| /* |
| * 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.phonetic; |
| |
| import java.util.Map; |
| import java.util.Set; |
| import org.apache.commons.codec.language.bm.Languages.LanguageSet; |
| import org.apache.commons.codec.language.bm.NameType; |
| import org.apache.commons.codec.language.bm.PhoneticEngine; |
| import org.apache.commons.codec.language.bm.RuleType; |
| import org.apache.lucene.analysis.TokenFilterFactory; |
| import org.apache.lucene.analysis.TokenStream; |
| |
| /** |
| * Factory for {@link BeiderMorseFilter}. |
| * |
| * <pre class="prettyprint"> |
| * <fieldType name="text_bm" class="solr.TextField" positionIncrementGap="100"> |
| * <analyzer> |
| * <tokenizer class="solr.StandardTokenizerFactory"/> |
| * <filter class="solr.BeiderMorseFilterFactory" |
| * nameType="GENERIC" ruleType="APPROX" |
| * concat="true" languageSet="auto" |
| * </filter> |
| * </analyzer> |
| * </fieldType></pre> |
| * |
| * @since 3.6.0 |
| * @lucene.spi {@value #NAME} |
| */ |
| public class BeiderMorseFilterFactory extends TokenFilterFactory { |
| |
| /** SPI name */ |
| public static final String NAME = "beiderMorse"; |
| |
| private final PhoneticEngine engine; |
| private final LanguageSet languageSet; |
| |
| /** Creates a new BeiderMorseFilterFactory */ |
| public BeiderMorseFilterFactory(Map<String, String> args) { |
| super(args); |
| // PhoneticEngine = NameType + RuleType + concat |
| // we use common-codec's defaults: GENERIC + APPROX + true |
| NameType nameType = NameType.valueOf(get(args, "nameType", NameType.GENERIC.toString())); |
| RuleType ruleType = RuleType.valueOf(get(args, "ruleType", RuleType.APPROX.toString())); |
| |
| boolean concat = getBoolean(args, "concat", true); |
| engine = new PhoneticEngine(nameType, ruleType, concat); |
| |
| // LanguageSet: defaults to automagic, otherwise a comma-separated list. |
| Set<String> langs = getSet(args, "languageSet"); |
| languageSet = |
| (null == langs || (1 == langs.size() && langs.contains("auto"))) |
| ? null |
| : LanguageSet.from(langs); |
| if (!args.isEmpty()) { |
| throw new IllegalArgumentException("Unknown parameters: " + args); |
| } |
| } |
| |
| /** Default ctor for compatibility with SPI */ |
| public BeiderMorseFilterFactory() { |
| throw defaultCtorException(); |
| } |
| |
| @Override |
| public TokenStream create(TokenStream input) { |
| return new BeiderMorseFilter(input, engine, languageSet); |
| } |
| } |