public StandardAnalyzer() 
{
             
    this(STOP_WORDS);
}

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

 public StandardAnalyzer(Set stopWords) 
{
    stopSet = stopWords;
}

Builds an analyzer with the given stop words.

 public StandardAnalyzer(String[] stopWords) 
{
    stopSet = StopFilter.makeStopSet(stopWords);
}

Builds an analyzer with the given stop words.

 public StandardAnalyzer(File stopwords) throws IOException 
{
    stopSet = WordlistLoader.getWordSet(stopwords);
}

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

Also see:

WordlistLoader#getWordSet(File)

 public StandardAnalyzer(Reader stopwords) throws IOException 
{
    stopSet = WordlistLoader.getWordSet(stopwords);
}

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

Also see:

WordlistLoader#getWordSet(Reader)

 public StandardAnalyzer(boolean replaceInvalidAcronym) 
{
    this(STOP_WORDS);
    this.replaceInvalidAcronym = replaceInvalidAcronym;
}

Parameters:

replaceInvalidAcronym - Set to true if this analyzer should replace mischaracterized acronyms in the StandardTokenizer See https://issues.apache.org/jira/browse/LUCENE-1068

 public StandardAnalyzer(Reader stopwords,
    boolean replaceInvalidAcronym) throws IOException 
{
    this(stopwords);
    this.replaceInvalidAcronym = replaceInvalidAcronym;
}

Parameters:

stopwords - The stopwords to use

replaceInvalidAcronym - Set to true if this analyzer should replace mischaracterized acronyms in the StandardTokenizer See https://issues.apache.org/jira/browse/LUCENE-1068

 public StandardAnalyzer(File stopwords,
    boolean replaceInvalidAcronym) throws IOException 
{
    this(stopwords);
    this.replaceInvalidAcronym = replaceInvalidAcronym;
}

Parameters:

stopwords - The stopwords to use

replaceInvalidAcronym - Set to true if this analyzer should replace mischaracterized acronyms in the StandardTokenizer See https://issues.apache.org/jira/browse/LUCENE-1068

 public StandardAnalyzer(String[] stopwords,
    boolean replaceInvalidAcronym) throws IOException 
{
    this(stopwords);
    this.replaceInvalidAcronym = replaceInvalidAcronym;
}

Parameters:

stopwords - The stopwords to use

replaceInvalidAcronym - Set to true if this analyzer should replace mischaracterized acronyms in the StandardTokenizer See https://issues.apache.org/jira/browse/LUCENE-1068

 public StandardAnalyzer(Set stopwords,
    boolean replaceInvalidAcronym) throws IOException 
{
    this(stopwords);
    this.replaceInvalidAcronym = replaceInvalidAcronym;
}

Parameters:

stopwords - The stopwords to use

replaceInvalidAcronym - Set to true if this analyzer should replace mischaracterized acronyms in the StandardTokenizer See https://issues.apache.org/jira/browse/LUCENE-1068

 public static boolean getDefaultReplaceInvalidAcronym() 
{
  // Default to true (fixed the bug), unless the system prop is set
    final String v = System.getProperty("org.apache.lucene.analysis.standard.StandardAnalyzer.replaceInvalidAcronym");
    if (v == null || v.equals("true"))
      defaultReplaceInvalidAcronym = true;
    else
      defaultReplaceInvalidAcronym = false;
    return defaultReplaceInvalidAcronym;
}

 public int getMaxTokenLength() 
{
    return maxTokenLength;
}

 public boolean isReplaceInvalidAcronym() 
{
    return replaceInvalidAcronym;
}

 public TokenStream reusableTokenStream(String fieldName,
    Reader reader) throws IOException 
{
    SavedStreams streams = (SavedStreams) getPreviousTokenStream();
    if (streams == null) {
      streams = new SavedStreams();
      setPreviousTokenStream(streams);
      streams.tokenStream = new StandardTokenizer(reader);
      streams.filteredTokenStream = new StandardFilter(streams.tokenStream);
      streams.filteredTokenStream = new LowerCaseFilter(streams.filteredTokenStream);
      streams.filteredTokenStream = new StopFilter(streams.filteredTokenStream, stopSet);
    } else {
      streams.tokenStream.reset(reader);
    }
    streams.tokenStream.setMaxTokenLength(maxTokenLength);
    streams.tokenStream.setReplaceInvalidAcronym(replaceInvalidAcronym);
    return streams.filteredTokenStream;
}

 public static  void setDefaultReplaceInvalidAcronym(boolean replaceInvalidAcronym) 
{
    defaultReplaceInvalidAcronym = replaceInvalidAcronym;
}

 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  void setReplaceInvalidAcronym(boolean replaceInvalidAcronym) 
{
    this.replaceInvalidAcronym = replaceInvalidAcronym;
}

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

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