Created
October 8, 2012 22:18
-
-
Save bukzor/3855335 to your computer and use it in GitHub Desktop.
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
| $ python | |
| Python 2.6.7 (r267:88850, Dec 2 2011, 20:27:26) | |
| [GCC 4.4.3] on linux2 | |
| Type "help", "copyright", "credits" or "license" for more information. | |
| >>> latin1 = ''.join(chr(x) for x in range(256)) | |
| >>> latin1.decode('latin1') | |
| u'\x00\x01\x02\x03\x04\x05\x06\x07\x08\t\n\x0b\x0c\r\x0e\x0f\x10\x11\x12\x13\x14\x15\x16\x17\x18\x19\x1a\x1b\x1c\x1d\x1e\x1f !"#$%&\'()*+,-./0123456789:;<=>?@ABCDEFGHIJKLMNOPQRSTUVWXYZ[\\]^_`abcdefghijklmnopqrstuvwxyz{|}~\x7f\x80\x81\x82\x83\x84\x85\x86\x87\x88\x89\x8a\x8b\x8c\x8d\x8e\x8f\x90\x91\x92\x93\x94\x95\x96\x97\x98\x99\x9a\x9b\x9c\x9d\x9e\x9f\xa0\xa1\xa2\xa3\xa4\xa5\xa6\xa7\xa8\xa9\xaa\xab\xac\xad\xae\xaf\xb0\xb1\xb2\xb3\xb4\xb5\xb6\xb7\xb8\xb9\xba\xbb\xbc\xbd\xbe\xbf\xc0\xc1\xc2\xc3\xc4\xc5\xc6\xc7\xc8\xc9\xca\xcb\xcc\xcd\xce\xcf\xd0\xd1\xd2\xd3\xd4\xd5\xd6\xd7\xd8\xd9\xda\xdb\xdc\xdd\xde\xdf\xe0\xe1\xe2\xe3\xe4\xe5\xe6\xe7\xe8\xe9\xea\xeb\xec\xed\xee\xef\xf0\xf1\xf2\xf3\xf4\xf5\xf6\xf7\xf8\xf9\xfa\xfb\xfc\xfd\xfe\xff' | |
| >>> latin1.decode('windows-1252') | |
| Traceback (most recent call last): | |
| File "<stdin>", line 1, in <module> | |
| File "/nail/home/buck/mypy/lib/python2.6/encodings/cp1252.py", line 15, in decode | |
| return codecs.charmap_decode(input,errors,decoding_table) | |
| UnicodeDecodeError: 'charmap' codec can't decode byte 0x81 in position 129: character maps to <undefined> | |
| >>> set(latin1) - set(latin1.decode('windows-1252', 'ignore').encode('windows-1252')) | |
| set(['\x81', '\x90', '\x9d', '\x8d', '\x8f']) |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment