com.googlecode.javaewah.IntIteratorOverIteratingRLW 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.javaewah;

import static com.googlecode.javaewah.EWAHCompressedBitmap.WORD_IN_BITS;

/*
 * 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.
 */

/**
 * Implementation of an IntIterator over an IteratingRLW.
 */
public class IntIteratorOverIteratingRLW implements IntIterator {
    final IteratingRLW parent;
    private int position;
    private int runningLength;
    private long word;
    private int wordPosition;
    private int wordLength;
    private int literalPosition;
    private boolean hasNext;

    /**
     * @param p iterator we wish to iterate over
     */
    public IntIteratorOverIteratingRLW(final IteratingRLW p) {
        this.parent = p;
        this.position = 0;
        setupForCurrentRunningLengthWord();
        this.hasNext = moveToNext();
    }

    /**
     * @return whether we could find another set bit; don't move if there is
     * an unprocessed value
     */
    private boolean moveToNext() {
        while (!runningHasNext() && !literalHasNext()) {
            if (this.parent.next())
                setupForCurrentRunningLengthWord();
            else
                return false;
        }
        return true;
    }

    @Override
    public boolean hasNext() {
        return this.hasNext;
    }

    @Override
    public final int next() {
        final int answer;
        if (runningHasNext()) {
            answer = this.position++;
        } else {
            final long t = this.word & -this.word;
            answer = this.literalPosition + Long.bitCount(t - 1);
            this.word ^= t;
        }
        this.hasNext = this.moveToNext();
        return answer;
    }

    private void setupForCurrentRunningLengthWord() {
        this.runningLength = WORD_IN_BITS * (int) this.parent.getRunningLength() + this.position;

        if (!this.parent.getRunningBit()) {
            this.position = this.runningLength;
        }
        this.wordPosition = 0;
        this.wordLength = this.parent.getNumberOfLiteralWords();
    }

    private boolean runningHasNext() {
        return this.position < this.runningLength;
    }

    private boolean literalHasNext() {
        while (this.word == 0 && this.wordPosition < this.wordLength) {
            this.word = this.parent.getLiteralWordAt(this.wordPosition++);
            this.literalPosition = this.position;
            this.position += WORD_IN_BITS;
        }
        return this.word != 0;
    }
}