Created
August 23, 2018 06:23
-
-
Save dmtucker/6a34397a67118cdee59324cde895d3eb to your computer and use it in GitHub Desktop.
This file contains 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
$ python3 sep.py | |
different: cp037 b'a' | |
different: cp273 b'a' | |
different: cp424 b'a' | |
different: cp500 b'a' | |
different: cp875 b'a' | |
different: cp1026 b'a' | |
different: cp1140 b'a' | |
untested: cp65001 | |
different: utf_32 b'\xff\xfe\x00\x00/\x00\x00\x00' | |
different: utf_32_be b'\x00\x00\x00/' | |
different: utf_32_le b'/\x00\x00\x00' | |
different: utf_16 b'\xff\xfe/\x00' | |
different: utf_16_be b'\x00/' | |
different: utf_16_le b'/\x00' | |
different: utf_8_sig b'\xef\xbb\xbf/' |
This file contains 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
encodings = [ | |
'ascii', | |
'big5', | |
'big5hkscs', | |
'cp037', | |
'cp273', | |
'cp424', | |
'cp437', | |
'cp500', | |
'cp720', | |
'cp737', | |
'cp775', | |
'cp850', | |
'cp852', | |
'cp855', | |
'cp856', | |
'cp857', | |
'cp858', | |
'cp860', | |
'cp861', | |
'cp862', | |
'cp863', | |
'cp864', | |
'cp865', | |
'cp866', | |
'cp869', | |
'cp874', | |
'cp875', | |
'cp932', | |
'cp949', | |
'cp950', | |
'cp1006', | |
'cp1026', | |
'cp1125', | |
'cp1140', | |
'cp1250', | |
'cp1251', | |
'cp1252', | |
'cp1253', | |
'cp1254', | |
'cp1255', | |
'cp1256', | |
'cp1257', | |
'cp1258', | |
'cp65001', | |
'euc_jp', | |
'euc_jis_2004', | |
'euc_jisx0213', | |
'euc_kr', | |
'gb2312', | |
'gbk', | |
'gb18030', | |
'hz', | |
'iso2022_jp', | |
'iso2022_jp_1', | |
'iso2022_jp_2', | |
'iso2022_jp_2004', | |
'iso2022_jp_3', | |
'iso2022_jp_ext', | |
'iso2022_kr', | |
'latin_1', | |
'iso8859_2', | |
'iso8859_3', | |
'iso8859_4', | |
'iso8859_5', | |
'iso8859_6', | |
'iso8859_7', | |
'iso8859_8', | |
'iso8859_9', | |
'iso8859_10', | |
'iso8859_11', | |
'iso8859_13', | |
'iso8859_14', | |
'iso8859_15', | |
'iso8859_16', | |
'johab', | |
'koi8_r', | |
'koi8_t', | |
'koi8_u', | |
'kz1048', | |
'mac_cyrillic', | |
'mac_greek', | |
'mac_iceland', | |
'mac_latin2', | |
'mac_roman', | |
'mac_turkish', | |
'ptcp154', | |
'shift_jis', | |
'shift_jis_2004', | |
'shift_jisx0213', | |
'utf_32', | |
'utf_32_be', | |
'utf_32_le', | |
'utf_16', | |
'utf_16_be', | |
'utf_16_le', | |
'utf_7', | |
'utf_8', | |
'utf_8_sig', | |
] | |
for encoding in encodings: | |
try: | |
encoded = u'/'.encode(encoding) | |
except UnicodeEncodeError: | |
print('unencodable:', encoding) | |
except LookupError: | |
print('untested:', encoding) | |
else: | |
if encoded != u'/'.encode('utf-8'): | |
print('different:', encoding, encoded) |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment