use of org.apache.kafka.streams.kstream.KStream in project apache-kafka-on-k8s by banzaicloud.
the class KStreamImplTest method testNumProcesses.
@Test
public void testNumProcesses() {
final StreamsBuilder builder = new StreamsBuilder();
KStream<String, String> source1 = builder.stream(Arrays.asList("topic-1", "topic-2"), consumed);
KStream<String, String> source2 = builder.stream(Arrays.asList("topic-3", "topic-4"), consumed);
KStream<String, String> stream1 = source1.filter(new Predicate<String, String>() {
@Override
public boolean test(String key, String value) {
return true;
}
}).filterNot(new Predicate<String, String>() {
@Override
public boolean test(String key, String value) {
return false;
}
});
KStream<String, Integer> stream2 = stream1.mapValues(new ValueMapper<String, Integer>() {
@Override
public Integer apply(String value) {
return new Integer(value);
}
});
KStream<String, Integer> stream3 = source2.flatMapValues(new ValueMapper<String, Iterable<Integer>>() {
@Override
public Iterable<Integer> apply(String value) {
return Collections.singletonList(new Integer(value));
}
});
KStream<String, Integer>[] streams2 = stream2.branch(new Predicate<String, Integer>() {
@Override
public boolean test(String key, Integer value) {
return (value % 2) == 0;
}
}, new Predicate<String, Integer>() {
@Override
public boolean test(String key, Integer value) {
return true;
}
});
KStream<String, Integer>[] streams3 = stream3.branch(new Predicate<String, Integer>() {
@Override
public boolean test(String key, Integer value) {
return (value % 2) == 0;
}
}, new Predicate<String, Integer>() {
@Override
public boolean test(String key, Integer value) {
return true;
}
});
final int anyWindowSize = 1;
final Joined<String, Integer, Integer> joined = Joined.with(stringSerde, intSerde, intSerde);
KStream<String, Integer> stream4 = streams2[0].join(streams3[0], new ValueJoiner<Integer, Integer, Integer>() {
@Override
public Integer apply(Integer value1, Integer value2) {
return value1 + value2;
}
}, JoinWindows.of(anyWindowSize), joined);
streams2[1].join(streams3[1], new ValueJoiner<Integer, Integer, Integer>() {
@Override
public Integer apply(Integer value1, Integer value2) {
return value1 + value2;
}
}, JoinWindows.of(anyWindowSize), joined);
stream4.to("topic-5");
streams2[1].through("topic-6").process(new MockProcessorSupplier<String, Integer>());
assertEquals(// sources
2 + // stream1
2 + // stream2
1 + // stream3
1 + 1 + // streams2
2 + 1 + // streams3
2 + // stream2-stream3 joins
5 * 2 + // to
1 + // through
2 + // process
1, StreamsBuilderTest.internalTopologyBuilder(builder).setApplicationId("X").build(null).processors().size());
}
use of org.apache.kafka.streams.kstream.KStream in project kafka-streams-examples by confluentinc.
the class PageViewRegionLambdaExample method main.
public static void main(final String[] args) throws Exception {
final String bootstrapServers = args.length > 0 ? args[0] : "localhost:9092";
final String schemaRegistryUrl = args.length > 1 ? args[1] : "http://localhost:8081";
final Properties streamsConfiguration = new Properties();
// Give the Streams application a unique name. The name must be unique in the Kafka cluster
// against which the application is run.
streamsConfiguration.put(StreamsConfig.APPLICATION_ID_CONFIG, "pageview-region-lambda-example");
streamsConfiguration.put(StreamsConfig.CLIENT_ID_CONFIG, "pageview-region-lambda-example-client");
// Where to find Kafka broker(s).
streamsConfiguration.put(StreamsConfig.BOOTSTRAP_SERVERS_CONFIG, bootstrapServers);
// Where to find the Confluent schema registry instance(s)
streamsConfiguration.put(AbstractKafkaAvroSerDeConfig.SCHEMA_REGISTRY_URL_CONFIG, schemaRegistryUrl);
// Specify default (de)serializers for record keys and for record values.
streamsConfiguration.put(StreamsConfig.DEFAULT_KEY_SERDE_CLASS_CONFIG, Serdes.String().getClass().getName());
streamsConfiguration.put(StreamsConfig.DEFAULT_VALUE_SERDE_CLASS_CONFIG, GenericAvroSerde.class);
streamsConfiguration.put(ConsumerConfig.AUTO_OFFSET_RESET_CONFIG, "earliest");
// Records should be flushed every 10 seconds. This is less than the default
// in order to keep this example interactive.
streamsConfiguration.put(StreamsConfig.COMMIT_INTERVAL_MS_CONFIG, 10 * 1000);
final Serde<String> stringSerde = Serdes.String();
final Serde<Long> longSerde = Serdes.Long();
final StreamsBuilder builder = new StreamsBuilder();
// Create a stream of page view events from the PageViews topic, where the key of
// a record is assumed to be null and the value an Avro GenericRecord
// that represents the full details of the page view event. See `pageview.avsc` under
// `src/main/avro/` for the corresponding Avro schema.
final KStream<String, GenericRecord> views = builder.stream("PageViews");
// Create a keyed stream of page view events from the PageViews stream,
// by extracting the user id (String) from the Avro value
final KStream<String, GenericRecord> viewsByUser = views.map((dummy, record) -> new KeyValue<>(record.get("user").toString(), record));
// Create a changelog stream for user profiles from the UserProfiles topic,
// where the key of a record is assumed to be the user id (String) and its value
// an Avro GenericRecord. See `userprofile.avsc` under `src/main/avro/` for the
// corresponding Avro schema.
final KTable<String, GenericRecord> userProfiles = builder.table("UserProfiles");
// Create a changelog stream as a projection of the value to the region attribute only
final KTable<String, String> userRegions = userProfiles.mapValues(record -> record.get("region").toString());
// We must specify the Avro schemas for all intermediate (Avro) classes, if any.
// In this example, we want to create an intermediate GenericRecord to hold the view region.
// See `pageviewregion.avsc` under `src/main/avro/`.
final InputStream pageViewRegionSchema = PageViewRegionLambdaExample.class.getClassLoader().getResourceAsStream("avro/io/confluent/examples/streams/pageviewregion.avsc");
final Schema schema = new Schema.Parser().parse(pageViewRegionSchema);
final KTable<Windowed<String>, Long> viewsByRegion = viewsByUser.leftJoin(userRegions, (view, region) -> {
GenericRecord viewRegion = new GenericData.Record(schema);
viewRegion.put("user", view.get("user"));
viewRegion.put("page", view.get("page"));
viewRegion.put("region", region);
return viewRegion;
}).map((user, viewRegion) -> new KeyValue<>(viewRegion.get("region").toString(), viewRegion)).groupByKey().windowedBy(TimeWindows.of(TimeUnit.MINUTES.toMillis(5)).advanceBy(TimeUnit.MINUTES.toMillis(1))).count();
// Note: The following operations would NOT be needed for the actual pageview-by-region
// computation, which would normally stop at `count` above. We use the operations
// below only to "massage" the output data so it is easier to inspect on the console via
// kafka-console-consumer.
final KStream<String, Long> viewsByRegionForConsole = viewsByRegion.toStream((windowedRegion, count) -> windowedRegion.toString());
viewsByRegionForConsole.to("PageViewsByRegion", Produced.with(stringSerde, longSerde));
final KafkaStreams streams = new KafkaStreams(builder.build(), streamsConfiguration);
// Always (and unconditionally) clean local state prior to starting the processing topology.
// We opt for this unconditional call here because this will make it easier for you to play around with the example
// when resetting the application for doing a re-run (via the Application Reset Tool,
// http://docs.confluent.io/current/streams/developer-guide.html#application-reset-tool).
//
// The drawback of cleaning up local state prior is that your app must rebuilt its local state from scratch, which
// will take time and will require reading all the state-relevant data from the Kafka cluster over the network.
// Thus in a production scenario you typically do not want to clean up always as we do here but rather only when it
// is truly needed, i.e., only under certain conditions (e.g., the presence of a command line flag for your app).
// See `ApplicationResetExample.java` for a production-like example.
streams.cleanUp();
streams.start();
// Add shutdown hook to respond to SIGTERM and gracefully close Kafka Streams
Runtime.getRuntime().addShutdownHook(new Thread(streams::close));
}
use of org.apache.kafka.streams.kstream.KStream in project kafka-streams-examples by confluentinc.
the class SumLambdaExample method main.
public static void main(final String[] args) throws Exception {
final String bootstrapServers = args.length > 0 ? args[0] : "localhost:9092";
final Properties streamsConfiguration = new Properties();
// Give the Streams application a unique name. The name must be unique in the Kafka cluster
// against which the application is run.
streamsConfiguration.put(StreamsConfig.APPLICATION_ID_CONFIG, "sum-lambda-example");
streamsConfiguration.put(StreamsConfig.CLIENT_ID_CONFIG, "sum-lambda-example-client");
// Where to find Kafka broker(s).
streamsConfiguration.put(StreamsConfig.BOOTSTRAP_SERVERS_CONFIG, bootstrapServers);
// Specify default (de)serializers for record keys and for record values.
streamsConfiguration.put(StreamsConfig.DEFAULT_KEY_SERDE_CLASS_CONFIG, Serdes.Integer().getClass().getName());
streamsConfiguration.put(StreamsConfig.DEFAULT_VALUE_SERDE_CLASS_CONFIG, Serdes.Integer().getClass().getName());
streamsConfiguration.put(ConsumerConfig.AUTO_OFFSET_RESET_CONFIG, "earliest");
streamsConfiguration.put(StreamsConfig.STATE_DIR_CONFIG, "/tmp/kafka-streams");
// Records should be flushed every 10 seconds. This is less than the default
// in order to keep this example interactive.
streamsConfiguration.put(StreamsConfig.COMMIT_INTERVAL_MS_CONFIG, 10 * 1000);
final StreamsBuilder builder = new StreamsBuilder();
// We assume the input topic contains records where the values are Integers.
// We don't really care about the keys of the input records; for simplicity, we assume them
// to be Integers, too, because we will re-key the stream later on, and the new key will be
// of type Integer.
final KStream<Integer, Integer> input = builder.stream(NUMBERS_TOPIC);
final KTable<Integer, Integer> sumOfOddNumbers = input.filter((k, v) -> v % 2 != 0).selectKey((k, v) -> 1).groupByKey().reduce((v1, v2) -> v1 + v2);
sumOfOddNumbers.toStream().to(SUM_OF_ODD_NUMBERS_TOPIC);
final KafkaStreams streams = new KafkaStreams(builder.build(), streamsConfiguration);
// Always (and unconditionally) clean local state prior to starting the processing topology.
// We opt for this unconditional call here because this will make it easier for you to play around with the example
// when resetting the application for doing a re-run (via the Application Reset Tool,
// http://docs.confluent.io/current/streams/developer-guide.html#application-reset-tool).
//
// The drawback of cleaning up local state prior is that your app must rebuilt its local state from scratch, which
// will take time and will require reading all the state-relevant data from the Kafka cluster over the network.
// Thus in a production scenario you typically do not want to clean up always as we do here but rather only when it
// is truly needed, i.e., only under certain conditions (e.g., the presence of a command line flag for your app).
// See `ApplicationResetExample.java` for a production-like example.
streams.cleanUp();
streams.start();
// Add shutdown hook to respond to SIGTERM and gracefully close Kafka Streams
Runtime.getRuntime().addShutdownHook(new Thread(streams::close));
}
use of org.apache.kafka.streams.kstream.KStream in project kafka-streams-examples by confluentinc.
the class StreamToTableJoinIntegrationTest method shouldCountClicksPerRegion.
@Test
public void shouldCountClicksPerRegion() throws Exception {
// Input 1: Clicks per user (multiple records allowed per user).
List<KeyValue<String, Long>> userClicks = Arrays.asList(new KeyValue<>("alice", 13L), new KeyValue<>("bob", 4L), new KeyValue<>("chao", 25L), new KeyValue<>("bob", 19L), new KeyValue<>("dave", 56L), new KeyValue<>("eve", 78L), new KeyValue<>("alice", 40L), new KeyValue<>("fang", 99L));
// Input 2: Region per user (multiple records allowed per user).
List<KeyValue<String, String>> userRegions = Arrays.asList(new KeyValue<>("alice", "asia"), /* Alice lived in Asia originally... */
new KeyValue<>("bob", "americas"), new KeyValue<>("chao", "asia"), new KeyValue<>("dave", "europe"), new KeyValue<>("alice", "europe"), /* ...but moved to Europe some time later. */
new KeyValue<>("eve", "americas"), new KeyValue<>("fang", "asia"));
List<KeyValue<String, Long>> expectedClicksPerRegion = Arrays.asList(new KeyValue<>("americas", 101L), new KeyValue<>("europe", 109L), new KeyValue<>("asia", 124L));
//
// Step 1: Configure and start the processor topology.
//
final Serde<String> stringSerde = Serdes.String();
final Serde<Long> longSerde = Serdes.Long();
Properties streamsConfiguration = new Properties();
streamsConfiguration.put(StreamsConfig.APPLICATION_ID_CONFIG, "stream-table-join-lambda-integration-test");
streamsConfiguration.put(StreamsConfig.BOOTSTRAP_SERVERS_CONFIG, CLUSTER.bootstrapServers());
streamsConfiguration.put(StreamsConfig.DEFAULT_KEY_SERDE_CLASS_CONFIG, Serdes.String().getClass().getName());
streamsConfiguration.put(StreamsConfig.DEFAULT_VALUE_SERDE_CLASS_CONFIG, Serdes.String().getClass().getName());
// The commit interval for flushing records to state stores and downstream must be lower than
// this integration test's timeout (30 secs) to ensure we observe the expected processing results.
streamsConfiguration.put(StreamsConfig.COMMIT_INTERVAL_MS_CONFIG, 10 * 1000);
streamsConfiguration.put(ConsumerConfig.AUTO_OFFSET_RESET_CONFIG, "earliest");
// Use a temporary directory for storing state, which will be automatically removed after the test.
streamsConfiguration.put(StreamsConfig.STATE_DIR_CONFIG, TestUtils.tempDirectory().getAbsolutePath());
StreamsBuilder builder = new StreamsBuilder();
// This KStream contains information such as "alice" -> 13L.
//
// Because this is a KStream ("record stream"), multiple records for the same user will be
// considered as separate click-count events, each of which will be added to the total count.
KStream<String, Long> userClicksStream = builder.stream(userClicksTopic, Consumed.with(stringSerde, longSerde));
// This KTable contains information such as "alice" -> "europe".
//
// Because this is a KTable ("changelog stream"), only the latest value (here: region) for a
// record key will be considered at the time when a new user-click record (see above) is
// received for the `leftJoin` below. Any previous region values are being considered out of
// date. This behavior is quite different to the KStream for user clicks above.
//
// For example, the user "alice" will be considered to live in "europe" (although originally she
// lived in "asia") because, at the time her first user-click record is being received and
// subsequently processed in the `leftJoin`, the latest region update for "alice" is "europe"
// (which overrides her previous region value of "asia").
KTable<String, String> userRegionsTable = builder.table(userRegionsTopic);
// Compute the number of clicks per region, e.g. "europe" -> 13L.
//
// The resulting KTable is continuously being updated as new data records are arriving in the
// input KStream `userClicksStream` and input KTable `userRegionsTable`.
KTable<String, Long> clicksPerRegion = userClicksStream.leftJoin(userRegionsTable, (clicks, region) -> new RegionWithClicks(region == null ? "UNKNOWN" : region, clicks)).map((user, regionWithClicks) -> new KeyValue<>(regionWithClicks.getRegion(), regionWithClicks.getClicks())).groupByKey(Serialized.with(stringSerde, longSerde)).reduce((firstClicks, secondClicks) -> firstClicks + secondClicks);
// Write the (continuously updating) results to the output topic.
clicksPerRegion.toStream().to(outputTopic, Produced.with(stringSerde, longSerde));
KafkaStreams streams = new KafkaStreams(builder.build(), streamsConfiguration);
streams.start();
//
// Step 2: Publish user-region information.
//
// To keep this code example simple and easier to understand/reason about, we publish all
// user-region records before any user-click records (cf. step 3). In practice though,
// data records would typically be arriving concurrently in both input streams/topics.
Properties userRegionsProducerConfig = new Properties();
userRegionsProducerConfig.put(ProducerConfig.BOOTSTRAP_SERVERS_CONFIG, CLUSTER.bootstrapServers());
userRegionsProducerConfig.put(ProducerConfig.ACKS_CONFIG, "all");
userRegionsProducerConfig.put(ProducerConfig.RETRIES_CONFIG, 0);
userRegionsProducerConfig.put(ProducerConfig.KEY_SERIALIZER_CLASS_CONFIG, StringSerializer.class);
userRegionsProducerConfig.put(ProducerConfig.VALUE_SERIALIZER_CLASS_CONFIG, StringSerializer.class);
IntegrationTestUtils.produceKeyValuesSynchronously(userRegionsTopic, userRegions, userRegionsProducerConfig);
//
// Step 3: Publish some user click events.
//
Properties userClicksProducerConfig = new Properties();
userClicksProducerConfig.put(ProducerConfig.BOOTSTRAP_SERVERS_CONFIG, CLUSTER.bootstrapServers());
userClicksProducerConfig.put(ProducerConfig.ACKS_CONFIG, "all");
userClicksProducerConfig.put(ProducerConfig.RETRIES_CONFIG, 0);
userClicksProducerConfig.put(ProducerConfig.KEY_SERIALIZER_CLASS_CONFIG, StringSerializer.class);
userClicksProducerConfig.put(ProducerConfig.VALUE_SERIALIZER_CLASS_CONFIG, LongSerializer.class);
IntegrationTestUtils.produceKeyValuesSynchronously(userClicksTopic, userClicks, userClicksProducerConfig);
//
// Step 4: Verify the application's output data.
//
Properties consumerConfig = new Properties();
consumerConfig.put(ConsumerConfig.BOOTSTRAP_SERVERS_CONFIG, CLUSTER.bootstrapServers());
consumerConfig.put(ConsumerConfig.GROUP_ID_CONFIG, "join-lambda-integration-test-standard-consumer");
consumerConfig.put(ConsumerConfig.AUTO_OFFSET_RESET_CONFIG, "earliest");
consumerConfig.put(ConsumerConfig.KEY_DESERIALIZER_CLASS_CONFIG, StringDeserializer.class);
consumerConfig.put(ConsumerConfig.VALUE_DESERIALIZER_CLASS_CONFIG, LongDeserializer.class);
List<KeyValue<String, Long>> actualClicksPerRegion = IntegrationTestUtils.waitUntilMinKeyValueRecordsReceived(consumerConfig, outputTopic, expectedClicksPerRegion.size());
streams.close();
assertThat(actualClicksPerRegion).containsExactlyElementsOf(expectedClicksPerRegion);
}
use of org.apache.kafka.streams.kstream.KStream in project kafka-streams-examples by confluentinc.
the class WordCountLambdaIntegrationTest method shouldCountWords.
@Test
public void shouldCountWords() throws Exception {
List<String> inputValues = Arrays.asList("Hello Kafka Streams", "All streams lead to Kafka", "Join Kafka Summit", "И теперь пошли русские слова");
List<KeyValue<String, Long>> expectedWordCounts = Arrays.asList(new KeyValue<>("hello", 1L), new KeyValue<>("all", 1L), new KeyValue<>("streams", 2L), new KeyValue<>("lead", 1L), new KeyValue<>("to", 1L), new KeyValue<>("join", 1L), new KeyValue<>("kafka", 3L), new KeyValue<>("summit", 1L), new KeyValue<>("и", 1L), new KeyValue<>("теперь", 1L), new KeyValue<>("пошли", 1L), new KeyValue<>("русские", 1L), new KeyValue<>("слова", 1L));
//
// Step 1: Configure and start the processor topology.
//
final Serde<String> stringSerde = Serdes.String();
final Serde<Long> longSerde = Serdes.Long();
Properties streamsConfiguration = new Properties();
streamsConfiguration.put(StreamsConfig.APPLICATION_ID_CONFIG, "wordcount-lambda-integration-test");
streamsConfiguration.put(StreamsConfig.BOOTSTRAP_SERVERS_CONFIG, CLUSTER.bootstrapServers());
streamsConfiguration.put(StreamsConfig.DEFAULT_KEY_SERDE_CLASS_CONFIG, Serdes.String().getClass().getName());
streamsConfiguration.put(StreamsConfig.DEFAULT_VALUE_SERDE_CLASS_CONFIG, Serdes.String().getClass().getName());
// The commit interval for flushing records to state stores and downstream must be lower than
// this integration test's timeout (30 secs) to ensure we observe the expected processing results.
streamsConfiguration.put(StreamsConfig.COMMIT_INTERVAL_MS_CONFIG, 10 * 1000);
streamsConfiguration.put(ConsumerConfig.AUTO_OFFSET_RESET_CONFIG, "earliest");
// Use a temporary directory for storing state, which will be automatically removed after the test.
streamsConfiguration.put(StreamsConfig.STATE_DIR_CONFIG, TestUtils.tempDirectory().getAbsolutePath());
StreamsBuilder builder = new StreamsBuilder();
KStream<String, String> textLines = builder.stream(inputTopic);
Pattern pattern = Pattern.compile("\\W+", Pattern.UNICODE_CHARACTER_CLASS);
KTable<String, Long> wordCounts = textLines.flatMapValues(value -> Arrays.asList(pattern.split(value.toLowerCase()))).groupBy((key, word) -> word).count();
wordCounts.toStream().to(outputTopic, Produced.with(stringSerde, longSerde));
KafkaStreams streams = new KafkaStreams(builder.build(), streamsConfiguration);
streams.start();
//
// Step 2: Produce some input data to the input topic.
//
Properties producerConfig = new Properties();
producerConfig.put(ProducerConfig.BOOTSTRAP_SERVERS_CONFIG, CLUSTER.bootstrapServers());
producerConfig.put(ProducerConfig.ACKS_CONFIG, "all");
producerConfig.put(ProducerConfig.RETRIES_CONFIG, 0);
producerConfig.put(ProducerConfig.KEY_SERIALIZER_CLASS_CONFIG, StringSerializer.class);
producerConfig.put(ProducerConfig.VALUE_SERIALIZER_CLASS_CONFIG, StringSerializer.class);
IntegrationTestUtils.produceValuesSynchronously(inputTopic, inputValues, producerConfig);
//
// Step 3: Verify the application's output data.
//
Properties consumerConfig = new Properties();
consumerConfig.put(ConsumerConfig.BOOTSTRAP_SERVERS_CONFIG, CLUSTER.bootstrapServers());
consumerConfig.put(ConsumerConfig.GROUP_ID_CONFIG, "wordcount-lambda-integration-test-standard-consumer");
consumerConfig.put(ConsumerConfig.AUTO_OFFSET_RESET_CONFIG, "earliest");
consumerConfig.put(ConsumerConfig.KEY_DESERIALIZER_CLASS_CONFIG, StringDeserializer.class);
consumerConfig.put(ConsumerConfig.VALUE_DESERIALIZER_CLASS_CONFIG, LongDeserializer.class);
List<KeyValue<String, Long>> actualWordCounts = IntegrationTestUtils.waitUntilMinKeyValueRecordsReceived(consumerConfig, outputTopic, expectedWordCounts.size());
streams.close();
assertThat(actualWordCounts).containsExactlyElementsOf(expectedWordCounts);
}
Aggregations