Soundex.java

Go to the documentation of this file.

/*
 * Turró i Cutiller Foundation. License notice.
 * Copyright (C) 2011 Lluis Turró Cutiller <http://www.turro.org/>
 *
 * This program is free software: you can redistribute it and/or modify
 * it under the terms of the GNU Affero General Public License as published by
 * the Free Software Foundation, either version 3 of the License, or
 * (at your option) any later version.
 *
 * This program is distributed in the hope that it will be useful,
 * but WITHOUT ANY WARRANTY; without even the implied warranty of
 * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
 * GNU Affero General Public License for more details.
 *
 * You should have received a copy of the GNU Affero General Public License
 * along with this program.  If not, see <http://www.gnu.org/licenses/>.
 */
package  org.turro.contacts.proposal;
 
import java.util.ArrayList;
import java.util.Arrays;
import java.util.logging.Level;
import java.util.logging.Logger;
import org.apache.commons.codec.EncoderException;
import org.apache.commons.codec.StringEncoder;
import org.turro.elephant.context.ElephantContext;
 
public class Soundex {
 
  private static StringEncoder encoder =
          new org.apache.commons.codec.language.RefinedSoundex();
 
  public static int difference(String s1, String s2) {
    s1 = replaceSpecialLetters(replacePunctuations(s1.toLowerCase()));
    s2 = replaceSpecialLetters(replacePunctuations(s2.toLowerCase()));
    return differenceWord(s1, s2);
  }
 
  public static String replacePunctuations(String s) {
    return s.replaceAll("[àáäâ]", "a")
            .replaceAll("[èéëê]", "e")
            .replaceAll("[ìíïî]", "i")
            .replaceAll("[òóöô]", "o")
            .replaceAll("[ùúüû]", "u");
  }
 
  public static String replaceSpecialLetters(String s) {
    return s.replaceAll("ñ", "ny")
            .replaceAll("ç", "s")
            .replaceAll("[^A-Za-z0-9]", "");
  }
 
  private static int differenceEncoded(String es1, String es2) {
    if (es1 == null || es2 == null) {
      return 0;
    }
    String words1[] = es1.split("[ \\.,\\(\\)]+"),
           words2[] = es2.split("[ \\.,\\(\\)]+");
    double count, diffPhrase = 0.0d;
    ArrayList<Double> diffWords = new ArrayList<Double>();
    for(String word1 : words1) {
      double diffW = 0;
      for(String word2 : words2) {
        diffW = Math.max(diffW, differenceWord(word1, word2));
      }
      diffWords.add(diffW);
    }
    count = Math.min(words1.length, words2.length);
    Double[] diffArray = diffWords.toArray(new Double[0]);
    Arrays.sort(diffArray);
    for(int i = 0; i < count; i++) {
      diffPhrase += diffArray[diffArray.length - i - 1];
    }
    return (int) (diffPhrase / count);
  }
 
  private static int differenceWord(String es1, String es2) {
    if (es1 == null || es2 == null) {
      return 0;
    }
    try {
      es1 = encoder.encode(es1);
      es2 = encoder.encode(es2);
    } catch (EncoderException ex) {
      Logger.getLogger(Soundex.class.getName()).log(Level.SEVERE, ElephantContext.logMsg(null), ex);
    }
    double lengthToMatch = Math.min(es1.length(), es2.length()),
           maxLength = Math.max(es1.length(), es2.length());
    double diff = 0;
    for (int i = 0; i < lengthToMatch; i++) {
      if (es1.charAt(i) == es2.charAt(i)) {
        diff++;
      }
    }
    return (int) ((diff * 100.0d / lengthToMatch) *
                 (lengthToMatch / maxLength));
  }
 
  private Soundex() {
  }
 
}