breakiterator.java

java源代码 请看看啊 提点宝贵的意见

/*
 * @(#)BreakIterator.java	1.32 03/01/23
 *
 * Copyright 2003 Sun Microsystems, Inc. All rights reserved.
 * SUN PROPRIETARY/CONFIDENTIAL. Use is subject to license terms.
 */

/*
 * (C) Copyright Taligent, Inc. 1996, 1997 - All Rights Reserved
 * (C) Copyright IBM Corp. 1996 - 1998 - All Rights Reserved
 *
 * The original version of this source code and documentation
 * is copyrighted and owned by Taligent, Inc., a wholly-owned
 * subsidiary of IBM. These materials are provided under terms
 * of a License Agreement between Taligent and Sun. This technology
 * is protected by multiple US and International patents.
 *
 * This notice and attribution to Taligent may not be removed.
 * Taligent is a registered trademark of Taligent, Inc.
 *
 */

package java.text;

import java.util.Vector;
import java.util.Locale;
import java.util.ResourceBundle;
import java.util.MissingResourceException;
import sun.text.resources.LocaleData;
import java.text.CharacterIterator;
import java.text.StringCharacterIterator;

import java.net.URL;
import java.io.InputStream;
import java.io.IOException;

import java.lang.ref.SoftReference;
import java.security.AccessController;
import java.security.PrivilegedAction;

/**
 * The <code>BreakIterator</code> class implements methods for finding
 * the location of boundaries in text. Instances of <code>BreakIterator</code>
 * maintain a current position and scan over text
 * returning the index of characters where boundaries occur.
 * Internally, <code>BreakIterator</code> scans text using a
 * <code>CharacterIterator</code>, and is thus able to scan text held
 * by any object implementing that protocol. A <code>StringCharacterIterator</code>
 * is used to scan <code>String</code> objects passed to <code>setText</code>.
 *
 * <p>
 * You use the factory methods provided by this class to create
 * instances of various types of break iterators. In particular,
 * use <code>getWordIterator</code>, <code>getLineIterator</code>,
 * <code>getSentenceIterator</code>, and <code>getCharacterIterator</code>
 * to create <code>BreakIterator</code>s that perform
 * word, line, sentence, and character boundary analysis respectively.
 * A single <code>BreakIterator</code> can work only on one unit
 * (word, line, sentence, and so on). You must use a different iterator
 * for each unit boundary analysis you wish to perform.
 *
 * <p>
 * Line boundary analysis determines where a text string can be
 * broken when line-wrapping. The mechanism correctly handles
 * punctuation and hyphenated words.
 *
 * <p>
 * Sentence boundary analysis allows selection with correct interpretation
 * of periods within numbers and abbreviations, and trailing punctuation
 * marks such as quotation marks and parentheses.
 *
 * <p>
 * Word boundary analysis is used by search and replace functions, as
 * well as within text editing applications that allow the user to
 * select words with a double click. Word selection provides correct
 * interpretation of punctuation marks within and following
 * words. Characters that are not part of a word, such as symbols
 * or punctuation marks, have word-breaks on both sides.
 *
 * <p>
 * Character boundary analysis allows users to interact with characters
 * as they expect to, for example, when moving the cursor through a text
 * string. Character boundary analysis provides correct navigation of
 * through character strings, regardless of how the character is stored.
 * For example, an accented character might be stored as a base character
 * and a diacritical mark. What users consider to be a character can
 * differ between languages.
 *
 * <p>
 * <code>BreakIterator</code> is intended for use with natural
 * languages only. Do not use this class to tokenize a programming language.
 *
 * <P>
 * <strong>Examples</strong>:<P>
 * Creating and using text boundaries
 * <blockquote>
 * <pre>
 * public static void main(String args[]) {
 *      if (args.length == 1) {
 *          String stringToExamine = args[0];
 *          //print each word in order
 *          BreakIterator boundary = BreakIterator.getWordInstance();
 *          boundary.setText(stringToExamine);
 *          printEachForward(boundary, stringToExamine);
 *          //print each sentence in reverse order
 *          boundary = BreakIterator.getSentenceInstance(Locale.US);
 *          boundary.setText(stringToExamine);
 *          printEachBackward(boundary, stringToExamine);
 *          printFirst(boundary, stringToExamine);
 *          printLast(boundary, stringToExamine);
 *      }
 * }
 * </pre>
 * </blockquote>
 *
 * Print each element in order
 * <blockquote>
 * <pre>
 * public static void printEachForward(BreakIterator boundary, String source) {
 *     int start = boundary.first();
 *     for (int end = boundary.next();
 *          end != BreakIterator.DONE;
 *          start = end, end = boundary.next()) {
 *          System.out.println(source.substring(start,end));
 *     }
 * }
 * </pre>
 * </blockquote>
 *
 * Print each element in reverse order
 * <blockquote>
 * <pre>
 * public static void printEachBackward(BreakIterator boundary, String source) {
 *     int end = boundary.last();
 *     for (int start = boundary.previous();
 *          start != BreakIterator.DONE;
 *          end = start, start = boundary.previous()) {
 *         System.out.println(source.substring(start,end));
 *     }
 * }
 * </pre>
 * </blockquote>
 *
 * Print first element
 * <blockquote>
 * <pre>
 * public static void printFirst(BreakIterator boundary, String source) {
 *     int start = boundary.first();
 *     int end = boundary.next();
 *     System.out.println(source.substring(start,end));
 * }
 * </pre>
 * </blockquote>
 *
 * Print last element
 * <blockquote>
 * <pre>
 * public static void printLast(BreakIterator boundary, String source) {
 *     int end = boundary.last();
 *     int start = boundary.previous();
 *     System.out.println(source.substring(start,end));
 * }
 * </pre>
 * </blockquote>
 *
 * Print the element at a specified position
 * <blockquote>
 * <pre>
 * public static void printAt(BreakIterator boundary, int pos, String source) {
 *     int end = boundary.following(pos);
 *     int start = boundary.previous();
 *     System.out.println(source.substring(start,end));
 * }
 * </pre>
 * </blockquote>
 *
 * Find the next word
 * <blockquote>
 * <pre>
 * public static int nextWordStartAfter(int pos, String text) {
 *     BreakIterator wb = BreakIterator.getWordInstance();
 *     wb.setText(text);
 *     int last = wb.following(pos);
 *     int current = wb.next();
 *     while (current != BreakIterator.DONE) {
 *         for (int p = last; p < current; p++) {
 *             if (Character.isLetter(text.charAt(p))
 *                 return last;
 *         }
 *         last = current;
 *         current = wb.next();
 *     }
 *     return BreakIterator.DONE;
 * }
 * </pre>
 * (The iterator returned by BreakIterator.getWordInstance() is unique in that
 * the break positions it returns don't represent both the start and end of the
 * thing being iterated over.  That is, a sentence-break iterator returns breaks
 * that each represent the end of one sentence and the beginning of the next.
 * With the word-break iterator, the characters between two boundaries might be a
 * word, or they might be the punctuation or whitespace between two words.  The
 * above code uses a simple heuristic to determine which boundary is the beginning
 * of a word: If the characters between this boundary and the next boundary
 * include at least one letter (this can be an alphabetical letter, a CJK ideograph,
 * a Hangul syllable, a Kana character, etc.), then the text between this boundary
 * and the next is a word; otherwise, it's the material between words.)
 * </blockquote>

 *
 * @see CharacterIterator
 *
 */

public abstract class BreakIterator implements Cloneable
{
    /**
     * Constructor. BreakIterator is stateless and has no default behavior.
     */
    protected BreakIterator()
    {
    }

    /**
     * Create a copy of this iterator
     * @return A copy of this
     */
    public Object clone()
    {
        try {
            return super.clone();
        }
        catch (CloneNotSupportedException e) {
            throw new InternalError();
        }
    }

    /**
     * DONE is returned by previous() and next() after all valid
     * boundaries have been returned.
     */
    public static final int DONE = -1;

    /**
     * Return the first boundary. The iterator's current position is set
     * to the first boundary.
     * @return The character index of the first text boundary.
     */
    public abstract int first();

    /**
     * Return the last boundary. The iterator's current position is set
     * to the last boundary.
     * @return The character index of the last text boundary.
     */
    public abstract int last();

    /**
     * Return the nth boundary from the current boundary
     * @param n which boundary to return.  A value of 0
     * does nothing.  Negative values move to previous boundaries
     * and positive values move to later boundaries.
     * @return The index of the nth boundary from the current position.
     */
    public abstract int next(int n);

    /**
     * Return the boundary following the current boundary.
     * @return The character index of the next text boundary or DONE if all
     * boundaries have been returned.  Equivalent to next(1).
     */
    public abstract int next();

    /**
     * Return the boundary preceding the current boundary.
     * @return The character index of the previous text boundary or DONE if all
     * boundaries have been returned.
     */
    public abstract int previous();

    /**
     * Return the first boundary following the specified offset.
     * The value returned is always greater than the offset or
     * the value BreakIterator.DONE
     * @param offset the offset to begin scanning. Valid values
     * are determined by the CharacterIterator passed to
     * setText().  Invalid values cause
     * an IllegalArgumentException to be thrown.