Simple lexer for parsing text, including Turkish chars

gistfile1.txt

/*
 * To change this template, choose Tools | Templates
 * and open the template in the editor.
 */
lexer grammar TestLexer;

@header {
package lexer;
}

Whitespace
    : [ \t\n\r]+ -> skip;

fragment Digit: [0-9];

// Letters
fragment Letters
    : [a-z\u00e7\u011f\u0131\u00f6\u015f\u00fc\u00e2\u00ee\u00fb];
//    : [a-z];

fragment LettersCapital
    : [A-Z\u00c7\u011e\u0130\u00d6\u015e\u00dc\u00c2\u00ce\u00db];
//    : [A-Z];

fragment AllAlphanumerical
    : [0-9a-zA-Z\u00e7\u011f\u0131\u00f6\u015f\u00fc\u00e2\u00ee\u00fb\u00c7\u011e\u0130\u00d6\u015e\u00dc\u00c2\u00ce\u00db\-];    
//    : [0-9a-zA-Z];

fragment AposAndSuffix: '\'' Letters+;

Number
    : Digit+ ;

Word
    : LettersCapital? Letters+;

WordWithApos
    : LettersCapital? Letters+ AposAndSuffix;

Alphanumerical
    : AllAlphanumerical+ AposAndSuffix?;

Punctuation
    : [.,?];

Unknown : .+? ;