/* * Copyright (c) 2013, University of Toronto. * * Licensed under the Apache License, Version 2.0 (the "License"); you may * not use this file except in compliance with the License. You may obtain * a copy of the License at * * http://www.apache.org/licenses/LICENSE-2.0 * * Unless required by applicable law or agreed to in writing, software * distributed under the License is distributed on an "AS IS" BASIS, WITHOUT * WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied. See the * License for the specific language governing permissions and limitations * under the License. */ package edu.toronto.cs.xml2rdf.string; import java.io.BufferedReader; import java.io.IOException; import java.io.InputStream; import java.io.InputStreamReader; import java.text.Normalizer; import java.util.regex.Pattern; public class StringUtils { public static String deAccent(String str) { String nfdNormalizedString = Normalizer.normalize(str, Normalizer.Form.NFD); Pattern pattern = Pattern.compile("\\p{InCombiningDiacriticalMarks}+"); return pattern.matcher(nfdNormalizedString).replaceAll(""); } public static String getContent(InputStream is) throws IOException { BufferedReader reader = new BufferedReader(new InputStreamReader(is)); String ret = ""; String line; while ((line = reader.readLine()) != null) { ret += line + "\n"; } return ret; } }