Ok I have to be missing something here. What do i need to stage a pipeline as a template? When I try to stage my template with via these instructions, it runs the module but doesn't stage anything., it appears to function as expected without errors, but I don't see any files actually get added to the bucket location listen in my --template_location. Should my python code be showing up there? I assume so right? I have made sure i have all the beam and google cloud SDKs installed, but maybe I'm missing something? What do you need to do to stage this dataflow template? Also can I manually just drop the file in a bucket and run it from there? The following is the template I am currently playing with:
import json
import apache_beam as beam
from apache_beam.options.pipeline_options import PipelineOptions
from apache_beam.io.gcp.bigquery import parse_table_schema_from_json
GC_PROJECT = 'my-proj'
BUCKET = 'test-bucket'
STAGING_BUCKET = '%s/test' % BUCKET
TEMP_BUCKET = '%s/test' % BUCKET
# RUNNER = 'DataflowRunner'
RUNNER = 'DirectRunner'
# pipeline_args = ['--save_main_session']
pipeline_args = []
pipeline_args.append('--project=%s' % GC_PROJECT)
pipeline_args.append('--runner=%s' % RUNNER)
pipeline_args.append('--staging_location=gs://%s' % STAGING_BUCKET)
pipeline_args.append('--temp_location=gs://%s' % TEMP_BUCKET)
BQ_DATASET = 'lake'
BQ_TABLE = 'whatever'
SCHEMA_OBJ = [
{"name": "id", "type": "STRING", "description": ""},
{"name": "value", "type": "STRING", "description": ""}
]
class ContactUploadOptions(PipelineOptions):
@classmethod
def _add_argparse_args(cls, parser):
parser.add_value_provider_argument(
'--infile',
type=str,
help='path of input file',
default='gs://%s/data_files/test.csv' % BUCKET)
def run(argv=None):
print('running')
p = beam.Pipeline(options=PipelineOptions(pipeline_args))
lines = (p
| beam.Create([
{"id": "some random name", "value": "i dont know"},
{"id": "id2", "value": "whatever man"}]))
schema_str = '{"fields": ' + json.dumps(SCHEMA_OBJ) + '}'
schema = parse_table_schema_from_json(schema_str)
output_destination = '%s.%s' % (BQ_DATASET, BQ_TABLE)
(lines
| 'Write lines to BigQuery' >> beam.io.WriteToBigQuery(
output_destination,
schema=schema,
create_disposition=beam.io.BigQueryDisposition.CREATE_IF_NEEDED,
write_disposition=beam.io.BigQueryDisposition.WRITE_APPEND))
p.run().wait_until_finish()
if __name__ == '__main__':
run(pipeline_args)
Also, if someone could link some sdk documentaion/resources that explain how/why the staging instructions above are supposed to work, that would be awesome!
