collationelementiterator.java

java源代码 请看看啊 提点宝贵的意见

/*
 * @(#)CollationElementIterator.java	1.45 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, 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.lang.Character;
import java.util.Vector;
import sun.text.Normalizer;
import sun.text.NormalizerUtilities;

/**
 * The <code>CollationElementIterator</code> class is used as an iterator
 * to walk through each character of an international string. Use the iterator
 * to return the ordering priority of the positioned character. The ordering
 * priority of a character, which we refer to as a key, defines how a character
 * is collated in the given collation object.
 *
 * <p>
 * For example, consider the following in Spanish:
 * <blockquote>
 * <pre>
 * "ca" -> the first key is key('c') and second key is key('a').
 * "cha" -> the first key is key('ch') and second key is key('a').
 * </pre>
 * </blockquote>
 * And in German,
 * <blockquote>
 * <pre>
 * "\u00e4b"-> the first key is key('a'), the second key is key('e'), and
 * the third key is key('b').
 * </pre>
 * </blockquote>
 * The key of a character is an integer composed of primary order(short),
 * secondary order(byte), and tertiary order(byte). Java strictly defines
 * the size and signedness of its primitive data types. Therefore, the static
 * functions <code>primaryOrder</code>, <code>secondaryOrder</code>, and
 * <code>tertiaryOrder</code> return <code>int</code>, <code>short</code>,
 * and <code>short</code> respectively to ensure the correctness of the key
 * value.
 *
 * <p>
 * Example of the iterator usage,
 * <blockquote>
 * <pre>
 *
 *  String testString = "This is a test";
 *  RuleBasedCollator ruleBasedCollator = (RuleBasedCollator)Collator.getInstance();
 *  CollationElementIterator collationElementIterator = ruleBasedCollator.getCollationElementIterator(testString);
 *  int primaryOrder = CollationElementIterator.primaryOrder(collationElementIterator.next());
 * </pre>
 * </blockquote>
 *
 * <p>
 * <code>CollationElementIterator.next</code> returns the collation order
 * of the next character. A collation order consists of primary order,
 * secondary order and tertiary order. The data type of the collation
 * order is <strong>int</strong>. The first 16 bits of a collation order
 * is its primary order; the next 8 bits is the secondary order and the
 * last 8 bits is the tertiary order.
 *
 * @see                Collator
 * @see                RuleBasedCollator
 * @version            1.24 07/27/98
 * @author             Helena Shih, Laura Werner, Richard Gillam
 */
public final class CollationElementIterator
{
    /**
     * Null order which indicates the end of string is reached by the
     * cursor.
     */
    public final static int NULLORDER = 0xffffffff;

    /**
     * CollationElementIterator constructor.  This takes the source string and
     * the collation object.  The cursor will walk thru the source string based
     * on the predefined collation rules.  If the source string is empty,
     * NULLORDER will be returned on the calls to next().
     * @param sourceText the source string.
     * @param order the collation object.
     */
    CollationElementIterator(String sourceText, RuleBasedCollator owner) {
        this.owner = owner;
        ordering = owner.getTables();
        if ( sourceText.length() != 0 ) {
            Normalizer.Mode mode =
                NormalizerUtilities.toNormalizerMode(owner.getDecomposition());
            text = new Normalizer(sourceText, mode);
        }
    }

    /**
     * CollationElementIterator constructor.  This takes the source string and
     * the collation object.  The cursor will walk thru the source string based
     * on the predefined collation rules.  If the source string is empty,
     * NULLORDER will be returned on the calls to next().
     * @param sourceText the source string.
     * @param order the collation object.
     */
    CollationElementIterator(CharacterIterator sourceText, RuleBasedCollator owner) {
        this.owner = owner;
        ordering = owner.getTables();
        Normalizer.Mode mode =
            NormalizerUtilities.toNormalizerMode(owner.getDecomposition());
        text = new Normalizer(sourceText, mode);
    }
    /**
     * Resets the cursor to the beginning of the string.  The next call
     * to next() will return the first collation element in the string.
     */
    public void reset()
    {
        if (text != null) {
            text.reset();
            Normalizer.Mode mode =
                NormalizerUtilities.toNormalizerMode(owner.getDecomposition());
            text.setMode(mode);
        }
        buffer = null;
        expIndex = 0;
        swapOrder = 0;
    }

    /**
     * Get the next collation element in the string.  <p>This iterator iterates
     * over a sequence of collation elements that were built from the string.
     * Because there isn't necessarily a one-to-one mapping from characters to
     * collation elements, this doesn't mean the same thing as "return the
     * collation element [or ordering priority] of the next character in the
     * string".</p>
     * <p>This function returns the collation element that the iterator is currently
     * pointing to and then updates the internal pointer to point to the next element.
     * previous() updates the pointer first and then returns the element.  This
     * means that when you change direction while iterating (i.e., call next() and
     * then call previous(), or call previous() and then call next()), you'll get
     * back the same element twice.</p>
     */
    public int next()
    {
        if (text == null) {
            return NULLORDER;
        }
        Normalizer.Mode textMode = text.getMode();
        // convert the owner's mode to something the Normalizer understands
        Normalizer.Mode ownerMode =
        NormalizerUtilities.toNormalizerMode(owner.getDecomposition());
        if (textMode != ownerMode) {
            text.setMode(ownerMode);
        }

        // if buffer contains any decomposed char values
        // return their strength orders before continuing in
        // the the Normalizer's CharacterIterator.
        if (buffer != null) {
            if (expIndex < buffer.length) {
                return strengthOrder(buffer[expIndex++]);
            } else {
                buffer = null;
                expIndex = 0;
            }
        } else if (swapOrder != 0) {
            int order = swapOrder << 16;
            swapOrder = 0;
            return order;
        }

        char ch  = text.next();

        // are we at the end of Normalizer's text?
        if (ch == Normalizer.DONE) {
            return NULLORDER;
        }

        int value = ordering.getUnicodeOrder(ch);
        if (value == RuleBasedCollator.UNMAPPED) {
            swapOrder = ch;
            return UNMAPPEDCHARVALUE;
        }
        else if (value >= RuleBasedCollator.CONTRACTCHARINDEX) {
            value = nextContractChar(ch);
        }
        if (value >= RuleBasedCollator.EXPANDCHARINDEX) {
            buffer = ordering.getExpandValueList(value);
            expIndex = 0;
            value = buffer[expIndex++];
        }

        if (ordering.isSEAsianSwapping()) {
            char consonant;
            if (isThaiPreVowel(ch)) {
                consonant = text.next();
                if (isThaiBaseConsonant(consonant)) {
                    buffer = makeReorderedBuffer(consonant, value, buffer, true);
                    value = buffer[0];
                    expIndex = 1;
                } else {
                    text.previous();
                }
            }
            if (isLaoPreVowel(ch)) {
                consonant = text.next();
                if (isLaoBaseConsonant(consonant)) {
                    buffer = makeReorderedBuffer(consonant, value, buffer, true);
                    value = buffer[0];
                    expIndex = 1;
                } else {
                    text.previous();
                }
            }
        }

        return strengthOrder(value);
    }

    /**
     * Get the previous collation element in the string.  <p>This iterator iterates
     * over a sequence of collation elements that were built from the string.
     * Because there isn't necessarily a one-to-one mapping from characters to
     * collation elements, this doesn't mean the same thing as "return the
     * collation element [or ordering priority] of the previous character in the
     * string".</p>
     * <p>This function updates the iterator's internal pointer to point to the
     * collation element preceding the one it's currently pointing to and then
     * returns that element, while next() returns the current element and then
     * updates the pointer.  This means that when you change direction while
     * iterating (i.e., call next() and then call previous(), or call previous()
     * and then call next()), you'll get back the same element twice.</p>
     * @since 1.2
     */
    public int previous()
    {
        if (text == null) {
            return NULLORDER;
        }
        Normalizer.Mode textMode = text.getMode();
        // convert the owner's mode to something the Normalizer understands
        Normalizer.Mode ownerMode =
        NormalizerUtilities.toNormalizerMode(owner.getDecomposition());
        if (textMode != ownerMode) {
            text.setMode(ownerMode);
        }
        if (buffer != null) {
            if (expIndex > 0) {
                return strengthOrder(buffer[--expIndex]);
            } else {
                buffer = null;
                expIndex = 0;
            }
        } else if (swapOrder != 0) {
              int order = swapOrder << 16;
            swapOrder = 0;
            return order;
        }
        char ch = text.previous();
        if (ch == Normalizer.DONE) {
            return NULLORDER;
        }

        int value = ordering.getUnicodeOrder(ch);

        if (value == RuleBasedCollator.UNMAPPED) {
            swapOrder = UNMAPPEDCHARVALUE;
            return ch;
        } else if (value >= RuleBasedCollator.CONTRACTCHARINDEX) {
            value = prevContractChar(ch);
        }
        if (value >= RuleBasedCollator.EXPANDCHARINDEX) {
            buffer = ordering.getExpandValueList(value);
            expIndex = buffer.length;
            value = buffer[--expIndex];
        }

        if (ordering.isSEAsianSwapping()) {
            char vowel;
            if (isThaiBaseConsonant(ch)) {
                vowel = text.previous();
                if (isThaiPreVowel(vowel)) {
                    buffer = makeReorderedBuffer(vowel, value, buffer, false);
                    expIndex = buffer.length - 1;
                    value = buffer[expIndex];
                } else {
                    text.next();
                }
            }
            if (isLaoBaseConsonant(ch)) {
                vowel = text.previous();
                if (isLaoPreVowel(vowel)) {
                    buffer = makeReorderedBuffer(vowel, value, buffer, false);
                    expIndex = buffer.length - 1;
                    value = buffer[expIndex];
                } else {
                    text.next();
                }
            }
        }

        return strengthOrder(value);
    }

    /**
     * Return the primary component of a collation element.
     * @param order the collation element
     * @return the element's primary component
     */
    public final static int primaryOrder(int order)
    {
        order &= RBCollationTables.PRIMARYORDERMASK;
        return (order >>> RBCollationTables.PRIMARYORDERSHIFT);
    }
    /**
     * Return the secondary component of a collation element.
     * @param order the collation element
     * @return the element's secondary component
     */
    public final static short secondaryOrder(int order)
    {
        order = order & RBCollationTables.SECONDARYORDERMASK;
        return ((short)(order >> RBCollationTables.SECONDARYORDERSHIFT));
    }
    /**
     * Return the tertiary component of a collation element.
     * @param order the collation element
     * @return the element's tertiary component
     */
    public final static short tertiaryOrder(int order)
    {
        return ((short)(order &= RBCollationTables.TERTIARYORDERMASK));
    }

    /**
     *  Get the comparison order in the desired strength.  Ignore the other
     *  differences.
     *  @param order The order value
     */
    final int strengthOrder(int order)
    {
        int s = owner.getStrength();
        if (s == Collator.PRIMARY)
        {
            order &= RBCollationTables.PRIMARYDIFFERENCEONLY;
        } else if (s == Collator.SECONDARY)
        {
            order &= RBCollationTables.SECONDARYDIFFERENCEONLY;
        }
        return order;
    }

    /**
     * Sets the iterator to point to the collation element corresponding to
     * the specified character (the parameter is a CHARACTER offset in the