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

		public override void  SetUp()
		{
			base.SetUp();
			
			
			System.String[] data = new System.String[]{"A 1 2 3 4 5 6", "Z       4 5 6", null, "B   2   4 5 6", "Y     3   5 6", null, "C     3     6", "X       4 5 6"};
			
			index = new RAMDirectory();
			IndexWriter writer = new IndexWriter(index, new WhitespaceAnalyzer(), true, IndexWriter.MaxFieldLength.LIMITED);
			
			for (int i = 0; i < data.Length; i++)
			{
				Document doc = new Document();
				doc.Add(new Field("id", System.Convert.ToString(i), Field.Store.YES, Field.Index.NOT_ANALYZED)); //Field.Keyword("id",String.valueOf(i)));
				doc.Add(new Field("all", "all", Field.Store.YES, Field.Index.NOT_ANALYZED)); //Field.Keyword("all","all"));
				if (null != data[i])
				{
					doc.Add(new Field("data", data[i], Field.Store.YES, Field.Index.ANALYZED)); //Field.Text("data",data[i]));
				}
				writer.AddDocument(doc);
			}
			
			writer.Optimize();
			writer.Close();
			
			r = IndexReader.Open(index, true);
			s = new IndexSearcher(r);
			
			//System.out.println("Set up " + getName());
		}

		public virtual void  SetUp()
		{
			// Create an index writer.
			directory = new RAMDirectory();
			IndexWriter writer = new IndexWriter(directory, new WhitespaceAnalyzer(), true);

			// oldest doc:
			// Add the first document.  text = "Document 1"  dateTime = Oct 10 03:25:22 EDT 2007
			writer.AddDocument(CreateDocument("Document 1", 633275835220000000L));
			// Add the second document.  text = "Document 2"  dateTime = Oct 10 03:25:26 EDT 2007 
			writer.AddDocument(CreateDocument("Document 2", 633275835260000000L));
			// Add the third document.  text = "Document 3"  dateTime = Oct 11 07:12:13 EDT 2007 
			writer.AddDocument(CreateDocument("Document 3", 633276835330000000L));
			// Add the fourth document.  text = "Document 4"  dateTime = Oct 11 08:02:09 EDT 2007
			writer.AddDocument(CreateDocument("Document 4", 633276865290000000L));
			// latest doc:
			// Add the fifth document.  text = "Document 5"  dateTime = Oct 12 13:25:43 EDT 2007
			writer.AddDocument(CreateDocument("Document 5", 633277923430000000L));

			//// oldest doc:
			//// Add the first document.  text = "Document 1"  dateTime = Oct 10 03:25:22 EDT 2007
			//writer.AddDocument(CreateDocument("Document 1", 1192001122000L));
			//// Add the second document.  text = "Document 2"  dateTime = Oct 10 03:25:26 EDT 2007 
			//writer.AddDocument(CreateDocument("Document 2", 1192001126000L));
			//// Add the third document.  text = "Document 3"  dateTime = Oct 11 07:12:13 EDT 2007 
			//writer.AddDocument(CreateDocument("Document 3", 1192101133000L));
			//// Add the fourth document.  text = "Document 4"  dateTime = Oct 11 08:02:09 EDT 2007
			//writer.AddDocument(CreateDocument("Document 4", 1192104129000L));
			//// latest doc:
			//// Add the fifth document.  text = "Document 5"  dateTime = Oct 12 13:25:43 EDT 2007
			//writer.AddDocument(CreateDocument("Document 5", 1192209943000L));
			
			writer.Optimize();
			writer.Close();
		}

		public static void  Main(System.String[] args)
		{
			System.String usage = typeof(IndexFiles) + " <root_directory>";
			if (args.Length == 0)
			{
				System.Console.Error.WriteLine("Usage: " + usage);
				System.Environment.Exit(1);
			}
			
			System.DateTime start = System.DateTime.Now;
			try
			{
				IndexWriter writer = new IndexWriter("index", new StandardAnalyzer(), true);
                IndexDocs(writer, new System.IO.FileInfo(args[0]));
				
				writer.Optimize();
				writer.Close();
				
				System.DateTime end = System.DateTime.Now;
				
				System.Console.Out.Write(end.Ticks - start.Ticks);
				System.Console.Out.WriteLine(" total milliseconds");
			}
			catch (System.IO.IOException e)
			{
				System.Console.Out.WriteLine(" caught a " + e.GetType() + "\n with message: " + e.Message);
			}
		}

		public virtual void  CreateRandomTerms(int nDocs, int nTerms, double power, Directory dir)
		{
			int[] freq = new int[nTerms];
			for (int i = 0; i < nTerms; i++)
			{
				int f = (nTerms + 1) - i; // make first terms less frequent
				freq[i] = (int) System.Math.Ceiling(System.Math.Pow(f, power));
				terms[i] = new Term("f", System.Convert.ToString((char) ('A' + i)));
			}
			
			IndexWriter iw = new IndexWriter(dir, new WhitespaceAnalyzer(), true);
			for (int i = 0; i < nDocs; i++)
			{
				Document d = new Document();
				for (int j = 0; j < nTerms; j++)
				{
					if (r.Next(freq[j]) == 0)
					{
						d.Add(new Field("f", terms[j].Text(), Field.Store.NO, Field.Index.UN_TOKENIZED));
						//System.out.println(d);
					}
				}
				iw.AddDocument(d);
			}
			iw.Optimize();
			iw.Close();
		}

        public void SearchFiltered(IndexWriter writer, Directory directory, Filter filter, bool optimize)
        {
            try
            {
                for (int i = 0; i < 60; i++)
                {//Simple docs
                    Document doc = new Document();
                    doc.Add(new Field(FIELD, i.ToString(), Field.Store.YES, Field.Index.NOT_ANALYZED));
                    writer.AddDocument(doc);
                }
                if (optimize)
                    writer.Optimize();
                writer.Close();

                BooleanQuery booleanQuery = new BooleanQuery();
                booleanQuery.Add(new TermQuery(new Term(FIELD, "36")), Occur.SHOULD);


                IndexSearcher indexSearcher = new IndexSearcher(directory);
                ScoreDoc[] hits = indexSearcher.Search(booleanQuery, filter, 1000).ScoreDocs;
                Assert.AreEqual(1, hits.Length, "Number of matched documents");

            }
            catch (System.IO.IOException e)
            {
                Assert.Fail(e.Message);
            }

        }

        public static void Main(System.String[] args)
        {
            System.DateTime start = System.DateTime.Now;
            try
            {
                var writer = new Lucene.Net.Index.IndexWriter(Lucene.Net.Store.FSDirectory.Open(INDEX_DIR),
                    new Lucene.Net.Analysis.Standard.StandardAnalyzer(Lucene.Net.Util.Version.LUCENE_CURRENT),
                    true,
                    Lucene.Net.Index.IndexWriter.MaxFieldLength.LIMITED);
                System.Console.Out.WriteLine("Indexing to directory '" + INDEX_DIR + "'...");

                // want to clean up if indexing gets "cancelled"
                try {
                    parse_email_messages(writer);
                }
                catch (Exception e)
                {
                    System.Console.Out.WriteLine(" caught a " + e.GetType() + "\n with message: " + e.Message);
                }

                System.Console.Out.WriteLine(System.DateTime.Now.Millisecond - start.Millisecond + "ms inserting docs");
                System.Console.Out.WriteLine("Optimizing...");

                writer.Optimize();
                writer.Close();

                System.Console.Out.WriteLine(System.DateTime.Now.Millisecond - start.Millisecond + "ms total");
            }
            catch (System.IO.IOException e)
            {
                System.Console.Out.WriteLine(" caught a " + e.GetType() + "\n with message: " + e.Message);
            }
        }

		public virtual void  TestPhrasePrefix()
		{
			RAMDirectory indexStore = new RAMDirectory();
			IndexWriter writer = new IndexWriter(indexStore, new SimpleAnalyzer(), true, IndexWriter.MaxFieldLength.LIMITED);
			Document doc1 = new Document();
			Document doc2 = new Document();
			Document doc3 = new Document();
			Document doc4 = new Document();
			Document doc5 = new Document();
			doc1.Add(new Field("body", "blueberry pie", Field.Store.YES, Field.Index.ANALYZED));
			doc2.Add(new Field("body", "blueberry strudel", Field.Store.YES, Field.Index.ANALYZED));
			doc3.Add(new Field("body", "blueberry pizza", Field.Store.YES, Field.Index.ANALYZED));
			doc4.Add(new Field("body", "blueberry chewing gum", Field.Store.YES, Field.Index.ANALYZED));
			doc5.Add(new Field("body", "piccadilly circus", Field.Store.YES, Field.Index.ANALYZED));
			writer.AddDocument(doc1);
			writer.AddDocument(doc2);
			writer.AddDocument(doc3);
			writer.AddDocument(doc4);
			writer.AddDocument(doc5);
			writer.Optimize();
			writer.Close();
			
			IndexSearcher searcher = new IndexSearcher(indexStore);
			
			//PhrasePrefixQuery query1 = new PhrasePrefixQuery();
			MultiPhraseQuery query1 = new MultiPhraseQuery();
			//PhrasePrefixQuery query2 = new PhrasePrefixQuery();
			MultiPhraseQuery query2 = new MultiPhraseQuery();
			query1.Add(new Term("body", "blueberry"));
			query2.Add(new Term("body", "strawberry"));
			
			System.Collections.ArrayList termsWithPrefix = new System.Collections.ArrayList();
			IndexReader ir = IndexReader.Open(indexStore);
			
			// this TermEnum gives "piccadilly", "pie" and "pizza".
			System.String prefix = "pi";
			TermEnum te = ir.Terms(new Term("body", prefix + "*"));
			do 
			{
				if (te.Term().Text().StartsWith(prefix))
				{
					termsWithPrefix.Add(te.Term());
				}
			}
			while (te.Next());
			
			query1.Add((Term[]) termsWithPrefix.ToArray(typeof(Term)));
			query2.Add((Term[]) termsWithPrefix.ToArray(typeof(Term)));
			
			ScoreDoc[] result;
			result = searcher.Search(query1, null, 1000).scoreDocs;
			Assert.AreEqual(2, result.Length);
			
			result = searcher.Search(query2, null, 1000).scoreDocs;
			Assert.AreEqual(0, result.Length);
		}

		public virtual void  TestBefore()
		{
			// create an index
			RAMDirectory indexStore = new RAMDirectory();
			IndexWriter writer = new IndexWriter(indexStore, new SimpleAnalyzer(), true);
			
			long now = (long) (DateTime.UtcNow - new DateTime(1970, 1, 1)).TotalMilliseconds;
			
			Lucene.Net.Documents.Document doc = new Lucene.Net.Documents.Document();
			// add time that is in the past
			doc.Add(new Field("datefield", Lucene.Net.Documents.DateTools.TimeToString(now - 1000 * 100000, Lucene.Net.Documents.DateTools.Resolution.MILLISECOND), Field.Store.YES, Field.Index.UN_TOKENIZED));
			doc.Add(new Field("body", "Today is a very sunny day in New York City", Field.Store.YES, Field.Index.TOKENIZED));
			writer.AddDocument(doc);
			writer.Optimize();
			writer.Close();
			
			IndexSearcher searcher = new IndexSearcher(indexStore);
			
			// filter that should preserve matches
			//DateFilter df1 = DateFilter.Before("datefield", now);
			RangeFilter df1 = new RangeFilter("datefield", Lucene.Net.Documents.DateTools.TimeToString(now - 2000 * 100000, Lucene.Net.Documents.DateTools.Resolution.MILLISECOND), Lucene.Net.Documents.DateTools.TimeToString(now, Lucene.Net.Documents.DateTools.Resolution.MILLISECOND), false, true);
			// filter that should discard matches
			//DateFilter df2 = DateFilter.Before("datefield", now - 999999);
			RangeFilter df2 = new RangeFilter("datefield", Lucene.Net.Documents.DateTools.TimeToString(0, Lucene.Net.Documents.DateTools.Resolution.MILLISECOND), Lucene.Net.Documents.DateTools.TimeToString(now - 2000 * 100000, Lucene.Net.Documents.DateTools.Resolution.MILLISECOND), true, false);
			
			// search something that doesn't exist with DateFilter
			Query query1 = new TermQuery(new Term("body", "NoMatchForThis"));
			
			// search for something that does exists
			Query query2 = new TermQuery(new Term("body", "sunny"));
			
			Hits result;
			
			// ensure that queries return expected results without DateFilter first
			result = searcher.Search(query1);
			Assert.AreEqual(0, result.Length());
			
			result = searcher.Search(query2);
			Assert.AreEqual(1, result.Length());
			
			
			// run queries with DateFilter
			result = searcher.Search(query1, df1);
			Assert.AreEqual(0, result.Length());
			
			result = searcher.Search(query1, df2);
			Assert.AreEqual(0, result.Length());
			
			result = searcher.Search(query2, df1);
			Assert.AreEqual(1, result.Length());
			
			result = searcher.Search(query2, df2);
			Assert.AreEqual(0, result.Length());
		}

        public virtual void  TestBefore()
        {
            // create an index
            RAMDirectory indexStore = new RAMDirectory();
            IndexWriter writer = new IndexWriter(indexStore, new SimpleAnalyzer(), true, IndexWriter.MaxFieldLength.LIMITED);
            
            long now = (DateTime.Now.Ticks / TimeSpan.TicksPerMillisecond);
            
            Document doc = new Document();
            // add time that is in the past
            doc.Add(new Field("datefield", DateTools.TimeToString(now - 1000, DateTools.Resolution.MILLISECOND), Field.Store.YES, Field.Index.NOT_ANALYZED));
            doc.Add(new Field("body", "Today is a very sunny day in New York City", Field.Store.YES, Field.Index.ANALYZED));
            writer.AddDocument(doc);
            writer.Optimize();
            writer.Close();

            IndexSearcher searcher = new IndexSearcher(indexStore, true);
            
            // filter that should preserve matches
            //DateFilter df1 = DateFilter.Before("datefield", now);
            TermRangeFilter df1 = new TermRangeFilter("datefield", DateTools.TimeToString(now - 2000, DateTools.Resolution.MILLISECOND), DateTools.TimeToString(now, DateTools.Resolution.MILLISECOND), false, true);
            // filter that should discard matches
            //DateFilter df2 = DateFilter.Before("datefield", now - 999999);
            TermRangeFilter df2 = new TermRangeFilter("datefield", DateTools.TimeToString(0, DateTools.Resolution.MILLISECOND), DateTools.TimeToString(now - 2000, DateTools.Resolution.MILLISECOND), true, false);
            
            // search something that doesn't exist with DateFilter
            Query query1 = new TermQuery(new Term("body", "NoMatchForThis"));
            
            // search for something that does exists
            Query query2 = new TermQuery(new Term("body", "sunny"));
            
            ScoreDoc[] result;
            
            // ensure that queries return expected results without DateFilter first
            result = searcher.Search(query1, null, 1000).ScoreDocs;
            Assert.AreEqual(0, result.Length);
            
            result = searcher.Search(query2, null, 1000).ScoreDocs;
            Assert.AreEqual(1, result.Length);
            
            
            // run queries with DateFilter
            result = searcher.Search(query1, df1, 1000).ScoreDocs;
            Assert.AreEqual(0, result.Length);
            
            result = searcher.Search(query1, df2, 1000).ScoreDocs;
            Assert.AreEqual(0, result.Length);
            
            result = searcher.Search(query2, df1, 1000).ScoreDocs;
            Assert.AreEqual(1, result.Length);
            
            result = searcher.Search(query2, df2, 1000).ScoreDocs;
            Assert.AreEqual(0, result.Length);
        }

		public virtual void  SetUp()
		{
			// Create an index writer.
			directory = new RAMDirectory();
			IndexWriter writer = new IndexWriter(directory, new WhitespaceAnalyzer(), true);
			for (int i = 0; i < N; i++)
			{
				writer.AddDocument(CreateDocument(i));
			}
			writer.Optimize();
			writer.Close();
		}

		public virtual void  TestBefore()
		{
			// create an index
			RAMDirectory indexStore = new RAMDirectory();
			IndexWriter writer = new IndexWriter(indexStore, new SimpleAnalyzer(), true);
			
			long now = (System.DateTime.Now.Ticks - 621355968000000000) / 10000;
			
			Document doc = new Document();
			// add time that is in the past
			doc.Add(Field.Keyword("datefield", DateField.TimeToString(now - 1000)));
			doc.Add(Field.Text("body", "Today is a very sunny day in New York City"));
			writer.AddDocument(doc);
			writer.Optimize();
			writer.Close();
			
			IndexSearcher searcher = new IndexSearcher(indexStore);
			
			// filter that should preserve matches
			DateFilter df1 = DateFilter.Before("datefield", now);
			
			// filter that should discard matches
			DateFilter df2 = DateFilter.Before("datefield", now - 999999);
			
			// search something that doesn't exist with DateFilter
			Query query1 = new TermQuery(new Term("body", "NoMatchForThis"));
			
			// search for something that does exists
			Query query2 = new TermQuery(new Term("body", "sunny"));
			
			Hits result;
			
			// ensure that queries return expected results without DateFilter first
			result = searcher.Search(query1);
			Assert.AreEqual(0, result.Length());
			
			result = searcher.Search(query2);
			Assert.AreEqual(1, result.Length());
			
			
			// run queries with DateFilter
			result = searcher.Search(query1, df1);
			Assert.AreEqual(0, result.Length());
			
			result = searcher.Search(query1, df2);
			Assert.AreEqual(0, result.Length());
			
			result = searcher.Search(query2, df1);
			Assert.AreEqual(1, result.Length());
			
			result = searcher.Search(query2, df2);
			Assert.AreEqual(0, result.Length());
		}

		public override void  SetUp()
		{
			base.SetUp();
			// Create an index writer.
			directory = new RAMDirectory();
			IndexWriter writer = new IndexWriter(directory, new WhitespaceAnalyzer(), true, IndexWriter.MaxFieldLength.LIMITED);
			for (int i = 0; i < N; i++)
			{
				writer.AddDocument(CreateDocument(i));
			}
			writer.Optimize();
			writer.Close();
		}

		public static void  Main(System.String[] args)
		{
			System.String usage = typeof(IndexFiles) + " <root_directory>";
			if (args.Length == 0)
			{
				System.Console.Error.WriteLine("Usage: " + usage);
				System.Environment.Exit(1);
			}
			
			bool tmpBool;
			if (System.IO.File.Exists(INDEX_DIR.FullName))
				tmpBool = true;
			else
				tmpBool = System.IO.Directory.Exists(INDEX_DIR.FullName);
			if (tmpBool)
			{
				System.Console.Out.WriteLine("Cannot save index to '" + INDEX_DIR + "' directory, please delete it first");
				System.Environment.Exit(1);
			}
			
			System.IO.FileInfo docDir = new System.IO.FileInfo(args[0]);
			bool tmpBool2;
			if (System.IO.File.Exists(docDir.FullName))
				tmpBool2 = true;
			else
				tmpBool2 = System.IO.Directory.Exists(docDir.FullName);
			if (!tmpBool2) // || !docDir.canRead()) // {{Aroush}} what is canRead() in C#?
			{
				System.Console.Out.WriteLine("Document directory '" + docDir.FullName + "' does not exist or is not readable, please check the path");
				System.Environment.Exit(1);
			}
			
			System.DateTime start = System.DateTime.Now;
			try
			{
				IndexWriter writer = new IndexWriter(FSDirectory.Open(INDEX_DIR), new StandardAnalyzer(Version.LUCENE_CURRENT), true, IndexWriter.MaxFieldLength.LIMITED);
				System.Console.Out.WriteLine("Indexing to directory '" + INDEX_DIR + "'...");
				IndexDocs(writer, docDir);
				System.Console.Out.WriteLine("Optimizing...");
				writer.Optimize();
				writer.Close();                
				
				System.DateTime end = System.DateTime.Now;
				System.Console.Out.WriteLine(end.Millisecond - start.Millisecond + " total milliseconds");
			}
			catch (System.IO.IOException e)
			{
				System.Console.Out.WriteLine(" caught a " + e.GetType() + "\n with message: " + e.Message);
			}
		}

		public virtual void  SetUp()
		{
			directory = new RAMDirectory();
			IndexWriter writer = new IndexWriter(directory, new WhitespaceAnalyzer(), true);
			
			Document doc = new Document();
			doc.Add(Field.Text("Field", "one two three four five"));
			writer.AddDocument(doc);
			
			writer.Optimize();
			writer.Close();
			
			searcher = new IndexSearcher(directory);
			query = new PhraseQuery();
		}

		private static void  StartServer()
		{
			// construct an index
			RAMDirectory indexStore = new RAMDirectory();
			IndexWriter writer = new IndexWriter(indexStore, new SimpleAnalyzer(), true);
			Document doc = new Document();
			doc.Add(Field.Text("test", "test text"));
			writer.AddDocument(doc);
			writer.Optimize();
			writer.Close();
			
			// publish it
			//// LocateRegistry.CreateRegistry(1099); // {{Aroush}}
			Lucene.Net.Search.Searchable local = new IndexSearcher(indexStore);
			RemoteSearchable impl = new RemoteSearchable(local);
			System.Runtime.Remoting.RemotingServices.Marshal(impl, "http://localhost/Searchable");
		}