/// <summary>Constructs a {@link StandardTokenizer} filtered by a {@link
/// StandardFilter}, a {@link LowerCaseFilter} and a {@link StopFilter}.
/// </summary>
public override TokenStream TokenStream(System.String fieldName, System.IO.TextReader reader)
{
TokenStream result = new StandardTokenizer(reader);
result = new StandardFilter(result);
result = new LowerCaseFilter(result);
if (stopSet != null)
result = new StopFilter(result, stopSet);
result = new SnowballFilter(result, name);
return result;
}
public override TokenStream TokenStream(string fieldName, TextReader reader)
{
TokenStream result = new SnowballFilter(
new StopFilter(true,
new LowerCaseFilter(
new StandardFilter(
new StandardTokenizer(_version, reader))), StopAnalyzer.ENGLISH_STOP_WORDS_SET),
new EnglishStemmer());
return result;
}
/// <summary>Constructs a <see cref="StandardTokenizer"/> filtered by a {@link
/// StandardFilter}, a <see cref="LowerCaseFilter"/> and a <see cref="StopFilter"/>.
/// </summary>
public override TokenStream TokenStream(System.String fieldName, System.IO.TextReader reader)
{
TokenStream result = new StandardTokenizer(matchVersion, reader);
result = new StandardFilter(result);
result = new LowerCaseFilter(result);
if (stopSet != null)
result = new StopFilter(StopFilter.GetEnablePositionIncrementsVersionDefault(matchVersion),
result, stopSet);
result = new SnowballFilter(result, name);
return result;
}
public override TokenStream TokenStream(string fieldName, System.IO.TextReader reader)
{
TokenStream result = new StandardTokenizer(Lucene.Net.Util.Version.LUCENE_29, reader);
//result = new StandardFilter(result);
result = new LowerCaseFilter(result);
if (STOP_WORDS != null)
result = new StopFilter(false, result, STOP_WORDS);
result = new ASCIIFoldingFilter(result);
result = new SnowballFilter(result, "English");
return result;
}
public override TokenStream TokenStream(string fieldName, TextReader reader)
{
//Apply standard tokenizer to input
var tokenizedInput = new StandardTokenizer(_version, reader);
//Apply standard, lowercase and English stop words filters to input
var filteredInput = new SnowballFilter(new StopFilter(true, new LowerCaseFilter(new StandardFilter(tokenizedInput)),
StopAnalyzer.ENGLISH_STOP_WORDS_SET), new EnglishStemmer());
//Apply EdgeNGram filter to front of words
//Min size of grams max size of grams
var grammedInput = new EdgeNGramTokenFilter(filteredInput, Side.FRONT, _mingram, _maxgram);
return grammedInput;
}
public virtual void TestFilterTokens()
{
Token tok = new Token("accents", 2, 7, "wrd");
tok.SetPositionIncrement(3);
SnowballFilter filter = new SnowballFilter(new AnonymousClassTokenStream(tok, this), "English");
Token newtok = filter.Next();
System.Diagnostics.Trace.Assert("accent" == newtok.TermText()); //// assertEquals("accent", newtok.TermText());
System.Diagnostics.Trace.Assert(2 == newtok.StartOffset()); //// assertEquals(2, newtok.StartOffset());
System.Diagnostics.Trace.Assert(7 == newtok.EndOffset()); //// assertEquals(7, newtok.EndOffset());
System.Diagnostics.Trace.Assert("wrd" == newtok.Type()); //// assertEquals("wrd", newtok.Type());
System.Diagnostics.Trace.Assert(3 == newtok.GetPositionIncrement()); //// assertEquals(3, newtok.GetPositionIncrement());
}
public virtual void TestFilterTokens()
{
Token tok = new Token("accents", 2, 7, "wrd");
tok.SetPositionIncrement(3);
SnowballFilter filter = new SnowballFilter(new AnonymousClassTokenStream(tok, this), "English");
Token newtok = filter.Next();
Assert.AreEqual("accent", newtok.TermText());
Assert.AreEqual(2, newtok.StartOffset());
Assert.AreEqual(7, newtok.EndOffset());
Assert.AreEqual("wrd", newtok.Type());
Assert.AreEqual(3, newtok.GetPositionIncrement());
}
public override TokenStream TokenStream(string fieldName, System.IO.TextReader reader)
{
TokenStream result = new StandardTokenizer(Lucene.Net.Util.Version.LUCENE_29, reader);
//result = new StandardFilter(result);
result = new LowerCaseFilter(result);
if (STOP_WORDS != null)
result = new StopFilter(false, result, STOP_WORDS);
result = new ASCIIFoldingFilter(result);
// we are using a distinct version of the Spanish stemmer, called Spanish2
// Please check if this class can be found in the Snowball library, the relative path
// should be: Snowball\SF\Snowball\Ext\
// just in case, I would leave a copy of this class in this project
result = new SnowballFilter(result, "Spanish");
return result;
}
public virtual void TestFilterTokens()
{
SnowballFilter filter = new SnowballFilter(new TestTokenStream(this), "English");
ICharTermAttribute termAtt = filter.GetAttribute <ICharTermAttribute>();
IOffsetAttribute offsetAtt = filter.GetAttribute <IOffsetAttribute>();
ITypeAttribute typeAtt = filter.GetAttribute <ITypeAttribute>();
IPayloadAttribute payloadAtt = filter.GetAttribute <IPayloadAttribute>();
IPositionIncrementAttribute posIncAtt = filter.GetAttribute <IPositionIncrementAttribute>();
IFlagsAttribute flagsAtt = filter.GetAttribute <IFlagsAttribute>();
filter.IncrementToken();
assertEquals("accent", termAtt.ToString());
assertEquals(2, offsetAtt.StartOffset());
assertEquals(7, offsetAtt.EndOffset());
assertEquals("wrd", typeAtt.Type);
assertEquals(3, posIncAtt.PositionIncrement);
assertEquals(77, flagsAtt.Flags);
assertEquals(new BytesRef(new byte[] { 0, 1, 2, 3 }), payloadAtt.Payload);
}
public void TestFilterTokens()
{
SnowballFilter filter = new SnowballFilter(new TestTokenStream(), "English");
ITermAttribute termAtt = filter.GetAttribute <ITermAttribute>();
IOffsetAttribute offsetAtt = filter.GetAttribute <IOffsetAttribute>();
ITypeAttribute typeAtt = filter.GetAttribute <ITypeAttribute>();
IPayloadAttribute payloadAtt = filter.GetAttribute <IPayloadAttribute>();
IPositionIncrementAttribute posIncAtt = filter.GetAttribute <IPositionIncrementAttribute>();
IFlagsAttribute flagsAtt = filter.GetAttribute <IFlagsAttribute>();
filter.IncrementToken();
Assert.AreEqual("accent", termAtt.Term);
Assert.AreEqual(2, offsetAtt.StartOffset);
Assert.AreEqual(7, offsetAtt.EndOffset);
Assert.AreEqual("wrd", typeAtt.Type);
Assert.AreEqual(3, posIncAtt.PositionIncrement);
Assert.AreEqual(77, flagsAtt.Flags);
Assert.AreEqual(new Payload(new byte[] { 0, 1, 2, 3 }), payloadAtt.Payload);
}
public override TokenStream TokenStream(string fieldName, TextReader reader)
{
Tokenizer src = new StandardTokenizer(Version.LUCENE_30, reader);
TokenStream filter = new StandardFilter(src);
//var stoplist = StopAnalyzer.ENGLISH_STOP_WORDS_SET;
HashSet<string> newWords = new HashSet<string>()
{
"said", "have", "the", "more", "from", "who", "he", "than", "it", "were", "use", "has", "also",
"been", "we", "which", "had", "you", "us", "them", "so", "in", "i", "our", "his", "to", "of", "a",
"st", "ad", "co", "re", "ve", "1", "2", "3", "4", "5", "6", "7", "8", "9", "0", "f", "g", "it"
};
foreach (var var in StopAnalyzer.ENGLISH_STOP_WORDS_SET)
{
newWords.Add(var);
}
TokenStream result = new StandardTokenizer(Version.LUCENE_30, reader);
result = new SnowballFilter(result, new EnglishStemmer());
result = new LowerCaseFilter(result);
result = new ASCIIFoldingFilter(result);
result = new StopFilter(true, result, newWords);
return result;
}
/// <summary>
/// Creates
/// <seealso cref="org.apache.lucene.analysis.Analyzer.TokenStreamComponents"/>
/// used to tokenize all the text in the provided <seealso cref="Reader"/>.
/// </summary>
/// <returns> <seealso cref="org.apache.lucene.analysis.Analyzer.TokenStreamComponents"/>
/// built from a <seealso cref="StandardTokenizer"/> filtered with
/// <seealso cref="StandardFilter"/>, <seealso cref="ElisionFilter"/>,
/// <seealso cref="LowerCaseFilter"/>, <seealso cref="StopFilter"/>,
/// <seealso cref="SetKeywordMarkerFilter"/> if a stem exclusion set is
/// provided, and <seealso cref="FrenchLightStemFilter"/> </returns>
///
public override TokenStreamComponents CreateComponents(string fieldName, TextReader reader)
{
#pragma warning disable 612, 618
if (matchVersion.OnOrAfter(LuceneVersion.LUCENE_31))
#pragma warning restore 612, 618
{
Tokenizer source = new StandardTokenizer(matchVersion, reader);
TokenStream result = new StandardFilter(matchVersion, source);
result = new ElisionFilter(result, DEFAULT_ARTICLES);
result = new LowerCaseFilter(matchVersion, result);
result = new StopFilter(matchVersion, result, stopwords);
if (excltable.Count > 0)
{
result = new SetKeywordMarkerFilter(result, excltable);
}
#pragma warning disable 612, 618
if (matchVersion.OnOrAfter(LuceneVersion.LUCENE_36))
#pragma warning restore 612, 618
{
result = new FrenchLightStemFilter(result);
}
else
{
result = new SnowballFilter(result, new Tartarus.Snowball.Ext.FrenchStemmer());
}
return new TokenStreamComponents(source, result);
}
else
{
Tokenizer source = new StandardTokenizer(matchVersion, reader);
TokenStream result = new StandardFilter(matchVersion, source);
result = new StopFilter(matchVersion, result, stopwords);
if (excltable.Count > 0)
{
result = new SetKeywordMarkerFilter(result, excltable);
}
#pragma warning disable 612, 618
result = new FrenchStemFilter(result);
#pragma warning restore 612, 618
// Convert to lowercase after stemming!
return new TokenStreamComponents(source, new LowerCaseFilter(matchVersion, result));
}
}
/// <summary>
/// Creates a
/// <seealso cref="org.apache.lucene.analysis.Analyzer.TokenStreamComponents"/>
/// which tokenizes all the text in the provided <seealso cref="Reader"/>.
/// </summary>
/// <returns> A
/// <seealso cref="org.apache.lucene.analysis.Analyzer.TokenStreamComponents"/>
/// built from an <seealso cref="StandardTokenizer"/> filtered with
/// <seealso cref="StandardFilter"/>, <seealso cref="LowerCaseFilter"/>, <seealso cref="StopFilter"/>
/// , <seealso cref="SetKeywordMarkerFilter"/> if a stem exclusion set is
/// provided and <seealso cref="SnowballFilter"/>. </returns>
public override TokenStreamComponents CreateComponents(string fieldName, TextReader reader)
{
Tokenizer source = new StandardTokenizer(matchVersion, reader);
TokenStream result = new StandardFilter(matchVersion, source);
result = new LowerCaseFilter(matchVersion, result);
result = new StopFilter(matchVersion, result, stopwords);
if (stemExclusionSet.Count > 0)
{
result = new SetKeywordMarkerFilter(result, stemExclusionSet);
}
result = new SnowballFilter(result, new DanishStemmer());
return new TokenStreamComponents(source, result);
}
/// <summary>Constructs a {@link StandardTokenizer} filtered by a {@link
/// StandardFilter}, a {@link LowerCaseFilter} and a {@link StopFilter}.
/// </summary>
public override TokenStream TokenStream(string fieldName, TextReader reader)
{
TokenStream result = new StandardTokenizer(reader);
if( TextFields == null || TextFields.Count == 0 || TextFields.Contains(fieldName) )
{
result = new StandardFilter(result);
result = new LowerCaseFilter(result);
if( StopWords != null ) result = new StopFilter(result, StopWords);
result = new SnowballFilter(result, StemmerName);
}
return result;
}
/// <summary>
/// Creates a
/// <seealso cref="org.apache.lucene.analysis.Analyzer.TokenStreamComponents"/>
/// which tokenizes all the text in the provided <seealso cref="Reader"/>.
/// </summary>
/// <returns> A
/// <seealso cref="org.apache.lucene.analysis.Analyzer.TokenStreamComponents"/>
/// built from an <seealso cref="StandardTokenizer"/> filtered with
/// <seealso cref="StandardFilter"/>, <seealso cref="TurkishLowerCaseFilter"/>,
/// <seealso cref="StopFilter"/>, <seealso cref="SetKeywordMarkerFilter"/> if a stem
/// exclusion set is provided and <seealso cref="SnowballFilter"/>. </returns>
public override TokenStreamComponents CreateComponents(string fieldName, TextReader reader)
{
Tokenizer source = new StandardTokenizer(matchVersion, reader);
TokenStream result = new StandardFilter(matchVersion, source);
if (matchVersion.OnOrAfter(LuceneVersion.LUCENE_48))
{
result = new ApostropheFilter(result);
}
result = new TurkishLowerCaseFilter(result);
result = new StopFilter(matchVersion, result, stopwords);
if (stemExclusionSet.Any())
{
result = new SetKeywordMarkerFilter(result, stemExclusionSet);
}
result = new SnowballFilter(result, new TurkishStemmer());
return new TokenStreamComponents(source, result);
}
public void TestFilterTokens()
{
SnowballFilter filter = new SnowballFilter(new TestTokenStream(), "English");
ITermAttribute termAtt = filter.GetAttribute<ITermAttribute>();
IOffsetAttribute offsetAtt = filter.GetAttribute<IOffsetAttribute>();
ITypeAttribute typeAtt = filter.GetAttribute<ITypeAttribute>();
IPayloadAttribute payloadAtt = filter.GetAttribute<IPayloadAttribute>();
IPositionIncrementAttribute posIncAtt = filter.GetAttribute<IPositionIncrementAttribute>();
IFlagsAttribute flagsAtt = filter.GetAttribute<IFlagsAttribute>();
filter.IncrementToken();
Assert.AreEqual("accent", termAtt.Term);
Assert.AreEqual(2, offsetAtt.StartOffset);
Assert.AreEqual(7, offsetAtt.EndOffset);
Assert.AreEqual("wrd", typeAtt.Type);
Assert.AreEqual(3, posIncAtt.PositionIncrement);
Assert.AreEqual(77, flagsAtt.Flags);
Assert.AreEqual(new Payload(new byte[] { 0, 1, 2, 3 }), payloadAtt.Payload);
}
/// <summary>
/// Creates
/// <seealso cref="org.apache.lucene.analysis.Analyzer.TokenStreamComponents"/>
/// used to tokenize all the text in the provided <seealso cref="Reader"/>.
/// </summary>
/// <returns> <seealso cref="org.apache.lucene.analysis.Analyzer.TokenStreamComponents"/>
/// built from a <seealso cref="StandardTokenizer"/> filtered with
/// <seealso cref="StandardFilter"/>, <seealso cref="LowerCaseFilter"/>, <seealso cref="StopFilter"/>
/// , <seealso cref="SetKeywordMarkerFilter"/> if a stem exclusion set is
/// provided, <seealso cref="GermanNormalizationFilter"/> and <seealso cref="GermanLightStemFilter"/> </returns>
public override TokenStreamComponents CreateComponents(string fieldName, TextReader reader)
{
Tokenizer source = new StandardTokenizer(matchVersion, reader);
TokenStream result = new StandardFilter(matchVersion, source);
result = new LowerCaseFilter(matchVersion, result);
result = new StopFilter(matchVersion, result, stopwords);
result = new SetKeywordMarkerFilter(result, exclusionSet);
#pragma warning disable 612, 618
if (matchVersion.OnOrAfter(LuceneVersion.LUCENE_36))
{
result = new GermanNormalizationFilter(result);
result = new GermanLightStemFilter(result);
}
else if (matchVersion.OnOrAfter(LuceneVersion.LUCENE_31))
#pragma warning restore 612, 618
{
result = new SnowballFilter(result, new German2Stemmer());
}
else
{
result = new GermanStemFilter(result);
}
return new TokenStreamComponents(source, result);
}
public override TokenStream TokenStream (string fieldName, TextReader reader)
{
bool is_text_prop = false;
// Strip off the first two characters in a property.
// We store type information in those two characters, so we don't
// want to index them.
if (fieldName.StartsWith ("prop:")) {
if (strip_extra_property_info) {
// Skip everything up to and including the first :
int c;
do {
c = reader.Read ();
} while (c != -1 && c != ':');
}
is_text_prop = fieldName.StartsWith ("prop:t");
// If this is non-text property, just return one token
// containing the entire string. We do this to avoid
// tokenizing keywords.
if (! is_text_prop) {
// We don't want to lower case the token if it's
// not in the private namespace.
TokenStream singleton_stream = new SingletonTokenStream (reader.ReadToEnd ());
if (fieldName.StartsWith ("prop:k:" + Property.PrivateNamespace))
return singleton_stream;
else
return new LowerCaseFilter (singleton_stream);
}
} else if (fieldName == "PropertyKeyword")
return new LowerCaseFilter (new SingletonTokenStream (reader.ReadToEnd ()));
else if (fieldName == "Properties")
return new WhitespaceTokenizer (new StringReader (reader.ReadToEnd ()));
else if (fieldName == "TextLinks")
return new WhitespaceTokenizer (new StringReader (reader.ReadToEnd ()));
TokenStream outstream;
outstream = base.TokenStream (fieldName, reader);
NoiseEmailHostFilter.LinkCallback add_link_callback = null;
lock (this) {
if (fieldName == "Text")
add_link_callback = add_link;
}
if (fieldName == "Text"
|| fieldName == "HotText"
|| fieldName == "PropertyText"
|| is_text_prop) {
outstream = new NoiseEmailHostFilter (outstream, tokenize_email_hostname, add_link_callback);
// Sharing Stemmer is not thread safe.
// Currently our underlying lucene indexing is not done in multiple threads.
StemmerInfo stemmer_info = GetStemmer (DEFAULT_STEMMER_LANGUAGE);
outstream = new SnowballFilter (outstream, stemmer_info.Stemmer, stemmer_info.StemMethod);
}
return outstream;
}
public virtual void TestFilterTokens()
{
Token tok = new Token("accents", 2, 7, "wrd");
tok.SetPositionIncrement(3);
SnowballFilter filter = new SnowballFilter(new AnonymousClassTokenStream(tok, this), "English");
Token newtok = filter.Next();
System.Diagnostics.Trace.Assert("accent" == newtok.TermText()); //// assertEquals("accent", newtok.TermText());
System.Diagnostics.Trace.Assert(2 == newtok.StartOffset()); //// assertEquals(2, newtok.StartOffset());
System.Diagnostics.Trace.Assert(7 == newtok.EndOffset()); //// assertEquals(7, newtok.EndOffset());
System.Diagnostics.Trace.Assert("wrd" == newtok.Type()); //// assertEquals("wrd", newtok.Type());
System.Diagnostics.Trace.Assert(3 == newtok.GetPositionIncrement()); //// assertEquals(3, newtok.GetPositionIncrement());
}
/// <summary>
/// Creates a
/// <seealso cref="org.apache.lucene.analysis.Analyzer.TokenStreamComponents"/>
/// which tokenizes all the text in the provided <seealso cref="Reader"/>.
/// </summary>
/// <returns> A
/// <seealso cref="org.apache.lucene.analysis.Analyzer.TokenStreamComponents"/>
/// built from an <seealso cref="StandardTokenizer"/> filtered with
/// <seealso cref="StandardFilter"/>, <seealso cref="IrishLowerCaseFilter"/>, <seealso cref="StopFilter"/>
/// , <seealso cref="SetKeywordMarkerFilter"/> if a stem exclusion set is
/// provided and <seealso cref="SnowballFilter"/>. </returns>
public override TokenStreamComponents CreateComponents(string fieldName, TextReader reader)
{
Tokenizer source = new StandardTokenizer(matchVersion, reader);
TokenStream result = new StandardFilter(matchVersion, source);
StopFilter s = new StopFilter(matchVersion, result, HYPHENATIONS);
#pragma warning disable 612, 618
if (!matchVersion.OnOrAfter(LuceneVersion.LUCENE_44))
#pragma warning restore 612, 618
{
s.EnablePositionIncrements = false;
}
result = s;
result = new ElisionFilter(result, DEFAULT_ARTICLES);
result = new IrishLowerCaseFilter(result);
result = new StopFilter(matchVersion, result, stopwords);
if (stemExclusionSet.Count > 0)
{
result = new SetKeywordMarkerFilter(result, stemExclusionSet);
}
result = new SnowballFilter(result, new IrishStemmer());
return new TokenStreamComponents(source, result);
}
/// <summary>
/// Creates
/// <seealso cref="org.apache.lucene.analysis.Analyzer.TokenStreamComponents"/>
/// used to tokenize all the text in the provided <seealso cref="Reader"/>.
/// </summary>
/// <returns> <seealso cref="org.apache.lucene.analysis.Analyzer.TokenStreamComponents"/>
/// built from a <seealso cref="StandardTokenizer"/> filtered with
/// <seealso cref="StandardFilter"/>, <seealso cref="LowerCaseFilter"/>, <seealso cref="StopFilter"/>
/// , <seealso cref="SetKeywordMarkerFilter"/> if a stem exclusion set is
/// provided, and <seealso cref="SnowballFilter"/> </returns>
public override TokenStreamComponents CreateComponents(string fieldName, TextReader reader)
{
#pragma warning disable 612, 618
if (matchVersion.OnOrAfter(LuceneVersion.LUCENE_31))
#pragma warning restore 612, 618
{
Tokenizer source = new StandardTokenizer(matchVersion, reader);
TokenStream result = new StandardFilter(matchVersion, source);
result = new LowerCaseFilter(matchVersion, result);
result = new StopFilter(matchVersion, result, stopwords);
if (stemExclusionSet.Count > 0)
{
result = new SetKeywordMarkerFilter(result, stemExclusionSet);
}
result = new SnowballFilter(result, new Tartarus.Snowball.Ext.RussianStemmer());
return new TokenStreamComponents(source, result);
}
else
{
#pragma warning disable 612, 618
Tokenizer source = new RussianLetterTokenizer(matchVersion, reader);
#pragma warning restore 612, 618
TokenStream result = new LowerCaseFilter(matchVersion, source);
result = new StopFilter(matchVersion, result, stopwords);
if (stemExclusionSet.Count > 0)
{
result = new SetKeywordMarkerFilter(result, stemExclusionSet);
}
result = new SnowballFilter(result, new Tartarus.Snowball.Ext.RussianStemmer());
return new TokenStreamComponents(source, result);
}
}
/// <summary>
/// Returns a (possibly reused) <seealso cref="TokenStream"/> which tokenizes all the
/// text in the provided <seealso cref="Reader"/>.
/// </summary>
/// <returns> A <seealso cref="TokenStream"/> built from a <seealso cref="StandardTokenizer"/>
/// filtered with <seealso cref="StandardFilter"/>, <seealso cref="LowerCaseFilter"/>,
/// <seealso cref="StopFilter"/>, <seealso cref="SetKeywordMarkerFilter"/> if a stem exclusion set is provided,
/// <seealso cref="StemmerOverrideFilter"/>, and <seealso cref="SnowballFilter"/> </returns>
public override TokenStreamComponents CreateComponents(string fieldName, TextReader aReader)
{
#pragma warning disable 612, 618
if (matchVersion.OnOrAfter(LuceneVersion.LUCENE_31))
#pragma warning restore 612, 618
{
Tokenizer source = new StandardTokenizer(matchVersion, aReader);
TokenStream result = new StandardFilter(matchVersion, source);
result = new LowerCaseFilter(matchVersion, result);
result = new StopFilter(matchVersion, result, stoptable);
if (excltable.Count > 0)
{
result = new SetKeywordMarkerFilter(result, excltable);
}
if (stemdict != null)
{
result = new StemmerOverrideFilter(result, stemdict);
}
result = new SnowballFilter(result, new Tartarus.Snowball.Ext.DutchStemmer());
return new TokenStreamComponents(source, result);
}
else
{
Tokenizer source = new StandardTokenizer(matchVersion, aReader);
TokenStream result = new StandardFilter(matchVersion, source);
result = new StopFilter(matchVersion, result, stoptable);
if (excltable.Count > 0)
{
result = new SetKeywordMarkerFilter(result, excltable);
}
#pragma warning disable 612, 618
result = new DutchStemFilter(result, origStemdict);
#pragma warning restore 612, 618
return new TokenStreamComponents(source, result);
}
}
public override TokenStream TokenStream (string fieldName, TextReader reader)
{
TokenStream outstream;
outstream = base.TokenStream (fieldName, reader);
outstream = new NoiseEmailHostFilter (outstream, true);
outstream = new SnowballFilter (outstream, "English");
return outstream;
}
/// <summary>
/// Constructs a <seealso cref="StandardTokenizer"/> filtered by a {@link
/// StandardFilter}, a <seealso cref="LowerCaseFilter"/>, a <seealso cref="StopFilter"/>,
/// and a <seealso cref="SnowballFilter"/>
/// </summary>
public override TokenStreamComponents CreateComponents(string fieldName, TextReader reader)
{
Tokenizer tokenizer = new StandardTokenizer(matchVersion, reader);
TokenStream result = new StandardFilter(matchVersion, tokenizer);
// remove the possessive 's for english stemmers
if (matchVersion.OnOrAfter(LuceneVersion.LUCENE_31) && (name.Equals("English") || name.Equals("Porter") || name.Equals("Lovins")))
{
result = new EnglishPossessiveFilter(result);
}
// Use a special lowercase filter for turkish, the stemmer expects it.
if (matchVersion.OnOrAfter(LuceneVersion.LUCENE_31) && name.Equals("Turkish"))
{
result = new TurkishLowerCaseFilter(result);
}
else
{
result = new LowerCaseFilter(matchVersion, result);
}
if (stopSet != null)
{
result = new StopFilter(matchVersion, result, stopSet);
}
result = new SnowballFilter(result, name);
return new TokenStreamComponents(tokenizer, result);
}
/// <summary>
/// Creates a
/// <seealso cref="org.apache.lucene.analysis.Analyzer.TokenStreamComponents"/>
/// which tokenizes all the text in the provided <seealso cref="Reader"/>.
/// </summary>
/// <returns> A
/// <seealso cref="org.apache.lucene.analysis.Analyzer.TokenStreamComponents"/>
/// built from an <seealso cref="StandardTokenizer"/> filtered with
/// <seealso cref="StandardFilter"/>, <seealso cref="ElisionFilter"/>, <seealso cref="LowerCaseFilter"/>, <seealso cref="StopFilter"/>
/// , <seealso cref="SetKeywordMarkerFilter"/> if a stem exclusion set is
/// provided and <seealso cref="ItalianLightStemFilter"/>. </returns>
public override TokenStreamComponents CreateComponents(string fieldName, TextReader reader)
{
Tokenizer source = new StandardTokenizer(matchVersion, reader);
TokenStream result = new StandardFilter(matchVersion, source);
#pragma warning disable 612, 618
if (matchVersion.OnOrAfter(LuceneVersion.LUCENE_32))
#pragma warning restore 612, 618
{
result = new ElisionFilter(result, DEFAULT_ARTICLES);
}
result = new LowerCaseFilter(matchVersion, result);
result = new StopFilter(matchVersion, result, stopwords);
if (stemExclusionSet.Count > 0)
{
result = new SetKeywordMarkerFilter(result, stemExclusionSet);
}
#pragma warning disable 612, 618
if (matchVersion.OnOrAfter(LuceneVersion.LUCENE_36))
#pragma warning restore 612, 618
{
result = new ItalianLightStemFilter(result);
}
else
{
result = new SnowballFilter(result, new ItalianStemmer());
}
return new TokenStreamComponents(source, result);
}
public virtual void TestFilterTokens()
{
Token tok = new Token("accents", 2, 7, "wrd");
tok.SetPositionIncrement(3);
SnowballFilter filter = new SnowballFilter(new AnonymousClassTokenStream(tok, this), "English");
Token newtok = filter.Next();
Assert.AreEqual("accent", newtok.TermText());
Assert.AreEqual(2, newtok.StartOffset());
Assert.AreEqual(7, newtok.EndOffset());
Assert.AreEqual("wrd", newtok.Type());
Assert.AreEqual(3, newtok.GetPositionIncrement());
}
public virtual void TestFilterTokens()
{
SnowballFilter filter = new SnowballFilter(new TestTokenStream(this), "English");
ICharTermAttribute termAtt = filter.GetAttribute<ICharTermAttribute>();
IOffsetAttribute offsetAtt = filter.GetAttribute<IOffsetAttribute>();
ITypeAttribute typeAtt = filter.GetAttribute<ITypeAttribute>();
IPayloadAttribute payloadAtt = filter.GetAttribute<IPayloadAttribute>();
IPositionIncrementAttribute posIncAtt = filter.GetAttribute<IPositionIncrementAttribute>();
IFlagsAttribute flagsAtt = filter.GetAttribute<IFlagsAttribute>();
filter.IncrementToken();
assertEquals("accent", termAtt.ToString());
assertEquals(2, offsetAtt.StartOffset());
assertEquals(7, offsetAtt.EndOffset());
assertEquals("wrd", typeAtt.Type);
assertEquals(3, posIncAtt.PositionIncrement);
assertEquals(77, flagsAtt.Flags);
assertEquals(new BytesRef(new byte[] { 0, 1, 2, 3 }), payloadAtt.Payload);
}
