Created
February 8, 2020 02:17
-
-
Save luisenriquecorona/67dfcacdca19414ce0517d1cf3c2559b to your computer and use it in GitHub Desktop.
Transform some Western typographical symbols into ASCII.
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
| single_map = str.maketrans("""‚ƒ„†ˆ‹‘’“”•–—˜›""", | |
| """'f"*^<''""---~>""") | |
| multi_map = str.maketrans({ | |
| '€': '<euro>', | |
| '…': '...', | |
| 'Œ': 'OE', | |
| '™': '(TM)', | |
| 'œ': 'oe', | |
| '‰': '<per mille>', | |
| '‡': '**', | |
| }) | |
| multi_map.update(single_map) | |
| def dewinize(txt): | |
| """Replace Win1252 symbols with ASCII chars or sequences""" | |
| return txt.translate(multi_map) | |
| def asciize(txt): | |
| no_marks = shave_marks_latin(dewinize(txt)) | |
| no_marks = no_marks.replace('ß', 'ss') | |
| return unicodedata.normalize('NFKC', no_marks) |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment