FileDocument


1   /*
2    * Copyright  1999-2004 The Apache Software Foundation
3    *
4    *  Licensed under the Apache License, Version 2.0 (the "License");
5    *  you may not use this file except in compliance with the License.
6    *  You may obtain a copy of the License at
7    *
8    *      http://www.apache.org/licenses/LICENSE-2.0
9    *
10   *  Unless required by applicable law or agreed to in writing, software
11   *  distributed under the License is distributed on an "AS IS" BASIS,
12   *  WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
13   *  See the License for the specific language governing permissions and
14   *  limitations under the License.
15   *
16   */
17  
18  /* $Id: FileDocument.java 42598 2004-03-01 16:18:28Z gregor $  */
19  
20  package org.apache.lenya.lucene;
21  
22  import java.io.BufferedReader  ;
23  import java.io.File  ;
24  import java.io.FileInputStream  ;
25  import java.io.InputStreamReader  ;
26  import java.io.Reader  ;
27  
28  import org.apache.lucene.document.DateField;
29  import org.apache.lucene.document.Document;
30  import org.apache.lucene.document.Field;
31  
32  /**
33   * A utility for making Lucene Documents from a File.
34   */
35  public class FileDocument {
36      private FileDocument() {
37      }
38  
39      /**
40       * Makes a document for a File.
41       *
42       * <p>
43       * The document has three fields:
44       *
45       * <ul>
46       * <li>
47       * <code>path</code>--containing the pathname of the file, as a stored, tokenized field;
48       * </li>
49       * <li>
50       * <code>modified</code>--containing the last modified date of the file as a keyword field as
51       * encoded by <a HREF="lucene.document.DateField.html">DateField</a>; and
52       * </li>
53       * <li>
54       * <code>contents</code>--containing the full contents of the file, as a Reader field.
55       * </li>
56       * </ul>
57       * </p>
58       *
59       * @param f DOCUMENT ME!
60       *
61       * @return DOCUMENT ME!
62       *
63       * @throws java.io.FileNotFoundException DOCUMENT ME!
64       */
65      public static Document Document(File   f) throws java.io.FileNotFoundException   {
66          // make a new, empty document
67          Document doc = new Document();
68  
69          // Add the path of the file as a field named "path".  Use a Text field, so
70          // that the index stores the path, and so that the path is searchable
71          doc.add(Field.Text("path", f.getPath()));
72  
73          // Add the last modified date of the file a field named "modified".  Use a
74          // Keyword field, so that it's searchable, but so that no attempt is made
75          // to tokenize the field into words.
76          doc.add(Field.Keyword("modified", DateField.timeToString(f.lastModified())));
77  
78          // Add the contents of the file a field named "contents".  Use a Text
79          // field, specifying a Reader, so that the text of the file is tokenized.
80          // ?? why doesn't FileReader work here ??
81          FileInputStream   is = new FileInputStream  (f);
82          Reader   reader = new BufferedReader  (new InputStreamReader  (is));
83          doc.add(Field.Text("contents", reader));
84  
85          // return the document
86          return doc;
87      }
88  }
89
A to Z: JavaDoc & Examples Daily Java News & Articles Open Source Projects Open Source Codes Free Computer Books Remove Frame
Popular Tags