You could at least partially side-step what the csv module does by creating your own version of a singleton None-like class/value:
from __future__ import print_function
import csv
class NONE(object):
''' None-like class. '''
def __repr__(self): # Method csv.writer class uses to write values.
return 'NONE' # Unique string value to represent None.
def __len__(self): # Method called to determine length and truthiness.
return 0
NONE = NONE() # Singleton instance of the class.
if __name__ == '__main__':
try:
from cStringIO import StringIO # Python 2.
except ModuleNotFoundError:
from io import StringIO # Python 3.
data = [['None value', None], ['NONE value', NONE], ['empty string', '']]
f = StringIO()
csv.writer(f).writerows(data)
f = StringIO(f.getvalue())
print(" input:", data)
print("output:", [e for e in csv.reader(f)])
Results:
input: [['None value', None], ['NONE value', NONE], ['empty string', '']]
output: [['None value', ''], ['NONE value', 'NONE'], ['empty string', '']]
Using NONE instead of None would preserve enough information for you to be able to differentiate between it and any actual empty-string data values.
Even better alternative…
You could use the same approach to implement a pair of relatively lightweight csv.reader and csv.writer “proxy” classes — necessary since you can't actually subclass the built-in csv classes which are written in C — without introducing a lot of overhead (since the majority of the processing would still be performed by the underlying built-ins). This would make what goes on completely transparent since it's all encapsulated within the proxies.
from __future__ import print_function
import csv
class csvProxyBase(object): _NONE = '<None>' # Unique value representing None.
class csvWriter(csvProxyBase):
def __init__(self, csvfile, *args, **kwrags):
self.writer = csv.writer(csvfile, *args, **kwrags)
def writerow(self, row):
self.writer.writerow([self._NONE if val is None else val for val in row])
def writerows(self, rows):
list(map(self.writerow, rows))
class csvReader(csvProxyBase):
def __init__(self, csvfile, *args, **kwrags):
self.reader = csv.reader(csvfile, *args, **kwrags)
def __iter__(self):
return self
def __next__(self):
return [None if val == self._NONE else val for val in next(self.reader)]
next = __next__ # Python2.x compatibility.
if __name__ == '__main__':
try:
from cStringIO import StringIO # Python 2.
except ModuleNotFoundError:
from io import StringIO # Python 3.
data = [['None value', None], ['empty string', '']]
f = StringIO()
csvWriter(f).writerows(data)
f = StringIO(f.getvalue())
print("input : ", data)
print("ouput : ", [e for e in csvReader(f)])
Results:
input: [['None value', None], ['empty string', '']]
output: [['None value', None], ['empty string', '']]
