use of io.cdap.cdap.etl.api.engine.sql.SQLEngine in project cdap by caskdata.
the class BatchSparkPipelineDriver method run.
@Override
public void run(DatasetContext context) throws Exception {
BatchPhaseSpec phaseSpec = GSON.fromJson(sec.getSpecification().getProperty(Constants.PIPELINEID), BatchPhaseSpec.class);
Path configFile = sec.getLocalizationContext().getLocalFile("HydratorSpark.config").toPath();
try (BufferedReader reader = Files.newBufferedReader(configFile, StandardCharsets.UTF_8)) {
String object = reader.readLine();
SparkBatchSourceSinkFactoryInfo sourceSinkInfo = GSON.fromJson(object, SparkBatchSourceSinkFactoryInfo.class);
sourceFactory = sourceSinkInfo.getSparkBatchSourceFactory();
sinkFactory = sourceSinkInfo.getSparkBatchSinkFactory();
stagePartitions = sourceSinkInfo.getStagePartitions();
}
datasetContext = context;
PipelinePluginContext pluginContext = new PipelinePluginContext(sec.getPluginContext(), sec.getMetrics(), phaseSpec.isStageLoggingEnabled(), phaseSpec.isProcessTimingEnabled());
Map<String, StageStatisticsCollector> collectors = new HashMap<>();
if (phaseSpec.pipelineContainsCondition()) {
Iterator<StageSpec> iterator = phaseSpec.getPhase().iterator();
while (iterator.hasNext()) {
StageSpec spec = iterator.next();
collectors.put(spec.getName(), new SparkStageStatisticsCollector(jsc));
}
}
boolean isSuccessful = true;
try {
PipelinePluginInstantiator pluginInstantiator = new PipelinePluginInstantiator(pluginContext, sec.getMetrics(), phaseSpec, new SingleConnectorFactory());
boolean shouldConsolidateStages = Boolean.parseBoolean(sec.getRuntimeArguments().getOrDefault(Constants.CONSOLIDATE_STAGES, Boolean.TRUE.toString()));
boolean shouldCacheFunctions = Boolean.parseBoolean(sec.getRuntimeArguments().getOrDefault(Constants.CACHE_FUNCTIONS, Boolean.TRUE.toString()));
boolean isPreviewEnabled = phaseSpec.getPhase().size() == 0 || sec.getDataTracer(phaseSpec.getPhase().iterator().next().getName()).isEnabled();
// Initialize SQL engine instance if needed.
if (!isPreviewEnabled && phaseSpec.getSQLEngineStageSpec() != null) {
String sqlEngineStage = SQLEngineUtils.buildStageName(phaseSpec.getSQLEngineStageSpec().getPlugin().getName());
// Instantiate SQL engine and prepare run.
try {
MacroEvaluator macroEvaluator = new DefaultMacroEvaluator(new BasicArguments(sec), sec.getLogicalStartTime(), sec.getSecureStore(), sec.getServiceDiscoverer(), sec.getNamespace());
Object instance = pluginInstantiator.newPluginInstance(sqlEngineStage, macroEvaluator);
sqlEngineAdapter = new BatchSQLEngineAdapter((SQLEngine<?, ?, ?, ?>) instance, sec, jsc, collectors);
sqlEngineAdapter.prepareRun();
} catch (InstantiationException ie) {
LOG.error("Could not create plugin instance for SQLEngine class", ie);
} finally {
if (sqlEngineAdapter == null) {
LOG.warn("Could not instantiate SQLEngine instance for Transformation Pushdown");
}
}
}
runPipeline(phaseSpec, BatchSource.PLUGIN_TYPE, sec, stagePartitions, pluginInstantiator, collectors, sinkFactory.getUncombinableSinks(), shouldConsolidateStages, shouldCacheFunctions);
} catch (Throwable t) {
// Mark this execution as not successful.
isSuccessful = false;
// Rethrow
throw t;
} finally {
updateWorkflowToken(sec.getWorkflowToken(), collectors);
// Close SQL Engine Adapter if neeeded,
if (sqlEngineAdapter != null) {
sqlEngineAdapter.onRunFinish(isSuccessful);
sqlEngineAdapter.close();
}
}
}
Aggregations