Java String Tokenize tokenize(String source, char separator)

Description

Tokenizes a string and takes into account escaping.

License

LGPL

Parameter

Parameter	Description
source	the string to tokenize.
separator	the separator character.

Return

the tokenized string (or null if source is null).

Declaration

public static String[] tokenize(String source, char separator) 

Method Source Code

//package com.java2s;
/* ************************************************************************
    //w  ww . ja va2 s  . c  om
   qooxdoo - the new era of web development
    
   http://qooxdoo.org
    
   Copyright:
 2006-2007 STZ-IDA, Germany, http://www.stz-ida.de
    
   License:
 LGPL: http://www.gnu.org/licenses/lgpl.html
 EPL: http://www.eclipse.org/org/documents/epl-v10.php
 See the LICENSE file in the project's top-level directory for details.
    
   Authors:
 * Andreas Junghans (lucidcake)
    
************************************************************************ */

import java.util.ArrayList;

public class Main {
    private static final int STATE_DEFAULT = 1;
    private static final int STATE_BACKSLASH = 2;

    /**
     * Tokenizes a string and takes into account escaping. The source string
     * may contain the seperator character escaped with a backslash. The
     * backslash itself can be generated by using a double backslash.
     * <p>
     * More than one separator in a row leeds to empty strings in the
     * resulting array ("a;;b" results in "a", "", "b"). The last trailing
     * separator is ignored ("a;;b;" results in "a", "", "b" - same as
     * above -, while "a;;b;;" results in "a", "", "b", "").
     * </p>
     *
     * @param       source              the string to tokenize.
     * @param       separator           the separator character.
     *
     * @return      the tokenized string (or <code>null</code> if
     *              <code>source</code> is <code>null</code>).
     */

    public static String[] tokenize(String source, char separator) {
        if (source == null) {
            return null;
        }
        int length = source.length();
        ArrayList result = new ArrayList();
        StringBuffer currentString = new StringBuffer();
        char c;
        int state = STATE_DEFAULT;
        for (int i = 0; i < length; ++i) {
            c = source.charAt(i);
            switch (state) {
            case STATE_DEFAULT:
                if (c == '\\') {
                    state = STATE_BACKSLASH;
                } else if (c == separator) {
                    result.add(currentString.toString());
                    currentString = new StringBuffer();
                } else {
                    currentString.append(c);
                }
                break;
            case STATE_BACKSLASH:
                currentString.append(c);
                state = STATE_DEFAULT;
                break;
            }
        }
        if (state == STATE_BACKSLASH) {
            throw new IllegalArgumentException("The string to tokenize ends with a single backslash");
        }
        if (currentString.length() > 0) {
            result.add(currentString.toString());
        }
        return (String[]) result.toArray(new String[result.size()]);
    }
}

Related

1. tokenize(String s, String delimiters)
2. tokenize(String s1)
3. Tokenize(String sent)
4. tokenize(String sentence)
5. tokenize(String source, char separator)
6. tokenize(String str, char delim)
7. tokenize(String str, String delims)
8. tokenize(String str, String delims, boolean returnDelims)
9. tokenize(String string, String splitOn)