breakiteratorrules.java

来自「This is a resource based on j2me embedde」· Java 代码 · 共 385 行 · 第 1/2 页

/*
 * 
 * @(#)BreakIteratorRules.java	1.22 06/10/10
 * 
 * Portions Copyright  2000-2008 Sun Microsystems, Inc. All Rights
 * Reserved.  Use is subject to license terms.
 * DO NOT ALTER OR REMOVE COPYRIGHT NOTICES OR THIS FILE HEADER
 * 
 * This program 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.
 * 
 * This program 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 at /legal/license.txt).
 * 
 * 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 Sun Microsystems, Inc., 4150 Network Circle, Santa
 * Clara, CA 95054 or visit www.sun.com if you need additional
 * information or have any questions.
 */

/*
 * Licensed Materials - Property of IBM
 *
 * (C) Copyright IBM Corp. 1999 All Rights Reserved.
 * (C) IBM Corp. 1997-1998.  All Rights Reserved.
 *
 * The program is provided "as is" without any warranty express or
 * implied, including the warranty of non-infringement and the implied
 * warranties of merchantibility and fitness for a particular purpose.
 * IBM will not be liable for any damages suffered by you as a result
 * of using the Program. In no event will IBM be liable for any
 * special, indirect or consequential damages or lost profits even if
 * IBM has been advised of the possibility of their occurrence. IBM
 * will not be liable for any third party claims against you.
 */

package sun.text.resources;

import java.util.ListResourceBundle;

/**
 * Default break-iterator rules.  These rules are more or less general for
 * all locales, although there are probably a few we're missing.  The
 * behavior currently mimics the behavior of BreakIterator in JDK 1.2.
 * There are known deficiencies in this behavior, including the fact that
 * the logic for handling CJK characters works for Japanese but not for
 * Chinese, and that we don't currently have an appropriate locale for
 * Thai.  The resources will eventually be updated to fix these problems.
 */

 /* Modified for Hindi 3/1/99. */

public class BreakIteratorRules extends ListResourceBundle {
    public Object[][] getContents() {
        return contents;
    }

    static final Object[][] contents = {
        // BreakIteratorClasses lists the class names to instantiate for each
        // built-in type of BreakIterator
        { "BreakIteratorClasses",
               new String[] { "RuleBasedBreakIterator",     // character-break iterator class
                              "RuleBasedBreakIterator",     // word-break iterator class
                              "RuleBasedBreakIterator",     // line-break iterator class
                              "RuleBasedBreakIterator" }    // sentence-break iterator class
        },

        // rules describing how to break between logical characters
        { "CharacterBreakRules",

      // ignore non-spacing marks and enclosing marks (since we never
      // put a break before ignore characters, this keeps combining
      // accents with the base characters they modify)
      "<enclosing>=[:Mn::Me:];"

      // other category definitions
      + "<choseong>=[\u1100-\u115f];"
      + "<jungseong>=[\u1160-\u11a7];"
      + "<jongseong>=[\u11a8-\u11ff];"
      + "<surr-hi>=[\ud800-\udbff];"
      + "<surr-lo>=[\udc00-\udfff];"

      // break after every character, except as follows:
      + ".;"

      // keep base and combining characters togethers
      + "<base>=[^<enclosing>^[:Cc::Cf::Zl::Zp:]];"
      + "<base><enclosing><enclosing>*;"

      // keep CRLF sequences together
      + "\r\n;"

      // keep surrogate pairs together
      + "<surr-hi><surr-lo>;"

      // keep Hangul syllables spelled out using conjoining jamo together
      + "<choseong>*<jungseong>*<jongseong>*;"

      // various additions for Hindi support
      + "<nukta>=[\u093c];"
      + "<danda>=[\u0964\u0965];"
      + "<virama>=[\u094d];"
      + "<devVowelSign>=[\u093e-\u094c\u0962\u0963];"
      + "<devConsonant>=[\u0915-\u0939];"
      + "<devNuktaConsonant>=[\u0958-\u095f];"
      + "<devCharEnd>=[\u0902\u0903\u0951-\u0954];"
      + "<devCAMN>=(<devConsonant>{<nukta>});"
      + "<devConsonant1>=(<devNuktaConsonant>|<devCAMN>);"
      + "<zwj>=[\u200d];"
      + "<devConjunct>=({<devConsonant1><virama>{<zwj>}}<devConsonant1>);"
      + "<devConjunct>{<devVowelSign>}{<devCharEnd>};"
      + "<danda><nukta>;"
        },

        // default rules for finding word boundaries
        { "WordBreakRules",
      // ignore non-spacing marks, enclosing marks, and format characters,
      // all of which should not influence the algorithm
      //"<ignore>=[:Mn::Me::Cf:];"
      "<ignore>=[:Cf:];"

      + "<enclosing>=[:Mn::Me:];"

      // Hindi phrase separator, kanji, katakana, hiragana, CJK diacriticals,
      // other letters, and digits
      + "<danda>=[\u0964\u0965];"
      + "<kanji>=[\u3005\u4e00-\u9fa5\uf900-\ufa2d];"
      + "<kata>=[\u30a1-\u30fa\u30fd\u30fe];"
      + "<hira>=[\u3041-\u3094\u309d\u309e];"
      + "<cjk-diacrit>=[\u3099-\u309c\u30fb\u30fc];"
      + "<letter-base>=[:L::Mc:^[<kanji><kata><hira><cjk-diacrit>]];"
      + "<let>=(<letter-base><enclosing>*);"
      + "<digit-base>=[:N:];"
      + "<dgt>=(<digit-base><enclosing>*);"

      // punctuation that can occur in the middle of a word: currently
      // dashes, apostrophes, quotation marks, and periods
      + "<mid-word>=[:Pd::Pc:\u00ad\u2027\\\"\\\'\\.];"

      // punctuation that can occur in the middle of a number: currently
      // apostrophes, qoutation marks, periods, commas, and the Arabic
      // decimal point
      + "<mid-num>=[\\\"\\\'\\,\u066b\\.];"

      // punctuation that can occur at the beginning of a number: currently
      // the period, the number sign, and all currency symbols except the cents sign
      + "<pre-num>=[:Sc:\\#\\.^\u00a2];"

      // punctuation that can occur at the end of a number: currently
      // the percent, per-thousand, per-ten-thousand, and Arabic percent
      // signs, the cents sign, and the ampersand
      + "<post-num>=[\\%\\&\u00a2\u066a\u2030\u2031];"

      // line separators: currently LF, FF, PS, and LS
      + "<ls>=[\n\u000c\u2028\u2029];"

      // whitespace: all space separators and the tab character
      + "<ws-base>=[:Zs:\t];"
      + "<ws>=(<ws-base><enclosing>*);"

      // a word is a sequence of letters that may contain internal
      // punctuation, as long as it begins and ends with a letter and
      // never contains two punctuation marks in a row
      + "<word>=((<let><let>*(<mid-word><let><let>*)*){<danda>});"

      // a number is a sequence of digits that may contain internal
      // punctuation, as long as it begins and ends with a digit and
      // never contains two punctuation marks in a row.
      + "<number>=(<dgt><dgt>*(<mid-num><dgt><dgt>*)*);"

      // break after every character, with the following exceptions
      // (this will cause punctuation marks that aren't considered
      // part of words or numbers to be treated as words unto themselves)
      + ".;"

      // keep together any sequence of contiguous words and numbers
      // (including just one of either), plus an optional trailing
      // number-suffix character
      + "{<word>}(<number><word>)*{<number>{<post-num>}};"

      // keep together and sequence of contiguous words and numbers
      // that starts with a number-prefix character and a number,
      // and may end with a number-suffix character
      + "<pre-num>(<number><word>)*{<number>{<post-num>}};"