package org.apache.lucene.analysis.de;
// This file is encoded in UTF-8

/**
 * Copyright 2004 The Apache Software Foundation
 *
 * 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.
 */

import org.apache.lucene.analysis.Analyzer;
import org.apache.lucene.analysis.LowerCaseFilter;
import org.apache.lucene.analysis.StopFilter;
import org.apache.lucene.analysis.TokenStream;
import org.apache.lucene.analysis.WordlistLoader;
import org.apache.lucene.analysis.standard.StandardFilter;
import org.apache.lucene.analysis.standard.StandardTokenizer;

import java.io.File;
import java.io.IOException;
import java.io.Reader;
import java.util.HashSet;
import java.util.Hashtable;
import java.util.Set;

/**
 * Analyzer for German language. Supports an external list of stopwords (words that
 * will not be indexed at all) and an external list of exclusions (word that will
 * not be stemmed, but indexed).
 * A default set of stopwords is used unless an alternative list is specified, the
 * exclusion list is empty by default.
 *
 * @author Gerhard Schwarz
 * @version $Id: GermanAnalyzer.java 151017 2004-11-29 22:22:48Z dnaber $
 */
public class GermanAnalyzer extends Analyzer {
  
  /**
   * List of typical german stopwords.
   */
  public final static String[] GERMAN_STOP_WORDS = {
    "einer", "eine", "eines", "einem", "einen",
    "der", "die", "das", "dass", "daÃ