override public object Clone()
{
PositionIncrementAttribute impl = new PositionIncrementAttribute();
impl.positionIncrement = positionIncrement;
return(impl);
}
public SingleCharTokenizer(TokenStream input): base(input)
{
_input = input;
_termAttribute = (TermAttribute)AddAttribute(typeof(TermAttribute));
_offsetAttribute = (OffsetAttribute)AddAttribute(typeof(OffsetAttribute));
_positionIncrementAttribute = (PositionIncrementAttribute)AddAttribute(typeof(PositionIncrementAttribute));
}
public SynonymFilter(TokenStream input, ISynonymEngine engine)
: base(input)
{
synonymStack = new Stack<string>();
this.engine = engine;
this.termAttr = AddAttribute(typeof(TermAttribute)) as TermAttribute;
this.posIncrAttr = AddAttribute(typeof(PositionIncrementAttribute)) as PositionIncrementAttribute;
}
/// <summary>
/// Creates a new HunspellStemFilter that will stem tokens from the given TokenStream using
/// affix rules in the provided HunspellDictionary.
/// </summary>
/// <param name="input">TokenStream whose tokens will be stemmed.</param>
/// <param name="dictionary">HunspellDictionary containing the affix rules and words that will be used to stem the tokens.</param>
/// <param name="dedup">true if only unique terms should be output.</param>
public HunspellStemFilter(TokenStream input, HunspellDictionary dictionary, Boolean dedup = true)
: base(input) {
_posIncAtt = (PositionIncrementAttribute)AddAttribute(typeof(PositionIncrementAttribute));
_termAtt = (TermAttribute)AddAttribute(typeof(TermAttribute));
_dedup = dedup;
_stemmer = new HunspellStemmer(dictionary);
}
public SynonymFilter(TokenStream in_Renamed, ISynonymEngine engine)
: base(in_Renamed)
{
synonymStack = new Stack<string>();
this.engine = engine;
termAtt = (TermAttribute)AddAttribute(typeof(TermAttribute));
posIncrAtt = (PositionIncrementAttribute)AddAttribute(typeof(PositionIncrementAttribute));
}
public AnsjTokenizer(AbstractAnalysis analysis, TextReader input, HashSet<string> filter, bool pstemming)
: base(input)
{
_analysis = analysis;
_termAtt = AddAttribute<TermAttribute>();
_offsetAtt = AddAttribute<OffsetAttribute>();
_positionAttr = AddAttribute<PositionIncrementAttribute>();
_filter = filter;
_pstemming = pstemming;
}
public SynonymFilter (TokenStream input, SynonymEngine engine) : base(input) {
if (engine == null)
throw new ArgumentNullException("synonymEngine");
synonymStack = new Stack<string>();
this.engine = engine;
this.termAtt = (TermAttribute)AddAttribute<ITermAttribute>();
this.posIncrAtt = (PositionIncrementAttribute)AddAttribute<IPositionIncrementAttribute>();
//this.termAtt = this.AddAttribute<string>();
//this.posIncrAtt = this.AddAttribute<string>();
}
public override bool Equals(object other)
{
if (other == this)
{
return(true);
}
if (other is PositionIncrementAttribute)
{
PositionIncrementAttribute _other = (PositionIncrementAttribute)other;
return(positionIncrement == _other.positionIncrement);
}
return(false);
}
public virtual void TestPositionIncrementAttribute()
{
PositionIncrementAttribute att = new PositionIncrementAttribute();
Assert.AreEqual(1, att.PositionIncrement);
att.PositionIncrement = 1234;
Assert.AreEqual("positionIncrement=1234", att.ToString());
PositionIncrementAttribute att2 = (PositionIncrementAttribute) AssertCloneIsEqual(att);
Assert.AreEqual(1234, att2.PositionIncrement);
att2 = (PositionIncrementAttribute) AssertCopyIsEqual(att);
Assert.AreEqual(1234, att2.PositionIncrement);
att.Clear();
Assert.AreEqual(1, att.PositionIncrement);
}
public virtual void TestPositionIncrementAttribute()
{
PositionIncrementAttribute att = new PositionIncrementAttribute();
Assert.AreEqual(1, att.PositionIncrement);
att.PositionIncrement = 1234;
Assert.AreEqual("positionIncrement=1234", att.ToString());
PositionIncrementAttribute att2 = (PositionIncrementAttribute)AssertCloneIsEqual(att);
Assert.AreEqual(1234, att2.PositionIncrement);
att2 = (PositionIncrementAttribute)AssertCopyIsEqual(att);
Assert.AreEqual(1234, att2.PositionIncrement);
att.Clear();
Assert.AreEqual(1, att.PositionIncrement);
}
public PrefixAwareTokenFilter(TokenStream prefix, TokenStream suffix) : base(suffix)
{
Suffix = suffix;
Prefix = prefix;
_prefixExhausted = false;
// ReSharper disable DoNotCallOverridableMethodsInConstructor
_termAtt = (TermAttribute) AddAttribute(typeof (TermAttribute));
_posIncrAtt = (PositionIncrementAttribute) AddAttribute(typeof (PositionIncrementAttribute));
_payloadAtt = (PayloadAttribute) AddAttribute(typeof (PayloadAttribute));
_offsetAtt = (OffsetAttribute) AddAttribute(typeof (OffsetAttribute));
_typeAtt = (TypeAttribute) AddAttribute(typeof (TypeAttribute));
_flagsAtt = (FlagsAttribute) AddAttribute(typeof (FlagsAttribute));
// ReSharper restore DoNotCallOverridableMethodsInConstructor
_pTermAtt = (TermAttribute) prefix.AddAttribute(typeof (TermAttribute));
_pPosIncrAtt = (PositionIncrementAttribute) prefix.AddAttribute(typeof (PositionIncrementAttribute));
_pPayloadAtt = (PayloadAttribute) prefix.AddAttribute(typeof (PayloadAttribute));
_pOffsetAtt = (OffsetAttribute) prefix.AddAttribute(typeof (OffsetAttribute));
_pTypeAtt = (TypeAttribute) prefix.AddAttribute(typeof (TypeAttribute));
_pFlagsAtt = (FlagsAttribute) prefix.AddAttribute(typeof (FlagsAttribute));
}
/// <summary>
/// Creates a shingle filter with ad hoc parameter settings.
/// </summary>
/// <param name="input">stream from which to construct the matrix</param>
/// <param name="minimumShingleSize">minimum number of tokens in any shingle.</param>
/// <param name="maximumShingleSize">maximum number of tokens in any shingle.</param>
/// <param name="spacerCharacter">character to use between texts of the token parts in a shingle. null for none.</param>
/// <param name="ignoringSinglePrefixOrSuffixShingle">if true, shingles that only contains permutation of the first of the last column will not be produced as shingles. Useful when adding boundary marker tokens such as '^' and '$'.</param>
/// <param name="settingsCodec">codec used to read input token weight and matrix positioning.</param>
public ShingleMatrixFilter(TokenStream input, int minimumShingleSize, int maximumShingleSize, Char? spacerCharacter, bool ignoringSinglePrefixOrSuffixShingle, TokenSettingsCodec settingsCodec)
{
_input = input;
MinimumShingleSize = minimumShingleSize;
MaximumShingleSize = maximumShingleSize;
SpacerCharacter = spacerCharacter;
IsIgnoringSinglePrefixOrSuffixShingle = ignoringSinglePrefixOrSuffixShingle;
_settingsCodec = settingsCodec;
// ReSharper disable DoNotCallOverridableMethodsInConstructor
_termAtt = (TermAttribute) AddAttribute(typeof (TermAttribute));
_posIncrAtt = (PositionIncrementAttribute) AddAttribute(typeof (PositionIncrementAttribute));
_payloadAtt = (PayloadAttribute) AddAttribute(typeof (PayloadAttribute));
_offsetAtt = (OffsetAttribute) AddAttribute(typeof (OffsetAttribute));
_typeAtt = (TypeAttribute) AddAttribute(typeof (TypeAttribute));
_flagsAtt = (FlagsAttribute) AddAttribute(typeof (FlagsAttribute));
// ReSharper restore DoNotCallOverridableMethodsInConstructor
_inTermAtt = (TermAttribute) input.AddAttribute(typeof (TermAttribute));
_inPosIncrAtt = (PositionIncrementAttribute) input.AddAttribute(typeof (PositionIncrementAttribute));
_inPayloadAtt = (PayloadAttribute) input.AddAttribute(typeof (PayloadAttribute));
_inOffsetAtt = (OffsetAttribute) input.AddAttribute(typeof (OffsetAttribute));
_inTypeAtt = (TypeAttribute) input.AddAttribute(typeof (TypeAttribute));
_inFlagsAtt = (FlagsAttribute) input.AddAttribute(typeof (FlagsAttribute));
}
/// <summary>
/// Creates a shingle filter based on a user defined matrix.
///
/// The filter /will/ delete columns from the input matrix! You will not be able to reset the filter if you used this constructor.
/// todo: don't touch the matrix! use a bool, set the input stream to null or something, and keep track of where in the matrix we are at.
///
/// </summary>
/// <param name="matrix">the input based for creating shingles. Does not need to contain any information until ShingleMatrixFilter.Next(Token) is called the first time.</param>
/// <param name="minimumShingleSize">minimum number of tokens in any shingle.</param>
/// <param name="maximumShingleSize">maximum number of tokens in any shingle.</param>
/// <param name="spacerCharacter">character to use between texts of the token parts in a shingle. null for none.</param>
/// <param name="ignoringSinglePrefixOrSuffixShingle">if true, shingles that only contains permutation of the first of the last column will not be produced as shingles. Useful when adding boundary marker tokens such as '^' and '$'.</param>
/// <param name="settingsCodec">codec used to read input token weight and matrix positioning.</param>
public ShingleMatrixFilter(Matrix.Matrix matrix, int minimumShingleSize, int maximumShingleSize, Char spacerCharacter, bool ignoringSinglePrefixOrSuffixShingle, TokenSettingsCodec settingsCodec)
{
Matrix = matrix;
MinimumShingleSize = minimumShingleSize;
MaximumShingleSize = maximumShingleSize;
SpacerCharacter = spacerCharacter;
IsIgnoringSinglePrefixOrSuffixShingle = ignoringSinglePrefixOrSuffixShingle;
_settingsCodec = settingsCodec;
// ReSharper disable DoNotCallOverridableMethodsInConstructor
_termAtt = (TermAttribute) AddAttribute(typeof (TermAttribute));
_posIncrAtt = (PositionIncrementAttribute) AddAttribute(typeof (PositionIncrementAttribute));
_payloadAtt = (PayloadAttribute) AddAttribute(typeof (PayloadAttribute));
_offsetAtt = (OffsetAttribute) AddAttribute(typeof (OffsetAttribute));
_typeAtt = (TypeAttribute) AddAttribute(typeof (TypeAttribute));
_flagsAtt = (FlagsAttribute) AddAttribute(typeof (FlagsAttribute));
// ReSharper restore DoNotCallOverridableMethodsInConstructor
// set the input to be an empty token stream, we already have the data.
_input = new EmptyTokenStream();
_inTermAtt = (TermAttribute) _input.AddAttribute(typeof (TermAttribute));
_inPosIncrAtt = (PositionIncrementAttribute) _input.AddAttribute(typeof (PositionIncrementAttribute));
_inPayloadAtt = (PayloadAttribute) _input.AddAttribute(typeof (PayloadAttribute));
_inOffsetAtt = (OffsetAttribute) _input.AddAttribute(typeof (OffsetAttribute));
_inTypeAtt = (TypeAttribute) _input.AddAttribute(typeof (TypeAttribute));
_inFlagsAtt = (FlagsAttribute) _input.AddAttribute(typeof (FlagsAttribute));
}
public override void CopyTo(Attribute target)
{
PositionIncrementAttribute t = (PositionIncrementAttribute)target;
t.PositionIncrement = positionIncrement;
}
private void Init(System.IO.TextReader input, HebMorph.StreamLemmatizer _lemmatizer,
HebMorph.LemmaFilters.LemmaFilterBase _lemmaFilter, bool AlwaysSaveMarkedOriginal)
{
termAtt = (TermAttribute)AddAttribute(typeof(TermAttribute));
offsetAtt = (OffsetAttribute)AddAttribute(typeof(OffsetAttribute));
posIncrAtt = (PositionIncrementAttribute)AddAttribute(typeof(PositionIncrementAttribute));
typeAtt = (TypeAttribute)AddAttribute(typeof(TypeAttribute));
//payAtt = (PayloadAttribute)AddAttribute(typeof(PayloadAttribute));
this._streamLemmatizer = _lemmatizer;
this._streamLemmatizer.SetStream(input);
this.alwaysSaveMarkedOriginal = AlwaysSaveMarkedOriginal;
this.lemmaFilter = _lemmaFilter;
}
override public System.Object Clone()
{
PositionIncrementAttribute impl = new PositionIncrementAttribute();
impl.positionIncrement = positionIncrement;
return impl;
}
public TokenListStream(ICollection<Token> tokens)
{
_tokens = tokens;
_termAtt = (TermAttribute) AddAttribute(typeof (TermAttribute));
_posIncrAtt = (PositionIncrementAttribute) AddAttribute(typeof (PositionIncrementAttribute));
_payloadAtt = (PayloadAttribute) AddAttribute(typeof (PayloadAttribute));
_offsetAtt = (OffsetAttribute) AddAttribute(typeof (OffsetAttribute));
_typeAtt = (TypeAttribute) AddAttribute(typeof (TypeAttribute));
_flagsAtt = (FlagsAttribute) AddAttribute(typeof (FlagsAttribute));
}
/// <summary>
/// Constructs a ShingleFilter with the specified single size from the TokenStream
/// </summary>
/// <param name="input">input token stream</param>
/// <param name="maxShingleSize">maximum shingle size produced by the filter.</param>
public ShingleFilter(TokenStream input, int maxShingleSize) : base(input)
{
SetMaxShingleSize(maxShingleSize);
// ReSharper disable DoNotCallOverridableMethodsInConstructor
_termAtt = (TermAttribute) AddAttribute(typeof (TermAttribute));
_offsetAtt = (OffsetAttribute) AddAttribute(typeof (OffsetAttribute));
_posIncrAtt = (PositionIncrementAttribute) AddAttribute(typeof (PositionIncrementAttribute));
_typeAtt = (TypeAttribute) AddAttribute(typeof (TypeAttribute));
// ReSharper restore DoNotCallOverridableMethodsInConstructor
}
/// <summary>
/// Creates NGramTokenFilter with given min and max n-grams. </summary>
/// <param name="version"> Lucene version to enable correct position increments.
/// See <a href="#version">above</a> for details. </param>
/// <param name="input"> <seealso cref="TokenStream"/> holding the input to be tokenized </param>
/// <param name="minGram"> the smallest n-gram to generate </param>
/// <param name="maxGram"> the largest n-gram to generate </param>
public NGramTokenFilter(Version version, TokenStream input, int minGram, int maxGram)
: base(new CodepointCountFilter(version, input, minGram, int.MaxValue))
{
this.version = version;
this.charUtils = version.OnOrAfter(Version.LUCENE_44) ? CharacterUtils.GetInstance(version) : CharacterUtils.Java4Instance;
if (minGram < 1)
{
throw new System.ArgumentException("minGram must be greater than zero");
}
if (minGram > maxGram)
{
throw new System.ArgumentException("minGram must not be greater than maxGram");
}
this.minGram = minGram;
this.maxGram = maxGram;
if (version.OnOrAfter(Version.LUCENE_44))
{
posIncAtt = AddAttribute(typeof(PositionIncrementAttribute));
posLenAtt = AddAttribute(typeof(PositionLengthAttribute));
}
else
{
posIncAtt = new PositionIncrementAttributeAnonymousInnerClassHelper(this);
posLenAtt = new PositionLengthAttributeAnonymousInnerClassHelper(this);
}
}
public override void CopyTo(AttributeImpl target)
{
PositionIncrementAttribute t = (PositionIncrementAttribute)target;
t.SetPositionIncrement(positionIncrement);
}
public SynonymFilter(TokenStream input) : base(input)
{
_termAtt = (TermAttribute) AddAttribute<ITermAttribute>();
_posIncrAtt = (PositionIncrementAttribute)AddAttribute<IPositionIncrementAttribute>();
}
