org.apache.flink.api.common.io.RichInputFormat Java Examples

private void cleanUp() throws Exception {
	LOG.debug("cleanup, state={}", state);

	RunnableWithException[] runClose = {
			() -> sourceContext.close(),
			() -> output.close(),
			() -> format.close(),
			() -> {
				if (this.format instanceof RichInputFormat) {
					((RichInputFormat) this.format).closeInputFormat();
				}
			}};
	Exception firstException = null;

	for (RunnableWithException r : runClose) {
		try {
			r.run();
		} catch (Exception e) {
			firstException = ExceptionUtils.firstOrSuppressed(e, firstException);
		}
	}
	currentSplit = null;
	if (firstException != null) {
		throw firstException;
	}
}
 

private void loadSplit(T split) throws IOException {
	Preconditions.checkState(state != ReaderState.READING && state != ReaderState.CLOSED, "can't load split in state %s", state);
	Preconditions.checkNotNull(split, "split is null");
	LOG.debug("load split: {}", split);
	currentSplit = split;
	if (this.format instanceof RichInputFormat) {
		((RichInputFormat) this.format).openInputFormat();
	}
	if (format instanceof CheckpointableInputFormat && currentSplit.getSplitState() != null) {
		// recovering after a node failure with an input
		// format that supports resetting the offset
		((CheckpointableInputFormat<T, Serializable>) format).
				reopen(currentSplit, currentSplit.getSplitState());
	} else {
		// we either have a new split, or we recovered from a node
		// failure but the input format does not support resetting the offset.
		format.open(currentSplit);
	}

	// reset the restored state to null for the next iteration
	currentSplit.resetSplitState();
}
 

private <OUT> List<OUT> executeDataSource(GenericDataSourceBase<?, ?> source, int superStep)
		throws Exception {
	@SuppressWarnings("unchecked")
	GenericDataSourceBase<OUT, ?> typedSource = (GenericDataSourceBase<OUT, ?>) source;
	// build the runtime context and compute broadcast variables, if necessary
	TaskInfo taskInfo = new TaskInfo(typedSource.getName(), 1, 0, 1, 0);
	
	RuntimeUDFContext ctx;

	MetricGroup metrics = new UnregisteredMetricsGroup();
	if (RichInputFormat.class.isAssignableFrom(typedSource.getUserCodeWrapper().getUserCodeClass())) {
		ctx = superStep == 0 ? new RuntimeUDFContext(taskInfo, userCodeClassLoader, executionConfig, cachedFiles, accumulators, metrics) :
				new IterationRuntimeUDFContext(taskInfo, userCodeClassLoader, executionConfig, cachedFiles, accumulators, metrics);
	} else {
		ctx = null;
	}
	return typedSource.executeOnCollections(ctx, executionConfig);
}
 

private <OUT> List<OUT> executeDataSource(GenericDataSourceBase<?, ?> source, int superStep)
		throws Exception {
	@SuppressWarnings("unchecked")
	GenericDataSourceBase<OUT, ?> typedSource = (GenericDataSourceBase<OUT, ?>) source;
	// build the runtime context and compute broadcast variables, if necessary
	TaskInfo taskInfo = new TaskInfo(typedSource.getName(), 1, 0, 1, 0);
	
	RuntimeUDFContext ctx;

	MetricGroup metrics = new UnregisteredMetricsGroup();
	if (RichInputFormat.class.isAssignableFrom(typedSource.getUserCodeWrapper().getUserCodeClass())) {
		ctx = superStep == 0 ? new RuntimeUDFContext(taskInfo, userCodeClassLoader, executionConfig, cachedFiles, accumulators, metrics) :
				new IterationRuntimeUDFContext(taskInfo, userCodeClassLoader, executionConfig, cachedFiles, accumulators, metrics);
	} else {
		ctx = null;
	}
	return typedSource.executeOnCollections(ctx, executionConfig);
}
 

private <OUT> List<OUT> executeDataSource(GenericDataSourceBase<?, ?> source, int superStep)
		throws Exception {
	@SuppressWarnings("unchecked")
	GenericDataSourceBase<OUT, ?> typedSource = (GenericDataSourceBase<OUT, ?>) source;
	// build the runtime context and compute broadcast variables, if necessary
	TaskInfo taskInfo = new TaskInfo(typedSource.getName(), 1, 0, 1, 0);
	
	RuntimeUDFContext ctx;

	MetricGroup metrics = new UnregisteredMetricsGroup();
	if (RichInputFormat.class.isAssignableFrom(typedSource.getUserCodeWrapper().getUserCodeClass())) {
		ctx = superStep == 0 ? new RuntimeUDFContext(taskInfo, userCodeClassLoader, executionConfig, cachedFiles, accumulators, metrics) :
				new IterationRuntimeUDFContext(taskInfo, userCodeClassLoader, executionConfig, cachedFiles, accumulators, metrics);
	} else {
		ctx = null;
	}
	return typedSource.executeOnCollections(ctx, executionConfig);
}
 

@Override
public void close() throws Exception {
	format.close();
	if (format instanceof RichInputFormat) {
		((RichInputFormat) format).closeInputFormat();
	}
}
 

@Override
public void open() throws Exception {
	super.open();

	checkState(this.serializer != null, "The serializer has not been set. " +
		"Probably the setOutputType() was not called. Please report it.");

	this.state = ReaderState.IDLE;
	if (this.format instanceof RichInputFormat) {
		((RichInputFormat) this.format).setRuntimeContext(getRuntimeContext());
	}
	this.format.configure(new Configuration());

	this.sourceContext = StreamSourceContexts.getSourceContext(
		getOperatorConfig().getTimeCharacteristic(),
		getProcessingTimeService(),
		new Object(), // no actual locking needed
		getContainingTask().getStreamStatusMaintainer(),
		output,
		getRuntimeContext().getExecutionConfig().getAutoWatermarkInterval(),
		-1);

	this.reusedRecord = serializer.createInstance();
	this.completedSplitsCounter = getMetricGroup().counter("numSplitsProcessed");
	this.splits = this.splits == null ? new PriorityQueue<>() : this.splits;

	if (!splits.isEmpty()) {
		enqueueProcessRecord();
	}
}
 

@Override
public void close() throws Exception {
	format.close();
	if (format instanceof RichInputFormat) {
		((RichInputFormat) format).closeInputFormat();
	}
}
 

@Override
public void run(SourceContext<OUT> ctx) throws Exception {
	try {

		Counter completedSplitsCounter = getRuntimeContext().getMetricGroup().counter("numSplitsProcessed");
		if (isRunning && format instanceof RichInputFormat) {
			((RichInputFormat) format).openInputFormat();
		}

		OUT nextElement = serializer.createInstance();
		while (isRunning) {
			format.open(splitIterator.next());

			// for each element we also check if cancel
			// was called by checking the isRunning flag

			while (isRunning && !format.reachedEnd()) {
				nextElement = format.nextRecord(nextElement);
				if (nextElement != null) {
					ctx.collect(nextElement);
				} else {
					break;
				}
			}
			format.close();
			completedSplitsCounter.inc();

			if (isRunning) {
				isRunning = splitIterator.hasNext();
			}
		}
	} finally {
		format.close();
		if (format instanceof RichInputFormat) {
			((RichInputFormat) format).closeInputFormat();
		}
		isRunning = false;
	}
}
 

@Override
@SuppressWarnings("unchecked")
public void open(Configuration parameters) throws Exception {
	StreamingRuntimeContext context = (StreamingRuntimeContext) getRuntimeContext();

	if (format instanceof RichInputFormat) {
		((RichInputFormat) format).setRuntimeContext(context);
	}
	format.configure(parameters);

	provider = context.getInputSplitProvider();
	serializer = typeInfo.createSerializer(getRuntimeContext().getExecutionConfig());
	splitIterator = getInputSplits();
	isRunning = splitIterator.hasNext();
}
 

protected List<OUT> executeOnCollections(RuntimeContext ctx, ExecutionConfig executionConfig) throws Exception {
	@SuppressWarnings("unchecked")
	InputFormat<OUT, InputSplit> inputFormat = (InputFormat<OUT, InputSplit>) this.formatWrapper.getUserCodeObject();
	//configure the input format
	inputFormat.configure(this.parameters);

	//open the input format
	if (inputFormat instanceof RichInputFormat) {
		((RichInputFormat) inputFormat).setRuntimeContext(ctx);
		((RichInputFormat) inputFormat).openInputFormat();
	}

	List<OUT> result = new ArrayList<OUT>();
	
	// splits
	InputSplit[] splits = inputFormat.createInputSplits(1);
	TypeSerializer<OUT> serializer = getOperatorInfo().getOutputType().createSerializer(executionConfig);
	
	for (InputSplit split : splits) {
		inputFormat.open(split);
		
		while (!inputFormat.reachedEnd()) {
			OUT next = inputFormat.nextRecord(serializer.createInstance());
			if (next != null) {
				result.add(serializer.copy(next));
			}
		}
		
		inputFormat.close();
	}
	
	//close the input format
	if (inputFormat instanceof RichInputFormat) {
		((RichInputFormat) inputFormat).closeInputFormat();
	}

	return result;
}
 

@Override
public void run(SourceContext<OUT> ctx) throws Exception {
	try {

		Counter completedSplitsCounter = getRuntimeContext().getMetricGroup().counter("numSplitsProcessed");
		if (isRunning && format instanceof RichInputFormat) {
			((RichInputFormat) format).openInputFormat();
		}

		OUT nextElement = serializer.createInstance();
		while (isRunning) {
			format.open(splitIterator.next());

			// for each element we also check if cancel
			// was called by checking the isRunning flag

			while (isRunning && !format.reachedEnd()) {
				nextElement = format.nextRecord(nextElement);
				if (nextElement != null) {
					ctx.collect(nextElement);
				} else {
					break;
				}
			}
			format.close();
			completedSplitsCounter.inc();

			if (isRunning) {
				isRunning = splitIterator.hasNext();
			}
		}
	} finally {
		format.close();
		if (format instanceof RichInputFormat) {
			((RichInputFormat) format).closeInputFormat();
		}
		isRunning = false;
	}
}
 

@Override
@SuppressWarnings("unchecked")
public void open(Configuration parameters) throws Exception {
	StreamingRuntimeContext context = (StreamingRuntimeContext) getRuntimeContext();

	if (format instanceof RichInputFormat) {
		((RichInputFormat) format).setRuntimeContext(context);
	}
	format.configure(parameters);

	provider = context.getInputSplitProvider();
	serializer = typeInfo.createSerializer(getRuntimeContext().getExecutionConfig());
	splitIterator = getInputSplits();
	isRunning = splitIterator.hasNext();
}
 

protected List<OUT> executeOnCollections(RuntimeContext ctx, ExecutionConfig executionConfig) throws Exception {
	@SuppressWarnings("unchecked")
	InputFormat<OUT, InputSplit> inputFormat = (InputFormat<OUT, InputSplit>) this.formatWrapper.getUserCodeObject();
	//configure the input format
	inputFormat.configure(this.parameters);

	//open the input format
	if (inputFormat instanceof RichInputFormat) {
		((RichInputFormat) inputFormat).setRuntimeContext(ctx);
		((RichInputFormat) inputFormat).openInputFormat();
	}

	List<OUT> result = new ArrayList<OUT>();
	
	// splits
	InputSplit[] splits = inputFormat.createInputSplits(1);
	TypeSerializer<OUT> serializer = getOperatorInfo().getOutputType().createSerializer(executionConfig);
	
	for (InputSplit split : splits) {
		inputFormat.open(split);
		
		while (!inputFormat.reachedEnd()) {
			OUT next = inputFormat.nextRecord(serializer.createInstance());
			if (next != null) {
				result.add(serializer.copy(next));
			}
		}
		
		inputFormat.close();
	}
	
	//close the input format
	if (inputFormat instanceof RichInputFormat) {
		((RichInputFormat) inputFormat).closeInputFormat();
	}

	return result;
}
 

@Override
public void close() throws Exception {
	format.close();
	if (format instanceof RichInputFormat) {
		((RichInputFormat) format).closeInputFormat();
	}
}
 

@Override
public void run(SourceContext<OUT> ctx) throws Exception {
	try {

		Counter completedSplitsCounter = getRuntimeContext().getMetricGroup().counter("numSplitsProcessed");
		if (isRunning && format instanceof RichInputFormat) {
			((RichInputFormat) format).openInputFormat();
		}

		OUT nextElement = serializer.createInstance();
		while (isRunning) {
			format.open(splitIterator.next());

			// for each element we also check if cancel
			// was called by checking the isRunning flag

			while (isRunning && !format.reachedEnd()) {
				nextElement = format.nextRecord(nextElement);
				if (nextElement != null) {
					ctx.collect(nextElement);
				} else {
					break;
				}
			}
			format.close();
			completedSplitsCounter.inc();

			if (isRunning) {
				isRunning = splitIterator.hasNext();
			}
		}
	} finally {
		format.close();
		if (format instanceof RichInputFormat) {
			((RichInputFormat) format).closeInputFormat();
		}
		isRunning = false;
	}
}
 

@Override
@SuppressWarnings("unchecked")
public void open(Configuration parameters) throws Exception {
	StreamingRuntimeContext context = (StreamingRuntimeContext) getRuntimeContext();

	if (format instanceof RichInputFormat) {
		((RichInputFormat) format).setRuntimeContext(context);
	}
	format.configure(parameters);

	provider = context.getInputSplitProvider();
	serializer = typeInfo.createSerializer(getRuntimeContext().getExecutionConfig());
	splitIterator = getInputSplits();
	isRunning = splitIterator.hasNext();
}
 

protected List<OUT> executeOnCollections(RuntimeContext ctx, ExecutionConfig executionConfig) throws Exception {
	@SuppressWarnings("unchecked")
	InputFormat<OUT, InputSplit> inputFormat = (InputFormat<OUT, InputSplit>) this.formatWrapper.getUserCodeObject();
	//configure the input format
	inputFormat.configure(this.parameters);

	//open the input format
	if (inputFormat instanceof RichInputFormat) {
		((RichInputFormat) inputFormat).setRuntimeContext(ctx);
		((RichInputFormat) inputFormat).openInputFormat();
	}

	List<OUT> result = new ArrayList<OUT>();
	
	// splits
	InputSplit[] splits = inputFormat.createInputSplits(1);
	TypeSerializer<OUT> serializer = getOperatorInfo().getOutputType().createSerializer(executionConfig);
	
	for (InputSplit split : splits) {
		inputFormat.open(split);
		
		while (!inputFormat.reachedEnd()) {
			OUT next = inputFormat.nextRecord(serializer.createInstance());
			if (next != null) {
				result.add(serializer.copy(next));
			}
		}
		
		inputFormat.close();
	}
	
	//close the input format
	if (inputFormat instanceof RichInputFormat) {
		((RichInputFormat) inputFormat).closeInputFormat();
	}

	return result;
}