/*
* Reads a stemdictionary file , that overrules the stemming algorithm
* This is a textfile that contains per line
* <tt>word<b>\t</b>stem</tt>, i.e: two tab seperated words
*/
public void SetStemDictionary(FileInfo stemdictFile)
{
try
{
stemdict = WordlistLoader.GetStemDict(stemdictFile);
PreviousTokenStream = null; // force a new stemmer to be created
}
catch (IOException e)
{
// TODO: throw IOException
throw new Exception(string.Empty, e);
}
}
/*
* Builds an exclusionlist from the words contained in the given file.
* @deprecated use {@link #DutchAnalyzer(Version, Set, Set)} instead
*/
public void SetStemExclusionTable(FileInfo exclusionlist)
{
try
{
excltable = WordlistLoader.GetWordSet(exclusionlist);
PreviousTokenStream = null; // force a new stemmer to be created
}
catch (IOException e)
{
// TODO: throw IOException
throw new Exception("", e);
}
}
/*
* Builds an analyzer with the given stop words.
*
* @param stopwords
* @deprecated use {@link #DutchAnalyzer(Version, Set)} instead
*/
public DutchAnalyzer(Version matchVersion, FileInfo stopwords)
{
// this is completely broken!
SetOverridesTokenStreamMethod <DutchAnalyzer>();
try
{
stoptable = WordlistLoader.GetWordSet(stopwords);
}
catch (IOException e)
{
// TODO: throw IOException
throw new Exception("", e);
}
this.matchVersion = matchVersion;
}
private static CharArraySet LoadDefaultStopSet() // LUCENENET: Avoid static constructors (see https://github.com/apache/lucenenet/pull/224#issuecomment-469284006)
{
try
{
return(WordlistLoader.GetSnowballWordSet(
IOUtils.GetDecodingReader(typeof(SnowballFilter), DEFAULT_STOPWORD_FILE, Encoding.UTF8),
#pragma warning disable 612, 618
LuceneVersion.LUCENE_CURRENT));
#pragma warning restore 612, 618
}
catch (IOException ex)
{
// default set should always be present as it is part of the
// distribution (JAR)
throw new Exception("Unable to load default stopword set", ex);
}
}
static DefaultSetHolder()
{
try
{
DEFAULT_STOP_SET = WordlistLoader.GetSnowballWordSet(
IOUtils.GetDecodingReader(typeof(SnowballFilter), typeof(SnowballFilter).Namespace + "." + DEFAULT_STOPWORD_FILE, Encoding.UTF8),
LuceneVersion.LUCENE_CURRENT);
}
catch (IOException)
{
// default set should always be present as it is part of the
// distribution (JAR)
throw new Exception("Unable to load default stopword set");
}
DEFAULT_STEM_DICT = new CharArrayMap <string>(LuceneVersion.LUCENE_CURRENT, 4, false);
DEFAULT_STEM_DICT.Put("fiets", "fiets"); //otherwise fiet
DEFAULT_STEM_DICT.Put("bromfiets", "bromfiets"); //otherwise bromfiet
DEFAULT_STEM_DICT.Put("ei", "eier");
DEFAULT_STEM_DICT.Put("kind", "kinder");
}
/// <summary>
/// Reads a stemdictionary file , that overrules the stemming algorithm
/// This is a textfile that contains per line
/// word\tstem
/// i.e: tabseperated
/// </summary>
/// <param name="stemdict"></param>
public void SetStemDictionary(FileInfo stemdict)
{
_stemdict = WordlistLoader.GetStemDict(stemdict);
}
/// <summary>
/// Builds an exclusionlist from the words contained in the given file.
/// </summary>
/// <param name="exclusionlist"></param>
public void SetStemExclusionTable(FileInfo exclusionlist)
{
excltable = WordlistLoader.GetWordtable(exclusionlist);
}
/// <summary>
/// Builds an analyzer with the given stop words.
/// </summary>
/// <param name="stopwords"></param>
public DutchAnalyzer(FileInfo stopwords)
{
stoptable = WordlistLoader.GetWordtable(stopwords);
}