standardtokenizerimpl.java

lucene-2.4.0 是一个全文收索的工具包

public final int yychar()
{
    return yychar;
}

/**
 * Fills Lucene token with the current token text.
 */
final void getText(Token t) {
  t.setTermBuffer(zzBuffer, zzStartRead, zzMarkedPos-zzStartRead);
}


  /**
   * 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.
   */
  StandardTokenizerImpl(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.
   */
  StandardTokenizerImpl(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 < 1154) {
      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;
      zzPushbackPos-= 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) {
      return true;
    }
    else {
      zzEndRead+= numRead;
      return false;
    }
  }

    
  /**
   * 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;
    zzEndRead = zzStartRead = 0;
    zzCurrentPos = zzMarkedPos = zzPushbackPos = 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 int getNextToken() 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;

      yychar+= zzMarkedPosL-zzStartRead;

      zzAction = -1;

      zzCurrentPosL = zzCurrentPos = zzStartRead = zzMarkedPosL;
  
      zzState = 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 4: 
          { return HOST;
          }
        case 11: break;
        case 9: 
          { return ACRONYM;
          }
        case 12: break;
        case 8: 
          { return ACRONYM_DEP;
          }
        case 13: break;
        case 1: 
          { /* ignore */
          }
        case 14: break;
        case 5: 
          { return NUM;
          }
        case 15: break;
        case 3: 
          { return CJ;
          }
        case 16: break;
        case 2: 
          { return ALPHANUM;
          }
        case 17: break;
        case 7: 
          { return COMPANY;
          }
        case 18: break;
        case 6: 
          { return APOSTROPHE;
          }
        case 19: break;
        case 10: 
          { return EMAIL;
          }
        case 20: break;
        default: 
          if (zzInput == YYEOF && zzStartRead == zzCurrentPos) {
            zzAtEOF = true;
            return YYEOF;
          } 
          else {
            zzScanError(ZZ_NO_MATCH);
          }
      }
    }
  }


}