def test_formating_removing_pieces_from_name_buckets(self):
hn = HumanName("Rev John A. Kenneth Doe III (Kenny)")
hn.string_format = "{title} {first} {middle} {last} {suffix} '{nickname}'"
assert u(hn) == "Rev John A. Kenneth Doe III 'Kenny'"
hn.string_format = "{title} {first} {middle} {last} {suffix}"
assert u(hn) == "Rev John A. Kenneth Doe III"
hn.middle = ""
assert u(hn) == "Rev John Doe III"
hn.suffix = ""
assert u(hn) == "Rev John Doe"
hn.title = ""
assert u(hn) == "John Doe"
def normalize(name):
norm_1 = unidecode(" ".join(name.strip().lower().split())).replace("-", " ")
norm_2 = re.sub(r'<[^>]+>', r'', norm_1) # remove html
hname = HumanName(norm_2)
hname.string_format = '{first} {middle} {last}'
# return str(hname).replace()
return re.sub(r'[^a-z\s]', r'', str(hname))
def clean_authors(authors):
cleaned_authors = []
authors = authors.lower()
# get rid of commas where there are suffixes, like Jr. or III
authors = authors.replace(", jr.", " jr.")
authors = authors.replace(", iii", " iii")
authors = authors.replace(", ph.d", "")
# special cases
authors = authors.replace("organizer:", "")
authors = authors.replace("roel m,", "roel m.")
if authors == 'kozue miyashiro, etsuko harada, t.':
author_list = ['kozue miyashiro', 'etsuko harada, t.']
else:
author_list = authors.split(",")
for author in author_list:
author = HumanName(author.lower())
if author.first == '' or author.last == '':
raise ValueError("invalid author name: {}".format(author))
author.capitalize()
author.string_format = u"{last}, {title} {first} {middle}, {suffix}"
cleaned_authors.append(unicode(author))
return cleaned_authors
def get_full_name(person):
if (len(person.display_name) > 0 and not person.display_name.isdigit()
and not person.display_name.isupper()):
return person.display_name
name = HumanName(person.full_name)
name.capitalize()
name.string_format = "{first} {last}"
return str(name)
def get_display_name(self):
if self.has_display_name():
return self.display_name
if self.has_first_name():
name = HumanName("%s %s" % (self.first_name, self.last_name))
else:
name = HumanName(self.last_name)
name.capitalize()
name.string_format = "{first} {last}"
return str(name)
def user_fullname(user):
if hasattr(user, 'display_name'):
if ((user.display_name is None or not len(user.display_name) or
user.display_name.isupper()) and hasattr(user, 'first_name')):
fullname = HumanName('%s %s' % (user.first_name, user.surname))
fullname.capitalize()
fullname.string_format = '{first} {last}'
return str(fullname)
else:
return user.display_name
elif hasattr(user, 'email'):
return user.email.split('@')[0] # CanvasUser
else:
raise UserPolicyException('Invalid user')
def test_formating_removing_keys_from_format_string(self):
hn = HumanName("Rev John A. Kenneth Doe III (Kenny)")
hn.string_format = "{title} {first} {middle} {last} {suffix} '{nickname}'"
assert u(hn) == "Rev John A. Kenneth Doe III 'Kenny'"
hn.string_format = "{last}, {title} {first} {middle}, {suffix}"
assert u(hn) == "Doe, Rev John A. Kenneth, III"
hn.string_format = "{last}, {title} {first} {middle}"
assert u(hn) == "Doe, Rev John A. Kenneth"
hn.string_format = "{last}, {first} {middle}"
assert u(hn) == "Doe, John A. Kenneth"
hn.string_format = "{last}, {first}"
assert u(hn) == "Doe, John"
hn.string_format = "{first} {last}"
assert u(hn) == "John Doe"
def parse_file(filepath):
with open('filepath', mode="r") as csv_file:
csv_reader = csv.reader(csv_file)
all_lines = []
single_line = []
for row in csv_reader:
# Remove rows with no name
if len(row[0]) == 0:
pass
else:
# Remove any other than first and last names
name = HumanName(row[0])
name.string_format = "{first} {last}"
row[0] = str(name)
# Remove prepended 0s
row[1] = row[1].strip("0")
# Add true if amount > 100
if row[0] != "name":
if float(row[1]) > 100:
row.append("true")
else:
row.append("false")
# Split the names to first and last names
split_row = ' '.join(row).split()
# Add them all into a nested list
all_lines.append(split_row)
# Create new columns for new csv
all_lines[0] = ["first_name", "last_name", "price", "above_100"]
with open("dataeng_test/parsed_dataset.csv", "w", newline="") as file:
writer = csv.writer(file)
writer.writerows(all_lines)
def remove_name_titles(name):
name = HumanName(name)
name.string_format = "{first} {last}"
return str(name)
def test_formating(self):
hn = HumanName("Rev John A. Kenneth Doe III")
hn.string_format = "{title} {first} {middle} {last} {suffix}"
self.assertEqual(unicode(hn), "Rev John A. Kenneth Doe III")
hn.string_format = "{last}, {title} {first} {middle}, {suffix}"
self.assertEqual(unicode(hn), "Doe, Rev John A. Kenneth, III")
def display_name(first_name, surname, reverse=False):
name = HumanName("%s %s" % (first_name, surname))
name.capitalize()
name.string_format = "{last}, {first}" if (
reverse is True) else "{first} {last}"
return unicode(name)
def test_formating_of_nicknames_with_double_quotes(self):
hn = HumanName("Rev John A. Kenneth Doe III (Kenny)")
hn.string_format = '{title} {first} {middle} {last} {suffix} "{nickname}"'
assert u(hn) == 'Rev John A. Kenneth Doe III "Kenny"'
hn.nickname = ""
assert u(hn) == "Rev John A. Kenneth Doe III"
def test_formating_of_nicknames_with_single_quotes(self):
hn = HumanName("Rev John A. Kenneth Doe III (Kenny)")
hn.string_format = "{title} {first} {middle} {last} {suffix} '{nickname}'"
assert u(hn) == "Rev John A. Kenneth Doe III 'Kenny'"
hn.nickname = ""
assert u(hn) == "Rev John A. Kenneth Doe III"
def test_formating_of_nicknames_with_parenthesis(self):
hn = HumanName("Rev John A. Kenneth Doe III (Kenny)")
hn.string_format = "{title} {first} {middle} {last} {suffix} ({nickname})"
assert u(hn) == "Rev John A. Kenneth Doe III (Kenny)"
hn.nickname = ""
assert u(hn) == "Rev John A. Kenneth Doe III"
def test_quote_nickname_formating(self):
hn = HumanName("Rev John A. Kenneth Doe III (Kenny)")
hn.string_format = "{title} {first} {middle} {last} {suffix} '{nickname}'"
assert u(hn) == "Rev John A. Kenneth Doe III 'Kenny'"
hn.string_format = "{last}, {title} {first} {middle}, {suffix} '{nickname}'"
assert u(hn) == "Doe, Rev John A. Kenneth, III 'Kenny'"
#!/usr/bin/python
# -*- coding: utf-8 -*-
from nameparser import HumanName
name = HumanName("Dr. Juan Q. Xavier de la Vega III (Doc Vega)")
#name
print(name.last)
print(name.as_dict())
print(str(name))
name.string_format = "{first} {last}"
print(str(name))
def test_formating_of_nicknames_in_middle(self):
hn = HumanName("Rev John A. Kenneth Doe III (Kenny)")
hn.string_format = "{title} {first} ({nickname}) {middle} {last} {suffix}"
assert u(hn) == "Rev John (Kenny) A. Kenneth Doe III"
hn.nickname = ""
assert u(hn) == "Rev John A. Kenneth Doe III"
