ahmedabu98 commented on code in PR #25325:
URL: https://github.com/apache/beam/pull/25325#discussion_r1097324853
##########
sdks/python/apache_beam/io/gcp/bigquery.py:
##########
@@ -405,6 +405,8 @@ def chain_after(result):
from apache_beam.utils.annotations import deprecated
from apache_beam.utils.annotations import experimental
+from google.api_core.exceptions import ClientError, GoogleAPICallError
Review Comment:
Current tests are failing with `ModuleNotFoundError: No module named
'google.api_core'`. This import should be in the try block on line 410
##########
sdks/python/apache_beam/io/gcp/bigquery.py:
##########
@@ -1551,17 +1553,23 @@ def _flush_batch(self, destination):
insert_ids = [None for r in rows_and_insert_ids]
else:
insert_ids = [r[1] for r in rows_and_insert_ids]
-
while True:
+ errors = []
+ passed = False
start = time.time()
- passed, errors = self.bigquery_wrapper.insert_rows(
- project_id=table_reference.projectId,
- dataset_id=table_reference.datasetId,
- table_id=table_reference.tableId,
- rows=rows,
- insert_ids=insert_ids,
- skip_invalid_rows=True,
- ignore_unknown_values=self.ignore_unknown_columns)
+ try:
+ passed, errors = self.bigquery_wrapper.insert_rows(
+ project_id=table_reference.projectId,
+ dataset_id=table_reference.datasetId,
+ table_id=table_reference.tableId,
+ rows=rows,
+ insert_ids=insert_ids,
+ skip_invalid_rows=True,
+ ignore_unknown_values=self.ignore_unknown_columns)
+ except (ClientError, GoogleAPICallError) as e:
+ if e.code == 404:
Review Comment:
Also maybe a comment here describing that sometimes a table can get deleted
in the middle of a streaming job.
##########
sdks/python/apache_beam/io/gcp/bigquery.py:
##########
@@ -1551,17 +1553,23 @@ def _flush_batch(self, destination):
insert_ids = [None for r in rows_and_insert_ids]
else:
insert_ids = [r[1] for r in rows_and_insert_ids]
-
while True:
+ errors = []
+ passed = False
start = time.time()
- passed, errors = self.bigquery_wrapper.insert_rows(
- project_id=table_reference.projectId,
- dataset_id=table_reference.datasetId,
- table_id=table_reference.tableId,
- rows=rows,
- insert_ids=insert_ids,
- skip_invalid_rows=True,
- ignore_unknown_values=self.ignore_unknown_columns)
+ try:
+ passed, errors = self.bigquery_wrapper.insert_rows(
+ project_id=table_reference.projectId,
+ dataset_id=table_reference.datasetId,
+ table_id=table_reference.tableId,
+ rows=rows,
+ insert_ids=insert_ids,
+ skip_invalid_rows=True,
+ ignore_unknown_values=self.ignore_unknown_columns)
+ except (ClientError, GoogleAPICallError) as e:
+ if e.code == 404:
Review Comment:
Can you also add a helpful log message here explaining that the previously
seen destination X no longer exists, so it will be removed from local cache and
bundle will retry.
##########
sdks/python/apache_beam/io/gcp/bigquery.py:
##########
@@ -1551,17 +1553,23 @@ def _flush_batch(self, destination):
insert_ids = [None for r in rows_and_insert_ids]
else:
insert_ids = [r[1] for r in rows_and_insert_ids]
-
while True:
+ errors = []
+ passed = False
start = time.time()
- passed, errors = self.bigquery_wrapper.insert_rows(
- project_id=table_reference.projectId,
- dataset_id=table_reference.datasetId,
- table_id=table_reference.tableId,
- rows=rows,
- insert_ids=insert_ids,
- skip_invalid_rows=True,
- ignore_unknown_values=self.ignore_unknown_columns)
+ try:
+ passed, errors = self.bigquery_wrapper.insert_rows(
+ project_id=table_reference.projectId,
+ dataset_id=table_reference.datasetId,
+ table_id=table_reference.tableId,
+ rows=rows,
+ insert_ids=insert_ids,
+ skip_invalid_rows=True,
+ ignore_unknown_values=self.ignore_unknown_columns)
+ except (ClientError, GoogleAPICallError) as e:
+ if e.code == 404:
Review Comment:
```suggestion
if e.code == 404 and destination in _KNOWN_TABLES:
```
--
This is an automated message from the Apache Git Service.
To respond to the message, please log on to GitHub and use the
URL above to go to the specific comment.
To unsubscribe, e-mail: [email protected]
For queries about this service, please contact Infrastructure at:
[email protected]
