2 files changed, 123 insertions, 3 deletions
diff --git a/tablib/formats/_csv.py b/tablib/formats/_csv.py
index 4b1dc02..bfe8b0f 100644
--- a/tablib/formats/_csv.py
+++ b/tablib/formats/_csv.py
@@ -5,12 +5,17 @@
 
 import sys
 if sys.version_info[0] > 2:
+    is_py3 = True
+
     from io import StringIO
+    import csv
 else:
+    is_py3 = False
     from cStringIO import StringIO
+    import tablib.packages.unicodecsv as csv
+
 
 
-import csv
 import os
 
 import tablib
@@ -20,11 +25,18 @@ title = 'csv'
 extentions = ('csv',)
 
 
+DEFAULT_ENCODING = 'utf-8'
+
+
 
 def export_set(dataset):
     """Returns CSV representation of Dataset."""
     stream = StringIO()
-    _csv = csv.writer(stream)
+
+    if is_py3:
+        _csv = csv.writer(stream)
+    else:
+        _csv = csv.writer(stream, encoding=DEFAULT_ENCODING)
 
     for row in dataset._package(dicts=False):
         _csv.writerow(row)
@@ -37,7 +49,10 @@ def import_set(dset, in_stream, headers=True):
 
     dset.wipe()
 
-    rows = csv.reader(in_stream.splitlines())
+    if is_py3:
+        rows = csv.reader(in_stream.splitlines())
+    else:
+        rows = csv.reader(in_stream.splitlines(), encoding=DEFAULT_ENCODING)
     for i, row in enumerate(rows):
 
         if (i == 0) and (headers):
diff --git a/tablib/packages/unicodecsv/__init__.py b/tablib/packages/unicodecsv/__init__.py
new file mode 100644
index 0000000..e640987
--- /dev/null
+++ b/tablib/packages/unicodecsv/__init__.py
@@ -0,0 +1,105 @@
+# -*- coding: utf-8 -*-
+import csv
+from csv import *
+
+#http://semver.org/
+VERSION = (0, 8, 0)
+__version__ = ".".join(map(str,VERSION))
+
+def _stringify(s, encoding):
+    if type(s)==unicode:
+        return s.encode(encoding)
+    elif isinstance(s, (int , float)):
+        pass #let csv.QUOTE_NONNUMERIC do its thing.
+    elif type(s) != str:
+        s=str(s)
+    return s
+
+def _stringify_list(l, encoding):
+    return [_stringify(s, encoding) for s in l]
+
+class UnicodeWriter(object):
+    """
+    >>> import unicodecsv
+    >>> from cStringIO import StringIO
+    >>> f = StringIO()
+    >>> w = unicodecsv.writer(f, encoding='utf-8')
+    >>> w.writerow((u'é', u'ñ'))
+    >>> f.seek(0)
+    >>> r = unicodecsv.reader(f, encoding='utf-8')
+    >>> row = r.next()
+    >>> print row[0], row[1]
+    é ñ
+    """
+    def __init__(self, f, dialect=csv.excel, encoding="utf-8", **kwds):
+        self.writer = csv.writer(f)
+        self.dialect = dialect
+        self.encoding = encoding
+        self.writer = csv.writer(f, dialect=dialect, **kwds)
+
+    def writerow(self, row):
+        self.writer.writerow(_stringify_list(row, self.encoding))
+
+    def writerows(self, rows):
+        for row in rows:
+          self.writerow(row)
+writer = UnicodeWriter
+
+class UnicodeReader(object):
+    def __init__(self, f, dialect=csv.excel, encoding="utf-8", **kwds):
+        self.reader = csv.reader(f, dialect=dialect, **kwds)
+        self.encoding = encoding
+
+    def next(self):
+        row = self.reader.next()
+        return [unicode(s, self.encoding) for s in row]
+
+    def __iter__(self):
+        return self
+reader = UnicodeReader
+
+class DictWriter(csv.DictWriter):
+    """
+    >>> from cStringIO import StringIO
+    >>> f = StringIO()
+    >>> w = DictWriter(f, ['a', 'b'], restval=u'î')
+    >>> w.writerow({'a':'1'})
+    >>> w.writerow({'a':'1', 'b':u'ø'})
+    >>> w.writerow({'a':u'é'})
+    >>> f.seek(0)
+    >>> r = DictReader(f, fieldnames=['a'], restkey='r')
+    >>> r.next() == {'a':u'1', 'r':[u"î"]}
+    True
+    >>> r.next() == {'a':u'1', 'r':[u"ø"]}
+    True
+    >>> r.next() == {'a':u'é', 'r':[u"î"]}
+    """
+    def __init__(self, csvfile, fieldnames, restval='', extrasaction='raise', dialect='excel', encoding='utf-8', *args, **kwds):
+        self.fieldnames = fieldnames
+        self.encoding = encoding
+        self.restval = restval
+        self.writer = csv.DictWriter(csvfile, fieldnames, restval, extrasaction, dialect, *args, **kwds)
+    def writerow(self, d):
+        for fieldname in self.fieldnames:
+            if fieldname in d:
+                d[fieldname] = _stringify(d[fieldname], self.encoding)
+            else:
+                d[fieldname] = _stringify(self.restval, self.encoding)
+        self.writer.writerow(d)
+
+class DictReader(csv.DictReader):
+    def __init__(self, csvfile, fieldnames=None, restkey=None, restval=None, dialect='excel', encoding='utf-8', *args, **kwds):
+        self.restkey = restkey
+        self.encoding = encoding
+        self.reader = csv.DictReader(csvfile, fieldnames, restkey, restval, dialect, *args, **kwds)
+    def next(self):
+        d = self.reader.next()
+        for k, v in d.items():
+            if k == self.restkey:
+                rest = v
+                if rest:
+                    d[self.restkey] = [unicode(v, self.encoding) for v in rest]
+            else:
+                if v is not None:
+                    d[k] = unicode(v, self.encoding)
+        return d