def convert_to_name_pair(dct):
""" Converts a dictionary {'family':'Last','given':'First'} to ('First','Last') """
result = None
if 'family' in dct and 'given' in dct:
result = (dct['given'],dct['family'])
elif 'family' in dct: # The 'Arvind' case
result = ('',dct['family'])
elif 'literal' in dct:
result = parse_comma_name(dct['literal'])
if result:
result = (normalize_name_words(result[0]), normalize_name_words(result[1]))
return result
def convert_to_name_pair(dct):
""" Converts a dictionary {'family':'Last','given':'First'} to ('First','Last') """
result = None
if 'family' in dct and 'given' in dct:
result = (dct['given'],dct['family'])
elif 'family' in dct: # The 'Arvind' case
result = ('',dct['family'])
elif 'literal' in dct:
result = parse_comma_name(dct['literal'])
if result:
result = (normalize_name_words(result[0]), normalize_name_words(result[1]))
return result
def name(self):
"""
Returns a parsed version of the "credit name" in the ORCID profile.
If there is no such name, returns the given and family names on the profile
(they should exist)
"""
name_item = jpath('orcid-profile/orcid-bio/personal-details', self.json)
name = jpath('credit-name/value', name_item)
if name is not None:
return parse_comma_name(name)
return (normalize_name_words(jpath('given-names/value', name_item, '')),
normalize_name_words(jpath('family-name/value', name_item, '')))
def name(self):
"""
Returns a parsed version of the "credit name" in the ORCID profile.
If there is no such name, returns the given and family names on the profile
(they should exist)
"""
name_item = jpath('person/name', self.json)
name = jpath('credit-name/value', name_item)
if name:
return parse_comma_name(name)
return (normalize_name_words(jpath('given-names/value', name_item,
'')),
normalize_name_words(jpath('family-name/value', name_item,
'')))
def import_from_tsv(filename):
f = open(filename, 'r', 'utf-8')
for line in f:
fields = line.strip().split('\t')
print fields
dept = fields[dept_f]
(department, found) = Department.objects.get_or_create(name__iexact=dept,
defaults={'name':dept.strip()})
email = fields[email_f]
if email == '':
email = None
first = fields[first_name_f]
last = normalize_name_words(fields[last_name_f])
homepage = fields[url_f]
role = fields[role_f]
if homepage == '':
homepage = None
try:
researcher = Researcher.create_from_scratch(first, last, department, email, role, homepage)
except ValueError:
print "ValueError"
continue
group = fields[group_f]
if group:
g, created = ResearchGroup.objects.get_or_create(name=group)
researcher.groups.add(g)
def other_names(self):
"""
Returns the list of other names listed on the ORCiD profile.
This includes the (given,family) name if a credit name was defined.
"""
name_item = jpath('orcid-profile/orcid-bio/personal-details', self.json)
names = []
credit_name = jpath('credit-name/value', name_item)
if credit_name is not None:
names.append((normalize_name_words(jpath('given-names/value', name_item)),
normalize_name_words(jpath('family-name/value', name_item))))
other_names = jpath('other-names/other-name', name_item, default=[])
for name in other_names:
val = name.get('value')
if val is not None:
names.append(parse_comma_name(val))
return names
def newUnaffiliatedResearcher(request):
form = AddUnaffiliatedResearcherForm(request.POST)
researcher = None
if form.is_valid():
first = normalize_name_words(form.cleaned_data['first'])
last = normalize_name_words(form.cleaned_data['last'])
# Check that the researcher is not already known under a different name.
if not form.cleaned_data.get('force'):
name, created = Name.get_or_create(first, last)
candidates = researcherCandidatesByName(name)
if candidates:
return {'disambiguation': candidates}
researcher = Researcher.create_by_name(first, last)
researcher.fetch_everything_if_outdated()
return {'url': researcher.url}
else:
return form.errors, 403
def newUnaffiliatedResearcher(request):
form = AddUnaffiliatedResearcherForm(request.POST)
researcher = None
if form.is_valid():
first = normalize_name_words(form.cleaned_data['first'])
last = normalize_name_words(form.cleaned_data['last'])
# Check that the researcher is not already known under a different name.
if not form.cleaned_data.get('force'):
name, created = Name.get_or_create(first, last)
candidates = researcherCandidatesByName(name)
if candidates:
return {'disambiguation':candidates}
researcher = Researcher.create_by_name(first, last)
researcher.fetch_everything_if_outdated()
return {'url':researcher.url}
else:
return form.errors, 403
def other_names(self):
"""
Returns the list of other names listed on the ORCiD profile.
This includes the (given,family) name if a credit name was defined.
"""
person = jpath('person', self.json)
names = []
credit_name = jpath('name/credit-name/value', person)
if credit_name is not None:
names.append((normalize_name_words(
jpath('name/given-names/value', person, '')),
normalize_name_words(
jpath('name/family-name/value', person, ''))))
other_names = jpath('other-names/other-name', person, default=[])
for name in other_names:
val = name.get('content')
if val is not None:
names.append(parse_comma_name(val))
return names
def test_involutive(self):
lst = [
'Jean',
'Jean-Pierre',
'John Mark',
'JEAN-PIERRE',
'JOHN MARK',
'JOSÉ',
'JOSÉ-ALAIN',
'José',
'ÉMILIE',
'Émilie',
'John Mark',
'Jean - Pierre',
'J.P. Morgan',
'JP. Morgan',
'Jp. Morgan',
]
for sample in lst:
normalized = normalize_name_words(sample)
self.assertEqual(normalized, normalize_name_words(normalized))
def other_names(self):
"""
Returns the list of other names listed on the ORCiD profile.
This includes the (given,family) name if a credit name was defined.
"""
name_item = jpath('orcid-profile/orcid-bio/personal-details',
self.json)
names = []
credit_name = jpath('credit-name/value', name_item)
if credit_name is not None:
names.append(
(normalize_name_words(jpath('given-names/value', name_item,
'')),
normalize_name_words(jpath('family-name/value', name_item,
''))))
other_names = jpath('other-names/other-name', name_item, default=[])
for name in other_names:
val = name.get('value')
if val is not None:
names.append(parse_comma_name(val))
return names
def test_involutive(self):
lst = [
'Jean',
'Jean-Pierre',
'John Mark',
'JEAN-PIERRE',
'JOHN MARK',
'JOSÉ',
'JOSÉ-ALAIN',
'José',
'ÉMILIE',
'Émilie',
'John Mark',
'Jean - Pierre',
'J.P. Morgan',
'JP. Morgan',
'Jp. Morgan',
]
for sample in lst:
normalized = normalize_name_words(sample)
self.assertEqual(normalized, normalize_name_words(normalized))
def test_simple(self):
self.assertEqual(normalize_name_words('Jean'), 'Jean')
self.assertEqual(normalize_name_words('Jean-Pierre'), 'Jean-Pierre')
self.assertEqual(normalize_name_words('Jean-pierre'), 'Jean-Pierre')
self.assertEqual(normalize_name_words('John Mark'), 'John Mark')
self.assertEqual(normalize_name_words('JEAN-PIERRE'), 'Jean-Pierre')
self.assertEqual(normalize_name_words('JOHN MARK'), 'John Mark')
def test_simple(self):
self.assertEqual(normalize_name_words('Jean'), 'Jean')
self.assertEqual(normalize_name_words('Jean-Pierre'), 'Jean-Pierre')
self.assertEqual(normalize_name_words('Jean-pierre'), 'Jean-Pierre')
self.assertEqual(normalize_name_words('John Mark'), 'John Mark')
self.assertEqual(normalize_name_words('JEAN-PIERRE'), 'Jean-Pierre')
self.assertEqual(normalize_name_words('JOHN MARK'), 'John Mark')
def test_flattened(self):
self.assertEqual(normalize_name_words('JP.'), 'J.-P.')
self.assertEqual(normalize_name_words('Jp.'), 'J.-P.')
def test_comma(self):
self.assertEqual(normalize_name_words('John, Mark'), 'John Mark')
self.assertEqual(normalize_name_words('John,, Mark'), 'John Mark')
self.assertEqual(normalize_name_words('John Mark,'), 'John Mark')
self.assertEqual(normalize_name_words('John Mark,,'), 'John Mark')
self.assertEqual(normalize_name_words('John, Mark,,'), 'John Mark')
def test_lower(self):
self.assertEqual(normalize_name_words('catalin'), 'Catalin')
self.assertEqual(normalize_name_words('Colin de Verdière'),
'Colin de Verdière')
def test_flattened(self):
self.assertEqual(normalize_name_words('JP.'), 'J.-P.')
self.assertEqual(normalize_name_words('Jp.'), 'J.-P.')
def test_spacing(self):
self.assertEqual(normalize_name_words('John Mark'), 'John Mark')
self.assertEqual(normalize_name_words(' John Mark'), 'John Mark')
self.assertEqual(normalize_name_words(' John Mark \n'), 'John Mark')
self.assertEqual(normalize_name_words('Jean - Pierre'), 'Jean-Pierre')
self.assertEqual(normalize_name_words('J.P.'), 'J. P.')
def test_unicode(self):
self.assertEqual(normalize_name_words('JOSÉ'), 'José')
self.assertEqual(normalize_name_words('JOSÉ-ALAIN'), 'José-Alain')
self.assertEqual(normalize_name_words('José'), 'José')
self.assertEqual(normalize_name_words('ÉMILIE'), 'Émilie')
self.assertEqual(normalize_name_words('Émilie'), 'Émilie')
def test_lower(self):
self.assertEqual(normalize_name_words('catalin'), 'Catalin')
self.assertEqual(normalize_name_words(
'Colin de Verdière'), 'Colin de Verdière')
def test_unicode(self):
self.assertEqual(normalize_name_words('JOSÉ'), 'José')
self.assertEqual(normalize_name_words('JOSÉ-ALAIN'), 'José-Alain')
self.assertEqual(normalize_name_words('José'), 'José')
self.assertEqual(normalize_name_words('ÉMILIE'), 'Émilie')
self.assertEqual(normalize_name_words('Émilie'), 'Émilie')
def test_spacing(self):
self.assertEqual(normalize_name_words('John Mark'), 'John Mark')
self.assertEqual(normalize_name_words(' John Mark'), 'John Mark')
self.assertEqual(normalize_name_words(' John Mark \n'), 'John Mark')
self.assertEqual(normalize_name_words('Jean - Pierre'), 'Jean-Pierre')
self.assertEqual(normalize_name_words('J.P.'), 'J. P.')
def test_comma(self):
self.assertEqual(normalize_name_words('John, Mark'), 'John Mark')
self.assertEqual(normalize_name_words('John,, Mark'), 'John Mark')
self.assertEqual(normalize_name_words('John Mark,'), 'John Mark')
self.assertEqual(normalize_name_words('John Mark,,'), 'John Mark')
self.assertEqual(normalize_name_words('John, Mark,,'), 'John Mark')
