C# IndexSearcher.Search方法代码示例

        public ActionResult Search(string query)
        {
            ViewData["Message"] = "query : " + query;

            var searcher = new IndexSearcher(
                new Lucene.Net.Store.SimpleFSDirectory(new DirectoryInfo(Configuration.IndexDirectory)),
                readOnly: true);

            var fieldsToSearchIn = new[] {Configuration.Fields.Name, Configuration.Fields.Description};
            var queryanalizer = new MultiFieldQueryParser(Version.LUCENE_CURRENT,
                                                          fieldsToSearchIn,
                                                          new BrazilianAnalyzer());

            var numberOfResults = 10;
            var top10Results = searcher.Search(queryanalizer.Parse(query), numberOfResults);
            var docs = new List<DocumentViewModel>();
            foreach (var scoreDoc in top10Results.scoreDocs)
            {
                var document = searcher.Doc(scoreDoc.doc);
                var name = document.GetField(Configuration.Fields.Name).StringValue();
                var description = document.GetField(Configuration.Fields.Description).StringValue();
                var link = document.GetField(Configuration.Fields.Link).StringValue();
                docs.Add(new DocumentViewModel(name, description, link));
            }
            return View(new SearchViewModel(docs));
        }

		public virtual void  TestBasic()
		{
			Directory dir = new RAMDirectory();
			IndexWriter writer = new IndexWriter(dir, new StandardAnalyzer(), true, IndexWriter.MaxFieldLength.LIMITED);
			Document doc = new Document();
			doc.Add(new Field("field", "value", Field.Store.NO, Field.Index.ANALYZED));
			writer.AddDocument(doc);
			writer.Close();
			
			TermQuery termQuery = new TermQuery(new Term("field", "value"));
			
			// should not throw exception with primitive query
			QueryWrapperFilter qwf = new QueryWrapperFilter(termQuery);
			
			IndexSearcher searcher = new IndexSearcher(dir, true);
			TopDocs hits = searcher.Search(new MatchAllDocsQuery(), qwf, 10);
			Assert.AreEqual(1, hits.totalHits);
			
			// should not throw exception with complex primitive query
			BooleanQuery booleanQuery = new BooleanQuery();
			booleanQuery.Add(termQuery, Occur.MUST);
			booleanQuery.Add(new TermQuery(new Term("field", "missing")), Occur.MUST_NOT);
			qwf = new QueryWrapperFilter(termQuery);
			
			hits = searcher.Search(new MatchAllDocsQuery(), qwf, 10);
			Assert.AreEqual(1, hits.totalHits);
			
			// should not throw exception with non primitive Query (doesn't implement
			// Query#createWeight)
			qwf = new QueryWrapperFilter(new FuzzyQuery(new Term("field", "valu")));
			
			hits = searcher.Search(new MatchAllDocsQuery(), qwf, 10);
			Assert.AreEqual(1, hits.totalHits);
		}

		public virtual void  TestQuery()
		{
			RAMDirectory dir = new RAMDirectory();
			IndexWriter iw = new IndexWriter(dir, new StandardAnalyzer(), true);
			AddDoc("one", iw);
			AddDoc("two", iw);
			AddDoc("three four", iw);
			iw.Close();
			
			IndexSearcher is_Renamed = new IndexSearcher(dir);
			Hits hits = is_Renamed.Search(new MatchAllDocsQuery());
			Assert.AreEqual(3, hits.Length());
			
			// some artificial queries to trigger the use of skipTo():
			
			BooleanQuery bq = new BooleanQuery();
			bq.Add(new MatchAllDocsQuery(), BooleanClause.Occur.MUST);
			bq.Add(new MatchAllDocsQuery(), BooleanClause.Occur.MUST);
			hits = is_Renamed.Search(bq);
			Assert.AreEqual(3, hits.Length());
			
			bq = new BooleanQuery();
			bq.Add(new MatchAllDocsQuery(), BooleanClause.Occur.MUST);
			bq.Add(new TermQuery(new Term("key", "three")), BooleanClause.Occur.MUST);
			hits = is_Renamed.Search(bq);
			Assert.AreEqual(1, hits.Length());
			
			// delete a document:
			is_Renamed.GetIndexReader().DeleteDocument(0);
			hits = is_Renamed.Search(new MatchAllDocsQuery());
			Assert.AreEqual(2, hits.Length());
			
			is_Renamed.Close();
		}

        public void TestTermSearch()
        {
            using (var dir = FSDirectory.Open(TestEnvironment.TestIndexDirectory))
            using (var indexSearcher = new IndexSearcher(dir))
            {
                var termSubjectAnt = new Term("subject", "ant");
                var termQuerySubjectAnt = new TermQuery(termSubjectAnt);
                var topDocsSubjectAnt = indexSearcher.Search(termQuerySubjectAnt, 10);

                // title=Ant in Action
                // subject=apache ant build tool junit java development
                Assert.Equal(1, topDocsSubjectAnt.TotalHits);


                var termSubjectJUnit = new Term("subject", "junit");
                var termQuerySubjectJUnit = new TermQuery(termSubjectJUnit);
                var topDocsSubjectJUnit = indexSearcher.Search(termQuerySubjectJUnit, 10);

//                ExplainResults(indexSearcher, termQuerySubjectJUnit, topDocsSubjectJUnit);

                // title=JUnit in Action, Second Edition
                // subject=junit unit testing mock objects

                // title=Ant in Action
                // subject=apache ant build tool junit java development
                Assert.Equal(2, topDocsSubjectJUnit.TotalHits); // Ants in Action, "JUnit in Action, Second Edition"
            }

        }

		// main search method
		private static IEnumerable<SampleData> _search(string searchQuery, string searchField = "") {
			// validation
			if (string.IsNullOrEmpty(searchQuery.Replace("*", "").Replace("?", ""))) return new List<SampleData>();

			// set up lucene searcher
			using (var searcher = new IndexSearcher(_directory, false)) {
				var hits_limit = 1000;
				var analyzer = new StandardAnalyzer(Version.LUCENE_30);

				// search by single field
				if (!string.IsNullOrEmpty(searchField)) {
					var parser = new QueryParser(Version.LUCENE_30, searchField, analyzer);
					var query = parseQuery(searchQuery, parser);
					var hits = searcher.Search(query, hits_limit).ScoreDocs;
					var results = _mapLuceneToDataList(hits, searcher);
					analyzer.Close();
					searcher.Dispose();
					return results;
				}
				// search by multiple fields (ordered by RELEVANCE)
				else {
					var parser = new MultiFieldQueryParser
						(Version.LUCENE_30, new[] {"Id", "Name", "Description"}, analyzer);
					var query = parseQuery(searchQuery, parser);
					var hits = searcher.Search(query, null, hits_limit, Sort.INDEXORDER).ScoreDocs;
					var results = _mapLuceneToDataList(hits, searcher);
					analyzer.Close();
					searcher.Dispose();
					return results;
				}
			}
		}

        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);
        }

        /// <summary>
        /// Searches the index.
        /// </summary>
        /// <param name="queryText"></param>
        /// <param name="keywordFilter">A Hashtable where the key is the fieldname of the keyword and 
        /// the value the keyword itself.</param>
        /// <param name="pageIndex"></param>
        /// <param name="pageSize"></param>
        /// <returns></returns>
        public SearchResultCollection Find(string queryText, Hashtable keywordFilter, int pageIndex, int pageSize)
        {
            long startTicks = DateTime.Now.Ticks;

            Hits hits;
            try
            {
                Query query = MultiFieldQueryParser.Parse(queryText, new string[] {"title", "contents"}, new StandardAnalyzer());
                IndexSearcher searcher = new IndexSearcher(this._indexDirectory);

                if (keywordFilter != null && keywordFilter.Count > 0)
                {
                    QueryFilter qf = BuildQueryFilterFromKeywordFilter(keywordFilter);
                    hits = searcher.Search(query, qf);
                }
                else
                {
                    hits = searcher.Search(query);
                }
                int start = pageIndex*pageSize;
                int end = (pageIndex + 1)*pageSize;
                if (hits.Length() <= end)
                {
                    end = hits.Length();
                }
                SearchResultCollection results = new SearchResultCollection();
                results.TotalCount = hits.Length();
                results.PageIndex = pageIndex;

                for (int i = start; i < end; i++)
                {
                    SearchResult result = new SearchResult();
                    result.Title = hits.Doc(i).Get("title");
                    result.Summary = hits.Doc(i).Get("summary");
                    result.Author = hits.Doc(i).Get("author");
                    result.ModuleType = hits.Doc(i).Get("moduletype");
                    result.Path = hits.Doc(i).Get("path");
                    result.Category = hits.Doc(i).Get("category");
                    result.DateCreated = DateTime.Parse((hits.Doc(i).Get("datecreated")));
                    result.Score = hits.Score(i);
                    result.Boost = hits.Doc(i).GetBoost();
                    result.SectionId = Int32.Parse(hits.Doc(i).Get("sectionid"));
                    results.Add(result);
                }
                searcher.Close();
                results.ExecutionTime = DateTime.Now.Ticks - startTicks;

                return results;
            }
            catch (Exception ex)
            {
                throw new SearchException("Error while performing full-text search.", ex);
            }
        }

		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);
			
			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 void Initialize_Indexes_All_Nodes()
        {
            string elementIdForTestingSearch = _deepNodeFinder.GetNodesForIndexing()[0].Id;
            int expectedNumNodes = _deepNodeFinder.GetNodesForIndexing().Length;

            Assert.AreEqual("usfr-pte_NetCashFlowsProvidedUsedOperatingActivitiesDirectAbstract", elementIdForTestingSearch,
                            "TEST SANITY: element id for test search");
            Assert.AreEqual(1595, expectedNumNodes, "TEST SANITY: Number of nodes in found in the test taxonomy");

            IndexReader indexReader = IndexReader.Open(_indexMgr.LuceneDirectory_ForTesting);

            Assert.AreEqual(expectedNumNodes, indexReader.NumDocs(),
                            "An incorrect number of documents were found in the Lucene directory after initialization");

            IndexSearcher searcher = new IndexSearcher(_indexMgr.LuceneDirectory_ForTesting);
            try
            {
                Hits results =
                    searcher.Search(new TermQuery(new Term(LuceneNodeIndexer.ELEMENTID_FOR_DELETING_FIELD, elementIdForTestingSearch)));

                Assert.AreEqual(1, results.Length(), "Search results should only have 1 hit");
                Assert.AreEqual(elementIdForTestingSearch, results.Doc(0).Get(LuceneNodeIndexer.ELEMENTID_FIELD),
                                "Search results yielded the wrong element!");
            }
            finally
            {
                searcher.Close();
            }
        }

        private static IList<int> SearchCore(SearchFilter searchFilter, out int totalHits)
        {
            if (!Directory.Exists(LuceneCommon.IndexDirectory))
            {
                totalHits = 0;
                return new int[0];
            }

            SortField sortField = GetSortField(searchFilter);
            int numRecords = searchFilter.Skip + searchFilter.Take;

            using (var directory = new LuceneFileSystem(LuceneCommon.IndexDirectory))
            {
                var searcher = new IndexSearcher(directory, readOnly: true);
                var query = ParseQuery(searchFilter);

                var filterTerm = searchFilter.IncludePrerelease ? "IsLatest" : "IsLatestStable";
                var termQuery = new TermQuery(new Term(filterTerm, Boolean.TrueString));
                Filter filter = new QueryWrapperFilter(termQuery);
                

                var results = searcher.Search(query, filter: filter, n: numRecords, sort: new Sort(sortField));
                var keys = results.scoreDocs.Skip(searchFilter.Skip)
                                            .Select(c => ParseKey(searcher.Doc(c.doc).Get("Key")))
                                            .ToList();

                totalHits = results.totalHits;
                searcher.Close();
                return keys;
            }
        }

        public Data searchLucene(Data data)
        {
            Search_gl search = new Search_gl();
            List<string> item = new List<string>();
            Lucene.Net.Store.Directory directory = FSDirectory.Open(new DirectoryInfo(Environment.CurrentDirectory + "\\LuceneIndex"));
            var analyzer = new StandardAnalyzer(Version.LUCENE_29);

            IndexReader reader = IndexReader.Open(directory, true);
            IndexSearcher searcher = new IndexSearcher(reader);

            //QueryParser queryParser = new QueryParser(Version.LUCENE_29, "summary", analyzer);  //search for single field
            MultiFieldQueryParser parser = new MultiFieldQueryParser(new string[] {"name", "summary"}, analyzer);  //search for multifield
            Query query = parser.Parse((data.getString("search")) + "*"); //cant search blank text with wildcard as first character

            TopScoreDocCollector collector = TopScoreDocCollector.create(1000, true);
            searcher.Search(query, collector);
            ScoreDoc[] hits = collector.TopDocs().ScoreDocs;
            int count = hits.Length;

            for (int i = 0; i < count; i++)
            {
                int docId = hits[i].doc;
                float score = hits[i].score;

                Document doc = searcher.Doc(docId);

                string id = doc.Get("id");
                item.Add(id);
            }
            Data list = search.search(data, item.ToArray());
            reader.Close();
            searcher.Close();

            return list;
        }

        public Data searchLucene(Data data)
        {
            Account_lg account = new Account_lg();
            List<string> item = new List<string>();
            Lucene.Net.Store.Directory directory = FSDirectory.Open(new DirectoryInfo("C:\\Visual Studio 2010\\Transaction" + "\\LuceneIndex"));
            var analyzer = new StandardAnalyzer(Version.LUCENE_29);
            IndexReader reader = IndexReader.Open(directory, true);
            IndexSearcher searcher = new IndexSearcher(reader);

            MultiFieldQueryParser parser = new MultiFieldQueryParser(Lucene.Net.Util.Version.LUCENE_29, new string[] { "name", "username" }, analyzer);  //search for multifield
            Query query = parser.Parse((data.getString("search")) + "*"); //cant search blank text with wildcard as first character

            TopScoreDocCollector collector = TopScoreDocCollector.Create(1000, true);
            searcher.Search(query, collector);
            ScoreDoc[] hits = collector.TopDocs().ScoreDocs;
            int count = hits.Length;

            for (int i = 0; i < count; i++)
            {
                int docId = hits[i].Doc;
                float score = hits[i].Score;

                Document doc = searcher.Doc(docId);

                string id = doc.Get("id");
                item.Add(id);
            }
            Data list = account.selectUser(data, item.ToArray());
            reader.Dispose();
            searcher.Dispose();

            return list;
        }

		private void HandleRangeFacet(string index, Facet facet, IndexQuery indexQuery, IndexSearcher currentIndexSearcher, Dictionary<string, IEnumerable<FacetValue>> results)
		{
			var rangeResults = new List<FacetValue>();
			foreach (var range in facet.Ranges)
			{
				var baseQuery = database.IndexStorage.GetLuceneQuery(index, indexQuery, database.IndexQueryTriggers);
				//TODO the built-in parser can't handle [NULL TO 100.0}, i.e. a mix of [ and }
				//so we need to handle this ourselves (greater and less-than-or-equal)
				var rangeQuery = database.IndexStorage.GetLuceneQuery(index, new IndexQuery
				{
					Query = facet.Name + ":" + range
				}, database.IndexQueryTriggers);

				var joinedQuery = new BooleanQuery();
				joinedQuery.Add(baseQuery, BooleanClause.Occur.MUST);
				joinedQuery.Add(rangeQuery, BooleanClause.Occur.MUST);

				var topDocs = currentIndexSearcher.Search(joinedQuery, null, 1);

				if (topDocs.TotalHits > 0)
				{
					rangeResults.Add(new FacetValue
					{
						Count = topDocs.TotalHits,
						Range = range
					});
				}
			}

			results[facet.Name] = rangeResults;
		}

        public ProjectData[] Search(string searchTerm)
        {
            IndexSearcher searcher = new IndexSearcher(luceneIndexDirectory);
            IntegralCollector searcherCollector = new IntegralCollector();
            // Setup the fields to search through
            string[] searchfields = new string[] { "name", "vessel" };

            // Build our booleanquery that will be a combination of all the queries for each individual search term
            var finalQuery = new BooleanQuery();
            var parser = new MultiFieldQueryParser(Lucene.Net.Util.Version.LUCENE_30, searchfields, analyzer);

            // Split the search string into separate search terms by word
            string[] terms = searchTerm.Split(new[] { " " }, StringSplitOptions.RemoveEmptyEntries);
            foreach (string term in terms)
                finalQuery.Add(parser.Parse(term.Replace("~", "") + "~"),Occur.SHOULD);

            searcher.Search(finalQuery, searcherCollector);
            var results = new ProjectData[searcherCollector.Docs.Count];
            for (int i = 0; i < searcherCollector.Docs.Count; i++)
            {
                var doc = searcher.Doc(searcherCollector.Docs[i]);
                results[i] = new ProjectData(doc.Get("name"), doc.Get("vessel"));
            }
            return results;
        }