Creazione di modelli Dataflow classici

  public interface WordCountOptions extends PipelineOptions {
    @Description("Path of the file to read from")
    @Default.String("gs://dataflow-samples/shakespeare/kinglear.txt")
    String getInputFile();
    void setInputFile(String value);
  }

  public static void main(String[] args) {
    WordCountOptions options =
          PipelineOptionsFactory.fromArgs(args).withValidation()
            .as(WordCountOptions.class);
    Pipeline p = Pipeline.create(options);

    p.apply("ReadLines", TextIO.read().from(options.getInputFile()));
    ...

  class WordcountOptions(PipelineOptions):
    @classmethod
    def _add_argparse_args(cls, parser):
      parser.add_argument(
          '--input',
          default='gs://dataflow-samples/shakespeare/kinglear.txt',
          help='Path of the file to read from')
      parser.add_argument(
          '--output',
          required=True,
          help='Output file to write results to.')
  pipeline_options = PipelineOptions(['--output', 'some/output_path'])
  p = beam.Pipeline(options=pipeline_options)

  wordcount_options = pipeline_options.view_as(WordcountOptions)
  lines = p | 'read' >> ReadFromText(wordcount_options.input)

  public interface WordCountOptions extends PipelineOptions {
    @Description("Path of the file to read from")
    @Default.String("gs://dataflow-samples/shakespeare/kinglear.txt")
    ValueProvider<String> getInputFile();
    void setInputFile(ValueProvider<String> value);
  }

  public static void main(String[] args) {
    WordCountOptions options =
          PipelineOptionsFactory.fromArgs(args).withValidation()
            .as(WordCountOptions.class);
    Pipeline p = Pipeline.create(options);

    p.apply("ReadLines", TextIO.read().from(options.getInputFile()));
    ...

 class WordcountOptions(PipelineOptions):
    @classmethod
    def _add_argparse_args(cls, parser):
      # Use add_value_provider_argument for arguments to be templatable
      # Use add_argument as usual for non-templatable arguments
      parser.add_value_provider_argument(
          '--input',
          default='gs://dataflow-samples/shakespeare/kinglear.txt',
          help='Path of the file to read from')
      parser.add_argument(
          '--output',
          required=True,
          help='Output file to write results to.')
  pipeline_options = PipelineOptions(['--output', 'some/output_path'])
  p = beam.Pipeline(options=pipeline_options)

  wordcount_options = pipeline_options.view_as(WordcountOptions)
  lines = p | 'read' >> ReadFromText(wordcount_options.input)

  public interface SumIntOptions extends PipelineOptions {
      // New runtime parameter, specified by the --int
      // option at runtime.
      ValueProvider<Integer> getInt();
      void setInt(ValueProvider<Integer> value);
  }

  class MySumFn extends DoFn<Integer, Integer> {
      ValueProvider<Integer> mySumInteger;

      MySumFn(ValueProvider<Integer> sumInt) {
          // Store the value provider
          this.mySumInteger = sumInt;
      }

      @ProcessElement
      public void processElement(ProcessContext c) {
         // Get the value of the value provider and add it to
         // the element's value.
         c.output(c.element() + mySumInteger.get());
      }
  }

  public static void main(String[] args) {
    SumIntOptions options =
          PipelineOptionsFactory.fromArgs(args).withValidation()
            .as(SumIntOptions.class);

    Pipeline p = Pipeline.create(options);

    p.apply(Create.of(1, 2, 3))
      // Get the value provider and pass it to MySumFn
     .apply(ParDo.of(new MySumFn(options.getInt())))
     .apply("ToString", MapElements.into(TypeDescriptors.strings()).via(x -> x.toString()))
     .apply("OutputNums", TextIO.write().to("numvalues"));

    p.run();
  }

  import apache_beam as beam
  from apache_beam.options.pipeline_options import PipelineOptions
  from apache_beam.options.value_provider import StaticValueProvider
  from apache_beam.io import WriteToText

  class UserOptions(PipelineOptions):
    @classmethod
    def _add_argparse_args(cls, parser):
      parser.add_value_provider_argument('--templated_int', type=int)

  class MySumFn(beam.DoFn):
    def __init__(self, templated_int):
      self.templated_int = templated_int

    def process(self, an_int):
      yield self.templated_int.get() + an_int

  pipeline_options = PipelineOptions()
  p = beam.Pipeline(options=pipeline_options)

  user_options = pipeline_options.view_as(UserOptions)
  sum = (p
         | 'ReadCollection' >> beam.io.ReadFromText(
             'gs://some/integer_collection')
         | 'StringToInt' >> beam.Map(lambda w: int(w))
         | 'AddGivenInt' >> beam.ParDo(MySumFn(user_options.templated_int))
         | 'WriteResultingCollection' >> WriteToText('some/output_path'))

  .apply(ParDo.of(new MySumFn(options.getInt())))

  .apply(ParDo.of(new MySumFn(StaticValueProvider.of(10))))

  beam.ParDo(MySumFn(user_options.templated_int))

  beam.ParDo(MySumFn(StaticValueProvider(int,10)))

  // Create a StaticValueProvider<String> from a regular String parameter
  // value, and then call .from() with this new StaticValueProvider.
  public Read from(String filepattern) {
    checkNotNull(filepattern, "Filepattern cannot be empty.");
    return from(StaticValueProvider.of(filepattern));
  }

  // This method takes a ValueProvider parameter.
  public Read from(ValueProvider<String> filepattern) {
    checkNotNull(filepattern, "Filepattern cannot be empty.");
    return toBuilder().setFilepattern(filepattern).build();
  }

class Read():

  def __init__(self, filepattern):
    if isinstance(filepattern, str):
      # Create a StaticValueProvider from a regular string parameter
      filepattern = StaticValueProvider(str, filepattern)

    self.filepattern = filepattern