protected internal override TokenStreamComponents CreateComponents(string fieldName)
{
StandardTokenizer src = new StandardTokenizer();
src.MaxTokenLength = DEFAULT_MAX_TOKEN_LENGTH;
TokenStream tok = new StandardFilter(src);
tok = new LowerCaseFilter(tok);
tok = new StopFilter(tok, stopwords);
tok = new ASCIIFoldingFilter(tok);
return(new TokenStreamComponents(src, tok));
}
/// <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>
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);
// prior to this we get the classic behavior, standardfilter does it for us.
if (matchVersion.onOrAfter(Version.LUCENE_31))
{
result = new EnglishPossessiveFilter(matchVersion, result);
}
result = new LowerCaseFilter(matchVersion, result);
result = new StopFilter(matchVersion, result, stopwords);
if (!stemExclusionSet.Empty)
{
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="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);
result = new LowerCaseFilter(matchVersion, result);
result = new StopFilter(matchVersion, result, stopwords);
if (!stemExclusionSet.Empty)
{
result = new SetKeywordMarkerFilter(result, stemExclusionSet);
}
result = new SnowballFilter(result, new DanishStemmer());
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="EnglishPossessiveFilter"/>,
/// <seealso cref="LowerCaseFilter"/>, <seealso cref="StopFilter"/>
/// , <seealso cref="SetKeywordMarkerFilter"/> if a stem exclusion set is
/// provided and <seealso cref="PorterStemFilter"/>. </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);
// prior to this we get the classic behavior, standardfilter does it for us.
if (matchVersion.onOrAfter(Version.LUCENE_31))
{
result = new EnglishPossessiveFilter(matchVersion, result);
}
result = new LowerCaseFilter(matchVersion, result);
result = new StopFilter(matchVersion, result, stopwords);
if (!stemExclusionSet.Empty)
{
result = new SetKeywordMarkerFilter(result, stemExclusionSet);
}
result = new PorterStemFilter(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="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>
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);
result = new LowerCaseFilter(matchVersion, result);
result = new StopFilter(matchVersion, result, stopwords);
result = new SetKeywordMarkerFilter(result, exclusionSet);
if (matchVersion.onOrAfter(Version.LUCENE_36))
{
result = new GermanNormalizationFilter(result);
result = new GermanLightStemFilter(result);
}
else if (matchVersion.onOrAfter(Version.LUCENE_31))
{
result = new SnowballFilter(result, new German2Stemmer());
}
else
{
result = new GermanStemFilter(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="IrishLowerCaseFilter"/>, <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);
StopFilter s = new StopFilter(matchVersion, result, HYPHENATIONS);
if (!matchVersion.onOrAfter(Version.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.Empty)
{
result = new SetKeywordMarkerFilter(result, stemExclusionSet);
}
result = new SnowballFilter(result, new IrishStemmer());
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>
protected internal override TokenStreamComponents createComponents(string fieldName, Reader aReader)
{
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, aReader);
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.Empty)
{
result = new SetKeywordMarkerFilter(result, excltable);
}
if (stemdict != null)
{
result = new StemmerOverrideFilter(result, stemdict);
}
result = new SnowballFilter(result, new org.tartarus.snowball.ext.DutchStemmer());
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, aReader);
Tokenizer source = new StandardTokenizer(matchVersion, aReader);
TokenStream result = new StandardFilter(matchVersion, source);
result = new StopFilter(matchVersion, result, stoptable);
if (!excltable.Empty)
{
result = new SetKeywordMarkerFilter(result, excltable);
}
result = new DutchStemFilter(result, origStemdict);
return new TokenStreamComponents(source, result);
}
}
/// <summary>
/// Not an explicit test, just useful to print out some info on performance
/// </summary>
//JAVA TO C# CONVERTER WARNING: Method 'throws' clauses are not available in .NET:
//ORIGINAL LINE: public void performance() throws Exception
public virtual void performance()
{
int[] tokCount = new int[] {100, 500, 1000, 2000, 5000, 10000};
int[] modCounts = new int[] {1, 2, 5, 10, 20, 50, 100, 200, 500};
for (int k = 0; k < tokCount.Length; k++)
{
StringBuilder buffer = new StringBuilder();
Console.WriteLine("-----Tokens: " + tokCount[k] + "-----");
for (int i = 0; i < tokCount[k]; i++)
{
buffer.Append(English.intToEnglish(i).toUpperCase(Locale.ROOT)).Append(' ');
}
//make sure we produce the same tokens
TeeSinkTokenFilter teeStream = new TeeSinkTokenFilter(new StandardFilter(TEST_VERSION_CURRENT, new StandardTokenizer(TEST_VERSION_CURRENT, new StringReader(buffer.ToString()))));
TokenStream sink = teeStream.newSinkTokenStream(new ModuloSinkFilter(this, 100));
teeStream.consumeAllTokens();
TokenStream stream = new ModuloTokenFilter(this, new StandardFilter(TEST_VERSION_CURRENT, new StandardTokenizer(TEST_VERSION_CURRENT, new StringReader(buffer.ToString()))), 100);
CharTermAttribute tfTok = stream.addAttribute(typeof(CharTermAttribute));
CharTermAttribute sinkTok = sink.addAttribute(typeof(CharTermAttribute));
for (int i = 0; stream.incrementToken(); i++)
{
assertTrue(sink.incrementToken());
assertTrue(tfTok + " is not equal to " + sinkTok + " at token: " + i, tfTok.Equals(sinkTok) == true);
}
//simulate two fields, each being analyzed once, for 20 documents
for (int j = 0; j < modCounts.Length; j++)
{
int tfPos = 0;
long start = DateTimeHelperClass.CurrentUnixTimeMillis();
for (int i = 0; i < 20; i++)
{
stream = new StandardFilter(TEST_VERSION_CURRENT, new StandardTokenizer(TEST_VERSION_CURRENT, new StringReader(buffer.ToString())));
PositionIncrementAttribute posIncrAtt = stream.getAttribute(typeof(PositionIncrementAttribute));
while (stream.incrementToken())
{
tfPos += posIncrAtt.PositionIncrement;
}
stream = new ModuloTokenFilter(this, new StandardFilter(TEST_VERSION_CURRENT, new StandardTokenizer(TEST_VERSION_CURRENT, new StringReader(buffer.ToString()))), modCounts[j]);
posIncrAtt = stream.getAttribute(typeof(PositionIncrementAttribute));
while (stream.incrementToken())
{
tfPos += posIncrAtt.PositionIncrement;
}
}
long finish = DateTimeHelperClass.CurrentUnixTimeMillis();
Console.WriteLine("ModCount: " + modCounts[j] + " Two fields took " + (finish - start) + " ms");
int sinkPos = 0;
//simulate one field with one sink
start = DateTimeHelperClass.CurrentUnixTimeMillis();
for (int i = 0; i < 20; i++)
{
teeStream = new TeeSinkTokenFilter(new StandardFilter(TEST_VERSION_CURRENT, new StandardTokenizer(TEST_VERSION_CURRENT, new StringReader(buffer.ToString()))));
sink = teeStream.newSinkTokenStream(new ModuloSinkFilter(this, modCounts[j]));
PositionIncrementAttribute posIncrAtt = teeStream.getAttribute(typeof(PositionIncrementAttribute));
while (teeStream.incrementToken())
{
sinkPos += posIncrAtt.PositionIncrement;
}
//System.out.println("Modulo--------");
posIncrAtt = sink.getAttribute(typeof(PositionIncrementAttribute));
while (sink.incrementToken())
{
sinkPos += posIncrAtt.PositionIncrement;
}
}
finish = DateTimeHelperClass.CurrentUnixTimeMillis();
Console.WriteLine("ModCount: " + modCounts[j] + " Tee fields took " + (finish - start) + " ms");
assertTrue(sinkPos + " does not equal: " + tfPos, sinkPos == tfPos);
}
Console.WriteLine("- End Tokens: " + tokCount[k] + "-----");
}
}
