Skip to content

Fix/gr ndsp 658 too many open files in orph check #166

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Merged
stevenhsd merged 3 commits into from
Sep 29, 2026
Merged

Fix/gr ndsp 658 too many open files in orph check #166

Changes from all commits
Commits
Show all changes
3 commits
Select commit Hold shift + click to select a range
db63b1c
perf: only check for orphaned records on entities with at least one r…
georgeRobertson Sep 28, 2026
872972b
fix: add the ability to cache entities in duckdb to hopefully improve…
georgeRobertson Sep 28, 2026
78a261b
Revert "fix: add the ability to cache entities in duckdb to hopefully…
georgeRobertson Sep 29, 2026
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
17 changes: 11 additions & 6 deletions src/dve/core_engine/backends/implementations/duckdb/rules.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -29,6 +29,7 @@
duckdb_write_parquet,
get_all_registered_udfs,
get_duckdb_type_from_annotation,
relation_is_empty,
)
from dve.core_engine.backends.implementations.duckdb.types import (
DuckDBEntities,
Expand Down Expand Up @@ -396,6 +397,10 @@ def identify_orphans(
target_rel: DuckDBPyRelation = entities[config.target_name]
target_rel = target_rel.set_alias(config.target_name)

if relation_is_empty(source_rel):
self.logger.info(f"{config.entity_name} is empty. Skipping orphan check.")
return [], 0

match_name = f"matched_{uuid4().hex}"
target_rel = target_rel.select(
StarExpression(exclude=[]), ConstantExpression(1).alias(match_name)
Expand All @@ -420,16 +425,16 @@ def identify_orphans(
_orph_records: tuple[int] = orphaned_rel.count(RECORD_INDEX_COLUMN_NAME).fetchone() # type: ignore # pylint: disable=C0301
if _orph_records:
_no_orphans = _orph_records[0]
if entities.get(ORPHANED_RECORD_ENTITY_NAME) is not None:
entities[ORPHANED_RECORD_ENTITY_NAME] = entities[ORPHANED_RECORD_ENTITY_NAME].union(
orphaned_rel
)
else:
entities[ORPHANED_RECORD_ENTITY_NAME] = orphaned_rel
else:
_no_orphans = 0
self.logger.info(f"Found {_no_orphans} orphaned records in {config.entity_name}.")

if entities.get(ORPHANED_RECORD_ENTITY_NAME) is not None:
entities[ORPHANED_RECORD_ENTITY_NAME] = entities[ORPHANED_RECORD_ENTITY_NAME].union(
orphaned_rel
)
else:
entities[ORPHANED_RECORD_ENTITY_NAME] = orphaned_rel
return [], _no_orphans

def remove_orphans(self, entities: DuckDBEntities, *, config: OrphanRemoval) -> Iterator:
Expand Down
Loading