mirror of https://github.com/apache/lucene.git
414 lines
15 KiB
HTML
414 lines
15 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="0.8">
|
|
<meta name="Forrest-skin-name" content="lucene">
|
|
<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">
|
|
<!--+
|
|
|breadtrail
|
|
+-->
|
|
<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>
|
|
<!--+
|
|
|header
|
|
+-->
|
|
<div class="header">
|
|
<!--+
|
|
|start group logo
|
|
+-->
|
|
<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>
|
|
<!--+
|
|
|end group logo
|
|
+-->
|
|
<!--+
|
|
|start Project Logo
|
|
+-->
|
|
<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>
|
|
<!--+
|
|
|end Project Logo
|
|
+-->
|
|
<!--+
|
|
|start Search
|
|
+-->
|
|
<div class="searchbox">
|
|
<form action="http://search.lucidimagination.com/p:lucene" method="get" class="roundtopsmall">
|
|
<input onFocus="getBlank (this, 'Search the site with Lucene');" size="25" name="q" id="query" type="text" value="Search the site with Lucene">
|
|
<input name="Search" value="Search" type="submit">
|
|
</form>
|
|
<div style="position: relative; top: -5px; left: -10px">Powered by <a href="http://www.lucidimagination.com" style="color: #033268">Lucid Imagination</a>
|
|
</div>
|
|
</div>
|
|
<!--+
|
|
|end search
|
|
+-->
|
|
<!--+
|
|
|start Tabs
|
|
+-->
|
|
<ul id="tabs">
|
|
<li class="current">
|
|
<a class="selected" href="http://lucene.apache.org/java/docs/">Main</a>
|
|
</li>
|
|
<li>
|
|
<a class="unselected" href="http://wiki.apache.org/lucene-java">Wiki</a>
|
|
</li>
|
|
<li class="current">
|
|
<a class="selected" href="index.html">Lucene 2.9 Documentation</a>
|
|
</li>
|
|
</ul>
|
|
<!--+
|
|
|end Tabs
|
|
+-->
|
|
</div>
|
|
</div>
|
|
<div id="main">
|
|
<div id="publishedStrip">
|
|
<!--+
|
|
|start Subtabs
|
|
+-->
|
|
<div id="level2tabs"></div>
|
|
<!--+
|
|
|end Endtabs
|
|
+-->
|
|
<script type="text/javascript"><!--
|
|
document.write("Last Published: " + document.lastModified);
|
|
// --></script>
|
|
</div>
|
|
<!--+
|
|
|breadtrail
|
|
+-->
|
|
<div class="breadtrail">
|
|
|
|
|
|
</div>
|
|
<!--+
|
|
|start Menu, mainarea
|
|
+-->
|
|
<!--+
|
|
|start Menu
|
|
+-->
|
|
<div id="menu">
|
|
<div onclick="SwitchMenu('menu_1.1', 'skin/')" id="menu_1.1Title" class="menutitle">Documentation</div>
|
|
<div id="menu_1.1" class="menuitemgroup">
|
|
<div class="menuitem">
|
|
<a href="index.html">Overview</a>
|
|
</div>
|
|
<div onclick="SwitchMenu('menu_1.1.2', 'skin/')" id="menu_1.1.2Title" class="menutitle">Javadocs</div>
|
|
<div id="menu_1.1.2" class="menuitemgroup">
|
|
<div class="menuitem">
|
|
<a href="api/all/index.html">All</a>
|
|
</div>
|
|
<div class="menuitem">
|
|
<a href="api/core/index.html">Core</a>
|
|
</div>
|
|
<div class="menuitem">
|
|
<a href="api/demo/index.html">Demo</a>
|
|
</div>
|
|
<div onclick="SwitchMenu('menu_1.1.2.4', 'skin/')" id="menu_1.1.2.4Title" class="menutitle">Contrib</div>
|
|
<div id="menu_1.1.2.4" class="menuitemgroup">
|
|
<div class="menuitem">
|
|
<a href="api/contrib-analyzers/index.html">Analyzers</a>
|
|
</div>
|
|
<div class="menuitem">
|
|
<a href="api/contrib-smartcn/index.html">Smart Chinese Analyzer</a>
|
|
</div>
|
|
<div class="menuitem">
|
|
<a href="api/contrib-ant/index.html">Ant</a>
|
|
</div>
|
|
<div class="menuitem">
|
|
<a href="api/contrib-bdb/index.html">Bdb</a>
|
|
</div>
|
|
<div class="menuitem">
|
|
<a href="api/contrib-bdb-je/index.html">Bdb-je</a>
|
|
</div>
|
|
<div class="menuitem">
|
|
<a href="api/contrib-benchmark/index.html">Benchmark</a>
|
|
</div>
|
|
<div class="menuitem">
|
|
<a href="api/contrib-collation/index.html">Collation</a>
|
|
</div>
|
|
<div class="menuitem">
|
|
<a href="api/contrib-fast-vector-highlighter/index.html">Fast Vector Highlighter</a>
|
|
</div>
|
|
<div class="menuitem">
|
|
<a href="api/contrib-highlighter/index.html">Highlighter</a>
|
|
</div>
|
|
<div class="menuitem">
|
|
<a href="api/contrib-instantiated/index.html">Instantiated</a>
|
|
</div>
|
|
<div class="menuitem">
|
|
<a href="api/contrib-lucli/index.html">Lucli</a>
|
|
</div>
|
|
<div class="menuitem">
|
|
<a href="api/contrib-memory/index.html">Memory</a>
|
|
</div>
|
|
<div class="menuitem">
|
|
<a href="api/contrib-misc/index.html">Miscellaneous</a>
|
|
</div>
|
|
<div class="menuitem">
|
|
<a href="api/contrib-queries/index.html">Queries</a>
|
|
</div>
|
|
<div class="menuitem">
|
|
<a href="api/contrib-queryparser/index.html">Query Parser Framework</a>
|
|
</div>
|
|
<div class="menuitem">
|
|
<a href="api/contrib-regex/index.html">Regex</a>
|
|
</div>
|
|
<div class="menuitem">
|
|
<a href="api/contrib-remote/index.html">Remote</a>
|
|
</div>
|
|
<div class="menuitem">
|
|
<a href="api/contrib-snowball/index.html">Snowball</a>
|
|
</div>
|
|
<div class="menuitem">
|
|
<a href="api/contrib-spatial/index.html">Spatial</a>
|
|
</div>
|
|
<div class="menuitem">
|
|
<a href="api/contrib-spellchecker/index.html">Spellchecker</a>
|
|
</div>
|
|
<div class="menuitem">
|
|
<a href="api/contrib-surround/index.html">Surround</a>
|
|
</div>
|
|
<div class="menuitem">
|
|
<a href="api/contrib-swing/index.html">Swing</a>
|
|
</div>
|
|
<div class="menuitem">
|
|
<a href="api/contrib-wikipedia/index.html">Wikipedia</a>
|
|
</div>
|
|
<div class="menuitem">
|
|
<a href="api/contrib-wordnet/index.html">Wordnet</a>
|
|
</div>
|
|
<div class="menuitem">
|
|
<a href="api/contrib-xml-query-parser/index.html">XML Query Parser</a>
|
|
</div>
|
|
</div>
|
|
</div>
|
|
<div class="menuitem">
|
|
<a href="contributions.html">Contributions</a>
|
|
</div>
|
|
<div class="menuitem">
|
|
<a href="http://wiki.apache.org/lucene-java/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/lucene-java">Wiki</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>
|
|
<!--+
|
|
|alternative credits
|
|
+-->
|
|
<div id="credit2"></div>
|
|
</div>
|
|
<!--+
|
|
|end Menu
|
|
+-->
|
|
<!--+
|
|
|start content
|
|
+-->
|
|
<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 <a href="api/demo/org/apache/lucene/demo/IndexFiles.html">IndexFiles</a> 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 <a href="api/core/org/apache/lucene/index/IndexWriter.html">IndexWriter</a>. It passes the string
|
|
"<span class="codefrag">index</span>" and a new instance of a class called <a href="api/core/org/apache/lucene/analysis/standard/StandardAnalyzer.html">StandardAnalyzer</a>.
|
|
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 <a href="api/core/org/apache/lucene/index/IndexWriter.html">IndexWriter</a> 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 <a href="api/core/org/apache/lucene/store/Directory.html">Directory</a>. In any case, you must also pass an
|
|
instance of <a href="api/core/org/apache/lucene/analysis/Analyzer.html">org.apache.lucene.analysis.Analyzer</a>.
|
|
</p>
|
|
<p>
|
|
The particular <a href="api/core/org/apache/lucene/analysis/Analyzer.html">Analyzer</a> we
|
|
are using, <a href="api/core/org/apache/lucene/analysis/standard/StandardAnalyzer.html">StandardAnalyzer</a>, is
|
|
little more than a standard Java Tokenizer, converting all strings to lowercase and filtering out
|
|
stop words and characters from the index. By stop words and characters I mean common language
|
|
words such as articles (a, an, the, etc.) and other strings that may have less value 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/common/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 <a href="api/demo/org/apache/lucene/demo/FileDocument.html">FileDocument</a> to create <a href="api/core/org/apache/lucene/document/Document.html">Document</a> objects. The <a href="api/core/org/apache/lucene/document/Document.html">Document</a> 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 <a href="api/demo/org/apache/lucene/demo/FileDocument.html">FileDocument</a>. It's not particularly
|
|
complicated. It just adds fields to the <a href="api/core/org/apache/lucene/document/Document.html">Document</a>.
|
|
</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 <a href="api/demo/org/apache/lucene/demo/IndexHTML.html">IndexHTML</a> class. It is a bit more
|
|
complex but builds upon this example.
|
|
</p>
|
|
</div>
|
|
|
|
|
|
<a name="N100A0"></a><a name="Searching Files"></a>
|
|
<h2 class="boxed">Searching Files</h2>
|
|
<div class="section">
|
|
<p>
|
|
The <a href="api/demo/org/apache/lucene/demo/SearchFiles.html">SearchFiles</a> class is
|
|
quite simple. It primarily collaborates with an <a href="api/core/org/apache/lucene/search/IndexSearcher.html">IndexSearcher</a>, <a href="api/core/org/apache/lucene/analysis/standard/StandardAnalyzer.html">StandardAnalyzer</a>
|
|
(which is used in the <a href="api/core/org/apache/lucene/demo/IndexFiles.html">IndexFiles</a> class as well) and a
|
|
<a href="api/core/org/apache/lucene/queryParser/QueryParser.html">QueryParser</a>. 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 <a href="api/core/org/apache/lucene/search/Query.html">Query</a> object contains
|
|
the results from the <a href="api/core/org/apache/lucene/queryParser/QueryParser.html">QueryParser</a> which is passed to
|
|
the searcher. Note that it's also possible to programmatically construct a rich <a href="api/core/org/apache/lucene/search/Query.html">Query</a> object without using the query
|
|
parser. The query parser just enables decoding the <a href="queryparsersyntax.html">Lucene query
|
|
syntax</a> into the corresponding <a href="api/core/org/apache/lucene/search/Query.html">Query</a> object. Search can be executed in
|
|
two different ways:
|
|
<ul>
|
|
|
|
<li>Streaming: A <a href="api/core/org/apache/lucene/search/Collector.html">Collector</a> subclass
|
|
simply prints out the document ID and score for each matching document.</li>
|
|
|
|
<li>Paging: Using a <a href="api/core/org/apache/lucene/search/TopScoreDocCollector.html">TopScoreDocCollector</a>
|
|
the search results are printed in pages, sorted by score (i. e. relevance).</li>
|
|
|
|
</ul>
|
|
|
|
</p>
|
|
</div>
|
|
|
|
|
|
<a name="N100E2"></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>
|
|
<!--+
|
|
|end content
|
|
+-->
|
|
<div class="clearboth"> </div>
|
|
</div>
|
|
<div id="footer">
|
|
<!--+
|
|
|start bottomstrip
|
|
+-->
|
|
<div class="lastmodified">
|
|
<script type="text/javascript"><!--
|
|
document.write("Last Published: " + document.lastModified);
|
|
// --></script>
|
|
</div>
|
|
<div class="copyright">
|
|
Copyright ©
|
|
2006 <a href="http://www.apache.org/licenses/">The Apache Software Foundation.</a>
|
|
</div>
|
|
<!--+
|
|
|end bottomstrip
|
|
+-->
|
|
</div>
|
|
</body>
|
|
</html>
|