python - How can I write to Big Query using a runtime value provider in Apache Beam?

Question

EDIT: I got this to work using beam.io.WriteToBigQuery with the sink experimental option turned on. I actually had it on but my issue was I was trying to "build" the full table reference from two variables (dataset + table) wrapped in str(). This was taking the whole value provider arguments data as a string instead of calling the get() method to get just the value.

OP

I am trying to generate a Dataflow template to then call from a GCP Cloud Function.(For reference, my dataflow job is supposed to read a file with a bunch of filenames in it and then reads all of those from GCS and writes the to BQ). Because of this I need to write it in such a way so that I can use runtime value providers to pass the BigQuery dataset/table.

At the bottom of my post is my code currently, omitting some stuff that's not relevant to the question from it. Pay attention to the BQ_flexible_writer(beam.DoFn) specifically - that's where I am trying to "customise" beam.io.WriteToBigQuery so that it accepts the runtime value providers.

My template generates fine and when I test run the pipeline without supplying runtime variables (relying on the defaults) it succeeds and I see the rows added when looking at the job in the console. However, when checking BigQuery there's no data (tripple checked the dataset/table name is correct in the logs). Not sure where it goes or what logging I can add to understand what's happening to the elements?

Any ideas what's happening here? Or suggestions on how I can write to BigQuery using runtime variables? Can I even call beam.io.WriteToBigQuery the way I've included it in my DoFn or do I have to take the actual code behind beam.io.WriteToBigQuery and work with that?

#=========================================================

class BQ_flexible_writer(beam.DoFn):
    def __init__(self, dataset, table):
        self.dataset = dataset
        self.table = table

    def process(self, element):
        dataset_res = self.dataset.get()
        table_res = self.table.get()
        logging.info('Writing to table: {}.{}'.format(dataset_res,table_res))
        beam.io.WriteToBigQuery(
        #dataset= runtime_options.dataset,
        table = str(dataset_res) + '.' + str(table_res), 
        schema = SCHEMA_ADFImpression,
        project = str(PROJECT_ID), #options.display_data()['project'],
        create_disposition = beam.io.BigQueryDisposition.CREATE_IF_NEEDED,  #'CREATE_IF_NEEDED',#create if does not exist.
        write_disposition = beam.io.BigQueryDisposition.WRITE_APPEND    #'WRITE_APPEND' #add to existing rows,partitoning
        )
# https://cloud.google.com/dataflow/docs/guides/templates/creating-templates#valueprovider
class FileIterator(beam.DoFn):
    def __init__(self, files_bucket):
        self.files_bucket = files_bucket

    def process(self, element):
        files = pd.read_csv(str(element), header=None).values[0].tolist()
        bucket = self.files_bucket.get()
        files = [str(bucket) + '/' + file for file in files]
        logging.info('Files list is: {}'.format(files))
        return files

# https://stackoverflow.com/questions/58240058/ways-of-using-value-provider-parameter-in-python-apache-beam   
class OutputValueProviderFn(beam.DoFn):
    def __init__(self, vp):
        self.vp = vp

    def process(self, unused_elm):
        yield self.vp.get()


class RuntimeOptions(PipelineOptions):
    @classmethod
    def _add_argparse_args(cls, parser):

        parser.add_value_provider_argument(
          '--dataset',
          default='EDITED FOR PRIVACY',
          help='BQ dataset to write to',
          type=str)

        parser.add_value_provider_argument(
          '--table',
          default='EDITED FOR PRIVACY',
          required=False,
          help='BQ table to write to',
          type=str)

        parser.add_value_provider_argument(
          '--filename',
          default='EDITED FOR PRIVACY',
          help='Filename of batch file',
          type=str)

        parser.add_value_provider_argument(
          '--batch_bucket',
          default='EDITED FOR PRIVACY',
          help='Bucket for batch file',
          type=str)

        #parser.add_value_provider_argument(
        #   '--bq_schema',
          #default='gs://dataflow-samples/shakespeare/kinglear.txt',
        #  help='Schema to specify for BQ')

        #parser.add_value_provider_argument(
        #   '--schema_list',
          #default='gs://dataflow-samples/shakespeare/kinglear.txt',
        #  help='Schema in list for processing')

        parser.add_value_provider_argument(
          '--files_bucket',
          default='EDITED FOR PRIVACY',
          help='Bucket where the raw files are',
          type=str)

        parser.add_value_provider_argument(
          '--complete_batch',
          default='EDITED FOR PRIVACY',
          help='Bucket where the raw files are',
          type=str)
#=========================================================

def run():
    #====================================
    # TODO PUT AS PARAMETERS 
    #====================================
    JOB_NAME_READING = 'adf-reading'
    JOB_NAME_PROCESSING = 'adf-'

    job_name = '{}-batch--{}'.format(JOB_NAME_PROCESSING,_millis())

    pipeline_options_batch = PipelineOptions()

    runtime_options = pipeline_options_batch.view_as(RuntimeOptions)

    setup_options = pipeline_options_batch.view_as(SetupOptions)
    setup_options.setup_file  = './setup.py'
    google_cloud_options = pipeline_options_batch.view_as(GoogleCloudOptions)
    google_cloud_options.project = PROJECT_ID
    google_cloud_options.job_name = job_name
    google_cloud_options.region = 'europe-west1'
    google_cloud_options.staging_location = GCS_STAGING_LOCATION
    google_cloud_options.temp_location = GCS_TMP_LOCATION


    #pipeline_options_batch.view_as(StandardOptions).runner = 'DirectRunner'

    # # If datflow runner [BEGIN]
    pipeline_options_batch.view_as(StandardOptions).runner = 'DataflowRunner'
    pipeline_options_batch.view_as(WorkerOptions).autoscaling_algorithm = 'THROUGHPUT_BASED'

    #pipeline_options_batch.view_as(WorkerOptions).machine_type = 'n1-standard-96' #'n1-highmem-32' #' 
    pipeline_options_batch.view_as(WorkerOptions).max_num_workers = 10
    #  [END]

    pipeline_options_batch.view_as(SetupOptions).save_main_session = True
    #Needed this in order to pass table to BQ at runtime
    pipeline_options_batch.view_as(DebugOptions).experiments = ['use_beam_bq_sink']


    with beam.Pipeline(options=pipeline_options_batch) as pipeline_2:

        try:

            final_data = (
            pipeline_2
            |'Create empty PCollection' >> beam.Create([None])
            |'Get accepted batch file 1/2:{}'.format(OutputValueProviderFn(runtime_options.complete_batch)) >> beam.ParDo(OutputValueProviderFn(runtime_options.complete_batch))
            |'Get accepted batch file 2/2:{}'.format(OutputValueProviderFn(runtime_options.complete_batch)) >> beam.ParDo(FileIterator(runtime_options.files_bucket))
            |'Read all files' >> beam.io.ReadAllFromText(skip_header_lines=1)
            |'Process all files' >> beam.ParDo(ProcessCSV(),COLUMNS_SCHEMA_0)
            |'Format all files' >> beam.ParDo(AdfDict())
            #|'WriteToBigQuery_{}'.format('test'+str(_millis())) >> beam.io.WriteToBigQuery(
            #        #dataset= runtime_options.dataset,
            #        table = str(runtime_options.dataset) + '.' + str(runtime_options.table), 
            #        schema = SCHEMA_ADFImpression,
            #        project = pipeline_options_batch.view_as(GoogleCloudOptions).project, #options.display_data()['project'],
            #        create_disposition = beam.io.BigQueryDisposition.CREATE_IF_NEEDED,  #'CREATE_IF_NEEDED',#create if does not exist.
            #        write_disposition = beam.io.BigQueryDisposition.WRITE_APPEND    #'WRITE_APPEND' #add to existing rows,partitoning
            #        )
            |'WriteToBigQuery' >> beam.ParDo(BQ_flexible_writer(runtime_options.dataset,runtime_options.table))
            )
        except Exception as exception:
            logging.error(exception)
            pass

Answer 1

Waitting for answers