Examples with EntityId uk.gov.gchq.gaffer.data.element.id.EntityId used on opensource projects

Example 76 with EntityId

use of uk.gov.gchq.gaffer.data.element.id.EntityId in project Gaffer by gchq.

the class AbstractExamplesFactoryTest method shouldUseSchemaToCreateGetElementsInput.

@Test
public void shouldUseSchemaToCreateGetElementsInput() throws InstantiationException, IllegalAccessException {
    // Given
    TestExamplesFactory examplesFactory = new TestExamplesFactory(SCHEMA);
    // When
    GetElements operation = (GetElements) examplesFactory.generateExample(GetElements.class);
    // Then
    int size = 0;
    for (ElementId e : operation.getInput()) {
        size++;
        if (e instanceof EntityId) {
            assertEquals(String.class, ((EntityId) e).getVertex().getClass());
        } else {
            assertEquals(String.class, ((EdgeId) e).getDestination().getClass());
            assertEquals(String.class, ((EdgeId) e).getSource().getClass());
        }
    }
    assertEquals(2, size);
}

Example 77 with EntityId

use of uk.gov.gchq.gaffer.data.element.id.EntityId in project Gaffer by gchq.

the class AccumuloIDWithinSetRetrieverTest method shouldLoadElementsWhenMoreElementsThanFitInBatchScanner.

private void shouldLoadElementsWhenMoreElementsThanFitInBatchScanner(final boolean loadIntoMemory, final AccumuloStore store) throws StoreException {
    store.getProperties().setMaxEntriesForBatchScanner("1");
    // Query for all edges in set {A0, A23}
    final Set<EntityId> seeds = new HashSet<>();
    seeds.add(AccumuloTestData.SEED_A0);
    seeds.add(AccumuloTestData.SEED_A23);
    final GetElementsWithinSet op = new GetElementsWithinSet.Builder().view(defaultView).input(seeds).build();
    final Set<Element> results = returnElementsFromOperation(store, op, new User(), loadIntoMemory);
    assertThat(results).contains(AccumuloTestData.EDGE_A0_A23, AccumuloTestData.A0_ENTITY, AccumuloTestData.A23_ENTITY);
    // Query for all edges in set {A1} - there shouldn't be any, but we will get the entity for A1
    final GetElementsWithinSet a1Operation = new GetElementsWithinSet.Builder().view(defaultView).input(AccumuloTestData.SEED_A1_SET).build();
    final Set<Element> a1Results = returnElementsFromOperation(store, a1Operation, new User(), loadIntoMemory);
    assertThat(a1Results).hasSize(1).contains(AccumuloTestData.A1_ENTITY);
    // Query for all edges in set {A1, A2} - there shouldn't be any edges but will
    // get the two entities
    final Set<EntityId> a1A2Seeds = new HashSet<>();
    a1A2Seeds.add(AccumuloTestData.SEED_A1);
    a1A2Seeds.add(AccumuloTestData.SEED_A2);
    final GetElementsWithinSet a1A23Operation = new GetElementsWithinSet.Builder().view(defaultView).input(a1A2Seeds).build();
    final Set<Element> a1A23Results = returnElementsFromOperation(store, a1A23Operation, new User(), loadIntoMemory);
    assertThat(a1A23Results).hasSize(2).contains(AccumuloTestData.A1_ENTITY, AccumuloTestData.A2_ENTITY);
}

Example 78 with EntityId

use of uk.gov.gchq.gaffer.data.element.id.EntityId in project Gaffer by gchq.

the class AccumuloIDWithinSetRetrieverTest method shouldDealWithOutgoingEdgesOnlyOption.

private void shouldDealWithOutgoingEdgesOnlyOption(final AccumuloStore store) {
    try {
        // Set outgoing edges only option, and query for the set {C,D}.
        final Set<EntityId> seeds = new HashSet<>();
        seeds.add(new EntitySeed("C"));
        seeds.add(new EntitySeed("D"));
        final Set<Element> expectedResults = new HashSet<>();
        expectedResults.add(AccumuloTestData.EDGE_C_D_DIRECTED);
        expectedResults.add(AccumuloTestData.EDGE_C_D_UNDIRECTED);
        final GetElementsWithinSet op = new GetElementsWithinSet.Builder().view(defaultView).input(seeds).build();
        final Set<Element> results = returnElementsFromOperation(store, op, new User(), true);
        assertEquals(expectedResults, results);
    } catch (final StoreException e) {
        fail("Failed to set up graph in Accumulo with exception: " + e);
    }
}

Example 79 with EntityId

use of uk.gov.gchq.gaffer.data.element.id.EntityId in project Gaffer by gchq.

the class AccumuloIDWithinSetRetrieverTest method shouldDealWithFalsePositives.

private void shouldDealWithFalsePositives(final boolean loadIntoMemory, final AccumuloStore store) throws StoreException {
    // Query for all edges in set {A0, A23}
    final Set<EntityId> seeds = new HashSet<>();
    seeds.add(AccumuloTestData.SEED_A0);
    seeds.add(AccumuloTestData.SEED_A23);
    // positive sensible.
    for (int i = 0; i < 10; i++) {
        seeds.add(new EntitySeed("abc" + i));
    }
    // Need to make sure that the Bloom filter we create has the same size and the same number of hashes as the
    // one that GraphElementsWithStatisticsWithinSetRetriever creates.
    final int numItemsToBeAdded = loadIntoMemory ? seeds.size() : 20;
    if (!loadIntoMemory) {
        store.getProperties().setMaxEntriesForBatchScanner("20");
    }
    // Find something that will give a false positive
    // Need to repeat the logic used in the getGraphElementsWithStatisticsWithinSet() method.
    // Calculate sensible size of filter, aiming for false positive rate of 1 in 10000, with a maximum size of
    // maxBloomFilterToPassToAnIterator bytes.
    int size = (int) (-numItemsToBeAdded * Math.log(0.0001) / Math.pow(Math.log(2.0), 2.0));
    size = Math.min(size, store.getProperties().getMaxBloomFilterToPassToAnIterator());
    // Work out optimal number of hashes to use in Bloom filter based on size of set - optimal number of hashes is
    // (m/n)ln 2 where m is the size of the filter in bits and n is the number of items that will be added to the set.
    final int numHashes = Math.max(1, (int) ((size / numItemsToBeAdded) * Math.log(2)));
    // Create Bloom filter and add seeds to it
    final BloomFilter filter = new BloomFilter(size, numHashes, Hash.MURMUR_HASH);
    for (final EntityId seed : seeds) {
        filter.add(new Key(store.getKeyPackage().getKeyConverter().serialiseVertex(seed.getVertex())));
    }
    // Test random items against it - should only have to shouldRetrieveElementsInRangeBetweenSeeds MAX_SIZE_BLOOM_FILTER / 2 on average before find a
    // false positive (but impose an arbitrary limit to avoid an infinite loop if there's a problem).
    int count = 0;
    int maxNumberOfTries = 50 * store.getProperties().getMaxBloomFilterToPassToAnIterator();
    while (count < maxNumberOfTries) {
        count++;
        if (filter.membershipTest(new Key(("" + count).getBytes()))) {
            break;
        }
    }
    if (count == maxNumberOfTries) {
        fail("Didn't find a false positive");
    }
    // False positive is "" + count so create an edge from seeds to that
    final GetElementsWithinSet op = new GetElementsWithinSet.Builder().view(defaultView).input(seeds).build();
    // Now query for all edges in set - shouldn't get the false positive
    final Set<Element> results = returnElementsFromOperation(store, op, new User(), loadIntoMemory);
    // Check results are as expected
    assertThat(results).contains(AccumuloTestData.EDGE_A0_A23, AccumuloTestData.A0_ENTITY, AccumuloTestData.A23_ENTITY);
}

Example 80 with EntityId

use of uk.gov.gchq.gaffer.data.element.id.EntityId in project Gaffer by gchq.

the class AbstractExamplesFactory method getAdjacentIds.

public GetAdjacentIds getAdjacentIds() {
    final GetAdjacentIds op = new GetAdjacentIds();
    final List<EntityId> seeds = new ArrayList<>();
    if (hasEntities()) {
        seeds.add(getEntityId(1));
    } else if (hasEdges()) {
        seeds.add(new EntitySeed(getEdgeId(1, 2).getSource()));
    }
    op.setInput(seeds);
    populateOperation(op);
    return op;
}