wikipediatokenizerimpl.java

Lucene a java open-source SearchEngine Framework

    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 =
    "\11\0\1\11\7\1\1\11\10\1\1\11\2\1\1\11"+
    "\13\1\1\11\6\1\2\11\3\0\1\11\14\0\2\1"+
    "\2\11\1\1\1\0\1\1\1\0\1\1\1\0\1\1"+
    "\3\0\7\1\2\0\1\1\1\0\15\1\3\0\1\1"+
    "\1\11\3\0\1\1\1\11\5\0\1\1\4\0\1\1"+
    "\2\0\2\1\2\0\1\1\5\0\1\11\3\1\3\0"+
    "\1\1\2\0\1\11\30\0\1\1\2\0\3\11";

  private static int [] zzUnpackAttribute() {
    int [] result = new int[178];
    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 textposition at the last state to be included in yytext */
  private int zzPushbackPos;

  /** 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;

  /* user code: */

public static final int ALPHANUM          = WikipediaTokenizer.ALPHANUM_ID;
public static final int APOSTROPHE        = WikipediaTokenizer.APOSTROPHE_ID;
public static final int ACRONYM           = WikipediaTokenizer.ACRONYM_ID;
public static final int COMPANY           = WikipediaTokenizer.COMPANY_ID;
public static final int EMAIL             = WikipediaTokenizer.EMAIL_ID;
public static final int HOST              = WikipediaTokenizer.HOST_ID;
public static final int NUM               = WikipediaTokenizer.NUM_ID;
public static final int CJ                = WikipediaTokenizer.CJ_ID;
public static final int INTERNAL_LINK     = WikipediaTokenizer.INTERNAL_LINK_ID;
public static final int EXTERNAL_LINK     = WikipediaTokenizer.EXTERNAL_LINK_ID;
public static final int CITATION          = WikipediaTokenizer.CITATION_ID;
public static final int CATEGORY          = WikipediaTokenizer.CATEGORY_ID;
public static final int BOLD              = WikipediaTokenizer.BOLD_ID;
public static final int ITALICS           = WikipediaTokenizer.ITALICS_ID;
public static final int BOLD_ITALICS      = WikipediaTokenizer.BOLD_ITALICS_ID;
public static final int HEADING           = WikipediaTokenizer.HEADING_ID;
public static final int SUB_HEADING       = WikipediaTokenizer.SUB_HEADING_ID;
public static final int EXTERNAL_LINK_URL = WikipediaTokenizer.EXTERNAL_LINK_URL_ID;


private int currentTokType;
private int numBalanced = 0;
private int positionInc = 1;
private int numLinkToks = 0;

public static final String [] TOKEN_TYPES = WikipediaTokenizer.TOKEN_TYPES;

public final int yychar()
{
    return yychar;
}

public final int getPositionIncrement(){
  return positionInc;
}

/**
 * Fills Lucene token with the current token text.
 */
final void getText(Token t, int tokType) {
  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.
   */
  WikipediaTokenizerImpl(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.
   */
  WikipediaTokenizerImpl(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 < 230) {
      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.
   */