C# Lucene.Net.Index.IndexWriter.SetMergeFactor方法代码示例

		public static void  Main(System.String[] args)
		{
			try
			{
				System.DateTime start = System.DateTime.Now;
				System.String tempFileName = System.IO.Path.GetTempFileName();
				System.String tempDirectory = System.IO.Path.GetDirectoryName(tempFileName);
				tempFileName = System.IO.Path.GetFileName(tempFileName);
				IndexWriter writer = new IndexWriter(System.IO.Path.Combine(tempDirectory, "luceneTest") + tempFileName + ".idx", new SimpleAnalyzer(), true);

				writer.SetMergeFactor(20);
				
				IndexDocs(writer, new System.IO.FileInfo("/tmp"));
				
				writer.Optimize();
				writer.Close();
				
				System.DateTime end = System.DateTime.Now;
				
				System.Console.Out.Write(end.Ticks - start.Ticks);
				System.Console.Out.WriteLine(" total milliseconds");
				
				System.Diagnostics.Process runtime = System.Diagnostics.Process.GetCurrentProcess();
				
				// System.Console.Out.Write(java.lang.Runtime.freeMemory());    // {{Aroush}} how do we get freeMemory() in .NET?
				System.Console.Out.WriteLine(" free memory before gc");
				// System.Console.Out.Write(java.lang.Runtime.totalMemory());   // {{Aroush}} how do we get totalMemory() in .NET?
				System.Console.Out.WriteLine(" total memory before gc");
				
				System.GC.Collect();
				
				// System.Console.Out.Write(java.lang.Runtime.freeMemory());    // {{Aroush}} how do we get freeMemory() in .NET?
				System.Console.Out.WriteLine(" free memory after gc");
				// System.Console.Out.Write(java.lang.Runtime.totalMemory());   // {{Aroush}} how do we get totalMemory() in .NET?
				System.Console.Out.WriteLine(" total memory after gc");
			}
			catch (System.Exception e)
			{
				System.Console.Out.WriteLine(" caught a " + e.GetType() + "\n with message: " + e.Message);
			}
		}

		private IndexSearcher GetFullStrings()
		{
			RAMDirectory indexStore = new RAMDirectory();
			IndexWriter writer = new IndexWriter(indexStore, new SimpleAnalyzer(), true, IndexWriter.MaxFieldLength.LIMITED);
			writer.SetMaxBufferedDocs(4);
			writer.SetMergeFactor(97);
			for (int i = 0; i < NUM_STRINGS; i++)
			{
				Document doc = new Document();
				System.String num = GetRandomCharString(GetRandomNumber(2, 8), 48, 52);
				doc.Add(new Field("tracer", num, Field.Store.YES, Field.Index.NO));
				//doc.add (new Field ("contents", Integer.toString(i), Field.Store.NO, Field.Index.ANALYZED));
				doc.Add(new Field("string", num, Field.Store.NO, Field.Index.NOT_ANALYZED));
				System.String num2 = GetRandomCharString(GetRandomNumber(1, 4), 48, 50);
				doc.Add(new Field("string2", num2, Field.Store.NO, Field.Index.NOT_ANALYZED));
				doc.Add(new Field("tracer2", num2, Field.Store.YES, Field.Index.NO));
				doc.SetBoost(2); // produce some scores above 1.0
				writer.SetMaxBufferedDocs(GetRandomNumber(2, 12));
				writer.AddDocument(doc);
			}
			//writer.optimize ();
			//System.out.println(writer.getSegmentCount());
			writer.Close();
			return new IndexSearcher(indexStore);
		}

		// create an index of all the documents, or just the x, or just the y documents
		private Searcher GetIndex(bool even, bool odd)
		{
			RAMDirectory indexStore = new RAMDirectory();
			IndexWriter writer = new IndexWriter(indexStore, new SimpleAnalyzer(), true, IndexWriter.MaxFieldLength.LIMITED);
			writer.SetMaxBufferedDocs(2);
			writer.SetMergeFactor(1000);
			for (int i = 0; i < data.Length; ++i)
			{
				if (((i % 2) == 0 && even) || ((i % 2) == 1 && odd))
				{
					Document doc = new Document();
					doc.Add(new Field("tracer", data[i][0], Field.Store.YES, Field.Index.NO));
					doc.Add(new Field("contents", data[i][1], Field.Store.NO, Field.Index.ANALYZED));
					if (data[i][2] != null)
						doc.Add(new Field("int", data[i][2], Field.Store.NO, Field.Index.NOT_ANALYZED));
					if (data[i][3] != null)
						doc.Add(new Field("float", data[i][3], Field.Store.NO, Field.Index.NOT_ANALYZED));
					if (data[i][4] != null)
						doc.Add(new Field("string", data[i][4], Field.Store.NO, Field.Index.NOT_ANALYZED));
					if (data[i][5] != null)
						doc.Add(new Field("custom", data[i][5], Field.Store.NO, Field.Index.NOT_ANALYZED));
					if (data[i][6] != null)
						doc.Add(new Field("i18n", data[i][6], Field.Store.NO, Field.Index.NOT_ANALYZED));
					if (data[i][7] != null)
						doc.Add(new Field("long", data[i][7], Field.Store.NO, Field.Index.NOT_ANALYZED));
					if (data[i][8] != null)
						doc.Add(new Field("double", data[i][8], Field.Store.NO, Field.Index.NOT_ANALYZED));
					if (data[i][9] != null)
						doc.Add(new Field("short", data[i][9], Field.Store.NO, Field.Index.NOT_ANALYZED));
					if (data[i][10] != null)
						doc.Add(new Field("byte", data[i][10], Field.Store.NO, Field.Index.NOT_ANALYZED));
					if (data[i][11] != null)
						doc.Add(new Field("parser", data[i][11], Field.Store.NO, Field.Index.NOT_ANALYZED));
					doc.SetBoost(2); // produce some scores above 1.0
					writer.AddDocument(doc);
				}
			}
			//writer.optimize ();
			writer.Close();
			IndexSearcher s = new IndexSearcher(indexStore);
			s.SetDefaultFieldSortScoring(true, true);
			return s;
		}

        /// <summary> Index a Dictionary</summary>
        /// <param name="dict">the dictionary to index
        /// </param>
        /// <throws>  IOException </throws>
        public virtual void  IndexDictionary(Dictionary dict)
        {
            IndexReader.Unlock(spellindex);
            IndexWriter writer = new IndexWriter(spellindex, new WhitespaceAnalyzer(), !IndexReader.IndexExists(spellindex));
            writer.SetMergeFactor(300);
            writer.SetMaxBufferedDocs(150);
			
            System.Collections.IEnumerator iter = dict.GetWordsIterator();
            while (iter.MoveNext())
            {
                System.String word = (System.String) iter.Current;
				
                int len = word.Length;
                if (len < 3)
                {
                    continue; // too short we bail but "too long" is fine...
                }
				
                if (this.Exist(word))
                {
                    // if the word already exist in the gramindex
                    continue;
                }
				
                // ok index the word
                Document doc = CreateDocument(word, GetMin(len), GetMax(len));
                writer.AddDocument(doc);
            }
            // close writer
            writer.Optimize();
            writer.Close();
			
            // close reader
            reader.Close();
            reader = null;
        }

		/// <summary> Forms a Lucene index based on the 2 maps.
		/// 
		/// </summary>
		/// <param name="indexDir">the direcotry where the index should be created
		/// </param>
		/// <param name="">word2Nums
		/// </param>
		/// <param name="">num2Words
		/// </param>
		private static void  Index(System.String indexDir, System.Collections.IDictionary word2Nums, System.Collections.IDictionary num2Words)
		{
			int row = 0;
			int mod = 1;
			
			// override the specific index if it already exists
			IndexWriter writer = new IndexWriter(indexDir, ana, true);
			writer.SetUseCompoundFile(true); // why?
			// blindly up these parameters for speed
			writer.SetMergeFactor(writer.GetMergeFactor() * 2);
			writer.SetMaxBufferedDocs(writer.GetMaxBufferedDocs() * 2);
			System.Collections.IEnumerator i1 = word2Nums.Keys.GetEnumerator();
			while (i1.MoveNext())
			// for each word
			{
				System.String g = (System.String) i1.Current;
				Document doc = new Document();
				
				int n = Index(word2Nums, num2Words, g, doc);
				if (n > 0)
				{
					doc.Add(new Field(F_WORD, g, Field.Store.YES, Field.Index.UN_TOKENIZED));
					if ((++row % mod) == 0)
					{
						o.WriteLine("\trow=" + row + "/" + word2Nums.Count + " doc= " + doc);
						mod *= 2;
					}
					writer.AddDocument(doc);
				} // else degenerate
			}
			o.WriteLine("Optimizing..");
			writer.Optimize();
			writer.Close();
		}

        /// <summary> Index a Dictionary</summary>
        /// <param name="dict">the dictionary to index</param>
        /// <param name="mergeFactor">mergeFactor to use when indexing</param>
        /// <param name="ramMB">the max amount or memory in MB to use</param>
        /// <throws>  IOException </throws>
        /// <throws>AlreadyClosedException if the Spellchecker is already closed</throws>
        public virtual void IndexDictionary(Dictionary dict, int mergeFactor, int ramMB)
        {
            lock (modifyCurrentIndexLock)
            {
                EnsureOpen();
                Directory dir = this.spellindex;
                IndexWriter writer = new IndexWriter(spellindex, new WhitespaceAnalyzer(), IndexWriter.MaxFieldLength.UNLIMITED);
                writer.SetMergeFactor(mergeFactor);
                writer.SetMaxBufferedDocs(ramMB);

                System.Collections.IEnumerator iter = dict.GetWordsIterator();
                while (iter.MoveNext())
                {
                    System.String word = (System.String)iter.Current;

                    int len = word.Length;
                    if (len < 3)
                    {
                        continue; // too short we bail but "too long" is fine...
                    }

                    if (this.Exist(word))
                    {
                        // if the word already exist in the gramindex
                        continue;
                    }

                    // ok index the word
                    Document doc = CreateDocument(word, GetMin(len), GetMax(len));
                    writer.AddDocument(doc);
                }
                // close writer
                writer.Optimize();
                writer.Close();
                // also re-open the spell index to see our own changes when the next suggestion
                // is fetched:
                SwapSearcher(dir);
            }
        }