Java example source code file (ComposedCharIter.java)

This example Java source code file (ComposedCharIter.java) is included in the alvinalexander.com "Java Source Code Warehouse" project. The intent of this project is to help you "Learn Java by Example" ^TM.

Learn more about this Java project at its project page.

Java - Java tags/keywords

composedchariter, done, string, tbd, unicode

The ComposedCharIter.java Java example source code

/*
 * Copyright (c) 2001, 2005, Oracle and/or its affiliates. All rights reserved.
 * DO NOT ALTER OR REMOVE COPYRIGHT NOTICES OR THIS FILE HEADER.
 *
 * This code is free software; you can redistribute it and/or modify it
 * under the terms of the GNU General Public License version 2 only, as
 * published by the Free Software Foundation.  Oracle designates this
 * particular file as subject to the "Classpath" exception as provided
 * by Oracle in the LICENSE file that accompanied this code.
 *
 * This code 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
 * version 2 for more details (a copy is included in the LICENSE file that
 * accompanied this code).
 *
 * You should have received a copy of the GNU General Public License version
 * 2 along with this work; if not, write to the Free Software Foundation,
 * Inc., 51 Franklin St, Fifth Floor, Boston, MA 02110-1301 USA.
 *
 * Please contact Oracle, 500 Oracle Parkway, Redwood Shores, CA 94065 USA
 * or visit www.oracle.com if you need additional information or have any
 * questions.
 */

package sun.text;

import sun.text.normalizer.NormalizerBase;
import sun.text.normalizer.NormalizerImpl;

public final class ComposedCharIter {
    /**
     * Constant that indicates the iteration has completed.
     * {@link #next} returns this value when there are no more composed characters
     * over which to iterate.
     */
    public static final int DONE = NormalizerBase.DONE;

    //cache the decomps mapping, so the seconde composedcharIter does
    //not need to get the data again.
    private static int chars[];
    private static String decomps[];
    private static int decompNum;

    static {
        int maxNum = 2000;     //TBD: Unicode 4.0 only has 1926 canoDecomp...
        chars = new int[maxNum];
        decomps = new String[maxNum];
        decompNum = NormalizerImpl.getDecompose(chars, decomps);
    }

    /**
     * Construct a new <tt>ComposedCharIter.  The iterator will return
     * all Unicode characters with canonical decompositions, excluding Korean
     * Hangul characters.
     */
    public ComposedCharIter() { }

    /**
     * Returns the next precomposed Unicode character.
     * Repeated calls to <tt>next return all of the precomposed characters defined
     * by Unicode, in ascending order.  After all precomposed characters have
     * been returned, {@link #hasNext} will return <tt>false and further calls
     * to <tt>next will return {@link #DONE}.
     */
    public int next() {
        if (curChar == decompNum - 1) {
            return DONE;
        }
        return chars[++curChar];
    }

    /**
     * Returns the Unicode decomposition of the current character.
     * This method returns the decomposition of the precomposed character most
     * recently returned by {@link #next}.  The resulting decomposition is
     * affected by the settings of the options passed to the constructor.
     */
    public String decomposition() {
        return decomps[curChar];
    }
    private int curChar = -1;
}