def test_search_inlet_no_instrument(crds_read):
locations = "hfd"
inlet = "100m"
species = "CH4"
results = search(locations=locations, species=species, inlet=inlet)
expected_keys = ["ch4_hfd_100m_picarro"]
assert list(results.keys()) == expected_keys
assert len(results["ch4_hfd_100m_picarro"]["keys"]
["2013-11-20-20:02:30_2019-07-04-21:29:30"]) == 25
expected_metadata = {
'site': 'hfd',
'instrument': 'picarro',
'time_resolution': '1_minute',
'inlet': '100m',
'port': '10',
'type': 'air',
'species': 'ch4',
'data_type': 'timeseries',
'scale': 'wmo-x2004a'
}
assert results["ch4_hfd_100m_picarro"]["metadata"] == expected_metadata
def test_search_nonsense_terms():
species = ["spam", "eggs", "terry"]
locations = ["capegrim"]
results = search(species=species, locations=locations)
assert not results
def test_search_find_all():
species = ["co2"]
locations = ["bsd"]
inlet = "108m"
instrument = "picarro"
start = get_datetime(year=2016, month=1, day=1)
end = get_datetime(year=2017, month=1, day=1)
results = search(species=species,
locations=locations,
find_all=True,
start_datetime=start,
end_datetime=end,
inlet=inlet,
instrument=instrument)
bsd_results = results["co2_bsd_108m_picarro"]
assert bsd_results["metadata"]["site"] == "bsd"
assert bsd_results["metadata"]["species"] == "co2"
assert bsd_results["metadata"]["time_resolution"] == "1_minute"
key_dates = [daterange.split("/")[-1] for daterange in bsd_results["keys"]]
assert key_dates == ['2016-01-19-17:17:30_2016-11-30-22:57:30']
def test_recombination_CRDS():
get_local_bucket(empty=True)
filename = "hfd.picarro.1minute.100m.min.dat"
filepath = get_datapath(filename=filename, data_type="CRDS")
crds = CRDS()
ObsSurface.read_file(filepath, data_type="CRDS")
gas_data = crds.read_data(data_filepath=filepath, site="HFD")
ch4_data_read = gas_data["ch4"]["data"]
gas_name = "ch4"
location = "hfd"
keys = search(species=gas_name, locations=location)
to_download = keys["ch4_hfd_100m_picarro"]["keys"][
"2013-12-04-14:02:30_2019-05-21-15:46:30"]
ch4_data_recombined = recombine_sections(data_keys=to_download)
ch4_data_recombined.attrs = {}
assert ch4_data_read.time.equals(ch4_data_recombined.time)
assert ch4_data_read["ch4"].equals(ch4_data_recombined["ch4"])
def test_search_incorrect_inlet_site_finds_nothing(crds_read):
locations = "hfd"
inlet = "3695m"
species = "CH4"
results = search(locations=locations, species=species, inlet=inlet)
assert not results
def test_search_no_species(crds_read):
locations = "bsd"
results = search(locations=locations)
expected_keys = sorted([
'ch4_bsd_248m_picarro', 'co2_bsd_248m_picarro', 'co_bsd_248m_picarro',
'co_bsd_108m_picarro5310', 'n2o_bsd_108m_picarro5310',
'ch4_bsd_108m_picarro', 'co2_bsd_108m_picarro', 'co_bsd_108m_picarro',
'co_bsd_248m_picarro5310', 'n2o_bsd_248m_picarro5310'
])
assert sorted(list(results.keys())) == expected_keys
def test_search_gc(gc_read):
results = search(species=["NF3"], locations="capegrim")
nf3_results = results["nf3_cgo_75m_4_medusa"]
metadata = {
"site": "cgo",
"instrument": "medusa",
"species": "nf3",
"units": "ppt",
"scale": "sio-12",
"inlet": "75m_4",
"data_type": "timeseries",
}
assert "2018-01-01-02:24:00_2018-01-31-23:33:00" in nf3_results["keys"]
assert nf3_results["metadata"] == metadata
def test_search_instrument_no_inlet(crds_read):
locations = "bsd"
species = "n2o"
instrument = "picarro5310"
results = search(locations=locations,
species=species,
instrument=instrument)
expected_keys = ["n2o_bsd_108m_picarro5310", "n2o_bsd_248m_picarro5310"]
assert sorted(list(results.keys())) == sorted(expected_keys)
assert len(results["n2o_bsd_108m_picarro5310"]["keys"]
["2019-03-06-14:03:30_2020-07-04-11:44:30"]) == 7
assert len(results["n2o_bsd_248m_picarro5310"]["keys"]
["2019-03-06-13:23:30_2020-07-05-03:38:30"]) == 7
metadata_108m = {
'site': 'bsd',
'instrument': 'picarro5310',
'time_resolution': '1_minute',
'inlet': '108m',
'port': '2',
'type': 'air',
'species': 'n2o',
'data_type': 'timeseries',
'scale': 'wmo-x2006a'
}
metadata_248m = {
'site': 'bsd',
'instrument': 'picarro5310',
'time_resolution': '1_minute',
'inlet': '248m',
'port': '1',
'type': 'air',
'species': 'n2o',
'data_type': 'timeseries',
'scale': 'wmo-x2006a'
}
assert results["n2o_bsd_108m_picarro5310"]["metadata"] == metadata_108m
assert results["n2o_bsd_248m_picarro5310"]["metadata"] == metadata_248m
def test_recombination_GC():
get_local_bucket(empty=True)
gc = GCWERKS()
data = get_datapath(filename="capegrim-medusa.18.C", data_type="GC")
precision = get_datapath(filename="capegrim-medusa.18.precisions.C",
data_type="GC")
ObsSurface.read_file((data, precision), data_type="GCWERKS")
data = gc.read_data(data_filepath=data,
precision_filepath=precision,
site="CGO",
instrument="medusa")
toluene_data = data["toluene"]["data"]
gas_name = "toluene"
location = "CGO"
keys = search(species=gas_name, locations=location)
to_download = keys["toluene_cgo_75m_4_medusa"]["keys"][
"2018-01-01-02:24:00_2018-01-31-23:33:00"]
toluene_data_recombined = recombine_sections(data_keys=to_download)
toluene_data.attrs = {}
toluene_data_recombined.attrs = {}
assert toluene_data.time.equals(toluene_data_recombined.time)
assert toluene_data["toluene"].equals(toluene_data_recombined["c6h5ch3"])
assert toluene_data["toluene repeatability"].equals(
toluene_data_recombined["c6h5ch3_repeatability"])
assert toluene_data["toluene status_flag"].equals(
toluene_data_recombined["c6h5ch3_status_flag"])
assert toluene_data["toluene integration_flag"].equals(
toluene_data_recombined["c6h5ch3_integration_flag"])
def test_location_search(crds_read):
species = ["co2", "ch4"]
locations = ["bsd", "hfd", "tac"]
start = None # get_datetime(year=2016, month=1, day=1)
end = None # get_datetime(year=2017, month=1, day=1)
results = search(
species=species,
locations=locations,
find_all=False,
start_datetime=start,
end_datetime=end,
)
results_list = sorted(list(results.keys()))
expected = sorted([
'ch4_bsd_108m_picarro', 'ch4_bsd_248m_picarro', 'ch4_hfd_100m_picarro',
'ch4_tac_100m_picarro', 'co2_bsd_108m_picarro', 'co2_bsd_248m_picarro',
'co2_hfd_100m_picarro', 'co2_tac_100m_picarro'
])
assert results_list == expected
assert len(results["co2_bsd_108m_picarro"]["keys"]
['2014-01-30-13:33:30_2019-07-04-04:23:30']) == 23
assert len(results["co2_hfd_100m_picarro"]["keys"]
['2013-11-20-20:02:30_2019-07-04-21:29:30']) == 25
assert len(results["co2_tac_100m_picarro"]["keys"]
['2012-07-26-12:01:30_2019-07-04-09:58:30']) == 30
assert len(results["ch4_bsd_108m_picarro"]["keys"]
['2014-01-30-13:33:30_2019-07-04-04:23:30']) == 23
assert len(results["ch4_hfd_100m_picarro"]["keys"]
['2013-11-20-20:02:30_2019-07-04-21:29:30']) == 25
assert len(results["ch4_tac_100m_picarro"]["keys"]
['2012-07-26-12:01:30_2019-07-04-09:58:30']) == 30
def test_search_datetimes():
species = ["co2"]
locations = ["bsd"]
start = get_datetime(year=2016, month=1, day=1)
end = get_datetime(year=2017, month=1, day=1)
results = search(
species=species,
locations=locations,
find_all=False,
start_datetime=start,
end_datetime=end,
)
result_keys = results["co2_bsd_108m_picarro"]["keys"]
date_strings = [v.split("/")[-1] for v in result_keys]
assert date_strings == ['2016-01-19-17:17:30_2016-11-30-22:57:30']
metadata = results["co2_bsd_108m_picarro"]["metadata"]
expected_metadata = {
"site": "bsd",
"instrument": "picarro",
"time_resolution": "1_minute",
"inlet": "108m",
"port": "9",
"type": "air",
"species": "co2",
"data_type": "timeseries",
'scale': 'wmo-x2007'
}
assert metadata == expected_metadata
def test_search_bad_site_raises():
species = ["spam", "eggs", "terry"]
locations = ["tintagel"]
with pytest.raises(ValueError):
search(species=species, locations=locations)