Function _eagerly_encode_cf_datetime

xarray/coding/times.py:1064–1189

(
    dates: T_DuckArray,  # type: ignore[misc]
    units: str | None = None,
    calendar: str | None = None,
    dtype: np.dtype | None = None,
    allow_units_modification: bool = True,
)

def _eagerly_encode_cf_datetime(
    dates: T_DuckArray,  # type: ignore[misc]
    units: str | None = None,
    calendar: str | None = None,
    dtype: np.dtype | None = None,
    allow_units_modification: bool = True,
) -> tuple[T_DuckArray, str, str]:
    dates = asarray(dates)
    data_units = infer_datetime_units(dates)
    if units is None:
        units = data_units
    else:
        units = _cleanup_netcdf_time_units(units)

    if calendar is None:
        calendar = infer_calendar_name(dates)

    raise_incompatible_units_error = False
    raise_gregorian_proleptic_gregorian_mismatch_error = False
    try:
        if not _is_standard_calendar(calendar) or dates.dtype.kind == "O":
            # parse with cftime instead
            raise OutOfBoundsDatetime
        assert np.issubdtype(dates.dtype, "datetime64")
        if (
            calendar in ["standard", "gregorian"]
            and dates.size > 0
            and np.nanmin(dates).astype("=M8[us]").astype(datetime)
            < datetime(1582, 10, 15)
        ):
            raise_gregorian_proleptic_gregorian_mismatch_error = True

        time_unit, ref_date = _unpack_time_unit_and_ref_date(units)
        # calendar equivalence only for days after the reform
        _check_date_is_after_shift(ref_date, calendar)
        time_delta = np.timedelta64(1, time_unit)

        # Wrap the dates in a DatetimeIndex to do the subtraction to ensure
        # an OverflowError is raised if the ref_date is too far away from
        # dates to be encoded (GH 2272).
        # DatetimeIndex will convert to units of ["s", "ms", "us", "ns"]
        dates_as_index = pd.DatetimeIndex(ravel(dates))
        time_deltas = dates_as_index - ref_date

        # retrieve needed units to faithfully encode to int64
        needed_units = _infer_needed_units_numpy(ref_date, data_units)
        needed_time_delta = _unit_timedelta_numpy(needed_units)

        floor_division = np.issubdtype(dtype, np.integer) or dtype is None
        if time_delta > needed_time_delta:
            floor_division = False
            if dtype is None:
                emit_user_level_warning(
                    f"Times can't be serialized faithfully to int64 with requested units {units!r}. "
                    f"Resolution of {needed_units!r} needed. Serializing times to floating point instead. "
                    f"Set encoding['dtype'] to integer dtype to serialize to int64. "
                    f"Set encoding['dtype'] to floating point dtype to silence this warning."
                )