smaheshwar-pltr commented on code in PR #2031:
URL: https://github.com/apache/iceberg-python/pull/2031#discussion_r2102729622
##########
pyiceberg/table/__init__.py:
##########
@@ -1688,102 +1888,252 @@ def _match_deletes_to_data_file(data_entry:
ManifestEntry, positional_delete_ent
return set()
-class DataScan(TableScan):
- def _build_partition_projection(self, spec_id: int) -> BooleanExpression:
- project = inclusive_projection(self.table_metadata.schema(),
self.table_metadata.specs()[spec_id], self.case_sensitive)
- return project(self.row_filter)
+class DataScan(FileBasedScan, TableScan):
+ """A scan of a table's data.
- @cached_property
+ Args:
+ row_filter:
+ A string or BooleanExpression that describes the
+ desired rows
+ selected_fields:
+ A tuple of strings representing the column names
+ to return in the output dataframe.
+ case_sensitive:
+ If True column matching is case sensitive
+ snapshot_id:
+ Optional Snapshot ID to time travel to. If None,
+ scans the table as of the current snapshot ID.
+ options:
+ Additional Table properties as a dictionary of
+ string key value pairs to use for this scan.
+ limit:
+ An integer representing the number of rows to
+ return in the scan result. If None, fetches all
+ matching rows.
+ """
+
+ def plan_files(self) -> Iterable[FileScanTask]:
+ """Plans the relevant files by filtering on the PartitionSpecs.
+
+ Returns:
+ List of FileScanTasks that contain both data and delete files.
+ """
+ snapshot = self.snapshot()
+ if not snapshot:
+ return iter([])
+
+ return
self._manifest_group_planner.plan_files(manifests=snapshot.manifests(self.io))
+
+ # TODO: Document motivation and un-caching
+ @property
Review Comment:
This was previously a `cached_property` but now that
`_manifest_group_planner` is cached, it can just be a property.
--
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
