Review

16

org/apache/lucene/analysis/standard/StandardFilter.java

incrementToken()

class StandardFilter {
  /** Returns the next token in the stream, or null at EOS.
   * <p>Removes <tt>'s</tt> from the end of words.
   * <p>Removes dots from acronyms.
   */
  public final boolean incrementToken() throws java.io.IOException {
    if (!input.incrementToken()) {
      return false;
    }

    char[] buffer = termAtt.termBuffer();
    final int bufferLength = termAtt.termLength();
    final String type = typeAtt.type();

    if (type == APOSTROPHE_TYPE &&      // remove 's
  bufferLength >= 2 &&
        buffer[bufferLength-2] == '\'' &&
        (buffer[bufferLength-1] == 's' || buffer[bufferLength-1] == 'S')) {
      // Strip last 2 characters off
      termAtt.setTermLength(bufferLength - 2);
    } else if (type == ACRONYM_TYPE) {      // remove dots
      int upto = 0;
      for(int i=0;i<bufferLength;i++) {
        char c = buffer[i];
        if (c != '.')
          buffer[upto++] = c;
      }
      termAtt.setTermLength(upto);
    }

    return true;
  }

}