3>
+main</H3>
+<PRE>
+public static void <B>main</B>(java.lang.String[]&nbsp;args)</PRE>
+<DL>
+<DD>Command line interface
+<P>
+<DD><DL>
+<DT><B>Parameters:</B><DD><CODE>args</CODE> - Configuration file crawler.xconf</DL>
+</DD>
+</DL>
+<HR>
+
+<A NAME="crawl(java.net.URL, java.lang.String)"><!-- --></A><H3>
+crawl</H3>
+<PRE>
+public void <B>crawl</B>(java.net.URL&nbsp;start,
+                  java.lang.String&nbsp;scope)</PRE>
+<DL>
+<DD>Crawl
+<P>
+<DD><DL>
+<DT><B>Parameters:</B><DD><CODE>start</CODE> - Start crawling at this URL<DD><CODE>scope</CODE> - Limit crawling to this scope</DL>
+</DD>
+</DL>
+<HR>
+
+<A NAME="addURL(java.lang.String, java.lang.String)"><!-- --></A><H3>
+addURL</H3>
+<PRE>
+public java.net.URL <B>addURL</B>(java.lang.String&nbsp;urlCandidate,
+                           java.lang.String&nbsp;currentURLPath)
+                    throws java.net.MalformedURLException</PRE>
+<DL>
+<DD>Add URLs to crawl
+<P>
+<DD><DL>
+<DT><B>Parameters:</B><DD><CODE>urlCandidate</CODE> - DOCUMENT ME!<DD><CODE>currentURLPath</CODE> - DOCUMENT ME!
+<DT><B>Returns:</B><DD>DOCUMENT ME!
+<DT><B>Throws:</B>
+<DD><CODE>java.net.MalformedURLException</CODE> - DOCUMENT ME!</DL>
+</DD>
+</DL>
+<HR>
+
+<A NAME="parsePage(java.lang.String)"><!-- --></A><H3>
+parsePage</H3>
+<PRE>
+public java.util.List <B>parsePage</B>(java.lang.String&nbsp;urlString)</PRE>
+<DL>
+<DD>DOCUMENT ME!
+<P>
+<DD><DL>
+<DT><B>Parameters:</B><DD><CODE>urlString</CODE> - DOCUMENT ME!
+<DT><B>Returns:</B><DD>ok, 404</DL>
+</DD>
+</DL>
+<HR>
+
+<A NAME="handleHTML(java.net.HttpURLConnection)"><!-- --></A><H3>
+handleHTML</H3>
+<PRE>
+public static java.util.List <B>handleHTML</B>(java.net.HttpURLConnection&nbsp;httpCon)
+                                 throws java.io.IOException</PRE>
+<DL>
+<DD>DOCUMENT ME!
+<P>
+<DD><DL>
+<DT><B>Parameters:</B><DD><CODE>httpCon</CODE> - DOCUMENT ME!
+<DT><B>Returns:</B><DD>DOCUMENT ME!
+<DT><B>Throws:</B>
+<DD><CODE>java.io.IOException</CODE> - DOCUMENT ME!</DL>
+</DD>
+</DL>
+<HR>
+
+<A NAME="handlePDF(java.net.HttpURLConnection)"><!-- --></A><H3>
+handlePDF</H3>
+<PRE>
+public void <B>handlePDF</B>(java.net.HttpURLConnection&nbsp;httpCon)</PRE>
+<DL>
+<DD>Parse PDF for links
+<P>
+<DD><DL>
+<DT><B>Parameters:</B><DD><CODE>httpCon</CODE> - DOCUMENT ME!</DL>
+</DD>
+</DL>
+<HR>
+
+<A NAME="filterURL(java.lang.String, java.lang.String, java.util.TreeSet)"><!-- --></A><H3>
+filterURL</H3>
+<PRE>
+public boolean <B>filterURL</B>(java.lang.String&nbsp;url,
+                         java.lang.String&nbsp;currentURLPath,
+                         java.util.TreeSet&nbsp;links)</PRE>
+<DL>
+<DD>DOCUMENT ME!
+<P>
+<DD><DL>
+<DT><B>Parameters:</B><DD><CODE>url</CODE> - DOCUMENT ME!<DD><CODE>currentURLPath</CODE> - DOCUMENT ME!<DD><CODE>links</CODE> - DOCUMENT ME!
+<DT><B>Returns:</B><DD>DOCUMENT ME!</DL>
+</DD>
+</DL>
+<HR>
+
+<A NAME="parseHREF(java.lang.String, java.lang.String, java.lang.String)"><!-- --></A><H3>
+parseHREF</H3>
+<PRE>
+public java.lang.String <B>parseHREF</B>(java.lang.String&nbsp;url,
+                                  java.lang.String&nbsp;urlLowCase,
+                                  java.lang.String&nbsp;currentURLPath)</PRE>
+<DL>
+<DD>Parse URL and complete if necessary
+<P>
+<DD><DL>
+<DT><B>Parameters:</B><DD><CODE>url</CODE> - URL from href<DD><CODE>urlLowCase</CODE> - url is lower case<DD><CODE>currentURLPath</CODE> - URL of current page
+<DT><B>Returns:</B><DD>Completed URL</DL>
+</DD>
+</DL>
+<HR>
+
+<A NAME="inScope(java.lang.String)"><!-- --></A><H3>
+inScope</H3>
+<PRE>
+public boolean <B>inScope</B>(java.lang.String&nbsp;url)</PRE>
+<DL>
+<DD>DOCUMENT ME!
+<P>
+<DD><DL>
+<DT><B>Parameters:</B><DD><CODE>url</CODE> - DOCUMENT ME!
+<DT><B>Returns:</B><DD>DOCUMENT ME!</DL>
+</DD>
+</DL>
+<HR>
+
+<A NAME="completeURL(java.net.URL, java.lang.String)"><!-- --></A><H3>
+completeURL</H3>
+<PRE>
+public java.net.URL <B>completeURL</B>(java.net.URL&nbsp;parent,
+                                java.lang.String&nbsp;child)
+                         throws java.net.MalformedURLException</PRE>
+<DL>
+<DD>DOCUMENT ME!
+<P>
+<DD><DL>
+<DT><B>Parameters:</B><DD><CODE>parent</CODE> - DOCUMENT ME!<DD><CODE>child</CODE> - DOCUMENT ME!
+<DT><B>Returns:</B><DD>DOCUMENT ME!
+<DT><B>Throws:</B>
+<DD><CODE>java.net.MalformedURLException</CODE> - DOCUMENT ME!</DL>
+</DD>
+</DL>
+<HR>
+
+<A NAME="dumpHTDoc(java.net.URL)"><!-- --></A><H3>
+dumpHTDoc</H3>
+<PRE>
+public void <B>dumpHTDoc</B>(java.net.URL&nbsp;url)</PRE>
+<DL>
+<DD>DOCUMENT ME!
+<P>
+<DD><DL>
+<DT><B>Parameters:</B><DD><CODE>url</CODE> - DOCUMENT ME!</DL>
+</DD>
+</DL>
+<HR>
+
+<A NAME="getExtension(java.net.URL)"><!-- --></A><H3>
+getExtension</H3>
+<PRE>
+public java.lang.String <B>getExtension</B>(java.net.URL&nbsp;url)</PRE>
+<DL>
+<DD>DOCUMENT ME!
+<P>
+<DD><DL>
+<DT><B>Parameters:</B><DD><CODE>url</CODE> - DOCUMENT ME!
+<DT><B>Returns:</B><DD>DOCUMENT ME!</DL>
+</DD>
+</DL>
+<HR>
+
+<A NAME="getExtension(java.io.File)"><!-- --></A><H3>
+getExtension</H3>
+<PRE>
+public java.lang.String <B>getExtension</B>(java.io.File&nbsp;file)</PRE>
+<DL>
+<DD>DOCUMENT ME!
+<P>
+<DD><DL>
+<DT><B>Parameters:</B><DD><CODE>file</CODE> - DOCUMENT ME!
+<DT><B>Returns:</B><DD>DOCUMENT ME!</DL>
+</DD>
+</DL>
+<!-- ========= END OF CLASS DATA ========= -->
+<HR>
+
+
+<!-- ======= START OF BOTTOM NAVBAR ====== -->
+<A NAME="navbar_bottom"><!-- --></A>
+<A HREF="#skip-navbar_bottom" title="Skip navigation links"></A>
+<TABLE BORDER="0" WIDTH="100%" CELLPADDING="1" CELLSPACING="0" SUMMARY="">
+<TR>
+<TD COLSPAN=3 BGCOLOR="#EEEEFF" CLASS="NavBarCell1">
+<A NAME="navbar_bottom_firstrow"><!-- --></A>
+<TABLE BORDER="0" CELLPADDING="0" CELLSPACING="3" SUMMARY="">
+  <TR ALIGN="center" VALIGN="top">
+  <TD BGCOLOR="#EEEEFF" CLASS="NavBarCell1">    <A HREF="../../../../../overview-summary.html"><FONT CLASS="NavBarFont1"><B>Overview</B></FONT></A>&nbsp;</TD>
+  <TD BGCOLOR="#EEEEFF" CLASS="NavBarCell1">    <A HREF="package-summary.html"><FONT CLASS="NavBarFont1"><B>Package</B></FONT></A>&nbsp;</TD>
+  <TD BGCOLOR="#FFFFFF" CLASS="NavBarCell1Rev"> &nbsp;<FONT CLASS="NavBarFont1Rev"><B>Class</B></FONT>&nbsp;</TD>
+  <TD BGCOLOR="#EEEEFF" CLASS="NavBarCell1">    <A HREF="package-tree.html"><FONT CLASS="NavBarFont1"><B>Tree</B></FONT></A>&nbsp;</TD>
+  <TD BGCOLOR="#EEEEFF" CLASS="NavBarCell1">    <A HREF="../../../../../deprecated-list.html"><FONT CLASS="NavBarFont1"><B>Deprecated</B></FONT></A>&nbsp;</TD>
+  <TD BGCOLOR="#EEEEFF" CLASS="NavBarCell1">    <A HREF="../../../../../help-doc.html"><FONT CLASS="NavBarFont1"><B>Help</B></FONT></A>&nbsp;</TD>
+  </TR>
+</TABLE>
+</TD>
+<TD ALIGN="right" VALIGN="top" ROWSPAN=3><EM>
+</EM>
+</TD>
+</TR>
+
+<TR>
+<TD BGCOLOR="white" CLASS="NavBarCell2"><FONT SIZE="-2">
+&nbsp;<A HREF="../../../../../org/apache/lenya/search/crawler/HTMLHandler.html" title="class in org.apache.lenya.search.crawler"><B>PREV CLASS</B></A>&nbsp;
+&nbsp;NEXT CLASS</FONT></TD>
+<TD BGCOLOR="white" CLASS="NavBarCell2"><FONT SIZE="-2">
+  <A HREF="../../../../../index.html" target="_top"><B>FRAMES</B></A>  &nbsp;
+&nbsp;<A HREF="IterativeHTMLCrawler.html" target="_top"><B>NO FRAMES</B></A>  &nbsp;
+&nbsp;<SCRIPT type="text/javascript">
+  <!--
+  if(window==top) {
+    document.writeln('<A HREF="../../../../../allclasses-noframe.html"><B>All Classes</B></A>');
+  }
+  //-->
+</SCRIPT>
+<NOSCRIPT>
+  <A HREF="../../../../../allclasses-noframe.html"><B>All Classes</B></A>
+</NOSCRIPT>
+
+</FONT></TD>
+</TR>
+<TR>
+<TD VALIGN="top" CLASS="NavBarCell3"><FONT SIZE="-2">
+  SUMMARY:&nbsp;NESTED&nbsp;|&nbsp;FIELD&nbsp;|&nbsp;<A HREF="#constructor_summary">CONSTR</A>&nbsp;|&nbsp;<A HREF="#method_summary">METHOD</A></FONT></TD>
+<TD VALIGN="top" CLASS="NavBarCell3"><FONT SIZE="-2">
+DETAIL:&nbsp;FIELD&nbsp;|&nbsp;<A HREF="#constructor_detail">CONSTR</A>&nbsp;|&nbsp;<A HREF="#method_detail">METHOD</A></FONT></TD>
+</TR>
+</TABLE>
+<A NAME="skip-navbar_bottom"></A>
+<!-- ======== END OF BOTTOM NAVBAR ======= -->
+
+<HR>
+Copyright © 1999-2004 Apache Software Foundation. All Rights Reserved.
+</BODY>
+</HTML>

Propchange: lenya/site/apidocs/1.2/org/apache/lenya/search/crawler/IterativeHTMLCrawler.html
------------------------------------------------------------------------------
    svn:eol-style = native

Propchange: lenya/site/apidocs/1.2/org/apache/lenya/search/crawler/IterativeHTMLCrawler.html
------------------------------------------------------------------------------
    svn:mime-type = text/html

Added: lenya/site/apidocs/1.2/org/apache/lenya/search/crawler/package-frame.html
URL: http://svn.apache.org/viewcvs/lenya/site/apidocs/1.2/org/apache/lenya/search/crawler/package-frame.html?rev=164448&view=auto
==============================================================================
--- lenya/site/apidocs/1.2/org/apache/lenya/search/crawler/package-frame.html (added)
+++ lenya/site/apidocs/1.2/org/apache/lenya/search/crawler/package-frame.html Sat Apr 23 22:30:06 2005
@@ -0,0 +1,47 @@
+<!DOCTYPE HTML PUBLIC "-//W3C//DTD HTML 4.01 Transitional//EN" "http://www.w3.org/TR/html4/loose.dtd">
+<!--NewPage-->
+<HTML>
+<HEAD>
+<!-- Generated by javadoc (build 1.4.2_03) on Mon Feb 21 17:32:38 EST 2005 -->
+<TITLE>
+org.apache.lenya.search.crawler (Apache Lenya API - Version 1.2.2)
+</TITLE>
+
+<META NAME="keywords" CONTENT="org.apache.lenya.search.crawler package">
+
+<LINK REL ="stylesheet" TYPE="text/css" HREF="../../../../../javadoc.css" TITLE="Style">
+
+
+</HEAD>
+
+<BODY BGCOLOR="white">
+<FONT size="+1" CLASS="FrameTitleFont">
+<A HREF="../../../../../org/apache/lenya/search/crawler/package-summary.html" target="classFrame">org.apache.lenya.search.crawler</A></FONT>
+<TABLE BORDER="0" WIDTH="100%" SUMMARY="">
+<TR>
+<TD NOWRAP><FONT size="+1" CLASS="FrameHeadingFont">
+Interfaces</FONT>&nbsp;
+<FONT CLASS="FrameItemFont">
+<BR>
+<A HREF="ContentHandler.html" title="interface in org.apache.lenya.search.crawler" target="classFrame"><I>ContentHandler</I></A></FONT></TD>
+</TR>
+</TABLE>
+
+
+<TABLE BORDER="0" WIDTH="100%" SUMMARY="">
+<TR>
+<TD NOWRAP><FONT size="+1" CLASS="FrameHeadingFont">
+Classes</FONT>&nbsp;
+<FONT CLASS="FrameItemFont">
+<BR>
+<A HREF="CrawlerConfiguration.html" title="class in org.apache.lenya.search.crawler" target="classFrame">CrawlerConfiguration</A>
+<BR>
+<A HREF="HTMLHandler.html" title="class in org.apache.lenya.search.crawler" target="classFrame">HTMLHandler</A>
+<BR>
+<A HREF="IterativeHTMLCrawler.html" title="class in org.apache.lenya.search.crawler" target="classFrame">IterativeHTMLCrawler</A></FONT></TD>
+</TR>
+</TABLE>
+
+
+</BODY>
+</HTML>

Propchange: lenya/site/apidocs/1.2/org/apache/lenya/search/crawler/package-frame.html
------------------------------------------------------------------------------
    svn:eol-style = native

Propchange: lenya/site/apidocs/1.2/org/apache/lenya/search/crawler/package-frame.html
------------------------------------------------------------------------------
    svn:mime-type = text/html



---------------------------------------------------------------------
To unsubscribe, e-mail: commits-unsubscribe@lenya.apache.org
For additional commands, e-mail: commits-help@lenya.apache.org