This TokenFilter provides the ability to set aside attribute states that have already been analyzed. This is useful in situations where multiple fields share many common analysis steps and then go their separate ways.

It is also useful for doing things like entity extraction or proper noun analysis as part of the analysis workflow and saving off those tokens for use in another field.

 TeeSinkTokenFilter source1 = new TeeSinkTokenFilter(new WhitespaceTokenizer(version, reader1)); TeeSinkTokenFilter.SinkTokenStream sink1 = source1.newSinkTokenStream(); TeeSinkTokenFilter.SinkTokenStream sink2 = source1.newSinkTokenStream(); TeeSinkTokenFilter source2 = new TeeSinkTokenFilter(new WhitespaceTokenizer(version, reader2)); source2.addSinkTokenStream(sink1); source2.addSinkTokenStream(sink2); TokenStream final1 = new LowerCaseFilter(version, source1); TokenStream final2 = source2; TokenStream final3 = new EntityDetect(sink1); TokenStream final4 = new URLDetect(sink2); d.add(new TextField("f1", final1, Field.Store.NO)); d.add(new TextField("f2", final2, Field.Store.NO)); d.add(new TextField("f3", final3, Field.Store.NO)); d.add(new TextField("f4", final4, Field.Store.NO)); 
In this example, sink1 and sink2 will both get tokens from both reader1 and reader2 after whitespace tokenizer and now we can further wrap any of these in extra analysis, and more "sources" can be inserted if desired. It is important, that tees are consumed before sinks (in the above example, the field names must be less the sink's field names). If you are not sure, which stream is consumed first, you can simply add another sink and then pass all tokens to the sinks at once using #consumeAllTokens. This TokenFilter is exhausted after this. In the above example, change the example above to:
 ... TokenStream final1 = new LowerCaseFilter(version, source1.newSinkTokenStream()); TokenStream final2 = source2.newSinkTokenStream(); sink1.consumeAllTokens(); sink2.consumeAllTokens(); ... 
In this case, the fields can be added in any order, because the sources are not used anymore and all sinks are ready.

Note, the EntityDetect and URLDetect TokenStreams are for the example and do not currently exist in Lucene.

Inheritance: TokenFilter
//JAVA TO C# CONVERTER WARNING: Method 'throws' clauses are not available in .NET:
//ORIGINAL LINE: public void test() throws java.io.IOException
        public virtual void test()
        {
            TokenRangeSinkFilter sinkFilter = new TokenRangeSinkFilter(2, 4);
            string             test         = "The quick red fox jumped over the lazy brown dogs";
            TeeSinkTokenFilter tee          = new TeeSinkTokenFilter(new MockTokenizer(new StringReader(test), MockTokenizer.WHITESPACE, false));

            TeeSinkTokenFilter.SinkTokenStream rangeToks = tee.newSinkTokenStream(sinkFilter);

            int count = 0;

            tee.reset();
            while (tee.incrementToken())
            {
                count++;
            }

            int sinkCount = 0;

            rangeToks.reset();
            while (rangeToks.incrementToken())
            {
                sinkCount++;
            }

            assertTrue(count + " does not equal: " + 10, count == 10);
            assertTrue("rangeToks Size: " + sinkCount + " is not: " + 2, sinkCount == 2);
        }
Exemplo n.º 2
0
//JAVA TO C# CONVERTER WARNING: Method 'throws' clauses are not available in .NET:
//ORIGINAL LINE: public void testMultipleSources() throws Exception
        public virtual void testMultipleSources()
        {
//JAVA TO C# CONVERTER WARNING: The original Java variable was marked 'final':
//ORIGINAL LINE: final TeeSinkTokenFilter tee1 = new TeeSinkTokenFilter(new MockTokenizer(new java.io.StringReader(buffer1.toString()), MockTokenizer.WHITESPACE, false));
            TeeSinkTokenFilter tee1 = new TeeSinkTokenFilter(new MockTokenizer(new StringReader(buffer1.ToString()), MockTokenizer.WHITESPACE, false));

//JAVA TO C# CONVERTER WARNING: The original Java variable was marked 'final':
//ORIGINAL LINE: final TeeSinkTokenFilter.SinkTokenStream dogDetector = tee1.newSinkTokenStream(dogFilter);
            TeeSinkTokenFilter.SinkTokenStream dogDetector = tee1.newSinkTokenStream(dogFilter);
//JAVA TO C# CONVERTER WARNING: The original Java variable was marked 'final':
//ORIGINAL LINE: final TeeSinkTokenFilter.SinkTokenStream theDetector = tee1.newSinkTokenStream(theFilter);
            TeeSinkTokenFilter.SinkTokenStream theDetector = tee1.newSinkTokenStream(theFilter);
            tee1.reset();
//JAVA TO C# CONVERTER WARNING: The original Java variable was marked 'final':
//ORIGINAL LINE: final TokenStream source1 = new CachingTokenFilter(tee1);
            TokenStream source1 = new CachingTokenFilter(tee1);

            tee1.addAttribute(typeof(CheckClearAttributesAttribute));
            dogDetector.addAttribute(typeof(CheckClearAttributesAttribute));
            theDetector.addAttribute(typeof(CheckClearAttributesAttribute));

//JAVA TO C# CONVERTER WARNING: The original Java variable was marked 'final':
//ORIGINAL LINE: final TeeSinkTokenFilter tee2 = new TeeSinkTokenFilter(new MockTokenizer(new java.io.StringReader(buffer2.toString()), MockTokenizer.WHITESPACE, false));
            TeeSinkTokenFilter tee2 = new TeeSinkTokenFilter(new MockTokenizer(new StringReader(buffer2.ToString()), MockTokenizer.WHITESPACE, false));

            tee2.addSinkTokenStream(dogDetector);
            tee2.addSinkTokenStream(theDetector);
//JAVA TO C# CONVERTER WARNING: The original Java variable was marked 'final':
//ORIGINAL LINE: final TokenStream source2 = tee2;
            TokenStream source2 = tee2;

            assertTokenStreamContents(source1, tokens1);
            assertTokenStreamContents(source2, tokens2);

            assertTokenStreamContents(theDetector, new string[] { "The", "the", "The", "the" });
            assertTokenStreamContents(dogDetector, new string[] { "Dogs", "Dogs" });

            source1.reset();
            TokenStream lowerCasing = new LowerCaseFilter(TEST_VERSION_CURRENT, source1);

            string[] lowerCaseTokens = new string[tokens1.Length];
            for (int i = 0; i < tokens1.Length; i++)
            {
                lowerCaseTokens[i] = tokens1[i].ToLower(Locale.ROOT);
            }
            assertTokenStreamContents(lowerCasing, lowerCaseTokens);
        }
Exemplo n.º 3
0
        // LUCENE-1448
        // TODO: instead of testing it this way, we can test
        // with BaseTokenStreamTestCase now...
//JAVA TO C# CONVERTER WARNING: Method 'throws' clauses are not available in .NET:
//ORIGINAL LINE: public void testEndOffsetPositionWithTeeSinkTokenFilter() throws Exception
        public virtual void testEndOffsetPositionWithTeeSinkTokenFilter()
        {
            Directory          dir         = newDirectory();
            Analyzer           analyzer    = new MockAnalyzer(random(), MockTokenizer.WHITESPACE, false);
            IndexWriter        w           = new IndexWriter(dir, newIndexWriterConfig(TEST_VERSION_CURRENT, analyzer));
            Document           doc         = new Document();
            TokenStream        tokenStream = analyzer.tokenStream("field", "abcd   ");
            TeeSinkTokenFilter tee         = new TeeSinkTokenFilter(tokenStream);
            TokenStream        sink        = tee.newSinkTokenStream();
            FieldType          ft          = new FieldType(TextField.TYPE_NOT_STORED);

            ft.StoreTermVectors         = true;
            ft.StoreTermVectorOffsets   = true;
            ft.StoreTermVectorPositions = true;
            Field f1 = new Field("field", tee, ft);
            Field f2 = new Field("field", sink, ft);

            doc.add(f1);
            doc.add(f2);
            w.addDocument(doc);
            w.close();

            IndexReader r      = DirectoryReader.open(dir);
            Terms       vector = r.getTermVectors(0).terms("field");

            assertEquals(1, vector.size());
            TermsEnum termsEnum = vector.iterator(null);

            termsEnum.next();
            assertEquals(2, termsEnum.totalTermFreq());
            DocsAndPositionsEnum positions = termsEnum.docsAndPositions(null, null);

            assertTrue(positions.nextDoc() != DocIdSetIterator.NO_MORE_DOCS);
            assertEquals(2, positions.freq());
            positions.nextPosition();
            assertEquals(0, positions.startOffset());
            assertEquals(4, positions.endOffset());
            positions.nextPosition();
            assertEquals(8, positions.startOffset());
            assertEquals(12, positions.endOffset());
            assertEquals(DocIdSetIterator.NO_MORE_DOCS, positions.nextDoc());
            r.close();
            dir.close();
        }
Exemplo n.º 4
0
//JAVA TO C# CONVERTER WARNING: Method 'throws' clauses are not available in .NET:
//ORIGINAL LINE: public void testGeneral() throws java.io.IOException
        public virtual void testGeneral()
        {
//JAVA TO C# CONVERTER WARNING: The original Java variable was marked 'final':
//ORIGINAL LINE: final TeeSinkTokenFilter source = new TeeSinkTokenFilter(new MockTokenizer(new java.io.StringReader(buffer1.toString()), MockTokenizer.WHITESPACE, false));
            TeeSinkTokenFilter source = new TeeSinkTokenFilter(new MockTokenizer(new StringReader(buffer1.ToString()), MockTokenizer.WHITESPACE, false));
//JAVA TO C# CONVERTER WARNING: The original Java variable was marked 'final':
//ORIGINAL LINE: final TokenStream sink1 = source.newSinkTokenStream();
            TokenStream sink1 = source.newSinkTokenStream();
//JAVA TO C# CONVERTER WARNING: The original Java variable was marked 'final':
//ORIGINAL LINE: final TokenStream sink2 = source.newSinkTokenStream(theFilter);
            TokenStream sink2 = source.newSinkTokenStream(theFilter);

            source.addAttribute(typeof(CheckClearAttributesAttribute));
            sink1.addAttribute(typeof(CheckClearAttributesAttribute));
            sink2.addAttribute(typeof(CheckClearAttributesAttribute));

            assertTokenStreamContents(source, tokens1);
            assertTokenStreamContents(sink1, tokens1);
            assertTokenStreamContents(sink2, new string[] { "The", "the" });
        }
Exemplo n.º 5
0
//JAVA TO C# CONVERTER WARNING: Method 'throws' clauses are not available in .NET:
//ORIGINAL LINE: public void test() throws java.io.IOException
        public virtual void test()
        {
            TokenTypeSinkFilter sinkFilter = new TokenTypeSinkFilter("D");
            string test = "The quick red fox jumped over the lazy brown dogs";

            TeeSinkTokenFilter ttf = new TeeSinkTokenFilter(new WordTokenFilter(this, new MockTokenizer(new StringReader(test), MockTokenizer.WHITESPACE, false)));

            TeeSinkTokenFilter.SinkTokenStream sink = ttf.newSinkTokenStream(sinkFilter);

            bool seenDogs = false;

            CharTermAttribute termAtt = ttf.addAttribute(typeof(CharTermAttribute));
            TypeAttribute     typeAtt = ttf.addAttribute(typeof(TypeAttribute));

            ttf.reset();
            while (ttf.incrementToken())
            {
                if (termAtt.ToString().Equals("dogs"))
                {
                    seenDogs = true;
                    assertTrue(typeAtt.type() + " is not equal to " + "D", typeAtt.type().Equals("D") == true);
                }
                else
                {
                    assertTrue(typeAtt.type() + " is not null and it should be", typeAtt.type().Equals("word"));
                }
            }
            assertTrue(seenDogs + " does not equal: " + true, seenDogs == true);

            int sinkCount = 0;

            sink.reset();
            while (sink.incrementToken())
            {
                sinkCount++;
            }

            assertTrue("sink Size: " + sinkCount + " is not: " + 1, sinkCount == 1);
        }
        //JAVA TO C# CONVERTER WARNING: Method 'throws' clauses are not available in .NET:
        //ORIGINAL LINE: public void test() throws java.io.IOException
        public virtual void test()
        {
            TokenRangeSinkFilter sinkFilter = new TokenRangeSinkFilter(2, 4);
            string test = "The quick red fox jumped over the lazy brown dogs";
            TeeSinkTokenFilter tee = new TeeSinkTokenFilter(new MockTokenizer(new StringReader(test), MockTokenizer.WHITESPACE, false));
            TeeSinkTokenFilter.SinkTokenStream rangeToks = tee.newSinkTokenStream(sinkFilter);

            int count = 0;
            tee.reset();
            while (tee.incrementToken())
            {
              count++;
            }

            int sinkCount = 0;
            rangeToks.reset();
            while (rangeToks.incrementToken())
            {
              sinkCount++;
            }

            assertTrue(count + " does not equal: " + 10, count == 10);
            assertTrue("rangeToks Size: " + sinkCount + " is not: " + 2, sinkCount == 2);
        }
        //JAVA TO C# CONVERTER WARNING: Method 'throws' clauses are not available in .NET:
        //ORIGINAL LINE: public void test() throws java.io.IOException
        public virtual void test()
        {
            TokenTypeSinkFilter sinkFilter = new TokenTypeSinkFilter("D");
            string test = "The quick red fox jumped over the lazy brown dogs";

            TeeSinkTokenFilter ttf = new TeeSinkTokenFilter(new WordTokenFilter(this, new MockTokenizer(new StringReader(test), MockTokenizer.WHITESPACE, false)));
            TeeSinkTokenFilter.SinkTokenStream sink = ttf.newSinkTokenStream(sinkFilter);

            bool seenDogs = false;

            CharTermAttribute termAtt = ttf.addAttribute(typeof(CharTermAttribute));
            TypeAttribute typeAtt = ttf.addAttribute(typeof(TypeAttribute));
            ttf.reset();
            while (ttf.incrementToken())
            {
              if (termAtt.ToString().Equals("dogs"))
              {
            seenDogs = true;
            assertTrue(typeAtt.type() + " is not equal to " + "D", typeAtt.type().Equals("D") == true);
              }
              else
              {
            assertTrue(typeAtt.type() + " is not null and it should be", typeAtt.type().Equals("word"));
              }
            }
            assertTrue(seenDogs + " does not equal: " + true, seenDogs == true);

            int sinkCount = 0;
            sink.reset();
            while (sink.incrementToken())
            {
              sinkCount++;
            }

            assertTrue("sink Size: " + sinkCount + " is not: " + 1, sinkCount == 1);
        }
Exemplo n.º 8
0
        /// <summary>
        /// Not an explicit test, just useful to print out some info on performance
        /// </summary>
        //JAVA TO C# CONVERTER WARNING: Method 'throws' clauses are not available in .NET:
        //ORIGINAL LINE: public void performance() throws Exception
        public virtual void performance()
        {
            int[] tokCount = new int[] {100, 500, 1000, 2000, 5000, 10000};
            int[] modCounts = new int[] {1, 2, 5, 10, 20, 50, 100, 200, 500};
            for (int k = 0; k < tokCount.Length; k++)
            {
              StringBuilder buffer = new StringBuilder();
              Console.WriteLine("-----Tokens: " + tokCount[k] + "-----");
              for (int i = 0; i < tokCount[k]; i++)
              {
            buffer.Append(English.intToEnglish(i).toUpperCase(Locale.ROOT)).Append(' ');
              }
              //make sure we produce the same tokens
              TeeSinkTokenFilter teeStream = new TeeSinkTokenFilter(new StandardFilter(TEST_VERSION_CURRENT, new StandardTokenizer(TEST_VERSION_CURRENT, new StringReader(buffer.ToString()))));
              TokenStream sink = teeStream.newSinkTokenStream(new ModuloSinkFilter(this, 100));
              teeStream.consumeAllTokens();
              TokenStream stream = new ModuloTokenFilter(this, new StandardFilter(TEST_VERSION_CURRENT, new StandardTokenizer(TEST_VERSION_CURRENT, new StringReader(buffer.ToString()))), 100);
              CharTermAttribute tfTok = stream.addAttribute(typeof(CharTermAttribute));
              CharTermAttribute sinkTok = sink.addAttribute(typeof(CharTermAttribute));
              for (int i = 0; stream.incrementToken(); i++)
              {
            assertTrue(sink.incrementToken());
            assertTrue(tfTok + " is not equal to " + sinkTok + " at token: " + i, tfTok.Equals(sinkTok) == true);
              }

              //simulate two fields, each being analyzed once, for 20 documents
              for (int j = 0; j < modCounts.Length; j++)
              {
            int tfPos = 0;
            long start = DateTimeHelperClass.CurrentUnixTimeMillis();
            for (int i = 0; i < 20; i++)
            {
              stream = new StandardFilter(TEST_VERSION_CURRENT, new StandardTokenizer(TEST_VERSION_CURRENT, new StringReader(buffer.ToString())));
              PositionIncrementAttribute posIncrAtt = stream.getAttribute(typeof(PositionIncrementAttribute));
              while (stream.incrementToken())
              {
                tfPos += posIncrAtt.PositionIncrement;
              }
              stream = new ModuloTokenFilter(this, new StandardFilter(TEST_VERSION_CURRENT, new StandardTokenizer(TEST_VERSION_CURRENT, new StringReader(buffer.ToString()))), modCounts[j]);
              posIncrAtt = stream.getAttribute(typeof(PositionIncrementAttribute));
              while (stream.incrementToken())
              {
                tfPos += posIncrAtt.PositionIncrement;
              }
            }
            long finish = DateTimeHelperClass.CurrentUnixTimeMillis();
            Console.WriteLine("ModCount: " + modCounts[j] + " Two fields took " + (finish - start) + " ms");
            int sinkPos = 0;
            //simulate one field with one sink
            start = DateTimeHelperClass.CurrentUnixTimeMillis();
            for (int i = 0; i < 20; i++)
            {
              teeStream = new TeeSinkTokenFilter(new StandardFilter(TEST_VERSION_CURRENT, new StandardTokenizer(TEST_VERSION_CURRENT, new StringReader(buffer.ToString()))));
              sink = teeStream.newSinkTokenStream(new ModuloSinkFilter(this, modCounts[j]));
              PositionIncrementAttribute posIncrAtt = teeStream.getAttribute(typeof(PositionIncrementAttribute));
              while (teeStream.incrementToken())
              {
                sinkPos += posIncrAtt.PositionIncrement;
              }
              //System.out.println("Modulo--------");
              posIncrAtt = sink.getAttribute(typeof(PositionIncrementAttribute));
              while (sink.incrementToken())
              {
                sinkPos += posIncrAtt.PositionIncrement;
              }
            }
            finish = DateTimeHelperClass.CurrentUnixTimeMillis();
            Console.WriteLine("ModCount: " + modCounts[j] + " Tee fields took " + (finish - start) + " ms");
            assertTrue(sinkPos + " does not equal: " + tfPos, sinkPos == tfPos);

              }
              Console.WriteLine("- End Tokens: " + tokCount[k] + "-----");
            }
        }
Exemplo n.º 9
0
        //JAVA TO C# CONVERTER WARNING: Method 'throws' clauses are not available in .NET:
        //ORIGINAL LINE: public void testMultipleSources() throws Exception
        public virtual void testMultipleSources()
        {
            //JAVA TO C# CONVERTER WARNING: The original Java variable was marked 'final':
            //ORIGINAL LINE: final TeeSinkTokenFilter tee1 = new TeeSinkTokenFilter(new MockTokenizer(new java.io.StringReader(buffer1.toString()), MockTokenizer.WHITESPACE, false));
            TeeSinkTokenFilter tee1 = new TeeSinkTokenFilter(new MockTokenizer(new StringReader(buffer1.ToString()), MockTokenizer.WHITESPACE, false));
            //JAVA TO C# CONVERTER WARNING: The original Java variable was marked 'final':
            //ORIGINAL LINE: final TeeSinkTokenFilter.SinkTokenStream dogDetector = tee1.newSinkTokenStream(dogFilter);
            TeeSinkTokenFilter.SinkTokenStream dogDetector = tee1.newSinkTokenStream(dogFilter);
            //JAVA TO C# CONVERTER WARNING: The original Java variable was marked 'final':
            //ORIGINAL LINE: final TeeSinkTokenFilter.SinkTokenStream theDetector = tee1.newSinkTokenStream(theFilter);
            TeeSinkTokenFilter.SinkTokenStream theDetector = tee1.newSinkTokenStream(theFilter);
            tee1.reset();
            //JAVA TO C# CONVERTER WARNING: The original Java variable was marked 'final':
            //ORIGINAL LINE: final TokenStream source1 = new CachingTokenFilter(tee1);
            TokenStream source1 = new CachingTokenFilter(tee1);

            tee1.addAttribute(typeof(CheckClearAttributesAttribute));
            dogDetector.addAttribute(typeof(CheckClearAttributesAttribute));
            theDetector.addAttribute(typeof(CheckClearAttributesAttribute));

            //JAVA TO C# CONVERTER WARNING: The original Java variable was marked 'final':
            //ORIGINAL LINE: final TeeSinkTokenFilter tee2 = new TeeSinkTokenFilter(new MockTokenizer(new java.io.StringReader(buffer2.toString()), MockTokenizer.WHITESPACE, false));
            TeeSinkTokenFilter tee2 = new TeeSinkTokenFilter(new MockTokenizer(new StringReader(buffer2.ToString()), MockTokenizer.WHITESPACE, false));
            tee2.addSinkTokenStream(dogDetector);
            tee2.addSinkTokenStream(theDetector);
            //JAVA TO C# CONVERTER WARNING: The original Java variable was marked 'final':
            //ORIGINAL LINE: final TokenStream source2 = tee2;
            TokenStream source2 = tee2;

            assertTokenStreamContents(source1, tokens1);
            assertTokenStreamContents(source2, tokens2);

            assertTokenStreamContents(theDetector, new string[]{"The", "the", "The", "the"});
            assertTokenStreamContents(dogDetector, new string[]{"Dogs", "Dogs"});

            source1.reset();
            TokenStream lowerCasing = new LowerCaseFilter(TEST_VERSION_CURRENT, source1);
            string[] lowerCaseTokens = new string[tokens1.Length];
            for (int i = 0; i < tokens1.Length; i++)
            {
              lowerCaseTokens[i] = tokens1[i].ToLower(Locale.ROOT);
            }
            assertTokenStreamContents(lowerCasing, lowerCaseTokens);
        }
Exemplo n.º 10
0
        //JAVA TO C# CONVERTER WARNING: Method 'throws' clauses are not available in .NET:
        //ORIGINAL LINE: public void testGeneral() throws java.io.IOException
        public virtual void testGeneral()
        {
            //JAVA TO C# CONVERTER WARNING: The original Java variable was marked 'final':
            //ORIGINAL LINE: final TeeSinkTokenFilter source = new TeeSinkTokenFilter(new MockTokenizer(new java.io.StringReader(buffer1.toString()), MockTokenizer.WHITESPACE, false));
            TeeSinkTokenFilter source = new TeeSinkTokenFilter(new MockTokenizer(new StringReader(buffer1.ToString()), MockTokenizer.WHITESPACE, false));
            //JAVA TO C# CONVERTER WARNING: The original Java variable was marked 'final':
            //ORIGINAL LINE: final TokenStream sink1 = source.newSinkTokenStream();
            TokenStream sink1 = source.newSinkTokenStream();
            //JAVA TO C# CONVERTER WARNING: The original Java variable was marked 'final':
            //ORIGINAL LINE: final TokenStream sink2 = source.newSinkTokenStream(theFilter);
            TokenStream sink2 = source.newSinkTokenStream(theFilter);

            source.addAttribute(typeof(CheckClearAttributesAttribute));
            sink1.addAttribute(typeof(CheckClearAttributesAttribute));
            sink2.addAttribute(typeof(CheckClearAttributesAttribute));

            assertTokenStreamContents(source, tokens1);
            assertTokenStreamContents(sink1, tokens1);
            assertTokenStreamContents(sink2, new string[]{"The", "the"});
        }
Exemplo n.º 11
0
        // LUCENE-1448
        // TODO: instead of testing it this way, we can test
        // with BaseTokenStreamTestCase now...
        //JAVA TO C# CONVERTER WARNING: Method 'throws' clauses are not available in .NET:
        //ORIGINAL LINE: public void testEndOffsetPositionWithTeeSinkTokenFilter() throws Exception
        public virtual void testEndOffsetPositionWithTeeSinkTokenFilter()
        {
            Directory dir = newDirectory();
            Analyzer analyzer = new MockAnalyzer(random(), MockTokenizer.WHITESPACE, false);
            IndexWriter w = new IndexWriter(dir, newIndexWriterConfig(TEST_VERSION_CURRENT, analyzer));
            Document doc = new Document();
            TokenStream tokenStream = analyzer.tokenStream("field", "abcd   ");
            TeeSinkTokenFilter tee = new TeeSinkTokenFilter(tokenStream);
            TokenStream sink = tee.newSinkTokenStream();
            FieldType ft = new FieldType(TextField.TYPE_NOT_STORED);
            ft.StoreTermVectors = true;
            ft.StoreTermVectorOffsets = true;
            ft.StoreTermVectorPositions = true;
            Field f1 = new Field("field", tee, ft);
            Field f2 = new Field("field", sink, ft);
            doc.add(f1);
            doc.add(f2);
            w.addDocument(doc);
            w.close();

            IndexReader r = DirectoryReader.open(dir);
            Terms vector = r.getTermVectors(0).terms("field");
            assertEquals(1, vector.size());
            TermsEnum termsEnum = vector.iterator(null);
            termsEnum.next();
            assertEquals(2, termsEnum.totalTermFreq());
            DocsAndPositionsEnum positions = termsEnum.docsAndPositions(null, null);
            assertTrue(positions.nextDoc() != DocIdSetIterator.NO_MORE_DOCS);
            assertEquals(2, positions.freq());
            positions.nextPosition();
            assertEquals(0, positions.startOffset());
            assertEquals(4, positions.endOffset());
            positions.nextPosition();
            assertEquals(8, positions.startOffset());
            assertEquals(12, positions.endOffset());
            assertEquals(DocIdSetIterator.NO_MORE_DOCS, positions.nextDoc());
            r.close();
            dir.close();
        }
Exemplo n.º 12
0
        /// <summary>
        /// Not an explicit test, just useful to print out some info on performance
        /// </summary>
//JAVA TO C# CONVERTER WARNING: Method 'throws' clauses are not available in .NET:
//ORIGINAL LINE: public void performance() throws Exception
        public virtual void performance()
        {
            int[] tokCount  = new int[] { 100, 500, 1000, 2000, 5000, 10000 };
            int[] modCounts = new int[] { 1, 2, 5, 10, 20, 50, 100, 200, 500 };
            for (int k = 0; k < tokCount.Length; k++)
            {
                StringBuilder buffer = new StringBuilder();
                Console.WriteLine("-----Tokens: " + tokCount[k] + "-----");
                for (int i = 0; i < tokCount[k]; i++)
                {
                    buffer.Append(English.intToEnglish(i).toUpperCase(Locale.ROOT)).Append(' ');
                }
                //make sure we produce the same tokens
                TeeSinkTokenFilter teeStream = new TeeSinkTokenFilter(new StandardFilter(TEST_VERSION_CURRENT, new StandardTokenizer(TEST_VERSION_CURRENT, new StringReader(buffer.ToString()))));
                TokenStream        sink      = teeStream.newSinkTokenStream(new ModuloSinkFilter(this, 100));
                teeStream.consumeAllTokens();
                TokenStream       stream  = new ModuloTokenFilter(this, new StandardFilter(TEST_VERSION_CURRENT, new StandardTokenizer(TEST_VERSION_CURRENT, new StringReader(buffer.ToString()))), 100);
                CharTermAttribute tfTok   = stream.addAttribute(typeof(CharTermAttribute));
                CharTermAttribute sinkTok = sink.addAttribute(typeof(CharTermAttribute));
                for (int i = 0; stream.incrementToken(); i++)
                {
                    assertTrue(sink.incrementToken());
                    assertTrue(tfTok + " is not equal to " + sinkTok + " at token: " + i, tfTok.Equals(sinkTok) == true);
                }

                //simulate two fields, each being analyzed once, for 20 documents
                for (int j = 0; j < modCounts.Length; j++)
                {
                    int  tfPos = 0;
                    long start = DateTimeHelperClass.CurrentUnixTimeMillis();
                    for (int i = 0; i < 20; i++)
                    {
                        stream = new StandardFilter(TEST_VERSION_CURRENT, new StandardTokenizer(TEST_VERSION_CURRENT, new StringReader(buffer.ToString())));
                        PositionIncrementAttribute posIncrAtt = stream.getAttribute(typeof(PositionIncrementAttribute));
                        while (stream.incrementToken())
                        {
                            tfPos += posIncrAtt.PositionIncrement;
                        }
                        stream     = new ModuloTokenFilter(this, new StandardFilter(TEST_VERSION_CURRENT, new StandardTokenizer(TEST_VERSION_CURRENT, new StringReader(buffer.ToString()))), modCounts[j]);
                        posIncrAtt = stream.getAttribute(typeof(PositionIncrementAttribute));
                        while (stream.incrementToken())
                        {
                            tfPos += posIncrAtt.PositionIncrement;
                        }
                    }
                    long finish = DateTimeHelperClass.CurrentUnixTimeMillis();
                    Console.WriteLine("ModCount: " + modCounts[j] + " Two fields took " + (finish - start) + " ms");
                    int sinkPos = 0;
                    //simulate one field with one sink
                    start = DateTimeHelperClass.CurrentUnixTimeMillis();
                    for (int i = 0; i < 20; i++)
                    {
                        teeStream = new TeeSinkTokenFilter(new StandardFilter(TEST_VERSION_CURRENT, new StandardTokenizer(TEST_VERSION_CURRENT, new StringReader(buffer.ToString()))));
                        sink      = teeStream.newSinkTokenStream(new ModuloSinkFilter(this, modCounts[j]));
                        PositionIncrementAttribute posIncrAtt = teeStream.getAttribute(typeof(PositionIncrementAttribute));
                        while (teeStream.incrementToken())
                        {
                            sinkPos += posIncrAtt.PositionIncrement;
                        }
                        //System.out.println("Modulo--------");
                        posIncrAtt = sink.getAttribute(typeof(PositionIncrementAttribute));
                        while (sink.incrementToken())
                        {
                            sinkPos += posIncrAtt.PositionIncrement;
                        }
                    }
                    finish = DateTimeHelperClass.CurrentUnixTimeMillis();
                    Console.WriteLine("ModCount: " + modCounts[j] + " Tee fields took " + (finish - start) + " ms");
                    assertTrue(sinkPos + " does not equal: " + tfPos, sinkPos == tfPos);
                }
                Console.WriteLine("- End Tokens: " + tokCount[k] + "-----");
            }
        }