Word Wrap : BreakIterator « I18N « Java Tutorial






/**
 * $Revision: 10205 $
 * $Date: 2008-04-11 15:48:27 -0700 (Fri, 11 Apr 2008) $
 *
 * Copyright (C) 2004-2008 Jive Software. All rights reserved.
 *
 * This software is published under the terms of the GNU Public License (GPL),
 * a copy of which is included in this distribution, or a commercial license
 * agreement with Jive.
 */

import java.io.UnsupportedEncodingException;
import java.security.MessageDigest;
import java.security.NoSuchAlgorithmException;
import java.text.BreakIterator;
import java.util.*;
import java.util.concurrent.ConcurrentHashMap;

/**
 * Utility class to peform common String manipulation algorithms.
 */
public class StringUtils {

    // Constants used by escapeHTMLTags
    private static final char[] QUOTE_ENCODE = """.toCharArray();
    private static final char[] AMP_ENCODE = "&".toCharArray();
    private static final char[] LT_ENCODE = "<".toCharArray();
    private static final char[] GT_ENCODE = ">".toCharArray();

    private StringUtils() {
        // Not instantiable.
    }

    /**
     * Reformats a string where lines that are longer than <tt>width</tt>
     * are split apart at the earliest wordbreak or at maxLength, whichever is
     * sooner. If the width specified is less than 5 or greater than the input
     * Strings length the string will be returned as is.
     * <p/>
     * Please note that this method can be lossy - trailing spaces on wrapped
     * lines may be trimmed.
     *
     * @param input the String to reformat.
     * @param width the maximum length of any one line.
     * @return a new String with reformatted as needed.
     */
    public static String wordWrap(String input, int width, Locale locale) {
        // protect ourselves
        if (input == null) {
            return "";
        }
        else if (width < 5) {
            return input;
        }
        else if (width >= input.length()) {
            return input;
        }

  

        StringBuilder buf = new StringBuilder(input);
        boolean endOfLine = false;
        int lineStart = 0;

        for (int i = 0; i < buf.length(); i++) {
            if (buf.charAt(i) == '\n') {
                lineStart = i + 1;
                endOfLine = true;
            }

            // handle splitting at width character
            if (i > lineStart + width - 1) {
                if (!endOfLine) {
                    int limit = i - lineStart - 1;
                    BreakIterator breaks = BreakIterator.getLineInstance(locale);
                    breaks.setText(buf.substring(lineStart, i));
                    int end = breaks.last();

                    // if the last character in the search string isn't a space,
                    // we can't split on it (looks bad). Search for a previous
                    // break character
                    if (end == limit + 1) {
                        if (!Character.isWhitespace(buf.charAt(lineStart + end))) {
                            end = breaks.preceding(end - 1);
                        }
                    }

                    // if the last character is a space, replace it with a \n
                    if (end != BreakIterator.DONE && end == limit + 1) {
                        buf.replace(lineStart + end, lineStart + end + 1, "\n");
                        lineStart = lineStart + end;
                    }
                    // otherwise, just insert a \n
                    else if (end != BreakIterator.DONE && end != 0) {
                        buf.insert(lineStart + end, '\n');
                        lineStart = lineStart + end + 1;
                    }
                    else {
                        buf.insert(i, '\n');
                        lineStart = i + 1;
                    }
                }
                else {
                    buf.insert(i, '\n');
                    lineStart = i + 1;
                    endOfLine = false;
                }
            }
        }

        return buf.toString();
    }

}








13.19.BreakIterator
13.19.1.Determining the Character Boundaries in a Unicode String
13.19.2.Determining the Word Boundaries in a Unicode String
13.19.3.Determining the Sentence Boundaries in a Unicode String
13.19.4.Determining Potential Line Breaks in a Unicode String
13.19.5.Word Wrap
13.19.6.Wrap multi-line strings (and get the individual lines)