| using Lucene.Net.Analysis.Core; |
| using Lucene.Net.Analysis.Miscellaneous; |
| using Lucene.Net.Analysis.Snowball; |
| using Lucene.Net.Analysis.Standard; |
| using Lucene.Net.Analysis.Util; |
| using Lucene.Net.Tartarus.Snowball.Ext; |
| using Lucene.Net.Util; |
| using System; |
| using System.IO; |
| |
| namespace Lucene.Net.Analysis.Tr |
| { |
| /* |
| * 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. |
| */ |
| |
| /// <summary> |
| /// <see cref="Analyzer"/> for Turkish. |
| /// </summary> |
| public sealed class TurkishAnalyzer : StopwordAnalyzerBase |
| { |
| private readonly CharArraySet stemExclusionSet; |
| |
| /// <summary> |
| /// File containing default Turkish stopwords. </summary> |
| public const string DEFAULT_STOPWORD_FILE = "stopwords.txt"; |
| /// <summary> |
| /// The comment character in the stopwords file. |
| /// All lines prefixed with this will be ignored. |
| /// </summary> |
| private const string STOPWORDS_COMMENT = "#"; |
| |
| /// <summary> |
| /// Returns an unmodifiable instance of the default stop words set. </summary> |
| /// <returns> default stop words set. </returns> |
| public static CharArraySet DefaultStopSet => DefaultSetHolder.DEFAULT_STOP_SET; |
| |
| /// <summary> |
| /// Atomically loads the <see cref="DEFAULT_STOP_SET"/> in a lazy fashion once the outer class |
| /// accesses the static final set the first time.; |
| /// </summary> |
| private class DefaultSetHolder |
| { |
| internal static readonly CharArraySet DEFAULT_STOP_SET = LoadDefaultStopSet(); |
| |
| private static CharArraySet LoadDefaultStopSet() // LUCENENET: Avoid static constructors (see https://github.com/apache/lucenenet/pull/224#issuecomment-469284006) |
| { |
| try |
| { |
| return LoadStopwordSet(false, typeof(TurkishAnalyzer), DEFAULT_STOPWORD_FILE, STOPWORDS_COMMENT); |
| } |
| catch (IOException ex) |
| { |
| // default set should always be present as it is part of the |
| // distribution (JAR) |
| throw new Exception("Unable to load default stopword set", ex); |
| } |
| } |
| } |
| |
| /// <summary> |
| /// Builds an analyzer with the default stop words: <see cref="DEFAULT_STOPWORD_FILE"/>. |
| /// </summary> |
| public TurkishAnalyzer(LuceneVersion matchVersion) |
| : this(matchVersion, DefaultSetHolder.DEFAULT_STOP_SET) |
| { |
| } |
| |
| /// <summary> |
| /// Builds an analyzer with the given stop words. |
| /// </summary> |
| /// <param name="matchVersion"> lucene compatibility version </param> |
| /// <param name="stopwords"> a stopword set </param> |
| public TurkishAnalyzer(LuceneVersion matchVersion, CharArraySet stopwords) |
| : this(matchVersion, stopwords, CharArraySet.EMPTY_SET) |
| { |
| } |
| |
| /// <summary> |
| /// Builds an analyzer with the given stop words. If a non-empty stem exclusion set is |
| /// provided this analyzer will add a <see cref="SetKeywordMarkerFilter"/> before |
| /// stemming. |
| /// </summary> |
| /// <param name="matchVersion"> lucene compatibility version </param> |
| /// <param name="stopwords"> a stopword set </param> |
| /// <param name="stemExclusionSet"> a set of terms not to be stemmed </param> |
| public TurkishAnalyzer(LuceneVersion matchVersion, CharArraySet stopwords, CharArraySet stemExclusionSet) |
| : base(matchVersion, stopwords) |
| { |
| this.stemExclusionSet = CharArraySet.UnmodifiableSet(CharArraySet.Copy(matchVersion, stemExclusionSet)); |
| } |
| |
| /// <summary> |
| /// Creates a |
| /// <see cref="TokenStreamComponents"/> |
| /// which tokenizes all the text in the provided <see cref="TextReader"/>. |
| /// </summary> |
| /// <returns> A |
| /// <see cref="TokenStreamComponents"/> |
| /// built from an <see cref="StandardTokenizer"/> filtered with |
| /// <see cref="StandardFilter"/>, <see cref="TurkishLowerCaseFilter"/>, |
| /// <see cref="StopFilter"/>, <see cref="SetKeywordMarkerFilter"/> if a stem |
| /// exclusion set is provided and <see cref="SnowballFilter"/>. </returns> |
| protected internal override TokenStreamComponents CreateComponents(string fieldName, TextReader reader) |
| { |
| Tokenizer source = new StandardTokenizer(m_matchVersion, reader); |
| TokenStream result = new StandardFilter(m_matchVersion, source); |
| if (m_matchVersion.OnOrAfter(LuceneVersion.LUCENE_48)) |
| { |
| result = new ApostropheFilter(result); |
| } |
| result = new TurkishLowerCaseFilter(result); |
| result = new StopFilter(m_matchVersion, result, m_stopwords); |
| if (stemExclusionSet.Count > 0) |
| { |
| result = new SetKeywordMarkerFilter(result, stemExclusionSet); |
| } |
| result = new SnowballFilter(result, new TurkishStemmer()); |
| return new TokenStreamComponents(source, result); |
| } |
| } |
| } |