public Token() 
{

}

Constructs a Token will null text.

 public Token(int start,
    int end) 
{
    startOffset = start;
    endOffset = end;
}

Constructs a Token with null text and start & end offsets.

Parameters:

start - start offset

end - end offset

 public Token(int start,
    int end,
    String typ) 
{
    startOffset = start;
    endOffset = end;
    type = typ;
}

Constructs a Token with null text and start & end offsets plus the Token type.

Parameters:

start - start offset

end - end offset

 public Token(String text,
    int start,
    int end) 
{
    termText = text;
    startOffset = start;
    endOffset = end;
}

Constructs a Token with the given term text, and start & end offsets. The type defaults to "word." NOTE: for better indexing speed you should instead use the char[] termBuffer methods to set the term text.

Parameters:

text - term text

start - start offset

end - end offset

 public Token(String text,
    int start,
    int end,
    String typ) 
{
    termText = text;
    startOffset = start;
    endOffset = end;
    type = typ;
}

Constructs a Token with the given text, start and end offsets, & type. NOTE: for better indexing speed you should instead use the char[] termBuffer methods to set the term text.

Parameters:

text - term text

start - start offset

end - end offset

typ - token type

 public  void clear() 
{
    payload = null;
    // Leave termBuffer to allow re-use
    termLength = 0;
    termText = null;
    positionIncrement = 1;
    // startOffset = endOffset = 0;
    // type = DEFAULT_TYPE;
}

Resets the term text, payload, and positionIncrement to default. Other fields such as startOffset, endOffset and the token type are not reset since they are normally overwritten by the tokenizer.

 public Object clone() 
{
    try {
      Token t = (Token)super.clone();
      if (termBuffer != null) {
        t.termBuffer = null;
        t.setTermBuffer(termBuffer, 0, termLength);
      }
      if (payload != null) {
        t.setPayload((Payload) payload.clone());
      }
      return t;
    } catch (CloneNotSupportedException e) {
      throw new RuntimeException(e);  // shouldn't happen
    }
}

 public final int endOffset() 
{
    return endOffset;
}

Returns this Token's ending offset, one greater than the position of the last character corresponding to this token in the source text.

 public Payload getPayload() 
{
    return this.payload;
}

Returns this Token's payload.

 public int getPositionIncrement() 
{
    return positionIncrement;
}

Returns the position increment of this Token.

 public char[] resizeTermBuffer(int newSize) 
{
    initTermBuffer();
    if (newSize  > termBuffer.length) {
      int size = termBuffer.length;
      while(size <  newSize)
        size *= 2;
      char[] newBuffer = new char[size];
      System.arraycopy(termBuffer, 0, newBuffer, 0, termBuffer.length);
      termBuffer = newBuffer;
    }
    return termBuffer;
}

Grows the termBuffer to at least size newSize.

 public  void setEndOffset(int offset) 
{
    this.endOffset = offset;
}

Set the ending offset.

 public  void setPayload(Payload payload) 
{
    this.payload = payload;
}

Sets this Token's payload.

 public  void setPositionIncrement(int positionIncrement) 
{
    if (positionIncrement <  0)
      throw new IllegalArgumentException
        ("Increment must be zero or greater: " + positionIncrement);
    this.positionIncrement = positionIncrement;
}

Set the position increment. This determines the position of this token relative to the previous Token in a TokenStream , used in phrase searching.

The default value is one.

Some common uses for this are:

• Set it to zero to put multiple terms in the same position. This is useful if, e.g., a word has multiple stems. Searches for phrases including either stem will match. In this case, all but the first stem's increment should be set to zero: the increment of the first instance should be one. Repeating a token with an increment of zero can also be used to boost the scores of matches on that token.
• Set it to values greater than one to inhibit exact phrase matches. If, for example, one does not want phrases to match across removed stop words, then one could build a stop word filter that removes stop words and also sets the increment to the number of stop words removed before each non-stop word. Then exact phrase queries will only match when the terms occur with no intervening stop words.

 public  void setStartOffset(int offset) 
{
    this.startOffset = offset;
}

Set the starting offset.

 public final  void setTermBuffer(char[] buffer,
    int offset,
    int length) 
{
    resizeTermBuffer(length);
    System.arraycopy(buffer, offset, termBuffer, 0, length);
    termLength = length;
}

Copies the contents of buffer, starting at offset for length characters, into the termBuffer array. NOTE: for better indexing speed you should instead retrieve the termBuffer, using #termBuffer() or #resizeTermBuffer(int) , and fill it in directly to set the term text. This saves an extra copy.

 public final  void setTermLength(int length) 
{
    initTermBuffer();
    termLength = length;
}

Set number of valid characters (length of the term) in the termBuffer array.

 public  void setTermText(String text) 
{
    termText = text;
    termBuffer = null;
}

Sets the Token's term text. NOTE: for better indexing speed you should instead use the char[] termBuffer methods to set the term text.

 public final  void setType(String type) 
{
    this.type = type;
}

Set the lexical type.

 public final int startOffset() 
{
    return startOffset;
}

Returns this Token's starting offset, the position of the first character corresponding to this token in the source text. Note that the difference between endOffset() and startOffset() may not be equal to termText.length(), as the term text may have been altered by a stemmer or some other filter.

 public final char[] termBuffer() 
{
    initTermBuffer();
    return termBuffer;
}

Returns the internal termBuffer character array which you can then directly alter. If the array is too small for your token, use #resizeTermBuffer(int) to increase it. After altering the buffer be sure to call #setTermLength to record the number of valid characters that were placed into the termBuffer.

 public final int termLength() 
{
    initTermBuffer();
    return termLength;
}

Return number of valid characters (length of the term) in the termBuffer array.

 public final String termText() 
{
    if (termText == null && termBuffer != null)
      termText = new String(termBuffer, 0, termLength);
    return termText;
}

Returns the Token's term text.

 public String toString() 
{
    StringBuffer sb = new StringBuffer();
    sb.append('(");
    initTermBuffer();
    if (termBuffer == null)
      sb.append("null");
    else
      sb.append(termBuffer, 0, termLength);
      sb.append(',").append(startOffset).append(',").append(endOffset);
    if (!type.equals("word"))
      sb.append(",type=").append(type);
    if (positionIncrement != 1)
      sb.append(",posIncr=").append(positionIncrement);
    sb.append(')");
    return sb.toString();
}

 public final String type() 
{
    return type;
}

Returns this Token's lexical type. Defaults to "word".