/** * Creates a * {@link org.apache.lucene.analysis.Analyzer.TokenStreamComponents} * which tokenizes all the text in the provided {@link Reader}. * * @return A * {@link org.apache.lucene.analysis.Analyzer.TokenStreamComponents} * built from an {@link StandardTokenizer} filtered with * {@link LowerCaseFilter}, {@link StopFilter} * , {@link SetKeywordMarkerFilter} if a stem exclusion set is * provided and {@link SnowballFilter}. */ @Override protected TokenStreamComponents createComponents(String fieldName) { final Tokenizer source = new StandardTokenizer(); TokenStream result = new LowerCaseFilter(source); result = new StopFilter(result, stopwords); if(!stemExclusionSet.isEmpty()) result = new SetKeywordMarkerFilter(result, stemExclusionSet); result = new SnowballFilter(result, new NorwegianStemmer()); return new TokenStreamComponents(source, result); }
among_var = find_among_b(a_0, 29); if (among_var == 0) slice_del(); break; case 2: v_3 = limit - cursor; lab1: do { if (!(in_grouping_b(g_s_ending, 98, 122))) if (!(eq_s_b(1, "k"))) if (!(out_grouping_b(g_v, 97, 248))) slice_del(); break; case 3: slice_from("er"); break;
if (!(in_grouping(g_v, 97, 248))) if (!(out_grouping(g_v, 97, 248)))
lab0: do { if (!r_mark_regions()) lab1: do { if (!r_main_suffix()) lab2: do { if (!r_consonant_pair()) lab3: do { if (!r_other_suffix())
if (find_among_b(a_1, 2) == 0) slice_del(); return true;
lab0: do { if (!r_mark_regions()) lab1: do { if (!r_main_suffix()) lab2: do { if (!r_consonant_pair()) lab3: do { if (!r_other_suffix())
among_var = find_among_b(a_2, 11); if (among_var == 0) slice_del(); break;
among_var = find_among_b(a_0, 29); if (among_var == 0) slice_del(); break; case 2: v_3 = limit - cursor; lab1: do { if (!(in_grouping_b(g_s_ending, 98, 122))) if (!(eq_s_b(1, "k"))) if (!(out_grouping_b(g_v, 97, 248))) slice_del(); break; case 3: slice_from("er"); break;
public NorwegianSnowballStemmer() { super(new NorwegianStemmer()); } public Language getLanguage() { return Language.NORWEGIAN; }
lab0: do { if (!r_mark_regions()) lab1: do { if (!r_main_suffix()) lab2: do { if (!r_consonant_pair()) lab3: do { if (!r_other_suffix())
if (find_among_b(a_1, 2) == 0) slice_del(); return true;
if (!(in_grouping(g_v, 97, 248))) if (!(out_grouping(g_v, 97, 248)))
among_var = find_among_b(a_0, 29); if (among_var == 0) slice_del(); break; case 2: v_3 = limit - cursor; lab1: do { if (!(in_grouping_b(g_s_ending, 98, 122))) if (!(eq_s_b(1, "k"))) if (!(out_grouping_b(g_v, 97, 248))) slice_del(); break; case 3: slice_from("er"); break;
@Override public TokenStream apply(final TokenStream input) { return new SnowballFilter(input, new NorwegianStemmer()); } };
if (find_among_b(a_1, 2) == 0) slice_del(); return true;
if (!(in_grouping(g_v, 97, 248))) if (!(out_grouping(g_v, 97, 248)))
static public TokenStream norwegian(TokenStream result) { result = new LowerCaseFilter(result); result = new SnowballFilter(result, new NorwegianStemmer()); return result; }
among_var = find_among_b(a_2, 11); if (among_var == 0) slice_del(); break;
@Override public TokenStream getTokenStream(Tokenizer tokenizer, CharArraySet stemExclusionSet) { TokenStream stream = new StandardFilter(matchVersion, tokenizer); if (caseInsensitive) stream = new LowerCaseFilter(matchVersion, stream); if (useStopWords) stream = new StopFilter(matchVersion, stream, NorwegianAnalyzer.getDefaultStopSet()); if (useStem) { if (!stemExclusionSet.isEmpty()) stream = new SetKeywordMarkerFilter(stream, stemExclusionSet); stream = new SnowballFilter(stream, new NorwegianStemmer()); } return stream; } }
among_var = find_among_b(a_2, 11); if (among_var == 0) slice_del(); break;