collator.java

java源代码 请看看啊 提点宝贵的意见

/*
 * @(#)Collator.java	1.34 03/01/27
 *
 * Copyright 2003 Sun Microsystems, Inc. All rights reserved.
 * SUN PROPRIETARY/CONFIDENTIAL. Use is subject to license terms.
 */

/*
 * (C) Copyright Taligent, Inc. 1996-1998 -  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.Locale;
import java.util.MissingResourceException;
import java.util.ResourceBundle;
import sun.misc.SoftCache;
import sun.text.resources.LocaleData;


/**
 * The <code>Collator</code> class performs locale-sensitive
 * <code>String</code> comparison. You use this class to build
 * searching and sorting routines for natural language text.
 *
 * <p>
 * <code>Collator</code> is an abstract base class. Subclasses
 * implement specific collation strategies. One subclass,
 * <code>RuleBasedCollator</code>, is currently provided with
 * the Java 2 platform and is applicable to a wide set of languages. Other
 * subclasses may be created to handle more specialized needs.
 *
 * <p>
 * Like other locale-sensitive classes, you can use the static
 * factory method, <code>getInstance</code>, to obtain the appropriate
 * <code>Collator</code> object for a given locale. You will only need
 * to look at the subclasses of <code>Collator</code> if you need
 * to understand the details of a particular collation strategy or
 * if you need to modify that strategy.
 *
 * <p>
 * The following example shows how to compare two strings using
 * the <code>Collator</code> for the default locale.
 * <blockquote>
 * <pre>
 * // Compare two strings in the default locale
 * Collator myCollator = Collator.getInstance();
 * if( myCollator.compare("abc", "ABC") < 0 )
 *     System.out.println("abc is less than ABC");
 * else
 *     System.out.println("abc is greater than or equal to ABC");
 * </pre>
 * </blockquote>
 *
 * <p>
 * You can set a <code>Collator</code>'s <em>strength</em> property
 * to determine the level of difference considered significant in
 * comparisons. Four strengths are provided: <code>PRIMARY</code>,
 * <code>SECONDARY</code>, <code>TERTIARY</code>, and <code>IDENTICAL</code>.
 * The exact assignment of strengths to language features is
 * locale dependant.  For example, in Czech, "e" and "f" are considered
 * primary differences, while "e" and "\u00EA" are secondary differences,
 * "e" and "E" are tertiary differences and "e" and "e" are identical.
 * The following shows how both case and accents could be ignored for
 * US English.
 * <blockquote>
 * <pre>
 * //Get the Collator for US English and set its strength to PRIMARY
 * Collator usCollator = Collator.getInstance(Locale.US);
 * usCollator.setStrength(Collator.PRIMARY);
 * if( usCollator.compare("abc", "ABC") == 0 ) {
 *     System.out.println("Strings are equivalent");
 * }
 * </pre>
 * </blockquote>
 * <p>
 * For comparing <code>String</code>s exactly once, the <code>compare</code>
 * method provides the best performance. When sorting a list of
 * <code>String</code>s however, it is generally necessary to compare each
 * <code>String</code> multiple times. In this case, <code>CollationKey</code>s
 * provide better performance. The <code>CollationKey</code> class converts
 * a <code>String</code> to a series of bits that can be compared bitwise
 * against other <code>CollationKey</code>s. A <code>CollationKey</code> is
 * created by a <code>Collator</code> object for a given <code>String</code>.
 * <br>
 * <strong>Note:</strong> <code>CollationKey</code>s from different
 * <code>Collator</code>s can not be compared. See the class description
 * for {@link CollationKey}
 * for an example using <code>CollationKey</code>s.
 *
 * @see         RuleBasedCollator
 * @see         CollationKey
 * @see         CollationElementIterator
 * @see         Locale
 * @version     1.34, 01/27/03
 * @author      Helena Shih, Laura Werner, Richard Gillam
 */

public abstract class Collator implements java.util.Comparator, Cloneable {
    /**
     * Collator strength value.  When set, only PRIMARY differences are
     * considered significant during comparison. The assignment of strengths
     * to language features is locale dependant. A common example is for
     * different base letters ("a" vs "b") to be considered a PRIMARY difference.
     * @see java.text.Collator#setStrength
     * @see java.text.Collator#getStrength
     */
    public final static int PRIMARY = 0;
    /**
     * Collator strength value.  When set, only SECONDARY and above differences are
     * considered significant during comparison. The assignment of strengths
     * to language features is locale dependant. A common example is for
     * different accented forms of the same base letter ("a" vs "\u00E4") to be
     * considered a SECONDARY difference.
     * @see java.text.Collator#setStrength
     * @see java.text.Collator#getStrength
     */
    public final static int SECONDARY = 1;
    /**
     * Collator strength value.  When set, only TERTIARY and above differences are
     * considered significant during comparison. The assignment of strengths
     * to language features is locale dependant. A common example is for
     * case differences ("a" vs "A") to be considered a TERTIARY difference.
     * @see java.text.Collator#setStrength
     * @see java.text.Collator#getStrength
     */
    public final static int TERTIARY = 2;

    /**
     * Collator strength value.  When set, all differences are
     * considered significant during comparison. The assignment of strengths
     * to language features is locale dependant. A common example is for control
     * characters ("&#092;u0001" vs "&#092;u0002") to be considered equal at the
     * PRIMARY, SECONDARY, and TERTIARY levels but different at the IDENTICAL
     * level.  Additionally, differences between pre-composed accents such as
     * "&#092;u00C0" (A-grave) and combining accents such as "A&#092;u0300"
     * (A, combining-grave) will be considered significant at the tertiary
     * level if decomposition is set to NO_DECOMPOSITION.
     */
    public final static int IDENTICAL = 3;

    /**
     * Decomposition mode value. With NO_DECOMPOSITION
     * set, accented characters will not be decomposed for collation. This
     * is the default setting and provides the fastest collation but 
     * will only produce correct results for languages that do not use accents.
     * @see java.text.Collator#getDecomposition
     * @see java.text.Collator#setDecomposition
     */
    public final static int NO_DECOMPOSITION = 0;

    /**
     * Decomposition mode value. With CANONICAL_DECOMPOSITION
     * set, characters that are canonical variants according to Unicode 2.0
     * will be decomposed for collation. This 
     * should be used to get correct collation of accented characters.
     * <p>
     * CANONICAL_DECOMPOSITION corresponds to Normalization Form D as
     * described in 
     * <a href="http://www.unicode.org/unicode/reports/tr15/">Unicode 
     * Technical Report #15</a>.
     * @see java.text.Collator#getDecomposition
     * @see java.text.Collator#setDecomposition
     */
    public final static int CANONICAL_DECOMPOSITION = 1;

    /**
     * Decomposition mode value. With FULL_DECOMPOSITION
     * set, both Unicode canonical variants and Unicode compatibility variants
     * will be decomposed for collation.  This causes not only accented
     * characters to be collated, but also characters that have special formats
     * to be collated with their norminal form. For example, the half-width and
     * full-width ASCII and Katakana characters are then collated together.
     * FULL_DECOMPOSITION is the most complete and therefore the slowest
     * decomposition mode.
     * <p>
     * FULL_DECOMPOSITION corresponds to Normalization Form KD as
     * described in 
     * <a href="http://www.unicode.org/unicode/reports/tr15/">Unicode 
     * Technical Report #15</a>.
     * @see java.text.Collator#getDecomposition
     * @see java.text.Collator#setDecomposition
     */
    public final static int FULL_DECOMPOSITION = 2;

    /**
     * Gets the Collator for the current default locale.
     * The default locale is determined by java.util.Locale.getDefault.
     * @return the Collator for the default locale.(for example, en_US)
     * @see java.util.Locale#getDefault
     */
    public static synchronized Collator getInstance() {
        return getInstance(Locale.getDefault());
    }

    /**
     * Gets the Collator for the desired locale.
     * @param desiredLocale the desired locale.
     * @return the Collator for the desired locale.
     * @see java.util.Locale
     * @see java.util.ResourceBundle
     */
    public static synchronized
    Collator getInstance(Locale desiredLocale)
    {
        RuleBasedCollator result = null;
        result = (RuleBasedCollator) cache.get(desiredLocale);
        if (result != null) {
                 return (Collator)result.clone();  // make the world safe
        }

        // Load the resource of the desired locale from resource
        // manager.
        String colString = "";
        int decomp = CANONICAL_DECOMPOSITION;
        
        try {
            ResourceBundle resource = LocaleData.getLocaleElements(desiredLocale);

            colString = resource.getString("CollationElements");
            decomp = ((Integer)resource.getObject("CollationDecomp")).intValue();
        } catch (MissingResourceException e) {
            // Use default values
        }
        try
        {
            result = new RuleBasedCollator( CollationRules.DEFAULTRULES +
                                            colString,
                                            decomp );
        }
        catch(ParseException foo)
        {
            // predefined tables should contain correct grammar