/// <summary>
/// Creates a
/// <see cref="TokenStreamComponents"/>
/// which tokenizes all the text in the provided <see cref="TextReader"/>.
/// </summary>
/// <returns> A
/// <see cref="TokenStreamComponents"/>
/// built from an <see cref="StandardTokenizer"/> filtered with
/// <see cref="StandardFilter"/>, <see cref="ElisionFilter"/>, <see cref="LowerCaseFilter"/>, <see cref="StopFilter"/>,
/// <see cref="SetKeywordMarkerFilter"/> if a stem exclusion set is
/// provided and <see cref="ItalianLightStemFilter"/>. </returns>
protected internal override TokenStreamComponents CreateComponents(string fieldName, TextReader reader)
{
Tokenizer source = new StandardTokenizer(m_matchVersion, reader);
TokenStream result = new StandardFilter(m_matchVersion, source);
#pragma warning disable 612, 618
if (m_matchVersion.OnOrAfter(LuceneVersion.LUCENE_32))
#pragma warning restore 612, 618
{
result = new ElisionFilter(result, DEFAULT_ARTICLES);
}
result = new LowerCaseFilter(m_matchVersion, result);
result = new StopFilter(m_matchVersion, result, m_stopwords);
if (stemExclusionSet.Count > 0)
{
result = new SetKeywordMarkerFilter(result, stemExclusionSet);
}
#pragma warning disable 612, 618
if (m_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));
}
/// <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>
protected internal override TokenStreamComponents createComponents(string fieldName, Reader reader)
{
//JAVA TO C# CONVERTER WARNING: The original Java variable was marked 'final':
//ORIGINAL LINE: final org.apache.lucene.analysis.Tokenizer source = new org.apache.lucene.analysis.standard.StandardTokenizer(matchVersion, reader);
Tokenizer source = new StandardTokenizer(matchVersion, reader);
TokenStream result = new StandardFilter(matchVersion, source);
if (matchVersion.onOrAfter(Version.LUCENE_32))
{
result = new ElisionFilter(result, DEFAULT_ARTICLES);
}
result = new LowerCaseFilter(matchVersion, result);
result = new StopFilter(matchVersion, result, stopwords);
if (!stemExclusionSet.Empty)
{
result = new SetKeywordMarkerFilter(result, stemExclusionSet);
}
if (matchVersion.onOrAfter(Version.LUCENE_36))
{
result = new ItalianLightStemFilter(result);
}
else
{
result = new SnowballFilter(result, new ItalianStemmer());
}
return(new TokenStreamComponents(source, result));
}
public virtual void TestElision_()
{
string test = "Plop, juste pour voir l'embrouille avec O'brian. M'enfin.";
Tokenizer tokenizer = new StandardTokenizer(TEST_VERSION_CURRENT, new StringReader(test));
CharArraySet articles = new CharArraySet(TEST_VERSION_CURRENT, AsSet("l", "M"), false);
TokenFilter filter = new ElisionFilter(tokenizer, articles);
IList<string> tas = Filter(filter);
assertEquals("embrouille", tas[4]);
assertEquals("O'brian", tas[6]);
assertEquals("enfin", tas[7]);
}
protected override TokenStreamComponents CreateComponents(string fieldName, TextReader reader)
{
Tokenizer source = new StandardTokenizer(Lucene.Net.Util.LuceneVersion.LUCENE_48, reader);
TokenStream result = new StandardFilter(Lucene.Net.Util.LuceneVersion.LUCENE_48, source);
result = new ElisionFilter(result, _defaultArticles);
result = new LowerCaseFilter(Lucene.Net.Util.LuceneVersion.LUCENE_48, result);
result = new StopFilter(Lucene.Net.Util.LuceneVersion.LUCENE_48, result, _defaultStopwords);
result = new PermutermTokenFilter(result);
return(new TokenStreamComponents(source, result));
}
//JAVA TO C# CONVERTER WARNING: Method 'throws' clauses are not available in .NET:
//ORIGINAL LINE: public void testElision() throws Exception
public virtual void testElision()
{
string test = "Plop, juste pour voir l'embrouille avec O'brian. M'enfin.";
Tokenizer tokenizer = new StandardTokenizer(TEST_VERSION_CURRENT, new StringReader(test));
CharArraySet articles = new CharArraySet(TEST_VERSION_CURRENT, asSet("l", "M"), false);
TokenFilter filter = new ElisionFilter(tokenizer, articles);
IList <string> tas = filter(filter);
assertEquals("embrouille", tas[4]);
assertEquals("O'brian", tas[6]);
assertEquals("enfin", tas[7]);
}
public void TestElision2()
{
String test = "Plop, juste pour voir l'embrouille avec O'brian. M'enfin.";
Tokenizer tokenizer = new StandardTokenizer(Version.LUCENE_CURRENT, new StringReader(test));
HashSet <String> articles = new HashSet <String>();
articles.Add("l");
articles.Add("M");
TokenFilter filter = new ElisionFilter(tokenizer, articles);
List <string> tas = Filtre(filter);
Assert.AreEqual("embrouille", tas[4]);
Assert.AreEqual("O'brian", tas[6]);
Assert.AreEqual("enfin", tas[7]);
}
/// <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="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_36))
{
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);
}
result = new SnowballFilter(result, new CatalanStemmer());
return(new TokenStreamComponents(source, result));
}
/// <summary>
/// Creates
/// <see cref="TokenStreamComponents"/>
/// used to tokenize all the text in the provided <see cref="TextReader"/>.
/// </summary>
/// <returns> <see cref="TokenStreamComponents"/>
/// built from a <see cref="StandardTokenizer"/> filtered with
/// <see cref="StandardFilter"/>, <see cref="ElisionFilter"/>,
/// <see cref="LowerCaseFilter"/>, <see cref="StopFilter"/>,
/// <see cref="SetKeywordMarkerFilter"/> if a stem exclusion set is
/// provided, and <see cref="FrenchLightStemFilter"/> </returns>
///
protected internal override TokenStreamComponents CreateComponents(string fieldName, TextReader reader)
{
#pragma warning disable 612, 618
if (m_matchVersion.OnOrAfter(LuceneVersion.LUCENE_31))
#pragma warning restore 612, 618
{
Tokenizer source = new StandardTokenizer(m_matchVersion, reader);
TokenStream result = new StandardFilter(m_matchVersion, source);
result = new ElisionFilter(result, DEFAULT_ARTICLES);
result = new LowerCaseFilter(m_matchVersion, result);
result = new StopFilter(m_matchVersion, result, m_stopwords);
if (excltable.Count > 0)
{
result = new SetKeywordMarkerFilter(result, excltable);
}
#pragma warning disable 612, 618
if (m_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(m_matchVersion, reader);
TokenStream result = new StandardFilter(m_matchVersion, source);
result = new StopFilter(m_matchVersion, result, m_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(m_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="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);
if (!matchVersion.OnOrAfter(LuceneVersion.LUCENE_44))
{
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 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="SnowballFilter"/>. </returns>
protected internal override TokenStreamComponents createComponents(string fieldName, Reader reader)
{
//JAVA TO C# CONVERTER WARNING: The original Java variable was marked 'final':
//ORIGINAL LINE: final org.apache.lucene.analysis.Tokenizer source = new org.apache.lucene.analysis.standard.StandardTokenizer(matchVersion, reader);
Tokenizer source = new StandardTokenizer(matchVersion, reader);
TokenStream result = new StandardFilter(matchVersion, source);
if (matchVersion.onOrAfter(Version.LUCENE_36))
{
result = new ElisionFilter(result, DEFAULT_ARTICLES);
}
result = new LowerCaseFilter(matchVersion, result);
result = new StopFilter(matchVersion, result, stopwords);
if (!stemExclusionSet.Empty)
{
result = new SetKeywordMarkerFilter(result, stemExclusionSet);
}
result = new SnowballFilter(result, new CatalanStemmer());
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="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
/// <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>
protected internal override TokenStreamComponents createComponents(string fieldName, Reader reader)
{
if (matchVersion.onOrAfter(Version.LUCENE_31))
{
//JAVA TO C# CONVERTER WARNING: The original Java variable was marked 'final':
//ORIGINAL LINE: final org.apache.lucene.analysis.Tokenizer source = new org.apache.lucene.analysis.standard.StandardTokenizer(matchVersion, reader);
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.Empty)
{
result = new SetKeywordMarkerFilter(result, excltable);
}
if (matchVersion.onOrAfter(Version.LUCENE_36))
{
result = new FrenchLightStemFilter(result);
}
else
{
result = new SnowballFilter(result, new org.tartarus.snowball.ext.FrenchStemmer());
}
return new TokenStreamComponents(source, result);
}
else
{
//JAVA TO C# CONVERTER WARNING: The original Java variable was marked 'final':
//ORIGINAL LINE: final org.apache.lucene.analysis.Tokenizer source = new org.apache.lucene.analysis.standard.StandardTokenizer(matchVersion, reader);
Tokenizer source = new StandardTokenizer(matchVersion, reader);
TokenStream result = new StandardFilter(matchVersion, source);
result = new StopFilter(matchVersion, result, stopwords);
if (!excltable.Empty)
{
result = new SetKeywordMarkerFilter(result, excltable);
}
result = new FrenchStemFilter(result);
// Convert to lowercase after stemming!
return new TokenStreamComponents(source, new LowerCaseFilter(matchVersion, result));
}
}
