org.apache.lucene.demo.IndexFiles Maven / Gradle / Ivy

Go to download
/*
 * Licensed to the Apache Software Foundation (ASF) under one or more
 * contributor license agreements.  See the NOTICE file distributed with
 * this work for additional information regarding copyright ownership.
 * The ASF licenses this file to You under the Apache License, Version 2.0
 * (the "License"); you may not use this file except in compliance with
 * the License.  You may obtain a copy of the License at
 *
 *     http://www.apache.org/licenses/LICENSE-2.0
 *
 * Unless required by applicable law or agreed to in writing, software
 * distributed under the License is distributed on an "AS IS" BASIS,
 * WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
 * See the License for the specific language governing permissions and
 * limitations under the License.
 */
package org.apache.lucene.demo;


import java.io.BufferedReader;
import java.io.IOException;
import java.io.InputStream;
import java.io.InputStreamReader;
import java.nio.charset.StandardCharsets;
import java.nio.file.FileVisitResult;
import java.nio.file.Files;
import java.nio.file.Path;
import java.nio.file.Paths;
import java.nio.file.SimpleFileVisitor;
import java.nio.file.attribute.BasicFileAttributes;
import java.util.Date;

import org.apache.lucene.analysis.Analyzer;
import org.apache.lucene.analysis.standard.StandardAnalyzer;
import org.apache.lucene.document.LongPoint;
import org.apache.lucene.document.Document;
import org.apache.lucene.document.Field;
import org.apache.lucene.document.StringField;
import org.apache.lucene.document.TextField;
import org.apache.lucene.index.IndexWriter;
import org.apache.lucene.index.IndexWriterConfig.OpenMode;
import org.apache.lucene.index.IndexWriterConfig;
import org.apache.lucene.index.Term;
import org.apache.lucene.store.Directory;
import org.apache.lucene.store.FSDirectory;

/** Index all text files under a directory.
 * 
 * This is a command-line application demonstrating simple Lucene indexing.
 * Run it with no command-line arguments for usage information.
 */
public class IndexFiles {
  
  private IndexFiles() {}

  /** Index all text files under a directory. */
  public static void main(String[] args) {
    String usage = "java org.apache.lucene.demo.IndexFiles"
                 + " [-index INDEX_PATH] [-docs DOCS_PATH] [-update]\n\n"
                 + "This indexes the documents in DOCS_PATH, creating a Lucene index"
                 + "in INDEX_PATH that can be searched with SearchFiles";
    String indexPath = "index";
    String docsPath = null;
    boolean create = true;
    for(int i=0;iWriteLineDocTask.
   *  
   * @param writer Writer to the index where the given file/dir info will be stored
   * @param path The file to index, or the directory to recurse into to find files to index
   * @throws IOException If there is a low-level I/O error
   */
  static void indexDocs(final IndexWriter writer, Path path) throws IOException {
    if (Files.isDirectory(path)) {
      Files.walkFileTree(path, new SimpleFileVisitor() {
        @Override
        public FileVisitResult visitFile(Path file, BasicFileAttributes attrs) throws IOException {
          try {
            indexDoc(writer, file, attrs.lastModifiedTime().toMillis());
          } catch (IOException ignore) {
            // don't index files that can't be read.
          }
          return FileVisitResult.CONTINUE;
        }
      });
    } else {
      indexDoc(writer, path, Files.getLastModifiedTime(path).toMillis());
    }
  }

  /** Indexes a single document */
  static void indexDoc(IndexWriter writer, Path file, long lastModified) throws IOException {
    try (InputStream stream = Files.newInputStream(file)) {
      // make a new, empty document
      Document doc = new Document();
      
      // Add the path of the file as a field named "path".  Use a
      // field that is indexed (i.e. searchable), but don't tokenize 
      // the field into separate words and don't index term frequency
      // or positional information:
      Field pathField = new StringField("path", file.toString(), Field.Store.YES);
      doc.add(pathField);
      
      // Add the last modified date of the file a field named "modified".
      // Use a LongPoint that is indexed (i.e. efficiently filterable with
      // PointRangeQuery).  This indexes to milli-second resolution, which
      // is often too fine.  You could instead create a number based on
      // year/month/day/hour/minutes/seconds, down the resolution you require.
      // For example the long value 2011021714 would mean
      // February 17, 2011, 2-3 PM.
      doc.add(new LongPoint("modified", lastModified));
      
      // Add the contents of the file to a field named "contents".  Specify a Reader,
      // so that the text of the file is tokenized and indexed, but not stored.
      // Note that FileReader expects the file to be in UTF-8 encoding.
      // If that's not the case searching for special characters will fail.
      doc.add(new TextField("contents", new BufferedReader(new InputStreamReader(stream, StandardCharsets.UTF_8))));
      
      if (writer.getConfig().getOpenMode() == OpenMode.CREATE) {
        // New index, so we just add the document (no old document can be there):
        System.out.println("adding " + file);
        writer.addDocument(doc);
      } else {
        // Existing index (an old copy of this document may have been indexed) so 
        // we use updateDocument instead to replace the old one matching the exact 
        // path, if present:
        System.out.println("updating " + file);
        writer.updateDocument(new Term("path", file.toString()), doc);
      }
    }
  }
}