documentation/manual/en/module_specs/Zend_Search_Lucene-JavaLucene.xml

   1 <?xml version="1.0" encoding="UTF-8"?>
   2 <!-- Reviewed: no -->
   3 <sect1 id="zend.search.lucene.java-lucene">
   4     <title>Interoperating with Java Lucene</title>
   5
   6     <sect2 id="zend.search.lucene.index-creation.file-formats">
   7         <title>File Formats</title>
   8
   9         <para>
  10             <classname>Zend_Search_Lucene</classname> index file formats are binary compatible with
  11             Java Lucene version 1.4 and greater.
  12         </para>
  13
  14         <para>
  15             A detailed description of this format is available here:
  16             <ulink url="http://lucene.apache.org/java/2_3_0/fileformats.html"/>
  17             <footnote>
  18                 <para>
  19                     The currently supported Lucene index file format version is 2.3 (starting from
  20                     Zend Framework 1.6).
  21                 </para>
  22             </footnote>.
  23         </para>
  24     </sect2>
  25
  26     <sect2 id="zend.search.lucene.index-creation.index-directory">
  27         <title>Index Directory</title>
  28
  29         <para>
  30             After index creation, the index directory will contain several files:
  31         </para>
  32
  33         <itemizedlist>
  34             <listitem>
  35                 <para>
  36                     The <filename>segments</filename> file is a list of index segments.
  37                 </para>
  38             </listitem>
  39
  40             <listitem>
  41                 <para>
  42                     The <filename>*.cfs</filename> files contain index segments.
  43                     Note! An optimized index always has only one segment.
  44                 </para>
  45             </listitem>
  46
  47             <listitem>
  48                 <para>
  49                     The <filename>deletable</filename> file is a list of files that are no longer
  50                     used by the index, but which could not be deleted.
  51                 </para>
  52             </listitem>
  53         </itemizedlist>
  54     </sect2>
  55
  56     <sect2 id="zend.search.lucene.java-lucene.source-code">
  57         <title>Java Source Code</title>
  58
  59         <para>
  60             The Java program listing below provides an example of how to index a file
  61             using Java Lucene:
  62         </para>
  63
  64         <programlisting language="java"><![CDATA[
  65 /**
  66 * Index creation:
  67 */
  68 import org.apache.lucene.index.IndexWriter;
  69 import org.apache.lucene.document.*;
  70
  71 import java.io.*
  72
  73 ...
  74
  75 IndexWriter indexWriter = new IndexWriter("/data/my_index",
  76                                           new SimpleAnalyzer(), true);
  77
  78 ...
  79
  80 String filename = "/path/to/file-to-index.txt"
  81 File f = new File(filename);
  82
  83 Document doc = new Document();
  84 doc.add(Field.Text("path", filename));
  85 doc.add(Field.Keyword("modified",DateField.timeToString(f.lastModified())));
  86 doc.add(Field.Text("author", "unknown"));
  87 FileInputStream is = new FileInputStream(f);
  88 Reader reader = new BufferedReader(new InputStreamReader(is));
  89 doc.add(Field.Text("contents", reader));
  90
  91 indexWriter.addDocument(doc);
  92 ]]></programlisting>
  93     </sect2>
  94 </sect1>
  95 <!--
  96 vim:se ts=4 sw=4 et:
  97 -->