segmentmerger.cs

Lucene.Net 版本源码 测试通过

/*
 * 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 FieldSelector = Lucene.Net.Documents.FieldSelector;
using FieldSelectorResult = Lucene.Net.Documents.FieldSelectorResult;
using Directory = Lucene.Net.Store.Directory;
using IndexOutput = Lucene.Net.Store.IndexOutput;
using RAMOutputStream = Lucene.Net.Store.RAMOutputStream;

namespace Lucene.Net.Index
{
	
	/// <summary> The SegmentMerger class combines two or more Segments, represented by an IndexReader ({@link #add},
	/// into a single Segment.  After adding the appropriate readers, call the merge method to combine the 
	/// segments.
	/// <P> 
	/// If the compoundFile flag is set, then the segments will be merged into a compound file.
	/// 
	/// 
	/// </summary>
	/// <seealso cref="#merge">
	/// </seealso>
	/// <seealso cref="#add">
	/// </seealso>
	sealed class SegmentMerger
	{
		private class AnonymousClassFieldSelector : FieldSelector
		{
			public AnonymousClassFieldSelector(SegmentMerger enclosingInstance)
			{
				InitBlock(enclosingInstance);
			}
			private void  InitBlock(SegmentMerger enclosingInstance)
			{
				this.enclosingInstance = enclosingInstance;
			}
			private SegmentMerger enclosingInstance;
			public SegmentMerger Enclosing_Instance
			{
				get
				{
					return enclosingInstance;
				}
				
			}
			public FieldSelectorResult Accept(System.String fieldName)
			{
				return FieldSelectorResult.LOAD_FOR_MERGE;
			}
		}
		private void  InitBlock()
		{
			termIndexInterval = IndexWriter.DEFAULT_TERM_INDEX_INTERVAL;
		}
		
		/// <summary>norms header placeholder </summary>
		internal static readonly byte[] NORMS_HEADER = new byte[]{(byte) 'N', (byte) 'R', (byte) 'M', (byte) 255};
		
		private Directory directory;
		private System.String segment;
		private int termIndexInterval;
		
		private System.Collections.ArrayList readers = System.Collections.ArrayList.Synchronized(new System.Collections.ArrayList(10));
		private FieldInfos fieldInfos;
		
		/// <summary>This ctor used only by test code.
		/// 
		/// </summary>
		/// <param name="dir">The Directory to merge the other segments into
		/// </param>
		/// <param name="name">The name of the new segment
		/// </param>
		public SegmentMerger(Directory dir, System.String name)
		{
			InitBlock();
			directory = dir;
			segment = name;
		}
		
		internal SegmentMerger(IndexWriter writer, System.String name)
		{
			InitBlock();
			directory = writer.GetDirectory();
			segment = name;
			termIndexInterval = writer.GetTermIndexInterval();
		}
		
		/// <summary> Add an IndexReader to the collection of readers that are to be merged</summary>
		/// <param name="">reader
		/// </param>
		public void  Add(IndexReader reader)
		{
			readers.Add(reader);
		}
		
		/// <summary> </summary>
		/// <param name="i">The index of the reader to return
		/// </param>
		/// <returns> The ith reader to be merged
		/// </returns>
		internal IndexReader SegmentReader(int i)
		{
			return (IndexReader) readers[i];
		}
		
		/// <summary> Merges the readers specified by the {@link #add} method into the directory passed to the constructor</summary>
		/// <returns> The number of documents that were merged
		/// </returns>
		/// <throws>  IOException </throws>
		public int Merge()
		{
			int value_Renamed;
			
			value_Renamed = MergeFields();
			MergeTerms();
			MergeNorms();
			
			if (fieldInfos.HasVectors())
				MergeVectors();
			
			return value_Renamed;
		}
		
		/// <summary> close all IndexReaders that have been added.
		/// Should not be called before merge().
		/// </summary>
		/// <throws>  IOException </throws>
		public void  CloseReaders()
		{
			for (int i = 0; i < readers.Count; i++)
			{
				// close readers
				IndexReader reader = (IndexReader) readers[i];
				reader.Close();
			}
		}
		
		public System.Collections.ArrayList CreateCompoundFile(System.String fileName)
		{
			CompoundFileWriter cfsWriter = new CompoundFileWriter(directory, fileName);
			
			System.Collections.ArrayList files = System.Collections.ArrayList.Synchronized(new System.Collections.ArrayList(IndexFileNames.COMPOUND_EXTENSIONS.Length + 1));
			
			// Basic files
			for (int i = 0; i < IndexFileNames.COMPOUND_EXTENSIONS.Length; i++)
			{
				files.Add(segment + "." + IndexFileNames.COMPOUND_EXTENSIONS[i]);
			}
			
			// Fieldable norm files
			for (int i = 0; i < fieldInfos.Size(); i++)
			{
				FieldInfo fi = fieldInfos.FieldInfo(i);
				if (fi.isIndexed && !fi.omitNorms)
				{
					files.Add(segment + "." + IndexFileNames.NORMS_EXTENSION);
					break;
				}
			}
			
			// Vector files
			if (fieldInfos.HasVectors())
			{
				for (int i = 0; i < IndexFileNames.VECTOR_EXTENSIONS.Length; i++)
				{
					files.Add(segment + "." + IndexFileNames.VECTOR_EXTENSIONS[i]);
				}
			}
			
			// Now merge all added files
			System.Collections.IEnumerator it = files.GetEnumerator();
			while (it.MoveNext())
			{
				cfsWriter.AddFile((System.String) it.Current);
			}
			
			// Perform the merge
			cfsWriter.Close();
			
			return files;
		}
		
		private void  AddIndexed(IndexReader reader, FieldInfos fieldInfos, System.Collections.ICollection names, bool storeTermVectors, bool storePositionWithTermVector, bool storeOffsetWithTermVector)
		{
			System.Collections.IEnumerator i = names.GetEnumerator();
			while (i.MoveNext())
			{
				System.Collections.DictionaryEntry e = (System.Collections.DictionaryEntry) i.Current;
				System.String field = (System.String) e.Key;
				fieldInfos.Add(field, true, storeTermVectors, storePositionWithTermVector, storeOffsetWithTermVector, !reader.HasNorms(field));
			}
		}
		
		/// <summary> </summary>
		/// <returns> The number of documents in all of the readers
		/// </returns>
		/// <throws>  IOException </throws>
		private int MergeFields()
		{
			fieldInfos = new FieldInfos(); // merge field names
			int docCount = 0;
			for (int i = 0; i < readers.Count; i++)
			{
				IndexReader reader = (IndexReader) readers[i];
				AddIndexed(reader, fieldInfos, reader.GetFieldNames(IndexReader.FieldOption.TERMVECTOR_WITH_POSITION_OFFSET), true, true, true);
				AddIndexed(reader, fieldInfos, reader.GetFieldNames(IndexReader.FieldOption.TERMVECTOR_WITH_POSITION), true, true, false);
				AddIndexed(reader, fieldInfos, reader.GetFieldNames(IndexReader.FieldOption.TERMVECTOR_WITH_OFFSET), true, false, true);
				AddIndexed(reader, fieldInfos, reader.GetFieldNames(IndexReader.FieldOption.TERMVECTOR), true, false, false);
				AddIndexed(reader, fieldInfos, reader.GetFieldNames(IndexReader.FieldOption.INDEXED), false, false, false);
				fieldInfos.Add(reader.GetFieldNames(IndexReader.FieldOption.UNINDEXED), false);
			}
			fieldInfos.Write(directory, segment + ".fnm");
			
			FieldsWriter fieldsWriter = new FieldsWriter(directory, segment, fieldInfos);
			
			// for merging we don't want to compress/uncompress the data, so to tell the FieldsReader that we're
			// in  merge mode, we use this FieldSelector
			FieldSelector fieldSelectorMerge = new AnonymousClassFieldSelector(this);
			
			try
			{
				for (int i = 0; i < readers.Count; i++)
				{
					IndexReader reader = (IndexReader) readers[i];
					int maxDoc = reader.MaxDoc();
					for (int j = 0; j < maxDoc; j++)
						if (!reader.IsDeleted(j))
						{
							// skip deleted docs
							fieldsWriter.AddDocument(reader.Document(j, fieldSelectorMerge));
							docCount++;
						}
				}
			}
			finally
			{
				fieldsWriter.Close();
			}
			return docCount;
		}
		
		/// <summary> Merge the TermVectors from each of the segments into the new one.</summary>
		/// <throws>  IOException </throws>
		private void  MergeVectors()
		{
			TermVectorsWriter termVectorsWriter = new TermVectorsWriter(directory, segment, fieldInfos);
			
			try
			{
				for (int r = 0; r < readers.Count; r++)
				{
					IndexReader reader = (IndexReader) readers[r];
					int maxDoc = reader.MaxDoc();
					for (int docNum = 0; docNum < maxDoc; docNum++)
					{
						// skip deleted docs
						if (reader.IsDeleted(docNum))