public PorterStemFilter(TokenStream in_Renamed):base(in_Renamed) { stemmer = new PorterStemmer(); termAtt = (TermAttribute) AddAttribute(typeof(TermAttribute)); }
/// <summary> Build a filter that removes words that are too long or too /// short from the text. /// </summary> public LengthFilter(TokenStream in_Renamed, int min, int max):base(in_Renamed) { this.min = min; this.max = max; termAtt = (TermAttribute) AddAttribute(typeof(TermAttribute)); }
public CachingTokenFilter(TokenStream input):base(input) { }
public LowerCaseFilter(TokenStream in_Renamed):base(in_Renamed) { termAtt = (TermAttribute) AddAttribute(typeof(TermAttribute)); }
public ISOLatin1AccentFilter(TokenStream input):base(input) { termAtt = (TermAttribute) AddAttribute(typeof(TermAttribute)); }
/// <summary> Construct a token stream filtering the given input. /// If <code>stopWords</code> is an instance of {@link CharArraySet} (true if /// <code>makeStopSet()</code> was used to construct the set) it will be directly used /// and <code>ignoreCase</code> will be ignored since <code>CharArraySet</code> /// directly controls case sensitivity. /// <p/> /// If <code>stopWords</code> is not an instance of {@link CharArraySet}, /// a new CharArraySet will be constructed and <code>ignoreCase</code> will be /// used to specify the case sensitivity of that set. /// /// </summary> /// <param name="enablePositionIncrements">true if token positions should record the removed stop words /// </param> /// <param name="input">Input TokenStream /// </param> /// <param name="stopWords">The set of Stop Words. /// </param> /// <param name="ignoreCase">-Ignore case when stopping. /// </param> public StopFilter(bool enablePositionIncrements, TokenStream input, System.Collections.Hashtable stopWords, bool ignoreCase):base(input) { if (stopWords is CharArraySet) { this.stopWords = (CharArraySet) stopWords; } else { this.stopWords = new CharArraySet(stopWords.Count, ignoreCase); this.stopWords.Add(stopWords); } this.enablePositionIncrements = enablePositionIncrements; Init(); }
public TeeTokenFilter(TokenStream input, SinkTokenizer sink):base(input) { this.sink = sink; }
public StopFilter(bool enablePositionIncrements, TokenStream in_Renamed, System.String[] stopWords, bool ignoreCase):base(in_Renamed) { this.stopWords = (CharArraySet) MakeStopSet(stopWords, ignoreCase); this.enablePositionIncrements = enablePositionIncrements; Init(); }
/// <summary> Instantiates a new TeeSinkTokenFilter.</summary> public TeeSinkTokenFilter(TokenStream input) : base(input) { }
public StopFilter(bool enablePositionIncrements, TokenStream input, System.String[] stopWords):this(enablePositionIncrements, input, stopWords, false) { }
public StopFilter(TokenStream in_Renamed, System.String[] stopWords, bool ignoreCase):this(ENABLE_POSITION_INCREMENTS_DEFAULT, in_Renamed, stopWords, ignoreCase) { }
public StopFilter(TokenStream input, System.String[] stopWords):this(ENABLE_POSITION_INCREMENTS_DEFAULT, input, stopWords, false) { }
/// <summary> Constructs a filter which removes words from the input /// TokenStream that are named in the Set. /// /// </summary> /// <param name="enablePositionIncrements">true if token positions should record the removed stop words /// </param> /// <param name="in">Input stream /// </param> /// <param name="stopWords">The set of Stop Words. /// </param> /// <seealso cref="MakeStopSet(java.lang.String[])"> /// </seealso> public StopFilter(bool enablePositionIncrements, TokenStream in_Renamed, System.Collections.Hashtable stopWords):this(enablePositionIncrements, in_Renamed, stopWords, false) { }
public StopFilter(TokenStream in_Renamed, System.Collections.Hashtable stopWords):this(ENABLE_POSITION_INCREMENTS_DEFAULT, in_Renamed, stopWords, false) { }
/// <summary>Construct a token stream filtering the given input. </summary> protected internal TokenFilter(TokenStream input):base(input) { this.input = input; }
/// <summary> Instantiates a new TeeSinkTokenFilter.</summary> public TeeSinkTokenFilter(TokenStream input):base(input) { }
public ASCIIFoldingFilter(TokenStream input):base(input) { termAtt = (TermAttribute) AddAttribute(typeof(TermAttribute)); }
public StopFilter(TokenStream input, System.Collections.Hashtable stopWords, bool ignoreCase):this(ENABLE_POSITION_INCREMENTS_DEFAULT, input, stopWords, ignoreCase) { }