Ejemplo n.º 1
0
  @UsesExternalServices
  @Test
  public void testRequestIndependence() {
    @SuppressWarnings("unchecked")
    final Controller controller =
        ControllerFactory.createCachingPooling(org.carrot2.core.IDocumentSource.class);
    closeAfterTest(controller);

    final Map<String, Object> attrs = Maps.newHashMap();

    CommonAttributesDescriptor.attributeBuilder(attrs).results(50).query("data mining");

    controller.process(
        attrs, org.carrot2.webapp.source.WebDocumentSource.class, LingoClusteringAlgorithm.class);

    attrs.clear();
    CommonAttributesDescriptor.attributeBuilder(attrs)
        .results(50)
        .query(WebDocumentSource.QUERY_FAILURE);

    try {
      controller.process(
          attrs, org.carrot2.webapp.source.WebDocumentSource.class, LingoClusteringAlgorithm.class);
      fail();
    } catch (ProcessingException e) {
      assertThat(e.getCause().getMessage()).contains("Synthetic failure");
    }
  }
Ejemplo n.º 2
0
 @SuppressWarnings("unchecked")
 @Override
 public List<String> getClusterByCarrotVersion2(String query) {
   // TODO Auto-generated method stub
   List<String> strs = new ArrayList<String>();
   final Controller controller = ControllerFactory.createPooling();
   final Map<String, Object> luceneGlobalAttributes = new HashMap<String, Object>();
   LuceneDocumentSourceDescriptor.attributeBuilder(luceneGlobalAttributes).directory(directory);
   SimpleFieldMapperDescriptor.attributeBuilder(luceneGlobalAttributes)
       .titleField(TITLE_FIELD)
       .contentField(CONTENTS_FIELD)
       .searchFields(Arrays.asList(new String[] {TITLE_FIELD, CONTENTS_FIELD}));
   controller.init(
       new HashMap<String, Object>(),
       new ProcessingComponentConfiguration(
           LuceneDocumentSource.class, "lucene", luceneGlobalAttributes));
   final Map<String, Object> processingAttributes = Maps.newHashMap();
   CommonAttributesDescriptor.attributeBuilder(processingAttributes).query(query);
   ProcessingResult process =
       controller.process(
           processingAttributes, "lucene", LingoClusteringAlgorithm.class.getName());
   for (Cluster c : process.getClusters()) {
     strs.add(c.getLabel() + " >>>> " + c.getAllDocuments().size());
   }
   return strs;
 }
Ejemplo n.º 3
0
  public static void main(String[] args) throws IOException {
    /*
     * We will use the CachingController for this example. Running
     * LuceneDocumentSource within the CachingController will let us open the index
     * once per component initialization and not once per query, which would be the
     * case with SimpleController. We will also use this opportunity to show how
     * component-specific attribute values can be passed during CachingComponent
     * initialization.
     */

    /*
     * Create a caching controller that will reuse processing component instances, but
     * will not perform any caching of results produced by components. We will leave
     * caching of documents from Lucene index to Lucene and the operating system
     * caches.
     */
    final Controller controller = ControllerFactory.createPooling();

    /*
     * Prepare a map with component-specific attributes. Here, this map will contain
     * the index location and names of fields to be used to fetch document title and
     * summary.
     */
    final Map<String, Object> luceneGlobalAttributes = new HashMap<String, Object>();

    String indexPath = "put your index path here or pass as the first argument";
    if (args.length == 1) {
      indexPath = args[0];
    }

    LuceneDocumentSourceDescriptor.attributeBuilder(luceneGlobalAttributes)
        .directory(FSDirectory.open(new File(indexPath)));

    /*
     * Specify fields providing data inside your Lucene index.
     */
    SimpleFieldMapperDescriptor.attributeBuilder(luceneGlobalAttributes)
        .titleField("title")
        .contentField("snippet")
        .searchFields(Arrays.asList(new String[] {"titleField", "fullContent"}));

    /*
     * Initialize the controller passing the above attributes as component-specific
     * for Lucene. The global attributes map will be empty. Note that we've provided
     * an identifier for our specially-configured Lucene component, we'll need to use
     * this identifier when performing processing.
     */
    controller.init(
        new HashMap<String, Object>(),
        new ProcessingComponentConfiguration(
            LuceneDocumentSource.class, "lucene", luceneGlobalAttributes));

    /*
     * Perform processing.
     */
    String query = "mining";
    final Map<String, Object> processingAttributes = Maps.newHashMap();
    CommonAttributesDescriptor.attributeBuilder(processingAttributes).query(query);

    /*
     * We need to refer to the Lucene component by its identifier we set during
     * initialization. As we've not assigned any identifier to the
     * LingoClusteringAlgorithm we want to use, we can its fully qualified class name.
     */
    ProcessingResult process =
        controller.process(
            processingAttributes, "lucene", LingoClusteringAlgorithm.class.getName());

    ConsoleFormatter.displayResults(process);
  }
  /** Entry point. */
  public static void main(String[] args) throws IOException {
    /*
     * We will use the CachingController for this example. Running
     * LuceneDocumentSource within the CachingController will let us open the index
     * once per component initialization and not once per query, which would be the
     * case with SimpleController. We will also use this opportunity to show how
     * component-specific attribute values can be passed during CachingComponent
     * initialization.
     */

    /*
     * Create a caching controller that will reuse processing component instances, but
     * will not perform any caching of results produced by components. We will leave
     * caching of documents from Lucene index to Lucene and the operating system
     * caches.
     */
    final Controller controller = ControllerFactory.createPooling();

    /*
     * Prepare a map with component-specific attributes. Here, this map will contain
     * the index location and names of fields to be used to fetch document title and
     * summary.
     */
    final Map<String, Object> luceneGlobalAttributes = new HashMap<String, Object>();

    String indexPath = "put your index path here or pass as the first argument";
    if (args.length == 1) {
      indexPath = args[0];
    }

    // Sanity check.
    if (!new File(indexPath).isDirectory()) {
      System.err.println("Index directory does not exist: " + indexPath);
      return;
    }

    LuceneDocumentSourceDescriptor.attributeBuilder(luceneGlobalAttributes)
        .directory(FSDirectory.open(new File(indexPath)));

    /*
     * In ClusteringDataFromLucene we used a simple configuration of
     * LuceneDocumentSource whereby we only provided the names of Lucene fields to be
     * used for titles and summaries. If more advanced mapping of Lucene documents is
     * required, you can implement your own version of IFieldMapper as below.
     *
     * Note that we could also provide here an instance of the mapper rather than
     * its class. The differences are summarized below:
     *
     * > Class: Class has to have a no-parameter constructor. Instances of the
     *   class will not be shared between processing threads, which means the
     *   implementation does not have to be thread-safe. Recommended in most
     *   situations unless the instances are expensive to create.
     *
     * > Instance: The provided instance will be shared across processing threads,
     *   which means the implementation MUST be thread-safe.
     */
    LuceneDocumentSourceDescriptor.attributeBuilder(luceneGlobalAttributes)
        .fieldMapper(new CustomFieldMapper());

    /*
     * The Analyzer used by Lucene while searching can also be provided via factory
     * because it does not have a parameterless constructor.
     */
    LuceneDocumentSourceDescriptor.attributeBuilder(luceneGlobalAttributes)
        .analyzer(StandardAnalyzerFactory.class);

    /*
     * Initialize the controller passing the above attributes as component-specific
     * for Lucene. The global attributes map will be empty. Note that we've provided
     * an identifier for our specially-configured Lucene component, we'll need to use
     * this identifier when performing processing.
     */
    controller.init(
        new HashMap<String, Object>(),
        new ProcessingComponentConfiguration(
            LuceneDocumentSource.class, "lucene", luceneGlobalAttributes));

    /*
     * Perform processing.
     */
    final String query = "mining";
    final Map<String, Object> processingAttributes = Maps.newHashMap();
    CommonAttributesDescriptor.attributeBuilder(processingAttributes).query(query);

    /*
     * We need to refer to the Lucene component by its identifier we set during
     * initialization. As we've not assigned any identifier to the
     * LingoClusteringAlgorithm we want to use, we can its fully qualified class name.
     */
    ProcessingResult process =
        controller.process(
            processingAttributes, "lucene", LingoClusteringAlgorithm.class.getName());

    ConsoleFormatter.displayResults(process);
  }