1 package org.apache.lucene.analysis.de;
2 // This file is encoded in UTF-8
5 * Licensed to the Apache Software Foundation (ASF) under one or more
6 * contributor license agreements. See the NOTICE file distributed with
7 * this work for additional information regarding copyright ownership.
8 * The ASF licenses this file to You under the Apache License, Version 2.0
9 * (the "License"); you may not use this file except in compliance with
10 * the License. You may obtain a copy of the License at
12 * http://www.apache.org/licenses/LICENSE-2.0
14 * Unless required by applicable law or agreed to in writing, software
15 * distributed under the License is distributed on an "AS IS" BASIS,
16 * WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
17 * See the License for the specific language governing permissions and
18 * limitations under the License.
22 import java.io.IOException;
23 import java.io.Reader;
24 import java.util.Arrays;
25 import java.util.HashSet;
29 import org.apache.lucene.analysis.Analyzer;
30 import org.apache.lucene.analysis.CharArraySet;
31 import org.apache.lucene.analysis.LowerCaseFilter;
32 import org.apache.lucene.analysis.KeywordMarkerFilter;
33 import org.apache.lucene.analysis.StopFilter;
34 import org.apache.lucene.analysis.StopwordAnalyzerBase;
35 import org.apache.lucene.analysis.TokenStream;
36 import org.apache.lucene.analysis.Tokenizer;
37 import org.apache.lucene.analysis.WordlistLoader;
38 import org.apache.lucene.analysis.snowball.SnowballFilter;
39 import org.apache.lucene.analysis.standard.StandardAnalyzer;
40 import org.apache.lucene.analysis.standard.StandardFilter;
41 import org.apache.lucene.analysis.standard.StandardTokenizer;
42 import org.apache.lucene.util.IOUtils;
43 import org.apache.lucene.util.Version;
44 import org.tartarus.snowball.ext.German2Stemmer;
47 * {@link Analyzer} for German language.
49 * Supports an external list of stopwords (words that
50 * will not be indexed at all) and an external list of exclusions (word that will
51 * not be stemmed, but indexed).
52 * A default set of stopwords is used unless an alternative list is specified, but the
53 * exclusion list is empty by default.
57 * <p>You must specify the required {@link Version}
58 * compatibility when creating GermanAnalyzer:
60 * <li> As of 3.1, Snowball stemming is done with SnowballFilter, and
61 * Snowball stopwords are used by default.
62 * <li> As of 2.9, StopFilter preserves position
66 * <p><b>NOTE</b>: This class uses the same {@link Version}
67 * dependent settings as {@link StandardAnalyzer}.</p>
69 public final class GermanAnalyzer extends StopwordAnalyzerBase {
72 * List of typical german stopwords.
73 * @deprecated use {@link #getDefaultStopSet()} instead
76 public final static String[] GERMAN_STOP_WORDS = {
77 "einer", "eine", "eines", "einem", "einen",
78 "der", "die", "das", "dass", "daß",
79 "du", "er", "sie", "es",
80 "was", "wer", "wie", "wir",
81 "und", "oder", "ohne", "mit",
82 "am", "im", "in", "aus", "auf",
83 "ist", "sein", "war", "wird",
84 "ihr", "ihre", "ihres",
85 "als", "für", "von", "mit",
86 "dich", "dir", "mich", "mir",
87 "mein", "sein", "kein",
88 "durch", "wegen", "wird"
91 /** File containing default German stopwords. */
92 public final static String DEFAULT_STOPWORD_FILE = "german_stop.txt";
95 * Returns a set of default German-stopwords
96 * @return a set of default German-stopwords
98 public static final Set<?> getDefaultStopSet(){
99 return DefaultSetHolder.DEFAULT_SET;
102 private static class DefaultSetHolder {
103 /** @deprecated remove in Lucene 5.0 */
105 private static final Set<?> DEFAULT_SET_30 = CharArraySet.unmodifiableSet(new CharArraySet(
106 Version.LUCENE_CURRENT, Arrays.asList(GERMAN_STOP_WORDS), false));
107 private static final Set<?> DEFAULT_SET;
110 DEFAULT_SET = WordlistLoader.getSnowballWordSet(IOUtils.getDecodingReader(SnowballFilter.class,
111 DEFAULT_STOPWORD_FILE, IOUtils.CHARSET_UTF_8), Version.LUCENE_CURRENT);
112 } catch (IOException ex) {
113 // default set should always be present as it is part of the
114 // distribution (JAR)
115 throw new RuntimeException("Unable to load default stopword set");
121 * Contains the stopwords used with the {@link StopFilter}.
125 * Contains words that should be indexed but not stemmed.
127 // TODO make this final in 3.1
128 private Set<?> exclusionSet;
131 * Builds an analyzer with the default stop words:
132 * {@link #getDefaultStopSet()}.
134 public GermanAnalyzer(Version matchVersion) {
136 matchVersion.onOrAfter(Version.LUCENE_31) ? DefaultSetHolder.DEFAULT_SET
137 : DefaultSetHolder.DEFAULT_SET_30);
141 * Builds an analyzer with the given stop words
143 * @param matchVersion
144 * lucene compatibility version
148 public GermanAnalyzer(Version matchVersion, Set<?> stopwords) {
149 this(matchVersion, stopwords, CharArraySet.EMPTY_SET);
153 * Builds an analyzer with the given stop words
155 * @param matchVersion
156 * lucene compatibility version
159 * @param stemExclusionSet
160 * a stemming exclusion set
162 public GermanAnalyzer(Version matchVersion, Set<?> stopwords, Set<?> stemExclusionSet) {
163 super(matchVersion, stopwords);
164 exclusionSet = CharArraySet.unmodifiableSet(CharArraySet.copy(matchVersion, stemExclusionSet));
168 * Builds an analyzer with the given stop words.
169 * @deprecated use {@link #GermanAnalyzer(Version, Set)}
172 public GermanAnalyzer(Version matchVersion, String... stopwords) {
173 this(matchVersion, StopFilter.makeStopSet(matchVersion, stopwords));
177 * Builds an analyzer with the given stop words.
178 * @deprecated use {@link #GermanAnalyzer(Version, Set)}
181 public GermanAnalyzer(Version matchVersion, Map<?,?> stopwords) {
182 this(matchVersion, stopwords.keySet());
187 * Builds an analyzer with the given stop words.
188 * @deprecated use {@link #GermanAnalyzer(Version, Set)}
191 public GermanAnalyzer(Version matchVersion, File stopwords) throws IOException {
192 this(matchVersion, WordlistLoader.getWordSet(
193 IOUtils.getDecodingReader(stopwords, IOUtils.CHARSET_UTF_8), matchVersion));
197 * Builds an exclusionlist from an array of Strings.
198 * @deprecated use {@link #GermanAnalyzer(Version, Set, Set)} instead
201 public void setStemExclusionTable(String[] exclusionlist) {
202 exclusionSet = StopFilter.makeStopSet(matchVersion, exclusionlist);
203 setPreviousTokenStream(null); // force a new stemmer to be created
207 * Builds an exclusionlist from a {@link Map}
208 * @deprecated use {@link #GermanAnalyzer(Version, Set, Set)} instead
211 public void setStemExclusionTable(Map<?,?> exclusionlist) {
212 exclusionSet = new HashSet<Object>(exclusionlist.keySet());
213 setPreviousTokenStream(null); // force a new stemmer to be created
217 * Builds an exclusionlist from the words contained in the given file.
218 * @deprecated use {@link #GermanAnalyzer(Version, Set, Set)} instead
221 public void setStemExclusionTable(File exclusionlist) throws IOException {
222 exclusionSet = WordlistLoader.getWordSet(IOUtils.getDecodingReader(exclusionlist,
223 IOUtils.CHARSET_UTF_8), matchVersion);
224 setPreviousTokenStream(null); // force a new stemmer to be created
229 * {@link org.apache.lucene.analysis.ReusableAnalyzerBase.TokenStreamComponents}
230 * used to tokenize all the text in the provided {@link Reader}.
232 * @return {@link org.apache.lucene.analysis.ReusableAnalyzerBase.TokenStreamComponents}
233 * built from a {@link StandardTokenizer} filtered with
234 * {@link StandardFilter}, {@link LowerCaseFilter}, {@link StopFilter}
235 * , {@link KeywordMarkerFilter} if a stem exclusion set is
236 * provided, and {@link SnowballFilter}
239 protected TokenStreamComponents createComponents(String fieldName,
241 final Tokenizer source = new StandardTokenizer(matchVersion, reader);
242 TokenStream result = new StandardFilter(matchVersion, source);
243 result = new LowerCaseFilter(matchVersion, result);
244 result = new StopFilter( matchVersion, result, stopwords);
245 result = new KeywordMarkerFilter(result, exclusionSet);
246 if (matchVersion.onOrAfter(Version.LUCENE_31))
247 result = new SnowballFilter(result, new German2Stemmer());
249 result = new GermanStemFilter(result);
250 return new TokenStreamComponents(source, result);