Skip to content

Instantly share code, notes, and snippets.

Embed
What would you like to do?
Unicode DictReader and DictWriter
id name age
0 aaron 34
1 tina 36
2 noah ©
#!/usr/bin/env python
import csv, codecs, cStringIO, sys
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 UnicodeDictReader:
"""
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)
self.header = self.reader.next()
def next(self):
row = self.reader.next()
vals = [unicode(s, "utf-8") for s in row]
return dict((self.header[x], vals[x]) for x in range(len(self.header)))
def __iter__(self):
return self
class UnicodeDictWriter:
"""
A CSV writer which will write rows to CSV file "f",
which is encoded in the given encoding.
"""
def __init__(self, f, fieldnames, dialect=csv.excel, encoding="utf-8", **kwds):
# Redirect output to a queue
self.fieldnames = fieldnames
self.queue = cStringIO.StringIO()
self.writer = csv.writer(self.queue, dialect=dialect, **kwds)
self.stream = f
self.encoder = codecs.getincrementalencoder(encoding)()
def writeheader(self):
self.writer.writerow(self.fieldnames)
def writerow(self, row):
self.writer.writerow([row[x].encode("utf-8") for x in self.fieldnames])
# 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)
if __name__ == '__main__':
args = sys.argv
if len(args) > 1:
# Make sure your file header is: id,name,age
filename = sys.argv[1]
else:
filename = 'data.csv'
data = 'id,name,age\n0,aaron,34\n1,john\u00A9,50'.encode('utf-8')
f = codecs.open(filename, encoding='utf-8', mode='w+')
f.write(data)
f.close()
r = UnicodeDictReader(open(filename, 'r'), skipinitialspace=True)
w = UnicodeDictWriter(open(filename.replace('.csv', '.out.csv'), 'w'), ['id', 'name', 'age'])
w.writeheader()
for row in r:
print row
w.writerow(row)
@twinforces

This comment has been minimized.

Copy link

@twinforces twinforces commented Oct 4, 2013

Thanks for this.

@vlcinsky

This comment has been minimized.

Copy link

@vlcinsky vlcinsky commented May 9, 2014

Excellent.

@twisss

This comment has been minimized.

Copy link

@twisss twisss commented May 28, 2014

Very helpful thanks a lot!

@aceed

This comment has been minimized.

Copy link

@aceed aceed commented Jul 11, 2014

it's exacly what i need, thx !

@TioBorracho

This comment has been minimized.

Copy link

@TioBorracho TioBorracho commented Feb 22, 2017

on line 55 you can use
row[x].encode("utf-8") if isinstance(row[x],basestring) else row[x]
since encode will fail if row[x] is not a string

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment