def test_get_data_at_different_levels(self):
file_path = os.path.join(DATA_DIR,
"exp_pers_amne_gy_kommun_amne_2018.xml")
with open(file_path) as f:
content = f.read()
data = [x for x in get_data_from_xml(content)]
assert data[0]["niva"] == "kommun"
def test_get_data_from_xml_with_uttag_dimension(self):
file_path = os.path.join(DATA_DIR,
"exp_pers_amne_gr_skola_2014_sample.xml")
with open(file_path) as f:
content = f.read()
data = [x for x in get_data_from_xml(content)]
assert data[0]["uttag"] == "2015-08-17"
def test_get_data_from_xml_with_amne_dimension(self):
file_path = os.path.join(DATA_DIR, "exp_personal_alder_gr_kommun_2017_sample.xml")
with open(file_path) as f:
content = f.read()
data = [x for x in get_data_from_xml(content)]
assert "amne" in data[0]
assert data[0]["amne"] == u"Samtliga lärare"
def get_data_from_xml(self):
file_path = os.path.join(DATA_DIR, "exp_kostnader_kommun_fklass_2016.xml")
with open(file_path) as f:
content = f.read()
data = [x for x in get_data_from_xml(content)]
assert len(data) == 1740
assert data[0]["niva"] == "skola"
def _fetch_data(self, dataset, query):
"""Make the actual query.
The only queryable dimensions are period.
>>> dataset.fetch({"period": "2016"})
>>> dataset.fetch({"period": ["2015", "2016"]})
>>> dataset.fetch({"period": "*"}) # Get all periods
"""
default_query = {
"period": dataset.latest_period[1],
}
if query is None:
query = {}
default_query.update(query)
query = default_query
allowed_query_dims = ["period"]
for dim in query.keys():
if dim not in allowed_query_dims:
msg = "Querying on {} is not implemented yet".format(dim)
raise NotImplementedError(msg)
if query["period"] == "*":
periods = [x[1] for x in dataset.periods]
else:
if not isinstance(query["period"], list):
periods = [query["period"]]
else:
periods = query["period"]
# Get the period id's needed to build url
periods = [dataset._get_period_id(x) for x in periods]
for period in periods:
# Hack: For datasets with multiple uttag we get the latest
# This should rather be a part of query
if dataset.has_uttag:
uttag = dataset.get_latest_uttag(period)[0]
else:
uttag = None
url = dataset.get_xml_url(period, uttag)
xml_data = self._get_html(url)
for datapoint in get_data_from_xml(xml_data):
value = datapoint["value"]
del datapoint["value"]
yield Result(value, datapoint)