Examples with Schema co.cask.cdap.api.data.schema.Schema used on opensource projects

Example 11 with Schema

use of co.cask.cdap.api.data.schema.Schema in project cdap by caskdata.

the class DataPipelineTest method testPostAction.

@Test
public void testPostAction() throws Exception {
    ETLBatchConfig etlConfig = ETLBatchConfig.builder("* * * * *").addStage(new ETLStage("source", MockSource.getPlugin("actionInput"))).addStage(new ETLStage("sink", MockSink.getPlugin("actionOutput"))).addPostAction(new ETLStage("tokenWriter", NodeStatesAction.getPlugin("tokenTable"))).addConnection("source", "sink").build();
    AppRequest<ETLBatchConfig> appRequest = new AppRequest<>(APP_ARTIFACT, etlConfig);
    ApplicationId appId = NamespaceId.DEFAULT.app("ActionApp");
    ApplicationManager appManager = deployApplication(appId.toId(), appRequest);
    Schema schema = Schema.recordOf("testRecord", Schema.Field.of("name", Schema.of(Schema.Type.STRING)));
    StructuredRecord recordSamuel = StructuredRecord.builder(schema).set("name", "samuel").build();
    StructuredRecord recordBob = StructuredRecord.builder(schema).set("name", "bob").build();
    StructuredRecord recordJane = StructuredRecord.builder(schema).set("name", "jane").build();
    DataSetManager<Table> inputManager = getDataset(NamespaceId.DEFAULT.dataset("actionInput"));
    MockSource.writeInput(inputManager, ImmutableList.of(recordSamuel, recordBob, recordJane));
    WorkflowManager workflowManager = appManager.getWorkflowManager(SmartWorkflow.NAME);
    workflowManager.start();
    workflowManager.waitForRun(ProgramRunStatus.COMPLETED, 5, TimeUnit.MINUTES);
    DataSetManager<Table> tokenTableManager = getDataset(NamespaceId.DEFAULT.dataset("tokenTable"));
    Table tokenTable = tokenTableManager.get();
    NodeStatus status = NodeStatus.valueOf(Bytes.toString(tokenTable.get(Bytes.toBytes("phase-1"), Bytes.toBytes("status"))));
    Assert.assertEquals(NodeStatus.COMPLETED, status);
}

Example 12 with Schema

use of co.cask.cdap.api.data.schema.Schema in project cdap by caskdata.

the class PreviewDataPipelineTest method testDataPipelinePreviewRun.

private void testDataPipelinePreviewRun(Engine engine) throws Exception {
    PreviewManager previewManager = getPreviewManager();
    String sourceTableName = "singleInput";
    String sinkTableName = "singleOutput";
    Schema schema = Schema.recordOf("testRecord", Schema.Field.of("name", Schema.of(Schema.Type.STRING)));
    /*
     * source --> transform -> sink
     */
    ETLBatchConfig etlConfig = ETLBatchConfig.builder("* * * * *").addStage(new ETLStage("source", MockSource.getPlugin(sourceTableName, schema))).addStage(new ETLStage("transform", IdentityTransform.getPlugin())).addStage(new ETLStage("sink", MockSink.getPlugin(sinkTableName))).addConnection("source", "transform").addConnection("transform", "sink").setEngine(engine).setNumOfRecordsPreview(100).build();
    // Construct the preview config with the program name and program type
    PreviewConfig previewConfig = new PreviewConfig(SmartWorkflow.NAME, ProgramType.WORKFLOW, Collections.<String, String>emptyMap(), 10);
    // Create the table for the mock source
    addDatasetInstance(Table.class.getName(), sourceTableName, DatasetProperties.of(ImmutableMap.of("schema", schema.toString())));
    DataSetManager<Table> inputManager = getDataset(NamespaceId.DEFAULT.dataset(sourceTableName));
    StructuredRecord recordSamuel = StructuredRecord.builder(schema).set("name", "samuel").build();
    StructuredRecord recordBob = StructuredRecord.builder(schema).set("name", "bob").build();
    MockSource.writeInput(inputManager, ImmutableList.of(recordSamuel, recordBob));
    AppRequest<ETLBatchConfig> appRequest = new AppRequest<>(APP_ARTIFACT_RANGE, etlConfig, previewConfig);
    // Start the preview and get the corresponding PreviewRunner.
    ApplicationId previewId = previewManager.start(NamespaceId.DEFAULT, appRequest);
    final PreviewRunner previewRunner = previewManager.getRunner(previewId);
    // Wait for the preview status go into COMPLETED.
    Tasks.waitFor(PreviewStatus.Status.COMPLETED, new Callable<PreviewStatus.Status>() {

        @Override
        public PreviewStatus.Status call() throws Exception {
            PreviewStatus status = previewRunner.getStatus();
            return status == null ? null : status.getStatus();
        }
    }, 5, TimeUnit.MINUTES);
    // Get the data for stage "source" in the PreviewStore, should contain two records.
    checkPreviewStore(previewRunner, "source", 2);
    // Get the data for stage "transform" in the PreviewStore, should contain two records.
    checkPreviewStore(previewRunner, "transform", 2);
    // Get the data for stage "sink" in the PreviewStore, should contain two records.
    checkPreviewStore(previewRunner, "sink", 2);
    // Validate the metrics for preview
    validateMetric(2, previewId, "source.records.in", previewRunner);
    validateMetric(2, previewId, "source.records.out", previewRunner);
    validateMetric(2, previewId, "transform.records.in", previewRunner);
    validateMetric(2, previewId, "transform.records.out", previewRunner);
    validateMetric(2, previewId, "sink.records.out", previewRunner);
    validateMetric(2, previewId, "sink.records.in", previewRunner);
    // Check the sink table is not created in the real space.
    DataSetManager<Table> sinkManager = getDataset(sinkTableName);
    Assert.assertNull(sinkManager.get());
    deleteDatasetInstance(NamespaceId.DEFAULT.dataset(sourceTableName));
}

Example 13 with Schema

use of co.cask.cdap.api.data.schema.Schema in project cdap by caskdata.

the class PreviewDataPipelineTest method testPreviewFailedRun.

private void testPreviewFailedRun(Engine engine) throws Exception {
    PreviewManager previewManager = getPreviewManager();
    String sourceTableName = "singleInput";
    String sinkTableName = "singleOutput";
    Schema schema = Schema.recordOf("testRecord", Schema.Field.of("name", Schema.of(Schema.Type.STRING)));
    /*
     * source --> transform -> sink
     */
    ETLBatchConfig etlConfig = ETLBatchConfig.builder("* * * * *").addStage(new ETLStage("source", MockSource.getPlugin(sourceTableName, schema))).addStage(new ETLStage("transform", ExceptionTransform.getPlugin("name", "samuel"))).addStage(new ETLStage("sink", MockSink.getPlugin(sinkTableName))).addConnection("source", "transform").addConnection("transform", "sink").setNumOfRecordsPreview(100).setEngine(engine).build();
    // Construct the preview config with the program name and program type.
    PreviewConfig previewConfig = new PreviewConfig(SmartWorkflow.NAME, ProgramType.WORKFLOW, Collections.<String, String>emptyMap(), 10);
    // Create the table for the mock source
    addDatasetInstance(Table.class.getName(), sourceTableName, DatasetProperties.of(ImmutableMap.of("schema", schema.toString())));
    DataSetManager<Table> inputManager = getDataset(NamespaceId.DEFAULT.dataset(sourceTableName));
    StructuredRecord recordSamuel = StructuredRecord.builder(schema).set("name", "samuel").build();
    StructuredRecord recordBob = StructuredRecord.builder(schema).set("name", "bob").build();
    MockSource.writeInput(inputManager, "1", recordSamuel);
    MockSource.writeInput(inputManager, "2", recordBob);
    AppRequest<ETLBatchConfig> appRequest = new AppRequest<>(APP_ARTIFACT, etlConfig, previewConfig);
    // Start the preview and get the corresponding PreviewRunner.
    ApplicationId previewId = previewManager.start(NamespaceId.DEFAULT, appRequest);
    final PreviewRunner previewRunner = previewManager.getRunner(previewId);
    // Wait for the preview status go into FAILED.
    Tasks.waitFor(PreviewStatus.Status.RUN_FAILED, new Callable<PreviewStatus.Status>() {

        @Override
        public PreviewStatus.Status call() throws Exception {
            PreviewStatus status = previewRunner.getStatus();
            return status == null ? null : status.getStatus();
        }
    }, 5, TimeUnit.MINUTES);
    // Get the data for stage "source" in the PreviewStore.
    checkPreviewStore(previewRunner, "source", 2);
    // Get the data for stage "transform" in the PreviewStore, should contain one less record than source.
    checkPreviewStore(previewRunner, "transform", 1);
    // Get the data for stage "sink" in the PreviewStore, should contain one less record than source.
    checkPreviewStore(previewRunner, "sink", 1);
    // Validate the metrics for preview
    validateMetric(2, previewId, "source.records.in", previewRunner);
    validateMetric(2, previewId, "source.records.out", previewRunner);
    validateMetric(2, previewId, "transform.records.in", previewRunner);
    validateMetric(1, previewId, "transform.records.out", previewRunner);
    validateMetric(1, previewId, "sink.records.out", previewRunner);
    validateMetric(1, previewId, "sink.records.in", previewRunner);
    // Check the sink table is not created in the real space.
    DataSetManager<Table> sinkManager = getDataset(sinkTableName);
    Assert.assertNull(sinkManager.get());
    deleteDatasetInstance(NamespaceId.DEFAULT.dataset(sourceTableName));
}

Example 14 with Schema

use of co.cask.cdap.api.data.schema.Schema in project cdap by caskdata.

the class DataStreamsSparkSinkTest method testSparkSink.

@Test
public // stream-rate-updater thread in Spark.
void testSparkSink() 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<>();
    StructuredRecord samuelRecord = StructuredRecord.builder(schema).set("id", "0").set("name", "samuel").build();
    StructuredRecord jacksonRecord = StructuredRecord.builder(schema).set("id", "1").set("name", "jackson").build();
    StructuredRecord dwayneRecord = StructuredRecord.builder(schema).set("id", "2").set("name", "dwayne").build();
    StructuredRecord johnsonRecord = StructuredRecord.builder(schema).set("id", "3").set("name", "johnson").build();
    input.add(samuelRecord);
    input.add(jacksonRecord);
    input.add(dwayneRecord);
    input.add(johnsonRecord);
    DataStreamsConfig etlConfig = DataStreamsConfig.builder().addStage(new ETLStage("source", MockSource.getPlugin(schema, input))).addStage(new ETLStage("sink", co.cask.cdap.etl.mock.spark.streaming.MockSink.getPlugin("${tablename}"))).addConnection("source", "sink").setBatchInterval("1s").build();
    ApplicationId appId = NamespaceId.DEFAULT.app("sparksinkapp");
    AppRequest<DataStreamsConfig> appRequest = new AppRequest<>(APP_ARTIFACT, etlConfig);
    ApplicationManager appManager = deployApplication(appId.toId(), appRequest);
    testSparkSink(appManager, "output1");
    testSparkSink(appManager, "output2");
}

Example 15 with Schema

use of co.cask.cdap.api.data.schema.Schema in project cdap by caskdata.

the class DataStreamsTest method testTransformComputeWithMacros.

@Test
public void testTransformComputeWithMacros() 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<>();
    StructuredRecord samuelRecord = StructuredRecord.builder(schema).set("id", "123").set("name", "samuel").build();
    StructuredRecord jacksonRecord = StructuredRecord.builder(schema).set("id", "456").set("name", "jackson").build();
    StructuredRecord dwayneRecord = StructuredRecord.builder(schema).set("id", "789").set("name", "dwayne").build();
    StructuredRecord johnsonRecord = StructuredRecord.builder(schema).set("id", "0").set("name", "johnson").build();
    input.add(samuelRecord);
    input.add(jacksonRecord);
    input.add(dwayneRecord);
    input.add(johnsonRecord);
    DataStreamsConfig etlConfig = DataStreamsConfig.builder().addStage(new ETLStage("source", MockSource.getPlugin(schema, input))).addStage(new ETLStage("sink", MockSink.getPlugin("${output}"))).addStage(new ETLStage("filter1", StringValueFilterTransform.getPlugin("${field}", "${val1}"))).addStage(new ETLStage("filter2", StringValueFilterCompute.getPlugin("${field}", "${val2}"))).addStage(new ETLStage("sleep", SleepTransform.getPlugin(2L))).addConnection("source", "sleep").addConnection("sleep", "filter1").addConnection("filter1", "filter2").addConnection("filter2", "sink").setBatchInterval("1s").build();
    ApplicationId appId = NamespaceId.DEFAULT.app("simpleApp");
    AppRequest<DataStreamsConfig> appRequest = new AppRequest<>(APP_ARTIFACT, etlConfig);
    ApplicationManager appManager = deployApplication(appId.toId(), appRequest);
    final Set<StructuredRecord> expected = new HashSet<>();
    expected.add(samuelRecord);
    expected.add(jacksonRecord);
    testTransformComputeRun(appManager, expected, "dwayne", "johnson", "macroOutput1");
    validateMetric(appId, "source.records.out", 4);
    validateMetric(appId, "sleep.records.in", 4);
    validateMetric(appId, "sleep.records.out", 4);
    validateMetric(appId, "filter1.records.in", 4);
    validateMetric(appId, "filter1.records.out", 3);
    validateMetric(appId, "filter2.records.in", 3);
    validateMetric(appId, "filter2.records.out", 2);
    validateMetric(appId, "sink.records.in", 2);
    Assert.assertTrue(getMetric(appId, "sleep." + co.cask.cdap.etl.common.Constants.Metrics.TOTAL_TIME) > 0L);
    expected.clear();
    expected.add(dwayneRecord);
    expected.add(johnsonRecord);
    testTransformComputeRun(appManager, expected, "samuel", "jackson", "macroOutput2");
}