This is an automated email from the ASF dual-hosted git repository.
ruifengz pushed a commit to branch master
in repository https://gitbox.apache.org/repos/asf/spark.git
The following commit(s) were added to refs/heads/master by this push:
new ebf4dd1889f3 [MINOR][PYTHON][TESTS] Use different temp table name in
foreachBatch tests
ebf4dd1889f3 is described below
commit ebf4dd1889f3404e856723f66851af48751b469f
Author: Hyukjin Kwon <gurwls...@apache.org>
AuthorDate: Wed Aug 13 12:24:30 2025 +0800
[MINOR][PYTHON][TESTS] Use different temp table name in foreachBatch tests
### What changes were proposed in this pull request?
This PR proposes to use different temp table name in foreachBatch tests.
### Why are the changes needed?
I think it fixes
https://github.com/apache/spark/actions/runs/16920826594/job/47946275434 . The
same names affect the test when they are async executed.
### Does this PR introduce _any_ user-facing change?
No, test-only.
### How was this patch tested?
Manually.
### Was this patch authored or co-authored using generative AI tooling?
No.
Closes #52002 from HyukjinKwon/minor-diff-table-name.
Authored-by: Hyukjin Kwon <gurwls...@apache.org>
Signed-off-by: Ruifeng Zheng <ruife...@apache.org>
---
.../sql/tests/streaming/test_streaming_foreach_batch.py | 12 ++++++------
1 file changed, 6 insertions(+), 6 deletions(-)
diff --git a/python/pyspark/sql/tests/streaming/test_streaming_foreach_batch.py
b/python/pyspark/sql/tests/streaming/test_streaming_foreach_batch.py
index 2ff95fb9c154..380f089d6a55 100644
--- a/python/pyspark/sql/tests/streaming/test_streaming_foreach_batch.py
+++ b/python/pyspark/sql/tests/streaming/test_streaming_foreach_batch.py
@@ -29,18 +29,18 @@ class StreamingTestsForeachBatchMixin:
q = None
def collectBatch(batch_df, batch_id):
- batch_df.write.format("parquet").saveAsTable("test_table")
+ batch_df.write.format("parquet").saveAsTable("test_table1")
try:
df =
self.spark.readStream.format("text").load("python/test_support/sql/streaming")
q = df.writeStream.foreachBatch(collectBatch).start()
q.processAllAvailable()
- collected = self.spark.sql("select * from test_table").collect()
+ collected = self.spark.sql("select * from test_table1").collect()
self.assertTrue(len(collected), 2)
finally:
if q:
q.stop()
- self.spark.sql("DROP TABLE IF EXISTS test_table")
+ self.spark.sql("DROP TABLE IF EXISTS test_table1")
def test_streaming_foreach_batch_tempview(self):
q = None
@@ -52,18 +52,18 @@ class StreamingTestsForeachBatchMixin:
# streaming query
assert len(batch_df.sparkSession.sql("SELECT * FROM
updates").collect()) == 2
# Write a table to verify on the repl/client side.
- batch_df.write.format("parquet").saveAsTable("test_table")
+ batch_df.write.format("parquet").saveAsTable("test_table2")
try:
df =
self.spark.readStream.format("text").load("python/test_support/sql/streaming")
q = df.writeStream.foreachBatch(collectBatch).start()
q.processAllAvailable()
- collected = self.spark.sql("SELECT * FROM test_table").collect()
+ collected = self.spark.sql("SELECT * FROM test_table2").collect()
self.assertTrue(len(collected[0]), 2)
finally:
if q:
q.stop()
- self.spark.sql("DROP TABLE IF EXISTS test_table")
+ self.spark.sql("DROP TABLE IF EXISTS test_table2")
def test_streaming_foreach_batch_propagates_python_errors(self):
from pyspark.errors import StreamingQueryException
---------------------------------------------------------------------
To unsubscribe, e-mail: commits-unsubscr...@spark.apache.org
For additional commands, e-mail: commits-h...@spark.apache.org
