Merge pull request numpy#26930 from seberg/issue-26922

BUG: Fix out-of-bound minimum offset for in1d table method

Author: charris

numpy/lib/_arraysetops_impl.py

@@ -922,8 +922,25 @@ def _in1d(ar1, ar2, assume_unique=False, invert=False, *, kind=None):
 
             # Mask out elements we know won't work
             basic_mask = (ar1 <= ar2_max) & (ar1 >= ar2_min)
+            in_range_ar1 = ar1[basic_mask]
+            if in_range_ar1.size == 0:
+                # Nothing more to do, since all values are out of range.
+                return outgoing_array
+
+            # Unfortunately, ar2_min can be out of range for `intp` even
+            # if the calculation result must fit in range (and be positive).
+            # In that case, use ar2.dtype which must work for all unmasked
+            # values.
+            try:
+                ar2_min = np.array(ar2_min, dtype=np.intp)
+                dtype = np.intp
+            except OverflowError:
+                dtype = ar2.dtype
+
+            out = np.empty_like(in_range_ar1, dtype=np.intp)
             outgoing_array[basic_mask] = isin_helper_ar[
-                    np.subtract(ar1[basic_mask], ar2_min, dtype=np.intp)]
+                    np.subtract(in_range_ar1, ar2_min, dtype=dtype,
+                                out=out, casting="unsafe")]
 
             return outgoing_array
         elif kind == 'table':  # not range_safe_from_overflow

numpy/lib/tests/test_arraysetops.py

@@ -440,6 +440,22 @@ def test_isin_mixed_dtype(self, dtype1, dtype2, kind):
         else:
             assert_array_equal(isin(ar1, ar2, kind=kind), expected)
 
+    @pytest.mark.parametrize("data", [
+        np.array([2**63, 2**63+1], dtype=np.uint64),
+        np.array([-2**62, -2**62-1], dtype=np.int64),
+    ])
+    @pytest.mark.parametrize("kind", [None, "sort", "table"])
+    def test_isin_mixed_huge_vals(self, kind, data):
+        """Test values outside intp range (negative ones if 32bit system)"""
+        query = data[1]
+        res = np.isin(data, query, kind=kind)
+        assert_array_equal(res, [False, True])
+        # Also check that nothing weird happens for values can't possibly
+        # in range.
+        data = data.astype(np.int32)  # clearly different values
+        res = np.isin(data, query, kind=kind)
+        assert_array_equal(res, [False, False])
+
     @pytest.mark.parametrize("kind", [None, "sort", "table"])
     def test_isin_mixed_boolean(self, kind):
         """Test that isin works as expected for bool/int input."""