home | career | drupal | java | mac | mysql | perl | scala | uml | unix  

Lucene example source code file (IndexSplitter.java)

This example Lucene source code file (IndexSplitter.java) is included in the DevDaily.com "Java Source Code Warehouse" project. The intent of this project is to help you "Learn Java by Example" TM.

Java - Lucene tags/keywords

arraylist, decimalformat, exception, file, file, indexsplitter, indexsplitter, io, ioexception, ioexception, list, segmentinfo, segmentinfos, string, string, text, util

The Lucene IndexSplitter.java source code

 * 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,
 * See the License for the specific language governing permissions and
 * limitations under the License.
package org.apache.lucene.index;

import java.io.File;
import java.io.FileInputStream;
import java.io.FileOutputStream;
import java.io.IOException;
import java.io.InputStream;
import java.io.OutputStream;
import java.text.DecimalFormat;
import java.util.ArrayList;
import java.util.List;

import org.apache.lucene.index.IndexWriter;       // javadocs
import org.apache.lucene.store.FSDirectory;

 * Command-line tool that enables listing segments in an
 * index, copying specific segments to another index, and
 * deleting segments from an index.
 * <p>This tool does file-level copying of segments files.
 * This means it's unable to split apart a single segment
 * into multiple segments.  For example if your index is
 * optimized, this tool won't help.  Also, it does basic
 * file-level copying (using simple
 * File{In,Out}putStream) so it will not work with non
 * FSDirectory Directory impls.</p>
 * @lucene.experimental You can easily
 * accidentally remove segments from your index so be
 * careful!
 * <p>NOTE: this tool is unaware of documents added
 * atomically via {@link IndexWriter#addDocuments} or {@link
 * IndexWriter#updateDocuments}, which means it can easily
 * break up such document groups.
public class IndexSplitter {
  public SegmentInfos infos;

  FSDirectory fsDir;

  File dir;

   * @param args
  public static void main(String[] args) throws Exception {
    if (args.length < 2) {
          .println("Usage: IndexSplitter <srcDir> -l (list the segments and their sizes)");
      System.err.println("IndexSplitter <srcDir>  +");
          .println("IndexSplitter <srcDir> -d (delete the following segments)");
    File srcDir = new File(args[0]);
    IndexSplitter is = new IndexSplitter(srcDir);
    if (!srcDir.exists()) {
      throw new Exception("srcdir:" + srcDir.getAbsolutePath()
          + " doesn't exist");
    if (args[1].equals("-l")) {
    } else if (args[1].equals("-d")) {
      List<String> segs = new ArrayList();
      for (int x = 2; x < args.length; x++) {
      is.remove(segs.toArray(new String[0]));
    } else {
      File targetDir = new File(args[1]);
      List<String> segs = new ArrayList();
      for (int x = 2; x < args.length; x++) {
      is.split(targetDir, segs.toArray(new String[0]));

  public IndexSplitter(File dir) throws IOException {
    this.dir = dir;
    fsDir = FSDirectory.open(dir);
    infos = new SegmentInfos();

  public void listSegments() throws IOException {
    DecimalFormat formatter = new DecimalFormat("###,###.###");
    for (int x = 0; x < infos.size(); x++) {
      SegmentInfo info = infos.info(x);
      String sizeStr = formatter.format(info.sizeInBytes(true));
      System.out.println(info.name + " " + sizeStr);

  private int getIdx(String name) {
    for (int x = 0; x < infos.size(); x++) {
      if (name.equals(infos.info(x).name))
        return x;
    return -1;

  private SegmentInfo getInfo(String name) {
    for (int x = 0; x < infos.size(); x++) {
      if (name.equals(infos.info(x).name))
        return infos.info(x);
    return null;

  public void remove(String[] segs) throws IOException {
    for (String n : segs) {
      int idx = getIdx(n);

  public void split(File destDir, String[] segs) throws IOException {
    FSDirectory destFSDir = FSDirectory.open(destDir);
    SegmentInfos destInfos = new SegmentInfos();
    destInfos.counter = infos.counter;
    for (String n : segs) {
      SegmentInfo info = getInfo(n);
      // now copy files over
      List<String> files = info.files();
      for (final String srcName : files) {
        File srcFile = new File(dir, srcName);
        File destFile = new File(destDir, srcName);
        copyFile(srcFile, destFile);
    // System.out.println("destDir:"+destDir.getAbsolutePath());

  private static final byte[] copyBuffer = new byte[32*1024];

  private static void copyFile(File src, File dst) throws IOException {
    InputStream in = new FileInputStream(src);
    OutputStream out = new FileOutputStream(dst);
    int len;
    while ((len = in.read(copyBuffer)) > 0) {
      out.write(copyBuffer, 0, len);

Other Lucene examples (source code examples)

Here is a short list of links related to this Lucene IndexSplitter.java source code file:

my book on functional programming


new blog posts


Copyright 1998-2019 Alvin Alexander, alvinalexander.com
All Rights Reserved.

A percentage of advertising revenue from
pages under the /java/jwarehouse URI on this website is
paid back to open source projects.