Last active
January 15, 2016 00:12
-
-
Save Shaunwei/31d0ba35ed66a906c6db to your computer and use it in GitHub Desktop.
File encoding issue with chardet library. A few characters '{', '}', '~' with several combinations will cause chardet to fail. Find out who are the bad guys!! For fancy looks, I used colorclass and terminaltables.
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
| #!/usr/bin/env python3 | |
| import chardet | |
| from colorclass import Color | |
| from terminaltables import AsciiTable | |
| def generate_test(chars_list): | |
| table_data = [['Chars', 'Confidence', 'Encoding', 'Issue'], ] | |
| for chars in chars_list: | |
| result = chardet.detect(chars.encode('utf-8')) | |
| conf, enco = result['confidence'], result['encoding'] | |
| if not conf or not enco: | |
| table_data.append( | |
| [chars, str(conf), 'None', Color('{red}x{/red}')] | |
| ) | |
| else: | |
| table_data.append( | |
| [chars, str(conf), enco, Color('{green}✔{/green}')] | |
| ) | |
| table = AsciiTable(sorted(table_data, key=lambda x: x[3], reverse=True)) | |
| print(table.table) | |
| def generate_chars_list(chars): | |
| chars_set = set() | |
| def permutation(vals, curt): | |
| chars_set.add(''.join(curt)) | |
| for i, v in enumerate(vals): | |
| permutation(vals[:i] + vals[i + 1:], curt + [v]) | |
| permutation(list(chars), []) | |
| return list(chars_set) | |
| if __name__ == '__main__': | |
| chars_list = generate_chars_list('{}~') | |
| generate_test(chars_list) | |
| """ | |
| +-------+------------+----------+-------+ | |
| | Chars | Confidence | Encoding | Issue | | |
| +-------+------------+----------+-------+ | |
| | { | 1.0 | ascii | ✔ | | |
| | {~} | 1.0 | ascii | ✔ | | |
| | {}~ | 1.0 | ascii | ✔ | | |
| | } | 1.0 | ascii | ✔ | | |
| | ~}{ | 1.0 | ascii | ✔ | | |
| | {} | 1.0 | ascii | ✔ | | |
| | ~} | 1.0 | ascii | ✔ | | |
| | }{~ | 1.0 | ascii | ✔ | | |
| | {~ | 1.0 | ascii | ✔ | | |
| | }{ | 1.0 | ascii | ✔ | | |
| | ~ | 1.0 | ascii | ✔ | | |
| | }~ | 1.0 | ascii | ✔ | | |
| | | 0.0 | None | x | | |
| | }~{ | 0.0 | None | x | | |
| | ~{} | 0.0 | None | x | | |
| | ~{ | 0.0 | None | x | | |
| +-------+------------+----------+-------+ | |
| """ |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment