def _process_crossref_name(self, contributor):
# Adapted from logic used in `api/citations/utils.py`
# If the user has a family and given name, use those
if contributor.family_name and contributor.given_name:
given = contributor.given_name
middle = contributor.middle_names
family = contributor.family_name
suffix = contributor.suffix
else:
names = impute_names(contributor.fullname)
given = names.get('given')
middle = names.get('middle')
family = names.get('family')
suffix = names.get('suffix')
given_name = ' '.join([given, middle]).strip()
given_stripped = remove_control_characters(given_name)
# For crossref, given_name is not allowed to have numbers or question marks
given_processed = ''.join(
[char for char in given_stripped if (not char.isdigit() and char != '?')]
)
surname_processed = remove_control_characters(family)
surname = surname_processed or given_processed or contributor.fullname
processed_names = {'surname': surname[:CROSSREF_SURNAME_LIMIT].strip()}
if given_processed and surname_processed:
processed_names['given_name'] = given_processed[:CROSSREF_GIVEN_NAME_LIMIT].strip()
if suffix and (surname_processed or given_processed):
processed_names['suffix'] = suffix[:CROSSREF_SUFFIX_LIMIT].strip()
return processed_names
def _process_crossref_name(self, contributor):
# Adapted from logic used in `api/citations/utils.py`
# If the user has a family and given name, use those
if contributor.family_name and contributor.given_name:
given = contributor.given_name
middle = contributor.middle_names
family = contributor.family_name
suffix = contributor.suffix
else:
names = impute_names(contributor.fullname)
given = names.get('given')
middle = names.get('middle')
family = names.get('family')
suffix = names.get('suffix')
given_name = ' '.join([given, middle]).strip()
given_stripped = remove_control_characters(given_name)
# For crossref, given_name is not allowed to have numbers or question marks
given_processed = ''.join([
char for char in given_stripped
if (not char.isdigit() and char != '?')
])
surname_processed = remove_control_characters(family)
surname = surname_processed or given_processed or contributor.fullname
processed_names = {'surname': surname[:CROSSREF_SURNAME_LIMIT].strip()}
if given_processed and surname_processed:
processed_names[
'given_name'] = given_processed[:
CROSSREF_GIVEN_NAME_LIMIT].strip(
)
if suffix and (surname_processed or given_processed):
processed_names['suffix'] = suffix[:CROSSREF_SUFFIX_LIMIT].strip()
return processed_names
def update_guessed_names(self):
"""Updates the CSL name fields inferred from the the full name.
"""
parsed = utils.impute_names(self.fullname)
self.given_name = parsed['given']
self.middle_names = parsed['middle']
self.family_name = parsed['family']
self.suffix = parsed['suffix']
def update_guessed_names(self):
"""Updates the CSL name fields inferred from the the full name.
"""
parsed = utils.impute_names(self.fullname)
self.given_name = parsed["given"]
self.middle_names = parsed["middle"]
self.family_name = parsed["family"]
self.suffix = parsed["suffix"]
def update_guessed_names(self):
"""Updates the CSL name fields inferred from the the full name.
"""
parsed = utils.impute_names(self.fullname)
self.given_name = parsed['given']
self.middle_names = parsed['middle']
self.family_name = parsed['family']
self.suffix = parsed['suffix']
def impute_names():
for user in models.User.find():
parsed = impute_names(user.fullname)
for field, value in parsed.items():
if getattr(user, field, None) is None:
setattr(user, field, value)
user.save()
def impute_names():
for user in models.User.find():
parsed = impute_names(user.fullname)
for field, value in parsed.items():
if getattr(user, field, None) is None:
setattr(user, field, value)
user.save()
def test_process_crossref_name(self, crossref_client):
contributor = AuthUserFactory()
# Given name and no family name
contributor.given_name = 'Hey'
contributor.family_name = ''
contributor.save()
meta = crossref_client._process_crossref_name(contributor)
imputed_names = impute_names(contributor.fullname)
assert meta == {'surname': imputed_names['family'], 'given_name': imputed_names['given']}
# Just one name
contributor.fullname = 'Ke$ha'
contributor.given_name = ''
contributor.family_name = ''
contributor.save()
meta = crossref_client._process_crossref_name(contributor)
assert meta == {'surname': contributor.fullname}
# Number and ? in given name
contributor.fullname = 'Scotty2Hotty? Ronald Garland II'
contributor.given_name = ''
contributor.family_name = ''
contributor.save()
meta = crossref_client._process_crossref_name(contributor)
assert meta == {'given_name': 'ScottyHotty Ronald', 'surname': 'Garland', 'suffix': 'II'}
# Long suffix is truncated to 10 characters
long_suffix = 'PhD MD Esq MPH IV'
contributor.given_name = 'Mark'
contributor.family_name = 'Henry'
contributor.suffix = long_suffix
contributor.save()
meta = crossref_client._process_crossref_name(contributor)
assert meta['suffix'] == long_suffix[:crossref.CROSSREF_SUFFIX_LIMIT]
# Long given_names and surnames are truncated to limit
long_given = 'Maaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaark'
long_surname = 'Henryyyyyyyyyyyyyyyyyyyyyyyyyyyyyyyyyyyyyyyyyyyyyyyyyyyyyyyyyyyyyyyyyyyyyyyyyyyy'
contributor.given_name = long_given
contributor.family_name = long_surname
contributor.save()
meta = crossref_client._process_crossref_name(contributor)
assert meta['given_name'] == long_given[:crossref.CROSSREF_GIVEN_NAME_LIMIT]
assert meta['surname'] == long_surname[:crossref.CROSSREF_SURNAME_LIMIT]
# Unparsable given or surname just returns fullname as surname
unparsable_fullname = 'Author (name withheld until double-blind peer review completes and this name is also really long)'
contributor.given_name = ''
contributor.family_name = ''
contributor.fullname = unparsable_fullname
contributor.save()
meta = crossref_client._process_crossref_name(contributor)
assert meta == {'surname': unparsable_fullname[:crossref.CROSSREF_SURNAME_LIMIT]}
def test_process_crossref_name(self, crossref_client):
contributor = AuthUserFactory()
# Given name and no family name
contributor.given_name = 'Hey'
contributor.family_name = ''
contributor.save()
meta = crossref_client._process_crossref_name(contributor)
imputed_names = impute_names(contributor.fullname)
assert meta == {'surname': imputed_names['family'], 'given_name': imputed_names['given']}
# Just one name
contributor.fullname = 'Ke$ha'
contributor.given_name = ''
contributor.family_name = ''
contributor.save()
meta = crossref_client._process_crossref_name(contributor)
assert meta == {'surname': contributor.fullname}
# Number and ? in given name
contributor.fullname = 'Scotty2Hotty? Ronald Garland II'
contributor.given_name = ''
contributor.family_name = ''
contributor.save()
meta = crossref_client._process_crossref_name(contributor)
assert meta == {'given_name': 'ScottyHotty Ronald', 'surname': 'Garland', 'suffix': 'II'}
# Long suffix is truncated to 10 characters
long_suffix = 'PhD MD Esq MPH IV'
contributor.given_name = 'Mark'
contributor.family_name = 'Henry'
contributor.suffix = long_suffix
contributor.save()
meta = crossref_client._process_crossref_name(contributor)
assert meta['suffix'] == long_suffix[:crossref.CROSSREF_SUFFIX_LIMIT]
# Long given_names and surnames are truncated to limit
long_given = 'Maaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaark'
long_surname = 'Henryyyyyyyyyyyyyyyyyyyyyyyyyyyyyyyyyyyyyyyyyyyyyyyyyyyyyyyyyyyyyyyyyyyyyyyyyyyy'
contributor.given_name = long_given
contributor.family_name = long_surname
contributor.save()
meta = crossref_client._process_crossref_name(contributor)
assert meta['given_name'] == long_given[:crossref.CROSSREF_GIVEN_NAME_LIMIT]
assert meta['surname'] == long_surname[:crossref.CROSSREF_SURNAME_LIMIT]
# Unparsable given or surname just returns fullname as surname
unparsable_fullname = 'Author (name withheld until double-blind peer review completes and this name is also really long)'
contributor.given_name = ''
contributor.family_name = ''
contributor.fullname = unparsable_fullname
contributor.save()
meta = crossref_client._process_crossref_name(contributor)
assert meta == {'surname': unparsable_fullname[:crossref.CROSSREF_SURNAME_LIMIT]}
def parse(self, csv_file):
""" Parse and add to csv file.
:param csv_file: Comma separated
:return: A list
"""
result = []
csv_reader = csv.reader(csv_file)
for index, row in enumerate(csv_reader):
if index == 0:
row.extend([
'OSF ID', 'Logs Since Workshop',
'Nodes Created Since Workshop', 'Last Log Date'
])
result.append(row)
continue
email = row[5]
user_by_email = self.find_user_by_email(email)
if not user_by_email:
full_name = row[4]
try:
family_name = impute_names(full_name)['family']
except UnicodeDecodeError:
row.extend(['Unable to parse name'])
result.append(row)
continue
user_by_name = self.find_user_by_full_name(
full_name) or self.find_user_by_family_name(family_name)
if not user_by_name:
row.extend(['', 0, 0, ''])
result.append(row)
continue
else:
user = user_by_name
else:
user = user_by_email
workshop_date = datetime.strptime(row[1], '%m/%d/%y')
nodes = self.get_user_nodes_since_workshop(user, workshop_date)
user_logs = self.get_user_logs_since_workshop(user, workshop_date)
try:
last_log_date = user_logs[-1].date.strftime('%m/%d/%y')
except IndexError:
last_log_date = ''
row.extend([user.pk, len(user_logs), len(nodes), last_log_date])
result.append(row)
return result
def parse(self, csv_file):
""" Parse and add to csv file.
:param csv_file: Comma separated
:return: A list
"""
result = []
csv_reader = csv.reader(csv_file)
for index, row in enumerate(csv_reader):
if index == 0:
row.extend([
'OSF ID', 'Logs Since Workshop', 'Nodes Created Since Workshop', 'Last Log Date'
])
result.append(row)
continue
email = row[5]
user_by_email = self.find_user_by_email(email)
if not user_by_email:
full_name = row[4]
try:
family_name = impute_names(full_name)['family']
except UnicodeDecodeError:
row.extend(['Unable to parse name'])
result.append(row)
continue
user_by_name = self.find_user_by_full_name(full_name) or self.find_user_by_family_name(family_name)
if not user_by_name:
row.extend(['', 0, 0, ''])
result.append(row)
continue
else:
user = user_by_name
else:
user = user_by_email
workshop_date = datetime.strptime(row[1], '%m/%d/%y')
nodes = self.get_user_nodes_since_workshop(user, workshop_date)
user_logs = self.get_user_logs_since_workshop(user, workshop_date)
try:
last_log_date = user_logs[-1].date.strftime('%m/%d/%y')
except IndexError:
last_log_date = ''
row.extend([
user.pk, len(user_logs), len(nodes), last_log_date
])
result.append(row)
return result
def create_fake_user():
email = fake.email()
name = fake.name()
parsed = utils.impute_names(name)
user = UserFactory(username=email, fullname=name,
is_registered=True, is_claimed=True,
date_registered=fake.date_time(),
emails=[email],
**parsed
)
user.set_password('faker123')
user.save()
logger.info('Created user: {0} <{1}>'.format(user.fullname, user.username))
return user
def create_fake_user():
email = fake.email()
name = fake.name()
parsed = impute_names(name)
user = UserFactory(username=email,
fullname=name,
is_registered=True,
is_claimed=True,
date_registered=fake.date_time(),
emails=[email],
**parsed)
user.set_password('faker123')
user.save()
return user
def create_fake_user():
email = fake.email()
name = fake.name()
parsed = impute_names(name)
user = UserFactory(username=email,
fullname=name,
is_registered=True,
is_claimed=True,
verification_key=security.random_string(15),
date_registered=fake.date_time(),
emails=[email],
**parsed)
user.set_password('faker123')
user.save()
return user
def create_fake_user():
email = fake.email()
name = fake.name()
parsed = impute_names(name)
user = UserFactory(
username=email,
fullname=name,
is_registered=True,
is_claimed=True,
date_registered=fake.date_time(),
emails=[email],
**parsed
)
user.set_password('faker123')
user.save()
return user
def create_fake_user():
email = fake.email()
name = fake.name()
parsed = impute_names(name)
user = UserFactory(
username=email,
fullname=name,
is_registered=True,
is_claimed=True,
verification_key=security.random_string(15),
date_registered=fake.date_time(),
emails=[email],
**parsed
)
user.set_password('faker123')
user.save()
return user
def get_users_from_csv(filename):
rows = set()
with open(filename, 'rU') as csvfile:
reader = csv.DictReader(csvfile)
for row in reader:
username = row['Email Address']
full_name = row['Name']
family_name = impute_names(full_name)['family']
parsed_date = row['Workshop_Date'].split("/")
day, month, year = int(parsed_date[0]), int(parsed_date[1]), int('20'+parsed_date[2])
date = datetime.datetime(year, month, day)
found_user = find_user_by_email(username) or find_user_by_fullname(full_name) or find_user_by_lastname(family_name)
if found_user:
log_count = count_user_logs(found_user, Q('date', 'gte', date))
node_count = count_user_nodes(found_user, Q('date_created', 'gte', date))
last_log = user_last_log(found_user)
rows.add((date, found_user.fullname, found_user.username, found_user._id, log_count, node_count, last_log))
return rows
def get_users_from_csv(filename):
rows = set()
with open(filename, 'rU') as csvfile:
reader = csv.DictReader(csvfile)
for row in reader:
email = row['Email Address']
full_name = row['Name'].decode('utf-8', 'ignore')
names = impute_names(full_name)
date = parse_date(row['Workshop_Date'])
found_user = find_user_by_email(email)
if not found_user and full_name:
found_user = find_user_by_fullname(full_name) or find_user_by_names(names)
if found_user:
log_count = count_user_logs(found_user, Q('date', 'gte', date))
node_count = count_user_nodes(found_user, Q('date_created', 'gte', date))
last_log = user_last_log(found_user)
rows.add((date, found_user.fullname, found_user.username, found_user._id, log_count, node_count, last_log))
return rows
def email_name(user):
logging.debug('Emailing user {0}'.format(user.fullname))
names = {'fullname': user.fullname}
names.update(impute_names(user.fullname))
message=email_template.format(**names).encode('utf-8')
success = send_email(
from_addr='*****@*****.**',
to_addr=user.username,
subject='Open Science Framework: Verify your citation information',
message=message,
mimetype='plain',
)
if success:
logging.debug('Emailing user {0}: Success'.format(user.fullname))
else:
logging.debug('Emailing user {0}: Failure'.format(user.fullname))
def process_name(node, user):
# If the user has a family and given name, use those
if user.family_name and user.given_name:
return {
'family_name': user.family_name,
'suffix': user.suffix,
'given_name': user.given_name,
'middle_names': user.middle_names,
}
elif user.is_registered or user.is_disabled:
name = user.fullname
else:
name = user.get_unclaimed_record(node._id)['name']
# If the user doesn't autofill his family and given name
parsed = utils.impute_names(name)
return {
'family_name': parsed['family'],
'suffix': parsed['suffix'],
'given_name': parsed['given'],
'middle_names': parsed['middle']
}
def process_name(node, user):
# If the user has a family and given name, use those
if user.family_name and user.given_name:
return {
'family_name': user.family_name,
'suffix': user.suffix,
'given_name': user.given_name,
'middle_names': user.middle_names,
}
elif user.is_registered or user.is_disabled:
name = user.fullname
else:
name = user.get_unclaimed_record(node._id)['name']
# If the user doesn't autofill his family and given name
parsed = utils.impute_names(name)
return {
'family_name': parsed['family'],
'suffix': parsed['suffix'],
'given_name': parsed['given'],
'middle_names': parsed['middle']
}
def get_users_from_csv(filename):
rows = set()
with open(filename, 'rU') as csvfile:
reader = csv.DictReader(csvfile)
for row in reader:
email = row['Email Address']
full_name = row['Name'].decode('utf-8', 'ignore')
names = impute_names(full_name)
date = parse_date(row['Workshop_Date'])
found_user = find_user_by_email(email)
if not found_user and full_name:
found_user = find_user_by_fullname(
full_name) or find_user_by_names(names)
if found_user:
log_count = count_user_logs(found_user, Q('date', 'gte', date))
node_count = count_user_nodes(found_user,
Q('date_created', 'gte', date))
last_log = user_last_log(found_user)
rows.add((date, found_user.fullname, found_user.username,
found_user._id, log_count, node_count, last_log))
return rows
def get_users_from_csv(filename):
rows = set()
with open(filename, 'rU') as csvfile:
reader = csv.DictReader(csvfile)
for row in reader:
username = row['Email Address']
full_name = row['Name']
family_name = impute_names(full_name)['family']
parsed_date = row['Workshop_Date'].split("/")
day, month, year = int(parsed_date[0]), int(
parsed_date[1]), int('20' + parsed_date[2])
date = datetime.datetime(year, month, day)
found_user = find_user_by_email(username) or find_user_by_fullname(
full_name) or find_user_by_lastname(family_name)
if found_user:
log_count = count_user_logs(found_user, Q('date', 'gte', date))
node_count = count_user_nodes(found_user,
Q('date_created', 'gte', date))
last_log = user_last_log(found_user)
rows.add((date, found_user.fullname, found_user.username,
found_user._id, log_count, node_count, last_log))
return rows
def impute_names(**kwargs):
name = request.args.get('name', '')
return auth_utils.impute_names(name)
"""
Impute name parts for all existing users.
"""
from framework.auth.utils import impute_names
from website.app import init_app
from website import models
app = init_app('website.settings', set_backends=True, routes=True)
def impute_names():
for user in models.User.find():
parsed = impute_names(user.fullname)
for field, value in parsed.items():
if getattr(user, field, None) is None:
setattr(user, field, value)
user.save()
if __name__ == '__main__':
impute_names()
def impute_names(**kwargs):
name = request.args.get("name", "")
return auth_utils.impute_names(name)
def impute_names(**kwargs):
name = request.args.get('name', '')
return auth_utils.impute_names(name)
"""
Impute name parts for all existing users.
"""
from framework.auth.utils import impute_names
from website.app import init_app
from website import models
app = init_app('website.settings', set_backends=True, routes=True)
def impute_names():
for user in models.User.find():
parsed = impute_names(user.fullname)
for field, value in parsed.items():
if getattr(user, field, None) is None:
setattr(user, field, value)
user.save()
if __name__ == '__main__':
impute_names()
