ENH: Add merge type validation on pandas.merge (#59435)

* add merge type validation on pandas.merge

* add ENH to latest whatsnew doc

* move merge type validation to _MergeOperation class

* add tests on merge validation; add asof as valid mergetype

* change merge_type from tuple to dict

* change ValueError message to updated change

* change Error message on merge type

* update test error messages for merge type errors

* [pre-commit.ci] auto fixes from pre-commit.com hooks

for more information, see https://pre-commit.ci

---------

Co-authored-by: pre-commit-ci[bot] <66853113+pre-commit-ci[bot]@users.noreply.github.com>
Co-authored-by: Matthew Roeschke <[email protected]>

Author: 3 people

doc/source/whatsnew/v3.0.0.rst

@@ -31,6 +31,7 @@ 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:`DataFrame.to_excel` now raises an ``UserWarning`` when the character count in a cell exceeds Excel's limitation of 32767 characters (:issue:`56954`)
+- :func:`pandas.merge` now validates the ``how`` parameter input (merge type) (:issue:`59435`)
 - :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`).
 - :meth:`Index.get_loc` now accepts also subclasses of ``tuple`` as keys (:issue:`57922`)

pandas/core/reshape/merge.py

@@ -982,6 +982,14 @@ 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: "
+                f"left, right, inner, outer, cross, asof"
+            )
+
         self.left_on, self.right_on = self._validate_left_right_on(left_on, right_on)
 
         (

pandas/tests/frame/methods/test_join.py

@@ -1,4 +1,5 @@
 from datetime import datetime
+import re
 import zoneinfo
 
 import numpy as np
@@ -276,7 +277,8 @@ def test_join_index(float_frame):
     tm.assert_index_equal(joined.index, float_frame.index.sort_values())
     tm.assert_index_equal(joined.columns, expected_columns)
 
-    with pytest.raises(ValueError, match="join method"):
+    join_msg = "'foo' is not a valid Merge type: left, right, inner, outer, cross, asof"
+    with pytest.raises(ValueError, match=re.escape(join_msg)):
         f.join(f2, how="foo")
 
     # corner case - overlapping columns

pandas/tests/reshape/merge/test_merge.py

@@ -1456,6 +1456,18 @@ 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"]: