Das deutsche Python-Forum

Code: Alles auswählen

$ python3 ex23.py utf-8 strict
b'Afrikaans' <===> Afrikaans
b'\xc3\xa1\xc5\xa0 \xc3\xa1\xcb\x86\xe2\x80\xba\xc3\xa1\xcb\x86\xc2\xad\xc3\xa1\xc5\xa0\xe2\x80\xba' <===> Traceback (most recent call last):
  File "ex23.py", line 23, in <module>
    main(languages, input_encoding, error)
  File "ex23.py", line 10, in main
    return main(language_file, encoding, errors)
  File "ex23.py", line 9, in main
    print_line(line, encoding, errors)
  File "ex23.py", line 18, in print_line
    print(raw_bytes, "<===>", cooked_string)
UnicodeEncodeError: 'ascii' codec can't encode characters in position 0-1: ordinal not in range(128)

Code: Alles auswählen

import sys
script, input_encoding, error = sys.argv


def main(language_file, encoding, errors):
    line = language_file.readline()

    if line:
        print_line(line, encoding, errors)
        return main(language_file, encoding, errors)


def print_line(line, encoding, errors):
    next_lang = line.strip()
    raw_bytes = next_lang.encode(encoding, errors=errors)
    cooked_string = raw_bytes.decode(encoding, errors=errors)

    print(raw_bytes, "<===>", cooked_string)


languages = open("languages.txt", encoding="utf-8")

main(languages, input_encoding, error)

Code: Alles auswählen

$ locale
locale: Cannot set LC_CTYPE to default locale: No such file or directory
locale: Cannot set LC_MESSAGES to default locale: No such file or directory
locale: Cannot set LC_ALL to default locale: No such file or directory
LANG=en_GB.UTF-8
LC_CTYPE="en_GB.UTF-8"
LC_NUMERIC="en_GB.UTF-8"
LC_TIME="en_GB.UTF-8"
LC_COLLATE="en_GB.UTF-8"
LC_MONETARY="en_GB.UTF-8"
LC_MESSAGES="en_GB.UTF-8"
LC_PAPER="en_GB.UTF-8"
LC_NAME="en_GB.UTF-8"
LC_ADDRESS="en_GB.UTF-8"
LC_TELEPHONE="en_GB.UTF-8"
LC_MEASUREMENT="en_GB.UTF-8"
LC_IDENTIFICATION="en_GB.UTF-8"
LC_ALL=

Code: Alles auswählen

import sys

def print_line(line, encoding, errors):
    raw_bytes = line.encode(encoding, errors=errors)
    print(raw_bytes, "<===>", line)

def main():
    _, input_encoding, error = sys.argv
    with open("languages.txt", encoding="utf-8") as lines:
        for line in lines:
            print_line(line.strip(), encoding, errors)

if __name__ == '__main__':
    main()