Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Fix error when create external table using table resource #17998

Merged
merged 7 commits into from
Sep 13, 2021
Merged

Fix error when create external table using table resource #17998

Changes from 4 commits
Commits
Show all changes
7 commits
Select commit Hold shift + click to select a range
7f2c5e7
Fix error when create external table
tnyz Sep 2, 2021
985269e
Update bigquery.py
tnyz Sep 7, 2021
2ccf1be
Update bigquery.py
tnyz Sep 7, 2021
3af651f
Update bigquery.py
tnyz Sep 7, 2021
2ae0ded
Update bigquery.py
tnyz Sep 8, 2021
9f4ce24
Update bigquery.py
tnyz Sep 8, 2021
c9a98fd
fix import
tnyz Sep 12, 2021
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
56 changes: 23 additions & 33 deletions airflow/providers/google/cloud/operators/bigquery.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -1119,7 +1119,6 @@ def __init__(
# BQ config
kwargs_passed = any(
[
destination_project_dataset_table,
Copy link
Member

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

I believe this should be restored now

Copy link
Contributor Author

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

good call

schema_fields,
source_format,
compression,
Expand Down Expand Up @@ -1184,6 +1183,11 @@ def execute(self, context) -> None:
location=self.location,
impersonation_chain=self.impersonation_chain,
)
if self.table_resource:
bq_hook.create_empty_table(
table_resource=self.table_resource,
)
return

if not self.schema_fields and self.schema_object and self.source_format != 'DATASTORE_BACKUP':
gcs_hook = GCSHook(
Expand All @@ -1195,36 +1199,24 @@ def execute(self, context) -> None:
else:
schema_fields = self.schema_fields

if schema_fields and self.table_resource:
self.table_resource["externalDataConfiguration"]["schema"] = schema_fields
Copy link
Member

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

Does removing this logic break backward compatibility?

Copy link
Contributor Author

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

Considering it was incorrectly introduced and table creation via table resource is not properly supported, I don't think this will break backwards compatibility

Copy link
Member

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

Agree.


if self.table_resource:
tab_ref = TableReference.from_string(self.destination_project_dataset_table)
bq_hook.create_empty_table(
table_resource=self.table_resource,
project_id=tab_ref.project,
table_id=tab_ref.table_id,
dataset_id=tab_ref.dataset_id,
)
else:
source_uris = [f"gs://{self.bucket}/{source_object}" for source_object in self.source_objects]

bq_hook.create_external_table(
external_project_dataset_table=self.destination_project_dataset_table,
schema_fields=schema_fields,
source_uris=source_uris,
source_format=self.source_format,
compression=self.compression,
skip_leading_rows=self.skip_leading_rows,
field_delimiter=self.field_delimiter,
max_bad_records=self.max_bad_records,
quote_character=self.quote_character,
allow_quoted_newlines=self.allow_quoted_newlines,
allow_jagged_rows=self.allow_jagged_rows,
src_fmt_configs=self.src_fmt_configs,
labels=self.labels,
encryption_configuration=self.encryption_configuration,
)
source_uris = [f"gs://{self.bucket}/{source_object}" for source_object in self.source_objects]

bq_hook.create_external_table(
external_project_dataset_table=self.destination_project_dataset_table,
schema_fields=schema_fields,
source_uris=source_uris,
source_format=self.source_format,
compression=self.compression,
skip_leading_rows=self.skip_leading_rows,
field_delimiter=self.field_delimiter,
max_bad_records=self.max_bad_records,
quote_character=self.quote_character,
allow_quoted_newlines=self.allow_quoted_newlines,
allow_jagged_rows=self.allow_jagged_rows,
src_fmt_configs=self.src_fmt_configs,
labels=self.labels,
encryption_configuration=self.encryption_configuration,
)


class BigQueryDeleteDatasetOperator(BaseOperator):
Expand Down Expand Up @@ -1492,7 +1484,6 @@ def __init__(
impersonation_chain: Optional[Union[str, Sequence[str]]] = None,
**kwargs,
) -> None:

self.dataset_id = dataset_id
self.project_id = project_id
self.gcp_conn_id = gcp_conn_id
Expand Down Expand Up @@ -1641,7 +1632,6 @@ def __init__(
impersonation_chain: Optional[Union[str, Sequence[str]]] = None,
**kwargs,
) -> None:

warnings.warn(
"This operator is deprecated. Please use BigQueryUpdateDatasetOperator.",
DeprecationWarning,
Expand Down