/// <summary>
/// Creates
/// <see cref="Analyzer.TokenStreamComponents"/>
/// used to tokenize all the text in the provided <see cref="TextReader"/>.
/// </summary>
/// <returns> <see cref="Analyzer.TokenStreamComponents"/>
/// built from a <see cref="StandardTokenizer"/> filtered with
/// <see cref="LowerCaseFilter"/>, <see cref="IndicNormalizationFilter"/>,
/// <see cref="HindiNormalizationFilter"/>, <see cref="SetKeywordMarkerFilter"/>
/// if a stem exclusion set is provided, <see cref="HindiStemFilter"/>, and
/// Hindi Stop words </returns>
protected override TokenStreamComponents CreateComponents(string fieldName, TextReader reader)
{
Tokenizer source;
#pragma warning disable 612, 618
if (m_matchVersion.OnOrAfter(LuceneVersion.LUCENE_36))
{
source = new StandardTokenizer(m_matchVersion, reader);
}
else
{
source = new IndicTokenizer(m_matchVersion, reader);
}
#pragma warning restore 612, 618
TokenStream result = new LowerCaseFilter(m_matchVersion, source);
if (stemExclusionSet.Count > 0)
{
result = new SetKeywordMarkerFilter(result, stemExclusionSet);
}
result = new IndicNormalizationFilter(result);
result = new HindiNormalizationFilter(result);
result = new StopFilter(m_matchVersion, result, m_stopwords);
result = new HindiStemFilter(result);
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="IndicNormalizationFilter"/>,
/// <seealso cref="HindiNormalizationFilter"/>, <seealso cref="SetKeywordMarkerFilter"/>
/// if a stem exclusion set is provided, <seealso cref="HindiStemFilter"/>, and
/// Hindi Stop words </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;
Tokenizer source;
if (matchVersion.onOrAfter(Version.LUCENE_36))
{
source = new StandardTokenizer(matchVersion, reader);
}
else
{
source = new IndicTokenizer(matchVersion, reader);
}
TokenStream result = new LowerCaseFilter(matchVersion, source);
if (!stemExclusionSet.Empty)
{
result = new SetKeywordMarkerFilter(result, stemExclusionSet);
}
result = new IndicNormalizationFilter(result);
result = new HindiNormalizationFilter(result);
result = new StopFilter(matchVersion, result, stopwords);
result = new HindiStemFilter(result);
return(new TokenStreamComponents(source, result));
}
private void check(string input, string output)
{
Tokenizer tokenizer = new MockTokenizer(new StringReader(input), MockTokenizer.WHITESPACE, false);
TokenFilter tf = new IndicNormalizationFilter(tokenizer);
AssertTokenStreamContents(tf, new string[] { output });
}