Skip to content

Instantly share code, notes, and snippets.

@ewalstad
Last active January 2, 2016 15:48
Show Gist options
  • Save ewalstad/8325465 to your computer and use it in GitHub Desktop.
Save ewalstad/8325465 to your computer and use it in GitHub Desktop.
Utilities to help with using CSV IO. See also: http://docs.python.org/2/library/csv.html#csv-examples
#-*- coding:utf-8 -*-
"""
====================================
Utilities to help with using CSV IO
====================================
Example usage
-------------
Code that used to do this::
writer = csv.writer(open('/path/to/file.csv'))
Can now do this to work with Unicode::
writer = UnicodeWriter(open('/path/to/file.csv'))
----
.. seealso::
* `Python csv docs <http://docs.python.org/2/library/csv.html#csv-examples>`_
* https://gist.github.com/ewalstad/8325465
"""
import csv, codecs, cStringIO
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
@property
def line_num(self):
"""The number of lines read from the source iterator. This is not the
same as the number of records returned, as records can span multiple
lines."""
return self.reader.line_num
@property
def dialect(self):
"""A read-only description of the dialect in use by the parser."""
return self.reader.dialect
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