More coercion, use _recode_for_categories

Author: TomAugspurger

pandas/_libs/parsers.pyx

@@ -45,7 +45,7 @@ from pandas.core.dtypes.common import (
     is_bool_dtype, is_object_dtype,
     is_string_dtype, is_datetime64_dtype,
     pandas_dtype)
-from pandas.core.categorical import Categorical
+from pandas.core.categorical import Categorical, _recode_for_categories
 from pandas.core.algorithms import take_1d
 from pandas.core.dtypes.concat import union_categoricals
 from pandas import Index, to_numeric, to_datetime, to_timedelta
@@ -1292,8 +1292,7 @@ cdef class TextReader:
                     dtype.categories is not None):
                 # recode for dtype.categories
                 categories = dtype.categories
-                indexer = categories.get_indexer(cats)
-                codes = take_1d(indexer, codes, fill_value=-1)
+                codes = _recode_for_categories(codes, cats, categories)
                 ordered = dtype.ordered
             elif not cats.is_monotonic_increasing:
                 # sort categories and recode if necessary

pandas/tests/io/parser/dtypes.py

@@ -203,6 +203,14 @@ def test_categoricaldtype_coerces_datetime(self):
         result = self.read_csv(StringIO(data), dtype=dtype)
         tm.assert_frame_equal(result, expected)
 
+        dtype = {
+            'b': CategoricalDtype([pd.Timestamp("2014")])
+        }
+        data = "b\n2014-01-01\n2014-01-01T00:00:00"
+        expected = pd.DataFrame({'b': Categorical([pd.Timestamp('2014')] * 2)})
+        result = self.read_csv(StringIO(data), dtype=dtype)
+        tm.assert_frame_equal(result, expected)
+
     def test_categoricaldtype_coerces_timedelta(self):
         dtype = {'b': CategoricalDtype(pd.to_timedelta(['1H', '2H', '3H']))}
         data = "b\n1H\n2H\n3H"