Example usage for java.text BreakIterator setText

Introduction

In this page you can find the example usage for java.text BreakIterator setText.

Prototype

public abstract void setText(CharacterIterator newText);

Source Link

Document

Set a new text for scanning.

Usage

From source file:com.tao.realweb.util.StringUtil.java

/**
 * 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.// w w  w  . ja va  2s .  com
 *
 * @param text a String of text to convert into an array of words
 * @return text broken up into an array of words.
 */
public static String[] toLowerCaseWordArray(String text) {
    if (text == null || text.length() == 0) {
        return new String[0];
    }

    List<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 wordList.toArray(new String[wordList.size()]);
}