def process_response_rows_for_bigquery(self, rows: list,
table_reference: TableReference):
rows_dataframe = DataFrame.from_records(rows)
rows_dataframe = concat(
[rows_dataframe, rows_dataframe['dimensions'].apply(Series)],
axis=1,
join='inner')
rows_dataframe = rows_dataframe.drop(['dimensions'], axis=1)
rows_dataframe['date'] = rows_dataframe['date'].apply(
lambda x: x.date())
job_config = LoadJobConfig()
job_config.write_disposition = WriteDisposition.WRITE_APPEND
job_config.time_partitioning = TimePartitioning(
type_=TimePartitioningType.DAY, field='date')
job_config.schema = [
self._get_schema_for_field(column)
for column in list(rows_dataframe.columns.values)
]
try:
load_job = self.bigquery.client.load_table_from_dataframe(
rows_dataframe, table_reference, job_config=job_config)
load_job.result()
except BadRequest as error:
print(error.errors)
def _load_to_bq(self, client, dataset, table_name, table_schema,
table_config, key_props, metadata_columns, truncate, rows):
logger = self.logger
partition_field = table_config.get("partition_field", None)
cluster_fields = table_config.get("cluster_fields", None)
force_fields = table_config.get("force_fields", {})
schema = build_schema(table_schema,
key_properties=key_props,
add_metadata=metadata_columns,
force_fields=force_fields)
load_config = LoadJobConfig()
load_config.ignore_unknown_values = True
load_config.schema = schema
if partition_field:
load_config.time_partitioning = bigquery.table.TimePartitioning(
type_=bigquery.table.TimePartitioningType.DAY,
field=partition_field)
if cluster_fields:
load_config.clustering_fields = cluster_fields
load_config.source_format = SourceFormat.NEWLINE_DELIMITED_JSON
if truncate:
logger.info(f"Load {table_name} by FULL_TABLE (truncate)")
load_config.write_disposition = WriteDisposition.WRITE_TRUNCATE
else:
logger.info(f"Appending to {table_name}")
load_config.write_disposition = WriteDisposition.WRITE_APPEND
logger.info("loading {} to BigQuery".format(table_name))
load_job = None
try:
load_job = client.load_table_from_file(rows,
dataset.table(table_name),
job_config=load_config,
rewind=True)
logger.info("loading job {}".format(load_job.job_id))
job = load_job.result()
logger.info(job._properties)
return job
except google_exceptions.BadRequest as err:
logger.error("failed to load table {} from file: {}".format(
table_name, str(err)))
if load_job and load_job.errors:
reason = err.errors[0]["reason"]
messages = [f"{err['message']}" for err in load_job.errors]
logger.error("reason: {reason}, errors:\n{e}".format(
reason=reason, e="\n".join(messages)))
err.message = f"reason: {reason}, errors: {';'.join(messages)}"
raise err
def _process_data_for_bigquery(self, data: DataFrame,
output_tablereference: TableReference):
job_config = LoadJobConfig()
job_config.write_disposition = WriteDisposition.WRITE_APPEND
job_config.time_partitioning = TimePartitioning(
type_=TimePartitioningType.DAY, field='date')
try:
load_job = self.bigquery.client.load_table_from_dataframe(
data, output_tablereference, job_config=job_config)
load_job.result()
except BadRequest as error:
print(error.errors)