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 virtual void Inform(ResourceLoader loader) { if (dictionaryFiles != null) { assureMatchVersion(); IList<string> files = splitFileNames(dictionaryFiles); if (files.Count > 0) { StemmerOverrideFilter.Builder builder = new StemmerOverrideFilter.Builder(ignoreCase); foreach (string file in files) { IList<string> list = getLines(loader, file.Trim()); foreach (string line in list) { string[] mapping = line.Split("\t", 2); builder.add(mapping[0], mapping[1]); } } dictionary = builder.build(); } } }