Examples of org.carrot2.core.Document

org.carrot2.core.Document
A document that to be processed by the framework. Each document is a collection of fields carrying different bits of information, e.g. {@link #TITLE} or{@link #CONTENT_URL}.

        List<Document> doc16 = result16.getDocuments();
        List<Document> doc8 = result8.getDocuments();
        assertThat(doc16.size()).isEqualTo(doc8.size());
        for (int i = 0; i < Math.min(doc16.size(), doc8.size()); i++)
        {
            Document d1 = doc16.get(i);
            Document d2 = doc8.get(i);
            assertThat(d1.getTitle()).isEqualTo(d2.getTitle());
            assertThat(d1.getSummary()).isEqualTo(d2.getSummary());
        }
    }

View Full Code Here

    private static final String FIELD = "field";


    @Test
    public void testScalarField()
    {
        final Document d11 = documentWithField("1");
        final Document d12 = documentWithField("1");
        final Document d21 = documentWithField("2");
        final Document d22 = documentWithField("2");
        final Document dn = documentWithField(null);
        final List<Document> documents = Lists.newArrayList(d11, d12, d21, d22, dn);


        check(documents, Lists.<Cluster> newArrayList(new Cluster("1", d11, d12),
            new Cluster("2", d21, d22)), dn);
    }

View Full Code Here

    }


    @Test
    public void testCollectionField()
    {
        final Document d11 = documentWithField(Lists.newArrayList("11", "12"));
        final Document d12 = documentWithField(Lists.newArrayList("11"));
        final Document d21 = documentWithField(Lists.newArrayList("21", "22"));
        final Document d22 = documentWithField(Lists.newArrayList("23"));
        final Document dn = documentWithField(null);
        final List<Document> documents = Lists.newArrayList(d11, d12, d21, d22, dn);


        check(documents, Lists.<Cluster> newArrayList(new Cluster("11", d11, d12),
            new Cluster("12", d11), new Cluster("21", d21), new Cluster("22", d21),
            new Cluster("23", d22)), dn);

View Full Code Here

        assertThatClusters(clusters).isEquivalentTo(expectedClusters);
    }


    private Document documentWithField(Object fieldValue)
    {
        final Document document = new Document();
        document.setField(FIELD, fieldValue);
        return document;
    }

View Full Code Here

    protected void createDocumentsWithFields(String [] fields, String... fieldValues)
    {
        int fieldValuesIndex = 0;
        while (fieldValuesIndex < fieldValues.length)
        {
            Document document = new Document();
            for (String fieldName : fields)
            {
                document.setField(fieldName, fieldValues[fieldValuesIndex++]);


                if (fieldValuesIndex >= fieldValues.length)
                {
                    break;
                }

View Full Code Here


                final int topicId = Integer.parseInt(topicSplit[0]);
                final int resultIndex = Integer.parseInt(topicSplit[1]);


                // Build document
                final Document document = new Document();
                document.setField(Document.CONTENT_URL, split[1]);
                document.setField(Document.TITLE, split[2]);
                if (split.length > 3)
                {
                    document.setField(Document.SUMMARY, split[3]);
                }
                document
                    .setField(
                        Document.PARTITIONS,
                        ImmutableList
                            .of(buildTopicId(
                                topicId,

View Full Code Here

        attrs = Maps.newHashMap();
    }
    
    private void check(String query, String snippetToHighlight, String expectedSnippet)
    {
        final Document document = new Document();
        document.setField(Document.SUMMARY, snippetToHighlight);


        final Controller controller = ControllerFactory.createSimple();
        try
        {
            controller.init(attrs);
            ProcessingResult result = controller.process(
                Lists.newArrayList(document),
                query, 
                QueryWordHighlighter.class);
            
            final Document highlightedDocument = result.getDocuments().get(0);
            assertThat(highlightedDocument.getField(Document.SUMMARY + QueryWordHighlighter.HIGHLIGHTED_FIELD_NAME_SUFFIX))
                .isEqualTo(expectedSnippet);
        }
        finally
        {
            controller.dispose();

View Full Code Here

        return newDoc(title, summary, null);
    }


    public PreprocessingContextBuilder newDoc(String title, String summary, String contentUrl)
    {
        documents.add(new Document(title, summary, contentUrl));
        return this;
    }

View Full Code Here

        return this;
    }


    public PreprocessingContextBuilder newDoc(FieldValue... fields)
    {
        Document doc = new Document();
        for (FieldValue fv : fields)
            doc.setField(fv.field, fv.value);
        documents.add(doc);
        return this;
    }

View Full Code Here

    {
        final List<Document> documents = Lists.newArrayList();
        final int documentCount = randomIntBetween(1, 100);
        for (int i = 0; i < documentCount; i++)
        {
            documents.add(new Document());
        }


        final List<Cluster> clusters = cluster(documents).getClusters();


        assertNotNull(clusters);

View Full Code Here

0 1 2 3 4 5 6 7 8 9

TOP

Related Classes of org.carrot2.core.Document

com.carrotsearch.hppc.IntArrayList

com.carrotsearch.hppc.IntIntOpenHashMap

com.carrotsearch.hppc.IntStack

com.tamingtext.carrot2.Carrot2ExampleTest

org.apache.http.message.BasicNameValuePair

org.apache.lucene.search.IndexSearcher

org.apache.mahout.math.matrix.DoubleMatrix2D

org.apache.velocity.VelocityContext

org.carrot2.cli.batch.BatchApp

org.carrot2.clustering.kmeans.BisectingKMeansClusteringAlgorithm

All source code are property of their respective owners. Java is a trademark of Sun Microsystems, Inc and owned by ORACLE Inc. Contact coftware#gmail.com.