get dataset coordinates from describe parts instead of only at service variables

[veenstrajelmer]

As originally described in Deltares/dfm_tools#1082, it would be useful to easily get the coordinates from a part that is returned by describe. Or maybe even from the dataset version, so one level up. For instance, getting the time extents is currently a bit cumbersome and not so robust since they are only available at the variables of the service:

import copernicusmarine
import pandas as pd
# importing a private xarray function here
from xarray.coding.times import decode_cf_datetime

data = copernicusmarine.describe(
    dataset_id='cmems_mod_glo_phy-cur_anfc_0.083deg_P1D-m',
    disable_progress_bar=True,
    )

def convert_time(time_raw, time_units):
    time_np = decode_cf_datetime(num_dates=[time_raw], units=time_units)
    time_pd = pd.Timestamp(time_np[0])
    return time_pd

# check if there is indeed only one of products/datasets/versions/parts
assert len(data.products) == 1
assert len(data.products[0].datasets) == 1
assert len(data.products[0].datasets[0].versions) == 1
assert len(data.products[0].datasets[0].versions[0].parts) == 1

# there are four services, but only geoseries and timeseries contain coordinates in their data variables.
# I expect that in the service "original-files" the time values 
# would be 12 hours different from those in geoseries/timeseries (netcdf vs ARCO)
part = data.products[0].datasets[0].versions[0].parts[0]
service_arco_geo_series = part.get_service_by_service_name(service_name="arco-geo-series")

# Therefore, we get the coordinates from the first data variable in the service.
# We assume now that all data variables contain the coordinates, might be tricky
# It would be useful to attach the coordinates also to the service itself,
# since I expect these are valid here. This would avoid some nesting
var0 = service_arco_geo_series.variables[0]
var0_coordinates = var0.coordinates

# get time coordinate by searching for coordinate_id="time"
coordinate_ids = [x.coordinate_id for x in var0_coordinates]
timecoord_idx = coordinate_ids.index("time")
time_coord = var0_coordinates[timecoord_idx]

# the time extents are raw numbers w.r.t. a reference date
time_units = time_coord.coordinate_unit
time_min_raw = time_coord.minimum_value
time_max_raw = time_coord.maximum_value

# convert to pandas timestamps
time_min = convert_time(time_min_raw, time_units)
time_max = convert_time(time_max_raw, time_units)
print(f"Minimum Value: {time_min}")
print(f"Maximum Value: {time_max}")