def test_update_ordered(tmppath):
p = tmppath / 'test'
with update_ordered(p) as obj:
obj['b'] = 2
obj['a'] = 1
with update_ordered(p) as obj:
assert list(obj.keys()) == ['b', 'a']
def run(args):
if fiona is None: # pragma: no cover
raise SystemExit(
'fiona and shapely must be installed for this command')
with fiona.collection(
str(args.repos.path("geo", "level2-shape/level2.shp")),
"r") as source:
regions = [f for f in source]
with update_ordered(args.repos.path("geo", "societies_tdwg.json"),
indent=4) as soc_tdwg:
for ds in args.repos.datasets:
for soc in ds.societies:
spec = soc_tdwg.get(
soc.id,
dict(lat=soc.Lat, lon=soc.Long, name=None, code=None))
if math.isclose(spec['lat'], soc.Lat) \
and math.isclose(spec['lon'], soc.Long) \
and spec['code']:
continue
region, dist = geo.match(spec['lon'], spec['lat'], regions)
spec['name'] = region['properties']['REGION_NAM']
spec['code'] = str(region['properties']['TDWG_CODE'])
if dist == 0: # pragma: no cover
args.log.info('{0} contained in region {1}'.format(
soc, spec['name']))
else:
args.log.warning(
'assigning {0} to nearest region {1}, distance {2}'.
format(soc, region['properties']['REGION_NAM'], dist))
soc_tdwg[soc.id] = spec
def update_gbif(self):
with update_ordered(self.path('gbif.json'), indent=4) as d:
api = gbif.GBIF()
for ex in self.experiments:
if ex.species_latin not in d:
try:
d[ex.species_latin] = api.species_data(
ex.species_latin)
except Exception as e:
print(ex.species_latin)
print(e)
continue
def run(args):
dataset = get_dataset(args)
dataset.concepticon = args.concepticon.api
dataset.glottolog = args.glottolog.api
with_dataset(args, 'makecldf', dataset=dataset)
if not dataset.cldf_dir.joinpath('sources.bib').exists():
raise ValueError('The dataset has no sources at {0}'.format(
dataset.cldf_dir.joinpath('sources.bib')))
creators, contributors = dataset.get_creators_and_contributors(
strict=False)
def contrib(d):
return {
k: v
for k, v in d.items()
if k in {'name', 'affiliation', 'orcid', 'type'}
}
with jsonlib.update_ordered(dataset.dir / '.zenodo.json', indent=4) as md:
md.update({
'title':
dataset.metadata.title,
"access_right":
"open",
"keywords":
sorted(
set(md.get('keywords', []) +
["linguistics", "cldf:Wordlist"])),
"creators": [contrib(p) for p in creators],
"contributors": [contrib(p) for p in contributors],
"communities":
sorted(md.get('communities', []) + [{
"identifier": "lexibank"
}],
key=lambda i: i['identifier']),
"upload_type":
"dataset",
})
if dataset.metadata.citation:
md['description'] = "<p>Cite the source of the dataset as:</p>\n\n" \
"<blockquote>\n<p>{}</p>\n</blockquote>".format(
html.escape(dataset.metadata.citation))
if dataset.metadata.zenodo_license:
md['license'] = {'id': dataset.metadata.zenodo_license}