scaletriereader.java

一个自然语言处理的Java开源工具包。LingPipe目前已有很丰富的功能

/*
 * LingPipe v. 3.5
 * Copyright (C) 2003-2008 Alias-i
 *
 * This program is licensed under the Alias-i Royalty Free License
 * Version 1 WITHOUT ANY WARRANTY, without even the implied warranty of
 * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the Alias-i
 * Royalty Free License Version 1 for more details.
 *
 * You should have received a copy of the Alias-i Royalty Free License
 * Version 1 along with this program; if not, visit
 * http://alias-i.com/lingpipe/licenses/lingpipe-license-1.txt or contact
 * Alias-i, Inc. at 181 North 11th Street, Suite 401, Brooklyn, NY 11211,
 * [phone].
 */

package com.aliasi.lm;

import java.io.IOException;

/**
 * A <code>ScaleTrieReader</code> filters a contained trie
 * reader by scaling all counts by a given multiple, removing
 * all subtrees with zero root counts.  Counts are rounded
 * after multiplication using {@link java.lang.Math#round(double)}.
 * Thus pruning will only occur if the scaling factor is less
 * than 0.5, because <code>0.5</code> rounds to <code>1</code>.
 *
 *
 * @author  Bob Carpenter
 * @version 2.3
 * @since   LingPipe2.3
 */
public class ScaleTrieReader extends DeletingTrieReader {

    private final double mScale;

    /**
     * Construct a scaling trie reader wrapping the specified
     * reader and scaling counts with the specified value.
     *
     * @param reader Contained reader.
     * @param scale Scaling factor.
     * @throws IllegalArgumentException If the scale is not a
     * positive, non-infinite value.
     */
    public ScaleTrieReader(TrieReader reader, double scale) 
    throws IOException {
    
    super(reader);
    if (scale <= 0.0 || Double.isNaN(scale) || Double.isInfinite(scale)) {
        String msg = "Scale must be positive and non-infinite."
        + " Found scale=" + scale;
        throw new IllegalArgumentException(msg);
    }
    mScale = scale;
    }


    boolean bufferCount() throws IOException {
    mNextCount = Math.round(mScale * (double)nextCount());
    return mNextCount > 0L;
    }


}