lawofcycles commented on code in PR #3320:
URL: https://github.com/apache/iceberg-python/pull/3320#discussion_r3605756850
##########
pyiceberg/table/update/snapshot.py:
##########
@@ -353,11 +397,116 @@ def new_manifest_output(self) -> OutputFile:
location_provider = self._transaction._table.location_provider()
file_name =
_new_manifest_file_name(num=next(self._manifest_num_counter),
commit_uuid=self.commit_uuid)
file_path = location_provider.new_metadata_location(file_name)
+ self._written_manifests.append(file_path)
return self._io.new_output(file_path)
def fetch_manifest_entry(self, manifest: ManifestFile, discard_deleted:
bool = True) -> list[ManifestEntry]:
return manifest.fetch_manifest_entry(io=self._io,
discard_deleted=discard_deleted)
+ def commit(self) -> None:
+ self._transaction._register_snapshot_producer(self)
+ super().commit()
+
+ def _cleanup_uncommitted(self) -> None:
+ """Delete manifest files and manifest lists from failed retry
attempts."""
+ for path in self._uncommitted_manifests:
+ try:
+ self._io.delete(path)
+ except Exception:
+ logger.warning("Failed to delete uncommitted manifest: %s",
path, exc_info=True)
+ self._uncommitted_manifests.clear()
+ # Delete all manifest lists except the last one (which the committed
snapshot references)
+ if len(self._written_manifest_lists) > 1:
+ for path in self._written_manifest_lists[:-1]:
+ try:
+ self._io.delete(path)
+ except Exception:
+ logger.warning("Failed to delete uncommitted manifest
list: %s", path, exc_info=True)
+ self._written_manifest_lists = self._written_manifest_lists[-1:]
+
+ def _clean_all_uncommitted(self) -> None:
+ """Clean up all manifests and manifest lists on abort."""
+ for path in itertools.chain(self._uncommitted_manifests,
self._written_manifests):
+ try:
+ self._io.delete(path)
+ except Exception:
+ logger.warning("Failed to delete uncommitted manifest: %s",
path, exc_info=True)
+ for path in self._written_manifest_lists:
+ try:
+ self._io.delete(path)
+ except Exception:
+ logger.warning("Failed to delete uncommitted manifest list:
%s", path, exc_info=True)
+ self._uncommitted_manifests.clear()
+ self._written_manifests.clear()
+ self._written_manifest_lists.clear()
+
+ def _refresh_for_retry(self) -> None:
+ """Reset state for a retry attempt with refreshed metadata."""
+ self._uncommitted_manifests.extend(self._written_manifests)
+ self._written_manifests.clear()
+ self._parent_snapshot_id = (
+ snapshot.snapshot_id if (snapshot :=
self._transaction.table_metadata.snapshot_by_name(self._target_branch)) else
None
+ )
+ self._snapshot_id = self._transaction.table_metadata.new_snapshot_id()
+ self._manifest_num_counter = itertools.count(0)
+ self.commit_uuid = uuid.uuid4()
+
+ def _validate_concurrency(self) -> None:
+ """Validate that concurrent changes do not conflict with this
operation.
+
+ Uses the CommitWindow to determine which catalog commits to validate
against.
+ The window spans from base (when the operation began) to head (latest
branch
+ HEAD), covering all external concurrent commits.
+
+ Subclasses that do not require validation (e.g. fast append) should
override
+ with a no-op.
+ """
+ from pyiceberg.table import TableProperties
+ from pyiceberg.table.snapshots import IsolationLevel
+ from pyiceberg.table.update.validate import (
+ _validate_added_data_files,
+ _validate_deleted_data_files,
+ _validate_no_new_delete_files,
+ _validate_no_new_deletes_for_data_files,
+ )
+
+ if self._commit_window is None or self._commit_window.is_empty():
+ return
+
+ catalog_head = self._commit_window.head
+ starting_snapshot = self._commit_window.base
+
+ if catalog_head is None or starting_snapshot is None:
+ return
+
+ table = self._transaction._table
+ isolation_level_str = table.metadata.properties.get(
+ self._isolation_level_property,
TableProperties.WRITE_ISOLATION_LEVEL_DEFAULT
+ )
+ isolation_level = IsolationLevel(isolation_level_str)
+ conflict_detection_filter = self._predicate if self._predicate !=
AlwaysFalse() else None
+
+ if isolation_level == IsolationLevel.SERIALIZABLE:
+ _validate_added_data_files(table, catalog_head,
conflict_detection_filter, starting_snapshot)
+
+ if conflict_detection_filter is not None:
+ _validate_no_new_delete_files(table, catalog_head,
conflict_detection_filter, None, starting_snapshot)
+ _validate_deleted_data_files(table, catalog_head,
conflict_detection_filter, starting_snapshot)
+
+ if self._deleted_data_files:
+ _validate_no_new_deletes_for_data_files(
+ table, catalog_head, conflict_detection_filter,
self._deleted_data_files, starting_snapshot
+ )
+
+ def _resolve_parent_snapshot(self) -> Snapshot | None:
Review Comment:
Fixed!
--
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]
