Follow-up to pandas-dev#17419 (pandas-dev#17497)

Author: jbrockmendel

pandas/_libs/period.pyx

@@ -33,11 +33,10 @@ from util cimport is_period_object, is_string_object
 from lib cimport is_null_datetimelike, is_period
 from pandas._libs import tslib, lib
 from pandas._libs.tslib import (Timedelta, Timestamp, iNaT,
-                                NaT, _get_utcoffset)
-from tslibs.timezones cimport _is_utc
+                                NaT)
+from tslibs.timezones cimport _is_utc, _is_tzlocal, _get_utcoffset
 from tslib cimport (
     maybe_get_tz,
-    _is_tzlocal,
     _get_dst_info,
     _nat_scalar_rules)
 

pandas/_libs/src/inference.pyx

@@ -2,7 +2,8 @@ import sys
 from decimal import Decimal
 cimport util
 cimport cython
-from tslib import NaT, get_timezone
+from tslib import NaT
+from tslibs.timezones cimport _get_zone
 from datetime import datetime, timedelta
 iNaT = util.get_nat()
 
@@ -900,13 +901,13 @@ cpdef bint is_datetime_with_singletz_array(ndarray[object] values):
     for i in range(n):
         base_val = values[i]
         if base_val is not NaT:
-            base_tz = get_timezone(getattr(base_val, 'tzinfo', None))
+            base_tz = _get_zone(getattr(base_val, 'tzinfo', None))
 
             for j in range(i, n):
                 val = values[j]
                 if val is not NaT:
                     tz = getattr(val, 'tzinfo', None)
-                    if base_tz != tz and base_tz != get_timezone(tz):
+                    if base_tz != tz and base_tz != _get_zone(tz):
                         return False
             break
 

pandas/_libs/tslib.pxd

@@ -3,7 +3,6 @@ from numpy cimport ndarray, int64_t
 cdef convert_to_tsobject(object, object, object, bint, bint)
 cpdef convert_to_timedelta64(object, object)
 cpdef object maybe_get_tz(object)
-cdef bint _is_tzlocal(object)
 cdef object _get_dst_info(object)
 cdef bint _nat_scalar_rules[6]
 cdef bint _check_all_nulls(obj)

pandas/_libs/tslib.pyx

@@ -107,7 +107,13 @@ cdef int64_t NPY_NAT = util.get_nat()
 iNaT = NPY_NAT
 
 
-from tslibs.timezones cimport _is_utc
+from tslibs.timezones cimport (
+    _is_utc, _is_tzlocal,
+    _treat_tz_as_dateutil, _treat_tz_as_pytz,
+    _get_zone,
+    _get_utcoffset)
+from tslibs.timezones import get_timezone, _get_utcoffset  # noqa
+
 
 cdef inline object create_timestamp_from_ts(
         int64_t value, pandas_datetimestruct dts,
@@ -235,10 +241,6 @@ def ints_to_pytimedelta(ndarray[int64_t] arr, box=False):
     return result
 
 
-cdef inline bint _is_tzlocal(object tz):
-    return isinstance(tz, _dateutil_tzlocal)
-
-
 cdef inline bint _is_fixed_offset(object tz):
     if _treat_tz_as_dateutil(tz):
         if len(tz._trans_idx) == 0 and len(tz._trans_list) == 0:
@@ -1443,11 +1445,6 @@ cdef class _TSObject:
         def __get__(self):
             return self.value
 
-cpdef _get_utcoffset(tzinfo, obj):
-    try:
-        return tzinfo._utcoffset
-    except AttributeError:
-        return tzinfo.utcoffset(obj)
 
 # helper to extract datetime and int64 from several different possibilities
 cdef convert_to_tsobject(object ts, object tz, object unit,
@@ -1712,48 +1709,6 @@ def _localize_pydatetime(object dt, object tz):
         return dt.replace(tzinfo=tz)
 
 
-def get_timezone(tz):
-    return _get_zone(tz)
-
-
-cdef inline object _get_zone(object tz):
-    """
-    We need to do several things here:
-    1) Distinguish between pytz and dateutil timezones
-    2) Not be over-specific (e.g. US/Eastern with/without DST is same *zone*
-       but a different tz object)
-    3) Provide something to serialize when we're storing a datetime object
-       in pytables.
-
-    We return a string prefaced with dateutil if it's a dateutil tz, else just
-    the tz name. It needs to be a string so that we can serialize it with
-    UJSON/pytables. maybe_get_tz (below) is the inverse of this process.
-    """
-    if _is_utc(tz):
-        return 'UTC'
-    else:
-        if _treat_tz_as_dateutil(tz):
-            if '.tar.gz' in tz._filename:
-                raise ValueError(
-                    'Bad tz filename. Dateutil on python 3 on windows has a '
-                    'bug which causes tzfile._filename to be the same for all '
-                    'timezone files. Please construct dateutil timezones '
-                    'implicitly by passing a string like "dateutil/Europe'
-                    '/London" when you construct your pandas objects instead '
-                    'of passing a timezone object. See '
-                    'https://github.com/pandas-dev/pandas/pull/7362')
-            return 'dateutil/' + tz._filename
-        else:
-            # tz is a pytz timezone or unknown.
-            try:
-                zone = tz.zone
-                if zone is None:
-                    return tz
-                return zone
-            except AttributeError:
-                return tz
-
-
 cpdef inline object maybe_get_tz(object tz):
     """
     (Maybe) Construct a timezone object from a string. If tz is a string, use
@@ -4285,13 +4240,6 @@ def tz_convert_single(int64_t val, object tz1, object tz2):
 # Timezone data caches, key is the pytz string or dateutil file name.
 dst_cache = {}
 
-cdef inline bint _treat_tz_as_pytz(object tz):
-    return hasattr(tz, '_utc_transition_times') and hasattr(
-        tz, '_transition_info')
-
-cdef inline bint _treat_tz_as_dateutil(object tz):
-    return hasattr(tz, '_trans_list') and hasattr(tz, '_trans_idx')
-
 
 def _p_tz_cache_key(tz):
     """ Python interface for cache function to facilitate testing."""

pandas/_libs/tslibs/timezones.pxd

@@ -2,3 +2,11 @@
 # cython: profile=False
 
 cdef bint _is_utc(object tz)
+cdef bint _is_tzlocal(object tz)
+
+cdef bint _treat_tz_as_pytz(object tz)
+cdef bint _treat_tz_as_dateutil(object tz)
+
+cdef object _get_zone(object tz)
+
+cpdef _get_utcoffset(tzinfo, obj)

pandas/_libs/tslibs/timezones.pyx

@@ -2,11 +2,77 @@
 # cython: profile=False
 
 # dateutil compat
-from dateutil.tz import tzutc as _dateutil_tzutc
+from dateutil.tz import (
+	tzutc as _dateutil_tzutc,
+	tzlocal as _dateutil_tzlocal)
 
 import pytz
 UTC = pytz.utc
 
 
 cdef inline bint _is_utc(object tz):
     return tz is UTC or isinstance(tz, _dateutil_tzutc)
+
+
+cdef inline bint _is_tzlocal(object tz):
+    return isinstance(tz, _dateutil_tzlocal)
+
+
+cdef inline bint _treat_tz_as_pytz(object tz):
+    return hasattr(tz, '_utc_transition_times') and hasattr(
+        tz, '_transition_info')
+
+
+cdef inline bint _treat_tz_as_dateutil(object tz):
+    return hasattr(tz, '_trans_list') and hasattr(tz, '_trans_idx')
+
+
+cdef inline object _get_zone(object tz):
+    """
+    We need to do several things here:
+    1) Distinguish between pytz and dateutil timezones
+    2) Not be over-specific (e.g. US/Eastern with/without DST is same *zone*
+       but a different tz object)
+    3) Provide something to serialize when we're storing a datetime object
+       in pytables.
+
+    We return a string prefaced with dateutil if it's a dateutil tz, else just
+    the tz name. It needs to be a string so that we can serialize it with
+    UJSON/pytables. maybe_get_tz (below) is the inverse of this process.
+    """
+    if _is_utc(tz):
+        return 'UTC'
+    else:
+        if _treat_tz_as_dateutil(tz):
+            if '.tar.gz' in tz._filename:
+                raise ValueError(
+                    'Bad tz filename. Dateutil on python 3 on windows has a '
+                    'bug which causes tzfile._filename to be the same for all '
+                    'timezone files. Please construct dateutil timezones '
+                    'implicitly by passing a string like "dateutil/Europe'
+                    '/London" when you construct your pandas objects instead '
+                    'of passing a timezone object. See '
+                    'https://github.com/pandas-dev/pandas/pull/7362')
+            return 'dateutil/' + tz._filename
+        else:
+            # tz is a pytz timezone or unknown.
+            try:
+                zone = tz.zone
+                if zone is None:
+                    return tz
+                return zone
+            except AttributeError:
+                return tz
+
+
+def get_timezone(tz):
+    return _get_zone(tz)
+
+#----------------------------------------------------------------------
+# UTC Offsets
+
+cpdef _get_utcoffset(tzinfo, obj):
+    try:
+        return tzinfo._utcoffset
+    except AttributeError:
+        return tzinfo.utcoffset(obj)