/// <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="LowerCaseFilter"/>, <see cref="ThaiWordFilter"/>, and
/// <see cref="StopFilter"/> </returns>
protected internal override TokenStreamComponents CreateComponents(string fieldName, TextReader reader)
{
if (m_matchVersion.OnOrAfter(LuceneVersion.LUCENE_48))
{
Tokenizer source = new ThaiTokenizer(reader);
TokenStream result = new LowerCaseFilter(m_matchVersion, source);
result = new StopFilter(m_matchVersion, result, m_stopwords);
return(new TokenStreamComponents(source, result));
}
else
{
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_31))
#pragma warning restore 612, 618
{
result = new LowerCaseFilter(m_matchVersion, result);
}
#pragma warning disable 612, 618
result = new ThaiWordFilter(m_matchVersion, result);
#pragma warning restore 612, 618
return(new TokenStreamComponents(source, new StopFilter(m_matchVersion, result, m_stopwords)));
}
}
public override TokenStream TokenStream(String fieldName, TextReader reader)
{
TokenStream ts = new StandardTokenizer(matchVersion, reader);
ts = new StandardFilter(ts);
ts = new ThaiWordFilter(ts);
ts = new StopFilter(StopFilter.GetEnablePositionIncrementsVersionDefault(matchVersion),
ts, StopAnalyzer.ENGLISH_STOP_WORDS_SET);
return ts;
}
public override TokenStream TokenStream(String fieldName, TextReader reader)
{
TokenStream ts = new StandardTokenizer(matchVersion, reader);
ts = new StandardFilter(ts);
ts = new ThaiWordFilter(ts);
ts = new StopFilter(StopFilter.GetEnablePositionIncrementsVersionDefault(matchVersion),
ts, StopAnalyzer.ENGLISH_STOP_WORDS_SET);
return(ts);
}
/// <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="ThaiWordFilter"/>, and
/// <seealso cref="StopFilter"/> </returns>
public override TokenStreamComponents CreateComponents(string fieldName, TextReader reader)
{
if (matchVersion.OnOrAfter(LuceneVersion.LUCENE_48))
{
Tokenizer source = new ThaiTokenizer(reader);
TokenStream result = new LowerCaseFilter(matchVersion, source);
result = new StopFilter(matchVersion, result, stopwords);
return(new TokenStreamComponents(source, result));
}
else
{
Tokenizer source = new StandardTokenizer(matchVersion, reader);
TokenStream result = new StandardFilter(matchVersion, source);
if (matchVersion.OnOrAfter(LuceneVersion.LUCENE_31))
{
result = new LowerCaseFilter(matchVersion, result);
}
result = new ThaiWordFilter(matchVersion, result);
return(new TokenStreamComponents(source, new StopFilter(matchVersion, result, stopwords)));
}
}