derrickaw commented on code in PR #39052:
URL: https://github.com/apache/beam/pull/39052#discussion_r3462350237
##########
sdks/python/apache_beam/yaml/integration_tests.py:
##########
@@ -618,6 +621,26 @@ def temp_pubsub_emulator(project_id="apache-beam-testing"):
yield created_topic_object.name
[email protected]
+def temp_delta_table():
+ with tempfile.TemporaryDirectory() as temp_dir:
+ log_dir = os.path.join(temp_dir, "_delta_log")
+ os.makedirs(log_dir, exist_ok=True)
+ table_data = pa.table({"name": ["a", "b", "c"]})
+ parquet_path = os.path.join(temp_dir, "part-00000.parquet")
+ pq.write_table(table_data, parquet_path)
+ file_size = os.path.getsize(parquet_path)
+ commit_content = (
+ '{"protocol":{"minReaderVersion":1,"minWriterVersion":2}}\n'
+
'{"metaData":{"id":"test-id","format":{"provider":"parquet","options":{}},"schemaString":"{\\"type\\":\\"struct\\",\\"fields\\":[{\\"name\\":\\"name\\",\\"type\\":\\"string\\",\\"nullable\\":true,\\"metadata\\":{}}]}","partitionColumns":[],"configuration":{},"createdAt":123456789}}\n'
+
f'{{"add":{{"path":"part-00000.parquet","partitionValues":{{}},"size":{file_size},"modificationTime":123456789,"dataChange":true}}}}\n'
+ )
+ commit_file = os.path.join(log_dir, "00000000000000000000.json")
+ with open(commit_file, "w") as f:
Review Comment:
will update in next PR
##########
sdks/python/apache_beam/yaml/integration_tests.py:
##########
@@ -618,6 +621,26 @@ def temp_pubsub_emulator(project_id="apache-beam-testing"):
yield created_topic_object.name
[email protected]
+def temp_delta_table():
+ with tempfile.TemporaryDirectory() as temp_dir:
+ log_dir = os.path.join(temp_dir, "_delta_log")
+ os.makedirs(log_dir, exist_ok=True)
+ table_data = pa.table({"name": ["a", "b", "c"]})
+ parquet_path = os.path.join(temp_dir, "part-00000.parquet")
+ pq.write_table(table_data, parquet_path)
+ file_size = os.path.getsize(parquet_path)
+ commit_content = (
+ '{"protocol":{"minReaderVersion":1,"minWriterVersion":2}}\n'
+
'{"metaData":{"id":"test-id","format":{"provider":"parquet","options":{}},"schemaString":"{\\"type\\":\\"struct\\",\\"fields\\":[{\\"name\\":\\"name\\",\\"type\\":\\"string\\",\\"nullable\\":true,\\"metadata\\":{}}]}","partitionColumns":[],"configuration":{},"createdAt":123456789}}\n'
+
f'{{"add":{{"path":"part-00000.parquet","partitionValues":{{}},"size":{file_size},"modificationTime":123456789,"dataChange":true}}}}\n'
+ )
+ commit_file = os.path.join(log_dir, "00000000000000000000.json")
+ with open(commit_file, "w") as f:
+ f.write(commit_content)
Review Comment:
will update in next PR
--
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]
