Mercurial > hg > mpdl-group
diff software/eXist/mpdl-modules/src/de/mpg/mpiwg/berlin/mpdl/lt/analyzer/lang/MpdlNormalizerLexDE.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/MpdlNormalizerLexDE.java Tue Feb 22 16:03:45 2011 +0100 @@ -0,0 +1,629 @@ +/* The following code was generated by JFlex 1.4.3 on 22.02.11 12:03 */ + +/* + * Normalization rules for German 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 12:03 from the specification file + * <tt>MpdlNormalizerLexDE.lex</tt> + */ +public class MpdlNormalizerLexDE { + + /** 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 SEARCH = 6; + public static final int DICT = 4; + public static final int YYINITIAL = 0; + public static final int CELEX = 8; + public static final int DISP = 2; + public static final int GRIMM = 10; + + /** + * 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, 1, 2, 2, 1, 1, 3, 3, 4, 4 + }; + + /** + * Translates characters to character classes + */ + private static final String ZZ_CMAP_PACKED = + "\12\0\1\1\65\0\1\15\32\2\6\0\1\6\15\2\1\10\5\2"+ + "\1\4\5\2\111\0\1\11\21\0\1\12\5\0\1\13\2\0\1\14"+ + "\4\0\1\11\21\0\1\12\5\0\1\13\202\0\1\3\u01e4\0\1\7"+ + "\1\0\1\5\ufc99\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 = + "\5\0\1\1\1\2\1\3\1\4\3\1\1\5\3\1"+ + "\1\6\1\7\1\10\1\11\1\12\1\13\1\14\1\15"+ + "\1\16"; + + private static int [] zzUnpackAction() { + int [] result = new int[25]; + 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\16\0\34\0\52\0\70\0\106\0\106\0\106"+ + "\0\106\0\124\0\142\0\160\0\106\0\176\0\214\0\232"+ + "\0\106\0\106\0\106\0\106\0\106\0\106\0\106\0\106"+ + "\0\106"; + + private static int [] zzUnpackRowMap() { + int [] result = new int[25]; + 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\6\1\0\1\6\1\7\11\6\1\10\1\6\1\11"+ + "\1\6\1\7\1\12\1\6\1\13\1\6\1\14\4\6"+ + "\1\10\1\6\1\15\1\6\1\7\1\12\1\6\1\13"+ + "\1\6\1\14\4\6\2\10\1\15\1\6\1\7\1\16"+ + "\1\10\1\17\1\10\1\20\1\21\1\22\1\23\1\24"+ + "\1\10\1\6\1\15\1\6\1\7\1\12\1\6\1\13"+ + "\1\6\1\14\3\6\1\25\1\10\23\0\1\26\1\0"+ + "\1\27\15\0\1\30\15\0\1\31\13\0\1\26\1\0"+ + "\1\23\15\0\1\21\15\0\1\22\6\0"; + + private static int [] zzUnpackTrans() { + int [] result = new int[168]; + 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 = + "\5\0\4\11\3\1\1\11\3\1\11\11"; + + private static int [] zzUnpackAttribute() { + int [] result = new int[25]; + 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 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 MpdlNormalizerLexDE(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 MpdlNormalizerLexDE(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 < 66) { + 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; + + zzAction = -1; + + zzCurrentPosL = zzCurrentPos = zzStartRead = zzMarkedPosL; + + 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 10: + { add("sz"); + } + case 15: break; + case 3: + { problem = 1; add(yytext()); + } + case 16: break; + case 6: + { add("ae"); + } + case 17: break; + case 2: + { add("s"); + } + case 18: break; + case 4: + { switch (problem) { + case 1: return original; + default: return normalized; + } + } + case 19: break; + case 12: + { add("ü"); + } + case 20: break; + case 8: + { add("ue"); + } + case 21: break; + case 11: + { add("u"); + } + case 22: break; + case 13: + { add("ä"); + } + case 23: break; + case 1: + { add(yytext()); + } + case 24: break; + case 9: + { add("ss"); + } + case 25: break; + case 7: + { add("oe"); + } + case 26: break; + case 14: + { add("ö"); + } + case 27: break; + case 5: + { switch (problem) { + case 1: return ""; + default: return normalized; + } + } + case 28: break; + default: + if (zzInput == YYEOF && zzStartRead == zzCurrentPos) { + zzAtEOF = true; + return null; + } + else { + zzScanError(ZZ_NO_MATCH); + } + } + } + } + + +}