com.googlecode.javaewah32.BufferedIterator32 Maven / Gradle / Ivy

Go to download

Show more of this group Show more artifacts with this name
Show all versions of JavaEWAH Show documentation

The bit array data structure is implemented in Java as the BitSet class. Unfortunately, this fails to scale without compression. JavaEWAH is a word-aligned compressed variant of the Java bitset class. It uses a 64-bit run-length encoding (RLE) compression scheme. The goal of word-aligned compression is not to achieve the best compression, but rather to improve query processing time. Hence, we try to save CPU cycles, maybe at the expense of storage. However, the EWAH scheme we implemented is always more efficient storage-wise than an uncompressed bitmap (implemented in Java as the BitSet class). Unlike some alternatives, javaewah does not rely on a patented scheme.

There is a newer version: 1.2.3

Show newest version

package com.googlecode.javaewah32;

import com.googlecode.javaewah.CloneableIterator;

/*
 * Copyright 2009-2016, Daniel Lemire, Cliff Moon, David McIntosh, Robert Becho, Google Inc., Veronika Zenz, Owen Kaser, Gregory Ssi-Yan-Kai, Rory Graves
 * Licensed under the Apache License, Version 2.0.
 */

/**
 * This class can be used to iterate over blocks of bitmap data.
 *
 * @author Daniel Lemire
 */
public class BufferedIterator32 implements IteratingRLW32, Cloneable {
    /**
     * Instantiates a new iterating buffered running length word.
     *
     * @param iterator iterator
     */
    public BufferedIterator32(
            final CloneableIterator iterator) {
        this.masterIterator = iterator;
        if (this.masterIterator.hasNext()) {
            iteratingBrlw = new IteratingBufferedRunningLengthWord32(this.masterIterator.next());
        }
    }

    /**
     * Discard first words, iterating to the next running length word if
     * needed.
     *
     * @param x the number of words to be discarded
     */
    @Override
    public void discardFirstWords(int x) {
        while (x > 0) {
            if (this.iteratingBrlw.getRunningLength() > x) {
                this.iteratingBrlw.discardFirstWords(x);
                return;
            }
            this.iteratingBrlw.discardFirstWords(this.iteratingBrlw.getRunningLength());
            x -= this.iteratingBrlw.getRunningLength();
            int toDiscard = x > this.iteratingBrlw.getNumberOfLiteralWords()
                    ? this.iteratingBrlw.getNumberOfLiteralWords()
                    : x;

            this.iteratingBrlw.discardFirstWords(toDiscard);
            x -= toDiscard;
            if ((x > 0) || (this.iteratingBrlw.size() == 0)) {
                if (!this.next()) {
                    break;
                }
            }
        }
    }

    @Override
    public void discardRunningWords() {
        this.iteratingBrlw.discardRunningWords();
        if (this.iteratingBrlw.getNumberOfLiteralWords() == 0)
            this.next();
    }

    /**
     * Move to the next RunningLengthWord
     *
     * @return whether the move was possible
     */
    @Override
    public boolean next() {
        if (!this.iteratingBrlw.next()) {
            if (!this.masterIterator.hasNext()) {
                return false;
            } else {
                this.iteratingBrlw = new IteratingBufferedRunningLengthWord32(this.masterIterator.next());
            }
        }
        return true;
    }

    /**
     * Get the nth literal word for the current running length word
     *
     * @param index zero based index
     * @return the literal word
     */
    @Override
    public int getLiteralWordAt(int index) {
        return this.iteratingBrlw.getLiteralWordAt(index);
    }

    /**
     * Gets the number of literal words for the current running length word.
     *
     * @return the number of literal words
     */
    @Override
    public int getNumberOfLiteralWords() {
        return this.iteratingBrlw.getNumberOfLiteralWords();
    }

    /**
     * Gets the running bit.
     *RunningBit
     * @return the running bit
     */
    @Override
    public boolean getRunningBit() {
        return this.iteratingBrlw.getRunningBit();
    }

    /**
     * Gets the running length.
     *
     * @return the running length
     */
    @Override
    public int getRunningLength() {
        return this.iteratingBrlw.getRunningLength();
    }

    /**
     * Size in uncompressed words of the current running length word.
     *
     * @return the size
     */
    @Override
    public int size() {
        return this.iteratingBrlw.size();
    }

    @Override
    public BufferedIterator32 clone() throws CloneNotSupportedException {
        BufferedIterator32 answer = (BufferedIterator32) super.clone();
        answer.iteratingBrlw = this.iteratingBrlw.clone();
        answer.masterIterator = this.masterIterator.clone();
        return answer;
    }

    private IteratingBufferedRunningLengthWord32 iteratingBrlw;
    private CloneableIterator masterIterator;

}