REF: collect get_dst_info-using functions in tslibs.vectorized (#35168)

asv_bench/benchmarks/tslibs/resolution.py

@@ -23,7 +23,10 @@
 import numpy as np
 import pytz
 
-from pandas._libs.tslibs.resolution import get_resolution
+try:
+    from pandas._libs.tslibs import get_resolution
+except ImportError:
+    from pandas._libs.tslibs.resolution import get_resolution
 
 
 class TimeResolution:

asv_bench/benchmarks/tslibs/tslib.py

@@ -21,7 +21,10 @@
 import numpy as np
 import pytz
 
-from pandas._libs.tslib import ints_to_pydatetime
+try:
+    from pandas._libs.tslibs import ints_to_pydatetime
+except ImportError:
+    from pandas._libs.tslib import ints_to_pydatetime
 
 _tzs = [
     None,

pandas/_libs/tslib.pyx

@@ -4,18 +4,14 @@ from cpython.datetime cimport (
     PyDate_Check,
     PyDateTime_Check,
     PyDateTime_IMPORT,
-    date,
     datetime,
-    time,
-    timedelta,
-    tzinfo,
 )
 # import datetime C API
 PyDateTime_IMPORT
 
 
 cimport numpy as cnp
-from numpy cimport float64_t, int64_t, ndarray, uint8_t, intp_t
+from numpy cimport float64_t, int64_t, ndarray
 import numpy as np
 cnp.import_array()
 
@@ -42,11 +38,6 @@ from pandas._libs.tslibs.np_datetime import OutOfBoundsDatetime
 
 from pandas._libs.tslibs.parsing import parse_datetime_string
 
-from pandas._libs.tslibs.timezones cimport (
-    get_dst_info,
-    is_utc,
-    is_tzlocal,
-)
 from pandas._libs.tslibs.conversion cimport (
     _TSObject,
     cast_from_unit,
@@ -60,174 +51,17 @@ from pandas._libs.tslibs.nattype cimport (
     c_nat_strings as nat_strings,
 )
 
-from pandas._libs.tslibs.offsets cimport to_offset
-
-from pandas._libs.tslibs.timestamps cimport create_timestamp_from_ts, _Timestamp
+from pandas._libs.tslibs.timestamps cimport _Timestamp
 from pandas._libs.tslibs.timestamps import Timestamp
 
 from pandas._libs.tslibs.tzconversion cimport (
-    tz_convert_utc_to_tzlocal,
     tz_localize_to_utc_single,
 )
 
 # Note: this is the only non-tslibs intra-pandas dependency here
 from pandas._libs.missing cimport checknull_with_nat_and_na
 
 
-cdef inline object create_datetime_from_ts(
-    int64_t value,
-    npy_datetimestruct dts,
-    tzinfo tz,
-    object freq,
-    bint fold,
-):
-    """
-    Convenience routine to construct a datetime.datetime from its parts.
-    """
-    return datetime(
-        dts.year, dts.month, dts.day, dts.hour, dts.min, dts.sec, dts.us, tz, fold=fold
-    )
-
-
-cdef inline object create_date_from_ts(
-    int64_t value,
-    npy_datetimestruct dts,
-    tzinfo tz,
-    object freq,
-    bint fold
-):
-    """
-    Convenience routine to construct a datetime.date from its parts.
-    """
-    # GH 25057 add fold argument to match other func_create signatures
-    return date(dts.year, dts.month, dts.day)
-
-
-cdef inline object create_time_from_ts(
-    int64_t value,
-    npy_datetimestruct dts,
-    tzinfo tz,
-    object freq,
-    bint fold
-):
-    """
-    Convenience routine to construct a datetime.time from its parts.
-    """
-    return time(dts.hour, dts.min, dts.sec, dts.us, tz, fold=fold)
-
-
-@cython.wraparound(False)
-@cython.boundscheck(False)
-def ints_to_pydatetime(
-    const int64_t[:] arr,
-    tzinfo tz=None,
-    object freq=None,
-    bint fold=False,
-    str box="datetime"
-):
-    """
-    Convert an i8 repr to an ndarray of datetimes, date, time or Timestamp.
-
-    Parameters
-    ----------
-    arr : array of i8
-    tz : str, optional
-         convert to this timezone
-    freq : str/Offset, optional
-         freq to convert
-    fold : bint, default is 0
-        Due to daylight saving time, one wall clock time can occur twice
-        when shifting from summer to winter time; fold describes whether the
-        datetime-like corresponds  to the first (0) or the second time (1)
-        the wall clock hits the ambiguous time
-
-        .. versionadded:: 1.1.0
-    box : {'datetime', 'timestamp', 'date', 'time'}, default 'datetime'
-        * If datetime, convert to datetime.datetime
-        * If date, convert to datetime.date
-        * If time, convert to datetime.time
-        * If Timestamp, convert to pandas.Timestamp
-
-    Returns
-    -------
-    ndarray of dtype specified by box
-    """
-    cdef:
-        Py_ssize_t i, n = len(arr)
-        ndarray[int64_t] trans
-        int64_t[:] deltas
-        intp_t[:] pos
-        npy_datetimestruct dts
-        object dt, new_tz
-        str typ
-        int64_t value, local_value, delta = NPY_NAT  # dummy for delta
-        ndarray[object] result = np.empty(n, dtype=object)
-        object (*func_create)(int64_t, npy_datetimestruct, tzinfo, object, bint)
-        bint use_utc = False, use_tzlocal = False, use_fixed = False
-        bint use_pytz = False
-
-    if box == "date":
-        assert (tz is None), "tz should be None when converting to date"
-
-        func_create = create_date_from_ts
-    elif box == "timestamp":
-        func_create = create_timestamp_from_ts
-
-        if isinstance(freq, str):
-            freq = to_offset(freq)
-    elif box == "time":
-        func_create = create_time_from_ts
-    elif box == "datetime":
-        func_create = create_datetime_from_ts
-    else:
-        raise ValueError(
-            "box must be one of 'datetime', 'date', 'time' or 'timestamp'"
-        )
-
-    if is_utc(tz) or tz is None:
-        use_utc = True
-    elif is_tzlocal(tz):
-        use_tzlocal = True
-    else:
-        trans, deltas, typ = get_dst_info(tz)
-        if typ not in ["pytz", "dateutil"]:
-            # static/fixed; in this case we know that len(delta) == 1
-            use_fixed = True
-            delta = deltas[0]
-        else:
-            pos = trans.searchsorted(arr, side="right") - 1
-            use_pytz = typ == "pytz"
-
-    for i in range(n):
-        new_tz = tz
-        value = arr[i]
-
-        if value == NPY_NAT:
-            result[i] = <object>NaT
-        else:
-            if use_utc:
-                local_value = value
-            elif use_tzlocal:
-                local_value = tz_convert_utc_to_tzlocal(value, tz)
-            elif use_fixed:
-                local_value = value + delta
-            elif not use_pytz:
-                # i.e. dateutil
-                # no zone-name change for dateutil tzs - dst etc
-                # represented in single object.
-                local_value = value + deltas[pos[i]]
-            else:
-                # pytz
-                # find right representation of dst etc in pytz timezone
-                new_tz = tz._tzinfos[tz._transition_info[pos[i]]]
-                local_value = value + deltas[pos[i]]
-
-            dt64_to_dtstruct(local_value, &dts)
-            result[i] = func_create(value, dts, new_tz, freq, fold)
-
-    return result
-
-
 def _test_parse_iso8601(ts: str):
     """
     TESTING ONLY: Parse string into Timestamp using iso8601 parser. Used

pandas/_libs/tslibs/__init__.py

@@ -11,8 +11,13 @@
     "Period",
     "Resolution",
     "Timedelta",
+    "normalize_i8_timestamps",
+    "is_date_array_normalized",
+    "dt64arr_to_periodarr",
     "delta_to_nanoseconds",
+    "ints_to_pydatetime",
     "ints_to_pytimedelta",
+    "get_resolution",
     "Timestamp",
     "tz_convert_single",
     "to_offset",
@@ -30,3 +35,10 @@
 from .timedeltas import Timedelta, delta_to_nanoseconds, ints_to_pytimedelta
 from .timestamps import Timestamp
 from .tzconversion import tz_convert_single
+from .vectorized import (
+    dt64arr_to_periodarr,
+    get_resolution,
+    ints_to_pydatetime,
+    is_date_array_normalized,
+    normalize_i8_timestamps,
+)

pandas/_libs/tslibs/conversion.pxd

@@ -25,5 +25,4 @@ cdef int64_t get_datetime64_nanos(object val) except? -1
 cpdef datetime localize_pydatetime(datetime dt, object tz)
 cdef int64_t cast_from_unit(object ts, str unit) except? -1
 
-cpdef ndarray[int64_t] normalize_i8_timestamps(const int64_t[:] stamps, tzinfo tz)
 cdef int64_t normalize_i8_stamp(int64_t local_val) nogil