1
package org.apache.lucene.analysis.lv;
4
* Licensed to the Apache Software Foundation (ASF) under one or more
5
* contributor license agreements. See the NOTICE file distributed with
6
* this work for additional information regarding copyright ownership.
7
* The ASF licenses this file to You under the Apache License, Version 2.0
8
* (the "License"); you may not use this file except in compliance with
9
* the License. You may obtain a copy of the License at
11
* http://www.apache.org/licenses/LICENSE-2.0
13
* Unless required by applicable law or agreed to in writing, software
14
* distributed under the License is distributed on an "AS IS" BASIS,
15
* WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
16
* See the License for the specific language governing permissions and
17
* limitations under the License.
20
import java.io.IOException;
21
import java.io.Reader;
24
import org.apache.lucene.analysis.Analyzer;
25
import org.apache.lucene.analysis.LowerCaseFilter;
26
import org.apache.lucene.analysis.StopFilter;
27
import org.apache.lucene.analysis.KeywordMarkerFilter;
28
import org.apache.lucene.analysis.TokenStream;
29
import org.apache.lucene.analysis.Tokenizer;
30
import org.apache.lucene.analysis.snowball.SnowballFilter;
31
import org.apache.lucene.analysis.standard.StandardFilter;
32
import org.apache.lucene.analysis.standard.StandardTokenizer;
33
import org.apache.lucene.analysis.CharArraySet;
34
import org.apache.lucene.analysis.StopwordAnalyzerBase;
35
import org.apache.lucene.analysis.WordlistLoader;
36
import org.apache.lucene.util.IOUtils;
37
import org.apache.lucene.util.Version;
40
* {@link Analyzer} for Latvian.
42
public final class LatvianAnalyzer extends StopwordAnalyzerBase {
43
private final Set<?> stemExclusionSet;
45
/** File containing default Latvian stopwords. */
46
public final static String DEFAULT_STOPWORD_FILE = "stopwords.txt";
49
* Returns an unmodifiable instance of the default stop words set.
50
* @return default stop words set.
52
public static Set<?> getDefaultStopSet(){
53
return DefaultSetHolder.DEFAULT_STOP_SET;
57
* Atomically loads the DEFAULT_STOP_SET in a lazy fashion once the outer class
58
* accesses the static final set the first time.;
60
private static class DefaultSetHolder {
61
static final Set<?> DEFAULT_STOP_SET;
65
DEFAULT_STOP_SET = WordlistLoader.getWordSet(IOUtils.getDecodingReader(LatvianAnalyzer.class,
66
DEFAULT_STOPWORD_FILE, IOUtils.CHARSET_UTF_8), Version.LUCENE_CURRENT);
67
} catch (IOException ex) {
68
// default set should always be present as it is part of the
70
throw new RuntimeException("Unable to load default stopword set");
76
* Builds an analyzer with the default stop words: {@link #DEFAULT_STOPWORD_FILE}.
78
public LatvianAnalyzer(Version matchVersion) {
79
this(matchVersion, DefaultSetHolder.DEFAULT_STOP_SET);
83
* Builds an analyzer with the given stop words.
85
* @param matchVersion lucene compatibility version
86
* @param stopwords a stopword set
88
public LatvianAnalyzer(Version matchVersion, Set<?> stopwords) {
89
this(matchVersion, stopwords, CharArraySet.EMPTY_SET);
93
* Builds an analyzer with the given stop words. If a non-empty stem exclusion set is
94
* provided this analyzer will add a {@link KeywordMarkerFilter} before
97
* @param matchVersion lucene compatibility version
98
* @param stopwords a stopword set
99
* @param stemExclusionSet a set of terms not to be stemmed
101
public LatvianAnalyzer(Version matchVersion, Set<?> stopwords, Set<?> stemExclusionSet) {
102
super(matchVersion, stopwords);
103
this.stemExclusionSet = CharArraySet.unmodifiableSet(CharArraySet.copy(
104
matchVersion, stemExclusionSet));
109
* {@link org.apache.lucene.analysis.ReusableAnalyzerBase.TokenStreamComponents}
110
* which tokenizes all the text in the provided {@link Reader}.
113
* {@link org.apache.lucene.analysis.ReusableAnalyzerBase.TokenStreamComponents}
114
* built from an {@link StandardTokenizer} filtered with
115
* {@link StandardFilter}, {@link LowerCaseFilter}, {@link StopFilter}
116
* , {@link KeywordMarkerFilter} if a stem exclusion set is
117
* provided and {@link LatvianStemFilter}.
120
protected TokenStreamComponents createComponents(String fieldName,
122
final Tokenizer source = new StandardTokenizer(matchVersion, reader);
123
TokenStream result = new StandardFilter(matchVersion, source);
124
result = new LowerCaseFilter(matchVersion, result);
125
result = new StopFilter(matchVersion, result, stopwords);
126
if(!stemExclusionSet.isEmpty())
127
result = new KeywordMarkerFilter(result, stemExclusionSet);
128
result = new LatvianStemFilter(result);
129
return new TokenStreamComponents(source, result);