def extract_on_complete(self, task_instance) -> [StepMetadata]:
log.debug(f"extract_on_complete({task_instance})")
context = self.parse_sql_context()
source = self._source()
try:
bigquery_job_id = self._get_xcom_bigquery_job_id(task_instance)
context['bigquery.job_id'] = bigquery_job_id
if bigquery_job_id is None:
raise Exception("Xcom could not resolve BigQuery job id." +
"Job may have failed.")
except Exception as e:
log.error(f"Cannot retrieve job details from BigQuery.Client. {e}",
exc_info=True)
context['bigquery.extractor.client_error'] = \
f"{e}: {traceback.format_exc()}"
return [StepMetadata(
name=get_job_name(task=self.operator),
context=context,
inputs=None,
outputs=None
)]
inputs = None
outputs = None
try:
client = bigquery.Client()
try:
job = client.get_job(job_id=bigquery_job_id)
job_properties_str = json.dumps(job._properties)
context['bigquery.job_properties'] = job_properties_str
inputs = self._get_input_from_bq(job, context, source, client)
outputs = self._get_output_from_bq(job, source, client)
finally:
# Ensure client has close() defined, otherwise ignore.
# NOTE: close() was introduced in python-bigquery v1.23.0
if hasattr(client, "close"):
client.close()
except Exception as e:
log.error(f"Cannot retrieve job details from BigQuery.Client. {e}",
exc_info=True)
context['bigquery.extractor.error'] = \
f"{e}: {traceback.format_exc()}"
return [StepMetadata(
name=get_job_name(task=self.operator),
inputs=inputs,
outputs=outputs,
context=context
)]
def extract_on_complete(self, task_instance) -> StepMetadata:
inputs = [
Dataset.from_table_schema(self.source, DbTableSchema(
schema_name='schema',
table_name=DbTableName('extract_on_complete_input1'),
columns=[DbColumn(
name='field1',
type='text',
description='',
ordinal_position=1
),
DbColumn(
name='field2',
type='text',
description='',
ordinal_position=2
)]
))
]
outputs = [
Dataset.from_table(self.source, "extract_on_complete_output1")
]
return StepMetadata(
name=get_job_name(task=self.operator),
inputs=inputs,
outputs=outputs,
context={
"extract_on_complete": "extract_on_complete"
}
)
def extract(self) -> [StepMetadata]:
inputs = [Dataset.from_table(self.source, "extract_input1")]
outputs = [Dataset.from_table(self.source, "extract_output1")]
return [
StepMetadata(name=get_job_name(task=self.operator),
inputs=inputs,
outputs=outputs,
context={"extract": "extract"})
]
def extract_on_complete(self, task_instance) -> Optional[StepMetadata]:
log.debug(f"extract_on_complete({task_instance})")
context = self.parse_sql_context()
try:
bigquery_job_id = self._get_xcom_bigquery_job_id(task_instance)
if bigquery_job_id is None:
raise Exception("Xcom could not resolve BigQuery job id." +
"Job may have failed.")
except Exception as e:
log.error(f"Cannot retrieve job details from BigQuery.Client. {e}",
exc_info=True)
return StepMetadata(
name=get_job_name(task=self.operator),
inputs=None,
outputs=None,
run_facets={
"bigQuery_error": BigQueryErrorRunFacet(
clientError=f"{e}: {traceback.format_exc()}",
parserError=context.parser_error
)
}
)
inputs = None
output = None
run_facets = {}
try:
client = bigquery.Client()
try:
job = client.get_job(job_id=bigquery_job_id)
props = job._properties
run_stat_facet, dataset_stat_facet = self._get_output_statistics(props)
run_facets.update({
"bigQuery_statistics": run_stat_facet
})
inputs = self._get_input_from_bq(props, client)
output = self._get_output_from_bq(props, client)
if output:
output.custom_facets.update({
"stats": dataset_stat_facet
})
finally:
# Ensure client has close() defined, otherwise ignore.
# NOTE: close() was introduced in python-bigquery v1.23.0
if hasattr(client, "close"):
client.close()
except Exception as e:
log.error(f"Cannot retrieve job details from BigQuery.Client. {e}",
exc_info=True)
run_facets.update({
"bigQuery_error": BigQueryErrorRunFacet(
clientError=f"{e}: {traceback.format_exc()}",
parserError=context.parser_error
)
})
return StepMetadata(
name=get_job_name(task=self.operator),
inputs=inputs,
outputs=[output] if output else [],
run_facets=run_facets
)
