Created
November 6, 2012 18:05
-
-
Save pkqk/4026444 to your computer and use it in GitHub Desktop.
Unicode safe extension to csv.DictReader
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
""" | |
Safely deal with unicode(utf-8) in csv files | |
removing nasty BOM surprises | |
""" | |
import csv | |
import codecs | |
def unicode_csv_dictreader(path, *args, **kwargs): | |
"create a csv dict reader that copes with encoding correctly" | |
# utf-8-sig strips off a BOM if it's present | |
stream = codecs.open(path, encoding='utf-8-sig') | |
return UnicodeCSVDictReader(stream, *args, **kwargs) | |
class UnicodeCSVDictReader(csv.DictReader): | |
def __init__(self, unicode_csvfile, *args, **kwargs): | |
decoder = codecs.getdecoder('utf-8') | |
self.decoder = lambda v: decoder(v)[0] | |
utf8_csvfile = codecs.iterencode(unicode_csvfile, encoding='utf-8') | |
# bollicks to csv.DictReader being an oldstyle class | |
csv.DictReader.__init__(self, utf8_csvfile, *args, **kwargs) | |
self.fieldnames = [self.decoder(f) for f in self.fieldnames] | |
def next(self): | |
data = csv.DictReader.next(self) | |
return {k: self.decoder(v) for (k,v) in data.iteritems()} |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment