public StandardAnalyzer(Version matchVersion) 
{
    this(matchVersion, STOP_WORDS_SET);
}

Builds an analyzer with the default stop words (#STOP_WORDS_SET ).

Parameters:

matchVersion - Lucene version to match See above

 public StandardAnalyzer(Version matchVersion,
    Set<?> stopWords) 
{
    stopSet = stopWords;
    setOverridesTokenStreamMethod(StandardAnalyzer.class);
    enableStopPositionIncrements = StopFilter.getEnablePositionIncrementsVersionDefault(matchVersion);
    replaceInvalidAcronym = matchVersion.onOrAfter(Version.LUCENE_24);
    this.matchVersion = matchVersion;
}

Builds an analyzer with the given stop words.

Parameters:

matchVersion - Lucene version to match See above

stopWords - stop words

 public StandardAnalyzer(Version matchVersion,
    File stopwords) throws IOException 
{
    this(matchVersion, WordlistLoader.getWordSet(stopwords));
}

Builds an analyzer with the stop words from the given file.

Parameters:

matchVersion - Lucene version to match See above

stopwords - File to read stop words from

Also see:

WordlistLoader#getWordSet(File)

 public StandardAnalyzer(Version matchVersion,
    Reader stopwords) throws IOException 
{
    this(matchVersion, WordlistLoader.getWordSet(stopwords));
}

Builds an analyzer with the stop words from the given reader.

Parameters:

matchVersion - Lucene version to match See above

stopwords - Reader to read stop words from

Also see:

WordlistLoader#getWordSet(Reader)

 public int getMaxTokenLength() 
{
    return maxTokenLength;
}

 public TokenStream reusableTokenStream(String fieldName,
    Reader reader) throws IOException 
{
    if (overridesTokenStreamMethod) {
      // LUCENE-1678: force fallback to tokenStream() if we
      // have been subclassed and that subclass overrides
      // tokenStream but not reusableTokenStream
      return tokenStream(fieldName, reader);
    }
    SavedStreams streams = (SavedStreams) getPreviousTokenStream();
    if (streams == null) {
      streams = new SavedStreams();
      setPreviousTokenStream(streams);
      streams.tokenStream = new StandardTokenizer(matchVersion, reader);
      streams.filteredTokenStream = new StandardFilter(streams.tokenStream);
      streams.filteredTokenStream = new LowerCaseFilter(streams.filteredTokenStream);
      streams.filteredTokenStream = new StopFilter(enableStopPositionIncrements,
                                                   streams.filteredTokenStream, stopSet);
    } else {
      streams.tokenStream.reset(reader);
    }
    streams.tokenStream.setMaxTokenLength(maxTokenLength);
    streams.tokenStream.setReplaceInvalidAcronym(replaceInvalidAcronym);
    return streams.filteredTokenStream;
}

 public  void setMaxTokenLength(int length) 
{
    maxTokenLength = length;
}

Set maximum allowed token length. If a token is seen that exceeds this length then it is discarded. This setting only takes effect the next time tokenStream or reusableTokenStream is called.

 public TokenStream tokenStream(String fieldName,
    Reader reader) 
{
    StandardTokenizer tokenStream = new StandardTokenizer(matchVersion, reader);
    tokenStream.setMaxTokenLength(maxTokenLength);
    TokenStream result = new StandardFilter(tokenStream);
    result = new LowerCaseFilter(result);
    result = new StopFilter(enableStopPositionIncrements, result, stopSet);
    return result;
}

Constructs a StandardTokenizer filtered by a StandardFilter , a LowerCaseFilter and a StopFilter .