Java String Split split(String string)

Description

Splits a string into an array of components.

License

Open Source License

Parameter

Parameter	Description
string	the String that should be split

Return

an array of String components extracted from the string

Declaration

public static String[] split(String string) 

Method Source Code

//package com.java2s;
/*==========================================================================*\
 |  $Id: ShellStringUtils.java,v 1.3 2009/09/13 12:59:29 aallowat Exp $
 |*-------------------------------------------------------------------------*|
 |  Copyright (C) 2006-2009 Virginia Tech 
 |
 |   This file is part of Web-CAT Eclipse Plugins.
 |
 |   Web-CAT is free software; you can redistribute it and/or modify
 |   it under the terms of the GNU General Public License as published by
 |   the Free Software Foundation; either version 2 of the License, or
 |   (at your option) any later version.
 |
 |   Web-CAT is distributed in the hope that it will be useful,
 |   but WITHOUT ANY WARRANTY; without even the implied warranty of
 |   MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
 |   GNU General Public License for more details.
 |
 |   You should have received a copy of the GNU General Public License
 |   along with Web-CAT; if not, see <http://www.gnu.org/licenses/>.
\*==========================================================================*/

import java.util.ArrayList;

public class Main {
    /**//from   w  w  w. j  a  v  a2  s  .c o m
     * State identifiers used by the DFA in the split method.
     */
    private static final int STATE_BEGIN = 0;
    private static final int STATE_PART = 1;
    private static final int STATE_ESCAPE_IN_PART = 2;
    private static final int STATE_DQUOTE = 3;
    private static final int STATE_ESCAPE_IN_DQUOTE = 4;
    private static final int STATE_SQUOTE = 5;
    private static final int STATE_ESCAPE_IN_SQUOTE = 6;

    /**
     * Splits a string into an array of components. Whitespace is used as the
     * delimiter, but single and double quotes are handled properly so that a
     * component in quotes is extracted as a single component, regardless of
     * whether it contains whitespace or not.
     * 
     * @param string
     *            the String that should be split
     * 
     * @return an array of String components extracted from the string
     */
    public static String[] split(String string) {
        ArrayList<String> parts = new ArrayList<String>();
        StringBuffer currentPart = new StringBuffer();

        int state = STATE_BEGIN;

        for (int i = 0; i < string.length(); i++) {
            char ch = string.charAt(i);

            switch (state) {
            case STATE_BEGIN:
                if (ch == '"') {
                    currentPart.append(ch);
                    state = STATE_DQUOTE;
                } else if (ch == '\'') {
                    currentPart.append(ch);
                    state = STATE_SQUOTE;
                } else if (ch == '\\') {
                    state = STATE_ESCAPE_IN_PART;
                } else if (!Character.isWhitespace(ch)) {
                    currentPart.append(ch);
                    state = STATE_PART;
                }
                break;

            case STATE_PART:
                if (Character.isWhitespace(ch)) {
                    parts.add(currentPart.toString());
                    currentPart = new StringBuffer();
                    state = STATE_BEGIN;
                } else if (ch == '"') {
                    currentPart.append(ch);
                    state = STATE_DQUOTE;
                } else if (ch == '\'') {
                    currentPart.append(ch);
                    state = STATE_SQUOTE;
                } else if (ch == '\\') {
                    currentPart.append(ch);
                    state = STATE_ESCAPE_IN_PART;
                } else {
                    currentPart.append(ch);
                }
                break;

            case STATE_ESCAPE_IN_PART:
                currentPart.append(ch);
                state = STATE_PART;
                break;

            case STATE_DQUOTE:
                currentPart.append(ch);

                if (ch == '"') {
                    state = STATE_PART;
                } else if (ch == '\\') {
                    state = STATE_ESCAPE_IN_DQUOTE;
                }
                break;

            case STATE_ESCAPE_IN_DQUOTE:
                currentPart.append(ch);
                state = STATE_DQUOTE;
                break;

            case STATE_SQUOTE:
                currentPart.append(ch);

                if (ch == '\'') {
                    state = STATE_PART;
                } else if (ch == '\\') {
                    state = STATE_ESCAPE_IN_SQUOTE;
                }
                break;

            case STATE_ESCAPE_IN_SQUOTE:
                currentPart.append(ch);
                state = STATE_SQUOTE;
                break;
            }
        }

        if (currentPart.length() > 0)
            parts.add(currentPart.toString());

        String[] array = new String[parts.size()];
        parts.toArray(array);
        return array;
    }
}

Related

1. split(String str, String id)
2. split(String str, String splitStr)
3. split(String str, String splitter)
4. split(String str, String token)
5. split(String string)
6. split(String string, String seperator)
7. split(String strSource, String strReg)
8. split(String text)
9. split(String text)