Mega Code Archive
Returns the string constructed from the specified character sequence by deaccenting each of its characters
<![CDATA[
/*
* LingPipe v. 3.9
* Copyright (C) 2003-2010 Alias-i
*
* This program is licensed under the Alias-i Royalty Free License
* Version 1 WITHOUT ANY WARRANTY, without even the implied warranty of
* MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the Alias-i
* Royalty Free License Version 1 for more details.
*
* You should have received a copy of the Alias-i Royalty Free License
* Version 1 along with this program; if not, visit
* http://alias-i.com/lingpipe/licenses/lingpipe-license-1.txt or contact
* Alias-i, Inc. at 181 North 11th Street, Suite 401, Brooklyn, NY 11211,
* +1 (718) 290-9170.
*/
//package com.aliasi.util;
import java.io.DataInput;
import java.io.DataOutput;
import java.io.IOException;
import java.text.DecimalFormat;
/**
* Static utility methods for processing strings, characters and
* string buffers.
*
* @author Bob Carpenter
* @version 4.0.1
* @since LingPipe1.0
* @see java.lang.Character
* @see java.lang.String
* @see java.lang.StringBuilder
*/
public class Strings {
/**
* Returns the string constructed from the specified character
* sequence by deaccenting each of its characters. See {@link
* #deAccentLatin1(char)} for details of the de-accenting.
*
* @param cSeq Character sequence to de accent.
* @return De-accented version of input.
*/
public static String deAccentLatin1(CharSequence cSeq) {
char[] cs = new char[cSeq.length()];
for (int i = 0; i < cs.length; ++i)
cs[i] = deAccentLatin1(cSeq.charAt(i));
return new String(cs);
}
/**
* Returns the equivalent de-accented character for characters in
* the Latin-1 (ISO-8859-1) range (0000-00FF). Characters not in
* the Latin-1 range are returned as-is.
*
* Note that Latin-1 is a superset of ASCII, and the unsigned byte
* encoding of Latin-1 characters (ISO-8859-1) provides the same
* code points as Unicode for characters.
*
* <p>The <code>unicode.org</code> site supplies a complete <a
* href="http://unicode.org/charts/PDF/U0080.pdf">Latin-1
* Supplement</code>, listing the code points for each character.
*
* @param c Character to de-accent.
* @return Equivalent character without accent.
*/
public static char deAccentLatin1(char c) {
switch (c) {
case '\u00C0': return 'A';
case '\u00C1': return 'A';
case '\u00C2': return 'A';
case '\u00C3': return 'A';
case '\u00C4': return 'A';
case '\u00C5': return 'A';
case '\u00C6': return 'A'; // capital AE ligature
case '\u00C7': return 'C';
case '\u00C8': return 'E';
case '\u00C9': return 'E';
case '\u00CA': return 'E';
case '\u00CB': return 'E';
case '\u00CC': return 'I';
case '\u00CD': return 'I';
case '\u00CE': return 'I';
case '\u00CF': return 'I';
case '\u00D0': return 'D';
case '\u00D1': return 'N';
case '\u00D2': return 'O';
case '\u00D3': return 'O';
case '\u00D4': return 'O';
case '\u00D5': return 'O';
case '\u00D6': return 'O';
case '\u00D8': return 'O';
case '\u00D9': return 'U';
case '\u00DA': return 'U';
case '\u00DB': return 'U';
case '\u00DC': return 'U';
case '\u00DD': return 'Y';
case '\u00DE': return 'P'; // runic letter thorn
case '\u00DF': return 's'; // upper case is SS
case '\u00E0': return 'a';
case '\u00E1': return 'a';
case '\u00E2': return 'a';
case '\u00E3': return 'a';
case '\u00E4': return 'a';
case '\u00E5': return 'a';
case '\u00E6': return 'a'; // ae ligature
case '\u00E7': return 'c';
case '\u00E8': return 'e';
case '\u00E9': return 'e';
case '\u00EA': return 'e';
case '\u00EB': return 'e';
case '\u00EC': return 'i';
case '\u00ED': return 'i';
case '\u00EE': return 'i';
case '\u00EF': return 'i';
case '\u00F0': return 'd';
case '\u00F1': return 'n';
case '\u00F2': return 'o';
case '\u00F3': return 'o';
case '\u00F4': return 'o';
case '\u00F5': return 'o';
case '\u00F6': return 'o';
case '\u00F8': return 'o';
case '\u00F9': return 'u';
case '\u00FA': return 'u';
case '\u00FB': return 'u';
case '\u00FC': return 'u';
case '\u00FD': return 'y';
case '\u00FE': return 'p'; // runic letter thorn
case '\u00FF': return 'y';
default: return c;
}
}
}
]]>