public virtual void TestPhraseQueryWithStopAnalyzer() { RAMDirectory directory = new RAMDirectory(); StopAnalyzer stopAnalyzer = new StopAnalyzer(); IndexWriter writer = new IndexWriter(directory, stopAnalyzer, true); Document doc = new Document(); doc.Add(Field.Text("Field", "the stop words are here")); writer.AddDocument(doc); writer.Close(); IndexSearcher searcher = new IndexSearcher(directory); // valid exact phrase query PhraseQuery query = new PhraseQuery(); query.Add(new Term("Field", "stop")); query.Add(new Term("Field", "words")); Hits hits = searcher.Search(query); Assert.AreEqual(1, hits.Length()); // currently StopAnalyzer does not leave "holes", so this matches. query = new PhraseQuery(); query.Add(new Term("Field", "words")); query.Add(new Term("Field", "here")); hits = searcher.Search(query); Assert.AreEqual(1, hits.Length()); searcher.Close(); }
public virtual void TestInclusiveLowerNull() { //http://issues.apache.org/jira/browse/LUCENE-38 Analyzer analyzer = new SingleCharAnalyzer(); Query query = new TermRangeQuery("content", null, "C", true, true); InitializeIndex(new System.String[] { "A", "B", "", "C", "D" }, analyzer); IndexSearcher searcher = new IndexSearcher(dir); Hits hits = searcher.Search(query); // When Lucene-38 is fixed, use the assert on the next line: Assert.AreEqual(4, hits.Length(), "A,B,<empty string>,C,D => A,B,<empty string>,C in range"); // until Lucene-38 is fixed, use this assert //Assert.AreEqual(3, hits.length(), "A,B,<empty string>,C,D => A,B,<empty string>,C in range"); searcher.Close(); InitializeIndex(new System.String[] { "A", "B", "", "D" }, analyzer); searcher = new IndexSearcher(dir); hits = searcher.Search(query); // When Lucene-38 is fixed, use the assert on the next line: Assert.AreEqual(3, hits.Length(), "A,B,<empty string>,D - A, B and <empty string> in range"); // until Lucene-38 is fixed, use this assert //Assert.AreEqual(2, hits.length(), "A,B,<empty string>,D => A, B and <empty string> in range"); searcher.Close(); AddDoc("C"); searcher = new IndexSearcher(dir); hits = searcher.Search(query); // When Lucene-38 is fixed, use the assert on the next line: Assert.AreEqual(4, hits.Length(), "C added => A,B,<empty string>,C in range"); // until Lucene-38 is fixed, use this assert //Assert.AreEqual(3, hits.length(), "C added => A,B,<empty string>,C in range"); searcher.Close(); }
public virtual void TestTermVectors_() { Query query = new TermQuery(new Term("Field", "seventy")); try { Hits hits = searcher.Search(query); Assert.AreEqual(100, hits.Length()); for (int i = 0; i < hits.Length(); i++) { TermFreqVector[] vector = searcher.reader.GetTermFreqVectors(hits.Id(i)); Assert.IsTrue(vector != null); Assert.IsTrue(vector.Length == 1); //Assert.IsTrue(); } TermFreqVector[] vector2 = searcher.reader.GetTermFreqVectors(hits.Id(50)); //System.out.println("Explain: " + searcher.explain(query, hits.id(50))); //System.out.println("Vector: " + vector[0].toString()); } catch (System.IO.IOException e) { Assert.IsTrue(false); } }
public virtual void TestPrefixQuery() { RAMDirectory directory = new RAMDirectory(); System.String[] categories = new System.String[] { "/Computers", "/Computers/Mac", "/Computers/Windows" }; IndexWriter writer = new IndexWriter(directory, new WhitespaceAnalyzer(), true); for (int i = 0; i < categories.Length; i++) { Document doc = new Document(); doc.Add(Field.Keyword("category", categories[i])); writer.AddDocument(doc); } writer.Close(); PrefixQuery query = new PrefixQuery(new Term("category", "/Computers")); IndexSearcher searcher = new IndexSearcher(directory); Hits hits = searcher.Search(query); Assert.AreEqual(3, hits.Length(), "All documents in /Computers category and below"); query = new PrefixQuery(new Term("category", "/Computers/Mac")); hits = searcher.Search(query); Assert.AreEqual(1, hits.Length(), "One in /Computers/Mac"); }
public virtual void TestFilteredQuery_() { Query filteredquery = new FilteredQuery(query, filter); Hits hits = searcher.Search(filteredquery); Assert.AreEqual(1, hits.Length()); Assert.AreEqual(1, hits.Id(0)); hits = searcher.Search(filteredquery, new Sort("sorter")); Assert.AreEqual(1, hits.Length()); Assert.AreEqual(1, hits.Id(0)); filteredquery = new FilteredQuery(new TermQuery(new Term("Field", "one")), filter); hits = searcher.Search(filteredquery); Assert.AreEqual(2, hits.Length()); filteredquery = new FilteredQuery(new TermQuery(new Term("Field", "x")), filter); hits = searcher.Search(filteredquery); Assert.AreEqual(1, hits.Length()); Assert.AreEqual(3, hits.Id(0)); filteredquery = new FilteredQuery(new TermQuery(new Term("Field", "y")), filter); hits = searcher.Search(filteredquery); Assert.AreEqual(0, hits.Length()); }
public virtual void TestFarsi() { /* build an index */ RAMDirectory farsiIndex = new RAMDirectory(); IndexWriter writer = new IndexWriter(farsiIndex, new SimpleAnalyzer(), T, IndexWriter.MaxFieldLength.LIMITED); Document doc = new Document(); doc.Add(new Field("content", "\u0633\u0627\u0628", Field.Store.YES, Field.Index.UN_TOKENIZED)); doc.Add(new Field("body", "body", Field.Store.YES, Field.Index.UN_TOKENIZED)); writer.AddDocument(doc); writer.Optimize(); writer.Close(); IndexReader reader = IndexReader.Open(farsiIndex); IndexSearcher search = new IndexSearcher(reader); Query q = new TermQuery(new Term("body", "body")); // Neither Java 1.4.2 nor 1.5.0 has Farsi Locale collation available in // RuleBasedCollator. However, the Arabic Locale seems to order the Farsi // characters properly. System.Globalization.CompareInfo collator = new System.Globalization.CultureInfo("ar").CompareInfo; // Unicode order would include U+0633 in [ U+062F - U+0698 ], but Farsi // orders the U+0698 character before the U+0633 character, so the single // index Term below should NOT be returned by a TermRangeFilter with a Farsi // Collator (or an Arabic one for the case when Farsi is not supported). Hits result = search.Search(q, new TermRangeFilter("content", "\u062F", "\u0698", T, T, collator)); Assert.AreEqual(0, result.Length(), "The index Term should not be included."); result = search.Search(q, new TermRangeFilter("content", "\u0633", "\u0638", T, T, collator)); Assert.AreEqual(1, result.Length(), "The index Term should be included."); search.Close(); }
public static void PrintDocNrs(Hits hits) { System.Console.Out.Write("new int[] {"); for (int i = 0; i < hits.Length(); i++) { System.Console.Out.Write(hits.Id(i)); if (i != hits.Length() - 1) System.Console.Out.Write(", "); } System.Console.Out.WriteLine("}"); }
private void DoTestSearchHitsDeleteEvery(int k, bool deleteInFront) { bool intermittent = k < 0; Log("Test search hits with " + (intermittent?"intermittent deletions.":"deletions of every " + k + " hit.")); IndexSearcher searcher = new IndexSearcher(directory); IndexReader reader = searcher.GetIndexReader(); Query q = new TermQuery(new Term(TEXT_FIELD, "text")); // matching all docs Hits hits = searcher.Search(q); Log("Got " + hits.Length() + " results"); Assert.AreEqual(N, hits.Length(), "must match all " + N + " docs, not only " + hits.Length() + " docs!"); if (deleteInFront) { Log("deleting hits that was not yet retrieved!"); reader.DeleteDocument(reader.MaxDoc() - 1); reader.DeleteDocument(reader.MaxDoc() - 2); reader.DeleteDocument(reader.MaxDoc() - 3); } try { for (int i = 0; i < hits.Length(); i++) { int id = hits.Id(i); Assert.AreEqual(i, hits.Id(i), "Hit " + i + " has doc id " + hits.Id(i) + " instead of " + i); if ((intermittent && (i == 50 || i == 250 || i == 950)) || (!intermittent && (k < 2 || (i > 0 && i % k == 0)))) { Document doc = hits.Doc(id); Log("Deleting hit " + i + " - doc " + doc + " with id " + id); reader.DeleteDocument(id); } if (intermittent) { // check internal behavior of Hits (go 50 ahead of getMoreDocs points because the deletions cause to use more of the available hits) if (i == 150 || i == 450 || i == 1650) { Assert.IsTrue(hits.debugCheckedForDeletions, "Hit " + i + ": hits should have checked for deletions in last call to getMoreDocs()"); } else if (i == 50 || i == 250 || i == 850) { Assert.IsFalse(hits.debugCheckedForDeletions, "Hit " + i + ": hits should have NOT checked for deletions in last call to getMoreDocs()"); } } } } catch (System.Exception e) { // this is the only valid exception, and only when deletng in front. Assert.IsTrue(deleteInFront, e.Message + " not expected unless deleting hits that were not yet seen!"); } searcher.Close(); }
public static void PrintDocNrs(Hits hits) { System.Console.Out.Write("new int[] {"); for (int i = 0; i < hits.Length(); i++) { System.Console.Out.Write(hits.Id(i)); if (i != hits.Length() - 1) { System.Console.Out.Write(", "); } } System.Console.Out.WriteLine("}"); }
public virtual void TestExact() { // slop is zero by default query.Add(new Term("Field", "four")); query.Add(new Term("Field", "five")); Hits hits = searcher.Search(query); Assert.AreEqual(1, hits.Length(), "exact match"); query = new PhraseQuery(); query.Add(new Term("Field", "two")); query.Add(new Term("Field", "one")); hits = searcher.Search(query); Assert.AreEqual(0, hits.Length(), "reverse not exact"); }
public void TestFastFilter() { DuplicateFilter df = new DuplicateFilter(KEY_FIELD); df.SetProcessingMode(DuplicateFilter.PM_FAST_INVALIDATION); Hashtable results = new Hashtable(); Hits h = searcher.Search(tq, df); Assert.IsTrue(h.Length() > 0, "Filtered searching should have found some matches"); for (int i = 0; i < h.Length(); i++) { Document d = h.Doc(i); String url = d.Get(KEY_FIELD); Assert.IsFalse(results.Contains(url), "No duplicate urls should be returned"); results.Add(url,url); } Assert.AreEqual(2, results.Count, "Two urls found"); }
public void TestNoFilter() { Hashtable results = new Hashtable(); Hits h = searcher.Search(tq); Assert.IsTrue(h.Length() > 0, "Default searching should have found some matches"); bool dupsFound = false; for (int i = 0; i < h.Length(); i++) { Document d = h.Doc(i); String url = d.Get(KEY_FIELD); if (!dupsFound) dupsFound = results.Contains(url); results[url]=url; } Assert.IsTrue(dupsFound, "Default searching should have found duplicate urls"); }
public static void CheckHits_(Query query, System.String defaultFieldName, Searcher searcher, int[] results, TestCase testCase) { Hits hits = searcher.Search(query); System.Collections.Hashtable correct = new System.Collections.Hashtable(); for (int i = 0; i < results.Length; i++) { correct.Add((System.Int32)results[i], null); } System.Collections.Hashtable actual = new System.Collections.Hashtable(); for (int i = 0; i < hits.Length(); i++) { actual.Add((System.Int32)hits.Id(i), null); } //Assert.AreEqual(correct, actual, query.ToString(defaultFieldName)); if (correct.Count != 0) { System.Collections.IDictionaryEnumerator iter = correct.GetEnumerator(); bool status = false; while (iter.MoveNext()) { status = actual.ContainsKey(iter.Key); if (status == false) { break; } } Assert.IsTrue(status, query.ToString(defaultFieldName)); } }
public void TestKeepsFirstFilter() { DuplicateFilter df = new DuplicateFilter(KEY_FIELD); df.SetKeepMode(DuplicateFilter.KM_USE_FIRST_OCCURRENCE); Hits h = searcher.Search(tq, df); Assert.IsTrue(h.Length() > 0, "Filtered searching should have found some matches"); for (int i = 0; i < h.Length(); i++) { Document d = h.Doc(i); String url = d.Get(KEY_FIELD); TermDocs td = reader.TermDocs(new Term(KEY_FIELD, url)); int lastDoc = 0; td.Next(); lastDoc = td.Doc(); Assert.AreEqual(lastDoc, h.Id((i)), "Duplicate urls should return first doc"); } }
public virtual void TestBarelyCloseEnough() { query.SetSlop(3); query.Add(new Term("Field", "one")); query.Add(new Term("Field", "five")); Hits hits = searcher.Search(query); Assert.AreEqual(1, hits.Length()); }
public virtual void TestOrderDoesntMatter() { SetUp(); query.SetSlop(2); // must be at least two for reverse order match query.Add(new Term("Field", "two")); query.Add(new Term("Field", "one")); Hits hits = searcher.Search(query); Assert.AreEqual(1, hits.Length(), "just sloppy enough"); query = new PhraseQuery(); query.SetSlop(2); query.Add(new Term("Field", "three")); query.Add(new Term("Field", "one")); hits = searcher.Search(query); Assert.AreEqual(0, hits.Length(), "not sloppy enough"); }
public virtual void TestRangeQuery() { RangeQuery rq = new RangeQuery(new Term("sorter", "b"), new Term("sorter", "d"), true); Query filteredquery = new FilteredQuery(rq, filter); Hits hits = searcher.Search(filteredquery); Assert.AreEqual(2, hits.Length()); }
public virtual void TestQueryFilter() { // try to search the published index Lucene.Net.Search.Searchable[] searchables = new Lucene.Net.Search.Searchable[] { Remote }; Searcher searcher = new MultiSearcher(searchables); Hits hits = searcher.Search(new TermQuery(new Term("test", "text")), new QueryFilter(new TermQuery(new Term("test", "test")))); Hits nohits = searcher.Search(new TermQuery(new Term("test", "text")), new QueryFilter(new TermQuery(new Term("test", "non-existent-term")))); Assert.AreEqual(0, nohits.Length()); }
private static void Search(Query query) { // try to search the published index Lucene.Net.Search.Searchable[] searchables = new Lucene.Net.Search.Searchable[] { Remote }; Searcher searcher = new MultiSearcher(searchables); Hits result = searcher.Search(query); Assert.AreEqual(1, result.Length()); Assert.AreEqual("test text", result.Doc(0).Get("test")); }
public virtual void TestSlop1() { SetUp(); // Ensures slop of 1 works with terms in order. query.SetSlop(1); query.Add(new Term("Field", "one")); query.Add(new Term("Field", "two")); Hits hits = searcher.Search(query); Assert.AreEqual(1, hits.Length(), "in order"); // Ensures slop of 1 does not work for phrases out of order; // must be at least 2. query = new PhraseQuery(); query.SetSlop(1); query.Add(new Term("Field", "two")); query.Add(new Term("Field", "one")); hits = searcher.Search(query); Assert.AreEqual(0, hits.Length(), "reversed, slop not 2 or more"); }
public virtual void TestTermPositionVectors() { Query query = new TermQuery(new Term("Field", "fifty")); try { Hits hits = searcher.Search(query); Assert.AreEqual(100, hits.Length()); for (int i = 0; i < hits.Length(); i++) { TermFreqVector[] vector = searcher.reader.GetTermFreqVectors(hits.Id(i)); Assert.IsTrue(vector != null); Assert.IsTrue(vector.Length == 1); //Assert.IsTrue(); } } catch (System.IO.IOException e) { Assert.IsTrue(false); } }
public void TestDefaultFilter() { DuplicateFilter df = new DuplicateFilter(KEY_FIELD); Hashtable results = new Hashtable(); Hits h = searcher.Search(tq, df); for (int i = 0; i < h.Length(); i++) { Document d = h.Doc(i); String url = d.Get(KEY_FIELD); Assert.IsFalse(results.Contains(url), "No duplicate urls should be returned"); results.Add(url,url); } }
private System.Collections.Hashtable GetScores(Hits hits) { System.Collections.Hashtable scoreMap = new System.Collections.Hashtable(); int n = hits.Length(); for (int i = 0; i < n; ++i) { Document doc = hits.Doc(i); System.String[] v = doc.GetValues("tracer"); Assert.AreEqual(v.Length, 1); scoreMap[v[0]] = (float)hits.Score(i); } return(scoreMap); }
public virtual void TestInclusive() { Query query = new RangeQuery(new Term("content", "A"), new Term("content", "C"), true); InitializeIndex(new System.String[] { "A", "B", "C", "D" }); IndexSearcher searcher = new IndexSearcher(dir); Hits hits = searcher.Search(query); Assert.AreEqual(3, hits.Length(), "A,B,C,D - A,B,C in range"); searcher.Close(); InitializeIndex(new System.String[] { "A", "B", "D" }); searcher = new IndexSearcher(dir); hits = searcher.Search(query); Assert.AreEqual(2, hits.Length(), "A,B,D - A and B in range"); searcher.Close(); AddDoc("C"); searcher = new IndexSearcher(dir); hits = searcher.Search(query); Assert.AreEqual(3, hits.Length(), "C added - A, B, C in range"); searcher.Close(); }
public virtual void TestMulipleTerms() { SetUp(); query.SetSlop(2); query.Add(new Term("Field", "one")); query.Add(new Term("Field", "three")); query.Add(new Term("Field", "five")); Hits hits = searcher.Search(query); Assert.AreEqual(1, hits.Length(), "two total moves"); query = new PhraseQuery(); query.SetSlop(5); // it takes six moves to match this phrase query.Add(new Term("Field", "five")); query.Add(new Term("Field", "three")); query.Add(new Term("Field", "one")); hits = searcher.Search(query); Assert.AreEqual(0, hits.Length(), "slop of 5 not close enough"); query.SetSlop(6); hits = searcher.Search(query); Assert.AreEqual(1, hits.Length(), "slop of 6 just right"); }
public virtual void TestDanish() { /* build an index */ RAMDirectory danishIndex = new RAMDirectory(); IndexWriter writer = new IndexWriter(danishIndex, new SimpleAnalyzer(), T, IndexWriter.MaxFieldLength.LIMITED); // Danish collation orders the words below in the given order // (example taken from TestSort.testInternationalSort() ). System.String[] words = new System.String[] { "H\u00D8T", "H\u00C5T", "MAND" }; for (int docnum = 0; docnum < words.Length; ++docnum) { Document doc = new Document(); doc.Add(new Field("content", words[docnum], Field.Store.YES, Field.Index.UN_TOKENIZED)); doc.Add(new Field("body", "body", Field.Store.YES, Field.Index.UN_TOKENIZED)); writer.AddDocument(doc); } writer.Optimize(); writer.Close(); IndexReader reader = IndexReader.Open(danishIndex); IndexSearcher search = new IndexSearcher(reader); Query q = new TermQuery(new Term("body", "body")); System.Globalization.CompareInfo collator = new System.Globalization.CultureInfo("da" + "-" + "dk").CompareInfo; Query query = new TermRangeQuery("content", "H\u00D8T", "MAND", false, false, collator); // Unicode order would not include "H\u00C5T" in [ "H\u00D8T", "MAND" ], // but Danish collation does. Hits result = search.Search(q, new TermRangeFilter("content", "H\u00D8T", "MAND", F, F, collator)); Assert.AreEqual(1, result.Length(), "The index Term should be included."); result = search.Search(q, new TermRangeFilter("content", "H\u00C5T", "MAND", F, F, collator)); Assert.AreEqual(0, result.Length(), "The index Term should not be included."); search.Close(); }
// make sure the documents returned by the search match the expected list private void AssertMatches(Searcher searcher, Query query, Sort sort, System.String expectedResult) { Hits result = searcher.Search(query, sort); System.Text.StringBuilder buff = new System.Text.StringBuilder(10); int n = result.Length(); for (int i = 0; i < n; ++i) { Document doc = result.Doc(i); System.String[] v = doc.GetValues("tracer"); for (int j = 0; j < v.Length; ++j) { buff.Append(v[j]); } } Assert.AreEqual(expectedResult, buff.ToString()); }
// make sure the documents returned by the search match the expected list pattern private void AssertMatchesPattern(Searcher searcher, Query query, Sort sort, System.String pattern) { Hits result = searcher.Search(query, sort); System.Text.StringBuilder buff = new System.Text.StringBuilder(10); int n = result.Length(); for (int i = 0; i < n; ++i) { Document doc = result.Doc(i); System.String[] v = doc.GetValues("tracer"); for (int j = 0; j < v.Length; ++j) { buff.Append(v[j]); } } // System.out.println ("matching \""+buff+"\" against pattern \""+pattern+"\""); System.Text.RegularExpressions.Regex regex = new System.Text.RegularExpressions.Regex(pattern); Assert.IsTrue(regex.IsMatch(buff.ToString())); }
public virtual void TestNot_() { RAMDirectory store = new RAMDirectory(); IndexWriter writer = new IndexWriter(store, new SimpleAnalyzer(), true); Document d1 = new Document(); d1.Add(Field.Text("Field", "a b")); writer.AddDocument(d1); writer.Optimize(); writer.Close(); Searcher searcher = new IndexSearcher(store); Query query = Lucene.Net.QueryParsers.QueryParser.Parse("a NOT b", "Field", new SimpleAnalyzer()); //System.out.println(query); Hits hits = searcher.Search(query); Assert.AreEqual(0, hits.Length()); }
public Hashtable GetStoredUriStrings(string server, string file) { Hashtable uris = new Hashtable(); Term term = new Term(PropertyToFieldName(PropertyType.Keyword, "fixme:file"), file); LNS.QueryFilter filter = new LNS.QueryFilter(new LNS.TermQuery(term)); term = new Term(PropertyToFieldName(PropertyType.Keyword, "fixme:account"), server); LNS.TermQuery query = new LNS.TermQuery(term); LNS.IndexSearcher searcher = LuceneCommon.GetSearcher(PrimaryStore); LNS.Hits hits = searcher.Search(query, filter); for (int i = 0; i < hits.Length(); i++) { StoredInfo info = DocumentToStoredInfo(hits.Doc(i)); uris.Add(info.Uri.ToString(), info.FullyIndexed); } LuceneCommon.ReleaseSearcher(searcher); return(uris); }
public virtual void TestKnownSetOfDocuments() { System.String[] termArray = new System.String[] { "eating", "chocolate", "in", "a", "computer", "lab", "grows", "old", "colored", "with", "an" }; System.String test1 = "eating chocolate in a computer lab"; //6 terms System.String test2 = "computer in a computer lab"; //5 terms System.String test3 = "a chocolate lab grows old"; //5 terms System.String test4 = "eating chocolate with a chocolate lab in an old chocolate colored computer lab"; //13 terms System.Collections.IDictionary test4Map = new System.Collections.Hashtable(); test4Map["chocolate"] = 3; test4Map["lab"] = 2; test4Map["eating"] = 1; test4Map["computer"] = 1; test4Map["with"] = 1; test4Map["a"] = 1; test4Map["colored"] = 1; test4Map["in"] = 1; test4Map["an"] = 1; test4Map["computer"] = 1; test4Map["old"] = 1; Document testDoc1 = new Document(); SetupDoc(testDoc1, test1); Document testDoc2 = new Document(); SetupDoc(testDoc2, test2); Document testDoc3 = new Document(); SetupDoc(testDoc3, test3); Document testDoc4 = new Document(); SetupDoc(testDoc4, test4); Directory dir = new RAMDirectory(); try { IndexWriter writer = new IndexWriter(dir, new SimpleAnalyzer(), true); Assert.IsTrue(writer != null); writer.AddDocument(testDoc1); writer.AddDocument(testDoc2); writer.AddDocument(testDoc3); writer.AddDocument(testDoc4); writer.Close(); IndexSearcher knownSearcher = new IndexSearcher(dir); TermEnum termEnum = knownSearcher.reader.Terms(); TermDocs termDocs = knownSearcher.reader.TermDocs(); //System.out.println("Terms: " + termEnum.size() + " Orig Len: " + termArray.length); Similarity sim = knownSearcher.GetSimilarity(); while (termEnum.Next() == true) { Term term = termEnum.Term(); //System.out.println("Term: " + term); termDocs.Seek(term); while (termDocs.Next()) { int docId = termDocs.Doc(); int freq = termDocs.Freq(); //System.out.println("Doc Id: " + docId + " freq " + freq); TermFreqVector vector = knownSearcher.reader.GetTermFreqVector(docId, "Field"); float tf = sim.Tf(freq); float idf = sim.Idf(term, knownSearcher); //float qNorm = sim.queryNorm() //This is fine since we don't have stop words float lNorm = sim.LengthNorm("Field", vector.GetTerms().Length); //float coord = sim.coord() //System.out.println("TF: " + tf + " IDF: " + idf + " LenNorm: " + lNorm); Assert.IsTrue(vector != null); System.String[] vTerms = vector.GetTerms(); int[] freqs = vector.GetTermFrequencies(); for (int i = 0; i < vTerms.Length; i++) { if (term.Text().Equals(vTerms[i]) == true) { Assert.IsTrue(freqs[i] == freq); } } } //System.out.println("--------"); } Query query = new TermQuery(new Term("Field", "chocolate")); Hits hits = knownSearcher.Search(query); //doc 3 should be the first hit b/c it is the shortest match Assert.IsTrue(hits.Length() == 3); float score = hits.Score(0); /*System.out.println("Hit 0: " + hits.id(0) + " Score: " + hits.score(0) + " String: " + hits.doc(0).toString()); * System.out.println("Explain: " + knownSearcher.explain(query, hits.id(0))); * System.out.println("Hit 1: " + hits.id(1) + " Score: " + hits.score(1) + " String: " + hits.doc(1).toString()); * System.out.println("Explain: " + knownSearcher.explain(query, hits.id(1))); * System.out.println("Hit 2: " + hits.id(2) + " Score: " + hits.score(2) + " String: " + hits.doc(2).toString()); * System.out.println("Explain: " + knownSearcher.explain(query, hits.id(2)));*/ Assert.IsTrue(testDoc3.ToString().Equals(hits.Doc(0).ToString())); Assert.IsTrue(testDoc4.ToString().Equals(hits.Doc(1).ToString())); Assert.IsTrue(testDoc1.ToString().Equals(hits.Doc(2).ToString())); TermFreqVector vector2 = knownSearcher.reader.GetTermFreqVector(hits.Id(1), "Field"); Assert.IsTrue(vector2 != null); //System.out.println("Vector: " + vector); System.String[] terms = vector2.GetTerms(); int[] freqs2 = vector2.GetTermFrequencies(); Assert.IsTrue(terms != null && terms.Length == 10); for (int i = 0; i < terms.Length; i++) { System.String term = terms[i]; //System.out.println("Term: " + term); int freq = freqs2[i]; Assert.IsTrue(test4.IndexOf(term) != -1); System.Int32 freqInt = (System.Int32)test4Map[term]; System.Object tmpFreqInt = test4Map[term]; Assert.IsTrue(tmpFreqInt != null); Assert.IsTrue(freqInt == freq); } knownSearcher.Close(); } catch (System.IO.IOException e) { System.Console.Error.WriteLine(e.StackTrace); Assert.IsTrue(false); } }
private System.Collections.Hashtable GetScores(Hits hits) { System.Collections.Hashtable scoreMap = new System.Collections.Hashtable(); int n = hits.Length(); for (int i = 0; i < n; ++i) { Document doc = hits.Doc(i); System.String[] v = doc.GetValues("tracer"); Assert.AreEqual(v.Length, 1); scoreMap[v[0]] = (float) hits.Score(i); } return scoreMap; }
private void button2_Click(object sender, EventArgs e) { if (_indexTarget == string.Empty) return; if (textBox4.Text == string.Empty) { return; } listBox4.Items.Clear(); if (IndexReader.IndexExists(_indexTarget)) { searcher = new IndexSearcher(_indexTarget); Query q = QueryParser.Parse(textBox4.Text, "contents", analyzer); hits = searcher.Search(q); if (hits.Length() == 0) { label8.Text = "No Hits :P"; return; } label8.Text = hits.Length() + " hit(s)."; for (int i = 0; i < hits.Length(); i++) { Document d = hits.Doc(i); listBox4.Items.Add(d.Get("filename")); } } }
private void button2_Click(object sender, EventArgs e) { listBox1.Items.Clear(); searcher = new IndexSearcher(new RAMDirectory(indexpath)); Query q = MultiFieldQueryParser.Parse(textBox1.Text, new string[] { "ayat_desc", "ayat_urdu", "ayat_arabic" }, new DiacriticAnalyzer(FilterData.stopWords)); //Query q = QueryParser.Parse(textBox1.Text, "contents", new DiacriticAnalyzer(FilterData.stopWords)); //Query q = QueryParser.Parse(textBox1.Text, "ayat_desc", new DiacriticAnalyzer(FilterData.stopWords)); hits = searcher.Search(q); label2.Text = string.Format("{0} hit(s).", hits.Length().ToString()); Application.DoEvents(); //for (int i = 0; i < hits.Length(); i++) //{ // foreach (Field f in hits.Doc(i).Fields()) // { // listBox1.Items.Add(f.Name()); // } //} for (int i = 0; i < hits.Length(); i++) { StringBuilder sb = new StringBuilder(); sb.Append("Para: ").Append(hits.Doc(i).Get("pid")); sb.Append(", Surat: ").Append(hits.Doc(i).Get("sid")); sb.Append(", Verse: ").Append(hits.Doc(i).Get("ayatno")); listBox1.Items.Add(sb.ToString()); } }
private void PrintHits(System.IO.StringWriter out_Renamed, Hits hits) { out_Renamed.WriteLine(hits.Length() + " total results\n"); for (int i = 0; i < hits.Length(); i++) { if (i < 10 || (i > 94 && i < 105)) { Document d = hits.Doc(i); out_Renamed.WriteLine(i + " " + d.Get(ID_FIELD)); } } }
public void AddResult(SearchInfo info, Hits hits, int maxMatches) { if ( docs == null) docs = new Dictionary<SearchInfo, List<ExDocument>>(); if (hits == null) return; if (info == null) return; List<ExDocument> exdl = new List<ExDocument>(); for (int i = 0; i < maxMatches && i < hits.Length(); i++) { exdl.Add(new ExDocument(hits.Doc(i),hits.Score(i))); } if ( exdl.Count > 0) docs.Add(info, exdl); }
protected internal virtual void PrintHits(System.String test, Hits h) { System.Console.Error.WriteLine("------- " + test + " -------"); for (int i = 0; i < h.Length(); i++) { Lucene.Net.Documents.Document d = h.Doc(i); float score = h.Score(i); System.Console.Error.WriteLine("#" + i + ": {0.000000000}" + score + " - " + d.Get("id")); } }
private void CheckHits(Hits hits, int expectedCount) { Assert.AreEqual(expectedCount, hits.Length(), "total results"); for (int i = 0; i < hits.Length(); i++) { if (i < 10 || (i > 94 && i < 105)) { Document d = hits.Doc(i); Assert.AreEqual(System.Convert.ToString(i), d.Get(ID_FIELD), "check " + i); } } }
private static void PrintHits(Hits hits) { System.Console.Out.WriteLine(hits.Length() + " total results\n"); for (int i = 0; i < hits.Length(); i++) { if (i < 10 || (i > 94 && i < 105)) { Lucene.Net.Documents.Document d = hits.Doc(i); System.Console.Out.WriteLine(i + " " + d.Get(ID_FIELD)); } } }
/// <summary>Tests that a Hits has an expected order of documents </summary> public static void CheckDocIds(System.String mes, int[] results, Hits hits) { Assert.AreEqual(results.Length, hits.Length(), mes + " nr of hits"); for (int i = 0; i < results.Length; i++) { Assert.AreEqual(results[i], hits.Id(i), mes + " doc nrs for hit " + i); } }
public static System.String Hits2str(Hits hits1, Hits hits2, int start, int end) { System.Text.StringBuilder sb = new System.Text.StringBuilder(); int len1 = hits1 == null?0:hits1.Length(); int len2 = hits2 == null?0:hits2.Length(); if (end <= 0) { end = System.Math.Max(len1, len2); } sb.Append("Hits length1=").Append(len1).Append("\tlength2=").Append(len2); sb.Append('\n'); for (int i = start; i < end; i++) { sb.Append("hit=").Append(i).Append(':'); if (i < len1) { sb.Append(" doc").Append(hits1.Id(i)).Append('=').Append(hits1.Score(i)); } else { sb.Append(" "); } sb.Append(",\t"); if (i < len2) { sb.Append(" doc").Append(hits2.Id(i)).Append('=').Append(hits2.Score(i)); } sb.Append('\n'); } return sb.ToString(); }
private SearchResult[] _prepareSearchResultsFromHits(string query, Hits hits) { List<SearchResult> results = new List<SearchResult>(); for (int i = 0; i < hits.Length(); i++) { SearchResult sr = new SearchResult(hits.Doc(i), _analyzer, query, _fragmentSize); sr.QueryParser = _parser; results.Add(sr); } return results.ToArray(); }
private void btnSearch_Click(object sender, EventArgs e) { lstResults.Items.Clear(); searcher = new IndexSearcher(new RAMDirectory(_indexTarget)); PerFieldAnalyzerWrapper analyzer = new PerFieldAnalyzerWrapper(new StandardAnalyzer()); analyzer.AddAnalyzer("ayat_arabic", new DiacriticAnalyzer(FilterData.stopWords)); //MyQueryParser parser = new MyQueryParser(new string[] { "ayat_desc", "ayat_urdu", "ayat_arabic" }, analyzer); //parser.SetDefaultOperator(QueryParser.Operator.AND); //Query q = parser.Parse(txtSearch.Text); //Query q = new TermQuery(new Term("ayatno", NumberTools.LongToString(long.Parse(txtSearch.Text)))); BooleanQuery q = new BooleanQuery(); long l1 = 1; long l2 = 500; long l3 = 1; long l4 = 1; //RangeQuery rq = new RangeQuery(new Term("ayatno", l1.ToString("00000")), new Term("ayatno", l2.ToString("00000")), true); //q.Add(rq, true, false); q.Add(new TermQuery(new Term("sid", l3.ToString("00000"))), true, false); q.Add(new TermQuery(new Term("ayatno", l4.ToString("00000"))), true, false); MessageBox.Show(q.ToString()); Sort sort = new Sort(new string[] { "pid", "sid", "ayatno" }); hits = searcher.Search(q, sort); lblHits.Text = hits.Length() + " hit(s)."; Application.DoEvents(); for (int i = 0; i < hits.Length(); i++) { StringBuilder sb = new StringBuilder(); sb.Append("Para: ").Append(hits.Doc(i).Get("pid")); sb.Append(", Surat: ").Append(hits.Doc(i).Get("sid")); sb.Append(", Verse: ").Append(hits.Doc(i).Get("ayatno")); lstResults.Items.Add(sb.ToString()); } }
public void AddResult(Hits hits, int maxMatches) { if (docList == null) docList = new List<ExDocument>(); if (hits == null) return; for (int i = 0; i < maxMatches && i < hits.Length(); i++) { docList.Add(new ExDocument(hits.Doc(i), hits.Score(i))); } }
public static void CheckEqual(Query query, Hits hits1, Hits hits2) { float scoreTolerance = 1.0e-6f; if (hits1.Length() != hits2.Length()) { Assert.Fail("Unequal lengths: hits1=" + hits1.Length() + ",hits2=" + hits2.Length()); } for (int i = 0; i < hits1.Length(); i++) { if (hits1.Id(i) != hits2.Id(i)) { Assert.Fail("Hit " + i + " docnumbers don't match\n" + Hits2str(hits1, hits2, 0, 0) + "for query:" + query.ToString()); } if ((hits1.Id(i) != hits2.Id(i)) || System.Math.Abs(hits1.Score(i) - hits2.Score(i)) > scoreTolerance) { Assert.Fail("Hit " + i + ", doc nrs " + hits1.Id(i) + " and " + hits2.Id(i) + "\nunequal : " + hits1.Score(i) + "\n and: " + hits2.Score(i) + "\nfor query:" + query.ToString()); } } }
/// <summary> Check the hits for duplicates.</summary> /// <param name="hits"> /// </param> private void CheckHits(Hits hits, System.String prefix) { if (hits != null) { System.Collections.IDictionary idMap = new System.Collections.SortedList(); for (int docnum = 0; docnum < hits.Length(); ++docnum) { System.Int32 luceneId; try { luceneId = (System.Int32) hits.Id(docnum); if (idMap.Contains(luceneId)) { System.Text.StringBuilder message = new System.Text.StringBuilder(prefix); message.Append("Duplicate key for hit index = "); message.Append(docnum); message.Append(", previous index = "); message.Append(((System.Int32) idMap[luceneId]).ToString()); message.Append(", Lucene ID = "); message.Append(luceneId); Log(message.ToString()); } else { idMap[luceneId] = (System.Int32) docnum; } } catch (System.IO.IOException ioe) { System.Text.StringBuilder message = new System.Text.StringBuilder(prefix); message.Append("Error occurred for hit index = "); message.Append(docnum); message.Append(" ("); message.Append(ioe.Message); message.Append(")"); Log(message.ToString()); } } } }