Пример #1
0
  /**
   * Get the frequency value for a word form. It is taken from the first entry with this word form.
   *
   * @param word the word to be tested
   * @return frequency value in range: 0..FREQ_RANGE-1 (0: less frequent).
   */
  public int getFrequency(final CharSequence word) {
    if (!dictionaryMetadata.isFrequencyIncluded()) {
      return 0;
    }

    final byte separator = dictionaryMetadata.getSeparator();
    try {
      byteBuffer = charSequenceToBytes(word);
    } catch (UnmappableInputException e) {
      return 0;
    }

    final MatchResult match =
        matcher.match(matchResult, byteBuffer.array(), 0, byteBuffer.remaining(), rootNode);
    if (match.kind == SEQUENCE_IS_A_PREFIX) {
      final int arc = fsa.getArc(match.node, separator);
      if (arc != 0 && !fsa.isArcFinal(arc)) {
        finalStatesIterator.restartFrom(fsa.getEndNode(arc));
        if (finalStatesIterator.hasNext()) {
          final ByteBuffer bb = finalStatesIterator.next();
          final byte[] ba = bb.array();
          final int bbSize = bb.remaining();
          // the last byte contains the frequency after a separator
          return ba[bbSize - 1] - FIRST_RANGE_CODE;
        }
      }
    }
    return 0;
  }
Пример #2
0
  /**
   * Test whether the word is found in the dictionary.
   *
   * @param word the word to be tested
   * @return True if it is found.
   */
  public boolean isInDictionary(final CharSequence word) {
    try {
      byteBuffer = charSequenceToBytes(word);
    } catch (UnmappableInputException e) {
      return false;
    }

    // Try to find a partial match in the dictionary.
    final MatchResult match =
        matcher.match(matchResult, byteBuffer.array(), 0, byteBuffer.remaining(), rootNode);

    if (match.kind == EXACT_MATCH) {
      containsSeparators = false;
      return true;
    }

    return containsSeparators
        && match.kind == SEQUENCE_IS_A_PREFIX
        && byteBuffer.remaining() > 0
        && fsa.getArc(match.node, dictionaryMetadata.getSeparator()) != 0;
  }