+ * Supports an external list of stopwords (words + * that will not be indexed at all). + * A default set of stopwords is used unless an alternative list is specified. + *
+ * + * + *You must specify the required {@link Version} + * compatibility when creating GreekAnalyzer: + *
NOTE: This class uses the same {@link Version} + * dependent settings as {@link StandardAnalyzer}.
+ */ +public final class GreekAnalyzer extends StopwordAnalyzerBase { + /** File containing default Greek stopwords. */ + public final static String DEFAULT_STOPWORD_FILE = "stopwords.txt"; + + /** + * Returns a set of default Greek-stopwords + * @return a set of default Greek-stopwords + */ + public static final Set getDefaultStopSet(){ + return DefaultSetHolder.DEFAULT_SET; + } + + private static class DefaultSetHolder { + private static final Set DEFAULT_SET; + + static { + try { + DEFAULT_SET = loadStopwordSet(false, GreekAnalyzer.class, DEFAULT_STOPWORD_FILE, "#"); + } catch (IOException ex) { + // default set should always be present as it is part of the + // distribution (JAR) + throw new RuntimeException("Unable to load default stopword set"); + } + } + } + + /** + * Builds an analyzer with the default stop words. + * @param matchVersion Lucene compatibility version, + * See above + */ + public GreekAnalyzer(Version matchVersion) { + this(matchVersion, DefaultSetHolder.DEFAULT_SET); + } + + /** + * Builds an analyzer with the given stop words. + *+ * NOTE: The stopwords set should be pre-processed with the logic of + * {@link GreekLowerCaseFilter} for best results. + * + * @param matchVersion Lucene compatibility version, + * See above + * @param stopwords a stopword set + */ + public GreekAnalyzer(Version matchVersion, Set stopwords) { + super(matchVersion, stopwords); + } + + /** + * Builds an analyzer with the given stop words. + * @param stopwords Array of stopwords to use. + * @deprecated use {@link #GreekAnalyzer(Version, Set)} instead + */ + @Deprecated + public GreekAnalyzer(Version matchVersion, String... stopwords) { + this(matchVersion, StopFilter.makeStopSet(matchVersion, stopwords)); + } + + /** + * Builds an analyzer with the given stop words. + * @deprecated use {@link #GreekAnalyzer(Version, Set)} instead + */ + @Deprecated + public GreekAnalyzer(Version matchVersion, Map stopwords) { + this(matchVersion, stopwords.keySet()); + } + + /** + * Creates + * {@link org.apache.lucene.analysis.ReusableAnalyzerBase.TokenStreamComponents} + * used to tokenize all the text in the provided {@link Reader}. + * + * @return {@link org.apache.lucene.analysis.ReusableAnalyzerBase.TokenStreamComponents} + * built from a {@link StandardTokenizer} filtered with + * {@link GreekLowerCaseFilter}, {@link StandardFilter}, + * {@link StopFilter}, and {@link GreekStemFilter} + */ + @Override + protected TokenStreamComponents createComponents(String fieldName, + Reader reader) { + final Tokenizer source = new StandardTokenizer(matchVersion, reader); + TokenStream result = new GreekLowerCaseFilter(matchVersion, source); + if (matchVersion.onOrAfter(Version.LUCENE_31)) + result = new StandardFilter(matchVersion, result); + result = new StopFilter(matchVersion, result, stopwords); + if (matchVersion.onOrAfter(Version.LUCENE_31)) + result = new GreekStemFilter(result); + return new TokenStreamComponents(source, result); + } +}