Mercurial > hg > mpdl-group
view software/mpdl-services/mpiwg-mpdl-lt/src/de/mpg/mpiwg/berlin/mpdl/lt/text/norm/lang/MpdlNormalizerLexLA.java @ 23:e845310098ba
diverse Korrekturen
author | Josef Willenborg <jwillenborg@mpiwg-berlin.mpg.de> |
---|---|
date | Tue, 27 Nov 2012 12:35:19 +0100 |
parents | 4a3641ae14d2 |
children |
line wrap: on
line source
/* The following code was generated by JFlex 1.4.3 on 28.03.12 18:57 */ /* * 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 28.03.12 18:57 from the specification file * <tt>/Users/jwillenborg/test/jflexNew/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 = 10; public static final int RENAISSANCE_DISP = 8; public static final int SEARCH = 6; public static final int DICT = 4; 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, 3, 4, 5, 6, 1, 2, 3, 4, 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\24\1\0\1\23\14\0\1\21"+ "\1\0\1\22\1\0\1\0\1\1\3\2\1\1\2\2\1\57\1\1"+ "\1\0\1\2\1\3\2\2\1\1\1\2\1\52\1\3\2\2\1\70"+ "\1\71\2\2\1\72\1\2\6\0\1\63\1\2\1\53\1\47\1\11"+ "\2\2\1\55\1\14\1\33\1\2\1\54\1\44\1\13\1\65\1\17"+ "\1\7\1\16\1\36\1\15\1\10\1\12\2\2\1\72\1\2\62\0"+ "\1\4\30\0\1\31\30\0\1\27\1\43\1\35\1\61\3\0\1\30"+ "\1\0\1\45\1\37\1\0\1\64\1\51\1\40\1\56\1\66\2\0"+ "\1\46\1\41\1\60\4\0\1\50\1\42\1\62\1\67\34\0\1\30"+ "\71\0\1\32\53\0\1\20\u0181\0\1\34\ud4fe\0\1\25\u0590\0\1\26"+ "\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 = "\14\0\1\1\1\2\2\3\1\1\1\4\1\3\1\2"+ "\1\3\1\2\1\5\3\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\5\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\22\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\12\1\0\1\54\6\0\1\55\3\0"+ "\1\56\1\57\1\60\3\0\1\61\5\0\1\53\1\0"; private static int [] zzUnpackAction() { int [] result = new int[190]; 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\73\0\166\0\261\0\354\0\u0127\0\u0162\0\u019d"+ "\0\u01d8\0\u0213\0\u024e\0\u0289\0\u02c4\0\u02c4\0\u02c4\0\u02ff"+ "\0\u033a\0\u02c4\0\u0375\0\u03b0\0\u03eb\0\u0426\0\u02c4\0\u0213"+ "\0\u0461\0\u0289\0\u02c4\0\u02c4\0\u02c4\0\u02c4\0\u049c\0\u04d7"+ "\0\u0512\0\u054d\0\u0588\0\u05c3\0\u05fe\0\u0639\0\u0674\0\u06af"+ "\0\u06ea\0\u0725\0\u0760\0\u079b\0\u07d6\0\u0811\0\u02c4\0\u084c"+ "\0\u0887\0\u08c2\0\u08fd\0\u0938\0\u0973\0\u09ae\0\u09e9\0\u0a24"+ "\0\u0a5f\0\u02c4\0\u02c4\0\u0a9a\0\u0ad5\0\u0b10\0\u0b4b\0\u0b86"+ "\0\u02c4\0\u02c4\0\u02c4\0\u02c4\0\u0bc1\0\u02c4\0\u02c4\0\u02c4"+ "\0\u02c4\0\u0bfc\0\u02c4\0\u0c37\0\u0c72\0\u0cad\0\u0ce8\0\u0d23"+ "\0\u0d5e\0\u0d99\0\u0dd4\0\u0e0f\0\u0e4a\0\u0e85\0\u0ec0\0\u0efb"+ "\0\u0f36\0\u0f71\0\u0fac\0\u02c4\0\u0fe7\0\u1022\0\u105d\0\u02c4"+ "\0\u1098\0\u10d3\0\u110e\0\u02c4\0\u1149\0\u02c4\0\u1184\0\u11bf"+ "\0\u11fa\0\u02c4\0\u02c4\0\u02c4\0\u1235\0\u02c4\0\u02c4\0\u1270"+ "\0\u12ab\0\u02c4\0\u12e6\0\u1321\0\u135c\0\u1397\0\u13d2\0\u140d"+ "\0\u1448\0\u1483\0\u14be\0\u02c4\0\u14f9\0\u1534\0\u156f\0\u15aa"+ "\0\u15e5\0\u1620\0\u165b\0\u0a24\0\u02c4\0\u1696\0\u02c4\0\u16d1"+ "\0\u02c4\0\u170c\0\u02c4\0\u02c4\0\u02c4\0\u02c4\0\u1747\0\u02c4"+ "\0\u1782\0\u02c4\0\u17bd\0\u02c4\0\u17f8\0\u02c4\0\u1833\0\u186e"+ "\0\u18a9\0\u08fd\0\u18e4\0\u191f\0\u195a\0\u1995\0\u19d0\0\u1a0b"+ "\0\u02c4\0\u1a46\0\u1a81\0\u14f9\0\u1abc\0\u02c4\0\u1af7\0\u1b32"+ "\0\u1b6d\0\u1ba8\0\u1be3\0\u1c1e\0\u02c4\0\u1c59\0\u1c94\0\u1ccf"+ "\0\u02c4\0\u02c4\0\u02c4\0\u1d0a\0\u1d45\0\u1d80\0\u02c4\0\u1dbb"+ "\0\u1df6\0\u1e31\0\u1e6c\0\u1ea7\0\u02c4\0\u1ee2"; private static int [] zzUnpackRowMap() { int [] result = new int[190]; 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\2\0\1\13\1\14\45\0\1\15\1\16"+ "\1\17\1\20\1\21\1\15\1\22\1\23\1\24\1\16"+ "\1\25\1\17\1\26\1\17\1\20\1\17\1\27\1\30"+ "\2\15\1\31\1\32\1\15\1\33\1\34\1\35\1\36"+ "\2\15\1\37\1\17\1\40\1\41\1\42\1\43\1\44"+ "\1\17\1\45\1\46\1\17\1\47\1\15\1\50\1\17"+ "\1\20\1\17\1\15\1\17\1\15\1\51\1\52\1\53"+ "\1\15\1\54\2\15\1\55\1\56\1\57\1\15\1\16"+ "\1\17\1\20\1\21\1\15\1\22\1\60\1\61\1\16"+ "\1\25\1\17\1\62\1\17\1\20\1\63\1\64\1\30"+ "\2\15\1\31\1\32\1\15\1\33\1\34\1\35\1\36"+ "\2\15\1\37\1\17\1\40\1\41\1\42\1\43\1\44"+ "\1\17\1\45\1\46\1\17\1\47\1\15\1\65\1\17"+ "\1\20\1\66\1\15\1\67\1\70\1\51\1\52\1\53"+ "\1\15\1\54\2\15\1\71\1\56\1\57\1\15\1\16"+ "\1\17\1\20\1\21\1\15\1\72\1\23\1\24\1\16"+ "\1\25\1\17\1\26\1\17\1\20\1\17\1\27\1\30"+ "\2\15\1\31\1\32\1\15\1\33\1\34\1\35\1\36"+ "\2\15\1\37\1\17\1\40\1\41\1\42\1\43\1\44"+ "\1\17\1\45\1\46\1\17\1\47\1\15\1\50\1\17"+ "\1\20\1\17\1\15\1\17\1\15\1\51\1\52\1\53"+ "\1\15\1\54\2\15\1\55\1\56\1\57\1\15\1\16"+ "\1\17\1\20\1\21\1\15\1\72\1\60\1\61\1\16"+ "\1\25\1\17\1\62\1\17\1\20\1\63\1\64\1\30"+ "\2\15\1\31\1\32\1\15\1\33\1\34\1\35\1\36"+ "\2\15\1\37\1\17\1\40\1\41\1\42\1\43\1\44"+ "\1\17\1\45\1\46\1\17\1\47\1\15\1\65\1\17"+ "\1\20\1\66\1\15\1\67\1\70\1\51\1\52\1\53"+ "\1\15\1\54\2\15\1\71\1\56\1\57\1\15\1\16"+ "\1\17\1\20\1\21\1\15\1\73\1\23\1\24\1\16"+ "\1\25\1\17\1\26\1\17\1\20\1\17\1\27\1\30"+ "\2\15\1\31\1\32\1\15\1\33\1\34\1\35\1\36"+ "\2\15\1\37\1\17\1\40\1\41\1\42\1\43\1\44"+ "\1\17\1\45\1\46\1\17\1\47\1\15\1\50\1\17"+ "\1\20\1\17\1\15\1\17\1\15\1\51\1\52\1\53"+ "\1\15\1\54\2\15\1\55\1\56\1\57\1\15\1\16"+ "\1\17\1\20\1\21\1\15\1\73\1\60\1\61\1\16"+ "\1\25\1\17\1\62\1\17\1\20\1\63\1\64\1\30"+ "\2\15\1\31\1\32\1\15\1\33\1\34\1\35\1\36"+ "\2\15\1\37\1\17\1\40\1\41\1\42\1\43\1\44"+ "\1\17\1\45\1\46\1\17\1\47\1\15\1\65\1\17"+ "\1\20\1\66\1\15\1\67\1\70\1\51\1\52\1\53"+ "\1\15\1\54\2\15\1\71\1\56\1\57\14\0\1\74"+ "\2\0\1\75\1\76\57\0\1\77\65\0\21\100\2\0"+ "\50\100\21\0\1\12\77\0\1\101\151\0\1\102\56\0"+ "\1\102\6\0\1\103\77\0\1\104\21\0\1\105\37\0"+ "\1\106\6\0\2\106\2\0\1\106\13\0\3\106\30\0"+ "\1\106\1\0\1\106\1\107\1\110\1\106\4\0\2\111"+ "\1\112\2\0\1\111\2\0\2\111\1\0\4\111\3\0"+ "\1\112\2\0\1\111\6\0\1\111\5\0\1\111\2\0"+ "\1\111\2\0\4\111\1\0\1\111\11\0\1\111\34\0"+ "\1\113\44\0\1\103\13\0\1\12\60\0\1\114\2\0"+ "\2\115\1\0\2\116\17\0\1\116\5\0\1\116\35\0"+ "\1\117\2\0\2\120\1\0\2\121\17\0\1\121\5\0"+ "\1\121\35\0\1\122\2\0\2\123\1\0\2\124\17\0"+ "\1\124\5\0\1\124\35\0\1\125\2\0\2\126\1\0"+ "\2\127\17\0\1\127\5\0\1\127\35\0\1\130\1\0"+ "\1\131\2\132\1\0\2\133\17\0\1\133\5\0\1\133"+ "\34\0\1\134\1\114\26\0\1\135\5\0\1\136\6\0"+ "\1\137\25\0\1\140\1\117\5\0\1\141\1\142\17\0"+ "\1\143\42\0\1\144\1\125\37\0\1\145\31\0\1\146"+ "\27\0\1\147\5\0\1\150\7\0\1\151\30\0\1\152"+ "\56\0\1\153\7\0\1\134\1\114\6\0\1\154\112\0"+ "\1\155\120\0\1\34\72\0\1\36\1\0\1\156\5\0"+ "\1\106\6\0\2\106\2\0\1\106\13\0\3\106\30\0"+ "\1\106\1\0\1\106\2\0\1\106\4\0\2\157\1\160"+ "\2\0\1\157\2\0\2\157\1\0\4\157\3\0\1\160"+ "\2\0\1\157\6\0\1\157\5\0\1\157\2\0\1\157"+ "\2\0\4\157\1\0\1\157\11\0\1\157\11\0\1\161"+ "\1\0\1\104\21\0\1\105\37\0\1\162\6\0\2\162"+ "\2\0\1\162\13\0\3\162\30\0\1\162\1\0\1\162"+ "\1\107\1\110\1\162\15\0\1\163\17\0\1\113\50\0"+ "\1\164\71\0\1\165\1\164\71\0\1\166\1\0\1\152"+ "\56\0\1\153\57\0\1\167\72\0\1\170\22\0\1\144"+ "\65\0\1\162\6\0\2\162\2\0\1\162\13\0\3\162"+ "\30\0\1\162\1\0\1\162\2\0\1\162\15\0\1\171"+ "\70\0\1\172\71\0\1\173\1\172\65\0\1\174\17\0"+ "\1\174\46\0\21\100\1\0\1\175\1\176\47\100\10\0"+ "\1\177\67\0\1\200\75\0\1\115\73\0\1\201\70\0"+ "\1\114\2\0\2\115\67\0\1\120\73\0\1\202\70\0"+ "\1\117\2\0\2\120\67\0\1\123\73\0\1\203\70\0"+ "\1\122\2\0\2\123\67\0\1\126\73\0\1\204\70\0"+ "\1\125\2\0\2\126\67\0\1\132\70\0\1\205\75\0"+ "\1\206\70\0\1\130\2\0\2\132\65\0\1\207\1\210"+ "\71\0\1\211\1\212\71\0\1\213\72\0\1\214\72\0"+ "\1\215\72\0\1\216\1\217\71\0\1\220\1\221\71\0"+ "\1\222\1\223\71\0\1\224\1\225\71\0\1\226\72\0"+ "\1\222\71\0\1\227\136\0\1\230\25\0\1\231\10\0"+ "\1\232\6\0\1\231\64\0\1\233\60\0\1\234\12\0"+ "\1\232\4\0\1\234\117\0\1\235\74\0\1\236\72\0"+ "\1\237\23\0\1\240\10\0\1\75\6\0\1\240\64\0"+ "\1\241\60\0\1\242\12\0\1\75\4\0\1\242\67\0"+ "\1\243\51\0\21\100\1\0\1\244\1\176\47\100\11\0"+ "\1\245\63\0\2\111\3\0\1\111\2\0\2\111\1\0"+ "\4\111\6\0\1\111\6\0\1\111\5\0\1\111\2\0"+ "\1\111\2\0\4\111\1\0\1\111\11\0\1\111\7\0"+ "\1\134\72\0\1\140\72\0\1\246\72\0\1\146\74\0"+ "\1\247\72\0\1\250\72\0\1\251\72\0\1\252\72\0"+ "\1\253\72\0\1\254\64\0\2\157\3\0\1\157\2\0"+ "\2\157\1\0\4\157\6\0\1\157\6\0\1\157\5\0"+ "\1\157\2\0\1\157\2\0\4\157\1\0\1\157\11\0"+ "\1\157\7\0\1\255\71\0\1\256\71\0\1\257\17\0"+ "\1\257\53\0\1\260\73\0\1\261\72\0\1\262\72\0"+ "\1\263\71\0\1\264\72\0\1\265\110\0\1\266\55\0"+ "\1\267\75\0\1\270\72\0\1\271\72\0\1\272\72\0"+ "\1\273\72\0\1\155\72\0\1\274\76\0\1\232\62\0"+ "\1\275\104\0\1\232\70\0\1\75\74\0\1\75\53\0"+ "\21\276\2\0\50\276\6\0\1\207\72\0\1\211\72\0"+ "\1\216\72\0\1\220\72\0\1\224\64\0\21\276\1\0"+ "\1\57\50\276"; private static int [] zzUnpackTrans() { int [] result = new int[7965]; 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\3\0\3\11\2\1\1\11\4\1\1\11"+ "\3\1\4\11\20\1\1\11\12\1\2\11\5\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\10\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\1\1\0\1\11\6\0\1\11\3\0\3\11"+ "\3\0\1\11\5\0\1\11\1\0"; private static int [] zzUnpackAttribute() { int [] result = new int[190]; 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 < 202) { 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); } } } } }