001/*
002 * Licensed to the Apache Software Foundation (ASF) under one or more
003 * contributor license agreements.  See the NOTICE file distributed with
004 * this work for additional information regarding copyright ownership.
005 * The ASF licenses this file to You under the Apache License, Version 2.0
006 * (the "License"); you may not use this file except in compliance with
007 * the License.  You may obtain a copy of the License at
008 *
009 *     http://www.apache.org/licenses/LICENSE-2.0
010 *
011 * Unless required by applicable law or agreed to in writing, software
012 * distributed under the License is distributed on an "AS IS" BASIS,
013 * WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
014 * See the License for the specific language governing permissions and
015 * limitations under the License.
016 */
017package org.apache.lucene.demo;
018
019
020import java.io.BufferedReader;
021import java.io.IOException;
022import java.io.InputStream;
023import java.io.InputStreamReader;
024import java.nio.charset.StandardCharsets;
025import java.nio.file.FileVisitResult;
026import java.nio.file.Files;
027import java.nio.file.Path;
028import java.nio.file.Paths;
029import java.nio.file.SimpleFileVisitor;
030import java.nio.file.attribute.BasicFileAttributes;
031import java.util.Date;
032
033import org.apache.lucene.analysis.Analyzer;
034import org.apache.lucene.analysis.standard.StandardAnalyzer;
035import org.apache.lucene.document.LongPoint;
036import org.apache.lucene.document.Document;
037import org.apache.lucene.document.Field;
038import org.apache.lucene.document.StringField;
039import org.apache.lucene.document.TextField;
040import org.apache.lucene.index.IndexWriter;
041import org.apache.lucene.index.IndexWriterConfig.OpenMode;
042import org.apache.lucene.index.IndexWriterConfig;
043import org.apache.lucene.index.Term;
044import org.apache.lucene.store.Directory;
045import org.apache.lucene.store.FSDirectory;
046
047/** Index all text files under a directory.
048 * <p>
049 * This is a command-line application demonstrating simple Lucene indexing.
050 * Run it with no command-line arguments for usage information.
051 */
052public class IndexFiles {
053  
054  private IndexFiles() {}
055
056  /** Index all text files under a directory. */
057  public static void main(String[] args) {
058    String usage = "java org.apache.lucene.demo.IndexFiles"
059                 + " [-index INDEX_PATH] [-docs DOCS_PATH] [-update]\n\n"
060                 + "This indexes the documents in DOCS_PATH, creating a Lucene index"
061                 + "in INDEX_PATH that can be searched with SearchFiles";
062    String indexPath = "index";
063    String docsPath = null;
064    boolean create = true;
065    for(int i=0;i<args.length;i++) {
066      if ("-index".equals(args[i])) {
067        indexPath = args[i+1];
068        i++;
069      } else if ("-docs".equals(args[i])) {
070        docsPath = args[i+1];
071        i++;
072      } else if ("-update".equals(args[i])) {
073        create = false;
074      }
075    }
076
077    if (docsPath == null) {
078      System.err.println("Usage: " + usage);
079      System.exit(1);
080    }
081
082    final Path docDir = Paths.get(docsPath);
083    if (!Files.isReadable(docDir)) {
084      System.out.println("Document directory '" +docDir.toAbsolutePath()+ "' does not exist or is not readable, please check the path");
085      System.exit(1);
086    }
087    
088    Date start = new Date();
089    try {
090      System.out.println("Indexing to directory '" + indexPath + "'...");
091
092      Directory dir = FSDirectory.open(Paths.get(indexPath));
093      Analyzer analyzer = new StandardAnalyzer();
094      IndexWriterConfig iwc = new IndexWriterConfig(analyzer);
095
096      if (create) {
097        // Create a new index in the directory, removing any
098        // previously indexed documents:
099        iwc.setOpenMode(OpenMode.CREATE);
100      } else {
101        // Add new documents to an existing index:
102        iwc.setOpenMode(OpenMode.CREATE_OR_APPEND);
103      }
104
105      // Optional: for better indexing performance, if you
106      // are indexing many documents, increase the RAM
107      // buffer.  But if you do this, increase the max heap
108      // size to the JVM (eg add -Xmx512m or -Xmx1g):
109      //
110      // iwc.setRAMBufferSizeMB(256.0);
111
112      IndexWriter writer = new IndexWriter(dir, iwc);
113      indexDocs(writer, docDir);
114
115      // NOTE: if you want to maximize search performance,
116      // you can optionally call forceMerge here.  This can be
117      // a terribly costly operation, so generally it's only
118      // worth it when your index is relatively static (ie
119      // you're done adding documents to it):
120      //
121      // writer.forceMerge(1);
122
123      writer.close();
124
125      Date end = new Date();
126      System.out.println(end.getTime() - start.getTime() + " total milliseconds");
127
128    } catch (IOException e) {
129      System.out.println(" caught a " + e.getClass() +
130       "\n with message: " + e.getMessage());
131    }
132  }
133
134  /**
135   * Indexes the given file using the given writer, or if a directory is given,
136   * recurses over files and directories found under the given directory.
137   * 
138   * NOTE: This method indexes one document per input file.  This is slow.  For good
139   * throughput, put multiple documents into your input file(s).  An example of this is
140   * in the benchmark module, which can create "line doc" files, one document per line,
141   * using the
142   * <a href="../../../../../contrib-benchmark/org/apache/lucene/benchmark/byTask/tasks/WriteLineDocTask.html"
143   * >WriteLineDocTask</a>.
144   *  
145   * @param writer Writer to the index where the given file/dir info will be stored
146   * @param path The file to index, or the directory to recurse into to find files to index
147   * @throws IOException If there is a low-level I/O error
148   */
149  static void indexDocs(final IndexWriter writer, Path path) throws IOException {
150    if (Files.isDirectory(path)) {
151      Files.walkFileTree(path, new SimpleFileVisitor<Path>() {
152        @Override
153        public FileVisitResult visitFile(Path file, BasicFileAttributes attrs) throws IOException {
154          try {
155            indexDoc(writer, file, attrs.lastModifiedTime().toMillis());
156          } catch (IOException ignore) {
157            // don't index files that can't be read.
158          }
159          return FileVisitResult.CONTINUE;
160        }
161      });
162    } else {
163      indexDoc(writer, path, Files.getLastModifiedTime(path).toMillis());
164    }
165  }
166
167  /** Indexes a single document */
168  static void indexDoc(IndexWriter writer, Path file, long lastModified) throws IOException {
169    try (InputStream stream = Files.newInputStream(file)) {
170      // make a new, empty document
171      Document doc = new Document();
172      
173      // Add the path of the file as a field named "path".  Use a
174      // field that is indexed (i.e. searchable), but don't tokenize 
175      // the field into separate words and don't index term frequency
176      // or positional information:
177      Field pathField = new StringField("path", file.toString(), Field.Store.YES);
178      doc.add(pathField);
179      
180      // Add the last modified date of the file a field named "modified".
181      // Use a LongPoint that is indexed (i.e. efficiently filterable with
182      // PointRangeQuery).  This indexes to milli-second resolution, which
183      // is often too fine.  You could instead create a number based on
184      // year/month/day/hour/minutes/seconds, down the resolution you require.
185      // For example the long value 2011021714 would mean
186      // February 17, 2011, 2-3 PM.
187      doc.add(new LongPoint("modified", lastModified));
188      
189      // Add the contents of the file to a field named "contents".  Specify a Reader,
190      // so that the text of the file is tokenized and indexed, but not stored.
191      // Note that FileReader expects the file to be in UTF-8 encoding.
192      // If that's not the case searching for special characters will fail.
193      doc.add(new TextField("contents", new BufferedReader(new InputStreamReader(stream, StandardCharsets.UTF_8))));
194      
195      if (writer.getConfig().getOpenMode() == OpenMode.CREATE) {
196        // New index, so we just add the document (no old document can be there):
197        System.out.println("adding " + file);
198        writer.addDocument(doc);
199      } else {
200        // Existing index (an old copy of this document may have been indexed) so 
201        // we use updateDocument instead to replace the old one matching the exact 
202        // path, if present:
203        System.out.println("updating " + file);
204        writer.updateDocument(new Term("path", file.toString()), doc);
205      }
206    }
207  }
208}