Java String Accent stripAccents(final String input)

Description

Removes diacritics (~= accents) from a string.

License

Apache License

Parameter

Parameter	Description
input	String to be stripped

Return

input text with diacritics removed

Declaration

static String stripAccents(final String input) 

Method Source Code

//package com.java2s;
/*//  w w w.  jav a 2  s .  c o  m
 * Licensed to the Apache Software Foundation (ASF) under one or more
 * contributor license agreements.  See the NOTICE file distributed with
 * this work for additional information regarding copyright ownership.
 * The ASF licenses this file to You 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.
 */

import java.text.Normalizer;
import java.util.regex.Pattern;

public class Main {
    private static final String EMPTY = "";

    /**
     * <p>Removes diacritics (~= accents) from a string. The case will not be altered.</p>
     * <p>For instance, '&agrave;' will be replaced by 'a'.</p>
     * <p>Note that ligatures will be left as is.</p>
     *
     * <pre>
     * StringUtils.stripAccents(null)                = null
     * StringUtils.stripAccents("")                  = ""
     * StringUtils.stripAccents("control")           = "control"
     * StringUtils.stripAccents("&eacute;clair")     = "eclair"
     * </pre>
     *
     * @param input String to be stripped
     * @return input text with diacritics removed
     *
     * @since 3.0
     */
    // See also Lucene's ASCIIFoldingFilter (Lucene 2.9) that replaces accented characters by their unaccented equivalent (and uncommitted bug fix: https://issues.apache.org/jira/browse/LUCENE-1343?focusedCommentId=12858907&page=com.atlassian.jira.plugin.system.issuetabpanels%3Acomment-tabpanel#action_12858907).
    static String stripAccents(final String input) {
        if (input == null) {
            return null;
        }
        final Pattern pattern = Pattern.compile("\\p{InCombiningDiacriticalMarks}+");//$NON-NLS-1$
        final StringBuilder decomposed = new StringBuilder(Normalizer.normalize(input, Normalizer.Form.NFD));
        convertRemainingAccentCharacters(decomposed);
        // Note that this doesn't correctly remove ligatures...
        return pattern.matcher(decomposed).replaceAll(EMPTY);
    }

    private static void convertRemainingAccentCharacters(StringBuilder decomposed) {
        for (int i = 0; i < decomposed.length(); i++) {
            if (decomposed.charAt(i) == '\u0141') {
                decomposed.deleteCharAt(i);
                decomposed.insert(i, 'L');
            } else if (decomposed.charAt(i) == '\u0142') {
                decomposed.deleteCharAt(i);
                decomposed.insert(i, 'l');
            }
        }
    }
}

Related

1. removeAccentsAndNonStandardCharacters(String string)
2. removeAccentuation(String str)
3. replaceAccent(String strInit)
4. replaceAccentedChars(StringBuilder buffer)
5. replaceAccents(String string)
6. stripAccents(final String input)
7. stripAccents(final String s)
8. stripAccents(String input)
9. stripAccents(String input)