ebyhr commented on code in PR #3603:
URL: https://github.com/apache/iceberg-python/pull/3603#discussion_r3525693714
##########
tests/table/test_inspect.py:
##########
@@ -68,3 +72,26 @@ def
test_inspect_entries_and_files_render_null_bound(catalog: InMemoryCatalog) -
files_metrics = tbl.inspect.files().to_pydict()["readable_metrics"][0]["s"]
assert files_metrics["lower_bound"] is None
assert files_metrics["upper_bound"] is None
+
+
[email protected]("newest_first", [False, True])
+def
test_partitions_last_updated_uses_latest_snapshot_regardless_of_order(newest_first:
bool) -> None:
+ # Manifest entries are visited in manifest order, which is not
chronological, so the
+ # `partitions` metadata table must keep the snapshot with the highest
commit timestamp
+ # per partition regardless of the order in which the entries are
aggregated.
+ older = Snapshot(snapshot_id=6446744073709551000, timestamp_ms=1000,
manifest_list="file:///dev/null")
+ newer = Snapshot(snapshot_id=8446744073709551111, timestamp_ms=5000,
manifest_list="file:///dev/null")
+
+ def _data_file() -> DataFile:
+ file = DataFile.from_args(content=DataFileContent.DATA,
record_count=1, file_size_in_bytes=1, partition=Record("a"))
+ file.spec_id = 0
+ return file
Review Comment:
nit: A single shared instance without the inner `_data_file()` works fine
here:
```py
data_file = DataFile.from_args(content=DataFileContent.DATA,
record_count=1, file_size_in_bytes=1, partition=Record("a"))
data_file.spec_id = 0
```
--
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]
