jayceslesar commented on code in PR #1958:
URL: https://github.com/apache/iceberg-python/pull/1958#discussion_r2067532346
##########
pyiceberg/table/__init__.py:
##########
@@ -1371,6 +1375,45 @@ def to_polars(self) -> pl.LazyFrame:
return pl.scan_iceberg(self)
+ def delete_orphaned_files(self) -> None:
+ """Delete orphaned files in the table."""
+ 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
+
+ location = self.location()
+
+ all_known_files = []
+ snapshots = self.snapshots()
+ snapshot_ids = [snapshot.snapshot_id for snapshot in snapshots]
+ all_manifests_table = self.inspect.all_manifests(snapshots)
+ all_known_files.extend(all_manifests_table["path"].to_pylist())
+
+ executor = ExecutorFactory.get_or_create()
+ files_by_snapshots: Iterator["pa.Table"] = executor.map(lambda
snapshot_id: self.inspect.files(snapshot_id), snapshot_ids)
+
all_known_files.extend(pa.concat_tables(files_by_snapshots)["file_path"].to_pylist())
Review Comment:
this probably belongs in `inspect.py`...
--
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
