StandardAnalyzer.cs

Go to the documentation of this file.

/* 
 * 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.
 */

using System;
using System.Collections;
using System.Collections.Generic;
using Lucene.Net.Analysis;
using Lucene.Net.Util;
using Version = Lucene.Net.Util.Version;

namespace Lucene.Net.Analysis.Standard
{
    
    public class StandardAnalyzer : Analyzer
    {
        private ISet<string> stopSet;
        
        private bool replaceInvalidAcronym, enableStopPositionIncrements;

        public static readonly ISet<string> STOP_WORDS_SET;
        private Version matchVersion;
        
        public StandardAnalyzer(Version matchVersion)
            : this(matchVersion, STOP_WORDS_SET)
        { }
        
        public StandardAnalyzer(Version matchVersion, ISet<string> stopWords)
        {
            stopSet = stopWords;
            SetOverridesTokenStreamMethod<StandardAnalyzer>();
            enableStopPositionIncrements = StopFilter.GetEnablePositionIncrementsVersionDefault(matchVersion);
            replaceInvalidAcronym = matchVersion.OnOrAfter(Version.LUCENE_24);
            this.matchVersion = matchVersion;
        }
        
        public StandardAnalyzer(Version matchVersion, System.IO.FileInfo stopwords)
            : this (matchVersion, WordlistLoader.GetWordSet(stopwords))
        {
        }
        
        public StandardAnalyzer(Version matchVersion, System.IO.TextReader stopwords)
            : this(matchVersion, WordlistLoader.GetWordSet(stopwords))
        { }
        
        public override TokenStream TokenStream(System.String fieldName, System.IO.TextReader reader)
        {
            StandardTokenizer tokenStream = new StandardTokenizer(matchVersion, reader);
            tokenStream.MaxTokenLength = maxTokenLength;
            TokenStream result = new StandardFilter(tokenStream);
            result = new LowerCaseFilter(result);
            result = new StopFilter(enableStopPositionIncrements, result, stopSet);
            return result;
        }
        
        private sealed class SavedStreams
        {
            internal StandardTokenizer tokenStream;
            internal TokenStream filteredTokenStream;
        }
        
        public const int DEFAULT_MAX_TOKEN_LENGTH = 255;
        
        private int maxTokenLength = DEFAULT_MAX_TOKEN_LENGTH;

        public virtual int MaxTokenLength
        {
            get { return maxTokenLength; }
            set { maxTokenLength = value; }
        }

        public override TokenStream ReusableTokenStream(System.String fieldName, System.IO.TextReader reader)
        {
            if (overridesTokenStreamMethod)
            {
                // LUCENE-1678: force fallback to tokenStream() if we
                // have been subclassed and that subclass overrides
                // tokenStream but not reusableTokenStream
                return TokenStream(fieldName, reader);
            }
            SavedStreams streams = (SavedStreams) PreviousTokenStream;
            if (streams == null)
            {
                streams = new SavedStreams();
                PreviousTokenStream = streams;
                streams.tokenStream = new StandardTokenizer(matchVersion, reader);
                streams.filteredTokenStream = new StandardFilter(streams.tokenStream);
                streams.filteredTokenStream = new LowerCaseFilter(streams.filteredTokenStream);
                streams.filteredTokenStream = new StopFilter(enableStopPositionIncrements, 
                                                             streams.filteredTokenStream, stopSet);
            }
            else
            {
                streams.tokenStream.Reset(reader);
            }
            streams.tokenStream.MaxTokenLength = maxTokenLength;
            
            streams.tokenStream.SetReplaceInvalidAcronym(replaceInvalidAcronym);
            
            return streams.filteredTokenStream;
        }
        static StandardAnalyzer()
        {
            STOP_WORDS_SET = StopAnalyzer.ENGLISH_STOP_WORDS_SET;
        }
    }
}