kevinjqliu commented on code in PR #3953:
URL: https://github.com/apache/iceberg-python/pull/3953#discussion_r3997415323
##########
tests/avro/test_file.py:
##########
@@ -225,12 +226,44 @@ def
test_write_manifest_entry_with_iceberg_read_with_fastavro_v2() -> None:
fa_entry = next(it)
v2_entry = todict(entry)
- for field in ("first_row_id", "referenced_data_file",
"content_offset", "content_size_in_bytes"):
+ for field in ("first_row_id", "content_offset",
"content_size_in_bytes"):
del v2_entry["data_file"][field]
assert v2_entry == fa_entry
+def test_write_v2_referenced_data_file_with_fastavro() -> None:
+ referenced_data_file = "s3://some-path/data-file.parquet"
+ entry = ManifestEntry.from_args(
+ status=ManifestEntryStatus.ADDED,
+ snapshot_id=25,
+ data_file=DataFile.from_args(
+ content=DataFileContent.POSITION_DELETES,
+ file_path="s3://some-path/delete-file.parquet",
+ file_format=FileFormat.PARQUET,
+ partition=Record(),
+ record_count=3,
+ file_size_in_bytes=47,
+ referenced_data_file=referenced_data_file,
+ ),
+ )
+
+ with TemporaryDirectory() as tmpdir:
+ tmp_avro_file = tmpdir + "/manifest_entry.avro"
+ with avro.AvroOutputFile[ManifestEntry](
+ output_file=PyArrowFileIO().new_output(tmp_avro_file),
+ file_schema=MANIFEST_ENTRY_SCHEMAS[2],
+ record_schema=MANIFEST_ENTRY_SCHEMAS[3],
Review Comment:
Tracking in #3957
--
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]
---------------------------------------------------------------------
To unsubscribe, e-mail: [email protected]
For additional commands, e-mail: [email protected]
