Dataflow パイプライン オプションを設定する

mvn -Pdataflow-runner compile exec:java \
  -Dexec.mainClass=org.apache.beam.examples.WordCount \
  -Dexec.args="--project=PROJECT_ID \
  --gcpTempLocation=gs://BUCKET_NAME/temp/ \
  --output=gs://BUCKET_NAME/output \
  --runner=DataflowRunner \
  --region=REGION"

python -m apache_beam.examples.wordcount \
  --region DATAFLOW_REGION \
  --input gs://dataflow-samples/shakespeare/kinglear.txt \
  --output gs://STORAGE_BUCKET/results/outputs \
  --runner DataflowRunner \
  --project PROJECT_ID \
  --temp_location gs://STORAGE_BUCKET/tmp/

go run wordcount.go --input gs://dataflow-samples/shakespeare/kinglear.txt \
   --output gs://BUCKET_NAME/results/outputs \
   --runner dataflow \
   --project PROJECT_ID \
   --region DATAFLOW_REGION \
   --staging_location gs://BUCKET_NAME/binaries/

options.setExperiments("streaming_boot_disk_size_gb=80")

beam_options = PipelineOptions(
  beam_args,
  experiments=['streaming_boot_disk_size_gb=80'])

--experiments=streaming_boot_disk_size_gb=80

--experiments=streaming_boot_disk_size_gb=80

--experiments=streaming_boot_disk_size_gb=80

gcloud dataflow jobs run JOB_NAME --additional-experiments=EXPERIMENT[,...]

gcloud dataflow flex-template run JOB_NAME --additional-experiments=EXPERIMENT[,...]

// Create and set your PipelineOptions.
DataflowPipelineOptions options = PipelineOptionsFactory.as(DataflowPipelineOptions.class);

// For cloud execution, set the Google Cloud project, staging location,
// and set DataflowRunner.
options.setProject("my-project-id");
options.setStagingLocation("gs://my-bucket/binaries");
options.setRunner(DataflowRunner.class);

// Create the Pipeline with the specified options.
Pipeline p = Pipeline.create(options);

import argparse

import apache_beam as beam
from apache_beam.options.pipeline_options import PipelineOptions

parser = argparse.ArgumentParser()
# parser.add_argument('--my-arg', help='description')
args, beam_args = parser.parse_known_args()

# Create and set your PipelineOptions.
# For Cloud execution, specify DataflowRunner and set the Cloud Platform
# project, job name, temporary files location, and region.
# For more information about regions, check:
# https://cloud.google.com/dataflow/docs/concepts/regional-endpoints
beam_options = PipelineOptions(
    beam_args,
    runner='DataflowRunner',
    project='my-project-id',
    job_name='unique-job-name',
    temp_location='gs://my-bucket/temp',
    region='us-central1')
# Note: Repeatable options like dataflow_service_options or experiments must
# be specified as a list of string(s).
# e.g. dataflow_service_options=['enable_prime']

# Create the Pipeline with the specified options.
with beam.Pipeline(options=beam_options) as pipeline:
  pass  # build your pipeline here.

// Use the Go flag package to parse custom options.
flag.Parse()

// Set the required options programmatically.
// For Cloud execution, specify the Dataflow runner, Google Cloud
// project ID, region, and staging location.
// For more information about regions, see
// https://cloud.google.com/dataflow/docs/concepts/regional-endpoints
flag.Set("runner", "dataflow")
flag.Set("project", "my-project-id")
flag.Set("region", "us-central1")
flag.Set("staging_location", "gs://my-bucket/binaries")

beam.Init()

// Create the Pipeline.
p := beam.NewPipeline()
s := p.Root()

// Set your PipelineOptions to the specified command-line options
MyOptions options = PipelineOptionsFactory.fromArgs(args).withValidation();

// Create the Pipeline with the specified options.
Pipeline p = Pipeline.create(options);

# Use Python argparse module to parse custom arguments
import argparse

import apache_beam as beam
from apache_beam.options.pipeline_options import PipelineOptions

# For more details on how to use argparse, take a look at:
#   https://docs.python.org/3/library/argparse.html
parser = argparse.ArgumentParser()
parser.add_argument(
    '--input-file',
    default='gs://dataflow-samples/shakespeare/kinglear.txt',
    help='The file path for the input text to process.')
parser.add_argument(
    '--output-path', required=True, help='The path prefix for output files.')
args, beam_args = parser.parse_known_args()

# Create the Pipeline with remaining arguments.
beam_options = PipelineOptions(beam_args)
with beam.Pipeline(options=beam_options) as pipeline:
  lines = (
      pipeline
      | 'Read files' >> beam.io.ReadFromText(args.input_file)
      | 'Write files' >> beam.io.WriteToText(args.output_path))

// Define configuration options
var (
  output = flag.String("output", "", "Output file (required).")
)

// Parse options before beam.Init()
flag.Parse()

beam.Init()

// Input validation must be done after beam.Init()
if *output == "" {
  log.Fatal("No output provided!")
}

p := beam.NewPipeline()

// Create and set our Pipeline Options.
PipelineOptions options = PipelineOptionsFactory.create();

// Create the Pipeline with the specified options.
Pipeline p = Pipeline.create(options);

import argparse

import apache_beam as beam
from apache_beam.options.pipeline_options import PipelineOptions

parser = argparse.ArgumentParser()
# parser.add_argument('--my-arg')
args, beam_args = parser.parse_known_args()

# Create and set your Pipeline Options.
beam_options = PipelineOptions(beam_args)
args = beam_options.view_as(MyOptions)

with beam.Pipeline(options=beam_options) as pipeline:
  lines = (
      pipeline
      | beam.io.ReadFromText(args.input)
      | beam.io.WriteToText(args.output))

// Parse options before beam.Init()
flag.Parse()

beam.Init()

p := beam.NewPipeline()

public interface MyOptions extends PipelineOptions {
  String getMyCustomOption();
  void setMyCustomOption(String myCustomOption);
}

from apache_beam.options.pipeline_options import PipelineOptions

class MyOptions(PipelineOptions):
  @classmethod
  def _add_argparse_args(cls, parser):
    parser.add_argument('--input')
    parser.add_argument('--output')

var (
  input  = flag.String("input", "", "")
  output = flag.String("output", "", "")
)

public interface MyOptions extends PipelineOptions {
  @Description("My custom command line argument.")
  @Default.String("DEFAULT")
  String getMyCustomOption();
  void setMyCustomOption(String myCustomOption);
}

PipelineOptionsFactory.register(MyOptions.class);
MyOptions options = PipelineOptionsFactory.fromArgs(args)
                                          .withValidation()
                                          .as(MyOptions.class);

from apache_beam.options.pipeline_options import PipelineOptions

class MyOptions(PipelineOptions):
  @classmethod
  def _add_argparse_args(cls, parser):
    parser.add_argument(
        '--input',
        default='gs://dataflow-samples/shakespeare/kinglear.txt',
        help='The file path for the input text to process.')
    parser.add_argument(
        '--output', required=True, help='The path prefix for output files.')

var (
  input  = flag.String("input", "gs://MY_STORAGE_BUCKET/input", "Input for the pipeline")
  output = flag.String("output", "gs://MY_STORAGE_BUCKET/output", "Output for the pipeline")
)