Skip to content

Instantly share code, notes, and snippets.

@stucka
Created May 9, 2017 20:00
Show Gist options
  • Save stucka/22dd755a1d96f98eb9972c316d60375a to your computer and use it in GitHub Desktop.
Save stucka/22dd755a1d96f98eb9972c316d60375a to your computer and use it in GitHub Desktop.
Cobbled-together Unicode CSV writer from docs
import csv
import codecs
import cStringIO
def UnicodeDictReader(utf8_data, **kwargs):
csv_reader = csv.DictReader(utf8_data, **kwargs)
for row in csv_reader:
yield {unicode(key, 'utf-8'):unicode(value, 'utf-8') for key, value in row.iteritems()}
class UTF8Recoder:
"""
Iterator that reads an encoded stream and reencodes the input to UTF-8
"""
def __init__(self, f, encoding):
self.reader = codecs.getreader(encoding)(f)
def __iter__(self):
return self
def next(self):
return self.reader.next().encode("utf-8")
class UnicodeReader:
"""
A CSV reader which will iterate over lines in the CSV file "f",
which is encoded in the given encoding.
"""
def __init__(self, f, dialect=csv.excel, encoding="utf-8", **kwds):
f = UTF8Recoder(f, encoding)
self.reader = csv.reader(f, dialect=dialect, **kwds)
def next(self):
row = self.reader.next()
return [unicode(s, "utf-8") for s in row]
def __iter__(self):
return self
class UnicodeWriter:
"""
A CSV writer which will write rows to CSV file "f",
which is encoded in the given encoding.
"""
def __init__(self, f, dialect=csv.excel, encoding="utf-8", **kwds):
# Redirect output to a queue
self.queue = cStringIO.StringIO()
self.writer = csv.writer(self.queue, dialect=dialect, **kwds)
self.stream = f
self.encoder = codecs.getincrementalencoder(encoding)()
def writerow(self, row):
self.writer.writerow([s.encode("utf-8") for s in row])
# Fetch UTF-8 output from the queue ...
data = self.queue.getvalue()
data = data.decode("utf-8")
# ... and reencode it into the target encoding
data = self.encoder.encode(data)
# write to the target stream
self.stream.write(data)
# empty queue
self.queue.truncate(0)
def writerows(self, rows):
for row in rows:
self.writerow(row)
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment