Created
August 22, 2016 09:37
-
-
Save Tarrasch/e8a9dd8057b9f25353097ce8b9e44ae5 to your computer and use it in GitHub Desktop.
Vietnamese diacritics
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
public class VietnameseDiacritics { | |
// this is only pseudo code, not meant to compile | |
public static String allVietnameseCombiningDiacriticalMarks() { | |
String s = "ạàáãảâăư"; // đ is not counted as a diacratic apparently | |
s = java.text.Normalizer.normalize(s, java.text.Normalizer.Form.NFD); | |
s = s.replaceAll("[^\\p{InCombiningDiacriticalMarks}]", ""); | |
return s; | |
} | |
private String removeNonVietnameseDiacritics(String input) { | |
input = java.text.Normalizer.normalize(input, java.text.Normalizer.Form.NFD); | |
input = input.replaceAll("[\\p{InCombiningDiacriticalMarks}&&[^" + VIETNAMESE_DIACRITICS + "]]", ""); | |
input = java.text.Normalizer.normalize(input, java.text.Normalizer.Form.NFKC); | |
return input; | |
} | |
} |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment