/// <summary>
/// Creates a new ThaiWordFilter with the specified match version. </summary>
public ThaiWordFilter(Version matchVersion, TokenStream input)
: base(matchVersion.onOrAfter(Version.LUCENE_31) ? input : new LowerCaseFilter(matchVersion, input))
{
if (!DBBI_AVAILABLE)
{
throw new System.NotSupportedException("This JRE does not have support for Thai segmentation");
}
handlePosIncr = matchVersion.onOrAfter(Version.LUCENE_31);
}
//JAVA TO C# CONVERTER WARNING: Method 'throws' clauses are not available in .NET:
//ORIGINAL LINE: @Override public final boolean incrementToken() throws java.io.IOException
public override bool incrementToken()
{
if (matchVersion.onOrAfter(Version.LUCENE_31))
{
return(input.incrementToken()); // TODO: add some niceties for the new grammar
}
else
{
return(incrementTokenClassic());
}
}
private StandardTokenizerInterface getScannerFor(Version matchVersion)
{
// best effort NPE if you dont call reset
if (matchVersion.onOrAfter(Version.LUCENE_47))
{
return(new UAX29URLEmailTokenizerImpl(input));
}
else if (matchVersion.onOrAfter(Version.LUCENE_40))
{
return(new UAX29URLEmailTokenizerImpl40(input));
}
else if (matchVersion.onOrAfter(Version.LUCENE_36))
{
return(new UAX29URLEmailTokenizerImpl36(input));
}
else if (matchVersion.onOrAfter(Version.LUCENE_34))
{
return(new UAX29URLEmailTokenizerImpl34(input));
}
else
{
return(new UAX29URLEmailTokenizerImpl31(input));
}
}
public RussianAnalyzer(Version matchVersion)
: this(matchVersion, matchVersion.onOrAfter(Version.LUCENE_31) ? DefaultSetHolder.DEFAULT_STOP_SET : DefaultSetHolder.DEFAULT_STOP_SET_30)
{
}
public DutchAnalyzer(Version matchVersion, CharArraySet stopwords, CharArraySet stemExclusionTable, CharArrayMap<string> stemOverrideDict)
{
this.matchVersion = matchVersion;
this.stoptable = CharArraySet.unmodifiableSet(CharArraySet.copy(matchVersion, stopwords));
this.excltable = CharArraySet.unmodifiableSet(CharArraySet.copy(matchVersion, stemExclusionTable));
if (stemOverrideDict.Empty || !matchVersion.onOrAfter(Version.LUCENE_31))
{
this.stemdict = null;
this.origStemdict = CharArrayMap.unmodifiableMap(CharArrayMap.copy(matchVersion, stemOverrideDict));
}
else
{
this.origStemdict = null;
// we don't need to ignore case here since we lowercase in this analyzer anyway
StemmerOverrideFilter.Builder builder = new StemmerOverrideFilter.Builder(false);
CharArrayMap<string>.EntryIterator iter = stemOverrideDict.entrySet().GetEnumerator();
CharsRef spare = new CharsRef();
while (iter.hasNext())
{
char[] nextKey = iter.nextKey();
spare.copyChars(nextKey, 0, nextKey.Length);
builder.add(spare, iter.currentValue());
}
try
{
this.stemdict = builder.build();
}
catch (IOException ex)
{
throw new Exception("can not build stem dict", ex);
}
}
}
public DutchAnalyzer(Version matchVersion, CharArraySet stopwords, CharArraySet stemExclusionTable)
: this(matchVersion, stopwords, stemExclusionTable, matchVersion.onOrAfter(Version.LUCENE_36) ? DefaultSetHolder.DEFAULT_STEM_DICT : CharArrayMap.emptyMap<string>())
{
// historically, this ctor never the stem dict!!!!!
// so we populate it only for >= 3.6
}
