public virtual void TestPayloadSpanUtil() { RAMDirectory directory = new RAMDirectory(); PayloadAnalyzer analyzer = new PayloadAnalyzer(this); IndexWriter writer = new IndexWriter(directory, analyzer, true, IndexWriter.MaxFieldLength.UNLIMITED); writer.SetSimilarity(similarity); Document doc = new Document(); doc.Add(new Field(PayloadHelper.FIELD, "xx rr yy mm pp", Field.Store.YES, Field.Index.ANALYZED)); writer.AddDocument(doc); writer.Close(); IndexSearcher searcher = new IndexSearcher(directory, true); IndexReader reader = searcher.IndexReader; PayloadSpanUtil psu = new PayloadSpanUtil(reader); System.Collections.Generic.ICollection <byte[]> payloads = psu.GetPayloadsForQuery(new TermQuery(new Term(PayloadHelper.FIELD, "rr"))); if (DEBUG) { System.Console.Out.WriteLine("Num payloads:" + payloads.Count); } System.Collections.IEnumerator it = payloads.GetEnumerator(); while (it.MoveNext()) { byte[] bytes = (byte[])it.Current; if (DEBUG) { System.Console.Out.WriteLine(new System.String(System.Text.UTF8Encoding.UTF8.GetChars(bytes))); } } }
public virtual void TestPayloadsPos0() { Directory dir = NewDirectory(); RandomIndexWriter writer = new RandomIndexWriter(Random(), dir, new MockPayloadAnalyzer()); Document doc = new Document(); doc.Add(new TextField("content", new StringReader("a a b c d e a f g h i j a b k k"))); writer.AddDocument(doc); IndexReader readerFromWriter = writer.Reader; AtomicReader r = SlowCompositeReaderWrapper.Wrap(readerFromWriter); DocsAndPositionsEnum tp = r.TermPositionsEnum(new Term("content", "a")); int count = 0; Assert.IsTrue(tp.NextDoc() != DocIdSetIterator.NO_MORE_DOCS); // "a" occurs 4 times Assert.AreEqual(4, tp.Freq()); Assert.AreEqual(0, tp.NextPosition()); Assert.AreEqual(1, tp.NextPosition()); Assert.AreEqual(3, tp.NextPosition()); Assert.AreEqual(6, tp.NextPosition()); // only one doc has "a" Assert.AreEqual(DocIdSetIterator.NO_MORE_DOCS, tp.NextDoc()); IndexSearcher @is = NewSearcher(readerFromWriter); SpanTermQuery stq1 = new SpanTermQuery(new Term("content", "a")); SpanTermQuery stq2 = new SpanTermQuery(new Term("content", "k")); SpanQuery[] sqs = new SpanQuery[] { stq1, stq2 }; SpanNearQuery snq = new SpanNearQuery(sqs, 30, false); count = 0; bool sawZero = false; if (VERBOSE) { Console.WriteLine("\ngetPayloadSpans test"); } Search.Spans.Spans pspans = MultiSpansWrapper.Wrap(@is.TopReaderContext, snq); while (pspans.Next()) { if (VERBOSE) { Console.WriteLine("doc " + pspans.Doc() + ": span " + pspans.Start() + " to " + pspans.End()); } var payloads = pspans.Payload; sawZero |= pspans.Start() == 0; foreach (var bytes in payloads) { count++; if (VERBOSE) { Console.WriteLine(" payload: " + Encoding.UTF8.GetString((byte[])(Array)bytes)); } } } Assert.IsTrue(sawZero); Assert.AreEqual(5, count); // System.out.println("\ngetSpans test"); Search.Spans.Spans spans = MultiSpansWrapper.Wrap(@is.TopReaderContext, snq); count = 0; sawZero = false; while (spans.Next()) { count++; sawZero |= spans.Start() == 0; // System.out.println(spans.Doc() + " - " + spans.Start() + " - " + // spans.End()); } Assert.AreEqual(4, count); Assert.IsTrue(sawZero); // System.out.println("\nPayloadSpanUtil test"); sawZero = false; PayloadSpanUtil psu = new PayloadSpanUtil(@is.TopReaderContext); var pls = psu.GetPayloadsForQuery(snq); count = pls.Count; foreach (var bytes in pls) { string s = Encoding.UTF8.GetString(bytes); //System.out.println(s); sawZero |= s.Equals("pos: 0"); } Assert.AreEqual(5, count); Assert.IsTrue(sawZero); writer.Dispose(); @is.IndexReader.Dispose(); dir.Dispose(); }
public virtual void TestPayloadSpanUtil() { Directory directory = NewDirectory(); RandomIndexWriter writer = new RandomIndexWriter(Random(), directory, NewIndexWriterConfig(TEST_VERSION_CURRENT, new PayloadAnalyzer(this)).SetSimilarity(Similarity)); Document doc = new Document(); doc.Add(NewTextField(PayloadHelper.FIELD, "xx rr yy mm pp", Field.Store.YES)); writer.AddDocument(doc); IndexReader reader = writer.Reader; writer.Dispose(); IndexSearcher searcher = NewSearcher(reader); PayloadSpanUtil psu = new PayloadSpanUtil(searcher.TopReaderContext); var payloads = psu.GetPayloadsForQuery(new TermQuery(new Term(PayloadHelper.FIELD, "rr"))); if (VERBOSE) { Console.WriteLine("Num payloads:" + payloads.Count); foreach (var bytes in payloads) { Console.WriteLine(Encoding.UTF8.GetString((byte[])(Array)bytes)); } } reader.Dispose(); directory.Dispose(); }
public virtual void TestPayloadSpanUtil() { 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, "xx rr yy mm pp", Field.Store.YES, Field.Index.ANALYZED)); writer.AddDocument(doc); writer.Close(); IndexSearcher searcher = new IndexSearcher(directory); IndexReader reader = searcher.GetIndexReader(); PayloadSpanUtil psu = new PayloadSpanUtil(reader); System.Collections.Generic.ICollection<byte[]> payloads = psu.GetPayloadsForQuery(new TermQuery(new Term(PayloadHelper.FIELD, "rr"))); if (DEBUG) System.Console.Out.WriteLine("Num payloads:" + payloads.Count); System.Collections.IEnumerator it = payloads.GetEnumerator(); while (it.MoveNext()) { byte[] bytes = (byte[]) it.Current; if (DEBUG) System.Console.Out.WriteLine(new System.String(System.Text.UTF8Encoding.UTF8.GetChars(bytes))); } }
public virtual void TestPayloadsPos0() { for (int x = 0; x < 2; x++) { Directory dir = new MockRAMDirectory(); IndexWriter writer = new IndexWriter(dir, new TestPayloadAnalyzer(), true, IndexWriter.MaxFieldLength.LIMITED); if (x == 1) { writer.SetAllowMinus1Position(); } Document doc = new Document(); System.IO.MemoryStream ms = new System.IO.MemoryStream(); System.IO.StreamWriter sw = new System.IO.StreamWriter(ms); sw.Write("a a b c d e a f g h i j a b k k"); // flush to stream & reset it's position so it can be read sw.Flush(); ms.Position = 0; doc.Add(new Field("content", new System.IO.StreamReader(ms))); writer.AddDocument(doc); IndexReader r = writer.GetReader(); TermPositions tp = r.TermPositions(new Term("content", "a")); int count = 0; Assert.IsTrue(tp.Next()); // "a" occurs 4 times Assert.AreEqual(4, tp.Freq()); int expected; if (x == 1) { expected = System.Int32.MaxValue; } else { expected = 0; } Assert.AreEqual(expected, tp.NextPosition()); if (x == 1) { continue; } Assert.AreEqual(1, tp.NextPosition()); Assert.AreEqual(3, tp.NextPosition()); Assert.AreEqual(6, tp.NextPosition()); // only one doc has "a" Assert.IsFalse(tp.Next()); IndexSearcher is_Renamed = new IndexSearcher(r); SpanTermQuery stq1 = new SpanTermQuery(new Term("content", "a")); SpanTermQuery stq2 = new SpanTermQuery(new Term("content", "k")); SpanQuery[] sqs = new SpanQuery[]{stq1, stq2}; SpanNearQuery snq = new SpanNearQuery(sqs, 30, false); count = 0; bool sawZero = false; //System.out.println("\ngetPayloadSpans test"); Lucene.Net.Search.Spans.Spans pspans = snq.GetSpans(is_Renamed.GetIndexReader()); while (pspans.Next()) { //System.out.println(pspans.doc() + " - " + pspans.start() + " - "+ pspans.end()); System.Collections.Generic.ICollection<byte[]> payloads = pspans.GetPayload(); sawZero |= pspans.Start() == 0; for (System.Collections.IEnumerator it = payloads.GetEnumerator(); it.MoveNext(); ) { count++; System.Object generatedAux2 = it.Current; //System.out.println(new String((byte[]) it.next())); } } Assert.AreEqual(5, count); Assert.IsTrue(sawZero); //System.out.println("\ngetSpans test"); Lucene.Net.Search.Spans.Spans spans = snq.GetSpans(is_Renamed.GetIndexReader()); count = 0; sawZero = false; while (spans.Next()) { count++; sawZero |= spans.Start() == 0; //System.out.println(spans.doc() + " - " + spans.start() + " - " + spans.end()); } Assert.AreEqual(4, count); Assert.IsTrue(sawZero); //System.out.println("\nPayloadSpanUtil test"); sawZero = false; PayloadSpanUtil psu = new PayloadSpanUtil(is_Renamed.GetIndexReader()); System.Collections.Generic.ICollection<byte[]> pls = psu.GetPayloadsForQuery(snq); count = pls.Count; for (System.Collections.IEnumerator it = pls.GetEnumerator(); it.MoveNext(); ) { System.String s = new System.String(System.Text.UTF8Encoding.UTF8.GetChars((byte[]) it.Current)); //System.out.println(s); sawZero |= s.Equals("pos: 0"); } Assert.AreEqual(5, count); Assert.IsTrue(sawZero); writer.Close(); is_Renamed.GetIndexReader().Close(); dir.Close(); } }
public virtual void TestPayloadsPos0() { Directory dir = new MockRAMDirectory(); IndexWriter writer = new IndexWriter(dir, new TestPayloadAnalyzer(), true, IndexWriter.MaxFieldLength.LIMITED); Document doc = new Document(); System.IO.MemoryStream ms = new System.IO.MemoryStream(); System.IO.StreamWriter sw = new System.IO.StreamWriter(ms); sw.Write("a a b c d e a f g h i j a b k k"); // flush to stream & reset it's position so it can be read sw.Flush(); ms.Position = 0; doc.Add(new Field("content", new System.IO.StreamReader(ms))); writer.AddDocument(doc); IndexReader r = writer.GetReader(); TermPositions tp = r.TermPositions(new Term("content", "a")); int count = 0; Assert.IsTrue(tp.Next()); // "a" occurs 4 times Assert.AreEqual(4, tp.Freq); int expected = 0; Assert.AreEqual(expected, tp.NextPosition()); Assert.AreEqual(1, tp.NextPosition()); Assert.AreEqual(3, tp.NextPosition()); Assert.AreEqual(6, tp.NextPosition()); // only one doc has "a" Assert.IsFalse(tp.Next()); IndexSearcher is_Renamed = new IndexSearcher(r); SpanTermQuery stq1 = new SpanTermQuery(new Term("content", "a")); SpanTermQuery stq2 = new SpanTermQuery(new Term("content", "k")); SpanQuery[] sqs = new SpanQuery[] { stq1, stq2 }; SpanNearQuery snq = new SpanNearQuery(sqs, 30, false); count = 0; bool sawZero = false; //System.out.println("\ngetPayloadSpans test"); Lucene.Net.Search.Spans.Spans pspans = snq.GetSpans(is_Renamed.IndexReader); while (pspans.Next()) { //System.out.println(pspans.doc() + " - " + pspans.start() + " - "+ pspans.end()); System.Collections.Generic.ICollection <byte[]> payloads = pspans.GetPayload(); sawZero |= pspans.Start() == 0; for (System.Collections.IEnumerator it = payloads.GetEnumerator(); it.MoveNext();) { count++; System.Object generatedAux2 = it.Current; //System.out.println(new String((byte[]) it.next())); } } Assert.AreEqual(5, count); Assert.IsTrue(sawZero); //System.out.println("\ngetSpans test"); Lucene.Net.Search.Spans.Spans spans = snq.GetSpans(is_Renamed.IndexReader); count = 0; sawZero = false; while (spans.Next()) { count++; sawZero |= spans.Start() == 0; //System.out.println(spans.doc() + " - " + spans.start() + " - " + spans.end()); } Assert.AreEqual(4, count); Assert.IsTrue(sawZero); //System.out.println("\nPayloadSpanUtil test"); sawZero = false; PayloadSpanUtil psu = new PayloadSpanUtil(is_Renamed.IndexReader); System.Collections.Generic.ICollection <byte[]> pls = psu.GetPayloadsForQuery(snq); count = pls.Count; for (System.Collections.IEnumerator it = pls.GetEnumerator(); it.MoveNext();) { System.String s = new System.String(System.Text.UTF8Encoding.UTF8.GetChars((byte[])it.Current)); //System.out.println(s); sawZero |= s.Equals("pos: 0"); } Assert.AreEqual(5, count); Assert.IsTrue(sawZero); writer.Close(); is_Renamed.IndexReader.Close(); dir.Close(); }