Mercurial > hg > mpdl-group
diff software/mpdl-services/mpiwg-mpdl-lt/src/de/mpg/mpiwg/berlin/mpdl/lt/text/norm/lang/MpdlNormalizerLexLA.java @ 19:4a3641ae14d2
Erstellung
author | Josef Willenborg <jwillenborg@mpiwg-berlin.mpg.de> |
---|---|
date | Wed, 09 Nov 2011 15:32:05 +0100 |
parents | |
children | e845310098ba |
line wrap: on
line diff
--- /dev/null Thu Jan 01 00:00:00 1970 +0000 +++ b/software/mpdl-services/mpiwg-mpdl-lt/src/de/mpg/mpiwg/berlin/mpdl/lt/text/norm/lang/MpdlNormalizerLexLA.java Wed Nov 09 15:32:05 2011 +0100 @@ -0,0 +1,1024 @@ +/* The following code was generated by JFlex 1.4.3 on 05.09.11 10:35 */ + +/* + * Normalization rules for Latin text + * [this is a JFlex specification] + * + * Wolfgang Schmidle + * version 2011-07-12 + * + */ + +package de.mpg.mpiwg.berlin.mpdl.lt.text.norm.lang; + + +/** + * This class is a scanner generated by + * <a href="http://www.jflex.de/">JFlex</a> 1.4.3 + * on 05.09.11 10:35 from the specification file + * <tt>MpdlNormalizerLexLA.lex</tt> + */ +public class MpdlNormalizerLexLA { + + /** 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 RENAISSANCE_DICT = 8; + public static final int SEARCH = 10; + public static final int RENAISSANCE_DISP = 4; + public static final int DICT = 6; + public static final int YYINITIAL = 0; + public static final int RENAISSANCE_SEARCH = 12; + public static final int DISP = 2; + + /** + * 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, 1, 2, 1, 2, 3, 4, 3, 4, 5, 6, 5, 6 + }; + + /** + * Translates characters to character classes + */ + private static final String ZZ_CMAP_PACKED = + "\12\0\1\6\25\0\1\5\14\0\1\4\22\0\1\0\1\1\3\2"+ + "\1\1\2\2\1\53\1\1\1\0\1\2\1\3\2\2\1\1\1\2"+ + "\1\46\1\3\2\2\1\64\1\65\2\2\1\66\1\2\6\0\1\57"+ + "\1\2\1\47\1\43\1\11\2\2\1\51\1\14\1\27\1\2\1\50"+ + "\1\40\1\13\1\61\1\17\1\7\1\16\1\32\1\15\1\10\1\12"+ + "\2\2\1\66\1\2\62\0\1\4\30\0\1\25\30\0\1\23\1\37"+ + "\1\31\1\55\3\0\1\24\1\0\1\41\1\33\1\0\1\60\1\45"+ + "\1\34\1\52\1\62\2\0\1\42\1\35\1\54\4\0\1\44\1\36"+ + "\1\56\1\63\34\0\1\24\71\0\1\26\53\0\1\20\u0181\0\1\30"+ + "\ud4fe\0\1\21\u0590\0\1\22\u226e\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 = + "\12\0\1\1\1\2\2\3\1\1\1\4\1\3\1\2"+ + "\1\3\1\2\1\5\1\1\1\6\1\7\1\10\1\11"+ + "\11\1\1\3\2\1\3\2\1\3\1\12\1\3\2\2"+ + "\1\3\1\5\3\3\1\1\1\2\1\13\1\14\4\0"+ + "\1\15\1\16\1\17\1\20\1\0\1\21\1\22\1\23"+ + "\1\24\1\0\1\25\20\0\1\26\3\0\1\27\3\0"+ + "\1\30\1\0\1\31\3\0\1\32\1\33\1\34\1\0"+ + "\1\35\1\36\2\0\1\37\20\0\1\40\1\0\1\41"+ + "\1\0\1\42\1\0\1\43\1\44\1\45\1\46\1\0"+ + "\1\47\1\0\1\50\1\0\1\51\1\0\1\52\4\0"+ + "\1\53\10\0\1\54\6\0\1\55\3\0\1\56\1\57"+ + "\1\60\2\0\1\61\5\0\1\53"; + + private static int [] zzUnpackAction() { + int [] result = new int[179]; + 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\67\0\156\0\245\0\334\0\u0113\0\u014a\0\u0181"+ + "\0\u01b8\0\u01ef\0\u0226\0\u0226\0\u0226\0\u025d\0\u0294\0\u0226"+ + "\0\u02cb\0\u0302\0\u0339\0\u0370\0\u0226\0\u01ef\0\u0226\0\u0226"+ + "\0\u0226\0\u0226\0\u03a7\0\u03de\0\u0415\0\u044c\0\u0483\0\u04ba"+ + "\0\u04f1\0\u0528\0\u055f\0\u0596\0\u05cd\0\u0604\0\u063b\0\u0672"+ + "\0\u06a9\0\u06e0\0\u0226\0\u0717\0\u074e\0\u0785\0\u07bc\0\u07f3"+ + "\0\u082a\0\u0861\0\u0898\0\u08cf\0\u0906\0\u0226\0\u0226\0\u093d"+ + "\0\u0974\0\u09ab\0\u09e2\0\u0226\0\u0226\0\u0226\0\u0226\0\u0a19"+ + "\0\u0226\0\u0226\0\u0226\0\u0226\0\u0a50\0\u0226\0\u0a87\0\u0abe"+ + "\0\u0af5\0\u0b2c\0\u0b63\0\u0b9a\0\u0bd1\0\u0c08\0\u0c3f\0\u0c76"+ + "\0\u0cad\0\u0ce4\0\u0d1b\0\u0d52\0\u0d89\0\u0dc0\0\u0226\0\u0df7"+ + "\0\u0e2e\0\u0e65\0\u0226\0\u0e9c\0\u0ed3\0\u0f0a\0\u0226\0\u0f41"+ + "\0\u0226\0\u0f78\0\u0faf\0\u0fe6\0\u0226\0\u0226\0\u0226\0\u101d"+ + "\0\u0226\0\u0226\0\u1054\0\u108b\0\u0226\0\u10c2\0\u10f9\0\u1130"+ + "\0\u1167\0\u119e\0\u11d5\0\u120c\0\u1243\0\u127a\0\u0226\0\u12b1"+ + "\0\u12e8\0\u131f\0\u1356\0\u138d\0\u08cf\0\u0226\0\u13c4\0\u0226"+ + "\0\u13fb\0\u0226\0\u1432\0\u0226\0\u0226\0\u0226\0\u0226\0\u1469"+ + "\0\u0226\0\u14a0\0\u0226\0\u14d7\0\u0226\0\u150e\0\u0226\0\u1545"+ + "\0\u157c\0\u15b3\0\u07bc\0\u15ea\0\u1621\0\u1658\0\u168f\0\u16c6"+ + "\0\u16fd\0\u0226\0\u1734\0\u176b\0\u0226\0\u17a2\0\u17d9\0\u1810"+ + "\0\u1847\0\u187e\0\u18b5\0\u0226\0\u18ec\0\u1923\0\u195a\0\u0226"+ + "\0\u0226\0\u0226\0\u1991\0\u19c8\0\u0226\0\u19ff\0\u1a36\0\u1a6d"+ + "\0\u1aa4\0\u1adb\0\u0226"; + + private static int [] zzUnpackRowMap() { + int [] result = new int[179]; + 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 = + "\21\0\1\12\45\0\1\13\1\14\1\15\1\16\1\17"+ + "\1\13\1\20\1\21\1\22\1\14\1\23\1\15\1\24"+ + "\1\15\1\16\1\15\1\25\1\26\1\13\1\27\1\30"+ + "\1\31\1\32\2\13\1\33\1\15\1\34\1\35\1\36"+ + "\1\37\1\40\1\15\1\41\1\42\1\15\1\43\1\13"+ + "\1\44\1\15\1\16\1\15\1\13\1\15\1\13\1\45"+ + "\1\46\1\47\1\13\1\50\2\13\1\51\1\52\1\53"+ + "\1\13\1\14\1\15\1\16\1\17\1\13\1\20\1\54"+ + "\1\55\1\14\1\23\1\15\1\56\1\15\1\16\1\57"+ + "\1\60\1\26\1\13\1\27\1\30\1\31\1\32\2\13"+ + "\1\33\1\15\1\34\1\35\1\36\1\37\1\40\1\15"+ + "\1\41\1\42\1\15\1\43\1\13\1\61\1\15\1\16"+ + "\1\62\1\13\1\63\1\64\1\45\1\46\1\47\1\13"+ + "\1\50\2\13\1\65\1\52\1\53\1\13\1\14\1\15"+ + "\1\16\1\17\1\13\1\66\1\21\1\22\1\14\1\23"+ + "\1\15\1\24\1\15\1\16\1\15\1\25\1\26\1\13"+ + "\1\27\1\30\1\31\1\32\2\13\1\33\1\15\1\34"+ + "\1\35\1\36\1\37\1\40\1\15\1\41\1\42\1\15"+ + "\1\43\1\13\1\44\1\15\1\16\1\15\1\13\1\15"+ + "\1\13\1\45\1\46\1\47\1\13\1\50\2\13\1\51"+ + "\1\52\1\53\1\13\1\14\1\15\1\16\1\17\1\13"+ + "\1\66\1\54\1\55\1\14\1\23\1\15\1\56\1\15"+ + "\1\16\1\57\1\60\1\26\1\13\1\27\1\30\1\31"+ + "\1\32\2\13\1\33\1\15\1\34\1\35\1\36\1\37"+ + "\1\40\1\15\1\41\1\42\1\15\1\43\1\13\1\61"+ + "\1\15\1\16\1\62\1\13\1\63\1\64\1\45\1\46"+ + "\1\47\1\13\1\50\2\13\1\65\1\52\1\53\1\13"+ + "\1\14\1\15\1\16\1\17\1\13\1\67\1\21\1\22"+ + "\1\14\1\23\1\15\1\24\1\15\1\16\1\15\1\25"+ + "\1\26\1\13\1\27\1\30\1\31\1\32\2\13\1\33"+ + "\1\15\1\34\1\35\1\36\1\37\1\40\1\15\1\41"+ + "\1\42\1\15\1\43\1\13\1\44\1\15\1\16\1\15"+ + "\1\13\1\15\1\13\1\45\1\46\1\47\1\13\1\50"+ + "\2\13\1\51\1\52\1\53\1\13\1\14\1\15\1\16"+ + "\1\17\1\13\1\67\1\54\1\55\1\14\1\23\1\15"+ + "\1\56\1\15\1\16\1\57\1\60\1\26\1\13\1\27"+ + "\1\30\1\31\1\32\2\13\1\33\1\15\1\34\1\35"+ + "\1\36\1\37\1\40\1\15\1\41\1\42\1\15\1\43"+ + "\1\13\1\61\1\15\1\16\1\62\1\13\1\63\1\64"+ + "\1\45\1\46\1\47\1\13\1\50\2\13\1\65\1\52"+ + "\1\53\14\0\1\70\2\0\1\71\1\72\53\0\1\73"+ + "\103\0\1\74\145\0\1\75\52\0\1\75\6\0\1\76"+ + "\73\0\1\77\15\0\1\100\37\0\1\101\6\0\2\101"+ + "\2\0\1\101\7\0\3\101\30\0\1\101\1\0\1\101"+ + "\1\102\1\103\1\101\4\0\2\104\1\105\2\0\1\104"+ + "\2\0\2\104\1\0\4\104\2\0\1\104\6\0\1\104"+ + "\5\0\1\104\2\0\1\104\2\0\4\104\1\0\1\104"+ + "\11\0\1\104\30\0\1\106\46\0\1\107\2\0\2\110"+ + "\1\0\2\111\13\0\1\111\5\0\1\111\35\0\1\112"+ + "\2\0\2\113\1\0\2\114\13\0\1\114\5\0\1\114"+ + "\35\0\1\115\2\0\2\116\1\0\2\117\13\0\1\117"+ + "\5\0\1\117\35\0\1\120\2\0\2\121\1\0\2\122"+ + "\13\0\1\122\5\0\1\122\35\0\1\123\1\0\1\124"+ + "\2\125\1\0\2\126\13\0\1\126\5\0\1\126\34\0"+ + "\1\127\1\107\22\0\1\130\5\0\1\131\6\0\1\132"+ + "\25\0\1\133\1\112\5\0\1\134\1\135\13\0\1\136"+ + "\42\0\1\137\1\120\33\0\1\140\31\0\1\141\23\0"+ + "\1\142\5\0\1\143\7\0\1\144\30\0\1\145\52\0"+ + "\1\146\7\0\1\127\1\107\6\0\1\147\102\0\1\150"+ + "\114\0\1\30\66\0\1\32\1\0\1\151\5\0\1\101"+ + "\6\0\2\101\2\0\1\101\7\0\3\101\30\0\1\101"+ + "\1\0\1\101\2\0\1\101\4\0\2\152\1\153\2\0"+ + "\1\152\2\0\2\152\1\0\4\152\2\0\1\152\6\0"+ + "\1\152\5\0\1\152\2\0\1\152\2\0\4\152\1\0"+ + "\1\152\11\0\1\152\11\0\1\154\1\0\1\77\15\0"+ + "\1\100\37\0\1\155\6\0\2\155\2\0\1\155\7\0"+ + "\3\155\30\0\1\155\1\0\1\155\1\102\1\103\1\155"+ + "\15\0\1\156\13\0\1\106\50\0\1\157\65\0\1\160"+ + "\1\157\65\0\1\161\1\0\1\145\52\0\1\146\53\0"+ + "\1\162\66\0\1\163\22\0\1\137\61\0\1\155\6\0"+ + "\2\155\2\0\1\155\7\0\3\155\30\0\1\155\1\0"+ + "\1\155\2\0\1\155\15\0\1\164\64\0\1\165\65\0"+ + "\1\166\1\165\61\0\1\167\72\0\1\170\63\0\1\171"+ + "\71\0\1\110\67\0\1\172\64\0\1\107\2\0\2\110"+ + "\63\0\1\113\67\0\1\173\64\0\1\112\2\0\2\113"+ + "\63\0\1\116\67\0\1\174\64\0\1\115\2\0\2\116"+ + "\63\0\1\121\67\0\1\175\64\0\1\120\2\0\2\121"+ + "\63\0\1\125\64\0\1\176\71\0\1\177\64\0\1\123"+ + "\2\0\2\125\61\0\1\200\1\201\65\0\1\202\1\203"+ + "\65\0\1\204\66\0\1\205\66\0\1\206\66\0\1\207"+ + "\1\210\65\0\1\211\1\212\65\0\1\213\1\214\65\0"+ + "\1\215\1\216\65\0\1\217\66\0\1\213\65\0\1\220"+ + "\126\0\1\221\25\0\1\222\10\0\1\223\67\0\1\224"+ + "\54\0\1\225\12\0\1\223\114\0\1\226\70\0\1\227"+ + "\66\0\1\230\23\0\1\231\10\0\1\71\67\0\1\232"+ + "\54\0\1\233\12\0\1\71\60\0\1\234\57\0\2\104"+ + "\3\0\1\104\2\0\2\104\1\0\4\104\2\0\1\104"+ + "\6\0\1\104\5\0\1\104\2\0\1\104\2\0\4\104"+ + "\1\0\1\104\11\0\1\104\7\0\1\127\66\0\1\133"+ + "\66\0\1\235\66\0\1\141\70\0\1\236\66\0\1\237"+ + "\66\0\1\240\66\0\1\241\66\0\1\242\66\0\1\243"+ + "\60\0\2\152\3\0\1\152\2\0\2\152\1\0\4\152"+ + "\2\0\1\152\6\0\1\152\5\0\1\152\2\0\1\152"+ + "\2\0\4\152\1\0\1\152\11\0\1\152\7\0\1\244"+ + "\65\0\1\245\65\0\1\246\67\0\1\247\67\0\1\250"+ + "\66\0\1\251\66\0\1\252\65\0\1\253\66\0\1\254"+ + "\67\0\1\255\71\0\1\256\66\0\1\257\66\0\1\260"+ + "\66\0\1\261\66\0\1\150\66\0\1\262\72\0\1\223"+ + "\56\0\1\263\100\0\1\223\64\0\1\71\70\0\1\71"+ + "\55\0\1\200\66\0\1\202\66\0\1\207\66\0\1\211"+ + "\66\0\1\215\60\0"; + + private static int [] zzUnpackTrans() { + int [] result = new int[6930]; + 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 = + "\10\0\1\1\1\0\3\11\2\1\1\11\4\1\1\11"+ + "\1\1\4\11\20\1\1\11\12\1\2\11\4\0\4\11"+ + "\1\0\4\11\1\0\1\11\20\0\1\11\3\0\1\11"+ + "\3\0\1\11\1\0\1\11\3\0\3\11\1\0\2\11"+ + "\2\0\1\11\11\0\1\11\6\0\1\11\1\0\1\11"+ + "\1\0\1\11\1\0\4\11\1\0\1\11\1\0\1\11"+ + "\1\0\1\11\1\0\1\11\4\0\1\1\5\0\1\11"+ + "\2\0\1\11\6\0\1\11\3\0\3\11\2\0\1\11"+ + "\5\0\1\11"; + + private static int [] zzUnpackAttribute() { + int [] result = new int[179]; + 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; + + /** For the backwards DFA of general lookahead statements */ + private boolean [] zzFin = new boolean [ZZ_BUFFERSIZE+1]; + + /* user code: */ + private static final int CONS = 1; + private static final int VOWEL = 2; + private int cv = 0; // consonant = 1, vowel = 2, everything else = 0 + + private String original = ""; + private String normalized = ""; + private int problem = 0; + + private void add (String norm) { + original += yytext(); + normalized += norm; + } + + private static final String LB = "[\u002d\u00ad] "; + + + /** + * 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. + */ + public MpdlNormalizerLexLA(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. + */ + public MpdlNormalizerLexLA(java.io.InputStream in) { + this(new java.io.InputStreamReader(in)); + } + + /** + * 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 < 190) { + 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>. + * + * @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; + } + + + /** + * 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 java.lang.String yylex() 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; + + if (zzMarkedPosL > zzStartRead) { + switch (zzBufferL[zzMarkedPosL-1]) { + case '\n': + case '\u000B': + case '\u000C': + case '\u0085': + case '\u2028': + case '\u2029': + zzAtBOL = true; + break; + case '\r': + if (zzMarkedPosL < zzEndReadL) + zzAtBOL = zzBufferL[zzMarkedPosL] != '\n'; + else if (zzAtEOF) + zzAtBOL = false; + else { + boolean eof = zzRefill(); + zzMarkedPosL = zzMarkedPos; + zzEndReadL = zzEndRead; + zzBufferL = zzBuffer; + if (eof) + zzAtBOL = false; + else + zzAtBOL = zzBufferL[zzMarkedPosL] != '\n'; + } + break; + default: + zzAtBOL = false; + } + } + zzAction = -1; + + zzCurrentPosL = zzCurrentPos = zzStartRead = zzMarkedPosL; + + if (zzAtBOL) + zzState = ZZ_LEXSTATE[zzLexicalState+1]; + else + zzState = ZZ_LEXSTATE[zzLexicalState]; + + + 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; + + int 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 41: + // lookahead expression with fixed base length + zzMarkedPos = zzStartRead + 2; + { add("um"); + } + case 50: break; + case 30: + // lookahead expression with fixed base length + zzMarkedPos = zzStartRead + 1; + { cv = CONS; add("U"); + } + case 51: break; + case 15: + { add(yytext()); + } + case 52: break; + case 48: + // lookahead expression with fixed base length + zzMarkedPos = zzStartRead + 3; + { add("Hic"); + } + case 53: break; + case 8: + { cv = VOWEL; add("AE"); + } + case 54: break; + case 1: + { problem = 1; cv = 0; add(yytext()); + } + case 55: break; + case 4: + { switch (problem) { + case 1: return original; + default: return normalized; + } + } + case 56: break; + case 20: + // lookahead expression with fixed base length + zzMarkedPos = zzStartRead + 1; + { cv = CONS; add("u"); + } + case 57: break; + case 10: + { cv = 0; add(yytext()); + } + case 58: break; + case 12: + { switch (problem) { + case 1: return original; + default: return normalized.replaceAll(LB, "").toLowerCase(); + } + } + case 59: break; + case 36: + // lookahead expression with fixed base length + zzMarkedPos = zzStartRead + 2; + { add("et"); + } + case 60: break; + case 23: + // lookahead expression with fixed base length + zzMarkedPos = zzStartRead + 1; + { add("e"); + } + case 61: break; + case 31: + // lookahead expression with fixed base length + zzMarkedPos = zzStartRead + 1; + { cv = VOWEL; add(yytext().replaceAll("u", "v").replaceAll("U", "V")); + } + case 62: break; + case 43: + // general lookahead, find correct zzMarkedPos + { int zzFState = 7; + int zzFPos = zzStartRead; + if (zzFin.length <= zzBufferL.length) { zzFin = new boolean[zzBufferL.length+1]; } + boolean zzFinL[] = zzFin; + while (zzFState != -1 && zzFPos < zzMarkedPos) { + if ((zzAttrL[zzFState] & 1) == 1) { zzFinL[zzFPos] = true; } + zzInput = zzBufferL[zzFPos++]; + zzFState = zzTransL[ zzRowMapL[zzFState] + zzCMapL[zzInput] ]; + } + if (zzFState != -1 && (zzAttrL[zzFState] & 1) == 1) { zzFinL[zzFPos] = true; } + + zzFState = 8; + zzFPos = zzMarkedPos; + while (!zzFinL[zzFPos] || (zzAttrL[zzFState] & 1) != 1) { + zzInput = zzBufferL[--zzFPos]; + zzFState = zzTransL[ zzRowMapL[zzFState] + zzCMapL[zzInput] ]; + }; + zzMarkedPos = zzFPos; + } + { cv = VOWEL; add(yytext().replace("ſ", "s")); + } + case 63: break; + case 3: + { cv = CONS; add(yytext()); + } + case 64: break; + case 29: + { cv = VOWEL; add("oi"); + } + case 65: break; + case 27: + { cv = CONS; add("QU"); + } + case 66: break; + case 17: + // lookahead expression with fixed base length + zzMarkedPos = zzStartRead + 1; + { switch(cv) { + case VOWEL: add(yytext().replace("u", "v").replace("U", "V")); break; + default: cv = VOWEL; add(yytext()); break; + } + } + case 67: break; + case 6: + { cv = CONS; add("ss"); + } + case 68: break; + case 5: + { cv = CONS; add("s"); + } + case 69: break; + case 11: + { switch (problem) { + case 1: return ""; + default: return normalized.replaceAll(LB, ""); + } + } + case 70: break; + case 24: + // lookahead expression with fixed base length + zzMarkedPos = zzStartRead + 1; + { add("o"); + } + case 71: break; + case 35: + // lookahead expression with fixed base length + zzMarkedPos = zzStartRead + 2; + { add("ac"); + } + case 72: break; + case 2: + { cv = VOWEL; add(yytext()); + } + case 73: break; + case 45: + // lookahead expression with fixed base length + zzMarkedPos = zzStartRead + 3; + { add("qui"); + } + case 74: break; + case 37: + // lookahead expression with fixed base length + zzMarkedPos = zzStartRead + 2; + { add("er"); + } + case 75: break; + case 26: + { cv = CONS; add("Qu"); + } + case 76: break; + case 32: + // lookahead expression with fixed base length + zzMarkedPos = zzStartRead + 2; + { add("ve"); + } + case 77: break; + case 40: + // lookahead expression with fixed base length + zzMarkedPos = zzStartRead + 2; + { add("us"); + } + case 78: break; + case 34: + // lookahead expression with fixed base length + zzMarkedPos = zzStartRead + 2; + { add("am"); + } + case 79: break; + case 7: + { cv = VOWEL; add("ae"); + } + case 80: break; + case 28: + { add("ar"); + } + case 81: break; + case 47: + // lookahead expression with fixed base length + zzMarkedPos = zzStartRead + 3; + { add("hic"); + } + case 82: break; + case 19: + { cv = VOWEL; add("uu"); + } + case 83: break; + case 42: + // lookahead expression with fixed base length + zzMarkedPos = zzStartRead + 2; + { add("ul"); + } + case 84: break; + case 22: + // lookahead expression with fixed base length + zzMarkedPos = zzStartRead + 1; + { add("a"); + } + case 85: break; + case 9: + { cv = VOWEL; add("oe"); + } + case 86: break; + case 18: + { cv = VOWEL; add("ui"); + } + case 87: break; + case 16: + { cv = CONS; add("qu"); + } + case 88: break; + case 49: + // lookahead expression with fixed base length + zzMarkedPos = zzStartRead + 4; + { add("que"); + } + case 89: break; + case 25: + // lookahead expression with fixed base length + zzMarkedPos = zzStartRead + 1; + { add("u"); + } + case 90: break; + case 38: + // lookahead expression with fixed base length + zzMarkedPos = zzStartRead + 2; + { add("es"); + } + case 91: break; + case 46: + // lookahead expression with fixed base length + zzMarkedPos = zzStartRead + 3; + { add("Qui"); + } + case 92: break; + case 44: + // lookahead expression with fixed base length + zzMarkedPos = zzStartRead + 1; + { add("i"); + } + case 93: break; + case 13: + { add("X"); + } + case 94: break; + case 14: + { switch(cv) { + case CONS: add(yytext().replace("v", "u").replace("V", "U")); break; + default: cv = CONS; add(yytext()); break; + } + } + case 95: break; + case 21: + { cv = VOWEL; add("ii"); + } + case 96: break; + case 33: + // lookahead expression with fixed base length + zzMarkedPos = zzStartRead + 2; + { add("as"); + } + case 97: break; + case 39: + // lookahead expression with fixed base length + zzMarkedPos = zzStartRead + 2; + { add("od"); + } + case 98: break; + default: + if (zzInput == YYEOF && zzStartRead == zzCurrentPos) { + zzAtEOF = true; + return null; + } + else { + zzScanError(ZZ_NO_MATCH); + } + } + } + } + + +}