mirror of https://github.com/apache/lucene.git
349 lines
12 KiB
XML
349 lines
12 KiB
XML
<?xml version="1.0"?>
|
|
<document>
|
|
<properties>
|
|
<author email="carlson@apache.org">
|
|
Peter Carlson
|
|
</author>
|
|
<title>
|
|
Contributions - Jakarta Lucene
|
|
</title>
|
|
</properties>
|
|
<body>
|
|
<section name="Overview">
|
|
<p>This page lists external resources for Lucene. If you've written something that should be included, please post all relevant information to one of the mailing lists. Nothing listed here is directly supported by the Lucene developers, if you encounter any problems with them, please use the contact information. </p>
|
|
</section>
|
|
<section name="Lucene Documents">
|
|
<p>
|
|
Lucene requires information you want to index to be converted into a Document class. Here are contributions for various Document classes for different formats.
|
|
</p>
|
|
<subsection name="RTF->XML->Lucene">
|
|
<table>
|
|
<tr>
|
|
<th>
|
|
URL
|
|
</th>
|
|
<td>
|
|
<a href="http://www.tetrasix.com/">
|
|
http://www.tetrasix.com/
|
|
</a>
|
|
</td>
|
|
</tr>
|
|
<tr>
|
|
<th>
|
|
author
|
|
</th>
|
|
<td>
|
|
N/A
|
|
</td>
|
|
</tr>
|
|
</table>
|
|
</subsection>
|
|
<subsection name="XML Document #1">
|
|
<table>
|
|
<tr>
|
|
<th>
|
|
URL
|
|
</th>
|
|
<td>
|
|
<a href="http://marc.theaimsgroup.com/?l=lucene-dev&m=100723333506246&w=2">
|
|
http://marc.theaimsgroup.com/?l=lucene-dev&m=100723333506246&w=2
|
|
</a>
|
|
</td>
|
|
</tr>
|
|
<tr>
|
|
<th>
|
|
author
|
|
</th>
|
|
<td>
|
|
Philip Ogren - ogren@mayo.edu
|
|
</td>
|
|
</tr>
|
|
</table>
|
|
</subsection>
|
|
<subsection name="XML Document #2">
|
|
<table>
|
|
<tr>
|
|
<th>
|
|
URL
|
|
</th>
|
|
<td>
|
|
<a href="http://www.mail-archive.com/lucene-user@jakarta.apache.org/msg00346.html">
|
|
http://www.mail-archive.com/lucene-user@jakarta.apache.org/msg00346.html
|
|
</a>
|
|
</td>
|
|
</tr>
|
|
<tr>
|
|
<th>
|
|
author
|
|
</th>
|
|
<td>
|
|
Peter Carlson - carlson@bookandhammer.com
|
|
</td>
|
|
</tr>
|
|
</table>
|
|
</subsection>
|
|
<subsection name="XML Document #3">
|
|
<table>
|
|
<tr>
|
|
<th>
|
|
URL
|
|
</th>
|
|
<td>
|
|
<a href="http://www.isogen.com/papers/lucene_xml_indexing.html">
|
|
http://www.isogen.com/papers/lucene_xml_indexing.html
|
|
</a>
|
|
</td>
|
|
</tr>
|
|
<tr>
|
|
<th>
|
|
author
|
|
</th>
|
|
<td>
|
|
W. Eliot Kimber - eliot@isogen.com
|
|
</td>
|
|
</tr>
|
|
</table>
|
|
</subsection>
|
|
<subsection name="XPDF - PDF Document Conversion">
|
|
<table>
|
|
<tr>
|
|
<th>
|
|
URL
|
|
</th>
|
|
<td>
|
|
<a href="http://www.foolabs.com/xpdf">
|
|
http://www.foolabs.com/xpdf
|
|
</a>
|
|
</td>
|
|
</tr>
|
|
<tr>
|
|
<th>
|
|
author
|
|
</th>
|
|
<td>
|
|
N/A
|
|
</td>
|
|
</tr>
|
|
</table>
|
|
</subsection>
|
|
<subsection name="PJ - PDF Document Conversion">
|
|
<table>
|
|
<tr>
|
|
<th>
|
|
URL
|
|
</th>
|
|
<td>
|
|
<a href=" http://www.etymon.com/pj/">
|
|
http://www.etymon.com/pj/
|
|
</a>
|
|
</td>
|
|
</tr>
|
|
<tr>
|
|
<th>
|
|
author
|
|
</th>
|
|
<td>
|
|
N/A
|
|
</td>
|
|
</tr>
|
|
</table>
|
|
</subsection>
|
|
<subsection name="PDF Parser">
|
|
<table>
|
|
<tr>
|
|
<th>
|
|
URL
|
|
</th>
|
|
<td>
|
|
<a href="http://www.csh.rit.edu/~ben/projects/pdfparser/">
|
|
http://www.csh.rit.edu/~ben/projects/pdfparser/
|
|
</a>
|
|
</td>
|
|
</tr>
|
|
<tr>
|
|
<th>
|
|
author
|
|
</th>
|
|
<td>
|
|
Ben Litchfield - ben@csh.rit.edu
|
|
</td>
|
|
</tr>
|
|
</table>
|
|
</subsection>
|
|
</section>
|
|
<section name="Lucene Analyzers">
|
|
<p>
|
|
</p>
|
|
<subsection name="Chinese Analyzer, Tokenizer, Filter">
|
|
<table>
|
|
<tr>
|
|
<th>
|
|
URL
|
|
</th>
|
|
<td>
|
|
<a href="http://marc.theaimsgroup.com/?l=lucene-dev&m=100705753831746&w=2">
|
|
http://marc.theaimsgroup.com/?l=lucene-dev&m=100705753831746&w=2
|
|
</a>
|
|
</td>
|
|
</tr>
|
|
<tr>
|
|
<th>
|
|
author
|
|
</th>
|
|
<td>
|
|
Yiyi Sun - yiyisun@yahoo.com
|
|
</td>
|
|
</tr>
|
|
</table>
|
|
</subsection>
|
|
</section>
|
|
<section name="Misc">
|
|
<p>
|
|
</p>
|
|
|
|
<subsection name="Term Highlighter">
|
|
<p>
|
|
</p>
|
|
<table>
|
|
<tr>
|
|
<th>
|
|
URL
|
|
</th>
|
|
<td>
|
|
<a href="http://www.iq-computing.de/lucene/highlight.htm">
|
|
http://www.iq-computing.de/lucene/highlight.htm
|
|
</a>
|
|
</td>
|
|
</tr>
|
|
<tr>
|
|
<th>
|
|
author
|
|
</th>
|
|
<td>
|
|
Maik Schreiber - info@iq-computing.de
|
|
</td>
|
|
</tr>
|
|
</table>
|
|
</subsection>
|
|
<subsection name="Chainable Filter">
|
|
<p>
|
|
</p>
|
|
<table>
|
|
<tr>
|
|
<th>
|
|
URL
|
|
</th>
|
|
<td>
|
|
<a href="http://www.mail-archive.com/lucene-user@jakarta.apache.org/msg01168.html">
|
|
http://www.mail-archive.com/lucene-user@jakarta.apache.org/msg01168.html
|
|
</a>
|
|
</td>
|
|
</tr>
|
|
<tr>
|
|
<th>
|
|
author
|
|
</th>
|
|
<td>
|
|
Kelvin Tan - kelvin@relevanz.com
|
|
</td>
|
|
</tr>
|
|
</table>
|
|
</subsection>
|
|
<subsection name="Multiple Field Searching">
|
|
<p>
|
|
</p>
|
|
<table>
|
|
<tr>
|
|
<th>
|
|
URL
|
|
</th>
|
|
<td>
|
|
<a href="http://http://www.mail-archive.com/lucene-user@jakarta.apache.org/msg00775.html">
|
|
http://www.mail-archive.com/lucene-user@jakarta.apache.org/msg00775.html
|
|
</a>
|
|
</td>
|
|
</tr>
|
|
<tr>
|
|
<th>
|
|
author
|
|
</th>
|
|
<td>
|
|
Kelvin Tan - kelvin@relevanz.com
|
|
</td>
|
|
</tr>
|
|
</table>
|
|
</subsection>
|
|
<subsection name="Lucene Tutorial">
|
|
<p>
|
|
</p>
|
|
<table>
|
|
<tr>
|
|
<th>
|
|
URL
|
|
</th>
|
|
<td>
|
|
<a href="http://www.darksleep.com/puff/lucene/lucene.html">
|
|
http://www.darksleep.com/puff/lucene/lucene.html
|
|
</a>
|
|
</td>
|
|
</tr>
|
|
<tr>
|
|
<th>
|
|
author
|
|
</th>
|
|
<td>
|
|
Steven J. Owens - puff@darksleep.com
|
|
</td>
|
|
</tr>
|
|
</table>
|
|
</subsection>
|
|
<subsection name="HTML Syntax Checker and Pretty Printer">
|
|
<p>
|
|
</p>
|
|
<table>
|
|
<tr>
|
|
<th>
|
|
URL
|
|
</th>
|
|
<td>
|
|
<a href="http://lempinen.net/sami/jtidy/">
|
|
http://lempinen.net/sami/jtidy/
|
|
</a>
|
|
</td>
|
|
</tr>
|
|
<tr>
|
|
<th>
|
|
author
|
|
</th>
|
|
<td>
|
|
N/A
|
|
</td>
|
|
</tr>
|
|
</table>
|
|
</subsection>
|
|
<subsection name="JavaCC">
|
|
<table>
|
|
<tr>
|
|
<th>
|
|
URL
|
|
</th>
|
|
<td>
|
|
<a href="http://www.webgain.com/products/java_cc/">
|
|
http://www.webgain.com/products/java_cc/
|
|
</a>
|
|
</td>
|
|
</tr>
|
|
<tr>
|
|
<th>
|
|
author
|
|
</th>
|
|
<td>
|
|
N/A
|
|
</td>
|
|
</tr>
|
|
</table>
|
|
</subsection>
|
|
</section>
|
|
</body>
|
|
</document>
|