Fix Index.union and get_indexer_non_unique bugs exposed by my categorical index fixes

Author: batterseapower

pandas/_libs/index.pyx

@@ -304,12 +304,20 @@ cdef class IndexEngine:
         if stargets and len(stargets) < 5 and self.is_monotonic_increasing:
             # if there are few enough stargets and the index is monotonically
             # increasing, then use binary search for each starget
+            remaining_stargets = set()
             for starget in stargets:
-                start = values.searchsorted(starget, side='left')
-                end = values.searchsorted(starget, side='right')
-                if start != end:
-                    d[starget] = list(range(start, end))
-        else:
+                try:
+                    start = values.searchsorted(starget, side='left')
+                    end = values.searchsorted(starget, side='right')
+                except TypeError: # e.g. if we tried to search for string in int array
+                    remaining_stargets.add(starget)
+                else:
+                    if start != end:
+                        d[starget] = list(range(start, end))
+
+            stargets = remaining_stargets
+        
+        if stargets:
             # otherwise, map by iterating through all items in the index
             for i in range(n):
                 val = values[i]

pandas/core/indexes/base.py

@@ -2489,8 +2489,14 @@ def _union(self, other, sort):
                 value_set = set(lvals)
                 result.extend([x for x in rvals if x not in value_set])
         else:
-            indexer = self.get_indexer(other)
-            indexer, = (indexer == -1).nonzero()
+            # find indexes of things in "other" that are not in "self"
+            try:
+                indexer = self.get_indexer(other)
+            except InvalidIndexError:
+                # duplicates
+                indexer = algos.unique1d(self.get_indexer_non_unique(other)[1])
+            else:
+                indexer, = (indexer == -1).nonzero()
 
             if len(indexer) > 0:
                 other_diff = algos.take_nd(rvals, indexer, allow_fill=False)

pandas/tests/test_base.py

@@ -990,6 +990,11 @@ def test_bool_indexing(self, indexer_klass, indexer):
             s = pd.Series(idx)
             tm.assert_series_equal(s[indexer_klass(indexer)], s.iloc[exp_idx])
 
+    def test_get_indexer_non_unique_dtype_mismatch(self):
+        indexes, missing = pd.Index(['A', 'B']).get_indexer_non_unique(pd.Index([0]))
+        tm.assert_numpy_array_equal(np.array([], dtype=np.intp), indexes)
+        tm.assert_numpy_array_equal(np.array([0, 1], dtype=np.intp), missing)
+
 
 class TestTranspose(Ops):
     errmsg = "the 'axes' parameter is not supported"