Last active
August 29, 2015 14:22
-
-
Save jongha/9c9287af6ed088c8c2d9 to your computer and use it in GitHub Desktop.
Soundex Algorithm
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
// reference: http://en.wikipedia.org/wiki/Soundex | |
public class SoundexUtil { | |
// public static void main(String[] args) { | |
// System.out.println(soundex("Gauss")); // G200 | |
// System.out.println(soundex("AHN")); // A500 | |
// } | |
public static String soundex(String text) { | |
StringBuilder builder = new StringBuilder(); | |
int numberCounter = 0; | |
for (int i = 0; i < text.length(); ++i) { | |
char c = text.charAt(i); | |
if (i == 0) { | |
builder.append(c); | |
} else { | |
char number = 0; | |
switch (Character.toLowerCase(c)) { | |
case 'a': | |
case 'e': | |
case 'h': | |
case 'i': | |
case 'o': | |
case 'u': | |
case 'w': | |
case 'y': | |
continue; | |
case 'b': | |
case 'f': | |
case 'p': | |
case 'v': | |
number = '1'; | |
break; | |
case 'c': | |
case 'g': | |
case 'j': | |
case 'k': | |
case 'q': | |
case 's': | |
case 'x': | |
case 'z': | |
number = '2'; | |
break; | |
case 'd': | |
case 't': | |
number = '3'; | |
break; | |
case 'l': | |
number = '4'; | |
break; | |
case 'm': | |
case 'n': | |
number = '5'; | |
break; | |
case 'r': | |
number = '6'; | |
break; | |
} | |
if (number > 0 | |
&& builder.charAt(builder.length() - 1) != number) { | |
builder.append(number); | |
++numberCounter; | |
} | |
} | |
} | |
while (numberCounter < 3) { | |
builder.append('0'); | |
++numberCounter; | |
} | |
String soundexText = builder.toString(); | |
return soundexText.substring(0, 4); | |
} | |
} |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment