def test_nickname(self):
name = 'Robert "Evan" Liebowitz'
assert_true(who.match(name, 'Evan Liebowitz'))
assert_true(who.match('Evan Liebowitz', name))
assert_false(who.match(name, 'Wrongbert Lieobwitz'))
assert_false(who.match(name, 'Robert Evan'))
assert_false(who.match(name, 'Evan Liebowitz',
options={'check_nickname': False}))
def test_suffixes(self):
name = 'Robert Liebowitz Jr'
assert_true(who.match(name, 'Robert Liebowitz'))
assert_true(who.match(name, 'Robert Liebowitz Jr'))
assert_true(who.match(name, 'Robert Liebowitz, PhD'))
assert_false(who.match(name, 'Robert Liebowitz, Sr'))
assert_false(who.match(name, 'Robert Liebowitz, Sr, PhD'))
assert_true(who.match(name, 'Robert Liebowitz, Jr, PhD'))
def find_gaps(parkings, people_off):
matches = []
for parking in parkings:
for person in people_off:
if person['type'] == 'holiday':
continue
if who.match(parking['name'], person['name']):
matches.append({
'name': person['name'],
'bay': parking['bay'],
'date_from': date_parser.parse(person['start']),
'date_to': date_parser.parse(person['end'])
})
return matches
def is_british(name):
'''Returns whether a speaker is likely to be an MEP from the United Kingdom'''
for possible_name in en_meps:
if who.match(name, possible_name):
return True
return False
def test_titles(self):
name = 'Mr. Robert Liebowitz'
assert_true(who.match(name, 'Robert Liebowitz'))
assert_true(who.match(name, 'Sir Robert Liebowitz'))
assert_true(who.match(name, 'Dr. Robert Liebowitz'))
assert_false(who.match(name, 'Mrs. Robert Liebowitz'))
def test_equivalent_suffixes(self):
name = 'Robert Liebowitz Jr'
assert_true(who.match(name, 'Robert Liebowitz Jnr'))
assert_false(who.match(name, 'Robert Liebowitz Snr'))
def test_short_names(self):
assert_true(who.match(self.name, 'Rob Liebowitz'))
# TODO: Should these be true?
assert_false(who.match(self.name, 'Bert Liebowitz'))
assert_false(who.match(self.name, 'Robbie Liebowitz'))
def test_different_initials(self):
assert_false(who.match(self.name, 'E. R. Liebowitz'))
assert_false(who.match(self.name, 'E. Liebowitz'))
assert_false(who.match(self.name, 'R. V. Liebowitz'))
assert_false(who.match(self.name, 'O. E. Liebowitz'))
def test_different_number_initials(self):
assert_true(who.match(self.name, 'Robert Liebowitz'))
assert_true(who.match(self.name, 'R. Liebowitz'))
assert_false(who.match(self.name, 'Robert E. E. Liebowitz'))
assert_false(who.match(self.name, 'R. E. E. Liebowitz'))
assert_true(who.match('R.E.E. Liebowitz', 'R. E. E. Liebowitz'))
def test_name_and_initials(self):
assert_true(who.match(self.name, 'R. Evan Liebowitz'))
assert_true(who.match(self.name, 'Robert E. Liebowitz'))
assert_true(who.match(self.name, 'R. E. Liebowitz'))
def test_unicode(self):
name = self.name
assert_true(who.match(name, 'attaché Robert Evan Liebowitz'))
assert_true(who.match(name, 'Rōbért Èvān Lîęböwitz'))
assert_false(who.match(name, 'Rōbért Èvān Lęîböwitz'))
def test_string(self):
# Only relevant for python 2.X
assert_true(who.match(self.name, str('Robert Liebowitz')))
def run(self):
while self.input_queue.empty() == False:
try:
ceo_row = self.input_queue.get()
ceo_year = ceo_row[1]
ceo_id = ceo_row[2]
ceo_name = ceo_row[4]
ceo_company = ceo_row[7]
ceo_company_name_first_word = (ceo_company.split())[0]
ceo_name = ceo_name.replace("\'", "\'\'")
ceo_company = ceo_company.replace("\'", "\'\'")
#Find the possible company name of the CEO
sql = 'SELECT cname, namefmac, compustatname, Acronym, year, exec_fullname from Company WHERE (cname = \"' + ceo_company + '\" OR namefmac = \"' + ceo_company + '\" OR compustatname = \"' + ceo_company + '\" OR Acronym = \"' + ceo_company + '\") AND (year=' + ceo_year + ');'
#print(sql)
self.cursor.execute(sql)
results = self.cursor.fetchall()
if (len(results) > 0):
print(
"Worker %d: in progress matching company, length: %s"
% (self.id, len(results)))
for row in results:
cname1 = row[0] if row[0] else "Condition never match"
cname2 = row[1] if row[1] else "Condition never match"
cname3 = row[2] if row[2] else "Condition never match"
cname4 = row[3] if row[3] else "Condition never match"
ceo_name = row[5]
cname1 = cname1.replace("\'", "\'\'")
cname2 = cname2.replace("\'", "\'\'")
cname3 = cname3.replace("\'", "\'\'")
cname4 = cname4.replace("\'", "\'\'")
cname_year1 = row[4]
cname_year2 = cname_year1 - 1
sql = 'SELECT Contrib from Donation WHERE Cycle in (' + str(
cname_year1
) + ',' + str(
cname_year2
) + ') AND ((Orgname in (\'' + cname1 + '\',\'' + cname2 + '\',\'' + cname3 + '\',\'' + cname4 + '\')) OR (Orgname LIKE \'' + ceo_company_name_first_word + ' %\')) AND Orgname <> \'\''
self.cursor.execute(sql)
donation_results = self.cursor.fetchall()
if (len(donation_results) > 0):
print(
"Worker %d: in progress finding donation, job id: %d CEO: %d Donation: %d Current: %d"
%
(self.id, self.input_queue.qsize(), len(results),
len(donation_results), self.output_queue.qsize()))
else:
print(
"Worker %d: in progress finding donation, job id: %d CEO: %d Current: %d"
% (self.id, self.input_queue.qsize(), len(results),
self.output_queue.qsize()))
for donation_result in donation_results:
donation_donor_name = donation_result[0]
donation_donor_name_in_sql_format = donation_donor_name.replace(
"\'", "\'\'")
if (who.match(ceo_name, donation_donor_name)):
sql = 'SELECT * from Donation WHERE Contrib = \"' + donation_donor_name_in_sql_format + '\";'
self.cursor.execute(sql)
name_matched_donation_results = self.cursor.fetchall(
)
if (len(name_matched_donation_results) > 0):
print(
"Worker %d: in progress matching name, length: %s"
% (self.id,
len(name_matched_donation_results)))
for name_matched_donation_result in name_matched_donation_results:
output_row = [
ceo_id
] + list(name_matched_donation_result)
self.output_queue.put(output_row)
except Exception:
traceback.print_exc()
finally:
# 處理資料
print("Worker %d: %s" % (self.id, self.input_queue.qsize()))
print("Worker %d End" % (self.id))
def main():
# 建立佇列
my_queue = queue.Queue()
# 將資料放入佇列
with open('Ceo.csv', newline='') as csvfile:
# 讀取 CSV 檔案內容
rows = csv.reader(csvfile)
next(rows, None)
# 以迴圈輸出每一列
for row in rows:
my_queue.put(row)
db = pymysql.connect("127.0.0.1", "wai", "123", "mm", charset='utf8')
cursor = db.cursor()
i = 0
found = 0
try:
output_rows = []
while not my_queue.empty():
i += 1
ceo_row = my_queue.get()
ceo_year = ceo_row[1]
ceo_id = ceo_row[2]
ceo_name = ceo_row[4]
ceo_company = ceo_row[7]
ceo_company_name_first_word = (ceo_company.split())[0]
ceo_name = ceo_name.replace("\'", "\'\'")
ceo_company = ceo_company.replace("\'", "\'\'")
#Find the possible company name of the CEO
sql = 'SELECT cname, namefmac, compustatname, Acronym, year, exec_fullname from Company WHERE (cname = \"' + ceo_company + '\" OR namefmac = \"' + ceo_company + '\" OR compustatname = \"' + ceo_company + '\" OR Acronym = \"' + ceo_company + '\") AND (year=' + ceo_year + ');'
#print(sql)
cursor.execute(sql)
results = cursor.fetchall()
if (i % 1 == 0):
print(i)
for row in results:
cname1 = row[0]
cname2 = row[1]
cname3 = row[2]
cname4 = row[3]
ceo_name = row[5]
cname1 = cname1.replace("\'", "\'\'")
cname2 = cname2.replace("\'", "\'\'")
cname3 = cname3.replace("\'", "\'\'")
cname4 = cname4.replace("\'", "\'\'")
cname_year1 = row[4]
cname_year2 = cname_year1 - 1
sql = 'SELECT * from Donation WHERE Cycle in (' + str(
cname_year1
) + ',' + str(
cname_year2
) + ') AND (Orgname in (\'' + cname1 + '\',\'' + cname2 + '\',\'' + cname3 + '\',\'' + cname4 + '\') OR (Orgname LIKE \"' + ceo_company_name_first_word + '%\")) AND Orgname <> \'\''
cursor.execute(sql)
donation_results = cursor.fetchall()
for donation_result in donation_results:
donation_donor_name = donation_result[3]
donation_donor_name = donation_donor_name.replace(
"\'", "\'\'")
if (who.match(ceo_name, donation_donor_name)):
sql = 'SELECT * from Donation WHERE RecipID = \"' + donation_donor_name + '\";'
cursor.execute(sql)
name_matched_donation_results = cursor.fetchall()
for name_matched_donation_result in name_matched_donation_results:
output_row = [
ceo_id
] + list(name_matched_donation_result)
output_rows.append(output_row)
print("current found: ", found)
found += 1
print("found: ", found)
with open('output.csv', 'w', newline='') as csvfile:
# 建立 CSV 檔寫入器
writer = csv.writer(csvfile)
writer.writerow([
'execid', 'Cycle', 'Date', 'ContribID', 'Contrib', 'RecipID',
'Orgname', 'UltOrg', 'Occupation', 'RealCode', 'Amount',
'State', 'Zip', 'RecipCode', 'Type', 'Gender', 'reccode1',
'reccode2'
])
for output_row in output_rows:
writer.writerow(output_row)
except Exception:
print(sql)
traceback.print_exc()
finally:
db.close()
"""
def are_same_author(author1: str, author2: str) -> bool:
return cast(bool, who.match(author1, author2))
