/// <summary>
/// Create a new IndonesianStemFilter.
/// <para>
/// If <code>stemDerivational</code> is false,
/// only inflectional suffixes (particles and possessive pronouns) are stemmed.
/// </para>
/// </summary>
public IndonesianStemFilter(TokenStream input, bool stemDerivational)
: base(input)
{
this.stemDerivational = stemDerivational;
termAtt = AddAttribute<ICharTermAttribute>();
keywordAtt = AddAttribute<IKeywordAttribute>();
}
/// <summary>
/// Creates a new NorwegianLightStemFilter </summary>
/// <param name="flags"> set to <seealso cref="NorwegianLightStemmer#BOKMAAL"/>,
/// <seealso cref="NorwegianLightStemmer#NYNORSK"/>, or both. </param>
public NorwegianMinimalStemFilter(TokenStream input, int flags)
: base(input)
{
this.stemmer = new NorwegianMinimalStemmer(flags);
termAtt = AddAttribute <ICharTermAttribute>();
keywordAttr = AddAttribute <IKeywordAttribute>();
}
/// <summary>
/// Create a new <see cref="IndonesianStemFilter"/>.
/// <para>
/// If <paramref name="stemDerivational"/> is false,
/// only inflectional suffixes (particles and possessive pronouns) are stemmed.
/// </para>
/// </summary>
public IndonesianStemFilter(TokenStream input, bool stemDerivational)
: base(input)
{
this.stemDerivational = stemDerivational;
termAtt = AddAttribute <ICharTermAttribute>();
keywordAtt = AddAttribute <IKeywordAttribute>();
}
public SnowballFilter(TokenStream input, SnowballProgram stemmer)
: base(input)
{
this.stemmer = stemmer;
this.termAtt = AddAttribute<ICharTermAttribute>();
this.keywordAttr = AddAttribute<IKeywordAttribute>();
}
public SnowballFilter(TokenStream input, SnowballProgram stemmer)
: base(input)
{
this.stemmer = stemmer;
this.termAtt = AddAttribute <ICharTermAttribute>();
this.keywordAttr = AddAttribute <IKeywordAttribute>();
}
public JapaneseKatakanaStemFilter(TokenStream input, int minimumLength)
: base(input)
{
this.minimumKatakanaLength = minimumLength;
this.termAttr = AddAttribute <ICharTermAttribute>();
this.keywordAttr = AddAttribute <IKeywordAttribute>();
}
/// <summary>
/// Creates a new <see cref="NorwegianLightStemFilter"/> </summary>
/// <param name="input"> the source <see cref="TokenStream"/> to filter </param>
/// <param name="flags"> set to <see cref="NorwegianStandard.BOKMAAL"/>,
/// <see cref="NorwegianStandard.NYNORSK"/>, or both. </param>
public NorwegianLightStemFilter(TokenStream input, NorwegianStandard flags)
: base(input)
{
stemmer = new NorwegianLightStemmer(flags);
termAtt = AddAttribute <ICharTermAttribute>();
keywordAttr = AddAttribute <IKeywordAttribute>();
}
/// <summary>
/// Creates a new NorwegianLightStemFilter </summary>
/// <param name="flags"> set to <seealso cref="NorwegianLightStemmer#BOKMAAL"/>,
/// <seealso cref="NorwegianLightStemmer#NYNORSK"/>, or both. </param>
public NorwegianMinimalStemFilter(TokenStream input, int flags)
: base(input)
{
this.stemmer = new NorwegianMinimalStemmer(flags);
termAtt = AddAttribute<ICharTermAttribute>();
keywordAttr = AddAttribute<IKeywordAttribute>();
}
public JapaneseBaseFormFilter(TokenStream input)
: base(input)
{
this.termAtt = AddAttribute <ICharTermAttribute>();
this.basicFormAtt = AddAttribute <IBaseFormAttribute>();
this.keywordAtt = AddAttribute <IKeywordAttribute>();
}
/// <summary>
/// Create a new <see cref="StemmerOverrideFilter"/>, performing dictionary-based stemming
/// with the provided dictionary (<paramref name="stemmerOverrideMap"/>).
/// <para>
/// Any dictionary-stemmed terms will be marked with <see cref="KeywordAttribute"/>
/// so that they will not be stemmed with stemmers down the chain.
/// </para>
/// </summary>
public StemmerOverrideFilter(TokenStream input, StemmerOverrideMap stemmerOverrideMap)
: base(input)
{
this.stemmerOverrideMap = stemmerOverrideMap;
fstReader = stemmerOverrideMap.GetBytesReader();
termAtt = AddAttribute <ICharTermAttribute>();
keywordAtt = AddAttribute <IKeywordAttribute>();
}
/// <summary>
/// Create filter using the supplied stemming table.
/// </summary>
/// <param name="in">input token stream</param>
/// <param name="stemmer">stemmer</param>
/// <param name="minLength">For performance reasons words shorter than minLength
/// characters are not processed, but simply returned.</param>
public StempelFilter(TokenStream @in, StempelStemmer stemmer, int minLength)
: base(@in)
{
this.stemmer = stemmer;
this.minLength = minLength;
this.termAtt = AddAttribute <ICharTermAttribute>();
this.keywordAtt = AddAttribute <IKeywordAttribute>();
}
/// <summary>
/// Create a new StemmerOverrideFilter, performing dictionary-based stemming
/// with the provided <code>dictionary</code>.
/// <para>
/// Any dictionary-stemmed terms will be marked with <seealso cref="KeywordAttribute"/>
/// so that they will not be stemmed with stemmers down the chain.
/// </para>
/// </summary>
public StemmerOverrideFilter(TokenStream input, StemmerOverrideMap stemmerOverrideMap)
: base(input)
{
this.stemmerOverrideMap = stemmerOverrideMap;
fstReader = stemmerOverrideMap.BytesReader;
termAtt = AddAttribute<ICharTermAttribute>();
keywordAtt = AddAttribute<IKeywordAttribute>();
}
/// <summary>
/// Create filter using the supplied stemming table.
/// </summary>
/// <param name="in">input token stream</param>
/// <param name="stemmer">stemmer</param>
/// <param name="minLength">For performance reasons words shorter than minLength
/// characters are not processed, but simply returned.</param>
public StempelFilter(TokenStream @in, StempelStemmer stemmer, int minLength)
: base(@in)
{
this.stemmer = stemmer;
this.minLength = minLength;
this.termAtt = AddAttribute<ICharTermAttribute>();
this.keywordAtt = AddAttribute<IKeywordAttribute>();
}
/// <summary>
/// Sole constructor. </summary>
public SuggestStopFilter(TokenStream input, CharArraySet stopWords)
: base(input)
{
this.stopWords = stopWords;
this.termAtt = AddAttribute<ICharTermAttribute>();
this.posIncAtt = AddAttribute<IPositionIncrementAttribute>();
this.keywordAtt = AddAttribute<IKeywordAttribute>();
this.offsetAtt = AddAttribute<IOffsetAttribute>();
}
private int lemmaNum = 0; // lemma counter
public OpenNLPLemmatizerFilter(TokenStream input, NLPLemmatizerOp lemmatizerOp)
: base(input)
{
this.lemmatizerOp = lemmatizerOp;
this.termAtt = AddAttribute <ICharTermAttribute>();
this.typeAtt = AddAttribute <ITypeAttribute>();
this.keywordAtt = AddAttribute <IKeywordAttribute>();
this.flagsAtt = AddAttribute <IFlagsAttribute>();
}
/// <summary>
/// Sole constructor. </summary>
public SuggestStopFilter(TokenStream input, CharArraySet stopWords)
: base(input)
{
this.stopWords = stopWords;
this.termAtt = AddAttribute <ICharTermAttribute>();
this.posIncAtt = AddAttribute <IPositionIncrementAttribute>();
this.keywordAtt = AddAttribute <IKeywordAttribute>();
this.offsetAtt = AddAttribute <IOffsetAttribute>();
}
public TruncateTokenFilter(TokenStream input, int length) : base(input)
{
if (length < 1)
{
throw new System.ArgumentOutOfRangeException("length parameter must be a positive number: " + length);
}
this.length = length;
this.termAttribute = AddAttribute <ICharTermAttribute>();
this.keywordAttr = AddAttribute <IKeywordAttribute>();
}
public TruncateTokenFilter(TokenStream input, int length) : base(input)
{
if (length < 1)
{
throw new System.ArgumentOutOfRangeException("length parameter must be a positive number: " + length);
}
this.length = length;
this.termAttribute = AddAttribute<ICharTermAttribute>();
this.keywordAttr = AddAttribute<IKeywordAttribute>();
}
/// <summary>
/// Creates a new HunspellStemFilter that will stem tokens from the given <see cref="TokenStream"/> using affix rules in the provided
/// Dictionary
/// </summary>
/// <param name="input"> <see cref="TokenStream"/> whose tokens will be stemmed </param>
/// <param name="dictionary"> Hunspell <see cref="Dictionary"/> containing the affix rules and words that will be used to stem the tokens </param>
/// <param name="dedup"> remove duplicates </param>
/// <param name="longestOnly"> true if only the longest term should be output. </param>
public HunspellStemFilter(TokenStream input, Dictionary dictionary, bool dedup, bool longestOnly)
: base(input)
{
this.dedup = dedup && longestOnly == false; // don't waste time deduping if longestOnly is set
this.stemmer = new Stemmer(dictionary);
this.longestOnly = longestOnly;
termAtt = AddAttribute <ICharTermAttribute>();
posIncAtt = AddAttribute <IPositionIncrementAttribute>();
keywordAtt = AddAttribute <IKeywordAttribute>();
}
public TruncateTokenFilter(TokenStream input, int length)
: base(input)
{
if (length < 1)
{
throw new ArgumentOutOfRangeException(nameof(length), "length parameter must be a positive number: " + length); // LUCENENET specific - changed from IllegalArgumentException to ArgumentOutOfRangeException (.NET convention)
}
this.length = length;
this.termAttribute = AddAttribute <ICharTermAttribute>();
this.keywordAttr = AddAttribute <IKeywordAttribute>();
}
/// <summary>
/// Creates a filter with a given dictionary.
/// </summary>
/// <param name="input">Input token stream.</param>
/// <param name="dict"><see cref="Dictionary"/> to use for stemming.</param>
public MorfologikFilter(TokenStream input, Dictionary dict)
: base(input)
{
this.termAtt = AddAttribute <ICharTermAttribute>();
this.tagsAtt = AddAttribute <IMorphosyntacticTagsAttribute>();
this.posIncrAtt = AddAttribute <IPositionIncrementAttribute>();
this.keywordAttr = AddAttribute <IKeywordAttribute>();
this.input = input;
this.stemmer = new DictionaryLookup(dict);
this.lemmaList = new List <WordData>();
}
/// <summary>
/// Construct the named stemming filter.
///
/// Available stemmers are listed in Lucene.Net.Tartarus.Snowball.Ext.
/// The name of a stemmer is the part of the class name before "Stemmer",
/// e.g., the stemmer in <see cref="Tartarus.Snowball.Ext.EnglishStemmer"/> is named "English".
/// </summary>
/// <param name="in"> the input tokens to stem </param>
/// <param name="name"> the name of a stemmer </param>
public SnowballFilter(TokenStream @in, string name)
: base(@in)
{
try
{
string className = typeof(SnowballProgram).Namespace + ".Ext." +
name + "Stemmer, " + this.GetType().GetTypeInfo().Assembly.GetName().Name;
Type stemClass = Type.GetType(className);
stemmer = (SnowballProgram)Activator.CreateInstance(stemClass);
}
catch (Exception e)
{
throw new System.ArgumentException("Invalid stemmer class specified: " + name, e);
}
this.termAtt = AddAttribute <ICharTermAttribute>();
this.keywordAttr = AddAttribute <IKeywordAttribute>();
}
public void TestCustomAttribute()
{
TokenStream stream = new KeywordTokenizer(new StringReader("D'Angelo"));
stream = new PatternKeywordMarkerFilter(stream, new Regex(".*"));
stream = new BeiderMorseFilter(stream, new PhoneticEngine(NameType.GENERIC, RuleType.EXACT, true));
IKeywordAttribute keyAtt = stream.AddAttribute <IKeywordAttribute>();
stream.Reset();
int i = 0;
while (stream.IncrementToken())
{
assertTrue(keyAtt.IsKeyword);
i++;
}
assertEquals(12, i);
stream.End();
stream.Dispose();
}
/// <summary>
/// Construct the named stemming filter.
///
/// Available stemmers are listed in <seealso cref="org.tartarus.snowball.ext"/>.
/// The name of a stemmer is the part of the class name before "Stemmer",
/// e.g., the stemmer in <seealso cref="org.tartarus.snowball.ext.EnglishStemmer"/> is named "English".
/// </summary>
/// <param name="in"> the input tokens to stem </param>
/// <param name="name"> the name of a stemmer </param>
public SnowballFilter(TokenStream @in, string name)
: base(@in)
{
try
{
// LUCENENET TODO: There should probably be a way to make this an extesibility point so
// custom extensions can be loaded.
string className = typeof(SnowballProgram).Namespace + ".Ext." +
name + "Stemmer, " + this.GetType().Assembly.GetName().Name;
Type stemClass = Type.GetType(className);
stemmer = (SnowballProgram)Activator.CreateInstance(stemClass);
}
catch (Exception e)
{
throw new System.ArgumentException("Invalid stemmer class specified: " + name, e);
}
this.termAtt = AddAttribute <ICharTermAttribute>();
this.keywordAttr = AddAttribute <IKeywordAttribute>();
}
public DutchStemFilter(TokenStream _in)
: base(_in)
{
termAtt = AddAttribute <ICharTermAttribute>();
keywordAttr = AddAttribute <IKeywordAttribute>();
}
/// <summary>
/// Construct the named stemming filter.
///
/// Available stemmers are listed in <seealso cref="org.tartarus.snowball.ext"/>.
/// The name of a stemmer is the part of the class name before "Stemmer",
/// e.g., the stemmer in <seealso cref="org.tartarus.snowball.ext.EnglishStemmer"/> is named "English".
/// </summary>
/// <param name="in"> the input tokens to stem </param>
/// <param name="name"> the name of a stemmer </param>
public SnowballFilter(TokenStream @in, string name)
: base(@in)
{
try
{
// LUCENENET TODO: There should probably be a way to make this an extesibility point so
// custom extensions can be loaded.
string className = typeof(SnowballProgram).Namespace + ".Ext." +
name + "Stemmer, " + this.GetType().Assembly.GetName().Name;
Type stemClass = Type.GetType(className);
stemmer = (SnowballProgram)Activator.CreateInstance(stemClass);
}
catch (Exception e)
{
throw new System.ArgumentException("Invalid stemmer class specified: " + name, e);
}
this.termAtt = AddAttribute<ICharTermAttribute>();
this.keywordAttr = AddAttribute<IKeywordAttribute>();
}
/// <summary>
/// Construct a token stream filtering the given input.
/// </summary>
public KeywordRepeatFilter(TokenStream input)
: base(input)
{
keywordAttribute = AddAttribute<IKeywordAttribute>();
posIncAttr = AddAttribute<IPositionIncrementAttribute>();
}
public GalicianMinimalStemFilter(TokenStream input)
: base(input)
{
termAtt = AddAttribute<ICharTermAttribute>();
keywordAttr = AddAttribute<IKeywordAttribute>();
}
public HindiNormalizationFilter(TokenStream input)
: base(input)
{
termAtt = AddAttribute <ICharTermAttribute>();
keywordAtt = AddAttribute <IKeywordAttribute>();
}
/// <summary>
/// Creates a new <seealso cref="KeywordMarkerFilter"/> </summary>
/// <param name="in"> the input stream </param>
protected internal KeywordMarkerFilter(TokenStream @in)
: base(@in)
{
keywordAttr = AddAttribute<IKeywordAttribute>();
}
public HungarianLightStemFilter(TokenStream input)
: base(input)
{
termAtt = AddAttribute<ICharTermAttribute>();
keywordAttr = AddAttribute<IKeywordAttribute>();
}
/// <summary>
/// Creates a new BrazilianStemFilter
/// </summary>
/// <param name="in"> the source <seealso cref="TokenStream"/> </param>
public BrazilianStemFilter(TokenStream @in)
: base(@in)
{
termAtt = AddAttribute<ICharTermAttribute>();
keywordAttr = AddAttribute<IKeywordAttribute>();
}
// offsetsAreCorrect also validates:
// - graph offsets are correct (all tokens leaving from
// pos X have the same startOffset; all tokens
// arriving to pos Y have the same endOffset)
// - offsets only move forwards (startOffset >=
// lastStartOffset)
public static void AssertTokenStreamContents(TokenStream ts, string[] output, int[] startOffsets, int[] endOffsets, string[] types, int[] posIncrements, int[] posLengths, int?finalOffset, int?finalPosInc, bool[] keywordAtts, bool offsetsAreCorrect)
{
Assert.IsNotNull(output);
var checkClearAtt = ts.AddAttribute <ICheckClearAttributesAttribute>();
ICharTermAttribute termAtt = null;
if (output.Length > 0)
{
Assert.IsTrue(ts.HasAttribute <ICharTermAttribute>(), "has no CharTermAttribute");
termAtt = ts.GetAttribute <ICharTermAttribute>();
}
IOffsetAttribute offsetAtt = null;
if (startOffsets != null || endOffsets != null || finalOffset != null)
{
Assert.IsTrue(ts.HasAttribute <IOffsetAttribute>(), "has no OffsetAttribute");
offsetAtt = ts.GetAttribute <IOffsetAttribute>();
}
ITypeAttribute typeAtt = null;
if (types != null)
{
Assert.IsTrue(ts.HasAttribute <ITypeAttribute>(), "has no TypeAttribute");
typeAtt = ts.GetAttribute <ITypeAttribute>();
}
IPositionIncrementAttribute posIncrAtt = null;
if (posIncrements != null || finalPosInc != null)
{
Assert.IsTrue(ts.HasAttribute <IPositionIncrementAttribute>(), "has no PositionIncrementAttribute");
posIncrAtt = ts.GetAttribute <IPositionIncrementAttribute>();
}
IPositionLengthAttribute posLengthAtt = null;
if (posLengths != null)
{
Assert.IsTrue(ts.HasAttribute <IPositionLengthAttribute>(), "has no PositionLengthAttribute");
posLengthAtt = ts.GetAttribute <IPositionLengthAttribute>();
}
IKeywordAttribute keywordAtt = null;
if (keywordAtts != null)
{
Assert.IsTrue(ts.HasAttribute <IKeywordAttribute>(), "has no KeywordAttribute");
keywordAtt = ts.GetAttribute <IKeywordAttribute>();
}
// Maps position to the start/end offset:
IDictionary <int?, int?> posToStartOffset = new Dictionary <int?, int?>();
IDictionary <int?, int?> posToEndOffset = new Dictionary <int?, int?>();
ts.Reset();
int pos = -1;
int lastStartOffset = 0;
for (int i = 0; i < output.Length; i++)
{
// extra safety to enforce, that the state is not preserved and also assign bogus values
ts.ClearAttributes();
termAtt.SetEmpty().Append("bogusTerm");
if (offsetAtt != null)
{
offsetAtt.SetOffset(14584724, 24683243);
}
if (typeAtt != null)
{
typeAtt.Type = "bogusType";
}
if (posIncrAtt != null)
{
posIncrAtt.PositionIncrement = 45987657;
}
if (posLengthAtt != null)
{
posLengthAtt.PositionLength = 45987653;
}
if (keywordAtt != null)
{
keywordAtt.Keyword = (i & 1) == 0;
}
bool reset = checkClearAtt.AndResetClearCalled; // reset it, because we called clearAttribute() before
Assert.IsTrue(ts.IncrementToken(), "token " + i + " does not exist");
Assert.IsTrue(reset, "ClearAttributes() was not called correctly in TokenStream chain");
Assert.AreEqual(output[i], termAtt.ToString(), "term " + i + ", output[i] = " + output[i] + ", termAtt = " + termAtt.ToString());
if (startOffsets != null)
{
Assert.AreEqual(startOffsets[i], offsetAtt.StartOffset(), "startOffset " + i);
}
if (endOffsets != null)
{
Assert.AreEqual(endOffsets[i], offsetAtt.EndOffset(), "endOffset " + i);
}
if (types != null)
{
Assert.AreEqual(types[i], typeAtt.Type, "type " + i);
}
if (posIncrements != null)
{
Assert.AreEqual(posIncrements[i], posIncrAtt.PositionIncrement, "posIncrement " + i);
}
if (posLengths != null)
{
Assert.AreEqual(posLengths[i], posLengthAtt.PositionLength, "posLength " + i);
}
if (keywordAtts != null)
{
Assert.AreEqual(keywordAtts[i], keywordAtt.Keyword, "keywordAtt " + i);
}
// we can enforce some basic things about a few attributes even if the caller doesn't check:
if (offsetAtt != null)
{
int startOffset = offsetAtt.StartOffset();
int endOffset = offsetAtt.EndOffset();
if (finalOffset != null)
{
Assert.IsTrue(startOffset <= (int)finalOffset, "startOffset must be <= finalOffset");
Assert.IsTrue(endOffset <= (int)finalOffset, "endOffset must be <= finalOffset: got endOffset=" + endOffset + " vs finalOffset=" + (int)finalOffset);
}
if (offsetsAreCorrect)
{
Assert.IsTrue(offsetAtt.StartOffset() >= lastStartOffset, "offsets must not go backwards startOffset=" + startOffset + " is < lastStartOffset=" + lastStartOffset);
lastStartOffset = offsetAtt.StartOffset();
}
if (offsetsAreCorrect && posLengthAtt != null && posIncrAtt != null)
{
// Validate offset consistency in the graph, ie
// all tokens leaving from a certain pos have the
// same startOffset, and all tokens arriving to a
// certain pos have the same endOffset:
int posInc = posIncrAtt.PositionIncrement;
pos += posInc;
int posLength = posLengthAtt.PositionLength;
if (!posToStartOffset.ContainsKey(pos))
{
// First time we've seen a token leaving from this position:
posToStartOffset[pos] = startOffset;
//System.out.println(" + s " + pos + " -> " + startOffset);
}
else
{
// We've seen a token leaving from this position
// before; verify the startOffset is the same:
//System.out.println(" + vs " + pos + " -> " + startOffset);
Assert.AreEqual((int)posToStartOffset[pos], startOffset, "pos=" + pos + " posLen=" + posLength + " token=" + termAtt);
}
int endPos = pos + posLength;
if (!posToEndOffset.ContainsKey(endPos))
{
// First time we've seen a token arriving to this position:
posToEndOffset[endPos] = endOffset;
//System.out.println(" + e " + endPos + " -> " + endOffset);
}
else
{
// We've seen a token arriving to this position
// before; verify the endOffset is the same:
//System.out.println(" + ve " + endPos + " -> " + endOffset);
Assert.AreEqual((int)posToEndOffset[endPos], endOffset, "pos=" + pos + " posLen=" + posLength + " token=" + termAtt);
}
}
}
if (posIncrAtt != null)
{
if (i == 0)
{
Assert.IsTrue(posIncrAtt.PositionIncrement >= 1, "first posIncrement must be >= 1");
}
else
{
Assert.IsTrue(posIncrAtt.PositionIncrement >= 0, "posIncrement must be >= 0");
}
}
if (posLengthAtt != null)
{
Assert.IsTrue(posLengthAtt.PositionLength >= 1, "posLength must be >= 1");
}
}
if (ts.IncrementToken())
{
Assert.Fail("TokenStream has more tokens than expected (expected count=" + output.Length + "); extra token=" + termAtt);
}
// repeat our extra safety checks for End()
ts.ClearAttributes();
if (termAtt != null)
{
termAtt.SetEmpty().Append("bogusTerm");
}
if (offsetAtt != null)
{
offsetAtt.SetOffset(14584724, 24683243);
}
if (typeAtt != null)
{
typeAtt.Type = "bogusType";
}
if (posIncrAtt != null)
{
posIncrAtt.PositionIncrement = 45987657;
}
if (posLengthAtt != null)
{
posLengthAtt.PositionLength = 45987653;
}
var reset_ = checkClearAtt.AndResetClearCalled; // reset it, because we called clearAttribute() before
ts.End();
Assert.IsTrue(checkClearAtt.AndResetClearCalled, "super.End()/ClearAttributes() was not called correctly in End()");
if (finalOffset != null)
{
Assert.AreEqual((int)finalOffset, offsetAtt.EndOffset(), "finalOffset");
}
if (offsetAtt != null)
{
Assert.IsTrue(offsetAtt.EndOffset() >= 0, "finalOffset must be >= 0");
}
if (finalPosInc != null)
{
Assert.AreEqual((int)finalPosInc, posIncrAtt.PositionIncrement, "finalPosInc");
}
ts.Dispose();
}
/// <summary>
/// Construct a token stream filtering the given input.
/// </summary>
public KeywordRepeatFilter(TokenStream input)
: base(input)
{
keywordAttribute = AddAttribute <IKeywordAttribute>();
posIncAttr = AddAttribute <IPositionIncrementAttribute>();
}
public LowerCaseFilterMock(TokenStream @in) : base(@in)
{
termAtt = AddAttribute <ICharTermAttribute>();
keywordAttr = AddAttribute <IKeywordAttribute>();
}
/// <summary>
/// Creates a new <see cref="KeywordMarkerFilter"/> </summary>
/// <param name="in"> the input stream </param>
protected KeywordMarkerFilter(TokenStream @in)
: base(@in)
{
keywordAttr = AddAttribute <IKeywordAttribute>();
}
public CzechStemFilter(TokenStream input)
: base(input)
{
termAtt = AddAttribute<ICharTermAttribute>();
keywordAttr = AddAttribute<IKeywordAttribute>();
}
public PortugueseMinimalStemFilter(TokenStream input)
: base(input)
{
termAtt = AddAttribute <ICharTermAttribute>();
keywordAttr = AddAttribute <IKeywordAttribute>();
}
public DutchStemFilter(TokenStream _in)
: base(_in)
{
termAtt = AddAttribute<ICharTermAttribute>();
keywordAttr = AddAttribute<IKeywordAttribute>();
}
public AdvancedBulgarianStemFilter(TokenStream input)
: base(input)
{
termAtt = AddAttribute <ICharTermAttribute>();
keywordAttr = AddAttribute <IKeywordAttribute>();
}
public HungarianLightStemFilter(TokenStream input)
: base(input)
{
termAtt = AddAttribute <ICharTermAttribute>();
keywordAttr = AddAttribute <IKeywordAttribute>();
}
public HindiNormalizationFilter(TokenStream input)
: base(input)
{
termAtt = AddAttribute<ICharTermAttribute>();
keywordAtt = AddAttribute<IKeywordAttribute>();
}
/// <summary>
/// Creates a new <see cref="BrazilianStemFilter"/>
/// </summary>
/// <param name="in"> the source <see cref="TokenStream"/> </param>
public BrazilianStemFilter(TokenStream @in)
: base(@in)
{
termAtt = AddAttribute <ICharTermAttribute>();
keywordAttr = AddAttribute <IKeywordAttribute>();
}
public GreekStemFilter(TokenStream input)
: base(input)
{
termAtt = AddAttribute <ICharTermAttribute>();
keywordAttr = AddAttribute <IKeywordAttribute>();
}
public PortugueseLightStemFilter(TokenStream input)
: base(input)
{
termAtt = AddAttribute<ICharTermAttribute>();
keywordAttr = AddAttribute<IKeywordAttribute>();
}
public LowerCaseFilterMock(TokenStream @in) : base(@in)
{
termAtt = AddAttribute<ICharTermAttribute>();
keywordAttr = AddAttribute<IKeywordAttribute>();
}
