use of co.cask.cdap.api.data.schema.Schema in project cdap by caskdata.
the class ObjectStores method objectStoreProperties.
/**
* Creates properties for {@link ObjectStore} dataset instance.
*
* @param type type of objects to be stored in dataset
* @return {@link DatasetProperties} for the dataset
* @throws UnsupportedTypeException
*/
public static DatasetProperties objectStoreProperties(Type type, DatasetProperties props) throws UnsupportedTypeException {
Schema schema = new ReflectionSchemaGenerator().generate(type);
TypeRepresentation typeRep = new TypeRepresentation(type);
return DatasetProperties.builder().add("schema", schema.toString()).add("type", new Gson().toJson(typeRep)).addAll(props.getProperties()).build();
}
use of co.cask.cdap.api.data.schema.Schema in project cdap by caskdata.
the class RecordFormat method initialize.
/**
* Initialize the format with the given desired schema and properties.
* Guaranteed to be called once before any other method is called.
*
* @param formatSpecification the specification for the format, containing the desired schema and settings
* @throws UnsupportedTypeException if the desired schema and properties are not supported
*/
public void initialize(@Nullable FormatSpecification formatSpecification) throws UnsupportedTypeException {
Schema desiredSchema = null;
Map<String, String> settings = Collections.emptyMap();
if (formatSpecification != null) {
desiredSchema = formatSpecification.getSchema();
settings = formatSpecification.getSettings();
}
desiredSchema = desiredSchema == null ? getDefaultSchema() : desiredSchema;
if (desiredSchema == null) {
String msg = "A schema must be provided to the format: ";
if (formatSpecification != null) {
msg += formatSpecification.getName();
}
throw new UnsupportedTypeException(msg);
}
validateIsRecord(desiredSchema);
validateSchema(desiredSchema);
this.schema = desiredSchema;
configure(settings);
}
use of co.cask.cdap.api.data.schema.Schema in project cdap by caskdata.
the class FlowVerification method verify.
/**
* Verifies a single {@link FlowSpecification} for a {@link co.cask.cdap.api.flow.Flow}.
*
* @param input to be verified
* @return An instance of {@link VerifyResult} depending of status of verification.
*/
@Override
public VerifyResult verify(ApplicationId appId, final FlowSpecification input) {
VerifyResult verifyResult = super.verify(appId, input);
if (!verifyResult.isSuccess()) {
return verifyResult;
}
String flowName = input.getName();
// Check if there are no flowlets.
if (input.getFlowlets().isEmpty()) {
return VerifyResult.failure(Err.Flow.ATLEAST_ONE_FLOWLET, flowName);
}
// Check if there no connections.
if (input.getConnections().isEmpty()) {
return VerifyResult.failure(Err.Flow.ATLEAST_ONE_CONNECTION, flowName);
}
// We go through each Flowlet and verify the flowlets.
// First collect all source flowlet names
Set<String> sourceFlowletNames = Sets.newHashSet();
for (FlowletConnection connection : input.getConnections()) {
if (connection.getSourceType() == FlowletConnection.Type.FLOWLET) {
sourceFlowletNames.add(connection.getSourceName());
}
}
for (Map.Entry<String, FlowletDefinition> entry : input.getFlowlets().entrySet()) {
FlowletDefinition defn = entry.getValue();
String flowletName = defn.getFlowletSpec().getName();
// Check if the Flowlet Name is an ID.
if (!EntityId.isValidId(defn.getFlowletSpec().getName())) {
return VerifyResult.failure(Err.NOT_AN_ID, flowName + ":" + flowletName);
}
// We check if all the dataset names used are ids
for (String dataSet : defn.getDatasets()) {
if (!EntityId.isValidDatasetId(dataSet)) {
return VerifyResult.failure(Err.NOT_AN_ID, flowName + ":" + flowletName + ":" + dataSet);
}
}
// Check if the flowlet has output, it must be appear as source flowlet in at least one connection
if (entry.getValue().getOutputs().size() > 0 && !sourceFlowletNames.contains(flowletName)) {
return VerifyResult.failure(Err.Flow.OUTPUT_NOT_CONNECTED, flowName, flowletName);
}
}
// NOTE: We should unify the logic here and the queue spec generation, as they are doing the same thing.
Table<QueueSpecificationGenerator.Node, String, Set<QueueSpecification>> queueSpecTable = new SimpleQueueSpecificationGenerator(appId).create(input);
// For all connections, there should be an entry in the table.
for (FlowletConnection connection : input.getConnections()) {
QueueSpecificationGenerator.Node node;
if (connection.getSourceType() == FlowletConnection.Type.FLOWLET) {
node = new QueueSpecificationGenerator.Node(connection.getSourceType(), connection.getSourceName());
} else {
String sourceNamespace = connection.getSourceNamespace() == null ? appId.getNamespace() : connection.getSourceNamespace();
node = new QueueSpecificationGenerator.Node(connection.getSourceType(), sourceNamespace, connection.getSourceName());
}
if (!queueSpecTable.contains(node, connection.getTargetName())) {
return VerifyResult.failure(Err.Flow.NO_INPUT_FOR_OUTPUT, flowName, connection.getTargetName(), connection.getSourceType(), connection.getSourceName());
}
}
// For each output entity, check for any unconnected output
for (QueueSpecificationGenerator.Node node : queueSpecTable.rowKeySet()) {
// For stream output, no need to check
if (node.getType() == FlowletConnection.Type.STREAM) {
continue;
}
// For all outputs of a flowlet, remove all the matched connected schema, if there is anything left,
// then it's a incomplete flow connection (has output not connect to any input).
Multimap<String, Schema> outputs = toMultimap(input.getFlowlets().get(node.getName()).getOutputs());
for (Map.Entry<String, Set<QueueSpecification>> entry : queueSpecTable.row(node).entrySet()) {
for (QueueSpecification queueSpec : entry.getValue()) {
outputs.remove(queueSpec.getQueueName().getSimpleName(), queueSpec.getOutputSchema());
}
}
if (!outputs.isEmpty()) {
return VerifyResult.failure(Err.Flow.MORE_OUTPUT_NOT_ALLOWED, flowName, node.getType().toString().toLowerCase(), node.getName(), outputs);
}
}
return VerifyResult.success();
}
use of co.cask.cdap.api.data.schema.Schema in project cdap by caskdata.
the class ETLWorkerTest method testOneSourceOneSink.
@Test
@Category(SlowTests.class)
public void testOneSourceOneSink() throws Exception {
Schema schema = Schema.recordOf("test", Schema.Field.of("id", Schema.of(Schema.Type.STRING)), Schema.Field.of("name", Schema.of(Schema.Type.STRING)));
List<StructuredRecord> input = new ArrayList<>();
input.add(StructuredRecord.builder(schema).set("id", "123").set("name", "samuel").build());
input.add(StructuredRecord.builder(schema).set("id", "456").set("name", "jackson").build());
File tmpDir = TMP_FOLDER.newFolder();
ETLRealtimeConfig etlConfig = ETLRealtimeConfig.builder().addStage(new ETLStage("source", MockSource.getPlugin(input))).addStage(new ETLStage("sink", MockSink.getPlugin(tmpDir))).addConnection("source", "sink").build();
ApplicationId appId = NamespaceId.DEFAULT.app("simpleApp");
AppRequest<ETLRealtimeConfig> appRequest = new AppRequest<>(APP_ARTIFACT, etlConfig);
ApplicationManager appManager = deployApplication(appId, appRequest);
WorkerManager workerManager = appManager.getWorkerManager(ETLWorker.NAME);
workerManager.start();
workerManager.waitForStatus(true, 10, 1);
try {
List<StructuredRecord> written = MockSink.getRecords(tmpDir, 0, 10, TimeUnit.SECONDS);
Assert.assertEquals(input, written);
} finally {
stopWorker(workerManager);
}
validateMetric(2, appId, "source.records.out");
validateMetric(2, appId, "sink.records.in");
}
use of co.cask.cdap.api.data.schema.Schema in project cdap by caskdata.
the class ETLWorkerTest method testLookup.
@Test
public void testLookup() throws Exception {
addDatasetInstance(KeyValueTable.class.getName(), "lookupTable");
DataSetManager<KeyValueTable> lookupTable = getDataset("lookupTable");
lookupTable.get().write("Bob".getBytes(Charsets.UTF_8), "123".getBytes(Charsets.UTF_8));
lookupTable.flush();
File outDir = TMP_FOLDER.newFolder();
ETLRealtimeConfig etlConfig = ETLRealtimeConfig.builder().addStage(new ETLStage("source", LookupSource.getPlugin(ImmutableSet.of("Bob", "Bill"), "lookupTable"))).addStage(new ETLStage("sink", MockSink.getPlugin(outDir))).addConnection("source", "sink").build();
ApplicationId appId = NamespaceId.DEFAULT.app("lookupTestApp");
AppRequest<ETLRealtimeConfig> appRequest = new AppRequest<>(APP_ARTIFACT, etlConfig);
ApplicationManager appManager = deployApplication(appId, appRequest);
WorkerManager workerManager = appManager.getWorkerManager(ETLWorker.NAME);
workerManager.start();
workerManager.waitForStatus(true, 10, 1);
Schema schema = Schema.recordOf("bobbill", Schema.Field.of("Bob", Schema.nullableOf(Schema.of(Schema.Type.STRING))), Schema.Field.of("Bill", Schema.nullableOf(Schema.of(Schema.Type.STRING))));
List<StructuredRecord> expected = new ArrayList<>();
expected.add(StructuredRecord.builder(schema).set("Bob", "123").build());
try {
List<StructuredRecord> actual = MockSink.getRecords(outDir, 0, 10, TimeUnit.SECONDS);
Assert.assertEquals(expected, actual);
} finally {
stopWorker(workerManager);
}
validateMetric(1, appId, "source.records.out");
validateMetric(1, appId, "sink.records.in");
}
Aggregations