/* * Licensed to ElasticSearch and Shay Banon under one * or more contributor license agreements. See the NOTICE file * distributed with this work for additional information * regarding copyright ownership. ElasticSearch 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.elasticsearch.index.analysis; import org.apache.lucene.analysis.*; import org.apache.lucene.analysis.standard.StandardAnalyzer; import org.apache.lucene.analysis.standard.StandardFilter; import org.apache.lucene.analysis.standard.StandardTokenizer; import org.apache.lucene.util.Version; import java.io.IOException; import java.io.Reader; public class StandardHtmlStripAnalyzer extends StopwordAnalyzerBase { public StandardHtmlStripAnalyzer(Version version) { super(version, StopAnalyzer.ENGLISH_STOP_WORDS_SET); } @Override protected TokenStreamComponents createComponents(final String fieldName, final Reader reader) { final StandardTokenizer src = new StandardTokenizer(matchVersion, reader); src.setMaxTokenLength(StandardAnalyzer.DEFAULT_MAX_TOKEN_LENGTH); TokenStream tok = new StandardFilter(matchVersion, src); tok = new LowerCaseFilter(matchVersion, tok); tok = new StopFilter(matchVersion, tok, stopwords); return new TokenStreamComponents(src, tok) { @Override protected boolean reset(final Reader reader) throws IOException { src.setMaxTokenLength(StandardAnalyzer.DEFAULT_MAX_TOKEN_LENGTH); return super.reset(reader); } }; } }