BUG: Pandas can't restore index from parquet with offset-specified timezone #35997

Author: alippai

pandas/_libs/tslibs/timezones.pyx

@@ -1,4 +1,4 @@
-from datetime import timezone
+from datetime import timedelta, timezone
 
 from cpython.datetime cimport datetime, timedelta, tzinfo
 
@@ -102,6 +102,14 @@ cpdef inline tzinfo maybe_get_tz(object tz):
             # On Python 3 on Windows, the filename is not always set correctly.
             if isinstance(tz, _dateutil_tzfile) and '.tar.gz' in tz._filename:
                 tz._filename = zone
+        elif tz[0] in {'-', '+'}:
+            hours = int(tz[0:3])
+            minutes = int(tz[0] + tz[4:6])
+            tz = timezone(timedelta(hours=hours, minutes=minutes))
+        elif tz[0:4] in {'UTC-', 'UTC+'}:
+            hours = int(tz[3:6])
+            minutes = int(tz[3] + tz[7:9])
+            tz = timezone(timedelta(hours=hours, minutes=minutes))
         else:
             tz = pytz.timezone(tz)
     elif is_integer_object(tz):

pandas/tests/io/test_parquet.py

@@ -123,6 +123,19 @@ def df_full():
     )
 
 
+@pytest.fixture(
+    params=[
+        datetime.datetime.now(datetime.timezone.utc),
+        datetime.datetime.strptime("2019-01-04T16:41:24+0200", "%Y-%m-%dT%H:%M:%S%z"),
+        datetime.datetime.strptime("2019-01-04T16:41:24+0215", "%Y-%m-%dT%H:%M:%S%z"),
+        datetime.datetime.strptime("2019-01-04T16:41:24-0200", "%Y-%m-%dT%H:%M:%S%z"),
+        datetime.datetime.strptime("2019-01-04T16:41:24-0215", "%Y-%m-%dT%H:%M:%S%z"),
+    ]
+)
+def timezone_aware_date_list(request):
+    return request.param
+
+
 def check_round_trip(
     df,
     engine=None,
@@ -712,6 +725,13 @@ def test_timestamp_nanoseconds(self, pa):
         df = pd.DataFrame({"a": pd.date_range("2017-01-01", freq="1n", periods=10)})
         check_round_trip(df, pa, write_kwargs={"version": "2.0"})
 
+    @td.skip_if_no("pyarrow", min_version="0.14")
+    def test_timezone_aware_index(self, pa, timezone_aware_date_list):
+        idx = 5 * [timezone_aware_date_list]
+
+        df = pd.DataFrame(index=idx)
+        check_round_trip(df, pa, write_kwargs={"version": "2.0"})
+
     @td.skip_if_no("pyarrow", min_version="0.17")
     def test_filter_row_groups(self, pa):
         # https://github.com/pandas-dev/pandas/issues/26551
@@ -850,3 +870,12 @@ def test_empty_dataframe(self, fp):
         expected = df.copy()
         expected.index.name = "index"
         check_round_trip(df, fp, expected=expected)
+
+    def test_timezone_aware_index(self, fp, timezone_aware_date_list):
+        idx = 5 * [timezone_aware_date_list]
+
+        df = pd.DataFrame(index=idx, data={"col": 5 * [0]})
+
+        expected = df.copy()
+        expected.index.name = "index"
+        check_round_trip(df, fp, expected=expected)