Add type hints to name resolvers

Author: hwalinga

pandas/core/computation/parsing.py

@@ -58,9 +58,7 @@ def create_valid_python_identifier(name: str) -> str:
     name = "BACKTICK_QUOTED_STRING_" + name
 
     if not name.isidentifier():
-        raise ValueError(
-            f"Could not convert '{name}' to a valid Python identifier."
-        )
+        raise SyntaxError(f"Could not convert '{name}' to a valid Python identifier.")
 
     return name
 
@@ -85,7 +83,7 @@ def tokenize_and_clean_column_names(name: Union[str, int]) -> Union[str, int]:
         tokenized = tokenize_string(f"`{name}`")
         tokval = next(tokenized)[1]
         return create_valid_python_identifier(tokval)
-    except ValueError:
+    except SyntaxError:
         # Rarely, a name cannot be converted to a valid Python identifier.
         # So, we just return the name.
         # If this name was used in the query string,

pandas/core/frame.py

@@ -3217,7 +3217,7 @@ def eval(self, expr, inplace=False, **kwargs):
         kwargs["level"] = kwargs.pop("level", 0) + 1
         if resolvers is None:
             index_resolvers = self._get_index_resolvers()
-            column_resolvers = self._get_special_character_free_column_resolvers()
+            column_resolvers = self._get_cleaned_column_resolvers()
             resolvers = column_resolvers, index_resolvers
         if "target" not in kwargs:
             kwargs["target"] = self

pandas/core/generic.py

@@ -90,6 +90,8 @@
 from pandas.io.formats.printing import pprint_thing
 from pandas.tseries.frequencies import to_offset
 
+NameResolver = Dict[Union[str, int], ABCSeries]
+
 # goal is to be able to define the docs close to function, while still being
 # able to share
 _shared_docs: Dict[str, str] = dict()
@@ -455,7 +457,7 @@ def _get_block_manager_axis(cls, axis):
             return m - axis
         return axis
 
-    def _get_axis_resolvers(self, axis):
+    def _get_axis_resolvers(self, axis: str) -> NameResolver:
         # index or columns
         axis_index = getattr(self, axis)
         d = dict()
@@ -485,16 +487,16 @@ def _get_axis_resolvers(self, axis):
         d[axis] = dindex
         return d
 
-    def _get_index_resolvers(self):
+    def _get_index_resolvers(self) -> NameResolver:
         from pandas.core.computation.parsing import tokenize_and_clean_column_names
 
-        d = {}
+        d: NameResolver = {}
         for axis_name in self._AXIS_ORDERS:
             d.update(self._get_axis_resolvers(axis_name))
 
-        return {tokenize_and_clean_column_names(k) or k: v for k, v in d.items()}
+        return {tokenize_and_clean_column_names(k): v for k, v in d.items()}
 
-    def _get_special_character_free_column_resolvers(self) -> dict:
+    def _get_cleaned_column_resolvers(self) -> NameResolver:
         """Return the special character free column resolvers of a dataframe.
 
         Column names with special characters are 'cleaned up' so that they can
@@ -503,7 +505,10 @@ def _get_special_character_free_column_resolvers(self) -> dict:
         """
         from pandas.core.computation.parsing import tokenize_and_clean_column_names
 
-        return {tokenize_and_clean_column_names(k) or k: v for k, v in self.items()}
+        if isinstance(self, ABCSeries):
+            return {tokenize_and_clean_column_names(self.name): self}
+
+        return {tokenize_and_clean_column_names(k): v for k, v in self.items()}
 
     @property
     def _info_axis(self):

pandas/tests/frame/test_query_eval.py

@@ -1161,13 +1161,13 @@ def test_lots_of_operators_string(self, df):
         tm.assert_frame_equal(res, expect)
 
     def test_failing_quote(self, df):
-        with pytest.raises(ValueError):
+        with pytest.raises(SyntaxError):
             df.query("`it's` > `that's`")
 
     def test_failing_character_outside_range(self, df):
-        with pytest.raises(ValueError):
+        with pytest.raises(SyntaxError):
             df.query("`☺` > 4")
 
     def test_failing_hashtag(self, df):
-        with pytest.raises(ValueError):
+        with pytest.raises(SyntaxError):
             df.query("`foo#bar` > 4")