Converts a line of text into an array of lower case words using a BreakIterator.wordInstance().

Description

Demo Code

/**/*from  w ww  . jav  a  2s.  co m*/
     * Turns an array of bytes into a String representing each byte as an
     * unsigned hex number.
     * <p>
     * Method by Santeri Paavolainen, Helsinki Finland 1996<br>
     * (c) Santeri Paavolainen, Helsinki Finland 1996<br>
     * Distributed under LGPL.
     *
     * @param bytes
     *            an array of bytes to convert to a hex-string
     * @return generated hex string
     */
//package com.java2s;

import java.text.*;
import java.util.*;

public class Main {

    /**
     * Converts a line of text into an array of lower case words using a
     * BreakIterator.wordInstance().
     * <p>
     *
     * This method is under the Jive Open Source Software License and was
     * written by Mark Imbriaco.
     *
     * @param text
     *            a String of text to convert into an array of words
     * @return text broken up into an array of words.
     */
    public static final String[] toLowerCaseWordArray(String text) {
        if (text == null || text.length() == 0) {
            return new String[0];
        }

        ArrayList<String> wordList = new ArrayList<String>();
        BreakIterator boundary = BreakIterator.getWordInstance();
        boundary.setText(text);
        int start = 0;

        for (int end = boundary.next(); end != BreakIterator.DONE; start = end, end = boundary
                .next()) {
            String tmp = text.substring(start, end).trim();
            // Remove characters that are not needed.
            tmp = replace(tmp, "+", "");
            tmp = replace(tmp, "/", "");
            tmp = replace(tmp, "\\", "");
            tmp = replace(tmp, "#", "");
            tmp = replace(tmp, "*", "");
            tmp = replace(tmp, ")", "");
            tmp = replace(tmp, "(", "");
            tmp = replace(tmp, "&", "");
            if (tmp.length() > 0) {
                wordList.add(tmp);
            }
        }
        return (String[]) wordList.toArray(new String[wordList.size()]);
    }

    /**
     * Replaces all instances of oldString with newString in line.
     *
     * @param line
     *            the String to search to perform replacements on
     * @param oldString
     *            the String that should be replaced by newString
     * @param newString
     *            the String that will replace all instances of oldString
     *
     * @return a String will all instances of oldString replaced by newString
     */
    public static final String replace(String line, String oldString,
            String newString) {
        if (line == null) {
            return null;
        }
        int i = 0;
        if ((i = line.indexOf(oldString, i)) >= 0) {
            char[] line2 = line.toCharArray();
            char[] newString2 = newString.toCharArray();
            int oLength = oldString.length();
            StringBuffer buf = new StringBuffer(line2.length);
            buf.append(line2, 0, i).append(newString2);
            i += oLength;
            int j = i;
            while ((i = line.indexOf(oldString, i)) > 0) {
                buf.append(line2, j, i - j).append(newString2);
                i += oLength;
                j = i;
            }
            buf.append(line2, j, line2.length - j);
            return buf.toString();
        }
        return line;
    }

    /**
     * Replaces all instances of oldString with newString in line. The count
     * Integer is updated with number of replaces.
     *
     * @param line
     *            the String to search to perform replacements on
     * @param oldString
     *            the String that should be replaced by newString
     * @param newString
     *            the String that will replace all instances of oldString
     *
     * @return a String will all instances of oldString replaced by newString
     */
    public static final String replace(String line, String oldString,
            String newString, int[] count) {
        if (line == null) {
            return null;
        }
        int i = 0;
        if ((i = line.indexOf(oldString, i)) >= 0) {
            int counter = 0;
            counter++;
            char[] line2 = line.toCharArray();
            char[] newString2 = newString.toCharArray();
            int oLength = oldString.length();
            StringBuffer buf = new StringBuffer(line2.length);
            buf.append(line2, 0, i).append(newString2);
            i += oLength;
            int j = i;
            while ((i = line.indexOf(oldString, i)) > 0) {
                counter++;
                buf.append(line2, j, i - j).append(newString2);
                i += oLength;
                j = i;
            }
            buf.append(line2, j, line2.length - j);
            count[0] = counter;
            return buf.toString();
        }
        return line;
    }
}
Converts a line of text into an array of lower case words using a BreakIterator.wordInstance(). - Java java.text

Description

Demo Code

Related Tutorials
