public DutchAnalyzer(LuceneVersion 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)); #pragma warning disable 612, 618 if (stemOverrideDict.Count == 0 || !matchVersion.OnOrAfter(LuceneVersion.LUCENE_31)) #pragma warning restore 612, 618 { 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 = (CharArrayMap <string> .EntryIterator)stemOverrideDict.EntrySet().GetEnumerator(); CharsRef spare = new CharsRef(); while (iter.HasNext) { char[] nextKey = iter.NextKey(); spare.CopyChars(nextKey, 0, nextKey.Length); builder.Add(new string(spare.Chars), 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(); } } }