alvinalexander.com | career | drupal | java | mac | mysql | perl | scala | uml | unix  

Lucene example source code file (ReaderUtil.java)

This example Lucene source code file (ReaderUtil.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, gather, gather, indexreader, indexreader, io, ioexception, ioexception, list, readerutil, readerutil, util

The Lucene ReaderUtil.java source code

package org.apache.lucene.util;

/**
 * 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.
 */

import java.io.IOException;
import java.util.ArrayList;
import java.util.List;

import org.apache.lucene.index.IndexReader;

/**
 * Common util methods for dealing with {@link IndexReader}s.
 *
 * @lucene.internal
 */
public final class ReaderUtil {

  private ReaderUtil() {} // no instance

  /**
   * Gathers sub-readers from reader into a List.
   * 
   * @param allSubReaders
   * @param reader
   */
  public static void gatherSubReaders(List<IndexReader> allSubReaders, IndexReader reader) {
    IndexReader[] subReaders = reader.getSequentialSubReaders();
    if (subReaders == null) {
      // Add the reader itself, and do not recurse
      allSubReaders.add(reader);
    } else {
      for (int i = 0; i < subReaders.length; i++) {
        gatherSubReaders(allSubReaders, subReaders[i]);
      }
    }
  }

  /** Recursively visits all sub-readers of a reader.  You
   *  should subclass this and override the add method to
   *  gather what you need.
   *
   * @lucene.experimental */
  public static abstract class Gather {
    private final IndexReader topReader;

    public Gather(IndexReader r) {
      topReader = r;
    }

    public int run() throws IOException {
      return run(0, topReader);
    }

    public int run(int docBase) throws IOException {
      return run(docBase, topReader);
    }

    private int run(int base, IndexReader reader) throws IOException {
      IndexReader[] subReaders = reader.getSequentialSubReaders();
      if (subReaders == null) {
        // atomic reader
        add(base, reader);
        base += reader.maxDoc();
      } else {
        // composite reader
        for (int i = 0; i < subReaders.length; i++) {
          base = run(base, subReaders[i]);
        }
      }

      return base;
    }

    protected abstract void add(int base, IndexReader r) throws IOException;
  }

  /**
   * Returns sub IndexReader that contains the given document id.
   *    
   * @param doc id of document
   * @param reader parent reader
   * @return sub reader of parent which contains the specified doc id
   */
  public static IndexReader subReader(int doc, IndexReader reader) {
    List<IndexReader> subReadersList = new ArrayList();
    ReaderUtil.gatherSubReaders(subReadersList, reader);
    IndexReader[] subReaders = subReadersList
        .toArray(new IndexReader[subReadersList.size()]);
    int[] docStarts = new int[subReaders.length];
    int maxDoc = 0;
    for (int i = 0; i < subReaders.length; i++) {
      docStarts[i] = maxDoc;
      maxDoc += subReaders[i].maxDoc();
    }
    return subReaders[ReaderUtil.subIndex(doc, docStarts)];
  }
  
  /**
   * Returns sub-reader subIndex from reader.
   * 
   * @param reader parent reader
   * @param subIndex index of desired sub reader
   * @return the subreader at subIndex
   */
  public static IndexReader subReader(IndexReader reader, int subIndex) {
    List<IndexReader> subReadersList = new ArrayList();
    ReaderUtil.gatherSubReaders(subReadersList, reader);
    IndexReader[] subReaders = subReadersList
        .toArray(new IndexReader[subReadersList.size()]);
    return subReaders[subIndex];
  }


  /**
   * Returns index of the searcher/reader for document <code>n in the
   * array used to construct this searcher/reader.
   */
  public static int subIndex(int n, int[] docStarts) { // find
    // searcher/reader for doc n:
    int size = docStarts.length;
    int lo = 0; // search starts array
    int hi = size - 1; // for first element less than n, return its index
    while (hi >= lo) {
      int mid = (lo + hi) >>> 1;
      int midValue = docStarts[mid];
      if (n < midValue)
        hi = mid - 1;
      else if (n > midValue)
        lo = mid + 1;
      else { // found a match
        while (mid + 1 < size && docStarts[mid + 1] == midValue) {
          mid++; // scan to last match
        }
        return mid;
      }
    }
    return hi;
  }
}

Other Lucene examples (source code examples)

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

... this post is sponsored by my books ...

#1 New Release!

FP Best Seller

 

new blog posts

 

Copyright 1998-2021 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.