fix bug #GH23020

Author: makbigc

doc/source/whatsnew/v0.24.0.txt

@@ -946,6 +946,7 @@ Reshaping
 - Bug in :func:`merge` when merging ``datetime64[ns, tz]`` data that contained a DST transition (:issue:`18885`)
 - Bug in :func:`merge_asof` when merging on float values within defined tolerance (:issue:`22981`)
 - Bug in :func:`pandas.concat` when concatenating a multicolumn DataFrame with tz-aware data against a DataFrame with a different number of columns (:issue`22796`)
+- Bug in :func:`pandas.merge` when merging on an Integer extension array (:issue:`23020`)
 
 .. _whatsnew_0240.bug_fixes.sparse:
 

pandas/core/reshape/merge.py

@@ -26,6 +26,7 @@
     is_number,
     is_numeric_dtype,
     is_integer,
+    is_extension_array_dtype,
     is_int_or_datetime_dtype,
     is_dtype_equal,
     is_bool,
@@ -1551,6 +1552,10 @@ def _factorize_keys(lk, rk, sort=True):
 
         lk = ensure_int64(lk.codes)
         rk = ensure_int64(rk)
+    elif is_extension_array_dtype(lk) and is_extension_array_dtype(rk):
+        klass = libhashtable.Factorizer
+        lk = ensure_object(lk)
+        rk = ensure_object(rk)
     elif is_int_or_datetime_dtype(lk) and is_int_or_datetime_dtype(rk):
         klass = libhashtable.Int64Factorizer
         lk = ensure_int64(com.values_from_object(lk))

pandas/tests/reshape/merge/test_merge.py

@@ -1842,6 +1842,16 @@ def test_merging_with_bool_or_int_cateorical_column(self, category_column,
             CDT(categories, ordered=ordered))
         assert_frame_equal(expected, result)
 
+    def test_merge_on_int_array(self):
+        # GH  23020
+        df = pd.DataFrame({'A': pd.Series([1, 2, np.nan], dtype='Int64'),
+                           'B': 1})
+        result = pd.merge(df, df, on='A')
+        expected = pd.DataFrame({'A': pd.Series([1, 2, np.nan], dtype='Int64'),
+                                 'B_x': 1,
+                                 'B_y': 1})
+        assert_frame_equal(result, expected, check_dtype=True)
+
 
 @pytest.fixture
 def left_df():