FileDocument


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