ENH: Add merge type validation on pandas.merge

doc/source/whatsnew/v3.0.0.rst

@@ -30,6 +30,7 @@ Other enhancements
 ^^^^^^^^^^^^^^^^^^
 - :class:`pandas.api.typing.FrozenList` is available for typing the outputs of :attr:`MultiIndex.names`, :attr:`MultiIndex.codes` and :attr:`MultiIndex.levels` (:issue:`58237`)
 - :class:`pandas.api.typing.SASReader` is available for typing the output of :func:`read_sas` (:issue:`55689`)
+- :func:`pandas.merge` now validates the ``how`` parameter input (merge type) (:issue:`59435`)
 - :func:`DataFrame.to_excel` now raises an ``UserWarning`` when the character count in a cell exceeds Excel's limitation of 32767 characters (:issue:`56954`)
 - :func:`read_stata` now returns ``datetime64`` resolutions better matching those natively stored in the stata format (:issue:`55642`)
 - :meth:`DataFrame.agg` called with ``axis=1`` and a ``func`` which relabels the result index now raises a ``NotImplementedError`` (:issue:`58807`).

pandas/core/reshape/merge.py

@@ -982,6 +982,11 @@ def __init__(
             )
             raise MergeError(msg)
 
+        # GH 59435: raise when "how" is not a valid Merge type
+        merge_type = ("left", "right", "inner", "outer", "cross", "asof")
+        if how not in merge_type:
+            raise ValueError(f"'{how}' is not a valid Merge type {merge_type}")
+
         self.left_on, self.right_on = self._validate_left_right_on(left_on, right_on)
 
         (

pandas/tests/reshape/merge/test_merge.py

@@ -1456,6 +1456,21 @@ def test_merge_readonly(self):
 
         data1.merge(data2)  # no error
 
+    def test_merge_how_validation(self):
+        # https://github.com/pandas-dev/pandas/issues/59422
+        data1 = DataFrame(
+            np.arange(20).reshape((4, 5)) + 1, columns=["a", "b", "c", "d", "e"]
+        )
+        data2 = DataFrame(
+            np.arange(20).reshape((5, 4)) + 1, columns=["a", "b", "x", "y"]
+        )
+        msg = (
+            "'full' is not a valid Merge type "
+            "('left', 'right', 'inner', 'outer', 'cross', 'asof')"
+        )
+        with pytest.raises(ValueError, match=re.escape(msg)):
+            data1.merge(data2, how="full")
+
 
 def _check_merge(x, y):
     for how in ["inner", "left", "outer"]: