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

public static String stripAccents(final String input) 

Method Source Code

//package com.java2s;
/*/* ww  w .  ja v  a 2  s  .  co 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 {
    /**
     * <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).
    public static String stripAccents(final String input) {
        if (input == null) {
            return null;
        }
        final Pattern pattern = Pattern.compile("\\p{InCombiningDiacriticalMarks}+");//$NON-NLS-1$
        final String decomposed = Normalizer.normalize(input, Normalizer.Form.NFD);
        // Note that this doesn't correctly remove ligatures...
        return pattern.matcher(decomposed).replaceAll("");//$NON-NLS-1$
    }

    public static String normalize(String s) {
        if (s == null)
            return null;
        if (s.length() == 0)
            return s;
        return s.toLowerCase().trim();
    }

    /**
     * Gets a CharSequence length or {@code 0} if the CharSequence is
     * {@code null}.
     *
     * @param cs
     *            a CharSequence or {@code null}
     * @return CharSequence length or {@code 0} if the CharSequence is
     *         {@code null}.
     * @since 2.4
     * @since 3.0 Changed signature from length(String) to length(CharSequence)
     */
    public static int length(final CharSequence cs) {
        return cs == null ? 0 : cs.length();
    }

    /**
     * <p>
     * Removes control characters (char &lt;= 32) from both ends of this String,
     * handling {@code null} by returning {@code null}.
     * </p>
     *
     * <p>
     * The String is trimmed using {@link String#trim()}. Trim removes start and
     * end characters &lt;= 32. To strip whitespace use {@link #strip(String)}.
     * </p>
     *
     * <p>
     * To trim your choice of characters, use the {@link #strip(String, String)}
     * methods.
     * </p>
     *
     * <pre>
     * StringUtils.trim(null)          = null
     * StringUtils.trim("")            = ""
     * StringUtils.trim("     ")       = ""
     * StringUtils.trim("abc")         = "abc"
     * StringUtils.trim("    abc    ") = "abc"
     * </pre>
     *
     * @param str
     *            the String to be trimmed, may be null
     * @return the trimmed string, {@code null} if null String input
     */
    public static String trim(final String str) {
        return str == null ? null : str.trim();
    }
}

Related

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