/* The following code was generated by JFlex 1.5.1 */
package edu.stanford.nlp.international.arabic.process;
import edu.stanford.nlp.util.logging.Redwood;
import java.io.Reader;
import java.util.Map;
import java.util.Properties;
import java.util.regex.Pattern;
import edu.stanford.nlp.ling.CoreLabel;
import edu.stanford.nlp.ling.CoreAnnotations;
import edu.stanford.nlp.process.LexedTokenFactory;
import edu.stanford.nlp.util.Generics;
import edu.stanford.nlp.util.PropertiesUtils;
/**
* Tokenizer for UTF-8 Arabic. Supports raw text and both sections
* (vocalized and unvocalized) of the ATB.
*
* @author Spence Green
*/
public class ArabicLexer {
/** A logger for this class */
private static Redwood.RedwoodChannels log = Redwood.channels(ArabicLexer.class);
/** This character denotes the end of file */
public static final int YYEOF = -1;
/** initial size of the lookahead buffer */
private static final int ZZ_BUFFERSIZE = 16384;
/** lexical states */
public static final int YYINITIAL = 0;
/**
* ZZ_LEXSTATE[l] is the state in the DFA for the lexical state l
* ZZ_LEXSTATE[l+1] is the state in the DFA for the lexical state l
* at the beginning of a line
* l is of the form l = 2*k, k a non negative integer
*/
private static final int ZZ_LEXSTATE[] = {
0, 0
};
/**
* Translates characters to character classes
*/
private static final String ZZ_CMAP_PACKED =
"\11\0\1\35\1\2\1\3\1\4\1\1\22\0\1\35\1\37\1\36"+
"\1\7\1\44\2\7\1\44\2\36\1\7\1\23\1\40\1\15\1\6"+
"\1\34\12\45\1\33\1\44\1\36\1\44\1\36\1\37\1\77\1\52"+
"\1\103\1\55\1\73\1\65\1\52\1\71\1\46\3\52\1\101\1\61"+
"\1\63\1\57\1\50\1\52\1\67\1\53\1\47\1\75\1\52\1\51"+
"\3\52\1\16\1\12\1\22\1\44\1\14\1\44\1\42\1\102\1\54"+
"\1\72\1\64\1\42\1\70\1\27\3\42\1\100\1\60\1\62\1\56"+
"\1\31\1\42\1\66\1\43\1\30\1\74\1\42\1\41\3\42\1\37"+
"\1\36\1\37\1\7\6\0\1\3\32\0\1\76\11\7\1\25\2\7"+
"\1\25\7\7\1\25\4\7\1\25\5\7\27\24\1\0\37\24\1\0"+
"\207\24\1\32\267\24\31\24\162\24\4\24\14\24\16\24\5\24\7\24"+
"\1\24\1\24\1\24\201\24\5\24\1\24\2\24\2\24\4\24\6\0"+
"\2\24\1\24\1\0\3\24\1\0\1\24\1\0\24\24\1\0\54\24"+
"\1\24\46\24\1\24\5\24\4\24\202\24\1\0\5\24\2\0\105\24"+
"\1\24\46\24\12\24\20\24\26\24\2\24\11\0\46\24\2\0\1\24"+
"\6\24\1\0\47\24\11\0\55\24\1\0\1\24\1\0\2\24\1\0"+
"\2\24\1\0\1\24\10\0\33\24\5\0\3\24\15\0\14\7\2\11"+
"\15\13\5\7\1\24\43\26\1\21\1\26\1\17\4\26\4\13\1\20"+
"\17\13\1\0\12\10\1\7\2\11\1\7\2\26\1\13\143\26\1\7"+
"\1\26\17\13\2\26\7\13\2\26\12\10\3\26\2\13\1\26\17\0"+
"\1\24\1\24\1\24\36\24\35\24\63\24\46\24\13\24\1\24\16\0"+
"\12\10\41\24\11\24\2\24\4\0\1\24\5\0\26\24\4\0\1\24"+
"\11\0\1\24\3\0\1\24\27\0\31\24\107\0\1\24\1\0\13\24"+
"\123\0\4\24\66\24\2\0\1\24\1\24\21\24\1\0\1\24\5\24"+
"\2\0\12\24\2\24\2\0\12\10\1\0\7\24\1\0\7\24\1\0"+
"\3\24\1\0\10\24\2\0\2\24\2\0\26\24\1\0\7\24\1\0"+
"\1\24\3\0\4\24\2\0\1\24\1\24\7\24\2\0\2\24\2\0"+
"\3\24\1\24\10\0\1\24\4\0\2\24\1\0\3\24\2\24\2\0"+
"\12\10\2\24\17\0\3\24\1\0\6\24\4\0\2\24\2\0\26\24"+
"\1\0\7\24\1\0\2\24\1\0\2\24\1\0\2\24\2\0\1\24"+
"\1\0\22\24\11\0\4\24\1\0\1\24\7\0\12\10\2\0\3\24"+
"\14\0\3\24\1\0\11\24\1\0\3\24\1\0\26\24\1\0\7\24"+
"\1\0\2\24\1\0\5\24\2\0\1\24\1\24\22\24\1\24\17\0"+
"\2\24\4\0\12\10\25\0\10\24\2\0\2\24\2\0\26\24\1\0"+
"\7\24\1\0\2\24\1\0\5\24\3\0\1\24\36\0\2\24\1\0"+
"\3\24\4\0\12\10\1\0\1\24\20\0\1\24\1\24\1\0\6\24"+
"\3\0\3\24\1\0\4\24\3\0\2\24\1\0\1\24\1\0\2\24"+
"\3\0\2\24\3\0\3\24\3\0\14\24\4\0\5\24\3\0\3\24"+
"\1\0\4\24\2\0\1\24\25\0\12\10\21\0\3\24\1\0\10\24"+
"\1\0\3\24\1\0\27\24\1\0\12\24\1\0\5\24\3\0\1\24"+
"\31\24\1\0\2\24\6\0\2\24\4\0\12\10\25\0\10\24\1\0"+
"\3\24\1\0\27\24\1\0\12\24\1\0\5\24\3\0\1\24\40\0"+
"\1\24\1\0\2\24\4\0\12\10\1\0\2\24\22\0\10\24\1\0"+
"\3\24\1\0\51\24\2\0\1\24\7\24\1\0\3\24\5\0\1\24"+
"\21\0\2\24\4\0\12\10\12\0\6\24\5\0\22\24\3\0\30\24"+
"\1\0\11\24\1\0\1\24\2\0\7\24\72\0\57\24\1\24\1\24"+
"\2\24\7\24\5\0\7\24\10\24\1\0\12\10\47\0\2\24\1\0"+
"\1\24\2\0\2\24\1\0\1\24\2\0\1\24\6\0\4\24\1\0"+
"\7\24\1\0\3\24\1\0\1\24\1\0\1\24\2\0\2\24\1\0"+
"\4\24\1\24\2\24\11\24\1\24\2\0\5\24\1\0\1\24\1\0"+
"\6\24\2\0\12\10\2\0\4\24\40\0\1\24\37\0\12\10\26\0"+
"\10\24\1\0\44\24\33\0\5\24\163\0\53\24\24\0\1\24\12\10"+
"\6\0\6\24\4\0\4\24\3\0\1\24\3\0\2\24\7\0\3\24"+
"\4\0\15\24\14\0\1\24\1\0\12\10\6\0\46\24\1\0\1\24"+
"\5\0\1\24\2\0\53\24\1\0\u014d\24\1\0\4\24\2\0\7\24"+
"\1\0\1\24\1\0\4\24\2\0\51\24\1\0\4\24\2\0\41\24"+
"\1\0\4\24\2\0\7\24\1\0\1\24\1\0\4\24\2\0\17\24"+
"\1\0\71\24\1\0\4\24\2\0\103\24\45\0\20\24\20\0\125\24"+
"\14\0\u026c\24\2\0\21\24\1\0\32\24\5\0\113\24\25\0\15\24"+
"\1\0\4\24\16\0\22\24\16\0\22\24\16\0\15\24\1\0\3\24"+
"\17\0\64\24\43\0\1\24\4\0\1\24\3\0\12\10\46\0\12\10"+
"\6\0\130\24\10\0\51\24\1\0\1\24\5\0\106\24\12\0\35\24"+
"\51\0\12\10\36\24\2\0\5\24\13\0\54\24\25\0\7\24\10\0"+
"\12\10\46\0\27\24\11\0\65\24\53\0\12\10\6\0\12\10\15\0"+
"\1\24\135\0\57\24\21\0\7\24\4\0\12\10\51\0\36\24\15\0"+
"\2\24\12\10\54\24\32\0\44\24\34\0\12\10\3\0\3\24\12\10"+
"\44\24\153\0\4\24\1\0\4\24\3\0\2\24\11\0\300\24\100\0"+
"\u0116\24\2\0\6\24\2\0\46\24\2\0\6\24\2\0\10\24\1\0"+
"\1\24\1\0\1\24\1\0\1\24\1\0\37\24\2\0\65\24\1\0"+
"\7\24\1\0\1\24\3\0\3\24\1\0\7\24\3\0\4\24\2\0"+
"\6\24\4\0\15\24\5\0\3\24\1\0\7\24\3\0\13\5\5\0"+
"\30\7\1\3\1\3\5\0\1\5\57\7\22\0\1\24\15\0\1\24"+
"\20\0\15\24\3\0\26\7\114\0\1\24\4\0\1\24\2\0\12\24"+
"\1\0\1\24\3\0\5\24\6\0\1\24\1\0\1\24\1\0\1\24"+
"\1\0\4\24\1\0\13\24\2\0\4\24\5\0\5\24\4\0\1\24"+
"\64\0\2\24\u0a7b\0\57\24\1\0\57\24\1\0\205\24\6\0\4\24"+
"\3\0\2\24\14\0\46\24\1\0\1\24\5\0\1\24\2\0\70\24"+
"\7\0\1\24\20\0\27\24\11\0\7\24\1\0\7\24\1\0\7\24"+
"\1\0\7\24\1\0\7\24\1\0\7\24\1\0\7\24\1\0\7\24"+
"\117\0\1\7\1\24\u01d0\0\1\5\4\0\2\24\52\0\5\24\5\0"+
"\2\24\4\0\126\24\6\0\3\24\1\0\132\24\1\0\4\24\5\0"+
"\51\24\3\0\136\24\21\0\33\24\65\0\20\24\u0200\0\u19b6\24\112\0"+
"\u51cd\24\63\0\u048d\24\103\0\56\24\2\0\u010d\24\3\0\20\24\12\10"+
"\2\24\24\0\57\24\20\0\31\24\10\0\106\24\61\0\11\24\2\0"+
"\147\24\2\0\4\24\1\0\4\24\14\0\13\24\115\0\12\24\1\0"+
"\3\24\1\0\4\24\1\0\27\24\35\0\64\24\16\0\62\24\34\0"+
"\12\10\30\0\6\24\3\0\1\24\4\0\12\10\34\24\12\0\27\24"+
"\31\0\35\24\7\0\57\24\34\0\1\24\12\10\46\0\51\24\27\0"+
"\3\24\1\0\10\24\4\0\12\10\6\0\27\24\3\0\1\24\5\0"+
"\60\24\1\0\1\24\3\0\2\24\2\0\5\24\2\0\1\24\1\0"+
"\1\24\30\0\3\24\2\0\13\24\7\0\3\24\14\0\6\24\2\0"+
"\6\24\2\0\6\24\11\0\7\24\1\0\7\24\221\0\43\24\15\0"+
"\12\10\6\0\u2ba4\24\14\0\27\24\4\0\61\24\u2104\0\u016e\24\2\0"+
"\152\24\46\0\7\24\14\0\5\24\5\0\1\24\1\0\12\24\1\0"+
"\15\24\1\0\5\24\1\0\1\24\1\0\2\24\1\0\2\24\1\0"+
"\154\24\41\0\u016b\24\22\0\100\24\2\0\66\24\50\0\14\24\164\0"+
"\5\24\1\0\207\24\23\0\12\10\7\0\32\24\6\0\32\24\13\0"+
"\131\24\3\0\6\24\2\0\6\24\2\0\6\24\2\0\3\24\43\0";
/**
* Translates characters to character classes
*/
private static final char [] ZZ_CMAP = zzUnpackCMap(ZZ_CMAP_PACKED);
/**
* Translates DFA states to action switch labels.
*/
private static final int [] ZZ_ACTION = zzUnpackAction();
private static final String ZZ_ACTION_PACKED_0 =
"\1\0\1\1\3\2\1\3\4\4\1\5\3\4\2\5"+
"\1\4\2\5\1\3\1\5\1\4\3\5\2\0\5\4"+
"\2\5\3\4\2\0\1\5\3\0\2\5\1\0\2\5"+
"\10\0\1\6\12\0\2\5\1\0\2\5\22\0\2\5"+
"\3\0\3\4\1\0\2\4\1\5\1\0\1\5\11\0"+
"\1\7\1\0\1\4\10\0\1\10\1\4\1\0\1\4"+
"\2\0\4\4\1\0\6\4";
private static int [] zzUnpackAction() {
int [] result = new int[141];
int offset = 0;
offset = zzUnpackAction(ZZ_ACTION_PACKED_0, offset, result);
return result;
}
private static int zzUnpackAction(String packed, int offset, int [] result) {
int i = 0; /* index in packed string */
int j = offset; /* index in unpacked array */
int l = packed.length();
while (i < l) {
int count = packed.charAt(i++);
int value = packed.charAt(i++);
do result[j++] = value; while (--count > 0);
}
return j;
}
/**
* Translates a state to a row index in the transition table
*/
private static final int [] ZZ_ROWMAP = zzUnpackRowMap();
private static final String ZZ_ROWMAP_PACKED_0 =
"\0\0\0\104\0\210\0\314\0\104\0\u0110\0\u0154\0\u0198"+
"\0\u01dc\0\u0220\0\u0264\0\u02a8\0\u02ec\0\u0330\0\u0374\0\u03b8"+
"\0\u03fc\0\u0440\0\u0484\0\u04c8\0\u050c\0\u0550\0\u0594\0\u05d8"+
"\0\u061c\0\104\0\u0660\0\u06a4\0\u06e8\0\u072c\0\u0770\0\u07b4"+
"\0\u07f8\0\u083c\0\u0880\0\u08c4\0\u0908\0\u094c\0\u0990\0\u09d4"+
"\0\u0a18\0\u0a5c\0\u0aa0\0\u0ae4\0\u0b28\0\u0b6c\0\u0bb0\0\u0bf4"+
"\0\u0c38\0\u0c7c\0\u0cc0\0\u0d04\0\u0d48\0\u0d8c\0\u0dd0\0\u0e14"+
"\0\u06a4\0\u0e58\0\u0e9c\0\u0ee0\0\u0f24\0\u0f68\0\u0fac\0\u0ff0"+
"\0\u1034\0\u1078\0\u10bc\0\u1100\0\u1144\0\u1188\0\u11cc\0\u1210"+
"\0\u1254\0\u1298\0\u12dc\0\u1320\0\u1364\0\u13a8\0\u13ec\0\u1430"+
"\0\u1474\0\u14b8\0\u14fc\0\u1540\0\u1584\0\u15c8\0\u160c\0\u1650"+
"\0\u1694\0\u16d8\0\u171c\0\u1760\0\u17a4\0\u17e8\0\u182c\0\u1870"+
"\0\u18b4\0\314\0\u18f8\0\u193c\0\u1980\0\u19c4\0\u1a08\0\u1a4c"+
"\0\u1a90\0\u1ad4\0\u1b18\0\u1b5c\0\u1ba0\0\u1be4\0\u1c28\0\u1c6c"+
"\0\u1cb0\0\u1cf4\0\u1980\0\u1d38\0\u1d7c\0\u1dc0\0\u1e04\0\u1e48"+
"\0\u1e8c\0\u1ed0\0\u1f14\0\u1f58\0\314\0\u1f9c\0\u1fe0\0\u2024"+
"\0\u2068\0\u20ac\0\u1f58\0\u1188\0\u20f0\0\u2134\0\u2178\0\u21bc"+
"\0\u2200\0\u2244\0\u2288\0\u22cc\0\u2310";
private static int [] zzUnpackRowMap() {
int [] result = new int[141];
int offset = 0;
offset = zzUnpackRowMap(ZZ_ROWMAP_PACKED_0, offset, result);
return result;
}
private static int zzUnpackRowMap(String packed, int offset, int [] result) {
int i = 0; /* index in packed string */
int j = offset; /* index in unpacked array */
int l = packed.length();
while (i < l) {
int high = packed.charAt(i++) << 16;
result[j++] = high | packed.charAt(i++);
}
return j;
}
/**
* The transition table of the DFA
*/
private static final int [] ZZ_TRANS = zzUnpackTrans();
private static final String ZZ_TRANS_PACKED_0 =
"\1\2\1\3\1\4\1\5\1\4\1\6\1\7\1\10"+
"\1\11\1\10\1\12\1\13\1\14\1\15\1\16\1\17"+
"\1\13\1\17\1\12\1\10\1\20\1\21\1\17\1\22"+
"\2\23\1\20\2\12\1\24\3\12\1\25\2\23\1\12"+
"\1\26\1\27\2\30\1\31\2\30\1\23\1\30\1\23"+
"\1\30\1\23\1\30\1\23\1\30\1\23\1\30\1\23"+
"\1\30\1\23\1\30\1\23\1\30\1\23\1\30\1\6"+
"\1\12\1\23\1\30\1\23\1\30\1\32\2\0\1\32"+
"\1\0\1\32\1\33\3\32\1\0\1\32\3\0\3\32"+
"\1\0\10\32\6\0\3\32\10\0\1\32\1\0\1\32"+
"\1\0\1\32\1\0\1\32\1\0\1\32\1\0\1\32"+
"\1\0\1\32\1\0\1\32\1\0\1\32\1\0\1\32"+
"\1\0\1\32\1\0\1\32\3\0\1\4\205\0\1\32"+
"\2\0\1\32\1\0\1\6\1\33\3\32\1\0\1\32"+
"\3\0\3\32\1\0\10\32\2\0\1\24\3\0\3\32"+
"\10\0\1\32\1\0\1\32\1\0\1\32\1\0\1\32"+
"\1\0\1\32\1\0\1\32\1\0\1\32\1\0\1\32"+
"\1\0\1\32\1\0\1\6\1\0\1\32\1\0\1\32"+
"\7\0\1\34\1\12\1\0\2\12\1\0\3\12\3\0"+
"\2\12\1\0\1\12\5\0\2\12\1\0\3\12\3\0"+
"\1\12\32\0\1\12\4\0\1\32\2\0\1\32\1\0"+
"\1\32\1\35\1\10\1\32\1\10\1\12\1\32\3\12"+
"\3\32\1\12\1\10\1\32\1\10\5\32\2\12\1\0"+
"\3\12\3\32\1\12\7\0\1\32\1\0\1\32\1\0"+
"\1\32\1\0\1\32\1\0\1\32\1\0\1\32\1\0"+
"\1\32\1\0\1\32\1\0\1\32\1\0\1\32\1\12"+
"\1\32\1\0\1\32\1\0\1\32\2\0\1\32\1\0"+
"\1\32\1\36\1\32\2\11\1\37\1\32\2\37\1\0"+
"\3\32\1\0\1\11\7\32\1\0\1\37\3\0\1\37"+
"\3\32\1\0\1\37\6\0\1\32\1\0\1\32\1\0"+
"\1\32\1\0\1\32\1\0\1\32\1\0\1\32\1\0"+
"\1\32\1\0\1\32\1\0\1\32\1\0\1\32\1\0"+
"\1\32\1\0\1\32\7\0\2\12\1\0\2\12\1\0"+
"\3\12\3\0\2\12\1\0\1\12\5\0\2\12\1\0"+
"\3\12\3\0\1\12\32\0\1\12\4\0\1\32\2\0"+
"\1\32\1\0\1\32\1\33\1\32\1\40\1\32\1\0"+
"\1\13\1\41\1\42\1\0\3\13\1\0\1\13\2\32"+
"\1\13\4\32\6\0\3\32\1\0\1\43\6\0\1\32"+
"\1\0\1\32\1\0\1\32\1\0\1\32\1\0\1\32"+
"\1\0\1\32\1\0\1\32\1\0\1\32\1\0\1\32"+
"\1\0\1\32\1\0\1\32\1\0\1\32\7\0\2\12"+
"\1\43\2\12\1\41\1\14\1\44\1\12\3\41\1\12"+
"\1\14\1\0\1\12\1\41\4\0\2\12\1\0\3\12"+
"\3\0\1\12\1\43\31\0\1\12\12\0\2\12\1\0"+
"\2\12\1\41\1\14\1\45\1\16\3\41\2\12\1\0"+
"\1\12\1\41\4\0\2\12\1\0\3\12\3\0\1\12"+
"\21\0\2\46\7\0\1\12\2\46\10\0\2\12\1\0"+
"\2\12\1\0\3\12\1\47\2\0\2\12\1\0\1\12"+
"\5\0\2\12\1\0\3\12\3\0\1\12\32\0\1\12"+
"\4\0\1\32\2\0\1\32\1\0\1\32\1\33\1\32"+
"\1\40\1\32\1\0\1\13\1\41\1\42\1\0\1\17"+
"\1\13\1\17\1\0\1\13\2\20\1\17\4\20\6\0"+
"\3\20\1\0\1\43\6\50\1\20\1\50\1\20\1\50"+
"\1\20\1\50\1\20\1\50\1\20\1\50\1\20\1\50"+
"\1\20\1\50\1\20\1\50\1\20\1\50\1\32\1\0"+
"\1\20\1\50\1\20\1\50\1\32\2\0\1\32\1\0"+
"\1\32\1\33\3\32\1\0\1\32\3\0\1\20\1\32"+
"\1\20\1\0\1\32\7\20\6\0\3\20\2\0\6\50"+
"\1\20\1\50\1\20\1\50\1\20\1\50\1\20\1\50"+
"\1\20\1\50\1\20\1\50\1\20\1\50\1\20\1\50"+
"\1\20\1\50\1\32\1\0\1\20\1\50\1\20\1\50"+
"\1\32\2\0\1\32\1\0\1\32\1\35\1\10\1\32"+
"\1\10\1\12\1\32\3\12\1\20\1\32\1\20\1\12"+
"\1\10\1\20\1\21\5\20\2\12\1\0\3\12\3\20"+
"\1\12\1\0\6\50\1\20\1\50\1\20\1\50\1\20"+
"\1\50\1\20\1\50\1\20\1\50\1\20\1\50\1\20"+
"\1\50\1\20\1\50\1\20\1\50\1\32\1\12\1\20"+
"\1\50\1\20\1\50\1\51\2\0\1\51\1\0\1\51"+
"\1\52\3\51\1\53\1\51\3\53\1\23\1\51\1\23"+
"\1\53\1\51\4\23\1\54\2\23\2\53\2\0\2\53"+
"\3\23\2\53\1\30\1\55\4\30\1\23\1\30\1\23"+
"\1\30\1\23\1\30\1\23\1\30\1\23\1\30\1\23"+
"\1\30\1\23\1\30\1\23\1\30\1\23\1\30\1\32"+
"\1\56\1\23\1\30\1\23\1\30\1\51\2\0\1\51"+
"\1\0\1\51\1\52\3\51\1\53\1\51\3\53\1\23"+
"\1\51\1\23\1\53\1\51\7\23\2\53\2\0\2\53"+
"\3\23\2\53\6\30\1\23\1\30\1\23\1\30\1\23"+
"\1\30\1\23\1\30\1\23\1\30\1\23\1\30\1\23"+
"\1\30\1\23\1\30\1\23\1\30\1\32\1\56\1\23"+
"\1\30\1\23\1\30\5\0\1\24\27\0\1\24\40\0"+
"\1\24\5\0\1\51\2\0\1\51\1\0\1\51\1\52"+
"\3\51\1\53\1\51\3\53\1\23\1\51\1\23\1\53"+
"\1\51\7\23\2\53\2\0\2\53\1\57\2\23\2\53"+
"\3\30\1\60\2\30\1\23\1\30\1\23\1\30\1\23"+
"\1\30\1\23\1\30\1\23\1\30\1\23\1\30\1\23"+
"\1\30\1\23\1\30\1\23\1\30\1\32\1\56\1\23"+
"\1\30\1\23\1\30\1\53\2\0\1\53\1\0\1\53"+
"\1\26\1\53\3\26\1\53\2\26\5\53\1\26\10\53"+
"\1\26\2\0\1\53\1\26\4\53\1\26\30\53\1\0"+
"\1\56\5\53\2\0\1\53\1\0\12\53\1\30\1\53"+
"\1\30\2\53\4\30\1\55\2\30\2\53\2\0\2\53"+
"\3\30\2\53\1\30\1\55\26\30\1\0\1\56\4\30"+
"\1\53\2\0\1\53\1\0\12\53\1\30\1\53\1\30"+
"\2\53\7\30\2\53\2\0\2\53\3\30\2\53\30\30"+
"\1\0\1\56\4\30\1\53\2\0\1\53\1\0\12\53"+
"\1\30\1\53\1\30\2\53\7\30\2\53\2\0\2\53"+
"\1\60\2\30\2\53\3\30\1\60\24\30\1\0\1\56"+
"\4\30\1\32\2\0\1\32\1\0\1\32\1\0\3\32"+
"\1\0\1\32\3\0\3\32\1\0\10\32\6\0\3\32"+
"\10\0\1\61\1\62\1\63\1\64\1\32\1\0\1\65"+
"\1\66\1\67\1\70\1\32\1\0\1\32\1\0\1\32"+
"\1\0\1\32\1\0\1\32\1\0\1\32\1\0\1\32"+
"\7\0\1\71\1\12\1\0\2\12\1\0\3\12\3\0"+
"\2\12\1\0\1\12\5\0\2\12\1\0\3\12\3\0"+
"\1\12\32\0\1\12\4\0\1\32\2\0\1\32\1\0"+
"\1\32\1\12\1\10\1\32\1\10\1\12\1\32\3\12"+
"\3\32\1\12\1\10\1\32\1\10\5\32\2\12\1\0"+
"\3\12\3\32\1\12\7\0\1\61\1\62\1\63\1\64"+
"\1\32\1\0\1\65\1\66\1\67\1\70\1\32\1\0"+
"\1\32\1\0\1\32\1\0\1\32\1\0\1\32\1\12"+
"\1\32\1\0\1\32\1\0\1\32\2\0\1\32\1\0"+
"\1\32\1\37\1\32\2\11\1\37\1\32\2\37\1\0"+
"\3\32\1\0\1\11\7\32\1\0\1\37\3\0\1\37"+
"\3\32\1\0\1\37\6\0\1\61\1\62\1\63\1\64"+
"\1\32\1\0\1\65\1\66\1\67\1\70\1\32\1\0"+
"\1\32\1\0\1\32\1\0\1\32\1\0\1\32\1\0"+
"\1\32\1\0\1\32\7\0\1\37\1\0\3\37\1\0"+
"\2\37\5\0\1\37\10\0\1\37\3\0\1\37\4\0"+
"\1\37\36\0\1\32\2\0\1\32\1\0\1\32\1\33"+
"\1\32\1\40\1\32\1\0\1\32\3\0\3\32\1\0"+
"\10\32\6\0\3\32\1\0\1\43\6\0\1\32\1\0"+
"\1\32\1\0\1\32\1\0\1\32\1\0\1\32\1\0"+
"\1\32\1\0\1\32\1\0\1\32\1\0\1\32\1\0"+
"\1\32\1\0\1\32\1\0\1\32\11\0\1\43\2\0"+
"\2\41\1\42\1\0\3\41\1\0\1\41\2\0\1\41"+
"\16\0\1\43\46\0\1\43\4\0\1\42\27\0\1\43"+
"\46\0\1\43\34\0\1\43\44\0\2\12\1\43\2\12"+
"\1\0\1\12\1\44\1\12\3\0\2\12\1\0\1\12"+
"\5\0\2\12\1\0\3\12\3\0\1\12\1\43\31\0"+
"\1\12\12\0\2\12\1\0\2\12\1\41\1\14\1\45"+
"\1\16\3\41\2\12\1\0\1\12\1\41\4\0\2\12"+
"\1\0\3\12\3\0\1\12\32\0\1\12\72\0\2\72"+
"\34\0\1\73\102\0\1\50\1\0\1\50\2\0\7\50"+
"\6\0\3\50\2\0\30\50\2\0\4\50\1\51\2\0"+
"\1\51\1\0\1\51\1\52\3\51\1\53\1\51\3\53"+
"\3\51\1\53\10\51\2\53\2\0\2\53\3\51\10\53"+
"\1\51\1\53\1\51\1\53\1\51\1\53\1\51\1\53"+
"\1\51\1\53\1\51\1\53\1\51\1\53\1\51\1\53"+
"\1\51\1\53\1\32\1\56\1\51\1\53\1\51\1\53"+
"\1\51\2\0\1\51\1\0\1\51\1\53\3\51\1\53"+
"\1\51\3\53\3\51\1\53\10\51\2\53\2\0\2\53"+
"\3\51\10\53\1\74\1\75\1\76\1\77\1\51\1\53"+
"\1\100\1\101\1\102\1\103\1\51\1\53\1\51\1\53"+
"\1\51\1\53\1\51\1\53\1\32\1\56\1\51\1\53"+
"\1\51\2\53\2\0\1\53\1\0\30\53\2\0\37\53"+
"\1\0\1\56\4\53\1\51\2\0\1\51\1\0\1\51"+
"\1\52\3\51\1\53\1\51\3\53\1\23\1\51\1\23"+
"\1\53\1\51\4\23\1\104\2\23\2\53\2\0\2\53"+
"\3\23\2\53\1\30\1\105\4\30\1\23\1\30\1\23"+
"\1\30\1\23\1\30\1\23\1\30\1\23\1\30\1\23"+
"\1\30\1\23\1\30\1\23\1\30\1\23\1\30\1\32"+
"\1\56\1\23\1\30\1\23\1\30\1\53\2\0\1\53"+
"\1\0\12\53\1\30\1\53\1\30\2\53\4\30\1\105"+
"\2\30\2\53\2\0\2\53\3\30\2\53\1\30\1\105"+
"\26\30\1\0\1\56\4\30\1\106\2\0\1\106\1\0"+
"\1\106\1\53\26\106\2\0\37\106\1\0\5\106\1\51"+
"\2\0\1\51\1\0\1\51\1\52\3\51\1\53\1\51"+
"\3\53\1\23\1\51\1\23\1\53\1\51\7\23\2\53"+
"\2\0\2\53\1\107\2\23\2\53\3\30\1\110\2\30"+
"\1\23\1\30\1\23\1\30\1\23\1\30\1\23\1\30"+
"\1\23\1\30\1\23\1\30\1\23\1\30\1\23\1\30"+
"\1\23\1\30\1\32\1\56\1\23\1\30\1\23\1\30"+
"\1\53\2\0\1\53\1\0\12\53\1\30\1\53\1\30"+
"\2\53\7\30\2\53\2\0\2\53\1\110\2\30\2\53"+
"\3\30\1\110\24\30\1\0\1\56\4\30\1\32\2\0"+
"\1\32\1\0\1\32\1\33\3\32\1\0\1\32\3\0"+
"\3\32\1\0\10\32\6\0\3\32\10\0\1\32\1\0"+
"\1\111\1\112\1\32\1\0\1\32\1\0\1\32\1\0"+
"\1\32\1\0\1\32\1\0\1\32\1\0\1\32\1\0"+
"\1\32\1\0\1\32\1\0\1\32\57\0\2\112\24\0"+
"\1\32\2\0\1\32\1\0\1\32\1\33\3\32\1\0"+
"\1\32\3\0\3\32\1\0\10\32\6\0\3\32\10\0"+
"\1\32\1\0\1\32\1\0\1\32\1\0\1\32\1\0"+
"\1\32\1\0\1\113\1\114\1\32\1\0\1\32\1\0"+
"\1\32\1\0\1\32\1\0\1\32\1\0\1\32\67\0"+
"\2\114\14\0\1\32\2\0\1\32\1\0\1\32\1\33"+
"\3\32\1\0\1\32\3\0\3\32\1\0\10\32\6\0"+
"\3\32\10\0\1\32\1\0\1\32\1\0\1\32\1\0"+
"\1\32\1\0\1\115\1\116\1\32\1\0\1\32\1\0"+
"\1\32\1\0\1\32\1\0\1\32\1\0\1\32\1\0"+
"\1\32\65\0\2\116\16\0\1\32\2\0\1\32\1\0"+
"\1\32\1\33\3\32\1\0\1\32\3\0\3\32\1\0"+
"\10\32\6\0\3\32\10\0\1\32\1\0\1\32\1\0"+
"\1\32\1\0\1\32\1\0\1\32\1\0\1\32\1\0"+
"\1\32\1\0\1\117\1\120\1\32\1\0\1\32\1\0"+
"\1\32\1\0\1\32\73\0\2\120\112\0\2\121\21\0"+
"\1\122\62\0\1\51\2\0\1\51\1\0\1\51\1\52"+
"\3\51\1\53\1\51\3\53\3\51\1\53\10\51\2\53"+
"\2\0\2\53\3\51\10\53\1\51\1\53\1\123\1\124"+
"\1\51\1\53\1\51\1\53\1\51\1\53\1\51\1\53"+
"\1\51\1\53\1\51\1\53\1\51\1\53\1\32\1\56"+
"\1\51\1\53\1\51\2\53\2\0\1\53\1\0\30\53"+
"\2\0\17\53\2\124\16\53\1\0\1\56\4\53\1\51"+
"\2\0\1\51\1\0\1\51\1\52\3\51\1\53\1\51"+
"\3\53\3\51\1\53\10\51\2\53\2\0\2\53\3\51"+
"\10\53\1\51\1\53\1\51\1\53\1\51\1\53\1\51"+
"\1\53\1\51\1\53\1\125\1\126\1\51\1\53\1\51"+
"\1\53\1\51\1\53\1\32\1\56\1\51\1\53\1\51"+
"\2\53\2\0\1\53\1\0\30\53\2\0\27\53\2\126"+
"\6\53\1\0\1\56\4\53\1\51\2\0\1\51\1\0"+
"\1\51\1\52\3\51\1\53\1\51\3\53\3\51\1\53"+
"\10\51\2\53\2\0\2\53\3\51\10\53\1\51\1\53"+
"\1\51\1\53\1\51\1\53\1\51\1\53\1\127\1\130"+
"\1\51\1\53\1\51\1\53\1\51\1\53\1\51\1\53"+
"\1\32\1\56\1\51\1\53\1\51\2\53\2\0\1\53"+
"\1\0\30\53\2\0\25\53\2\130\10\53\1\0\1\56"+
"\4\53\1\51\2\0\1\51\1\0\1\51\1\52\3\51"+
"\1\53\1\51\3\53\3\51\1\53\10\51\2\53\2\0"+
"\2\53\3\51\10\53\1\51\1\53\1\51\1\53\1\51"+
"\1\53\1\51\1\53\1\51\1\53\1\51\1\53\1\51"+
"\1\53\1\131\1\132\1\51\1\53\1\32\1\56\1\51"+
"\1\53\1\51\2\53\2\0\1\53\1\0\30\53\2\0"+
"\33\53\2\132\2\53\1\0\1\56\4\53\1\51\2\0"+
"\1\51\1\0\1\51\1\52\3\51\1\53\1\51\3\53"+
"\1\23\1\51\1\23\1\53\1\51\5\23\1\133\1\23"+
"\2\53\2\0\2\53\3\23\2\53\2\30\1\134\3\30"+
"\1\23\1\30\1\23\1\30\1\23\1\30\1\23\1\30"+
"\1\23\1\30\1\23\1\30\1\23\1\30\1\23\1\30"+
"\1\23\1\30\1\32\1\56\1\23\1\30\1\23\1\30"+
"\1\53\2\0\1\53\1\0\12\53\1\30\1\53\1\30"+
"\2\53\5\30\1\134\1\30\2\53\2\0\2\53\3\30"+
"\2\53\2\30\1\134\25\30\1\0\1\56\4\30\1\106"+
"\2\0\1\106\1\0\1\106\1\135\26\106\2\0\37\106"+
"\1\0\5\106\1\51\2\0\1\51\1\0\1\51\1\136"+
"\3\51\1\53\1\51\3\53\1\23\1\51\1\23\1\53"+
"\1\51\7\23\2\53\2\0\2\53\3\23\2\53\6\30"+
"\1\23\1\30\1\23\1\30\1\23\1\30\1\23\1\30"+
"\1\23\1\30\1\23\1\30\1\23\1\30\1\23\1\30"+
"\1\23\1\30\1\32\1\56\1\23\1\30\1\23\1\30"+
"\1\53\2\0\1\53\1\0\1\53\1\137\10\53\1\30"+
"\1\53\1\30\2\53\7\30\2\53\2\0\2\53\3\30"+
"\2\53\30\30\1\0\1\56\4\30\1\32\2\0\1\32"+
"\1\0\1\32\1\33\3\32\1\0\1\32\3\0\3\32"+
"\1\0\10\32\6\0\3\32\10\0\1\32\1\0\1\32"+
"\1\0\1\140\1\141\1\32\1\0\1\32\1\0\1\32"+
"\1\0\1\32\1\0\1\32\1\0\1\32\1\0\1\32"+
"\1\0\1\32\1\0\1\32\61\0\2\141\22\0\1\32"+
"\2\0\1\32\1\0\1\32\1\33\3\32\1\0\1\32"+
"\3\0\3\32\1\0\10\32\6\0\3\32\10\0\1\32"+
"\1\0\1\32\1\0\1\32\1\0\1\32\1\0\1\32"+
"\1\0\1\32\1\0\1\140\1\141\1\32\1\0\1\32"+
"\1\0\1\32\1\0\1\32\1\0\1\32\71\0\2\141"+
"\12\0\1\32\2\0\1\32\1\0\1\32\1\33\3\32"+
"\1\0\1\32\3\0\3\32\1\0\5\32\1\140\2\32"+
"\6\0\3\32\3\0\1\141\4\0\1\32\1\0\1\32"+
"\1\0\1\32\1\0\1\32\1\0\1\32\1\0\1\32"+
"\1\0\1\32\1\0\1\32\1\0\1\32\1\0\1\32"+
"\1\0\1\32\1\0\1\32\31\0\1\141\16\0\1\141"+
"\34\0\1\32\2\0\1\32\1\0\1\32\1\33\3\32"+
"\1\0\1\32\3\0\3\32\1\0\10\32\6\0\3\32"+
"\10\0\1\32\1\0\1\32\1\0\1\32\1\0\1\32"+
"\1\0\1\32\1\0\1\32\1\0\1\32\1\0\1\32"+
"\1\0\1\140\1\141\1\32\1\0\1\32\1\0\1\32"+
"\75\0\2\141\23\0\1\142\107\0\1\143\62\0\1\51"+
"\2\0\1\51\1\0\1\51\1\52\3\51\1\53\1\51"+
"\3\53\3\51\1\53\10\51\2\53\2\0\2\53\3\51"+
"\10\53\1\51\1\53\1\51\1\53\1\144\1\145\1\51"+
"\1\53\1\51\1\53\1\51\1\53\1\51\1\53\1\51"+
"\1\53\1\51\1\53\1\32\1\56\1\51\1\53\1\51"+
"\2\53\2\0\1\53\1\0\30\53\2\0\21\53\2\145"+
"\14\53\1\0\1\56\4\53\1\51\2\0\1\51\1\0"+
"\1\51\1\52\3\51\1\53\1\51\3\53\3\51\1\53"+
"\10\51\2\53\2\0\2\53\3\51\10\53\1\51\1\53"+
"\1\51\1\53\1\51\1\53\1\51\1\53\1\51\1\53"+
"\1\51\1\53\1\144\1\145\1\51\1\53\1\51\1\53"+
"\1\32\1\56\1\51\1\53\1\51\2\53\2\0\1\53"+
"\1\0\30\53\2\0\31\53\2\145\4\53\1\0\1\56"+
"\4\53\1\51\2\0\1\51\1\0\1\51\1\52\3\51"+
"\1\53\1\51\3\53\3\51\1\53\5\51\1\144\2\51"+
"\2\53\2\0\2\53\3\51\3\53\1\145\4\53\1\51"+
"\1\53\1\51\1\53\1\51\1\53\1\51\1\53\1\51"+
"\1\53\1\51\1\53\1\51\1\53\1\51\1\53\1\51"+
"\1\53\1\32\1\56\1\51\1\53\1\51\2\53\2\0"+
"\1\53\1\0\23\53\1\145\4\53\2\0\10\53\1\145"+
"\26\53\1\0\1\56\4\53\1\51\2\0\1\51\1\0"+
"\1\51\1\52\3\51\1\53\1\51\3\53\3\51\1\53"+
"\10\51\2\53\2\0\2\53\3\51\10\53\1\51\1\53"+
"\1\51\1\53\1\51\1\53\1\51\1\53\1\51\1\53"+
"\1\51\1\53\1\51\1\53\1\51\1\53\1\144\1\145"+
"\1\32\1\56\1\51\1\53\1\51\2\53\2\0\1\53"+
"\1\0\30\53\2\0\35\53\2\145\1\0\1\56\4\53"+
"\1\51\2\0\1\51\1\0\1\51\1\52\3\51\1\53"+
"\1\51\3\53\1\23\1\51\1\23\1\53\1\51\6\23"+
"\1\146\1\147\1\53\2\0\2\53\2\23\1\146\2\53"+
"\5\30\1\150\1\23\1\30\1\23\1\30\1\23\1\30"+
"\1\23\1\30\1\23\1\30\1\23\1\30\1\23\1\30"+
"\1\23\1\30\1\23\1\30\1\32\1\56\1\23\1\30"+
"\1\23\1\30\1\53\2\0\1\53\1\0\12\53\1\30"+
"\1\53\1\30\2\53\6\30\1\150\1\147\1\53\2\0"+
"\2\53\2\30\1\150\2\53\5\30\1\150\22\30\1\0"+
"\1\56\4\30\1\106\2\0\1\106\1\0\1\106\1\53"+
"\20\106\3\151\3\106\2\0\2\106\3\151\2\106\30\151"+
"\1\0\1\106\4\151\1\152\2\0\1\152\1\0\1\152"+
"\1\53\26\152\2\0\2\53\13\152\2\153\2\154\2\152"+
"\2\155\2\156\10\152\1\157\1\160\5\152\2\0\1\152"+
"\1\0\1\152\1\53\26\152\2\0\2\53\35\152\1\157"+
"\1\160\4\152\1\32\2\0\1\32\1\0\1\32\1\33"+
"\3\32\1\0\1\32\3\0\3\32\1\0\10\32\1\0"+
"\1\161\4\0\3\32\10\0\1\32\1\0\1\32\1\0"+
"\1\32\1\0\1\32\1\0\1\32\1\0\1\32\1\0"+
"\1\32\1\0\1\32\1\0\1\32\1\0\1\32\1\0"+
"\1\32\1\0\1\32\35\0\1\161\71\0\1\162\61\0"+
"\1\51\2\0\1\51\1\0\1\51\1\52\3\51\1\53"+
"\1\51\3\53\3\51\1\53\10\51\1\53\1\161\2\0"+
"\2\53\3\51\10\53\1\51\1\53\1\51\1\53\1\51"+
"\1\53\1\51\1\53\1\51\1\53\1\51\1\53\1\51"+
"\1\53\1\51\1\53\1\51\1\53\1\32\1\56\1\51"+
"\1\53\1\51\2\53\2\0\1\53\1\0\27\53\1\161"+
"\2\0\37\53\1\0\1\56\4\53\1\51\2\0\1\51"+
"\1\0\1\51\1\52\3\51\1\53\1\51\3\53\1\23"+
"\1\51\1\23\1\53\1\51\7\23\1\147\1\53\2\0"+
"\2\53\3\23\2\53\6\30\1\23\1\30\1\23\1\30"+
"\1\23\1\30\1\23\1\30\1\23\1\30\1\23\1\30"+
"\1\23\1\30\1\23\1\30\1\23\1\30\1\32\1\56"+
"\1\23\1\30\1\23\1\30\1\53\2\0\1\53\1\0"+
"\27\53\1\163\2\0\37\53\1\0\1\56\5\53\2\0"+
"\1\53\1\0\12\53\1\30\1\53\1\30\2\53\7\30"+
"\1\147\1\53\2\0\2\53\3\30\2\53\30\30\1\0"+
"\1\56\4\30\1\106\2\0\1\106\1\0\1\106\1\135"+
"\20\106\3\164\3\106\2\0\2\106\3\164\2\106\30\164"+
"\1\0\1\106\4\164\1\152\2\0\1\152\1\0\1\152"+
"\1\165\26\152\2\0\2\53\35\152\1\157\1\160\5\152"+
"\2\0\1\152\1\0\1\152\1\165\26\152\2\0\2\53"+
"\15\152\2\166\16\152\1\157\1\160\5\152\2\0\1\152"+
"\1\0\1\152\1\165\26\152\2\0\2\53\25\152\2\167"+
"\6\152\1\157\1\160\5\152\2\0\1\152\1\0\1\152"+
"\1\165\26\152\2\0\2\53\23\152\2\170\10\152\1\157"+
"\1\160\5\152\2\0\1\152\1\0\1\152\1\165\26\152"+
"\2\0\2\53\31\152\2\171\2\152\1\157\1\160\4\152"+
"\1\157\2\0\1\157\1\0\1\157\1\172\26\157\4\0"+
"\43\157\1\173\2\0\1\173\1\0\1\173\1\165\26\173"+
"\2\0\2\106\35\173\1\157\5\173\1\174\2\0\1\174"+
"\1\0\30\174\2\0\45\174\15\0\1\175\66\0\1\106"+
"\2\0\1\106\1\0\1\106\1\135\20\106\3\176\3\106"+
"\2\0\2\106\3\176\2\106\30\176\1\0\1\106\4\176"+
"\1\152\2\0\1\152\1\0\1\152\1\53\20\152\3\177"+
"\3\152\2\0\2\53\3\177\2\152\30\177\1\157\1\160"+
"\4\177\1\152\2\0\1\152\1\0\1\152\1\165\26\152"+
"\2\0\2\53\17\152\2\200\14\152\1\157\1\160\5\152"+
"\2\0\1\152\1\0\1\152\1\165\26\152\2\0\2\53"+
"\27\152\2\200\4\152\1\157\1\160\5\152\2\0\1\152"+
"\1\0\1\152\1\165\21\152\1\200\4\152\2\0\2\53"+
"\6\152\1\200\26\152\1\157\1\160\5\152\2\0\1\152"+
"\1\0\1\152\1\165\26\152\2\0\2\53\33\152\2\200"+
"\1\157\1\160\4\152\1\157\2\0\1\157\1\0\1\157"+
"\1\0\20\157\3\201\3\157\4\0\3\201\2\157\30\201"+
"\2\157\4\201\1\173\2\0\1\173\1\0\1\173\1\202"+
"\26\173\2\0\2\106\35\173\1\157\5\173\1\203\2\0"+
"\1\203\1\0\1\203\1\174\6\203\1\174\17\203\2\0"+
"\2\174\43\203\1\106\2\0\1\106\1\0\1\106\1\135"+
"\20\106\3\204\3\106\2\0\2\106\3\204\2\106\30\204"+
"\1\0\1\106\4\204\1\152\2\0\1\152\1\0\1\152"+
"\1\165\20\152\3\205\3\152\2\0\2\53\3\205\2\152"+
"\30\205\1\157\1\160\4\205\1\152\2\0\1\152\1\0"+
"\1\152\1\165\25\152\1\161\2\0\2\53\35\152\1\157"+
"\1\160\4\152\1\157\2\0\1\157\1\0\1\157\1\172"+
"\20\157\3\206\3\157\4\0\3\206\2\157\30\206\2\157"+
"\4\206\1\173\2\0\1\173\1\0\1\173\1\53\20\173"+
"\3\207\3\173\2\0\2\106\3\207\2\173\30\207\1\157"+
"\1\173\4\207\1\152\2\0\1\152\1\0\1\152\1\165"+
"\20\152\3\210\2\152\1\161\2\0\2\53\3\210\2\152"+
"\30\210\1\157\1\160\4\210\1\157\2\0\1\157\1\0"+
"\1\157\1\172\20\157\3\211\2\157\1\161\4\0\3\211"+
"\2\157\30\211\2\157\4\211\1\173\2\0\1\173\1\0"+
"\1\173\1\202\20\173\3\212\3\173\2\0\2\106\3\212"+
"\2\173\30\212\1\157\1\173\4\212\1\152\2\0\1\152"+
"\1\0\1\152\1\165\20\152\3\200\2\152\1\161\2\0"+
"\2\53\3\200\2\152\30\200\1\157\1\160\4\200\1\157"+
"\2\0\1\157\1\0\1\157\1\172\20\157\3\213\2\157"+
"\1\161\4\0\3\213\2\157\30\213\2\157\4\213\1\173"+
"\2\0\1\173\1\0\1\173\1\202\20\173\3\214\2\173"+
"\1\161\2\0\2\106\3\214\2\173\30\214\1\157\1\173"+
"\4\214\1\157\2\0\1\157\1\0\1\157\1\172\25\157"+
"\1\161\4\0\43\157\1\173\2\0\1\173\1\0\1\173"+
"\1\202\20\173\3\215\2\173\1\161\2\0\2\106\3\215"+
"\2\173\30\215\1\157\1\173\4\215\1\173\2\0\1\173"+
"\1\0\1\173\1\202\25\173\1\161\2\0\2\106\35\173"+
"\1\157\5\173";
private static int [] zzUnpackTrans() {
int [] result = new int[9044];
int offset = 0;
offset = zzUnpackTrans(ZZ_TRANS_PACKED_0, offset, result);
return result;
}
private static int zzUnpackTrans(String packed, int offset, int [] result) {
int i = 0; /* index in packed string */
int j = offset; /* index in unpacked array */
int l = packed.length();
while (i < l) {
int count = packed.charAt(i++);
int value = packed.charAt(i++);
value--;
do result[j++] = value; while (--count > 0);
}
return j;
}
/* error codes */
private static final int ZZ_UNKNOWN_ERROR = 0;
private static final int ZZ_NO_MATCH = 1;
private static final int ZZ_PUSHBACK_2BIG = 2;
/* error messages for the codes above */
private static final String ZZ_ERROR_MSG[] = {
"Unkown internal scanner error",
"Error: could not match input",
"Error: pushback value was too large"
};
/**
* ZZ_ATTRIBUTE[aState] contains the attributes of state <code>aState</code>
*/
private static final int [] ZZ_ATTRIBUTE = zzUnpackAttribute();
private static final String ZZ_ATTRIBUTE_PACKED_0 =
"\1\0\2\1\1\11\25\1\2\0\12\1\2\0\1\1"+
"\3\0\2\1\1\0\2\1\10\0\1\1\12\0\2\1"+
"\1\0\2\1\22\0\2\1\3\0\2\1\1\11\1\0"+
"\3\1\1\0\1\1\11\0\1\1\1\0\1\1\10\0"+
"\1\11\1\1\1\0\1\1\2\0\4\1\1\0\6\1";
private static int [] zzUnpackAttribute() {
int [] result = new int[141];
int offset = 0;
offset = zzUnpackAttribute(ZZ_ATTRIBUTE_PACKED_0, offset, result);
return result;
}
private static int zzUnpackAttribute(String packed, int offset, int [] result) {
int i = 0; /* index in packed string */
int j = offset; /* index in unpacked array */
int l = packed.length();
while (i < l) {
int count = packed.charAt(i++);
int value = packed.charAt(i++);
do result[j++] = value; while (--count > 0);
}
return j;
}
/** the input device */
private java.io.Reader zzReader;
/** the current state of the DFA */
private int zzState;
/** the current lexical state */
private int zzLexicalState = YYINITIAL;
/** this buffer contains the current text to be matched and is
the source of the yytext() string */
private char zzBuffer[] = new char[ZZ_BUFFERSIZE];
/** the textposition at the last accepting state */
private int zzMarkedPos;
/** the current text position in the buffer */
private int zzCurrentPos;
/** startRead marks the beginning of the yytext() string in the buffer */
private int zzStartRead;
/** endRead marks the last character in the buffer, that has been read
from input */
private int zzEndRead;
/** number of newlines encountered up to the start of the matched text */
private int yyline;
/** the number of characters up to the start of the matched text */
private int yychar;
/**
* the number of characters from the last newline up to the start of the
* matched text
*/
private int yycolumn;
/**
* zzAtBOL == true <=> the scanner is currently at the beginning of a line
*/
private boolean zzAtBOL = true;
/** zzAtEOF == true <=> the scanner is at the EOF */
private boolean zzAtEOF;
/** denotes if the user-EOF-code has already been executed */
private boolean zzEOFDone;
/* user code: */
private LexedTokenFactory<?> tokenFactory;
private boolean invertible;
// Convert Arabic digits to ASCII digits
private boolean normArDigits;
// Convert Arabic punctuation to ASCII equivalents
private boolean normArPunc;
// Substitute newlines with newlineChar.
// Otherwise, treat them like whitespace
private boolean tokenizeNLs;
public static final String NEWLINE_TOKEN = "*NL*";
// Use \u2026 for ellipses
private boolean useUTF8Ellipsis;
// Arabic-specific orthographic normalization rules
private boolean normAlif;
private boolean normYa;
private boolean removeDiacritics;
private boolean removeTatweel;
private boolean removeQuranChars;
// Penn ATB vocalized section normalizations
private boolean removeProMarker;
private boolean removeSegMarker;
private boolean removeMorphMarker;
// Lengthening effects (yAAAAAAA): replace three or more of the same character with one
private boolean removeLengthening;
private final Pattern segmentationMarker = Pattern.compile("^-+|-+$");
// Escape parens for ATB parsing
private boolean atbEscaping;
private Map<String,String> normMap;
public ArabicLexer(Reader r, LexedTokenFactory<?> tf, Properties props) {
this(r);
this.tokenFactory = tf;
tokenizeNLs = PropertiesUtils.getBool(props, "tokenizeNLs", false);
useUTF8Ellipsis = PropertiesUtils.getBool(props, "useUTF8Ellipsis", false);
invertible = PropertiesUtils.getBool(props, "invertible", false);
normArDigits = PropertiesUtils.getBool(props, "normArDigits", false);
normArPunc = PropertiesUtils.getBool(props, "normArPunc", false);
normAlif = PropertiesUtils.getBool(props, "normAlif", false);
normYa = PropertiesUtils.getBool(props, "normYa", false);
removeDiacritics = PropertiesUtils.getBool(props, "removeDiacritics", false);
removeTatweel = PropertiesUtils.getBool(props, "removeTatweel", false);
removeQuranChars = PropertiesUtils.getBool(props, "removeQuranChars", false);
removeProMarker = PropertiesUtils.getBool(props, "removeProMarker", false);
removeSegMarker = PropertiesUtils.getBool(props, "removeSegMarker", false);
removeMorphMarker = PropertiesUtils.getBool(props, "removeMorphMarker", false);
removeLengthening = PropertiesUtils.getBool(props, "removeLengthening", false);
atbEscaping = PropertiesUtils.getBool(props, "atbEscaping", false);
setupNormalizationMap();
}
private void setupNormalizationMap() {
normMap = Generics.newHashMap(200);
// Junk characters that we always remove
normMap.put("\u0600","#");
normMap.put("\u0601","");
normMap.put("\u0602","");
normMap.put("\u0603","");
normMap.put("\u0606","\u221B");
normMap.put("\u0607","\u221C");
normMap.put("\u0608","");
normMap.put("\u0609","%");
normMap.put("\u060A","%");
normMap.put("\u060B","");
normMap.put("\u060E","");
normMap.put("\u060F","");
normMap.put("\u066E","\u0628");
normMap.put("\u066F","\u0642");
normMap.put("\u06CC","\u0649");
normMap.put("\u06D6","");
normMap.put("\u06D7","");
normMap.put("\u06D8","");
normMap.put("\u06D9","");
normMap.put("\u06DA","");
normMap.put("\u06DB","");
normMap.put("\u06DC","");
normMap.put("\u06DD","");
normMap.put("\u06DE","");
normMap.put("\u06DF","");
normMap.put("\u06E0","");
normMap.put("\u06E1","");
normMap.put("\u06E2","");
normMap.put("\u06E3","");
normMap.put("\u06E4","");
normMap.put("\u06E5","");
normMap.put("\u06E6","");
normMap.put("\u06E7","");
normMap.put("\u06E8","");
normMap.put("\u06E9","");
normMap.put("\u06EA","");
normMap.put("\u06EB","");
normMap.put("\u06EC","");
normMap.put("\u06ED","");
if (normArDigits) {
normMap.put("\u0660","0");
normMap.put("\u0661","1");
normMap.put("\u0662","2");
normMap.put("\u0663","3");
normMap.put("\u0664","4");
normMap.put("\u0665","5");
normMap.put("\u0666","6");
normMap.put("\u0667","7");
normMap.put("\u0668","8");
normMap.put("\u0669","9");
normMap.put("\u06F0","0");
normMap.put("\u06F1","1");
normMap.put("\u06F2","2");
normMap.put("\u06F3","3");
normMap.put("\u06F4","4");
normMap.put("\u06F5","5");
normMap.put("\u06F6","6");
normMap.put("\u06F7","7");
normMap.put("\u06F8","8");
normMap.put("\u06F9","9");
}
if (normArPunc) {
normMap.put("\u00BB","\"");
normMap.put("\u00AB","\"");
normMap.put("\u060C",",");
normMap.put("\u060D",",");
normMap.put("\u061B",";");
normMap.put("\u061E",".");
normMap.put("\u061F","?");
normMap.put("\u066A","%");
normMap.put("\u066B",",");
normMap.put("\u066C","\u0027");
normMap.put("\u066F","*");
normMap.put("\u06DF",".");
}
if (normAlif) {
normMap.put("\u0622","\u0627");
normMap.put("\u0623","\u0627");
normMap.put("\u0625","\u0627");
normMap.put("\u0671","\u0627");
normMap.put("\u0672","\u0627");
normMap.put("\u0673","\u0627");
}
if (normYa) {
normMap.put("\u064A","\u0649");
}
if (removeDiacritics) {
normMap.put("\u064B","");
normMap.put("\u064C","");
normMap.put("\u064D","");
normMap.put("\u064E","");
normMap.put("\u064F","");
normMap.put("\u0650","");
normMap.put("\u0651","");
normMap.put("\u0652","");
normMap.put("\u0653","");
normMap.put("\u0654","");
normMap.put("\u0655","");
normMap.put("\u0656","");
normMap.put("\u0657","");
normMap.put("\u0658","");
normMap.put("\u0659","");
normMap.put("\u065A","");
normMap.put("\u065B","");
normMap.put("\u065C","");
normMap.put("\u065D","");
normMap.put("\u065E","");
normMap.put("\u0670","");
}
if (removeTatweel) {
normMap.put("\u0640","");
normMap.put("_","");
}
if (removeQuranChars) {
// Arabic honorifics
normMap.put("\u0610","");
normMap.put("\u0611","");
normMap.put("\u0612","");
normMap.put("\u0613","");
normMap.put("\u0614","");
normMap.put("\u0615","");
normMap.put("\u0616","");
normMap.put("\u0617","");
normMap.put("\u0618","");
normMap.put("\u0619","");
normMap.put("\u061A","");
}
if (atbEscaping) {
normMap.put("(","-LRB-");
normMap.put(")","-RRB-");
}
}
private String normalizeToken(String text, boolean isWord) {
// Remove segmentation markers from the ATB
if (isWord && removeSegMarker) {
text = segmentationMarker.matcher(text).replaceAll("");
}
int len = text.length();
StringBuilder sb = new StringBuilder(len);
for (int i = 0; i < len; ++i) {
String thisChar = String.valueOf(text.charAt(i));
// Remove morpheme markers from the ATB vocalized section
if (isWord && removeMorphMarker && thisChar.equals("+")) {
continue;
}
if (removeLengthening && isLengthening(text, i)) {
continue;
}
if (normMap.containsKey(thisChar)) {
thisChar = normMap.get(thisChar);
}
if (thisChar.length() > 0) {
sb.append(thisChar);
}
}
return sb.toString();
}
private boolean isLengthening(String text, int pos) {
if (pos == 0) return false;
String thisChar = String.valueOf(text.charAt(pos));
if (!thisChar.equals(String.valueOf(text.charAt(pos - 1))))
return false;
if (pos < text.length() - 1 && thisChar.equals(String.valueOf(text.charAt(pos + 1))))
return true;
if (pos >= 2 && thisChar.equals(String.valueOf(text.charAt(pos - 2))))
return true;
return false;
}
/** Make the next token.
*
* @param txt What the token should be
* @param originalText The original String that got transformed into txt
*/
private Object getNext(String txt, String originalText) {
if (tokenFactory == null) {
throw new RuntimeException(this.getClass().getName() + ": Token factory is null.");
}
if (invertible) {
//String str = prevWordAfter.toString();
//prevWordAfter.setLength(0);
CoreLabel word = (CoreLabel) tokenFactory.makeToken(txt, yychar, yylength());
word.set(CoreAnnotations.OriginalTextAnnotation.class, originalText);
//word.set(CoreAnnotations.BeforeAnnotation.class, str);
//prevWord.set(CoreAnnotations.AfterAnnotation.class, str);
//prevWord = word;
return word;
} else {
return tokenFactory.makeToken(txt, yychar, yylength());
}
}
private Object getNext(boolean isWord) {
String text = yytext();
String normText = normalizeToken(text, isWord);
return getNext(normText, text);
}
private Object getEllipsis() {
String ellipsisString = useUTF8Ellipsis ? "\u2026" : "...";
return getNext(ellipsisString, yytext());
}
/**
* Creates a new scanner
* There is also a java.io.InputStream version of this constructor.
*
* @param in the java.io.Reader to read input from.
*/
ArabicLexer(java.io.Reader in) {
this.zzReader = in;
}
/**
* Creates a new scanner.
* There is also java.io.Reader version of this constructor.
*
* @param in the java.io.Inputstream to read input from.
*/
ArabicLexer(java.io.InputStream in) {
this(new java.io.InputStreamReader
(in, java.nio.charset.Charset.forName("UTF-8")));
}
/**
* Unpacks the compressed character translation table.
*
* @param packed the packed character translation table
* @return the unpacked character translation table
*/
private static char [] zzUnpackCMap(String packed) {
char [] map = new char[0x10000];
int i = 0; /* index in packed string */
int j = 0; /* index in unpacked array */
while (i < 1960) {
int count = packed.charAt(i++);
char value = packed.charAt(i++);
do map[j++] = value; while (--count > 0);
}
return map;
}
/**
* Refills the input buffer.
*
* @return <code>false</code>, iff there was new input.
*
* @exception java.io.IOException if any I/O-Error occurs
*/
private boolean zzRefill() throws java.io.IOException {
/* first: make room (if you can) */
if (zzStartRead > 0) {
System.arraycopy(zzBuffer, zzStartRead,
zzBuffer, 0,
zzEndRead-zzStartRead);
/* translate stored positions */
zzEndRead-= zzStartRead;
zzCurrentPos-= zzStartRead;
zzMarkedPos-= zzStartRead;
zzStartRead = 0;
}
/* is the buffer big enough? */
if (zzCurrentPos >= zzBuffer.length) {
/* if not: blow it up */
char newBuffer[] = new char[zzCurrentPos*2];
System.arraycopy(zzBuffer, 0, newBuffer, 0, zzBuffer.length);
zzBuffer = newBuffer;
}
/* finally: fill the buffer with new input */
int numRead = zzReader.read(zzBuffer, zzEndRead,
zzBuffer.length-zzEndRead);
if (numRead > 0) {
zzEndRead+= numRead;
return false;
}
// unlikely but not impossible: read 0 characters, but not at end of stream
if (numRead == 0) {
int c = zzReader.read();
if (c == -1) {
return true;
} else {
zzBuffer[zzEndRead++] = (char) c;
return false;
}
}
// numRead < 0
return true;
}
/**
* Closes the input stream.
*/
public final void yyclose() throws java.io.IOException {
zzAtEOF = true; /* indicate end of file */
zzEndRead = zzStartRead; /* invalidate buffer */
if (zzReader != null)
zzReader.close();
}
/**
* Resets the scanner to read from a new input stream.
* Does not close the old reader.
*
* All internal variables are reset, the old input stream
* <b>cannot</b> be reused (internal buffer is discarded and lost).
* Lexical state is set to <tt>ZZ_INITIAL</tt>.
*
* Internal scan buffer is resized down to its initial length, if it has grown.
*
* @param reader the new input stream
*/
public final void yyreset(java.io.Reader reader) {
zzReader = reader;
zzAtBOL = true;
zzAtEOF = false;
zzEOFDone = false;
zzEndRead = zzStartRead = 0;
zzCurrentPos = zzMarkedPos = 0;
yyline = yychar = yycolumn = 0;
zzLexicalState = YYINITIAL;
if (zzBuffer.length > ZZ_BUFFERSIZE)
zzBuffer = new char[ZZ_BUFFERSIZE];
}
/**
* Returns the current lexical state.
*/
public final int yystate() {
return zzLexicalState;
}
/**
* Enters a new lexical state
*
* @param newState the new lexical state
*/
public final void yybegin(int newState) {
zzLexicalState = newState;
}
/**
* Returns the text matched by the current regular expression.
*/
public final String yytext() {
return new String( zzBuffer, zzStartRead, zzMarkedPos-zzStartRead );
}
/**
* Returns the character at position <tt>pos</tt> from the
* matched text.
*
* It is equivalent to yytext().charAt(pos), but faster
*
* @param pos the position of the character to fetch.
* A value from 0 to yylength()-1.
*
* @return the character at position pos
*/
public final char yycharat(int pos) {
return zzBuffer[zzStartRead+pos];
}
/**
* Returns the length of the matched text region.
*/
public final int yylength() {
return zzMarkedPos-zzStartRead;
}
/**
* Reports an error that occured while scanning.
*
* In a wellformed scanner (no or only correct usage of
* yypushback(int) and a match-all fallback rule) this method
* will only be called with things that "Can't Possibly Happen".
* If this method is called, something is seriously wrong
* (e.g. a JFlex bug producing a faulty scanner etc.).
*
* Usual syntax/scanner level error handling should be done
* in error fallback rules.
*
* @param errorCode the code of the errormessage to display
*/
private void zzScanError(int errorCode) {
String message;
try {
message = ZZ_ERROR_MSG[errorCode];
}
catch (ArrayIndexOutOfBoundsException e) {
message = ZZ_ERROR_MSG[ZZ_UNKNOWN_ERROR];
}
throw new Error(message);
}
/**
* Pushes the specified amount of characters back into the input stream.
*
* They will be read again by then next call of the scanning method
*
* @param number the number of characters to be read again.
* This number must not be greater than yylength()!
*/
public void yypushback(int number) {
if ( number > yylength() )
zzScanError(ZZ_PUSHBACK_2BIG);
zzMarkedPos -= number;
}
/**
* Resumes scanning until the next regular expression is matched,
* the end of input is encountered or an I/O-Error occurs.
*
* @return the next token
* @exception java.io.IOException if any I/O-Error occurs
*/
public Object next() throws java.io.IOException {
int zzInput;
int zzAction;
// cached fields:
int zzCurrentPosL;
int zzMarkedPosL;
int zzEndReadL = zzEndRead;
char [] zzBufferL = zzBuffer;
char [] zzCMapL = ZZ_CMAP;
int [] zzTransL = ZZ_TRANS;
int [] zzRowMapL = ZZ_ROWMAP;
int [] zzAttrL = ZZ_ATTRIBUTE;
while (true) {
zzMarkedPosL = zzMarkedPos;
yychar+= zzMarkedPosL-zzStartRead;
zzAction = -1;
zzCurrentPosL = zzCurrentPos = zzStartRead = zzMarkedPosL;
zzState = ZZ_LEXSTATE[zzLexicalState];
// set up zzAction for empty match case:
int zzAttributes = zzAttrL[zzState];
if ( (zzAttributes & 1) == 1 ) {
zzAction = zzState;
}
zzForAction: {
while (true) {
if (zzCurrentPosL < zzEndReadL)
zzInput = zzBufferL[zzCurrentPosL++];
else if (zzAtEOF) {
zzInput = YYEOF;
break zzForAction;
}
else {
// store back cached positions
zzCurrentPos = zzCurrentPosL;
zzMarkedPos = zzMarkedPosL;
boolean eof = zzRefill();
// get translated positions and possibly new buffer
zzCurrentPosL = zzCurrentPos;
zzMarkedPosL = zzMarkedPos;
zzBufferL = zzBuffer;
zzEndReadL = zzEndRead;
if (eof) {
zzInput = YYEOF;
break zzForAction;
}
else {
zzInput = zzBufferL[zzCurrentPosL++];
}
}
int zzNext = zzTransL[ zzRowMapL[zzState] + zzCMapL[zzInput] ];
if (zzNext == -1) break zzForAction;
zzState = zzNext;
zzAttributes = zzAttrL[zzState];
if ( (zzAttributes & 1) == 1 ) {
zzAction = zzState;
zzMarkedPosL = zzCurrentPosL;
if ( (zzAttributes & 8) == 8 ) break zzForAction;
}
}
}
// store back cached position
zzMarkedPos = zzMarkedPosL;
switch (zzAction < 0 ? zzAction : ZZ_ACTION[zzAction]) {
case 1:
{ System.err.printf("Untokenizable: %s%n", yytext());
return getNext(true);
}
case 9: break;
case 2:
{ if (tokenizeNLs) {
return getNext(NEWLINE_TOKEN, yytext());
}
}
case 10: break;
case 3:
{
}
case 11: break;
case 4:
{ return getNext(false);
}
case 12: break;
case 5:
{ return getNext(true);
}
case 13: break;
case 6:
{ return getEllipsis();
}
case 14: break;
case 7:
{ if (! removeProMarker) return getNext(false);
}
case 15: break;
case 8:
{ if (removeProMarker) {
if ( ! removeSegMarker) {
return getNext("-", yytext());
}
} else {
return getNext(false);
}
}
case 16: break;
default:
if (zzInput == YYEOF && zzStartRead == zzCurrentPos) {
zzAtEOF = true;
{
return null;
}
}
else {
zzScanError(ZZ_NO_MATCH);
}
}
}
}
}