CLN: more consistent error message for construct_from_string wrong type (#31387)

Author: simonjayhawkins

pandas/core/arrays/numpy_.py

@@ -74,9 +74,11 @@ def construct_from_string(cls, string):
         try:
             return cls(np.dtype(string))
         except TypeError as err:
-            raise TypeError(
-                f"Cannot construct a 'PandasDtype' from '{string}'"
-            ) from err
+            if not isinstance(string, str):
+                msg = f"'construct_from_string' expects a string, got {type(string)}"
+            else:
+                msg = f"Cannot construct a 'PandasDtype' from '{string}'"
+            raise TypeError(msg) from err
 
     @classmethod
     def construct_array_type(cls):

pandas/core/arrays/sparse/dtype.py

@@ -206,6 +206,10 @@ def construct_from_string(cls, string):
         -------
         SparseDtype
         """
+        if not isinstance(string, str):
+            raise TypeError(
+                f"'construct_from_string' expects a string, got {type(string)}"
+            )
         msg = f"Cannot construct a 'SparseDtype' from '{string}'"
         if string.startswith("Sparse"):
             try:

pandas/core/dtypes/base.py

@@ -235,8 +235,9 @@ def construct_from_string(cls, string: str):
         ...             " "'{string}'")
         """
         if not isinstance(string, str):
-            raise TypeError(f"Expects a string, got {type(string).__name__}")
-
+            raise TypeError(
+                f"'construct_from_string' expects a string, got {type(string)}"
+            )
         # error: Non-overlapping equality check (left operand type: "str", right
         #  operand type: "Callable[[ExtensionDtype], str]")  [comparison-overlap]
         assert isinstance(cls.name, str), (cls, type(cls.name))

pandas/core/dtypes/dtypes.py

@@ -352,7 +352,9 @@ def construct_from_string(cls, string: str_type) -> "CategoricalDtype":
             If a CategoricalDtype cannot be constructed from the input.
         """
         if not isinstance(string, str):
-            raise TypeError(f"Expects a string, got {type(string)}")
+            raise TypeError(
+                f"'construct_from_string' expects a string, got {type(string)}"
+            )
         if string != cls.name:
             raise TypeError(f"Cannot construct a 'CategoricalDtype' from '{string}'")
 
@@ -728,22 +730,24 @@ def construct_from_string(cls, string: str_type):
         >>> DatetimeTZDtype.construct_from_string('datetime64[ns, UTC]')
         datetime64[ns, UTC]
         """
-        if isinstance(string, str):
-            msg = f"Cannot construct a 'DatetimeTZDtype' from '{string}'"
-            match = cls._match.match(string)
-            if match:
-                d = match.groupdict()
-                try:
-                    return cls(unit=d["unit"], tz=d["tz"])
-                except (KeyError, TypeError, ValueError) as err:
-                    # KeyError if maybe_get_tz tries and fails to get a
-                    #  pytz timezone (actually pytz.UnknownTimeZoneError).
-                    # TypeError if we pass a nonsense tz;
-                    # ValueError if we pass a unit other than "ns"
-                    raise TypeError(msg) from err
-            raise TypeError(msg)
+        if not isinstance(string, str):
+            raise TypeError(
+                f"'construct_from_string' expects a string, got {type(string)}"
+            )
 
-        raise TypeError("Cannot construct a 'DatetimeTZDtype'")
+        msg = f"Cannot construct a 'DatetimeTZDtype' from '{string}'"
+        match = cls._match.match(string)
+        if match:
+            d = match.groupdict()
+            try:
+                return cls(unit=d["unit"], tz=d["tz"])
+            except (KeyError, TypeError, ValueError) as err:
+                # KeyError if maybe_get_tz tries and fails to get a
+                #  pytz timezone (actually pytz.UnknownTimeZoneError).
+                # TypeError if we pass a nonsense tz;
+                # ValueError if we pass a unit other than "ns"
+                raise TypeError(msg) from err
+        raise TypeError(msg)
 
     def __str__(self) -> str_type:
         return f"datetime64[{self.unit}, {self.tz}]"
@@ -1075,7 +1079,9 @@ def construct_from_string(cls, string):
         if its not possible
         """
         if not isinstance(string, str):
-            raise TypeError(f"a string needs to be passed, got type {type(string)}")
+            raise TypeError(
+                f"'construct_from_string' expects a string, got {type(string)}"
+            )
 
         if string.lower() == "interval" or cls._match.search(string) is not None:
             return cls(string)

pandas/tests/dtypes/test_dtypes.py

@@ -244,11 +244,12 @@ def test_construct_from_string_raises(self):
         with pytest.raises(TypeError, match="notatz"):
             DatetimeTZDtype.construct_from_string("datetime64[ns, notatz]")
 
-        msg = "^Cannot construct a 'DatetimeTZDtype'"
-        with pytest.raises(TypeError, match=msg):
+        msg = "'construct_from_string' expects a string, got <class 'list'>"
+        with pytest.raises(TypeError, match=re.escape(msg)):
             # list instead of string
             DatetimeTZDtype.construct_from_string(["datetime64[ns, notatz]"])
 
+        msg = "^Cannot construct a 'DatetimeTZDtype'"
         with pytest.raises(TypeError, match=msg):
             # non-nano unit
             DatetimeTZDtype.construct_from_string("datetime64[ps, UTC]")
@@ -547,9 +548,9 @@ def test_construction_from_string(self):
     @pytest.mark.parametrize("string", [0, 3.14, ("a", "b"), None])
     def test_construction_from_string_errors(self, string):
         # these are invalid entirely
-        msg = "a string needs to be passed, got type"
+        msg = f"'construct_from_string' expects a string, got {type(string)}"
 
-        with pytest.raises(TypeError, match=msg):
+        with pytest.raises(TypeError, match=re.escape(msg)):
             IntervalDtype.construct_from_string(string)
 
     @pytest.mark.parametrize("string", ["foo", "foo[int64]", "IntervalA"])

pandas/tests/extension/base/dtype.py

@@ -105,3 +105,10 @@ def test_construct_from_string_another_type_raises(self, dtype):
         msg = f"Cannot construct a '{type(dtype).__name__}' from 'another_type'"
         with pytest.raises(TypeError, match=msg):
             type(dtype).construct_from_string("another_type")
+
+    def test_construct_from_string_wrong_type_raises(self, dtype):
+        with pytest.raises(
+            TypeError,
+            match="'construct_from_string' expects a string, got <class 'int'>",
+        ):
+            type(dtype).construct_from_string(0)