Here you can find the source of normalizeUnicode(CharSequence text)
public static String normalizeUnicode(CharSequence text)
//package com.java2s; /* ************************************************************************* * * TMPotter - Bi-text Aligner/TMX Editor * * Copyright (C) 2015 Hiroshi Miura//from www. j a v a 2 s.c o m * * This file come from OmegaT project * * Copyright (C) 2007 - Zoltan Bartko * 2011 Alex Buloichik * * This file is part of TMPotter. * * TMPotter is free software; you can redistribute it and/or modify * it under the terms of the GNU General Public License as published by * the Free Software Foundation; either version 3 of the License, or * (at your option) any later version. * * TMPotter 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 General Public License for more details. * * You should have received a copy of the GNU General Public License * along with TMPotter. If not, see http://www.gnu.org/licenses/. * * *************************************************************************/ import java.text.Normalizer; public class Main { /** * Apply Unicode NFC normalization to a string. */ public static String normalizeUnicode(CharSequence text) { return Normalizer.isNormalized(text, Normalizer.Form.NFC) ? text.toString() : Normalizer.normalize(text, Normalizer.Form.NFC); } }