Fokko commented on code in PR #1958:
URL: https://github.com/apache/iceberg-python/pull/1958#discussion_r2093644910
##########
pyiceberg/table/inspect.py:
##########
@@ -657,3 +665,62 @@ 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 all_known_files(self) -> dict[str, set[str]]:
+ """Get all the known files in the table.
+
+ Returns:
+ dict of {file_type: set of file paths} for each file type.
+ """
+ snapshots = self.tbl.snapshots()
+
+ _all_known_files = {}
+ _all_known_files["manifests"] =
set(self.all_manifests(snapshots)["path"].to_pylist())
+ _all_known_files["manifest_lists"] = {snapshot.manifest_list for
snapshot in snapshots}
+ _all_known_files["statistics"] = {statistic.statistics_path for
statistic in self.tbl.metadata.statistics}
+
+ executor = ExecutorFactory.get_or_create()
+ snapshot_ids = [snapshot.snapshot_id for snapshot in snapshots]
+ files_by_snapshots: Iterator[Set[str]] = executor.map(
+ lambda snapshot_id:
set(self.files(snapshot_id)["file_path"].to_pylist()), snapshot_ids
+ )
+ _all_known_files["datafiles"] = reduce(set.union, files_by_snapshots,
set())
+
+ return _all_known_files
+
+ def orphaned_files(self, location: str, older_than: Optional[timedelta] =
timedelta(days=3)) -> Set[str]:
Review Comment:
Yes :) The less we expose publicly, the easier it is to evolve the API in
the future (otherwise we have to go through a deprecation cycle).
--
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
