public virtual void TestLowerCaseFilterLowSurrogateLeftover()
{
// test if the limit of the termbuffer is correctly used with supplementary
// chars
WhitespaceTokenizer tokenizer = new WhitespaceTokenizer(TEST_VERSION_CURRENT, new StringReader("BogustermBogusterm\udc16"));
LowerCaseFilter filter = new LowerCaseFilter(TEST_VERSION_CURRENT, tokenizer);
AssertTokenStreamContents(filter, new string[] { "bogustermbogusterm\udc16" });
filter.Reset();
string highSurEndingUpper = "BogustermBoguster\ud801";
string highSurEndingLower = "bogustermboguster\ud801";
tokenizer.SetReader(new StringReader(highSurEndingUpper));
AssertTokenStreamContents(filter, new string[] { highSurEndingLower });
assertTrue(filter.HasAttribute <ICharTermAttribute>());
char[] termBuffer = filter.GetAttribute <ICharTermAttribute>().Buffer;
int length = highSurEndingLower.Length;
assertEquals('\ud801', termBuffer[length - 1]);
}
public override TokenStreamComponents CreateComponents(string fieldName, TextReader reader)
{
Tokenizer source = new StandardTokenizer(TEST_VERSION_CURRENT, reader);
TokenStream result = new LowerCaseFilter(TEST_VERSION_CURRENT, source);
return new TokenStreamComponents(source, new PortugueseStemFilter(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>
/// 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="LowerCaseFilter"/>, <seealso cref="StandardFilter"/>, <seealso cref="StopFilter"/>
/// , and <seealso cref="BrazilianStemFilter"/>. </returns>
public override TokenStreamComponents CreateComponents(string fieldName, TextReader reader)
{
Tokenizer source = new StandardTokenizer(matchVersion, reader);
TokenStream result = new LowerCaseFilter(matchVersion, source);
result = new StandardFilter(matchVersion, result);
result = new StopFilter(matchVersion, result, stopwords);
if (excltable != null && excltable.Count > 0)
{
result = new SetKeywordMarkerFilter(result, excltable);
}
return new TokenStreamComponents(source, new BrazilianStemFilter(result));
}
public override TokenStreamComponents CreateComponents(string fieldName, Reader reader)
{
UAX29URLEmailTokenizer src = new UAX29URLEmailTokenizer(matchVersion, reader);
src.MaxTokenLength = maxTokenLength;
TokenStream tok = new StandardFilter(matchVersion, src);
tok = new LowerCaseFilter(matchVersion, tok);
tok = new StopFilter(matchVersion, tok, stopwords);
return new TokenStreamComponentsAnonymousInnerClassHelper(this, src, tok, reader);
}
/// <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="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>
/// 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);
}
public override TokenStreamComponents CreateComponents(string fieldName, TextReader reader)
{
#pragma warning disable 612, 618
if (matchVersion.OnOrAfter(LuceneVersion.LUCENE_36))
#pragma warning restore 612, 618
{
Tokenizer source = new StandardTokenizer(matchVersion, reader);
// run the widthfilter first before bigramming, it sometimes combines characters.
TokenStream result = new CJKWidthFilter(source);
result = new LowerCaseFilter(matchVersion, result);
result = new CJKBigramFilter(result);
return new TokenStreamComponents(source, new StopFilter(matchVersion, result, stopwords));
}
else
{
#pragma warning disable 612, 618
Tokenizer source = new CJKTokenizer(reader);
#pragma warning restore 612, 618
return new TokenStreamComponents(source, new StopFilter(matchVersion, source, stopwords));
}
}
public virtual void TestLowerCaseFilterLowSurrogateLeftover()
{
// test if the limit of the termbuffer is correctly used with supplementary
// chars
WhitespaceTokenizer tokenizer = new WhitespaceTokenizer(TEST_VERSION_CURRENT, new StringReader("BogustermBogusterm\udc16"));
LowerCaseFilter filter = new LowerCaseFilter(TEST_VERSION_CURRENT, tokenizer);
AssertTokenStreamContents(filter, new string[] { "bogustermbogusterm\udc16" });
filter.Reset();
string highSurEndingUpper = "BogustermBoguster\ud801";
string highSurEndingLower = "bogustermboguster\ud801";
tokenizer.Reader = new StringReader(highSurEndingUpper);
AssertTokenStreamContents(filter, new string[] { highSurEndingLower });
assertTrue(filter.HasAttribute<ICharTermAttribute>());
char[] termBuffer = filter.GetAttribute<ICharTermAttribute>().Buffer();
int length = highSurEndingLower.Length;
assertEquals('\ud801', termBuffer[length - 1]);
}
/// <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="EnglishPossessiveFilter"/>,
/// <seealso cref="LowerCaseFilter"/>, <seealso cref="StopFilter"/>
/// , <seealso cref="SetKeywordMarkerFilter"/> if a stem exclusion set is
/// provided and <seealso cref="PorterStemFilter"/>. </returns>
public override TokenStreamComponents CreateComponents(string fieldName, TextReader reader)
{
Tokenizer source = new StandardTokenizer(matchVersion, reader);
TokenStream result = new StandardFilter(matchVersion, source);
// prior to this we get the classic behavior, standardfilter does it for us.
#pragma warning disable 612, 618
if (matchVersion.OnOrAfter(LuceneVersion.LUCENE_31))
#pragma warning restore 612, 618
{
result = new EnglishPossessiveFilter(matchVersion, result);
}
result = new LowerCaseFilter(matchVersion, result);
result = new StopFilter(matchVersion, result, stopwords);
if (stemExclusionSet.Any())
{
result = new SetKeywordMarkerFilter(result, stemExclusionSet);
}
result = new PorterStemFilter(result);
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>
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);
}
//JAVA TO C# CONVERTER WARNING: 'final' parameters are not available in .NET:
//ORIGINAL LINE: @Override protected TokenStreamComponents createComponents(final String fieldName, final java.io.Reader reader)
protected internal override TokenStreamComponents createComponents(string fieldName, Reader reader)
{
//JAVA TO C# CONVERTER WARNING: The original Java variable was marked 'final':
//ORIGINAL LINE: final UAX29URLEmailTokenizer src = new UAX29URLEmailTokenizer(matchVersion, reader);
UAX29URLEmailTokenizer src = new UAX29URLEmailTokenizer(matchVersion, reader);
src.MaxTokenLength = maxTokenLength;
TokenStream tok = new StandardFilter(matchVersion, src);
tok = new LowerCaseFilter(matchVersion, tok);
tok = new StopFilter(matchVersion, tok, stopwords);
return new TokenStreamComponentsAnonymousInnerClassHelper(this, src, tok, reader);
}
/// <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 an <seealso cref="StandardTokenizer"/> filtered with
/// <seealso cref="LowerCaseFilter"/>, <seealso cref="StopFilter"/>,
/// <seealso cref="ArabicNormalizationFilter"/>, <seealso cref="SetKeywordMarkerFilter"/>
/// if a stem exclusion set is provided and <seealso cref="ArabicStemFilter"/>. </returns>
public override TokenStreamComponents CreateComponents(string fieldName, TextReader reader)
{
#pragma warning disable 612, 618
Tokenizer source = matchVersion.OnOrAfter(LuceneVersion.LUCENE_31)
? new StandardTokenizer(matchVersion, reader)
: (Tokenizer)new ArabicLetterTokenizer(matchVersion, reader);
#pragma warning restore 612, 618
TokenStream result = new LowerCaseFilter(matchVersion, source);
// the order here is important: the stopword list is not normalized!
result = new StopFilter(matchVersion, result, stopwords);
// TODO maybe we should make ArabicNormalization filter also KeywordAttribute aware?!
result = new ArabicNormalizationFilter(result);
if (stemExclusionSet.Count > 0)
{
result = new SetKeywordMarkerFilter(result, stemExclusionSet);
}
return new TokenStreamComponents(source, new ArabicStemFilter(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);
}
}
/// <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"/>
/// , and <seealso cref="CzechStemFilter"/> (only if version is >= LUCENE_31). If
/// a version is >= LUCENE_31 and a stem exclusion set is provided via
/// <seealso cref="#CzechAnalyzer(Version, CharArraySet, CharArraySet)"/> a
/// <seealso cref="SetKeywordMarkerFilter"/> is added before
/// <seealso cref="CzechStemFilter"/>. </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);
#pragma warning disable 612, 618
if (matchVersion.OnOrAfter(LuceneVersion.LUCENE_31))
#pragma warning restore 612, 618
{
if (this.stemExclusionTable.Any())
{
result = new SetKeywordMarkerFilter(result, stemExclusionTable);
}
result = new CzechStemFilter(result);
}
return new TokenStreamComponents(source, result);
}
