1   package org.apache.lucene.demo;
    2   
    3   /**
    4    * Licensed to the Apache Software Foundation (ASF) under one or more
    5    * contributor license agreements.  See the NOTICE file distributed with
    6    * this work for additional information regarding copyright ownership.
    7    * The ASF licenses this file to You under the Apache License, Version 2.0
    8    * (the "License"); you may not use this file except in compliance with
    9    * the License.  You may obtain a copy of the License at
   10    *
   11    *     http://www.apache.org/licenses/LICENSE-2.0
   12    *
   13    * Unless required by applicable law or agreed to in writing, software
   14    * distributed under the License is distributed on an "AS IS" BASIS,
   15    * WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
   16    * See the License for the specific language governing permissions and
   17    * limitations under the License.
   18    */
   19   
   20   import java.io.File;
   21   import java.io.FileReader;
   22   
   23   import org.apache.lucene.document.DateTools;
   24   import org.apache.lucene.document.Document;
   25   import org.apache.lucene.document.Field;
   26   
   27   /** A utility for making Lucene Documents from a File. */
   28   
   29   public class FileDocument {
   30     /** Makes a document for a File.
   31       <p>
   32       The document has three fields:
   33       <ul>
   34       <li><code>path</code>--containing the pathname of the file, as a stored,
   35       untokenized field;
   36       <li><code>modified</code>--containing the last modified date of the file as
   37       a field as created by <a
   38       href="lucene.document.DateTools.html">DateTools</a>; and
   39       <li><code>contents</code>--containing the full contents of the file, as a
   40       Reader field;
   41       */
   42     public static Document Document(File f)
   43          throws java.io.FileNotFoundException {
   44   	 
   45       // make a new, empty document
   46       Document doc = new Document();
   47   
   48       // Add the path of the file as a field named "path".  Use a field that is 
   49       // indexed (i.e. searchable), but don't tokenize the field into words.
   50       doc.add(new Field("path", f.getPath(), Field.Store.YES, Field.Index.NOT_ANALYZED));
   51   
   52       // Add the last modified date of the file a field named "modified".  Use 
   53       // a field that is indexed (i.e. searchable), but don't tokenize the field
   54       // into words.
   55       doc.add(new Field("modified",
   56           DateTools.timeToString(f.lastModified(), DateTools.Resolution.MINUTE),
   57           Field.Store.YES, Field.Index.NOT_ANALYZED));
   58   
   59       // Add the contents of the file to a field named "contents".  Specify a Reader,
   60       // so that the text of the file is tokenized and indexed, but not stored.
   61       // Note that FileReader expects the file to be in the system's default encoding.
   62       // If that's not the case searching for special characters will fail.
   63       doc.add(new Field("contents", new FileReader(f)));
   64   
   65       // return the document
   66       return doc;
   67     }
   68   
   69     private FileDocument() {}
   70   }