com.code972.hebmorph.HebrewCharacters Maven / Gradle / Ivy

Go to download
Show more of this group Show more artifacts with this name
Show all versions of hebmorph-lucene Show documentation
There is a newer version: 6.6.1
/***************************************************************************
 *   Copyright (C) 2010-2015 by                                            *
 *      Itamar Syn-Hershko                      *
 *                                                                         *
 *   This program is free software; you can redistribute it and/or modify  *
 *   it under the terms of the GNU Affero General Public License           *
 *   version 3, 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 Affero General Public License for more details.                   *
 *                                                                         *
 *   You should have received a copy of the GNU Affero General Public      *
 *   License along with this program; if not, see                          *
 *   .                                       *
 **************************************************************************/
package com.code972.hebmorph;

import java.util.HashMap;

/**
 * Hebrew language constants
 *
 * @author synhershko
 */
public final class HebrewCharacters {
    // Letters
    public static char ALEPH = '\u05D0';
    public static char BET = '\u05D1';
    public static char GIMMEL = '\u05D2';
    public static char DALET = '\u05D3';
    public static char HE = '\u05D4';
    public static char VAV = '\u05D5';
    public static char ZAYIN = '\u05D6';
    public static char HET = '\u05D7';
    public static char TET = '\u05D8';
    public static char YOD = '\u05D9';
    public static char KAF_FINAL = '\u05DA';
    public static char KAF = '\u05DB';
    public static char LAMED = '\u05DC';
    public static char MEM_FINAL = '\u05DD';
    public static char MEM = '\u05DE';
    public static char NUN_FINAL = '\u05DF';
    public static char NUN = '\u05E0';
    public static char SAMEKH = '\u05E1';
    public static char AYIN = '\u05E2';
    public static char PE_FINAL = '\u05E3';
    public static char PE = '\u05E4';
    public static char TSADI = '\u05E5';
    public static char TSADI_FINAL = '\u05E6';
    public static char QUF = '\u05E7';
    public static char RESH = '\u05E8';
    public static char SHIN = '\u05E9';
    public static char TAV = '\u05EA';

    // Punctuation
    public static char GERESH = '\u05F3';
    public static char GERSHAYIM = '\u05F4';

    private static HashMap alternateCharacters = new HashMap<>();
    static{
        alternateCharacters.put('\uFB20', AYIN);
        alternateCharacters.put('\uFB21', ALEPH);
        alternateCharacters.put('\uFB22', DALET);
        alternateCharacters.put('\uFB23', HE);
        alternateCharacters.put('\uFB24', KAF);
        alternateCharacters.put('\uFB25', LAMED);
        alternateCharacters.put('\uFB26', MEM_FINAL);
        alternateCharacters.put('\uFB27', RESH);
        alternateCharacters.put('\uFB28', TAV);
    }

    public static char collapseAlternate(char ch){
        if (alternateCharacters.containsKey(ch)){
            return alternateCharacters.get(ch);
        }
        return ch;
    }
}