Mercurial > hg > mpdl-group
view software/eXist/mpdl-modules/src/de/mpg/mpiwg/berlin/mpdl/lt/analyzer/lang/MpdlNormalizerLexAll.java @ 6:2396a569e446
new functions: externalObjects, normalizer, Unicode2Betacode
author | Josef Willenborg <jwillenborg@mpiwg-berlin.mpg.de> |
---|---|
date | Tue, 08 Feb 2011 14:54:09 +0100 |
parents | |
children |
line wrap: on
line source
/* The following code was generated by JFlex 1.4.3 on 27.01.11 13:29 */ /* * Normalization rules for all languages * [this is a JFlex specification] * * Wolfgang Schmidle * 2011-01-25 * */ 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 27.01.11 13:29 from the specification file * <tt>MpdlNormalizerLexAll.lex</tt> */ public class MpdlNormalizerLexAll { /** 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 YYINITIAL = 0; public static final int ZH = 4; public static final int LA = 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, 3 }; /** * Translates characters to character classes */ private static final String ZZ_CMAP_PACKED = "\12\0\1\7\66\0\1\1\3\2\1\1\3\2\1\1\1\0\1\2"+ "\1\3\2\2\1\1\1\2\1\40\1\3\2\2\1\36\1\41\2\2"+ "\1\0\1\2\6\0\1\31\1\2\1\21\1\27\1\6\2\2\1\17"+ "\1\15\1\16\1\2\1\3\1\23\1\2\1\33\1\2\1\4\1\3"+ "\1\24\1\2\1\5\1\37\2\2\1\0\1\2\113\0\1\13\30\0"+ "\1\11\1\22\5\0\1\12\1\0\1\25\2\0\1\32\2\0\1\20"+ "\1\34\2\0\1\26\6\0\1\30\2\0\1\35\34\0\1\12\71\0"+ "\1\14\53\0\1\10\u6479\0\1\43\u057a\0\1\44\u0f5d\0\1\42\u5dab\0"+ "\1\46\u040e\0\1\47\u1d8f\0\1\45\u05e2\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 = "\4\0\1\1\1\2\1\3\1\4\3\5\1\4\1\6"+ "\1\7\1\10\1\11\1\12\1\13\10\4\4\5\1\14"+ "\1\15\1\16\1\17\1\1\1\20\1\21\1\22\1\23"+ "\1\24\1\25\1\26\1\0\1\27\3\0\1\30\1\0"+ "\1\31\3\0\1\32\1\33\1\34\1\35\1\36\1\37"+ "\1\0\1\40\2\0\1\41\1\0\1\42\3\0\1\43"+ "\1\0\1\44\1\0\1\45\11\0\1\46\5\0"; private static int [] zzUnpackAction() { int [] result = new int[89]; 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\50\0\120\0\170\0\240\0\240\0\240\0\240"+ "\0\240\0\310\0\360\0\u0118\0\240\0\240\0\240\0\240"+ "\0\240\0\240\0\u0140\0\u0168\0\u0190\0\u01b8\0\u01e0\0\u0208"+ "\0\u0230\0\u0258\0\u0280\0\u02a8\0\u02d0\0\u02f8\0\240\0\240"+ "\0\240\0\240\0\u0320\0\240\0\240\0\240\0\240\0\240"+ "\0\240\0\240\0\u0348\0\240\0\u0370\0\u0398\0\u03c0\0\240"+ "\0\u03e8\0\240\0\u0410\0\u0438\0\u0460\0\240\0\240\0\240"+ "\0\240\0\240\0\240\0\u0488\0\240\0\u04b0\0\u04d8\0\240"+ "\0\u0500\0\240\0\u0528\0\u0550\0\u0578\0\240\0\u05a0\0\240"+ "\0\u05c8\0\240\0\u05f0\0\u0618\0\u0640\0\u0668\0\u0690\0\u06b8"+ "\0\u06e0\0\u0708\0\u0730\0\240\0\u0758\0\u0780\0\u07a8\0\u07d0"+ "\0\u07f8"; private static int [] zzUnpackRowMap() { int [] result = new int[89]; 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 = "\7\5\1\6\40\5\1\7\1\10\1\11\1\12\1\13"+ "\1\14\1\10\1\15\1\16\1\17\1\20\1\21\1\22"+ "\1\23\1\7\1\11\1\7\1\11\1\24\2\11\1\25"+ "\1\26\1\11\1\27\1\30\1\7\1\31\2\7\1\32"+ "\1\33\1\34\1\35\7\7\1\10\1\11\1\12\1\13"+ "\1\14\1\10\1\15\1\16\1\17\1\20\1\21\1\22"+ "\1\23\1\7\1\36\1\7\1\11\1\24\2\11\1\25"+ "\1\26\1\11\1\27\1\30\1\7\1\31\2\7\1\32"+ "\1\33\1\34\1\35\6\7\7\5\1\6\32\5\1\37"+ "\1\40\1\41\1\42\1\43\1\5\107\0\1\44\1\0"+ "\1\45\45\0\1\46\11\0\1\47\3\0\2\47\3\0"+ "\4\47\4\0\1\47\2\0\2\47\1\0\2\47\1\0"+ "\1\47\1\50\1\51\1\47\27\0\1\52\35\0\1\53"+ "\2\0\1\54\13\0\1\55\1\56\27\0\1\57\2\0"+ "\1\60\44\0\1\61\2\0\1\62\17\0\1\63\43\0"+ "\1\64\1\65\55\0\1\20\47\0\1\22\1\0\1\66"+ "\14\0\1\67\3\0\2\67\3\0\4\67\4\0\1\67"+ "\2\0\2\67\1\0\2\67\1\0\1\67\2\0\1\67"+ "\13\0\3\70\3\0\2\70\5\0\1\70\1\0\1\70"+ "\1\0\2\70\2\0\1\70\7\0\3\70\45\0\1\71"+ "\1\0\1\72\10\0\3\73\3\0\2\73\5\0\1\73"+ "\1\0\1\73\1\0\2\73\2\0\1\73\7\0\3\73"+ "\26\0\1\74\76\0\1\75\5\0\1\76\46\0\1\77"+ "\2\0\1\100\44\0\1\101\2\0\1\102\45\0\1\103"+ "\47\0\1\104\46\0\1\105\2\0\1\106\44\0\1\107"+ "\2\0\1\110\44\0\1\111\2\0\1\112\61\0\1\113"+ "\34\0\1\114\46\0\1\115\47\0\1\116\50\0\1\117"+ "\47\0\1\120\46\0\1\121\47\0\1\122\47\0\1\123"+ "\51\0\1\124\47\0\1\54\46\0\1\125\47\0\1\126"+ "\50\0\1\60\47\0\1\62\46\0\1\127\47\0\1\130"+ "\47\0\1\131\50\0\1\100\47\0\1\102\47\0\1\106"+ "\47\0\1\110\47\0\1\112\40\0"; private static int [] zzUnpackTrans() { int [] result = new int[2080]; 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 = "\4\0\5\11\3\1\6\11\14\1\4\11\1\1\7\11"+ "\1\0\1\11\3\0\1\11\1\0\1\11\3\0\6\11"+ "\1\0\1\11\2\0\1\11\1\0\1\11\3\0\1\11"+ "\1\0\1\11\1\0\1\11\11\0\1\11\5\0"; private static int [] zzUnpackAttribute() { int [] result = new int[89]; 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: */ int cv = 0; // consonant = 1, vowel = 2, everything else = 0 /** * 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 MpdlNormalizerLexAll(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 MpdlNormalizerLexAll(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 < 172) { 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 25: // lookahead expression with fixed base length zzMarkedPos = zzStartRead + 1; { return "o"; } case 39: break; case 22: { cv = 2; return "ii"; } case 40: break; case 35: // lookahead expression with fixed base length zzMarkedPos = zzStartRead + 2; { return "od"; } case 41: break; case 7: { cv = 1; return "s"; } case 42: break; case 24: // lookahead expression with fixed base length zzMarkedPos = zzStartRead + 1; { return "e"; } case 43: break; case 29: { cv = 1; return "Qu"; } case 44: break; case 19: // lookahead expression with fixed base length zzMarkedPos = zzStartRead + 1; { switch(cv) { case 2: return "v"; default: cv = 2; return "u"; } } case 45: break; case 9: { cv = 2; return "ae"; } case 46: break; case 15: { return "精"; } case 47: break; case 3: { cv = 0; return yytext(); } case 48: break; case 27: // lookahead expression with fixed base length zzMarkedPos = zzStartRead + 1; { switch(cv) { case 2: return "V"; default: cv = 2; return "U"; } } case 49: break; case 2: { return ""; } case 50: break; case 33: // lookahead expression with fixed base length zzMarkedPos = zzStartRead + 2; { return "am"; } case 51: break; case 18: { cv = 1; return "qu"; } case 52: break; case 14: { return "歷"; } case 53: break; case 8: { cv = 1; return "ss"; } case 54: break; case 4: { cv = 2; return yytext(); } case 55: break; case 32: { return "庶"; } case 56: break; case 6: { cv = 0; return ""; } case 57: break; case 16: { switch(cv) { case 1: return yytext().replace("v", "u"); default: cv = 1; return yytext(); } } case 58: break; case 12: { return "奇"; } case 59: break; case 38: { return "hic"; } case 60: break; case 26: { cv = 2; return "oi"; } case 61: break; case 36: // lookahead expression with fixed base length zzMarkedPos = zzStartRead + 2; { return "um"; } case 62: break; case 17: { switch(cv) { case 1: return yytext().replace("V", "U"); default: cv = 1; return yytext(); } } case 63: break; case 21: { cv = 2; return "uu"; } case 64: break; case 31: // lookahead expression with fixed base length zzMarkedPos = zzStartRead + 1; { cv = 1; return "U"; } case 65: break; case 1: { return yytext(); } case 66: break; case 34: // lookahead expression with fixed base length zzMarkedPos = zzStartRead + 2; { return "as"; } case 67: break; case 23: // lookahead expression with fixed base length zzMarkedPos = zzStartRead + 1; { return "a"; } case 68: break; case 13: { return "時"; } case 69: break; case 10: { cv = 2; return "AE"; } case 70: break; case 37: // lookahead expression with fixed base length zzMarkedPos = zzStartRead + 2; { return "us"; } case 71: break; case 5: { cv = 1; return yytext(); } case 72: break; case 28: // lookahead expression with fixed base length zzMarkedPos = zzStartRead + 1; { cv = 1; return "u"; } case 73: break; case 30: { cv = 1; return "QU"; } case 74: break; case 20: { cv = 2; return "ui"; } case 75: break; case 11: { cv = 2; return "oe"; } case 76: break; default: if (zzInput == YYEOF && zzStartRead == zzCurrentPos) { zzAtEOF = true; return null; } else { zzScanError(ZZ_NO_MATCH); } } } } }