def test_drop_white_space_method_returns_correct_result(self):
u = DameUtils()
self.assertEqual("In", u.drop_white_space("In "))
self.assertEqual("Ines", u.drop_accents(u.drop_white_space("Inés ")))
def test_drop_white_space(self):
u = DameUtils()
self.assertEqual("In", u.drop_white_space("In "))
self.assertEqual("Ines", u.drop_accents(u.drop_white_space("Inés ")))
self.assertEqual("JuanCarlosI",
u.drop_accents(u.drop_white_space("Juan Carlos I ")))
if (len(sys.argv) > 1):
cmd = 'grep -i " ' + args.name + ' " files/names/nam_dict.txt > files/grep.tmp'
print(cmd)
os.system(cmd)
results = [i for i in open('files/grep.tmp', 'r').readlines()]
males = []
females = []
both = []
for rowres in results:
regex = "(M|F|=|\?|1)( |M|F)?( )(\w+)( )?(\w+)?( )?(\w+)?"
n = re.match(regex, rowres)
if (n.group(6)):
string = n.group(4) + n.group(5) + str(n.group(6))
else:
string = n.group(4) + n.group(5)
if (du.drop_white_space(args.name) == du.drop_white_space(string)):
for i in range(30, 84):
if (exists_in_country(int(i), rowres)):
if (rowres[0].title() == "M"):
males.append(keyscountries[str(i)])
elif (rowres[0].title() == "F"):
females.append(keyscountries[str(i)])
elif (rowres[0].title() == "="):
both.append(keyscountries[str(i)])
print("males: " + (str(sorted(males))))
print("females: " + str(sorted(females)))
print("both: " + str(sorted(both)))
def name_frec(self, name, dataset='ine'):
if (dataset == 'ine'):
du = DameUtils()
name = du.drop_accents(name)
file_males = open('files/names/names_es/masculinos_original.csv',
'r')
inereader_males = csv.reader(file_males,
delimiter=',',
quotechar='|')
males = 0
for row in inereader_males:
if ((len(row) > 1) and (row[1].lower() == name.lower())):
males = row[2]
males = du.drop_dots(males)
file_females = open('files/names/names_es/femeninos_original.csv',
'r')
inereader_females = csv.reader(file_females,
delimiter=',',
quotechar='|')
females = 0
for row in inereader_females:
if ((len(row) > 1) and (row[1].lower() == name.lower())):
females = row[2]
females = du.drop_dots(females)
dicc = {"females": females, "males": males}
elif (dataset == 'uscensus'):
du = DameUtils()
usfile = open('files/names/yob2017.txt', 'r')
usreader = csv.reader(usfile, delimiter=',', quotechar='|')
males = 0
females = 0
for row in usreader:
if ((len(row) > 1) and (row[0].lower() == name.lower())):
if (row[1] == 'F'):
females = row[2]
elif (row[1] == 'M'):
males = row[2]
dicc = {"females": females, "males": males}
elif (dataset == 'ukcensus'):
du = DameUtils()
name = du.drop_accents(name)
file_males = open('files/names/2017boysnames-uk.csv', 'r')
reader_males = csv.reader(file_males, delimiter=',', quotechar='|')
males = 0
for row in reader_males:
if (len(row) > 1):
ukname = du.drop_accents(du.drop_white_space(
row[1])).lower()
if (ukname == name.lower()):
ukname = du.drop_accents(du.drop_white_space(
row[1])).lower()
males = row[2]
males = du.drop_dots(males)
file_females = open('files/names/2017girlsnames-uk.csv', 'r')
reader_females = csv.reader(file_females,
delimiter=',',
quotechar='|')
females = 0
for row in reader_females:
if (len(row) > 1):
ukname = du.drop_accents(du.drop_white_space(
row[1])).lower()
if (ukname == name.lower()):
females = row[2]
females = du.drop_dots(females)
dicc = {"females": females, "males": males}
return dicc
if (len(sys.argv) > 1):
cmd = 'grep -i " ' + args.name + ' " files/names/nam_dict.txt > files/logs/grep.tmp'
print(cmd)
os.system(cmd)
results = [i for i in open('files/logs/grep.tmp', 'r').readlines()]
males = []
females = []
both = []
for rowres in results:
regex = "(M|F|=|\?|1)( |M|F)?( )(\w+)( )?(\w+)?( )?(\w+)?"
n = re.match(regex, rowres)
if (n.group(6)):
string = str(n.group(4)) + str(n.group(5)) + str(n.group(6))
else:
string = str(n.group(4)) + str(n.group(5))
if (du.drop_white_space(
args.name.capitalize()) == du.drop_white_space(string)):
twochars = rowres[0] + rowres[1]
for i in range(30, 84):
if (exists_in_country(int(i), rowres)):
if ((rowres[0].title() == "M") | (twochars.title() == "1M")
| (twochars.title() == "?M")):
males.append(keyscountries[str(i)])
elif (
(rowres[0].title() == "F") | (twochars.title() == "1F")
| (twochars.title() == "?F")):
females.append(keyscountries[str(i)])
elif (rowres[0].title() == "="):
both.append(keyscountries[str(i)])
print("males: " + (str(sorted(males))))
print("females: " + str(sorted(females)))
