Rename cleanup_temp_tables to cleanup_tables in warehouse and catalog (#218)

Author: amritghimire

src/datachain/catalog/catalog.py

@@ -1217,16 +1217,14 @@ def remove_dataset_version(
     def get_temp_table_names(self) -> list[str]:
         return self.warehouse.get_temp_table_names()
 
-    def cleanup_temp_tables(self, names: Iterable[str]) -> None:
+    def cleanup_tables(self, names: Iterable[str]) -> None:
         """
-        Drop tables created temporarily when processing datasets.
+        Drop tables passed.
 
-        This should be implemented even if temporary tables are used to
-        ensure that they are cleaned up as soon as they are no longer
-        needed. When running the same `DatasetQuery` multiple times we
-        may use the same temporary table names.
+        This should be implemented to ensure that the provided tables
+        are cleaned up as soon as they are no longer needed.
         """
-        self.warehouse.cleanup_temp_tables(names)
+        self.warehouse.cleanup_tables(names)
         self.id_generator.delete_uris(names)
 
     def create_dataset_from_sources(

src/datachain/cli.py

@@ -910,7 +910,7 @@ def garbage_collect(catalog: "Catalog"):
         print("Nothing to clean up.")
     else:
         print(f"Garbage collecting {len(temp_tables)} tables.")
-        catalog.cleanup_temp_tables(temp_tables)
+        catalog.cleanup_tables(temp_tables)
 
 
 def completion(shell: str) -> str:

src/datachain/data_storage/metastore.py

@@ -97,7 +97,7 @@ def init(self, uri: StorageURI) -> None:
     def close(self) -> None:
         """Closes any active database or HTTP connections."""
 
-    def cleanup_temp_tables(self, temp_table_names: list[str]) -> None:
+    def cleanup_tables(self, temp_table_names: list[str]) -> None:
         """Cleanup temp tables."""
 
     def cleanup_for_tests(self) -> None:
@@ -457,7 +457,7 @@ def close(self) -> None:
         """Closes any active database connections."""
         self.db.close()
 
-    def cleanup_temp_tables(self, temp_table_names: list[str]) -> None:
+    def cleanup_tables(self, temp_table_names: list[str]) -> None:
         """Cleanup temp tables."""
         self.id_generator.delete_uris(temp_table_names)
 

src/datachain/data_storage/warehouse.py

@@ -915,14 +915,12 @@ def get_temp_table_names(self) -> list[str]:
             if self.is_temp_table_name(t)
         ]
 
-    def cleanup_temp_tables(self, names: Iterable[str]) -> None:
+    def cleanup_tables(self, names: Iterable[str]) -> None:
         """
-        Drop tables created temporarily when processing datasets.
+        Drop tables passed.
 
-        This should be implemented even if temporary tables are used to
-        ensure that they are cleaned up as soon as they are no longer
-        needed. When running the same `DatasetQuery` multiple times we
-        may use the same temporary table names.
+        This should be implemented to ensure that the provided tables
+        are cleaned up as soon as they are no longer needed.
         """
         for name in names:
             self.db.drop_table(Table(name, self.db.metadata), if_exists=True)

src/datachain/query/dataset.py

@@ -1201,10 +1201,10 @@ def cleanup(self) -> None:
         # implementations, as errors may close or render unusable the existing
         # connections.
         metastore = self.catalog.metastore.clone(use_new_connection=True)
-        metastore.cleanup_temp_tables(self.temp_table_names)
+        metastore.cleanup_tables(self.temp_table_names)
         metastore.close()
         warehouse = self.catalog.warehouse.clone(use_new_connection=True)
-        warehouse.cleanup_temp_tables(self.temp_table_names)
+        warehouse.cleanup_tables(self.temp_table_names)
         warehouse.close()
         self.temp_table_names = []
 

tests/func/test_catalog.py

@@ -1120,7 +1120,7 @@ def test_garbage_collect(cloud_test_catalog, from_cli, capsys):
         captured = capsys.readouterr()
         assert captured.out == "Garbage collecting 4 tables.\n"
     else:
-        catalog.cleanup_temp_tables(temp_tables)
+        catalog.cleanup_tables(temp_tables)
     assert catalog.get_temp_table_names() == []