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 in the source text

end - end offset in the source text

 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 in the source text

end - end offset in the source text

typ - the lexical type of this Token

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

Constructs a Token with null text and start & end offsets plus flags. NOTE: flags is EXPERIMENTAL.

Parameters:

start - start offset in the source text

end - end offset in the source text

flags - The bits to set for this token

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

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 -

start -

end -

flags - token type bits

 public Token(char[] startTermBuffer,
    int termBufferOffset,
    int termBufferLength,
    int start,
    int end) 
{
    setTermBuffer(startTermBuffer, termBufferOffset, termBufferLength);
    startOffset = start;
    endOffset = end;
}

Constructs a Token with the given term buffer (offset & length), start and end offsets

Parameters:

startTermBuffer -

termBufferOffset -

termBufferLength -

start -

end -

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

Resets the term text, payload, flags, 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();
      // Do a deep clone
      if (termBuffer != null) {
        t.termBuffer = (char[]) termBuffer.clone();
      }
      if (payload != null) {
        t.setPayload((Payload) payload.clone());
      }
      return t;
    } catch (CloneNotSupportedException e) {
      throw new RuntimeException(e);  // shouldn't happen
    }
}

 public Token clone(char[] newTermBuffer,
    int newTermOffset,
    int newTermLength,
    int newStartOffset,
    int newEndOffset) 
{
    final Token t = new Token(newTermBuffer, newTermOffset, newTermLength, newStartOffset, newEndOffset);
    t.positionIncrement = positionIncrement;
    t.flags = flags;
    t.type = type;
    if (payload != null)
      t.payload = (Payload) payload.clone();
    return t;
}

Makes a clone, but replaces the term buffer & start/end offset in the process. This is more efficient than doing a full clone (and then calling setTermBuffer) because it saves a wasted copy of the old termBuffer.

 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. The length of the token in the source text is (endOffset - startOffset).

 public boolean equals(Object obj) 
{
    if (obj == this)
      return true;
    if (obj instanceof Token) {
      Token other = (Token) obj;
      initTermBuffer();
      other.initTermBuffer();
      if (termLength == other.termLength &&
          startOffset == other.startOffset &&
          endOffset == other.endOffset && 
          flags == other.flags &&
          positionIncrement == other.positionIncrement &&
          subEqual(type, other.type) &&
          subEqual(payload, other.payload)) {
        for(int i=0;i< termLength;i++)
          if (termBuffer[i] != other.termBuffer[i])
            return false;
        return true;
      } else
        return false;
    } else
      return false;
}

 public int getFlags() 
{
    return flags;
}

EXPERIMENTAL: While we think this is here to stay, we may want to change it to be a long.

Get the bitset for any bits that have been set. This is completely distinct from #type() , although they do share similar purposes. The flags can be used to encode information about the token for use by other org.apache.lucene.analysis.TokenFilter s.

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

Returns this Token's payload.

 public int getPositionIncrement() 
{
    return positionIncrement;
}

Returns the position increment of this Token.

 public int hashCode() 
{
    initTermBuffer();
    int code = termLength;
    code = code * 31 + startOffset;
    code = code * 31 + endOffset;
    code = code * 31 + flags;
    code = code * 31 + positionIncrement;
    code = code * 31 + type.hashCode();
    code = (payload == null ? code : code * 31 + payload.hashCode());
    code = code * 31 + ArrayUtil.hashCode(termBuffer, 0, termLength);
    return code;
}

 public  void reinit(Token prototype) 
{
    prototype.initTermBuffer();
    setTermBuffer(prototype.termBuffer, 0, prototype.termLength);
    positionIncrement = prototype.positionIncrement;
    flags = prototype.flags;
    startOffset = prototype.startOffset;
    endOffset = prototype.endOffset;
    type = prototype.type;
    payload =  prototype.payload;
}

Copy the prototype token's fields into this one. Note: Payloads are shared.

 public  void reinit(Token prototype,
    String newTerm) 
{
    setTermBuffer(newTerm);
    positionIncrement = prototype.positionIncrement;
    flags = prototype.flags;
    startOffset = prototype.startOffset;
    endOffset = prototype.endOffset;
    type = prototype.type;
    payload =  prototype.payload;
}

Copy the prototype token's fields into this one, with a different term. Note: Payloads are shared.

 public Token reinit(String newTerm,
    int newStartOffset,
    int newEndOffset) 
{
    clearNoTermBuffer();
    setTermBuffer(newTerm);
    startOffset = newStartOffset;
    endOffset = newEndOffset;
    type = DEFAULT_TYPE;
    return this;
}

Shorthand for calling #clear , #setTermBuffer(String) , #setStartOffset , #setEndOffset #setType on Token.DEFAULT_TYPE

 public Token reinit(String newTerm,
    int newStartOffset,
    int newEndOffset,
    String newType) 
{
    clearNoTermBuffer();
    setTermBuffer(newTerm);
    startOffset = newStartOffset;
    endOffset = newEndOffset;
    type = newType;
    return this;
}

Shorthand for calling #clear , #setTermBuffer(String) , #setStartOffset , #setEndOffset #setType

 public  void reinit(Token prototype,
    char[] newTermBuffer,
    int offset,
    int length) 
{
    setTermBuffer(newTermBuffer, offset, length);
    positionIncrement = prototype.positionIncrement;
    flags = prototype.flags;
    startOffset = prototype.startOffset;
    endOffset = prototype.endOffset;
    type = prototype.type;
    payload =  prototype.payload;
}

Copy the prototype token's fields into this one, with a different term. Note: Payloads are shared.

 public Token reinit(char[] newTermBuffer,
    int newTermOffset,
    int newTermLength,
    int newStartOffset,
    int newEndOffset) 
{
    clearNoTermBuffer();
    setTermBuffer(newTermBuffer, newTermOffset, newTermLength);
    startOffset = newStartOffset;
    endOffset = newEndOffset;
    type = DEFAULT_TYPE;
    return this;
}

Shorthand for calling #clear , #setTermBuffer(char[], int, int) , #setStartOffset , #setEndOffset #setType on Token.DEFAULT_TYPE

 public Token reinit(String newTerm,
    int newTermOffset,
    int newTermLength,
    int newStartOffset,
    int newEndOffset) 
{
    clearNoTermBuffer();
    setTermBuffer(newTerm, newTermOffset, newTermLength);
    startOffset = newStartOffset;
    endOffset = newEndOffset;
    type = DEFAULT_TYPE;
    return this;
}

Shorthand for calling #clear , #setTermBuffer(String, int, int) , #setStartOffset , #setEndOffset #setType on Token.DEFAULT_TYPE

 public Token reinit(char[] newTermBuffer,
    int newTermOffset,
    int newTermLength,
    int newStartOffset,
    int newEndOffset,
    String newType) 
{
    clearNoTermBuffer();
    payload = null;
    positionIncrement = 1;
    setTermBuffer(newTermBuffer, newTermOffset, newTermLength);
    startOffset = newStartOffset;
    endOffset = newEndOffset;
    type = newType;
    return this;
}

Shorthand for calling #clear , #setTermBuffer(char[], int, int) , #setStartOffset , #setEndOffset , #setType

 public Token reinit(String newTerm,
    int newTermOffset,
    int newTermLength,
    int newStartOffset,
    int newEndOffset,
    String newType) 
{
    clearNoTermBuffer();
    setTermBuffer(newTerm, newTermOffset, newTermLength);
    startOffset = newStartOffset;
    endOffset = newEndOffset;
    type = newType;
    return this;
}

Shorthand for calling #clear , #setTermBuffer(String, int, int) , #setStartOffset , #setEndOffset #setType

 public char[] resizeTermBuffer(int newSize) 
{
    char[] newCharBuffer = growTermBuffer(newSize);
    if (termBuffer == null) {
      // If there were termText, then preserve it.
      // note that if termBuffer is null then newCharBuffer cannot be null
      assert newCharBuffer != null;
      if (termText != null) {
        termText.getChars(0, termText.length(), newCharBuffer, 0);
      }
      termBuffer = newCharBuffer;
    } else if (newCharBuffer != null) {
      // Note: if newCharBuffer != null then termBuffer needs to grow.
      // If there were a termBuffer, then preserve it
      System.arraycopy(termBuffer, 0, newCharBuffer, 0, termBuffer.length);
      termBuffer = newCharBuffer;      
    }
    termText = null;
    return termBuffer;
}

Grows the termBuffer to at least size newSize, preserving the existing content. Note: If the next operation is to change the contents of the term buffer use #setTermBuffer(char[], int, int) , #setTermBuffer(String) , or #setTermBuffer(String, int, int) to optimally combine the resize with the setting of the termBuffer.

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

Set the ending offset.

 public  void setFlags(int flags) 
{
    this.flags = flags;
}

 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(String buffer) 
{
    termText = null;
    int length = buffer.length();
    char[] newCharBuffer = growTermBuffer(length);
    if (newCharBuffer != null) {
      termBuffer = newCharBuffer;
    }
    buffer.getChars(0, length, termBuffer, 0);
    termLength = length;
}

Copies the contents of buffer into the termBuffer array.

 public final  void setTermBuffer(char[] buffer,
    int offset,
    int length) 
{
    termText = null;
    char[] newCharBuffer = growTermBuffer(length);
    if (newCharBuffer != null) {
      termBuffer = newCharBuffer;
    }
    System.arraycopy(buffer, offset, termBuffer, 0, length);
    termLength = length;
}

Copies the contents of buffer, starting at offset for length characters, into the termBuffer array.

 public final  void setTermBuffer(String buffer,
    int offset,
    int length) 
{
    assert offset < = buffer.length();
    assert offset + length < = buffer.length();
    termText = null;
    char[] newCharBuffer = growTermBuffer(length);
    if (newCharBuffer != null) {
      termBuffer = newCharBuffer;
    }
    buffer.getChars(offset, offset + length, termBuffer, 0);
    termLength = length;
}

Copies the contents of buffer, starting at offset and continuing for length characters, into the termBuffer array.

 public final  void setTermLength(int length) 
{
    initTermBuffer();
    if (length  > termBuffer.length)
      throw new IllegalArgumentException("length " + length + " exceeds the size of the termBuffer (" + termBuffer.length + ")");
    termLength = length;
}

Set number of valid characters (length of the term) in the termBuffer array. Use this to truncate the termBuffer or to synchronize with external manipulation of the termBuffer. Note: to grow the size of the array, use #resizeTermBuffer(int) first.

 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 String term() 
{
    if (termText != null)
      return termText;
    initTermBuffer();
    return new String(termBuffer, 0, termLength);
}

Returns the Token's term text. This method has a performance penalty because the text is stored internally in a char[]. If possible, use #termBuffer() and #termLength() directly instead. If you really need a String, use this method, which is nothing more than a convenience call to new String(token.termBuffer(), 0, token.termLength())

 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".