Last active
July 20, 2017 14:22
-
-
Save fabienhinault/cb22773bd60a838eb5b75866aca77c7f to your computer and use it in GitHub Desktop.
Python3 script used to anonymize bulletins.ps
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/python3 | |
| import re | |
| import io | |
| import unicodedata | |
| f = open('/home/fab/Documents/dp/election/bulletins.ps', | |
| encoding="latin-1") | |
| output = open('/home/fab/Documents/dp/election/bulletins_anonym_1.ps', 'w', | |
| encoding='latin-1') | |
| for line in f: | |
| m = re.search('\([^\(]+\)', line) | |
| if m: | |
| r = io.StringIO() | |
| r.write(line[0 : m.start()]) | |
| for i in range(m.start(), m.end()): | |
| category = unicodedata.category(line[i]) | |
| if category == 'Ll': | |
| r.write('a') | |
| elif category == 'Lu': | |
| r.write('A') | |
| else: | |
| r.write(line[i]) | |
| r.write(line[m.end() : ]) | |
| output.write(r.getvalue()) | |
| else: | |
| output.write(line) |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment