/* * Copyright (c) 2011 LinkedIn, Inc * * Licensed 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. */ package com.flaptor.indextank.query.analyzers; import java.util.HashSet; import java.util.Map; import java.util.Set; import org.apache.lucene.analysis.standard.StandardAnalyzer; import org.apache.lucene.util.Version; import org.json.simple.JSONArray; import com.google.common.collect.ImmutableSet; public abstract class StopAnalyzer extends StandardAnalyzer { private static final String STOPWORDS = "stopwords"; public StopAnalyzer(Map<Object, Object> analyzerConfiguration) { super(Version.LUCENE_CURRENT, getStopWords(analyzerConfiguration)); } private static Set<String> getStopWords(Map<Object, Object> analyzerConfiguration) { if (analyzerConfiguration.containsKey(STOPWORDS)) { JSONArray stopwordList = (JSONArray)analyzerConfiguration.get(STOPWORDS); Set<String> stopwords = new HashSet<String>(stopwordList.size()); for (Object stopword : stopwordList){ if ( !(stopword instanceof String) ) { throw new IllegalArgumentException("Stopwords aren't Strings"); } stopwords.add((String)stopword); } return stopwords; } else { return ImmutableSet.of(); } } }