def create_geo_coordinate_from(content: str,
**kwargs) -> wdi_core.WDGlobeCoordinate:
""" Create a WDGlobecoordinate object from the point representation in a str. """
latitude, longitude = content[5:].strip('()').split(" ")
precision = max(latitude[::-1].find('.'), longitude[::-1].find('.'))
return wdi_core.WDGlobeCoordinate(float(latitude), float(longitude),
precision, **kwargs)
def test_geocoordinates_mapping():
result = datatype2wdiobject[f"{GEO_BASE}wktLiteral"]("Point(36.834 2.463)",
prop_nr=-1)
expected = wdi_core.WDGlobeCoordinate(latitude=36.834,
longitude=2.463,
precision=3,
prop_nr=-1)
assert result == expected
def test_new_item_creation(self):
data = [
wdi_core.WDString(value='test', prop_nr='P1'),
wdi_core.WDString(value='test1', prop_nr='P2'),
wdi_core.WDMath("xxx", prop_nr="P3"),
wdi_core.WDExternalID("xxx", prop_nr="P4"),
wdi_core.WDItemID("Q123", prop_nr="P5"),
wdi_core.WDTime('+%Y-%m-%dT%H:%M:%SZ', "P6"),
wdi_core.WDUrl("http://www.google.com", "P7"),
wdi_core.WDMonolingualText("xxx", prop_nr="P8"),
wdi_core.WDQuantity(5, prop_nr="P9"),
wdi_core.WDQuantity(5, upper_bound=9, lower_bound=2,
prop_nr="P10"),
wdi_core.WDCommonsMedia("xxx", prop_nr="P11"),
wdi_core.WDGlobeCoordinate(1.2345, 1.2345, 12, prop_nr="P12"),
wdi_core.WDGeoShape("xxx", prop_nr="P13"),
wdi_core.WDProperty("P123", "P14")
]
core_props = set(["P{}".format(x) for x in range(20)])
for d in data:
item = wdi_core.WDItemEngine(item_name='dae',
domain="szadf",
data=[d],
core_props=core_props)
assert item.get_wd_json_representation()
item = wdi_core.WDItemEngine(item_name='dae',
domain="szadf",
data=[d],
core_props=set())
assert item.get_wd_json_representation()
item = wdi_core.WDItemEngine(item_name='dae',
domain="szadf",
data=data,
core_props=core_props)
assert item.get_wd_json_representation()
item = wdi_core.WDItemEngine(item_name='dae',
domain="szadf",
data=data,
core_props=set())
assert item.get_wd_json_representation()
description="License"),
prop_nr="P5"))
data.append(
wdi_core.WDUrl(observations[observation]["url"], prop_nr="P6"))
for image_url in observations[observation]["image_url"]:
try:
data.append(
wdi_core.WDUrl(image_url.split("?")[0].replace(
"medium", "original"),
prop_nr="P7"))
except:
pass
data.append(
wdi_core.WDGlobeCoordinate(
latitude=observations[observation]["latitude"],
longitude=observations[observation]["longitude"],
precision=0.016666666666667,
prop_nr="P8"))
data.append(
wdi_core.WDItemID(value=get_or_createItem(
observations[observation]["scientific_name"],
description="Scientific taxon name"),
prop_nr="P9"))
# data.append(wdiobservations[observation]["taxon_id"], prop_nr="P10")
item = wikibaseEntityEngine(data=data)
item.set_label("iNaturalist observation " + observation, lang="en")
item.set_description("Observation of " +
observations[observation]["scientific_name"],
lang="en")
# pprint.pprint(item.get_wd_json_representation())
def create_grid_item(grid_data, grid_id, grid_release_item_id, login_instance):
reference_info = [
wdi_core.WDItemID(grid_release_item_id, 'P248', is_reference=True),
wdi_core.WDExternalID(grid_id, p_grid_id, is_reference=True)
]
base_data = grid_data.base_data_for_id(grid_id)
org_name = base_data['label']
org_description = base_data['description']
org_type_qid = base_data['type_qid']
org_country_qid = base_data['country_qid']
website = base_data['website']
org_inception = base_data['inception']
latitude = base_data['latitude']
longitude = base_data['longitude']
org_aliases = grid_data.aliases_for_id(grid_id)
org_labels = grid_data.labels_for_id(grid_id)
statements = []
statements.append(
wdi_core.WDItemID(org_type_qid,
p_instance_of,
references=[reference_info]))
statements.append(
wdi_core.WDExternalID(grid_id, p_grid_id, references=[reference_info]))
if org_country_qid:
statements.append(
wdi_core.WDItemID(org_country_qid,
p_country,
references=[reference_info]))
if website and (len(website) < 500):
statements.append(
wdi_core.WDUrl(website,
p_official_website,
references=[reference_info]))
if org_inception and (int(org_inception) > 900):
org_inception_date = datetime.date(int(org_inception), 1, 1)
statements.append(
wdi_core.WDTime(
org_inception_date.strftime('+%Y-%m-%dT%H:%M:%SZ'),
p_inception,
precision=9,
references=[
reference_info
])) # year-level precision in inception dates from GRID
if latitude and longitude and (abs(latitude) <= 90.0) and (abs(longitude)
<= 360.0):
precision = 1.0
longitude_parts = str(longitude).split('.')
if len(longitude_parts) > 1:
exp = len(longitude_parts[1])
precision = pow(10.0, -exp)
statements.append(
wdi_core.WDGlobeCoordinate(float(latitude),
float(longitude),
precision,
p_coordinate_location,
references=[reference_info]))
wd_item = wdi_core.WDItemEngine(data=statements)
wd_item.set_label(label=org_name, lang='en')
wd_item.set_description(description=org_description, lang='en')
if org_aliases and len(org_aliases) > 0:
wd_item.set_aliases(org_aliases, lang='en')
for label_hash in org_labels:
if label_hash['language'] == 'en':
wd_item.set_aliases([label_hash['label']], 'en', append=True)
else:
wd_item.set_label(label=label_hash['label'],
lang=label_hash['language'])
new_item_id = wd_item.write(
login_instance,
edit_summary=
'Creating item from GRID record via APSbot_grid_create script (APSbot task 3)'
)
print("created {0}".format(new_item_id))
def initiate(self):
dfWikibaseItems = pd.DataFrame
#wd_item = wdi_core.WDItemEngine(data=data) # create new item
#wd_item.entity_metadata.get('id') #retriev item id
columns_inst = [
1, 7, 8, 9, 19, 11, 12, 13, 14, 15, 16, 17, 18, 19, 20, 21, 22, 23,
24, 25, 26, 27, 28, 29, 30, 31, 32, 33, 34, 35, 36, 37
]
columns_Instituicao = [
'_pageName', 'tipo', 'data_fundação', 'data_extinção',
'paralisação_início', 'paralisação_fim', 'Localização1',
'Localização_data_início1', 'Localização_data_fim1',
'Localização2', 'Localização_data_início2',
'Localização_data_fim2', 'Localização3',
'Localização_data_início3', 'Localização_data_fim3',
'Localização4', 'Localização_data_início4',
'Localização_data_fim4', 'Localização5',
'Localização_data_início5', 'Localização_data_fim5',
'Localização6', 'Localização_data_início6',
'Localização_data_fim6', 'Localização7',
'Localização_data_início7', 'Localização_data_fim7',
'Localização8', 'Localização_data_início8',
'Localização_data_fim8', 'antecessora', 'sucessora'
]
columns_Coordenada = ['_pageName', '1', '5']
r_file = open(datasetpath + coord_file, 'rb').read()
result = chardet.detect(r_file)
file_encoding = result['encoding']
dfInstituicao = pd.read_csv(datasetpath + instituicao_file,
encoding=file_encoding,
header=0,
usecols=columns_inst)
dfCoordenadas = pd.read_csv(datasetpath + coord_file,
encoding=file_encoding,
header=0,
nrows=175,
usecols=columns_Coordenada)
dfCoordenadas_Encode = pd.read_csv(datasetpath + coord_file,
encoding=file_encoding,
header=0,
skiprows=175)
#,usecols=columns_Coordenada)
dfCoordenadas = dfCoordenadas.reindex(
columns=dfCoordenadas.columns.tolist())
dataCoordNames = dfCoordenadas['_pageName'].replace(' ',
'_',
regex=True)
#dataTemp = dataTemp.replace(['\[','\]'], ['',''], regex=True)
coordenadas = {}
#print(dataCoordNames.head(10))
#frame = pd.DataFrame(dataTemp['_pageName'])
#print(dataCoordNames.values)
for i in range(len(dfCoordenadas)):
coord_name = dfCoordenadas['_pageName']
url_coord = URL_EVITERBO + dfCoordenadas['_pageName'].replace(
' ', '_', regex=True)
lat = dfCoordenadas['1']
long = dfCoordenadas['5']
data = [
wdi_core.WDUrl(prop_nr='P30', value=url_coord),
wdi_core.WDGlobeCoordinate(prop_nr='P29',
latitude=lat,
longitude=long,
precision=0.0001),
wdi_core.WDString(prop_nr='P45',
value=dfCoordenadas['_pageName'])
]
# wd_item = wdi_core.WDItemEngine(data=data) # create new item
# wd_item.set_label(label=dfCoordenadas['_pageName'],lang='pt')
item_id = 'Q001' #wd_item.entity_metadata.get('id') #retrieve item id
# wd_item.write(self.login_instance)
coordenadas = {
'nome':
dfCoordenadas['_pageName'],
'urleviterbo':
URL_EVITERBO +
dfCoordenadas['_pageName'].replace(' ', '_', regex=True),
'coord_1':
dfCoordenadas['1'],
'coord_5':
dfCoordenadas['5'],
'item_id':
item_id
}
if isinstance(row["familyKey"], int):
item_data.append(
wdi_core.WDExternalID(str(row["familyKey"]), prop_nr="P39"))
if isinstance(row["genusKey"], int):
item_data.append(
wdi_core.WDExternalID(str(row["genusKey"]), prop_nr="P40"))
if isinstance(row["subgenusKey"], int):
item_data.append(
wdi_core.WDExternalID(str(row["subgenusKey"]), prop_nr="P41"))
if isinstance(row["speciesKey"], int):
item_data.append(
wdi_core.WDExternalID(str(row["speciesKey"]), prop_nr="P42"))
if row["decimalLatitude"] != "":
item_data.append(
wdi_core.WDGlobeCoordinate(row["decimalLatitude"],
row["decimalLongitude"],
precision=0.016666666666667,
prop_nr="P45"))
for index2, row2 in multimediaSelection[multimediaSelection["gbifID"] ==
row["gbifID"]].iterrows():
qualifiers = []
creatorQID = wdi_core.WDItemEngine.get_wd_search_results(
search_string=row2["creator"], mediawiki_api_url=api)
if len(creatorQID) == 0:
creator_item = wdi_core.WDItemEngine(new_item=True,
mediawiki_api_url=api,
sparql_endpoint_url=sparql)
creator_item.set_label(row2["creator"], lang="en")
try_write(creator_item,
record_id=row2["creator"],
record_prop="",