INNER CODE UNIT · Python

accent_case_normalization

WorldHealthOrganization/app · tools/iso_countries.py:30

def accent_case_normalization(name):
    return unicodedata.normalize("NFKD", name.casefold()).encode('ASCII', 'ignore')

def main(argv):
    print('Reading: ' + sys.argv[1])
    with open(sys.argv[1], newline='', encoding='utf-8') as csvfile:
        reader = csv.DictReader(csvfile)
        countries = []
        old_alpha2 = ''
        for row in reader:
            alpha2 = row[iso_2_code]
            assert(len(alpha2) == 2)
            country = [alpha2]
            for field in fields:
                name = row[fields[field]]
                if name in substitutions:
                    name = substitutions[name]
                country.append(name)

View source record →