You are viewing a plain text version of this content. The canonical link for it is here.
Posted to github@beam.apache.org by "BjornPrime (via GitHub)" <gi...@apache.org> on 2023/08/30 16:54:14 UTC
[GitHub] [beam] BjornPrime commented on a diff in pull request #28185: Integration tests for GCSFileSystem
BjornPrime commented on code in PR #28185:
URL: https://github.com/apache/beam/pull/28185#discussion_r1310567956
##########
sdks/python/apache_beam/io/gcp/gcsfilesystem_integration_test.py:
##########
@@ -0,0 +1,139 @@
+#
+# Licensed to the Apache Software Foundation (ASF) under one or more
+# contributor license agreements. See the NOTICE file distributed with
+# this work for additional information regarding copyright ownership.
+# The ASF licenses this file to You under the Apache License, Version 2.0
+# (the "License"); you may not use this file except in compliance with
+# the License. You may obtain a copy of the License at
+#
+# http://www.apache.org/licenses/LICENSE-2.0
+#
+# Unless required by applicable law or agreed to in writing, software
+# distributed under the License is distributed on an "AS IS" BASIS,
+# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
+# See the License for the specific language governing permissions and
+# limitations under the License.
+#
+
+"""Integration tests for gcsfilesystem module.
+
+Runs tests against Google Cloud Storage service.
+Instantiates a TestPipeline to get options such as GCP project name, but
+doesn't actually start a Beam pipeline or test any specific runner.
+
+To run these tests manually:
+ ./gradlew :sdks:python:test-suites:dataflow:integrationTest \
+ -Dtests=apache_beam.io.gcp.gcsfilesystem_integration_test:GcsFileSystemIntegrationTest # pylint: disable=line-too-long
+"""
+
+# pytype: skip-file
+
+import logging
+import unittest
+import uuid
+
+import pytest
+
+from apache_beam.io.filesystem import BeamIOError
+from apache_beam.io.filesystems import FileSystems
+from apache_beam.testing.test_pipeline import TestPipeline
+
+try:
+ from apache_beam.io.gcp.gcsfilesystem import GCSFileSystem
+ fs_not_available = False
+except ImportError:
+ fs_not_available = True # type: ignore
+
+
+@unittest.skipIf(fs_not_available, 'GCP dependencies are not installed')
+class GcsFileSystemIntegrationTest(unittest.TestCase):
+
+ INPUT_FILE = 'gs://dataflow-samples/shakespeare/kinglear.txt'
+ # Larger than 1MB to test maxBytesRewrittenPerCall.
+ # Also needs to be in a different region than the dest to take effect.
+ INPUT_FILE_LARGE = 'gs://apache-beam-samples-us-east1/wikipedia_edits/wiki_data-000000000000.json' # pylint: disable=line-too-long
+
+ def setUp(self):
+ self.test_pipeline = TestPipeline(is_integration_test=True)
+ self.runner_name = type(self.test_pipeline.runner).__name__
+ if self.runner_name != 'TestDataflowRunner':
Review Comment:
I will keep that in mind for the future. I was just following gcsio_integration_test's lead here.
--
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: github-unsubscribe@beam.apache.org
For queries about this service, please contact Infrastructure at:
users@infra.apache.org