use of org.apache.flink.storm.wrappers.SpoutWrapper in project flink by apache.
the class FlinkTopology method translateTopology.
/**
* Creates a Flink program that uses the specified spouts and bolts.
*/
private void translateTopology() {
unprocessdInputsPerBolt.clear();
outputStreams.clear();
declarers.clear();
availableInputs.clear();
// Storm defaults to parallelism 1
env.setParallelism(1);
for (final Entry<String, IRichSpout> spout : spouts.entrySet()) {
final String spoutId = spout.getKey();
final IRichSpout userSpout = spout.getValue();
final FlinkOutputFieldsDeclarer declarer = new FlinkOutputFieldsDeclarer();
userSpout.declareOutputFields(declarer);
final HashMap<String, Fields> sourceStreams = declarer.outputStreams;
this.outputStreams.put(spoutId, sourceStreams);
declarers.put(spoutId, declarer);
final HashMap<String, DataStream<Tuple>> outputStreams = new HashMap<String, DataStream<Tuple>>();
final DataStreamSource<?> source;
if (sourceStreams.size() == 1) {
final SpoutWrapper<Tuple> spoutWrapperSingleOutput = new SpoutWrapper<Tuple>(userSpout, spoutId, null, null);
spoutWrapperSingleOutput.setStormTopology(stormTopology);
final String outputStreamId = (String) sourceStreams.keySet().toArray()[0];
DataStreamSource<Tuple> src = env.addSource(spoutWrapperSingleOutput, spoutId, declarer.getOutputType(outputStreamId));
outputStreams.put(outputStreamId, src);
source = src;
} else {
final SpoutWrapper<SplitStreamType<Tuple>> spoutWrapperMultipleOutputs = new SpoutWrapper<SplitStreamType<Tuple>>(userSpout, spoutId, null, null);
spoutWrapperMultipleOutputs.setStormTopology(stormTopology);
@SuppressWarnings({ "unchecked", "rawtypes" }) DataStreamSource<SplitStreamType<Tuple>> multiSource = env.addSource(spoutWrapperMultipleOutputs, spoutId, (TypeInformation) TypeExtractor.getForClass(SplitStreamType.class));
SplitStream<SplitStreamType<Tuple>> splitSource = multiSource.split(new StormStreamSelector<Tuple>());
for (String streamId : sourceStreams.keySet()) {
SingleOutputStreamOperator<Tuple> outStream = splitSource.select(streamId).map(new SplitStreamMapper<Tuple>());
outStream.getTransformation().setOutputType(declarer.getOutputType(streamId));
outputStreams.put(streamId, outStream);
}
source = multiSource;
}
availableInputs.put(spoutId, outputStreams);
final ComponentCommon common = stormTopology.get_spouts().get(spoutId).get_common();
if (common.is_set_parallelism_hint()) {
int dop = common.get_parallelism_hint();
source.setParallelism(dop);
} else {
common.set_parallelism_hint(1);
}
}
/**
* 1. Connect all spout streams with bolts streams
* 2. Then proceed with the bolts stream already connected
*
* Because we do not know the order in which an iterator steps over a set, we might process a consumer before
* its producer
* ->thus, we might need to repeat multiple times
*/
boolean makeProgress = true;
while (bolts.size() > 0) {
if (!makeProgress) {
StringBuilder strBld = new StringBuilder();
strBld.append("Unable to build Topology. Could not connect the following bolts:");
for (String boltId : bolts.keySet()) {
strBld.append("\n ");
strBld.append(boltId);
strBld.append(": missing input streams [");
for (Entry<GlobalStreamId, Grouping> streams : unprocessdInputsPerBolt.get(boltId)) {
strBld.append("'");
strBld.append(streams.getKey().get_streamId());
strBld.append("' from '");
strBld.append(streams.getKey().get_componentId());
strBld.append("'; ");
}
strBld.append("]");
}
throw new RuntimeException(strBld.toString());
}
makeProgress = false;
final Iterator<Entry<String, IRichBolt>> boltsIterator = bolts.entrySet().iterator();
while (boltsIterator.hasNext()) {
final Entry<String, IRichBolt> bolt = boltsIterator.next();
final String boltId = bolt.getKey();
final IRichBolt userBolt = copyObject(bolt.getValue());
final ComponentCommon common = stormTopology.get_bolts().get(boltId).get_common();
Set<Entry<GlobalStreamId, Grouping>> unprocessedBoltInputs = unprocessdInputsPerBolt.get(boltId);
if (unprocessedBoltInputs == null) {
unprocessedBoltInputs = new HashSet<>();
unprocessedBoltInputs.addAll(common.get_inputs().entrySet());
unprocessdInputsPerBolt.put(boltId, unprocessedBoltInputs);
}
// check if all inputs are available
final int numberOfInputs = unprocessedBoltInputs.size();
int inputsAvailable = 0;
for (Entry<GlobalStreamId, Grouping> entry : unprocessedBoltInputs) {
final String producerId = entry.getKey().get_componentId();
final String streamId = entry.getKey().get_streamId();
final HashMap<String, DataStream<Tuple>> streams = availableInputs.get(producerId);
if (streams != null && streams.get(streamId) != null) {
inputsAvailable++;
}
}
if (inputsAvailable != numberOfInputs) {
// traverse other bolts first until inputs are available
continue;
} else {
makeProgress = true;
boltsIterator.remove();
}
final Map<GlobalStreamId, DataStream<Tuple>> inputStreams = new HashMap<>(numberOfInputs);
for (Entry<GlobalStreamId, Grouping> input : unprocessedBoltInputs) {
final GlobalStreamId streamId = input.getKey();
final Grouping grouping = input.getValue();
final String producerId = streamId.get_componentId();
final Map<String, DataStream<Tuple>> producer = availableInputs.get(producerId);
inputStreams.put(streamId, processInput(boltId, userBolt, streamId, grouping, producer));
}
final SingleOutputStreamOperator<?> outputStream = createOutput(boltId, userBolt, inputStreams);
if (common.is_set_parallelism_hint()) {
int dop = common.get_parallelism_hint();
outputStream.setParallelism(dop);
} else {
common.set_parallelism_hint(1);
}
}
}
}
use of org.apache.flink.storm.wrappers.SpoutWrapper in project flink by apache.
the class SpoutSourceWordCount method getTextDataStream.
private static DataStream<String> getTextDataStream(final StreamExecutionEnvironment env) {
if (fileOutput) {
// read the text file from given input path
final String[] tokens = textPath.split(":");
final String localFile = tokens[tokens.length - 1];
return env.addSource(new SpoutWrapper<String>(new WordCountFileSpout(localFile), new String[] { Utils.DEFAULT_STREAM_ID }, -1), TypeExtractor.getForClass(String.class)).setParallelism(1);
}
return env.addSource(new SpoutWrapper<String>(new WordCountInMemorySpout(), new String[] { Utils.DEFAULT_STREAM_ID }, -1), TypeExtractor.getForClass(String.class)).setParallelism(1);
}
use of org.apache.flink.storm.wrappers.SpoutWrapper in project flink by apache.
the class ExclamationWithSpout method getTextDataStream.
private static DataStream<String> getTextDataStream(final StreamExecutionEnvironment env) {
if (fileOutput) {
final String[] tokens = textPath.split(":");
final String inputFile = tokens[tokens.length - 1];
// set Storm configuration
StormConfig config = new StormConfig();
config.put(FiniteFileSpout.INPUT_FILE_PATH, inputFile);
env.getConfig().setGlobalJobParameters(config);
return env.addSource(new SpoutWrapper<String>(new FiniteFileSpout(), new String[] { Utils.DEFAULT_STREAM_ID }), TypeExtractor.getForClass(String.class)).setParallelism(1);
}
return env.addSource(new SpoutWrapper<String>(new FiniteInMemorySpout(WordCountData.WORDS), new String[] { Utils.DEFAULT_STREAM_ID }), TypeExtractor.getForClass(String.class)).setParallelism(1);
}
Aggregations