C# Lucene.Net.Search.IndexSearcher.SetSimilarity方法代码示例

		public override void  SetUp()
		{
			base.SetUp();
			RAMDirectory directory = new RAMDirectory();
			PayloadAnalyzer analyzer = new PayloadAnalyzer(this);
			IndexWriter writer = new IndexWriter(directory, analyzer, true, IndexWriter.MaxFieldLength.LIMITED);
			writer.SetSimilarity(similarity);
			//writer.infoStream = System.out;
			for (int i = 0; i < 1000; i++)
			{
				Document doc = new Document();
				Field noPayloadField = new Field(PayloadHelper.NO_PAYLOAD_FIELD, English.IntToEnglish(i), Field.Store.YES, Field.Index.ANALYZED);
				//noPayloadField.setBoost(0);
				doc.Add(noPayloadField);
				doc.Add(new Field("field", English.IntToEnglish(i), Field.Store.YES, Field.Index.ANALYZED));
				doc.Add(new Field("multiField", English.IntToEnglish(i) + "  " + English.IntToEnglish(i), Field.Store.YES, Field.Index.ANALYZED));
				writer.AddDocument(doc);
			}
			writer.Optimize();
			writer.Close();
			
			searcher = new IndexSearcher(directory);
			searcher.SetSimilarity(similarity);
		}

		public virtual void  TestIgnoreSpanScorer()
		{
			PayloadTermQuery query = new PayloadTermQuery(new Term(PayloadHelper.MULTI_FIELD, "seventy"), new MaxPayloadFunction(), false);
			
			IndexSearcher theSearcher = new IndexSearcher(directory, true);
			theSearcher.SetSimilarity(new FullSimilarity());
			TopDocs hits = searcher.Search(query, null, 100);
			Assert.IsTrue(hits != null, "hits is null and it shouldn't be");
			Assert.IsTrue(hits.totalHits == 100, "hits Size: " + hits.totalHits + " is not: " + 100);
			
			//they should all have the exact same score, because they all contain seventy once, and we set
			//all the other similarity factors to be 1
			
			//System.out.println("Hash: " + seventyHash + " Twice Hash: " + 2*seventyHash);
			Assert.IsTrue(hits.GetMaxScore() == 4.0, hits.GetMaxScore() + " does not equal: " + 4.0);
			//there should be exactly 10 items that score a 4, all the rest should score a 2
			//The 10 items are: 70 + i*100 where i in [0-9]
			int numTens = 0;
			for (int i = 0; i < hits.scoreDocs.Length; i++)
			{
				ScoreDoc doc = hits.scoreDocs[i];
				if (doc.doc % 10 == 0)
				{
					numTens++;
					Assert.IsTrue(doc.score == 4.0, doc.score + " does not equal: " + 4.0);
				}
				else
				{
					Assert.IsTrue(doc.score == 2, doc.score + " does not equal: " + 2);
				}
			}
			Assert.IsTrue(numTens == 10, numTens + " does not equal: " + 10);
			CheckHits.CheckExplanations(query, "field", searcher, true);
			Lucene.Net.Search.Spans.Spans spans = query.GetSpans(searcher.GetIndexReader());
			Assert.IsTrue(spans != null, "spans is null and it shouldn't be");
			Assert.IsTrue(spans is TermSpans, "spans is not an instanceof " + typeof(TermSpans));
			//should be two matches per document
			int count = 0;
			//100 hits times 2 matches per hit, we should have 200 in count
			while (spans.Next())
			{
				count++;
			}
		}

		public virtual IndexSearcher GetSpanNotSearcher()
		{
			RAMDirectory directory = new RAMDirectory();
			PayloadAnalyzer analyzer = new PayloadAnalyzer(this);
			IndexWriter writer = new IndexWriter(directory, analyzer, true);
			writer.SetSimilarity(similarity);
			
			Document doc = new Document();
			doc.Add(new Field(PayloadHelper.FIELD, "one two three one four three", Field.Store.YES, Field.Index.ANALYZED));
			writer.AddDocument(doc);
			
			writer.Close();
			
			IndexSearcher searcher = new IndexSearcher(directory);
			searcher.SetSimilarity(similarity);
			return searcher;
		}

		public override void  SetUp()
		{
			base.SetUp();
			RAMDirectory directory = new RAMDirectory();
			PayloadAnalyzer analyzer = new PayloadAnalyzer(this);
			IndexWriter writer = new IndexWriter(directory, analyzer, true, IndexWriter.MaxFieldLength.LIMITED);
			writer.SetSimilarity(similarity);
			//writer.infoStream = System.out;
			for (int i = 0; i < 1000; i++)
			{
				Document doc = new Document();
				doc.Add(new Field("field", English.IntToEnglish(i), Field.Store.YES, Field.Index.ANALYZED));
				System.String txt = English.IntToEnglish(i) + ' ' + English.IntToEnglish(i + 1);
				doc.Add(new Field("field2", txt, Field.Store.YES, Field.Index.ANALYZED));
				writer.AddDocument(doc);
			}
			writer.Optimize();
			writer.Close();
			
			searcher = new IndexSearcher(directory, true);
			searcher.SetSimilarity(similarity);
		}

		public virtual void  TestBasic()
		{
			Directory dir = new MockRAMDirectory();
			Analyzer analyzer = new StandardAnalyzer();
			IndexWriter writer = new IndexWriter(dir, analyzer, true, IndexWriter.MaxFieldLength.LIMITED);
			writer.SetMergeFactor(2);
			writer.SetMaxBufferedDocs(2);
			writer.SetSimilarity(new SimpleSimilarity());
			
			
			System.Text.StringBuilder sb = new System.Text.StringBuilder(265);
			System.String term = "term";
			for (int i = 0; i < 30; i++)
			{
				Document d = new Document();
				sb.Append(term).Append(" ");
				System.String content = sb.ToString();
				Field noTf = new Field("noTf", content + (i % 2 == 0?"":" notf"), Field.Store.NO, Field.Index.ANALYZED);
				noTf.SetOmitTermFreqAndPositions(true);
				d.Add(noTf);
				
				Field tf = new Field("tf", content + (i % 2 == 0?" tf":""), Field.Store.NO, Field.Index.ANALYZED);
				d.Add(tf);
				
				writer.AddDocument(d);
				//System.out.println(d);
			}
			
			writer.Optimize();
			// flush
			writer.Close();
			_TestUtil.CheckIndex(dir);
			
			/*
			* Verify the index
			*/
			Searcher searcher = new IndexSearcher(dir);
			searcher.SetSimilarity(new SimpleSimilarity());
			
			Term a = new Term("noTf", term);
			Term b = new Term("tf", term);
			Term c = new Term("noTf", "notf");
			Term d2 = new Term("tf", "tf");
			TermQuery q1 = new TermQuery(a);
			TermQuery q2 = new TermQuery(b);
			TermQuery q3 = new TermQuery(c);
			TermQuery q4 = new TermQuery(d2);
			
			
			searcher.Search(q1, new AnonymousClassCountingHitCollector(this));
			//System.out.println(CountingHitCollector.getCount());
			
			
			searcher.Search(q2, new AnonymousClassCountingHitCollector1(this));
			//System.out.println(CountingHitCollector.getCount());
			
			
			
			
			
			searcher.Search(q3, new AnonymousClassCountingHitCollector2(this));
			//System.out.println(CountingHitCollector.getCount());
			
			
			searcher.Search(q4, new AnonymousClassCountingHitCollector3(this));
			//System.out.println(CountingHitCollector.getCount());
			
			
			
			BooleanQuery bq = new BooleanQuery();
			bq.Add(q1, Occur.MUST);
			bq.Add(q4, Occur.MUST);
			
			searcher.Search(bq, new AnonymousClassCountingHitCollector4(this));
			Assert.IsTrue(15 == CountingHitCollector.GetCount());
			
			searcher.Close();
			dir.Close();
		}

		/// <summary> Sets up a RAMDirectory, and adds documents (using English.intToEnglish()) with two fields: field and multiField
		/// and analyzes them using the PayloadAnalyzer
		/// </summary>
		/// <param name="similarity">The Similarity class to use in the Searcher
		/// </param>
		/// <param name="numDocs">The num docs to add
		/// </param>
		/// <returns> An IndexSearcher
		/// </returns>
		/// <throws>  IOException </throws>
		public virtual IndexSearcher SetUp(Similarity similarity, int numDocs)
		{
			RAMDirectory directory = new RAMDirectory();
			PayloadAnalyzer analyzer = new PayloadAnalyzer(this);
			IndexWriter writer = new IndexWriter(directory, analyzer, true);
			writer.SetSimilarity(similarity);
			//writer.infoStream = System.out;
			for (int i = 0; i < numDocs; i++)
			{
				Document doc = new Document();
				doc.Add(new Field(FIELD, English.IntToEnglish(i), Field.Store.YES, Field.Index.ANALYZED));
				doc.Add(new Field(MULTI_FIELD, English.IntToEnglish(i) + "  " + English.IntToEnglish(i), Field.Store.YES, Field.Index.ANALYZED));
				doc.Add(new Field(NO_PAYLOAD_FIELD, English.IntToEnglish(i), Field.Store.YES, Field.Index.ANALYZED));
				writer.AddDocument(doc);
			}
			//writer.optimize();
			writer.Close();
			
			IndexSearcher searcher = new IndexSearcher(directory);
			searcher.SetSimilarity(similarity);
			return searcher;
		}