porterstemmer.java

天乙代码src_531.rar 天乙代码src_531.rar 天乙代码src_531.rar 天乙代码src_531.rar

package org.apache.lucene.analysis;

/* ====================================================================
 * The Apache Software License, Version 1.1
 *
 * Copyright (c) 2001 The Apache Software Foundation.  All rights
 * reserved.
 *
 * Redistribution and use in source and binary forms, with or without
 * modification, are permitted provided that the following conditions
 * are met:
 *
 * 1. Redistributions of source code must retain the above copyright
 *    notice, this list of conditions and the following disclaimer.
 *
 * 2. Redistributions in binary form must reproduce the above copyright
 *    notice, this list of conditions and the following disclaimer in
 *    the documentation and/or other materials provided with the
 *    distribution.
 *
 * 3. The end-user documentation included with the redistribution,
 *    if any, must include the following acknowledgment:
 *       "This product includes software developed by the
 *        Apache Software Foundation (http://www.apache.org/)."
 *    Alternately, this acknowledgment may appear in the software itself,
 *    if and wherever such third-party acknowledgments normally appear.
 *
 * 4. The names "Apache" and "Apache Software Foundation" and
 *    "Apache Lucene" must not be used to endorse or promote products
 *    derived from this software without prior written permission. For
 *    written permission, please contact [e-mail].
 *
 * 5. Products derived from this software may not be called "Apache",
 *    "Apache Lucene", nor may "Apache" appear in their name, without
 *    prior written permission of the Apache Software Foundation.
 *
 * THIS SOFTWARE IS PROVIDED ``AS IS'' AND ANY EXPRESSED OR IMPLIED
 * WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE IMPLIED WARRANTIES
 * OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE ARE
 * DISCLAIMED.  IN NO EVENT SHALL THE APACHE SOFTWARE FOUNDATION OR
 * ITS CONTRIBUTORS BE LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL,
 * SPECIAL, EXEMPLARY, OR CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT
 * LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS OR SERVICES; LOSS OF
 * USE, DATA, OR PROFITS; OR BUSINESS INTERRUPTION) HOWEVER CAUSED AND
 * ON ANY THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY,
 * OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT
 * OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF
 * SUCH DAMAGE.
 * ====================================================================
 *
 * This software consists of voluntary contributions made by many
 * individuals on behalf of the Apache Software Foundation.  For more
 * information on the Apache Software Foundation, please see
 * <http://www.apache.org/>.
 */

/*

   Porter stemmer in Java. The original paper is in

       Porter, 1980, An algorithm for suffix stripping, Program, Vol. 14,
       no. 3, pp 130-137,

   See also http://www.muscat.com/~martin/stem.html

   Bug 1 (reported by Gonzalo Parra 16/10/99) fixed as marked below.
   Tthe words 'aed', 'eed', 'oed' leave k at 'a' for step 3, and b[k-1]
   is then out outside the bounds of b.

   Similarly,

   Bug 2 (reported by Steve Dyrdahl 22/2/00) fixed as marked below.
   'ion' by itself leaves j = -1 in the test for 'ion' in step 5, and
   b[j] is then outside the bounds of b.

   Release 3.

   [ This version is derived from Release 3, modified by Brian Goetz to 
     optimize for fewer object creations.  ]

*/


import java.io.*;

/**
 *
 * Stemmer, implementing the Porter Stemming Algorithm
 *
 * The Stemmer class transforms a word into its root form.  The input
 * word can be provided a character at time (by calling add()), or at once
 * by calling one of the various stem(something) methods.  
 */

class PorterStemmer
{   
  private char[] b;
  private int i,    /* offset into b */
    j, k, k0;
  private boolean dirty = false;
  private static final int INC = 50; /* unit of size whereby b is increased */
  private static final int EXTRA = 1;

  public PorterStemmer() {  
    b = new char[INC];
    i = 0;
  }

  /** 
   * reset() resets the stemmer so it can stem another word.  If you invoke
   * the stemmer by calling add(char) and then stem(), you must call reset()
   * before starting another word.
   */
  public void reset() { i = 0; dirty = false; }

  /**
   * Add a character to the word being stemmed.  When you are finished 
   * adding characters, you can call stem(void) to process the word. 
   */ 
  public void add(char ch) {
    if (b.length <= i + EXTRA) {
      char[] new_b = new char[b.length+INC];
      for (int c = 0; c < b.length; c++) 
        new_b[c] = b[c];
      b = new_b;
    }
    b[i++] = ch;
  }

  /**
   * After a word has been stemmed, it can be retrieved by toString(), 
   * or a reference to the internal buffer can be retrieved by getResultBuffer
   * and getResultLength (which is generally more efficient.)
   */
  public String toString() { return new String(b,0,i); }

  /**
   * Returns the length of the word resulting from the stemming process.
   */
  public int getResultLength() { return i; }

  /**
   * Returns a reference to a character buffer containing the results of
   * the stemming process.  You also need to consult getResultLength()
   * to determine the length of the result.
   */
  public char[] getResultBuffer() { return b; }

  /* cons(i) is true <=> b[i] is a consonant. */

  private final boolean cons(int i) {
    switch (b[i]) {
    case 'a': case 'e': case 'i': case 'o': case 'u': 
      return false;
    case 'y': 
      return (i==k0) ? true : !cons(i-1);
    default: 
      return true;
    }
  }

  /* m() measures the number of consonant sequences between k0 and j. if c is
     a consonant sequence and v a vowel sequence, and <..> indicates arbitrary
     presence,

          <c><v>       gives 0
          <c>vc<v>     gives 1
          <c>vcvc<v>   gives 2
          <c>vcvcvc<v> gives 3
          ....
  */

  private final int m() {
    int n = 0;
    int i = k0;
    while(true) {
      if (i > j) 
        return n;
      if (! cons(i)) 
        break; 
      i++;
    }
    i++;
    while(true) {
      while(true) {
        if (i > j) 
          return n;
        if (cons(i)) 
          break;
        i++;
      }
      i++;
      n++;
      while(true) {
        if (i > j) 
          return n;
        if (! cons(i)) 
          break;
        i++;
      }
      i++;
    }
  }

  /* vowelinstem() is true <=> k0,...j contains a vowel */

  private final boolean vowelinstem() {
    int i; 
    for (i = k0; i <= j; i++) 
      if (! cons(i)) 
        return true;
    return false;
  }

  /* doublec(j) is true <=> j,(j-1) contain a double consonant. */

  private final boolean doublec(int j) {
    if (j < k0+1) 
      return false;
    if (b[j] != b[j-1]) 
      return false;
    return cons(j);
  }

  /* cvc(i) is true <=> i-2,i-1,i has the form consonant - vowel - consonant
     and also if the second c is not w,x or y. this is used when trying to
     restore an e at the end of a short word. e.g.

          cav(e), lov(e), hop(e), crim(e), but
          snow, box, tray.

  */

  private final boolean cvc(int i) {
    if (i < k0+2 || !cons(i) || cons(i-1) || !cons(i-2)) 
      return false;
    else {
      int ch = b[i];
      if (ch == 'w' || ch == 'x' || ch == 'y') return false;
    }
    return true;
  }

  private final boolean ends(String s) {
    int l = s.length();
    int o = k-l+1;
    if (o < k0) 
      return false;
    for (int i = 0; i < l; i++) 
      if (b[o+i] != s.charAt(i)) 
        return false;
    j = k-l;
    return true;
  }

  /* setto(s) sets (j+1),...k to the characters in the string s, readjusting
     k. */

  void setto(String s) {
    int l = s.length();
    int o = j+1;
    for (int i = 0; i < l; i++) 
      b[o+i] = s.charAt(i);
    k = j+l;
    dirty = true;
  }

  /* r(s) is used further down. */

  void r(String s) { if (m() > 0) setto(s); }

  /* step1() gets rid of plurals and -ed or -ing. e.g.

           caresses  ->  caress
           ponies    ->  poni
           ties      ->  ti
           caress    ->  caress
           cats      ->  cat

           feed      ->  feed
           agreed    ->  agree
           disabled  ->  disable

           matting   ->  mat
           mating    ->  mate
           meeting   ->  meet
           milling   ->  mill
           messing   ->  mess

           meetings  ->  meet

  */