jayceslesar commented on code in PR #1958:
URL: https://github.com/apache/iceberg-python/pull/1958#discussion_r2072445679
##########
pyiceberg/table/inspect.py:
##########
@@ -657,3 +665,37 @@ def all_manifests(self) -> "pa.Table":
lambda args: self._generate_manifests_table(*args), [(snapshot,
True) for snapshot in snapshots]
)
return pa.concat_tables(manifests_by_snapshots)
+
+ def orphaned_files(self, location: str, older_than: Optional[timedelta] =
timedelta(days=3)) -> Set[str]:
+ try:
+ import pyarrow as pa # noqa: F401
+ except ModuleNotFoundError as e:
+ raise ModuleNotFoundError("For deleting orphaned files PyArrow
needs to be installed") from e
+
+ from pyarrow.fs import FileSelector, FileType
+
+ from pyiceberg.io.pyarrow import _fs_from_file_path
+
+ all_known_files = set()
Review Comment:
I see! I just pushed a change that will capture those, as well as the
statistic file paths
--
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: issues-unsubscr...@iceberg.apache.org
For queries about this service, please contact Infrastructure at:
us...@infra.apache.org
---------------------------------------------------------------------
To unsubscribe, e-mail: issues-unsubscr...@iceberg.apache.org
For additional commands, e-mail: issues-h...@iceberg.apache.org
