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

Lucene example source code file (SegmentTermPositions.java)

This example Lucene source code file (SegmentTermPositions.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

either, indexinput, indexinput, io, ioexception, ioexception, override, override, segmenttermdocs, segmenttermpositions, segmenttermpositions, term, termpositions, unsupportedoperationexception, use

The Lucene SegmentTermPositions.java source code

package org.apache.lucene.index;

 * 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.

import org.apache.lucene.store.IndexInput;

import java.io.IOException;

final class SegmentTermPositions
extends SegmentTermDocs implements TermPositions {
  private IndexInput proxStream;
  private int proxCount;
  private int position;
  // the current payload length
  private int payloadLength;
  // indicates whether the payload of the current position has
  // been read from the proxStream yet
  private boolean needToLoadPayload;
  // these variables are being used to remember information
  // for a lazy skip
  private long lazySkipPointer = -1;
  private int lazySkipProxCount = 0;
  SegmentTermPositions(SegmentReader p) {
    this.proxStream = null;  // the proxStream will be cloned lazily when nextPosition() is called for the first time

  final void seek(TermInfo ti, Term term) throws IOException {
    super.seek(ti, term);
    if (ti != null)
      lazySkipPointer = ti.proxPointer;
    lazySkipProxCount = 0;
    proxCount = 0;
    payloadLength = 0;
    needToLoadPayload = false;

  public final void close() throws IOException {
    if (proxStream != null) proxStream.close();

  public final int nextPosition() throws IOException {
    if (currentFieldOmitTermFreqAndPositions)
      // This field does not store term freq, positions, payloads
      return 0;
    // perform lazy skips if necessary
    return position += readDeltaPosition();

  private final int readDeltaPosition() throws IOException {
    int delta = proxStream.readVInt();
    if (currentFieldStoresPayloads) {
      // if the current field stores payloads then
      // the position delta is shifted one bit to the left.
      // if the LSB is set, then we have to read the current
      // payload length
      if ((delta & 1) != 0) {
        payloadLength = proxStream.readVInt();
      delta >>>= 1;
      needToLoadPayload = true;
    return delta;
  protected final void skippingDoc() throws IOException {
    // we remember to skip a document lazily
    lazySkipProxCount += freq;

  public final boolean next() throws IOException {
    // we remember to skip the remaining positions of the current
    // document lazily
    lazySkipProxCount += proxCount;
    if (super.next()) {               // run super
      proxCount = freq;               // note frequency
      position = 0;               // reset position
      return true;
    return false;

  public final int read(final int[] docs, final int[] freqs) {
    throw new UnsupportedOperationException("TermPositions does not support processing multiple documents in one call. Use TermDocs instead.");

  /** Called by super.skipTo(). */
  protected void skipProx(long proxPointer, int payloadLength) throws IOException {
    // we save the pointer, we might have to skip there lazily
    lazySkipPointer = proxPointer;
    lazySkipProxCount = 0;
    proxCount = 0;
    this.payloadLength = payloadLength;
    needToLoadPayload = false;

  private void skipPositions(int n) throws IOException {
    assert !currentFieldOmitTermFreqAndPositions;
    for (int f = n; f > 0; f--) {        // skip unread positions
  private void skipPayload() throws IOException {
    if (needToLoadPayload && payloadLength > 0) {
      proxStream.seek(proxStream.getFilePointer() + payloadLength);
    needToLoadPayload = false;

  // It is not always necessary to move the prox pointer
  // to a new document after the freq pointer has been moved.
  // Consider for example a phrase query with two terms:
  // the freq pointer for term 1 has to move to document x
  // to answer the question if the term occurs in that document. But
  // only if term 2 also matches document x, the positions have to be
  // read to figure out if term 1 and term 2 appear next
  // to each other in document x and thus satisfy the query.
  // So we move the prox pointer lazily to the document
  // as soon as positions are requested.
  private void lazySkip() throws IOException {
    if (proxStream == null) {
      // clone lazily
      proxStream = (IndexInput) parent.core.proxStream.clone();
    // we might have to skip the current payload
    // if it was not read yet
    if (lazySkipPointer != -1) {
      lazySkipPointer = -1;
    if (lazySkipProxCount != 0) {
      lazySkipProxCount = 0;
  public int getPayloadLength() {
    return payloadLength;

  public byte[] getPayload(byte[] data, int offset) throws IOException {
    if (!needToLoadPayload) {
      throw new IOException("Either no payload exists at this term position or an attempt was made to load it more than once.");

    // read payloads lazily
    byte[] retArray;
    int retOffset;
    if (data == null || data.length - offset < payloadLength) {
      // the array is too small to store the payload data,
      // so we allocate a new one
      retArray = new byte[payloadLength];
      retOffset = 0;
    } else {
      retArray = data;
      retOffset = offset;
    proxStream.readBytes(retArray, retOffset, payloadLength);
    needToLoadPayload = false;
    return retArray;

  public boolean isPayloadAvailable() {
    return needToLoadPayload && payloadLength > 0;


Other Lucene examples (source code examples)

Here is a short list of links related to this Lucene SegmentTermPositions.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.