Java Code Examples for org.apache.samza.application.descriptors.TaskApplicationDescriptor#withDefaultSystem()

The following examples show how to use org.apache.samza.application.descriptors.TaskApplicationDescriptor#withDefaultSystem() . You can vote up the ones you like or vote down the ones you don't like, and go to the original project or source file by following the links above each example. You may check out the related API usage on the sidebar.
Example 1
Source File: WikipediaFeedTaskApplication.java    From samza-hello-samza with Apache License 2.0 5 votes vote down vote up 
@Override
public void describe(TaskApplicationDescriptor taskApplicationDescriptor) {

  // Define a SystemDescriptor for Wikipedia data
  WikipediaSystemDescriptor wikipediaSystemDescriptor = new WikipediaSystemDescriptor("irc.wikimedia.org", 6667);

  // Define InputDescriptors for consuming wikipedia data
  WikipediaInputDescriptor wikipediaInputDescriptor =
      wikipediaSystemDescriptor.getInputDescriptor("en-wikipedia").withChannel("#en.wikipedia");
  WikipediaInputDescriptor wiktionaryInputDescriptor =
      wikipediaSystemDescriptor.getInputDescriptor("en-wiktionary").withChannel("#en.wiktionary");
  WikipediaInputDescriptor wikiNewsInputDescriptor =
      wikipediaSystemDescriptor.getInputDescriptor("en-wikinews").withChannel("#en.wikinews");

  // Define a system descriptor for Kafka, which is our output system
  KafkaSystemDescriptor kafkaSystemDescriptor =
      new KafkaSystemDescriptor("kafka").withConsumerZkConnect(KAFKA_CONSUMER_ZK_CONNECT)
          .withProducerBootstrapServers(KAFKA_PRODUCER_BOOTSTRAP_SERVERS)
          .withDefaultStreamConfigs(KAFKA_DEFAULT_STREAM_CONFIGS);

  // Define an output descriptor
  KafkaOutputDescriptor kafkaOutputDescriptor =
      kafkaSystemDescriptor.getOutputDescriptor("wikipedia-raw", new JsonSerde<>());

  // Set the default system descriptor to Kafka, so that it is used for all
  // internal resources, e.g., kafka topic for checkpointing, coordinator stream.
  taskApplicationDescriptor.withDefaultSystem(kafkaSystemDescriptor);

  // Set the inputs
  taskApplicationDescriptor.withInputStream(wikipediaInputDescriptor);
  taskApplicationDescriptor.withInputStream(wiktionaryInputDescriptor);
  taskApplicationDescriptor.withInputStream(wikiNewsInputDescriptor);

  // Set the output
  taskApplicationDescriptor.withOutputStream(kafkaOutputDescriptor);

  // Set the task factory
  taskApplicationDescriptor.withTaskFactory((StreamTaskFactory) () -> new WikipediaFeedStreamTask());
}
Example 2
Source File: WikipediaParserTaskApplication.java    From samza-hello-samza with Apache License 2.0 5 votes vote down vote up 
@Override
public void describe(TaskApplicationDescriptor taskApplicationDescriptor) {

  // Define a system descriptor for Kafka, which is both our input and output system
  KafkaSystemDescriptor kafkaSystemDescriptor =
      new KafkaSystemDescriptor("kafka").withConsumerZkConnect(KAFKA_CONSUMER_ZK_CONNECT)
          .withProducerBootstrapServers(KAFKA_PRODUCER_BOOTSTRAP_SERVERS)
          .withDefaultStreamConfigs(KAFKA_DEFAULT_STREAM_CONFIGS);

  // Input descriptor for the wikipedia-raw topic
  KafkaInputDescriptor kafkaInputDescriptor =
      kafkaSystemDescriptor.getInputDescriptor("wikipedia-raw", new JsonSerde<>());

  // Output descriptor for the wikipedia-edits topic
  KafkaOutputDescriptor kafkaOutputDescriptor =
      kafkaSystemDescriptor.getOutputDescriptor("wikipedia-edits", new JsonSerde<>());

  // Set the default system descriptor to Kafka, so that it is used for all
  // internal resources, e.g., kafka topic for checkpointing, coordinator stream.
  taskApplicationDescriptor.withDefaultSystem(kafkaSystemDescriptor);

  // Set the input
  taskApplicationDescriptor.withInputStream(kafkaInputDescriptor);

  // Set the output
  taskApplicationDescriptor.withOutputStream(kafkaOutputDescriptor);

  // Set the task factory
  taskApplicationDescriptor.withTaskFactory((StreamTaskFactory) () -> new WikipediaParserStreamTask());
}
Example 3
Source File: WikipediaStatsTaskApplication.java    From samza-hello-samza with Apache License 2.0 5 votes vote down vote up 
@Override
public void describe(TaskApplicationDescriptor taskApplicationDescriptor) {

  // Define a system descriptor for Kafka
  KafkaSystemDescriptor kafkaSystemDescriptor = new KafkaSystemDescriptor("kafka")
      .withConsumerZkConnect(KAFKA_CONSUMER_ZK_CONNECT)
      .withProducerBootstrapServers(KAFKA_PRODUCER_BOOTSTRAP_SERVERS)
      .withDefaultStreamConfigs(KAFKA_DEFAULT_STREAM_CONFIGS);

  // Input descriptor for the wikipedia-edits topic
  KafkaInputDescriptor kafkaInputDescriptor =
      kafkaSystemDescriptor.getInputDescriptor("wikipedia-edits", new JsonSerde<>());

  // Set the default system descriptor to Kafka, so that it is used for all
  // internal resources, e.g., kafka topic for checkpointing, coordinator stream.
  taskApplicationDescriptor.withDefaultSystem(kafkaSystemDescriptor);

  // Set the input
  taskApplicationDescriptor.withInputStream(kafkaInputDescriptor);

  // Set the output
  taskApplicationDescriptor.withOutputStream(
      kafkaSystemDescriptor.getOutputDescriptor("wikipedia-stats", new JsonSerde<>()));

  // Set the task factory
  taskApplicationDescriptor.withTaskFactory((StreamTaskFactory) () -> new WikipediaStatsStreamTask());
}