Skip to content

Replace null bytes in csv file for Python 2.x #278

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Closed
rhenanbartels wants to merge 1 commit into from
Closed

Replace null bytes in csv file for Python 2.x #278

Changes from all commits
Commits
Show all changes
1 commit
Select commit
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
34 changes: 24 additions & 10 deletions rows/plugins/plugin_csv.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -18,6 +18,7 @@
from __future__ import unicode_literals

from io import BytesIO, BufferedReader
from io import open as io_open

import six
import unicodecsv
Expand All @@ -28,18 +29,17 @@
sniffer = unicodecsv.Sniffer()


class NotNullBytesWrapper(BufferedReader):

def read(self, *args, **kwargs):
data = super().read(*args, **kwargs)
return data.replace(b'\x00', b'')
if six.PY2:

def readline(self, *args, **kwargs):
data = super().readline(*args, **kwargs)
return data.replace(b'\x00', b'')
class NotNullBytesWrapper(BufferedReader):

def read(self, *args, **kwargs):
data = super(NotNullBytesWrapper, self).read(*args, **kwargs)
return data.replace(b'\x00', b'')

if six.PY2:
def readline(self, *args, **kwargs):
data = super(NotNullBytesWrapper, self).readline(*args, **kwargs)
return data.replace(b'\x00', b'')

def discover_dialect(sample, encoding=None,
delimiters=(b',', b';', b'\t', b'|')):
Expand All @@ -61,6 +61,16 @@ def discover_dialect(sample, encoding=None,

elif six.PY3:

class NotNullBytesWrapper(BufferedReader):

def read(self, *args, **kwargs):
data = super().read(*args, **kwargs)
return data.replace(b'\x00', b'')

def readline(self, *args, **kwargs):
data = super().readline(*args, **kwargs)
return data.replace(b'\x00', b'')

def discover_dialect(sample, encoding, delimiters=(',', ';', '\t', '|')):
"""Discover a CSV dialect based on a sample size

Expand Down Expand Up @@ -116,7 +126,11 @@ def import_from_csv(filename_or_fobj, encoding='utf-8', dialect=None,
"""

filename, fobj = get_filename_and_fobj(filename_or_fobj, mode='rb')
fobj = NotNullBytesWrapper(fobj)

if six.PY2:
fobj = NotNullBytesWrapper(io_open(filename, mode='rb'))
elif six.PY3:
fobj = NotNullBytesWrapper(fobj)

if dialect is None:
dialect = discover_dialect(sample=read_sample(fobj, sample_size),
Expand Down