從 Apache Kafka 讀取資料到 Dataflow

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;
  }
}

import argparse

import apache_beam as beam

from apache_beam import window
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.
            | beam.managed.Read(
                beam.managed.KAFKA,
                config={
                  "bootstrap_servers": options.bootstrap_server,
                  "topic": options.topic,
                  "data_format": "RAW",
                  "auto_offset_reset_config": "earliest",
                  # The max_read_time_seconds parameter is intended for testing.
                  # Avoid using this parameter in production.
                  "max_read_time_seconds": 5
                }
            )
            # 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
            )
        )

import java.util.List;
import org.apache.beam.sdk.Pipeline;
import org.apache.beam.sdk.PipelineResult;
import org.apache.beam.sdk.io.TextIO;
import org.apache.beam.sdk.io.kafka.KafkaIO;
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.Filter;
import org.apache.beam.sdk.transforms.MapElements;
import org.apache.beam.sdk.values.TypeDescriptors;
import org.apache.kafka.common.serialization.LongDeserializer;
import org.apache.kafka.common.serialization.StringDeserializer;
import org.joda.time.Duration;
import org.joda.time.Instant;

public class KafkaReadTopics {

  public static Pipeline createPipeline(Options options) {
    String topic1 = options.getTopic1();
    String topic2 = options.getTopic2();

    // Build the pipeline.
    var pipeline = Pipeline.create(options);
    var allTopics = pipeline
        .apply(KafkaIO.<Long, String>read()
            .withTopics(List.of(topic1, topic2))
            .withBootstrapServers(options.getBootstrapServer())
            .withKeyDeserializer(LongDeserializer.class)
            .withValueDeserializer(StringDeserializer.class)
            .withMaxReadTime(Duration.standardSeconds(10))
            .withStartReadTime(Instant.EPOCH)
        );

    // Create separate pipeline branches for each topic.
    // The first branch filters on topic1.
    allTopics
        .apply(Filter.by(record -> record.getTopic().equals(topic1)))
        .apply(MapElements
            .into(TypeDescriptors.strings())
            .via(record -> record.getKV().getValue()))
        .apply(TextIO.write()
            .to(topic1)
            .withSuffix(".txt")
            .withNumShards(1)
        );

    // The second branch filters on topic2.
    allTopics
        .apply(Filter.by(record -> record.getTopic().equals(topic2)))
        .apply(MapElements
            .into(TypeDescriptors.strings())
            .via(record -> record.getKV().getValue()))
        .apply(TextIO.write()
            .to(topic2)
            .withSuffix(".txt")
            .withNumShards(1)
        );
    return pipeline;
  }
}

import argparse

import apache_beam as beam

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:
    #   --bootstrap_server=$BOOTSTRAP_SERVER --output=$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('--bootstrap_server')
            parser.add_argument('--output')

    options = MyOptions()
    with beam.Pipeline(options=options) as pipeline:
        # Read from two Kafka topics.
        all_topics = pipeline | ReadFromKafka(consumer_config={
                "bootstrap.servers": options.bootstrap_server
            },
            topics=["topic1", "topic2"],
            with_metadata=True,
            max_num_records=10,
            start_read_time=0
        )

        # Filter messages from one topic into one branch of the pipeline.
        (all_topics
            | beam.Filter(lambda message: message.topic == 'topic1')
            | beam.Map(lambda message: message.value.decode('utf-8'))
            | "Write topic1" >> WriteToText(
                file_path_prefix=options.output + '/topic1/output',
                file_name_suffix='.txt',
                num_shards=1))

        # Filter messages from the other topic.
        (all_topics
            | beam.Filter(lambda message: message.topic == 'topic2')
            | beam.Map(lambda message: message.value.decode('utf-8'))
            | "Write topic2" >> WriteToText(
                file_path_prefix=options.output + '/topic2/output',
                file_name_suffix='.txt',
                num_shards=1))