Created
January 29, 2012 16:08
-
-
Save thepian/1699453 to your computer and use it in GitHub Desktop.
Better unicode
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
| from __future__ import with_statement | |
| import sys,os,yaml | |
| def split_file(content,header): | |
| if content[:3] == "---": | |
| parts = content.split("---") | |
| matter = yaml.load(unicode(parts[1],"utf-8")) or {} | |
| for key in header.keys(): | |
| matter[key] = header[key] | |
| encoding = 'utf-8' | |
| if 'encoding' in matter: | |
| encoding = matter['encoding'] | |
| rest = "---".join(parts[2:]) | |
| #print "parts", parts | |
| return matter, unicode(rest,"utf-8") | |
| return header, content | |
| content = None | |
| with open("test-unicode-matter.txt","rb") as f: | |
| matter,content = split_file(f.read(),{}) | |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment