view software/mpdl-services/mpiwg-mpdl-lt/src/de/mpg/mpiwg/berlin/mpdl/lt/text/norm/lang/MpdlNormalizerLexIT.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 source

/* The following code was generated by JFlex 1.4.3 on 21.07.11 11:22 */

/*
 * Normalization rules for Italian 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 21.07.11 11:22 from the specification file
 * <tt>MpdlNormalizerLexIT.lex</tt>
 */
public class MpdlNormalizerLexIT {

  /** 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 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
  };

  /** 
   * 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\52\1\1\3\2"+
    "\1\1\3\2\1\41\1\0\1\2\1\3\2\2\1\42\1\2\1\50"+
    "\1\3\1\2\1\40\1\45\1\51\2\2\1\0\1\2\6\0\1\44"+
    "\3\2\1\12\2\2\1\43\1\7\1\36\1\2\1\3\1\2\1\10"+
    "\1\37\1\14\1\46\1\13\1\2\1\11\1\16\1\47\2\2\1\0"+
    "\1\2\62\0\1\4\22\0\1\17\5\0\1\33\1\0\1\20\3\0"+
    "\1\21\5\0\1\22\6\0\1\23\5\0\1\31\1\24\5\0\1\32"+
    "\1\0\1\25\3\0\1\26\5\0\1\27\6\0\1\30\37\0\1\1"+
    "\70\0\1\35\1\34\53\0\1\15\ufe80\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 =
    "\11\0\1\1\1\2\2\3\1\1\1\4\1\2\1\3"+
    "\1\5\1\2\1\6\1\7\1\10\1\11\1\12\5\3"+
    "\1\13\1\2\1\3\1\5\1\2\1\14\1\15\1\16"+
    "\1\17\1\20\1\21\1\22\1\23\1\24\1\25\1\26"+
    "\1\27\1\30\4\0\1\31\1\32\1\33\1\0\1\34"+
    "\1\0\1\35\1\36\1\0\1\37\1\40\1\41\4\0"+
    "\1\42\6\0\1\43\1\44\4\0\1\45\1\0\1\46"+
    "\10\0\1\47\4\0\1\45\2\0\1\50";

  private static int [] zzUnpackAction() {
    int [] result = new int[100];
    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\53\0\126\0\201\0\254\0\327\0\u0102\0\u012d"+
    "\0\u0158\0\0\0\0\0\0\0\u0183\0\u01ae\0\0\0\u01d9"+
    "\0\u0204\0\0\0\u022f\0\0\0\0\0\0\0\0\0\0"+
    "\0\u025a\0\u0285\0\u02b0\0\u02db\0\u0306\0\0\0\u0331\0\u035c"+
    "\0\u0387\0\u03b2\0\u03dd\0\0\0\0\0\0\0\0\0\0"+
    "\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\u0408"+
    "\0\u0433\0\u045e\0\u0489\0\0\0\0\0\0\0\u04b4\0\0"+
    "\0\u04df\0\0\0\0\0\u050a\0\0\0\0\0\0\0\u0535"+
    "\0\u0560\0\u058b\0\u05b6\0\0\0\u05e1\0\u060c\0\u0637\0\u0662"+
    "\0\u068d\0\0\0\0\0\0\0\u06b8\0\u06e3\0\u070e\0\u035c"+
    "\0\u0739\0\u0764\0\0\0\u078f\0\u07ba\0\u07e5\0\0\0\u0810"+
    "\0\u083b\0\u0866\0\u0891\0\0\0\u08bc\0\u08e7\0\u0912\0\u093d"+
    "\0\0\0\u0968\0\u0993\0\0";

  private static int [] zzUnpackRowMap() {
    int [] result = new int[100];
    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 =
    "\53\0\1\12\1\13\1\14\1\15\1\16\1\12\1\17"+
    "\1\20\1\14\1\21\1\13\1\15\1\14\1\22\1\23"+
    "\5\12\2\13\1\12\2\13\1\24\1\25\1\26\1\27"+
    "\1\30\1\12\1\13\1\31\2\13\1\14\1\13\1\23"+
    "\1\32\1\33\1\34\1\35\1\36\1\12\1\13\1\14"+
    "\1\15\1\16\1\12\1\17\1\37\1\14\1\21\1\13"+
    "\1\15\1\40\1\41\1\42\5\12\2\13\1\12\2\13"+
    "\1\24\1\25\1\26\1\27\1\30\1\12\1\13\1\31"+
    "\2\13\1\43\1\13\1\42\1\32\1\33\1\34\1\35"+
    "\1\36\1\12\1\13\1\14\1\15\1\16\1\12\1\44"+
    "\1\20\1\14\1\21\1\13\1\15\1\14\1\22\1\23"+
    "\1\45\1\46\1\47\1\50\1\51\1\52\1\53\1\54"+
    "\1\55\1\56\1\24\1\25\1\26\1\27\1\30\1\12"+
    "\1\13\1\31\2\13\1\14\1\13\1\23\1\32\1\33"+
    "\1\34\1\35\1\36\1\12\1\13\1\14\1\15\1\16"+
    "\1\12\1\44\1\37\1\14\1\21\1\13\1\15\1\40"+
    "\1\41\1\42\1\45\1\46\1\47\1\50\1\51\1\52"+
    "\1\53\1\54\1\55\1\56\1\24\1\25\1\26\1\27"+
    "\1\30\1\12\1\13\1\31\2\13\1\43\1\13\1\42"+
    "\1\32\1\33\1\34\1\35\1\36\1\12\1\13\1\14"+
    "\1\15\1\16\1\12\1\57\1\20\1\14\1\21\1\13"+
    "\1\15\1\14\1\22\1\23\1\45\1\46\1\47\1\50"+
    "\1\51\1\52\1\53\1\54\1\55\1\56\1\24\1\25"+
    "\1\26\1\27\1\30\1\12\1\13\1\31\2\13\1\14"+
    "\1\13\1\23\1\32\1\33\1\34\1\35\1\36\1\12"+
    "\1\13\1\14\1\15\1\16\1\12\1\57\1\37\1\14"+
    "\1\21\1\13\1\15\1\40\1\41\1\42\1\45\1\46"+
    "\1\47\1\50\1\51\1\52\1\53\1\54\1\55\1\56"+
    "\1\24\1\25\1\26\1\27\1\30\1\12\1\13\1\31"+
    "\2\13\1\43\1\13\1\42\1\32\1\33\1\34\1\35"+
    "\1\36\7\0\1\60\4\0\1\61\1\62\42\0\1\63"+
    "\114\0\1\64\1\0\1\64\6\0\1\65\103\0\1\66"+
    "\23\0\1\67\44\0\1\70\5\0\1\70\2\0\1\70"+
    "\3\0\1\70\5\0\2\70\1\0\2\70\1\0\3\70"+
    "\2\0\1\70\1\0\2\70\1\0\2\70\46\0\1\71"+
    "\60\0\1\72\5\0\2\73\1\74\3\0\2\73\1\0"+
    "\3\73\13\0\1\73\6\0\1\73\2\0\1\73\2\0"+
    "\4\73\50\0\1\75\1\0\1\76\3\0\2\77\1\100"+
    "\3\0\2\77\1\0\3\77\13\0\1\77\6\0\1\77"+
    "\2\0\1\77\2\0\4\77\11\0\1\101\25\0\1\66"+
    "\26\0\1\102\52\0\1\102\3\0\1\103\35\0\1\104"+
    "\5\0\1\104\2\0\1\104\3\0\1\104\5\0\2\104"+
    "\1\0\2\104\1\0\3\104\2\0\1\104\1\0\2\104"+
    "\1\0\2\104\44\0\1\105\4\0\1\106\16\0\1\107"+
    "\54\0\1\110\52\0\1\110\3\0\1\111\40\0\1\112"+
    "\105\0\1\113\55\0\1\114\15\0\1\115\52\0\1\116"+
    "\51\0\1\117\4\0\1\120\54\0\1\121\43\0\1\122"+
    "\7\0\1\120\44\0\1\123\52\0\1\123\1\124\1\125"+
    "\46\0\1\126\4\0\1\61\54\0\1\127\43\0\1\130"+
    "\7\0\1\61\40\0\2\73\4\0\2\73\1\0\3\73"+
    "\13\0\1\73\6\0\1\73\2\0\1\73\2\0\4\73"+
    "\3\0\2\77\4\0\2\77\1\0\3\77\13\0\1\77"+
    "\6\0\1\77\2\0\1\77\2\0\4\77\6\0\1\131"+
    "\51\0\1\132\53\0\1\133\53\0\1\134\50\0\1\135"+
    "\3\0\1\136\47\0\1\137\52\0\1\140\56\0\1\120"+
    "\46\0\1\141\61\0\1\120\43\0\1\142\104\0\1\143"+
    "\24\0\1\61\55\0\1\61\46\0\1\136\50\0\1\144"+
    "\44\0";

  private static int [] zzUnpackTrans() {
    int [] result = new int[2494];
    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 =
    "\1\10\7\0\1\1\3\11\2\1\1\11\2\1\1\11"+
    "\1\1\5\11\5\1\1\11\5\1\14\11\4\0\3\11"+
    "\1\0\1\11\1\0\2\11\1\0\3\11\4\0\1\11"+
    "\5\0\3\11\4\0\1\1\1\0\1\11\3\0\1\11"+
    "\4\0\1\11\4\0\1\11\2\0\1\11";

  private static int [] zzUnpackAttribute() {
    int [] result = new int[100];
    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 MpdlNormalizerLexIT(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 MpdlNormalizerLexIT(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 33: 
          // lookahead expression with fixed base length
          zzMarkedPos = zzStartRead + 1;
          { cv = CONS; add("U");
          }
        case 41: break;
        case 14: 
          { add("Á");
          }
        case 42: break;
        case 40: 
          // lookahead expression with fixed lookahead length
          yypushback(1);
          { add(yytext());
          }
        case 43: break;
        case 39: 
          // lookahead expression with fixed base length
          zzMarkedPos = zzStartRead + 3;
          { add(yytext());
          }
        case 44: break;
        case 38: 
          // lookahead expression with fixed base length
          zzMarkedPos = zzStartRead + 2;
          { add(yytext());
          }
        case 45: break;
        case 26: 
          { add(yytext());
          }
        case 46: break;
        case 21: 
          { add("í");
          }
        case 47: break;
        case 8: 
          { cv = VOWEL; add("AE");
          }
        case 48: break;
        case 11: 
          { problem = 1; cv = 0; add(yytext());
          }
        case 49: break;
        case 4: 
          { switch (problem) {
			case 1: return original;
			default: return normalized;
		}
          }
        case 50: break;
        case 30: 
          // lookahead expression with fixed base length
          zzMarkedPos = zzStartRead + 1;
          { cv = CONS; add("u");
          }
        case 51: break;
        case 19: 
          { add("á");
          }
        case 52: break;
        case 1: 
          { cv = 0; add(yytext());
          }
        case 53: break;
        case 24: 
          { switch (problem) {
			case 1: return original;
			default: return normalized.replaceAll(LB, "").toLowerCase();
		}
          }
        case 54: break;
        case 34: 
          // lookahead expression with fixed base length
          zzMarkedPos = zzStartRead + 1;
          { cv = VOWEL; add(yytext().replaceAll("u", "v").replaceAll("U", "V"));
          }
        case 55: break;
        case 35: 
          { cv = VOWEL; add("zio");
          }
        case 56: break;
        case 10: 
          { cv = VOWEL; add("OE");
          }
        case 57: break;
        case 18: 
          { add("Ú");
          }
        case 58: break;
        case 37: 
          // 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 59: break;
        case 3: 
          { cv = CONS; add(yytext());
          }
        case 60: break;
        case 32: 
          { cv = CONS; add("QU");
          }
        case 61: break;
        case 15: 
          { add("É");
          }
        case 62: break;
        case 28: 
          // 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 6: 
          { cv = CONS; add("ss");
          }
        case 64: break;
        case 5: 
          { cv = CONS; add("s");
          }
        case 65: break;
        case 13: 
          { switch (problem) {
			case 1: return "";
			default: return normalized.replaceAll(LB, "");
		}
          }
        case 66: break;
        case 36: 
          { cv = VOWEL; add("ZIO");
          }
        case 67: break;
        case 2: 
          { cv = VOWEL; add(yytext());
          }
        case 68: break;
        case 17: 
          { add("Ó");
          }
        case 69: break;
        case 23: 
          { add("ú");
          }
        case 70: break;
        case 31: 
          { cv = CONS; add("Qu");
          }
        case 71: break;
        case 20: 
          { add("é");
          }
        case 72: break;
        case 7: 
          { cv = VOWEL; add("ae");
          }
        case 73: break;
        case 12: 
          { add("");
          }
        case 74: break;
        case 22: 
          { add("ó");
          }
        case 75: break;
        case 9: 
          { cv = VOWEL; add("oe");
          }
        case 76: break;
        case 29: 
          { cv = CONS; add("qu");
          }
        case 77: break;
        case 25: 
          { switch(cv) {
			case CONS: add(yytext().replace("v", "u").replace("V", "U")); break;
			default: cv = CONS; add(yytext()); break;
		}
          }
        case 78: break;
        case 27: 
          { cv = VOWEL; add("ii");
          }
        case 79: break;
        case 16: 
          { add("Í");
          }
        case 80: break;
        default: 
          if (zzInput == YYEOF && zzStartRead == zzCurrentPos) {
            zzAtEOF = true;
            return null;
          } 
          else {
            zzScanError(ZZ_NO_MATCH);
          }
      }
    }
  }


}