| /* |
| * 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. |
| */ |
| package org.apache.lucene.analysis.util; |
| |
| |
| import java.io.IOException; |
| import java.util.Map; |
| |
| import org.apache.lucene.analysis.CharArraySet; |
| import org.apache.lucene.analysis.TokenStream; |
| import org.apache.lucene.analysis.fr.FrenchAnalyzer; |
| |
| /** |
| * Factory for {@link ElisionFilter}. |
| * <pre class="prettyprint"> |
| * <fieldType name="text_elsn" class="solr.TextField" positionIncrementGap="100"> |
| * <analyzer> |
| * <tokenizer class="solr.StandardTokenizerFactory"/> |
| * <filter class="solr.LowerCaseFilterFactory"/> |
| * <filter class="solr.ElisionFilterFactory" |
| * articles="stopwordarticles.txt" ignoreCase="true"/> |
| * </analyzer> |
| * </fieldType></pre> |
| * |
| * @since 3.1 |
| * @lucene.spi {@value #NAME} |
| */ |
| public class ElisionFilterFactory extends TokenFilterFactory implements ResourceLoaderAware { |
| |
| /** SPI name */ |
| public static final String NAME = "elision"; |
| |
| private final String articlesFile; |
| private final boolean ignoreCase; |
| private CharArraySet articles; |
| |
| /** Creates a new ElisionFilterFactory */ |
| public ElisionFilterFactory(Map<String,String> args) { |
| super(args); |
| articlesFile = get(args, "articles"); |
| ignoreCase = getBoolean(args, "ignoreCase", false); |
| if (!args.isEmpty()) { |
| throw new IllegalArgumentException("Unknown parameters: " + args); |
| } |
| } |
| |
| @Override |
| public void inform(ResourceLoader loader) throws IOException { |
| if (articlesFile == null) { |
| articles = FrenchAnalyzer.DEFAULT_ARTICLES; |
| } else { |
| articles = getWordSet(loader, articlesFile, ignoreCase); |
| } |
| } |
| |
| @Override |
| public TokenStream create(TokenStream input) { |
| return new ElisionFilter(input, articles); |
| } |
| |
| @Override |
| public TokenStream normalize(TokenStream input) { |
| return create(input); |
| } |
| } |
| |