Mercurial > hg > mpdl-group
diff software/eXist/mpdl-modules/src/de/mpg/mpiwg/berlin/mpdl/lt/analyzer/lang/MpdlNormalizerLexLA.java @ 9:1ec29fdd0db8
neue .lex Dateien f?r Normalisierung / externe Objekte update
author | Josef Willenborg <jwillenborg@mpiwg-berlin.mpg.de> |
---|---|
date | Tue, 22 Feb 2011 16:03:45 +0100 |
parents | |
children | 5df60f24e997 |
line wrap: on
line diff
--- /dev/null Thu Jan 01 00:00:00 1970 +0000 +++ b/software/eXist/mpdl-modules/src/de/mpg/mpiwg/berlin/mpdl/lt/analyzer/lang/MpdlNormalizerLexLA.java Tue Feb 22 16:03:45 2011 +0100 @@ -0,0 +1,990 @@ +/* The following code was generated by JFlex 1.4.3 on 22.02.11 12:04 */ + +/* + * Normalization rules for Latin text + * [this is a JFlex specification] + * + * Wolfgang Schmidle + * version 0.96 + * 2011-02-21 + * + */ + +package de.mpg.mpiwg.berlin.mpdl.lt.analyzer.lang; + + +/** + * This class is a scanner generated by + * <a href="http://www.jflex.de/">JFlex</a> 1.4.3 + * on 22.02.11 12:04 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 = 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, 1, 2, 1, 2, 3, 4, 1, 2 + }; + + /** + * Translates characters to character classes + */ + private static final String ZZ_CMAP_PACKED = + "\12\0\1\5\42\0\1\4\23\0\1\1\3\2\1\1\2\2\1\52"+ + "\1\1\1\0\1\2\1\3\2\2\1\1\1\2\1\45\1\3\2\2"+ + "\1\63\1\64\2\2\1\0\1\2\6\0\1\56\1\2\1\46\1\42"+ + "\1\10\2\2\1\50\1\13\1\26\1\2\1\47\1\37\1\12\1\60"+ + "\1\16\1\6\1\15\1\31\1\14\1\7\1\11\2\2\1\0\1\2"+ + "\62\0\1\4\30\0\1\24\30\0\1\22\1\36\1\30\1\54\3\0"+ + "\1\23\1\0\1\40\1\32\1\0\1\57\1\44\1\33\1\51\1\61"+ + "\2\0\1\41\1\34\1\53\4\0\1\43\1\35\1\55\1\62\34\0"+ + "\1\23\71\0\1\25\53\0\1\17\u0181\0\1\27\ud4fe\0\1\20\u0590\0"+ + "\1\21\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 = + "\10\0\1\1\1\2\2\3\1\4\1\5\1\3\1\2"+ + "\1\3\1\2\1\6\1\1\1\7\1\10\1\11\1\12"+ + "\11\1\1\3\2\1\3\2\2\3\2\2\1\3\1\6"+ + "\3\3\1\1\1\2\1\13\4\0\1\14\1\15\1\16"+ + "\1\0\1\17\1\20\1\21\1\22\1\0\1\23\20\0"+ + "\1\24\3\0\1\25\3\0\1\26\1\0\1\27\3\0"+ + "\1\30\1\31\1\32\1\0\1\33\1\34\2\0\1\35"+ + "\16\0\1\36\1\0\1\37\1\0\1\40\1\0\1\41"+ + "\1\42\1\43\1\44\1\0\1\45\1\0\1\46\1\0"+ + "\1\47\1\0\1\50\3\0\1\51\10\0\1\52\6\0"+ + "\1\53\1\51\1\54\1\55\1\56\1\57\5\0"; + + private static int [] zzUnpackAction() { + int [] result = new int[166]; + 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\65\0\152\0\237\0\324\0\u0109\0\u013e\0\u0173"+ + "\0\u01a8\0\u01a8\0\u01a8\0\u01dd\0\u01a8\0\u01a8\0\u0212\0\u0247"+ + "\0\u027c\0\u02b1\0\u01a8\0\u0173\0\u01a8\0\u01a8\0\u01a8\0\u01a8"+ + "\0\u02e6\0\u031b\0\u0350\0\u0385\0\u03ba\0\u03ef\0\u0424\0\u0459"+ + "\0\u048e\0\u04c3\0\u04f8\0\u052d\0\u0562\0\u0597\0\u05cc\0\u0601"+ + "\0\u0636\0\u066b\0\u06a0\0\u06d5\0\u070a\0\u073f\0\u0774\0\u07a9"+ + "\0\u07de\0\u0813\0\u01a8\0\u0848\0\u087d\0\u08b2\0\u01a8\0\u01a8"+ + "\0\u01a8\0\u01a8\0\u08e7\0\u01a8\0\u01a8\0\u01a8\0\u01a8\0\u091c"+ + "\0\u01a8\0\u0951\0\u0986\0\u09bb\0\u09f0\0\u0a25\0\u0a5a\0\u0a8f"+ + "\0\u0ac4\0\u0af9\0\u0b2e\0\u0b63\0\u0b98\0\u0bcd\0\u0c02\0\u0c37"+ + "\0\u0c6c\0\u01a8\0\u0ca1\0\u0cd6\0\u0d0b\0\u01a8\0\u0d40\0\u0d75"+ + "\0\u0daa\0\u01a8\0\u0ddf\0\u01a8\0\u0e14\0\u0e49\0\u0e7e\0\u01a8"+ + "\0\u01a8\0\u01a8\0\u0eb3\0\u01a8\0\u01a8\0\u0ee8\0\u0f1d\0\u01a8"+ + "\0\u0f52\0\u0f87\0\u0fbc\0\u0ff1\0\u1026\0\u105b\0\u1090\0\u10c5"+ + "\0\u10fa\0\u112f\0\u1164\0\u1199\0\u11ce\0\u07de\0\u01a8\0\u1203"+ + "\0\u01a8\0\u1238\0\u01a8\0\u126d\0\u01a8\0\u01a8\0\u01a8\0\u01a8"+ + "\0\u12a2\0\u01a8\0\u12d7\0\u01a8\0\u130c\0\u01a8\0\u1341\0\u01a8"+ + "\0\u1376\0\u13ab\0\u06d5\0\u13e0\0\u1415\0\u144a\0\u147f\0\u14b4"+ + "\0\u14e9\0\u01a8\0\u151e\0\u1553\0\u01a8\0\u1588\0\u15bd\0\u15f2"+ + "\0\u1627\0\u165c\0\u1691\0\u01a8\0\u01a8\0\u01a8\0\u01a8\0\u01a8"+ + "\0\u01a8\0\u16c6\0\u16fb\0\u1730\0\u1765\0\u179a"; + + private static int [] zzUnpackRowMap() { + int [] result = new int[166]; + 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 = + "\20\0\1\10\44\0\1\11\1\12\1\13\1\14\1\15"+ + "\1\16\1\17\1\20\1\12\1\21\1\13\1\22\1\13"+ + "\1\14\1\13\1\23\1\24\1\11\1\25\1\26\1\27"+ + "\1\30\2\11\1\31\1\13\1\32\1\33\1\34\1\35"+ + "\1\36\1\13\1\37\1\40\1\13\1\41\1\11\1\42"+ + "\1\13\1\14\1\13\1\11\1\13\1\11\1\43\1\44"+ + "\1\45\1\11\1\46\2\11\1\47\1\50\1\11\1\12"+ + "\1\13\1\14\1\15\1\16\1\51\1\52\1\12\1\21"+ + "\1\13\1\53\1\13\1\14\1\54\1\55\1\24\1\11"+ + "\1\25\1\26\1\27\1\30\2\11\1\31\1\13\1\32"+ + "\1\33\1\34\1\35\1\36\1\13\1\37\1\40\1\13"+ + "\1\41\1\11\1\56\1\13\1\14\1\57\1\11\1\60"+ + "\1\61\1\43\1\44\1\45\1\11\1\46\2\11\1\62"+ + "\1\50\1\11\1\12\1\13\1\14\1\15\1\63\1\17"+ + "\1\20\1\12\1\21\1\13\1\22\1\13\1\14\1\13"+ + "\1\23\1\24\1\11\1\25\1\26\1\27\1\30\2\11"+ + "\1\31\1\13\1\32\1\33\1\34\1\35\1\36\1\13"+ + "\1\37\1\40\1\13\1\41\1\11\1\42\1\13\1\14"+ + "\1\13\1\11\1\13\1\11\1\43\1\44\1\45\1\11"+ + "\1\46\2\11\1\47\1\50\1\11\1\12\1\13\1\14"+ + "\1\15\1\63\1\51\1\52\1\12\1\21\1\13\1\53"+ + "\1\13\1\14\1\54\1\55\1\24\1\11\1\25\1\26"+ + "\1\27\1\30\2\11\1\31\1\13\1\32\1\33\1\34"+ + "\1\35\1\36\1\13\1\37\1\40\1\13\1\41\1\11"+ + "\1\56\1\13\1\14\1\57\1\11\1\60\1\61\1\43"+ + "\1\44\1\45\1\11\1\46\2\11\1\62\1\50\13\0"+ + "\1\64\2\0\1\65\1\66\51\0\1\67\101\0\1\70"+ + "\141\0\1\71\52\0\1\71\11\0\1\72\15\0\1\73"+ + "\36\0\1\74\5\0\2\74\2\0\1\74\42\0\1\74"+ + "\1\0\1\74\1\75\1\76\1\74\3\0\2\77\1\100"+ + "\1\0\1\77\2\0\2\77\1\0\4\77\2\0\1\77"+ + "\6\0\1\77\5\0\1\77\2\0\1\77\2\0\4\77"+ + "\1\0\1\77\11\0\1\77\26\0\1\101\44\0\1\102"+ + "\2\0\2\103\1\0\2\104\13\0\1\104\5\0\1\104"+ + "\33\0\1\105\2\0\2\106\1\0\2\107\13\0\1\107"+ + "\5\0\1\107\33\0\1\110\2\0\2\111\1\0\2\112"+ + "\13\0\1\112\5\0\1\112\33\0\1\113\2\0\2\114"+ + "\1\0\2\115\13\0\1\115\5\0\1\115\33\0\1\116"+ + "\1\0\1\117\2\120\1\0\2\121\13\0\1\121\5\0"+ + "\1\121\32\0\1\122\1\102\22\0\1\123\5\0\1\124"+ + "\6\0\1\125\23\0\1\126\1\105\5\0\1\127\1\130"+ + "\13\0\1\131\40\0\1\132\1\113\33\0\1\133\27\0"+ + "\1\134\23\0\1\135\5\0\1\136\7\0\1\137\26\0"+ + "\1\140\52\0\1\141\5\0\1\122\1\102\6\0\1\142"+ + "\100\0\1\143\112\0\1\26\64\0\1\30\1\0\1\144"+ + "\4\0\1\74\5\0\2\74\2\0\1\74\42\0\1\74"+ + "\1\0\1\74\2\0\1\74\3\0\2\145\1\146\1\0"+ + "\1\145\2\0\2\145\1\0\4\145\2\0\1\145\6\0"+ + "\1\145\5\0\1\145\2\0\1\145\2\0\4\145\1\0"+ + "\1\145\11\0\1\145\7\0\1\147\1\0\1\72\15\0"+ + "\1\73\36\0\1\150\5\0\2\150\2\0\1\150\42\0"+ + "\1\150\1\0\1\150\1\75\1\76\1\150\13\0\1\151"+ + "\13\0\1\101\46\0\1\152\63\0\1\153\1\152\63\0"+ + "\1\154\1\0\1\140\52\0\1\141\51\0\1\155\64\0"+ + "\1\156\20\0\1\132\60\0\1\150\5\0\2\150\2\0"+ + "\1\150\42\0\1\150\1\0\1\150\2\0\1\150\13\0"+ + "\1\157\62\0\1\160\63\0\1\161\1\160\63\0\1\162"+ + "\57\0\2\77\2\0\1\77\2\0\2\77\1\0\4\77"+ + "\2\0\1\77\6\0\1\77\5\0\1\77\2\0\1\77"+ + "\2\0\4\77\1\0\1\77\11\0\1\77\7\0\1\103"+ + "\65\0\1\163\62\0\1\102\2\0\2\103\61\0\1\106"+ + "\65\0\1\164\62\0\1\105\2\0\2\106\61\0\1\111"+ + "\65\0\1\165\62\0\1\110\2\0\2\111\61\0\1\114"+ + "\65\0\1\166\62\0\1\113\2\0\2\114\61\0\1\120"+ + "\62\0\1\167\67\0\1\170\62\0\1\116\2\0\2\120"+ + "\57\0\1\171\1\172\63\0\1\173\1\174\63\0\1\175"+ + "\64\0\1\176\64\0\1\177\64\0\1\200\1\201\63\0"+ + "\1\202\1\203\63\0\1\204\1\205\63\0\1\206\1\207"+ + "\63\0\1\210\64\0\1\204\61\0\2\145\2\0\1\145"+ + "\2\0\2\145\1\0\4\145\2\0\1\145\6\0\1\145"+ + "\5\0\1\145\2\0\1\145\2\0\4\145\1\0\1\145"+ + "\11\0\1\145\44\0\1\211\24\0\1\212\7\0\1\213"+ + "\65\0\1\214\53\0\1\215\11\0\1\213\112\0\1\216"+ + "\66\0\1\217\64\0\1\220\22\0\1\221\7\0\1\65"+ + "\65\0\1\222\53\0\1\223\11\0\1\65\56\0\1\224"+ + "\61\0\1\122\64\0\1\126\64\0\1\225\64\0\1\134"+ + "\66\0\1\226\64\0\1\227\64\0\1\230\64\0\1\231"+ + "\64\0\1\232\64\0\1\233\62\0\1\234\73\0\1\213"+ + "\54\0\1\235\76\0\1\213\53\0\1\236\64\0\1\237"+ + "\64\0\1\240\73\0\1\65\66\0\1\65\53\0\1\241"+ + "\67\0\1\242\64\0\1\243\64\0\1\244\64\0\1\245"+ + "\64\0\1\143\64\0\1\246\61\0\1\171\64\0\1\173"+ + "\64\0\1\200\64\0\1\202\64\0\1\206\57\0"; + + private static int [] zzUnpackTrans() { + int [] result = new int[6095]; + 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 = + "\6\0\1\1\1\0\3\11\1\1\2\11\4\1\1\11"+ + "\1\1\4\11\32\1\1\11\3\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"+ + "\16\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"+ + "\3\0\1\1\5\0\1\11\2\0\1\11\6\0\6\11"+ + "\5\0"; + + private static int [] zzUnpackAttribute() { + int [] result = new int[166]; + 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; + } + + + /** + * 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 < 184) { + 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 39: + // lookahead expression with fixed base length + zzMarkedPos = zzStartRead + 2; + { add("um"); + } + case 48: break; + case 28: + // lookahead expression with fixed base length + zzMarkedPos = zzStartRead + 1; + { cv = CONS; add("U"); + } + case 49: break; + case 4: + { add(yytext()); + } + case 50: break; + case 46: + // lookahead expression with fixed base length + zzMarkedPos = zzStartRead + 3; + { add("Hic"); + } + case 51: break; + case 9: + { cv = VOWEL; add("AE"); + } + case 52: break; + case 1: + { problem = 1; cv = 0; add(yytext()); + } + case 53: break; + case 5: + { switch (problem) { + case 1: return original; + default: return normalized; + } + } + case 54: break; + case 18: + // lookahead expression with fixed base length + zzMarkedPos = zzStartRead + 1; + { cv = CONS; add("u"); + } + case 55: break; + case 21: + // lookahead expression with fixed base length + zzMarkedPos = zzStartRead + 1; + { add("e"); + } + case 56: break; + case 29: + // lookahead expression with fixed base length + zzMarkedPos = zzStartRead + 1; + { cv = VOWEL; add(yytext().replaceAll("u", "v").replaceAll("U", "V")); + } + case 57: break; + case 34: + // lookahead expression with fixed base length + zzMarkedPos = zzStartRead + 2; + { add("et"); + } + case 58: break; + case 41: + // general lookahead, find correct zzMarkedPos + { int zzFState = 5; + 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 = 6; + 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 59: break; + case 3: + { cv = CONS; add(yytext()); + } + case 60: break; + case 27: + { cv = VOWEL; add("oi"); + } + case 61: break; + case 25: + { cv = CONS; add("QU"); + } + case 62: break; + case 15: + // 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 63: break; + case 7: + { cv = CONS; add("ss"); + } + case 64: break; + case 6: + { cv = CONS; add("s"); + } + case 65: break; + case 22: + // lookahead expression with fixed base length + zzMarkedPos = zzStartRead + 1; + { add("o"); + } + case 66: break; + case 33: + // lookahead expression with fixed base length + zzMarkedPos = zzStartRead + 2; + { add("ac"); + } + case 67: break; + case 2: + { cv = VOWEL; add(yytext()); + } + case 68: break; + case 43: + // lookahead expression with fixed base length + zzMarkedPos = zzStartRead + 3; + { add("qui"); + } + case 69: break; + case 35: + // lookahead expression with fixed base length + zzMarkedPos = zzStartRead + 2; + { add("er"); + } + case 70: break; + case 24: + { cv = CONS; add("Qu"); + } + case 71: break; + case 30: + // lookahead expression with fixed base length + zzMarkedPos = zzStartRead + 2; + { add("ve"); + } + case 72: break; + case 38: + // lookahead expression with fixed base length + zzMarkedPos = zzStartRead + 2; + { add("us"); + } + case 73: break; + case 32: + // lookahead expression with fixed base length + zzMarkedPos = zzStartRead + 2; + { add("am"); + } + case 74: break; + case 8: + { cv = VOWEL; add("ae"); + } + case 75: break; + case 11: + { switch (problem) { + case 1: return ""; + default: return normalized; + } + } + case 76: break; + case 26: + { add("ar"); + } + case 77: break; + case 45: + // lookahead expression with fixed base length + zzMarkedPos = zzStartRead + 3; + { add("hic"); + } + case 78: break; + case 17: + { cv = VOWEL; add("uu"); + } + case 79: break; + case 40: + // lookahead expression with fixed base length + zzMarkedPos = zzStartRead + 2; + { add("ul"); + } + case 80: break; + case 20: + // lookahead expression with fixed base length + zzMarkedPos = zzStartRead + 1; + { add("a"); + } + case 81: break; + case 10: + { cv = VOWEL; add("oe"); + } + case 82: break; + case 16: + { cv = VOWEL; add("ui"); + } + case 83: break; + case 14: + { cv = CONS; add("qu"); + } + case 84: break; + case 47: + // lookahead expression with fixed base length + zzMarkedPos = zzStartRead + 4; + { add("que"); + } + case 85: break; + case 23: + // lookahead expression with fixed base length + zzMarkedPos = zzStartRead + 1; + { add("u"); + } + case 86: break; + case 36: + // lookahead expression with fixed base length + zzMarkedPos = zzStartRead + 2; + { add("es"); + } + case 87: break; + case 44: + // lookahead expression with fixed base length + zzMarkedPos = zzStartRead + 3; + { add("Qui"); + } + case 88: break; + case 42: + // lookahead expression with fixed base length + zzMarkedPos = zzStartRead + 1; + { add("i"); + } + case 89: break; + case 12: + { add("X"); + } + case 90: break; + case 13: + { switch(cv) { + case CONS: add(yytext().replace("v", "u").replace("V", "U")); break; + default: cv = CONS; add(yytext()); break; + } + } + case 91: break; + case 19: + { cv = VOWEL; add("ii"); + } + case 92: break; + case 31: + // lookahead expression with fixed base length + zzMarkedPos = zzStartRead + 2; + { add("as"); + } + case 93: break; + case 37: + // lookahead expression with fixed base length + zzMarkedPos = zzStartRead + 2; + { add("od"); + } + case 94: break; + default: + if (zzInput == YYEOF && zzStartRead == zzCurrentPos) { + zzAtEOF = true; + return null; + } + else { + zzScanError(ZZ_NO_MATCH); + } + } + } + } + + +}