rulebasedbreakiterator.java

java源代码 请看看啊 提点宝贵的意见

/*
 * @(#)RuleBasedBreakIterator.java	1.13 03/01/23
 *
 * Copyright 2003 Sun Microsystems, Inc. All rights reserved.
 * SUN PROPRIETARY/CONFIDENTIAL. Use is subject to license terms.
 */

/*
 * @(#)RuleBasedBreakIterator.java	1.3 99/04/07
 *
 * (C) Copyright Taligent, Inc. 1996, 1997 - All Rights Reserved
 * (C) Copyright IBM Corp. 1996 - 2002 - 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.Stack;
import java.util.Hashtable;
import java.util.Enumeration;
import java.text.CharacterIterator;
import java.text.StringCharacterIterator;
import sun.text.CompactByteArray;

/**
 * <p>A subclass of BreakIterator whose behavior is specified using a list of rules.</p>
 *
 * <p>There are two kinds of rules, which are separated by semicolons: <i>substitutions</i>
 * and <i>regular expressions.</i></p>
 *
 * <p>A substitution rule defines a name that can be used in place of an expression. It
 * consists of a name, which is a string of characters contained in angle brackets, an equals
 * sign, and an expression. (There can be no whitespace on either side of the equals sign.)
 * To keep its syntactic meaning intact, the expression must be enclosed in parentheses or
 * square brackets. A substitution is visible after its definition, and is filled in using
 * simple textual substitution. Substitution definitions can contain other substitutions, as
 * long as those substitutions have been defined first. Substitutions are generally used to
 * make the regular expressions (which can get quite complex) shorted and easier to read.
 * They typically define either character categories or commonly-used subexpressions.</p>
 *
 * <p>There is one special substitution.&nbsp; If the description defines a substitution
 * called &quot;&lt;ignore&gt;&quot;, the expression must be a [] expression, and the
 * expression defines a set of characters (the &quot;<em>ignore characters</em>&quot;) that
 * will be transparent to the BreakIterator.&nbsp; A sequence of characters will break the
 * same way it would if any ignore characters it contains are taken out.&nbsp; Break
 * positions never occur befoer ignore characters.</p>
 *
 * <p>A regular expression uses a subset of the normal Unix regular-expression syntax, and
 * defines a sequence of characters to be kept together. With one significant exception, the
 * iterator uses a longest-possible-match algorithm when matching text to regular
 * expressions. The iterator also treats descriptions containing multiple regular expressions
 * as if they were ORed together (i.e., as if they were separated by |).</p>
 *
 * <p>The special characters recognized by the regular-expression parser are as follows:</p>
 *
 * <blockquote>
 *   <table border="1" width="100%">
 *     <tr>
 *       <td width="6%">*</td>
 *       <td width="94%">Specifies that the expression preceding the asterisk may occur any number
 *       of times (including not at all).</td>
 *     </tr>
 *     <tr>
 *       <td width="6%">{}</td>
 *       <td width="94%">Encloses a sequence of characters that is optional.</td>
 *     </tr>
 *     <tr>
 *       <td width="6%">()</td>
 *       <td width="94%">Encloses a sequence of characters.&nbsp; If followed by *, the sequence
 *       repeats.&nbsp; Otherwise, the parentheses are just a grouping device and a way to delimit
 *       the ends of expressions containing |.</td>
 *     </tr>
 *     <tr>
 *       <td width="6%">|</td>
 *       <td width="94%">Separates two alternative sequences of characters.&nbsp; Either one
 *       sequence or the other, but not both, matches this expression.&nbsp; The | character can
 *       only occur inside ().</td>
 *     </tr>
 *     <tr>
 *       <td width="6%">.</td>
 *       <td width="94%">Matches any character.</td>
 *     </tr>
 *     <tr>
 *       <td width="6%">*?</td>
 *       <td width="94%">Specifies a non-greedy asterisk.&nbsp; *? works the same way as *, except
 *       when there is overlap between the last group of characters in the expression preceding the
 *       * and the first group of characters following the *.&nbsp; When there is this kind of
 *       overlap, * will match the longest sequence of characters that match the expression before
 *       the *, and *? will match the shortest sequence of characters matching the expression
 *       before the *?.&nbsp; For example, if you have &quot;xxyxyyyxyxyxxyxyxyy&quot; in the text,
 *       &quot;x[xy]*x&quot; will match through to the last x (i.e., &quot;<strong>xxyxyyyxyxyxxyxyx</strong>yy&quot;,
 *       but &quot;x[xy]*?x&quot; will only match the first two xes (&quot;<strong>xx</strong>yxyyyxyxyxxyxyxyy&quot;).</td>
 *     </tr>
 *     <tr>
 *       <td width="6%">[]</td>
 *       <td width="94%">Specifies a group of alternative characters.&nbsp; A [] expression will
 *       match any single character that is specified in the [] expression.&nbsp; For more on the
 *       syntax of [] expressions, see below.</td>
 *     </tr>
 *     <tr>
 *       <td width="6%">/</td>
 *       <td width="94%">Specifies where the break position should go if text matches this
 *       expression.&nbsp; (e.g., &quot;[a-z]&#42;/[:Zs:]*[1-0]&quot; will match if the iterator sees a run
 *       of letters, followed by a run of whitespace, followed by a digit, but the break position
 *       will actually go before the whitespace).&nbsp; Expressions that don't contain / put the
 *       break position at the end of the matching text.</td>
 *     </tr>
 *     <tr>
 *       <td width="6%">\</td>
 *       <td width="94%">Escape character.&nbsp; The \ itself is ignored, but causes the next
 *       character to be treated as literal character.&nbsp; This has no effect for many
 *       characters, but for the characters listed above, this deprives them of their special
 *       meaning.&nbsp; (There are no special escape sequences for Unicode characters, or tabs and
 *       newlines; these are all handled by a higher-level protocol.&nbsp; In a Java string,
 *       &quot;\n&quot; will be converted to a literal newline character by the time the
 *       regular-expression parser sees it.&nbsp; Of course, this means that \ sequences that are
 *       visible to the regexp parser must be written as \\ when inside a Java string.)&nbsp; All
 *       characters in the ASCII range except for letters, digits, and control characters are
 *       reserved characters to the parser and must be preceded by \ even if they currently don't
 *       mean anything.</td>
 *     </tr>
 *     <tr>
 *       <td width="6%">!</td>
 *       <td width="94%">If ! appears at the beginning of a regular expression, it tells the regexp
 *       parser that this expression specifies the backwards-iteration behavior of the iterator,
 *       and not its normal iteration behavior.&nbsp; This is generally only used in situations
 *       where the automatically-generated backwards-iteration brhavior doesn't produce
 *       satisfactory results and must be supplemented with extra client-specified rules.</td>
 *     </tr>
 *     <tr>
 *       <td width="6%"><em>(all others)</em></td>
 *       <td width="94%">All other characters are treated as literal characters, which must match
 *       the corresponding character(s) in the text exactly.</td>
 *     </tr>
 *   </table>
 * </blockquote>
 *
 * <p>Within a [] expression, a number of other special characters can be used to specify
 * groups of characters:</p>
 *
 * <blockquote>
 *   <table border="1" width="100%">
 *     <tr>
 *       <td width="6%">-</td>
 *       <td width="94%">Specifies a range of matching characters.&nbsp; For example
 *       &quot;[a-p]&quot; matches all lowercase Latin letters from a to p (inclusive).&nbsp; The -
 *       sign specifies ranges of continuous Unicode numeric values, not ranges of characters in a
 *       language's alphabetical order: &quot;[a-z]&quot; doesn't include capital letters, nor does
 *       it include accented letters such as a-umlaut.</td>
 *     </tr>
 *     <tr>
 *       <td width="6%">::</td>
 *       <td width="94%">A pair of colons containing a one- or two-letter code matches all
 *       characters in the corresponding Unicode category.&nbsp; The two-letter codes are the same
 *       as the two-letter codes in the Unicode database (for example, &quot;[:Sc::Sm:]&quot;
 *       matches all currency symbols and all math symbols).&nbsp; Specifying a one-letter code is
 *       the same as specifying all two-letter codes that begin with that letter (for example,
 *       &quot;[:L:]&quot; matches all letters, and is equivalent to
 *       &quot;[:Lu::Ll::Lo::Lm::Lt:]&quot;).&nbsp; Anything other than a valid two-letter Unicode
 *       category code or a single letter that begins a Unicode category code is illegal within
 *       colons.</td>
 *     </tr>
 *     <tr>
 *       <td width="6%">[]</td>
 *       <td width="94%">[] expressions can nest.&nbsp; This has no effect, except when used in
 *       conjunction with the ^ token.</td>
 *     </tr>
 *     <tr>
 *       <td width="6%">^</td>
 *       <td width="94%">Excludes the character (or the characters in the [] expression) following
 *       it from the group of characters.&nbsp; For example, &quot;[a-z^p]&quot; matches all Latin
 *       lowercase letters except p.&nbsp; &quot;[:L:^[&#92;u4e00-&#92;u9fff]]&quot; matches all letters
 *       except the Han ideographs.</td>
 *     </tr>
 *     <tr>
 *       <td width="6%"><em>(all others)</em></td>
 *       <td width="94%">All other characters are treated as literal characters.&nbsp; (For
 *       example, &quot;[aeiou]&quot; specifies just the letters a, e, i, o, and u.)</td>
 *     </tr>
 *   </table>
 * </blockquote>
 *
 * <p>For a more complete explanation, see <a
 * href="http://www.ibm.com/java/education/boundaries/boundaries.html">http://www.ibm.com/java/education/boundaries/boundaries.html</a>.
 * &nbsp; For examples, see the resource data (which is annotated).</p>
 *
 * @author Richard Gillam
 * @version $RCSFile$ $Revision: 1.1 $ $Date: 1998/11/05 19:32:04 $
 */
class RuleBasedBreakIterator extends BreakIterator {

    /**
     * A token used as a character-category value to identify ignore characters
     */
    protected static final byte IGNORE = -1;

    /**
     * The state number of the starting state
     */
    private static final short START_STATE = 1;

    /**
     * The state-transition value indicating "stop"
     */
    private static final short STOP_STATE = 0;

    /**
     * The textual description this iterator was created from
     */
    private String description;

    /**
     * A table that indexes from character values to character category numbers
     */
    private CompactByteArray charCategoryTable = null;

    /**
     * The table of state transitions used for forward iteration
     */
    private short[] stateTable = null;

    /**
     * The table of state transitions used to sync up the iterator with the
     * text in backwards and random-access iteration
     */
    private short[] backwardsStateTable = null;

    /**
     * A list of flags indicating which states in the state table are accepting
     * ("end") states
     */
    private boolean[] endStates = null;

    /**
     * A list of flags indicating which states in the state table are
     * lookahead states (states which turn lookahead on and off)
     */
    private boolean[] lookaheadStates = null;

    /**
     * The number of character categories (and, thus, the number of columns in
     * the state tables)
     */
    private int numCategories;

    /**
     * The character iterator through which this BreakIterator accesses the text
     */
    private CharacterIterator text = null;

    //=======================================================================
    // constructors
    //=======================================================================

    /**
     * Constructs a RuleBasedBreakIterator according to the description
     * provided.  If the description is malformed, throws an
     * IllegalArgumentException.  Normally, instead of constructing a
     * RuleBasedBreakIterator directory, you'll use the factory methods
     * on BreakIterator to create one indirectly from a description
     * in the framework's resource files.  You'd use this when you want
     * special behavior not provided by the built-in iterators.
     */
    public RuleBasedBreakIterator(String description) {
        this.description = description;

        // the actual work is done by the Builder class
        Builder builder = makeBuilder();
        builder.buildBreakIterator();
    }

    /**
     * Creates a Builder.
     */
    protected Builder makeBuilder() {
        return new Builder();
    }

    //=======================================================================
    // boilerplate
    //=======================================================================
    /**
     * Clones this iterator.
     * @return A newly-constructed RuleBasedBreakIterator with the same
     * behavior as this one.