/*
* 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.
*
* The unicode.org site supplies a complete
* Supplement
, listing the code points for each character.