Java tutorial
package edu.mit.ll.vizlincdb.document; /** * Licensed to the Apache Software Foundation (ASF) under one or more * contributor license agreements. See the NOTICE file distributed with * this work for additional information regarding copyright ownership. * The ASF licenses this file to You under the Apache License, Version 2.0 * (the "License"); you may not use this file except in compliance with * the License. You may obtain a copy of the License at * * http://www.apache.org/licenses/LICENSE-2.0 * * Unless required by applicable law or agreed to in writing, software * distributed under the License is distributed on an "AS IS" BASIS, * WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied. * See the License for the specific language governing permissions and * limitations under the License. */ import java.io.IOException; import java.io.Reader; import java.util.Set; import org.apache.lucene.analysis.ASCIIFoldingFilter; import org.apache.lucene.analysis.Analyzer; import org.apache.lucene.analysis.CharArraySet; import org.apache.lucene.analysis.KeywordMarkerFilter; import org.apache.lucene.analysis.LowerCaseFilter; import org.apache.lucene.analysis.StopFilter; import org.apache.lucene.analysis.StopwordAnalyzerBase; import org.apache.lucene.analysis.TokenStream; import org.apache.lucene.analysis.Tokenizer; import org.apache.lucene.analysis.WordlistLoader; import org.apache.lucene.analysis.es.SpanishLightStemFilter; import org.apache.lucene.analysis.snowball.SnowballFilter; import org.apache.lucene.analysis.standard.StandardFilter; import org.apache.lucene.analysis.standard.StandardTokenizer; import org.apache.lucene.util.IOUtils; import org.apache.lucene.util.Version; /** * {@link Analyzer} for Spanish; this is a slight variation on the Lucene SpanishAnalyzer which * folds accented characters into ASCII. * Unfortunately the SpanishAnalyzer is declared final so we have to copy the code. * <p> * <a name="version"/> * <p>You must specify the required {@link Version} * compatibility when creating FoldingSpanishAnalyzer: * <ul> * <li> As of 3.6, SpanishLightStemFilter is used for less aggressive stemming. * </ul> */ public final class FoldingSpanishAnalyzer extends StopwordAnalyzerBase { private final Set<?> stemExclusionSet; /** File containing default Spanish stopwords. */ public final static String DEFAULT_STOPWORD_FILE = "spanish_stop.txt"; /** * Returns an unmodifiable instance of the default stop words set. * @return default stop words set. */ public static Set<?> getDefaultStopSet() { return DefaultSetHolder.DEFAULT_STOP_SET; } /** * Atomically loads the DEFAULT_STOP_SET in a lazy fashion once the outer class * accesses the static final set the first time.; */ private static class DefaultSetHolder { static final Set<?> DEFAULT_STOP_SET; static { try { DEFAULT_STOP_SET = WordlistLoader.getSnowballWordSet(IOUtils.getDecodingReader(SnowballFilter.class, DEFAULT_STOPWORD_FILE, IOUtils.CHARSET_UTF_8), Version.LUCENE_CURRENT); } 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: {@link #DEFAULT_STOPWORD_FILE}. */ public FoldingSpanishAnalyzer(Version matchVersion) { this(matchVersion, DefaultSetHolder.DEFAULT_STOP_SET); } /** * Builds an analyzer with the given stop words. * * @param matchVersion lucene compatibility version * @param stopwords a stopword set */ public FoldingSpanishAnalyzer(Version matchVersion, Set<?> stopwords) { this(matchVersion, stopwords, CharArraySet.EMPTY_SET); } /** * Builds an analyzer with the given stop words. If a non-empty stem exclusion set is * provided this analyzer will add a {@link KeywordMarkerFilter} before * stemming. * * @param matchVersion lucene compatibility version * @param stopwords a stopword set * @param stemExclusionSet a set of terms not to be stemmed */ public FoldingSpanishAnalyzer(Version matchVersion, Set<?> stopwords, Set<?> stemExclusionSet) { super(matchVersion, stopwords); this.stemExclusionSet = CharArraySet.unmodifiableSet(CharArraySet.copy(matchVersion, stemExclusionSet)); } /** * Creates a * {@link org.apache.lucene.analysis.ReusableAnalyzerBase.TokenStreamComponents} * which tokenizes all the text in the provided {@link Reader}. * * @return A * {@link org.apache.lucene.analysis.ReusableAnalyzerBase.TokenStreamComponents} * built from an {@link StandardTokenizer} filtered with * {@link StandardFilter}, {@link LowerCaseFilter}, {@link StopFilter} * , {@link KeywordMarkerFilter} if a stem exclusion set is * provided and {@link SpanishLightStemFilter}. */ @Override protected TokenStreamComponents createComponents(String fieldName, Reader reader) { final Tokenizer source = new StandardTokenizer(matchVersion, reader); TokenStream result = new StandardFilter(matchVersion, source); result = new LowerCaseFilter(matchVersion, result); // result = new StopFilter(matchVersion, result, stopwords); if (!stemExclusionSet.isEmpty()) result = new KeywordMarkerFilter(result, stemExclusionSet); // SpanishLightStemFilter is used by default in Lucene 3.6.1 instead of the Snowball stemmer. // Neo4J is using 3.5.0. There is no difference between the stemming code in 3.5.0 and 3.6.1 so just use // the newer choice. // Do not stem, because it's not very interesting to stem people, locations, organizations etc. //result = new SpanishLightStemFilter(result); result = new ASCIIFoldingFilter(result); return new TokenStreamComponents(source, result); } }