mirror of https://github.com/apache/lucene.git
325 lines
13 KiB
HTML
325 lines
13 KiB
HTML
<!DOCTYPE HTML PUBLIC "-//W3C//DTD HTML 4.01 Transitional//EN" "http://www.w3.org/TR/html4/loose.dtd">
|
|
<html>
|
|
<head>
|
|
<META http-equiv="Content-Type" content="text/html; charset=UTF-8">
|
|
<meta content="Apache Forrest" name="Generator">
|
|
<meta name="Forrest-version" content="0.7">
|
|
<meta name="Forrest-skin-name" content="pelt">
|
|
<title>
|
|
Apache Lucene - Basic Demo Sources Walk-through
|
|
</title>
|
|
<link type="text/css" href="skin/basic.css" rel="stylesheet">
|
|
<link media="screen" type="text/css" href="skin/screen.css" rel="stylesheet">
|
|
<link media="print" type="text/css" href="skin/print.css" rel="stylesheet">
|
|
<link type="text/css" href="skin/profile.css" rel="stylesheet">
|
|
<script src="skin/getBlank.js" language="javascript" type="text/javascript"></script><script src="skin/getMenu.js" language="javascript" type="text/javascript"></script><script src="skin/fontsize.js" language="javascript" type="text/javascript"></script>
|
|
<link rel="shortcut icon" href="images/favicon.ico">
|
|
</head>
|
|
<body onload="init()">
|
|
<script type="text/javascript">ndeSetTextSize();</script>
|
|
<div id="top">
|
|
<div class="breadtrail">
|
|
<a href="http://www.apache.org/">Apache</a> > <a href="http://lucene.apache.org/">Lucene</a><script src="skin/breadcrumbs.js" language="JavaScript" type="text/javascript"></script>
|
|
</div>
|
|
<div class="header">
|
|
<div class="grouplogo">
|
|
<a href="http://lucene.apache.org/"><img class="logoImage" alt="Lucene" src="http://www.apache.org/images/asf_logo_simple.png" title="Apache Lucene"></a>
|
|
</div>
|
|
<div class="projectlogo">
|
|
<a href="http://lucene.apache.org/java/"><img class="logoImage" alt="Lucene" src="http://lucene.apache.org/images/lucene_green_300.gif" title="Apache Lucene is a high-performance, full-featured text search engine library written entirely in
|
|
Java. It is a technology suitable for nearly any application that requires full-text search, especially cross-platform."></a>
|
|
</div>
|
|
<div class="searchbox">
|
|
<form action="http://www.google.com/search" method="get" class="roundtopsmall">
|
|
<input value="lucene.apache.org" name="sitesearch" type="hidden"><input onFocus="getBlank (this, 'Search the site with google');" size="25" name="q" id="query" type="text" value="Search the site with google">
|
|
<input attr="value" name="Search" value="Search" type="submit">
|
|
</form>
|
|
</div>
|
|
<ul id="tabs">
|
|
<li class="current">
|
|
<a class="base-selected" href="index.html">Main</a>
|
|
</li>
|
|
<li>
|
|
<a class="base-not-selected" href="http://wiki.apache.org/jakarta-lucene">Wiki</a>
|
|
</li>
|
|
</ul>
|
|
</div>
|
|
</div>
|
|
<div id="main">
|
|
<div id="publishedStrip">
|
|
<div id="level2tabs"></div>
|
|
<script type="text/javascript"><!--
|
|
document.write("<text>Last Published:</text> " + document.lastModified);
|
|
// --></script>
|
|
</div>
|
|
<div class="breadtrail">
|
|
|
|
|
|
</div>
|
|
<div id="menu">
|
|
<div onclick="SwitchMenu('menu_1.1', 'skin/')" id="menu_1.1Title" class="menutitle">About</div>
|
|
<div id="menu_1.1" class="menuitemgroup">
|
|
<div class="menuitem">
|
|
<a href="index.html" title="Welcome to Java Lucene">Overview</a>
|
|
</div>
|
|
<div class="menuitem">
|
|
<a href="features.html">Features</a>
|
|
</div>
|
|
<div class="menuitem">
|
|
<a href="http://wiki.apache.org/jakarta-lucene/PoweredBy">Powered by Lucene</a>
|
|
</div>
|
|
<div class="menuitem">
|
|
<a href="whoweare.html">Who We Are</a>
|
|
</div>
|
|
</div>
|
|
<div onclick="SwitchMenu('menu_1.2', 'skin/')" id="menu_1.2Title" class="menutitle">Documentation</div>
|
|
<div id="menu_1.2" class="menuitemgroup">
|
|
<div class="menuitem">
|
|
<a href="api/">API Docs</a>
|
|
</div>
|
|
<div class="menuitem">
|
|
<a href="benchmarks.html">Benchmarks</a>
|
|
</div>
|
|
<div class="menuitem">
|
|
<a href="contributions.html">Contributions</a>
|
|
</div>
|
|
<div class="menuitem">
|
|
<a href="http://wiki.apache.org/jakarta-lucene/LuceneFAQ">FAQ</a>
|
|
</div>
|
|
<div class="menuitem">
|
|
<a href="fileformats.html">File Formats</a>
|
|
</div>
|
|
<div class="menuitem">
|
|
<a href="gettingstarted.html">Getting Started</a>
|
|
</div>
|
|
<div class="menuitem">
|
|
<a href="lucene-sandbox/index.html">Lucene Sandbox</a>
|
|
</div>
|
|
<div class="menuitem">
|
|
<a href="queryparsersyntax.html">Query Syntax</a>
|
|
</div>
|
|
<div class="menuitem">
|
|
<a href="scoring.html">Scoring</a>
|
|
</div>
|
|
<div class="menuitem">
|
|
<a href="http://wiki.apache.org/jakarta-lucene">Wiki</a>
|
|
</div>
|
|
</div>
|
|
<div onclick="SwitchMenu('menu_1.3', 'skin/')" id="menu_1.3Title" class="menutitle">Resources</div>
|
|
<div id="menu_1.3" class="menuitemgroup">
|
|
<div class="menuitem">
|
|
<a href="developer-resources.html">Developers</a>
|
|
</div>
|
|
<div class="menuitem">
|
|
<a href="http://issues.apache.org/jira/browse/LUCENE">Issue Tracking</a>
|
|
</div>
|
|
<div class="menuitem">
|
|
<a href="mailinglists.html">Mailing Lists</a>
|
|
</div>
|
|
<div class="menuitem">
|
|
<a href="releases.html">Releases</a>
|
|
</div>
|
|
<div class="menuitem">
|
|
<a href="systemrequirements.html">System Requirements</a>
|
|
</div>
|
|
<div class="menuitem">
|
|
<a href="http://svn.apache.org/viewcvs.cgi/lucene/java/">Version Control</a>
|
|
</div>
|
|
</div>
|
|
<div onclick="SwitchMenu('menu_1.4', 'skin/')" id="menu_1.4Title" class="menutitle">Site Versions</div>
|
|
<div id="menu_1.4" class="menuitemgroup">
|
|
<div class="menuitem">
|
|
<a href="./">Main</a>
|
|
</div>
|
|
<div class="menuitem">
|
|
<a href="http://lucene.apache.org/java/1_4_3/">1.4.3</a>
|
|
</div>
|
|
<div class="menuitem">
|
|
<a href="http://lucene.apache.org/java/1_9_0/">1.9.0</a>
|
|
</div>
|
|
<div class="menuitem">
|
|
<a href="http://lucene.apache.org/java/1_9_1/">1.9.1</a>
|
|
</div>
|
|
<div class="menuitem">
|
|
<a href="http://lucene.apache.org/java/2_0_0/">2.0.0</a>
|
|
</div>
|
|
</div>
|
|
<div onclick="SwitchMenu('menu_1.5', 'skin/')" id="menu_1.5Title" class="menutitle">Related Projects</div>
|
|
<div id="menu_1.5" class="menuitemgroup">
|
|
<div class="menuitem">
|
|
<a href="http://lucene.apache.org">Lucene (Top-Level)</a>
|
|
</div>
|
|
<div class="menuitem">
|
|
<a href="http://lucene.apache.org/hadoop/">Hadoop</a>
|
|
</div>
|
|
<div class="menuitem">
|
|
<a href="http://lucene.apache.org/lucy/">Lucy</a>
|
|
</div>
|
|
<div class="menuitem">
|
|
<a href="http://incubator.apache.org/projects/lucene.net.html">Lucene.Net</a>
|
|
</div>
|
|
<div class="menuitem">
|
|
<a href="http://lucene.apache.org/nutch/">Nutch</a>
|
|
</div>
|
|
<div class="menuitem">
|
|
<a href="http://incubator.apache.org/solr/">SOLR</a>
|
|
</div>
|
|
</div>
|
|
<div id="credit"></div>
|
|
<div id="roundbottom">
|
|
<img style="display: none" class="corner" height="15" width="15" alt="" src="skin/images/rc-b-l-15-1body-2menu-3menu.png"></div>
|
|
<div id="credit2"></div>
|
|
</div>
|
|
<div id="content">
|
|
<div title="Portable Document Format" class="pdflink">
|
|
<a class="dida" href="demo2.pdf"><img alt="PDF -icon" src="skin/images/pdfdoc.gif" class="skin"><br>
|
|
PDF</a>
|
|
</div>
|
|
<h1>
|
|
Apache Lucene - Basic Demo Sources Walk-through
|
|
</h1>
|
|
<div id="minitoc-area">
|
|
<ul class="minitoc">
|
|
<li>
|
|
<a href="#About the Code">About the Code</a>
|
|
</li>
|
|
<li>
|
|
<a href="#Location of the source">Location of the source</a>
|
|
</li>
|
|
<li>
|
|
<a href="#IndexFiles">IndexFiles</a>
|
|
</li>
|
|
<li>
|
|
<a href="#Searching Files">Searching Files</a>
|
|
</li>
|
|
<li>
|
|
<a href="#The Web example...">The Web example...</a>
|
|
</li>
|
|
</ul>
|
|
</div>
|
|
|
|
|
|
<a name="N10013"></a><a name="About the Code"></a>
|
|
<h2 class="boxed">About the Code</h2>
|
|
<div class="section">
|
|
<p>
|
|
In this section we walk through the sources behind the command-line Lucene demo: where to find them,
|
|
their parts and their function. This section is intended for Java developers wishing to understand
|
|
how to use Lucene in their applications.
|
|
</p>
|
|
</div>
|
|
|
|
|
|
|
|
<a name="N1001C"></a><a name="Location of the source"></a>
|
|
<h2 class="boxed">Location of the source</h2>
|
|
<div class="section">
|
|
<p>
|
|
Relative to the directory created when you extracted Lucene or retrieved it from Subversion, you
|
|
should see a directory called <span class="codefrag">src</span> which in turn contains a directory called
|
|
<span class="codefrag">demo</span>. This is the root for all of the Lucene demos. Under this directory is
|
|
<span class="codefrag">org/apache/lucene/demo</span>. This is where all the Java sources for the demos live.
|
|
</p>
|
|
<p>
|
|
Within this directory you should see the <span class="codefrag">IndexFiles.java</span> class we executed earlier.
|
|
Bring it up in <span class="codefrag">vi</span> or your editor of choice and let's take a look at it.
|
|
</p>
|
|
</div>
|
|
|
|
|
|
<a name="N10037"></a><a name="IndexFiles"></a>
|
|
<h2 class="boxed">IndexFiles</h2>
|
|
<div class="section">
|
|
<p>
|
|
As we discussed in the previous walk-through, the <span class="codefrag">IndexFiles</span> class creates a Lucene
|
|
Index. Let's take a look at how it does this.
|
|
</p>
|
|
<p>
|
|
The first substantial thing the <span class="codefrag">main</span> function does is instantiate <span class="codefrag">IndexWriter</span>. It passes the string
|
|
"<span class="codefrag">index</span>" and a new instance of a class called <span class="codefrag">StandardAnalyzer</span>.
|
|
The "<span class="codefrag">index</span>" string is the name of the filesystem directory where all index information
|
|
should be stored. Because we're not passing a full path, this will be created as a subdirectory of
|
|
the current working directory (if it does not already exist). On some platforms, it may be created
|
|
in other directories (such as the user's home directory).
|
|
</p>
|
|
<p>
|
|
The <span class="codefrag">IndexWriter</span> is the main
|
|
class responsible for creating indices. To use it you must instantiate it with a path that it can
|
|
write the index into. If this path does not exist it will first create it. Otherwise it will
|
|
refresh the index at that path. You can also create an index using one of the subclasses of <span class="codefrag">Directory</span>. In any case, you must also pass an
|
|
instance of <span class="codefrag">org.apache.lucene.analysis.Analyzer</span>.
|
|
</p>
|
|
<p>
|
|
The particular <span class="codefrag">Analyzer</span> we
|
|
are using, <span class="codefrag">StandardAnalyzer</span>, is
|
|
little more than a standard Java Tokenizer, converting all strings to lowercase and filtering out
|
|
useless words and characters from the index. By useless words and characters I mean common language
|
|
words such as articles (a, an, the, etc.) and other strings that would be useless for searching
|
|
(e.g. <b>'s</b>) . It should be noted that there are different rules for every language, and you
|
|
should use the proper analyzer for each. Lucene currently provides Analyzers for a number of
|
|
different languages (see the <span class="codefrag">*Analyzer.java</span> sources under <a href="http://svn.apache.org/repos/asf/lucene/java/trunk/contrib/analyzers/src/java/org/apache/lucene/analysis/">contrib/analyzers/src/java/org/apache/lucene/analysis</a>).
|
|
</p>
|
|
<p>
|
|
Looking further down in the file, you should see the <span class="codefrag">indexDocs()</span> code. This recursive
|
|
function simply crawls the directories and uses <span class="codefrag">FileDocument</span> to create <span class="codefrag">Document</span> objects. The <span class="codefrag">Document</span> is simply a data object to
|
|
represent the content in the file as well as its creation time and location. These instances are
|
|
added to the <span class="codefrag">indexWriter</span>. Take a look inside <span class="codefrag">FileDocument</span>. It's not particularly
|
|
complicated. It just adds fields to the <span class="codefrag">Document</span>.
|
|
</p>
|
|
<p>
|
|
As you can see there isn't much to creating an index. The devil is in the details. You may also
|
|
wish to examine the other samples in this directory, particularly the <span class="codefrag">IndexHTML</span> class. It is a bit more
|
|
complex but builds upon this example.
|
|
</p>
|
|
</div>
|
|
|
|
|
|
<a name="N100AE"></a><a name="Searching Files"></a>
|
|
<h2 class="boxed">Searching Files</h2>
|
|
<div class="section">
|
|
<p>
|
|
The <span class="codefrag">SearchFiles</span> class is
|
|
quite simple. It primarily collaborates with an <span class="codefrag">IndexSearcher</span>, <span class="codefrag">StandardAnalyzer</span>
|
|
(which is used in the <span class="codefrag">IndexFiles</span> class as well) and a
|
|
<span class="codefrag">QueryParser</span>. The
|
|
query parser is constructed with an analyzer used to interpret your query text in the same way the
|
|
documents are interpreted: finding the end of words and removing useless words like 'a', 'an' and
|
|
'the'. The <span class="codefrag">Query</span> object contains
|
|
the results from the <span class="codefrag">QueryParser</span> which is passed to
|
|
the searcher. Note that it's also possible to programmatically construct a rich <span class="codefrag">Query</span> object without using the query
|
|
parser. The query parser just enables decoding the <a href="queryparsersyntax.html">Lucene query
|
|
syntax</a> into the corresponding <span class="codefrag">Query</span> object. The searcher results are
|
|
returned in a collection of Documents called <span class="codefrag">Hits</span> which is then iterated through and
|
|
displayed to the user.
|
|
</p>
|
|
</div>
|
|
|
|
|
|
<a name="N100ED"></a><a name="The Web example..."></a>
|
|
<h2 class="boxed">The Web example...</h2>
|
|
<div class="section">
|
|
<p>
|
|
|
|
<a href="demo3.html">read on>>></a>
|
|
|
|
</p>
|
|
</div>
|
|
|
|
|
|
</div>
|
|
<div class="clearboth"> </div>
|
|
</div>
|
|
<div id="footer">
|
|
<div class="lastmodified">
|
|
<script type="text/javascript"><!--
|
|
document.write("<text>Last Published:</text> " + document.lastModified);
|
|
// --></script>
|
|
</div>
|
|
<div class="copyright">
|
|
Copyright ©
|
|
2006 <a href="http://www.apache.org/licenses/">The Apache Software Foundation.</a>
|
|
</div>
|
|
</div>
|
|
</body>
|
|
</html>
|