stemmeren.java

java编写的OCR软件

package de.spieleck.app.lang;

/*

   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

*/


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.  
 * @author lucene-dev
 * @author fsn
 * @version taken by fsn
 */

public class StemmerEN
    implements Stemmer
{   
  public final static String NORM_ATE = "ate";
  public final static String NORM_BLE = "ble";
  public final static String NORM_IZE = "ize";
  public final static String NORM_AL = "al";
  public final static String NORM_IC = "ic";

  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 StemmerEN() {  
    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

  */
  
  private final void step1() {
    if (b[k] == 's') {
      if (ends("sses")) k -= 2; 
      else if (ends("ies")) setto("i"); 
      else if (b[k-1] != 's') k--;
    }
    if (ends("eed")) { 
      if (m() > 0) 
        k--; 
    } 
    else if ((ends("ed") || ends("ing")) && vowelinstem()) {  
      k = j;
      if (ends("at")) setto(NORM_ATE); 
      else if (ends("bl")) setto(NORM_BLE); 
      else if (ends("iz")) setto(NORM_IZE); 
      else if (doublec(k)) {
        int ch = b[k--];
        if (ch == 'l' || ch == 's' || ch == 'z') 
          k++;
      }
      else if (m() == 1 && cvc(k)) 
        setto("e");
    }
  }

  /* step2() turns terminal y to i when there is another vowel in the stem. */
  
  private final void step2() { 
    if (ends("y") && vowelinstem()) {
      b[k] = 'i'; 
      dirty = true;
    }
  }

  /* step3() maps double suffices to single ones. so -ization ( = -ize plus
     -ation) maps to -ize etc. note that the string before the suffix must give
     m() > 0. */

  private final void step3() { 
    if (k == k0) return;
    switch (b[k-1]) {
    case 'a': 
      if (ends("ational")) { r(NORM_ATE); break; }
      if (ends("tional")) { r("tion"); break; }
      break;
    case 'c': 
      if (ends("enci")) { r("ence"); break; }
      if (ends("anci")) { r("ance"); break; }
      break;
    case 'e': 
      if (ends("izer")) { r(NORM_IZE); break; }
      break;
    case 'l': 
      if (ends("bli")) { r(NORM_BLE); break; }
      if (ends("alli")) { r(NORM_AL); break; }
      if (ends("entli")) { r("ent"); break; }
      if (ends("eli")) { r("e"); break; }
      if (ends("ousli")) { r("ous"); break; }
      break;
    case 'o': 
      if (ends("ization")) { r(NORM_IZE); break; }
      if (ends("ation")) { r(NORM_ATE); break; }
      if (ends("ator")) { r(NORM_ATE); break; }
      break;
    case 's': 
      if (ends("alism")) { r(NORM_AL); break; }