This is an automated email from the ASF dual-hosted git repository.
pabloem 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 7962018 [BEAM-11705] Fixing ignore_insert_id implementation
new 9e18310 Merge pull request #13827 from [BEAM-11705] Fixing
ignore_insert_id implementation
7962018 is described below
commit 7962018bfffb07d51f324c666bd4169347f02dfa
Author: Pablo Estrada <pabl...@apache.org>
AuthorDate: Thu Jan 28 11:39:37 2021 -0800
[BEAM-11705] Fixing ignore_insert_id implementation
---
sdks/python/apache_beam/io/gcp/bigquery.py | 5 ++---
1 file changed, 2 insertions(+), 3 deletions(-)
diff --git a/sdks/python/apache_beam/io/gcp/bigquery.py
b/sdks/python/apache_beam/io/gcp/bigquery.py
index 3875c79..a1ce2b1 100644
--- a/sdks/python/apache_beam/io/gcp/bigquery.py
+++ b/sdks/python/apache_beam/io/gcp/bigquery.py
@@ -1297,7 +1297,7 @@ class BigQueryWriteFn(DoFn):
rows = [r[0] for r in rows_and_insert_ids]
if self.ignore_insert_ids:
- insert_ids = None
+ insert_ids = [None for r in rows_and_insert_ids]
else:
insert_ids = [r[1] for r in rows_and_insert_ids]
@@ -1419,8 +1419,7 @@ class _StreamToBigQuery(PTransform):
| 'AddInsertIdsWithRandomKeys' >> beam.ParDo(
_StreamToBigQuery.InsertIdPrefixFn()))
- if not self.ignore_insert_ids:
- sharded_data = (sharded_data | 'CommitInsertIds' >> ReshufflePerKey())
+ sharded_data = (sharded_data | 'CommitInsertIds' >> ReshufflePerKey())
return (
sharded_data
