Merge pull request #752 from datafold/minor-type-annotations

Correct a few misleading type annotations

Author: dlawin

data_diff/databases/base.py

@@ -996,7 +996,9 @@ def _process_table_schema(
         # Return a dict of form {name: type} after normalization
         return col_dict
 
-    def _refine_coltypes(self, table_path: DbPath, col_dict: Dict[str, ColType], where: str = None, sample_size=64):
+    def _refine_coltypes(
+        self, table_path: DbPath, col_dict: Dict[str, ColType], where: Optional[str] = None, sample_size=64
+    ):
         """Refine the types in the column dict, by querying the database for a sample of their values
 
         'where' restricts the rows to be sampled.

data_diff/diff_tables.py

@@ -244,7 +244,7 @@ def _diff_tables_wrapper(self, table1: TableSegment, table2: TableSegment, info_
             if error:
                 raise error
 
-    def _validate_and_adjust_columns(self, table1: TableSegment, table2: TableSegment) -> DiffResult:
+    def _validate_and_adjust_columns(self, table1: TableSegment, table2: TableSegment) -> None:
         pass
 
     def _diff_tables_root(self, table1: TableSegment, table2: TableSegment, info_tree: InfoTree) -> DiffResult:

data_diff/hashdiff_tables.py

@@ -82,7 +82,7 @@ def __attrs_post_init__(self):
         if self.bisection_factor < 2:
             raise ValueError("Must have at least two segments per iteration (i.e. bisection_factor >= 2)")
 
-    def _validate_and_adjust_columns(self, table1, table2, *, strict: bool = True):
+    def _validate_and_adjust_columns(self, table1: TableSegment, table2: TableSegment, *, strict: bool = True) -> None:
         for c1, c2 in safezip(table1.relevant_columns, table2.relevant_columns):
             if c1 not in table1._schema:
                 raise ValueError(f"Column '{c1}' not found in schema for table {table1}")

tests/test_utils.py

@@ -27,7 +27,9 @@ def test_remove_passwords_in_dict(self):
         assert d["info"]["password"] == "%%"
 
         # Test replacing a motherduck token in nested dictionary
-        d = {'database1': {'driver': 'duckdb', 'filepath':'md:datafold_demo?motherduck_token=awieojfaowiejacijobhiwaef'}}
+        d = {
+            "database1": {"driver": "duckdb", "filepath": "md:datafold_demo?motherduck_token=awieojfaowiejacijobhiwaef"}
+        }
         remove_passwords_in_dict(d, "%%")
         assert d["database1"]["filepath"] == "md:datafold_demo?motherduck_token=%%"
 
@@ -54,7 +56,9 @@ def test__main__remove_passwords_in_dict(self):
         assert d["info"]["password"] == "**********"
 
         # Test replacing a motherduck token in nested dictionary
-        d = {'database1': {'driver': 'duckdb', 'filepath':'md:datafold_demo?motherduck_token=awieojfaowiejacijobhiwaef'}}
+        d = {
+            "database1": {"driver": "duckdb", "filepath": "md:datafold_demo?motherduck_token=awieojfaowiejacijobhiwaef"}
+        }
         _remove_passwords_in_dict(d)
         assert d["database1"]["filepath"] == "md:datafold_demo?motherduck_token=**********"