This is an automated email from the ASF dual-hosted git repository.
yhu pushed a commit to branch master
in repository https://gitbox.apache.org/repos/asf/beam.git
The following commit(s) were added to refs/heads/master by this push:
new e00a81f400c Allow JSON type in TableSchema for WriteToBigQuery with
FILE_LOAD method in Python SDK (#30340)
e00a81f400c is described below
commit e00a81f400c0dc3fd72d7de43605574bf2626d6b
Author: Edward Cui <[email protected]>
AuthorDate: Mon Feb 19 23:42:38 2024 -0500
Allow JSON type in TableSchema for WriteToBigQuery with FILE_LOAD method in
Python SDK (#30340)
* remove JSON type checking and raise error in WriteoToBigQuery with
FILE_LOADS method
* Changing to warning instead
* update warning message. Nw should be the same with Java sdk
* fix lie length
* fixing formatting
---
sdks/python/apache_beam/io/gcp/bigquery.py | 12 +++++-------
1 file changed, 5 insertions(+), 7 deletions(-)
diff --git a/sdks/python/apache_beam/io/gcp/bigquery.py
b/sdks/python/apache_beam/io/gcp/bigquery.py
index 7648ab4064d..ad9e31d5285 100644
--- a/sdks/python/apache_beam/io/gcp/bigquery.py
+++ b/sdks/python/apache_beam/io/gcp/bigquery.py
@@ -2178,13 +2178,11 @@ bigquery_v2_messages.TableSchema`. or a `ValueProvider`
that has a JSON string,
def find_in_nested_dict(schema):
for field in schema['fields']:
if field['type'] == 'JSON':
- raise ValueError(
- 'Found JSON type in table schema. JSON data '
- 'insertion is currently not supported with '
- 'FILE_LOADS write method. This is supported with '
- 'STREAMING_INSERTS. For more information: '
- 'https://cloud.google.com/bigquery/docs/reference/'
- 'standard-sql/json-data#ingest_json_data')
+ logging.warning(
+ 'Found JSON type in TableSchema for "File_LOADS" write '
+ 'method. Make sure the TableSchema field is a parsed '
+ 'JSON to ensure the read as a JSON type. Otherwise it '
+ 'will read as a raw (escaped) string.')
elif field['type'] == 'STRUCT':
find_in_nested_dict(field)
