From 80e72cfa27264efb9f525bd92ce6476c5eadb3e9 Mon Sep 17 00:00:00 2001
From: Bruno Alla <bruno.alla@founders4schools.org.uk>
Date: Thu, 12 Jan 2017 09:49:45 +0000
Subject: Fix unicode encode errors on Python 2 -- Fixes #215 Switch csv
 library to backports.csv as the implementation is closer to the python 3 one.
 Add a test case covering the problem.

Run tests with unicode_literals from future

Fix unicode encode errors with unicode characters

- Use `backports.csv` instead of `unicodecsv`
- Use StringIO instead of cStringIO
- Clean-up some Python 2 specific code
---
 tablib/compat.py       | 4 ++--
 tablib/core.py         | 2 +-
 tablib/formats/_csv.py | 9 ++-------
 tablib/formats/_tsv.py | 4 ++--
 4 files changed, 7 insertions(+), 12 deletions(-)

(limited to 'tablib')

diff --git a/tablib/compat.py b/tablib/compat.py
index 43e0bbc..d18a781 100644
--- a/tablib/compat.py
+++ b/tablib/compat.py
@@ -37,11 +37,11 @@ if is_py3:
 
 else:
     from cStringIO import StringIO as BytesIO
-    from cStringIO import StringIO
+    from StringIO import StringIO
     from tablib.packages import markup
     from itertools import ifilter
 
-    import unicodecsv as csv
+    from backports import csv
     import tablib.packages.dbfpy as dbfpy
 
     unicode = unicode
diff --git a/tablib/core.py b/tablib/core.py
index c44c6ac..b97da54 100644
--- a/tablib/core.py
+++ b/tablib/core.py
@@ -831,7 +831,7 @@ class Dataset(object):
            against each cell value.
         """
 
-        if isinstance(col, str):
+        if isinstance(col, unicode):
             if col in self.headers:
                 col = self.headers.index(col) # get 'key' index from each data
             else:
diff --git a/tablib/formats/_csv.py b/tablib/formats/_csv.py
index 994b23b..b74afd7 100644
--- a/tablib/formats/_csv.py
+++ b/tablib/formats/_csv.py
@@ -3,15 +3,14 @@
 """ Tablib - *SV Support.
 """
 
-from tablib.compat import is_py3, csv, StringIO
+from tablib.compat import csv, StringIO, unicode
 
 
 title = 'csv'
 extensions = ('csv',)
 
 
-DEFAULT_ENCODING = 'utf-8'
-DEFAULT_DELIMITER = ','
+DEFAULT_DELIMITER = unicode(',')
 
 
 def export_set(dataset, **kwargs):
@@ -19,8 +18,6 @@ def export_set(dataset, **kwargs):
     stream = StringIO()
 
     kwargs.setdefault('delimiter', DEFAULT_DELIMITER)
-    if not is_py3:
-        kwargs.setdefault('encoding', DEFAULT_ENCODING)
 
     _csv = csv.writer(stream, **kwargs)
 
@@ -36,8 +33,6 @@ def import_set(dset, in_stream, headers=True, **kwargs):
     dset.wipe()
 
     kwargs.setdefault('delimiter', DEFAULT_DELIMITER)
-    if not is_py3:
-        kwargs.setdefault('encoding', DEFAULT_ENCODING)
 
     rows = csv.reader(StringIO(in_stream), **kwargs)
     for i, row in enumerate(rows):
diff --git a/tablib/formats/_tsv.py b/tablib/formats/_tsv.py
index 9380b3b..1c6d6a1 100644
--- a/tablib/formats/_tsv.py
+++ b/tablib/formats/_tsv.py
@@ -3,6 +3,7 @@
 """ Tablib - TSV (Tab Separated Values) Support.
 """
 
+from tablib.compat import unicode
 from tablib.formats._csv import (
     export_set as export_set_wrapper,
     import_set as import_set_wrapper,
@@ -12,8 +13,7 @@ from tablib.formats._csv import (
 title = 'tsv'
 extensions = ('tsv',)
 
-DEFAULT_ENCODING = 'utf-8'
-DELIMITER = '\t'
+DELIMITER = unicode('\t')
 
 def export_set(dataset):
     """Returns TSV representation of Dataset."""
-- 
cgit v1.2.1