Read from Apache Kafka to Dataflow

Shows how to create a Dataflow pipeline that reads from Apache Kafka

Explore further

For detailed documentation that includes this code sample, see the following:

• Read from Apache Kafka to Dataflow

Code sample

Java

To authenticate to Dataflow, set up Application Default Credentials. For more information, see Set up authentication for a local development environment.

import com.google.common.collect.ImmutableMap;
import java.io.UnsupportedEncodingException;
import org.apache.beam.sdk.Pipeline;
import org.apache.beam.sdk.PipelineResult;
import org.apache.beam.sdk.io.TextIO;
import org.apache.beam.sdk.managed.Managed;
import org.apache.beam.sdk.options.Description;
import org.apache.beam.sdk.options.PipelineOptionsFactory;
import org.apache.beam.sdk.options.StreamingOptions;
import org.apache.beam.sdk.transforms.MapElements;
import org.apache.beam.sdk.values.TypeDescriptors;

public class KafkaRead {

  public static Pipeline createPipeline(Options options) {

    // Create configuration parameters for the Managed I/O transform.
    ImmutableMap<String, Object> config = ImmutableMap.<String, Object>builder()
        .put("bootstrap_servers", options.getBootstrapServer())
        .put("topic", options.getTopic())
        .put("data_format", "RAW")
        .put("max_read_time_seconds", 15)
        .put("auto_offset_reset_config", "earliest")
        .build();

    // Build the pipeline.
    var pipeline = Pipeline.create(options);
    pipeline
        // Read messages from Kafka.
        .apply(Managed.read(Managed.KAFKA).withConfig(config)).getSinglePCollection()
        // Get the payload of each message and convert to a string.
        .apply(MapElements
            .into(TypeDescriptors.strings())
            .via((row -> {
              var bytes = row.getBytes("payload");
              try {
                return new String(bytes, "UTF-8");
              } catch (UnsupportedEncodingException e) {
                throw new RuntimeException(e);
              }
            })))
        // Write the payload to a text file.
        .apply(TextIO
            .write()
            .to(options.getOutputPath())
            .withSuffix(".txt")
            .withNumShards(1));
    return pipeline;
  }
}

Python

To authenticate to Dataflow, set up Application Default Credentials. For more information, see Set up authentication for a local development environment.

import argparse

import apache_beam as beam

from apache_beam import window
from apache_beam.io.kafka import ReadFromKafka
from apache_beam.io.textio import WriteToText
from apache_beam.options.pipeline_options import PipelineOptions


def read_from_kafka() -> None:
    # Parse the pipeline options passed into the application. Example:
    #     --topic=$KAFKA_TOPIC --bootstrap_server=$BOOTSTRAP_SERVER
    #     --output=$CLOUD_STORAGE_BUCKET --streaming
    # For more information, see
    # https://beam.apache.org/documentation/programming-guide/#configuring-pipeline-options
    class MyOptions(PipelineOptions):
        @staticmethod
        def _add_argparse_args(parser: argparse.ArgumentParser) -> None:
            parser.add_argument("--topic")
            parser.add_argument("--bootstrap_server")
            parser.add_argument("--output")

    options = MyOptions()
    with beam.Pipeline(options=options) as pipeline:
        (
            pipeline
            # Read messages from an Apache Kafka topic.
            | ReadFromKafka(
                consumer_config={"bootstrap.servers": options.bootstrap_server},
                topics=[options.topic],
                with_metadata=False,
                max_num_records=5,
                start_read_time=0,
            )
            # The previous step creates a key-value collection, keyed by message ID.
            # The values are the message payloads.
            | beam.Values()
            # Subdivide the output into fixed 5-second windows.
            | beam.WindowInto(window.FixedWindows(5))
            | WriteToText(
                file_path_prefix=options.output, file_name_suffix=".txt", num_shards=1
            )
        )

What's next

To search and filter code samples for other Google Cloud products, see the Google Cloud sample browser.